- 11 Mar, 2016 40 commits
-
-
Mike Marciniszyn authored
The current implementation of the sdma_wait variable has a timing hole that can cause a completion Q entry to be returned from a pio send prior to an older sdma packets completion queue entry. The sdma_wait variable used to be decremented prior to calling the packet complete routine. The hole is between decrement and the verbs completion where send engine using pio could return a out of order completion in that window. This patch closes the hole by allowing an API option to specify an sdma_drained callback. The atomic dec is positioned after the complete callback to avoid the window as long as the pio path doesn't execute when there is a non-zero sdma count. Reviewed-by:
Jubin John <jubin.john@intel.com> Signed-off-by:
Dean Luick <dean.luick@intel.com> Signed-off-by:
Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by:
Doug Ledford <dledford@redhat.com>
-
Mike Marciniszyn authored
The non-rdamvt versions of qib and hfi1 allow for a differing heuristic to override a schedule progress in favor of a direct call the the progress routine. This patch adds that for both drivers and rdmavt. Reviewed-by:
Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by:
-
Mike Marciniszyn authored
The change requires a new pio_busy field in the iowait structure to track the number of outstanding pios. The new counter together with the sdma counter serve as the basis for a packet by packet decision as to which egress mechanism to use. Since packets given to different egress mechanisms are not ordered, this scheme will preserve the order. The iowait drain/wait mechanisms are extended for a pio case. An additional qp wait flag is added for the PIO drain wait case. Currently the only pio wait is for buffers, so the no_bufs_available() routine name is changed to pio_wait() and a third argument is passed with one of the two pio wait flags to generalize the routine. A module parameter is added to hold a configurable threshold. For now, the module parameter is zero. A heuristic routine is added to return the func pointer of the proper egress routine to use. The heuristic is as follows: - SMI always uses pio - GSI,UD qps <= threshold use pio - UD qps > threadhold use sdma o No coordination with sdma is required because order is not required and this qp pio count is not maintained for UD - RC/UC ONLY packets <= threshold chose as follows: o If sdmas pending, use SDMA o Otherwise use pio and enable the pio tracking count at the time the pio buffer is allocated - RC/UC ONLY packets > threshold use SDMA o If pio's are pending the pio_wait with the new wait flag is called to delay for pios to drain The threshold is potentially reduced by the QP's mtu. The sc_buffer_alloc() has two additional args (a callback, a void *) which are exploited by the RC/UC cases to pass a new complete routine and a qp *. When the shadow ring completes the credit associated with a packet, the new complete routine is called. The verbs_pio_complete() will then decrement the busy count and trigger any drain waiters in qp destroy or reset. Reviewed-by: -
Mike Marciniszyn authored
The use should match the universal container size. Reviewed-by:
Ira Weiny <ira.weiny@intel.com> Signed-off-by:
-
Mike Marciniszyn authored
The send engine wasn't correctly handling pre-built packets, and worse, the pointer to a packet state's txreq wasn't initialized correctly. To fix: - all waiters need to save any prebuilt packets (smda waits already did) - the progress routine needs to handle a QPs prebuilt packet and initialize the txreq pointer properly To keep SDMA working, the dma send code needs to see if a packet has been built already. If not the code will build it. Reviewed-by:
-
Mike Marciniszyn authored
It is in the qp. Reviewed-by:
-
Jubin John authored
s_sendcontext will be used to map the QPs to the send contexts for PIO. Reviewed-by:
-
Mike Marciniszyn authored
It can be conveyed in the verbs_txreq. Reviewed-by:
-
Dennis Dalessandro authored
Instead of writing the header into a buffer then copying it into another buffer to be sent, remove that memcpy and instead build the header directly into the tx request that will be sent. Reviewed-by:
Vennila Megavannan <vennila.megavannan@intel.com> Signed-off-by:
-
Mike Marciniszyn authored
The patch separates the txreq defines into new files, one for verbs and one for sdma. The verbs_txreq implementation handles the setup and teardown of the txreq cache, so the register routine is changed to call the new init/exit routines. This patch allows for followup patches enhance the send engine. Reviewed-by:
-
Mike Marciniszyn authored
pahole noted the wasted 4 bytes after s_lock and r_lock. Move s_flags and r_psn to fill the holes. Reviewed-by:
-
Mike Marciniszyn authored
This diagnostic capability was missed in the dual lock series. Signed-off-by:
-
Harish Chegondi authored
If SMI AH is not destroyed before de-allocating the PD, it would result in non-zero PD use count when de-allocating the PD, triggering a WARN_ON() at drivers/infiniband/core/verbs.c:284 ib_dealloc_pd+0x69/0xb0 [ib_core]() when unloading the qib driver on systems with dual-port card. This problem has always been there in qib and was detected only after the commit 7dd78647 ("IB/core: Make ib_dealloc_pd return void") introduced a WARN_ON in ib_dealloc_pd() that triggers if a PD's use count is non-zero before de-allocating the PD. Below is the call trace from the dmesg log. [ 7264.966129] Call Trace: [ 7264.969652] [<ffffffff81338470>] dump_stack+0x44/0x64 [ 7264.976181] [<ffffffff81086bb6>] warn_slowpath_common+0x86/0xc0 [ 7264.983656] [<ffffffff81086cfa>] warn_slowpath_null+0x1a/0x20 [ 7264.990961] [<ffffffffa025c2d9>] ib_dealloc_pd+0x69/0xb0 [ib_core] [ 7264.998717] [<ffffffffa0044de8>] ib_mad_port_close+0xb8/0x120 [ib_mad] [ 7265.006866] [<ffffffffa0044ebf>] ib_mad_remove_device+0x6f/0xc0 [ib_mad] [ 7265.015224] [<ffffffffa025fc87>] ib_unregister_device+0xa7/0x140 [ib_core] [ 7265.023738] [<ffffffffa04b5b79>] rvt_unregister_device+0x29/0x80 [rdmavt] [ 7265.032181] [<ffffffffa088d2a2>] qib_unregister_ib_device+0x22/0x210 [ib_qib] [ 7265.040993] [<ffffffffa085f73f>] qib_remove_one+0x1f/0x250 [ib_qib] [ 7265.048823] [<ffffffff8137a319>] pci_device_remove+0x39/0xc0 [ 7265.055984] [<ffffffff81466a1a>] __device_release_driver+0x9a/0x140 [ 7265.063821] [<ffffffff81466bc8>] driver_detach+0xb8/0xc0 [ 7265.070579] [<ffffffff81465a15>] bus_remove_driver+0x55/0xd0 [ 7265.077717] [<ffffffff8146732c>] driver_unregister+0x2c/0x50 [ 7265.084849] [<ffffffff813789ba>] pci_unregister_driver+0x2a/0x80 [ 7265.092366] [<ffffffffa08921bd>] qib_ib_cleanup+0x37/0x65 [ib_qib] [ 7265.100068] [<ffffffff811096d0>] SyS_delete_module+0x190/0x220 [ 7265.107379] [<ffffffff816a7bae>] entry_SYSCALL_64_fastpath+0x12/0x71 Reviewed-by:
Harish Chegondi <harish.chegondi@intel.com> Signed-off-by:
-
Dennis Dalessandro authored
Remove exported functions which are no longer required as the functionality has moved into rdmavt. This also requires re-ordering some of the functions since their prototype no longer appears in a header file. Rather than add forward declarations it is just cleaner to re-order some of the functions. Reviewed-by:
-
Dennis Dalessandro authored
Initially it was intended that rdmavt would support some signaling between the underlying driver and itself. However this turned out to be unnecessary for qib and hfi1. If we need to add something like this in later to support another driver we should do it then. As of now this essentially dead code so remove it. Reviewed-by:
-
Dennis Dalessandro authored
While hfi1 and qib were still supporting bits and pieces of core verbs components there needed to be a way to convey if rdmavt should handle allocation and initialize of resources like the queue pair table. Now that all of this is moved into rdmavt there is no need for these flags. They are no longer used in the drivers. Reviewed-by:
-
Dennis Dalessandro authored
Rdmavt adopted an smi_ah from qib which is not needed by hfi1. Move this back to qib and get it out of the common library. Reviewed-by:
-
Dennis Dalessandro authored
Qib needs to be notified when mad agents are created and freed, there is some counter maintenance that needs to be performed. Add those callbacks at registration time with rdmavt. Reviewed-by:
-
Dennis Dalessandro authored
For each verb validate that all requirements for driver callbacks are met. If a function is called without checking for a valid pointer, it is a required function. Also document what each callback function does. Reviewed-by:
-
Dennis Dalessandro authored
Add, remove, and otherwise clean up existing comments that are leftover from the initial code postings of rdmavt. Many of the comments were added to provide an idea on the direction we were thinking of going. Now that the design is solidified make a pass over and clean everything up. Also add details where lacking. Ensure all non static functions have nano comments. Reviewed-by:
-
Kaike Wan authored
If an SL->SC mapping table change occurs after an RC/UC QP is created, there is no mechanism to change the SC nor the VL for that QP. The fix is to place the QP into error state so that ULP can recreate the QP with the new SL->SC mapping. Reviewed-by:
Kaike Wan <kaike.wan@intel.com> Signed-off-by:
-
Harish Chegondi authored
These trace and error print statements would help in debugging issues which are caused due to messed up QP ring buffer pointers. Reviewed-by:
-
Mike Marciniszyn authored
This patch adds an additional lock to reduce contention on the s_lock. This lock is used in post_send() so that the post_send is not serialized with the send engine and other send related processing. To do this the s_next_psn is now maintained on post_send() while post_send() related fields are moved to a new cache line. There is an s_avail maintained for the post_send() to mitigate trading cache lines with the send engine. The lock is released/acquired around releasing the just built packet to the egress mechanism. Reviewed-by:
-
Harish Chegondi authored
This would avoid conflict with the functions in hfi1 that have similar names when both qib and hfi1 drivers are configured to be built into the kernel. This issue came up in the 0-day build report. Reviewed-by:
-
Vennila Megavannan authored
A busy_jiffies variable is maintained and updated when rc qps are created and deleted. busy_jiffies is a scaled value of the number of rc qps in the device. busy_jiffies is incremented every rc qp scaling interval. busy_jiffies is added to the rc timeout in add_retry_timer and mod_retry_timer. The rc qp scaling interval is selected based on extensive performance evaluation of targeted workloads. Reviewed-by:
-
Sebastian Sanchez authored
It prevents the LED from staying on when the QSFP module is not present. Reviewed-by:
Easwar Hariharan <easwar.hariharan@intel.com> Signed-off-by:
Sebastian Sanchez <sebastian.sanchez@intel.com> Signed-off-by:
-
Mike Marciniszyn authored
The patch series which added a new API for the RNR timer did not include an updated call in the loopback path. RC/UC RNR loopback would be broken without this. Reviewed-by:
-
Easwar Hariharan authored
Currently, the driver fails to tune the SerDes and therefore prevents link up if the configuration file is missing or fails parsing or validation. This patch adds a fallback option so that the 8051 is asked to tune for an unknown channel and possibly get the link up if tuning succeeds. It also adds a user-friendly message to update the configuration file if it is out-of-date. Reviewed-by:
-
Easwar Hariharan authored
The platform configuration data has been moved into the EFI variable store where it is populated by the HFI1 option ROM. This patch pulls the configuration data from the new location, retaining a fallback to request_firmware. Reviewed-by:
-
Hari Prasath Gujulan Elango authored
Replace the timer API's to initialize a timer & then assign the callback function by the setup_timer() API. Signed-off-by:
Hari Prasath Gujulan Elango <hgujulan@visteon.com> Signed-off-by:
-
Mike Marciniszyn authored
The field is a vestige from ipath. Reviewed-by:
-
Mike Marciniszyn authored
This patch is a prerequisite for adding a separate lock for post send. The timing of updating s_last needs to be before returning any send completion to avoid a race between a poll cq seeing a completion and the post send checking for a full queue. Reviewed-by:
-
Mike Marciniszyn authored
This patch is a prerequisite for adding a separate lock for post send. The timing of updating s_last needs to be before returning any send completion to avoid a race between a poll cq seeing a completion and the post send checking for a full queue. Reviewed-by:
-
Mike Marciniszyn authored
This is needed to debug ULP issues with getting retry attributes correctly specified. Reviewed-by:
-
Mike Marciniszyn authored
The qp->timeout field is duplicated in the seqfile print. Remove it. Reviewed-by:
-
Mike Marciniszyn authored
Use the new RNR timer for hfi1. For qib, this timer doesn't exist, so exploit driver callbacks to use the new timer as appropriate. Reviewed-by:
-
Mike Marciniszyn authored
Add a new rnr timer to hfi1. This allows for future optimizations having the retry and rnr timers separate. Reviewed-by:
-
Mike Marciniszyn authored
Use new timer API to optimize maintenance of timers during ACK processing. When we are still expecting ACKs, mod the timer to avoid a heavyweight delete/add. Otherwise, insure do_rc_ack() maintains the timer as it had. Reviewed-by:
-
Mike Marciniszyn authored
Use the new timer routines. Reviewed-by:
-
Mike Marciniszyn authored
Centralize disparate timer maintenance. This allow for central control and changes to the RC timer handling including future optimizations. Reviewed-by:
-
