aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)AuthorFilesLines
2016-08-02IB/hfi1: Read all firmware versionsDean Luick4-25/+130
Read the version of the SBus, PCIe SerDes, and Fabric Serdes firmwares at driver load time. Reviewed-by: Dennis Dalessandro <[email protected]> Signed-off-by: Dean Luick <[email protected]> Signed-off-by: Dennis Dalessandro <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-08-02IB/hfi1: Explain state complete frame detailsDean Luick1-8/+126
When link up fails in LNI, the local and peer state complete frames are reported as numbers. Explain what the values mean so the operator can better diagnose the problem. Reviewed-by: Easwar Hariharan <[email protected]> Signed-off-by: Dean Luick <[email protected]> Signed-off-by: Dennis Dalessandro <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-08-02IB/hfi1: Modify the default number of kernel receive conextsHarish Chegondi1-4/+2
Currently, the default number of kernel receive contexts is set to the number of NUMA nodes on the system plus one for control context. However, the systems that have a single socket and/or have NUMA disabled in the BIOS will have only one receive context by default. This patch would ensure that by default there will be at least two kernel receive contexts plus one for control context regardless of the number of NUMA nodes on the system. The user can override the default number of kernel receive contexts with the krcvqs module parameter. Reviewed-by: Dean Luick <[email protected]> Reviewed-by: Mike Marciniszyn <[email protected]> Signed-off-by: Harish Chegondi <[email protected]> Signed-off-by: Dennis Dalessandro <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-08-02IB/hfi1: Add support for extended memory managementJianxin Xiong2-2/+21
Advertise and add the capability of handing all aspects of IBTA extended memory management support in post send. Reviewed-by: Mike Marciniszyn <[email protected]> Reviewed-by: Dennis Dalessandro <[email protected]> Signed-off-by: Jianxin Xiong <[email protected]> Signed-off-by: Dennis Dalessandro <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-08-02IB/hfi1: Work request processing for fast register mr and invalidateJianxin Xiong4-3/+98
In order to support extended memory management support, add send side processing of work requests of type IB_WR_REG_MR, IB_WR_LOCAL_INV, and IB_WR_SEND_WITH_INV. The first two are local operations and are supported for both RC and UC. Send with invalidate is only supported for RC because the corresponding IB opcodes are not defined for UC. Reviewed-by: Mike Marciniszyn <[email protected]> Reviewed-by: Dennis Dalessandro <[email protected]> Signed-off-by: Jianxin Xiong <[email protected]> Signed-off-by: Dennis Dalessandro <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-08-02IB/hfi1: Handle send with invalidate opcode in the RC recv pathJianxin Xiong2-1/+17
As part of enabling extended memory management support, add the processing of the RC send with invalidate. Reviewed-by: Mike Marciniszyn <[email protected]> Reviewed-by: Dennis Dalessandro <[email protected]> Signed-off-by: Jianxin Xiong <[email protected]> Signed-off-by: Dennis Dalessandro <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-08-02IB/rdmavt: Handle local operations in post sendJianxin Xiong2-5/+43
Some work requests are local operations, such as IB_WR_REG_MR and IB_WR_LOCAL_INV. They differ from non-local operations in that: (1) Local operations can be processed immediately without being posted to the send queue if neither fencing nor completion generation is needed. However, to ensure correct ordering, once a local operation is posted to the work queue due to fencing or completion requiement, all subsequent local operations must also be posted to the work queue until all the local operations on the work queue have completed. (2) Local operations don't send packets over the wire and thus don't need (and shouldn't update) the packet sequence numbers. Define a new a flag bit for the post send table to identify local operations. Add a new field to the QP structure to track the number of local operations on the send queue to determine if direct processing of new local operations should be enabled/disabled. Reviewed-by: Mike Marciniszyn <[email protected]> Reviewed-by: Dennis Dalessandro <[email protected]> Signed-off-by: Jianxin Xiong <[email protected]> Signed-off-by: Dennis Dalessandro <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-08-02IB/rdmavt: Add mechanism to invalidate MR keysJianxin Xiong3-2/+75
In order to support extended memory management, add the mechanism to invalidate MR keys. This includes a flag "lkey_invalid" in the MR data structure that is to be checked when validating access to the MR via the associated key, and two utility functions to perform fast memory registration and memory key invalidate operations. Reviewed-by: Mike Marciniszyn <[email protected]> Reviewed-by: Dennis Dalessandro <[email protected]> Signed-off-by: Jianxin Xiong <[email protected]> Signed-off-by: Dennis Dalessandro <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-08-02IB/rdmavt: Add support for ib_map_mr_sgJianxin Xiong3-0/+60
This implements the device specific function needed by the verbs API function ib_map_mr_sg(). Reviewed-by: Mike Marciniszyn <[email protected]> Reviewed-by: Dennis Dalessandro <[email protected]> Signed-off-by: Jianxin Xiong <[email protected]> Signed-off-by: Dennis Dalessandro <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-08-02IB/hfi1: Pull FECN/BECN processing to a common placeMitko Haralanov5-97/+45
There were multiple places where FECN/BECN processing was being done for the different types of QPs. All of that code was very similar, which meant that it could be pulled into a single function used by the different QP types. To retain the performance in the fastpath, the common code starts with an inline function, which only calls the slow path if the packet has any of the [FB]ECN bits set. Reviewed-by: Mike Marciniszyn <[email protected]> Reviewed-by: Dennis Dalessandro <[email protected]> Signed-off-by: Mitko Haralanov <[email protected]> Signed-off-by: Dennis Dalessandro <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-08-02IB/hfi1: Fix to fully initialize send context areaTymoteusz Kielan1-1/+1
While handling buffer control MAD, partially initialized dd->kernel_send_context area may cause potential dereference of uninitialized pointers. Fix by using kzalloc_node() instead of kmalloc_node(). Reviewed-by: Mike Marciniszyn <[email protected]> Reviewed-by: Dennis Dalessandro <[email protected]> Reviewed-by: Andrzej Kacprowski <[email protected]> Signed-off-by: Tymoteusz Kielan <[email protected]> Signed-off-by: Andrzej Kacprowski <[email protected]> Signed-off-by: Dennis Dalessandro <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-08-02IB/hfi1: Fix integrity errors counter value calculationJakub Pawlak1-23/+9
PMA should not sum TX and RX replay counts when reporting local link integrity errors. Fixed by removing C_DC_TX_REPLAY counter from calculation of the link integrity errors counter value. Reviewed-by: Ira Weiny <[email protected]> Reviewed-by: Dennis Dalessandro <[email protected]> Reviewed-by: Mike Marciniszyn <[email protected]> Signed-off-by: Jakub Pawlak <[email protected]> Signed-off-by: Dennis Dalessandro <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-08-02IB/rdmavt: Use new driver specific post send tableMike Marciniszyn2-39/+10
Change rvt_post_one_wr to use the new table mechanism for post send. Validate that each low level driver specifies the table. Reviewed-by: Jianxin Xiong <[email protected]> Reviewed-by: Dennis Dalessandro <[email protected]> Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Dennis Dalessandro <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-08-02IB/qib: Add qib post send tableMike Marciniszyn3-0/+47
Add initial table for table driven post_send support. Reviewed-by: Jianxin Xiong <[email protected]> Reviewed-by: Dennis Dalessandro <[email protected]> Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Dennis Dalessandro <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-08-02IB/hfi1: Add hfi1 post send tablesMike Marciniszyn3-0/+49
Add initial table for table driven post_send support. Reviewed-by: Jianxin Xiong <[email protected]> Reviewed-by: Dennis Dalessandro <[email protected]> Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Dennis Dalessandro <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-08-02IB/rdmavt: Add data structures and routines for table driven post sendMike Marciniszyn3-9/+89
Add flexibility for driver dependent operations in post send because different drivers will have differing post send operation support. This includes data structure definitions to support a table driven scheme along with the necessary validation routine using the new table. Reviewed-by: Ashutosh Dixit <[email protected]> Reviewed-by: Jianxin Xiong <[email protected]> Reviewed-by: Dennis Dalessandro <[email protected]> Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Dennis Dalessandro <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-08-02IB/hfi1: Correct receive packet handler assignmentJakub Pawlak1-13/+16
Prevent processing receive packet in case when opcode is accepted by QP but handler for this type of packet is not defined. Reviewed-by: Mike Marciniszyn <[email protected]> Signed-off-by: Jakub Pawlak <[email protected]> Signed-off-by: Dennis Dalessandro <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-08-02IB/hfi1: Improve SDMA engine assignment for user SDMAJianxin Xiong1-1/+28
Currently each user context is assigned a single SDMA engine based on the VL, context id, and subcontext id. That means for MPI applications, each rank can only use one SDMA engine for all messages. This may create unwanted backup for independent messages going to different destinations upon congestion at one destination. This patch adds the packet "dlid" to the formula of SDMA engine selection for user SDMA requests. A simple hash table is used to maintain even distribution among the available SDMA engines regardless how the "dlid" values are distributed. Reviewed-by: Dean Luick <[email protected]> Reviewed-by: Tadeusz Struk <[email protected]> Signed-off-by: Jianxin Xiong <[email protected]> Signed-off-by: Dennis Dalessandro <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-08-02IB/hfi1: Remove TWSI referencesDean Luick5-588/+1
Remove the TWSI code. The driver now uses the kernel's built-in i2c bit bus module. Cc: Jason Gunthorpe <[email protected]> Reviewed-by: Easwar Hariharan <[email protected]> Reviewed-by: Dennis Dalessandro <[email protected]> Signed-off-by: Dean Luick <[email protected]> Signed-off-by: Dennis Dalessandro <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-08-02IB/hfi1: Use built-in i2c bit-shift bus adapterDean Luick6-115/+341
Use built-in i2c bit-shift bus adapter to control the i2c busses on the chip. Cc: Jason Gunthorpe <[email protected]> Reviewed-by: Easwar Hariharan <[email protected]> Reviewed-by: Dennis Dalessandro <[email protected]> Signed-off-by: Dean Luick <[email protected]> Signed-off-by: Dennis Dalessandro <[email protected]> Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-08-02IB/hfi1: Refine user process affinity algorithmSebastian Sanchez3-62/+174
When performing process affinity recommendations for MPI ranks, the current algorithm doesn't take into account multiple HFI units. Also, real cores and HT cores are not distinguished from one another. Therefore, all HT cores are recommended to be assigned first within the local NUMA node before recommending the assignments of cores in other NUMA nodes. It's ideal to assign all real cores across all NUMA nodes first, then all HT 1 cores, then all HT 2 cores, and so on to balance CPU workload. CPU cores in other NUMA nodes could be running interrupt handlers, and this is not taken into account. To balance the CPU workload for user processes, the following recommendation algorithm is used: For each user process that is opening a context on HFI Y: a) If all cores are assigned to user processes, start assignments all over from the first core b) Assign real cores first, then HT cores (First set of HT cores on all physical cores, then second set of HT cores, and, so on) in the following order: 1. Same NUMA node as HFI Y and not running an IRQ handler 2. Same NUMA node as HFI Y and running an IRQ handler 3. Different NUMA node to HFI Y and not running an IRQ handler 4. Different NUMA node to HFI Y and running an IRQ handler c) Mark core as assigned in the global affinity structure. As user processes are done, remove core assignments from global affinity structure. This implementation allows an arbitrary number of HT cores and provides support for multiple HFIs. This is being included in the kernel rather than user space due to the fact that user space has no way of knowing the CPU recommendations for contexts running as part of other jobs. Reviewed-by: Ira Weiny <[email protected]> Reviewed-by: Mitko Haralanov <[email protected]> Reviewed-by: Dennis Dalessandro <[email protected]> Signed-off-by: Sebastian Sanchez <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-08-02IB/hfi1: Reserve and collapse CPU cores for contextsSebastian Sanchez4-28/+84
Kernel receive queues oversubscribe CPU cores on multi-HFI systems. To prevent this, the kernel receive queues are separated onto different cores, and the SDMA engine interrupts are constrained to a lesser number of cores. hfi1s_on_numa_node*krcvqs is the number of CPU cores that are reserved for kernel receive queues for all HFIs. Each HFI initializes its kernel receive queues to one of the reserved CPU cores. If there ends up being 0 CPU cores leftover for SDMA engines, use the same CPU cores as receive contexts. In addition, general and control contexts are assigned to their own CPU core, however, both types of contexts tend to have low traffic. To save CPU cores, collapse general and control contexts to one CPU core for all HFI units. This change prevents SDMA engine interrupts from wrapping around general contexts. Reviewed-by: Dean Luick <[email protected]> Signed-off-by: Sebastian Sanchez <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-08-02IB/hfi1: Add global structure for affinity assignmentsDennis Dalessandro4-97/+198
When HFI units get initialized, they each use their own mask copy for affinity assignments. On a multi-HFI system, affinity assignments overbook CPU cores as each HFI doesn't have knowledge of affinity assignments for other HFI units. Therefore, some CPU cores are never used for interrupt handlers in systems with high number of CPU cores per NUMA node. For multi-HFI systems, SDMA engine interrupt assignments start all over from the first CPU in the local NUMA node after the first HFI initialization. This change allows assignments to continue where the last HFI unit left off. Add global structure for affinity assignments for multiple HFIs to share affinity mask. Reviewed-by: Jianxin Xiong <[email protected]> Reviewed-by: Jubin John <[email protected]> Reviewed-by: Mike Marciniszyn <[email protected]> Signed-off-by: Sebastian Sanchez <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-08-02perf tests: objdump output can contain multi byte chunksJan Stancek1-29/+71
objdump's raw insn output can vary across architectures on the number of bytes per chunk (bpc) displayed and their endianness. The code-reading test relied on reading objdump output as 1 bpc. Kaixu Xia reported test failure on ARM64, where objdump displays 4 bpc: 70c48: f90027bf str xzr, [x29,#72] 70c4c: 91224000 add x0, x0, #0x890 70c50: f90023a0 str x0, [x29,#64] This patch adds support to read raw insn output for any bpc length. In case of 2+ bpc it also guesses objdump's display endian. Reported-and-Tested-by: Kaixu Xia <[email protected]> Signed-off-by: Jan Stancek <[email protected]> Acked-by: Adrian Hunter <[email protected]> Cc: Corey Ashford <[email protected]> Cc: David Ahern <[email protected]> Cc: Frederic Weisbecker <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Paul Mackerras <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lkml.kernel.org/r/07f0f7bcbda78deb423298708ef9b6a54d6b92bd.1452592712.git.jstancek@redhat.com [ Fix up pr_fmt() call to use %zd for size_t variables, fixing the build on Ubuntu cross-compiling to armhf and ppc64 ] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2016-08-02Orangefs: update orangefs.txtMike Marshall1-4/+46
Describe use of jiffy-based timeout values involved in inode maintenance. Signed-off-by: Mike Marshall <[email protected]> Signed-off-by: Martin Brandenburg <[email protected]>
2016-08-02orangefs: Account for jiffies wraparound.Martin Brandenburg3-8/+8
Signed-off-by: Martin Brandenburg <[email protected]>
2016-08-02orangefs: Change default dcache and getattr timeout to 50 msec.Martin Brandenburg1-2/+2
Signed-off-by: Martin Brandenburg <[email protected]>
2016-08-02orangefs: Allow dcache and getattr cache time to be configured.Martin Brandenburg6-7/+52
Signed-off-by: Martin Brandenburg <[email protected]>
2016-08-02orangefs: Cache getattr results.Martin Brandenburg5-29/+34
The userspace component attempts to do this, but this will prevent us from even needing to go into userspace to satisfy certain getattr requests. Signed-off-by: Martin Brandenburg <[email protected]>
2016-08-02orangefs: Use d_time to avoid excessive lookupsMartin Brandenburg2-0/+9
Signed-off-by: Martin Brandenburg <[email protected]>
2016-08-02perf record: Add --sample-cpu optionJiri Olsa4-1/+6
Adding --sample-cpu option to be able to explicitly enable CPU sample type. Currently it's only enable implicitly in case the target is cpu related. It will be useful for following c2c record tool. Signed-off-by: Jiri Olsa <[email protected]> Cc: David Ahern <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lkml.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2016-08-02perf hists: Introduce output_resort_cb methodJiri Olsa2-3/+16
When dealing with nested hist entries it's helpful to have a way to resort those nested objects. Adding optional callback call into output_resort function and following new interface function: typedef int (*hists__resort_cb_t)(struct hist_entry *he); void hists__output_resort_cb(struct hists *hists, struct ui_progress *prog, hists__resort_cb_t cb); Signed-off-by: Jiri Olsa <[email protected]> Cc: David Ahern <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lkml.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2016-08-02perf tools: Move config/Makefile into Makefile.configJiri Olsa2-3/+3
There's no reason to keep it in separate directory now when we moved out the rest of the files. Signed-off-by: Jiri Olsa <[email protected]> Cc: David Ahern <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lkml.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2016-08-02perf tests: Add test for bitmap_scnprintf functionJiri Olsa4-0/+59
Automatically test the bitmap_scnprintf function. Signed-off-by: Jiri Olsa <[email protected]> Tested-by: Arnaldo Carvalho de Melo <[email protected]> Cc: David Ahern <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lkml.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2016-08-02tools lib: Add bitmap_and functionJiri Olsa2-0/+32
Add support to perform logical and on bitmaps. Code taken from kernel's include/linux/bitmap.h. Signed-off-by: Jiri Olsa <[email protected]> Cc: David Ahern <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lkml.kernel.org/r/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2016-08-02tools lib: Add bitmap_scnprintf functionJiri Olsa2-0/+39
Add support to print bitmap list. Code mostly taken from kernel's bitmap_list_string. Signed-off-by: Jiri Olsa <[email protected]> Cc: David Ahern <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lkml.kernel.org/r/[email protected] [ s/bitmap_snprintf/bitmap_scnprintf/g as it is a scnprintf wrapper, having the same semantics wrt return value ] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2016-08-02tools lib: Add bitmap_alloc functionJiri Olsa1-0/+10
Adding bitmap_alloc function to dynamically allocate bitmap. Signed-off-by: Jiri Olsa <[email protected]> Cc: David Ahern <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Link: http://lkml.kernel.org/r/20160802113302.GA7479@krava Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2016-08-02tracing: Fix use-after-free in hist_register_trigger()Tom Zanussi1-3/+3
This fixes a use-after-free case flagged by KASAN; make sure the test happens before the potential free in this case. Link: http://lkml.kernel.org/r/48fd74ab61bebd7dca9714386bb47d7c5ccd6a7b.1467247517.git.tom.zanussi@linux.intel.com Signed-off-by: Tom Zanussi <[email protected]> Signed-off-by: Steven Rostedt <[email protected]>
2016-08-02tracing: Fix use-after-free in hist_unreg_all/hist_enable_unreg_allSteven Rostedt1-4/+4
While running tools/testing/selftests test suite with KASAN, Dmitry Vyukov hit the following use-after-free report: ================================================================== BUG: KASAN: use-after-free in hist_unreg_all+0x1a1/0x1d0 at addr ffff880031632cc0 Read of size 8 by task ftracetest/7413 ================================================================== BUG kmalloc-128 (Not tainted): kasan: bad access detected ------------------------------------------------------------------ This fixes the problem, along with the same problem in hist_enable_unreg_all(). Link: http://lkml.kernel.org/r/c3d05b79e42555b6e36a3a99aae0e37315ee5304.1467247517.git.tom.zanussi@linux.intel.com Cc: Dmitry Vyukov <[email protected]> [Copied Steve's hist_enable_unreg_all() fix to hist_unreg_all()] Signed-off-by: Tom Zanussi <[email protected]> Signed-off-by: Steven Rostedt <[email protected]>
2016-08-02IB/mlx5: Fix port counter ID association to QP offsetAlex Vesker1-1/+1
The q-counter-id is given in modify-QP command associates the QP with the counter. The offset to which the counter ID was set is incorrect, causing IB port counters not to count on QP. Fixes: 0837e86a7a34 ('IB/mlx5: Add per port counters') Signed-off-by: Alex Vesker <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Tested-by: Mark Bloch <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-08-02IB/mlx5: Fix iteration overrun in GSI qpsSlava Shwartsman1-13/+6
Number of outstanding_pi may overflow and as a result may indicate that there are no elements in the queue. The effect of doing this is that the MAD layer will get stuck waiting for completions. The MAD layer will think that the QP is full - because it didn't receive these completions. This fix changes it so the outstanding_pi number is increased with 32-bit wraparound and is not limited to max_send_wr so that the difference between outstanding_pi and outstanding_ci will really indicate the number of outstanding completions. Cc: Stable <[email protected]> Fixes: ea6dc2036224 ('IB/mlx5: Reorder GSI completions') Signed-off-by: Slava Shwartsman <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Reviewed-by: Haggai Eran <[email protected]> Reviewed-by: Sagi Grimberg <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-08-02i40iw: Add NULL check for puda bufferMustafa Ismail1-0/+4
i40iw_puda_get_listbuf may return NULL if the list is empty. Add NULL check prior to accessing the pointer. Signed-off-by: Mustafa Ismail <[email protected]> Signed-off-by: Shiraz Saleem <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-08-02i40iw: Change dup_ack_thresh to u8Mustafa Ismail1-1/+1
Change dup_ack_thressh to u8 since it is a 3 bit field. Signed-off-by: Mustafa Ismail <[email protected]> Signed-off-by: Shiraz Saleem <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-08-02i40iw: Remove unnecessary check for moving CQ headMustafa Ismail2-5/+4
In i40iw_cq_poll_completion, we always move the tail. So there is no reason to check for overflow everytime we move the head. Signed-off-by: Mustafa Ismail <[email protected]> Signed-off-by: Shiraz Saleem <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-08-02i40iw: Simplify code to set fragments in SQ WQEMustafa Ismail1-6/+6
Replace a subtract and multiply with an add; while populating fragments in SQ wqe. Signed-off-by: Mustafa Ismail <[email protected]> Signed-off-by: Shiraz Saleem <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-08-02i40iw: Remove unnecessary parameter to i40iw_cq_poll_completionMustafa Ismail3-9/+6
Post_cq parameter passed to i40iw_cq_poll_completion is always true; so remove. Signed-off-by: Mustafa Ismail <[email protected]> Signed-off-by: Shiraz Saleem <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-08-02i40iw: Do not access pointer after freeMustafa Ismail1-2/+2
Child_listen_node pointer is used in a debug print after kfree. Move the print before kfree. Signed-off-by: Mustafa Ismail <[email protected]> Signed-off-by: Shiraz Saleem <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-08-02i40iw: Correct and use size parameter to i40iw_reg_phys_mrMustafa Ismail1-1/+2
Fix size parameter passed to i40iw_reg_phys_mr and use it to register memory. Signed-off-by: Mustafa Ismail <[email protected]> Signed-off-by: Shiraz Saleem <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-08-02i40iw: Fix return codesShiraz Saleem1-16/+31
Fix incorrect usage of ENOSYS and other return codes. Signed-off-by: Shiraz Saleem <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-08-02iw_cm: free cm_id resources on the last derefSteve Wise2-38/+18
Remove the complicated logic to free the iw_cm_id inside iw_cm event handlers vs when an application thread destroys the cm_id. Also remove the block in iw_destroy_cm_id() to block the application until all references are removed. This block can cause a deadlock when disconnecting or destroying cm_ids inside an rdma_cm event handler. Simply allowing the last deref of the iw_cm_id to free the memory is cleaner and avoids this potential deadlock. Also a flag is added, IW_CM_DROP_EVENTS, that is set when the cm_id is marked for destruction. If any events are pending on this iw_cm_id, then as they are processed they will be dropped vs posted upstream if IW_CM_DROP_EVENTS is set. Signed-off-by: Steve Wise <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
Powered by cgit, Gruvboxed by Blaster4385.