- 21 Dec, 2015 40 commits
-
-
Sebastian Sanchez authored
num_rcv_contexts sets the number of user contexts, both receive and send. Renaming it to num_user_contexts makes sense to reflect its true meaning. When num_rcv_contexts is 0, the default behavior is the number of CPU cores instead of 0 contexts. This commit changes the variable num_rcv_contexts to num_user_contexts, and it also makes any negative value for this variable default to the number of CPU cores, so if num_user_contexts is set >= 0, the value will number of contexts. Reviewed-by:
Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by:
Sebastian Sanchez <sebastian.sanchez@intel.com> Signed-off-by:
Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-
Sebastian Sanchez authored
If driver is loaded with parameter hdrq_entsize=0, then there's a NULL dereference when the driver gets unloaded. This causes a kernel Oops and prevents the module from being unloaded. This patch fixes this issue by making sure -EINVAL gets returned when hdrq_entsize=0. Reviewed-by:
Chegondi, Harish <harish.chegondi@intel.com> Reviewed-by:
Haralanov, Mitko <mitko.haralanov@intel.com> Signed-off-by:
-
Easwar Hariharan authored
A code inspection pointed out that kmalloc_array may return NULL and memset doesn't check the input pointer for NULL, resulting in a possible NULL dereference. This patch fixes this. Reviewed-by:
Easwar Hariharan <easwar.hariharan@intel.com> Signed-off-by:
-
Erik E. Kahn authored
send_trap() was still using old ib_smp instead of opa_smp for formatting and sending traps. Reviewed-by:
Arthur Kepner <arthur.kepner@intel.com> Reviewed-by:
Ira Weiny <ira.weiny@intel.com> Reviewed-by:
Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by:
Jubin John <jubin.john@intel.com> Signed-off-by:
Erik E. Kahn <erik.kahn@intel.com> Signed-off-by:
-
Jubin John authored
These new definitions will be used by follow-on patches for formating and sending OPA traps. Reviewed-by:
-
Yash Shah authored
The kmem_cache_destroy() function tests whether its argument is NULL and then returns immediately. Thus the NULL check before calling this function is not needed. This issue was detected by using the Coccinelle software. Signed-off-by:
Yash Shah <yshah1@visteon.com> Signed-off-by:
-
Mike Marciniszyn authored
Profiling has shown the the atomic is a performance issue for the pio hot path. If multiple cpus allocated an sc's buffer, the cacheline containing the atomic will bounce from L0 to L0. Convert the atomic to a percpu variable. Reviewed-by:
-
Mike Marciniszyn authored
There are holes in the sdma build support routines that do not clean any partially built sdma descriptors after mapping or allocate failures. This patch corrects these issues. Reviewed-by:
-
Mike Marciniszyn authored
The allocation code assumes that the shadow ring cannot be overrun because the credits will limit the allocation. Unfortuately, the progress mechanism in sc_release_update() updates the free count prior to processing the shadow ring, allowing the shadow ring to be overrun by an allocation. Reviewed-by:
Mark Debbage <mark.debbage@intel.com> Signed-off-by:
-
Mitko Haralanov authored
It is possible for an SDMA transmission error to happen during the processing of an user SDMA transfer. In that case it is better to detect it early and abort any further attempts to send more packets. Reviewed-by:
-
Mitko Haralanov authored
Clean-up unnecessary goto statements based on feedback from the mailing list on previous patch submissions. Reviewed-by:
-
Mitko Haralanov authored
The driver pins pages on behalf of user processes in two separate instances - when the process has submitted a SDMA transfer and when the process programs an expected receive buffer. When pinning pages, the driver is required to observe the locked page limit set by the system administrator and refuse to lock more pages than allowed. Such a check was done for expected receives but was missing from the SDMA transfer code path. This commit adds the missing check for SDMA transfers. As of this commit, user SDMA or expected receive requests will be rejected if the number of pages required to be pinned will exceed the set limit. Due to the fact that the driver needs to take the MM semaphore in order to update the locked page count (which can sleep), this cannot be done by the callback function as it [the callback] is executed in interrupt context. Therefore, it is necessary to put all the completed SDMA tx requests onto a separate list (txcmp) and offload the actual clean-up and unpinning work to a workqueue. Reviewed-by:
-
Mitko Haralanov authored
Convert hfi1_get_user_pages() to use get_user_pages_fast(), which is much fatster. The mm semaphore is still taken to update the pinned page count but is for a much shorter amount of time. Reviewed-by:
-
Mitko Haralanov authored
There is no need to cleck if the packet queue is allocated when cleaning up a user context. The hfi1_user_sdma_free_queues() function already does all the required checks. Reviewed-by:
-
Dennis Dalessandro authored
Now that the spinlock is not taken throughout hfi1_ioctl it is safe to return early rather than setting a variable and falling through the switch. Reviewed-by:
-
Dennis Dalessandro authored
This patch avoids issues while calling into copy from/to user while holding the lock by only taking the lock when it is absolutely required. The only commands which require the snoop lock are: *Set Filter *Clear Filter *Clear Queue Reviewed-by:
-
Ira Weiny authored
Final clean up of the if/then/else clause for the parameter checks of hfi1_ioctl Signed-off-by:
-
Ira Weiny authored
Set link state is not supported remove from the switch statement and allow the default to return -ENOTTY Signed-off-by:
-
Ira Weiny authored
Rather than have a switch in a large else clause make the parameter checks return immediately. Signed-off-by:
-
Ira Weiny authored
physState, linkState, and devState should be phys_state, link_state, and dev_state Signed-off-by:
-
Ira Weiny authored
sizeof should use the variable rather than the struct definition to ensure that type changes are properly accounted for. Signed-off-by:
-
Ira Weiny authored
Else statements should continue using braces even if there is only 1 line in the block. Found by checkpatch --strict Signed-off-by:
-
Ira Weiny authored
Use !foo rather than (foo == NULL) as recommended by checkpatch --strict Signed-off-by:
-
Ira Weiny authored
Add or remove whitespace according to checkpatch --strict Signed-off-by:
-
Ira Weiny authored
Place logical operators at the end of the previous line when using a multi-line statement. Found by checkpatch --strict Signed-off-by:
-
Ira Weiny authored
Fix line alignment in various places as caught by checkpatch --strict. Signed-off-by:
-
Ira Weiny authored
Use BIT macros rather than shifts. Signed-off-by:
-
Andrea Lowe authored
Changing the 32-bit reserved field in opa_port_data_counters_msg to the new 'resolution' field. PMA will use resolutions to right- shift values for LocalLinkIntegrity and LinkErrorRecovery when computing the ErrorCounterSummary for a DataPortCounters request. Reviewed-by:
Andrea Lowe <andrea.l.lowe@intel.com> Signed-off-by:
-
Harish Chegondi authored
Currently, only MTUs of VLs 0-7 are checked when calculating the maximum VL MTU which is used to set the port MTU capability in DCC_CFG_PORT_CONFIG CSR This can cause a port MTU capability to be set to 0 if MTUs of VLs 0-7 is 0 This would affect the VL15 traffic. Reviewed-by:
Dean Luick <dean.luick@intel.com> Reviewed-by:
-
Dean Luick authored
Change reported unknown frame messages into a counter. These are informational, no errors. Reviewed-by:
-
Dean Luick authored
An SPC freeze is not an error. Remove the messages. Reviewed-by:
-
Dean Luick authored
Only warn when link up pkeys are not what we expect. Also, allow for the pkey to already be initialized. Reviewed-by:
-
Harish Chegondi authored
Currently, if hfi1_register_ib_device() call is unsuccessful, workqueues are not being destroyed before bailing out. This patch fixes this issue. Reviewed-by:
-
Joel Rosenzweig authored
Provides error status counters for CceErrStatus, Send*ErrStatus, RcvErrStatus and MISC_ERR_STATUS Reviewed-by:
Joel Rosenzweig <joel.b.rosenzweig@intel.com> Signed-off-by:
-
Dean Luick authored
Correctly reduce the number of VLs when limited by the number of SDMA engines. The hardware has multiple egress mechanisms, SDMA and pio, and multiples of those. These mechanisms are chosen using the VL (8) The fix corrects a panic issue with one of the platforms that doesn't have enough SDMA (4) mechanisms for the typical number of VLs. Reviewed-by:
-
Dean Luick authored
When sending a diagnostic packet, if the send context does not have enough room, force a credit return and try again. Reviewed-by:
-
Dean Luick authored
The longest quiet timeout is now 6s. Extend the driver wait to 6s. The driver wasn't following our internal specification: 6 seconds. This patch corrects that issue. Reviewed-by:
-
Dean Luick authored
Add one-time LCB reset on driver load to pre-emptively work around any LCB power cycle issues. Reviewed-by:
-
Kaike Wan authored
This patch fixes a few incorrect header file comments in qp.h Reviewed-by:
Kaike Wan <kaike.wan@intel.com> Signed-off-by:
-
Dean Luick authored
Add aeth name syndrome decode to enhance debugging. The IBTA RC ACK contains an ACK extended transport header. Part of that header is the syndrome field that qualifies the RC ACK as an ACK, NAK, or RNR NAK. Without the patch here is the syndrome decode: aeth syn 0x00 Here is the decode with the fix: aeth syn 0x00 ACK Reviewed-by:
-
