- 11 Mar, 2016 40 commits
-
-
Jubin John authored
Fix 3 memory leaks reported by the LeakCheck tool in the KEDR framework. The following resources were allocated memory during their respective initializations but not freed during cleanup: 1. SDMA map elements 2. PIO map elements 3. HW send context to SW index map This patch fixes the memory leaks by freeing the allocated memory in the cleanup path. Reviewed-by:
Dean Luick <dean.luick@intel.com> Reviewed-by:
Dennis Dalessandro <dennis.dalessandro@intel.com> Reviewed-by:
Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by:
Jubin John <jubin.john@intel.com> Signed-off-by:
Doug Ledford <dledford@redhat.com>
-
Easwar Hariharan authored
The LedInfo SMA attribute is redefined to control the LED beaconing state machine instead of the LED directly. In accordance, we now return the state of LED beaconing, represented by whether the beaconing timer is active, instead of the state of the LED itself for SMA queries Get(LedInfo) and Get(PortInfo). While we are at it, we fix the beaconing timer control code so that the state of the timer is accurately updated. Reviewed-by:
Ira Weiny <ira.weiny@intel.com> Reviewed-by:
Easwar Hariharan <easwar.hariharan@intel.com> Signed-off-by:
-
Kaike Wan authored
This patch tests the interrupt registers when the driver has no access to its upstream component. In this case, it is highly likely that it is running in a virtual machine (eg, Qemu-kvm guest). If the interrupt registers are not mapped properly by the virtual machine monitor, an error message will be printed and the probing will be terminated. This will help the user identify the issue. On the other hand, if the driver is running in a host or has access to its upstream component in some other VM, it will do nothing. Reviewed-by:
Kaike Wan <kaike.wan@intel.com> Signed-off-by:
-
Kaike Wan authored
When the hfi1 device is assigned to a VM (eg KVM), the hfi1 driver has no access to the upstream component and therefore cannot use it to perform some operations, such as secondary bus reset. As a result, the hfi1 driver cannot perform the pcie Gen3 transition. Instead, those operation should be done in the host environment, preferrably done during the Option ROM initialization. Similarly, the hfi1 driver cannot support ASPM and tune the pcie capability under this circumstance. Reviewed-by:
-
Jianxin Xiong authored
There is a header size counter in both the QP struture and the txreq structure. The counter in the txreq structure is not updated properly for RC and UC queue pairs with GRH enabled, and thus causing SDMA send to fail. This patch fixes the RC and UC path. Reviewed-by:
Jianxin Xiong <jianxin.xiong@intel.com> Signed-off-by:
-
Jubin John authored
The lkey_table_size driver specific parameter value is used before its value is sanity checked and restricted to RVT_MAX_LKEY_TABLE_BITS. This causes a vmalloc allocation failure for large values. Fix this by moving the value check before the first usage of the value. Reviewed-by:
-
Dean Luick authored
A cp or cat of /sys/kernel/debug/hfi1/hfi1_0/port1counters produces the following message: hfi1 0000:81:00.0: hfi1_0: index not supported hfi1 0000:81:00.0: hfi1_0: read_cntrs does not support indexing Fix by removing the file position logic and the associated messages and make the file positioning the responsibility of the caller. The port counter read function argument is changed to the per port data structure since the counters are relative to the port and not the device. Reviewed-by:
Sebastian Sanchez <sebastian.sanchez@intel.com> Signed-off-by:
-
Dean Luick authored
An attempt to cp or cat /sys/kernel/debug/hfi1/hfi1_0/i2c1 produces this message: hfi1 0000:81:00.0: hfi1_0: IB0:1 I2C failed even retrying Fix the issue by explicitly rejecting a simple cat/cp with an -EINVAL error return. Reviewed-by:
-
Mike Marciniszyn authored
The new check routine causes a larger than supported frame size on s390. Changing the check routine to noinline fixes the issue. Reviewed-by:
-
Dean Luick authored
Improve logging messages when there are i2c failures. Clean i2c read error handling. Reviewed-by:
-
Dean Luick authored
Debugfs access races with the driver being ready. Make sure the driver is ready before debugfs files appear and debufs files are gone before the driver starts tearing down. Reviewed-by:
-
Easwar Hariharan authored
This is a set of minor fixes including comment and log message cleanups and improvements to the PHY layer code. Reviewed-by:
-
Dean Luick authored
Count only the errors that apply to xmit discards. Update the comment to better explain the limitations of the count. Reviewed-by:
-
Mike Marciniszyn authored
Setting CONFIG_HFI1_DEBUG_SDMA_ORDER causes a syntax error: sdma.c: In function ‘complete_tx’: sdma.c:370: error: ‘txp’ undeclared (first use in this function) sdma.c:370: error: (Each undeclared identifier is reported only once sdma.c:370: error: for each function it appears in.) Adjust code under ifdef to reference the tx properly. Reviewed-by:
-
Jubin John authored
Fix the header by moving the copyright notice out of the license text and to the top of the header. Also, update the copyright date. Reviewed-by:
-
Jubin John authored
Remove else after break to fix checkpatch warning: WARNING: else is not generally useful after a break or return Reviewed-by:
-
Jubin John authored
Add braces on all arms of statements to fix checkpatch check: CHECK: braces {} should be used on all arms of this statement Reviewed-by: -
Jubin John authored
Fix code alignment to fix checkpatch check: CHECK: Alignment should match open parenthesis Reviewed-by:
-
Jubin John authored
Fix block comments with proper formatting to fix checkpatch warnings: WARNING: Block comments use * on subsequent lines WARNING: Block comments use a trailing */ on a separate line Reviewed-by:
-
Jubin John authored
Add comments describing the spinlock for spinlock_t definitions to fix checkpatch check: CHECK: spinlock_t definition without comment Reviewed-by:
-
Jubin John authored
Remove return statement at the end of a void function to fix checkpatch warning: WARNING: void function return statements are not generally useful Reviewed-by:
-
Jubin John authored
Use sizeof(*p) instead of sizeof(struct foo) to fix checkpatch check: CHECK: Prefer alloc(sizeof(*p)...) over alloc(sizeof(struct foo)...) Reviewed-by:
-
Jubin John authored
Remove CamelCase to fix checkpatch check: CHECK: Avoid CamelCase: <PLS_CONFIGPHY_ESTcOMM_LOCAL_COMPLETE> Reviewed-by:
-
Jubin John authored
Fix misspelled word based on checkpatch check: CHECK: 'ffoo' may be misspelled - perhaps 'foo'? Reviewed-by:
-
Jubin John authored
Split multiple assignments into individual assignments to fix checkpatch check: CHECK: multiple assignments should be avoided Reviewed-by:
-
Jubin John authored
Use BIT_ULL macro to fix checkpatch check: CHECK: Prefer using the BIT_ULL macro Reviewed-by:
-
Jubin John authored
Remove unnecessary parentheses around addressof single $Lvals to fix checkpatch check: CHECK: Unnecessary parentheses around $var Reviewed-by:
-
Jubin John authored
Add blank line after declarations to fix checkpatch check: CHECK: Please use a blank line after function/struct/union/enum declarations Reviewed-by:
-
Jubin John authored
Move logical continuations to previous line to fix checkpatch check: CHECK: Logical continuations should be on the previous line Reviewed-by:
-
Jubin John authored
Remove extra blank line before close brace to fix checkpatch check: CHECK: Blank lines aren't necessary before a close brace '}' Reviewed-by:
-
Jubin John authored
Remove blank line after an open brace to fix checkpatch check: CHECK: Blank lines aren't necessary after an open brace '{' Reviewed-by: -
Jubin John authored
Convert pointer comparisons to NULL to !pointer to fix checkpatch check: CHECK: Comparison to NULL could be written "!pointer" Reviewed-by:
-
Jubin John authored
Remove the space after a cast to fix checkpatch check: CHECK: No space is necessary after a cast Reviewed-by:
-
Jubin John authored
Remove multiple blank lines to fix checkpatch check: CHECK: Please don't use multiple blank lines Reviewed-by:
-
Jubin John authored
Add spaces around binary operators. Fixes checkpatch check: CHECK: spaces preferred around that 'x' where x is a binary operator Reviewed-by:
-
Vennila Megavannan authored
This enables debugging issues related to cq event signalling mechanism Reviewed-by:
Vennila Megavannan <vennila.megavannan@intel.com> Signed-off-by:
-
Jubin John authored
Print the qp's send context sw index in the qpstats Reviewed-by:
-
Mike Marciniszyn authored
Use shared credits and dedicated credits for each VL to determine the actual number of operational VLs. Reviewed-by:
-
Jubin John authored
PIO send context mapping is changed from per-VL to QPN based. qp to send context mapping is done using a mapping infrastructure similar to the current vl to sdma engine mapping. Reviewed-by:
-
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:
-
