openslx-ng/ipxe.git/src/drivers/infiniband, branch master

[golan] Set log_max_qp to 1

2018-03-20T15:55:04+00:00

This is required to work around a bug in some firmware versions. Signed-off-by: Ameer Mahagneh Signed-off-by: Michael Brown

[golan] Do not assume all devices are identical

2018-03-18T13:41:21+00:00

Remove the global variable shomron_nodnic_supported, since it may have different values for different PCI devices. Originally-fixed-by: Mohammed Taha Signed-off-by: Michael Brown

[build] Avoid implicit-fallthrough warnings on GCC 7

2017-03-29T07:36:45+00:00

Reported-by: Vinson Lee Reported-by: Liang Yan Signed-off-by: Michael Brown

[golan] Bug fixes and improved paging allocation method

2017-03-23T14:03:40+00:00

Updates: - revert Support for clear interrupt via BAR Signed-off-by: Raed Salem Signed-off-by: Michael Brown

[hermon] Assert that mapping length is non-zero

2017-03-22T13:20:14+00:00

An (impossible) mapping length of zero produces a negative bit shift, which is technically undefined. Signed-off-by: Michael Brown

[arbel] Assert that mapping length is non-zero

2017-03-22T13:18:54+00:00

An (impossible) mapping length of zero produces a negative bit shift, which is technically undefined. Signed-off-by: Michael Brown

[infiniband] Return status code from ib_create_cq() and ib_create_qp()

2017-03-22T09:18:02+00:00

Any underlying errors arising during ib_create_cq() or ib_create_qp() are lost since the functions simply return NULL on error. This makes debugging harder, since a debug-enabled build is required to discover the root cause of the error. Fix by returning a status code from these functions, thereby allowing any underlying errors to be propagated. Signed-off-by: Michael Brown

[qib7322] Use correct length for memset()

2017-03-21T11:51:56+00:00

Signed-off-by: Michael Brown

[linda] Use correct length for memset()

2017-03-21T11:50:51+00:00

Signed-off-by: Michael Brown

[arbel] Avoid potential integer overflow when calculating memory mappings

2017-03-21T10:01:55+00:00

When the area to be mapped straddles the 2GB boundary, the expression (high+size) will overflow on the first loop iteration. Fix by using (end-size), which cannot underflow. Signed-off-by: Michael Brown