- 24 Apr, 2018 3 commits
-
-
Jens Korinth authored
-
Jens Korinth authored
-
Jens Korinth authored
-
- 20 Apr, 2018 3 commits
-
-
Jens Korinth authored
-
Jens Korinth authored
-
Jens Korinth authored
-
- 19 Apr, 2018 2 commits
-
-
Jens Korinth authored
* insmod/rmmod'ing works fine * all interrupts are gotten etc. * all basic functionality should be available
-
Jens Korinth authored
-
- 18 Apr, 2018 2 commits
-
-
Jens Korinth authored
* several changes: tlkm_device contains all device data directly * tlkm_class contains information relevant to a class of devices (e.g., pcie/zynq) * classes are automatically enumerated at start, only access type is checked in create (device instances remain until unloaded) * added micro-API for status core base queries
-
Jens Korinth authored
* tricky to get all refs in place for requesting while staying platform-neutral * need to think about it some more
-
- 17 Apr, 2018 1 commit
-
-
Jens Korinth authored
* independent of platform, using status core base addresses * generic interrupt mechanism * not implemented yet: DMA engines do not request interrupts
-
- 14 Apr, 2018 3 commits
-
-
Jens Korinth authored
-
Jens Korinth authored
-
Jens Korinth authored
-
- 13 Apr, 2018 3 commits
-
-
Jens Korinth authored
-
Jens Korinth authored
-
Jens Korinth authored
-
- 12 Apr, 2018 2 commits
-
-
Jens Korinth authored
-
Jens Korinth authored
* libplatform now automatically logs the contents of perf when destroying the device * fixed awkward platform_destroy_device: can be destroyed by pointer now, not only id
-
- 09 Apr, 2018 8 commits
-
-
Jens Korinth authored
-
Jens Korinth authored
* building in main dir, like libplatform * closely mirrored changes in libplatform: tapasco_ctx_t matches platform_ctx_t, and tapasco_devctx_t with platform_devctx_t * this whole change requires a lot of changes all over the place * tapasco-debug builds, but does not work yet * tapasco-benchmark does not build yet
-
Jens Korinth authored
-
Jens Korinth authored
* read_mem and write_mem work now, too * changed a few things, e.g., handing out DMA address now, instead of id * works with platform-stress-alloc test (mode 1) * default implementation should now be working
-
Jens Korinth authored
* changed allocation flags from GFP_DMA (obsolete, discouraged) to GFP_KERNEL | __GFP_MEMALLOC * with >256MB CMA areas this should mean that we do not run into ENOMEMs soon, which could be confirmed * however, DMA allocations tend to destabilize the system, sooner or later a memory oops will occur (see platform_stress_alloc) * not sure how/if to fix that; thought leaving an FPGA-exclusive space on top of the DDR via mem= bootarg, but kernel does not boot below 500M * will keep this for now
-
Jens Korinth authored
-
Jens Korinth authored
-
Jens Korinth authored
-
- 06 Apr, 2018 8 commits
-
-
Jens Korinth authored
-
Jens Korinth authored
-
Jens Korinth authored
* minor memory leaks fixed * destroy sequence fixed * using DEV logging macros
-
Jens Korinth authored
* continued refactoring: some file renames in device/ * changed deactivate compile flag for performance counters to NPERFC * re-inserted per-device perfc file with default output * changed performance counter names and implemented counting * implemented add function for counters to increase by more than 1 * added filename pattern to tlkm_device_ioctl_cmds.h
-
Jens Korinth authored
* fixed some bugs, mmapping works now * also improved portability of read/write ioctls
-
Jens Korinth authored
* devices can set their mmap field to provide mmap-support * reduced log chatter * removed redundant struct tlkm_dev_cmd * fixed bug in general read/write via ioctls
-
Jens Korinth authored
-
Jens Korinth authored
-
- 04 Apr, 2018 2 commits
-
-
Jens Korinth authored
-
Jens Korinth authored
-
- 03 Apr, 2018 3 commits
-
-
Jens Korinth authored
* libplatform and libtapasco can be built in the same location now
-
Jens Korinth authored
-
Jens Korinth authored
-