#
6489b77d |
|
06-Jul-2022 |
Augustin Cavalier <waddlesplash@gmail.com> |
nvme_disk: Fix build on non-PAE 32-bit architectures.
|
#
138d4bbd |
|
06-Jul-2022 |
Augustin Cavalier <waddlesplash@gmail.com> |
nvme_disk: Refactor 64-bit BAR handling into nvme_pcicfg_get_bar_addr_len. Then invoke this function in nvme_pcicfg_map_bar instead of duplicating the logic.
|
#
f7179d9f |
|
18-Oct-2021 |
Augustin Cavalier <waddlesplash@gmail.com> |
nvme_disk: Improve nvme_pcicfg_map_bar logic. The 64-bit address accounting that was added used a hardcoded bar of 0, which is not what we want here, so use the correct offsets instead. Also account for sizes, too.
|
#
0877e4d7 |
|
25-Jul-2021 |
X512 <danger_mail@list.ru> |
nvme: add legacy interrupts support Change-Id: I29b9676c6c2407e7795af4c7b1c56a7afb546f6e Reviewed-on: https://review.haiku-os.org/c/haiku/+/4312 Reviewed-by: Alex von Gluck IV <kallisti5@unixzen.com> Reviewed-by: waddlesplash <waddlesplash@gmail.com>
|
#
1b3ccbc5 |
|
27-Apr-2020 |
Augustin Cavalier <waddlesplash@gmail.com> |
nvme_disk: Overhaul to use physical-buffer-based I/O. This fixes the virtual/physical mixup problems that plagued the driver until now. This is rather inefficent, though, as it does its own page-based bouncing instead of using DMAResource. That will come in the next commit.
|
#
d4304f43 |
|
20-Apr-2020 |
Augustin Cavalier <waddlesplash@gmail.com> |
nvme_disk: Correct get_memory_map invocation. Passing "1" as the bytes argument instead of "0" means that get_memory_map would never return an error in the case that one physical_entry was not enough for the vaddr's map. This reveals the true cause of the disk corruptions: libnvme is assuming some of the passed buffers are physically contiguous, and they are not.
|
#
4b88e723 |
|
14-Apr-2019 |
Augustin Cavalier <waddlesplash@gmail.com> |
nvme: Import glue code to our PCI and VM APIs. Largely simple and painless, thanks to libnvme's abstractions.
|