Project

General

Profile

PCIe->PCI bridges » History » Version 7

manawyrm, 02/10/2022 09:44 PM

1 1 manawyrm
h1. PCIe->PCI bridges
2
3
Many interesting chipsets for retro networking are equipped with the older PCI bus instead of the current PCIe interface.
4
There are a number of PCIe->PCI bridge chipsets available, with varying levels of quality/reliability.
5
6 3 manawyrm
If you have tested a new chipset or revision of a bridge chip listed here, please update this page.
7
8 1 manawyrm
h3. ASMedia ASM1083/1085
9
10 4 manawyrm
The ASMedia ASM1083 (PCIe to 2x PCI) and ASM1085 (PCIe to 5x PCI) chipsets seem to have problems with interrupt handling.
11 1 manawyrm
This will flood the kernel log with messages like:
12
<pre>pcieport [...]: PME: Spurious native interrupt!</pre>
13
ASM1083/1085 also seem to have other issues related to DMA/IRQ handling. Many soundcards seem to have issues as well.
14
15
Tested revisions:
16 5 manawyrm
- ASM1085, datecode: 1040 (40th week 2010), rev 01 (not working)
17 7 manawyrm
- ASM1083, datecode: 1127 (27th week 2011), rev 01 (unknown)
18 6 manawyrm
- ASM1083, datecode: 1218 (18th week 2012), rev unknown (not working)
19 3 manawyrm
- ASM1083, datecode: 1346 (46th week 2013), rev 04 (working with pcie_aspm=off cmdline)
20
- ASM1083, datecode: 1350 (50th week 2013), rev 03 (not working)
21 1 manawyrm
22 3 manawyrm
Cards with a revision (check lspci) higher than 03 seem to work better. With ASPM enabled (by default), they will still flood messages about interrupts.
23
*Make sure you get Revision 04 or higher and disable ASPM!*
24 1 manawyrm
25
h3. ITE IT8892E
26
27
Common on many Gigabyte motherboards. Untested.
28
29
30
h3. Diodes/Pericom PI7C9X111SL
31
32
Common on "PCI-E To Dual PCI Riser Cards" and some PCIe->PCI adapters. Untested.
33
34
35
h3. Diodes/Pericom PI7C9X113SL
36
37
Untested.
38
39
40
h3. PLX chips
41
42
Untested.
43
44
h3. TI XIO2001
45
46 2 laforge
Issues reported with Sangoma Wanpipe cards, specifically: Cards enumerate quite fine, are visible in lusb and driver binds to it. However, their interrupts never reach Linux, neither the registered interrupt handler, nor does the counter in /proc/interrupts ever count up.
Add picture from clipboard (Maximum size: 48.8 MB)