Ported ISA bus manager and PS/2 driver.

* Implemented PS2_CMD_RESEND command handlig;

* Workaround for touchpad reset timeouts on some HP/Compaq KBCs. Looks like such
KBC marks the mouse reset request (xFF) as correctly sent (by xFA answer) but
does not wait enough time for the answer from touchpad. So complete answer
finally contains xFE xAA x00 bytes. The workaround detects this xFE xAA answer
and issues the RESEND (xFE) request to touchpad. This forces touchpad to resend
the last packet of data (xAA x00) that can be processed normally by the host;

* Fix for handling passthrough_command() call. The parent device was disabled at
start of processing command and was not re-enabled back in case any error return.
This fixes the touchpad "pass-through" feature handling on the same HP/Compaq HW.
This KBC has the "pass-through" capability marked ON but cannot handle it as
currently implemented - there is no answer from corresponding port. The parent
device stay in disabled state after this;

* Fix ps2_dev_publish() for handling passthrough devices (parent_dev != NULL)
This workaround postpone the publishing such device until the parent device
finishes it's opening and set the PS2_ENABLED_FALG. It prevent from mixing
the Synaptics multi-command sequences from synaptics_open() and ps2_dev_publish()
routines and failing both initializations;

Fixes #2867 #3594 #4315



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@42325 a95241bf-73f2-0310-859d-f6bbb57e9c96

Reapply the ps2 cpp patch. Thanks Axel.



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@41134 a95241bf-73f2-0310-859d-f6bbb57e9c96

Revert r41129 to get history back.



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@41133 a95241bf-73f2-0310-859d-f6bbb57e9c96

Making the ps2 busmanager c++.



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@41129 a95241bf-73f2-0310-859d-f6bbb57e9c96

Ported ISA bus manager and PS/2 driver.

* Implemented PS2_CMD_RESEND command handlig;

* Workaround for touchpad reset timeouts on some HP/Compaq KBCs. Looks like such
KBC marks the mouse reset request (xFF) as correctly sent (by xFA answer) but
does not wait enough time for the answer from touchpad. So complete answer
finally contains xFE xAA x00 bytes. The workaround detects this xFE xAA answer
and issues the RESEND (xFE) request to touchpad. This forces touchpad to resend
the last packet of data (xAA x00) that can be processed normally by the host;

* Fix for handling passthrough_command() call. The parent device was disabled at
start of processing command and was not re-enabled back in case any error return.
This fixes the touchpad "pass-through" feature handling on the same HP/Compaq HW.
This KBC has the "pass-through" capability marked ON but cannot handle it as
currently implemented - there is no answer from corresponding port. The parent
device stay in disabled state after this;

* Fix ps2_dev_publish() for handling passthrough devices (parent_dev != NULL)
This workaround postpone the publishing such device until the parent device
finishes it's opening and set the PS2_ENABLED_FALG. It prevent from mixing
the Synaptics multi-command sequences from synaptics_open() and ps2_dev_publish()
routines and failing both initializations;

Fixes #2867 #3594 #4315



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@42325 a95241bf-73f2-0310-859d-f6bbb57e9c96

Reapply the ps2 cpp patch. Thanks Axel.



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@41134 a95241bf-73f2-0310-859d-f6bbb57e9c96

Revert r41129 to get history back.



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@41133 a95241bf-73f2-0310-859d-f6bbb57e9c96

Making the ps2 busmanager c++.



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@41129 a95241bf-73f2-0310-859d-f6bbb57e9c96