* The previous xhci endian fixes performed some double
conversions.
* Tighten down conversions to only where the driver interacts
with raw trb3 data in the ring buffer
* No impact to x86*
Connecting to wifi is very slow, there are several issues.
Easiest to find and fis is that on my wifi DHCP always took
4s, as first request fails. Still investigating why..
Reducing timeout to 0.25s makes DHCP process fast.
Moved timout handling into its own struct, and changed state
timeout from max(remaing, 60s) to min(remaining, MAX_TIMEOUT)
Not sure about that change, but why would you want a max value
that is at least 60s?
* BView incorrectly passed the current width and height to
FrameResized(), not the one from the message. Since there is such
a call for each size change, a Draw() might have been called for
each of those in return.
* This should also fix such problems in BMenuBar, as it used the size
from FrameResized() as it should have.
* BBox now correctly takes the update events into account, and no
longer ignores the size passed to FrameResized().
* This fixes bug #3037.
* Solves #13388 and likely a bunch of other bug reports.
* While this *is* an issue that can potentially be serious,
there really isn't a risk of data loss or a system
instability, only broken PCI devices. Show warning and
keep going.
Bug fix- show correct version on package uninstall list item tooltip
Correct if else formatting
Use the BPackageManager FullSync() function instead of Update
Change warning strings in BPackageManager to sentence casing
Show list item tooltip on a mouse down (helps with touch devices)
Bug fix- use a proper sized 32 pixel application icon for notifications
Bug fix- sorting list of packages to install and uninstall added
Removed use of FinalWindow class now that resizing issues are resolved
Diaplsy alert if no network connections are found at application start
* Reintroduce change in last 2016 acpica upgrade
* Our semaphores are int's. This is the only change needed
to the acpica source code to get it to function under
Haiku.
* We could also disable this int-conversion warning,
however lets go with the "more correct" behaviour in
something that pretty much controls how our kernel finds
PCI devices, CPU's, etc :-|
Notable changes since 20160729:
* Will be dual licensed going forward. We choose the Intel License.
* Fixed two issues with auto-repair double-delete an internal object
* New hook for sleep support (AcpiOsEnterSleep)
* Fixed a regression introduced in 20160729, "FADT support cleanup"
around early 64-bit address support.
* Fixed a problem where runtime implicit conversion was
incorrectly disabled for the ASL operators below. This brings the
behavior into compliance with the ACPI specification:
FromBCD,ToBCD,ToDecimalString,ToHexString,ToInteger,ToBuffer
* Fixed a regression in the internal AcpiTbFindTable function where
a non AE_OK exception could inadvertently be returned even if the
function did not fail. This problem affects the following operators:
DataTableRegion,LoadTable
It was licensed with a "no commercial usage allowed" license, which if
we were using it would be a gray area at best. We weren't using it at all,
and AGG seems to have disabled building it by default, so just remove it
from the tree entirely.
Briefly discussed on IRC.
Changes:
Fixed window resizing bug that happens after packages start downloading
Application icon and left stripe are sized relative to font size
Added alert window dialog to display BPackageManager warnings
Added tooltips to the packages in the list view
Found item has data offset higher than block size. Move the stream to get the
data. If the data does not fit in the block, fetch it directly from the device.
Signed-off-by: Adrien Destugues <pulkomandy@pulkomandy.tk>
Fixes #12788.
- Larger columns to fit new name of file system and new default mount points.
- Correct unit names based on norm IEC 60027-2.
Signed-off-by: Adrien Destugues <pulkomandy@pulkomandy.tk>
Fixes #13312.
If a HEAD request was sent to PoorMan, for example from curl
("curl --HEAD http://x.x.x.x") then the client would hang due to the connection
never being closed.
In PoorManServer::_Worker, after httpd_start_request() is called, a null
file_address is used to detect when libhttpd has already sent a directory
listing. In this situation, PoorMan assumes libhttpd already fully handled the
request. However httpd_start_request() didn't properly set this flag for HEAD
requests. In the if block for a null file_address, the file descriptor was
incorrectly invalidated, which prevented the connection from closing. Fixing
this revealed two more bugs. The first is libhttpd was not actually sending
the http headers for HEAD directory listing requests. The second is
PoorManServer would increment its hit count for HEAD directory listing
requests. This change also refactors file_address to a more sensible name and
type that reflects its use.
Signed-off-by: Adrien Destugues <pulkomandy@pulkomandy.tk>
Fixes #13347.
Committing work done to make SoftwareUpdater functional. The
application will find available updates, confirm with the user to
apply updates, download packages and apply them. There are a few bugs
and features remaining to be fixed and completed:
*Bug with window resizing after packages start downloading- list view
does not resize down
*Tooltips to be implemented (showing repository and other details)
*Proper handling of no network or failed repository connections
*Testing of the problem solver
*Mode to only check for availability of updates and post notification
with results
The checkmark symbol is not available in the Noto font, replacing it
with plain text language until font fallback for symbols can be
implemented. Fixes #13368
