Commit Graph

15 Commits

Author SHA1 Message Date
Alexander Boettcher
0f2c2a675a nova: support write combining
Fixes #1566
2015-08-31 09:09:22 +02:00
Alexander Boettcher
b438181188 nova: use updated r9 kernel branch
Fixes a kernel regression (because of using builtin_retrun_address)
introduced by the out-of-memory commits.

Issue #1601
2015-08-27 12:02:16 +02:00
Alexander Boettcher
df662cc2f3 nova: use kernel branch with quota handling
Fixes #1601
2015-08-21 10:59:45 +02:00
Christian Prochaska
2337dc03f4 nova: use branch supporting changing PDPTE by VMM
Fixes #1637
2015-08-21 10:58:59 +02:00
Alexander Boettcher
9506c89f88 nova: fix memory leaks / invariant TSCs
- free up kernel memory of empty slabs (if already one empty slab is in
  place)
- free up more page table entries
- handle CPUs with invariant TSCs gracefully

  Genode/Nova running on CPUs without the invariant TSC feature may seem
  to 'hang'. The referenced commit of the nova branch fixes the issue
  for some older Intel CPUs.

Fixes #1615
2015-07-07 19:48:07 +02:00
Alexander Boettcher
7b6cd28dcb nova: update to r9
Fixes compiler warnings and re-enables debug commits regarding out of memory
situations.

Fixes #1551
2015-06-03 12:53:48 +02:00
Alexander Boettcher
3e90542559 nova: use signals with irqs in core
Avoids the need to have per IRQ a thread that blocks synchronously for next
interrupt. Now a thread may wait for multiple IRQs as other signals
simultaneously.

In core no threads are required anymore for IRQs/MSI - the clients (either
the pci_drv or in case of MSI the driver) gets the IRQ delivered directly as
a ordinary Genode signal.

Useful since #1216 and #1487 is now available.
Commit applies feature of #1446 also to IRQ/MSIs.
2015-05-26 09:39:51 +02:00
Alexander Boettcher
f5329c23b7 nova: update to kernel branch introducing signals
+ adjust syscall headers accordingly

Issue #1446
2015-03-27 11:53:11 +01:00
Alexander Boettcher
3279346f80 nova: update kernel (fixes endless loop)
If running multiple VBox VMMs with Windows as guest concurrently then it may
happen that the system seem to hang. It turned out that actually
a VM-exit storm (vmx_exception->handle_exc_nm) causes a endless loop between
kernel and vCPU. Nothing gets scheduled nor interrupts are received anymore.
The referenced kernel commit fixes this issue.

Issue #1343
2015-03-13 12:17:24 +01:00
Alexander Boettcher
a31378476d nova: use in core one pager per CPU
Fixes #1394
2015-02-27 11:40:58 +01:00
Alexander Boettcher
8842ba2e1c nova: remove timer delay heuristic
The commit uses a fixed kernel branch (r8), which fixes a caching bug
observable in the Genode host. The quirk detecting the circumstance in the
timer service is obsolete now and is removed.

Fixes #1338
2015-01-06 12:39:11 +01:00
Alexander Boettcher
eedf3fa413 nova: update to r7 branch
Fixes #1297
2014-11-28 12:00:44 +01:00
Alexander Boettcher
e70c13ce1f nova: update to r6 nova kernel branch
- adds general support for semaphore timeouts
- fixes PCID feature (aka tagged TLB) seeen on Lenovo X201

Fixes #1211
2014-07-24 10:18:06 +02:00
Norman Feske
615830e107 Enable hash checks for ports mechanism 2014-05-27 13:45:03 +02:00
Norman Feske
7d4f8fa746 base-nova: migrate to new ports mechanism
Issue #1082
2014-05-27 11:14:43 +02:00