Commit Graph

1467 Commits

Author SHA1 Message Date
Alexander Boettcher
8d9e7d0da2 lwip: set some reasonable default rcv buf size
lwip reports via getsockopt the size of the default size of the receive buffer
to the netperf server. lwip returns 2GB and netperf server uses this value to
allocate some buffers - which of course fails with out of memory.

Reduces the "default size" to some smaller value.

With the commit we are not forced anymore to (but still can) use specific
netperf client options regarding memory allocations of the receive buffer.
2013-06-26 17:42:02 +02:00
Alexander Boettcher
e35dbd3353 run: add TCP_MAERTS to netperf test
MAERTS is STREAM backwards and effectively lets the netserver sends the packets
to the netperf client. So, TCP_STREAM measure the receive performance of the
lwIP stack on Genode and TCP_MAERTS the send performance of the lwIP stack
on Genode.
2013-06-26 17:41:54 +02:00
Martin Stein
198f8b65a4 ahci & exynos5: compliant exceptions on creation
Use Root::Unavailable exceptions instead of driver specific ones
on session construction.
2013-06-26 16:02:30 +02:00
Stefan Kalkowski
cfa3d38417 Use Genode's memcpy in L4Linux block driver 2013-06-26 16:02:20 +02:00
Martin Stein
276dbdab60 l4lx: raise block TX buffer size to 5 MiB
Buffer sizes lower than 5 MiB slow down the Arndale AHCI benchmark
with fast 6 Gbps SSDs and 1MiB blocks.
2013-06-26 16:02:13 +02:00
Martin Stein
9d23cdc27f part_blk: raise max packet size to 1 MiB
This is because the old packet size of 128 KiB slowed
down l4linux AHCI benchmark on arndale with large block sizes.
2013-06-26 15:05:20 +02:00
Martin Stein
3fb7e74287 ahci & exynos5: avoid large DMA buf in AHCI bench
Normally this bench has read all data to one large buffer and
than written it back to the drive but for SATA 3 (6 Gbps) benchmarks
we would need a buffer of approximately 1.2 GB to do it this way
and reach 2 seconds bench time. Thus we use a buffer of SATA request size
and override it with every request.
2013-06-26 15:05:20 +02:00
Martin Stein
0ad284febe ahci & exynos5: AHCI (+ part_blk) bench in l4linux 2013-06-26 15:05:19 +02:00
Martin Stein
ad3427e857 ahci & exynos5: allow 6 Gbps port speed 2013-06-26 15:05:15 +02:00
Martin Stein
da930d146f ahci & exynos5: enable SSDs like OCZ Agility 3
Declare ATA device-register structure and check it with more detail.

Fasten error recovery about 9 ms.
2013-06-26 15:05:11 +02:00
Stefan Kalkowski
770157fea0 Enable re-use of singleton, but closed IRQ session
Fix #784
2013-06-26 14:27:19 +02:00
Stefan Kalkowski
664d0036c8 Use cpu regulator in cli_monitor only on Arndale
This commit splits the Fiasco.OC-specific extension for the cli_monitor
into one for the Arndale platform, and one for all others. On Arndale
we add the cpu_frequency command beside the ones defined on all platforms.
2013-06-26 11:29:26 +02:00
Alexander Boettcher
9f2097669a netperf: add support to timeout if host went away 2013-06-25 17:42:42 +02:00
Alexander Boettcher
5d79c6be1a lwip: increase send performance for arndale USB2.0
Getting up to 91 Mbit out of a 100 Mbit card.
2013-06-25 17:42:42 +02:00
Alexander Boettcher
8a623c6317 lwip: support send, recv timeouts 2013-06-25 17:42:42 +02:00
Alexander Boettcher
494bb8ff0d run: print packets/s at end of netperf script 2013-06-25 17:42:42 +02:00
Alexander Boettcher
4bffa249fd lwip: tweak foc_panda to netperf tcp >90MBit/s 2013-06-25 17:42:42 +02:00
Alexander Boettcher
f1c99b190f run: add platform_drv to netperf run script 2013-06-25 17:42:42 +02:00
Alexander Boettcher
ef6450d5d3 run: fix noux_net_netcat for most x86_32 platforms
native pistachio x86 is broken in general

arm fix still pending

Issue #782
2013-06-25 17:36:34 +02:00
Martin Stein
ada408d2f7 ahci & exynos5: enable HDDs like Seagate Barracuda
Initialize and limit port speed to 3 Gbps in general because the Seagate
Barracuda 1TB throws much errors with 6 Gbps by now.

Try all port speeds from the highest to the lowest as long as debouncing fails
and try them all again in this order when falling back to slower debouncing.

Try to recover from all types of interface error.

When a port was recovered from an error during a NCQ command
get the last LBA that was accessed successfully and continue command from
this point.

Use a platform driver through the 'Regulator' service to do CMU and PMU config.

Switch off verbosity by default.
2013-06-25 16:35:22 +02:00
Martin Stein
686c551b66 ahci & exynos5: driver internal benchmark
To raise expressiveness of the benchmark it dynamically adjusts the
transfer amount at any test to get a result that was measured
over a transfer time of 2000 ms at least and 2300 ms at a max.
2013-06-25 15:08:33 +02:00
Martin Stein
6ae5d3a04b ahci & exynos5: basic recovery from NCQ errors
Fix little bugs in scatter/gather-list setup, FIS creation, and
command-slot creation of Exynos5 AHCI driver.
2013-06-25 15:00:52 +02:00
Martin Stein
53b186fe01 ahci & exynos5: enable SSDs like Samsung 840 Pro
* Retry debouncing first with a higher trial time and if this also doesn't
  work with lower link speed additionaly.
* Ignore DevSlp feature because it isn't needed anyway as far as i can see.
* Relax some restrictions according the feedback of the drive as far as it
  seem to have no effect in Linux too

Fix #753
2013-06-25 15:00:42 +02:00
Martin Stein
c93e770316 ahci & exynos5: use platform driver in AHCI test 2013-06-25 15:00:35 +02:00
Martin Stein
0c7c285079 mmio: provide basic verbosity
The verbosity must be enabled at two levels: at compile time
via an enum that switches the availability of verbosity code
and via two members of 'Mmio' named '_read_verbose' and
'_write_verbose'. The latter are initialized to 0 (change this to
enable verbosity globally) and can be used to locally enable
(or disable) verbosity in deriving classes.

Ref #753
2013-06-25 14:52:53 +02:00
Stefan Kalkowski
e23f24505b Add platform_drv to relevant run-scripts (fix #778) 2013-06-25 14:37:03 +02:00
Stefan Kalkowski
ae49f6216d Add regulators for EHCI controller on Arndale
Fix #780
2013-06-25 14:36:57 +02:00
Alexander Boettcher
059bf1c576 nova: fix page fault during core bootup
Fixes #781
2013-06-25 11:16:22 +02:00
Stefan Kalkowski
a73dc1b581 Fix coding style in regulator interface (fix #777) 2013-06-25 11:10:59 +02:00
Stefan Kalkowski
5a3c2c33b7 Add 'cpu_frequency' command to cli_monitor (fix #776)
This commit extends the Fiasco.OC specific extensions of the cli_monitor
to enable the user to interactively change or show current CPU frequency
2013-06-25 11:10:58 +02:00
Christian Prochaska
cb01f75a9d foc-arndale: use same context area location
Currently, on the Arndale platform, core uses a different thread context
area base address than the other tasks (0x20000000 vs. 0x40000000). This
is problematic, because core calculates the location of the UTCB area of a
new thread relatively to core's own thread context area base. So, the UTCB
area of non-core threads ends up in a virtual address range which is
outside of the task's thread context area and not marked as used in the
task's RM session.

With this patch, the same thread context area base address gets used in
core and in the other tasks.

Fixes #779.
2013-06-25 11:10:58 +02:00
Stefan Kalkowski
a4eb4bfa07 Arndale: save power by default (Fix #774)
* Use regulator interface in eMMC driver to enable its clock
2013-06-24 11:50:53 +02:00
Sebastian Sumpf
cc0f4bc9d2 usb_drv: Fix performance of ASIX AX88772
Caused by #773
2013-06-24 11:48:37 +02:00
Sebastian Sumpf
98ee7612f1 base: ARM-FPU 'memcpy_cpu' implementation
Added spec file for ARM-VFPv3 floating-point unit. This shadows
'base/include/arm/' with 'base/include/arm/vfp' and enables a 'memcpy_cpu'
version that mainly uses the FPU. Enabled VFP support for 'foc_arndale'.

Ref #773
2013-06-24 11:48:37 +02:00
Sebastian Sumpf
71490e131b usb_drv: Dimension queues for usbnet
+ Some code cleanup

Ref #773
2013-06-24 11:48:37 +02:00
Sebastian Sumpf
c3537d175c usb_drv: Use platform drivers and regulator
Ref #773
2013-06-24 11:48:37 +02:00
Stefan Kalkowski
f7034369b2 Extend clock and power units in platform driver
* Add clock and power management for SATA and USB3.0 for Arndale

Fix #771
2013-06-24 11:48:37 +02:00
Stefan Kalkowski
1d34589f84 Implement cpu frequency scaling for Arndale
* Implements platform driver for Arndale providing Regulator for CPU clock
* Implements a cpu frequency scaling test using the affinity test
* Fixes #770
2013-06-24 11:48:36 +02:00
Stefan Kalkowski
8fb8cf1c8b Implement abstract regulator session interface
Ref #770
2013-06-24 11:48:36 +02:00
Sebastian Sumpf
231d92f88a usb: Fix AX88179 receive CRC errors
Call 'set_multicast' and 'link_reset' during card startup. Increase TX skb
buffer allocator.

Ref #773
2013-06-24 11:48:36 +02:00
Sebastian Sumpf
8cf893e8c6 ports-foc: Add l4linux netperf run script
Ref #773
2013-06-24 11:48:36 +02:00
Alexander Boettcher
52cf25982a run: clean pulsar config file during a clean_run
tool/autopilot complains about this left over file
2013-06-17 12:14:10 +02:00
Alexander Boettcher
e5eeda2ec9 run: support TFTP servers using absolute paths
TFTP server requiring absolute directory names are supported (better) -
specify in RUN_OPT "--tftp-absolute" to create Pulsar config with absolute
path names for PXE boot.

Additional a symbolic link is created from the build directory to
"$PXE_TFTP_DIR_BASE$PXE_TFTP_DIR_OFFSET" automatically. This eases the use
together with autopilot for x86.
2013-06-14 14:27:14 +02:00
Alexander Boettcher
1b60fd6147 run: power off only the port which was switched on 2013-06-12 15:32:26 +02:00
Alexander Boettcher
27b6839ee0 fiasco: use bender, read out comport from BDA
Fix #768
2013-06-12 11:36:14 +02:00
Alexander Boettcher
bdd2935d4a pistachio: use bender, read out comport from BDA
Issue #768
2013-06-12 11:36:14 +02:00
Alexander Boettcher
1887222b53 okl4: use bender, read out comport from BDA
Issue #768
2013-06-12 11:36:14 +02:00
Alexander Boettcher
32fb7bbddd foc: add 'bender' to pulsar run script
Depends on - https://github.com/ssumpf/foc/pull/4 - which adds BDA read out
of I/O ports to FOC kernel.

Issue #768
2013-06-12 11:36:14 +02:00
Stefan Kalkowski
c61d832ae3 Fix nic_loopback, after recent NIC session changes
Commit c464ee2e6673fe328a8717342dca30f3b0204cb8 removed the RX_BUF_SIZE from
the NIC session interface. Mistakenly, the nic_loopback server was missed
when doing this change.
2013-06-12 11:35:13 +02:00
Stefan Kalkowski
e06a154294 Add __initial_sp variable to base-hw specific crt0
Fixes #756
2013-06-12 11:35:13 +02:00