Instead of allowing the client to set a caching attribute
in the io_mem() call of the device interface, which was
only used to decide in between of the memory being
write-combined or not, remove it from the API.
Instead use the information delivered by the devices ROM,
whether memory from a PCI BAR is prefetchable or not,
to decide whether it is mapped write-combined or not.
Ref genodelabs/genode#4578
Memory descriptors in PCI BARs have a prefetchable bit, which can
be used to optimize memory access when setting, e.g. write-combined
in page-table entries.
Ref genodelabs/genode#4578
The DHCP client used to always send packets with a size of 1024 regardless of
the size of the actual content, which was always significantly lower. 1024
bytes was simply a guess to provide enough space for all types of DHCP client
packets. As we know the exact size of each packet the DHCP client sends even
before packet creation, this commit makes use of the knowledge resulting in
much smaller packets sent by the DHCP client.
Fixes#4619
On some Cortex A9 platforms (Qemu 4.2.1 PBXA9), the IRQ status register is not
reliable. Sometimes, it indicates an IRQ too early, i.e., shortly before the
counter wraps. Therefore we have to accomplish wrap detection via counter
comparison only. We check whether the current counter value is higher than the
start counter value of the current timeout.
However, this implies that we have to take care to always read out the counter
before it hits the max timout value again. And, therefore, the max timeout
value has to be far away from the first value the counter has after wrapping.
Consequently, we propagate a max timeout value of half the max counter value.
Fixes#4209
* Remove wrapper for legacy x86 platform API
* Move PCI configuration space quirks to corresponding driver
(pc_usb_host_drv, pc_wifi_drv, pc_intel_fb_drv)
* Adapt driver test run-scripts to changed configuration
Ref genodelabs/genode#4578
Consumes the information about reserved memory region reports from
the devices ROM, and adds appropriated mappings to the corresponding
device PD.
Ref genodelabs/genode#4578
We need the information about reserved memory region reports
from the ACPI tables within the platform driver to pre-fill
IOMMU tables with the corresponding mappings. Therefore,
the pci_decode component now parses the information from the
ACPI ROM, and adds "reserved_memory" nodes to all related
devices in the devices report.
Ref genodelabs/genode#4578
In case of the GPU multiplexer, we need to delegate MMIO memory
to the framebuffer client in form of a managed dataspace. To be
able to attach a given Platform::Device::Mmio object to a region map
we need to access its capability.
Ref genodelabs/genode#4578
* Modernize routines, eliminate pointers, use constructibles, etc.
* Use absolute time instead of relative time consumption when
updating the scheduler
Ref genodelabs/genode#4151
This commit fixes two issues with the timeout lib and the base-hw src recipe:
* Add source files of timeout lib to recipe content.
The files weren't copied to the depot until now. However, the archive
nonetheless built successfully because of the second issue that is described
below.
* Get rid of the usage of the BASE_DIR variable in the timeout lib.
The BASE_DIR variable always resolves to the repos/base directory even when
building in a depot. That said, the use of BASE_DIR in make-files that are
not part of the build system itself must be avoided. Instead, REP_DIR,
REP_INC_DIR, and $(call select_from_repositories, ...) should be used.
Ref #4209
This commit gets rid of the router-local wrapper of Genode's AVL string tree
and replaces it with Genode's new Dictionary structure. The Dictionary is now
used for managing domains and NIC clients. Due to this change, the formerly
necessary helper classes Domain_base and Nic_client_base could be removed as
well.
Ref #4610
When creating an Irq connection to a component (not core), e.g. a pin
driver, we typically need a to provide a session label in order to apply
a session policy and to distinguish multiple sessions from the same
component.
genodelabs/genode#4606
This is a follow-up commit for "menu_view: configurable alpha channel
and bg color", which simplifies the code. The '_no_alpha' surface is not
needed because the 'Gui_buffer' provides a 0x0 alpha surface when using
the opaque mode.
The default file-system communication-buffer size of 128 KiB combined
with the clamping of requests to 1/4th the buffer size results in the
fragementation of read operations into 32 KiB chunks. This is overly
conservative and causes high context-switch overhead down the storage
stack (vfs server -> part_block -> block driver).
Related to #4613
With the increase of MAXPHYS, the rump kernel requests a contiguous
allocation of 2101248 bytes, which exceeds the allocator's block size of
2 MiB.
Error: backend allocator: Unable to allocate memory (size: 2101248 align: 12)
The patch avoids this corner case by increasing the allocator's block
size to 4 MiB.
Fixes#4613
The NIC router README claims that the 'dns_config_from' attribute in a DHCP
server configuration binds the propagated link state of all interfaces at the
domain of the server to the validity of the IP config of the domain that is
given through 'dns_config_from'.
However, this was not true. The router missed to implement this detail which
led to clients of such a DHCP server sending DHCP DISCOVER packets too early.
These early DHCP DISCOVER packets were dropped by the router potentially
causing a big delay until the client started a new attempt. Unnecessary long
network boot-up delays were observed with at least the lwip run script and
Sculpt on the PinePhone and could be tracked down to this former
inconsistency in the router.
This commit fixes the inconsistency.
Fixes#4612
This patch changes the access of pkg-archives files such that the file
read only once per pkg, not for each ROM module used by the package.
Issue #4611
By caching directory listings, the performance of depot_query is no
longer impeded by a massive amount of stat calls while searching for ROM
module locations.
Issue #4611
Upon closer inspection of real-world access patterns, it turns out that
the 'Stat_cache' and 'Cached_rom_query' are not as effective as hoped
for because cache hits are rare while querying pkg blueprints.
However, by increasing the initial size of the blueprint reporter from 4
KiB (default) to 64 KiB has a great effect. With the small default
report size, the querying of blueprints is repeated until the buffer
size suffices, incrementing the buffer size by 4 KiB in each iteration.
Issue #4611
The new 'Dictionary' provides an easy way to access objects using
strings as key. The 'String' received the 'operator >' to simplify the
organization of strings in an AVL tree.
The patch removes the former definition of the 'operator >' from the
platform driver because it would be ambigious now.
Fixes#4610
This patch avoids repetitive depot queries at the start of the Sculpt
system.
We don't need to trigger a query unconditionally whenever the
managed/deploy changes because the call of 'handle_deploy' triggers a
query when needed.
We don't need to trigger a query once the prepare step is completed
because the depot_query component is spawned at this point. The initial
blueprint produced by the depot_query component, in turn, triggers the
'handle_deploy' mechanics in the sculpt manager.
The constructor of the Sculpt manager's 'Main' does not need to call
'depot_deploy' because the prepare step - which is a precondition for
the deployment - cannot be completed at this point anyway.
Do not advance ring buffer positions when playing silence, additionally
to not send progress signals when playing silence. Silence implies
underrun in the client side - not progress.
issue #4609
In case a driver is waiting for data, is should only investigate 'pos'.
It should not advance the ring in any way until there is data available.
issue #4609
This patch consolidates the repetitive error handling across the RPC
functions, which take node handles or directory handles as arguments.
During this change, I noticed that directory handles - which are values
provided by the client - were not checked for their type before being
used. A misbehaving client may open a file, manually construct a
directory handle using the number of the file handle, and invoke a
directory operation at lx_fs, which would then wrongly access a file
node as directory node.
This patch solves this issue by introducing two distinct methods
_with_open_node and _with_open_dir_node, which perform the respective
safety checks.
Fixes#4608
Creating and destructing an interface was not considered a change of its real
link state as defined in the description of the <report link_state_triggers="">
config attribute in the router's README. In case of Uplink sessions this is
obviously a problem as they communicate their real link state through session
lifetime. But also in case of NIC sessions it's a possible to create an
interface that is immediately "up" after creation or destruct an interface
without its link state going "down" beforehand.
Taking into account also the practical application of the
<report link_state_triggers=""> attribute, reporting only on destruction and
construction of interfaces that are "up" seems shorthanded. This is because a
report-receiver most likely needs to be able to synchronize the lifetime of
the objects that keep track of the link states with the lifetime of the
corresponding sessions.
That said, with this commit, the router triggers a report update on each
session construction/destruction when <report link_state_triggers=""> is
set.
Fixes#4462
The NIC router used to generate reports triggered by IP config changes or link
state changes synchonously, i.e., inline with the activation context that
caused the change. This has two disadvantages. First, it can lead to an
excessive number of report updates in situations with quick bursts of
triggering changes. In such situations it is preferable to collect the changes
and reflect them with only one final report update.
Second, synchronous reporting may happen while the router is in a state that
leads to an incorrect report (e.g. during reconfiguration). To prevent this
from happening, the router so far explicitely switched off reporting when
entering incoherent states and back on when leaving them. However, this
solution is error-prone as the exclusion windows must be maintained manually.
Both issues can be solved by not directly generating a report when necessary
but instead submitting a signal and letting the signal handler do the work in
a dedicated activation context.
Ref #4462
This patch splits the querying of the number of directory entries from
the directory's 'status' information. Subsuming the number of directory
entries as part of the status makes 'stat' calls too costly for some
file systems that need to read a directory for determining the number of
entries. So when stat'ing the entries of one directory that contains sub
directories, all entries of each sub directory are visited.
Thanks to Cedric Degea for pointing out this performance bottleneck!
With this change, the 'status' function returns a 'Status::size' value
of 0 when called for a directory handle.
Fixes#4603
This patch splits the former DEPOT=omit option into two variants.
The new 'list' option behaves like the former 'omit' option, skipping
the creation of the tar archive from the depot content referenced by the
deploy configuration but showing a list of depot archives that need to
be published for the deployment.
When specifying 'omit' in th new version, the local depot is not queried
for the packages referenced in the deploy configuration. So the
deployment can refer to packaged hosted only remotely.
Fixes#4605
Tracing must be inhibited in attach/detach as RPC trace points may
trigger attachment of trace dataspaces, which would result in nested
mutex acquisition.
This prevents errors in test-trace_logger like follows.
[init -> depot_autopilot] 0.140 [init -> dynamic_rom] Error: deadlock ahead, mutex=0x500e6f00, return ip=0x50053ed7
Fixes#4607
The DHCP client of the NIC router used to end up in an uncaught exception if
an IP address in the DNS server option of a DHCP ACK was invalid. This commit
makes the 'Dns_server' constructor (where the exception originated from)
private and instead introduces a public lambda method 'construct' that calls
one lambda argument on success and another on failure. This is also in line
with the most recent changes to the 'find_by_*' methods of other classes in
the NIC router and contributes to the goal of reducing expensive exception
handling.
Fixes#4465
The Interface class of the router is an abstraction for NIC client sessions,
NIC server sessions, and Uplink sessions. Nonetheless, Interface generally used
to use the packet stream types of the Nic namespace and it worked because the
Uplink packet stream types are factually the same (the are typedef'd from the
same base type templates with the same parameters).
The initial intention of this issue was to remove dependency on the diverse
packet stream stream types from Interface. However, this turned out to be more
tricky than thought. The Interface class calls function templates on the packet
stream types, making a generic virtual interface impossible. And moving the
calling code to the session classes as well would produce a lot of redundancy.
Therefore, this commit removes only the use of the Nic namespace in the
interface.* files by typedef'ing the packet stream types from the generic
Genode type templates with the same parameters as in Nic and Uplink.
Fixes#4385
The libc kernel used to silently go on if one of the files given through
stdin/stdout/stderr or <fd path=""> was missing (with possibly vital
functionality for the component not working). A pointer to the presumably
simple configuration issue of the underlying scenario was not given to the
user.
With this commit, the libc kernel prints a descriptive warning before
proceeding with the invalid file descriptor
Fixes#4218
The libc kernel used to end up in an uncaught exception if one of the
directories in the paths given through stdin/stdout/stderr or <fd path=""> was
missing. The resulting error didn't point the user to the presumably simple
configuration issue of his scenario in any way and killed the affected
component.
With this commit, the libc kernel prints a descriptive warning instead and
simply continues to run the component with the corresponding file descriptor
missing. At least in case of stdin/stdout/stderr, the libc deals gracefully
with this approach.
Ref #4218
If provided with a config that does not include a `<static>` or
`<common_routes>` node, depot_deploy exits due to a `Nonexistent_sub_node`
exception. Instead, we should output a more useful warning.
Fixesgenodelabs/genode#4600
The `with_sub_node` method is renamed to `with_optional_sub_node` to
better reflect that the non-existence of a sub node with the desired type is
ignored.
At the same time, the new `with_sub_node` now takes a second functor that is
called when no sub node of the desired type exists.
genodelabs/genode#4600
This patch refines the rules for generating a base-hw src archive
for a given board by enumerating the content of the lib/mk/spec/*
directories instead of including entire directories. This avoids
the inclusion of lib.mk files found in SoC-specific repositories
(like genode-allwinner) in the kernel source archives.
When building a binary archive from such a src archive with the changes
of issue #4599, the build system would otherwise try (and fail) to build
the libraries for the accidentally included lib.mk files.
The 'file' library makes the gems API depend on the libc, which is not
desireable because most users of the gems API have no direct libc
dependency.
With the changes of issue #4599, the build of each src archive that
depends on the gems API would attempt to build the 'file' library and
thereby demand the libc.
Note that the 'file' library is a relic that should better not be
promoted as part of the gems API. Hence, this patch removes the file
library from the gems API and adds it to the src archives of the few
remaining users.
Issue #4599
The 'base-linux' API is used by hybrid Genode/Linux programs for the
lx_hybrid library. This API archive happend to contain other libraries -
like seccomp - that are solely needed for building core. With the change
of the build system in issue #4599, the build system would attempt to
build all libraries instead of merely the library dependencies of the
available targets. Hence, it would trigger the build of, e.g., the
seccomp library for each user of the base-linux API.
This patch avoids these superfluous build steps by pruning the content
of lib/mk/ to the libraries actually needed for lx_hybrid users.
Issue #4599
The ld.lib.so stub library generated by base/lib/mk/ld.mk has no
purpose at runtime. On the contrary, it must not be integrated into the
boot image because its name collides with the kernel-specific dynamic
linker.
The build system automatically announces the names of shared libraries
as build artifacts. However, in rare cases, it is required to manually
define them. In particular, the 'ld' stub library plays no role at runtime
and should not be integrated into the boot image.
This patch adds a customization hook following the same pattern as used
for target.mk files, namely the BUILD_ARTIFACTS variable. If defined,
its value is taken as the list of boot artifacts generated by the
library-description file.
Issue #4368
This patch adds special handling for lib/<libname> arguments to the
build system, which supersedes the former LIB=<libname> mechanism.
Whereas the old mechanism was limited to a single library, the new
convention allows multiple library arguments, similar to regular
targets. The change brings the two immediate benefits.
First, the streamlining of library and target arguments allows for the
building of libraries via the 'build' command of the run tool.
Second, it alleviates the need for pseudo target.mk files for building
shared libraries that have no direct dependencies, in particular VFS
plugins.
Since this change eases the explicit creation of shared libraries
from run scripts, we may reconsider the automatic implicit building
of shared libraries driven by targets. E.g., while developing a Qt
application, a run script could import the Qt libraries from the
depot and combine those with the developed (fresh built) target without
triggering the build of the Qt libraries in the build directory.
When issueing 'make' without arguments, all targets are built. This
patch applies this behavior to libraries as well, thereby removing the
need for the base/src/lib/target.mk pseudo target as used by the CI
tools to build all libraries.
Note that target.mk files located under src/lib/ are no longer
reachable. Therefore, all run scripts that used to trigger the
build of a shared library via a pseudo target must be adapted.
E.g., 'build lib/vfs/tap' must be replaced by 'build lib/vfs_tap'.
With this patch, the LIB=<libname> option is no longer supported.
Fixes#4599
changes. The alternative settings get reread on all interfaces as done before
"qemu-usb: fix device endpoint update" commit by introducing specific
reset_alt_settings function. The fallthrough case was intentionally before
the "qemu-usb: fix device endpoint update" case, which now is wrong.
Issue #4596
This style is used by the upcoming phone version of Sculpt for GUI
elements that are supposed to stand out a little bit more than the
regular frame style.
This patch enhances menu_view with the optional configuration attributes
'opaque' and 'background'. Setting 'opaque' to "yes" suppresses the use
of the alpha channel at the GUI session. This improves the drawing
performance by 20% on the PinePhone. Since the menu_view uses the
gems/gui_buffer.h utility, the 'Gui_buffer' received a new 'Alpha'
argument at construction time.
The 'background' attribute can be specified to define the reset color of
the GUI buffer. It alleviates the need to create a frame widget for the
top level.
The patch also switches the optimization level for compiling menu_view
to -O3, which increases the drawing performance on the PinePhone by 30%.
Fixes#4592
This change increases the quota to allow the use of bigger fonts, and
tweaks the style such that the keyboard gets a decent appearance on the
PinePhone's 1440x720 display.
This patch adds principle support for using a USB-net modem as
mobile-data uplink. The change is motivated by the upcoming phone
manager for the PinePhone where the modem serves as the primary network
uplink. For the regular PC version of Sculpt, the feature is not needed
(hence remains disabled) because USB net can be deployed from a package
as described in:
https://genodians.org/jschlatow/2021-07-21-mobile-network
The patch also renames the "Local" network option to "Disconnected" to
be more intuitive.
By decoupling the network dialog's menu view from the 'Network' class,
we become able to host the network dialog in the same menu view instance
as other dialogs.
This patch allows the sculpt manager hosted in the leitzentrale
subsystem to observe the toggling between the runtime and the
administrative GUI. This enables alternatives to the use of the
gui_fader for switching between both views. In particular, the
upcoming phone_manager toggles the visibility of its own GUI
depending on the leitzentrale state.
In a Sculpt system based on the upcoming phone_manager, the event filter
obtains its static configuration from /config/managed/event_filter.
Without the requirement for changes at runtime, there is no need to
have the phone_manager in the loop after all.
Without this patch however, this file was always initialized with the
template gems/sculpt/event_filter/default, which was presumably used
only at boot time until the sculpt manager has produced the first
generated event-filter configuration.
This patch applies the choice of optional configs - i.e., a custom
event_filter config - to both the config/ and the initial content of
config/managed/. So in cases where the /config/managed/event_filter
remains entirely static, the latter properly reflects the choosen
variant.
By using the new functions provided by the base API, this patch removes
the dependency of several components from include/decorator/xml_utils.h.
Issue #4584
The NIC router used to send an ICMP "Destination Unreachable" packet as
response to every unroutable IPv4 packet. However, RFC 1812 section 4.3.2.7
defines certain properties that must be fullfilled by an incoming packet in
order to be answered with this type of ICMP. One requirement is that the packet
is no IPv4 multicast.
This commit prevents sending the mentioned ICMP response for unroutable IPv4
multicasts and instead drops them silently.
Fixes#4563
This patch allows the leitzentrale subsystem to control an audio driver
hosted in the drivers subsystem. An example use case is the toggling of
the speaker during phone calls.
Instead of having a generic "virt_qemu" board use "virt_qemu_<arch>" in
order to have a clean distinction between boards. Current supported
boards are "virt_qemu_arm_v7a", "virt_qemu_arm_v8a", and
"virt_qemu_riscv".
issue #4034
Define custom analyses that can be imported into TraceCompass (>= 7.3)
for evaluating the traced component interactions and checkpoints.
genodelabs/genode#4352
The NIC router used to add the DNS servers field to DHCP replies regardless of
whether there were DNS servers or not. As reported by a Genode user, the empty
DNS server field irritated at least Windows 10 guests (Vbox 6) that connected
to the NIC router. This resulted in Windows 10 ignoring DHCP offers from the
router with such characteristic.
With this commit adding the DNS server DHCP option is skipped if there are no
DNS servers at the corresponding DHCP server or the domain IP config the server
shall fetch its DNS servers from.
Fixes#4581
Skip SET_CONFIGURATION requests if the device already has the selected
config as active config. This workaround prevents issues with Linux
guests in VirtualBox and SDC-reader passthrough.
Thanks to Peter for the patch.
The commit introduces means to mark a task for destruction that is
removed on the next scheduling cycle. This fixes stack leakage from
dynamic kworker tasks.
Issue #4575.
Provide additional PCI register information inside the pci-config part
of the devices ROM for clients able to access an Intel graphic card,
namely the GMCH control register content, which contains for instance
the GTT size and stolen memory size.
Ref genodelabs/genode#4578
Implement BIOS handover and Intel resume register update
apart from device driver to circumvent export of PCI
config space to drivers.
Ref genodelabs/genode#4578
The pci_decode has to extract the additional fields from the PCI configuration
space. The platform driver again has to parse and forward the knowledge too.
The PCI BAR indices are exported when info="yes" is set in the policy node for
the corresponding session.
Fixgenodelabs/genode#4577
The base address of I/O ports has a different encoding than
those of I/O memory. This needs to be encountered in the PCI
config helper utilities.
Fixgenodelabs/genode#4576
Under high TX load, 'irq_handler()' is rarely executed but packets
are still received since 'netdev_poll()' is called for every TX packet.
'netdev_poll()' not only handles completed transmissions but also
puts the IO buffers of received packets into the RX queue and refills the RX
ring by allocating more IO buffers. However, the IO buffers can only be freed
after they have been dequeued and passed to the 'rx_callback()'. Since
this was only done by 'irq_handler()', we exhaust the slab allocator
under high TX load.
A fix for this is to process the RX queue not only in the IRQ handler
but also when transmitting packets.
genodelabs/genode#4555
m/udelay is called with closed interrupts. Linux contrib code expects no
other task to be run respectively to be re-scheduled. usleep_range leads to
executing other tasks, which causes assertions in "spinlock taken twice" or
"unexpected preempt count" errors, seen on runtime with wifi_drv and intel_fb.
The assertion triggered with the changes by #4562.
On okl4, pistachio, sel4 the test didn't come up fast enough in order to still
experience the first configuration of NIC router #1. This commit doubles the
lifetime of the first configuration of NIC router #1 to 4 seconds and raises
the overall test timeout accordingly.
Ref #4555
* Move common SMP and NO_HZ_IDLE variables and functions into
generic lx_emul shadow implementations, and integrate them
into the common lx_emul import rules
* Enable SMP and NO_HZ_IDLE within virt_linux kernel configuration
* Adapt pc drivers and wireguard accordingly
* Use original Linux softirq implementation in wireguard
* Remove erroneous softirq shadow implementation
Ref genodelabs/genode#4540
Ref genodelabs/genode#4562
In overload situations, i.e. when a sender fills up the entire buffer, we land
in situations where the sender receives an ack_avail signal, releases one
packet, allocates and sends a packet and fails to allocate a second packet.
This is especially relevant if the receiver does not batch ack_avail signals
(such as vfs_lwip). In those ping-pong scheduling scenarios, the overhead from
catching the Packet_alloc_failed exception becomes significant. In case of the
NIC router, we will land in an overload situation if the sender is faster than
the receiver. The packet buffer will be filled up at some point and the NIC
router starts to drop packets. For every dropped packet, we currently have to
catch the Packet_alloc_failed exception.
This commit adds a new method alloc_packet_attempt to Packet_stream_source that
has almost the same signature as the older alloc_packet method but returns
an Attempt<Packet_descriptor, Alloc_packet_error> object. As the method already
used the allocator back end exception-less, changes on lower levels were not
needed. Furthermore, the NIC router was modified to use the new exception-less
alloc_packet_attempt instead of alloc_packet.
Ref #4555
Replaces the former implementation of the 'find_by_ip' method at the data
structure for ARP cache entries. This method used to return a reference to the
found object and threw an exception if no matching object was found.
The new implementation doesn't return anything and doesn't throw exceptions. It
takes two lambda arguments instead. One for handling the case that a match was
found with a reference to the matching object as argument and another for
handling the case that no object matches.
This way, expensive exception handling can be avoided and object references
stay in a local scope.
Ref #4555
According to a benchmarking series on Zynq (base-hw) and x260 (base-nova) using
test-nic_perf_router, increasing the 'max_packets_per_signal' has a significant
effect on the packet throughput. By increasing the default value from 32
to 150, we could gain a few hundred Mbit/s. Increasing the value further
does not seem to have such a strong effect, though.
genodelabs/genode#4555
The checksums for forwarded/routed UDP, TCP and ICMP, used to be always
re-calculated from scratch in the NIC router although the router changes only
a few packet fields. This commit replaces the old approach whereever sensible
with an algorithm for incremental checksum updates suggested in RFC 1071.
The goal is to improve router performance.
Ref #4555
The checksums for forwarded/routed IPv4, used to be always re-calculated from
scratch in the NIC router although the router changes only a few packet fields.
This commit replaces the old approach whereever sensible with an algorithm for
incremental checksum updates suggested in RFC 1071. The goal is to improve
router performance.
Ref #4555
We used to use 'unsigned long' for the accumulating variable when calculating
internet checksums. However, 'signed long' is more in accordance with RFC 1071
and will allow us to share the same back end for folding, once we implement
incremental updating of internet checksums.
Ref #4555
Prevent public reflection of the only internally used 'init_sum' argument in
'uint16_t internet_checksum(...)' that, in addition, added a default value to
the function interface.
Ref #4555
When sending an ICMP ECHO reply, the router merely swaps SRC and DST of the
IPv4 header of the corresponding request and these changes cancel each other
out in checksum calculation. Therefore, with this commit, the router skips
updating the IPv4 checksum in this context.
Ref #4555
The router used to update IPv4 checksums when routing via an <ip> rule
despite the fact that it doesn't change any IPv4 header fields in this case.
Ref #4555
The NIC router used to update IPv4 and layer 4 checksums of a packet for each
interface it was sent to (say, all interfaces of the domain the packet was
routed to). However, there was and is no technical reason for not doing it
only once and then iterating over the interfaces with the already updated
packet. This is what this commit does in an intent to raise the router's
performance.
Ref #4555
The NIC router uses the timer for relatively coarse-grained timeouts.
It therefore suffices to update and store the current time when the NIC router
is signalled and use the cached time instead. This prevents frequent
syscalls or RPCs when acquiring the current time for every packet.
genodelabs/genode#4555
The link dissolve timeout is updated for every packet, which leads to
trigger_once() RPCs that only marginally change the scheduled timeout but
significantly slow down the packet throughput.
genodelabs/genode#4555
The wakeup call only emits a single signal as it assumed both are
handled by the same signal handler. However, the original implementation
did not reset the wakeup_needed variable properly.
genodelabs/genode#4555
When using signal batching, ack_avail and packet_avail should always
be emitted and preferred over ready_to_submit and ready_to_ack.
A signal receiver might decide to not register the ready_to_* signals when it
handles congestion by dropping packets. The Nic router is an example of
such a signal receiver.
genodelabs/genode#4555
Enables symetric-multi-processor support in the Linux kernel configuration
used as base for the driver ports for PC. This is done to be compliant with
common usage of x86 drivers today.
Moreover, this commit uses the original kernel source for softirq/tasklet
implementation to get rid of the insufficient shadow implementation
in the lx_emul sources.
Ref genodelabs/genode#4562
Prepare shadow implementations in spinlocks, pagetable defines,
and irq_stack assembler macros to be able to enable SMP on x86/PC.
Ref genodelabs/genode#4562
