Previous work introduce verbs priorities, whereas the PMD is making
translation between Flow priority into Verbs. Rename this to make more
sense on what the PMD has to translate.
Signed-off-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
Acked-by: Yongseok Koh <yskoh@mellanox.com>
Drop queues are essentially used in flows due to Verbs API, the
information if the fate of the flow is a drop or not is already present
in the flow. Due to this, drop queues can be fully mapped on regular
queues.
Signed-off-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
Acked-by: Yongseok Koh <yskoh@mellanox.com>
This start a series to re-work the flow engine in mlx5 to easily support
flow conversion to Verbs or TC. This is necessary to handle both regular
flows and representors flows.
As the full file needs to be clean-up to re-write all items/actions
processing, this patch starts to disable the regular code and only let the
PMD to start in isolated mode.
After this patch flow API will not be usable.
Signed-off-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
Acked-by: Yongseok Koh <yskoh@mellanox.com>
Prior to this patch, all port representors detected on a given device were
probed and Ethernet devices instantiated for each of them.
This patch adds support for the standard "representor" parameter, which
implies that port representors are not probed by default anymore, except
for the list provided through device arguments.
(Patch based on prior work from Yuanhan Liu)
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Reviewed-by: Xueming Li <xuemingl@mellanox.com>
Port representors are probed in whatever unspecified order
ibv_get_device_list() returns them.
This is counterintuitive to users since DPDK port IDs assignment almost
never follows the same sequence as representor IDs. Additionally, the
master device does not necessarily inherit the lowest DPDK port ID.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Probe existing port representors in addition to their master device and
associate them automatically.
To avoid collision between Ethernet devices, they are named as follows:
- "{DBDF}" for master/switch devices.
- "{DBDF}_representor_{rep}" with "rep" starting from 0 for port
representors.
(Patch based on prior work from Yuanhan Liu)
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Signed-off-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
Reviewed-by: Xueming Li <xuemingl@mellanox.com>
The current PCI probing method is not aware of Verbs port representors,
which appear as standard Verbs devices bound to the same PCI address and
cannot be distinguished.
Problem is that more often than not, the wrong Verbs device is used,
resulting in unexpected traffic.
This patch makes the driver discard representors to only use the master
device. If unable to identify it (e.g. kernel drivers not recent enough),
either:
- There is only one matching device which isn't identified as a
representor, in that case use it.
- Otherwise log an error and do not probe the device.
(Patch based on prior work from Yuanhan Liu)
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Reviewed-by: Xueming Li <xuemingl@mellanox.com>
Since commit "net/mlx5: drop useless support for several Verbs ports"
removed an inner loop, mlx5_dev_spawn() is left with an unnecessary indent
level.
This patch eliminates a block, moves its local variables to function scope,
and re-indents its contents (diff best viewed with --ignore-all-space).
No functional impact.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Reviewed-by: Xueming Li <xuemingl@mellanox.com>
All the generic probing code needs is an IB device. While this device is
currently supplied by a PCI lookup, other methods will be added soon.
This patch divides the original function, which has become huge over time,
as follows:
1. PCI-specific (mlx5_pci_probe()).
2. Verbs device (mlx5_dev_spawn()).
(Patch based on prior work from Yuanhan Liu)
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Reviewed-by: Xueming Li <xuemingl@mellanox.com>
Unlike mlx4 from which this capability was inherited, mlx5 devices expose
exactly one Verbs port per PCI bus address. Each physical port gets
assigned its own bus address with a single Verbs port.
While harmless, this code requires an extra loop that would get in the way
of subsequent refactoring.
No functional impact.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
This patch gets rid of redundant calls to open the device and query its
attributes in order to simplify the code.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Reviewed-by: Xueming Li <xuemingl@mellanox.com>
There are several attribute objects in this function:
- IB device attributes (struct ibv_device_attr_ex device_attr).
- Direct Verbs attributes (struct mlx5dv_context attrs_out).
- Port attributes (struct ibv_port_attr).
- IB device attributes again (struct ibv_device_attr_ex device_attr_ex).
"attrs_out" is both odd and initialized using a nonstandard syntax. Rename
it "dv_attr" for consistency.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Reviewed-by: Xueming Li <xuemingl@mellanox.com>
Compilation issue:
test/test/test_power_acpi_cpufreq.c:556:31:
error: format ‘%lx’ expects argument of type ‘long unsigned int’,
but argument 2 has type ‘uint64_t {aka long long unsigned int}’
printf("ACPI: Capabilities %lx\n", caps.capabilities);
~~^ ~~~~~~~~~~~~~~~~~
%llx
Fixes: 39e38d583075 ("test/power: add unit test for get capabilities API")
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Radu Nicolau <radu.nicolau@intel.com>
Add rte_flow_expand_rss in map file and tag it as experimental.
Fixes: 4ed05fcd441b ("ethdev: add flow API to expand RSS flows")
Signed-off-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
Acked-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Implement the final piece of the in-memory mode puzzle - enable running
DPDK entirely in memory, without creating any files.
To do it, use mmap with MAP_HUGETLB and size flags to enable DPDK to work
without hugetlbfs mountpoints. In order to enable this, a few things needed
to be changed.
First of all, we need to allow empty hugetlbfs mountpoints in
hugepage_info, and handle them correctly (by not trying to create any
files and lock any directories).
Next, we need to reorder the mapping sequence, because the page is not
really allocated until the page fault, and we cannot get its IOVA
address before we trigger the page fault.
Finally, decide at compile time whether we are going to be supporting
anonymous hugepages or not, because we cannot check for it at runtime.
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
This command-line option will cause DPDK to operate entirely in
memory and not create any shared files at runtime, including any
shared configuration or hugetlbfs files. This is useful for debug
purposes, as well as for certain use cases like containers or
automatic memory cleanup.
Currently, this option acts as a strict superset of --no-shconf and
--huge-unlink commands.
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Unlink hugepages after creating them, to honor the hugepage-unlink mode.
We cannot resize non-existing files, so make single file segments
explicitly unsupported.
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Now that the rest of the EAL is adjusted to not create any shared
files, prevent runtime directory from ever being created.
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Do not create any shared hugepage size info files if we were
asked to not create any shared files.
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
IPC is an inter-process communication mechanism. Since no secondaries
can ever be expected to run in no-shconf mode, IPC will be useless, so
do not enable it in the first place. In the interests of API usage
convenience, we will still allow registering callbacks, but obviously
they won't ever be triggered.
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
When using --no-shconf option, the expectation is that no multiprocess
will be supported as no shared files are created. However, fbarray still
creates some shared files that prevent multiple processes with the same
prefix from starting.
Fix this by avoiding creating shared files whenever noshconf option is
specified. Since virtual areas we get from eal_get_virtual_area() are
read-only, remap them as writable.
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
As per deprecation notice [1], move DPDK runtime config to default
DPDK runtime data location. Also, remove the deprecation notice and
update release notes to indicate the changes.
[1] http://dpdk.org/patch/40418
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
For asynchronous requests, user callback may be triggered either from
IPC thread or from interrupt thread. Because of this, delivery of
other interrupt-based events such as alarms may not be possible inside
the asynchronous IPC request callback handler. Document this
limitation.
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Previously, we were using two IPC threads - one to handle messages
and synchronous requests, and another to handle asynchronous requests.
To handle replies for an async request, rte_mp_handle woke up the
rte_mp_handle_async thread to process through pthread_cond variable.
Change it to handle asynchronous messages within the main IPC thread.
To handle timeout events, for each async request which is sent,
we set an alarm for it. If its reply is received before timeout,
we will cancel the alarm when we handle the reply; otherwise,
alarm will invoke the async_reply_handle() as the alarm callback.
Signed-off-by: Jianfeng Tan <jianfeng.tan@intel.com>
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Suggested-by: Thomas Monjalon <thomas@monjalon.net>
Next commit will make asynchronous IPC requests rely on alarm API,
which in turn relies on interrupts to work. Therefore, move the EAL
interrupt initialization before IPC initialization to avoid breaking
IPC in the next commit.
Signed-off-by: Jianfeng Tan <jianfeng.tan@intel.com>
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Implement EAL alarm API support for FreeBSD. The implementation
is largely identical to that of Linux version, with one key
difference.
The alarm API is a little Linux-centric in that it is expecting
the alarm API to manage alarm timeouts without involvement of the
interrupt thread. This works on Linux because in Linux, there's
timerfd API which allows waiting for timer events on an fd.
On FreeBSD, however, there are no timerfd's, and timer events are
set up directly in kevent. There is no way to pass information from
the alarm API to the interrupt thread, so we also add a little
back-channel magic to get soonest alarm timeout from the alarm API.
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Add interrupt thread to FreeBSD. It is largely a copy-paste from
Linuxapp interrupt thread, except for a few key differences:
* Use kevent instead of epoll
* Do not recreate the event queue on adding/removing interrupt
sources, add/remove them to/from the queue on the fly instead
* No support for UIO/VFIO handles
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
IPC uses interrupts API internally, and memory subsystem uses IPC.
Therefore, IPC should not use rte_malloc to avoid circular dependency.
Switch to using regular glibc malloc in interrupts API.
Signed-off-by: Jianfeng Tan <jianfeng.tan@intel.com>
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Alarm API is going to be used by IPC internally. However, because
memory subsystem depends on IPC, alarm API cannot use rte_malloc as
it creates a circular dependency.
To avoid such chicken and egg problem, we change to use glibc malloc
in the alarm API.
Signed-off-by: Jianfeng Tan <jianfeng.tan@intel.com>
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Some static analyzers complain about it, even though
value is never used if not initialized. To avoid additional
false positives about a potential null-pointer dereferences,
also add a null-check.
Bugzilla ID: 58
Fixes: ea2dc1066870 ("vfio: add multi container support")
Cc: stable@dpdk.org
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
The value is not used, but some static analyzers may give out a
warning. Fix it by assigning default value of zero.
Bugzilla ID: 58
Fixes: cdc242f260e7 ("eal/linux: support running as unprivileged user")
Cc: stable@dpdk.org
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Parentheses were missing. It worked because macro is enclosed in
parentheses, so syntax was valid after macro expansion.
Bugzilla ID: 58
Fixes: 0a45657a6794 ("pci: rework interrupt handling")
Cc: stable@dpdk.org
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Previously, it was possible to limit maximum amount of memory
allowed for allocation by creating validator callbacks. Although a
powerful tool, it's a bit of a hassle and requires modifying the
application for it to work with DPDK example applications.
Fix this by adding a new parameter "--socket-limit", with syntax
similar to "--socket-mem", which would set per-socket memory
allocation limits, and set up a default validator callback to deny
all allocations above the limit.
This option is incompatible with legacy mode, as validator callbacks
are not supported there.
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Currently, reserving zero-length memzones is done by looking at
malloc statistics, and reserving biggest sized element found in those
statistics. This has two issues.
First, there is a race condition. The heap is unlocked between the
time we check stats, and the time we reserve malloc element for memzone.
This may lead to inability to reserve the memzone we wanted to reserve,
because another allocation might have taken place and biggest sized
element may no longer be available.
Second, the size returned by malloc statistics does not include any
alignment information, which is worked around by being conservative and
subtracting alignment length from the final result. This leads to
fragmentation and reserving memzones that could have been bigger but
aren't.
Fix all of this by using earlier-introduced operation to reserve
biggest possible malloc element. This, however, comes with a trade-off,
because we can only lock one heap at a time. So, if we check the first
available heap and find *any* element at all, that element will be
considered "the biggest", even though other heaps might have bigger
elements. We cannot know what other heaps have before we try and
allocate it, and it is not a good idea to lock all of the heaps at
the same time, so, we will just document this limitation and
encourage users to reserve memzones with socket id properly set.
Also, fixup unit tests to account for the new behavior.
Fixes: fafcc11985a2 ("mem: rework memzone to be allocated by malloc")
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Add an internal-only function to allocate biggest element from
the heap. Nominally, it supports SOCKET_ID_ANY as its socket
argument, but it's essentially useless because other sockets
will only be allocated from if the entire heap on current or
specified socket is busy.
Still, asking to reserve a biggest element will allow fixing
race condition in memzone reserve that has been there for a
long time.
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: Remy Horton <remy.horton@intel.com>
Adding internal-only function to find biggest free IOVA-contiguous
malloc element. This is not exposed to external API.
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: Remy Horton <remy.horton@intel.com>
Acked-by: Shreyansh Jain <shreyansh.jain@nxp.com>
Previously, when joining adjacent free elements, we were erasing
trailer and header, but did not erase the padding. Fix this by
accounting for padding on erase, and do not erase padding twice
by adjusting data pointer and data len to not include padding.
Fixes: bb372060dad4 ("malloc: make heap a doubly-linked list")
Cc: stable@dpdk.org
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Sometimes, user code needs to walk memseg list while being inside
a memory-related callback. Rather than making everyone copy around
the same iteration code and depending on DPDK internals, provide an
official way to do memseg_list_walk() inside callbacks.
Also, remove existing reimplementation from memalloc code and use
the new API instead.
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
