The following commit break vm2vm hard mode test cases:
commit db4014f2b6 ("use factorized default Rx/Tx configuration")
Investigation show that it needs enabling vlan offload since it is turn off
by default in some drivers, and Tx need it, especially when vm2vm is in hard mode.
Signed-off-by: Changchun Ouyang <changchun.ouyang@intel.com>
Tested-by: Jingguo Fu <jingguox.fu@intel.com>
Fix a typo: cmdline_parse_token_string_t was used in place of
cmdline_parse_num_string_t.
Seen with clang-3.5.
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Compiling the netmap example with clang-3.5 triggered the following
warning:
compat_netmap.c:783:11: error: overflow converting case value to
switch condition type (3225184658 to 18446744072639768978)
[-Werror,-Wswitch]
case NIOCREGIF:
^
Indeed, an ioctl value should be an unsigned 32 bits, not an int.
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Fix the following error:
error: unused function 'l3fwd_simple_forward'
The l3fwd_simple_forward() is maybe unused, due to compilation options
(APP_LOOKUP_METHOD, ENABLE_MULTI_BUFFER_OPTIMIZE). As the combinatorial
is quite big, it looks simpler to add the __attribute__((unused)) on
this function, so that the compiler does not complain.
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
The check for NULL is in the wrong position in the "if" error leg. The
pointer should be checked for NULL before checking what the value of
what the pointer points to is.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
The length of the path to a unix socket is not PATH_MAX but instead is
UNIX_PATH_MAX which is generally just over 100 bytes in size. It's not
actually defined in sys/un.h on linux - despite the man page referencing
it, so calculate the size in the case where it's not defined.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Static analysis shows that once instance of rte_zmalloc is missing
a return value check in the code. This is fixed by adding a return
value check. The malloc call itself is moved to earlier in the function
so that no work is done unless all memory allocation requests have
succeeded - thereby removing the need for rollback on error.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
At error app_acl_init() can return without freeing dynamically allocated memory.
Not really a big problem, as if app_acl_init() fails,
then application would terminate immediately anyway.
Though it is a good coding practise to make a function to cleanup after itself.
Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
When the routing is through the same queue, the app crashed.
Signed-off-by: Daniel Mrzyglod <danielx.t.mrzyglod@intel.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Search the right segment to increase its data length, rather than
wrongly early return and exit the tx function, which leads to drop all jumbo frame packets
when vm2vm is in hard forward mode.
Signed-off-by: Changchun Ouyang <changchun.ouyang@intel.com>
Increase MAX_QUEUES from 256 to 512.
In vhost example, MAX_QUEUES macro should be the maximum possible queue number of the port.
Theoretically we should only set up the queues that are used, i.e., first rx queue of each pool, or
at most queues from 0 to MAX_QUEUES. Before we revise the implementation and are certain all NICs support
this well, add a remind message to user.
Signed-off-by: Huawei Xie <huawei.xie@intel.com>
Refer to Pablo's commit (81f7ecd934):
"use factorized default Rx/Tx configuration
For apps that were using default rte_eth_rxconf and rte_eth_txconf
structures, these have been removed and now they are obtained by
calling rte_eth_dev_info_get, just before setting up RX/TX queues."
Move zero copy's deferred start set up ahead.
Signed-off-by: Huawei Xie <huawei.xie@intel.com>
In Niantic, if VMDQ mode is set, all queues are allocated to VMDQ in DPDK.
In I40E, only configured part of continous queues are allocated to VMDQ.
The rte_eth_dev_info structure is extended to provide VMDQ queue base,
queue number, and VMDQ pool base information.
This patch support the new VMDQ API in vhost example.
FIXME in PMD:
* added mac address will be flushed at rte_eth_dev_start.
* we don't support selectively setting up queues well.
Test report: http://dpdk.org/ml/archives/dev/2014-December/009427.html
Signed-off-by: Huawei Xie <huawei.xie@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
Tested-by: Jingguo Fu <jingguox.fu@intel.com>
The symmetric_mp example app is set up to allow two processes to
share a NIC port, with each pulling packets from one queue. In order
to have the app continue working when one of the process dies, the
drop_en bit should be set in the NIC configuration. Without this bit
set, the NIC will stall once any queue fills. With the bit set, once
a queue fills, all subsequent packets for that queue are discarded
allowing other queues to continue operating as normal.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
When using test-pmd with flow director in FreeBSD, the application will
segfault/Bus error while parsing the command-line. This is due to how
each commands result structure is represented during parsing, where the offsets
for each tokens value is stored in a character array(char result_buf[BUFSIZ])
in cmdline_parse()(./lib/librte_cmdline/cmdline_parse.c).
The overflow occurs where BUFSIZ is less than the size of a commands result
structure, in this case "struct cmd_pkt_filter_result"
(app/test-pmd/cmdline.c) is 1088 bytes and BUFSIZ on FreeBSD is 1024 bytes as
opposed to 8192 bytes on Linux.
The problem can be reproduced by running test-pmd on FreeBSD:
./testpmd -c 0x3 -n 4 -- -i --portmask=0x3 --pkt-filter-mode=perfect
And adding a filter:
add_perfect_filter 0 udp src 192.168.0.0 1024 dst 192.168.0.0 1024 flexbytes
0x800 vlan 0 queue 0 soft 0x17
This patch removes the OS dependency on BUFSIZ and defines and uses a
library #define CMDLINE_PARSE_RESULT_BUFSIZE 8192
Added boundary checking to ensure this buffer size cannot overflow, with
an error message being produced.
Suggested-by: Olivier Matz <olivier.matz@6wind.com>
http://git.droids-corp.org/?p=libcmdline.git;a=commitdiff;h=b1d5b169352e57df3fc14c51ffad4b83f3e5613f
Signed-off-by: Alan Carew <alan.carew@intel.com>
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Tested-by: Bruce Richardson <bruce.richardson@intel.com>
CACHE_LINE_SIZE is a macro defined in machine/param.h in FreeBSD and
conflicts with DPDK macro version.
Adding RTE_ prefix to avoid conflicts.
CACHE_LINE_MASK and CACHE_LINE_ROUNDUP are also prefixed.
Signed-off-by: Sergio Gonzalez Monroy <sergio.gonzalez.monroy@intel.com>
[Thomas: updated on HEAD, including PPC]
Signed-off-by: David Marchand <david.marchand@6wind.com>
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Some of the NICs supported by DPDK have a possibility to accelerate TCP
traffic by using segmentation offload. The application prepares a packet
with valid TCP header with size up to 64K and deleguates the
segmentation to the NIC.
Implement the generic part of TCP segmentation offload in rte_mbuf. It
introduces 2 new fields in rte_mbuf: l4_len (length of L4 header in bytes)
and tso_segsz (MSS of packets).
To delegate the TCP segmentation to the hardware, the user has to:
- set the PKT_TX_TCP_SEG flag in mbuf->ol_flags (this flag implies
PKT_TX_TCP_CKSUM)
- set the flag PKT_TX_IPV4 or PKT_TX_IPV6
- set PKT_TX_IP_CKSUM if it's IPv4, and set the IP checksum to 0 in
the packet
- fill the mbuf offload information: l2_len, l3_len, l4_len, tso_segsz
- calculate the pseudo header checksum without taking ip_len in account,
and set it in the TCP header, for instance by using
rte_ipv4_phdr_cksum(ip_hdr, ol_flags)
The API is inspired from ixgbe hardware (the next commit adds the
support for ixgbe), but it seems generic enough to be used for other
hw/drivers in the future.
This commit also reworks the way l2_len and l3_len are used in igb
and ixgbe drivers as the l2_l3_len is not available anymore in mbuf.
Signed-off-by: Mirek Walukiewicz <miroslaw.walukiewicz@intel.com>
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Provides a small sample application(guest_vm_power_mgr) to run on a VM.
The application is run by providing a core mask(-c) and number of memory
channels(-n). The core mask corresponds to the number of lcore channels to
attempt to open. A maximum of 64 channels per VM is allowed. The channels must
be monitored by the host.
After successful initialisation a CPU frequency command can be sent to the host
using:
set_cpu_freq <lcore_num> <up|down|min|max>.
Signed-off-by: Alan Carew <alan.carew@intel.com>
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
For launching CLI thread and Monitor thread and initialising
resources.
Requires a minimum of two lcores to run, additional cores specified by eal core
mask are not used.
Signed-off-by: Alan Carew <alan.carew@intel.com>
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
A wrapper around librte_power(using ACPI cpufreq), providing locking around the
non-threadsafe library, allowing for frequency changes based on core masks and
core numbers from both the CLI thread and epoll monitor thread.
Signed-off-by: Alan Carew <alan.carew@intel.com>
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
The CLI is used for administrating the channel monitor and manager and
manually setting the CPU frequency on the host.
Supports the following commands:
add_vm [Mul-choice STRING]: add_vm|rm_vm <name>, add a VM for subsequent
operations with the CLI or remove a previously added VM from the VM Power
Manager
rm_vm [Mul-choice STRING]: add_vm|rm_vm <name>, add a VM for subsequent
operations with the CLI or remove a previously added VM from the VM Power
Manager
add_channels [Fixed STRING]: add_channels <vm_name> <list>|all, add
communication channels for the specified VM, the virtio channels must be
enabled in the VM configuration(qemu/libvirt) and the associated VM must be
active. <list> is a comma-separated list of channel numbers to add, using the
keyword 'all' will attempt to add all channels for the VM
set_channel_status [Fixed STRING]:
set_channel_status <vm_name> <list>|all enabled|disabled, enable or disable
the communication channels in list(comma-separated) for the specified VM,
alternatively list can be replaced with keyword 'all'. Disabled channels will
still receive packets on the host, however the commands they specify will be
ignored. Set status to 'enabled' to begin processing requests again.
show_vm [Fixed STRING]: show_vm <vm_name>, prints the information on the
specified VM(s), the information lists the number of vCPUS, the pinning to
pCPU(s) as a bit mask, along with any communication channels associated with
each VM
show_cpu_freq_mask [Fixed STRING]: show_cpu_freq_mask <mask>, Get the current
frequency for each core specified in the mask
set_cpu_freq_mask [Fixed STRING]: set_cpu_freq <core_mask> <up|down|min|max>,
Set the current frequency for the cores specified in <core_mask> by scaling
each up/down/min/max.
show_cpu_freq [Fixed STRING]: Get the current frequency for the specified core
set_cpu_freq [Fixed STRING]: set_cpu_freq <core_num> <up|down|min|max>,
Set the current frequency for the specified core by scaling up/down/min/max
quit [Fixed STRING]: close the application
Signed-off-by: Alan Carew <alan.carew@intel.com>
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
The manager is responsible for adding communications channels to the Monitor
thread, tracking and reporting VM state and employs the libvirt API for
synchronization with the KVM Hypervisor. The manager interacts with the
Hypervisor to discover the mapping of virtual CPUS(vCPUs) to the host
physical CPUS(pCPUs) and to inspect the VM running state.
The manager provides the following functionality to the CLI:
1) Connect to a libvirtd instance, default: qemu:///system
2) Add a VM to an internal list, each VM is identified by a "name" which must
correspond a valid libvirt Domain Name.
3) Add communication channels associated with a VM to the epoll based Monitor
thread.
The channels must exist and be in the form of:
/tmp/powermonitor/<vm_name>.<channel_number>. Each channel is a
Virtio-Serial endpoint configured as an AF_UNIX file socket and opened in
non-blocking mode.
Each VM can have a maximum of 64 channels associated with it.
4) Disable or re-enable VM communication channels, channels once added to the
Monitor thread remain in that threads control, however acting on channel
requests can be disabled and renabled via CLI.
The monitor is an epoll based infinite loop running in a separate thread that
waits on channel events from VMs and calls the corresponding functions. Channel
definitions from the manager are registered via the epoll event opaque pointer
when calling epoll_ctl(EPOLL_CTL_ADD), this allows for obtaining the channels
file descriptor for reading EPOLLIN events and mapping the vCPU to pCPU(s)
associated with a request from a particular VM.
Signed-off-by: Alan Carew <alan.carew@intel.com>
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
This is a very simple example app for doing packet forwarding with the
Intel DPDK. It's designed to serve as a start point for people new to
the Intel DPDK and who want to develop a new app.
Therefore it's meant to:
* have as good a performance out-of-the-box as possible, using the
best-known settings for configuring the PMDs, so that any new apps can
be based off it.
* be kept as short as possible to make it easy to understand it and get
started with it.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Since commit 08b563ffb1 ("mbuf: replace data pointer by an offset"),
data is not an mbuf field anymore.
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
A new sample app that shows the usage of the distributor library. This
app works as follows:
* An RX thread runs which pulls packets from each ethernet port in turn
and passes those packets to worker using a distributor component.
* The workers take the packets in turn, and determine the output port
for those packets using basic l2forwarding doing an xor on the source
port id.
* The RX thread takes the returned packets from the workers and enqueue
those packets into an rte_ring structure.
* A TX thread pulls the packets off the rte_ring structure and then
sends each packet out the output port specified previously by the worker
* Command-line option support provided only for portmask.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Signed-off-by: Reshma Pattan <reshma.pattan@intel.com>
Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
This is to enable user space vhost receiving and forwarding broadcast
and multicast packets:
Use new option in command line to enable promisc mode;
Enable 2 bits in VMDQ RX mode: ETH_VMDQ_ACCEPT_BROADCAST and ETH_VMDQ_ACCEPT_MULTICAST.
Signed-off-by: Changchun Ouyang <changchun.ouyang@intel.com>
This patch supports new VMDQ API in vmdq example.
Besides, it allows users to specify num_pools different with
max_nb_pools, thus the polling thread needn't to poll queues
of all pools.
Due to i40e implementation issue, there is no default mac for
VMDQ pool, so app needs to specify mac address for each pool
explicitly.
Signed-off-by: Huawei Xie <huawei.xie@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
These references to drivers break the layering isolation between
application and drivers.
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Acked-by: Helin Zhang <helin.zhang@intel.com>
This patch checks the packet length offset value, and checks if the
extra bytes inside buffer cross page boundary.
Signed-off-by: Changchun Ouyang <changchun.ouyang@intel.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Extract a function to replace duplicated codes in one copy and zero copy TX function.
Signed-off-by: Changchun Ouyang <changchun.ouyang@intel.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
As HW vlan strip will reduce the packet length by minus length of vlan tag,
so it need restore the packet length by plus it.
Signed-off-by: Changchun Ouyang <changchun.ouyang@intel.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Acked-by: Huawei Xie <huawei.xie@intel.com>
Since the commit 33e79bed3e has fixed the issue in vector PMD,
and then it can receive jumbo frame by scatter-gather mode, so remove this check.
Signed-off-by: Changchun Ouyang <changchun.ouyang@intel.com>
Acked-by: Huawei Xie <huawei.xie@intel.com>
The packet passed to virtio_tx_route has been allocated
mbuf, so there is no need to allocate mbuf for it.
Use vlan offload to transmit vlan tagged packet.
Signed-off-by: Huawei Xie <huawei.xie@intel.com>
Acked-by: Changchun Ouyang <changchun.ouyang@intel.com>
[Thomas: remove useless mbuf pool]
In switch_worker and virtio_tx_local, rte_vhost_enqueue_burst is called to
push host packets to guest VM.
Before enqueue packets to guest VM, vhost example uses configure-able retry logic
to wait for enough vring entries.
In switch_worker, rte_vhost_dequeue_burst is called to get packets from guest VM,
then virtio device will be bound to a queue in VMDQ for the first transmitted
packet.
Signed-off-by: Huawei Xie <huawei.xie@intel.com>
Acked-by: Changchun Ouyang <changchun.ouyang@intel.com>
check_hpa_regions, fill_hpa_memory_regions and hpa memory region
data structure are added back from old virtio-net.c.
Add hpa (host physical address) region generation/destroy logic.
gpa<->hpa memory translation regions are generated at new_device,
when a virtio device is ready for packet processing.
Signed-off-by: Huawei Xie <huawei.xie@intel.com>
Acked-by: Changchun Ouyang <changchun.ouyang@intel.com>
Define vhost_dev data structure.
Change reference to virtio_dev to vhost_dev.
The vhost example use vdev data structure for switching related logic
and container for virtio_dev.
Signed-off-by: Huawei Xie <huawei.xie@intel.com>
Acked-by: Changchun Ouyang <changchun.ouyang@intel.com>
Those functions are integrated into the user space vhost library:
virtio_dev_rx, virtio_dev_merge_rx, virtio_dev_tx, virtio_dev_merge_tx,
copy_from_mbuf_to_ring, gpa_to_vva.
Signed-off-by: Huawei Xie <huawei.xie@intel.com>
Acked-by: Changchun Ouyang <changchun.ouyang@intel.com>
This patch copies two files main.c/main.h from most recent vhost example
(before transforming into a library) as the base for new vhost example.
Signed-off-by: Huawei Xie <huawei.xie@intel.com>
Acked-by: Changchun Ouyang <changchun.ouyang@intel.com>
The previous implementation of rte_kni_alloc() was allocating memzones with a
name composed of a fixed string and the interface name. When an application was
allocating and deallocating multiple interfaces with different names, memzones
were quickly exhausted, even though memzones from deallocated interfaces were
never used anymore (unless an interface with the same name was re-allocated).
As a result, the application was unable to allocate more KNI interfaces with
different names.
This patch implements the KNI memzone pool in order to prevent memzone
exhaustion when allocating/deallocating KNI interfaces. It adds a new API call,
rte_kni_init(max_kni_ifaces) that shall be called before any call to
rte_kni_alloc() if KNI is used. The memzones are pre-allocated with interface-
independent names so that they can be reused.
Signed-off-by: Marc Sune <marc.sune@bisdn.de>
Acked-by: Helin Zhang <helin.zhang@intel.com>
Those files will be refactored in subsequent patches to form user space
vhost library.
Makefile and main.h are removed.
main.c is renamed to vhost_rxtx.c and will provide vring enqueue/dequeue API.
virtio-net.h is renamed to rte_virtio_net.h which is the API header file.
Signed-off-by: Huawei Xie <huawei.xie@intel.com>
Acked-by: Changchun Ouyang <changchun.ouyang@intel.com>
[Thomas: remove from examples Makefile and merge file renaming]
