Yongseok Koh [Thu, 2 May 2019 09:07:53 +0000 (02:07 -0700)]
bus/pci: add Mellanox kernel driver type
When checking RTE_PCI_DRV_IOVA_AS_VA flag to determine IOVA mode,
pci_one_device_has_iova_va() returns true only if kernel driver of the
device is vfio. However, Mellanox mlx4/5 PMD doesn't need to be detached
from kernel driver and attached to VFIO/UIO. Control path still goes
through the existing kernel driver, which is mlx4_core/mlx5_core. In order
to make RTE_PCI_DRV_IOVA_AS_VA effective for mlx4/mlx5 PMD, a new kernel
driver type has to be introduced.
Bruce Richardson [Tue, 14 May 2019 13:37:02 +0000 (14:37 +0100)]
eal/x86: check rdrand and rdseed
The meson build never checked for the presence of rdrand and rdseed
instructions, while make build never checked for rdseed. Ensure builds
always have the appropriate checks - and therefore defines - for these
instructions. For runtime, we also add in rdseed to the list of known
bits returned from cpuid() instruction, so we can confirm its presence at
application init time.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com> Tested-by: Mattias Rönnblom <mattias.ronnblom@ericsson.com>
Bruce Richardson [Wed, 15 May 2019 11:38:47 +0000 (12:38 +0100)]
build: warn on unused parameter
To improve code quality we want to turn on as many warnings as we can in
the DPDK code, so turn on the "unused-parameter" warning in meson builds to
match that of the make builds. To ensure correct compilation, disable the
warning selectively for driver base code that otherwise would have issues.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com> Acked-by: Luca Boccassi <bluca@debian.org>
Bruce Richardson [Tue, 28 May 2019 11:07:48 +0000 (12:07 +0100)]
build: add libatomic dependency for 32-bit clang
When compiling with clang on 32-bit platforms, we are missing copies
of 64-bit atomic functions. We can solve this by linking against
libatomic for the drivers and libs which need those atomic ops.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com> Acked-by: Luca Boccassi <bluca@debian.org>
Bruce Richardson [Tue, 28 May 2019 11:07:47 +0000 (12:07 +0100)]
mem: mark unused function in 32-bit builds
The get_socket_mem_size() function is only used in 64-bit builds,
causing clang to warn about it for 32-bit builds. Add the __rte_unused
attribute to the function to silence the warning.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com> Acked-by: Luca Boccassi <bluca@debian.org>
Bruce Richardson [Tue, 28 May 2019 11:07:46 +0000 (12:07 +0100)]
build: remove unnecessary large file support defines
Since we now always use _FILE_OFFSET_BITS=64 flag when building
DPDK, we can remove the Makefile and C-file #defines setting it
individually for parts of the build.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com> Acked-by: Luca Boccassi <bluca@debian.org>
Bruce Richardson [Tue, 28 May 2019 11:07:45 +0000 (12:07 +0100)]
build: enable large file support on 32-bit
By default on 32-bit systems, file offsets are given as 32-bit values
which prevents support for large files. While this is unlikely to be
a problem, enabling large file support globally makes "make" and
"meson" builds consistent, since meson always enables large file
support, and without this change, the size of "struct stat" fields
will be different between the two builds.
The only location where this appears to be significant is in the
dpaax common code, where a printf needs to be updated for 32-bit
builds.
The fields of the internal EAL core configuration are currently
laid bare as part of the API. This is not good practice and limits
fixing issues with layout and sizes.
Make new accessor functions for the fields used by current drivers
and examples.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: David Marchand <david.marchand@redhat.com>
David Marchand [Wed, 22 May 2019 15:06:56 +0000 (17:06 +0200)]
test/hash: use existing lcore API
Prefer the existing apis rather than direct access the configuration
structure.
test_hash_multi_add_lookup() currently starts n readers and N writers
using rte_eal_remote_launch().
It then waits for the N writers to complete with a custom
multi_writer_done[] array to synchronise over.
Jump on the occasion to use rte_eal_wait_lcore() so that the code is
more straightforward:
- we start n readers with rte_eal_remote_launch(),
- we start N writers with rte_eal_remote_launch(),
- we wait for N writers to join with rte_eal_wait_lcore(),
- we wait for n readers to join with rte_eal_wait_lcore(),
David Marchand [Wed, 15 May 2019 07:54:21 +0000 (09:54 +0200)]
examples/multi_process: do not dereference global config struct
Prefer the existing apis rather than direct access the configuration
structure.
Fixes: af75078fece3 ("first public release") Cc: stable@dpdk.org Signed-off-by: David Marchand <david.marchand@redhat.com> Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
David Marchand [Wed, 15 May 2019 07:54:20 +0000 (09:54 +0200)]
net/softnic: do not dereference global config struct
Prefer the existing apis rather than direct access the configuration
structure.
Fixes: a958a5c07f4b ("net/softnic: support service cores") Cc: stable@dpdk.org Signed-off-by: David Marchand <david.marchand@redhat.com> Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Bruce Richardson [Fri, 17 May 2019 13:45:29 +0000 (14:45 +0100)]
kernel/linux: remove unneeded meson variables
The local variables for the error message aren't needed, since the messages
aren't used more than once, and the indent levels are now such that the
lines printing the message are not much longer than the lines defining the
variables to hold the messages themselves. Therefore the use of the
variables is pointless.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com> Reviewed-by: David Marchand <david.marchand@redhat.com> Acked-by: Luca Boccassi <bluca@debian.org>
Bruce Richardson [Fri, 17 May 2019 13:45:28 +0000 (14:45 +0100)]
kernel/linux: reduce unneeded indents in meson file
Since meson 0.46, meson has supported the subdir_done() function, which
allows us to abort processing of a file early. Using this we can reduce the
indentation in our files by eliminating unnecessary else blocks.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com> Reviewed-by: David Marchand <david.marchand@redhat.com> Acked-by: Luca Boccassi <bluca@debian.org>
Ferruh Yigit [Fri, 24 May 2019 16:55:20 +0000 (17:55 +0100)]
kni: remove ethtool support
Current design requires kernel drivers and they need to be probed by
Linux up to some level so that they can be usable by DPDK for ethtool
support, this requires maintaining the Linux drivers in DPDK.
Also ethtool support is limited and hard, if not impossible, to expand
to other PMDs.
Since KNI ethtool support is not used commonly, if not used at all,
removing the support for the sake of simplicity and maintenance.
Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Stephen Hemminger <stephen@networkplumber.org> Acked-by: Neil Horman <nhorman@tuxdriver.com> Acked-by: Thomas Monjalon <thomas@monjalon.net>
Thomas Monjalon [Wed, 22 May 2019 17:55:24 +0000 (19:55 +0200)]
doc: robustify PDF build
In some environment like the current dpdk.org server,
there can be some errors due to symbols in titles,
as it was the case before this commit in DPDK 18.05:
commit 551d148944dc ("doc: remove flow API migration section")
! LaTeX Error: Bad math environment delimiter.
It can be avoided thanks to the Latex command \robustify.
Cc: stable@dpdk.org Signed-off-by: Thomas Monjalon <thomas@monjalon.net> Acked-by: John McNamara <john.mcnamara@intel.com>
Michael Santana [Fri, 10 May 2019 14:53:12 +0000 (10:53 -0400)]
fix off-by-one errors in snprintf
snprintf guarantees to always correctly place a null terminator
in the buffer string. So manually placing a null terminator
in a buffer right after a call to snprintf is redundant code.
Additionally, there is no need to use 'sizeof(buffer) - 1' in snprintf as this
means we are not using the last character in the buffer. 'sizeof(buffer)' is
enough.
Cc: stable@dpdk.org Signed-off-by: Michael Santana <msantana@redhat.com> Acked-by: Bruce Richardson <bruce.richardson@intel.com> Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
Ashijeet Acharya [Fri, 24 May 2019 09:30:15 +0000 (11:30 +0200)]
net/ixgbe/base: wait for link after copper MAC setup
After setting up the link on x552/X557-AT 10GBASE-T NICs, sometimes the
link does not get set up properly and as a result all the subsequent
calls to ixgbe_check_link() from ixgbe_dev_link_update_share() fail.
Introduce a delay time of 1s in ixgbe_setup_mac_link_t_X550em() before
beginning to set up the external PHY link speed to ensure that the
controller can acquire the link.
Ajit Khaparde [Wed, 15 May 2019 18:08:17 +0000 (11:08 -0700)]
net/bnxt: support bulk free of Tx mbufs
The driver currently uses rte_pktmbuf_free() to free each mbuf
after transmit completion. This is optimized to free multiple
mbufs using rte_mempool_put_bulk().
This patch adds a few optimizations to Tx batching. Instead of
specifying 'cmpl_next' to bnxt_start_xmit() as a hint to enable
completion for a given packet, request for completion on the last
successfully enqueued TxBD. This takes care of both success and
error cases. It eliminates 'cmpl_next' arg and related per-packet
condition checks around it.
This patch addresses the following issues with Tx batching:
1. Tx stall observed in some conditions:
The batching code doesn't request for a completion when only a partial
chain of packets is transmitted due to mbuf allocation errors. Because
of this, Tx consumer index is not updated correctly and it eventually
leads to qfull condition. Fix this by requesting a completion for the
last packet in the partial chain that is transmitted successfully.
2. Tx stall seen with Jumbo frames:
With jumbo frames, number of TxBDs is > 1. While setting up these
additional BDs in bnxt_start_xmit(), the flags field is being set using
the OR-assignment operator. We end up using a stale value of the flags
field (from a previous use of that descriptor). This results in an
invalid completion and eventually leads to tx stall. Fix this to just
assign the flags field with the right value.
Ajit Khaparde [Wed, 15 May 2019 18:08:14 +0000 (11:08 -0700)]
net/bnxt: check for error conditions in Tx path
The HW can have limits on the minimum packet size it can support,
or the maximum number of segments it can support. Check for such
possibilities. Also check if we are going to have a 0 length buffer.
Ajit Khaparde [Wed, 15 May 2019 18:08:12 +0000 (11:08 -0700)]
net/bnxt: fix TSO
We wrongly update lflags in the Tx descriptor; avoid it.
Also, instead of calculating the last producer index to see if mbuf
segments are chained, check if the pointer is NULL to iterate through
the segment list.
Dekel Peled [Mon, 20 May 2019 08:07:26 +0000 (11:07 +0300)]
net/mlx5: fix memory free on queue create error
In function mlx5_rxq_ibv_new(), pointer *tmpl allocation is attempted
at the start, but not validated or freed in case of error.
In function mlx5_txq_ibv_new(), pointer *txq_ibv allocation is
attempted at the start, but not freed in case of error.
This patch adds pointers initialization, validation and freeing.
Fixes: 09cb5b581762 ("net/mlx5: separate DPDK from verbs Rx queue objects") Fixes: faf2667fe8d5 ("net/mlx5: separate DPDK from verbs Tx queue objects") Cc: stable@dpdk.org Signed-off-by: Dekel Peled <dekelp@mellanox.com> Acked-by: Ori Kam <orika@mellanox.com>
Dekel Peled [Wed, 15 May 2019 10:11:38 +0000 (13:11 +0300)]
net/mlx5: remove redundant size calculation macro
Patch [1] added, among other definitions, the macro MLX5_ST_SZ_DB.
Patch [2] added later the macro MLX5_ST_SZ_BYTES, which is exactly
the same macro with a different name.
Each of these macros was used in very few places.
This patch removes the definition of MLX5_ST_SZ_DB, and replaces it
with MLX5_ST_SZ_BYTES wherever it was used.
Macro MLX5_ST_SZ_BYTES was preffered since it is the same macro
name used in kernel code, see [3].
Dekel Peled [Wed, 8 May 2019 08:29:41 +0000 (11:29 +0300)]
net/mlx5: move locally used functions to static
Multiple functions were declared in header file mlx5_rxtx.h,
implemented in mlx5_rxq.c, and called only in mlx5_rxq.c.
This patch moves all these functions declarations into mlx5_rxq.c,
as static functions.
Some functions implementation was copied higher in the file to
precede the functions calls.
Dekel Peled [Wed, 8 May 2019 08:29:39 +0000 (11:29 +0300)]
net/mlx5: fix missing validation of null pointer
Function mlx5_rxq_ibv_release() is called in several places.
Before each call except one, the input parameter is validated to make
sure it is not null.
This patch adds the validation where it is missing.
It also changes a priv_ prefix, left in a comment, to mlx5_ prefix.
Mesut Ali Ergin [Thu, 16 May 2019 04:28:03 +0000 (21:28 -0700)]
net/i40e: support MARK and RSS flow action
Currently, i40e Flow Director action parser only allows following nine
action combinations: (QUEUE, PASSTHRU, DROP, QUEUE + MARK, PASSTHRU +
MARK, DROP + MARK, QUEUE + FLAG, PASSTHRU + FLAG, DROP + FLAG)
Using the existing Cloud Filter profile on the NIC, it is possible to
add support for two more combinations as: (MARK + RSS, MARK + FLAG +
RSS)
Addition of these new combinations would allow more applications to
utilize DPDK rte_flow to implement hardware flow offloads with Intel
Ethernet 700 series network adapters, including but not limited to the
existing OVS DPDK partial hardware flow offload feature.
Signed-off-by: Mesut Ali Ergin <mesut.a.ergin@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Olivier Matz [Tue, 21 May 2019 16:13:11 +0000 (18:13 +0200)]
net: add rte prefix to IP defines
Add 'RTE_' prefix to defines:
- rename IPv4( as RTE_IPv4(.
- rename IPV4_MAX_PKT_LEN as RTE_IPV4_MAX_PKT_LEN.
- rename IPV4_HDR_IHL_MASK as RTE_IPV4_HDR_IHL_MASK.
- rename IPV4_IHL_MULTIPLIER as RTE_IPV4_IHL_MULTIPLIER.
- rename IPV4_HDR_DF_SHIFT as RTE_IPV4_HDR_DF_SHIFT.
- rename IPV4_HDR_MF_SHIFT as RTE_IPV4_HDR_MF_SHIFT.
- rename IPV4_HDR_FO_SHIFT as RTE_IPV4_HDR_FO_SHIFT.
- rename IPV4_HDR_DF_FLAG as RTE_IPV4_HDR_DF_FLAG.
- rename IPV4_HDR_MF_FLAG as RTE_IPV4_HDR_MF_FLAG.
- rename IPV4_HDR_OFFSET_MASK as RTE_IPV4_HDR_OFFSET_MASK.
- rename IPV4_HDR_OFFSET_UNITS as RTE_IPV4_HDR_OFFSET_UNITS.
- rename IPV4_ANY as RTE_IPV4_ANY.
- rename IPV4_LOOPBACK as RTE_IPV4_LOOPBACK.
- rename IPV4_BROADCAST as RTE_IPV4_BROADCAST.
- rename IPV4_ALLHOSTS_GROUP as RTE_IPV4_ALLHOSTS_GROUP.
- rename IPV4_ALLRTRS_GROUP as RTE_IPV4_ALLRTRS_GROUP.
- rename IPV4_MAX_LOCAL_GROUP as RTE_IPV4_MAX_LOCAL_GROUP.
- rename IPV4_MIN_MCAST as RTE_IPV4_MIN_MCAST.
- rename IPV4_MAX_MCAST as RTE_IPV4_MAX_MCAST.
- rename IS_IPV4_MCAST as RTE_IS_IPV4_MCAST.
- rename IPV6_HDR_FL_SHIFT as RTE_IPV6_HDR_FL_SHIFT.
- rename IPV6_HDR_TC_SHIFT as RTE_IPV6_HDR_TC_SHIFT.
- rename IPV6_HDR_FL_MASK as RTE_IPV6_HDR_FL_MASK.
- rename IPV6_HDR_TC_MASK as RTE_IPV6_HDR_TC_MASK.
Signed-off-by: Olivier Matz <olivier.matz@6wind.com> Reviewed-by: Stephen Hemminger <stephen@networkplumber.org> Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Olivier Matz [Tue, 21 May 2019 16:13:05 +0000 (18:13 +0200)]
net: add rte prefix to ether defines
Add 'RTE_' prefix to defines:
- rename ETHER_ADDR_LEN as RTE_ETHER_ADDR_LEN.
- rename ETHER_TYPE_LEN as RTE_ETHER_TYPE_LEN.
- rename ETHER_CRC_LEN as RTE_ETHER_CRC_LEN.
- rename ETHER_HDR_LEN as RTE_ETHER_HDR_LEN.
- rename ETHER_MIN_LEN as RTE_ETHER_MIN_LEN.
- rename ETHER_MAX_LEN as RTE_ETHER_MAX_LEN.
- rename ETHER_MTU as RTE_ETHER_MTU.
- rename ETHER_MAX_VLAN_FRAME_LEN as RTE_ETHER_MAX_VLAN_FRAME_LEN.
- rename ETHER_MAX_VLAN_ID as RTE_ETHER_MAX_VLAN_ID.
- rename ETHER_MAX_JUMBO_FRAME_LEN as RTE_ETHER_MAX_JUMBO_FRAME_LEN.
- rename ETHER_MIN_MTU as RTE_ETHER_MIN_MTU.
- rename ETHER_LOCAL_ADMIN_ADDR as RTE_ETHER_LOCAL_ADMIN_ADDR.
- rename ETHER_GROUP_ADDR as RTE_ETHER_GROUP_ADDR.
- rename ETHER_TYPE_IPv4 as RTE_ETHER_TYPE_IPv4.
- rename ETHER_TYPE_IPv6 as RTE_ETHER_TYPE_IPv6.
- rename ETHER_TYPE_ARP as RTE_ETHER_TYPE_ARP.
- rename ETHER_TYPE_VLAN as RTE_ETHER_TYPE_VLAN.
- rename ETHER_TYPE_RARP as RTE_ETHER_TYPE_RARP.
- rename ETHER_TYPE_QINQ as RTE_ETHER_TYPE_QINQ.
- rename ETHER_TYPE_ETAG as RTE_ETHER_TYPE_ETAG.
- rename ETHER_TYPE_1588 as RTE_ETHER_TYPE_1588.
- rename ETHER_TYPE_SLOW as RTE_ETHER_TYPE_SLOW.
- rename ETHER_TYPE_TEB as RTE_ETHER_TYPE_TEB.
- rename ETHER_TYPE_LLDP as RTE_ETHER_TYPE_LLDP.
- rename ETHER_TYPE_MPLS as RTE_ETHER_TYPE_MPLS.
- rename ETHER_TYPE_MPLSM as RTE_ETHER_TYPE_MPLSM.
- rename ETHER_VXLAN_HLEN as RTE_ETHER_VXLAN_HLEN.
- rename ETHER_ADDR_FMT_SIZE as RTE_ETHER_ADDR_FMT_SIZE.
- rename VXLAN_GPE_TYPE_IPV4 as RTE_VXLAN_GPE_TYPE_IPV4.
- rename VXLAN_GPE_TYPE_IPV6 as RTE_VXLAN_GPE_TYPE_IPV6.
- rename VXLAN_GPE_TYPE_ETH as RTE_VXLAN_GPE_TYPE_ETH.
- rename VXLAN_GPE_TYPE_NSH as RTE_VXLAN_GPE_TYPE_NSH.
- rename VXLAN_GPE_TYPE_MPLS as RTE_VXLAN_GPE_TYPE_MPLS.
- rename VXLAN_GPE_TYPE_GBP as RTE_VXLAN_GPE_TYPE_GBP.
- rename VXLAN_GPE_TYPE_VBNG as RTE_VXLAN_GPE_TYPE_VBNG.
- rename ETHER_VXLAN_GPE_HLEN as RTE_ETHER_VXLAN_GPE_HLEN.
Do not update the command line library to avoid adding a dependency to
librte_net.
Signed-off-by: Olivier Matz <olivier.matz@6wind.com> Reviewed-by: Stephen Hemminger <stephen@networkplumber.org> Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Olivier Matz [Tue, 21 May 2019 16:13:04 +0000 (18:13 +0200)]
net: add rte prefix to ether functions
Add 'rte_' prefix to functions:
- rename is_same_ether_addr() as rte_is_same_ether_addr().
- rename is_zero_ether_addr() as rte_is_zero_ether_addr().
- rename is_unicast_ether_addr() as rte_is_unicast_ether_addr().
- rename is_multicast_ether_addr() as rte_is_multicast_ether_addr().
- rename is_broadcast_ether_addr() as rte_is_broadcast_ether_addr().
- rename is_universal_ether_addr() as rte_is_universal_ether_addr().
- rename is_local_admin_ether_addr() as rte_is_local_admin_ether_addr().
- rename is_valid_assigned_ether_addr() as rte_is_valid_assigned_ether_addr().
- rename eth_random_addr() as rte_eth_random_addr().
- rename ether_addr_copy() as rte_ether_addr_copy().
- rename ether_format_addr() as rte_ether_format_addr().
Signed-off-by: Olivier Matz <olivier.matz@6wind.com> Reviewed-by: Stephen Hemminger <stephen@networkplumber.org> Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Olivier Matz [Tue, 21 May 2019 16:13:02 +0000 (18:13 +0200)]
net: add rte prefix to ARP defines
Add 'RTE_' prefix to defines:
- rename ARP_HRD_ETHER as RTE_ARP_HRD_ETHER.
- rename ARP_OP_REQUEST as RTE_ARP_OP_REQUEST.
- rename ARP_OP_REPLY as RTE_ARP_OP_REPLY.
- rename ARP_OP_REVREQUEST as RTE_ARP_OP_REVREQUEST.
- rename ARP_OP_REVREPLY as RTE_ARP_OP_REVREPLY.
- rename ARP_OP_INVREQUEST as RTE_ARP_OP_INVREQUEST.
- rename ARP_OP_INVREPLY as RTE_ARP_OP_INVREPLY.
Signed-off-by: Olivier Matz <olivier.matz@6wind.com> Reviewed-by: Stephen Hemminger <stephen@networkplumber.org> Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Haiyue Wang [Mon, 20 May 2019 08:14:33 +0000 (16:14 +0800)]
net/ice: update RSS RETA size with supported values
Since ice can support 128, 512, 2K RSS RETA size value, change the
update API to set it to resize the RSS RETA table. And by default,
use 512 to sync with ETH_RSS_RETA_SIZE_x maximum value definition.
Also the flag ICE_FLAG_RSS_AQ_CAPABLE is missed to set.
Fixes: 690175ee51bf ("net/ice: support getting device information") Fixes: ff963bfa7cb1 ("net/ice: support RSS") Cc: stable@dpdk.org Signed-off-by: Haiyue Wang <haiyue.wang@intel.com> Acked-by: Qiming Yang <qiming.yang@intel.com>
Qi Zhang [Sat, 4 May 2019 09:29:39 +0000 (17:29 +0800)]
net/ixgbe: fix Tx threshold setup
Tx desc's DD status is not cleaned by NIC automatically after packets
have been transmitted until software refill a new packet during next
loop. So when tx_free_thresh + tx_rs_thresh > nb_desc, it is possible
that an outdated DD status be checked as tx_next_dd, then segment fault
happen due to free a NULL mbuf pointer.
Then patch fixes this issue by
1. try to adapt tx_rs_thresh to an aggressive tx_free_thresh.
2. queue setup fail when tx_free_thresh + tx_rs_thresh > nb_desc
Qi Zhang [Sat, 4 May 2019 09:29:38 +0000 (17:29 +0800)]
net/ice: fix Tx threshold setup
Tx desc's DD status is not cleaned by NIC automatically after packets
have been transmitted until software refill a new packet during next
loop. So when tx_free_thresh + tx_rs_thresh > nb_desc, it is possible
that an outdated DD status be checked as tx_next_dd, then segment fault
happen due to free a NULL mbuf pointer.
Then patch fixes this issue by
1. try to adapt tx_rs_thresh to an aggressive tx_free_thresh.
2. queue setup fail when tx_free_thresh + tx_rs_thresh > nb_desc
Fixes: 50370662b727 ("net/ice: support device and queue ops") Cc: stable@dpdk.org Signed-off-by: Qi Zhang <qi.z.zhang@intel.com> Acked-by: Beilei Xing <beilei.xing@intel.com>
Qi Zhang [Sat, 4 May 2019 09:29:37 +0000 (17:29 +0800)]
net/i40e: fix Tx threshold setup
Tx desc's DD status is not cleaned by NIC automatically after packets
have been transmitted until software refill a new packet during next
loop. So when tx_free_thresh + tx_rs_thresh > nb_desc, it is possible
that an outdated DD status be checked as tx_next_dd, then segment fault
happen due to free a NULL mbuf pointer.
Then patch fixes this issue by
1. try to adapt tx_rs_thresh to an aggressive tx_free_thresh.
2. queue setup fail when tx_free_thresh + tx_rs_thresh > nb_desc
Xiao Wang [Mon, 6 May 2019 08:44:34 +0000 (16:44 +0800)]
net/fm10k: advertise supported RSS hash function
PMD should advertise supported RSS hash functions via
dev_info.flow_type_rss_offloads variable [1], otherwise upper level check
would fail on configuring RSS, leading to MQ RSS failure.
[1] commit aa1a6d87f15d ("ethdev: force RSS offload rules again") Cc: stable@dpdk.org Signed-off-by: Xiao Wang <xiao.w.wang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Yunjian Wang [Wed, 8 May 2019 12:51:38 +0000 (20:51 +0800)]
net/ixgbe: fix unexpected link handler
The nic's interrupt source has some active handler, which maybe call
ixgbe_dev_link_update() to set link handler. We should cancel the
link handler before remove dev to prevent executing the link handler.
It triggers segfault.
Fixes: 0408f47ba4d6 ("net/ixgbe: fix busy polling while fiber link update") Cc: stable@dpdk.org Signed-off-by: Yunjian Wang <wangyunjian@huawei.com> Acked-by: Wei Zhao <wei.zhao1@intel.com>
Qi Zhang [Tue, 7 May 2019 01:53:46 +0000 (09:53 +0800)]
net/ice: set min and max MTU
This commit sets the min and max supported MTU values for ice devices
via the ice_dev_info_get() function. Min MTU supported is set to
ETHER_MIN_MTU and max mtu is calculated as the max packet length
supported minus the transport overhead.
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com> Acked-by: Qiming Yang <qiming.yang@intel.com>
Wei Zhao [Thu, 9 May 2019 02:59:30 +0000 (10:59 +0800)]
net/i40e: forbid two RSS flow rules
Refuse to create the second RSS flow rule as only one RSS key and
HASH register for each PF port. Users should delete the first rule
before setup the second rule.
Xiao Wang [Wed, 24 Apr 2019 07:51:36 +0000 (15:51 +0800)]
net/fm10k: support Rx queue count API
Some application, e.g. the l3fwd-power sample uses rte_eth_rx_queue_count()
API to get the get the number of used descriptors of a Rx queue. This patch
adds fm10k implementation for this API.
Signed-off-by: Xiao Wang <xiao.w.wang@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Bruce Richardson [Fri, 17 May 2019 12:02:31 +0000 (13:02 +0100)]
examples: fix make clean when using pkg-config
The "make clean" command had a number of issues:
- the "--ignore-fail-on-non-empty" flag is not present on BSD
- the call to remove the build folder would fail if there was no build
folder present.
These are fixed by only removing the build folder if it exists, and by
using -p flag to rmdir in place of --ignore-fail-on-non-empty
Fixes: 22119c4591a0 ("examples: use pkg-config in makefiles") Cc: stable@dpdk.org Signed-off-by: Bruce Richardson <bruce.richardson@intel.com> Acked-by: Luca Boccassi <bluca@debian.org>
Bruce Richardson [Fri, 17 May 2019 12:02:30 +0000 (13:02 +0100)]
examples: remove auto-generation of examples list
The examples/meson.build file scanned the filesystem to find all examples
to build (for examples=all option) and install. However, using run_command
and scanning the filesystem prevented ninja from properly detecting the
addition or removal of any examples - one had to recreate the build
directory from scratch to guarantee correct detection of all examples. This
patch replaces this generated list with a static list of examples, thereby
allowing proper tracking by ninja/meson, but at the cost of having to
update this file when a new example is added or removed.
This also fixes an issue with Windows builds, since "sh" is not available
there.
Fixes: 2daf565f91b5 ("examples: install as part of ninja install") Cc: stable@dpdk.org Signed-off-by: Bruce Richardson <bruce.richardson@intel.com> Acked-by: Luca Boccassi <bluca@debian.org>
Bruce Richardson [Fri, 17 May 2019 12:02:29 +0000 (13:02 +0100)]
examples: fix install with empty meson parameter
While the examples were being installed into the appropriate install path
when processing the examples/meson.build file, that file was only processed
if the "examples" meson parameter was non-empty. Since we now do more than
just build the examples, we need to unconditionally process the file.
Fixes: 2daf565f91b5 ("examples: install as part of ninja install") Cc: stable@dpdk.org Signed-off-by: Bruce Richardson <bruce.richardson@intel.com> Acked-by: Luca Boccassi <bluca@debian.org>
Add deprecation note for making changes in data structures, APIs
and macros in order to have more traffic classes, flexible
mapping of pipe queues to traffic classes, subport level
configuration of pipes and queues, etc. These changes are aligned
to improvements suggested in the RFC-
https://mails.dpdk.org/archives/dev/2018-November/120035.html
Signed-off-by: Jasvinder Singh <jasvinder.singh@intel.com> Acked-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com> Acked-by: Mohammad Abdul Awal <mohammad.abdul.awal@intel.com> Acked-by: Reshma Pattan <reshma.pattan@intel.com>
This patch adds deprecation notice of changing iv behaviour
when using Galois Counter Mode of operation.
With this change, IV of all supported sizes can be used.
Signed-off-by: Arek Kusztal <arkadiuszx.kusztal@intel.com> Acked-by: Fiona Trahe <fiona.trahe@intel.com> Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com> Acked-by: Akhil Goyal <akhil.goyal@nxp.com> Acked-by: Anoob Joseph <anoobj@marvell.com>
doc: announce removal of memory config struct from API
It is planned to make the rte_mem_config struct of the EAL private to
remove it from the visible ABI. Add a notice to announce the intention.
Signed-off-by: Erik Gabriel Carrillo <erik.g.carrillo@intel.com> Acked-by: Anatoly Burakov <anatoly.burakov@intel.com> Acked-by: Bruce Richardson <bruce.richardson@intel.com> Acked-by: David Marchand <david.marchand@redhat.com>
Thomas Monjalon [Tue, 7 May 2019 16:02:31 +0000 (18:02 +0200)]
doc: prepare security process for vulnerabilities
In case a vulnerability is discovered, the process to follow
is described in this document.
It has been inspired by the process of some referenced projects
and with the help of experts from Intel, RedHat, Mellanox
and the Linux Foundation.
Signed-off-by: Thomas Monjalon <thomas@monjalon.net> Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com> Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Stephen Hemminger <stephen@networkplumber.org> Acked-by: Luca Boccassi <bluca@debian.org>
Now that some of the symbols in the timer lib are versioned, the
Doxygen documentation that is generated is incorrect. Group all
versioned symbols, listing the generic name first, and remove comments
for older versions of symbols.
Fixes: c0749f7096c7 ("timer: allow management in shared memory") Signed-off-by: Erik Gabriel Carrillo <erik.g.carrillo@intel.com>
Wei Zhao [Thu, 9 May 2019 07:20:47 +0000 (15:20 +0800)]
app/testpmd: fix offload flags after port config
There is an error in function rxtx_port_config(), which may overwrite
offloads configuration get from function launch_args_parse() when run
testpmd app. So rxtx_port_config() should do "or" for port offloads.
net/mlx5: fix device removal handler for multiport
IBV_EVENT_DEVICE_FATAL event is generated by the driver once for
the entire multiport Infiniband device, not for each existing ports.
The port index is zero and it causes dropping the device removal
event. We should invoke the removal event processing routine
for each port we have installed handler for.
Mattias Rönnblom [Fri, 10 May 2019 12:18:16 +0000 (14:18 +0200)]
event/dsw: ignore scheduling type for single-link queues
The scheduling type parameter is not applicable for single link
queues. DSW would, at the time of rte_event_queue_setup(), erroneously
verify that scheduling type was one of the supported types, and
returned -ENOTSUP in case of RTE_SCHED_TYPE_ORDERED.
Nikhil Rao [Fri, 10 May 2019 08:08:10 +0000 (13:38 +0530)]
eventdev: fix Rx adapter event flush
The Rx adapter flushes events only if it has BATCH_SIZE
events buffered where BATCH_SIZE is set to 32, e.g., if a
single packet is sent, it is never passed to
eventdev. Fix this issue by adding an event buffer flush
either when a Rx queue is found to be empty or the adapter service
function has processed the max number of packets for an invocation.
git.droids-corp.org / dpdk.git / log