[ Upstream commit 998e5166e6 ]
Since commit 92418fb147 ("i40e/i40evf: Use usec value instead of reg
value for ITR defines") the driver tracks the interrupt throttling
intervals in single usec units, although the actual ITRN/ITR0 registers are
programmed in 2 usec units. Most register programming flows in the driver
correctly handle the conversion, although it is currently not applied when
the registers are initialized to their default values. Most of the time
this doesn't present a problem since the default values are usually
immediately overwritten through the standard adaptive throttling mechanism,
or updated manually by the user, but if adaptive throttling is disabled and
the interval values are left alone then the incorrect value will persist.
Since the intended default interval of 50 usecs (vs. 100 usecs as
programmed) performs better for most traffic workloads, this can lead to
performance regressions.
This patch adds the correct conversion when writing the initial values to
the ITRN registers.
Signed-off-by: Nicholas Nunley <nicholas.d.nunley@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 7c3758f783 ]
On link types that do not support autoneg, we cannot attempt to restart
nway negotiation. This results in a dead link that requires a power
cycle to remedy.
Fix this by saving off the autoneg state and checking this value before
we try to restart nway.
Signed-off-by: Mitch Williams <mitch.a.williams@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 43ade6ad18 ]
Clang warns when one enumerated type is converted implicitly to another.
drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c:4214:42: warning:
implicit conversion from enumeration type 'enum i40e_aq_link_speed' to
different enumeration type 'enum virtchnl_link_speed'
[-Wenum-conversion]
pfe.event_data.link_event.link_speed = I40E_LINK_SPEED_40GB;
~ ^~~~~~~~~~~~~~~~~~~~
1 warning generated.
Use the proper enum from virtchnl_link_speed, which has the same value
as I40E_LINK_SPEED_40GB, VIRTCHNL_LINK_SPEED_40GB. This appears to be
missed by commit ff3f4cc267 ("virtchnl: finish conversion to virtchnl
interface").
Link: https://github.com/ClangBuiltLinux/linux/issues/81
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit e78d9a39fd ]
If our card has been put in an unstable state due to
other drivers interacting with it, speed settings
might be incorrect. If incorrect, forcefully reset them
on open to known default values.
Signed-off-by: Jan Sokolowski <jan.sokolowski@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit a7542b8760 upstream.
While testing VF spawn/destroy the following panic occurred.
BUG: unable to handle kernel NULL pointer dereference at 0000000000000029
[...]
Workqueue: i40e i40e_service_task [i40e]
RIP: 0010:i40e_sync_vsi_filters+0x6fd/0xc60 [i40e]
[...]
Call Trace:
? __switch_to_asm+0x35/0x70
? __switch_to_asm+0x41/0x70
? __switch_to_asm+0x35/0x70
? _cond_resched+0x15/0x30
i40e_sync_filters_subtask+0x56/0x70 [i40e]
i40e_service_task+0x382/0x11b0 [i40e]
? __switch_to_asm+0x41/0x70
? __switch_to_asm+0x41/0x70
process_one_work+0x1a7/0x3b0
worker_thread+0x30/0x390
? create_worker+0x1a0/0x1a0
kthread+0x112/0x130
? kthread_bind+0x30/0x30
ret_from_fork+0x35/0x40
Investigation revealed a race where pf->vf[vsi->vf_id].trusted may get
accessed by the watchdog via i40e_sync_filters_subtask() although
i40e_free_vfs() already free'd pf->vf.
To avoid this the call to i40e_sync_vsi_filters() in
i40e_sync_filters_subtask() needs to be guarded by __I40E_VF_DISABLE,
which is also used by i40e_free_vfs().
Note: put the __I40E_VF_DISABLE check after the
__I40E_MACVLAN_SYNC_PENDING check as the latter is more likely to
trigger.
CC: stable@vger.kernel.org
Signed-off-by: Stefan Assmann <sassmann@kpanic.de>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 3e957b377b ]
Added a new local variable in the i40e_setup_tc function named
old_queue_pairs so num_queue_pairs can be restored to the correct
value in case configuring queue channels fails. Additionally, moved
the exit label in the i40e_setup_tc function so the if (need_reset)
block can be executed.
Also, fixed data packing in the i40e_setup_tc function.
Signed-off-by: Adam Ludkiewicz <adam.ludkiewicz@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit bfb0ebed53 ]
Modifying the VLAN stripping options when a port VLAN is configured
will break traffic for the VSI, and conceptually doesn't make sense,
so don't allow this.
Signed-off-by: Nicholas Nunley <nicholas.d.nunley@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 06b6e2a233 ]
This patch fixes the problem with the driver being able to add only 7
multicast MAC address filters instead of 16. The problem is fixed by
changing the maximum number of MAC address filters to 16+1+1 (two extra
are needed because the driver uses 1 for unicast MAC address and 1 for
broadcast).
Signed-off-by: Adam Ludkiewicz <adam.ludkiewicz@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit cdec2141c2 upstream.
When XDP is enabled, the driver will report incorrect
statistics. Received frames will reported as transmitted frames.
This commits fixes the i40e implementation of ndo_get_stats64 (struct
net_device_ops), so that iproute2 will report correct statistics
(e.g. when running "ip -stats link show dev eth0") even when XDP is
enabled.
Reported-by: Jesper Dangaard Brouer <brouer@redhat.com>
Fixes: 74608d17fe ("i40e: add support for XDP_TX action")
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Cc: Emeric Brun <ebrun@haproxy.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 31389b53b3 ]
Out of bound read reported by KASan.
i40iw_net_event() reads unconditionally 16 bytes from
neigh->primary_key while the memory allocated for
"neighbour" struct is evaluated in neigh_alloc() as
tbl->entry_size + dev->neigh_priv_len
where "dev" is a net_device.
But the driver does not setup dev->neigh_priv_len and
we read beyond the neigh entry allocated memory,
so the patch in the next mail fixes this.
Signed-off-by: Konstantin Khorenko <khorenko@virtuozzo.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit d5585b7b68 ]
If a TX hang occurs, we attempt to recover by incrementally resetting.
If we're starved for CPU time, it's possible the reset doesn't actually
complete (or even fire) before another tx_timeout fires causing us to
fly through the different resets without actually doing them.
This adds a bit to set and check if a timeout recovery is already
pending and, if so, bail out of tx_timeout. The bit will get cleared at
the end of i40e_rebuild when reset is complete.
Signed-off-by: Alan Brady <alan.brady@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 158daed16e ]
A previous commit moved the ether_addr_copy() in i40e_set_mac() before
the mac filter del/add to avoid a race. However it wasn't taken into
account that this alters the mac address being handed to
i40e_del_mac_filter().
Also changed i40e_add_mac_filter() to operate on netdev->dev_addr,
hopefully that makes the code easier to read.
Fixes: 458867b2ca ("i40e: don't remove netdev->dev_addr when syncing uc list")
Signed-off-by: Stefan Assmann <sassmann@kpanic.de>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Acked-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit eab077aa84 upstream.
In __i40e_del_filter function, the flag __I40E_MACVLAN_SYNC_PENDING for
the PF state is wrongly set for the VSI. Deleting any of the MAC filters
has caused the incorrect syncing for the PF. Fix it by setting this state
flag to the intended PF.
CC: stable <stable@vger.kernel.org>
Signed-off-by: Lihong Yang <lihong.yang@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit ba766b8b99 ]
Since commit bacd75cfac ("i40e/i40evf: Add capability exchange for
outer checksum", 2017-04-06) the i40e driver has not reported support
for IP-in-IP offloads. This likely occurred due to a bad rebase, as the
commit extracts hw_enc_features into its own variable. As part of this
change, it dropped the NETIF_F_FSO_IPXIP flags from the
netdev->hw_enc_features. This was unfortunately not caught during code
review.
Fix this by adding back the missing feature flags.
For reference, NETIF_F_GSO_IPXIP4 was added in commit 7e13318daa
("net: define gso types for IPx over IPv4 and IPv6", 2016-05-20),
replacing NETIF_F_GSO_IPIP and NETIF_F_GSO_SIT.
NETIF_F_GSO_IPXIP6 was added in commit bf2d1df395 ("intel: Add support
for IPv6 IP-in-IP offload", 2016-05-20).
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Commit 9b10df596b ("i40e: use WARN_ONCE to replace the commented
BUG_ON size check") introduced a warning check to make sure
that the size of the stat strings was always the expected value. This
code accidentally inverted the check of the data pointer. Fix this so
that we accurately count the size of the stats we copied in.
This fixes an erroneous WARN kernel splat that occurs when requesting
ethtool statistics.
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Tested-by: Mauro S M Rodrigues <maurosr@linux.vnet.ibm.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
If interface is connected to switch port configured for DCB there are
TX timeouts when bringing up interface. Problem started appearing after
adding in i40e driver code mqprio hardware offload mode. In function
i40e_vsi_configure_bw_alloc was added resetting BW rate which should
be executing when mqprio qdisc is removed but was also when there was
no mqprio qdisc added and DCB was enabled. In this patch was added
additional check for DCB flag so now when DCB is enabled the correct
DCB configs from before mqprio patch are restored.
Signed-off-by: Martyna Szapar <martyna.szapar@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.
Addresses-Coverity-ID: 114791 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.
Addresses-Coverity-ID: 114790 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This function accidentally failed to update the data pointer, which
caused the reported stats to be incorrect. Additionally, statistics
which follow queue stats in the output would potentially read non-zeroed
garbage data from the ethtool buffer.
This occurred because the data double pointer was not dereferenced
before incrementing the size.
Additionally, make sure this issue is more visible by adding a WARN_ONCE
to the i40e_get_ethtool_stats function. This warning will trigger
whenever the data pointer is not at the expected address, similar to the
check that we make in the i40e_get_stat_strings() function.
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
During switching between old NVM structure approach (called structured
NVM) to new one (called flat NVM) or backward flash needs to be
rearranged to required NVM structure. This is a part of transition from
one NVM structure to another. The function is introduced to command
firmware to start rearrangement process.
Signed-off-by: Piotr Azarewicz <piotr.azarewicz@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
In commit 147e81ec75 ("i40e: Test memory before ethtool alloc succeeds")
code was added to handle ring allocation on systems with low memory.
It shadowed the ring parameter pointer by introducing a local ring
pointer inside the for loop. Most of the code in the loop already just
accessed the ring via &rx_rings[i]. Since most of the code already does
this, just remove the local variable.
If someone considers it worth keeping a local around, they should use it
for the whole section instead of just a couple of accesses.
This fixes a warning when -Wshadow is enabled
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Commit c61c8fe1d5 ("i40e: Implement an ethtool private flag to stop
LLDP in FW") added an extra for-loop which added a shadowing 'i'
variable as the index.
However, the local variable i already exists, and we already use it as
a loop index. Additionally, at this point, there is no further use of
the variable, so it's safe to simply overwrite the variable contents.
This fixes a -Wshadow warning which has started being enabled on some
distributions
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Patryk Malek <patryk.malek@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
The priority flow control statistics are laid out in the stats structure
using arrays. This made it unwieldy to use as part of an i40e_stats
array.
Add a new structure type, i40e_pfc_stats, and a helper function
i40e_get_pfc_stats which can return the stats for a given priority
value as an i40e_pfc_stats structure.
Use this to create an i40e_stats array, which we'll use to format and
copy the strings and stats into the supplied buffers.
This reduces even more boiler plate code in i40e_get_ethtool_stats and
i40e_get_stat_strings.
An alternative would be to modify the structure definition for the pfc
stats, but this is more invasive to the rest of the code base.
Note that a macro was used to setup the copy of stats from the
pf->stats, as this reduces the chance of typos in the code names. It
will produce a checkpatch.pl warning due to re-use of a macro argument.
In this case, it should be safe, as the macro will fail to compile in
cases where the argument is not a simple structure member name, and thus
arguments with side effects should not be an issue.
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
The VEB TC stats are currently implemented with separate parsing,
instead of using the i40e_stats array and associated helper functions.
This is likely because the stats rely on embedding the TC number into
the stat name.
Update i40e_add_stat_strings to take variadic arguments, and use these
to vsnprintf the i40e_stats string as a string containing format
specifiers.
Create a stats array for the VEB TC related stats,
i40e_gstrings_veb_tc_stats, and use this along with the helper functions
to remove the specialized boiler plate code.
Always call i40e_add_ethtool_stats for both this array and the general
VEB stats array. This ensures that we zero out any memory in case it was
not zero-allocated for us.
This ultimately results in less boiler plate code for the
i40e_get_stat_strings and i40e_get_ethtool_stats.
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
This patch configures FEC setting in i40e_force_link_state().
For some reason setting this field was overlooked thus causing
25G link to be configured incorrectly.
Signed-off-by: Mariusz Stachura <mariusz.stachura@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Similar to the helper function to copy the ethtool stats strings, add
and use a helper function for copying the ethtool stats into the
supplied buffer.
Just like before, we use a macro to avoid having to pass ARRAY_SIZE
manually, so as to reduce chance of bugs.
Some of the stats, especially queue stats, are a bit trickier, and will
be handled in future patches.
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Many of the ethtool statistics use the same basic logic for copying
strings into the supplied buffer. A set of stats are stored in a const
array of i40e_stats structures, and we apply these all together.
Simplify the stats code by introducing a helper function which can take
a stats array and copy the strings into the buffer, updating the buffer
pointer as we go.
We use a macro to implement i40e_add_stat_strings so that ARRAY_SIZE can
be used on the array passed in. This ensures that we always use the
matching size in __i40e_add_stat_strings.
More complex stats currently do not use i40e_stats arrays, usually due
to custom formatted strings, or because the stats are not laid out in
the expected way. These stats will be updated to use the helper function
in separate future patches.
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Function call to i40e_prep_for_reset() is duplicated in
i40e_shutdown routine and gets called before
i40e_enable_mc_magic_wake() which blocks it from being executed
correctly on system reboot or shutdown because adminq is already
disabled by first i40e_prep_for_reset() call.
Two register write calls are also duplicated.
Signed-off-by: Sergey Nemov <sergey.nemov@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
prog_attached of struct netdev_bpf should have been superseded
by simply setting prog_id long time ago, but we kept it around
to allow offloading drivers to communicate attachment mode (drv
vs hw). Subsequently drivers were also allowed to report back
attachment flags (prog_flags), and since nowadays only programs
attached will XDP_FLAGS_HW_MODE can get offloaded, we can tell
the attachment mode from the flags driver reports. Remove
prog_attached member.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Simple overlapping changes in stmmac driver.
Adjust skb_gro_flush_final_remcsum function signature to make GRO list
changes in net-next, as per Stephen Rothwell's example merge
resolution.
Signed-off-by: David S. Miller <davem@davemloft.net>
The driver was combining the XDP_TX tail flush and XDP_REDIRECT
map flushing (xdp_do_flush_map). This is suboptimal, these two
flush operations should be kept separate.
It looks like the mistake was copy-pasted from ixgbe.
Fixes: d9314c474d ("i40e: add support for XDP_REDIRECT")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pass the extact struct from a tc qdisc add to the block bind function and,
in turn, to the setup_tc ndo of binding device via the tc_block_offload
struct. Pass this back to any block callback registrations to allow
netlink logging of fails in the bind process.
Signed-off-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
-EOPNOTSUPP is the error value that should be reported if a flower
command is not supported by a driver. Fix it in couple of Intel drivers.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
random_ether_addr is a #define for eth_random_addr which is
generally preferred in kernel code by ~3:1
Convert the uses of random_ether_addr to enable removing the #define
Miscellanea:
o Convert &vfmac[0] to equivalent vfmac and avoid unnecessary line wrap
Signed-off-by: Joe Perches <joe@perches.com>
Acked-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Using skb_reserve(skb, I40E_SKB_PAD + (xdp->data - xdp->data_hard_start))
is clearly wrong since I40E_SKB_PAD already points to the offset where
the original xdp->data was sitting since xdp->data_hard_start is defined
as xdp->data - i40e_rx_offset(rx_ring) where latter offsets to I40E_SKB_PAD
when build skb is used.
However, also before cc5b114dcf ("bpf, i40e: add meta data support")
this seems broken since bpf_xdp_adjust_head() helper could have been used
to alter headroom and enlarge / shrink the frame and with that the assumption
that the xdp->data remains unchanged does not hold and would push a bogus
packet to upper stack.
ixgbe got this right in 9247080816 ("ixgbe: add XDP support for pass and
drop actions"). In any case, fix it by removing the I40E_SKB_PAD from both
skb_reserve() and truesize calculation.
Fixes: cc5b114dcf ("bpf, i40e: add meta data support")
Fixes: 0c8493d90b ("i40e: add XDP support for pass and drop actions")
Reported-by: Keith Busch <keith.busch@linux.intel.com>
Reported-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Björn Töpel <bjorn.topel@intel.com>
Cc: John Fastabend <john.fastabend@gmail.com>
Tested-by: Keith Busch <keith.busch@linux.intel.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Daniel Borkmann says:
====================
pull-request: bpf-next 2018-06-05
The following pull-request contains BPF updates for your *net-next* tree.
The main changes are:
1) Add a new BPF hook for sendmsg similar to existing hooks for bind and
connect: "This allows to override source IP (including the case when it's
set via cmsg(3)) and destination IP:port for unconnected UDP (slow path).
TCP and connected UDP (fast path) are not affected. This makes UDP support
complete, that is, connected UDP is handled by connect hooks, unconnected
by sendmsg ones.", from Andrey.
2) Rework of the AF_XDP API to allow extending it in future for type writer
model if necessary. In this mode a memory window is passed to hardware
and multiple frames might be filled into that window instead of just one
that is the case in the current fixed frame-size model. With the new
changes made this can be supported without having to add a new descriptor
format. Also, core bits for the zero-copy support for AF_XDP have been
merged as agreed upon, where i40e bits will be routed via Jeff later on.
Various improvements to documentation and sample programs included as
well, all from Björn and Magnus.
3) Given BPF's flexibility, a new program type has been added to implement
infrared decoders. Quote: "The kernel IR decoders support the most
widely used IR protocols, but there are many protocols which are not
supported. [...] There is a 'long tail' of unsupported IR protocols,
for which lircd is need to decode the IR. IR encoding is done in such
a way that some simple circuit can decode it; therefore, BPF is ideal.
[...] user-space can define a decoder in BPF, attach it to the rc
device through the lirc chardev.", from Sean.
4) Several improvements and fixes to BPF core, among others, dumping map
and prog IDs into fdinfo which is a straight forward way to correlate
BPF objects used by applications, removing an indirect call and therefore
retpoline in all map lookup/update/delete calls by invoking the callback
directly for 64 bit archs, adding a new bpf_skb_cgroup_id() BPF helper
for tc BPF programs to have an efficient way of looking up cgroup v2 id
for policy or other use cases. Fixes to make sure we zero tunnel/xfrm
state that hasn't been filled, to allow context access wrt pt_regs in
32 bit archs for tracing, and last but not least various test cases
for fixes that landed in bpf earlier, from Daniel.
5) Get rid of the ndo_xdp_flush API and extend the ndo_xdp_xmit with
a XDP_XMIT_FLUSH flag instead which allows to avoid one indirect
call as flushing is now merged directly into ndo_xdp_xmit(), from Jesper.
6) Add a new bpf_get_current_cgroup_id() helper that can be used in
tracing to retrieve the cgroup id from the current process in order
to allow for e.g. aggregation of container-level events, from Yonghong.
7) Two follow-up fixes for BTF to reject invalid input values and
related to that also two test cases for BPF kselftests, from Martin.
8) Various API improvements to the bpf_fib_lookup() helper, that is,
dropping MPLS bits which are not fully hashed out yet, rejecting
invalid helper flags, returning error for unsupported address
families as well as renaming flowlabel to flowinfo, from David.
9) Various fixes and improvements to sockmap BPF kselftests in particular
in proper error detection and data verification, from Prashant.
10) Two arm32 BPF JIT improvements. One is to fix imm range check with
regards to whether immediate fits into 24 bits, and a naming cleanup
to get functions related to rsh handling consistent to those handling
lsh, from Wang.
11) Two compile warning fixes in BPF, one for BTF and a false positive
to silent gcc in stack_map_get_build_id_offset(), from Arnd.
12) Add missing seg6.h header into tools include infrastructure in order
to fix compilation of BPF kselftests, from Mathieu.
13) Several formatting cleanups in the BPF UAPI helper description that
also fix an error during rst2man compilation, from Quentin.
14) Hide an unused variable in sk_msg_convert_ctx_access() when IPv6 is
not built into the kernel, from Yue.
15) Remove a useless double assignment in dev_map_enqueue(), from Colin.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Remove the ndo_xdp_flush call implementation i40e_xdp_flush
as no callers of ndo_xdp_flush are left.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Add support for XDP meta data when using build skb variant of
the i40e driver. Implementation is analogous to the existing
ixgbe and ixgbevf support for meta data from 366a88fe2f ("bpf,
ixgbe: add meta data support") and be8333322e ("ixgbevf: Add
support for meta data"). With the build skb variant we get
192 bytes of extra headroom which can be used for encaps or
meta data.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Tested-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
When passed the XDP_XMIT_FLUSH flag i40e_xdp_xmit now performs the
same kind of ring tail update as in i40e_xdp_flush. The advantage is
that all the necessary checks have been performed and xdp_ring can be
updated, instead of having to perform the exact same steps/checks in
i40e_xdp_flush
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This patch only change the API and reject any use of flags. This is an
intermediate step that allows us to implement the flush flag operation
later, for each individual driver in a separate patch.
The plan is to implement flush operation via XDP_XMIT_FLUSH flag
and then remove XDP_XMIT_FLAGS_NONE when done.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Alexei Starovoitov says:
====================
pull-request: bpf-next 2018-05-24
The following pull-request contains BPF updates for your *net-next* tree.
The main changes are:
1) Björn Töpel cleans up AF_XDP (removes rebind, explicit cache alignment from uapi, etc).
2) David Ahern adds mtu checks to bpf_ipv{4,6}_fib_lookup() helpers.
3) Jesper Dangaard Brouer adds bulking support to ndo_xdp_xmit.
4) Jiong Wang adds support for indirect and arithmetic shifts to NFP
5) Martin KaFai Lau cleans up BTF uapi and makes the btf_header extensible.
6) Mathieu Xhonneux adds an End.BPF action to seg6local with BPF helpers allowing
to edit/grow/shrink a SRH and apply on a packet generic SRv6 actions.
7) Sandipan Das adds support for bpf2bpf function calls in ppc64 JIT.
8) Yonghong Song adds BPF_TASK_FD_QUERY command for introspection of tracing events.
9) other misc fixes from Gustavo A. R. Silva, Sirio Balmelli, John Fastabend, and Magnus Karlsson
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch change the API for ndo_xdp_xmit to support bulking
xdp_frames.
When kernel is compiled with CONFIG_RETPOLINE, XDP sees a huge slowdown.
Most of the slowdown is caused by DMA API indirect function calls, but
also the net_device->ndo_xdp_xmit() call.
Benchmarked patch with CONFIG_RETPOLINE, using xdp_redirect_map with
single flow/core test (CPU E5-1650 v4 @ 3.60GHz), showed
performance improved:
for driver ixgbe: 6,042,682 pps -> 6,853,768 pps = +811,086 pps
for driver i40e : 6,187,169 pps -> 6,724,519 pps = +537,350 pps
With frames avail as a bulk inside the driver ndo_xdp_xmit call,
further optimizations are possible, like bulk DMA-mapping for TX.
Testing without CONFIG_RETPOLINE show the same performance for
physical NIC drivers.
The virtual NIC driver tun sees a huge performance boost, as it can
avoid doing per frame producer locking, but instead amortize the
locking cost over the bulk.
V2: Fix compile errors reported by kbuild test robot <lkp@intel.com>
V4: Isolated ndo, driver changes and callers.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Since we no longer use i as an array index for the data variable,
replace the use of 'j' with 'i' so that we match the general loop
variable name.
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Add documentation for the i40e_get_stats_count, i40e_get_stat_strings
and i40e_get_ethtool_stats explaining that the number and ordering of
statistics must remain constant for a given netdevice.
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
A future patch is going to add a helper function i40e_add_ethtool_stats
that will help lower the amount of boiler plate code in the
i40e_get_ethtool_stats function.
This conversion will take place over many patches, and the helper
function will work by directly updating a reference to the data pointer.
Since this would not work combined with the current method of accessing
data like an array, update all the code that copies stats into the data
buffer to use direct updates to the pointer instead of array accesses.
This will prevent incorrect stat updates for patches in between the
conversion.
Similarly, when copying strings, we used a separate char *p pointer.
Instead, use the data pointer directly as it's already a (u8 *) type
which is the same size.
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
We always prefix these stats with a fixed string, so just fold this
prefix into the stat string definition. This preparatory work will make
it easier to implement a helper function to copy stats and strings into
the supplied buffers in a future patch.
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
