David S. Miller [Tue, 29 Aug 2017 16:42:48 +0000 (09:42 -0700)]
Merge tag 'rxrpc-next-
20170829' of git://git./linux/kernel/git/dhowells/linux-fs
David Howells says:
====================
rxrpc: Miscellany
Here are a number of patches that make some changes/fixes and add a couple
of extensions to AF_RXRPC for kernel services to use. The changes and
fixes are:
(1) Use time64_t rather than u32 outside of protocol or
UAPI-representative structures.
(2) Use the correct time stamp when loading a key from an XDR-encoded
Kerberos 5 key.
(3) Fix IPv6 support.
(4) Fix some places where the error code is being incorrectly made
positive before returning.
(5) Remove some white space.
And the extensions:
(6) Add an end-of-Tx phase notification, thereby allowing kAFS to
transition the state on its own call record at the correct point,
rather than having to do it in advance and risk non-completion of the
call in the wrong state.
(7) Allow a kernel client call to be retried if it fails on a network
error, thereby making it possible for kAFS to iterate over a number of
IP addresses without having to reload the Tx queue and re-encrypt data
each time.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Tue, 29 Aug 2017 16:41:56 +0000 (09:41 -0700)]
Merge branch 'addrlabel-no-rtnl-locking'
Florian Westphal says:
====================
addrlabel: don't use rtnl locking
addrlabel doesn't appear to require rtnl lock as the addrlabel
table uses a spinlock to serialize add/delete operations.
Also, entries are reference counted so it should be safe
to call the rtnl ops without the rtnl mutex.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Florian Westphal [Tue, 29 Aug 2017 11:29:42 +0000 (13:29 +0200)]
addrlabel: add/delete/get can run without rtnl
There appears to be no need to use rtnl, addrlabel entries are refcounted
and add/delete is serialized by the addrlabel table spinlock.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
Florian Westphal [Tue, 29 Aug 2017 11:29:41 +0000 (13:29 +0200)]
selftests: add addrlabel add/delete to rtnetlink.sh
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
Greg Kroah-Hartman [Tue, 29 Aug 2017 07:09:29 +0000 (09:09 +0200)]
staging: irda: update MAINTAINERS
Now that the IRDA code has moved under drivers/staging/irda/, update the
MAINTAINERS file with the new location.
Reported-by: Joe Perches <joe@perches.com>
Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org
Signed-off-by: David S. Miller <davem@davemloft.net>
Sathya Perla [Tue, 29 Aug 2017 06:15:03 +0000 (11:45 +0530)]
bnxt_en: add a dummy definition for bnxt_vf_rep_get_fid()
When bnxt VF-reps are not compiled in (CONFIG_BNXT_SRIOV is off)
bnxt_tc.c needs a dummy definition of the routine bnxt_vf_rep_get_fid().
Reported-by: kbuild test robot <fengguang.wu@intel.com>
Fixes: 2ae7408fedfe ("bnxt_en: bnxt: add TC flower filter offload support")
Signed-off-by: Sathya Perla <sathya.perla@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David Howells [Tue, 29 Aug 2017 09:19:01 +0000 (10:19 +0100)]
rxrpc: Allow failed client calls to be retried
Allow a client call that failed on network error to be retried, provided
that the Tx queue still holds DATA packet 1. This allows an operation to
be submitted to another server or another address for the same server
without having to repackage and re-encrypt the data so far processed.
Two new functions are provided:
(1) rxrpc_kernel_check_call() - This is used to find out the completion
state of a call to guess whether it can be retried and whether it
should be retried.
(2) rxrpc_kernel_retry_call() - Disconnect the call from its current
connection, reset the state and submit it as a new client call to a
new address. The new address need not match the previous address.
A call may be retried even if all the data hasn't been loaded into it yet;
a partially constructed will be retained at the same point it was at when
an error condition was detected. msg_data_left() can be used to find out
how much data was packaged before the error occurred.
Signed-off-by: David Howells <dhowells@redhat.com>
David Howells [Tue, 29 Aug 2017 09:18:56 +0000 (10:18 +0100)]
rxrpc: Add notification of end-of-Tx phase
Add a callback to rxrpc_kernel_send_data() so that a kernel service can get
a notification that the AF_RXRPC call has transitioned out the Tx phase and
is now waiting for a reply or a final ACK.
This is called from AF_RXRPC with the call state lock held so the
notification is guaranteed to come before any reply is passed back.
Further, modify the AFS filesystem to make use of this so that we don't have
to change the afs_call state before sending the last bit of data.
Signed-off-by: David Howells <dhowells@redhat.com>
David Howells [Tue, 29 Aug 2017 09:18:50 +0000 (10:18 +0100)]
rxrpc: Remove some excess whitespace
Remove indentation from some blank lines.
Signed-off-by: David Howells <dhowells@redhat.com>
David Howells [Tue, 29 Aug 2017 09:18:43 +0000 (10:18 +0100)]
rxrpc: Don't negate call->error before returning it
call->error is stored as 0 or a negative error code. Don't negate this
value (ie. make it positive) before returning it from a kernel function
(though it should still be negated before passing to userspace through a
control message).
Signed-off-by: David Howells <dhowells@redhat.com>
David Howells [Tue, 29 Aug 2017 09:18:37 +0000 (10:18 +0100)]
rxrpc: Fix IPv6 support
Fix IPv6 support in AF_RXRPC in the following ways:
(1) When extracting the address from a received IPv4 packet, if the local
transport socket is open for IPv6 then fill out the sockaddr_rxrpc
struct for an IPv4-mapped-to-IPv6 AF_INET6 transport address instead
of an AF_INET one.
(2) When sending CHALLENGE or RESPONSE packets, the transport length needs
to be set from the sockaddr_rxrpc::transport_len field rather than
sizeof() on the IPv4 transport address.
(3) When processing an IPv4 ICMP packet received by an IPv6 socket, set up
the address correctly before searching for the affected peer.
Signed-off-by: David Howells <dhowells@redhat.com>
David Howells [Tue, 29 Aug 2017 09:15:40 +0000 (10:15 +0100)]
rxrpc: Use correct timestamp from Kerberos 5 ticket
When an XDR-encoded Kerberos 5 ticket is added as an rxrpc-type key, the
expiry time should be drawn from the k5 part of the token union (which was
what was filled in), rather than the kad part of the union.
Reported-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David Howells <dhowells@redhat.com>
Baolin Wang [Tue, 29 Aug 2017 09:15:40 +0000 (10:15 +0100)]
net: rxrpc: Replace time_t type with time64_t type
Since the 'expiry' variable of 'struct key_preparsed_payload' has been
changed to 'time64_t' type, which is year 2038 safe on 32bits system.
In net/rxrpc subsystem, we need convert 'u32' type to 'time64_t' type
when copying ticket expires time to 'prep->expiry', then this patch
introduces two helper functions to help convert 'u32' to 'time64_t'
type.
This patch also uses ktime_get_real_seconds() to get current time instead
of get_seconds() which is not year 2038 safe on 32bits system.
Signed-off-by: Baolin Wang <baolin.wang@linaro.org>
Signed-off-by: David Howells <dhowells@redhat.com>
Vitaly Kuznetsov [Mon, 28 Aug 2017 13:16:05 +0000 (15:16 +0200)]
hinic: don't build the module by default
We probably don't want to enable code supporting particular hardware by
default e.g. when someone does 'make defconfig'. Other ethernet modules
don't do it.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Mon, 28 Aug 2017 23:57:10 +0000 (16:57 -0700)]
Merge branch 'bnxt_en-next'
Michael Chan says:
====================
bnxt_en: Updates.
Various changes including updated firmware interface, improved TX ring
allocation scheme, improved out-of-memory logic in NAPI loop, reduced
default rings on multi-port devices, new PCI IDs. Of particular note,
CPU affinity hints from Vasundhara Volam.
TC Flower eswitch support from Sathya Perla.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Sathya Perla [Mon, 28 Aug 2017 17:40:35 +0000 (13:40 -0400)]
bnxt_en: add code to query TC flower offload stats
This patch adds code to implement TC_CLSFLOWER_STATS TC-cmd and the
required FW code to query the stats from the HW.
Signed-off-by: Sathya Perla <sathya.perla@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Sathya Perla [Mon, 28 Aug 2017 17:40:34 +0000 (13:40 -0400)]
bnxt_en: add TC flower offload flow_alloc/free FW cmds
This patch adds the hwrm_cfa_flow_alloc/free() routines
that are needed to issue the FW cmds needed for TC flower offload.
Signed-off-by: Sathya Perla <sathya.perla@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Sathya Perla [Mon, 28 Aug 2017 17:40:33 +0000 (13:40 -0400)]
bnxt_en: bnxt: add TC flower filter offload support
This patch adds support for offloading TC based flow
rules and actions for the 'flower' classifier in the bnxt_en driver.
It includes logic to parse flow rules and actions received from the
TC subsystem, store them and issue the corresponding
hwrm_cfa_flow_alloc/free FW cmds. L2/IPv4/IPv6 flows and drop,
redir, vlan push/pop actions are supported in this patch.
In this patch the hwrm_cfa_flow_xxx routines are just stubs.
The code for these routines is introduced in the next patch for easier
review. Also, the code to query the TC/flower action stats will
be introduced in a subsequent patch.
Signed-off-by: Sathya Perla <sathya.perla@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Sathya Perla [Mon, 28 Aug 2017 17:40:32 +0000 (13:40 -0400)]
bnxt_en: fix clearing devlink ptr from bnxt struct
The routine bnxt_link_bp_to_dl() is used to set the devlink ptr
in bnxt struct (bp) and also to set the bnxt back ptr in
the devlink struct. If devlink_register() fails, bp->dl must
be cleared which is not happening currently. This patch fixes
bnxt_link_bp_to_dl() to clear bp->dl by passing a NULL dl ptr.
Fixes: 4ab0c6a8ffd7 ("bnxt_en: add support to enable VF-representors")
Signed-off-by: Sathya Perla <sathya.perla@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Michael Chan [Mon, 28 Aug 2017 17:40:31 +0000 (13:40 -0400)]
bnxt_en: Reduce default rings on multi-port cards.
Reduce default rings from 8 to 4 on multi-port cards to reduce memory
usage.
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Michael Chan [Mon, 28 Aug 2017 17:40:30 +0000 (13:40 -0400)]
bnxt_en: Improve -ENOMEM logic in NAPI poll loop.
If we cannot allocate RX buffers in the NAPI poll loop when processing
an RX event, the current code does not count that event towards the NAPI
budget. This can cause us to potentially loop forever in NAPI if we
consistently cannot allocate new buffers. Improve it by counting
-ENOMEM event as 1 towards the NAPI budget.
Cc: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Reported-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Scott Branden [Mon, 28 Aug 2017 17:40:29 +0000 (13:40 -0400)]
bnxt: initialize board_info values with proper enums
initialize board_info values with proper enums for defensive programming
purposes. This will avoid any errors of the enums being declared not
lining up with the board_info array.
Signed-off-by: Scott Branden <scott.branden@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ray Jui [Mon, 28 Aug 2017 17:40:28 +0000 (13:40 -0400)]
bnxt: Add PCIe device IDs for bcm58802/bcm58808
Add PCIe device ID for bcm58802 and bcm58808. Also add chip number
update to declare bcm588xx as chip class phase 4 and later
Signed-off-by: Ray Jui <ray.jui@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Vasundhara Volam [Mon, 28 Aug 2017 17:40:27 +0000 (13:40 -0400)]
bnxt_en: assign CPU affinity hints to bnxt_en IRQs
This patch provides hints to irqbalance to map bnxt_en device IRQs
to specific CPU cores. cpumask_local_spread() is used, which first
maps IRQs to near NUMA cores; when those cores are exhausted, IRQs
are mapped to far NUMA cores.
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Michael Chan [Mon, 28 Aug 2017 17:40:26 +0000 (13:40 -0400)]
bnxt_en: Improve tx ring reservation logic.
When the number of TX rings is changed (e.g. ethtool -L, enabling XDP TX
rings, etc), the current code tries to reserve the new number of TX rings
before closing and re-opening the NIC. If we are unable to reserve the
new TX rings, we abort the operation and keep the current TX rings.
The problem is that the firmware will disable the current TX rings even
when it cannot reserve the new set of TX rings. We fix it as follows:
1. Instead of reserving the new set of TX rings, just ask the firmware
to check if the new set of TX rings is available. There is a flag in
the firmware message to do that. If not available, abort and the
current TX rings will not be disabled.
2. Do the actual TX ring reservation in the path that opens the NIC.
We keep the number of TX rings currently successfully reserved. If the
number of TX rings is different than the reserved TX rings, we call
firmware and reserve again.
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Michael Chan [Mon, 28 Aug 2017 17:40:25 +0000 (13:40 -0400)]
bnxt_en: Update firmware interface spec. to 1.8.1.4.
Flow APIs are added in this firmware interface.
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Mon, 28 Aug 2017 23:49:49 +0000 (16:49 -0700)]
Merge branch 'NCSI-vlan-filtering'
Samuel Mendoza-Jonas says:
====================
NCSI VLAN Filtering Support
This series (mainly patch 2) adds VLAN filtering to the NCSI implementation.
A fair amount of code already exists in the NCSI stack for VLAN filtering but
none of it is actually hooked up. This goes the final mile and fixes a few
bugs in the existing code found along the way (patch 1).
Patch 3 adds the appropriate flag and callbacks to the ftgmac100 driver to
enable filtering as it's a large consumer of NCSI (and what I've been
testing on).
v3: - Add comment describing change to ncsi_find_filter()
- Catch NULL in clear_one_vid() from ncsi_get_filter()
- Simplify state changes when kicking updated channel
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Samuel Mendoza-Jonas [Mon, 28 Aug 2017 06:18:43 +0000 (16:18 +1000)]
ftgmac100: Support NCSI VLAN filtering when available
Register the ndo_vlan_rx_{add,kill}_vid callbacks and set the
NETIF_F_HW_VLAN_CTAG_FILTER if NCSI is available.
This allows the VLAN core to notify the NCSI driver when changes occur
so that the remote NCSI channel can be properly configured to filter on
the set VLAN tags.
Signed-off-by: Samuel Mendoza-Jonas <sam@mendozajonas.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Samuel Mendoza-Jonas [Mon, 28 Aug 2017 06:18:42 +0000 (16:18 +1000)]
net/ncsi: Configure VLAN tag filter
Make use of the ndo_vlan_rx_{add,kill}_vid callbacks to have the NCSI
stack process new VLAN tags and configure the channel VLAN filter
appropriately.
Several VLAN tags can be set and a "Set VLAN Filter" packet must be sent
for each one, meaning the ncsi_dev_state_config_svf state must be
repeated. An internal list of VLAN tags is maintained, and compared
against the current channel's ncsi_channel_filter in order to keep track
within the state. VLAN filters are removed in a similar manner, with the
introduction of the ncsi_dev_state_config_clear_vids state. The maximum
number of VLAN tag filters is determined by the "Get Capabilities"
response from the channel.
Signed-off-by: Samuel Mendoza-Jonas <sam@mendozajonas.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Samuel Mendoza-Jonas [Mon, 28 Aug 2017 06:18:41 +0000 (16:18 +1000)]
net/ncsi: Fix several packet definitions
Signed-off-by: Samuel Mendoza-Jonas <sam@mendozajonas.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Mon, 28 Aug 2017 23:46:25 +0000 (16:46 -0700)]
Merge branch '40GbE' of git://git./linux/kernel/git/jkirsher/next-queue
Jeff Kirsher says:
====================
40GbE Intel Wired LAN Driver Updates 2017-08-27
This series contains updates to i40e and i40evf only.
Sudheer updates code comments and state variable so that adminq_subtask
will have accutate information whenever it gets scheduled.
Mariusz stores information about FEC modes, to be used to printing link
states information, so that we do not need to call admin queue when
reporting link status. Adds VF support for controlling VLAN tag
stripping via ethtool.
Jake provides the majority of changes in this series, starting with
increasing the size of the prefix buffer so that it can hold enough
characters for every possible input, which prevents snprintf truncation.
Fixed other string truncation errors/warnings produced by GCC 7.x.
Removed an unnecessary workaround for resetting XPS. Fixed an issue
where there is a mismatched affinity mask value, so initialize the value
to cpu_possible_mask and invert the logic for checking incorrect CPU vs
IRQ affinity so that the exceptional case is handled at the check.
Removed ULTRA latency mode due to several issues found and will be
looking at better solution for small packet workloads.
Akeem fixes an issue where the incorrect flag was being used to set
promiscuous mode for unicast, which was enabling promiscuous mode only
for multicast instead of unicast.
Carolyn fixes an issue where an error return value is set, but this
value can be overwritten before we actually do exit the function. So
remove the error code assignment and add code comments for better
understanding on why we do not need to set and return the error.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Aviad Krawczyk [Sun, 27 Aug 2017 17:35:30 +0000 (01:35 +0800)]
net-next/hinic: fix comparison of a uint16_t type with -1
Remove the search for index of constant buffer size
Signed-off-by: Aviad Krawczyk <aviad.krawczyk@huawei.com>
Signed-off-by: Zhao Chen <zhaochen6@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Aviad Krawczyk [Sun, 27 Aug 2017 17:20:26 +0000 (01:20 +0800)]
net-next/hinic: Fix MTU limitation
Fix the hw MTU limitation by setting max_mtu
Signed-off-by: Aviad Krawczyk <aviad.krawczyk@huawei.com>
Signed-off-by: Zhao Chen <zhaochen6@huawei.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Mon, 28 Aug 2017 23:42:57 +0000 (16:42 -0700)]
Merge branch 'irda-move-to-staging'
Greg Kroah-Hartman says:
====================
irda: move it to drivers/staging so we can delete it
The IRDA code has long been obsolete and broken. So, to keep people
from trying to use it, and to prevent people from having to maintain it,
let's move it to drivers/staging/ so that we can delete it entirely from
the kernel in a few releases.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Greg Kroah-Hartman [Sun, 27 Aug 2017 15:03:34 +0000 (17:03 +0200)]
staging: irda: add a TODO file.
The irda code will be deleted in a future kernel release, so no need to
have anyone do any new work on it.
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Greg Kroah-Hartman [Sun, 27 Aug 2017 15:03:33 +0000 (17:03 +0200)]
irda: move include/net/irda into staging subdirectory
And finally, move the irda include files into
drivers/staging/irda/include/net/irda. Yes, it's a long path, but it
makes it easy for us to just add a Makefile directory path addition and
all of the net and drivers code "just works".
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Greg Kroah-Hartman [Sun, 27 Aug 2017 15:03:32 +0000 (17:03 +0200)]
irda: move drivers/net/irda to drivers/staging/irda/drivers
Move the irda drivers from drivers/net/irda/ to
drivers/staging/irda/drivers as they will be deleted in a future kernel
release.
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Greg Kroah-Hartman [Sun, 27 Aug 2017 15:03:31 +0000 (17:03 +0200)]
irda: move net/irda/ to drivers/staging/irda/net/
It's time to get rid of IRDA. It's long been broken, and no one seems
to use it anymore. So move it to staging and after a while, we can
delete it from there.
To start, move the network irda core from net/irda to
drivers/staging/irda/net/
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Mon, 28 Aug 2017 23:41:01 +0000 (16:41 -0700)]
Merge branch 'dpaa_eth-rss'
Madalin Bucur says:
====================
Add RSS to DPAA 1.x Ethernet driver
This patch set introduces Receive Side Scaling for the DPAA Ethernet
driver. Documentation is updated with details related to the new
feature and limitations that apply.
Added also a small fix.
v2: removed a C++ style comment
v3: move struct fman to header file to avoid exporting a function
v4: addressed compilation issues introduced in v3
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Madalin Bucur [Sun, 27 Aug 2017 13:13:43 +0000 (16:13 +0300)]
dpaa_eth: check allocation result
Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Madalin Bucur [Sun, 27 Aug 2017 13:13:42 +0000 (16:13 +0300)]
Documentation: networking: add RSS information
Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Madalin Bucur [Sun, 27 Aug 2017 13:13:41 +0000 (16:13 +0300)]
dpaa_eth: add NETIF_F_RXHASH
Set the skb hash when then FMan Keygen hash result is available.
Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Madalin Bucur [Sun, 27 Aug 2017 13:13:40 +0000 (16:13 +0300)]
dpaa_eth: enable Rx hashing control
Allow ethtool control of the Rx flow hashing. By default RSS is
enabled, this allows to turn it off by bypassing the FMan Keygen
block and sending all traffic on the default Rx frame queue.
Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Madalin Bucur [Sun, 27 Aug 2017 13:13:39 +0000 (16:13 +0300)]
dpaa_eth: use multiple Rx frame queues
Add a block of 128 Rx frame queues per port. The FMan hardware will
send traffic on one of these queues based on the FMan port Parse
Classify Distribute setup. The hash computed by the FMan Keygen
block will select the Rx FQ.
Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Iordache Florinel-R70177 [Sun, 27 Aug 2017 13:13:38 +0000 (16:13 +0300)]
fsl/fman: enable FMan Keygen
Add support for the FMan Keygen with a hardcoded scheme to spread
incoming traffic on a FQ range based on source and destination IPs
and ports.
Signed-off-by: Iordache Florinel <florinel.iordache@nxp.com>
Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Madalin Bucur [Sun, 27 Aug 2017 13:13:37 +0000 (16:13 +0300)]
fsl/fman: move struct fman to header file
Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Himanshu Jha [Sat, 26 Aug 2017 20:17:47 +0000 (01:47 +0530)]
net: ethernet: broadcom: Remove null check before kfree
Kfree on NULL pointer is a no-op and therefore checking is redundant.
Signed-off-by: Himanshu Jha <himanshujha199640@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Gao Feng [Sat, 26 Aug 2017 14:58:58 +0000 (22:58 +0800)]
sched: sfq: drop packets after root qdisc lock is released
The commit
520ac30f4551 ("net_sched: drop packets after root qdisc lock
is released) made a big change of tc for performance. But there are
some points which are not changed in SFQ enqueue operation.
1. Fail to find the SFQ hash slot;
2. When the queue is full;
Now use qdisc_drop instead free skb directly.
Signed-off-by: Gao Feng <gfree.wind@vip.163.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Mon, 28 Aug 2017 22:41:15 +0000 (15:41 -0700)]
Merge branch 'mlxsw-dpipe-fixes'
Jiri Pirko says:
====================
mlxsw: spectrum: Fix couple of dpipe ipv4 host table bugs
Arkadi Sharshevsky (1):
mlxsw: spectrum_dpipe: Fix host table dump
Jiri Pirko (1):
mlxsw: spectrum: compile-in dpipe support only if devlink is enabled
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Arkadi Sharshevsky [Sat, 26 Aug 2017 06:35:39 +0000 (08:35 +0200)]
mlxsw: spectrum_dpipe: Fix host table dump
During the neighbor traversal the neighbors from different families
should be ignored.
Fixes: c58035a74aba ("mlxsw: spectrum_dpipe: Add support for IPv4 host table dump")
Signed-off-by: Arkadi Sharshevsky <arkadis@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Pirko [Sat, 26 Aug 2017 06:35:38 +0000 (08:35 +0200)]
mlxsw: spectrum: compile-in dpipe support only if devlink is enabled
Makes no sense to have dpipe compiled in when devlink is not enabled,
because the devlink dpipe registation is noop function. So don't compile
it in. This also fixes missing extern structs errors.
Reported-by: kbuild test robot <fengguang.wu@intel.com>
Fixes: a86f030915f2 ("mlxsw: spectrum_dpipe: Add support for IPv4 host table dump")
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Dexuan Cui [Sat, 26 Aug 2017 04:52:43 +0000 (04:52 +0000)]
hv_sock: implements Hyper-V transport for Virtual Sockets (AF_VSOCK)
Hyper-V Sockets (hv_sock) supplies a byte-stream based communication
mechanism between the host and the guest. It uses VMBus ringbuffer as the
transportation layer.
With hv_sock, applications between the host (Windows 10, Windows Server
2016 or newer) and the guest can talk with each other using the traditional
socket APIs.
More info about Hyper-V Sockets is available here:
"Make your own integration services":
https://docs.microsoft.com/en-us/virtualization/hyper-v-on-windows/user-guide/make-integration-service
The patch implements the necessary support in Linux guest by introducing a new
vsock transport for AF_VSOCK.
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: Andy King <acking@vmware.com>
Cc: Dmitry Torokhov <dtor@vmware.com>
Cc: George Zhang <georgezhang@vmware.com>
Cc: Jorgen Hansen <jhansen@vmware.com>
Cc: Reilly Grant <grantr@vmware.com>
Cc: Asias He <asias@redhat.com>
Cc: Stefan Hajnoczi <stefanha@redhat.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Cathy Avery <cavery@redhat.com>
Cc: Rolf Neugebauer <rolf.neugebauer@docker.com>
Cc: Marcelo Cerri <marcelo.cerri@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jakub Kicinski [Fri, 25 Aug 2017 21:39:57 +0000 (14:39 -0700)]
selftests/bpf: check the instruction dumps are populated
Add a basic test for checking whether kernel is populating
the jited and xlated BPF images. It was used to confirm
the behaviour change from commit
d777b2ddbecf ("bpf: don't
zero out the info struct in bpf_obj_get_info_by_fd()"),
which made bpf_obj_get_info_by_fd() usable for retrieving
the image dumps.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Dan Carpenter [Fri, 25 Aug 2017 20:27:14 +0000 (23:27 +0300)]
bpf: fix oops on allocation failure
"err" is set to zero if bpf_map_area_alloc() fails so it means we return
ERR_PTR(0) which is NULL. The caller, find_and_alloc_map(), is not
expecting NULL returns and will oops.
Fixes: 174a79ff9515 ("bpf: sockmap with sk redirect support")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David Ahern [Mon, 28 Aug 2017 22:14:20 +0000 (15:14 -0700)]
net: Add comment that early_demux can change via sysctl
Twice patches trying to constify inet{6}_protocol have been reverted:
39294c3df2a8 ("Revert "ipv6: constify inet6_protocol structures"") to
revert
3a3a4e3054137 and then
03157937fe0b5 ("Revert "ipv4: make
net_protocol const"") to revert
aa8db499ea67.
Add a comment that the structures can not be const because the
early_demux field can change based on a sysctl.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Willem de Bruijn [Fri, 25 Aug 2017 17:10:43 +0000 (13:10 -0400)]
xen-netback: update ubuf_info initialization to anonymous union
The xen driver initializes struct ubuf_info fields using designated
initializers. I recently moved these fields inside a nested anonymous
struct inside an anonymous union. I had missed this use case.
This breaks compilation of xen-netback with older compilers.
>From kbuild bot with gcc-4.4.7:
drivers/net//xen-netback/interface.c: In function
'xenvif_init_queue':
>> drivers/net//xen-netback/interface.c:554: error: unknown field 'ctx' specified in initializer
>> drivers/net//xen-netback/interface.c:554: warning: missing braces around initializer
drivers/net//xen-netback/interface.c:554: warning: (near initialization for '(anonymous).<anonymous>')
>> drivers/net//xen-netback/interface.c:554: warning: initialization makes integer from pointer without a cast
>> drivers/net//xen-netback/interface.c:555: error: unknown field 'desc' specified in initializer
Add double braces around the designated initializers to match their
nested position in the struct. After this, compilation succeeds again.
Fixes: 4ab6c99d99bb ("sock: MSG_ZEROCOPY notification coalescing")
Reported-by: kbuild bot <lpk@intel.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Wei Liu <wei.liu2@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Mon, 28 Aug 2017 22:04:52 +0000 (15:04 -0700)]
Merge branch 'gre-add-collect_md-mode-for-ERSPAN-tunnel'
William Tu says:
====================
gre: add collect_md mode for ERSPAN tunnel
This patch series provide collect_md mode for ERSPAN tunnel. The fist patch
refactors the existing gre_fb_xmit function by exacting the route cache
portion into a new function called prepare_fb_xmit. The second patch
introduces the collect_md mode for ERSPAN tunnel, by calling the
prepare_fb_xmit function and adding ERSPAN specific logic. The final patch
adds the test case using bpf_skb_{set,get}_tunnel_{key,opt}.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
William Tu [Fri, 25 Aug 2017 16:21:29 +0000 (09:21 -0700)]
samples/bpf: extend test_tunnel_bpf.sh with ERSPAN
Extend existing tests for vxlan, gre, geneve, ipip to
include ERSPAN tunnel.
Signed-off-by: William Tu <u9012063@gmail.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
William Tu [Fri, 25 Aug 2017 16:21:28 +0000 (09:21 -0700)]
gre: add collect_md mode to ERSPAN tunnel
Similar to gre, vxlan, geneve, ipip tunnels, allow ERSPAN tunnels to
operate in 'collect metadata' mode. bpf_skb_[gs]et_tunnel_key() helpers
can make use of it right away. OVS can use it as well in the future.
Signed-off-by: William Tu <u9012063@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
William Tu [Fri, 25 Aug 2017 16:21:27 +0000 (09:21 -0700)]
gre: refactor the gre_fb_xmit
The patch refactors the gre_fb_xmit function, by creating
prepare_fb_xmit function for later ERSPAN collect_md mode patch.
Signed-off-by: William Tu <u9012063@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David Ahern [Mon, 28 Aug 2017 20:23:09 +0000 (13:23 -0700)]
Revert "ipv4: make net_protocol const"
This reverts commit
aa8db499ea67cff1f5f049033810ffede2fe5ae4.
Early demux structs can not be made const. Doing so results in:
[ 84.967355] BUG: unable to handle kernel paging request at
ffffffff81684b10
[ 84.969272] IP: proc_configure_early_demux+0x1e/0x3d
[ 84.970544] PGD
1a0a067
[ 84.970546] P4D
1a0a067
[ 84.971212] PUD
1a0b063
[ 84.971733] PMD
80000000016001e1
[ 84.972669] Oops: 0003 [#1] SMP
[ 84.973065] Modules linked in: ip6table_filter ip6_tables veth vrf
[ 84.973833] CPU: 0 PID: 955 Comm: sysctl Not tainted 4.13.0-rc6+ #22
[ 84.974612] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.7.5-20140531_083030-gandalf 04/01/2014
[ 84.975855] task:
ffff88003854ce00 task.stack:
ffffc900005a4000
[ 84.976580] RIP: 0010:proc_configure_early_demux+0x1e/0x3d
[ 84.977253] RSP: 0018:
ffffc900005a7dd0 EFLAGS:
00010246
[ 84.977891] RAX:
ffffffff81684b10 RBX:
0000000000000001 RCX:
0000000000000000
[ 84.978759] RDX:
0000000000000000 RSI:
0000000000000006 RDI:
0000000000000000
[ 84.979628] RBP:
ffffc900005a7dd0 R08:
0000000000000000 R09:
0000000000000000
[ 84.980501] R10:
0000000000000001 R11:
0000000000000008 R12:
0000000000000001
[ 84.981373] R13:
ffffffffffffffea R14:
ffffffff81a9b4c0 R15:
0000000000000002
[ 84.982249] FS:
00007feb237b7700(0000) GS:
ffff88003fc00000(0000) knlGS:
0000000000000000
[ 84.983231] CS: 0010 DS: 0000 ES: 0000 CR0:
0000000080050033
[ 84.983941] CR2:
ffffffff81684b10 CR3:
0000000038492000 CR4:
00000000000406f0
[ 84.984817] Call Trace:
[ 84.985133] proc_tcp_early_demux+0x29/0x30
I think this is the second time such a patch has been reverted.
Cc: Bhumika Goyal <bhumirks@gmail.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Bhumika Goyal [Fri, 25 Aug 2017 14:21:45 +0000 (19:51 +0530)]
RDS: make rhashtable_params const
Make this const as it is either used during a copy operation or passed
to a const argument of the function rhltable_init
Signed-off-by: Bhumika Goyal <bhumirks@gmail.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Bhumika Goyal [Fri, 25 Aug 2017 14:21:44 +0000 (19:51 +0530)]
ipv4: make net_protocol const
Make these const as they are only passed to a const argument of the
function inet_add_protocol.
Signed-off-by: Bhumika Goyal <bhumirks@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Bhumika Goyal [Fri, 25 Aug 2017 14:21:42 +0000 (19:51 +0530)]
bridge: make ebt_table const
Make this const as it is only passed to a const argument of the function
ebt_register_table.
Signed-off-by: Bhumika Goyal <bhumirks@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Mon, 28 Aug 2017 18:13:22 +0000 (11:13 -0700)]
Merge branch 'sockmap-uapi-updates-and-fixes'
John Fastabend says:
====================
sockmap UAPI updates and fixes
This series updates sockmap UAPI, adds additional test cases and
provides a couple fixes.
First the UAPI changes. The original API added two sockmap specific
API artifacts (a) a new map_flags field with a sockmap specific update
command and (b) a new sockmap specific attach field in the attach data
structure. After this series instead of attaching programs with a
single command now two commands are used to attach programs to maps
individually. This allows us to add new programs easily in the future
and avoids any specific sockmap data structure additions. The
map_flags field is also removed and instead we allow socks to be
added to multiple maps that may or may not have programs attached.
This allows users to decide if a sock should run a SK_SKB program type
on receive based on the map it is attached to. This is a nice
improvement. See patches for specific details.
More test cases were added to test above changes and also stress test
the interface.
Finally two fixes/improvements were made. First a missing rcu
section was added. Second now sockmap can build without KCM being
used to trigger 'y' on CONFIG_STREAM_PARSER by selecting a new
BPF config option.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
John Fastabend [Mon, 28 Aug 2017 14:12:41 +0000 (07:12 -0700)]
bpf: test_maps add sockmap stress test
Sockmap is a bit different than normal stress tests that can run
in parallel as is. We need to reuse the same socket pool and map
pool to get good stress test cases.
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
John Fastabend [Mon, 28 Aug 2017 14:12:21 +0000 (07:12 -0700)]
bpf: sockmap requires STREAM_PARSER add Kconfig entry
SOCKMAP uses strparser code (compiled with Kconfig option
CONFIG_STREAM_PARSER) to run the parser BPF program. Without this
config option set sockmap wont be compiled. However, at the moment
the only way to pull in the strparser code is to enable KCM.
To resolve this create a BPF specific config option to pull
only the strparser piece in that sockmap needs. This also
allows folks who want to use BPF/syscall/maps but don't need
sockmap to easily opt out.
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
John Fastabend [Mon, 28 Aug 2017 14:12:01 +0000 (07:12 -0700)]
bpf: sockmap indicate sock events to listeners
After userspace pushes sockets into a sockmap it may not be receiving
data (assuming stream_{parser|verdict} programs are attached). But, it
may still want to manage the socks. A common pattern is to poll/select
for a POLLRDHUP event so we can close the sock.
This patch adds the logic to wake up these listeners.
Also add TCP_SYN_SENT to the list of events to handle. We don't want
to break the connection just because we happen to be in this state.
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
John Fastabend [Mon, 28 Aug 2017 14:11:43 +0000 (07:11 -0700)]
bpf: harden sockmap program attach to ensure correct map type
When attaching a program to sockmap we need to check map type
is correct.
Fixes: 174a79ff9515 ("bpf: sockmap with sk redirect support")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
John Fastabend [Mon, 28 Aug 2017 14:11:24 +0000 (07:11 -0700)]
bpf: more SK_SKB selftests
Tests packet read/writes and additional skb fields.
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
John Fastabend [Mon, 28 Aug 2017 14:11:05 +0000 (07:11 -0700)]
bpf: additional sockmap self tests
Add some more sockmap tests to cover,
- forwarding to NULL entries
- more than two maps to test list ops
- forwarding to different map
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
John Fastabend [Mon, 28 Aug 2017 14:10:45 +0000 (07:10 -0700)]
bpf: sockmap add missing rcu_read_(un)lock in smap_data_ready
References to psock must be done inside RCU critical section.
Fixes: 174a79ff9515 ("bpf: sockmap with sk redirect support")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
John Fastabend [Mon, 28 Aug 2017 14:10:25 +0000 (07:10 -0700)]
bpf: sockmap, remove STRPARSER map_flags and add multi-map support
The addition of map_flags BPF_SOCKMAP_STRPARSER flags was to handle a
specific use case where we want to have BPF parse program disabled on
an entry in a sockmap.
However, Alexei found the API a bit cumbersome and I agreed. Lets
remove the STRPARSER flag and support the use case by allowing socks
to be in multiple maps. This allows users to create two maps one with
programs attached and one without. When socks are added to maps they
now inherit any programs attached to the map. This is a nice
generalization and IMO improves the API.
The API rules are less ambiguous and do not need a flag:
- When a sock is added to a sockmap we have two cases,
i. The sock map does not have any attached programs so
we can add sock to map without inheriting bpf programs.
The sock may exist in 0 or more other maps.
ii. The sock map has an attached BPF program. To avoid duplicate
bpf programs we only add the sock entry if it does not have
an existing strparser/verdict attached, returning -EBUSY if
a program is already attached. Otherwise attach the program
and inherit strparser/verdict programs from the sock map.
This allows for socks to be in a multiple maps for redirects and
inherit a BPF program from a single map.
Also this patch simplifies the logic around BPF_{EXIST|NOEXIST|ANY}
flags. In the original patch I tried to be extra clever and only
update map entries when necessary. Now I've decided the complexity
is not worth it. If users constantly update an entry with the same
sock for no reason (i.e. update an entry without actually changing
any parameters on map or sock) we still do an alloc/release. Using
this and allowing multiple entries of a sock to exist in a map the
logic becomes much simpler.
Note: Now that multiple maps are supported the "maps" pointer called
when a socket is closed becomes a list of maps to remove the sock from.
To keep the map up to date when a sock is added to the sockmap we must
add the map/elem in the list. Likewise when it is removed we must
remove it from the list. This results in searching the per psock list
on delete operation. On TCP_CLOSE events we walk the list and remove
the psock from all map/entry locations. I don't see any perf
implications in this because at most I have a psock in two maps. If
a psock were to be in many maps its possibly this might be noticeable
on delete but I can't think of a reason to dup a psock in many maps.
The sk_callback_lock is used to protect read/writes to the list. This
was convenient because in all locations we were taking the lock
anyways just after working on the list. Also the lock is per sock so
in normal cases we shouldn't see any contention.
Suggested-by: Alexei Starovoitov <ast@kernel.org>
Fixes: 174a79ff9515 ("bpf: sockmap with sk redirect support")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
John Fastabend [Mon, 28 Aug 2017 14:10:04 +0000 (07:10 -0700)]
bpf: convert sockmap field attach_bpf_fd2 to type
In the initial sockmap API we provided strparser and verdict programs
using a single attach command by extending the attach API with a the
attach_bpf_fd2 field.
However, if we add other programs in the future we will be adding a
field for every new possible type, attach_bpf_fd(3,4,..). This
seems a bit clumsy for an API. So lets push the programs using two
new type fields.
BPF_SK_SKB_STREAM_PARSER
BPF_SK_SKB_STREAM_VERDICT
This has the advantage of having a readable name and can easily be
extended in the future.
Updates to samples and sockmap included here also generalize tests
slightly to support upcoming patch for multiple map support.
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Fixes: 174a79ff9515 ("bpf: sockmap with sk redirect support")
Suggested-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
David Wu [Tue, 22 Aug 2017 09:24:25 +0000 (17:24 +0800)]
ARM: dts: rk3228-evb: Fix the compiling error
This patch solves the following error:
arch/arm/boot/dts/rk3228-evb.dtb: ERROR (phandle_references): Reference to non-existent node or label "phy0"
Fixess
db40f15b53e4 ("ARM: dts: rk3228-evb: Enable the integrated PHY for gmac")
Signed-off-by: David Wu <david.wu@rock-chips.com>
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jacob Keller [Fri, 14 Jul 2017 13:10:13 +0000 (09:10 -0400)]
i40e/i40evf: avoid dynamic ITR updates when polling or low packet rate
The dynamic ITR algorithm depends on a calculation of usecs which
assumes that the interrupts have been firing constantly at the interrupt
throttle rate. This is not guaranteed because we could have a low packet
rate, or have been polling in software.
We'll estimate whether this is the case by using jiffies to determine if
we've been too long. If the time difference of jiffies is larger we are
guaranteed to have an incorrect calculation. If the time difference of
jiffies is smaller we might have been polling some but the difference
shouldn't affect the calculation too much.
This ensures that we don't get stuck in BULK latency during certain rare
situations where we receive bursts of packets that force us into NAPI
polling.
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>
Jacob Keller [Fri, 14 Jul 2017 13:10:12 +0000 (09:10 -0400)]
i40e/i40evf: remove ULTRA latency mode
Since commit
c56625d59726 ("i40e/i40evf: change dynamic interrupt
thresholds") a new higher latency ITR setting called I40E_ULTRA_LATENCY
was added with a cryptic comment about how it was meant for adjusting Rx
more aggressively when streaming small packets.
This mode was attempting to calculate packets per second and then kick
in when we have a huge number of small packets.
Unfortunately, the ULTRA setting was kicking in for workloads it wasn't
intended for including single-thread UDP_STREAM workloads.
This wasn't caught for a variety of reasons. First, the ip_defrag
routines were improved somewhat which makes the UDP_STREAM test still
reasonable at 10GbE, even when dropped down to 8k interrupts a second.
Additionally, some other obvious workloads appear to work fine, such
as TCP_STREAM.
The number 40k doesn't make sense for a number of reasons. First, we
absolutely can do more than 40k packets per second. Second, we calculate
the value inline in an integer, which sometimes can overflow resulting
in using incorrect values.
If we fix this overflow it makes it even more likely that we'll enter
ULTRA mode which is the opposite of what we want.
The ULTRA mode was added originally as a way to reduce CPU utilization
during a small packet workload where we weren't keeping up anyways. It
should never have been kicking in during these other workloads.
Given the issues outlined above, let's remove the ULTRA latency mode. If
necessary, a better solution to the CPU utilization issue for small
packet workloads will be added 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>
Jacob Keller [Fri, 14 Jul 2017 13:10:11 +0000 (09:10 -0400)]
i40e: invert logic for checking incorrect cpu vs irq affinity
In commit
96db776a3682 ("i40e/vf: fix interrupt affinity bug")
we added some code to force exit of polling in case we did
not have the correct CPU. This is important since it was possible for
the IRQ affinity to be changed while the CPU is pegged at 100%. This can
result in the polling routine being stuck on the wrong CPU until
traffic finally stops.
Unfortunately, the implementation, "if the CPU is correct, exit as
normal, otherwise, fall-through to the end-polling exit" is incredibly
confusing to reason about. In this case, the normal flow looks like the
exception, while the exception actually occurs far away from the if
statement and comment.
We recently discovered and fixed a bug in this code because we were
incorrectly initializing the affinity mask.
Re-write the code so that the exceptional case is handled at the check,
rather than having the logic be spread through the regular exit flow.
This does end up with minor code duplication, but the resulting code is
much easier to reason about.
The new logic is identical, but inverted. If we are running on a CPU not
in our affinity mask, we'll exit polling. However, the code flow is much
easier to understand.
Note that we don't actually have to check for MSI-X, because in the MSI
case we'll only have one q_vector, but its default affinity mask should
be correct as it includes all CPUs when it's initialized. Further, we
could at some point add code to setup the notifier for the non-MSI-X
case and enable this workaround for that case too, if desired, though
there isn't much gain since its unlikely to be the common case.
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>
Jacob Keller [Fri, 14 Jul 2017 13:10:10 +0000 (09:10 -0400)]
i40e: initialize our affinity_mask based on cpu_possible_mask
On older kernels a call to irq_set_affinity_hint does not guarantee that
the IRQ affinity will be set. If nothing else on the system sets the IRQ
affinity this can result in a bug in the i40e_napi_poll() routine where
we notice that our interrupt fired on the "wrong" CPU according to our
internal affinity_mask variable.
This results in a bug where we continuously tell NAPI to stop polling to
move the interrupt to a new CPU, but the CPU never changes because our
affinity mask does not match the actual mask setup for the IRQ.
The root problem is a mismatched affinity mask value. So lets initialize
the value to cpu_possible_mask instead. This ensures that prior to the
first time we get an IRQ affinity notification we'll have the mask set
to include every possible CPU.
We use cpu_possible_mask instead of cpu_online_mask since the former is
almost certainly never going to change, while the later might change
after we've made a copy.
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>
Jacob Keller [Fri, 14 Jul 2017 13:10:09 +0000 (09:10 -0400)]
i40e: move enabling icr0 into i40e_update_enable_itr
If we don't have MSI-X enabled, we handle interrupts on all icr0. This
is a special case, so let's move the conditional into
i40e_update_enable_itr() in order to make i40e_napi_poll easier to
read about.
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>
Jacob Keller [Fri, 14 Jul 2017 13:10:08 +0000 (09:10 -0400)]
i40e: remove workaround for resetting XPS
Since commit
3ffa037d7f78 ("i40e: Set XPS bit mask to zero in DCB mode")
we've tried to reset the XPS settings by building a custom
empty CPU mask.
This workaround is not necessary because we're not really removing the
XPS setting, but simply setting it so that no CPU is valid.
Second, we shorten the code further by using zalloc_cpumask_var instead
of a separate call to bitmap_zero().
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>
Carolyn Wyborny [Fri, 14 Jul 2017 13:10:07 +0000 (09:10 -0400)]
i40e: Fix for unused value issue found by static analysis
This patch fixes an issue where an error return value is
set, but without an immediate exit, the value can be overwritten
by the following code execution. The condition at this point
is not fatal, so remove the error assignment and comment the
intent for future code maintainers
Signed-off-by: Carolyn Wyborny <carolyn.wyborny@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Mariusz Stachura [Wed, 12 Jul 2017 09:46:14 +0000 (05:46 -0400)]
i40e: 25G FEC status improvements
This patch improves the system log message. The log message will
be expanded to include the FEC mode the FW requested before link
was established.
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>
Mariusz Stachura [Tue, 18 Jul 2017 05:09:45 +0000 (22:09 -0700)]
i40e/i40evf: support for VF VLAN tag stripping control
This patch gives VF capability to control VLAN tag stripping via
ethtool. As rx-vlan-offload was fixed before, now the VF is able to
change it using "ethtool --offload <IF> rxvlan on/off" settings.
Signed-off-by: Mariusz Stachura <mariusz.stachura@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Jacob Keller [Wed, 12 Jul 2017 09:46:12 +0000 (05:46 -0400)]
i40e: force VMDQ device name truncation
In new versions of GCC since 7.x a new warning exists which warns when
a string is truncated before all of the format can be completed.
When we setup VMDQ netdev names we are copying a pre-existing interface
name which could be up to 15 characters in length. Since we also add
4 bytes, v, the literal %, the d and a \0 null, we would overrun the
available size unless snprintf truncated for us.
The snprintf call will of course truncate on the end, so lets instead
modify the code to force truncation of the copied netdev name by
4 characters, to create enough space for the 4 bytes we're adding.
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>
Jacob Keller [Wed, 12 Jul 2017 09:46:11 +0000 (05:46 -0400)]
i40evf: fix possible snprintf truncation of q_vector->name
The q_vector names are based on the interface name with a driver prefix,
the type of q_vector setup, and the queue number. We previously set the
size of this variable to IFNAMSIZ + 9, which is incorrect, because we
actually include a minimum of 14 characters extra beyond the interface
name size.
New versions of GCC since 7 include a new warning that detects this
possible truncation and complains. We can fix this by increasing the
size in case our interface name is too large to avoid truncation. We
don't need to go beyond 14 because the compiler is smart enough to
realize our values can never exceed size of 1. We do go up to 15 here
because possible future changes may increase the number of queues beyond
one digit.
While we are here, also change some variables to be unsigned (since they
are never negative) and stop using an extra unnecessary %s format
specifier.
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>
Akeem G Abodunrin [Wed, 12 Jul 2017 09:46:10 +0000 (05:46 -0400)]
i40e: Use correct flag to enable egress traffic for unicast promisc
Albeit, we usually set true promiscuous mode for both multicast and
unicast at the same time - however, it is possible to set it
individually, so using allmulti flag which is only for allmulticast might
caused unwanted behavior in mirroring egress traffic promiscuous for
unicast in VF.
Signed-off-by: Akeem G Abodunrin <akeem.g.abodunrin@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Jacob Keller [Wed, 12 Jul 2017 09:46:09 +0000 (05:46 -0400)]
i40e: prevent snprintf format specifier truncation
Increase the size of the prefix buffer so that it can hold enough
characters for every possible input. Although 20 is enough for all
expected inputs, it is possible for the values to be larger than
expected, resulting in a possibly truncated string. Additionally, lets
use sizeof(prefix) in order to ensure we use the correct size if we need
to change the array length in the future.
New versions of GCC starting at 7 now include warnings to prevent
truncation unless you handle the return code. At most 27 bytes can be
written here, so lets just increase the buffer size even if for all
expected hw->bus.* values we only needed 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>
Mariusz Stachura [Wed, 12 Jul 2017 09:46:08 +0000 (05:46 -0400)]
i40e: Store the requested FEC information
Store information about FEC modes, that were requested. It will be used
in printing link status information function and this way there is no
need to call admin queue there.
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>
Sudheer Mogilappagari [Sun, 27 Aug 2017 22:07:47 +0000 (15:07 -0700)]
i40e: Update state variable for adminq subtask
During NVM update, state machine gets into unrecoverable state because
i40e_clean_adminq_subtask can get scheduled after the admin queue
command but before other state variables are updated. This causes
incorrect input to i40e_nvmupd_check_wait_event and state transitions
don't happen.
This fix updates the state variables so that adminq_subtask will have
accurate information whenever it gets scheduled.
Signed-off-by: Sudheer Mogilappagari <sudheer.mogilappagari@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Antoine Ténart [Fri, 25 Aug 2017 13:24:46 +0000 (15:24 +0200)]
net: mvpp2: fix the packet size configuration for 10G
The MVPP22_XLG_CTRL1_FRAMESIZELIMIT define is used as an offset, but is
defined as BIT(0). Updated its name to contains "OFFS" as in offset and
fix its value using the offset value, 0.
Reported-by: Stefan Chulski <stefanc@marvell.com>
Signed-off-by: Antoine Tenart <antoine.tenart@free-electrons.com>
Fixes: 76eb1b1de5b6 ("net: mvpp2: set maximum packet size for 10G ports")
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Sat, 26 Aug 2017 02:39:58 +0000 (19:39 -0700)]
Merge branch '40GbE' of git://git./linux/kernel/git/jkirsher/next-queue
Jeff Kirsher says:
====================
40GbE Intel Wired LAN Driver Updates 2017-08-25
This series contains updates to i40e and i40evf only.
Mitch adjusts the max packet size to account for two VLAN tags.
Sudheer provides a fix to ensure that the watchdog timer is scheduled
immediately after admin queue operations are scheduled in i40evf_down().
Fixes an issue by adding locking around the admin queue command and
update of state variables so that adminq_subtask will have the accurate
information whenever it gets scheduled.
Anjali fixes a bug where the PF flag setup should happen before the VMDq
RSS queue count is initialized for VMDq VSI to get the right number of
queues for RSS in the case of x722 devices. Fixed a problem with the
hardware ATR eviction feature where the NVM setting was incorrect.
Jake separates the flags into two types, hw_features and flags. The
hw_features flags contain a set of features which are enabled at init
time and will not contain feature flags that can be toggled. Everything
else will remain in the flags variable, and can be modified anytime
during run time. We should not be directly copying a cpumask_t, since
it is bitmap and might not be copied correctly, so use cpumask_copy()
instead.
Stefan Assmann makes vf _offload_flags more "generic" by renaming it to
vf_cap_flags, which allows other capabilities besides offloading to be
added.
Alan makes it such that if adaptive-rx/tx is enabled, the user cannot
make any manual adjustments to interrupt moderation. Also makes it so
that if ITR is disabled by adaptive-rx/tx is then enabled, ITR will be
re-enabled.
v2: Dropped patches #1 & #8 from the original patch series submission,
while Jesse and Jake re-work their patches based on feedback from
David Miller. Also removed the duplicate patch 3 that was
accidentally sent out twice in the previous submission.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Sat, 26 Aug 2017 02:24:59 +0000 (19:24 -0700)]
Merge branch 'nfp-SR-IOV-ndos-support'
Jakub Kicinski says:
====================
nfp: SR-IOV ndos support
This set adds basic SR-IOV including setting/getting VF MAC addresses,
VLANs, link state and spoofcheck settings. It is wired up for both
vNICs and representors (note: ip link will not report VF settings on
VF/PF representors because they are not linked to the PF PCI device).
Pablo and team add the basic implementation, Simon and Dirk follow
up with the representor plumbing.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Simon Horman [Fri, 25 Aug 2017 04:31:50 +0000 (21:31 -0700)]
nfp: add basic SR-IOV ndo functions to representors
Add basic ndo_set/get_vf to support SR-IOV on all types
of port representors.
Signed-off-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pablo Cascón [Fri, 25 Aug 2017 04:31:49 +0000 (21:31 -0700)]
nfp: add basic SR-IOV ndo functions
Add basic ndo_set/get_vf to support SR-IOV.
VF to egress phy static mapping by now.
Use vfcfg ABI version 2 to write the info to the FW and collect
the return value from the mailbox.
Signed-off-by: Pablo Cascón <pablo.cascon@netronome.com>
Signed-off-by: Jimmy Kizito <jimmy.kizito@netronome.com>
Signed-off-by: Rami Tomer <rami.tomer@netronome.com>
Signed-off-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Fri, 25 Aug 2017 13:27:05 +0000 (06:27 -0700)]
tcp: fix hang in tcp_sendpage_locked()
syszkaller got a hang in tcp stack, related to a bug in
tcp_sendpage_locked()
root@syzkaller:~# cat /proc/3059/stack
[<
ffffffff83de926c>] __lock_sock+0x1dc/0x2f0
[<
ffffffff83de9473>] lock_sock_nested+0xf3/0x110
[<
ffffffff8408ce01>] tcp_sendmsg+0x21/0x50
[<
ffffffff84163b6f>] inet_sendmsg+0x11f/0x5e0
[<
ffffffff83dd8eea>] sock_sendmsg+0xca/0x110
[<
ffffffff83dd9547>] kernel_sendmsg+0x47/0x60
[<
ffffffff83de35dc>] sock_no_sendpage+0x1cc/0x280
[<
ffffffff8408916b>] tcp_sendpage_locked+0x10b/0x160
[<
ffffffff84089203>] tcp_sendpage+0x43/0x60
[<
ffffffff841641da>] inet_sendpage+0x1aa/0x660
[<
ffffffff83dd4fcd>] kernel_sendpage+0x8d/0xe0
[<
ffffffff83dd50ac>] sock_sendpage+0x8c/0xc0
[<
ffffffff81b63300>] pipe_to_sendpage+0x290/0x3b0
[<
ffffffff81b67243>] __splice_from_pipe+0x343/0x750
[<
ffffffff81b6a459>] splice_from_pipe+0x1e9/0x330
[<
ffffffff81b6a5e0>] generic_splice_sendpage+0x40/0x50
[<
ffffffff81b6b1d7>] SyS_splice+0x7b7/0x1610
[<
ffffffff84d77a01>] entry_SYSCALL_64_fastpath+0x1f/0xbe
Fixes: 306b13eb3cf9 ("proto_ops: Add locked held versions of sendmsg and sendpage")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Tom Herbert <tom@quantonium.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Sat, 26 Aug 2017 00:19:11 +0000 (17:19 -0700)]
Merge branch 'net_sched-clean-up-tc-classes-and-u32-filter'
Cong Wang says:
====================
net_sched: clean up tc classes and u32 filter
Patch 1 and patch 2 prepare for patch 3. Major changes
are in patch 3 and patch 4, details are there too.
v2: Add patch 1 and 2, group all into a patchset
Fix a coding style issue in patch 4
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
WANG Cong [Thu, 24 Aug 2017 23:51:30 +0000 (16:51 -0700)]
net_sched: kill u32_node pointer in Qdisc
It is ugly to hide a u32-filter-specific pointer inside Qdisc,
this breaks the TC layers:
1. Qdisc is a generic representation, should not have any specific
data of any type
2. Qdisc layer is above filter layer, should only save filters in
the list of struct tcf_proto.
This pointer is used as the head of the chain of u32 hash tables,
that is struct tc_u_hnode, because u32 filter is very special,
it allows to create multiple hash tables within one qdisc and
across multiple u32 filters.
Instead of using this ugly pointer, we can just save it in a global
hash table key'ed by (dev ifindex, qdisc handle), therefore we can
still treat it as a per qdisc basis data structure conceptually.
Of course, because of network namespaces, this key is not unique
at all, but it is fine as we already have a pointer to Qdisc in
struct tc_u_common, we can just compare the pointers when collision.
And this only affects slow paths, has no impact to fast path,
thanks to the pointer ->tp_c.
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
WANG Cong [Thu, 24 Aug 2017 23:51:29 +0000 (16:51 -0700)]
net_sched: remove tc class reference counting
For TC classes, their ->get() and ->put() are always paired, and the
reference counting is completely useless, because:
1) For class modification and dumping paths, we already hold RTNL lock,
so all of these ->get(),->change(),->put() are atomic.
2) For filter bindiing/unbinding, we use other reference counter than
this one, and they should have RTNL lock too.
3) For ->qlen_notify(), it is special because it is called on ->enqueue()
path, but we already hold qdisc tree lock there, and we hold this
tree lock when graft or delete the class too, so it should not be gone
or changed until we release the tree lock.
Therefore, this patch removes ->get() and ->put(), but:
1) Adds a new ->find() to find the pointer to a class by classid, no
refcnt.
2) Move the original class destroy upon the last refcnt into ->delete(),
right after releasing tree lock. This is fine because the class is
already removed from hash when holding the lock.
For those who also use ->put() as ->unbind(), just rename them to reflect
this change.
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
WANG Cong [Thu, 24 Aug 2017 23:51:28 +0000 (16:51 -0700)]
net_sched: introduce tclass_del_notify()
Like for TC actions, ->delete() is a special case,
we have to prepare and fill the notification before delete
otherwise would get use-after-free after we remove the
reference count.
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>