Arnd Bergmann [Tue, 24 Nov 2015 11:34:49 +0000 (12:34 +0100)]
net: dsa: include gpio consumer header file
After the introduction of the switch gpio reset API, I'm getting
build errors in configurations that disable CONFIG_GPIOLIB:
net/dsa/dsa.c:783:16: error: implicit declaration of function 'gpio_to_desc' [-Werror=implicit-function-declaration]
The reason is that linux/gpio/consumer.h is not automatically
included without gpiolib support. This adds an explicit #include
statement to make it compile in all configurations. The reset
functionality will not work without gpiolib, which is what you
get when disabling the feature.
As far as I can tell, gpiolib is supported on all architectures
on which you can have DSA at the moment.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Fixes: cc30c16344fc ("net: dsa: Add support for a switch reset gpio")
Acked-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Tue, 24 Nov 2015 15:08:08 +0000 (10:08 -0500)]
Merge branch 'master' of git://git./linux/kernel/git/jkirsher/next-queue
Jeff Kirsher says:
====================
Intel Wired LAN Driver Updates 2015-11-23
This series contains updates to ixgbe, ixgbevf, fm10k, i40e and i40evf.
Jacob fixes an issue where VF could attempt to read queues it does not own,
so prevent this we check queue 0 before we continue.
Matthew fixes the MTU for jumbo frames for fm10k.
Julia Lawall cleans up a unneeded NULL test in ixgbe.
Mark cleans up a redundant header inclusion. Adds KR mode support for
CS4227 chip. Cleaned up diagnostic code, which is no longer needed, for
the CS4227 chip.
Jean Sacren fixes kernel documentation for ixgbe.
Alex Duyck fixes an fm10k and ixgbe issue in which the polling routine would
increase the budget for receive to at least 1 per queue if multiple queues were
present. This would result in receive packets being processed when the budget
was 0 which is meant to indicate that no receive can be handled. Also fixes
an ixgbevf performance issue where netperf test will starve for memory in the
time form one transmit interrupt to the next, so limit lowest interrupt rate
for adaptive interrupt moderation to 12K. Fixed up ixgbe and ixgbevf to
use napi_schedule_irqoff() where the drivers were run from hard interrupt
context or with interrupts already disabled in netpoll.
Jesse fixes a compiler warning about an unused variable for i40evf.
John Greene fixes an issue with ixgbevf, where if the VF driver is loaded
while the corresponding PH interface is down, the driver assigns a random
MAC address, can be overwritten with the value of hw->mac.perm_addr which
is 0 at that point. So avoid this case by initializing hw->mac.perm_addr
to the randomly generated address and do not set it unless we receive an
ACK from ixgbe.
Rasmus Villemoes cleans up some confusing code in i40e debugfs code.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Julia Lawall [Sat, 21 Nov 2015 17:39:17 +0000 (18:39 +0100)]
VSOCK: constify vmci_transport_notify_ops structures
The vmci_transport_notify_ops structures are never modified, so declare
them as const.
Done with the help of Coccinelle.
Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
Julia Lawall [Sat, 21 Nov 2015 17:28:05 +0000 (18:28 +0100)]
net: atm: constify in_cache_ops and eg_cache_ops structures
The in_cache_ops and eg_cache_ops structures are never modified, so declare
them as const.
Done with the help of Coccinelle.
Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Mon, 23 Nov 2015 20:06:40 +0000 (15:06 -0500)]
Merge branch 'ipmr-cleanups'
Nikolay Aleksandrov says:
====================
net: ipmr: cleanups and minor improvements
Since I'll have to work with ipmr, I decided to clean it up and do some
minor improvements. Functionally there're almost no changes except the
SLAB_PANIC removal. Most of the patches just re-design some functions to
be clearer and more concise and try to remove the ifdef web that was
inside. There's more information in each commit. This is the first set,
the end goal is to introduce complete netlink support and control over
the mfc and vif devices.
I've tried to test all of the setsockopt/getsockopt options, and also
made builds with various ipmr kconfig options turned on and off.
v2: change patch 7 to keep SLAB_PANIC and just drop the unnecessary null
check
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Nikolay Aleksandrov [Sat, 21 Nov 2015 14:57:32 +0000 (15:57 +0100)]
net: ipmr: factor out common vif init code
Factor out common vif init code used in both tunnel and pimreg
initialization and create ipmr_init_vif_indev() function.
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Nikolay Aleksandrov [Sat, 21 Nov 2015 14:57:31 +0000 (15:57 +0100)]
net: ipmr: rearrange and cleanup setsockopt
Take rtnl in the beginning unconditionally as most options already need
it (one exception - MRT_DONE, see the comment inside), make the
lock/unlock places central and move out the switch() local variables.
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Nikolay Aleksandrov [Sat, 21 Nov 2015 14:57:30 +0000 (15:57 +0100)]
net: ipmr: drop ip_mr_init() mrt_cachep null check as we'll panic if it fails
It's not necessary to check for null as SLAB_PANIC is used and we'll
panic if the alloc fails, so just drop it.
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Nikolay Aleksandrov [Sat, 21 Nov 2015 14:57:29 +0000 (15:57 +0100)]
net: ipmr: drop an instance of CONFIG_IP_MROUTE_MULTIPLE_TABLES
Trivial replace of ifdef with IS_BUILTIN().
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Nikolay Aleksandrov [Sat, 21 Nov 2015 14:57:28 +0000 (15:57 +0100)]
net: ipmr: make ip_mroute_getsockopt more understandable
Use a switch to determine if optname is correct and set val accordingly.
This produces a much more straight-forward and readable code.
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Nikolay Aleksandrov [Sat, 21 Nov 2015 14:57:27 +0000 (15:57 +0100)]
net: ipmr: fix code and comment style
Trivial code and comment style fixes, also removed some extra newlines,
spaces and tabs.
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Nikolay Aleksandrov [Sat, 21 Nov 2015 14:57:26 +0000 (15:57 +0100)]
net: ipmr: remove some pimsm ifdefs and simplify
Add the helper pimsm_enabled() which replaces the old CONFIG_IP_PIMSM
define and is used to check if any version of PIM-SM has been enabled.
Use a single if defined(CONFIG_IP_PIMSM_V1) || defined(CONFIG_IP_PIMSM_V2)
for the pim-sm shared code. This is okay w.r.t IGMPMSG_WHOLEPKT because
only a VIFF_REGISTER device can send such packet, and it can't be
created if pimsm_enabled() is false.
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Nikolay Aleksandrov [Sat, 21 Nov 2015 14:57:25 +0000 (15:57 +0100)]
net: ipmr: always define mroute_reg_vif_num
Before mroute_reg_vif_num was defined only if any of the CONFIG_PIMSM_
options were set, but that's not really necessary as the size of the
struct is the same in both cases (checked with pahole, both cases size
is 3256 bytes) and we can remove some unnecessary ifdefs to simplify the
code.
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Nikolay Aleksandrov [Sat, 21 Nov 2015 14:57:24 +0000 (15:57 +0100)]
net: ipmr: move the tbl id check in ipmr_new_table
Move the table id check in ipmr_new_table and make it return error
pointer. We need this change for the upcoming netlink table manipulation
support in order to avoid code duplication and a race condition.
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Rasmus Villemoes [Sat, 17 Oct 2015 20:58:19 +0000 (22:58 +0200)]
intel: i40e: fix confused code
This code is pretty confused. The variable name 'bytes_not_copied'
clearly indicates that the programmer knew the semantics of
copy_{to,from}_user, but then the return value is checked for being
negative and used as a -Exxx return value.
I'm not sure this is the proper fix, but at least we get rid of the
dead code which pretended to check for access faults.
Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Acked-by: Shannon Nelson <shannon.nelson@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Emil Tantilov [Mon, 12 Oct 2015 17:56:00 +0000 (10:56 -0700)]
ixgbevf: fix spoofed packets with random MAC
If ixgbevf is loaded while the corresponding PF interface is down
and the driver assigns a random MAC address, that address can be
overwritten with the value of hw->mac.perm_addr, which would be 0 at
that point.
To avoid this case we init hw->mac.perm_addr to the randomly generated
address and do not set it unless we receive ACK from ixgbe.
Reported-by: John Greene <jogreene@redhat.com>
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Tested-by: Krishneil Singh <Krishneil.k.singh@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Emil Tantilov [Mon, 12 Oct 2015 17:55:51 +0000 (10:55 -0700)]
ixgbevf: use ether_addr_copy instead of memcpy
replace some instances of memcpy for setting up the mac address with
ether_addr_copy()
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Tested-by: Darin Miller <darin.j.miller@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Jesse Brandeburg [Sun, 4 Oct 2015 08:09:49 +0000 (01:09 -0700)]
i40evf: fix compiler warning of unused variable
Compiler complained of an unused variable, which the driver was just
using to store the result of a rd32 which is used to clear a register
unconditionally. Just drop the unused variable and re-use one.
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Mark Rustad [Fri, 2 Oct 2015 16:23:53 +0000 (09:23 -0700)]
ixgbe: Remove CS4227 diagnostic code
Testing has now shown that the diagnostic code used with the CS4227
is no longer needed, so remove it.
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com>
Tested-by: Darin Miller <darin.j.miller@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Alexander Duyck [Tue, 29 Sep 2015 22:19:43 +0000 (15:19 -0700)]
ixgbe/ixgbevf: use napi_schedule_irqoff()
The ixgbe_intr and ixgbe/ixgbevf_msix_clean_rings functions run from hard
interrupt context or with interrupts already disabled in netpoll.
They can use napi_schedule_irqoff() instead of napi_schedule()
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Tested-by: Darin Miller <darin.j.miller@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Alexander Duyck [Tue, 29 Sep 2015 20:11:15 +0000 (13:11 -0700)]
ixgbevf: Limit lowest interrupt rate for adaptive interrupt moderation to 12K
This patch is the ixgbevf version of commit
8ac34f10a5ea4 "ixgbe: Limit
lowest interrupt rate for adaptive interrupt moderation to 12K"
The same logic applies here as well as the same results since a netperf
test will starve for memory in the time from one Tx interrupt to the next.
As a result the ixgbevf driver underperformed when compared to vhost_net.
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Tested-by: Darin Miller <darin.j.miller@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Mark Rustad [Mon, 28 Sep 2015 21:37:47 +0000 (14:37 -0700)]
ixgbe: Add KR mode support for CS4227 chip
KR auto-neg mode is what we will be using going forward. The SW
interface for this mode is different that what was used for iXFI.
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Alexander Duyck [Tue, 22 Sep 2015 21:35:41 +0000 (14:35 -0700)]
ixgbe: Fix handling of NAPI budget when multiple queues are enabled per vector
This patch corrects an issue in which the polling routine would increase
the budget for Rx to at least 1 per queue if multiple queues were present.
This would result in Rx packets being processed when the budget was 0 which
is meant to indicate that no Rx can be handled.
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Tested-by: Darin Miller <darin.j.miller@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Alexander Duyck [Tue, 22 Sep 2015 21:35:35 +0000 (14:35 -0700)]
fm10k: Fix handling of NAPI budget when multiple queues are enabled per vector
This patch corrects an issue in which the polling routine would increase
the budget for Rx to at least 1 per queue if multiple queues were present.
This would result in Rx packets being processed when the budget was 0 which
is meant to indicate that no Rx can be handled.
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Tested-by: Krishneil Singh <Krishneil.k.singh@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Jean Sacren [Sat, 19 Sep 2015 11:08:44 +0000 (05:08 -0600)]
ixgbe: fix multiple kernel-doc errors
The commit
dfaf891dd3e1 ("ixgbe: Refactor the RSS configuration code")
introduced a few kernel-doc errors:
1) The function name is missing;
2) The format is wrong;
3) The short description is redundant.
Fix all the above for the correct execution of the kernel doc.
Signed-off-by: Jean Sacren <sakiwit@gmail.com>
Tested-by: Darin Miller <darin.j.miller@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Mark Rustad [Fri, 18 Sep 2015 17:08:00 +0000 (10:08 -0700)]
ixgbe: Delete redundant include file
Delete a redundant include of net/vxlan.h.
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com>
Tested-by: Darin Miller <darin.j.miller@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Julia Lawall [Sun, 13 Sep 2015 12:15:13 +0000 (14:15 +0200)]
ixgbe: drop null test before destroy functions
Remove unneeded NULL test.
The semantic patch that makes this change is as follows:
(http://coccinelle.lip6.fr/)
// <smpl>
@@ expression x; @@
-if (x != NULL)
\(kmem_cache_destroy\|mempool_destroy\|dma_pool_destroy\)(x);
// </smpl>
Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr>
Tested-by: Darin Miller <darin.j.miller@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Jacob Keller [Tue, 25 Aug 2015 20:49:11 +0000 (13:49 -0700)]
fm10k: Correct MTU for jumbo frames
Based on hardware testing, the host interface supports up to 15368 bytes
as the maximum frame size. To determine the correct MTU, we subtract 8
for the internal switch tag, 14 for the L2 header, and 4 for the
appended FCS header, resulting in 15342 bytes of payload for our maximum
MTU on jumbo frames.
Signed-off-by: Matthew Vick <matthew.vick@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Acked-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Krishneil Singh <krishneil.k.singh@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Jacob Keller [Tue, 25 Aug 2015 00:27:24 +0000 (17:27 -0700)]
fm10k: do not assume VF always has 1 queue
It is possible that the PF has not yet assigned resources to the VF.
Although rare, this could result in the VF attempting to read queues it
does not own and result in FUM or THI faults in the PF. To prevent this,
check queue 0 before we continue in init_hw_vf.
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Krishneil Singh <Krishneil.k.singh@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
David S. Miller [Mon, 23 Nov 2015 17:36:09 +0000 (12:36 -0500)]
Merge branch 'rhashtable-test-enhancements'
Phil Sutter says:
====================
improve fault-tolerance of rhashtable runtime-test
The following series aims to improve lib/test_rhashtable in different
situations:
Patch 1 allows the kernel to reschedule so the test does not block too
long on slow systems.
Patch 2 fixes behaviour under pressure, retrying inserts in non-permanent
error case (-EBUSY).
Patch 3 auto-adjusts the upper table size limit according to the number
of threads (in concurrency test). In fact, the current default is
already too small.
Patch 4 makes it possible to retry inserts even in supposedly permanent
error case (-ENOMEM) to expose rhashtable's remaining problem of
-ENOMEM being not as permanent as it is expected to be.
Changes since v1:
- Introduce insert_retry() which is then used in single-threaded test as
well.
- Do not retry inserts by default if -ENOMEM was returned.
- Rename the retry counter to be a bit more verbose about what it
contains.
- Add patch 4 as a debugging aid.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Phil Sutter [Fri, 20 Nov 2015 17:17:20 +0000 (18:17 +0100)]
rhashtable-test: allow to retry even if -ENOMEM was returned
This is rather a hack to expose the current issue with rhashtable to
under high pressure sometimes return -ENOMEM even though system memory
is not exhausted and a consecutive insert may succeed.
Signed-off-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>
Phil Sutter [Fri, 20 Nov 2015 17:17:19 +0000 (18:17 +0100)]
rhashtable-test: calculate max_entries value by default
A maximum table size of 64k entries is insufficient for the multiple
threads test even in default configuration (10 threads * 50000 objects =
500000 objects in total). Since we know how many objects will be
inserted, calculate the max size unless overridden by parameter.
Note that specifying the exact number of objects upon table init won't
suffice as that value is being rounded down to the next power of two -
anticipate this by rounding up to the next power of two in beforehand.
Signed-off-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>
Phil Sutter [Fri, 20 Nov 2015 17:17:18 +0000 (18:17 +0100)]
rhashtable-test: retry insert operations
After adding cond_resched() calls to threadfunc(), a surprisingly high
rate of insert failures occurred probably due to table resizes getting a
better chance to run in background. To not soften up the remaining
tests, retry inserts until they either succeed or fail permanently.
Also change the non-threaded test to retry insert operations, too.
Suggested-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>
Phil Sutter [Fri, 20 Nov 2015 17:17:17 +0000 (18:17 +0100)]
rhashtable-test: add cond_resched() to thread test
This should fix for soft lockup bugs triggered on slow systems.
Signed-off-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Mon, 23 Nov 2015 16:53:11 +0000 (11:53 -0500)]
Merge branch 'dsa-gpio-reset'
Andrew Lunn says:
====================
DSA: GPIO to reset switches
These two patches add support for using a GPIO to hard reset a switch
during reset.
v2:
Thanks to a clue from Neil Armstrong, i figured out how to convert the
gpio into a gpiod, while keeping the ACTIVE_LOW flag, so simplifiying
the set/reset code.
I have not included the Tested-by: from Phil Reid, since i made a lot
of changes.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Andrew Lunn [Fri, 20 Nov 2015 02:56:24 +0000 (03:56 +0100)]
dsa: mv88e6xxx.c: Hardware reset the chip if available
The device tree binding now allows a gpio to be specified which is
attached to the switch chips reset line. If it is defined, perform
a hardware reset on the switch during setup.
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Andrew Lunn [Fri, 20 Nov 2015 02:56:23 +0000 (03:56 +0100)]
net: dsa: Add support for a switch reset gpio
Some boards have a gpio line tied to the switch reset pin. Allow this
gpio to be retrieved from the device tree, and take the switch out of
reset before performing the probe.
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Saurabh Sengar [Fri, 20 Nov 2015 17:53:58 +0000 (23:23 +0530)]
gianfar: use of_property_read_bool()
use of_property_read_bool() for testing bool property
Signed-off-by: Saurabh Sengar <saurabh.truth@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Yuval Mintz [Sun, 22 Nov 2015 13:01:29 +0000 (15:01 +0200)]
bnx2x: Utilize FW 7.13.1.0.
Commit
46e8a249423ff "bnx2x: Add FW 7.13.1.0" added said .bin FW to
linux-firmware; This patch incorporates the FW in the bnx2x driver.
This introduces 2 fixes/enhancements:
- In some management protocols there are outer-vlan configurations
that can be dynamically changed while device is running. This fixes
some corner cases where such a change did not take effect.
- Prevent VFs from sending MAC control frames; FW would treat a VF
sending such a packet as malicious and block any further communication
done by the VF.
Signed-off-by: Yuval Mintz <Yuval.Mintz@qlogic.com>
Signed-off-by: Ariel Elior <Ariel.Elior@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David Ahern [Thu, 19 Nov 2015 20:24:22 +0000 (12:24 -0800)]
net: IPv6 fib lookup tracepoint
Add tracepoint to show fib6 table lookups and result.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Thu, 19 Nov 2015 20:11:23 +0000 (12:11 -0800)]
net: avoid NULL deref in napi_get_frags()
napi_alloc_skb() can return NULL.
We should not crash should this happen.
Fixes: 93f93a440415 ("net: move skb_mark_napi_id() into core networking stack")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Simon Horman [Fri, 20 Nov 2015 19:29:39 +0000 (11:29 -0800)]
ravb: use clock rate as basis for GTI.TIV
The GTI.TIV may be set to 2GHz^2 / rate, where rate is
that of the clock of the device. Rather than assuming a
rate of 130MHz use the actual rate of the clock.
The motivation for this is to use the correct rate on
the r8a7795/Salvator-X which is advertised as 133MHz but
may differ depending on the extal present on the Salvator-X.
Signed-off-by: Simon Horman <horms+renesas@verge.net.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ondrej Zary [Thu, 19 Nov 2015 19:13:06 +0000 (20:13 +0100)]
dl2k: Implement suspend
Add suspend/resume support to dl2k driver.
This requires RX/TX rings to be reset so split out the required
functionality from alloc_list() into new rio_reset_ring().
Tested on Asus NX1101 (IP1000A) and D-Link DGE-550T (DL-2000).
Signed-off-by: Ondrej Zary <linux@rainbow-software.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ondrej Zary [Thu, 19 Nov 2015 19:13:05 +0000 (20:13 +0100)]
dl2k: Reorder and cleanup initialization
Move HW init and stop into separate functions.
Request IRQ only after the HW has been reset (so interrupts are
disabled and no stale interrupts are pending).
Signed-off-by: Ondrej Zary <linux@rainbow-software.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ondrej Zary [Thu, 19 Nov 2015 19:13:04 +0000 (20:13 +0100)]
dl2k: Handle memory allocation errors in alloc_list
If memory allocation fails in alloc_list(), free the already allocated
memory and return -ENOMEM. In rio_open(), call alloc_list() first and
abort if it fails. Move HW access (set RFDListPtr) out ot alloc_list().
Signed-off-by: Ondrej Zary <linux@rainbow-software.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Fri, 20 Nov 2015 19:06:11 +0000 (14:06 -0500)]
Merge branch 'tipc-cleanups-improvements'
Jon Maloy says:
====================
tipc: some cleanups and improvements
This series mostly contains cleanups and cosmetic code changes.
The only real functional change is in #4 and #5, where we change the
locking structure for nodes and links in order to permit full
concurrency between links working in parallel on different interfaces.
Since the groundwork for this has been done in previous commit series,
this change constitutes only the final, small step to achieve that goal.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Jon Paul Maloy [Thu, 19 Nov 2015 19:30:47 +0000 (14:30 -0500)]
tipc: eliminate remnants of hungarian notation
The number of variables with Hungarian notation (l_ptr, n_ptr etc.)
has been significantly reduced over the last couple of years.
We now root out the last traces of this practice.
There are no functional changes in this commit.
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jon Paul Maloy [Thu, 19 Nov 2015 19:30:46 +0000 (14:30 -0500)]
tipc: narrow down interface towards struct tipc_link
We move the definition of struct tipc_link from link.h to link.c in
order to minimize its exposure to the rest of the code.
When needed, we define new functions to make it possible for external
entities to access and set data in the link.
Apart from the above, there are no functional changes.
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jon Paul Maloy [Thu, 19 Nov 2015 19:30:45 +0000 (14:30 -0500)]
tipc: narrow down exposure of struct tipc_node
In our effort to have less code and include dependencies between
entities such as node, link and bearer, we try to narrow down
the exposed interface towards the node as much as possible.
In this commit, we move the definition of struct tipc_node, along
with many of its associated function declarations, from node.h to
node.c. We also move some function definitions from link.c and
name_distr.c to node.c, since they access fields in struct tipc_node
that should not be externally visible. The moved functions are renamed
according to new location, and made static whenever possible.
There are no functional changes in this commit.
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jon Paul Maloy [Thu, 19 Nov 2015 19:30:44 +0000 (14:30 -0500)]
tipc: convert node lock to rwlock
According to the node FSM a node in state SELF_UP_PEER_UP cannot
change state inside a lock context, except when a TUNNEL_PROTOCOL
(SYNCH or FAILOVER) packet arrives. However, the node's individual
links may still change state.
Since each link now is protected by its own spinlock, we finally have
the conditions in place to convert the node spinlock to an rwlock_t.
If the node state and arriving packet type are rigth, we can let the
link directly receive the packet under protection of its own spinlock
and the node lock in read mode. In all other cases we use the node
lock in write mode. This enables full concurrent execution between
parallel links during steady-state traffic situations, i.e., 99+ %
of the time.
This commit implements this change.
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jon Paul Maloy [Thu, 19 Nov 2015 19:30:43 +0000 (14:30 -0500)]
tipc: introduce per-link spinlock
As a preparation to allow parallel links to work more independently
from each other we introduce a per-link spinlock, to be stored in the
struct nodes's link entry area. Since the node lock still is a regular
spinlock there is no increase in parallellism at this stage.
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jon Paul Maloy [Thu, 19 Nov 2015 19:30:42 +0000 (14:30 -0500)]
tipc: reduce code dependency between binding table and node layer
The file name_distr.c currently contains three functions,
named_cluster_distribute(), tipc_publ_subcscribe() and
tipc_publ_unsubscribe() that all directly access fields in
struct tipc_node. We want to eliminate such dependencies, so
we move those functions to the file node.c and rename them to
tipc_node_broadcast(), tipc_node_subscribe() and tipc_node_unsubscribe()
respectively.
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jon Paul Maloy [Thu, 19 Nov 2015 19:30:41 +0000 (14:30 -0500)]
tipc: small cleanup of function tipc_node_check_state()
The function tipc_node_check_state() contains the core logics
for handling link synchronization and failover. For this reason,
it is important to keep it as comprehensible as possible.
In this commit, we make three small cleanups.
1) If the node is in state SELF_DOWN_PEER_LEAVING and the received
packet confirms that the peer has lost contact, there will be no
further action in this function. To make this clearer, we return
from the function directly after the state change.
2) Since commit
0f8b8e28fb3241f9fd ("tipc: eliminate risk of stalled
link synchronization") only the logically first TUNNEL_PROTO/SYNCH
packet can alter the link state and set the synch point,
independently of arrival order. Hence, there is not any longer any
need to adjust the synch value in case such packets arrive in
disorder. We remove this adjustment.
3) It is the intention that any message arriving on any of the links
may trig a check for and possible termination of a node SYNCH state.
A redundant and unnoticed check for tipc_link_is_synching() obviously
beats this purpose, with the effect that only packets arriving on the
synching link may currently end the synch state. We remove this check.
This change will further shorten the synchronization period between
parallel links.
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jon Paul Maloy [Thu, 19 Nov 2015 19:30:40 +0000 (14:30 -0500)]
tipc: move linearization of buffers to generic code
In commit
5cbb28a4bf65c7e4 ("tipc: linearize arriving NAME_DISTR
and LINK_PROTO buffers") we added linearization of NAME_DISTRIBUTOR,
LINK_PROTOCOL/RESET and LINK_PROTOCOL/ACTIVATE to the function
tipc_udp_recv(). The location of the change was selected in order
to make the commit easily appliable to 'net' and 'stable'.
We now move this linearization to where it should be done, in the
functions tipc_named_rcv() and tipc_link_proto_rcv() respectively.
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Fri, 20 Nov 2015 17:14:53 +0000 (12:14 -0500)]
Merge branch 'bnx2x-stats'
Yuval Mintz says:
====================
bnx2x: Statistics patch series
This series contains 2 small statistics-related patches,
first adding a new SW statistics and the other exposing port stats
for multi-function devices.
Please consider applying this series to `net-next'.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Yuval Mintz [Thu, 19 Nov 2015 15:04:36 +0000 (17:04 +0200)]
bnx2x: Show port statistics in Multi-function
Today, port statistics are being presented when using `ethool -S' only
for single-function devices, but there are some port statistics which are
crucial for analyzing bottle-necks. E.g., HW Rx discards due to lack of
buffer space [when device isn't handling ingress traffic fast enough].
Judging the pros and cons, it was decided that in-order to better support
automatic dump-gathering tools, bnx2x should no longer hide those stats.
This leaves only VFs lacking the port statistics.
Signed-off-by: Yuval Mintz <Yuval.Mintz@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Yuval Mintz [Thu, 19 Nov 2015 15:04:35 +0000 (17:04 +0200)]
bnx2x: Add new SW stat 'tx_exhaustion_events'
Driver already has an internal counter for number of times a given queue
had to be stopped due to Tx ring exhaustion.
This add the counter to the statistics presented by driver, e.g., by using
`ethtool -S'.
Signed-off-by: Yuval Mintz <Yuval.Mintz@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Fri, 20 Nov 2015 16:31:27 +0000 (11:31 -0500)]
Merge branch 'ppp-kill-zombie-state'
Guillaume Nault says:
====================
ppp: Remove PPPOX_ZOMBIE socket state
Several issues have been found lately wrt. the PPPOX_ZOMBIE socket
state. This state is now only set upon reception of a PADT to stop
further transmissions. However this is redundant with the PADT
workqueue mechanism introduced by
287f3a943fef ("pppoe: Use workqueue
to die properly when a PADT is received").
We can thus simplify pppox socket state handling by getting rid of
PPPOX_ZOMBIE entirely.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Guillaume Nault [Thu, 19 Nov 2015 11:53:21 +0000 (12:53 +0100)]
ppp: remove PPPOX_ZOMBIE socket state
PPPOX_ZOMBIE is never set anymore.
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
Guillaume Nault [Thu, 19 Nov 2015 11:52:56 +0000 (12:52 +0100)]
ppp: don't set sk_state to PPPOX_ZOMBIE in pppoe_disc_rcv()
Since
287f3a943fef ("pppoe: Use workqueue to die properly when a PADT
is received"), pppoe_disc_rcv() disconnects the socket by scheduling
pppoe_unbind_sock_work(). This is enough to stop socket transmission
and makes the PPPOX_ZOMBIE state uncessary.
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Fri, 20 Nov 2015 16:06:03 +0000 (11:06 -0500)]
Merge branch 'mlxsw-vlan'
Jiri Pirko says:
====================
mlxsw: small driver update
Couple of VLAN-related patches.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Ido Schimmel [Thu, 19 Nov 2015 11:27:40 +0000 (12:27 +0100)]
mlxsw: spectrum: Add error paths to __mlxsw_sp_port_vlans_add
The operation of adding VLANs on a port via switchdev ops can fail and
we need to be prepared for it. If we do not rollback hardware operations
following a failure, hardware and software will remain in an
inconsistent state.
Solve that by adding suitable error paths to __mlxsw_sp_port_vlans_add.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ido Schimmel [Thu, 19 Nov 2015 11:27:39 +0000 (12:27 +0100)]
mlxsw: spectrum: Unify setting of HW VLAN filters
When adding or deleting VLANs from a bridged port, HW VLAN filters must be
set accordingly. Instead of having the same code in both add and delete
functions, just wrap it in a function and call it with the appropriate
parameters.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Elad Raz <eladr@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ido Schimmel [Thu, 19 Nov 2015 11:27:38 +0000 (12:27 +0100)]
mlxsw: spectrum: Use correct PVID value when removing VLANs
When removing a range of VLANs in which PVID is a member we should use
the correct PVID value instead of some VLAN in the range.
Also, change two print statements to use 'dev' instead of
'mlxsw_sp_port->dev', as it's already used in other print statements in
the function.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Daniel Borkmann [Thu, 19 Nov 2015 10:56:22 +0000 (11:56 +0100)]
bpf: add show_fdinfo handler for maps
Add a handler for show_fdinfo() to be used by the anon-inodes
backend for eBPF maps, and dump the map specification there. Not
only useful for admins, but also it provides a minimal way to
compare specs from ELF vs pinned object.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jon Ringle [Wed, 18 Nov 2015 21:22:21 +0000 (16:22 -0500)]
net: encx24j600: move rev announcement to probe function
When encx24j600 is open and closed many times due to userspace polling the
interface, the log gets noise with this log message.
Moving this to encx24j600_spi_probe function where it belongs.
Signed-off-by: Jon Ringle <jringle@gridpoint.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Wed, 18 Nov 2015 21:17:43 +0000 (16:17 -0500)]
Merge branch 'net-generic-busy-polling'
Eric Dumazet says:
====================
net: extend busy polling support
This patch series extends busy polling range to tunnels devices,
and adds busy polling generic support to all NAPI drivers.
No need to provide ndo_busy_poll() method and extra synchronization
between ndo_busy_poll() and normal napi->poll() method.
This was proven very difficult and bug prone.
mlx5 driver is changed to support busy polling using this new method,
and a second mlx5 patch adds napi_complete_done() support and proper
SNMP accounting.
bnx2x and mlx4 drivers are converted to new infrastructure,
reducing kernel bloat and improving performance.
Latest patch, adding generic support, adds a new requirement :
-free_netdev() and netif_napi_del() must be called from process context.
Since this might not be the case in some drivers, we might have to
either : fix the non conformant drivers (by disabling busy polling on them)
or revert this last patch.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Wed, 18 Nov 2015 14:31:03 +0000 (06:31 -0800)]
net: provide generic busy polling to all NAPI drivers
NAPI drivers no longer need to observe a particular protocol
to benefit from busy polling (CONFIG_NET_RX_BUSY_POLL=y)
napi_hash_add() and napi_hash_del() are automatically called
from core networking stack, respectively from
netif_napi_add() and netif_napi_del()
This patch depends on free_netdev() and netif_napi_del() being
called from process context, which seems to be the norm.
Drivers might still prefer to call napi_hash_del() on their
own, since they might combine all the rcu grace periods into
a single one, knowing their NAPI structures lifetime, while
core networking stack has no idea of a possible combining.
Once this patch proves to not bring serious regressions,
we will cleanup drivers to either remove napi_hash_del()
or provide appropriate rcu grace periods combining.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Wed, 18 Nov 2015 14:31:02 +0000 (06:31 -0800)]
net: napi_hash_del() returns a boolean status
napi_hash_del() will soon be used from both drivers (if they want)
or core networking stack.
Callers are responsibles to ensure an RCU grace period is respected
before freeing napi structure : napi_hash_del() can signal if
this RCU grace period is needed or not.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Wed, 18 Nov 2015 14:31:01 +0000 (06:31 -0800)]
net: move napi_hash[] into read mostly section
We do not often add/delete a napi context.
Moving napi_hash[] into read mostly section avoids potential false sharing.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Wed, 18 Nov 2015 14:31:00 +0000 (06:31 -0800)]
net: add netif_tx_napi_add()
netif_tx_napi_add() is a variant of netif_napi_add()
It should be used by drivers that use a napi structure
to exclusively poll TX.
We do not want to add this kind of napi in napi_hash[] in following
patches, adding generic busy polling to all NAPI drivers.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Wed, 18 Nov 2015 14:30:59 +0000 (06:30 -0800)]
net: move skb_mark_napi_id() into core networking stack
We would like to automatically provide busy polling support
to all NAPI drivers, without them having to implement anything.
skb_mark_napi_id() can be called from napi_gro_receive() and
napi_get_frags().
Few drivers are still calling skb_mark_napi_id() because
they use netif_receive_skb(). They should eventually call
napi_gro_receive() instead. I will leave this to drivers
maintainers.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Wed, 18 Nov 2015 14:30:58 +0000 (06:30 -0800)]
mlx4: remove mlx4_en_low_latency_recv()
Busy polling can now be handled in generic NAPI poll infrastructure.
This removes complexity and fast path overhead :
mlx4 used two spin_lock()/spin_unlock() pair per napi->poll() call
in mlx4_en_cq_lock_napi()/mlx4_en_cq_unlock_napi()
Tested:
Without busy polling :
lpaa23:~# echo 0 >/proc/sys/net/core/busy_read
lpaa24:~# echo 0 >/proc/sys/net/core/busy_read
lpaa23:~# ./netperf -H lpaa24 -t TCP_RR
MIGRATED TCP REQUEST/RESPONSE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to lpaa24.prod.google.com () port 0 AF_INET : first burst 0
Local /Remote
Socket Size Request Resp. Elapsed Trans.
Send Recv Size Size Time Rate
bytes Bytes bytes bytes secs. per sec
16384 87380 1 1 10.00 47330.78
With busy polling :
lpaa23:~# echo 70 >/proc/sys/net/core/busy_read
lpaa24:~# echo 70 >/proc/sys/net/core/busy_read
lpaa23:~# ./netperf -H lpaa24 -t TCP_RR
MIGRATED TCP REQUEST/RESPONSE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to lpaa24.prod.google.com () port 0 AF_INET : first burst 0
Local /Remote
Socket Size Request Resp. Elapsed Trans.
Send Recv Size Size Time Rate
bytes Bytes bytes bytes secs. per sec
16384 87380 1 1 10.00 97643.55
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Wed, 18 Nov 2015 14:30:57 +0000 (06:30 -0800)]
bnx2x: remove bnx2x_low_latency_recv() support
Switch to native NAPI polling, as this reduces overhead and complexity.
Normal path is faster, since one cmpxchg() is not anymore requested,
and busy polling with the NAPI polling has same performance.
Tested:
lpk50:~# cat /proc/sys/net/core/busy_read
70
lpk50:~# nstat >/dev/null;./netperf -H lpk55 -t TCP_RR;nstat
MIGRATED TCP REQUEST/RESPONSE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to lpk55.prod.google.com () port 0 AF_INET : first burst 0
Local /Remote
Socket Size Request Resp. Elapsed Trans.
Send Recv Size Size Time Rate
bytes Bytes bytes bytes secs. per sec
16384 87380 1 1 10.00 40095.07
16384 87380
IpInReceives 401062 0.0
IpInDelivers 401062 0.0
IpOutRequests 401079 0.0
TcpActiveOpens 7 0.0
TcpPassiveOpens 3 0.0
TcpAttemptFails 3 0.0
TcpEstabResets 5 0.0
TcpInSegs 401036 0.0
TcpOutSegs 401052 0.0
TcpOutRsts 38 0.0
UdpInDatagrams 26 0.0
UdpOutDatagrams 27 0.0
Ip6OutNoRoutes 1 0.0
TcpExtDelayedACKs 1 0.0
TcpExtTCPPrequeued 98 0.0
TcpExtTCPDirectCopyFromPrequeue 98 0.0
TcpExtTCPHPHits 4 0.0
TcpExtTCPHPHitsToUser 98 0.0
TcpExtTCPPureAcks 5 0.0
TcpExtTCPHPAcks 101 0.0
TcpExtTCPAbortOnData 6 0.0
TcpExtBusyPollRxPackets 400832 0.0
TcpExtTCPOrigDataSent 400983 0.0
IpExtInOctets
21273867 0.0
IpExtOutOctets
21261254 0.0
IpExtInNoECTPkts 401064 0.0
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Wed, 18 Nov 2015 14:30:56 +0000 (06:30 -0800)]
mlx5: support napi_complete_done()
A NAPI poll handler should return number of RX packets processed,
instead of 0 / budget.
This allows proper busy poll accounting through LINUX_MIB_BUSYPOLLRXPACKETS
SNMP counter.
napi_complete_done() allows /sys/class/net/ethX/gro_flush_timeout
to be used for finer GRO aggregation control.
Tested:
Enabled busy polling, and checked TcpExtBusyPollRxPackets counter is increasing.
echo 70 >/proc/sys/net/core/busy_read
nstat >/dev/null
netperf -H target -t TCP_RR >/dev/null
nstat | grep TcpExtBusyPollRxPackets
TcpExtBusyPollRxPackets 490958 0.0
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Eli Cohen <eli@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Wed, 18 Nov 2015 14:30:55 +0000 (06:30 -0800)]
mlx5: add busy polling support
It is now easy to add busy polling support to a NAPI driver,
with very little impact on normal input path.
This patch serves as a reference implementation.
Note:
A followup patch will add proper napi_complete_done() in mlx5,
so that LINUX_MIB_BUSYPOLLRXPACKETS snmp counter is properly handled.
Tested:
Normal TCP_RR results without busy polling :
lpk51:~# echo 0 >/proc/sys/net/core/busy_read
lpk52:~# echo 0 >/proc/sys/net/core/busy_read
lpk51:~# ./netperf -H 192.168.4.52 -t TCP_RR -l 10
MIGRATED TCP REQUEST/RESPONSE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.4.52 () port 0 AF_INET : first burst 0
Local /Remote
Socket Size Request Resp. Elapsed Trans.
Send Recv Size Size Time Rate
bytes Bytes bytes bytes secs. per sec
16384 87380 1 1 10.00 53509.49
16384 87380
Now enable busy polling :
lpk51:~# echo 70 >/proc/sys/net/core/busy_read
lpk52:~# echo 70 >/proc/sys/net/core/busy_read
lpk51:~# ./netperf -H 192.168.4.52 -t TCP_RR -l 10
MIGRATED TCP REQUEST/RESPONSE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.4.52 () port 0 AF_INET : first burst 0
Local /Remote
Socket Size Request Resp. Elapsed Trans.
Send Recv Size Size Time Rate
bytes Bytes bytes bytes secs. per sec
16384 87380 1 1 10.00 97530.92
16384 87380
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Wed, 18 Nov 2015 14:30:54 +0000 (06:30 -0800)]
net: network drivers no longer need to implement ndo_busy_poll()
Instead of having to implement complex ndo_busy_poll() method,
drivers can simply rely on NAPI poll logic.
Busy polling gains are mainly coming from polling itself,
not on exact details on how we poll the device.
ndo_busy_poll() if implemented can avoid touching
napi state, but it adds extra synchronization between
normal napi->poll() and busy poll handler, slowing down
the common path (non busy polling) with extra atomic operations.
In practice few drivers ever got busy poll because of the complexity.
We could go one step further, and make busy polling
available for all NAPI drivers, but this would require
that all netif_napi_del() calls are done in process context
so that we can call synchronize_rcu().
Full audit would be required.
Before this is done, a driver still needs to call :
- skb_mark_napi_id() for each skb provided to the stack.
- napi_hash_add() and napi_hash_del() to allocate a napi_id per napi struct.
- Make sure RCU grace period is respected after napi_hash_del() before
memory containing napi structure is freed.
Followup patch implements busy poll for mlx5 driver as an example.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Wed, 18 Nov 2015 14:30:53 +0000 (06:30 -0800)]
net: allow BH servicing in sk_busy_loop()
Instead of blocking BH in whole sk_busy_loop(), block them
only around ->ndo_busy_poll() calls.
This has many benefits.
1) allow tunneled traffic to use busy poll as well as native traffic.
Tunnels handlers usually call netif_rx() and depend on net_rx_action()
being run (from sofirq handler)
2) allow RFS/RPS being used (sending IPI to other cpus if needed)
3) use the 'lets burn cpu cycles' budget to do useful work
(like TX completions, timers, RCU callbacks...)
4) reduce BH latencies, making busy poll a better citizen.
Tested:
Tested with SIT tunnel
lpaa5:~# echo 0 >/proc/sys/net/core/busy_read
lpaa5:~# ./netperf -H 2002:af6:786::1 -t TCP_RR
MIGRATED TCP REQUEST/RESPONSE TEST from ::0 (::) port 0 AF_INET6 to 2002:af6:786::1 () port 0 AF_INET6 : first burst 0
Local /Remote
Socket Size Request Resp. Elapsed Trans.
Send Recv Size Size Time Rate
bytes Bytes bytes bytes secs. per sec
16384 87380 1 1 10.00 37373.93
16384 87380
Now enable busy poll on both hosts
lpaa5:~# echo 70 >/proc/sys/net/core/busy_read
lpaa6:~# echo 70 >/proc/sys/net/core/busy_read
lpaa5:~# ./netperf -H 2002:af6:786::1 -t TCP_RR
MIGRATED TCP REQUEST/RESPONSE TEST from ::0 (::) port 0 AF_INET6 to 2002:af6:786::1 () port 0 AF_INET6 : first burst 0
Local /Remote
Socket Size Request Resp. Elapsed Trans.
Send Recv Size Size Time Rate
bytes Bytes bytes bytes secs. per sec
16384 87380 1 1 10.00 58314.77
16384 87380
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Wed, 18 Nov 2015 14:30:52 +0000 (06:30 -0800)]
net: un-inline sk_busy_loop()
There is really little gain from inlining this big function.
We'll soon make it even bigger in following patches.
This means we no longer need to export napi_by_id()
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Wed, 18 Nov 2015 14:30:51 +0000 (06:30 -0800)]
mlx4: mlx4_en_low_latency_recv() called with BH disabled
mlx4_en_low_latency_recv() is called with BH disabled,
as other ndo_busy_poll() methods.
No need for spin_lock_bh()/spin_unlock_bh()
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Wed, 18 Nov 2015 14:30:50 +0000 (06:30 -0800)]
net: better skb->sender_cpu and skb->napi_id cohabitation
skb->sender_cpu and skb->napi_id share a common storage,
and we had various bugs about this.
We had to call skb_sender_cpu_clear() in some places to
not leave a prior skb->napi_id and fool netdev_pick_tx()
As suggested by Alexei, we could split the space so that
these errors can not happen.
0 value being reserved as the common (not initialized) value,
let's reserve [1 .. NR_CPUS] range for valid sender_cpu,
and [NR_CPUS+1 .. ~0U] for valid napi_id.
This will allow proper busy polling support over tunnels.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Suggested-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ivan Vecera [Wed, 18 Nov 2015 13:06:34 +0000 (14:06 +0100)]
be2net: remove local variable 'status'
The lancer_cmd_get_file_len() uses lancer_cmd_read_object() to get
the current size of registers for ethtool registers dump. Returned status
value is stored but not checked. The check itself is not necessary as
the data_read output variable is initialized to 0 and status variable
can be removed.
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
huangdaode [Wed, 18 Nov 2015 02:08:00 +0000 (10:08 +0800)]
net: hisilicon: fix binding document of mdio
This patch explains the occasion of "hisilcon,mdio" and
"hisilicon,hns-mdio" according to Arnd's comments.
and reformat it according to comments from Rob<robh@kernel.org>.
Signed-off-by: huangdaode <huangdaode@hisilicon.com>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
Bastian Stender [Fri, 13 Nov 2015 10:40:34 +0000 (11:40 +0100)]
net ipv4: use preferred log methods
Replace printk calls with preferred unconditional log method calls to keep
kernel messages clean.
Added newline to "too small MTU" message.
Signed-off-by: Bastian Stender <bst@pengutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
Linus Torvalds [Wed, 18 Nov 2015 16:59:29 +0000 (08:59 -0800)]
Merge branch 'for-linus' of git://git./linux/kernel/git/s390/linux
Pull s390 fixes from Martin Schwidefsky:
"Assorted bug fixes, the mlock2 system call gets added, and one
improvement. The boot from dasd devices is now possible from a wider
range of devices"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux:
s390: remove SALIPL loader
s390: wire up mlock2 system call
s390: remove g5 elf platform support
s390: avoid cache aliasing under z/VM and KVM
s390/sclp: _sclp_wait_int(): retain full PSW mask
s390/zcrypt: Fix initialisation when zcrypt is built-in
s390/zcrypt: Fix kernel crash on systems without AP bus support
s390: add support for ipl devices in subchannel sets > 0
s390/ipl: fix out of bounds access in scpdata_write
s390/pci_dma: improve debugging of errors during dma map
s390/pci_dma: handle dma table failures
s390/pci_dma: unify label of invalid translation table entries
s390/syscalls: remove system call number calculation
s390/cio: simplify css_generate_pgid
s390/diag: add a s390 prefix to the diagnose trace point
s390/head: fix error message on unsupported hardware
Linus Torvalds [Wed, 18 Nov 2015 16:43:29 +0000 (08:43 -0800)]
Merge tag 'hwmon-for-linus-v4.4-rc2' of git://git./linux/kernel/git/groeck/linux-staging
Pull hwmon fixes from Guenter Roeck:
"Fix build issues in scpi and ina2xx drivers, update scpi driver to
support recent firmware, and fix an uninitialized variable warning in
applesmc driver"
* tag 'hwmon-for-linus-v4.4-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/groeck/linux-staging:
hwmon: (scpi) skip unsupported sensors properly
hwmon: (scpi) add thermal-of dependency
hwmon : (applesmc) Fix uninitialized variables warnings
hwmon: (ina2xx) Fix build issue by selecting REGMAP_I2C
Linus Torvalds [Tue, 17 Nov 2015 21:52:59 +0000 (13:52 -0800)]
Merge git://git./linux/kernel/git/davem/net
Pull networking fixes from David Miller:
1) Fix list tests in netfilter ingress support, from Florian Westphal.
2) Fix reversal of input and output interfaces in ingress hook
invocation, from Pablo Neira Ayuso.
3) We have a use after free in r8169, caught by Dave Jones, fixed by
Francois Romieu.
4) Splice use-after-free fix in AF_UNIX frmo Hannes Frederic Sowa.
5) Three ipv6 route handling bug fixes from Martin KaFai Lau:
a) Don't create clone routes not managed by the fib6 tree
b) Don't forget to check expiration of DST_NOCACHE routes.
c) Handle rt->dst.from == NULL properly.
6) Several AF_PACKET fixes wrt transport header setting and SKB
protocol setting, from Daniel Borkmann.
7) Fix thunder driver crash on shutdown, from Pavel Fedin.
8) Several Mellanox driver fixes (max MTU calculations, use of correct
DMA unmap in TX path, etc.) from Saeed Mahameed, Tariq Toukan, Doron
Tsur, Achiad Shochat, Eran Ben Elisha, and Noa Osherovich.
9) Several mv88e6060 DSA driver fixes (wrong bit definitions for
certain registers, etc.) from Neil Armstrong.
10) Make sure to disable preemption while updating per-cpu stats of ip
tunnels, from Jason A. Donenfeld.
11) Various ARM64 bpf JIT fixes, from Yang Shi.
12) Flush icache properly in ARM JITs, from Daniel Borkmann.
13) Fix masking of RX and TX interrupts in ravb driver, from Masaru
Nagai.
14) Fix netdev feature propagation for devices not implementing
->ndo_set_features(). From Nikolay Aleksandrov.
15) Big endian fix in vmxnet3 driver, from Shrikrishna Khare.
16) RAW socket code increments incorrect SNMP counters, fix from Ben
Cartwright-Cox.
17) IPv6 multicast SNMP counters are bumped twice, fix from Neil Horman.
18) Fix handling of VLAN headers on stacked devices when REORDER is
disabled. From Vlad Yasevich.
19) Fix SKB leaks and use-after-free in ipvlan and macvlan drivers, from
Sabrina Dubroca.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (83 commits)
MAINTAINERS: Update Mellanox's Eth NIC driver entries
net/core: revert "net: fix __netdev_update_features return.." and add comment
af_unix: take receive queue lock while appending new skb
rtnetlink: fix frame size warning in rtnl_fill_ifinfo
net: use skb_clone to avoid alloc_pages failure.
packet: Use PAGE_ALIGNED macro
packet: Don't check frames_per_block against negative values
net: phy: Use interrupts when available in NOLINK state
phy: marvell: Add support for
88E1540 PHY
arm64: bpf: make BPF prologue and epilogue align with ARM64 AAPCS
macvlan: fix leak in macvlan_handle_frame
ipvlan: fix use after free of skb
ipvlan: fix leak in ipvlan_rcv_frame
vlan: Do not put vlan headers back on bridge and macvlan ports
vlan: Fix untag operations of stacked vlans with REORDER_HEADER off
via-velocity: unconditionally drop frames with bad l2 length
ipg: Remove ipg driver
dl2k: Add support for IP1000A-based cards
snmp: Remove duplicate OUTMCAST stat increment
net: thunder: Check for driver data in nicvf_remove()
...
Or Gerlitz [Tue, 17 Nov 2015 16:25:07 +0000 (18:25 +0200)]
MAINTAINERS: Update Mellanox's Eth NIC driver entries
Eugenia (Jenny) Emantayev is replacing Amir Vadai as the
mlx4 Ethernet driver maintainer.
Saeed Mahameed is assigned to maintain mlx5 Eth functionality.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Nikolay Aleksandrov [Tue, 17 Nov 2015 14:49:06 +0000 (15:49 +0100)]
net/core: revert "net: fix __netdev_update_features return.." and add comment
This reverts commit
00ee59271777 ("net: fix __netdev_update_features return
on ndo_set_features failure")
and adds a comment explaining why it's okay to return a value other than
0 upon error. Some drivers might actually change flags and return an
error so it's better to fire a spurious notification rather than miss
these.
CC: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Hannes Frederic Sowa [Tue, 17 Nov 2015 14:10:59 +0000 (15:10 +0100)]
af_unix: take receive queue lock while appending new skb
While possibly in future we don't necessarily need to use
sk_buff_head.lock this is a rather larger change, as it affects the
af_unix fd garbage collector, diag and socket cleanups. This is too much
for a stable patch.
For the time being grab sk_buff_head.lock without disabling bh and irqs,
so don't use locked skb_queue_tail.
Fixes: 869e7c62486e ("net: af_unix: implement stream sendpage support")
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Reported-by: Eric Dumazet <edumazet@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Hannes Frederic Sowa [Tue, 17 Nov 2015 13:16:52 +0000 (14:16 +0100)]
rtnetlink: fix frame size warning in rtnl_fill_ifinfo
Fix the following warning:
CC net/core/rtnetlink.o
net/core/rtnetlink.c: In function ‘rtnl_fill_ifinfo’:
net/core/rtnetlink.c:1308:1: warning: the frame size of 2864 bytes is larger than 2048 bytes [-Wframe-larger-than=]
}
^
by splitting up the huge rtnl_fill_ifinfo into some smaller ones, so we
don't have the huge frame allocations at the same time.
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Martin Zhang [Tue, 17 Nov 2015 12:49:30 +0000 (20:49 +0800)]
net: use skb_clone to avoid alloc_pages failure.
1. new skb only need dst and ip address(v4 or v6).
2. skb_copy may need high order pages, which is very rare on long running server.
Signed-off-by: Junwei Zhang <linggao.zjw@alibaba-inc.com>
Signed-off-by: Martin Zhang <martinbj2008@gmail.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Tobias Klauser [Tue, 17 Nov 2015 09:40:21 +0000 (10:40 +0100)]
packet: Use PAGE_ALIGNED macro
Use PAGE_ALIGNED(...) instead of open-coding it.
Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Tobias Klauser [Tue, 17 Nov 2015 09:38:36 +0000 (10:38 +0100)]
packet: Don't check frames_per_block against negative values
rb->frames_per_block is an unsigned int, thus can never be negative.
Also fix spacing in the calculation of frames_per_block.
Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Andrew Lunn [Mon, 16 Nov 2015 22:36:46 +0000 (23:36 +0100)]
net: phy: Use interrupts when available in NOLINK state
The NOLINK state will poll the phy once a second to see if the link
has come up. If the phy has an interrupt line, this polling can be
skipped, since the phy should interrupt when the link returns.
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Andrew Lunn [Mon, 16 Nov 2015 22:34:41 +0000 (23:34 +0100)]
phy: marvell: Add support for
88E1540 PHY
The
88E1540 can be found embedded in the Marvell
88E6352 switch. It
is compatible with the
88E1510, so add support for it, using the
88E1510 specific functions.
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Yang Shi [Mon, 16 Nov 2015 22:35:35 +0000 (14:35 -0800)]
arm64: bpf: make BPF prologue and epilogue align with ARM64 AAPCS
Save and restore FP/LR in BPF prog prologue and epilogue, save SP to FP
in prologue in order to get the correct stack backtrace.
However, ARM64 JIT used FP (x29) as eBPF fp register, FP is subjected to
change during function call so it may cause the BPF prog stack base address
change too.
Use x25 to replace FP as BPF stack base register (fp). Since x25 is callee
saved register, so it will keep intact during function call.
It is initialized in BPF prog prologue when BPF prog is started to run
everytime. Save and restore x25/x26 in BPF prologue and epilogue to keep
them intact for the outside of BPF. Actually, x26 is unnecessary, but SP
requires 16 bytes alignment.
So, the BPF stack layout looks like:
high
original A64_SP => 0:+-----+ BPF prologue
|FP/LR|
current A64_FP => -16:+-----+
| ... | callee saved registers
+-----+
| | x25/x26
BPF fp register => -80:+-----+
| |
| ... | BPF prog stack
| |
| |
current A64_SP => +-----+
| |
| ... | Function call stack
| |
+-----+
low
CC: Zi Shen Lim <zlim.lnx@gmail.com>
CC: Xi Wang <xi.wang@gmail.com>
Signed-off-by: Yang Shi <yang.shi@linaro.org>
Acked-by: Zi Shen Lim <zlim.lnx@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Sabrina Dubroca [Mon, 16 Nov 2015 21:54:20 +0000 (22:54 +0100)]
macvlan: fix leak in macvlan_handle_frame
Reset pskb in macvlan_handle_frame in case skb_share_check returned a
clone.
Fixes: 8a4eb5734e8d ("net: introduce rx_handler results and logic around that")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Sabrina Dubroca [Mon, 16 Nov 2015 21:44:53 +0000 (22:44 +0100)]
ipvlan: fix use after free of skb
ipvlan_handle_frame is a rx_handler, and when it returns a value other
than RX_HANDLER_CONSUMED (here, NET_RX_DROP aka RX_HANDLER_ANOTHER),
__netif_receive_skb_core expects that the skb still exists and will
process it further, but we just freed it.
Fixes: 2ad7bf363841 ("ipvlan: Initial check-in of the IPVLAN driver.")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Sabrina Dubroca [Mon, 16 Nov 2015 21:34:26 +0000 (22:34 +0100)]
ipvlan: fix leak in ipvlan_rcv_frame
Pass a **skb to ipvlan_rcv_frame so that if skb_share_check returns a
new skb, we actually use it during further processing.
It's safe to ignore the new skb in the ipvlan_xmit_* functions, because
they call ipvlan_rcv_frame with local == true, so that dev_forward_skb
is called and always takes ownership of the skb.
Fixes: 2ad7bf363841 ("ipvlan: Initial check-in of the IPVLAN driver.")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>