Since of_get_mac_address() is now defined even if CONFIG_OF_NET
is not configured, the ifdef around the code calling it is no longer
necessary and can be removed.
Similar, since of_get_phy_mode() is now defined as dummy function
if OF_NET is not configured, it is no longer necessary to provide
an OF dependent function as front-end. Also, the function depends
on OF_NET, not on OF, so the conditional code was not correct anyway.
Drop the front-end function and call of_get_phy_mode() directly.
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
With of_get_mac_address() and of_get_phy_mode() now defined as dummy
functions if OF_NET is not configured, it is no longer necessary to
provide OF dependent functions as front-end. Also, the two functions
depend on OF_NET, not on OF, so the conditional code was not correct
anyway.
Drop the front-end functions and call of_get_mac_address() and
of_get_phy_mode() directly instead.
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
With of_get_mac_address() and of_get_phy_mode() now defined as dummy
functions if OF_NET is not configured, it is no longer necessary to
provide OF dependent functions as front-end. Also, the two functions
depend on OF_NET, not on OF, so the conditional code was not correct
anyway.
Drop the front-end functions and call of_get_mac_address() and
of_get_phy_mode() directly instead.
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
of_get_mac_address() and of_get_phy_mode() are only provided if OF_NET
is configured. While most callers check for the define, not all do, and those
who do require #ifdef around the code. For those who don't, the missing check
can result in errors such as
arch/powerpc/sysdev/tsi108_dev.c:107:3: error: implicit declaration of
function 'of_get_mac_address' [-Werror=implicit-function-declaration]
arch/powerpc/sysdev/mv64x60_dev.c:253:2: error: implicit declaration of
function 'of_get_mac_address' [-Werror=implicit-function-declaration]
Provide empty functions if OF_NET is not configured.
This is safe because all callers do check the return values.
Cc: David Daney <david.daney@cavium.com>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Acked-by: Rob Herring <rob.herring@calxeda.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
One locking regression fix, and a couple of other i915 ones.
* 'drm-intel-fixes' of git://people.freedesktop.org/~danvet/drm-intel:
drm: don't unlock in the addfb error paths
drm/i915: Fix build failure
drm/i915: Be sure to turn hsync/vsync back on at crt enable (v2)
drm/i915: duct-tape locking when eDP init fails
The VMCI context ID of a virtual machine may change at any time. There
is a VMCI event which signals this but datagrams may be processed before
this is handled. It is therefore necessary to be flexible about the
destination context ID of any datagrams received. (It can be assumed to
be correct because it is provided by the hypervisor.) The context ID on
existing sockets should be updated to reflect how the hypervisor is
currently referring to the system.
Signed-off-by: Reilly Grant <grantr@vmware.com>
Acked-by: Andy King <acking@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
IPv6 Routing table becomes broken once we do ifdown, ifup of the loopback(lo)
interface. After down-up, routes of other interface's IPv6 addresses through
'lo' are lost.
IPv6 addresses assigned to all interfaces are routed through 'lo' for internal
communication. Once 'lo' is down, those routing entries are removed from routing
table. But those removed entries are not being re-created properly when 'lo' is
brought up. So IPv6 addresses of other interfaces becomes unreachable from the
same machine. Also this breaks communication with other machines because of
NDISC packet processing failure.
This patch fixes this issue by reading all interface's IPv6 addresses and adding
them to IPv6 routing table while bringing up 'lo'.
==Testing==
Before applying the patch:
$ route -A inet6
Kernel IPv6 routing table
Destination Next Hop Flag Met Ref Use If
2000::20/128 :: U 256 0 0 eth0
fe80::/64 :: U 256 0 0 eth0
::/0 :: !n -1 1 1 lo
::1/128 :: Un 0 1 0 lo
2000::20/128 :: Un 0 1 0 lo
fe80::xxxx:xxxx:xxxx:xxxx/128 :: Un 0 1 0 lo
ff00::/8 :: U 256 0 0 eth0
::/0 :: !n -1 1 1 lo
$ sudo ifdown lo
$ sudo ifup lo
$ route -A inet6
Kernel IPv6 routing table
Destination Next Hop Flag Met Ref Use If
2000::20/128 :: U 256 0 0 eth0
fe80::/64 :: U 256 0 0 eth0
::/0 :: !n -1 1 1 lo
::1/128 :: Un 0 1 0 lo
ff00::/8 :: U 256 0 0 eth0
::/0 :: !n -1 1 1 lo
$
After applying the patch:
$ route -A inet6
Kernel IPv6 routing
table
Destination Next Hop Flag Met Ref Use If
2000::20/128 :: U 256 0 0 eth0
fe80::/64 :: U 256 0 0 eth0
::/0 :: !n -1 1 1 lo
::1/128 :: Un 0 1 0 lo
2000::20/128 :: Un 0 1 0 lo
fe80::xxxx:xxxx:xxxx:xxxx/128 :: Un 0 1 0 lo
ff00::/8 :: U 256 0 0 eth0
::/0 :: !n -1 1 1 lo
$ sudo ifdown lo
$ sudo ifup lo
$ route -A inet6
Kernel IPv6 routing table
Destination Next Hop Flag Met Ref Use If
2000::20/128 :: U 256 0 0 eth0
fe80::/64 :: U 256 0 0 eth0
::/0 :: !n -1 1 1 lo
::1/128 :: Un 0 1 0 lo
2000::20/128 :: Un 0 1 0 lo
fe80::xxxx:xxxx:xxxx:xxxx/128 :: Un 0 1 0 lo
ff00::/8 :: U 256 0 0 eth0
::/0 :: !n -1 1 1 lo
$
Signed-off-by: Balakumaran Kannan <Balakumaran.Kannan@ap.sony.com>
Signed-off-by: Maruthi Thotad <Maruthi.Thotad@ap.sony.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 3fb72f1e6e ("ipconfig wait
for carrier") added a "wait for carrier on at least one interface"
policy, with a worst case maximum wait of two minutes.
However, if you encounter this, you won't get any feedback from
the console as to the nature of what is going on. You just see
the booting process hang for two minutes and then continue.
Here we add a message so the user knows what is going on, and
hence can take action to rectify the situation (e.g. fix network
cable or whatever.) After the 1st 10s pause, output now begins
that looks like this:
Waiting up to 110 more seconds for network.
Waiting up to 100 more seconds for network.
Waiting up to 90 more seconds for network.
Waiting up to 80 more seconds for network.
...
Since most systems will have no problem getting link/carrier in the
1st 10s, the only people who will see these messages are people with
genuine issues that need to be resolved.
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
delete useless 'break' after 'return'.
let 'return 0' instead of 'return (0)'
also give a comment for 'break' to let readers notice it.
Signed-off-by: Chen Gang <gang.chen@asianux.com>
Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
currently cbq works incorrectly for limits > 10% real link bandwidth,
and practically does not work for limits > 50% real link bandwidth.
Below are results of experiments taken on 1 Gbit link
In shaper | Actual Result
-----------+---------------
100M | 108 Mbps
200M | 244 Mbps
300M | 412 Mbps
500M | 893 Mbps
This happen because of q->now changes incorrectly in cbq_dequeue():
when it is called before real end of packet transmitting,
L2T is greater than real time delay, q_now gets an extra boost
but never compensate it.
To fix this problem we prevent change of q->now until its synchronization
with real time.
Signed-off-by: Vasily Averin <vvs@openvz.org>
Reviewed-by: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
warning: 'pf_info.max_tx_ques' may be used uninitialized in this function
[-Wmaybe-uninitialized]
Signed-off-by: Rajesh Borundia <rajesh.borundia@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
o Fix for smatch tool reported error
drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c:2029
qlcnic_probe() error: potential NULL dereference 'adapter'.
o While returning from an error path in probe, adapter is not
initialized. So do not access adapter in cleanup path.
Signed-off-by: Rajesh Borundia <rajesh.borundia@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
[net-next:master 301/302] drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c:563
qlcnic_set_multi() error: potential null dereference 'cur'. (kzalloc returns null)
o Break out of the loop after memory allocation failure. Program all the
MAC addresses that were cached in the return path.
Reported-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Rajesh Borundia <rajesh.borundia@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Remove a declaration left over from the TCPCT-ectomy. This sysctl is
no longer referenced anywhere since 1a2c6181c4 ("tcp: Remove TCPCT").
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Make sure that msg pointer is set back to error value in case of
MSG_COPY flag is set and desired message to copy wasn't found. This
garantees that msg is either a error pointer or a copy address.
Otherwise the last message in queue will be freed without unlinking from
the queue (which leads to memory corruption) and the dummy allocated
copy won't be released.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
commit 00cfec3748 (net: add a synchronize_net() in
netdev_rx_handler_unregister())
allows us to remove the synchronized_net() call from del_nbp()
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Veaceslav Falico <vfalico@redhat.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Veaceslav Falico <vfalico@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 6bbb6d9 "net/mlx4_en: Optimize Rx fast path filter checks" introduced a regression
under which the MAC address read from the card was not converted correctly
(the most significant byte was not handled), fix that.
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Yan Burman <yanb@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Now that netdev_rx_handler_unregister contains synchronize_net(), we need
to call it outside of bond->lock, cause it might sleep. Also, remove the
already unneded synchronize_net().
Signed-off-by: Veaceslav Falico <vfalico@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
After a quiet set of fixes for 3.9-rc4, a lot of people woke up and sent
urgent fixes for 3.9. I pushed back on a number of them that got
deferred to 3.10, but these are the ones that seemed important.
Regression in 3.9:
- Multiple regressions in OMAP2+ clock cleanup
- SH-Mobile frame buffer bug fix that merged here because of maintainer MIA
- ux500 prcmu changes broke DT booting
- MMCI duplicated regulator setup on ux500
- New ux500 clock driver broke ethernet on snowball
- Local interrupt driver for mvebu broke ethernet
- MVEBU GPIO driver did not get set up right on Orion DT
- incorrect interrupt number on Orion crypto for DT
Long-standing bugs, including candidates for stable:
- Kirkwood MMC needs to disable invalid card detect pins
- MV SDIO pinmux was wrong on Mirabox
- GoFlex Net board file needs to set NAND chip delay
- MSM timer restart race
- ep93xx early debug code broke in 3.7
- i.MX CPU hotplug race
- Incorrect clock setup for OMAP1 USB
- Workaround for bad clock setup by some old OMAP4 boot loaders
- Static I/O mappings on cns3xxx since 3.2
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.12 (GNU/Linux)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=oQbL
-----END PGP SIGNATURE-----
Merge tag 'fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc
Pull ARM SoC bug fixes from Arnd Bergmann:
"After a quiet set of fixes for 3.9-rc4, a lot of people woke up and
sent urgent fixes for 3.9. I pushed back on a number of them that got
deferred to 3.10, but these are the ones that seemed important.
Regression in 3.9:
- Multiple regressions in OMAP2+ clock cleanup
- SH-Mobile frame buffer bug fix that merged here because of
maintainer MIA
- ux500 prcmu changes broke DT booting
- MMCI duplicated regulator setup on ux500
- New ux500 clock driver broke ethernet on snowball
- Local interrupt driver for mvebu broke ethernet
- MVEBU GPIO driver did not get set up right on Orion DT
- incorrect interrupt number on Orion crypto for DT
Long-standing bugs, including candidates for stable:
- Kirkwood MMC needs to disable invalid card detect pins
- MV SDIO pinmux was wrong on Mirabox
- GoFlex Net board file needs to set NAND chip delay
- MSM timer restart race
- ep93xx early debug code broke in 3.7
- i.MX CPU hotplug race
- Incorrect clock setup for OMAP1 USB
- Workaround for bad clock setup by some old OMAP4 boot loaders
- Static I/O mappings on cns3xxx since 3.2"
* tag 'fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc:
ARM: cns3xxx: fix mapping of private memory region
arm: mvebu: Fix pinctrl for Armada 370 Mirabox SDIO port.
arm: orion5x: correct IRQ used in dtsi for mv_cesa
arm: orion5x: fix orion5x.dtsi gpio parameters
ARM: Kirkwood: fix unused mvsdio gpio pins
arm: mvebu: Use local interrupt only for the timer 0
ARM: kirkwood: Fix chip-delay for GoFlex Net
ARM: ux500: Enable the clock controlling Ethernet on Snowball
ARM: ux500: Stop passing ios_handler() as an MMCI power controlling call-back
ARM: ux500: Apply the TCPM and TCDM locations and sizes to dbx5x0 DT
fbdev: sh_mobile_lcdc: fixup B side hsync adjust settings
ARM: OMAP: clocks: Delay clk inits atleast until slab is initialized
ARM: imx: fix sync issue between imx_cpu_die and imx_cpu_kill
ARM: msm: Stop counting before reprogramming clockevent
ARM: ep93xx: Fix wait for UART FIFO to be empty
ARM: OMAP4: PM: fix PM regression introduced by recent clock cleanup
ARM: OMAP3: hwmod data: keep MIDLEMODE in force-standby for musb
ARM: OMAP4: clock data: lock USB DPLL on boot
ARM: OMAP1: fix USB host on 1710
From Anton Vorontsov <anton@enomsg.org>:
This tag includes Mac Lin's work to revive CNS3xxx booting:
"Since commit 0536bdf33f (ARM: move iotable mappings within the vmalloc
region), [...] the pre-defined iotable mappings is not in the vmalloc
region. [...] move the iotable mappings into the vmalloc region, and
merge the MPCore private memory region (containing the SCU, the GIC and
the TWD) as a single region."
Plus there is a small cosmetic fix, also from Mac Lin.
* tag 'v3.9-rc1_cns3xxx_fixes' of git://git.infradead.org/users/cbou/linux-cns3xxx:
ARM: cns3xxx: fix mapping of private memory region
[arnd: dropped the cosmetic fix from the merge as it is not needed for 3.9]
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Because rev1 and rev3 of the target share the same hashing
generalize it by introduing nfqueue_hash().
Signed-off-by: Holger Eitzenberger <holger@eitzenberger.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Current NFQUEUE target uses a hash, computed over source and
destination address (and other parameters), for steering the packet
to the actual NFQUEUE. This, however forgets about the fact that the
packet eventually is handled by a particular CPU on user request.
If E. g.
1) IRQ affinity is used to handle packets on a particular CPU already
(both single-queue or multi-queue case)
and/or
2) RPS is used to steer packets to a specific softirq
the target easily chooses an NFQUEUE which is not handled by a process
pinned to the same CPU.
The idea is therefore to use the CPU index for determining the
NFQUEUE handling the packet.
E. g. when having a system with 4 CPUs, 4 MQ queues and 4 NFQUEUEs it
looks like this:
+-----+ +-----+ +-----+ +-----+
|NFQ#0| |NFQ#1| |NFQ#2| |NFQ#3|
+-----+ +-----+ +-----+ +-----+
^ ^ ^ ^
| |NFQUEUE | |
+ + + +
+-----+ +-----+ +-----+ +-----+
|rx-0 | |rx-1 | |rx-2 | |rx-3 |
+-----+ +-----+ +-----+ +-----+
The NFQUEUEs not necessarily have to start with number 0, setups with
less NFQUEUEs than packet-handling CPUs are not a problem as well.
This patch extends the NFQUEUE target to accept a new
NFQ_FLAG_CPU_FANOUT flag. If this is specified the target uses the
CPU index for determining the NFQUEUE being used. I have to introduce
rev3 for this. The 'flags' are folded into _v2 'bypass'.
By changing the way which queue is assigned, I'm able to improve the
performance if the processes reading on the NFQUEUs are pinned
correctly.
Signed-off-by: Holger Eitzenberger <holger@eitzenberger.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
struct block_device lifecycle is defined by its inode (see fs/block_dev.c) -
block_device allocated first time we access /dev/loopXX and deallocated on
bdev_destroy_inode. When we create the device "losetup /dev/loopXX afile"
we want that block_device stay alive until we destroy the loop device
with "losetup -d".
But because we do not hold /dev/loopXX inode its counter goes 0, and
inode/bdev can be destroyed at any moment. Usually it happens at memory
pressure or when user drops inode cache (like in the test below). When later in
loop_clr_fd() we want to use bdev we have use-after-free error with following
stack:
BUG: unable to handle kernel NULL pointer dereference at 0000000000000280
bd_set_size+0x10/0xa0
loop_clr_fd+0x1f8/0x420 [loop]
lo_ioctl+0x200/0x7e0 [loop]
lo_compat_ioctl+0x47/0xe0 [loop]
compat_blkdev_ioctl+0x341/0x1290
do_filp_open+0x42/0xa0
compat_sys_ioctl+0xc1/0xf20
do_sys_open+0x16e/0x1d0
sysenter_dispatch+0x7/0x1a
To prevent use-after-free we need to grab the device in loop_set_fd()
and put it later in loop_clr_fd().
The issue is reprodusible on current Linus head and v3.3. Here is the test:
dd if=/dev/zero of=loop.file bs=1M count=1
while [ true ]; do
losetup /dev/loop0 loop.file
echo 2 > /proc/sys/vm/drop_caches
losetup -d /dev/loop0
done
[ Doing bdgrab/bput in loop_set_fd/loop_clr_fd is safe, because every
time we call loop_set_fd() we check that loop_device->lo_state is
Lo_unbound and set it to Lo_bound If somebody will try to set_fd again
it will get EBUSY. And if we try to loop_clr_fd() on unbound loop
device we'll get ENXIO.
loop_set_fd/loop_clr_fd (and any other loop ioctl) is called under
loop_device->lo_ctl_mutex. ]
Signed-off-by: Anatol Pomozov <anatol.pomozov@gmail.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
We used a global BH disable in LOCAL_OUT hook.
Add _bh suffix to all places that need it and remove
the disabling from LOCAL_OUT and sync code.
Functions like ip_defrag need protection from
BH, so add it. As for nf_nat_mangle_tcp_packet, it needs
RCU lock.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
This is the final step in RCU conversion.
Things that are removed:
- svc->usecnt: now svc is accessed under RCU read lock
- svc->inc: and some unused code
- ip_vs_bind_pe and ip_vs_unbind_pe: no ability to replace PE
- __ip_vs_svc_lock: replaced with RCU
- IP_VS_WAIT_WHILE: now readers lookup svcs and dests under
RCU and work in parallel with configuration
Other changes:
- before now, a RCU read-side critical section included the
calling of the schedule method, now it is extended to include
service lookup
- ip_vs_svc_table and ip_vs_svc_fwm_table are now using hlist
- svc->pe and svc->scheduler remain to the end (of grace period),
the schedulers are prepared for such RCU readers
even after done_service is called but they need
to use synchronize_rcu because last ip_vs_scheduler_put
can happen while RCU read-side critical sections
use an outdated svc->scheduler pointer
- as planned, update_service is removed
- empty services can be freed immediately after grace period.
If dests were present, the services are freed from
the dest trash code
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
In previous commits the schedulers started to access
svc->destinations with _rcu list traversal primitives
because the IP_VS_WAIT_WHILE macro still plays the role of
grace period. Now it is time to finish the updating part,
i.e. adding and deleting of dests with _rcu suffix before
removing the IP_VS_WAIT_WHILE in next commit.
We use the same rule for conns as for the
schedulers: dests can be searched in RCU read-side critical
section where ip_vs_dest_hold can be called by ip_vs_bind_dest.
Some things are not perfect, for example, calling
functions like ip_vs_lookup_dest from updating code under
RCU, just because we use some function both from reader
and from updater.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
This method releases the scheduler state,
it can not fail. Such change will help to properly
replace the scheduler in following patch.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
All dests will go to trash, no exceptions.
But we have to use new list node t_list for this, due
to RCU changes in following patches. Dests will wait there
initial grace period and later all conns and schedulers to
put their reference. The dests don't get reference for
staying in dest trash as before.
As result, we do not load ip_vs_dest_put with
extra checks for last refcnt and the schedulers do not
need to play games with atomic_inc_not_zero while
selecting best destination.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
The schedule method now needs _rcu list-traversal
primitive for svc->destinations. As the weight for some
dest can be reduced during dest selection, change the
algorithm to check weights by using minimum weights in the
1 .. max_weight-(di-1) range, with the same step (di). By this
way we ensure that there will be always a weight >= 1 check
before claiming that all destinations are overloaded.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
The schedule method now needs _rcu list-traversal
primitive for svc->destinations.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
The schedule method now needs _rcu list-traversal
primitive for svc->destinations.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
The schedule method now needs _rcu list-traversal
primitive for svc->destinations. As the previous entry
could be unlinked, limit the list traversals to 2 when
lookup started from previous entry.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
The schedule method now needs _rcu list-traversal
primitive for svc->destinations.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
The schedule method now needs _rcu list-traversal
primitive for svc->destinations.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
The schedule method now needs _rcu list-traversal
primitive for svc->destinations. The read_lock for sched_lock is
removed. The set.lock is removed because now it is used in
rare cases, mostly under sched_lock.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
The schedule method now needs _rcu list-traversal
primitive for svc->destinations. The read_lock for sched_lock is
removed. Use a dead flag to prevent new entries to be created
while scheduler is reclaimed. Use hlist for the hash table.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Use the new add_dest and del_dest methods
to reassign dests.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
ip_vs_dest_hold will be used under RCU lock
while ip_vs_dest_put can be called even after dest
is removed from service, as it happens for conns and
some schedulers.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Allow schedulers to use rcu_dereference when
returning destination on lookup. The RCU read-side critical
section will allow ip_vs_bind_dest to get dest refcnt as
preparation for the step where destinations will be
deleted without an IP_VS_WAIT_WHILE guard that holds the
packet processing during update.
Add new optional scheduler methods add_dest,
del_dest and upd_dest. For now the methods are called
together with update_service but update_service will be
removed in a following change.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
The global list with schedulers ip_vs_schedulers
is accessed only from user context - configuration and
scheduler module [un]registration. Use ip_vs_sched_mutex
instead.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
We have many fields to set and few to reset,
use kmem_cache_alloc instead to save some cycles.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off by: Hans Schillstrom <hans@schillstrom.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
__ip_vs_conn_in_get and ip_vs_conn_out_get are
hot places. Optimize them, so that ports are matched first.
By moving net and fwmark below, on 32-bit arch we can fit
caddr in 32-byte cache line and all addresses in 64-byte
cache line.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off by: Hans Schillstrom <hans@schillstrom.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
