On x86_64, its rather unfortunate that "wait_queue_head_t wait"
field of "struct socket" spans two cache lines (assuming a 64
bytes cache line in current cpus)
offsetof(struct socket, wait)=0x30
sizeof(wait_queue_head_t)=0x18
This might explain why Kenny Chang noticed that his multicast workload
was performing bad with 64 bit kernels, since more cache lines ping pongs
were involved.
This litle patch moves "wait" field next "fasync_list" so that both
fields share a single cache line, to speedup sock_def_readable()
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
I found the PPP subsystem to not work properly when connecting channels
with different speeds to the same bundle.
Problem Description:
As the "ppp_mp_explode" function fragments the sk_buff buffer evenly
among the PPP channels that are connected to a certain PPP unit to
make up a bundle, if we are transmitting using an upper layer protocol
that requires an Ack before sending the next packet (like TCP/IP for
example), we will have a bandwidth bottleneck on the slowest channel
of the bundle.
Let's clarify by an example. Let's consider a scenario where we have
two PPP links making up a bundle: a slow link (10KB/sec) and a fast
link (1000KB/sec) working at the best (full bandwidth). On the top we
have a TCP/IP stack sending a 1000 Bytes sk_buff buffer down to the
PPP subsystem. The "ppp_mp_explode" function will divide the buffer in
two fragments of 500B each (we are neglecting all the headers, crc,
flags etc?.). Before the TCP/IP stack sends out the next buffer, it
will have to wait for the ACK response from the remote peer, so it
will have to wait for both fragments to have been sent over the two
PPP links, received by the remote peer and reconstructed. The
resulting behaviour is that, rather than having a bundle working
@1010KB/sec (the sum of the channels bandwidths), we'll have a bundle
working @20KB/sec (the double of the slowest channels bandwidth).
Problem Solution:
The problem has been solved by redesigning the "ppp_mp_explode"
function in such a way to make it split the sk_buff buffer according
to the speeds of the underlying PPP channels (the speeds of the serial
interfaces respectively attached to the PPP channels). Referring to
the above example, the redesigned "ppp_mp_explode" function will now
divide the 1000 Bytes buffer into two fragments whose sizes are set
according to the speeds of the channels where they are going to be
sent on (e.g . 10 Byets on 10KB/sec channel and 990 Bytes on
1000KB/sec channel). The reworked function grants the same
performances of the original one in optimal working conditions (i.e. a
bundle made up of PPP links all working at the same speed), while
greatly improving performances on the bundles made up of channels
working at different speeds.
Signed-off-by: Gabriele Paoloni <gabriele.paoloni@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
It closes a race in phy_stop_machine when reprogramming of phy_timer
(from phy_state_machine) happens between del_timer_sync and cancel_work_sync.
Without this change it could lead to crash if phy_device would be freed after
phy_stop_machine (timer would fire and schedule freed work).
Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com>
Acked-by: Jean Delvare <khali@linux-fr.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
This adds SSB functionality to register a fallback SPROM image from the
architecture setup code.
Weird architectures exist that have half-assed SSB devices without SPROM attached to
their PCI busses. The architecture can register a fallback SPROM image that is
used if no SPROM is found on the SSB device.
Signed-off-by: Michael Buesch <mb@bu3sch.de>
Cc: Florian Fainelli <florian@openwrt.org>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
As analyzed by Patrick McHardy, vlan needs to reset it's
netdev_ops pointer in it's ->init() function but this
leaves the compat method pointers stale.
Add a netdev_resync_ops() and call it from the vlan code.
Any other driver which changes ->netdev_ops after register_netdevice()
will need to call this new function after doing so too.
With help from Patrick McHardy.
Tested-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently it is possible to do just about everything with the arp table
from user space except treat an entry like you are using it. To that end
implement and a flag NTF_USE that when set in a netwlink update request
treats the neighbour table entry like the kernel does on the output path.
This allows user space applications to share the kernel's arp cache.
Signed-off-by: Eric Biederman <ebiederm@aristanetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
* 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
sched: don't allow setuid to succeed if the user does not have rt bandwidth
sched_rt: don't start timer when rt bandwidth disabled
* 'core-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
rcu: Teach RCU that idle task is not quiscent state at boot
* 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
fix warning in io_mapping_map_wc()
x86: i915 needs pgprot_writecombine() and is_io_mapping_possible()
Fix skbuff.h kernel-doc for timestamps: must include "struct" keyword,
otherwise there are kernel-doc errors:
Error(linux-next-20090227//include/linux/skbuff.h:161): cannot understand prototype: 'struct skb_shared_hwtstamps '
Error(linux-next-20090227//include/linux/skbuff.h:177): cannot understand prototype: 'union skb_shared_tx '
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Allow the device to give the driver RX data with reorder information.
When that is done, the device will indicate the driver if a packet has
to be held in a (sorted) queue. It will also tell the driver when held
packets have to be released to the OS.
This is done to improve the WiMAX-protocol level retransmission
support when missing frames are detected.
The code docs provide details about the implementation.
In general, this just hooks into the RX path in rx.c; if a packet with
the reorder bit in the RX header is detected, the reorder information
in the header is extracted and one of the four main reorder operations
are executed. In one case (queue) no packet will be delivered to the
networking stack, just queued, whereas in the others (reset, update_ws
and queue_update_ws), queued packet might be delivered depending on
the window start for the specific queue.
The modifications to files other than rx.c are:
- control.c: during device initialization, enable reordering support
if the rx_reorder_disabled module parameter is not enabled
- driver.c: expose a rx_reorder_disable module parameter and call
i2400m_rx_setup/release() to initialize/shutdown RX reorder
support.
- i2400m.h: introduce members in 'struct i2400m' needed for
implementing reorder support.
- linux/i2400m.h: introduce TLVs, commands and constant definitions
related to RX reorder
Last but not least, the rx reorder code includes an small circular log
where the last N reorder operations are recorded to be displayed in
case of inconsistency. Otherwise diagnosing issues would be almost
impossible.
Signed-off-by: Inaky Perez-Gonzalez <inaky@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Newer i2400m firmwares (>= v1.4) extend the data RX protocol so that
each packet has a 16 byte header. This header is mainly used to
implement host reordeing (which is addressed in later commits).
However, this header also allows us to overwrite it (once data has
been extracted) with an Ethernet header and deliver to the networking
stack without having to reallocate the skb (as it happened in fw <=
v1.3) to make room for it.
- control.c: indicate the device [dev_initialize()] that the driver
wants to use the extended data RX protocol. Also involves adding the
definition of the needed data types in include/linux/wimax/i2400m.h.
- rx.c: handle the new payload type for the extended RX data
protocol. Prepares the skb for delivery to
netdev.c:i2400m_net_erx().
- netdev.c: Introduce i2400m_net_erx() that adds the fake ethernet
address to a prepared skb and delivers it to the networking
stack.
- cleanup: in most instances in rx.c, the variable 'single' was
renamed to 'single_last' for it better conveys its meaning.
Signed-off-by: Inaky Perez-Gonzalez <inaky@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
For power saving reasons, WiMAX links can be put in idle mode while
connected after a certain time of the link not being used for tx or
rx. In this mode, the device pages the base-station regularly and when
data is ready to be transmitted, the link is revived.
This patch allows the user to control the time the device has to be
idle before it decides to go to idle mode from a sysfs
interace.
It also updates the initialization code to acknowledge the module
variable 'idle_mode_disabled' when the firmware is a newer version
(upcoming 1.4 vs 2.6.29's v1.3).
The method for setting the idle mode timeout in the older firmwares is
much more limited and can be only done at initialization time. Thus,
the sysfs file will return -ENOSYS on older ones.
Signed-off-by: Inaky Perez-Gonzalez <inaky@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Also fixes insignificant bug that would cause sending of stale
SACK block (would occur in some corner cases).
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
The DCB netlink interface is required for building the userspace tools
available at e1000.sourceforge.net
Signed-off-by: Chris Leech <christopher.leech@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
1) add an include for <linux/types.h>
2) change dcbmsg.dcb_family from unsigned char to __u8 to be more
consistent with use of kernel types
Signed-off-by: Chris Leech <christopher.leech@intel.com>
Acked-by: Sam Ravnborg <sam@ravnborg.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
* 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86: enable DMAR by default
xen: disable interrupts early, as start_kernel expects
gpu/drm, x86, PAT: io_mapping_create_wc and resource_size_t
gpu/drm, x86, PAT: Handle io_mapping_create_wc() errors in a clean way
x86, Voyager: fix compile by lifting the degeneracy of phys_cpu_present_map
x86, doc: fix references to Documentation/x86/i386/boot.txt
free_uid() and free_user_ns() are corecursive when CONFIG_USER_SCHED=n,
but free_user_ns() is called from free_uid() by way of uid_hash_remove(),
which requires uidhash_lock to be held. free_user_ns() then calls
free_uid() to complete the destruction.
Fix this by deferring the destruction of the user_namespace.
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Serge Hallyn <serue@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The TX/RX packet counters are needed to fill in RADIUS Accounting
attributes Acct-Output-Packets and Acct-Input-Packets. We already
collect the needed information, but only the TX/RX bytes were
previously exposed through nl80211. Allow applications to fetch the
packet counters, too, to provide more complete support for accounting.
Signed-off-by: Jouni Malinen <jouni.malinen@atheros.com>
Acked-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Impact: fix hung task with certain (non-default) rt-limit settings
Corey Hickey reported that on using setuid to change the uid of a
rt process, the process would be unkillable and not be running.
This is because there was no rt runtime for that user group. Add
in a check to see if a user can attach an rt task to its task group.
On failure, return EINVAL, which is also returned in
CONFIG_CGROUP_SCHED.
Reported-by: Corey Hickey <bugfood-ml@fatooh.org>
Signed-off-by: Dhaval Giani <dhaval@linux.vnet.ibm.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Applications include this header in order to use RDS sockets.
Signed-off-by: Andy Grover <andy.grover@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
RDS is a reliable datagram protocol used for IPC on Oracle
database clusters. This adds address and protocol family numbers
for it.
Signed-off-by: Andy Grover <andy.grover@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch fixes a bug located by Vegard Nossum with the aid of
kmemcheck, updated based on review comments from Nick Piggin,
Ingo Molnar, and Andrew Morton. And cleans up the variable-name
and function-name language. ;-)
The boot CPU runs in the context of its idle thread during boot-up.
During this time, idle_cpu(0) will always return nonzero, which will
fool Classic and Hierarchical RCU into deciding that a large chunk of
the boot-up sequence is a big long quiescent state. This in turn causes
RCU to prematurely end grace periods during this time.
This patch changes the rcutree.c and rcuclassic.c rcu_check_callbacks()
function to ignore the idle task as a quiescent state until the
system has started up the scheduler in rest_init(), introducing a
new non-API function rcu_idle_now_means_idle() to inform RCU of this
transition. RCU maintains an internal rcu_idle_cpu_truthful variable
to track this state, which is then used by rcu_check_callback() to
determine if it should believe idle_cpu().
Because this patch has the effect of disallowing RCU grace periods
during long stretches of the boot-up sequence, this patch also introduces
Josh Triplett's UP-only optimization that makes synchronize_rcu() be a
no-op if num_online_cpus() returns 1. This allows boot-time code that
calls synchronize_rcu() to proceed normally. Note, however, that RCU
callbacks registered by call_rcu() will likely queue up until later in
the boot sequence. Although rcuclassic and rcutree can also use this
same optimization after boot completes, rcupreempt must restrict its
use of this optimization to the portion of the boot sequence before the
scheduler starts up, given that an rcupreempt RCU read-side critical
section may be preeempted.
In addition, this patch takes Nick Piggin's suggestion to make the
system_state global variable be __read_mostly.
Changes since v4:
o Changes the name of the introduced function and variable to
be less emotional. ;-)
Changes since v3:
o WARN_ON(nr_context_switches() > 0) to verify that RCU
switches out of boot-time mode before the first context
switch, as suggested by Nick Piggin.
Changes since v2:
o Created rcu_blocking_is_gp() internal-to-RCU API that
determines whether a call to synchronize_rcu() is itself
a grace period.
o The definition of rcu_blocking_is_gp() for rcuclassic and
rcutree checks to see if but a single CPU is online.
o The definition of rcu_blocking_is_gp() for rcupreempt
checks to see both if but a single CPU is online and if
the system is still in early boot.
This allows rcupreempt to again work correctly if running
on a single CPU after booting is complete.
o Added check to rcupreempt's synchronize_sched() for there
being but one online CPU.
Tested all three variants both SMP and !SMP, booted fine, passed a short
rcutorture test on both x86 and Power.
Located-by: Vegard Nossum <vegard.nossum@gmail.com>
Tested-by: Vegard Nossum <vegard.nossum@gmail.com>
Tested-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
During host driver module removal del_gendisk() results in a final
put on drive->gendev and freeing the drive by drive_release_dev().
Convert device drivers from using struct kref to use struct device
so device driver's object holds reference on ->gendev and prevents
drive from prematurely going away.
Also fix ->remove methods to not erroneously drop reference on a
host driver by using only put_device() instead of ide*_put().
Reported-by: Stanislaw Gruszka <stf_xl@wp.pl>
Tested-by: Stanislaw Gruszka <stf_xl@wp.pl>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
io_mapping_create_wc should take a resource_size_t parameter in place of
unsigned long. With unsigned long, there will be no way to map greater than 4GB
address in i386/32 bit.
On x86, greater than 4GB addresses cannot be mapped on i386 without PAE. Return
error for such a case.
Patch also adds a structure for io_mapping, that saves the base, size and
type on HAVE_ATOMIC_IOMAP archs, that can be used to verify the offset on
io_mapping_map calls.
Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: Dave Airlie <airlied@redhat.com>
Cc: Jesse Barnes <jbarnes@virtuousgeek.org>
Cc: Eric Anholt <eric@anholt.net>
Cc: Keith Packard <keithp@keithp.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This patch changes the return value of nlmsg_notify() as follows:
If NETLINK_BROADCAST_ERROR is set by any of the listeners and
an error in the delivery happened, return the broadcast error;
else if there are no listeners apart from the socket that
requested a change with the echo flag, return the result of the
unicast notification. Thus, with this patch, the unicast
notification is handled in the same way of a broadcast listener
that has set the NETLINK_BROADCAST_ERROR socket flag.
This patch is useful in case that the caller of nlmsg_notify()
wants to know the result of the delivery of a netlink notification
(including the broadcast delivery) and take any action in case
that the delivery failed. For example, ctnetlink can drop packets
if the event delivery failed to provide reliable logging and
state-synchronization at the cost of dropping packets.
This patch also modifies the rtnetlink code to ignore the return
value of rtnl_notify() in all callers. The function rtnl_notify()
(before this patch) returned the error of the unicast notification
which makes rtnl_set_sk_err() reports errors to all listeners. This
is not of any help since the origin of the change (the socket that
requested the echoing) notices the ENOBUFS error if the notification
fails and should resync itself.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Acked-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
The unit in which user-space can set the bus timeout value is jiffies
for historical reasons (back when HZ was always 100.) This is however
not good because user-space doesn't know how long a jiffy lasts. The
timeout value should instead be set in a fixed time unit. Given the
original value of HZ, this unit should be 10 ms, for compatibility.
Signed-off-by: Jean Delvare <khali@linux-fr.org>
Acked-by: Wolfram Sang <w.sang@pengutronix.de>
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6:
netns: fix double free at netns creation
veth : add the set_mac_address capability
sunlance: Beyond ARRAY_SIZE of ib->btx_ring
sungem: another error printed one too early
ISDN: fix sc/shmem printk format warning
SMSC: timeout reaches -1
smsc9420: handle magic field of ethtool_eeprom
sundance: missing parentheses?
smsc9420: fix another postfixed timeout
wimax/i2400m: driver loads firmware v1.4 instead of v1.3
vlan: Update skb->mac_header in __vlan_put_tag().
cxgb3: Add support for PCI ID 0x35.
tcp: remove obsoleted comment about different passes
TG3: &&/|| confusion
ATM: misplaced parentheses?
net/mv643xx: don't disable the mib timer too early and lock properly
net/mv643xx: use GFP_ATOMIC while atomic
atl1c: Atheros L1C Gigabit Ethernet driver
net: Kill skb_truesize_check(), it only catches false-positives.
net: forcedeth: Fix wake-on-lan regression
Move the sysdev_suspend/resume from the callee to the callers, with
no real change in semantics, so that we can rework the disabling of
interrupts during suspend/hibernation.
This is based on an earlier patch from Linus.
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* hibernate:
PM: Fix suspend_console and resume_console to use only one semaphore
PM: Wait for console in resume
PM: Fix pm_notifiers during user mode hibernation
swsusp: clean up shrink_all_zones()
swsusp: dont fiddle with swappiness
PM: fix build for CONFIG_PM unset
PM/hibernate: fix "swap breaks after hibernation failures"
PM/resume: wait for device probing to finish
Consolidate driver_probe_done() loops into one place
there's a few places that currently loop over driver_probe_done(), and
I'm about to add another one. This patch abstracts it into a helper
to reduce duplication.
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Cc: Len Brown <lenb@kernel.org>
Acked-by: Greg KH <gregkh@suse.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Intel 8257x Ethernet boards have a feature called Serial Over Lan.
This feature works by emulating a serial port, and it is detected by
kernel as a normal 8250 port. However, this emulation is not perfect, as
also noticed on changeset 7500b1f602.
Before this patch, the kernel were trying to check if the serial TX is
capable of work using IRQ's.
This were done with a code similar this:
serial_outp(up, UART_IER, UART_IER_THRI);
lsr = serial_in(up, UART_LSR);
iir = serial_in(up, UART_IIR);
serial_outp(up, UART_IER, 0);
if (lsr & UART_LSR_TEMT && iir & UART_IIR_NO_INT)
up->bugs |= UART_BUG_TXEN;
This works fine for other 8250 ports, but, on 8250-emulated SoL port, the
chip is a little lazy to down UART_IIR_NO_INT at UART_IIR register.
Due to that, UART_BUG_TXEN is sometimes enabled. However, as TX IRQ keeps
working, and the TX polling is now enabled, the driver miss-interprets the
IRQ received later, hanging up the machine until a key is pressed at the
serial console.
This is the 6 version of this patch. Previous versions were trying to
introduce a large enough delay between serial_outp and serial_in(up,
UART_IIR), but not taking forever. However, the needed delay couldn't be
safely determined.
At the experimental tests, a delay of 1us solves most of the cases, but
still hangs sometimes. Increasing the delay to 5us was better, but still
doesn't solve. A very high delay of 50 ms seemed to work every time.
However, poking around with delays and pray for it to be enough doesn't
seem to be a good approach, even for a quirk.
So, instead of playing with random large arbitrary delays, let's just
disable UART_BUG_TXEN for all SoL ports.
[akpm@linux-foundation.org: fix warnings]
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Cc: Alan Cox <alan@lxorguk.ukuu.org.uk>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This adds more documentation of the lowlevel API to avoid future bugs.
Signed-off-by: Michael Buesch <mb@bu3sch.de>
Acked-by: David Brownell <dbrownell@users.sourceforge.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
kzfree() is a wrapper for kfree() that additionally zeroes the underlying
memory before releasing it to the slab allocator.
Currently there is code which memset()s the memory region of an object
before releasing it back to the slab allocator to make sure
security-sensitive data are really zeroed out after use.
These callsites can then just use kzfree() which saves some code, makes
users greppable and allows for a stupid destructor that isn't necessarily
aware of the actual object size.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Matt Mackall <mpm@selenic.com>
Acked-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patch adds NETLINK_BROADCAST_ERROR which is a netlink
socket option that the listener can set to make netlink_broadcast()
return errors in the delivery to the caller. This option is useful
if the caller of netlink_broadcast() do something with the result
of the message delivery, like in ctnetlink where it drops a network
packet if the event delivery failed, this is used to enable reliable
logging and state-synchronization. If this socket option is not set,
netlink_broadcast() only reports ESRCH errors and silently ignore
ENOBUFS errors, which is what most netlink_broadcast() callers
should do.
This socket option is based on a suggestion from Patrick McHardy.
Patrick McHardy can exchange this patch for a beer from me ;).
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Acked-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
