Commit Graph

35834 Commits

Author SHA1 Message Date
Johan Hedberg
a250e048a7 Bluetooth: Add helpers for src/dst bdaddr type conversion
The current bdaddr_type() usage in l2cap_core.c is a bit funny in that
it's always passed a hci_conn + a hci_conn member. Because of this only
the hci_conn is really needed. Since the second parameter is always
either hcon->src_type or hcon->dst type this patch adds two helper
functions for each purpose: bdaddr_src_type() and bdaddr_dst_type().

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
2015-01-15 16:54:14 +01:00
Marcel Holtmann
162a3bac8d Bluetooth: Bind the SMP channel registration to management power state
When the controller gets powered on via the management interface, then
register the supported SMP channels. There is no point in registering
these channels earlier since it is not know what identity address the
controller is going to operate with.

When powering down a controller unregister all SMP channels. This is
required since a powered down controller is allowed to change its
identity address.

In addition the SMP channels are only available when the controller
is powered via the management interface. When using legacy ioctl, then
Bluetooth Low Energy is not supported and registering kernel side SMP
integration may actually cause confusion.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
2015-01-15 12:54:31 +02:00
Marcel Holtmann
7e7ec44564 Bluetooth: Don't register any SMP channel if LE is not supported
When LE features are not supported, then do not bother registering any
kind of SMP channel.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
2015-01-15 12:54:30 +02:00
Marcel Holtmann
157029ba30 Bluetooth: Fix LE SMP channel source address and source address type
The source address and source address type of the LE SMP channel can
either be the public address of the controller or the static random
address configured by the host.

Right now the public address is used for the LE SMP channel and
obviously that is not correct if the controller operates with the
configured static random address.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
2015-01-15 12:54:30 +02:00
Marcel Holtmann
111e4bccd1 Bluetooth: Fix issue with switching BR/EDR back on when disabled
For dual-mode controllers it is possible to disable BR/EDR and operate
as LE single mode controllers with a static random address. If that is
the case, then refuse switching BR/EDR back on after the controller has
been powered.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
2015-01-15 10:27:47 +02:00
Marcel Holtmann
eeb5a067d1 Bluetooth: Show device address type for L2CAP debugfs entries
The devices address types are BR/EDR Public, LE Public and LE Random and
any of these three is valid for L2CAP connections. So show the correct
type in the debugfs list.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
2015-01-15 10:23:47 +02:00
Jukka Rissanen
7b2ed60ed4 Bluetooth: 6lowpan: Remove PSM setting code
Removing PSM setting debugfs interface as the IPSP has a well
defined PSM value that should be used.

The patch introduces enable flag that can be used to toggle
6lowpan on/off.

Signed-off-by: Jukka Rissanen <jukka.rissanen@linux.intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
2015-01-14 22:48:13 +01:00
Johan Hedberg
e12af489b9 Bluetooth: Fix valid Identity Address check
According to the Bluetooth core specification valid identity addresses
are either Public Device Addresses or Static Random Addresses. IRKs
received with any other type of address should be discarded since we
cannot assume to know the permanent identity of the peer device.

This patch fixes a missing check for the Identity Address when receiving
the Identity Address Information SMP PDU.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Cc: stable@vger.kernel.org # 3.17+
2015-01-14 22:48:06 +01:00
Gowtham Anandha Babu
36c269cecf Bluetooth: Remove dead code
Variable 'controller' is assigned a value that is never used.
Identified by cppcheck tool.

Signed-off-by: Gowtham Anandha Babu <gowtham.ab@samsung.com>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
2015-01-14 11:16:17 +02:00
Marcel Holtmann
5ced24644b Bluetooth: Use %llu for printing duration details of selftests
The duration variable for the selftests is unsigned long long and with
that use %llu instead of %lld when printing the results.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
2015-01-14 10:02:45 +02:00
Marcel Holtmann
36f260ceff Bluetooth: Move Delete Stored Link Key to 4th phase of initialization
This moves the execution of Delete Stored Link Key command to the
hci_init4_req phase. No actual code has been changed. The command
is just executed at a later stage of the initialization.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
2015-01-14 10:02:21 +02:00
Marcel Holtmann
a936612036 Bluetooth: Process result of HCI Delete Stored Link Key command
When the HCI Delete Stored Link Key command completes, then update the
value of current stored keys in hci_dev structure.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
2015-01-12 21:56:06 +02:00
Marcel Holtmann
48ce62c4fa Bluetooth: Read stored link key information when powering on controller
The information about max stored link keys and current stored link keys
should be read at controller initialization. So issue HCI Read Stored
Link Key command with BDADDR_ANY and read_all flag set to 0x01 to
retrieve this information.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
2015-01-12 21:54:48 +02:00
Marcel Holtmann
c2f0f97927 Bluetooth: Handle command complete event for HCI Read Stored Link Keys
When the HCI Read Stored Link Keys command completes it gives useful
information of the current stored keys and maximum keys a controller
can actually store. So process this event and store these information
in hci_dev structure.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
2015-01-12 21:54:16 +02:00
Marcel Holtmann
41e91e71f6 Bluetooth: Replace send_monitor_event with queue_monitor_skb
The send_monitor_event function is essentially the same as the newly
introduced queue_monitor_skb. So instead of having duplicated code,
replace send_monitor_event with queue_monitor_skb.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
2015-01-12 11:26:09 +02:00
Marcel Holtmann
d7f72f6195 Bluetooth: Create generic queue_monitor_skb helper function
The hci_send_to_monitor function contains generic code for queueing the
packet into the receive queue of every monitor client. To avoid code
duplication, create a generic queue_monitor_skb function to interate
over all monitor sockets.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
2015-01-12 11:26:07 +02:00
Marcel Holtmann
2b531294b0 Bluetooth: Simplify packet copy in hci_send_to_monitor function
Within the monitor functionality, the global atomic variable called
monitor_promisc ensures that no memory allocation happend when there
is actually no client listening. This means it is safe to just create
a copy of the skb since it is guaranteed that at least one client
exists. No extra checks needed.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
2015-01-12 11:26:04 +02:00
Marcel Holtmann
15762fa772 Bluetooth: Add BUILD_BUG_ON for size of struct sockaddr_sco
This adds an extra check for ensuring that the size of sockaddr_sco
does not grow larger than sockaddr.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
2015-01-12 11:24:24 +02:00
Marcel Holtmann
74b3fb8d0d Bluetooth: Add BUILD_BUG_ON for size of struct sockaddr_rc
This adds an extra check for ensuring that the size of sockaddr_rc
does not grow larger than sockaddr.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
2015-01-12 11:24:21 +02:00
Marcel Holtmann
dd6255588a Bluetooth: Add BUILD_BUG_ON for size of struct sockaddr_l2
This adds an extra check for ensuring that the size of sockaddr_l2
does not grow larger than sockaddr.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
2015-01-12 11:24:19 +02:00
Marcel Holtmann
b0a8e282b5 Bluetooth: Add BUILD_BUG_ON for size of struct sockaddr_hci
This adds an extra check for ensuring that the size of sockaddr_hci
does not grow larger than sockaddr.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
2015-01-12 11:24:16 +02:00
Marcel Holtmann
1904a853fa Bluetooth: Add opcode parameter to hci_req_complete_t callback
When hci_req_run() calls its provided complete function and one of the
HCI commands in the sequence fails, then provide the opcode of failing
command. In case of success HCI_OP_NOP is provided since all commands
completed.

This patch fixes the prototype of hci_req_complete_t and all its users.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
2015-01-12 11:16:31 +02:00
Alexander Aring
bc6efeeeb5 ieee802154: 6lowpan: fix Makefile entry
Since commit ea81ac2e70 ("ieee802154:
create 6lowpan sub-directory") we have a subdirectory for the ieee802154
6lowpan implementation. This commit also moves the Kconfig entry inside
of net/ieee802154/6lowpan/ and forgot to rename the Makefile entry from
obj-$(CONFIG_IEEE802154_6LOWPAN) to obj-y and handle the
obj-$(CONFIG_IEEE802154_6LOWPAN) inside the created 6lowpan directory.
This will occur that the ieee802154_6lowpan can't be build.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
2015-01-08 15:48:06 +01:00
Alexander Aring
52d84ffc54 ieee802154: 6lowpan: rename to core
This patch renames the 6lowpan_rtnl.c file to core.c. 6lowpan_rtnl.c
contains functionality to put all 802.15.4 6LoWPAN functionality
together.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
2015-01-08 07:25:59 +01:00
Alexander Aring
4dc315e267 ieee802154: 6lowpan: move transmit functionality
This patch moves all relevant transmit functionality into a separate tx.c
file. We can simple separate this functionality like we did it in mac802154.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
2015-01-08 07:25:59 +01:00
Alexander Aring
4662a0da54 ieee802154: 6lowpan: move receive functionality
This patch moves all relevant receive functionality into a separate rx.c
file. We can simple separate this functionality like we did it in mac802154.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
2015-01-08 07:25:59 +01:00
Alexander Aring
8691ee592c ieee802154: 6lowpan: rename internal header
This patch renames the internal header for af802154. This naming
convention is like ieee802154_i.h in mac802154 and avoids naming
confusing with the global af802154 header. Furthermore this header
contains more ieee802154 specific definitions.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
2015-01-08 07:25:59 +01:00
Alexander Aring
ea81ac2e70 ieee802154: create 6lowpan sub-directory
This patch creates an 6lowpan sub-directory inside ieee802154.
Additional we move all ieee802154 6lowpan relevant files into
this sub-directory instead of placing the 6lowpan related files
inside ieee802154.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
2015-01-08 07:25:59 +01:00
Marcel Holtmann
043ec9bf7b Bluetooth: Introduce HCI_QUIRK_FIXUP_INQUIRY_MODE option
The HCI_QUIRK_FIXUP_INQUIRY_MODE option allows to force Inquiry Result
with RSSI setting on controllers that do not indicate support for it,
but where it is known to be fully functional.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
2015-01-03 22:31:09 +02:00
Marcel Holtmann
04422da990 Bluetooth: Remove dead code for manufacturer inquiry mode quirks
There are some old Bluetooth modules from Silicon Wave and Broadcom
which support Inquiry Result with RSSI, but do not advertise it. The
core has quirks in the code to enable that inquiry mode. However as
it stands right now, that code is not even executed since entering
the function to determine which inquiry mode requires that the device
has the feature bit for Inquiry Result with RSSI set in the first
place. So this makes this dead code that hasn't work for a long
time.

In conclusion, just remove these extra quirks and simplify the setup
of the inquiry mode to be inline and with that a lot easier to read
and understand.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
2015-01-03 22:31:08 +02:00
Alexander Aring
36cf942adf mac802154: fix kbuild test robot warning
This patch fixs the following kbuild test robot warning:

coccinelle warnings: (new ones prefixed by >>)

>> net/mac802154/cfg.c:53:1-3: WARNING: PTR_ERR_OR_ZERO can be used

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
2015-01-03 01:51:51 +01:00
Alexander Aring
9dc52d49e2 ieee802154: handle config as menuconfig
This patch handles the IEEE802154 Kconfig entry as menuconfig.
Furthermore we move this entry out of "Network Options" and put it into
"Networking" where the other networking subsystems are. This requires a
menuconfig entry like all other networking subsystems.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
2015-01-03 01:49:24 +01:00
Alexander Aring
71e36b1b01 ieee802154: rename af_ieee802154.c to socket.c
This patch renames the "af_ieee802154.c" to "socket.c". This is just a
cleanup to have a short name for it which describes the implementationm
stuff more human understandable.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
2015-01-03 01:49:24 +01:00
Alexander Aring
df2f65de4b ieee802154: socket: fix checkpatch issue
This patch solves the following checkpatch issue:

CHECK: Comparison to NULL could be written "skb"
+		if (skb != NULL) {

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
2015-01-03 01:49:24 +01:00
Alexander Aring
78f821b648 ieee802154: socket: put handling into one file
This patch puts all related socket handling into one file. This is just
a cleanup to do all socket handling stuff inside of one implementation
file.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
2015-01-03 01:49:24 +01:00
Alexander Aring
79300e3a43 ieee802154: socket: change module name
This patch changes the module name of af_802154 to ieee802154_socket.
Just for keeping the name convention according to the 6LoWPAN module
ieee802154_6lowpan.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
2015-01-03 01:49:24 +01:00
Alexander Aring
955d7fc93e ieee802154: handle socket functionality as module
This patch makes the ieee802154 socket handling as module. Currently
this is part of ieee802154 module. It pointed out that ieee802154 module
has also two module_init/module_exit functions. One inside of core.c and
the other in af_ieee802154.c. This patch will also solve this issue by
handle the af_802154 as separate module.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
2015-01-03 01:49:23 +01:00
Marcel Holtmann
ec6cef9cd9 Bluetooth: Fix SMP channel registration for unconfigured controllers
When the Bluetooth controllers requires an unconfigured state (for
example when the BD_ADDR is missing), then it is important to try
to register the SMP channels when the controller transitions to the
configured state.

This also fixes an issue with the debugfs entires that are not present
for controllers that start out as unconfigured.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
2015-01-02 22:22:04 +01:00
Marcel Holtmann
203de21bf6 Bluetooth: Fix for a leftover debug of pairing credentials
One of the LE Secure Connections security credentials was still using
the BT_DBG instead of SMP_DBG.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
2015-01-02 22:22:04 +01:00
Marcel Holtmann
cb0d2faeb1 Bluetooth: Fix scope of sc_only_mode debugfs entry
The sc_only_mode debugfs entry is used to read the current state of the
Secure Connections Only mode. Before Bluetooth 4.2 this mode was only
for BR/EDR controllers and with that tight to the support Secure Simple
Pairing. Since Secure Connections is now available for BR/EDR and LE
this debugfs entry is no longer correctly place.

Move it to the common section and enable it when either BR/EDR Secure
Connections feature is supported or when the controller has LE support.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
2015-01-02 22:22:04 +01:00
Marcel Holtmann
05b3c3e790 Bluetooth: Remove no longer needed force_sc_support debugfs option
The force_sc_support debugfs option was introduced to easily work with
pre-production Bluetooth 4.1 silicon. This option is no longer needed
since controllers supporting BR/EDR Secure Connections feature are now
available.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
2015-01-02 22:22:04 +01:00
Marcel Holtmann
91389af67c Bluetooth: Remove broken force_lesc_support debugfs option
The force_lesc_support debugfs option never really worked. It has a race
condition between creating the debugfs entry and registering the L2CAP
fixed channel for BR/EDR SMP support.

Also this has been replaced with a working force_bredr_smp debugfs
switch that developers can use now.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
2015-01-02 22:22:03 +01:00
Marcel Holtmann
300acfdec9 Bluetooth: Introduce force_bredr_smp debugfs option for testing
Testing cross-transport pairing that starts on BR/EDR is only valid when
using a controller with BR/EDR Secure Connections. Devices will indicate
this by providing BR/EDR SMP fixed channel over L2CAP. To allow testing
of this feature on Bluetooth 4.0 controller or controllers without the
BR/EDR Secure Connections features, introduce a force_bredr_smp debugfs
option that allows faking the required AES connection.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
2015-01-02 22:22:03 +01:00
Florian Westphal
e8768f9715 net: skbuff: don't zero tc members when freeing skb
Not needed, only four cases:
 - kfree_skb (or one of its aliases).
   Don't need to zero, memory will be freed.
 - kfree_skb_partial and head was stolen:  memory will be freed.
 - skb_morph:  The skb header fields (including tc ones) will be
   copied over from the 'to-be-morphed' skb right after
   skb_release_head_state returns.
 - skb_segment:  Same as before, all the skb header
   fields are copied over from the original skb right away.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-02 16:04:29 -05:00
David S. Miller
6c032edc8a Merge branch 'for-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/bluetooth/bluetooth-next
Johan Hedberg say:

====================
pull request: bluetooth-next 2014-12-31

Here's the first batch of bluetooth patches for 3.20.

 - Cleanups & fixes to ieee802154  drivers
 - Fix synchronization of mgmt commands with respective HCI commands
 - Add self-tests for LE pairing crypto functionality
 - Remove 'BlueFritz!' specific handling from core using a new quirk flag
 - Public address configuration support for ath3012
 - Refactor debugfs support into a dedicated file
 - Initial support for LE Data Length Extension feature from Bluetooth 4.2

Please let me know if there are any issues pulling. Thanks.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-02 15:58:21 -05:00
Joe Stringer
a4c9ea5e8f geneve: Add Geneve GRO support
This results in an approximately 30% increase in throughput
when handling encapsulated bulk traffic.

Signed-off-by: Joe Stringer <joestringer@nicira.com>
Signed-off-by: Jesse Gross <jesse@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-02 15:46:41 -05:00
Jesse Gross
9b174d88c2 net: Add Transparent Ethernet Bridging GRO support.
Currently the only tunnel protocol that supports GRO with encapsulated
Ethernet is VXLAN. This pulls out the Ethernet code into a proper layer
so that it can be used by other tunnel protocols such as GRE and Geneve.

Signed-off-by: Jesse Gross <jesse@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-02 15:46:41 -05:00
Alexander Duyck
5405afd1a3 fib_trie: Add tracking value for suffix length
This change adds a tracking value for the maximum suffix length of all
prefixes stored in any given tnode.  With this value we can determine if we
need to backtrace or not based on if the suffix is greater than the pos
value.

By doing this we can reduce the CPU overhead for lookups in the local table
as many of the prefixes there are 32b long and have a suffix length of 0
meaning we can immediately backtrace to the root node without needing to
test any of the nodes between it and where we ended up.

Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-31 18:25:55 -05:00
Alexander Duyck
21d1f11db0 fib_trie: Remove checks for index >= tnode_child_length from tnode_get_child
For some reason the compiler doesn't seem to understand that when we are in
a loop that runs from tnode_child_length - 1 to 0 we don't expect the value
of tn->bits to change.  As such every call to tnode_get_child was rerunning
tnode_chile_length which ended up consuming quite a bit of space in the
resultant assembly code.

I have gone though and verified that in all cases where tnode_get_child
is used we are either winding though a fixed loop from tnode_child_length -
1 to 0, or are in a fastpath case where we are verifying the value by
either checking for any remaining bits after shifting index by bits and
testing for leaf, or by using tnode_child_length.

size net/ipv4/fib_trie.o
Before:
   text	   data	    bss	    dec	    hex	filename
  15506	    376	      8	  15890	   3e12	net/ipv4/fib_trie.o

After:
   text	   data	    bss	    dec	    hex	filename
  14827	    376	      8	  15211	   3b6b	net/ipv4/fib_trie.o

Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-31 18:25:55 -05:00
Alexander Duyck
12c081a5c8 fib_trie: inflate/halve nodes in a more RCU friendly way
This change pulls the node_set_parent functionality out of put_child_reorg
and instead leaves that to the function to take care of as well.  By doing
this we can fully construct the new cluster of tnodes and all of the
pointers out of it before we start routing pointers into it.

I am suspecting this will likely fix some concurency issues though I don't
have a good test to show as such.

Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-31 18:25:55 -05:00