Skip to content

K
Kernel

openeuler / Kernel
1 年多 前同步成功

通知 8
Star 0
Fork 0
K
Kernel
切换分支/标签
  1. 24 4月, 2015 2 次提交
  3. 23 4月, 2015 1 次提交
  5. 22 4月, 2015 7 次提交
    • J
      mac80211: allow segmentation offloads · 80616c0d
      由 Johannes Berg 提交于 
      Implement the necessary software segmentation on the normal
TX path so that fast-xmit can use segmentation offload if
the hardware (or driver) supports it.
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
      80616c0d
    • J
      mac80211: allow drivers to support S/G · 680a0dab
      由 Johannes Berg 提交于 
      If drivers want to support S/G (really just gather DMA on TX) then
we can now easily support this on the fast-xmit path since it just
needs to write to the ethernet header (and already has a check for
that being possible.)

However, disallow this on the regular TX path (which has to handle
fragmentation, software crypto, etc.) by calling skb_linearize().

Also allow the related HIGHDMA since that's not interesting to the
code in mac80211 at all anyway.
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
      680a0dab
    • J
      mac80211: allow checksum offload only in fast-xmit · 2d981fdd
      由 Johannes Berg 提交于 
      When we go through the complete TX processing, there are a number
of things like fragmentation and software crypto that require the
checksum to be calculated already.

In favour of maintainability, instead of adding the necessary call
to skb_checksum_help() in all the places that need it, just do it
once before the regular TX processing.

Right now this only affects the TI wlcore and QCA ath10k drivers
since they're the only ones using checksum offload. The previous
commits enabled fast-xmit for them in almost all cases.

For wlcore this even fixes a corner case: when a key fails to be
programmed to hardware software encryption gets used, encrypting
frames with a bad checksum.
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
      2d981fdd
    • J
      mac80211: extend fast-xmit to cover IBSS · 3ffd8840
      由 Johannes Berg 提交于 
      IBSS can be supported very easily since it uses the standard station
authorization state etc. so it just needs to be covered by the header
building switch statement.
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
      3ffd8840
    • J
      mac80211: extend fast-xmit for more ciphers · e495c247
      由 Johannes Berg 提交于 
      When crypto is offloaded then in some cases it's all handled
by the device, and in others only some space for the IV must
be reserved in the frame. Handle both of these cases in the
fast-xmit path, up to a limit of 18 bytes of space for IVs.
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
      e495c247
    • J
      mac80211: extend fast-xmit to driver fragmentation · 725b812c
      由 Johannes Berg 提交于 
      If the driver handles fragmentation then it wouldn't
be done in software so we can still use the fast-xmit
path in that case.
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
      725b812c
    • J
      mac80211: add TX fastpath · 17c18bf8
      由 Johannes Berg 提交于 
      In order to speed up mac80211's TX path, add the "fast-xmit" cache
that will cache the data frame 802.11 header and other data to be
able to build the frame more quickly. This cache is rebuilt when
external triggers imply changes, but a lot of the checks done per
packet today are simplified away to the check for the cache.

There's also a more detailed description in the code.
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
      17c18bf8
  7. 20 4月, 2015 2 次提交
    • J
      mac80211: lock rate control · 35c347ac
      由 Johannes Berg 提交于 
      Both minstrel (reported by Sven Eckelmann) and the iwlwifi rate
control aren't properly taking concurrency into account. It's
likely that the same is true for other rate control algorithms.

In the case of minstrel this manifests itself in crashes when an
update and other data access are run concurrently, for example
when the stations change bandwidth or similar. In iwlwifi, this
can cause firmware crashes.

Since fixing all rate control algorithms will be very difficult,
just provide locking for invocations. This protects the internal
data structures the algorithms maintain.

I've manipulated hostapd to test this, by having it change its
advertised bandwidth roughly ever 150ms. At the same time, I'm
running a flood ping between the client and the AP, which causes
this race of update vs. get_rate/status to easily happen on the
client. With this change, the system survives this test.
Reported-by: NSven Eckelmann <sven@open-mesh.com>
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
      35c347ac
    • B
      mac80211: introduce plink lock for plink fields · 48bf6bed
      由 Bob Copeland 提交于 
      The mesh plink code uses sta->lock to serialize access to the
plink state fields between the peer link state machine and the
peer link timer.  Some paths (e.g. those involving
mps_qos_null_tx()) unfortunately hold this spinlock across
frame tx, which is soon to be disallowed.  Add a new spinlock
just for plink access.
Signed-off-by: NBob Copeland <me@bobcopeland.com>
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
      48bf6bed
  9. 08 4月, 2015 1 次提交
  11. 07 4月, 2015 1 次提交
  13. 02 4月, 2015 10 次提交
  15. 01 4月, 2015 4 次提交
    • J
      mac80211: fix RX A-MPDU session reorder timer deletion · 788211d8
      由 Johannes Berg 提交于 
      There's an issue with the way the RX A-MPDU reorder timer is
deleted that can cause a kernel crash like this:

 * tid_rx is removed - call_rcu(ieee80211_free_tid_rx)
 * station is destroyed
 * reorder timer fires before ieee80211_free_tid_rx() runs,
   accessing the station, thus potentially crashing due to
   the use-after-free

The station deletion is protected by synchronize_net(), but
that isn't enough -- ieee80211_free_tid_rx() need not have
run when that returns (it deletes the timer.) We could use
rcu_barrier() instead of synchronize_net(), but that's much
more expensive.

Instead, to fix this, add a field tracking that the session
is being deleted. In this case, the only re-arming of the
timer happens with the reorder spinlock held, so make that
code not rearm it if the session is being deleted and also
delete the timer after setting that field. This ensures the
timer cannot fire after ___ieee80211_stop_rx_ba_session()
returns, which fixes the problem.

Cc: stable@vger.kernel.org
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
      788211d8
    • T
      mac80211: enhance readability of Minstrel-HTs rc_stats output · 9c00bb72
      由 Thomas Huehn 提交于 
      This patch restructures the rc_stats debugfs table of Minstrel-HT in
order to achieve better human readability. A new layout of the
statistics and a new header is added. In addition to the old layout
there are two new columns of information added:
idx	- representing the rate index of each rate in mac80211 which
	  can be used to set specific rates as fixed rate via debugfs
airtime	- the tx-time in micro seconds that a 1200 Byte packet
	  takes to be transmitted over the air at the given rate

The old layout of rc_stats:

type           rate      tpt eprob *prob ret  *ok(*cum)        ok(      cum)
HT20/LGI       MCS0      5.6 100.0 100.0   1    0(   0)         1(        1)
HT20/LGI   B   MCS1     10.5 100.0 100.0   0    0(   0)         1(        1)
HT20/LGI  A    MCS2     14.8 100.0 100.0   0    0(   0)         1(        1)
...

is changed into this new layout:

            best   ________rate______    __statistics__    ________last_______    ______sum-of________
mode guard #  rate  [name   idx airtime]  [ ø(tp) ø(prob)]  [prob.|retry|suc|att]  [#success | #attempts]
HT20  LGI  1         MCS0     0    1480      0.0      0.0      0.0   1     0 0             0   0
HT20  LGI  1     B   MCS1     1     740     10.5    100.0    100.0   0     0 0             1   1
HT20  LGI  1    A    MCS2     2     496     14.8    100.0    100.0   0     0 0             1   1
...
Signed-off-by: NThomas Huehn <thomas@net.t-labs.tu-berlin.de>
Signed-off-by: NStefan Venz <ikstream86@gmail.com>
Acked-by: NFelix Fietkau <nbd@openwrt.org>
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
      9c00bb72
    • T
      mac80211: enhance readability of Minstrels rc_stats output · e161f7f6
      由 Thomas Huehn 提交于 
      This patch restructures the rc_stats debugfs table of Minstrel in
order to achieve better human readability. A new layout of the
statistics and a new header is added. In addition to the old layout
there are two new columns of information added:
idx	- representing the rate index of each rate in mac80211 which
	  can be used to set specific rates as fixed rate via debugfs
airtime - the tx-time in micro seconds that a 1200 Byte packet
	  takes to be transmitted over the air at the given rate

The old layout of rc_stats:

    rate      tpt  eprob *prob ret  *ok(*cum)        ok(      cum)
 DP 1          0.9  93.5 100.0   1    0(   0)         2(        2)
    2          0.4  40.0 100.0   0    0(   0)         4(        10)
    5.5        0.0   0.0   0.0   0    0(   0)         0(        0)
...

is changed into this new layout:

best   _______rate_____    __statistics__    ________last_______    ______sum-of________
rate  [name idx tx-time]  [ ø(tp) ø(prob)]  [prob.|retry|suc|att]  [#success | #attempts]
 DP   1     0     9738      0.9    93.5     100.0   1     1 1             2   2
      2     1     4922      0.4    40.0     100.0   1     0 0             4   10
      5.5   2     1858      0.0     0.0       0.0   2     0 0             0   0
...
Signed-off-by: NThomas Huehn <thomas@net.t-labs.tu-berlin.de>
Signed-off-by: NStefan Venz <ikstream86@gmail.com>
Acked-by: NFelix Fietkau <nbd@openwrt.org>
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
      e161f7f6
    • J
      mac80211: use rhashtable for station table · 7bedd0cf
      由 Johannes Berg 提交于 
      We currently have a hand-rolled table with 256 entries and are
using the last byte of the MAC address as the hash. This hash
is obviously very fast, but collisions are easily created and
we waste a lot of space in the common case of just connecting
as a client to an AP where we just have a single station. The
other common case of an AP is also suboptimal due to the size
of the hash table and the ease of causing collisions.

Convert all of this to use rhashtable with jhash, which gives
us the advantage of a far better hash function (with random
perturbation to avoid hash collision attacks) and of course
that the hash table grows and shrinks dynamically with chain
length, improving both cases above.

Use a specialised hash function (using jhash, but with fixed
length) to achieve better compiler optimisation as suggested
by Sergey Ryazanov.
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
      7bedd0cf
  17. 30 3月, 2015 12 次提交