This adds a memory barrier to ensure the writes to the ring memory
are committed before the DMA ring pointer is updated.
We do a similar thing on the TX side already.
Signed-off-by: Michael Buesch <m@bues.ch>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
gcc 4.6.0 warnings for b43:
CC [M] drivers/net/wireless/b43/lo.o
drivers/net/wireless/b43/lo.c: In function ‘lo_measure_gain_values’:
drivers/net/wireless/b43/lo.c:304:7: warning: variable ‘trsw_rx’ set but not used [-Wunused-but-set-variable]
CC [M] drivers/net/wireless/b43/dma.o
drivers/net/wireless/b43/dma.c: In function ‘free_all_descbuffers’:
drivers/net/wireless/b43/dma.c:760:30: warning: variable ‘desc’ set but not used [-Wunused-but-set-variable]
drivers/net/wireless/b43/dma.c: In function ‘b43_dma_handle_txstatus’:
drivers/net/wireless/b43/dma.c:1391:30: warning: variable ‘desc’ set but not used [-Wunused-but-set-variable]
Signed-off-by: Larry Finger <Larry.Finger@lwfinger.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
We free name "dev" for something generic (like dev abstraction layer).
Additionaly code is cleaner now, especially magic dev->dev-dev chains.
Signed-off-by: Rafał Miłecki <zajec5@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Cc: Stefano Brivio <stefano.brivio@polimi.it>
Cc: John W. Linville <linville@tuxdriver.com>
Acked-by: Michael Buesch <mb@bu3sch.de>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Larry Finger <Larry.Finger@lwfinger.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Use kmemdup when some other buffer is immediately copied into the
allocated region.
A simplified version of the semantic patch that makes this change is as
follows: (http://coccinelle.lip6.fr/)
// <smpl>
@@
expression from,to,size,flag;
statement S;
@@
- to = \(kmalloc\|kzalloc\)(size,flag);
+ to = kmemdup(from,size,flag);
if (to==NULL || ...) S
- memcpy(to, from, size);
// </smpl>
Signed-off-by: Julia Lawall <julia@diku.dk>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
get_tx_stats() will be removed from mac80211.
Compile-tested only.
Cc: Stefano Brivio <stefano.brivio@polimi.it>
Cc: Michael Buesch <mb@bu3sch.de>
Cc: Larry Finger <Larry.Finger@lwfinger.net>
Signed-off-by: Kalle Valo <kalle.valo@iki.fi>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
If userencounter the "Fatal DMA Problem" with a BCM43XX device, and
still wish to use b43 as the driver, their only option is to rebuild
the kernel with CONFIG_B43_FORCE_PIO. This patch removes this option and
allows PIO mode to be selected with a load-time parameter for the module.
Note that the configuration variable CONFIG_B43_PIO is also removed.
Once the DMA problem with the BCM4312 devices is solved, this patch will
likely be reverted.
Signed-off-by: Larry Finger <Larry.Finger@lwfinger.net>
Tested-by: John Daiker <daikerjohn@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
This rewrites the error handling policies in the TX status handler.
It tries to be error-tolerant as in "try hard to not crash the machine".
It won't recover from errors (that are bugs in the firmware or driver),
because that's impossible. However, it will return a more or less useful
error message and bail out. It also tries hard to use rate-limited messages
to not flood the syslog in case of a failure.
Signed-off-by: Michael Buesch <mb@bu3sch.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Enforce all device constraints on the descriptor memory region.
There are several constraints on the descriptor memory, as documented
in the specification. The current code does not enforce them and/or
incorrectly enforces them.
Those constraints are:
- The address limitations on 30/32bit engines, that also apply to
the skbs.
- The 4k alignment requirement on 30/32bit engines.
- The 8k alignment requirement on 64bit engines.
Signed-off-by: Michael Buesch <mb@bu3sch.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Do not mess with the original skb, but allocate an independent bouncebuffer.
This protects against bad interference with mac80211's assumptions about
the skb (which already caused bugs).
Signed-off-by: Michael Buesch <mb@bu3sch.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
b43 allocates a bouncebuffer, if the supplied TX skb is in an invalid
memory range for DMA.
However, this is broken in that it fails to copy over some metadata to the
new skb.
This patch fixes three problems:
* Failure to adjust the ieee80211_tx_info pointer to the new buffer.
This results in a kmemcheck warning.
* Failure to copy the skb cb, which contains ieee80211_tx_info, to the new skb.
This results in breakage of various TX-status postprocessing (Rate control).
* Failure to transfer the queue mapping.
This results in the wrong queue being stopped on saturation and can result in queue overflow.
Signed-off-by: Michael Buesch <mb@bu3sch.de>
Tested-by: Christian Casteyde <casteyde.christian@free.fr>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
This removes the DMA/PIO queue locks. Locking is handled by
wl->mutex now.
Signed-off-by: Michael Buesch <mb@bu3sch.de>
Tested-by: Larry Finger <Larry.Finger@lwfinger.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Use a threaded IRQ handler to allow locking the mutex and
sleeping while executing an interrupt.
This removes usage of the irq_lock spinlock, but introduces
a new hardirq_lock, which is _only_ used for the PCI/SSB lowlevel
hard-irq handler. Sleeping busses (SDIO) will use mutex instead.
Signed-off-by: Michael Buesch <mb@bu3sch.de>
Tested-by: Larry Finger <Larry.Finger@lwfinger.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
This add hardware tkip for b43.
Signed-off-by: Gregor Kowski <gregor.kowski@gmail.com>
Acked-by: Michael Buesch <mb@bu3sch.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
As shown in http://thread.gmane.org/gmane.linux.kernel.wireless.general/36497,
mac80211 has a bug that allows a call to the TX routine after the queues have
been stopped. This situation will only occur under extreme stress. Although
b43 does not crash when this condition occurs, it does generate a WARN_ON and
also logs a queue overrun message. This patch recognizes b43 is not at fault
and logs a message only when the most verbose debugging mode is enabled. In
the unlikely event that the queue is not stopped when the DMA queue becomes
full, then a warning is issued.
During testing of this patch with one output stream running repeated tcpperf
writes and a second running a flood ping, this routine was entered with
the DMA ring stopped about once per hour. The condition where the DMA queue is
full but the ring has not been stopped has never been seen by me.
Signed-off-by: Larry Finger <Larry.Finger@lwfinger.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Add automagic feature flags, so the firmware can tell the driver
about supported features and the driver can switch features on/off as
needed.
Signed-off-by: Michael Buesch <mb@bu3sch.de>
Signed-off-by: Stefan Lippers-Hollmann <s.l-h@gmx.de>
Tested-by: Stefan Lippers-Hollmann <s.l-h@gmx.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
The RX buffer poison needs to be refreshed, if we recycle an RX buffer,
because it might be (partially) overwritten by some DMA operations.
Cc: stable@kernel.org
Cc: Francesco Gringoli <francesco.gringoli@ing.unibs.it>
Signed-off-by: Michael Buesch <mb@bu3sch.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
This patch adds poisoning and sanity checking to the RX DMA buffers.
This is used for protection against buggy hardware/firmware that raises
RX interrupts without doing an actual DMA transfer.
This mechanism protects against rare "bad packets" (due to uninitialized skb data)
and rare kernel crashes due to uninitialized RX headers.
The poison is selected to not match on valid frames and to be cheap for checking.
The poison check mechanism _might_ trigger incorrectly, if we are voluntarily
receiving frames with bad PLCP headers. However, this is nonfatal, because the
chance of such a match is basically zero and in case it happens it just results
in dropping the packet.
Bad-PLCP RX defaults to off, and you should leave it off unless you want to listen
to the latest news broadcasted by your microwave oven.
This patch also moves the initialization of the RX-header "length" field in front of
the mapping of the DMA buffer. The CPU should not touch the buffer after we mapped it.
Cc: stable@kernel.org
Reported-by: Francesco Gringoli <francesco.gringoli@ing.unibs.it>
Signed-off-by: Michael Buesch <mb@bu3sch.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Replace all DMA_30BIT_MASK macro with DMA_BIT_MASK(30)
Signed-off-by: Yang Hongyang<yanghy@cn.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Replace all DMA_32BIT_MASK macro with DMA_BIT_MASK(32)
Signed-off-by: Yang Hongyang<yanghy@cn.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Replace all DMA_64BIT_MASK macro with DMA_BIT_MASK(64)
Signed-off-by: Yang Hongyang<yanghy@cn.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This changes the RX handler to pass more status flags to mac80211.
It also changes part of the drop policy, if bad frames were requested. (Note that
currently mac80211 will throw a WARN_ON in that case. But nothing bad will happen).
This also removes some obsolete unused timestamping code.
Signed-off-by: Michael Buesch <mb@bu3sch.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Keeping this one simple.
Changing a few "foo * bar" to "foo *bar"
Removes 22 checkpatch.pl errors, with no introduced warnings.
Signed-off-by: John Daiker <daikerjohn@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
This adds a compiletime assertion for a recently introduced
assumption on the slot counts.
The tx header cache handling code assumes that the TX slot count
can be divided evenly by the number of TX slots per frame.
Signed-off-by: Michael Buesch <mb@bu3sch.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
In the old days we used one slot per frame. But when we changed that to 2,
we didn't raise the overall slot count. Which resulted in an effective
division of two to the number of slots.
Double the number of TX slots, so we have an effective hardware queue
of 128 frames per QoS queue.
Also optimize the TX header cache handling. We don't need a cached TX header
for slots that will never carry an actual header.
So we reduce the memory consumption of the cache by 50%.
So as a net result we end up with more or less the same memory usage before
and after this patch (except a few tiny meta structures), but have twice
the number of TX slots available.
Signed-off-by: Michael Buesch <mb@bu3sch.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
This fixes hidden bugs in the size handling of the DMA buffers.
This sets the RX buffer size to the theoretical max packet size and
fixes passing of the size values to the device (must not subtract the header offset).
These bugs are hidden and don't actually trigger due to the magic +100
offset for the buffer size.
Signed-off-by: Michael Buesch <mb@bu3sch.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Move the DMA stop sanity check up a few lines, so it's actually
theoretically possible to trigger. (But it still shouldn't trigger, of course).
Signed-off-by: Michael Buesch <mb@bu3sch.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
So after the previous changes we were still unhappy with how
convoluted the API is and decided to make things simpler for
everybody. This completely changes the rate control API, now
taking into account 802.11n with MCS rates and more control,
most drivers don't support that though.
Signed-off-by: Felix Fietkau <nbd@openwrt.org>
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
This is a rewrite of the DMA API for SSB devices.
This is needed, because the old (non-existing) "API" made too many bad
assumptions on the API of the host-bus (PCI).
This introduces an almost complete SSB-DMA-API that maps to the lowlevel
bus-API based on the bustype.
Signed-off-by: Michael Buesch <mb@bu3sch.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
This fixes a possible NULL pointer dereference in an error path of the
DMA allocation error checking code. This is also necessary for a future
DMA API change that is on its way into the mainline kernel that adds
an additional dev parameter to dma_mapping_error().
This patch moves the whole struct b43_dmaring struct initialization
right before any DMA allocation operation.
Reported-by: Miles Lane <miles.lane@gmail.com>
Signed-off-by: Michael Buesch <mb@bu3sch.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
This patch updates mac80211 and drivers to be multi-queue aware and
use that instead of the internal queue mapping. Also does a number
of cleanups in various pieces of the code that fall out and reduces
internal mac80211 state size.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
This patch converts mac80211 and all drivers to have transmit
information and status in skb->cb rather than allocating extra
memory for it and copying all the data around. To make it fit,
a union is used where only data that is necessary for all steps
is kept outside of the union.
A number of fixes were done by Ivo, as well as the rt2x00 part
of this patch.
Signed-off-by: Ivo van Doorn <IvDoorn@gmail.com>
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
The callback takes a ieee80211_tx_queue_stats with a contained
array of ieee80211_tx_queue_stats_data, remove the former, rename
the latter to ieee80211_tx_queue_stats and make tx_stats() take
the array directly.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Some mainboards/CPUs don't allow DMA masks bigger than a certain limit.
Some VIA crap^h^h^h^hdevices have an upper limit of 0xFFFFFFFF. So in this
case a 64-bit b43 device would always fail to acquire the mask.
Implement a workaround to fallback to lower DMA mask, as we can always
also support a lower mask.
Signed-off-by: Michael Buesch <mb@bu3sch.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
This fixes DMA on architectures where DMA is nontrivial, like PPC64.
We must use the host-device's (PCI) struct device for any DMA
operation instead of the SSB device. For this we add a new
struct device pointer to the SSB device structure that will always
point to the right device for DMAing.
Without this patch b43 and b44 drivers won't work on complex-DMA
architectures, that for example need dev->archdata for DMA operations.
Signed-off-by: Michael Buesch <mb@bu3sch.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
This adds PIO support back (D'oh!) for PCMCIA devices.
This is a complete rewrite of the old PIO code. It does actually work
and we get reasonable performance out of it on a modern machine.
On a PowerBook G4 I get a few MBit for TX and a few more for RX.
So it doesn't work as well as DMA (of course), but it's a _lot_ faster
than the old PIO code (only got a few kBit with that).
The limiting factor is the host CPU speed. So it will generate 100%
CPU usage when the network interface is heavily loaded. A voluntary preemption
point in the RX path makes sure Desktop Latency isn't hurt.
PIO is needed for 16bit PCMCIA devices, as we really don't want to poke with
the braindead DMA mechanisms on PCMCIA sockets. Additionally, not all
PCMCIA sockets do actually support DMA in 16bit mode (mine doesn't).
Signed-off-by: Michael Buesch <mb@bu3sch.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
This adds messages for some DMA mapping failures.
These are useful for debugging DMA address problems, as they appear
on x86_64 machines with IOMMU enabled.
Signed-off-by: Michael Buesch <mb@bu3sch.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Rafał Miłecki