When queueing iso packets, the run time is dominated by the two
MMIO accesses that set the DMA context's wake bit.  Because most
drivers submit packets in batches, we can save much time by
removing all but the last wakeup.

The internal kernel API is changed to require a call to
fw_iso_context_queue_flush() after a batch of queued packets.
The user space API does not change, so one call to
FW_CDEV_IOC_QUEUE_ISO must specify multiple packets to take
advantage of this optimization.

In my measurements, this patch reduces the time needed to queue
fifty skip packets from userspace to one sixth on a 2.5 GHz CPU,
or to one third at 800 MHz.
Signed-off-by: NClemens Ladisch <clemens@ladisch.de>
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>

We do not need slab allocations anymore in order to satisfy
streaming DMA mapping constraints, thanks to commit da28947e
"firewire: ohci: avoid separate DMA mapping for small AT payloads".

(Besides, the slab-allocated buffers that firewire-core, firewire-sbp2,
and firedtv used to provide for 8-byte write and lock requests were
still not fully portable since they crossed cacheline boundaries or
shared a cacheline with unrelated CPU-accessed data.  snd-firewire-lib
got this aspect right by using an extra kmalloc/ kfree just for the
8-byte transaction buffer.)

This change replaces kmalloc'ed lock transaction scratch buffers in
firewire-core, firedtv, and snd-firewire-lib by local stack allocations.
Perhaps the most notable result of the change is simpler locking because
there is no need to serialize usages of preallocated per-device buffers
anymore.  Also, allocations and deallocations are simpler.
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>
Acked-by: NClemens Ladisch <clemens@ladisch.de>

Add a driver for two playback-only FireWire devices based on the OXFW970
chip.

v2: better AMDTP API abstraction; fix fw_unit leak; small fixes
v3: cache the iPCR value
v4: FireWave constraints; fix fw_device reference counting;
    fix PCR caching; small changes and fixes
v5: volume/mute support; fix crashing due to pcm stop races
v6: fix build; one-channel volume for LaCie
v7: use signed values to make volume (range checks) work; fix function
    block IDs for volume/mute; always use channel 0 for LaCie volume
Signed-off-by: NClemens Ladisch <clemens@ladisch.de>
Acked-by: NStefan Richter <stefanr@s5r6.in-berlin.de>
Tested-by: NJay Fenlason <fenlason@redhat.com>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

In manage_channel(), rename the variables "c" and "i" to the more
expressive "bit" and "channel".
Signed-off-by: NClemens Ladisch <clemens@ladisch.de>
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>

This adds the DMA context programming and userspace ABI for multichannel
reception, i.e. for listening on multiple channel numbers by means of a
single DMA context.

The use case is reception of more streams than there are IR DMA units
offered by the link layer.  This is already implemented by the older
ohci1394 + ieee1394 + raw1394 stack.  And as discussed recently on
linux1394-devel, this feature is occasionally used in practice.

The big drawbacks of this mode are that buffer layout and interrupt
generation necessarily differ from single-channel reception:  Headers
and trailers are not stripped from packets, packets are not aligned with
buffer chunks, interrupts are per buffer chunk, not per packet.

These drawbacks also cause a rather hefty code footprint to support this
rarely used OHCI-1394 feature.  (367 lines added, among them 94 lines of
added userspace ABI documentation.)

This implementation enforces that a multichannel reception context may
only listen to channels to which no single-channel context on the same
link layer is presently listening to.  OHCI-1394 would allow to overlay
single-channel contexts by the multi-channel context, but this would be
a departure from the present first-come-first-served policy of IR
context creation.

The implementation is heavily based on an earlier one by Jay Fenlason.
Thanks Jay.
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>

The present inline documentation of the fw_send_request() in-kernel API
refers to userland code that is not applicable to kernel drivers at all.
Reported-by: NBen Gamari <bgamari.foss@gmail.com>

While we are at fixing the whole documentation of fw_send_request(),
also improve the rest of firewire-core's kerneldoc comments:
  - Add a bit of text concerning fw_run_transaction()'s call parameters.
  - Append () to function names and tab-align parameter descriptions as
    suggested by the example in Documentation/kernel-doc-nano-HOWTO.txt.
  - Remove kerneldoc markers from comments on static functions.
  - Remove outdated parameter descriptions at build_tree().
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>

Returning -EIO for all errors would not allow clients to determine if
the resource allocation process itself failed, or if the resources are
not available.  (The latter information is needed by CMP to synchronize
restoring of overlayed connections after a bus reset.)
Signed-off-by: NClemens Ladisch <clemens@ladisch.de>
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>

If there is a permanent error condition when communicating with the IRM,
after the sixth error, the retry variable will be decremented to -1.
If, in this case, the bits in channels_mask are not yet exhausted, the
next channel is retried 2^32 times.

To fix this, check that retry is never decremented beyond zero.
Signed-off-by: NClemens Ladisch <clemens@ladisch.de>
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>

include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h

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: NTejun Heo <tj@kernel.org>
Guess-its-ok-by: NChristoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>

If the bandwidth allocation fails, the error must be returned in
*channel regardless of whether the channel allocation succeeded.
Checking for c >= 0 is not correct if no channel allocation was
requested, in which case this part of the code is reached with
c == -EINVAL.
Signed-off-by: NClemens Ladisch <clemens@ladisch.de>
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>

This fixes a regression due to post 2.6.30 commit "firewire: core: do
not DMA-map stack addresses" 6fdc0370.

As David Moore noted, a previously correct sizeof() expression became
wrong since the commit changed its argument from an array to a pointer.
This resulted in an oops in ohci_cancel_packet in the shared workqueue
thread's context when an isochronous resource was to be freed.
Reported-by: NJonathan Cameron <jic23@cam.ac.uk>
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>

The DMA mapping API cannot map on-stack addresses, as explained in
Documentation/DMA-mapping.txt.  Convert the two cases of on-stack packet
payload buffers in firewire-core (payload of lock requests in the bus
manager work and in iso resource management) to slab-allocated memory.

There are a number on-stack buffers for quadlet write or quadlet read
requests in firewire-core and firewire-sbp2.  These are harmless; they
are copied to/ from card driver internal DMA buffers since quadlet
payloads are inlined with packet headers.
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>

dmap_unmap_page() shall use the same direction as dma_map_page().
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>

Implement IPv4 over IEEE 1394 as per RFC 2734 for the newer firewire
stack.  This feature has only been present in the older ieee1394 stack
via the eth1394 driver.

Still to do:
  - fix ipv4_priv and ipv4_node lifetime logic
  - fix determination of speeds and max payloads
  - fix bus reset handling
  - fix unaligned memory accesses
  - fix coding style
  - further testing/ improvement of fragment reassembly
  - perhaps multicast support
Signed-off-by: NJay Fenlason <fenlason@redhat.com>
Signed-off-by: Stefan Richter <stefanr@s5r6.in-berlin.de> (rebased, copyright note, changelog)

The source files of firewire-core, firewire-ohci, firewire-sbp2, i.e.
 "drivers/firewire/fw-*.c"
are renamed to
 "drivers/firewire/core-*.c",
 "drivers/firewire/ohci.c",
 "drivers/firewire/sbp2.c".

The old fw- prefix was redundant to the directory name.  The new core-
prefix distinguishes the files according to which driver they belong to.

This change comes a little late, but still before further firewire
drivers are added as anticipated RSN.
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>

The three header files of firewire-core, i.e.
 "drivers/firewire/fw-device.h",
 "drivers/firewire/fw-topology.h",
 "drivers/firewire/fw-transaction.h",
are replaced by
 "drivers/firewire/core.h",
 "include/linux/firewire.h".

The latter includes everything which a firewire high-level driver (like
firewire-sbp2) needs besides linux/firewire-constants.h, while core.h
contains the rest which is needed by firewire-core itself and by low-
level drivers (card drivers) like firewire-ohci.

High-level drivers can now also reside outside of drivers/firewire
without having to add drivers/firewire to the header file search path in
makefiles.  At least the firedtv driver will be such a driver.

I also considered to spread the contents of core.h over several files,
one for each .c file where the respective implementation resides.  But
it turned out that most core .c files will end up including most of the
core .h files.  Also, the combined core.h isn't unreasonably big, and it
will lose more of its contents to linux/firewire.h anyway soon when more
firewire drivers are added.  (IP-over-1394, firedtv, and there are plans
for one or two more.)

Furthermore, fw-ohci.h is renamed to ohci.h.  The name of core.h and
ohci.h is chosen with regard to name changes of the .c files in a
follow-up change.
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>

Include required headers which were only indirectly included.
Remove unused includes and an unused constant.
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>

Standardize on  if (err)
                        handle_error;
           and  if (ret < 0)
                        handle_error;

Don't call a variable err if we store values in it which mean success.
Also, offset some return statements by a blank line since this how we do
it in drivers/firewire.
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>

Some fixes:
  - Remove stale documentation.
  - Fix a != vs. == thinko that got in the way of channel management.
  - Try bandwidth deallocation even if channel deallocation failed.

A simplification:
  - fw_cdev_allocate_iso_resource.channels is now ordered like
    libdc1394's dc1394_iso_allocate_channel() channels_allowed
    argument.

By the way, I looked closer at cards from NEC, TI, and VIA, and noticed
that they all don't implement IEEE 1394a behaviour which is meant to
deviate from IEEE 1212's notion of lock compare-swap.  This means that
we have to do two lock transactions instead of one in many cases where
one transaction would already succeed on a fully 1394a compliant IRM.
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>

Based on
    Date: Tue, 18 Nov 2008 11:41:27 -0500
    From: Jay Fenlason <fenlason@redhat.com>
    Subject: [Patch V4] Add ISO resource management support
with several changes to the ABI and implementation.  Only the part of
the ABI which enables auto-reallocation and auto-deallocation is
included here.

This implements ioctls for kernel-assisted allocation of isochronous
channels and isochronous bandwidth.  The benefits are:
  - The client does not have to have write access to the /dev/fw* device
    corresponding to the IRM.
  - The client does not have to perform reallocation after bus resets.
  - Channel and bandwidth are deallocated by the kernel if the file is
    closed before the client deallocated the resources.  Thus resources
    are released even if the client crashes.

It is anticipated that future in-kernel code (firewire-core IRM code;
the firewire port of firedtv), will use the fw-iso.c portions of this
code too.
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>
Tested-by: NDavid Moore <dcm@acm.org>

OHCI-1394 1.1 clause 10.4.3 says:  "If more than one IR DMA context
specifies receives for packets from the same isochronous channel, the
context destination for that channel's packets is undefined."

Any userspace client and in the future also kernelspace clients can
allocate IR DMA contexts for any channel.  We don't want them to
interfere with each other, hence it is preferable to return -EBUSY if
allocation of a second context for a channel is attempted.

Notes:
  - This limitation is OHCI-1394 specific, therefore its proper place of
    implementation is down in the low-level driver.

  - Since the <linux/firewire-cdev.h> ABI simply maps one userspace iso
    client context to one hardware iso context, this OHCI-1394
    limitation alas requires userspace to implement its own multiplexing
    of iso reception from the same channel and card to multiple clients
    when needed.

  - The limitation is independent of channel allocation at the IRM; the
    latter is really only important for the initiation of iso 
    transmission but not of iso reception.

  - We don't need to do the same for IT DMA because OHCI-1394 does not
    have any ties between IT contexts and channels.  Only the voluntary
    channel allocation protocol via the IRM, globally to the FireWire
    bus, can ensure proper isochronous transmit behaviour anyway.
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>

type
    function_name(parameters);

is nice to look at but was not used consistently.
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>

"ret" is the new "retval".
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>

Add per-device dma_mapping_ops support for CONFIG_X86_64 as POWER
architecture does:

This enables us to cleanly fix the Calgary IOMMU issue that some devices
are not behind the IOMMU (http://lkml.org/lkml/2008/5/8/423).

I think that per-device dma_mapping_ops support would be also helpful for
KVM people to support PCI passthrough but Andi thinks that this makes it
difficult to support the PCI passthrough (see the above thread).  So I
CC'ed this to KVM camp.  Comments are appreciated.

A pointer to dma_mapping_ops to struct dev_archdata is added.  If the
pointer is non NULL, DMA operations in asm/dma-mapping.h use it.  If it's
NULL, the system-wide dma_ops pointer is used as before.

If it's useful for KVM people, I plan to implement a mechanism to register
a hook called when a new pci (or dma capable) device is created (it works
with hot plugging).  It enables IOMMUs to set up an appropriate
dma_mapping_ops per device.

The major obstacle is that dma_mapping_error doesn't take a pointer to the
device unlike other DMA operations.  So x86 can't have dma_mapping_ops per
device.  Note all the POWER IOMMUs use the same dma_mapping_error function
so this is not a problem for POWER but x86 IOMMUs use different
dma_mapping_error functions.

The first patch adds the device argument to dma_mapping_error.  The patch
is trivial but large since it touches lots of drivers and dma-mapping.h in
all the architecture.

This patch:

dma_mapping_error() doesn't take a pointer to the device unlike other DMA
operations.  So we can't have dma_mapping_ops per device.

Note that POWER already has dma_mapping_ops per device but all the POWER
IOMMUs use the same dma_mapping_error function.  x86 IOMMUs use device
argument.

[akpm@linux-foundation.org: fix sge]
[akpm@linux-foundation.org: fix svc_rdma]
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: fix bnx2x]
[akpm@linux-foundation.org: fix s2io]
[akpm@linux-foundation.org: fix pasemi_mac]
[akpm@linux-foundation.org: fix sdhci]
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: fix sparc]
[akpm@linux-foundation.org: fix ibmvscsi]
Signed-off-by: NFUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Cc: Muli Ben-Yehuda <muli@il.ibm.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Avi Kivity <avi@qumranet.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This patch contains the following cleanups:
- #if 0 the following unused structs:
  - fw-transaction.c:fw_low_memory_region
  - fw-transaction.c:fw_private_region
  - fw-transaction.c:fw_csr_region
  - fw-transaction.c:fw_unit_space_region
- remove the following unused EXPORT_SYMBOL's:
  - fw-card.c:fw_core_add_descriptor
  - fw-card.c:fw_core_remove_descriptor
  - fw-iso.c:fw_iso_context_create
  - fw-iso.c:fw_iso_context_destroy
  - fw-iso.c:fw_iso_context_start
  - fw-iso.c:fw_iso_context_queue
  - fw-iso.c:fw_iso_context_stop
Signed-off-by: NAdrian Bunk <bunk@kernel.org>
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>

Drop filenames from file preamble, drop editor annotations and
use standard indent style for block comments.
Signed-off-by: NKristian Hoegsberg <krh@redhat.com>
Signed-off-by: Stefan Richter <stefanr@s5r6.in-berlin.de> (fixed typo)

Setting these at create_context time or start_iso time doesn't matter
much, but raw1394 sets them at start_iso time so that will be easier to
emulate this way.
Signed-off-by: NKristian Høgsberg <krh@redhat.com>
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>

Remove space before tab and trailing whitespace.
Unify indentation of goto target labels.
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>

Signed-off-by: NKristian Høgsberg <krh@redhat.com>
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>

We need the channel number as we queue up iso packets for transmission
so we can fill out the header correctly.
Signed-off-by: NKristian Høgsberg <krh@redhat.com>
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>

Signed-off-by: NKristian Høgsberg <krh@redhat.com>
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>

When the DMA is setup to not strip any headers, we need to use
the buffer fill descriptor instead of the dual buffer, since the
dual buffer descriptor must strip a non-zero number of header quadlets.
Signed-off-by: NKristian Høgsberg <krh@redhat.com>
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>

Signed-off-by: NKristian Høgsberg <krh@redhat.com>
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>

Signed-off-by: NKristian Høgsberg <krh@redhat.com>
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>

Signed-off-by: NKristian Høgsberg <krh@redhat.com>
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>

This patch splits out the iso buffer so we can initialize it at mmap
time with the size provided in the mmap call.  Furthermore, allocate
the backing pages using alloc_page to avoid setting up kernel side
virtual memory mappings for the pages.
Signed-off-by: NKristian Høgsberg <krh@redhat.com>
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>

Pointed out by Pete Zaitcev.
Signed-off-by: NKristian Høgsberg <krh@redhat.com>
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>

Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>
Signed-off-by: NKristian Høgsberg <krh@redhat.com>

Signed-off-by: NKristian Høgsberg <krh@redhat.com>
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>

Signed-off-by: NKristian Høgsberg <krh@redhat.com>
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>