1) Remove an explicit memset(.., 0, ...) to a variable allocated with
kzalloc (i.e. 'dest').
2) Allocate 'src' with kmalloc instead of kzalloc as all elements of the
'src' buffer are initialized in a 'for(...)' loop just after.
3) remove useless 'sizeof(u8)', which always returns 1, when computing the
size of the memory to be allocated.
Signed-off-by: Christophe Jaillet <christophe.jaillet@wanadoo.fr>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
'ack' is currently a simple integer that flags whether or not a client is done
touching fields in the given descriptor. It is effectively just a single bit
of information. Converting this to a flags parameter allows the other bits to
be put to use to control completion actions, like dma-unmap, and capture
results, like xor-zero-sum == 0.
Changes are one of:
1/ convert all open-coded ->ack manipulations to use async_tx_ack
and async_tx_test_ack.
2/ set the ack bit at prep time where possible
3/ make drivers store the flags at prep time
4/ add flags to the device_prep_dma_interrupt prototype
Acked-by: Maciej Sosnowski <maciej.sosnowski@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
DMA drivers no longer need to be notified of dependency submission
events as async_tx_run_dependencies and async_tx_channel_switch will
handle the scheduling and execution of dependent operations.
[sfr@canb.auug.org.au: extend this for fsldma]
Acked-by: Shannon Nelson <shannon.nelson@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Shrink struct dma_async_tx_descriptor and introduce
async_tx_channel_switch to properly inject a channel switch interrupt in
the descriptor stream. This simplifies the locking model as drivers no
longer need to handle dma_async_tx_descriptor.lock.
Acked-by: Shannon Nelson <shannon.nelson@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Split MPC83xx EOCDI event from MPC85xx EOLNI event, which is
also need to update cookie and start the next transfer.
The DMA channel irq handler function code is refined.
The patch is tested on MPC8377MDS board.
Signed-off-by: Zhang Wei <wei.zhang@freescale.com>
Signed-off-by; Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Always enabling the fsl_dma_self_test() to ensure the DMA controller
should works well after the driver probed.
Signed-off-by: Zhang Wei <wei.zhang@freescale.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Documentation/powerpc/booting-without-of.txt specifies the
compatiables we should bind to for this driver (elo, eloplus).
Use these instead of the extremely specific 'mpc8540' and 'mpc8349'
compatiables.
Acked-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
a) every bitwise declaration will give a unique type; use typedefs.
b) no need to bother with the stuff pointed to by iomem pointers,
unless it's accessed directly. noderef will force us to use helpers
anyway.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The DMA_INTERRUPT async_tx is a NULL transfer, thus the BCR(count register)
is 0. When the transfer started with a byte count of zero, the DMA
controller will triger a PE(programming error) event and halt, not a normal
interrupt. I add special codes for PE event and DMA_INTERRUPT
async_tx testing.
Signed-off-by: Zhang Wei <wei.zhang@freescale.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
__FUNCTION__ is gcc-specific, use __func__
Signed-off-by: Harvey Harrison <harvey.harrison@gmail.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
The patch 'fsldma: do not cleanup descriptors in hardirq context'
(commit 222ccf9ab8) removed descriptors
cleanup function to tasklet but the completed cookie do not updated.
Thus, the DMA controller will get lots of duplicated transfer
interrupts. Just make a completed cookie update in interrupt handler.
And keep other cleanup jobs in tasklet function.
Tested-by: Sebastian Siewior <bigeasy@linutronix.de>
Signed-off-by: Zhang Wei <wei.zhang@freescale.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
This is a bug that I assigned DMA_INTERRUPT capability to fsldma
but missing device_prep_dma_interrupt function. For a bug in
dmaengine.c the driver passed BUG_ON() checking. The patch fixes it.
Signed-off-by: Zhang Wei <wei.zhang@freescale.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
The device->device_prep_dma_interrupt function is used by
DMA_INTERRUPT capability, not DMA_ZERO_SUM.
Signed-off-by: Zhang Wei <wei.zhang@freescale.com>
Acked-by: Maciej Sosnowski <maciej.sosnowski@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
There are warning messages reported by Stephen Rothwell with
ARCH=powerpc allmodconfig build:
drivers/dma/fsldma.c: In function 'fsl_dma_prep_memcpy':
drivers/dma/fsldma.c:439: warning: comparison of distinct pointer types
lacks a cast
drivers/dma/fsldma.c: In function 'fsl_chan_xfer_ld_queue':
drivers/dma/fsldma.c:584: warning: format '%016llx' expects type 'long long
unsigned int', but argument 4 has type 'dma_addr_t'
drivers/dma/fsldma.c: In function 'fsl_dma_chan_do_interrupt':
drivers/dma/fsldma.c:668: warning: format '%x' expects type 'unsigned int',
but argument 5 has type 'dma_addr_t'
drivers/dma/fsldma.c:684: warning: format '%016llx' expects type 'long long
unsigned int', but argument 4 has type 'dma_addr_t'
drivers/dma/fsldma.c:684: warning: format '%016llx' expects type 'long long
unsigned int', but argument 5 has type 'dma_addr_t'
drivers/dma/fsldma.c:701: warning: format '%02x' expects type 'unsigned
int', but argument 4 has type 'dma_addr_t'
drivers/dma/fsldma.c: In function 'fsl_dma_self_test':
drivers/dma/fsldma.c:840: warning: format '%d' expects type 'int', but
argument 5 has type 'size_t'
drivers/dma/fsldma.c: In function 'of_fsl_dma_probe':
drivers/dma/fsldma.c:1010: warning: format '%08x' expects type 'unsigned
int', but argument 5 has type 'resource_size_t'
This patch fixed the above warning messages.
Signed-off-by: Zhang Wei <wei.zhang@freescale.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Initialize 'ack' to zero in case the descriptor has been recycled.
Prevents "kernel BUG at crypto/async_tx/async_xor.c:185!"
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Acked-by: Shannon Nelson <shannon.nelson@intel.com>
Cc: stable@kernel.org
"Cleaning" descriptors involves calling pending callbacks and clients
assume that their callback will only ever happen in softirq context.
Delay cleanup to the tasklet.
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Acked-by: Zhang Wei <wei.zhang@freescale.com>
The driver implements DMA engine API for Freescale MPC85xx DMA controller,
which could be used by devices in the silicon. The driver supports the
Basic mode of Freescale MPC85xx DMA controller. The MPC85xx processors
supported include MPC8540/60, MPC8555, MPC8548, MPC8641 and so on.
The MPC83xx(MPC8349, MPC8360) are also supported.
[kamalesh@linux.vnet.ibm.com: build fix]
[dan.j.williams@intel.com: merge mm fixes, rebase on async_tx-2.6.25]
Signed-off-by: Zhang Wei <wei.zhang@freescale.com>
Signed-off-by: Ebony Zhu <ebony.zhu@freescale.com>
Acked-by: Kumar Gala <galak@gate.crashing.org>
Cc: Shannon Nelson <shannon.nelson@intel.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Pass a full set of flags to drivers' per-operation 'prep' routines.
Currently the only flag passed is DMA_PREP_INTERRUPT. The expectation is
that arch-specific async_tx_find_channel() implementations can exploit this
capability to find the best channel for an operation.
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Acked-by: Shannon Nelson <shannon.nelson@intel.com>
Reviewed-by: Haavard Skinnemoen <hskinnemoen@atmel.com>
The tx_set_src and tx_set_dest methods were originally implemented to allow
an array of addresses to be passed down from async_xor to the dmaengine
driver while minimizing stack overhead. Removing these methods allows
drivers to have all transaction parameters available at 'prep' time, saves
two function pointers in struct dma_async_tx_descriptor, and reduces the
number of indirect branches..
A consequence of moving this data to the 'prep' routine is that
multi-source routines like async_xor need temporary storage to convert an
array of linear addresses into an array of dma addresses. In order to keep
the same stack footprint of the previous implementation the input array is
reused as storage for the dma addresses. This requires that
sizeof(dma_addr_t) be less than or equal to sizeof(void *). As a
consequence CONFIG_DMADEVICES now depends on !CONFIG_HIGHMEM64G. It also
requires that drivers be able to make descriptor resources available when
the 'prep' routine is polled.
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Acked-by: Shannon Nelson <shannon.nelson@intel.com>
these three list_head are all local variables, but can also use LIST_HEAD.
Signed-off-by: Denis Cheng <crquan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Tony Jones <tonyj@suse.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Cc: Shannon Nelson <shannon.nelson@intel.com>
Cc: Kay Sievers <kay.sievers@vrfy.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
We can't use the device in a dev_err() after a kzalloc failure or after the
kfree, so simplify it to the pdev that was originally passed in.
Cc: Eric Sesterhenn <snakebyte@gmx.de>
Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
A few fixups from Andrew's code comments.
- removed "static inline" forward-declares
- changed use of min() to min_t()
- removed some unnecessary NULL initializations
- removed a couple of BUG() calls
Fixes this:
drivers/dma/ioat_dma.c: In function `ioat1_tx_submit':
drivers/dma/ioat_dma.c:177: sorry, unimplemented: inlining failed in call to '__ioat1_dma_memcpy_issue_pending': function body not available
drivers/dma/ioat_dma.c:268: sorry, unimplemented: called from here
Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
Cc: "Williams, Dan J" <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patch corrects recently changed (and now invalid) Kconfig descriptions
for the DMA engine framework:
- Non-Intel(R) hardware also has DMA engines;
- DMA is used for more than memcpy and RAID offloading.
In fact, on most platforms memcpy and RAID aren't factors, and DMA
exists so that peripherals can transfer data to/from memory while
the CPU does other work.
Signed-off-by: Haavard Skinnemoen <hskinnemoen@atmel.com>
Signed-off-by: David Brownell <dbrownell@users.sourceforge.net>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Add support for version 2 of the ioatdma device. This device handles
the descriptor chain and DCA services slightly differently:
- Instead of moving the dma descriptors between a busy and an idle chain,
this new version uses a single circular chain so that we don't have
rewrite the next_descriptor pointers as we add new requests, and the
device doesn't need to re-read the last descriptor.
- The new device has the DCA tags defined internally instead of needing
them defined statically.
Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
Cc: "Williams, Dan J" <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When a DMA device is unregistered, its reference count is decremented twice
for each channel: Once dma_class_dev_release() and once in
dma_chan_cleanup(). This may result in the DMA device driver's remove()
function completing before all channels have been cleaned up, causing lots
of use-after-free fun.
Fix it by incrementing the device's reference count twice for each
channel during registration.
[dan.j.williams@intel.com: kill unnecessary client refcounting]
Signed-off-by: Haavard Skinnemoen <hskinnemoen@atmel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
No reason I can think of of making them default y Most people don't have
the hardware and with default y they just pollute lots of configs during
make oldconfig.
Signed-off-by: Andi Kleen <ak@suse.de>
Acked-by: Jeff Garzik <jeff@garzik.org>
Acked-by: "Nelson, Shannon" <shannon.nelson@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The async_tx interface includes a completion callback. This adds support
for using that callback, including using interrupts on completion.
[akpm@linux-foundation.org: various fixes]
Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The change to the async_tx interface cost this driver some performance by
spreading the descriptor setup across several functions, including multiple
passes over the new descriptor chain. Here we bring the work back into one
primary function and only do one pass.
[akpm@linux-foundation.org: cleanups, uninline]
Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Make better use of dev_err(), and catch an error where the transaction
creation might fail.
Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Don't start ioat_dca if ioat_dma didn't start, and then stop ioat_dca
before stopping ioat_dma. Since the ioat_dma side does the pci device
work, This takes care of ioat_dca trying to use a bad device reference.
Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Reorder the pci release actions
Letting go of the resources in the right order helps get rid of
occasional kernel complaints.
Fix the pci_driver object name [Randy Dunlap]
Rename the struct pci_driver data so that false section mismatch
warnings won't be produced.
Cc: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Adrian Bunk points out that "unsafe" was used to mark modules touched by
the deprecated MOD_INC_USE_COUNT interface, which has long gone. It's time
to remove the member from the module structure, as well.
If you want a module which can't unload, don't register an exit function.
(Vlad Yasevich says SCTP is now safe to unload, so just remove the
__unsafe there).
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Shannon Nelson <shannon.nelson@intel.com>
Acked-by: Dan Williams <dan.j.williams@intel.com>
Acked-by: Vlad Yasevich <vladislav.yasevich@hp.com>
Cc: Sridhar Samudrala <sri@us.ibm.com>
Cc: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Add code to connect to the DCA driver and provide cpu tags for use by
drivers that would like to use Direct Cache Access hints.
[Adrian Bunk] Several Kconfig cleanup items
[Andrew Morten, Chris Leech] Fix for using cpu_physical_id() even when
built for uni-processor
Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Add support for MSI and MSI-X interrupt handling, including the ability
to choose the desired interrupt method.
Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
Acked-by: David S. Miller <davem@davemloft.net>
[bunk@kernel.org: drivers/dma/ioat_dma.c: make 3 functions static]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Split the general PCI startup from the DMA handling code in order to
prepare for adding support for DCA services and future versions of the
ioatdma device.
[Rusty Russell] Removal of __unsafe() usage.
Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Take care of a bunch of little code nits in ioatdma files
Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Rename the ioatdma.c file in preparation for splitting into multiple files,
which will allow for easier adding new functionality.
Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Add device ids for new revs of the Intel I/OAT DMA engine
Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Now that the DMA engine has a multi-client interface, fix the ioatdma
driver to play along. At the same time, remove a couple of unnecessary
reads and writes.
Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Al Viro pointed out that dma_memcpy_to_kernel_iovec() really was
unreachable and thus unused. The code originally was there to support
in-kernel dma needs, but since it remains unused, we'll pull it out.
Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Continuing the work started in 411f0f3edc ...
This enables code with a dma path, that compiles away, to build without
requiring additional code factoring. It also prevents code that calls
dma_alloc_coherent and dma_free_coherent from linking whereas previously
the code would hit a BUG() at run time. Finally, it allows archs that set
!HAS_DMA to delete their asm/dma-mapping.h file.
Cc: Cornelia Huck <cornelia.huck@de.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: John W. Linville <linville@tuxdriver.com>
Cc: Kyle McMartin <kyle@parisc-linux.org>
Cc: James Bottomley <James.Bottomley@SteelEye.com>
Cc: Tejun Heo <htejun@gmail.com>
Cc: Jeff Garzik <jeff@garzik.org>
Cc: <geert@linux-m68k.org>
Cc: <zippel@linux-m68k.org>
Cc: <spyro@f2s.com>
Cc: <ysato@users.sourceforge.jp>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: John Magolan <john.magolan@unisys.com>
Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
The Intel(R) IOP series of i/o processors integrate an Xscale core with
raid acceleration engines. The capabilities per platform are:
iop219:
(2) copy engines
iop321:
(2) copy engines
(1) xor and block fill engine
iop33x:
(2) copy and crc32c engines
(1) xor, xor zero sum, pq, pq zero sum, and block fill engine
iop34x (iop13xx):
(2) copy, crc32c, xor, xor zero sum, and block fill engines
(1) copy, crc32c, xor, xor zero sum, pq, pq zero sum, and block fill engine
The driver supports the features of the async_tx api:
* asynchronous notification of operation completion
* implicit (interupt triggered) handling of inter-channel transaction
dependencies
The driver adapts to the platform it is running by two methods.
1/ #include <asm/arch/adma.h> which defines the hardware specific
iop_chan_* and iop_desc_* routines as a series of static inline
functions
2/ The private platform data attached to the platform_device defines the
capabilities of the channels
20070626: Callbacks are run in a tasklet. Given the recent discussion on
LKML about killing tasklets in favor of workqueues I did a quick conversion
of the driver. Raid5 resync performance dropped from 50MB/s to 30MB/s, so
the tasklet implementation remains until a generic softirq interface is
available.
Changelog:
* fixed a slot allocation bug in do_iop13xx_adma_xor that caused too few
slots to be requested eventually leading to data corruption
* enabled the slot allocation routine to attempt to free slots before
returning -ENOMEM
* switched the cleanup routine to solely use the software chain and the
status register to determine if a descriptor is complete. This is
necessary to support other IOP engines that do not have status writeback
capability
* make the driver iop generic
* modified the allocation routines to understand allocating a group of
slots for a single operation
* added a null xor initialization operation for the xor only channel on
iop3xx
* support xor operations on buffers larger than the hardware maximum
* split the do_* routines into separate prep, src/dest set, submit stages
* added async_tx support (dependent operations initiation at cleanup time)
* simplified group handling
* added interrupt support (callbacks via tasklets)
* brought the pending depth inline with ioat (i.e. 4 descriptors)
* drop dma mapping methods, suggested by Chris Leech
* don't use inline in C files, Adrian Bunk
* remove static tasklet declarations
* make iop_adma_alloc_slots easier to read and remove chances for a
corrupted descriptor chain
* fix locking bug in iop_adma_alloc_chan_resources, Benjamin Herrenschmidt
* convert capabilities over to dma_cap_mask_t
* fixup sparse warnings
* add descriptor flush before iop_chan_enable
* checkpatch.pl fixes
* gpl v2 only correction
* move set_src, set_dest, submit to async_tx methods
* move group_list and phys to async_tx
Cc: Russell King <rmk@arm.linux.org.uk>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
The async_tx api provides methods for describing a chain of asynchronous
bulk memory transfers/transforms with support for inter-transactional
dependencies. It is implemented as a dmaengine client that smooths over
the details of different hardware offload engine implementations. Code
that is written to the api can optimize for asynchronous operation and the
api will fit the chain of operations to the available offload resources.
I imagine that any piece of ADMA hardware would register with the
'async_*' subsystem, and a call to async_X would be routed as
appropriate, or be run in-line. - Neil Brown
async_tx exploits the capabilities of struct dma_async_tx_descriptor to
provide an api of the following general format:
struct dma_async_tx_descriptor *
async_<operation>(..., struct dma_async_tx_descriptor *depend_tx,
dma_async_tx_callback cb_fn, void *cb_param)
{
struct dma_chan *chan = async_tx_find_channel(depend_tx, <operation>);
struct dma_device *device = chan ? chan->device : NULL;
int int_en = cb_fn ? 1 : 0;
struct dma_async_tx_descriptor *tx = device ?
device->device_prep_dma_<operation>(chan, len, int_en) : NULL;
if (tx) { /* run <operation> asynchronously */
...
tx->tx_set_dest(addr, tx, index);
...
tx->tx_set_src(addr, tx, index);
...
async_tx_submit(chan, tx, flags, depend_tx, cb_fn, cb_param);
} else { /* run <operation> synchronously */
...
<operation>
...
async_tx_sync_epilog(flags, depend_tx, cb_fn, cb_param);
}
return tx;
}
async_tx_find_channel() returns a capable channel from its pool. The
channel pool is organized as a per-cpu array of channel pointers. The
async_tx_rebalance() routine is tasked with managing these arrays. In the
uniprocessor case async_tx_rebalance() tries to spread responsibility
evenly over channels of similar capabilities. For example if there are two
copy+xor channels, one will handle copy operations and the other will
handle xor. In the SMP case async_tx_rebalance() attempts to spread the
operations evenly over the cpus, e.g. cpu0 gets copy channel0 and xor
channel0 while cpu1 gets copy channel 1 and xor channel 1. When a
dependency is specified async_tx_find_channel defaults to keeping the
operation on the same channel. A xor->copy->xor chain will stay on one
channel if it supports both operation types, otherwise the transaction will
transition between a copy and a xor resource.
Currently the raid5 implementation in the MD raid456 driver has been
converted to the async_tx api. A driver for the offload engines on the
Intel Xscale series of I/O processors, iop-adma, is provided in a later
commit. With the iop-adma driver and async_tx, raid456 is able to offload
copy, xor, and xor-zero-sum operations to hardware engines.
On iop342 tiobench showed higher throughput for sequential writes (20 - 30%
improvement) and sequential reads to a degraded array (40 - 55%
improvement). For the other cases performance was roughly equal, +/- a few
percentage points. On a x86-smp platform the performance of the async_tx
implementation (in synchronous mode) was also +/- a few percentage points
of the original implementation. According to 'top' on iop342 CPU
utilization drops from ~50% to ~15% during a 'resync' while the speed
according to /proc/mdstat doubles from ~25 MB/s to ~50 MB/s.
The tiobench command line used for testing was: tiobench --size 2048
--block 4096 --block 131072 --dir /mnt/raid --numruns 5
* iop342 had 1GB of memory available
Details:
* if CONFIG_DMA_ENGINE=n the asynchronous path is compiled away by making
async_tx_find_channel a static inline routine that always returns NULL
* when a callback is specified for a given transaction an interrupt will
fire at operation completion time and the callback will occur in a
tasklet. if the the channel does not support interrupts then a live
polling wait will be performed
* the api is written as a dmaengine client that requests all available
channels
* In support of dependencies the api implicitly schedules channel-switch
interrupts. The interrupt triggers the cleanup tasklet which causes
pending operations to be scheduled on the next channel
* Xor engines treat an xor destination address differently than a software
xor routine. To the software routine the destination address is an implied
source, whereas engines treat it as a write-only destination. This patch
modifies the xor_blocks routine to take a an explicit destination address
to mirror the hardware.
Changelog:
* fixed a leftover debug print
* don't allow callbacks in async_interrupt_cond
* fixed xor_block changes
* fixed usage of ASYNC_TX_XOR_DROP_DEST
* drop dma mapping methods, suggested by Chris Leech
* printk warning fixups from Andrew Morton
* don't use inline in C files, Adrian Bunk
* select the API when MD is enabled
* BUG_ON xor source counts <= 1
* implicitly handle hardware concerns like channel switching and
interrupts, Neil Brown
* remove the per operation type list, and distribute operation capabilities
evenly amongst the available channels
* simplify async_tx_find_channel to optimize the fast path
* introduce the channel_table_initialized flag to prevent early calls to
the api
* reorganize the code to mimic crypto
* include mm.h as not all archs include it in dma-mapping.h
* make the Kconfig options non-user visible, Adrian Bunk
* move async_tx under crypto since it is meant as 'core' functionality, and
the two may share algorithms in the future
* move large inline functions into c files
* checkpatch.pl fixes
* gpl v2 only correction
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Acked-By: NeilBrown <neilb@suse.de>
The current implementation assumes that a channel will only be used by one
client at a time. In order to enable channel sharing the dmaengine core is
changed to a model where clients subscribe to channel-available-events.
Instead of tracking how many channels a client wants and how many it has
received the core just broadcasts the available channels and lets the
clients optionally take a reference. The core learns about the clients'
needs at dma_event_callback time.
In support of multiple operation types, clients can specify a capability
mask to only be notified of channels that satisfy a certain set of
capabilities.
Changelog:
* removed DMA_TX_ARRAY_INIT, no longer needed
* dma_client_chan_free -> dma_chan_release: switch to global reference
counting only at device unregistration time, before it was also happening
at client unregistration time
* clients now return dma_state_client to dmaengine (ack, dup, nak)
* checkpatch.pl fixes
* fixup merge with git-ioat
Cc: Chris Leech <christopher.leech@intel.com>
Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Acked-by: David S. Miller <davem@davemloft.net>
Christophe Jaillet