linux-toradex.git/drivers/dma/Kconfig, branch v3.4.85

net_dma: mark broken

2014-01-08T17:42:11+00:00

commit 77873803363c9e831fc1d1e6895c084279090c22 upstream.

net_dma can cause data to be copied to a stale mapping if a
copy-on-write fault occurs during dma.  The application sees missing
data.

The following trace is triggered by modifying the kernel to WARN if it
ever triggers copy-on-write on a page that is undergoing dma:

 WARNING: CPU: 24 PID: 2529 at lib/dma-debug.c:485 debug_dma_assert_idle+0xd2/0x120()
 ioatdma 0000:00:04.0: DMA-API: cpu touching an active dma mapped page [pfn=0x16bcd9]
 Modules linked in: iTCO_wdt iTCO_vendor_support ioatdma lpc_ich pcspkr dca
 CPU: 24 PID: 2529 Comm: linbug Tainted: G        W    3.13.0-rc1+ #353
  00000000000001e5 ffff88016f45f688 ffffffff81751041 ffff88017ab0ef70
  ffff88016f45f6d8 ffff88016f45f6c8 ffffffff8104ed9c ffffffff810f3646
  ffff8801768f4840 0000000000000282 ffff88016f6cca10 00007fa2bb699349
 Call Trace:
  [] dump_stack+0x46/0x58
  [] warn_slowpath_common+0x8c/0xc0
  [] ? ftrace_pid_func+0x26/0x30
  [] warn_slowpath_fmt+0x46/0x50
  [] debug_dma_assert_idle+0xd2/0x120
  [] do_wp_page+0xd0/0x790
  [] handle_mm_fault+0x51c/0xde0
  [] ? copy_user_enhanced_fast_string+0x9/0x20
  [] __do_page_fault+0x19c/0x530
  [] ? _raw_spin_lock_bh+0x16/0x40
  [] ? trace_clock_local+0x9/0x10
  [] ? rb_reserve_next_event+0x64/0x310
  [] ? ioat2_dma_prep_memcpy_lock+0x60/0x130 [ioatdma]
  [] do_page_fault+0xe/0x10
  [] page_fault+0x22/0x30
  [] ? __kfree_skb+0x51/0xd0
  [] ? copy_user_enhanced_fast_string+0x9/0x20
  [] ? memcpy_toiovec+0x52/0xa0
  [] skb_copy_datagram_iovec+0x5f/0x2a0
  [] tcp_rcv_established+0x674/0x7f0
  [] tcp_v4_do_rcv+0x2e5/0x4a0
  [..]
 ---[ end trace e30e3b01191b7617 ]---
 Mapped at:
  [] debug_dma_map_page+0xb9/0x160
  [] dma_async_memcpy_pg_to_pg+0x127/0x210
  [] dma_memcpy_pg_to_iovec+0x119/0x1f0
  [] dma_skb_copy_datagram_iovec+0x11c/0x2b0
  [] tcp_rcv_established+0x74a/0x7f0:

...the problem is that the receive path falls back to cpu-copy in
several locations and this trace is just one of the areas.  A few
options were considered to fix this:

1/ sync all dma whenever a cpu copy branch is taken

2/ modify the page fault handler to hold off while dma is in-flight

Option 1 adds yet more cpu overhead to an "offload" that struggles to compete
with cpu-copy.  Option 2 adds checks for behavior that is already documented as
broken when using get_user_pages().  At a minimum a debug mode is warranted to
catch and flag these violations of the dma-api vs get_user_pages().

Thanks to David for his reproducer.

Cc: Dave Jiang 
Cc: Vinod Koul 
Cc: Alexander Duyck 
Reported-by: David Whipple 
Acked-by: David S. Miller 
Signed-off-by: Dan Williams 
Signed-off-by: Greg Kroah-Hartman

dmaengine: Kconfig: fix Atmel at_hdmac entry

2012-04-17T14:29:41+00:00

Remove SoC dependency and make it generic for every Atmel ARM AT91. That will
allow to select this driver for newer chips. Keep dependency on AT91 because of
the use of an header file located in include/mach directory.
Modify the comment to reflect this.

Signed-off-by: Nicolas Ferre 
Acked-by: Vinod Koul

Merge branch 'next' of git://git.infradead.org/users/vkoul/slave-dma

2012-03-29T22:34:57+00:00

Pull slave-dmaengine update from Vinod Koul:
 "This includes the cookie cleanup by Russell, the addition of context
  parameter for dmaengine APIs, more arm dmaengine driver cleanup by
  moving code to dmaengine, this time for imx by Javier and pl330 by
  Boojin along with the usual driver fixes."

Fix up some fairly trivial conflicts with various other cleanups.

* 'next' of git://git.infradead.org/users/vkoul/slave-dma: (67 commits)
  dmaengine: imx: fix the build failure on x86_64
  dmaengine: i.MX: Fix merge of cookie branch.
  dmaengine: i.MX: Add support for interleaved transfers.
  dmaengine: imx-dma: use 'dev_dbg' and 'dev_warn' for messages.
  dmaengine: imx-dma: remove 'imx_dmav1_baseaddr' and 'dma_clk'.
  dmaengine: imx-dma: remove unused arg of imxdma_sg_next.
  dmaengine: imx-dma: remove internal structure.
  dmaengine: imx-dma: remove 'resbytes' field of 'internal' structure.
  dmaengine: imx-dma: remove 'in_use' field of 'internal' structure.
  dmaengine: imx-dma: remove sg member from internal structure.
  dmaengine: imx-dma: remove 'imxdma_setup_sg_hw' function.
  dmaengine: imx-dma: remove 'imxdma_config_channel_hw' function.
  dmaengine: imx-dma: remove 'imxdma_setup_mem2mem_hw' function.
  dmaengine: imx-dma: remove dma_mode member of internal structure.
  dmaengine: imx-dma: remove data member from internal structure.
  dmaengine: imx-dma: merge old dma-v1.c with imx-dma.c
  dmaengine: at_hdmac: add slave config operation
  dmaengine: add context parameter to prep_slave_sg and prep_dma_cyclic
  dmaengine/dma_slave: introduce inline wrappers
  dma: imx-sdma: Treat firmware messages as warnings instead of erros
  ...

dmaengine: imx: fix the build failure on x86_64

2012-03-27T16:16:21+00:00

commit 6bd081277ea0 "dmaengine: imx-dma: merge old dma-v1.c with
imx-dma.c" removed the dependency in config for the imx dma driver,
whereas it should depend on ARCH_MXS

Signed-off-by: Vinod Koul

dmaengine: imx-dma: merge old dma-v1.c with imx-dma.c

2012-03-26T06:01:29+00:00

It is mainly a simple merge changing the prefix of some
functions to fit the imx-dma namings.

As there are no users of the old dma-v1.c api we can safely
remove this file.

Signed-off-by: Javier Martin 
Acked-by: Sascha Hauer 
Signed-off-by: Vinod Koul

DMA: PL330: Merge PL330 driver into drivers/dma/

2012-03-08T12:29:28+00:00

Currently there were two part of DMAC PL330 driver for
support old styled s3c-pl330 which has been merged into
drivers/dma/pl330.c driver. Actually, there is no reason
to separate them now.

Basically this patch merges arch/arm/common/pl330.c into
drivers/dma/pl330.c driver and removes useless exported
symbol, externed function and so on.

The newer pl330 driver tested on SMDKV310 and SMDK4212 boards

Cc: Jassi Brar 
Cc: Russell King 
Acked-by: Linus Walleij 
Acked-by: Vinod Koul 
Signed-off-by: Boojin Kim 
Signed-off-by: Kukjin Kim 
Acked-by: Jassi Brar 
Signed-off-by: Vinod Koul

DMA: sa11x0: add SA-11x0 DMA driver

2012-03-07T11:32:21+00:00

Add support for the SA-11x0 DMA driver, which replaces the private
API version in arch/arm/mach-sa1100/dma.c.

We model this as a set of virtual DMA channels, one for each request
signal, and assign the virtual DMA channel to a physical DMA channel
when there is work to be done.  This allows DMA users to claim their
channels, and hold them while not in use, without affecting the
availability of the physical channels.

Another advantage over this approach, compared to the private version,
is that a channel can be reconfigured on the fly without having to
release and re-request it - which for the IrDA driver, allows us to
use DMA for SIR mode transmit without eating up three physical
channels.  As IrDA is half-duplex, we actually only need one physical
channel, and this architecture allows us to achieve that.

Signed-off-by: Russell King

dmaengine: add CSR SiRFprimaII DMAC driver

2011-11-18T06:55:22+00:00

Cc: Jassi Brar 
Cc: Arnd Bergmann 
Cc: Linus Walleij 
Signed-off-by: Rongjun Ying 
Signed-off-by: Barry Song 
[fixed direction enums and cyclic api based on changes
 already merged]
Signed-off-by: Vinod Koul

pch_dma: Support new device LAPIS Semiconductor ML7831 IOH

2011-11-17T08:57:41+00:00

ML7831 is companion chip for Intel Atom E6xx series.

Signed-off-by: Tomoya MORINAGA 
Signed-off-by: Vinod Koul

pch_dma: Change company name OKI SEMICONDUCTOR to LAPIS Semiconductor

2011-11-17T08:57:41+00:00

On October 1 in 2011,
OKI SEMICONDUCTOR Co., Ltd. changed the company name in to LAPIS Semiconductor
Co., Ltd.

Signed-off-by: Tomoya MORINAGA 
Signed-off-by: Vinod Koul