| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
By default dma_map_sg syncs the mapped buffer to the device. But
buf_prepare expects a buffer syncs for the cpu and the buffer
will be synced to the device in the prepare memop.
The reverse is true for dma_unmap_sg, buf_finish and the finish
memop.
To prevent unnecessary syncs we ask dma_(un)map_sg to skip the
sync.
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Pawel Osciak <pawel@osciak.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
|
|
Add DMABUF export support to vb2-dma-sg.
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Acked-by: Pawel Osciak <pawel@osciak.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
|
|
Add support for importing dmabuf to videobuf2-dma-sg.
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Pawel Osciak <pawel@osciak.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
|
|
This moves dma_(un)map_sg to the get_userptr/put_userptr and alloc/put
memops of videobuf2-dma-sg.c and adds dma_sync_sg_for_device/cpu to the
prepare/finish memops.
Now that vb2-dma-sg will sync the buffers for you in the prepare/finish
memops we can drop that from the drivers that use dma-sg.
For the solo6x10 driver that was a bit more involved because it needs to
copy JPEG or MPEG headers to the buffer before returning it to userspace,
and that cannot be done in the old place since the buffer there is still
setup for DMA access, not for CPU access. However, the buf_finish
op is the ideal place to do this. By the time buf_finish is called
the buffer is available for CPU access, so copying to the buffer is fine.
[mchehab@osg.samsung.com: Fix a compilation breakage:
drivers/media/v4l2-core/videobuf2-dma-sg.c:150:19: error: 'struct vb2_dma_sg_buf' has no member named 'dma_sgt']
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Pawel Osciak <pawel@osciak.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
|
|
Require that dma-sg also uses an allocation context. This is in preparation
for adding prepare/finish memops to sync the memory between DMA and CPU.
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Pawel Osciak <pawel@osciak.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
|
|
This is needed for the next patch where the dma-sg alloc memop needs
to know the dma_dir.
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Pawel Osciak <pawel@osciak.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
|
|
The 'write' argument is very ambiguous. I first assumed that if it is 1,
then we're doing video output but instead it meant the reverse.
Since it is used to setup the dma_dir value anyway it is now replaced by
the correct dma_dir value which is unambiguous.
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Pawel Osciak <pawel@osciak.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
|
|
sg_alloc_table_from_pages() only allocates a sg_table, so it should just use
GFP_KERNEL, not gfp_flags. If gfp_flags contains __GFP_DMA32 then mm/sl[au]b.c
will call BUG_ON:
[ 358.027515] ------------[ cut here ]------------
[ 358.027546] kernel BUG at mm/slub.c:1416!
[ 358.027558] invalid opcode: 0000 [#1] PREEMPT SMP
[ 358.027576] Modules linked in: mt2131 s5h1409 tda8290 tuner cx25840 cx23885 btcx_risc altera_ci tda18271 altera_stapl videobuf2_dvb tveeprom cx2341x videobuf2_dma_sg dvb_core rc_core videobuf2_memops videobuf2_core nouveau zr36067 videocodec v4l2_common videodev media x86_pkg_temp_thermal cfbfillrect cfbimgblt cfbcopyarea ttm drm_kms_helper processor button isci
[ 358.027712] CPU: 19 PID: 3654 Comm: cat Not tainted 3.16.0-rc6-telek #167
[ 358.027723] Hardware name: ASUSTeK COMPUTER INC. Z9PE-D8 WS/Z9PE-D8 WS, BIOS 5404 02/10/2014
[ 358.027741] task: ffff880897c7d960 ti: ffff88089b4d4000 task.ti: ffff88089b4d4000
[ 358.027753] RIP: 0010:[<ffffffff81196040>] [<ffffffff81196040>] new_slab+0x280/0x320
[ 358.027776] RSP: 0018:ffff88089b4d7ae8 EFLAGS: 00010002
[ 358.027787] RAX: ffff880897c7d960 RBX: 0000000000000000 RCX: ffff88089b4d7b50
[ 358.027798] RDX: 00000000ffffffff RSI: 0000000000000004 RDI: ffff88089f803b00
[ 358.027809] RBP: ffff88089b4d7bb8 R08: 0000000000000000 R09: 0000000100400040
[ 358.027821] R10: 0000160000000000 R11: ffff88109bc02c40 R12: 0000000000000001
[ 358.027832] R13: ffff88089f8000c0 R14: ffff88089f803b00 R15: ffff8810bfcf4be0
[ 358.027845] FS: 00007f83fe5c0700(0000) GS:ffff8810bfce0000(0000) knlGS:0000000000000000
[ 358.027858] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 358.027868] CR2: 0000000001dfd568 CR3: 0000001097d5a000 CR4: 00000000000407e0
[ 358.027878] Stack:
[ 358.027885] ffffffff81198860 ffff8810bfcf4be0 ffff880897c7d960 0000000000001b00
[ 358.027905] ffff880897c7d960 0000000000000000 ffff8810bfcf4bf0 0000000000000000
[ 358.027924] 0000000000000000 0000000100000100 ffffffff813ef84a 00000004ffffffff
[ 358.027944] Call Trace:
[ 358.027956] [<ffffffff81198860>] ? __slab_alloc+0x400/0x4e0
[ 358.027973] [<ffffffff813ef84a>] ? sg_kmalloc+0x1a/0x30
[ 358.027985] [<ffffffff81198f17>] __kmalloc+0x127/0x150
[ 358.027997] [<ffffffff813ef84a>] ? sg_kmalloc+0x1a/0x30
[ 358.028009] [<ffffffff813ef84a>] sg_kmalloc+0x1a/0x30
[ 358.028023] [<ffffffff813eff84>] __sg_alloc_table+0x74/0x180
[ 358.028035] [<ffffffff813ef830>] ? sg_kfree+0x20/0x20
[ 358.028048] [<ffffffff813f00af>] sg_alloc_table+0x1f/0x60
[ 358.028061] [<ffffffff813f0174>] sg_alloc_table_from_pages+0x84/0x1f0
[ 358.028077] [<ffffffffa007c3f9>] vb2_dma_sg_alloc+0x159/0x230 [videobuf2_dma_sg]
[ 358.028095] [<ffffffffa003d55a>] __vb2_queue_alloc+0x10a/0x680 [videobuf2_core]
[ 358.028113] [<ffffffffa003e110>] __reqbufs.isra.14+0x220/0x3e0 [videobuf2_core]
[ 358.028130] [<ffffffffa003e79d>] __vb2_init_fileio+0xbd/0x380 [videobuf2_core]
[ 358.028147] [<ffffffffa003f563>] __vb2_perform_fileio+0x5b3/0x6e0 [videobuf2_core]
[ 358.028164] [<ffffffffa003f871>] vb2_fop_read+0xb1/0x100 [videobuf2_core]
[ 358.028184] [<ffffffffa06dd2e5>] v4l2_read+0x65/0xb0 [videodev]
[ 358.028198] [<ffffffff811a243f>] vfs_read+0x8f/0x170
[ 358.028210] [<ffffffff811a30a1>] SyS_read+0x41/0xb0
[ 358.028224] [<ffffffff818f02e9>] system_call_fastpath+0x16/0x1b
[ 358.028234] Code: 66 90 e9 dc fd ff ff 0f 1f 40 00 41 8b 4d 68 e9 d5 fe ff ff 0f 1f 80 00 00 00 00 f0 41 80 4d 00 40 e9 03 ff ff ff 0f 1f 44 00 00 <0f> 0b 66 0f 1f 44 00 00 44 89 c6 4c 89 45 d0 e8 0c 82 ff ff 48
[ 358.028415] RIP [<ffffffff81196040>] new_slab+0x280/0x320
[ 358.028432] RSP <ffff88089b4d7ae8>
[ 358.032208] ---[ end trace 6443240199c706e4 ]---
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Cc: stable@vger.kernel.org # for v3.13 and up
Acked-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
|
|
vb2_get_vma() copy the content of the vma to a new structure but set
some of its pointers to NULL.
One of this pointer is used by follow_pte() called by follow_pfn()
on io memory.
This can lead to a NULL pointer derreference.
The version of vma that has not been cleared must be used.
[ 406.143320] BUG: unable to handle kernel NULL pointer dereference at 0000000000000040
[ 406.143427] IP: [<ffffffff8115204c>] follow_pfn+0x2c/0x70
[ 406.143491] PGD 6c3f0067 PUD 6c3ef067 PMD 0
[ 406.143546] Oops: 0000 [#1] SMP
[ 406.143587] Modules linked in: qtec_mem qt5023_video qtec_testgen qtec_xform videobuf2_core gpio_xilinx videobuf2_vmalloc videobuf2_dma_sg qtec_cmosis videobuf2_memops qtec_pcie qtec_white fglrx(PO) qt5023 spi_xilinx spi_bitbang
[ 406.143852] CPU: 0 PID: 299 Comm: tracker Tainted: P O 3.13.0-qtec-standard #10
[ 406.143927] Hardware name: QTechnology QT5022/QT5022, BIOS PM_2.1.0.309 X64 04/04/2013
[ 406.144000] task: ffff880085c82d60 ti: ffff880085abe000 task.ti: ffff880085abe000
[ 406.144067] RIP: 0010:[<ffffffff8115204c>] [<ffffffff8115204c>] follow_pfn+0x2c/0x70
[ 406.144145] RSP: 0018:ffff880085abf888 EFLAGS: 00010296
[ 406.144195] RAX: 0000000000000000 RBX: ffff880085abf8e0 RCX: ffff880085abf888
[ 406.144260] RDX: ffff880085abf890 RSI: 00007fc52e173000 RDI: ffff8800863cbe40
[ 406.144325] RBP: ffff880085abf8a8 R08: 0000000000000018 R09: ffff8800863cbf00
[ 406.144388] R10: ffff880086703b80 R11: 00000000000001e0 R12: 0000000000018000
[ 406.144452] R13: 0000000000000000 R14: ffffea0000000000 R15: ffff88015922fea0
[ 406.144517] FS: 00007fc536e7c740(0000) GS:ffff88015ec00000(0000) knlGS:0000000000000000
[ 406.144591] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 406.144644] CR2: 0000000000000040 CR3: 0000000066c9d000 CR4: 00000000000007f0
[ 406.144708] Stack:
[ 406.144731] 0000000000018000 00007fc52e18b000 0000000000000000 00007fc52e173000
[ 406.144813] ffff880085abf918 ffffffffa083b2fd ffff880085ab1ba8 0000000000000000
[ 406.144894] 0000000000000000 0000000100000000 ffff880085abf928 ffff880159a20800
[ 406.144976] Call Trace:
[ 406.145011] [<ffffffffa083b2fd>] vb2_dma_sg_get_userptr+0x14d/0x310 [videobuf2_dma_sg]
[ 406.145089] [<ffffffffa08507df>] __qbuf_userptr+0xbf/0x3e0 [videobuf2_core]
[ 406.147229] [<ffffffffa0041454>] ? mc_heap_lock_memory+0x1f4/0x490 [fglrx]
[ 406.149234] [<ffffffff813428f3>] ? cpumask_next_and+0x23/0x50
[ 406.151223] [<ffffffff810b2e38>] ? enqueue_task_fair+0x658/0xde0
[ 406.153199] [<ffffffff81061888>] ? native_smp_send_reschedule+0x48/0x60
[ 406.155184] [<ffffffff815836b9>] ? get_ctrl+0xa9/0xd0
[ 406.157161] [<ffffffff8116f4e4>] ? __kmalloc+0x1a4/0x1b0
[ 406.159135] [<ffffffffa0850b9c>] ? __vb2_queue_alloc+0x9c/0x4a0 [videobuf2_core]
[ 406.161130] [<ffffffffa0852d08>] __buf_prepare+0x1a8/0x210 [videobuf2_core]
[ 406.163171] [<ffffffffa0854c57>] __vb2_qbuf+0x27/0xcc [videobuf2_core]
[ 406.165229] [<ffffffffa0851dfd>] vb2_queue_or_prepare_buf+0x1ed/0x270 [videobuf2_core]
[ 406.167325] [<ffffffffa0854c30>] ? vb2_ioctl_querybuf+0x30/0x30 [videobuf2_core]
[ 406.169419] [<ffffffffa0851e9c>] vb2_qbuf+0x1c/0x20 [videobuf2_core]
[ 406.171508] [<ffffffffa0851ef8>] vb2_ioctl_qbuf+0x58/0x70 [videobuf2_core]
[ 406.173604] [<ffffffff8157d3a8>] v4l_qbuf+0x48/0x60
[ 406.175681] [<ffffffff8157b29c>] __video_do_ioctl+0x2bc/0x340
[ 406.177779] [<ffffffff8116f43c>] ? __kmalloc+0xfc/0x1b0
[ 406.179883] [<ffffffff8157cd0e>] ? video_usercopy+0x7e/0x470
[ 406.181961] [<ffffffff8157ce81>] video_usercopy+0x1f1/0x470
[ 406.184021] [<ffffffff8157afe0>] ? v4l_printk_ioctl+0xb0/0xb0
[ 406.186085] [<ffffffff810ae1ed>] ? account_system_time+0x8d/0x190
[ 406.188149] [<ffffffff8157d115>] video_ioctl2+0x15/0x20
[ 406.190216] [<ffffffff815781b3>] v4l2_ioctl+0x123/0x160
[ 406.192251] [<ffffffff810ce415>] ? rcu_eqs_enter+0x65/0xa0
[ 406.194256] [<ffffffff81186b28>] do_vfs_ioctl+0x88/0x560
[ 406.196258] [<ffffffff810ae145>] ? account_user_time+0x95/0xb0
[ 406.198262] [<ffffffff810ae6a4>] ? vtime_account_user+0x44/0x70
[ 406.200215] [<ffffffff81187091>] SyS_ioctl+0x91/0xb0
[ 406.202107] [<ffffffff817be109>] tracesys+0xd0/0xd5
[ 406.203946] Code: 66 66 66 90 48 f7 47 50 00 44 00 00 b8 ea ff ff ff 74 52 55 48 89 e5 53 48 89 d3 48 8d 4d e0 48 8d 55 e8 48 83 ec 18 48 8b 47 40 <48> 8b 78 40 e8 8b fe ff ff 85 c0 75 27 48 8b 55 e8 48 b9 00 f0
[ 406.208011] RIP [<ffffffff8115204c>] follow_pfn+0x2c/0x70
[ 406.209908] RSP <ffff880085abf888>
[ 406.211760] CR2: 0000000000000040
[ 406.213676] ---[ end trace 996d9f64e6739a04 ]---
Signed-off-by: Ricardo Ribalda Delgado <ricardo.ribalda@gmail.com>
Acked-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
|
|
Merge the media fixes merged upstream for v3.13-rc4
* upstream-fixes: (30 commits)
[media] videobuf2-dma-sg: fix possible memory leak
[media] vb2: regression fix: always set length field.
[media] mt9p031: Include linux/of.h header
[media] rtl2830: add parent for I2C adapter
[media] media: marvell-ccic: use devm to release clk
[media] ths7303: Declare as static a private function
[media] em28xx-video: Swap release order to avoid lock nesting
[media] usbtv: Add support for PAL video source
[media] media_tree: Fix spelling errors
[media] videobuf2: Add support for file access mode flags for DMABUF exporting
[media] radio-shark2: Mark shark_resume_leds() inline to kill compiler warning
[media] radio-shark: Mark shark_resume_leds() inline to kill compiler warning
[media] af9035: unlock on error in af9035_i2c_master_xfer()
[media] af9033: fix broken I2C
[media] v4l: omap3isp: Don't check for missing get_fmt op on remote subdev
[media] af9035: fix broken I2C and USB I/O
[media] wm8775: fix broken audio routing
[media] marvell-ccic: drop resource free in driver remove
[media] tef6862/radio-tea5764: actually assign clamp result
[media] cx231xx: use after free on error path in probe
...
|
|
Fix the return when 'buf->pages' allocation error.
Signed-off-by: Geyslan G. Bem <geyslan@gmail.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
|
|
Memory exported via remap_pfn_range cannot be remapped via
get_user_pages.
Other videobuf2 methods (like the dma-contig) supports io memory.
This patch adds support for this kind of memory.
v2: Comments by Marek Szyprowski
-Use vb2_get_vma and vb2_put_vma
Signed-off-by: Ricardo Ribalda Delgado <ricardo.ribalda@gmail.com>
Acked-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
|
|
num_pages_from_user and buf->num_pages were swapped.
Signed-off-by: Ricardo Ribalda Delgado <ricardo.ribalda@gmail.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
|
|
Replace the private struct vb2_dma_sg_desc with the struct sg_table so
we can benefit from all the helping functions in lib/scatterlist.c for
things like allocating the sg or compacting the descriptor.
marvel-ccic and solo6x10 drivers, that use this API have been updated.
Acked-by: Marek Szyprowski <m.szyprowski@samsung.com>
Reviewed-by: Andre Heider <a.heider@gmail.com>
Signed-off-by: Ricardo Ribalda Delgado <ricardo.ribalda@gmail.com>
[s.nawrocki@samsung.com: minor corrections of the changelog]
Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
|
|
Most DMA engines have limitations regarding the number of DMA segments
(sg-buffers) that they can handle. Videobuffers can easily spread
through hundreds of pages.
In the previous aproach, the pages were allocated individually, this
could led to the creation houndreds of dma segments (sg-buffers) that
could not be handled by some DMA engines.
This patch tries to minimize the number of DMA segments by using
alloc_pages. In the worst case it will behave as before, but most
of the times it will reduce the number of dma segments
Acked-by: Marek Szyprowski <m.szyprowski@samsung.com>
Reviewed-by: Andre Heider <a.heider@gmail.com>
Signed-off-by: Ricardo Ribalda Delgado <ricardo.ribalda@gmail.com>
Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
|
|
Memory maps typically require that the buffer size to be page
aligned. Currently, two memops drivers do such alignment
internally, but videobuf-vmalloc doesn't.
Also, the buffer overflow check doesn't take it into account.
So, instead of doing it at each memops driver, enforce it at
VB2 core.
Reported-by: Prabhakar lad <prabhakar.csengg@gmail.com>
Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Acked-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
|
|
This prevents the kernel log from being spammed with these messages.
By turning on the debug option you will see them again.
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
|
|
Some drivers have special memory requirements for their buffers, usually
related to DMA (e.g. GFP_DMA or __GFP_DMA32). Make it possible to specify
additional GFP flags for those buffers by adding a gfp_flags field to
vb2_queue.
Note that this field will be replaced in the future with a different
mechanism, but that is still work in progress and we need this feature
now so we won't be able to convert drivers with such requirements to vb2.
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Marek Szyprowski <m.szyprowski@samsung.com>
Acked-by: Federico Vaga <federico.vaga@gmail.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
|
|
Currently, the v4l2 core is mixed together with other non-core drivers.
Move them into a separate directory.
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
|
Hans Verkuil
Hans Verkuil
Hans Verkuil
Ricardo Ribalda
Mauro Carvalho Chehab
Geyslan G. Bem
Mauro Carvalho Chehab