linux/drivers/staging/imx-drm
Russell King d9fdb9fba7 imx-drm: imx-ldb: fix NULL pointer in imx_ldb_unbind()
When trying to unbind imx-drm, the following oops was observed from
the imx-ldb driver:

Unable to handle kernel NULL pointer dereference at virtual address 0000001c
pgd = de954000
[0000001c] *pgd=2e92c831, *pte=00000000, *ppte=00000000
Internal error: Oops: 17 [#1] SMP ARM
Modules linked in: bnep rfcomm bluetooth nfsd exportfs hid_cypress brcmfmac brcmutil snd_soc_fsl_ssi snd_soc_fsl_spdif imx_pcm_fiq imx_pcm_dma imx_ldb(C) imx_thermal imx_sdma imx2_wdt snd_soc_sgtl5000 snd_soc_imx_sgtl5000 snd_soc_imx_spdif snd_soc_imx_audmux
CPU: 1 PID: 1228 Comm: bash Tainted: G         C    3.16.0-rc2+ #1229
task: ea378d80 ti: de948000 task.ti: de948000
PC is at imx_ldb_unbind+0x1c/0x58 [imx_ldb]
LR is at component_unbind+0x38/0x70
pc : [<bf025068>]    lr : [<c0353108>]    psr: 200f0013
sp : de949da8  ip : de949dc0  fp : de949dbc
r10: e9a44b0c  r9 : 00000000  r8 : de949f78
r7 : 00000012  r6 : e9b3f400  r5 : e9b133b8  r4 : e9b13010
r3 : 00000000  r2 : e9b3f400  r1 : ea9a0210  r0 : e9b13020
Flags: nzCv  IRQs on  FIQs on  Mode SVC_32  ISA ARM  Segment user
Control: 10c53c7d  Table: 2e95404a  DAC: 00000015
Process bash (pid: 1228, stack limit = 0xde948240)
Stack: (0xde949da8 to 0xde94a000)
...
Backtrace:
[<bf02504c>] (imx_ldb_unbind [imx_ldb]) from [<c0353108>] (component_unbind+0x38/0x70)
[<c03530d0>] (component_unbind) from [<c03531d4>] (component_unbind_all+0x94/0xc8)
[<c0353140>] (component_unbind_all) from [<c04bc224>] (imx_drm_driver_unload+0x34/0x4c)
[<c04bc1f0>] (imx_drm_driver_unload) from [<c03394a4>] (drm_dev_unregister+0x2c/0xa0)
[<c0339478>] (drm_dev_unregister) from [<c0339f8c>] (drm_put_dev+0x30/0x6c)
[<c0339f5c>] (drm_put_dev) from [<c04bc1cc>] (imx_drm_unbind+0x14/0x18)
[<c04bc1b8>] (imx_drm_unbind) from [<c03530b4>] (component_master_del+0xbc/0xd8)
...
Code: e5904058 e2840010 e2845fea e59430a0 (e593301c)
---[ end trace 4f211c6dbbcd4963 ]---

This is caused by only having one channel out of the pair configured in
DT; the second channel remains uninitialised, but upon unbind, the
driver attempts to clean up both, thereby dereferencing a NULL pointer.
Avoid this by checking that the second channel is initialised.

Fixes: 1b3f767566 ("imx-drm: initialise drm components directly")
Cc: <stable@vger.kernel.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-08 12:10:28 -07:00
..
Kconfig gpu: ipu-v3: Move i.MX IPUv3 core driver out of staging 2014-06-04 11:06:52 +02:00
Makefile gpu: ipu-v3: Move i.MX IPUv3 core driver out of staging 2014-06-04 11:06:52 +02:00
TODO staging: imx-drm: Update TODO 2014-03-07 16:18:01 +00:00
imx-drm-core.c Merge branch 'drm-next' of git://people.freedesktop.org/~airlied/linux 2014-08-07 17:36:12 -07:00
imx-drm.h drm: make mode_valid callback optional 2014-04-22 11:18:12 +02:00
imx-hdmi.c Merge branch 'drm-next' of git://people.freedesktop.org/~airlied/linux 2014-06-12 11:32:30 -07:00
imx-hdmi.h imx-drm: Add mx6 hdmi transmitter support 2013-12-08 17:23:18 -08:00
imx-ldb.c imx-drm: imx-ldb: fix NULL pointer in imx_ldb_unbind() 2014-09-08 12:10:28 -07:00
imx-tve.c Merge branch 'topic/ipu-destaging' of git://git.pengutronix.de/git/pza/linux into drm-next 2014-06-11 10:13:58 +10:00
ipuv3-crtc.c Merge branch 'drm-next' of git://people.freedesktop.org/~airlied/linux 2014-06-12 11:32:30 -07:00
ipuv3-plane.c imx-drm: ipuv3-plane: fix ipu_plane_dpms() 2014-09-08 12:10:28 -07:00
ipuv3-plane.h staging: drm/imx: add drm plane support 2013-10-11 15:30:33 -07:00
parallel-display.c imx-drm: parallel-display: Fix DPMS default state. 2014-06-19 17:33:37 -07:00