linux, branch v3.12.2

Linux 3.12.2

2013-11-29T19:28:26Z

cris: media platform drivers: fix build

2013-11-29T19:28:13Z

commit 72a0c5571351f5184195754d23db3e14495b2080 upstream. On cris arch, the functions below aren't defined: drivers/media/platform/sh_veu.c: In function 'sh_veu_reg_read': drivers/media/platform/sh_veu.c:228:2: error: implicit declaration of function 'ioread32' [-Werror=implicit-function-declaration] drivers/media/platform/sh_veu.c: In function 'sh_veu_reg_write': drivers/media/platform/sh_veu.c:234:2: error: implicit declaration of function 'iowrite32' [-Werror=implicit-function-declaration] drivers/media/platform/vsp1/vsp1.h: In function 'vsp1_read': drivers/media/platform/vsp1/vsp1.h:66:2: error: implicit declaration of function 'ioread32' [-Werror=implicit-function-declaration] drivers/media/platform/vsp1/vsp1.h: In function 'vsp1_write': drivers/media/platform/vsp1/vsp1.h:71:2: error: implicit declaration of function 'iowrite32' [-Werror=implicit-function-declaration] drivers/media/platform/vsp1/vsp1.h: In function 'vsp1_read': drivers/media/platform/vsp1/vsp1.h:66:2: error: implicit declaration of function 'ioread32' [-Werror=implicit-function-declaration] drivers/media/platform/vsp1/vsp1.h: In function 'vsp1_write': drivers/media/platform/vsp1/vsp1.h:71:2: error: implicit declaration of function 'iowrite32' [-Werror=implicit-function-declaration] drivers/media/platform/soc_camera/rcar_vin.c: In function 'rcar_vin_setup': drivers/media/platform/soc_camera/rcar_vin.c:284:3: error: implicit declaration of function 'iowrite32' [-Werror=implicit-function-declaration] drivers/media/platform/soc_camera/rcar_vin.c: In function 'rcar_vin_request_capture_stop': drivers/media/platform/soc_camera/rcar_vin.c:353:2: error: implicit declaration of function 'ioread32' [-Werror=implicit-function-declaration] Yet, they're available, as CONFIG_GENERIC_IOMAP is defined. What happens is that asm/io.h was not including asm-generic/iomap.h. Suggested-by: Ben Hutchings Signed-off-by: Mauro Carvalho Chehab Cc: Mikael Starvik Cc: Jesper Nilsson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman

GFS2: fix dentry leaks

2013-11-29T19:28:13Z

commit 5ca1db41ecdeb0358b968265fadb755213558a85 upstream. We need to dput() the result of d_splice_alias(), unless it is passed to finish_no_open(). Edited by Steven Whitehouse in order to make it apply to the current GFS2 git tree, and taking account of a prerequisite patch which hasn't been applied. Signed-off-by: Miklos Szeredi Signed-off-by: Steven Whitehouse Signed-off-by: Greg Kroah-Hartman

GFS2: d_splice_alias() can't return error

2013-11-29T19:28:12Z

commit 0d0d110720d7960b77c03c9f2597faaff4b484ae upstream. unless it was given an IS_ERR(inode), which isn't the case here. So clean up the unnecessary error handling in gfs2_create_inode(). This paves the way for real fixes (hence the stable Cc). Signed-off-by: Miklos Szeredi Signed-off-by: Steven Whitehouse Signed-off-by: Greg Kroah-Hartman

configfs: fix race between dentry put and lookup

2013-11-29T19:28:12Z

commit 76ae281f6307331aa063288edb6422ae99f435f0 upstream. A race window in configfs, it starts from one dentry is UNHASHED and end before configfs_d_iput is called. In this window, if a lookup happen, since the original dentry was UNHASHED, so a new dentry will be allocated, and then in configfs_attach_attr(), sd->s_dentry will be updated to the new dentry. Then in configfs_d_iput(), BUG_ON(sd->s_dentry != dentry) will be triggered and system panic. sys_open: sys_close: ... fput dput dentry_kill __d_drop <--- dentry unhashed here, but sd->dentry still point to this dentry. lookup_real configfs_lookup configfs_attach_attr---> update sd->s_dentry to new allocated dentry here. d_kill configfs_d_iput <--- BUG_ON(sd->s_dentry != dentry) triggered here. To fix it, change configfs_d_iput to not update sd->s_dentry if sd->s_count > 2, that means there are another dentry is using the sd beside the one that is going to be put. Use configfs_dirent_lock in configfs_attach_attr to sync with configfs_d_iput. With the following steps, you can reproduce the bug. 1. enable ocfs2, this will mount configfs at /sys/kernel/config and fill configure in it. 2. run the following script. while [ 1 ]; do cat /sys/kernel/config/cluster/$your_cluster_name/idle_timeout_ms > /dev/null; done & while [ 1 ]; do cat /sys/kernel/config/cluster/$your_cluster_name/idle_timeout_ms > /dev/null; done & Signed-off-by: Junxiao Bi Cc: Joel Becker Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman

s390/vtime: correct idle time calculation

2013-11-29T19:28:12Z

commit 4560e7c3317c7a2b370e36dadd3a3bac2ed70818 upstream. Use the ACCESS_ONCE macro for both accesses to idle->sequence in the loops to calculate the idle time. If only one access uses the macro, the compiler is free to cache the value for the second access which can cause endless loops. Signed-off-by: Martin Schwidefsky Signed-off-by: Greg Kroah-Hartman

s390/time: fix get_tod_clock_ext inline assembly

2013-11-29T19:28:12Z

commit 7ab64a85e1a009046f97413a573e83fd85f7804d upstream. The get_tod_clock_ext inline assembly does not specify its output operands correctly. This can cause incorrect code to be generated. Signed-off-by: Martin Schwidefsky Signed-off-by: Greg Kroah-Hartman

usb: musb: core: properly free host / device structs in err path

2013-11-29T19:28:12Z

commit 0d2dd7eaed1dac07b266ca2c662ff4a184a3060f upstream. The patch fixes two issues in the error path cleanup: - in MUSB_PORT_MODE_DUAL_ROLE mode, if musb_gadget_setup() fails we never cleanup the host struct earlier allocated. - if musb_init_debugfs() or sysfs_create_group() fails, then we never free the host part initialization, only device part. Cc: Daniel Mack Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Felipe Balbi Signed-off-by: Greg Kroah-Hartman

usb: musb: dsps: redo the otg timer

2013-11-29T19:28:11Z

commit 0f901c980110cd69b63670096465b35377e73b1c upstream. According to the comments, we rely on the OTG timer because the core does not expose some important OTG details. So far this is all I know. After playing with OTG I stumbled over a problem: musb is recognized as a B-device without a problem. Whenever a cable is plugged, the VBUS rises, musb recognizes this as a starting session, sets the MUSB_DEVCTL_SESSION bit by itself and a RESET interrupt occurs, the session starts. Good. After a disconnect, the timer is started and re-starts itself because it remains in B_IDLE with the BDEVICE set. I didn't figure the the reason or the need for it. Nothing changes here except for OTG state from B to A device if the BDEVICE bit disappears. This doesn't make much sense to me because nothing happens after this. _IF_ we receive an interrupt before the state change then we may act on wrong condition. Plugging a B-device (and letting MUSB act as host) doesn't work here. The reason seems to be that the MUSB tries to start a session, it fails and then it removes the bit. So we never start as a host. This patch sets the MUSB_DEVCTL_SESSION bit in the IDLE state so musb can try to establish a session as host. After the bit is set, musb tries to start a session and if it fails it clears the bit. Therefore it will try over and over again until a session either as host or as device is established. The readout of the MUSB_DEVCTL register after the removal the MUSB_DEVCTL_SESSION (in A_WAIT_BCON) has been removed because it did not contain the BDEVICE bit set (in the second read) leading to A_IDLE. After plugging a host musb assumed that it is also a host and complained about a missing reset. However a third read of the register has has the BDEVICE bit set so it seems that it is not stable. This mostly what da8xx.c is doing except that we set the timer also after A_WAIT_BCON so the session bit can be triggered. Whit this change I was able to keep am335x-evm in OTG mode and plug in either a HOST or a DEVICE and in a random order and the device was recognized. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Felipe Balbi Signed-off-by: Greg Kroah-Hartman

usb: musb: dsps: move try_idle to start hook

2013-11-29T19:28:11Z

commit 8b9fcce2d88586b9a120ff3e039d8f42413f0bb0 upstream. The timer is initialized right after musb is probed. There is actually no need to have this timer running because _nothing_ will happen until we have the gadget loaded. Also we need this timer only if we run in OTG mode _and_ we need it also after the gadget has been replaced with another one. I've been looking at am35x.c, da8xx.c, omap2430.c, tusb6010.c. da8xx seem to have the same problem as dsps and doing mostly the same thing. tusb6010 seem to do something different and do some actual "idle / power saving" work so I am not too comfortable to remove musb_platform_try_idle() from musb_gadget_setup(). Therefore this patch does not start the timer if there is no gadget active (which is at musb_gadget_setup() at time). In order to have the timer active after the gadget is loaded it will be triggered from dsps_musb_enable(). Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Felipe Balbi Signed-off-by: Greg Kroah-Hartman