The sceanrio is like this.
inline_data i_size page write_begin/vm_page_mkwrite
X 30 dirty_page
X 30 write to #4096 position
X 30 get_dnode_of_data wait for get_dnode_of_data
O 30 write inline_data
O 30 get_dnode_of_data
O 30 reserve data block
..
In this case, we have #0 = NEW_ADDR and inline_data as well.
We should not allow this condition for further access.
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Let's consider the following scenario.
blkaddr[0] inline_data i_size i_blocks writepage truncate
NEW X 4096 2 dirty page #0
NEW X 0 change i_size
NEW X 0 2 f2fs_write_inline_data
NEW X 0 2 get_dnode_of_data
NEW X 0 2 truncate_data_blocks_range
NULL O 0 1 memcpy(inline_data)
NULL O 0 1 f2fs_put_dnode
NULL O 0 1 f2fs_truncate
NULL O 0 1 get_dnode_of_data
NULL O 0 1 *invalid block addr*
This patch adds checking inline_data flag during f2fs_truncate not to refer
corrupted block indices.
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
When trying to write inline_data, we should truncate any data block allocated
and pointed by the inode block.
We should consider the data index is not 0.
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
This patch removes some unneeded white space after casts within the
channel.c file. The checkpatch script was run after these changes,
and no further checks or warnings were seen.
Signed-off-by: Ken Depro <kenneth.depro@unisys.com>
Signed-off-by: Ben Romer <benjamin.romer@unisys.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Rename the following local variables in virtpci_device_add()
pIoChan changed to io_chan
pDev changed to dev
Signed-off-by: Bryan Thompson <bryan.thompson@unisys.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Rename the following local variables in fix_vbus_dev_info()
Change pChan to chan
Change devInfo to dev_info
Signed-off-by: Bryan Thompson <bryan.thompson@unisys.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Rename pDev to dev in delete_vbus_device()
Signed-off-by: Bryan Thompson <bryan.thompson@unisys.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Delete the macros and related preprocessor code for DBG_GETFILE_PAYLOAD(),
DBG_GETFILE(), and DBG_PUTFILE().
Signed-off-by: Benjamin Romer <benjamin.romer@unisys.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
No one is using this definition so remove it.
Signed-off-by: Benjamin Romer <benjamin.romer@unisys.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Delete visorchipset_get_switch_info() and visorchipset_get_externalport_info()
as these functions were declared but not defined, or used.
Signed-off-by: Benjamin Romer <benjamin.romer@unisys.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Get rid of the typedef and just use struct visorchipset_busdev_responders
instead. Fix CamelCase parameter names in the function pointer definitions for
the structure:
busNo => bus_no
devNo => dev_no
Update references to changed names.
Signed-off-by: Benjamin Romer <benjamin.romer@unisys.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Get rid of the typedef and just use struct visorchipset_busdev_notifiers
instead. Fix CamelCase names in parameters for the function pointers:
busNo => bus_no
devNo => dev_no
typeGuid => type_uuid
minSize => min_size
maxSize => max_size
Update references.
Signed-off-by: Benjamin Romer <benjamin.romer@unisys.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Fix the CamelCase parameter name in findbus() in visorchipset.h.
busNo => bus_no
Signed-off-by: Benjamin Romer <benjamin.romer@unisys.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Fix the CamelCase parameter in delbusdevices() in visorchipset.h:
busNo => bus_no
Signed-off-by: Benjamin Romer <benjamin.romer@unisys.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Remove the typedef from this type and use struct visorchipset_channel_info
instead. Fix CamelCase member names:
addrType => addr_type
channelAddr => channel_addr
nChannelBytes => n_channel_bytes
channelTypeGuid => channel_type_uuid
channelInstGuid => channel_inst_uuid
Signed-off-by: Benjamin Romer <benjamin.romer@unisys.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Remove the typedef from the enumeration and replace references to it with
enum crash_obj_type. Fix CamelCase names:
CRASH_dev => CRASH_DEV
CRASH_bus => CRASH_BUS
Update all references to changed names.
Signed-off-by: Benjamin Romer <benjamin.romer@unisys.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Get rid of VISORCHIPSET_ADDRESSTYPE and replace it with enum
visorchipset_addresstype. Fix CamelCase names:
ADDRTYPE_localPhysical => ADDRTYPE_LOCALPHYSICAL
ADDRTYPE_localTest => ADDRTYPE_LOCALTEST
Update all references to changed names.
Signed-off-by: Benjamin Romer <benjamin.romer@unisys.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Remove the typedef for VISORCHIPSET_STATE and replace it with enum
visorchipset_state.
Signed-off-by: Benjamin Romer <benjamin.romer@unisys.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
We have host client in connect/disconnect response processors,
so use client print functions to simplify and unify code.
Signed-off-by: Alexander Usyskin <alexander.usyskin@intel.com>
Signed-off-by: Tomas Winkler <tomas.winkler@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
<debugfs>meiX/meclients: display also fixed/connectionless clients
Use better name for fixed client field:
fixed_address is boolean and indicates whether a client
is fixed or dynamic.
Signed-off-by: Tomas Winkler <tomas.winkler@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Use local cl variable instead of dev->iamthif_cl and dev->wd_cl
as the first step to use dynamic allocation of these clients
as their are not supported on all platforms
Signed-off-by: Tomas Winkler <tomas.winkler@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The pointer to client in the callback structure (cb->cl)
can't be NULL with current locking.
We can drop check and warnings as in some cases this just
uselessly complicates the code flow.
Signed-off-by: Alexander Usyskin <alexander.usyskin@intel.com>
Signed-off-by: Tomas Winkler <tomas.winkler@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Since we notify disconnecting based on the usb device is existed
(port_dev->child, the child device at roothub is not NULL), we
need to notify connect after device has been registered.
This fixes a bug that do fast plug in/out test, and the notify_disconnect
is not called due to roothub child is NULL and the enumeration has failed.
Cc: v3.17+ <stable@vger.kernel.org>
Signed-off-by: Tony Zheng <Tony.Zheng@freescale.com>
Signed-off-by: Peter Chen <peter.chen@freescale.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
These drives hang when receiving ATA12 commands, so set the US_FL_NO_ATA_1X
quirk to filter these out.
Cc: stable@vger.kernel.org # 3.16
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The switch back is limited to ULT even on HP. The contrary
finding arose by bad luck in BIOS versions for testing.
This fixes spontaneous resume from S3 on some HP laptops.
Signed-off-by: Oliver Neukum <oneukum@suse.de>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>