Pull workqueue updates from Tejun Heo:
"A lot of activities on workqueue side this time. The changes achieve
the followings.
- WQ_UNBOUND workqueues - the workqueues which are per-cpu - are
updated to be able to interface with multiple backend worker pools.
This involved a lot of churning but the end result seems actually
neater as unbound workqueues are now a lot closer to per-cpu ones.
- The ability to interface with multiple backend worker pools are
used to implement unbound workqueues with custom attributes.
Currently the supported attributes are the nice level and CPU
affinity. It may be expanded to include cgroup association in
future. The attributes can be specified either by calling
apply_workqueue_attrs() or through /sys/bus/workqueue/WQ_NAME/* if
the workqueue in question is exported through sysfs.
The backend worker pools are keyed by the actual attributes and
shared by any workqueues which share the same attributes. When
attributes of a workqueue are changed, the workqueue binds to the
worker pool with the specified attributes while leaving the work
items which are already executing in its previous worker pools
alone.
This allows converting custom worker pool implementations which
want worker attribute tuning to use workqueues. The writeback pool
is already converted in block tree and there are a couple others
are likely to follow including btrfs io workers.
- WQ_UNBOUND's ability to bind to multiple worker pools is also used
to make it NUMA-aware. Because there's no association between work
item issuer and the specific worker assigned to execute it, before
this change, using unbound workqueue led to unnecessary cross-node
bouncing and it couldn't be helped by autonuma as it requires tasks
to have implicit node affinity and workers are assigned randomly.
After these changes, an unbound workqueue now binds to multiple
NUMA-affine worker pools so that queued work items are executed in
the same node. This is turned on by default but can be disabled
system-wide or for individual workqueues.
Crypto was requesting NUMA affinity as encrypting data across
different nodes can contribute noticeable overhead and doing it
per-cpu was too limiting for certain cases and IO throughput could
be bottlenecked by one CPU being fully occupied while others have
idle cycles.
While the new features required a lot of changes including
restructuring locking, it didn't complicate the execution paths much.
The unbound workqueue handling is now closer to per-cpu ones and the
new features are implemented by simply associating a workqueue with
different sets of backend worker pools without changing queue,
execution or flush paths.
As such, even though the amount of change is very high, I feel
relatively safe in that it isn't likely to cause subtle issues with
basic correctness of work item execution and handling. If something
is wrong, it's likely to show up as being associated with worker pools
with the wrong attributes or OOPS while workqueue attributes are being
changed or during CPU hotplug.
While this creates more backend worker pools, it doesn't add too many
more workers unless, of course, there are many workqueues with unique
combinations of attributes. Assuming everything else is the same,
NUMA awareness costs an extra worker pool per NUMA node with online
CPUs.
There are also a couple things which are being routed outside the
workqueue tree.
- block tree pulled in workqueue for-3.10 so that writeback worker
pool can be converted to unbound workqueue with sysfs control
exposed. This simplifies the code, makes writeback workers
NUMA-aware and allows tuning nice level and CPU affinity via sysfs.
- The conversion to workqueue means that there's no 1:1 association
between a specific worker, which makes writeback folks unhappy as
they want to be able to tell which filesystem caused a problem from
backtrace on systems with many filesystems mounted. This is
resolved by allowing work items to set debug info string which is
printed when the task is dumped. As this change involves unifying
implementations of dump_stack() and friends in arch codes, it's
being routed through Andrew's -mm tree."
* 'for-3.10' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq: (84 commits)
workqueue: use kmem_cache_free() instead of kfree()
workqueue: avoid false negative WARN_ON() in destroy_workqueue()
workqueue: update sysfs interface to reflect NUMA awareness and a kernel param to disable NUMA affinity
workqueue: implement NUMA affinity for unbound workqueues
workqueue: introduce put_pwq_unlocked()
workqueue: introduce numa_pwq_tbl_install()
workqueue: use NUMA-aware allocation for pool_workqueues
workqueue: break init_and_link_pwq() into two functions and introduce alloc_unbound_pwq()
workqueue: map an unbound workqueues to multiple per-node pool_workqueues
workqueue: move hot fields of workqueue_struct to the end
workqueue: make workqueue->name[] fixed len
workqueue: add workqueue->unbound_attrs
workqueue: determine NUMA node of workers accourding to the allowed cpumask
workqueue: drop 'H' from kworker names of unbound worker pools
workqueue: add wq_numa_tbl_len and wq_numa_possible_cpumask[]
workqueue: move pwq_pool_locking outside of get/put_unbound_pool()
workqueue: fix memory leak in apply_workqueue_attrs()
workqueue: fix unbound workqueue attrs hashing / comparison
workqueue: fix race condition in unbound workqueue free path
workqueue: remove pwq_lock which is no longer used
...
Now that devtmpfs is caring about uid/gid, we need to use the correct
internal types so users who have USER_NS enabled will have things work
properly for them.
Thanks to Eric for pointing this out, and the patch review.
Reported-by: Eric W. Biederman <ebiederm@xmission.com>
Cc: Kay Sievers <kay@vrfy.org>
Cc: Ming Lei <ming.lei@canonical.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Some drivers want to tell userspace what uid and gid should be used for
their device nodes, so allow that information to percolate through the
driver core to userspace in order to make this happen. This means that
some systems (i.e. Android and friends) will not need to even run a
udev-like daemon for their device node manager and can just rely in
devtmpfs fully, reducing their footprint even more.
Signed-off-by: Kay Sievers <kay@vrfy.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Kay tells me the most appropriate place to expose workqueues to
userland would be /sys/devices/virtual/workqueues/WQ_NAME which is
symlinked to /sys/bus/workqueue/devices/WQ_NAME and that we're lacking
a way to do that outside of driver core as virtual_device_parent()
isn't exported and there's no inteface to conveniently create a
virtual subsystem.
This patch implements subsys_virtual_register() by factoring out
subsys_register() from subsys_system_register() and using it with
virtual_device_parent() as the origin directory. It's identical to
subsys_system_register() other than the origin directory but we aren't
gonna restrict the device names which should be used under it.
This will be used to expose workqueue attributes to userland.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Kay Sievers <kay.sievers@vrfy.org>
Pull driver core patches from Greg Kroah-Hartman:
"Here is the big driver core merge for 3.9-rc1
There are two major series here, both of which touch lots of drivers
all over the kernel, and will cause you some merge conflicts:
- add a new function called devm_ioremap_resource() to properly be
able to check return values.
- remove CONFIG_EXPERIMENTAL
Other than those patches, there's not much here, some minor fixes and
updates"
Fix up trivial conflicts
* tag 'driver-core-3.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core: (221 commits)
base: memory: fix soft/hard_offline_page permissions
drivercore: Fix ordering between deferred_probe and exiting initcalls
backlight: fix class_find_device() arguments
TTY: mark tty_get_device call with the proper const values
driver-core: constify data for class_find_device()
firmware: Ignore abort check when no user-helper is used
firmware: Reduce ifdef CONFIG_FW_LOADER_USER_HELPER
firmware: Make user-mode helper optional
firmware: Refactoring for splitting user-mode helper code
Driver core: treat unregistered bus_types as having no devices
watchdog: Convert to devm_ioremap_resource()
thermal: Convert to devm_ioremap_resource()
spi: Convert to devm_ioremap_resource()
power: Convert to devm_ioremap_resource()
mtd: Convert to devm_ioremap_resource()
mmc: Convert to devm_ioremap_resource()
mfd: Convert to devm_ioremap_resource()
media: Convert to devm_ioremap_resource()
iommu: Convert to devm_ioremap_resource()
drm: Convert to devm_ioremap_resource()
...
All in-kernel users of class_find_device() don't really need mutable
data for match callback.
In two places (kernel/power/suspend_test.c, drivers/scsi/osd/osd_uld.c)
this patch changes match callbacks to use const search data.
The const is propagated to rtc_class_open() and power_supply_get_by_name()
parameters.
Note that there's a dev reference leak in suspend_test.c that's not
touched in this patch.
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Acked-by: Grant Likely <grant.likely@secretlab.ca>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This makes the device core auto-grab the pinctrl handle and set
the "default" (PINCTRL_STATE_DEFAULT) state for every device
that is present in the device model right before probe. This will
account for the lion's share of embedded silicon devcies.
A modification of the semantics for pinctrl_get() is also done:
previously if the pinctrl handle for a certain device was already
taken, the pinctrl core would return an error. Now, since the
core may have already default-grabbed the handle and set its
state to "default", if the handle was already taken, this will
be disregarded and the located, previously instanitated handle
will be returned to the caller.
This way all code in drivers explicitly requesting their pinctrl
handlers will still be functional, and drivers that want to
explicitly retrieve and switch their handles can still do that.
But if the desired functionality is just boilerplate of this
type in the probe() function:
struct pinctrl *p;
p = devm_pinctrl_get_select_default(&dev);
if (IS_ERR(p)) {
if (PTR_ERR(p) == -EPROBE_DEFER)
return -EPROBE_DEFER;
dev_warn(&dev, "no pinctrl handle\n");
}
The discussion began with the addition of such boilerplate
to the omap4 keypad driver:
http://marc.info/?l=linux-input&m=135091157719300&w=2
A previous approach using notifiers was discussed:
http://marc.info/?l=linux-kernel&m=135263661110528&w=2
This failed because it could not handle deferred probes.
This patch alone does not solve the entire dilemma faced:
whether code should be distributed into the drivers or
if it should be centralized to e.g. a PM domain. But it
solves the immediate issue of the addition of boilerplate
to a lot of drivers that just want to grab the default
state. As mentioned, they can later explicitly retrieve
the handle and set different states, and this could as
well be done by e.g. PM domains as it is only related
to a certain struct device * pointer.
ChangeLog v4->v5 (Stephen):
- Simplified the devicecore grab code.
- Deleted a piece of documentation recommending that pins
be mapped to a device rather than hogged.
ChangeLog v3->v4 (Linus):
- Drop overzealous NULL checks.
- Move kref initialization to pinctrl_create().
- Seeking Tested-by from Stephen Warren so we do not disturb
the Tegra platform.
- Seeking ACK on this from Greg (and others who like it) so I
can merge it through the pinctrl subsystem.
ChangeLog v2->v3 (Linus):
- Abstain from using IS_ERR_OR_NULL() in the driver core,
Russell recently sent a patch to remove it. Handle the
NULL case explicitly even though it's a bogus case.
- Make sure we handle probe deferral correctly in the device
core file. devm_kfree() the container on error so we don't
waste memory for devices without pinctrl handles.
- Introduce reference counting into the pinctrl core using
<linux/kref.h> so that we don't release pinctrl handles
that have been obtained for two or more places.
ChangeLog v1->v2 (Linus):
- Only store a pointer in the device struct, and only allocate
this if it's really used by the device.
Cc: Felipe Balbi <balbi@ti.com>
Cc: Benoit Cousson <b-cousson@ti.com>
Cc: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Cc: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Cc: Mitch Bradley <wmb@firmworks.com>
Cc: Ulf Hansson <ulf.hansson@linaro.org>
Cc: Rafael J. Wysocki <rjw@sisk.pl>
Cc: Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
Cc: Rickard Andersson <rickard.andersson@stericsson.com>
Cc: Russell King <linux@arm.linux.org.uk>
Reviewed-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
[swarren: fixed and simplified error-handling in pinctrl_bind_pins(), to
correctly handle deferred probe. Removed admonition from docs not to use
pinctrl hogs for devices]
Signed-off-by: Stephen Warren <swarren@nvidia.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
The devm_request_and_ioremap() function is very useful and helps avoid a
whole lot of boilerplate. However, one issue that keeps popping up is
its lack of a specific error code to determine which of the steps that
it performs failed. Furthermore, while the function gives an example and
suggests what error code to return on failure, a wide variety of error
codes are used throughout the tree.
In an attempt to fix these problems, this patch adds a new function that
drivers can transition to. The devm_ioremap_resource() returns a pointer
to the remapped I/O memory on success or an ERR_PTR() encoded error code
on failure. Callers can check for failure using IS_ERR() and determine
its cause by extracting the error code using PTR_ERR().
devm_request_and_ioremap() is implemented as a wrapper around the new
API and return NULL on failure as before. This ensures that backwards
compatibility is maintained until all users have been converted to the
new API, at which point the old devm_request_and_ioremap() function
should be removed.
A semantic patch is included which can be used to convert from the old
devm_request_and_ioremap() API to the new devm_ioremap_resource() API.
Some non-trivial cases may require manual intervention, though.
Signed-off-by: Thierry Reding <thierry.reding@avionic-design.de>
Cc: Arnd Bergmann <arnd@arndb.de>
Acked-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Pull x86 RAS update from Ingo Molnar:
"Rework all config variables used throughout the MCA code and collect
them together into a mca_config struct. This keeps them tightly and
neatly packed together instead of spilled all over the place.
Then, convert those which are used as booleans into real booleans and
save some space. These bits are exposed via
/sys/devices/system/machinecheck/machinecheck*/"
* 'x86-ras-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86, MCA: Finish mca_config conversion
x86, MCA: Convert the next three variables batch
x86, MCA: Convert rip_msr, mce_bootlog, monarch_timeout
x86, MCA: Convert dont_log_ce, banks and tolerant
drivers/base: Add a DEVICE_BOOL_ATTR macro
To avoid adding an ACPI handle pointer to struct device on
architectures that don't use ACPI, or generally when CONFIG_ACPI is
not set, in which cases that pointer is useless, define struct
acpi_dev_node that will contain the handle pointer if CONFIG_ACPI is
set and will be empty otherwise and use it to represent the ACPI
device node field in struct device.
In addition to that define macros for reading and setting the ACPI
handle of a device that don't generate code when CONFIG_ACPI is
unset. Modify the ACPI subsystem to use those macros instead of
referring to the given device's ACPI handle directly.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
With ACPI 5 we are starting to see devices that don't natively support
discovery but can be enumerated with the help of the ACPI namespace.
Typically, these devices can be represented in the Linux device driver
model as platform devices or some serial bus devices, like SPI or I2C
devices.
Since we want to re-use existing drivers for those devices, we need a
way for drivers to specify the ACPI IDs of supported devices, so that
they can be matched against device nodes in the ACPI namespace. To
this end, it is sufficient to add a pointer to an array of supported
ACPI device IDs, that can be provided by the driver, to struct device.
Moreover, things like ACPI power management need to have access to
the ACPI handle of each supported device, because that handle is used
to invoke AML methods associated with the corresponding ACPI device
node. The ACPI handles of devices are now stored in the archdata
member structure of struct device whose definition depends on the
architecture and includes the ACPI handle only on x86 and ia64. Since
the pointer to an array of supported ACPI IDs is added to struct
device_driver in an architecture-independent way, it is logical to
move the ACPI handle from archdata to struct device itself at the same
time. This also makes code more straightforward in some places and
follows the example of Device Trees that have a poiter to struct
device_node in there too.
This changeset is based on Mika Westerberg's work.
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: H. Peter Anvin <hpa@zytor.com>
Acked-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
... which, analogous to DEVICE_INT_ATTR provides functionality to
set/clear bools. Its purpose is to be used where values need to be used
as booleans in configuration context.
Next patch uses this.
Signed-off-by: Borislav Petkov <bp@alien8.de>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Tony Luck <tony.luck@intel.com>
Pull power management updates from Rafael J Wysocki:
- Improved system suspend/resume and runtime PM handling for the SH
TMU, CMT and MTU2 clock event devices (also used by ARM/shmobile).
- Generic PM domains framework extensions related to cpuidle support
and domain objects lookup using names.
- ARM/shmobile power management updates including improved support for
the SH7372's A4S power domain containing the CPU core.
- cpufreq changes related to AMD CPUs support from Matthew Garrett,
Andre Przywara and Borislav Petkov.
- cpu0 cpufreq driver from Shawn Guo.
- cpufreq governor fixes related to the relaxing of limit from Michal
Pecio.
- OMAP cpufreq updates from Axel Lin and Richard Zhao.
- cpuidle ladder governor fixes related to the disabling of states from
Carsten Emde and me.
- Runtime PM core updates related to the interactions with the system
suspend core from Alan Stern and Kevin Hilman.
- Wakeup sources modification allowing more helper functions to be
called from interrupt context from John Stultz and additional
diagnostic code from Todd Poynor.
- System suspend error code path fix from Feng Hong.
Fixed up conflicts in cpufreq/powernow-k8 that stemmed from the
workqueue fixes conflicting fairly badly with the removal of support for
hardware P-state chips. The changes were independent but somewhat
intertwined.
* tag 'pm-for-3.7-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (76 commits)
Revert "PM QoS: Use spinlock in the per-device PM QoS constraints code"
PM / Runtime: let rpm_resume() succeed if RPM_ACTIVE, even when disabled, v2
cpuidle: rename function name "__cpuidle_register_driver", v2
cpufreq: OMAP: Check IS_ERR() instead of NULL for omap_device_get_by_hwmod_name
cpuidle: remove some empty lines
PM: Prevent runtime suspend during system resume
PM QoS: Use spinlock in the per-device PM QoS constraints code
PM / Sleep: use resume event when call dpm_resume_early
cpuidle / ACPI : move cpuidle_device field out of the acpi_processor_power structure
ACPI / processor: remove pointless variable initialization
ACPI / processor: remove unused function parameter
cpufreq: OMAP: remove loops_per_jiffy recalculate for smp
sections: fix section conflicts in drivers/cpufreq
cpufreq: conservative: update frequency when limits are relaxed
cpufreq / ondemand: update frequency when limits are relaxed
properly __init-annotate pm_sysrq_init()
cpufreq: Add a generic cpufreq-cpu0 driver
PM / OPP: Initialize OPP table from device tree
ARM: add cpufreq transiton notifier to adjust loops_per_jiffy for smp
cpufreq: Remove support for hardware P-state chips from powernow-k8
...
Add utility functions to consolidate the use of
create_syslog_header and vprintk_emit.
This allows conversion of logging functions that
call create_syslog_header and then call vprintk_emit
or printk_emit to the dev_ equivalents.
Signed-off-by: Joe Perches <joe@perches.com>
Acked-by: David S. Miller <davem@davemloft.net>
Tested-by: Jim Cromie <jim.cromie@gmail.com>
Acked-by: Jason Baron <jbaron@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit c4e00daaa9
("driver-core: extend dev_printk() to pass structured data")
changed __dev_printk and broke dynamic-debug's ability to control the
dynamic prefix of dev_dbg(dev,..).
commit af7f2158fd
("drivers-core: make structured logging play nice with dynamic-debug")
made a minimal correction.
The current dynamic debug code uses up to 3 recursion levels via %pV.
This can consume quite a bit of stack. Directly call printk_emit to
reduce the recursion depth.
These changes include:
dev_dbg:
o Create and use function create_syslog_header to format the syslog
header for printk_emit uses.
o Call create_syslog_header and neaten __dev_printk
o Make __dev_printk static not global
o Remove include header declaration of __dev_printk
o Remove now unused EXPORT_SYMBOL() of __dev_printk
o Whitespace neatening
dynamic_dev_dbg:
o Remove KERN_DEBUG from dynamic_emit_prefix
o Call create_syslog_header and printk_emit
o Whitespace neatening
Signed-off-by: Joe Perches <joe@perches.com>
Acked-by: David S. Miller <davem@davemloft.net>
Tested-by: Jim Cromie <jim.cromie@gmail.com>
Acked-by: Jason Baron <jbaron@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The syscore device PM flag used to mark the devices (belonging to
PM domains) that should never be turned off, except for the system
core (syscore) suspend/hibernation and resume stages, need not be
accessed by the runtime PM core functions, because all of the devices
it is set for need to be marked as "irq safe" anyway and are
protected from being turned off by runtime PM by ensuring that their
usage counters are always set.
For this reason, make the syscore flag system-wide PM-specific
and simplify the code used for manipulating it, because it need not
acquire the device's power.lock any more.
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
This patch introduces one devres API of devres_for_each_res
so that the device's driver can iterate each resource it has
interest in.
The firmware loader will use the API to get each firmware name
from the device instance.
Signed-off-by: Ming Lei <ming.lei@canonical.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Pull driver core changes from Greg Kroah-Hartman:
"Here's the big driver core pull request for 3.6-rc1.
Unlike 3.5, this kernel should be a lot tamer, with the printk changes
now settled down. All we have here is some extcon driver updates, w1
driver updates, a few printk cleanups that weren't needed for 3.5, but
are good to have now, and some other minor fixes/changes in the driver
core.
All of these have been in the linux-next releases for a while now.
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>"
* tag 'driver-core-3.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core: (38 commits)
printk: Export struct log size and member offsets through vmcoreinfo
Drivers: hv: Change the hex constant to a decimal constant
driver core: don't trigger uevent after failure
extcon: MAX77693: Add extcon-max77693 driver to support Maxim MAX77693 MUIC device
sysfs: fail dentry revalidation after namespace change fix
sysfs: fail dentry revalidation after namespace change
extcon: spelling of detach in function doc
extcon: arizona: Stop microphone detection if we give up on it
extcon: arizona: Update cable reporting calls and split headset
PM / Runtime: Do not increment device usage counts before probing
kmsg - do not flush partial lines when the console is busy
kmsg - export "continuation record" flag to /dev/kmsg
kmsg - avoid warning for CONFIG_PRINTK=n compilations
kmsg - properly print over-long continuation lines
driver-core: Use kobj_to_dev instead of re-implementing it
driver-core: Move kobj_to_dev from genhd.h to device.h
driver core: Move deferred devices to the end of dpm_list before probing
driver core: move uevent call to driver_register
driver core: fix shutdown races with probe/remove(v3)
Extcon: Arizona: Add driver for Wolfson Arizona class devices
...
Commit a7a20d1039 ("sd: limit the scope of the async probe domain")
make the SCSI device probing run device discovery in it's own async
domain.
However, as a result, the partition detection was no longer synchronized
by async_synchronize_full() (which, despite the name, only synchronizes
the global async space, not all of them). Which in turn meant that
"wait_for_device_probe()" would not wait for the SCSI partitions to be
parsed.
And "wait_for_device_probe()" was what the boot time init code relied on
for mounting the root filesystem.
Now, most people never noticed this, because not only is it
timing-dependent, but modern distributions all use initrd. So the root
filesystem isn't actually on a disk at all. And then before they
actually mount the final disk filesystem, they will have loaded the
scsi-wait-scan module, which not only does the expected
wait_for_device_probe(), but also does scsi_complete_async_scans().
[ Side note: scsi_complete_async_scans() had also been partially broken,
but that was fixed in commit 43a8d39d01 ("fix async probe
regression"), so that same commit a7a20d1039 had actually broken
setups even if you used scsi-wait-scan explicitly ]
Solve this problem by just moving the scsi_complete_async_scans() call
into wait_for_device_probe(). Everybody who wants to wait for device
probing to finish really wants the SCSI probing to complete, so there's
no reason not to do this.
So now "wait_for_device_probe()" really does what the name implies, and
properly waits for device probing to finish. This also removes the now
unnecessary extra calls to scsi_complete_async_scans().
Reported-and-tested-by: Artem S. Tashkinov <t.artem@mailcity.com>
Cc: Dan Williams <dan.j.williams@gmail.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: James Bottomley <jbottomley@parallels.com>
Cc: Borislav Petkov <bp@amd64.org>
Cc: linux-scsi <linux-scsi@vger.kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This function is not really specific to the genhd layer and there are various
re-implementations or open-coded variants of it all throughout the kernel. To
avoid further duplications move the function to a more generic place.
While moving also convert it from a macro to a inline function.
Potential users of this function can be detected and converted using the
following coccinelle patch:
// <smpl>
@@
expression k;
@@
-container_of(k, struct device, kobj)
+kobj_to_dev(kobj)
// </smpl>
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
