There are several races reported in cpufreq core around governors (only
ondemand and conservative) by different people.

There are at least two race scenarios present in governor code:
 (a) Concurrent access/updates of governor internal structures.

 It is possible that fields such as 'dbs_data->usage_count', etc.  are
 accessed simultaneously for different policies using same governor
 structure (i.e. CPUFREQ_HAVE_GOVERNOR_PER_POLICY flag unset). And
 because of this we can dereference bad pointers.

 For example consider a system with two CPUs with separate 'struct
 cpufreq_policy' instances. CPU0 governor: ondemand and CPU1: powersave.
 CPU0 switching to powersave and CPU1 to ondemand:
	CPU0				CPU1

	store*				store*

	cpufreq_governor_exit()		cpufreq_governor_init()
					dbs_data = cdata->gdbs_data;

	if (!--dbs_data->usage_count)
		kfree(dbs_data);

					dbs_data->usage_count++;
					*Bad pointer dereference*

 There are other races possible between EXIT and START/STOP/LIMIT as
 well. Its really complicated.

 (b) Switching governor state in bad sequence:

 For example trying to switch a governor to START state, when the
 governor is in EXIT state. There are some checks present in
 __cpufreq_governor() but they aren't sufficient as they compare events
 against 'policy->governor_enabled', where as we need to take governor's
 state into account, which can be used by multiple policies.

These two issues need to be solved separately and the responsibility
should be properly divided between cpufreq and governor core.

The first problem is more about the governor core, as it needs to
protect its structures properly. And the second problem should be fixed
in cpufreq core instead of governor, as its all about sequence of
events.

This patch is trying to solve only the first problem.

There are two types of data we need to protect,
- 'struct common_dbs_data': No matter what, there is going to be a
  single copy of this per governor.
- 'struct dbs_data': With CPUFREQ_HAVE_GOVERNOR_PER_POLICY flag set, we
  will have per-policy copy of this data, otherwise a single copy.

Because of such complexities, the mutex present in 'struct dbs_data' is
insufficient to solve our problem. For example we need to protect
fetching of 'dbs_data' from different structures at the beginning of
cpufreq_governor_dbs(), to make sure it isn't currently being updated.

This can be fixed if we can guarantee serialization of event parsing
code for an individual governor. This is best solved with a mutex per
governor, and the placeholder for that is 'struct common_dbs_data'.

And so this patch moves the mutex from 'struct dbs_data' to 'struct
common_dbs_data' and takes it at the beginning and drops it at the end
of cpufreq_governor_dbs().

Tested with and without following configuration options:

CONFIG_LOCKDEP_SUPPORT=y
CONFIG_DEBUG_RT_MUTEXES=y
CONFIG_DEBUG_PI_LIST=y
CONFIG_DEBUG_SPINLOCK=y
CONFIG_DEBUG_MUTEXES=y
CONFIG_DEBUG_LOCK_ALLOC=y
CONFIG_PROVE_LOCKING=y
CONFIG_LOCKDEP=y
CONFIG_DEBUG_ATOMIC_SLEEP=y
Signed-off-by: NViresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: NPreeti U Murthy <preeti@linux.vnet.ibm.com>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

cpufreq_governor_dbs() is hardly readable, it is just too big and
complicated. Lets make it more readable by splitting out event specific
routines.

Order of statements is changed at few places, but that shouldn't bring
any functional change.
Signed-off-by: NViresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: NPreeti U Murthy <preeti@linux.vnet.ibm.com>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

Notifiers are required only for conservative governor and the common
governor code is unnecessarily polluted with that. Handle that from
cs_init/exit() instead of cpufreq_governor_dbs().
Signed-off-by: NViresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: NPreeti U Murthy <preeti@linux.vnet.ibm.com>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

cpufreq_update_policy() was kept as a separate routine earlier as it was
handling migration of sysfs directories, which isn't the case anymore.
It is only updating policy->cpu now and is called by a single caller.

The WARN_ON() isn't really required anymore, as we are just updating the
cpu now, not moving the sysfs directories.
Signed-off-by: NViresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

__cpufreq_remove_dev_finish() is doing two things today:
- Restarts the governor if some CPUs from concerned policy are still
  online.
- Frees the policy if all CPUs are offline.

The first task of restarting the governor can be moved to
__cpufreq_remove_dev_prepare() to restart the governor early. There is
no race between _prepare() and _finish() as they would be handling
completely different cases. _finish() will only be required if we are
going to free the policy and that has nothing to do with restarting the
governor.
Original-by: NSaravana Kannan <skannan@codeaurora.org>
Signed-off-by: NViresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

cpufreq_policy_put_kobj() is actually part of freeing the policy and can
be called from cpufreq_policy_free() directly instead of a separate
call.
Signed-off-by: NViresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

policy->kobj is required to be initialized once in the lifetime of a
policy.  Currently we are initializing it from __cpufreq_add_dev() and
that doesn't look to be the best place for doing so as we have to do
this on special cases (like: !recover_policy).

We can initialize it from a more obvious place cpufreq_policy_alloc()
and that will make code look cleaner, specially the error handling part.

The error handling part of __cpufreq_add_dev() was doing almost the same
thing while recover_policy is true or false. Fix that as well by always
calling cpufreq_policy_put_kobj() with an additional parameter to skip
notification part of it.
Signed-off-by: NViresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

When we hot-unplug a cpu, we remove its sysfs cpufreq directory and if
the outgoing cpu was the owner of policy->kobj earlier then we migrate
the sysfs directory to under another online cpu.

There are few disadvantages this brings:
- Code Complexity
- Slower hotplug/suspend/resume
- sysfs file permissions are reset after all policy->cpus are offlined
- CPUFreq stats history lost after all policy->cpus are offlined
- Special management of sysfs stuff during suspend/resume

To overcome these, this patch modifies the way sysfs directories are
managed:
- Select sysfs kobjects owner while initializing policy and don't change
  it during hotplugs. Track it with kobj_cpu created earlier.

- Create symlinks for all related CPUs (can be offline) instead of
  affected CPUs on policy initialization and remove them only when the
  policy is freed.

- Free policy structure only on the removal of cpufreq-driver and not
  during hotplug/suspend/resume, detected by checking 'struct
  subsys_interface *' (Valid only when called from
  subsys_interface_unregister() while unregistering driver).

Apart from this, special care is taken to handle physical hoplug of CPUs
as we wouldn't remove sysfs links or remove policies on logical
hotplugs. Physical hotplug happens in the following sequence.

Hot removal:
- CPU is offlined first, ~ 'echo 0 >
  /sys/devices/system/cpu/cpuX/online'
- Then its device is removed along with all sysfs files, cpufreq core
  notified with cpufreq_remove_dev() callback from subsys-interface..

Hot addition:
- First the device along with its sysfs files is added, cpufreq core
  notified with cpufreq_add_dev() callback from subsys-interface..
- CPU is onlined, ~ 'echo 1 > /sys/devices/system/cpu/cpuX/online'

We call the same routines with both hotplug and subsys callbacks, and we
sense physical hotplug with cpu_offline() check in subsys callback. We
can handle most of the stuff with regular hotplug callback paths and
add/remove cpufreq sysfs links or free policy from subsys callbacks.
Original-by: NSaravana Kannan <skannan@codeaurora.org>
Signed-off-by: NViresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

Later commits would change the way policies are managed today. Policies
wouldn't be freed on cpu hotplug (currently they aren't freed only for
suspend), and while the CPU is offline, the sysfs cpufreq files would
still be present.

User may accidentally try to update the sysfs files in following
directory: '/sys/devices/system/cpu/cpuX/cpufreq/'. And that would
result in undefined behavior as policy wouldn't be active then.

Apart from updating the store() routine, we also update __cpufreq_get()
which can call cpufreq_out_of_sync(). The later routine tries to update
policy->cur and starts notifying kernel about it.
Signed-off-by: NViresh Kumar <viresh.kumar@linaro.org>
Acked-by: NSaravana Kannan <skannan@codeaurora.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

During initialization and exit it is possible that the target pstate
might not actually be set. Furthermore, the result can be that the
driver and the processor are out of synch and, under some conditions,
the driver might never send the processor the proper target pstate.

This patch adds a bypass or do_checks flag to the call to
intel_pstate_set_pstate. If bypass, then specifically bypass clamp
checks and the do not send if it is the same as last time check. If
do_checks, then, and as before, do the current policy clamp checks,
and do not do actual send if the new target is the same as the old.
Signed-off-by: NDoug Smythies <dsmythies@telus.net>
Reported-by: NMarien Zwart <marien.zwart@gmail.com>
Reported-by: NAlex Lochmann <alexander.lochmann@tu-dortmund.de>
Reported-by: NPiotr Ko?aczkowski <pkolaczk@gmail.com>
Reported-by: NClemens Eisserer <linuxhippy@gmail.com>
Tested-by: NMarien Zwart <marien.zwart@gmail.com>
Tested-by: NDoug Smythies <dsmythies@telus.net>
[ rjw: Dropped pointless symbol definitions, rebased ]
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

Commit ce717613 (intel_pstate: Turn per cpu printk into pr_debug)
turned per cpu printk into pr_debug.  However, only half of the change
was done, introducing an inconsistency between entry and exit from
driver pstate control.  This patch changes the exit message to pr_debug
also.

The various messages are inconsistent with respect to any identifier
text that can be used to help isolate the desired information from a
huge log.  This patch makes a consistent identifier portion of the
string.

Amends: ce717613 (intel_pstate: Turn per cpu printk into pr_debug)
Signed-off-by: NDoug Smythies <dsmythies@telus.net>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

In order to prepare for the next few commits, that will stop migrating
sysfs files on cpu hotplug, this patch starts managing sysfs-cpu
separately.

The behavior is still the same as we are still migrating sysfs files on
hotplug, later commits would change that.
Signed-off-by: NSaravana Kannan <skannan@codeaurora.org>
Signed-off-by: NViresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

Signed-off-by: NShailendra Verma <shailendra.capricorn@gmail.com>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

Later commits would change the way policies are managed today. Policies
wouldn't be freed on cpu hotplug (currently they aren't freed on
suspend), and while the CPU is offline, the sysfs cpufreq files would
still be present.

Because we don't mark policy->governor as NULL, it still contains
pointer of the last used governor. And if the governor is removed, while
all the CPUs of a policy are hotplugged out, this pointer wouldn't be
valid anymore. And if we try to read the 'scaling_governor', etc.  from
sysfs, it will result in kernel OOPs.

To prevent this, mark policy->governor as NULL for all inactive policies
while the governor is removed from kernel.
Signed-off-by: NViresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

History of which governor was used last is common to all CPUs within a
policy and maintaining it per-cpu isn't the best approach for sure.

Apart from wasting memory, this also increases the complexity of
managing this data structure as it has to be updated for all CPUs.

To make that somewhat simpler, lets store this information in a new
field 'last_governor' in struct cpufreq_policy and update it on removal
of last cpu of a policy.

As a side-effect it also solves an old problem, consider a system with
two clusters 0 & 1. And there is one policy per cluster.

Cluster 0: CPU0 and 1.
Cluster 1: CPU2 and 3.

 - CPU2 is first brought online, and governor is set to performance
   (default as cpufreq_cpu_governor wasn't set).
 - Governor is changed to ondemand.
 - CPU2 is taken offline and cpufreq_cpu_governor is updated for CPU2.
 - CPU3 is brought online.
 - Because cpufreq_cpu_governor wasn't set for CPU3, the default governor
   performance is picked for CPU3.

This patch fixes the bug as we now have a single variable to update for
policy.
Signed-off-by: NViresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

We reach here while adding policy for a CPU and enter into the 'if'
block only if a policy already exists for the CPU.

As cpufreq_cpu_data is set for all policy->related_cpus now, when the
policy is first added, we can use that to find the CPU's policy instead
of traversing the list of all active policies.
Acked-by: NSaravana Kannan <skannan@codeaurora.org>
Signed-off-by: NViresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

We can extract the same information from cpufreq_cpu_data as it is also
available for inactive policies now. And so don't need
cpufreq_cpu_data_fallback anymore.

Also add a WARN_ON() for the case where we try to restore from an active
policy.
Acked-by: NSaravana Kannan <skannan@codeaurora.org>
Signed-off-by: NViresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

Now that we can check policy->cpus to find if policy is active or not,
we don't need to clean cpufreq_cpu_data and delete policy from the list
on light weight tear down of policies (like in suspend).

To make it consistent and clean, set cpufreq_cpu_data for all related
CPUs when the policy is first created and clean it only while it is
freed.

Also update cpufreq_cpu_get_raw() to check if cpu is part of
policy->cpus mask, so that we don't end up getting policies for offline
CPUs.

In order to make sure that no users of 'policy' are using an inactive
policy, use cpufreq_cpu_get_raw() instead of directly accessing
cpufreq_cpu_data.
Signed-off-by: NViresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

policy->cpus is cleared unconditionally now on hotplug-out of a CPU and
it can be checked to know if a policy is active or not. Create helper
routines to iterate over all active/inactive policies, based on
policy->cpus field.

Replace all instances of for_each_policy() with for_each_active_policy()
to make them iterate only for active policies. (We haven't made changes
yet to keep inactive policies in the same list, but that will be
followed in a later patch).
Signed-off-by: NViresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

With the addition of switcher code, there's compile-time dependency on
BIG_LITTLE to get arm_big_little driver compiling on ARM64. Since ARM64
will never add support for bL switcher, it's better to remove the
dependency so that the driver can be reused on ARM64 platforms.

This patch adds stubs to remove BIG_LITTLE dependency in the driver.
Signed-off-by: NSudeep Holla <sudeep.holla@arm.com>
Acked-by: NViresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

Commit 007bea09 (intel_pstate: Add setting voltage value for
baytrail P states.) introduced byt_set_pstate() with the assumption that
it would always be run by the CPU whose MSR is to be written by it.  It
turns out, however, that is not always the case in practice, so modify
byt_set_pstate() to enforce the MSR write done by it to always happen on
the right CPU.

Fixes: 007bea09 (intel_pstate: Add setting voltage value for baytrail P states.)
Signed-off-by: NJoe Konno <joe.konno@intel.com>
Acked-by: NKristen Carlson Accardi <kristen@linux.intel.com>
Cc: 3.14+ <stable@vger.kernel.org> # 3.14+
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

We clear policy->cpus mask while CPUs are hotplugged out. We do it for all CPUs
except the last CPU of the policy. I don't remember what the rationale behind
that was, but I couldn't think of anything that will break if we remove this
conditional clearing and always clear policy->cpus.

The benefit we get out of it is, we can know if a policy is active or not by
checking if this field is empty or not. That will be used by later commits.
Signed-off-by: NViresh Kumar <viresh.kumar@linaro.org>
Acked-by: NSaravana Kannan <skannan@codeaurora.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

There are two cases when we may try to add CPUs we're already handling:
 - On boot, the first cpu has marked all policy->cpus managed and so we
   will find policy for all other policy->cpus later on.
 - When a managed cpu is hotplugged out and later brought back in.

Currently, separate paths and checks take care of the two.  While the
first one is detected by testing cpu against 'policy->cpus', the other
one is detected by testing cpu against 'policy->related_cpus'.

We can handle them both via a single path and there is no need to do
special checking for the first one.
Signed-off-by: NViresh Kumar <viresh.kumar@linaro.org>
Acked-by: NSaravana Kannan <skannan@codeaurora.org>
[ rjw: Changelog, comments ]
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

Simply returning here with an error is not enough. It shouldn't be allowed at
all to try calling cpufreq_cpu_get() for an invalid CPU.

Add a WARN here to make it clear that it wouldn't be acceptable at all.
Signed-off-by: NViresh Kumar <viresh.kumar@linaro.org>
Acked-by: NSaravana Kannan <skannan@codeaurora.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

cpufreq_add_dev() is an unnecessary wrapper over __cpufreq_add_dev(). Merge
them.
Signed-off-by: NViresh Kumar <viresh.kumar@linaro.org>
Acked-by: NSaravana Kannan <skannan@codeaurora.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

This clearly states what the code inside these routines is doing and how these
must be used.
Signed-off-by: NViresh Kumar <viresh.kumar@linaro.org>
Acked-by: NSaravana Kannan <skannan@codeaurora.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

The intel_pstate driver is difficult to debug and investigate without tsc.

Also, it is likely use of tsc, and some version of C0 percentage,
will be re-introdcued in futute.

There have also been occasions where it is desirebale to know, and
confirm, the previous target pstate.

This patch brings back tsc, adds previous target pstate,
and adds both to the trace data collection.
Signed-off-by: NDoug Smythies <dsmythies@telus.net>
Acked-by: NKristen Carlson Accardi <kristen@linux.intel.com>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

The "cpu-cluster.<n>" used to get the cluster clock is not used by any
platform. Moreover __of_clk_get_by_name used in clk_get return error if
the "clock-names" in the DT doesn't match this string. When using DT,
it's not compulsory to specify the clock name unless there are multiple
clock input entries in the consumer.

This patch removes the unused clock string from the driver.
Acked-by: NViresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: NSudeep Holla <sudeep.holla@arm.com>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

The actual frequency is set through "clk_change_rate" which is void
function. If the underlying hardware fails and returns error, the error
is lost in the clk layer. In order to track such failures, we need to
read back the frequency(just the cached value as clk_recalc called after
clk->ops->set_rate gets the frequency)

This patch adds check to see if the frequency is set correctly or if
they were any hardware failures and sends the appropriate errors to the
cpufreq core.
Reviewed-by: NMichael Turquette <mike.turquette@linaro.org>
Signed-off-by: NSudeep Holla <sudeep.holla@arm.com>
Acked-by: NViresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

pxa255_run_freqs and pxa255_turbo_freqs are only read.
This patch updates arrays declaration, find_freq_tables()
and its callsites.
Suggested-by: NJoe Perches <joe@perches.com>
Signed-off-by: NFabian Frederick <fabf@skynet.be>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

typedef is not really useful here. Replace it by structure
to improve readability. typedef should only be used in some cases.
(See Documentation/CodingStyle Chapter 5 for details).
Signed-off-by: NFabian Frederick <fabf@skynet.be>
Acked-by: NViresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

When we end I/O struct request with error, we need to pass
obj_request->length as @nr_bytes so that the entire obj_request worth
of bytes is completed.  Otherwise block layer ends up confused and we
trip on

    rbd_assert(more ^ (which == img_request->obj_request_count));

in rbd_img_obj_callback() due to more being true no matter what.  We
already do it in most cases but we are missing some, in particular
those where we don't even get a chance to submit any obj_requests, due
to an early -ENOMEM for example.

A number of obj_request->xferred assignments seem to be redundant but
I haven't touched any of obj_request->xferred stuff to keep this small
and isolated.

Cc: Alex Elder <elder@linaro.org>
Cc: stable@vger.kernel.org # 3.10+
Reported-by: NShawn Edwards <lesser.evil@gmail.com>
Reviewed-by: NSage Weil <sage@redhat.com>
Signed-off-by: NIlya Dryomov <idryomov@gmail.com>

RGMII-ID uses an internal delay within the transmitter or receiver. This
feature is phy specific. The rest of the communication is normal RGMII.

So the fec driver has to check for all RGMII modes, not only
'PHY_INTERFACE_MODE_RGMII'.
Signed-off-by: NMarkus Pargmann <mpa@pengutronix.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When system is out of memory, refilling of RX buffers fails while
the driver continue to pass the received packets to the kernel stack.
At some point, when all RX buffers deplete, driver may fall into a
sleep, and not recover when memory for new RX buffers is once again
availible. This is because hardware does not have valid descriptors,
so no interrupt will be generated for the driver to return to work
in napi context. Fix it by schedule the napi poll function from
stats_task delayed workqueue, as long as the allocations fail.
Signed-off-by: NIdo Shamay <idos@mellanox.com>
Signed-off-by: NAmir Vadai <amirv@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

While testing this driver with DEBUG_LOCKDEP and DEBUG_SPINLOCK
enabled did not produce any traces, it would be more prudent in the
case of tx_clean_lock to use spin_[un]lock_bh, since this lock is
manipulated in both the process and softirq contexts.

This patch was tested for functionality and regressions with netperf
and DEBUG_LOCKDEP and DEBUG_SPINLOCK enabled.
Signed-off-by: NTony Camuso <tcamuso@redhat.com>
Acked-by: NNeil Horman <nhorman@tuxdriver.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Addresses the following kernel logs seen during boot:

Kernel unaligned access at TPC[100ee150] mlx4_QUERY_HCA+0x80/0x248 [mlx4_core]
Kernel unaligned access at TPC[100f071c] mlx4_QUERY_ADAPTER+0x100/0x12c [mlx4_core]
Kernel unaligned access at TPC[100f071c] mlx4_QUERY_ADAPTER+0x100/0x12c [mlx4_core]
Kernel unaligned access at TPC[100f071c] mlx4_QUERY_ADAPTER+0x100/0x12c [mlx4_core]
Kernel unaligned access at TPC[100f071c] mlx4_QUERY_ADAPTER+0x100/0x12c [mlx4_core]
Signed-off-by: NDavid Ahern <david.ahern@oracle.com>
Acked-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NBenjamin Poirier <bpoirier@suse.de>
Fixes: 9e311e77 ("net/mlx4_en: Use affinity hint")
Acked-by: NAmir Vadai <amirv@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Commit 02233342 ("dm: optimize dm_mq_queue_rq to _not_ use kthread if
using pure blk-mq") mistakenly removed free_rq_clone()'s clone->q check
before testing clone->q->mq_ops.  It was an oversight to discontinue
that check for 1 of the 2 use-cases for free_rq_clone():
1) free_rq_clone() called when an unmapped original request is requeued
2) free_rq_clone() called in the request-based IO completion path

The clone->q check made sense for case #1 but not for #2.  However, we
cannot just reinstate the check as it'd mask a serious bug in the IO
completion case #2 -- no in-flight request should have an uninitialized
request_queue (basic block layer refcounting _should_ ensure this).

The NULL pointer seen for case #1 is detailed here:
https://www.redhat.com/archives/dm-devel/2015-April/msg00160.html

Fix this free_rq_clone() NULL pointer by simply checking if the
mapped_device's type is DM_TYPE_MQ_REQUEST_BASED (clone's queue is
blk-mq) rather than checking clone->q->mq_ops.  This avoids the need to
dereference clone->q, but a WARN_ON_ONCE is added to let us know if an
uninitialized clone request is being completed.
Reported-by: NBart Van Assche <bart.vanassche@sandisk.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

Commit bfebd1cd ("dm: add full blk-mq support to request-based DM")
didn't properly account for the need to short-circuit re-initializing
DM's blk-mq request_queue if it was already initialized.

Otherwise, reloading a blk-mq request-based DM table (either manually
or via multipathd) resulted in errors, see:
 https://www.redhat.com/archives/dm-devel/2015-April/msg00132.html

Fix is to only initialize the request_queue on the initial table load
(when the mapped_device type is assigned).

This is better than having dm_init_request_based_blk_mq_queue() return
early if the queue was already initialized because it elevates the
constraint to a more meaningful location in DM core.  As such the
pre-existing early return in dm_init_request_based_queue() can now be
removed.

Fixes: bfebd1cd ("dm: add full blk-mq support to request-based DM")
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

Commit 6559a7e8 ("cxgb4: Cleanup macros so they follow the same
style and look consistent") introduced a regression where reading MC1
memory in adapters where MC0 isn't present or MC0 size is not equal to MC1
size caused the adapter to crash due to incorrect computation of memoffset.
Fix is to read the size of MC0 instead of MC1 for offset calculation
Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NHariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>