If the userspace hasn't been prepared to ignore the unreliable "opened"
events and the unreliable initial state notification, Linux users can use
the following kernel parameters to handle the possible issues:
-A. button.lid_init_state=open:
+A. button.lid_init_state=method:
+ When this option is specified, the ACPI button driver reports the
+ initial lid state using the returning value of the _LID control method
+ and whether the "opened"/"closed" events are paired fully relies on the
+ firmware implementation.
+ This option can be used to fix some platforms where the returning value
+ of the _LID control method is reliable but the initial lid state
+ notification is missing.
+ This option is the default behavior during the period the userspace
+ isn't ready to handle the buggy AML tables.
+B. button.lid_init_state=open:
When this option is specified, the ACPI button driver always reports the
initial lid state as "opened" and whether the "opened"/"closed" events
are paired fully relies on the firmware implementation.
This may fix some platforms where the returning value of the _LID
control method is not reliable and the initial lid state notification is
missing.
- This option is the default behavior during the period the userspace
- isn't ready to handle the buggy AML tables.
If the userspace has been prepared to ignore the unreliable "opened" events
and the unreliable initial state notification, Linux users should always
use the following kernel parameter:
-B. button.lid_init_state=ignore:
+C. button.lid_init_state=ignore:
When this option is specified, the ACPI button driver never reports the
initial lid state and there is a compensation mechanism implemented to
ensure that the reliable "closed" notifications can always be delievered
dscc4.setup= [NET]
+ dt_cpu_ftrs= [PPC]
+ Format: {"off" | "known"}
+ Control how the dt_cpu_ftrs device-tree binding is
+ used for CPU feature discovery and setup (if it
+ exists).
+ off: Do not use it, fall back to legacy cpu table.
+ known: Do not pass through unknown features to guests
+ or userspace, only those that the kernel is aware of.
+
dump_apple_properties [X86]
Dump name and content of EFI device properties on
x86 Macs. Useful for driver authors to determine
.. |struct cpufreq_policy| replace:: :c:type:`struct cpufreq_policy <cpufreq_policy>`
+.. |intel_pstate| replace:: :doc:`intel_pstate <intel_pstate>`
=======================
CPU Performance Scaling
interface it comes from and may not be easily represented in an abstract,
platform-independent way. For this reason, ``CPUFreq`` allows scaling drivers
to bypass the governor layer and implement their own performance scaling
-algorithms. That is done by the ``intel_pstate`` scaling driver.
+algorithms. That is done by the |intel_pstate| scaling driver.
``CPUFreq`` Policy Objects
into account. That is achieved by invoking the governor's ``->stop`` and
``->start()`` callbacks, in this order, for the entire policy.
-As mentioned before, the ``intel_pstate`` scaling driver bypasses the scaling
+As mentioned before, the |intel_pstate| scaling driver bypasses the scaling
governor layer of ``CPUFreq`` and provides its own P-state selection algorithms.
-Consequently, if ``intel_pstate`` is used, scaling governors are not attached to
+Consequently, if |intel_pstate| is used, scaling governors are not attached to
new policy objects. Instead, the driver's ``->setpolicy()`` callback is invoked
to register per-CPU utilization update callbacks for each policy. These
callbacks are invoked by the CPU scheduler in the same way as for scaling
-governors, but in the ``intel_pstate`` case they both determine the P-state to
+governors, but in the |intel_pstate| case they both determine the P-state to
use and change the hardware configuration accordingly in one go from scheduler
context.
``scaling_available_governors``
List of ``CPUFreq`` scaling governors present in the kernel that can
- be attached to this policy or (if the ``intel_pstate`` scaling driver is
+ be attached to this policy or (if the |intel_pstate| scaling driver is
in use) list of scaling algorithms provided by the driver that can be
applied to this policy.
the CPU is actually running at (due to hardware design and other
limitations).
- Some scaling drivers (e.g. ``intel_pstate``) attempt to provide
+ Some scaling drivers (e.g. |intel_pstate|) attempt to provide
information more precisely reflecting the current CPU frequency through
this attribute, but that still may not be the exact current CPU
frequency as seen by the hardware at the moment.
``scaling_governor``
The scaling governor currently attached to this policy or (if the
- ``intel_pstate`` scaling driver is in use) the scaling algorithm
+ |intel_pstate| scaling driver is in use) the scaling algorithm
provided by the driver that is currently applied to this policy.
This attribute is read-write and writing to it will cause a new scaling
governor to be attached to this policy or a new scaling algorithm
provided by the scaling driver to be applied to it (in the
- ``intel_pstate`` case), as indicated by the string written to this
+ |intel_pstate| case), as indicated by the string written to this
attribute (which must be one of the names listed by the
``scaling_available_governors`` attribute described above).
the "boost" setting for the whole system. It is not present if the underlying
scaling driver does not support the frequency boost mechanism (or supports it,
but provides a driver-specific interface for controlling it, like
-``intel_pstate``).
+|intel_pstate|).
If the value in this file is 1, the frequency boost mechanism is enabled. This
means that either the hardware can be put into states in which it is able to
:maxdepth: 2
cpufreq
+ intel_pstate
.. only:: subproject and html
--- /dev/null
+===============================================
+``intel_pstate`` CPU Performance Scaling Driver
+===============================================
+
+::
+
+ Copyright (c) 2017 Intel Corp., Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+
+
+General Information
+===================
+
+``intel_pstate`` is a part of the
+:doc:`CPU performance scaling subsystem <cpufreq>` in the Linux kernel
+(``CPUFreq``). It is a scaling driver for the Sandy Bridge and later
+generations of Intel processors. Note, however, that some of those processors
+may not be supported. [To understand ``intel_pstate`` it is necessary to know
+how ``CPUFreq`` works in general, so this is the time to read :doc:`cpufreq` if
+you have not done that yet.]
+
+For the processors supported by ``intel_pstate``, the P-state concept is broader
+than just an operating frequency or an operating performance point (see the
+`LinuxCon Europe 2015 presentation by Kristen Accardi <LCEU2015_>`_ for more
+information about that). For this reason, the representation of P-states used
+by ``intel_pstate`` internally follows the hardware specification (for details
+refer to `Intel® 64 and IA-32 Architectures Software Developer’s Manual
+Volume 3: System Programming Guide <SDM_>`_). However, the ``CPUFreq`` core
+uses frequencies for identifying operating performance points of CPUs and
+frequencies are involved in the user space interface exposed by it, so
+``intel_pstate`` maps its internal representation of P-states to frequencies too
+(fortunately, that mapping is unambiguous). At the same time, it would not be
+practical for ``intel_pstate`` to supply the ``CPUFreq`` core with a table of
+available frequencies due to the possible size of it, so the driver does not do
+that. Some functionality of the core is limited by that.
+
+Since the hardware P-state selection interface used by ``intel_pstate`` is
+available at the logical CPU level, the driver always works with individual
+CPUs. Consequently, if ``intel_pstate`` is in use, every ``CPUFreq`` policy
+object corresponds to one logical CPU and ``CPUFreq`` policies are effectively
+equivalent to CPUs. In particular, this means that they become "inactive" every
+time the corresponding CPU is taken offline and need to be re-initialized when
+it goes back online.
+
+``intel_pstate`` is not modular, so it cannot be unloaded, which means that the
+only way to pass early-configuration-time parameters to it is via the kernel
+command line. However, its configuration can be adjusted via ``sysfs`` to a
+great extent. In some configurations it even is possible to unregister it via
+``sysfs`` which allows another ``CPUFreq`` scaling driver to be loaded and
+registered (see `below <status_attr_>`_).
+
+
+Operation Modes
+===============
+
+``intel_pstate`` can operate in three different modes: in the active mode with
+or without hardware-managed P-states support and in the passive mode. Which of
+them will be in effect depends on what kernel command line options are used and
+on the capabilities of the processor.
+
+Active Mode
+-----------
+
+This is the default operation mode of ``intel_pstate``. If it works in this
+mode, the ``scaling_driver`` policy attribute in ``sysfs`` for all ``CPUFreq``
+policies contains the string "intel_pstate".
+
+In this mode the driver bypasses the scaling governors layer of ``CPUFreq`` and
+provides its own scaling algorithms for P-state selection. Those algorithms
+can be applied to ``CPUFreq`` policies in the same way as generic scaling
+governors (that is, through the ``scaling_governor`` policy attribute in
+``sysfs``). [Note that different P-state selection algorithms may be chosen for
+different policies, but that is not recommended.]
+
+They are not generic scaling governors, but their names are the same as the
+names of some of those governors. Moreover, confusingly enough, they generally
+do not work in the same way as the generic governors they share the names with.
+For example, the ``powersave`` P-state selection algorithm provided by
+``intel_pstate`` is not a counterpart of the generic ``powersave`` governor
+(roughly, it corresponds to the ``schedutil`` and ``ondemand`` governors).
+
+There are two P-state selection algorithms provided by ``intel_pstate`` in the
+active mode: ``powersave`` and ``performance``. The way they both operate
+depends on whether or not the hardware-managed P-states (HWP) feature has been
+enabled in the processor and possibly on the processor model.
+
+Which of the P-state selection algorithms is used by default depends on the
+:c:macro:`CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE` kernel configuration option.
+Namely, if that option is set, the ``performance`` algorithm will be used by
+default, and the other one will be used by default if it is not set.
+
+Active Mode With HWP
+~~~~~~~~~~~~~~~~~~~~
+
+If the processor supports the HWP feature, it will be enabled during the
+processor initialization and cannot be disabled after that. It is possible
+to avoid enabling it by passing the ``intel_pstate=no_hwp`` argument to the
+kernel in the command line.
+
+If the HWP feature has been enabled, ``intel_pstate`` relies on the processor to
+select P-states by itself, but still it can give hints to the processor's
+internal P-state selection logic. What those hints are depends on which P-state
+selection algorithm has been applied to the given policy (or to the CPU it
+corresponds to).
+
+Even though the P-state selection is carried out by the processor automatically,
+``intel_pstate`` registers utilization update callbacks with the CPU scheduler
+in this mode. However, they are not used for running a P-state selection
+algorithm, but for periodic updates of the current CPU frequency information to
+be made available from the ``scaling_cur_freq`` policy attribute in ``sysfs``.
+
+HWP + ``performance``
+.....................
+
+In this configuration ``intel_pstate`` will write 0 to the processor's
+Energy-Performance Preference (EPP) knob (if supported) or its
+Energy-Performance Bias (EPB) knob (otherwise), which means that the processor's
+internal P-state selection logic is expected to focus entirely on performance.
+
+This will override the EPP/EPB setting coming from the ``sysfs`` interface
+(see `Energy vs Performance Hints`_ below).
+
+Also, in this configuration the range of P-states available to the processor's
+internal P-state selection logic is always restricted to the upper boundary
+(that is, the maximum P-state that the driver is allowed to use).
+
+HWP + ``powersave``
+...................
+
+In this configuration ``intel_pstate`` will set the processor's
+Energy-Performance Preference (EPP) knob (if supported) or its
+Energy-Performance Bias (EPB) knob (otherwise) to whatever value it was
+previously set to via ``sysfs`` (or whatever default value it was
+set to by the platform firmware). This usually causes the processor's
+internal P-state selection logic to be less performance-focused.
+
+Active Mode Without HWP
+~~~~~~~~~~~~~~~~~~~~~~~
+
+This is the default operation mode for processors that do not support the HWP
+feature. It also is used by default with the ``intel_pstate=no_hwp`` argument
+in the kernel command line. However, in this mode ``intel_pstate`` may refuse
+to work with the given processor if it does not recognize it. [Note that
+``intel_pstate`` will never refuse to work with any processor with the HWP
+feature enabled.]
+
+In this mode ``intel_pstate`` registers utilization update callbacks with the
+CPU scheduler in order to run a P-state selection algorithm, either
+``powersave`` or ``performance``, depending on the ``scaling_cur_freq`` policy
+setting in ``sysfs``. The current CPU frequency information to be made
+available from the ``scaling_cur_freq`` policy attribute in ``sysfs`` is
+periodically updated by those utilization update callbacks too.
+
+``performance``
+...............
+
+Without HWP, this P-state selection algorithm is always the same regardless of
+the processor model and platform configuration.
+
+It selects the maximum P-state it is allowed to use, subject to limits set via
+``sysfs``, every time the P-state selection computations are carried out by the
+driver's utilization update callback for the given CPU (that does not happen
+more often than every 10 ms), but the hardware configuration will not be changed
+if the new P-state is the same as the current one.
+
+This is the default P-state selection algorithm if the
+:c:macro:`CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE` kernel configuration option
+is set.
+
+``powersave``
+.............
+
+Without HWP, this P-state selection algorithm generally depends on the
+processor model and/or the system profile setting in the ACPI tables and there
+are two variants of it.
+
+One of them is used with processors from the Atom line and (regardless of the
+processor model) on platforms with the system profile in the ACPI tables set to
+"mobile" (laptops mostly), "tablet", "appliance PC", "desktop", or
+"workstation". It is also used with processors supporting the HWP feature if
+that feature has not been enabled (that is, with the ``intel_pstate=no_hwp``
+argument in the kernel command line). It is similar to the algorithm
+implemented by the generic ``schedutil`` scaling governor except that the
+utilization metric used by it is based on numbers coming from feedback
+registers of the CPU. It generally selects P-states proportional to the
+current CPU utilization, so it is referred to as the "proportional" algorithm.
+
+The second variant of the ``powersave`` P-state selection algorithm, used in all
+of the other cases (generally, on processors from the Core line, so it is
+referred to as the "Core" algorithm), is based on the values read from the APERF
+and MPERF feedback registers and the previously requested target P-state.
+It does not really take CPU utilization into account explicitly, but as a rule
+it causes the CPU P-state to ramp up very quickly in response to increased
+utilization which is generally desirable in server environments.
+
+Regardless of the variant, this algorithm is run by the driver's utilization
+update callback for the given CPU when it is invoked by the CPU scheduler, but
+not more often than every 10 ms (that can be tweaked via ``debugfs`` in `this
+particular case <Tuning Interface in debugfs_>`_). Like in the ``performance``
+case, the hardware configuration is not touched if the new P-state turns out to
+be the same as the current one.
+
+This is the default P-state selection algorithm if the
+:c:macro:`CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE` kernel configuration option
+is not set.
+
+Passive Mode
+------------
+
+This mode is used if the ``intel_pstate=passive`` argument is passed to the
+kernel in the command line (it implies the ``intel_pstate=no_hwp`` setting too).
+Like in the active mode without HWP support, in this mode ``intel_pstate`` may
+refuse to work with the given processor if it does not recognize it.
+
+If the driver works in this mode, the ``scaling_driver`` policy attribute in
+``sysfs`` for all ``CPUFreq`` policies contains the string "intel_cpufreq".
+Then, the driver behaves like a regular ``CPUFreq`` scaling driver. That is,
+it is invoked by generic scaling governors when necessary to talk to the
+hardware in order to change the P-state of a CPU (in particular, the
+``schedutil`` governor can invoke it directly from scheduler context).
+
+While in this mode, ``intel_pstate`` can be used with all of the (generic)
+scaling governors listed by the ``scaling_available_governors`` policy attribute
+in ``sysfs`` (and the P-state selection algorithms described above are not
+used). Then, it is responsible for the configuration of policy objects
+corresponding to CPUs and provides the ``CPUFreq`` core (and the scaling
+governors attached to the policy objects) with accurate information on the
+maximum and minimum operating frequencies supported by the hardware (including
+the so-called "turbo" frequency ranges). In other words, in the passive mode
+the entire range of available P-states is exposed by ``intel_pstate`` to the
+``CPUFreq`` core. However, in this mode the driver does not register
+utilization update callbacks with the CPU scheduler and the ``scaling_cur_freq``
+information comes from the ``CPUFreq`` core (and is the last frequency selected
+by the current scaling governor for the given policy).
+
+
+.. _turbo:
+
+Turbo P-states Support
+======================
+
+In the majority of cases, the entire range of P-states available to
+``intel_pstate`` can be divided into two sub-ranges that correspond to
+different types of processor behavior, above and below a boundary that
+will be referred to as the "turbo threshold" in what follows.
+
+The P-states above the turbo threshold are referred to as "turbo P-states" and
+the whole sub-range of P-states they belong to is referred to as the "turbo
+range". These names are related to the Turbo Boost technology allowing a
+multicore processor to opportunistically increase the P-state of one or more
+cores if there is enough power to do that and if that is not going to cause the
+thermal envelope of the processor package to be exceeded.
+
+Specifically, if software sets the P-state of a CPU core within the turbo range
+(that is, above the turbo threshold), the processor is permitted to take over
+performance scaling control for that core and put it into turbo P-states of its
+choice going forward. However, that permission is interpreted differently by
+different processor generations. Namely, the Sandy Bridge generation of
+processors will never use any P-states above the last one set by software for
+the given core, even if it is within the turbo range, whereas all of the later
+processor generations will take it as a license to use any P-states from the
+turbo range, even above the one set by software. In other words, on those
+processors setting any P-state from the turbo range will enable the processor
+to put the given core into all turbo P-states up to and including the maximum
+supported one as it sees fit.
+
+One important property of turbo P-states is that they are not sustainable. More
+precisely, there is no guarantee that any CPUs will be able to stay in any of
+those states indefinitely, because the power distribution within the processor
+package may change over time or the thermal envelope it was designed for might
+be exceeded if a turbo P-state was used for too long.
+
+In turn, the P-states below the turbo threshold generally are sustainable. In
+fact, if one of them is set by software, the processor is not expected to change
+it to a lower one unless in a thermal stress or a power limit violation
+situation (a higher P-state may still be used if it is set for another CPU in
+the same package at the same time, for example).
+
+Some processors allow multiple cores to be in turbo P-states at the same time,
+but the maximum P-state that can be set for them generally depends on the number
+of cores running concurrently. The maximum turbo P-state that can be set for 3
+cores at the same time usually is lower than the analogous maximum P-state for
+2 cores, which in turn usually is lower than the maximum turbo P-state that can
+be set for 1 core. The one-core maximum turbo P-state is thus the maximum
+supported one overall.
+
+The maximum supported turbo P-state, the turbo threshold (the maximum supported
+non-turbo P-state) and the minimum supported P-state are specific to the
+processor model and can be determined by reading the processor's model-specific
+registers (MSRs). Moreover, some processors support the Configurable TDP
+(Thermal Design Power) feature and, when that feature is enabled, the turbo
+threshold effectively becomes a configurable value that can be set by the
+platform firmware.
+
+Unlike ``_PSS`` objects in the ACPI tables, ``intel_pstate`` always exposes
+the entire range of available P-states, including the whole turbo range, to the
+``CPUFreq`` core and (in the passive mode) to generic scaling governors. This
+generally causes turbo P-states to be set more often when ``intel_pstate`` is
+used relative to ACPI-based CPU performance scaling (see `below <acpi-cpufreq_>`_
+for more information).
+
+Moreover, since ``intel_pstate`` always knows what the real turbo threshold is
+(even if the Configurable TDP feature is enabled in the processor), its
+``no_turbo`` attribute in ``sysfs`` (described `below <no_turbo_attr_>`_) should
+work as expected in all cases (that is, if set to disable turbo P-states, it
+always should prevent ``intel_pstate`` from using them).
+
+
+Processor Support
+=================
+
+To handle a given processor ``intel_pstate`` requires a number of different
+pieces of information on it to be known, including:
+
+ * The minimum supported P-state.
+
+ * The maximum supported `non-turbo P-state <turbo_>`_.
+
+ * Whether or not turbo P-states are supported at all.
+
+ * The maximum supported `one-core turbo P-state <turbo_>`_ (if turbo P-states
+ are supported).
+
+ * The scaling formula to translate the driver's internal representation
+ of P-states into frequencies and the other way around.
+
+Generally, ways to obtain that information are specific to the processor model
+or family. Although it often is possible to obtain all of it from the processor
+itself (using model-specific registers), there are cases in which hardware
+manuals need to be consulted to get to it too.
+
+For this reason, there is a list of supported processors in ``intel_pstate`` and
+the driver initialization will fail if the detected processor is not in that
+list, unless it supports the `HWP feature <Active Mode_>`_. [The interface to
+obtain all of the information listed above is the same for all of the processors
+supporting the HWP feature, which is why they all are supported by
+``intel_pstate``.]
+
+
+User Space Interface in ``sysfs``
+=================================
+
+Global Attributes
+-----------------
+
+``intel_pstate`` exposes several global attributes (files) in ``sysfs`` to
+control its functionality at the system level. They are located in the
+``/sys/devices/system/cpu/cpufreq/intel_pstate/`` directory and affect all
+CPUs.
+
+Some of them are not present if the ``intel_pstate=per_cpu_perf_limits``
+argument is passed to the kernel in the command line.
+
+``max_perf_pct``
+ Maximum P-state the driver is allowed to set in percent of the
+ maximum supported performance level (the highest supported `turbo
+ P-state <turbo_>`_).
+
+ This attribute will not be exposed if the
+ ``intel_pstate=per_cpu_perf_limits`` argument is present in the kernel
+ command line.
+
+``min_perf_pct``
+ Minimum P-state the driver is allowed to set in percent of the
+ maximum supported performance level (the highest supported `turbo
+ P-state <turbo_>`_).
+
+ This attribute will not be exposed if the
+ ``intel_pstate=per_cpu_perf_limits`` argument is present in the kernel
+ command line.
+
+``num_pstates``
+ Number of P-states supported by the processor (between 0 and 255
+ inclusive) including both turbo and non-turbo P-states (see
+ `Turbo P-states Support`_).
+
+ The value of this attribute is not affected by the ``no_turbo``
+ setting described `below <no_turbo_attr_>`_.
+
+ This attribute is read-only.
+
+``turbo_pct``
+ Ratio of the `turbo range <turbo_>`_ size to the size of the entire
+ range of supported P-states, in percent.
+
+ This attribute is read-only.
+
+.. _no_turbo_attr:
+
+``no_turbo``
+ If set (equal to 1), the driver is not allowed to set any turbo P-states
+ (see `Turbo P-states Support`_). If unset (equalt to 0, which is the
+ default), turbo P-states can be set by the driver.
+ [Note that ``intel_pstate`` does not support the general ``boost``
+ attribute (supported by some other scaling drivers) which is replaced
+ by this one.]
+
+ This attrubute does not affect the maximum supported frequency value
+ supplied to the ``CPUFreq`` core and exposed via the policy interface,
+ but it affects the maximum possible value of per-policy P-state limits
+ (see `Interpretation of Policy Attributes`_ below for details).
+
+.. _status_attr:
+
+``status``
+ Operation mode of the driver: "active", "passive" or "off".
+
+ "active"
+ The driver is functional and in the `active mode
+ <Active Mode_>`_.
+
+ "passive"
+ The driver is functional and in the `passive mode
+ <Passive Mode_>`_.
+
+ "off"
+ The driver is not functional (it is not registered as a scaling
+ driver with the ``CPUFreq`` core).
+
+ This attribute can be written to in order to change the driver's
+ operation mode or to unregister it. The string written to it must be
+ one of the possible values of it and, if successful, the write will
+ cause the driver to switch over to the operation mode represented by
+ that string - or to be unregistered in the "off" case. [Actually,
+ switching over from the active mode to the passive mode or the other
+ way around causes the driver to be unregistered and registered again
+ with a different set of callbacks, so all of its settings (the global
+ as well as the per-policy ones) are then reset to their default
+ values, possibly depending on the target operation mode.]
+
+ That only is supported in some configurations, though (for example, if
+ the `HWP feature is enabled in the processor <Active Mode With HWP_>`_,
+ the operation mode of the driver cannot be changed), and if it is not
+ supported in the current configuration, writes to this attribute with
+ fail with an appropriate error.
+
+Interpretation of Policy Attributes
+-----------------------------------
+
+The interpretation of some ``CPUFreq`` policy attributes described in
+:doc:`cpufreq` is special with ``intel_pstate`` as the current scaling driver
+and it generally depends on the driver's `operation mode <Operation Modes_>`_.
+
+First of all, the values of the ``cpuinfo_max_freq``, ``cpuinfo_min_freq`` and
+``scaling_cur_freq`` attributes are produced by applying a processor-specific
+multiplier to the internal P-state representation used by ``intel_pstate``.
+Also, the values of the ``scaling_max_freq`` and ``scaling_min_freq``
+attributes are capped by the frequency corresponding to the maximum P-state that
+the driver is allowed to set.
+
+If the ``no_turbo`` `global attribute <no_turbo_attr_>`_ is set, the driver is
+not allowed to use turbo P-states, so the maximum value of ``scaling_max_freq``
+and ``scaling_min_freq`` is limited to the maximum non-turbo P-state frequency.
+Accordingly, setting ``no_turbo`` causes ``scaling_max_freq`` and
+``scaling_min_freq`` to go down to that value if they were above it before.
+However, the old values of ``scaling_max_freq`` and ``scaling_min_freq`` will be
+restored after unsetting ``no_turbo``, unless these attributes have been written
+to after ``no_turbo`` was set.
+
+If ``no_turbo`` is not set, the maximum possible value of ``scaling_max_freq``
+and ``scaling_min_freq`` corresponds to the maximum supported turbo P-state,
+which also is the value of ``cpuinfo_max_freq`` in either case.
+
+Next, the following policy attributes have special meaning if
+``intel_pstate`` works in the `active mode <Active Mode_>`_:
+
+``scaling_available_governors``
+ List of P-state selection algorithms provided by ``intel_pstate``.
+
+``scaling_governor``
+ P-state selection algorithm provided by ``intel_pstate`` currently in
+ use with the given policy.
+
+``scaling_cur_freq``
+ Frequency of the average P-state of the CPU represented by the given
+ policy for the time interval between the last two invocations of the
+ driver's utilization update callback by the CPU scheduler for that CPU.
+
+The meaning of these attributes in the `passive mode <Passive Mode_>`_ is the
+same as for other scaling drivers.
+
+Additionally, the value of the ``scaling_driver`` attribute for ``intel_pstate``
+depends on the operation mode of the driver. Namely, it is either
+"intel_pstate" (in the `active mode <Active Mode_>`_) or "intel_cpufreq" (in the
+`passive mode <Passive Mode_>`_).
+
+Coordination of P-State Limits
+------------------------------
+
+``intel_pstate`` allows P-state limits to be set in two ways: with the help of
+the ``max_perf_pct`` and ``min_perf_pct`` `global attributes
+<Global Attributes_>`_ or via the ``scaling_max_freq`` and ``scaling_min_freq``
+``CPUFreq`` policy attributes. The coordination between those limits is based
+on the following rules, regardless of the current operation mode of the driver:
+
+ 1. All CPUs are affected by the global limits (that is, none of them can be
+ requested to run faster than the global maximum and none of them can be
+ requested to run slower than the global minimum).
+
+ 2. Each individual CPU is affected by its own per-policy limits (that is, it
+ cannot be requested to run faster than its own per-policy maximum and it
+ cannot be requested to run slower than its own per-policy minimum).
+
+ 3. The global and per-policy limits can be set independently.
+
+If the `HWP feature is enabled in the processor <Active Mode With HWP_>`_, the
+resulting effective values are written into its registers whenever the limits
+change in order to request its internal P-state selection logic to always set
+P-states within these limits. Otherwise, the limits are taken into account by
+scaling governors (in the `passive mode <Passive Mode_>`_) and by the driver
+every time before setting a new P-state for a CPU.
+
+Additionally, if the ``intel_pstate=per_cpu_perf_limits`` command line argument
+is passed to the kernel, ``max_perf_pct`` and ``min_perf_pct`` are not exposed
+at all and the only way to set the limits is by using the policy attributes.
+
+
+Energy vs Performance Hints
+---------------------------
+
+If ``intel_pstate`` works in the `active mode with the HWP feature enabled
+<Active Mode With HWP_>`_ in the processor, additional attributes are present
+in every ``CPUFreq`` policy directory in ``sysfs``. They are intended to allow
+user space to help ``intel_pstate`` to adjust the processor's internal P-state
+selection logic by focusing it on performance or on energy-efficiency, or
+somewhere between the two extremes:
+
+``energy_performance_preference``
+ Current value of the energy vs performance hint for the given policy
+ (or the CPU represented by it).
+
+ The hint can be changed by writing to this attribute.
+
+``energy_performance_available_preferences``
+ List of strings that can be written to the
+ ``energy_performance_preference`` attribute.
+
+ They represent different energy vs performance hints and should be
+ self-explanatory, except that ``default`` represents whatever hint
+ value was set by the platform firmware.
+
+Strings written to the ``energy_performance_preference`` attribute are
+internally translated to integer values written to the processor's
+Energy-Performance Preference (EPP) knob (if supported) or its
+Energy-Performance Bias (EPB) knob.
+
+[Note that tasks may by migrated from one CPU to another by the scheduler's
+load-balancing algorithm and if different energy vs performance hints are
+set for those CPUs, that may lead to undesirable outcomes. To avoid such
+issues it is better to set the same energy vs performance hint for all CPUs
+or to pin every task potentially sensitive to them to a specific CPU.]
+
+.. _acpi-cpufreq:
+
+``intel_pstate`` vs ``acpi-cpufreq``
+====================================
+
+On the majority of systems supported by ``intel_pstate``, the ACPI tables
+provided by the platform firmware contain ``_PSS`` objects returning information
+that can be used for CPU performance scaling (refer to the `ACPI specification`_
+for details on the ``_PSS`` objects and the format of the information returned
+by them).
+
+The information returned by the ACPI ``_PSS`` objects is used by the
+``acpi-cpufreq`` scaling driver. On systems supported by ``intel_pstate``
+the ``acpi-cpufreq`` driver uses the same hardware CPU performance scaling
+interface, but the set of P-states it can use is limited by the ``_PSS``
+output.
+
+On those systems each ``_PSS`` object returns a list of P-states supported by
+the corresponding CPU which basically is a subset of the P-states range that can
+be used by ``intel_pstate`` on the same system, with one exception: the whole
+`turbo range <turbo_>`_ is represented by one item in it (the topmost one). By
+convention, the frequency returned by ``_PSS`` for that item is greater by 1 MHz
+than the frequency of the highest non-turbo P-state listed by it, but the
+corresponding P-state representation (following the hardware specification)
+returned for it matches the maximum supported turbo P-state (or is the
+special value 255 meaning essentially "go as high as you can get").
+
+The list of P-states returned by ``_PSS`` is reflected by the table of
+available frequencies supplied by ``acpi-cpufreq`` to the ``CPUFreq`` core and
+scaling governors and the minimum and maximum supported frequencies reported by
+it come from that list as well. In particular, given the special representation
+of the turbo range described above, this means that the maximum supported
+frequency reported by ``acpi-cpufreq`` is higher by 1 MHz than the frequency
+of the highest supported non-turbo P-state listed by ``_PSS`` which, of course,
+affects decisions made by the scaling governors, except for ``powersave`` and
+``performance``.
+
+For example, if a given governor attempts to select a frequency proportional to
+estimated CPU load and maps the load of 100% to the maximum supported frequency
+(possibly multiplied by a constant), then it will tend to choose P-states below
+the turbo threshold if ``acpi-cpufreq`` is used as the scaling driver, because
+in that case the turbo range corresponds to a small fraction of the frequency
+band it can use (1 MHz vs 1 GHz or more). In consequence, it will only go to
+the turbo range for the highest loads and the other loads above 50% that might
+benefit from running at turbo frequencies will be given non-turbo P-states
+instead.
+
+One more issue related to that may appear on systems supporting the
+`Configurable TDP feature <turbo_>`_ allowing the platform firmware to set the
+turbo threshold. Namely, if that is not coordinated with the lists of P-states
+returned by ``_PSS`` properly, there may be more than one item corresponding to
+a turbo P-state in those lists and there may be a problem with avoiding the
+turbo range (if desirable or necessary). Usually, to avoid using turbo
+P-states overall, ``acpi-cpufreq`` simply avoids using the topmost state listed
+by ``_PSS``, but that is not sufficient when there are other turbo P-states in
+the list returned by it.
+
+Apart from the above, ``acpi-cpufreq`` works like ``intel_pstate`` in the
+`passive mode <Passive Mode_>`_, except that the number of P-states it can set
+is limited to the ones listed by the ACPI ``_PSS`` objects.
+
+
+Kernel Command Line Options for ``intel_pstate``
+================================================
+
+Several kernel command line options can be used to pass early-configuration-time
+parameters to ``intel_pstate`` in order to enforce specific behavior of it. All
+of them have to be prepended with the ``intel_pstate=`` prefix.
+
+``disable``
+ Do not register ``intel_pstate`` as the scaling driver even if the
+ processor is supported by it.
+
+``passive``
+ Register ``intel_pstate`` in the `passive mode <Passive Mode_>`_ to
+ start with.
+
+ This option implies the ``no_hwp`` one described below.
+
+``force``
+ Register ``intel_pstate`` as the scaling driver instead of
+ ``acpi-cpufreq`` even if the latter is preferred on the given system.
+
+ This may prevent some platform features (such as thermal controls and
+ power capping) that rely on the availability of ACPI P-states
+ information from functioning as expected, so it should be used with
+ caution.
+
+ This option does not work with processors that are not supported by
+ ``intel_pstate`` and on platforms where the ``pcc-cpufreq`` scaling
+ driver is used instead of ``acpi-cpufreq``.
+
+``no_hwp``
+ Do not enable the `hardware-managed P-states (HWP) feature
+ <Active Mode With HWP_>`_ even if it is supported by the processor.
+
+``hwp_only``
+ Register ``intel_pstate`` as the scaling driver only if the
+ `hardware-managed P-states (HWP) feature <Active Mode With HWP_>`_ is
+ supported by the processor.
+
+``support_acpi_ppc``
+ Take ACPI ``_PPC`` performance limits into account.
+
+ If the preferred power management profile in the FADT (Fixed ACPI
+ Description Table) is set to "Enterprise Server" or "Performance
+ Server", the ACPI ``_PPC`` limits are taken into account by default
+ and this option has no effect.
+
+``per_cpu_perf_limits``
+ Use per-logical-CPU P-State limits (see `Coordination of P-state
+ Limits`_ for details).
+
+
+Diagnostics and Tuning
+======================
+
+Trace Events
+------------
+
+There are two static trace events that can be used for ``intel_pstate``
+diagnostics. One of them is the ``cpu_frequency`` trace event generally used
+by ``CPUFreq``, and the other one is the ``pstate_sample`` trace event specific
+to ``intel_pstate``. Both of them are triggered by ``intel_pstate`` only if
+it works in the `active mode <Active Mode_>`_.
+
+The following sequence of shell commands can be used to enable them and see
+their output (if the kernel is generally configured to support event tracing)::
+
+ # cd /sys/kernel/debug/tracing/
+ # echo 1 > events/power/pstate_sample/enable
+ # echo 1 > events/power/cpu_frequency/enable
+ # cat trace
+ gnome-terminal--4510 [001] ..s. 1177.680733: pstate_sample: core_busy=107 scaled=94 from=26 to=26 mperf=1143818 aperf=1230607 tsc=29838618 freq=2474476
+ cat-5235 [002] ..s. 1177.681723: cpu_frequency: state=2900000 cpu_id=2
+
+If ``intel_pstate`` works in the `passive mode <Passive Mode_>`_, the
+``cpu_frequency`` trace event will be triggered either by the ``schedutil``
+scaling governor (for the policies it is attached to), or by the ``CPUFreq``
+core (for the policies with other scaling governors).
+
+``ftrace``
+----------
+
+The ``ftrace`` interface can be used for low-level diagnostics of
+``intel_pstate``. For example, to check how often the function to set a
+P-state is called, the ``ftrace`` filter can be set to to
+:c:func:`intel_pstate_set_pstate`::
+
+ # cd /sys/kernel/debug/tracing/
+ # cat available_filter_functions | grep -i pstate
+ intel_pstate_set_pstate
+ intel_pstate_cpu_init
+ ...
+ # echo intel_pstate_set_pstate > set_ftrace_filter
+ # echo function > current_tracer
+ # cat trace | head -15
+ # tracer: function
+ #
+ # entries-in-buffer/entries-written: 80/80 #P:4
+ #
+ # _-----=> irqs-off
+ # / _----=> need-resched
+ # | / _---=> hardirq/softirq
+ # || / _--=> preempt-depth
+ # ||| / delay
+ # TASK-PID CPU# |||| TIMESTAMP FUNCTION
+ # | | | |||| | |
+ Xorg-3129 [000] ..s. 2537.644844: intel_pstate_set_pstate <-intel_pstate_timer_func
+ gnome-terminal--4510 [002] ..s. 2537.649844: intel_pstate_set_pstate <-intel_pstate_timer_func
+ gnome-shell-3409 [001] ..s. 2537.650850: intel_pstate_set_pstate <-intel_pstate_timer_func
+ <idle>-0 [000] ..s. 2537.654843: intel_pstate_set_pstate <-intel_pstate_timer_func
+
+Tuning Interface in ``debugfs``
+-------------------------------
+
+The ``powersave`` algorithm provided by ``intel_pstate`` for `the Core line of
+processors in the active mode <powersave_>`_ is based on a `PID controller`_
+whose parameters were chosen to address a number of different use cases at the
+same time. However, it still is possible to fine-tune it to a specific workload
+and the ``debugfs`` interface under ``/sys/kernel/debug/pstate_snb/`` is
+provided for this purpose. [Note that the ``pstate_snb`` directory will be
+present only if the specific P-state selection algorithm matching the interface
+in it actually is in use.]
+
+The following files present in that directory can be used to modify the PID
+controller parameters at run time:
+
+| ``deadband``
+| ``d_gain_pct``
+| ``i_gain_pct``
+| ``p_gain_pct``
+| ``sample_rate_ms``
+| ``setpoint``
+
+Note, however, that achieving desirable results this way generally requires
+expert-level understanding of the power vs performance tradeoff, so extra care
+is recommended when attempting to do that.
+
+
+.. _LCEU2015: http://events.linuxfoundation.org/sites/events/files/slides/LinuxConEurope_2015.pdf
+.. _SDM: http://www.intel.com/content/www/us/en/architecture-and-technology/64-ia-32-architectures-software-developer-system-programming-manual-325384.html
+.. _ACPI specification: http://www.uefi.org/sites/default/files/resources/ACPI_6_1.pdf
+.. _PID controller: https://en.wikipedia.org/wiki/PID_controller
+++ /dev/null
-Intel P-State driver
---------------------
-
-This driver provides an interface to control the P-State selection for the
-SandyBridge+ Intel processors.
-
-The following document explains P-States:
-http://events.linuxfoundation.org/sites/events/files/slides/LinuxConEurope_2015.pdf
-As stated in the document, P-State doesn’t exactly mean a frequency. However, for
-the sake of the relationship with cpufreq, P-State and frequency are used
-interchangeably.
-
-Understanding the cpufreq core governors and policies are important before
-discussing more details about the Intel P-State driver. Based on what callbacks
-a cpufreq driver provides to the cpufreq core, it can support two types of
-drivers:
-- with target_index() callback: In this mode, the drivers using cpufreq core
-simply provide the minimum and maximum frequency limits and an additional
-interface target_index() to set the current frequency. The cpufreq subsystem
-has a number of scaling governors ("performance", "powersave", "ondemand",
-etc.). Depending on which governor is in use, cpufreq core will call for
-transitions to a specific frequency using target_index() callback.
-- setpolicy() callback: In this mode, drivers do not provide target_index()
-callback, so cpufreq core can't request a transition to a specific frequency.
-The driver provides minimum and maximum frequency limits and callbacks to set a
-policy. The policy in cpufreq sysfs is referred to as the "scaling governor".
-The cpufreq core can request the driver to operate in any of the two policies:
-"performance" and "powersave". The driver decides which frequency to use based
-on the above policy selection considering minimum and maximum frequency limits.
-
-The Intel P-State driver falls under the latter category, which implements the
-setpolicy() callback. This driver decides what P-State to use based on the
-requested policy from the cpufreq core. If the processor is capable of
-selecting its next P-State internally, then the driver will offload this
-responsibility to the processor (aka HWP: Hardware P-States). If not, the
-driver implements algorithms to select the next P-State.
-
-Since these policies are implemented in the driver, they are not same as the
-cpufreq scaling governors implementation, even if they have the same name in
-the cpufreq sysfs (scaling_governors). For example the "performance" policy is
-similar to cpufreq’s "performance" governor, but "powersave" is completely
-different than the cpufreq "powersave" governor. The strategy here is similar
-to cpufreq "ondemand", where the requested P-State is related to the system load.
-
-Sysfs Interface
-
-In addition to the frequency-controlling interfaces provided by the cpufreq
-core, the driver provides its own sysfs files to control the P-State selection.
-These files have been added to /sys/devices/system/cpu/intel_pstate/.
-Any changes made to these files are applicable to all CPUs (even in a
-multi-package system, Refer to later section on placing "Per-CPU limits").
-
- max_perf_pct: Limits the maximum P-State that will be requested by
- the driver. It states it as a percentage of the available performance. The
- available (P-State) performance may be reduced by the no_turbo
- setting described below.
-
- min_perf_pct: Limits the minimum P-State that will be requested by
- the driver. It states it as a percentage of the max (non-turbo)
- performance level.
-
- no_turbo: Limits the driver to selecting P-State below the turbo
- frequency range.
-
- turbo_pct: Displays the percentage of the total performance that
- is supported by hardware that is in the turbo range. This number
- is independent of whether turbo has been disabled or not.
-
- num_pstates: Displays the number of P-States that are supported
- by hardware. This number is independent of whether turbo has
- been disabled or not.
-
-For example, if a system has these parameters:
- Max 1 core turbo ratio: 0x21 (Max 1 core ratio is the maximum P-State)
- Max non turbo ratio: 0x17
- Minimum ratio : 0x08 (Here the ratio is called max efficiency ratio)
-
-Sysfs will show :
- max_perf_pct:100, which corresponds to 1 core ratio
- min_perf_pct:24, max_efficiency_ratio / max 1 Core ratio
- no_turbo:0, turbo is not disabled
- num_pstates:26 = (max 1 Core ratio - Max Efficiency Ratio + 1)
- turbo_pct:39 = (max 1 core ratio - max non turbo ratio) / num_pstates
-
-Refer to "Intel® 64 and IA-32 Architectures Software Developer’s Manual
-Volume 3: System Programming Guide" to understand ratios.
-
-There is one more sysfs attribute in /sys/devices/system/cpu/intel_pstate/
-that can be used for controlling the operation mode of the driver:
-
- status: Three settings are possible:
- "off" - The driver is not in use at this time.
- "active" - The driver works as a P-state governor (default).
- "passive" - The driver works as a regular cpufreq one and collaborates
- with the generic cpufreq governors (it sets P-states as
- requested by those governors).
- The current setting is returned by reads from this attribute. Writing one
- of the above strings to it changes the operation mode as indicated by that
- string, if possible. If HW-managed P-states (HWP) are enabled, it is not
- possible to change the driver's operation mode and attempts to write to
- this attribute will fail.
-
-cpufreq sysfs for Intel P-State
-
-Since this driver registers with cpufreq, cpufreq sysfs is also presented.
-There are some important differences, which need to be considered.
-
-scaling_cur_freq: This displays the real frequency which was used during
-the last sample period instead of what is requested. Some other cpufreq driver,
-like acpi-cpufreq, displays what is requested (Some changes are on the
-way to fix this for acpi-cpufreq driver). The same is true for frequencies
-displayed at /proc/cpuinfo.
-
-scaling_governor: This displays current active policy. Since each CPU has a
-cpufreq sysfs, it is possible to set a scaling governor to each CPU. But this
-is not possible with Intel P-States, as there is one common policy for all
-CPUs. Here, the last requested policy will be applicable to all CPUs. It is
-suggested that one use the cpupower utility to change policy to all CPUs at the
-same time.
-
-scaling_setspeed: This attribute can never be used with Intel P-State.
-
-scaling_max_freq/scaling_min_freq: This interface can be used similarly to
-the max_perf_pct/min_perf_pct of Intel P-State sysfs. However since frequencies
-are converted to nearest possible P-State, this is prone to rounding errors.
-This method is not preferred to limit performance.
-
-affected_cpus: Not used
-related_cpus: Not used
-
-For contemporary Intel processors, the frequency is controlled by the
-processor itself and the P-State exposed to software is related to
-performance levels. The idea that frequency can be set to a single
-frequency is fictional for Intel Core processors. Even if the scaling
-driver selects a single P-State, the actual frequency the processor
-will run at is selected by the processor itself.
-
-Per-CPU limits
-
-The kernel command line option "intel_pstate=per_cpu_perf_limits" forces
-the intel_pstate driver to use per-CPU performance limits. When it is set,
-the sysfs control interface described above is subject to limitations.
-- The following controls are not available for both read and write
- /sys/devices/system/cpu/intel_pstate/max_perf_pct
- /sys/devices/system/cpu/intel_pstate/min_perf_pct
-- The following controls can be used to set performance limits, as far as the
-architecture of the processor permits:
- /sys/devices/system/cpu/cpu*/cpufreq/scaling_max_freq
- /sys/devices/system/cpu/cpu*/cpufreq/scaling_min_freq
- /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
-- User can still observe turbo percent and number of P-States from
- /sys/devices/system/cpu/intel_pstate/turbo_pct
- /sys/devices/system/cpu/intel_pstate/num_pstates
-- User can read write system wide turbo status
- /sys/devices/system/cpu/no_turbo
-
-Support of energy performance hints
-It is possible to provide hints to the HWP algorithms in the processor
-to be more performance centric to more energy centric. When the driver
-is using HWP, two additional cpufreq sysfs attributes are presented for
-each logical CPU.
-These attributes are:
- - energy_performance_available_preferences
- - energy_performance_preference
-
-To get list of supported hints:
-$ cat energy_performance_available_preferences
- default performance balance_performance balance_power power
-
-The current preference can be read or changed via cpufreq sysfs
-attribute "energy_performance_preference". Reading from this attribute
-will display current effective setting. User can write any of the valid
-preference string to this attribute. User can always restore to power-on
-default by writing "default".
-
-Since threads can migrate to different CPUs, this is possible that the
-new CPU may have different energy performance preference than the previous
-one. To avoid such issues, either threads can be pinned to specific CPUs
-or set the same energy performance preference value to all CPUs.
-
-Tuning Intel P-State driver
-
-When the performance can be tuned using PID (Proportional Integral
-Derivative) controller, debugfs files are provided for adjusting performance.
-They are presented under:
-/sys/kernel/debug/pstate_snb/
-
-The PID tunable parameters are:
- deadband
- d_gain_pct
- i_gain_pct
- p_gain_pct
- sample_rate_ms
- setpoint
-
-To adjust these parameters, some understanding of driver implementation is
-necessary. There are some tweeks described here, but be very careful. Adjusting
-them requires expert level understanding of power and performance relationship.
-These limits are only useful when the "powersave" policy is active.
-
--To make the system more responsive to load changes, sample_rate_ms can
-be adjusted (current default is 10ms).
--To make the system use higher performance, even if the load is lower, setpoint
-can be adjusted to a lower number. This will also lead to faster ramp up time
-to reach the maximum P-State.
-If there are no derivative and integral coefficients, The next P-State will be
-equal to:
- current P-State - ((setpoint - current cpu load) * p_gain_pct)
-
-For example, if the current PID parameters are (Which are defaults for the core
-processors like SandyBridge):
- deadband = 0
- d_gain_pct = 0
- i_gain_pct = 0
- p_gain_pct = 20
- sample_rate_ms = 10
- setpoint = 97
-
-If the current P-State = 0x08 and current load = 100, this will result in the
-next P-State = 0x08 - ((97 - 100) * 0.2) = 8.6 (rounded to 9). Here the P-State
-goes up by only 1. If during next sample interval the current load doesn't
-change and still 100, then P-State goes up by one again. This process will
-continue as long as the load is more than the setpoint until the maximum P-State
-is reached.
-
-For the same load at setpoint = 60, this will result in the next P-State
-= 0x08 - ((60 - 100) * 0.2) = 16
-So by changing the setpoint from 97 to 60, there is an increase of the
-next P-State from 9 to 16. So this will make processor execute at higher
-P-State for the same CPU load. If the load continues to be more than the
-setpoint during next sample intervals, then P-State will go up again till the
-maximum P-State is reached. But the ramp up time to reach the maximum P-State
-will be much faster when the setpoint is 60 compared to 97.
-
-Debugging Intel P-State driver
-
-Event tracing
-To debug P-State transition, the Linux event tracing interface can be used.
-There are two specific events, which can be enabled (Provided the kernel
-configs related to event tracing are enabled).
-
-# cd /sys/kernel/debug/tracing/
-# echo 1 > events/power/pstate_sample/enable
-# echo 1 > events/power/cpu_frequency/enable
-# cat trace
-gnome-terminal--4510 [001] ..s. 1177.680733: pstate_sample: core_busy=107
- scaled=94 from=26 to=26 mperf=1143818 aperf=1230607 tsc=29838618
- freq=2474476
-cat-5235 [002] ..s. 1177.681723: cpu_frequency: state=2900000 cpu_id=2
-
-
-Using ftrace
-
-If function level tracing is required, the Linux ftrace interface can be used.
-For example if we want to check how often a function to set a P-State is
-called, we can set ftrace filter to intel_pstate_set_pstate.
-
-# cd /sys/kernel/debug/tracing/
-# cat available_filter_functions | grep -i pstate
-intel_pstate_set_pstate
-intel_pstate_cpu_init
-...
-
-# echo intel_pstate_set_pstate > set_ftrace_filter
-# echo function > current_tracer
-# cat trace | head -15
-# tracer: function
-#
-# entries-in-buffer/entries-written: 80/80 #P:4
-#
-# _-----=> irqs-off
-# / _----=> need-resched
-# | / _---=> hardirq/softirq
-# || / _--=> preempt-depth
-# ||| / delay
-# TASK-PID CPU# |||| TIMESTAMP FUNCTION
-# | | | |||| | |
- Xorg-3129 [000] ..s. 2537.644844: intel_pstate_set_pstate <-intel_pstate_timer_func
- gnome-terminal--4510 [002] ..s. 2537.649844: intel_pstate_set_pstate <-intel_pstate_timer_func
- gnome-shell-3409 [001] ..s. 2537.650850: intel_pstate_set_pstate <-intel_pstate_timer_func
- <idle>-0 [000] ..s. 2537.654843: intel_pstate_set_pstate <-intel_pstate_timer_func
control gpios
- threshold: allows setting the "click"-threshold in the range
- from 20 to 80.
+ from 0 to 80.
- gain: allows setting the sensitivity in the range from 0 to
31. Note that lower values indicate higher
- reg: Base address of PMIC on Hi6220 SoC.
- interrupt-controller: Hi655x has internal IRQs (has own IRQ domain).
- pmic-gpios: The GPIO used by PMIC IRQ.
+- #clock-cells: From common clock binding; shall be set to 0
+
+Optional properties:
+- clock-output-names: From common clock binding to override the
+ default output clock name
Example:
pmic: pmic@f8000000 {
interrupt-controller;
#interrupt-cells = <2>;
pmic-gpios = <&gpio1 2 GPIO_ACTIVE_HIGH>;
+ #clock-cells = <0>;
}
"ext_clock" (External clock provided to the card).
- post-power-on-delay-ms : Delay in ms after powering the card and
de-asserting the reset-gpios (if any)
+- power-off-delay-us : Delay in us after asserting the reset-gpios (if any)
+ during power off of the card.
Example:
- interrupt-controller : Indicates the switch is itself an interrupt
controller. This is used for the PHY interrupts.
#interrupt-cells = <2> : Controller uses two cells, number and flag
+- eeprom-length : Set to the length of an EEPROM connected to the
+ switch. Must be set if the switch can not detect
+ the presence and/or size of a connected EEPROM,
+ otherwise optional.
- mdio : Container of PHY and devices on the switches MDIO
bus.
- mdio? : Container of PHYs and devices on the external MDIO
- phy-reset-active-high : If present then the reset sequence using the GPIO
specified in the "phy-reset-gpios" property is reversed (H=reset state,
L=operation state).
+- phy-reset-post-delay : Post reset delay in milliseconds. If present then
+ a delay of phy-reset-post-delay milliseconds will be observed after the
+ phy-reset-gpios has been toggled. Can be omitted thus no delay is
+ observed. Delay is in range of 1ms to 1000ms. Other delays are invalid.
- phy-supply : regulator that powers the Ethernet PHY.
- phy-handle : phandle to the PHY device connected to this device.
- fixed-link : Assume a fixed link. See fixed-link.txt in the same directory.
bias-pull-up - pull up the pin
bias-pull-down - pull down the pin
bias-pull-pin-default - use pin-default pull state
-bi-directional - pin supports simultaneous input/output operations
drive-push-pull - drive actively high and low
drive-open-drain - drive with open drain
drive-open-source - drive with open source
power-source - select between different power supplies
low-power-enable - enable low power mode
low-power-disable - disable low power mode
-output-enable - enable output on pin regardless of output value
output-low - set the pin to output mode with low level
output-high - set the pin to output mode with high level
slew-rate - set the slew rate
+++ /dev/null
-Hi6220 SoC ION
-===================================================================
-Required properties:
-- compatible : "hisilicon,hi6220-ion"
-- list of the ION heaps
- - heap name : maybe heap_sys_user@0
- - heap id : id should be unique in the system.
- - heap base : base ddr address of the heap,0 means that
- it is dynamic.
- - heap size : memory size and 0 means it is dynamic.
- - heap type : the heap type of the heap, please also
- see the define in ion.h(drivers/staging/android/uapi/ion.h)
--------------------------------------------------------------------
-Example:
- hi6220-ion {
- compatible = "hisilicon,hi6220-ion";
- heap_sys_user@0 {
- heap-name = "sys_user";
- heap-id = <0x0>;
- heap-base = <0x0>;
- heap-size = <0x0>;
- heap-type = "ion_system";
- };
- heap_sys_contig@0 {
- heap-name = "sys_contig";
- heap-id = <0x1>;
- heap-base = <0x0>;
- heap-size = <0x0>;
- heap-type = "ion_system_contig";
- };
- };
- "rockchip,rk3288-usb", "rockchip,rk3066-usb", "snps,dwc2": for rk3288 Soc;
- "lantiq,arx100-usb": The DWC2 USB controller instance in Lantiq ARX SoCs;
- "lantiq,xrx200-usb": The DWC2 USB controller instance in Lantiq XRX SoCs;
+ - "amlogic,meson8-usb": The DWC2 USB controller instance in Amlogic Meson8 SoCs;
- "amlogic,meson8b-usb": The DWC2 USB controller instance in Amlogic Meson8b SoCs;
- "amlogic,meson-gxbb-usb": The DWC2 USB controller instance in Amlogic S905 SoCs;
- "amcc,dwc-otg": The DWC2 USB controller instance in AMCC Canyonlands 460EX SoCs;
The driver allows configuration of the touch screen via a set of sysfs files:
/sys/class/input/eventX/device/device/threshold:
- allows setting the "click"-threshold in the range from 20 to 80.
+ allows setting the "click"-threshold in the range from 0 to 80.
/sys/class/input/eventX/device/device/gain:
allows setting the sensitivity in the range from 0 to 31. Note that
--- /dev/null
+The QorIQ DPAA Ethernet Driver
+==============================
+
+Authors:
+Madalin Bucur <madalin.bucur@nxp.com>
+Camelia Groza <camelia.groza@nxp.com>
+
+Contents
+========
+
+ - DPAA Ethernet Overview
+ - DPAA Ethernet Supported SoCs
+ - Configuring DPAA Ethernet in your kernel
+ - DPAA Ethernet Frame Processing
+ - DPAA Ethernet Features
+ - Debugging
+
+DPAA Ethernet Overview
+======================
+
+DPAA stands for Data Path Acceleration Architecture and it is a
+set of networking acceleration IPs that are available on several
+generations of SoCs, both on PowerPC and ARM64.
+
+The Freescale DPAA architecture consists of a series of hardware blocks
+that support Ethernet connectivity. The Ethernet driver depends upon the
+following drivers in the Linux kernel:
+
+ - Peripheral Access Memory Unit (PAMU) (* needed only for PPC platforms)
+ drivers/iommu/fsl_*
+ - Frame Manager (FMan)
+ drivers/net/ethernet/freescale/fman
+ - Queue Manager (QMan), Buffer Manager (BMan)
+ drivers/soc/fsl/qbman
+
+A simplified view of the dpaa_eth interfaces mapped to FMan MACs:
+
+ dpaa_eth /eth0\ ... /ethN\
+ driver | | | |
+ ------------- ---- ----------- ---- -------------
+ -Ports / Tx Rx \ ... / Tx Rx \
+ FMan | | | |
+ -MACs | MAC0 | | MACN |
+ / dtsec0 \ ... / dtsecN \ (or tgec)
+ / \ / \(or memac)
+ --------- -------------- --- -------------- ---------
+ FMan, FMan Port, FMan SP, FMan MURAM drivers
+ ---------------------------------------------------------
+ FMan HW blocks: MURAM, MACs, Ports, SP
+ ---------------------------------------------------------
+
+The dpaa_eth relation to the QMan, BMan and FMan:
+ ________________________________
+ dpaa_eth / eth0 \
+ driver / \
+ --------- -^- -^- -^- --- ---------
+ QMan driver / \ / \ / \ \ / | BMan |
+ |Rx | |Rx | |Tx | |Tx | | driver |
+ --------- |Dfl| |Err| |Cnf| |FQs| | |
+ QMan HW |FQ | |FQ | |FQs| | | | |
+ / \ / \ / \ \ / | |
+ --------- --- --- --- -v- ---------
+ | FMan QMI | |
+ | FMan HW FMan BMI | BMan HW |
+ ----------------------- --------
+
+where the acronyms used above (and in the code) are:
+DPAA = Data Path Acceleration Architecture
+FMan = DPAA Frame Manager
+QMan = DPAA Queue Manager
+BMan = DPAA Buffers Manager
+QMI = QMan interface in FMan
+BMI = BMan interface in FMan
+FMan SP = FMan Storage Profiles
+MURAM = Multi-user RAM in FMan
+FQ = QMan Frame Queue
+Rx Dfl FQ = default reception FQ
+Rx Err FQ = Rx error frames FQ
+Tx Cnf FQ = Tx confirmation FQs
+Tx FQs = transmission frame queues
+dtsec = datapath three speed Ethernet controller (10/100/1000 Mbps)
+tgec = ten gigabit Ethernet controller (10 Gbps)
+memac = multirate Ethernet MAC (10/100/1000/10000)
+
+DPAA Ethernet Supported SoCs
+============================
+
+The DPAA drivers enable the Ethernet controllers present on the following SoCs:
+
+# PPC
+P1023
+P2041
+P3041
+P4080
+P5020
+P5040
+T1023
+T1024
+T1040
+T1042
+T2080
+T4240
+B4860
+
+# ARM
+LS1043A
+LS1046A
+
+Configuring DPAA Ethernet in your kernel
+========================================
+
+To enable the DPAA Ethernet driver, the following Kconfig options are required:
+
+# common for arch/arm64 and arch/powerpc platforms
+CONFIG_FSL_DPAA=y
+CONFIG_FSL_FMAN=y
+CONFIG_FSL_DPAA_ETH=y
+CONFIG_FSL_XGMAC_MDIO=y
+
+# for arch/powerpc only
+CONFIG_FSL_PAMU=y
+
+# common options needed for the PHYs used on the RDBs
+CONFIG_VITESSE_PHY=y
+CONFIG_REALTEK_PHY=y
+CONFIG_AQUANTIA_PHY=y
+
+DPAA Ethernet Frame Processing
+==============================
+
+On Rx, buffers for the incoming frames are retrieved from one of the three
+existing buffers pools. The driver initializes and seeds these, each with
+buffers of different sizes: 1KB, 2KB and 4KB.
+
+On Tx, all transmitted frames are returned to the driver through Tx
+confirmation frame queues. The driver is then responsible for freeing the
+buffers. In order to do this properly, a backpointer is added to the buffer
+before transmission that points to the skb. When the buffer returns to the
+driver on a confirmation FQ, the skb can be correctly consumed.
+
+DPAA Ethernet Features
+======================
+
+Currently the DPAA Ethernet driver enables the basic features required for
+a Linux Ethernet driver. The support for advanced features will be added
+gradually.
+
+The driver has Rx and Tx checksum offloading for UDP and TCP. Currently the Rx
+checksum offload feature is enabled by default and cannot be controlled through
+ethtool.
+
+The driver has support for multiple prioritized Tx traffic classes. Priorities
+range from 0 (lowest) to 3 (highest). These are mapped to HW workqueues with
+strict priority levels. Each traffic class contains NR_CPU TX queues. By
+default, only one traffic class is enabled and the lowest priority Tx queues
+are used. Higher priority traffic classes can be enabled with the mqprio
+qdisc. For example, all four traffic classes are enabled on an interface with
+the following command. Furthermore, skb priority levels are mapped to traffic
+classes as follows:
+
+ * priorities 0 to 3 - traffic class 0 (low priority)
+ * priorities 4 to 7 - traffic class 1 (medium-low priority)
+ * priorities 8 to 11 - traffic class 2 (medium-high priority)
+ * priorities 12 to 15 - traffic class 3 (high priority)
+
+tc qdisc add dev <int> root handle 1: \
+ mqprio num_tc 4 map 0 0 0 0 1 1 1 1 2 2 2 2 3 3 3 3 hw 1
+
+Debugging
+=========
+
+The following statistics are exported for each interface through ethtool:
+
+ - interrupt count per CPU
+ - Rx packets count per CPU
+ - Tx packets count per CPU
+ - Tx confirmed packets count per CPU
+ - Tx S/G frames count per CPU
+ - Tx error count per CPU
+ - Rx error count per CPU
+ - Rx error count per type
+ - congestion related statistics:
+ - congestion status
+ - time spent in congestion
+ - number of time the device entered congestion
+ - dropped packets count per cause
+
+The driver also exports the following information in sysfs:
+
+ - the FQ IDs for each FQ type
+ /sys/devices/platform/dpaa-ethernet.0/net/<int>/fqids
+
+ - the IDs of the buffer pools in use
+ /sys/devices/platform/dpaa-ethernet.0/net/<int>/bpids
TCP protocol
============
-Last updated: 9 February 2008
+Last updated: 3 June 2017
Contents
========
A congestion control mechanism can be registered through functions in
tcp_cong.c. The functions used by the congestion control mechanism are
registered via passing a tcp_congestion_ops struct to
-tcp_register_congestion_control. As a minimum name, ssthresh,
-cong_avoid must be valid.
+tcp_register_congestion_control. As a minimum, the congestion control
+mechanism must provide a valid name and must implement either ssthresh,
+cong_avoid and undo_cwnd hooks or the "omnipotent" cong_control hook.
Private data for a congestion control mechanism is stored in tp->ca_priv.
tcp_ca(tp) returns a pointer to this space. This is preallocated space - it
is important to check the size of your private data will fit this space, or
-alternatively space could be allocated elsewhere and a pointer to it could
+alternatively, space could be allocated elsewhere and a pointer to it could
be stored here.
There are three kinds of congestion control algorithms currently: The
simplest ones are derived from TCP reno (highspeed, scalable) and just
-provide an alternative the congestion window calculation. More complex
+provide an alternative congestion window calculation. More complex
ones like BIC try to look at other events to provide better
heuristics. There are also round trip time based algorithms like
Vegas and Westwood+.
needs to maintain fairness and performance. Please review current
research and RFC's before developing new modules.
-The method that is used to determine which congestion control mechanism is
-determined by the setting of the sysctl net.ipv4.tcp_congestion_control.
-The default congestion control will be the last one registered (LIFO);
-so if you built everything as modules, the default will be reno. If you
-build with the defaults from Kconfig, then CUBIC will be builtin (not a
-module) and it will end up the default.
+The default congestion control mechanism is chosen based on the
+DEFAULT_TCP_CONG Kconfig parameter. If you really want a particular default
+value then you can set it using sysctl net.ipv4.tcp_congestion_control. The
+module will be autoloaded if needed and you will get the expected protocol. If
+you ask for an unknown congestion method, then the sysctl attempt will fail.
-If you really want a particular default value then you will need
-to set it with the sysctl. If you use a sysctl, the module will be autoloaded
-if needed and you will get the expected protocol. If you ask for an
-unknown congestion method, then the sysctl attempt will fail.
-
-If you remove a tcp congestion control module, then you will get the next
+If you remove a TCP congestion control module, then you will get the next
available one. Since reno cannot be built as a module, and cannot be
-deleted, it will always be available.
+removed, it will always be available.
How the new TCP output machine [nyi] works.
===========================================
6-jack in back, 2-jack in front
6stack-digout
6-jack with a SPDIF out
+6stack-automute
+ 6-jack with headphone jack detection
ALC260
======
Enables docking station I/O for some Lenovos
hp-gpio-led
GPIO LED support on HP laptops
+hp-dock-gpio-mic1-led
+ HP dock with mic LED support
dell-headset-multi
Headset jack, which can also be used as mic-in
dell-headset-dock
Combo jack sensing on ALC283
tpt440-dock
Pin configs for Lenovo Thinkpad Dock support
+tpt440
+ Lenovo Thinkpad T440s setup
+tpt460
+ Lenovo Thinkpad T460/560 setup
+dual-codecs
+ Lenovo laptops with dual codecs
ALC66x/67x/892
==============
Inverted internal mic workaround
dell-headset-multi
Headset jack, which can also be used as mic-in
+dual-codecs
+ Lenovo laptops with dual codecs
ALC680
======
Inverted internal mic workaround
no-primary-hp
VAIO Z/VGC-LN51JGB workaround (for fixed speaker DAC)
+dual-codecs
+ ALC1220 dual codecs for Gaming mobos
ALC861/660
==========
Conexant 5045
=============
-laptop-hpsense
- Laptop with HP sense (old model laptop)
-laptop-micsense
- Laptop with Mic sense (old model fujitsu)
-laptop-hpmicsense
- Laptop with HP and Mic senses
-benq
- Benq R55E
-laptop-hp530
- HP 530 laptop
-test
- for testing/debugging purpose, almost all controls can be
- adjusted. Appearing only when compiled with $CONFIG_SND_DEBUG=y
+cap-mix-amp
+ Fix max input level on mixer widget
+toshiba-p105
+ Toshiba P105 quirk
+hp-530
+ HP 530 quirk
Conexant 5047
=============
-laptop
- Basic Laptop config
-laptop-hp
- Laptop config for some HP models (subdevice 30A5)
-laptop-eapd
- Laptop config with EAPD support
-test
- for testing/debugging purpose, almost all controls can be
- adjusted. Appearing only when compiled with $CONFIG_SND_DEBUG=y
+cap-mix-amp
+ Fix max input level on mixer widget
Conexant 5051
=============
-laptop
- Basic Laptop config (default)
-hp
- HP Spartan laptop
-hp-dv6736
- HP dv6736
-hp-f700
- HP Compaq Presario F700
-ideapad
- Lenovo IdeaPad laptop
-toshiba
- Toshiba Satellite M300
+lenovo-x200
+ Lenovo X200 quirk
Conexant 5066
=============
-laptop
- Basic Laptop config (default)
-hp-laptop
- HP laptops, e g G60
-asus
- Asus K52JU, Lenovo G560
-dell-laptop
- Dell laptops
-dell-vostro
- Dell Vostro
-olpc-xo-1_5
- OLPC XO 1.5
-ideapad
- Lenovo IdeaPad U150
+stereo-dmic
+ Workaround for inverted stereo digital mic
+gpio1
+ Enable GPIO1 pin
+headphone-mic-pin
+ Enable headphone mic NID 0x18 without detection
+tp410
+ Thinkpad T400 & co quirks
thinkpad
- Lenovo Thinkpad
+ Thinkpad mute/mic LED quirk
+lemote-a1004
+ Lemote A1004 quirk
+lemote-a1205
+ Lemote A1205 quirk
+olpc-xo
+ OLPC XO quirk
+mute-led-eapd
+ Mute LED control via EAPD
+hp-dock
+ HP dock support
+mute-led-gpio
+ Mute LED control via GPIO
STAC9200
========
Dell desktops/laptops
alienware
Alienware M17x
+asus-mobo
+ Pin configs for ASUS mobo with 5.1/SPDIF out
auto
BIOS setup (default)
Pin fixup for HP Envy TS bass speaker (NID 0x10)
hp-bnb13-eq
Hardware equalizer setup for HP laptops
+hp-envy-ts-bass
+ HP Envy TS bass support
auto
BIOS setup (default)
Cirrus Logic CS4206/4207
========================
+mbp53
+ MacBook Pro 5,3
mbp55
MacBook Pro 5,5
imac27
IMac 27 Inch
+imac27_122
+ iMac 12,2
+apple
+ Generic Apple quirk
+mbp101
+ MacBookPro 10,1
+mbp81
+ MacBookPro 8,1
+mba42
+ MacBookAir 4,2
auto
BIOS setup (default)
MacBook Air 6,1 and 6,2
gpio0
Enable GPIO 0 amp
+mbp11
+ MacBookPro 11,2
+macmini
+ MacMini 7,1
auto
BIOS setup (default)
registering/unregistering cables and their plugs:
.. kernel-doc:: drivers/usb/typec/typec.c
- :functions: typec_register_cable typec_unregister_cable typec_register_plug
- typec_unregister_plug
+ :functions: typec_register_cable typec_unregister_cable typec_register_plug typec_unregister_plug
The class will provide a handle to struct typec_cable and struct typec_plug if
the registration is successful, or NULL if it isn't.
APIs to report it to the class:
.. kernel-doc:: drivers/usb/typec/typec.c
- :functions: typec_set_data_role typec_set_pwr_role typec_set_vconn_role
- typec_set_pwr_opmode
+ :functions: typec_set_data_role typec_set_pwr_role typec_set_vconn_role typec_set_pwr_opmode
Alternate Modes
~~~~~~~~~~~~~~~
-------------------------------------------------
iTCO_wdt:
heartbeat: Watchdog heartbeat in seconds.
- (2<heartbeat<39 (TCO v1) or 613 (TCO v2), default=30)
+ (5<=heartbeat<=74 (TCO v1) or 1226 (TCO v2), default=30)
nowayout: Watchdog cannot be stopped once started
(default=kernel config parameter)
-------------------------------------------------
M: Sumit Semwal <sumit.semwal@linaro.org>
L: devel@driverdev.osuosl.org
S: Supported
-F: Documentation/devicetree/bindings/staging/ion/
F: drivers/staging/android/ion
F: drivers/staging/android/uapi/ion.h
F: drivers/staging/android/uapi/ion_test.h
ARM/CIRRUS LOGIC EP93XX ARM ARCHITECTURE
M: Hartley Sweeten <hsweeten@visionengravers.com>
-M: Ryan Mallon <rmallon@gmail.com>
+M: Alexander Sverdlin <alexander.sverdlin@gmail.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
F: arch/arm/mach-ep93xx/
M: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
-F: arch/arm/mach-mvebu/
-F: drivers/rtc/rtc-armada38x.c
F: arch/arm/boot/dts/armada*
F: arch/arm/boot/dts/kirkwood*
+F: arch/arm/configs/mvebu_*_defconfig
+F: arch/arm/mach-mvebu/
F: arch/arm64/boot/dts/marvell/armada*
F: drivers/cpufreq/mvebu-cpufreq.c
-F: arch/arm/configs/mvebu_*_defconfig
+F: drivers/irqchip/irq-armada-370-xp.c
+F: drivers/irqchip/irq-mvebu-*
+F: drivers/rtc/rtc-armada38x.c
ARM/Marvell Berlin SoC support
M: Jisheng Zhang <jszhang@marvell.com>
ARM/SAMSUNG EXYNOS ARM ARCHITECTURES
M: Kukjin Kim <kgene@kernel.org>
M: Krzysztof Kozlowski <krzk@kernel.org>
-R: Javier Martinez Canillas <javier@osg.samsung.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
L: linux-samsung-soc@vger.kernel.org (moderated for non-subscribers)
Q: https://patchwork.kernel.org/project/linux-samsung-soc/list/
ARM/STI ARCHITECTURE
M: Patrice Chotard <patrice.chotard@st.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-L: kernel@stlinux.com
W: http://www.stlinux.com
S: Maintained
F: arch/arm/mach-sti/
F: include/linux/spi/cc2520.h
F: Documentation/devicetree/bindings/net/ieee802154/cc2520.txt
+CCREE ARM TRUSTZONE CRYPTOCELL 700 REE DRIVER
+M: Gilad Ben-Yossef <gilad@benyossef.com>
+L: linux-crypto@vger.kernel.org
+L: driverdev-devel@linuxdriverproject.org
+S: Supported
+F: drivers/staging/ccree/
+W: https://developer.arm.com/products/system-ip/trustzone-cryptocell/cryptocell-700-family
+
CEC FRAMEWORK
M: Hans Verkuil <hans.verkuil@cisco.com>
L: linux-media@vger.kernel.org
GENWQE (IBM Generic Workqueue Card)
M: Frank Haverkamp <haver@linux.vnet.ibm.com>
-M: Gabriel Krisman Bertazi <krisman@linux.vnet.ibm.com>
+M: Guilherme G. Piccoli <gpiccoli@linux.vnet.ibm.com>
S: Supported
F: drivers/misc/genwqe/
GPIO SUBSYSTEM
M: Linus Walleij <linus.walleij@linaro.org>
-M: Alexandre Courbot <gnurou@gmail.com>
L: linux-gpio@vger.kernel.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio.git
S: Maintained
M: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
S: Maintained
F: drivers/staging/greybus/
-L: greybus-dev@lists.linaro.org
+L: greybus-dev@lists.linaro.org (moderated for non-subscribers)
GREYBUS AUDIO PROTOCOLS DRIVERS
M: Vaibhav Agarwal <vaibhav.sr@gmail.com>
F: drivers/media/platform/rcar_jpu.c
JSM Neo PCI based serial card
-M: Gabriel Krisman Bertazi <krisman@linux.vnet.ibm.com>
+M: Guilherme G. Piccoli <gpiccoli@linux.vnet.ibm.com>
L: linux-serial@vger.kernel.org
S: Maintained
F: drivers/tty/serial/jsm/
LIVE PATCHING
M: Josh Poimboeuf <jpoimboe@redhat.com>
-M: Jessica Yu <jeyu@redhat.com>
+M: Jessica Yu <jeyu@kernel.org>
M: Jiri Kosina <jikos@kernel.org>
M: Miroslav Benes <mbenes@suse.cz>
R: Petr Mladek <pmladek@suse.com>
F: drivers/media/radio/radio-miropcm20*
MELLANOX MLX4 core VPI driver
-M: Yishai Hadas <yishaih@mellanox.com>
+M: Tariq Toukan <tariqt@mellanox.com>
L: netdev@vger.kernel.org
L: linux-rdma@vger.kernel.org
W: http://www.mellanox.com
S: Supported
F: drivers/net/ethernet/mellanox/mlx4/
F: include/linux/mlx4/
-F: include/uapi/rdma/mlx4-abi.h
MELLANOX MLX4 IB driver
M: Yishai Hadas <yishaih@mellanox.com>
S: Supported
F: drivers/infiniband/hw/mlx4/
F: include/linux/mlx4/
+F: include/uapi/rdma/mlx4-abi.h
MELLANOX MLX5 core VPI driver
M: Saeed Mahameed <saeedm@mellanox.com>
S: Supported
F: drivers/net/ethernet/mellanox/mlx5/core/
F: include/linux/mlx5/
-F: include/uapi/rdma/mlx5-abi.h
MELLANOX MLX5 IB driver
M: Matan Barak <matanb@mellanox.com>
S: Supported
F: drivers/infiniband/hw/mlx5/
F: include/linux/mlx5/
+F: include/uapi/rdma/mlx5-abi.h
MELEXIS MLX90614 DRIVER
M: Crt Mori <cmo@melexis.com>
F: drivers/media/dvb-frontends/mn88473*
MODULE SUPPORT
-M: Jessica Yu <jeyu@redhat.com>
+M: Jessica Yu <jeyu@kernel.org>
M: Rusty Russell <rusty@rustcorp.com.au>
T: git git://git.kernel.org/pub/scm/linux/kernel/git/jeyu/linux.git modules-next
S: Maintained
OSD LIBRARY and FILESYSTEM
M: Boaz Harrosh <ooo@electrozaur.com>
-M: Benny Halevy <bhalevy@primarydata.com>
-L: osd-dev@open-osd.org
-W: http://open-osd.org
-T: git git://git.open-osd.org/open-osd.git
S: Maintained
F: drivers/scsi/osd/
F: include/scsi/osd_*
PXA RTC DRIVER
M: Robert Jarzmik <robert.jarzmik@free.fr>
-L: rtc-linux@googlegroups.com
+L: linux-rtc@vger.kernel.org
S: Maintained
QAT DRIVER
REAL TIME CLOCK (RTC) SUBSYSTEM
M: Alessandro Zummo <a.zummo@towertech.it>
M: Alexandre Belloni <alexandre.belloni@free-electrons.com>
-L: rtc-linux@googlegroups.com
+L: linux-rtc@vger.kernel.org
Q: http://patchwork.ozlabs.org/project/rtc-linux/list/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/abelloni/linux.git
S: Maintained
STI CEC DRIVER
M: Benjamin Gaignard <benjamin.gaignard@linaro.org>
-L: kernel@stlinux.com
S: Maintained
F: drivers/staging/media/st-cec/
F: Documentation/devicetree/bindings/media/stih-cec.txt
S: Supported
F: arch/arm/mach-davinci/
F: drivers/i2c/busses/i2c-davinci.c
+F: arch/arm/boot/dts/da850*
TI DAVINCI SERIES MEDIA DRIVER
M: "Lad, Prabhakar" <prabhakar.csengg@gmail.com>
F: drivers/net/wireless/wl3501*
WOLFSON MICROELECTRONICS DRIVERS
-L: patches@opensource.wolfsonmicro.com
+L: patches@opensource.cirrus.com
T: git https://github.com/CirrusLogic/linux-drivers.git
W: https://github.com/CirrusLogic/linux-drivers/wiki
S: Supported
VERSION = 4
PATCHLEVEL = 12
SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc5
NAME = Fearless Coyote
# *DOCUMENTATION*
PHONY += headers_check
headers_check: headers_install
$(Q)$(MAKE) $(hdr-inst)=include/uapi HDRCHECK=1
- $(Q)$(MAKE) $(hdr-inst)=arch/$(hdr-arch)/include/uapi/ $(hdr-dst) HDRCHECK=1
+ $(Q)$(MAKE) $(hdr-inst)=arch/$(hdr-arch)/include/uapi $(hdr-dst) HDRCHECK=1
# ---------------------------------------------------------------------------
# Kernel selftest
if (!access_ok(VERIFY_WRITE, ur, sizeof(*ur)))
return -EFAULT;
- err = 0;
- err |= put_user(status, ustatus);
+ err = put_user(status, ustatus);
+ if (ret < 0)
+ return err ? err : ret;
+
err |= __put_user(r.ru_utime.tv_sec, &ur->ru_utime.tv_sec);
err |= __put_user(r.ru_utime.tv_usec, &ur->ru_utime.tv_usec);
err |= __put_user(r.ru_stime.tv_sec, &ur->ru_stime.tv_sec);
@ there.
.inst 'M' | ('Z' << 8) | (0x1310 << 16) @ tstne r0, #0x4d000
#else
- mov r0, r0
+ W(mov) r0, r0
#endif
.endm
.macro __EFI_HEADER
#ifdef CONFIG_EFI_STUB
- b __efi_start
-
.set start_offset, __efi_start - start
.org start + 0x3c
@
.rept 7
__nop
.endr
- ARM( mov r0, r0 )
- ARM( b 1f )
- THUMB( badr r12, 1f )
- THUMB( bx r12 )
+#ifndef CONFIG_THUMB2_KERNEL
+ mov r0, r0
+#else
+ AR_CLASS( sub pc, pc, #3 ) @ A/R: switch to Thumb2 mode
+ M_CLASS( nop.w ) @ M: already in Thumb2 mode
+ .thumb
+#endif
+ W(b) 1f
.word _magic_sig @ Magic numbers to help the loader
.word _magic_start @ absolute load/run zImage address
.word _magic_end @ zImage end address
.word 0x04030201 @ endianness flag
- THUMB( .thumb )
-1: __EFI_HEADER
-
+ __EFI_HEADER
+1:
ARM_BE8( setend be ) @ go BE8 if compiled for BE8
AR_CLASS( mrs r9, cpsr )
#ifdef CONFIG_ARM_VIRT_EXT
/ {
aliases {
- ethernet = ðernet;
+ ethernet0 = ðernet;
};
};
/ {
aliases {
- ethernet = ðernet;
+ ethernet0 = ðernet;
};
};
#include <dt-bindings/clock/bcm2835-aux.h>
#include <dt-bindings/gpio/gpio.h>
+/* firmware-provided startup stubs live here, where the secondary CPUs are
+ * spinning.
+ */
+/memreserve/ 0x00000000 0x00001000;
+
/* This include file covers the common peripherals and configuration between
* bcm2835 and bcm2836 implementations, leaving the CPU configuration to
* bcm2835.dtsi and bcm2836.dtsi.
brcm,pins = <0 1>;
brcm,function = <BCM2835_FSEL_ALT0>;
};
- i2c0_gpio32: i2c0_gpio32 {
- brcm,pins = <32 34>;
+ i2c0_gpio28: i2c0_gpio28 {
+ brcm,pins = <28 29>;
brcm,function = <BCM2835_FSEL_ALT0>;
};
i2c0_gpio44: i2c0_gpio44 {
/* Separate from the uart0_gpio14 group
* because it conflicts with spi1_gpio16, and
* people often run uart0 on the two pins
- * without flow contrl.
+ * without flow control.
*/
uart0_ctsrts_gpio16: uart0_ctsrts_gpio16 {
brcm,pins = <16 17>;
brcm,function = <BCM2835_FSEL_ALT3>;
};
- uart0_gpio30: uart0_gpio30 {
+ uart0_ctsrts_gpio30: uart0_ctsrts_gpio30 {
brcm,pins = <30 31>;
brcm,function = <BCM2835_FSEL_ALT3>;
};
- uart0_ctsrts_gpio32: uart0_ctsrts_gpio32 {
+ uart0_gpio32: uart0_gpio32 {
brcm,pins = <32 33>;
brcm,function = <BCM2835_FSEL_ALT3>;
};
+ uart0_gpio36: uart0_gpio36 {
+ brcm,pins = <36 37>;
+ brcm,function = <BCM2835_FSEL_ALT2>;
+ };
+ uart0_ctsrts_gpio38: uart0_ctsrts_gpio38 {
+ brcm,pins = <38 39>;
+ brcm,function = <BCM2835_FSEL_ALT2>;
+ };
uart1_gpio14: uart1_gpio14 {
brcm,pins = <14 15>;
brcm,pins = <30 31>;
brcm,function = <BCM2835_FSEL_ALT5>;
};
- uart1_gpio36: uart1_gpio36 {
- brcm,pins = <36 37 38 39>;
- brcm,function = <BCM2835_FSEL_ALT2>;
- };
uart1_gpio40: uart1_gpio40 {
brcm,pins = <40 41>;
brcm,function = <BCM2835_FSEL_ALT5>;
tps659038: tps659038@58 {
compatible = "ti,tps659038";
reg = <0x58>;
+ ti,palmas-override-powerhold;
+ ti,system-power-controller;
tps659038_pmic {
compatible = "ti,tps659038-pmic";
coefficients = <0 2000>;
};
+&cpu_crit {
+ temperature = <120000>; /* milli Celsius */
+};
+
/include/ "dra7xx-clocks.dtsi"
imx53-qsrb {
pinctrl_pmic: pmicgrp {
fsl,pins = <
- MX53_PAD_CSI0_DAT5__GPIO5_23 0x1e4 /* IRQ */
+ MX53_PAD_CSI0_DAT5__GPIO5_23 0x1c4 /* IRQ */
>;
};
};
model = "Freescale i.MX6 SoloX SDB RevB Board";
};
-&cpu0 {
- operating-points = <
- /* kHz uV */
- 996000 1250000
- 792000 1175000
- 396000 1175000
- 198000 1175000
- >;
- fsl,soc-operating-points = <
- /* ARM kHz SOC uV */
- 996000 1250000
- 792000 1175000
- 396000 1175000
- 198000 1175000
- >;
-};
-
&i2c1 {
clock-frequency = <100000>;
pinctrl-names = "default";
ethphy0: ethernet-phy@2 {
reg = <2>;
+ micrel,led-mode = <1>;
+ clocks = <&clks IMX6UL_CLK_ENET_REF>;
+ clock-names = "rmii-ref";
};
ethphy1: ethernet-phy@1 {
reg = <1>;
+ micrel,led-mode = <1>;
+ clocks = <&clks IMX6UL_CLK_ENET2_REF>;
+ clock-names = "rmii-ref";
};
};
};
+++ /dev/null
-..
\ No newline at end of file
+++ /dev/null
-../../../../arm64/boot/dts
\ No newline at end of file
+++ /dev/null
-../../../../../include/dt-bindings
\ No newline at end of file
/* NetCP address range */
ranges = <0 0x26000000 0x1000000>;
- clocks = <&clkpa>, <&clkcpgmac>, <&chipclk12>, <&clkosr>;
- clock-names = "pa_clk", "ethss_clk", "cpts", "osr_clk";
+ clocks = <&clkpa>, <&clkcpgmac>, <&chipclk12>;
+ clock-names = "pa_clk", "ethss_clk", "cpts";
dma-coherent;
ti,navigator-dmas = <&dma_gbe 0>,
};
};
+ osr: sram@70000000 {
+ compatible = "mmio-sram";
+ reg = <0x70000000 0x10000>;
+ #address-cells = <1>;
+ #size-cells = <1>;
+ clocks = <&clkosr>;
+ };
+
dspgpio0: keystone_dsp_gpio@02620240 {
compatible = "ti,keystone-dsp-gpio";
gpio-controller;
OMAP3_CORE1_IOPAD(0x2110, PIN_INPUT | MUX_MODE0) /* cam_xclka.cam_xclka */
OMAP3_CORE1_IOPAD(0x2112, PIN_INPUT | MUX_MODE0) /* cam_pclk.cam_pclk */
- OMAP3_CORE1_IOPAD(0x2114, PIN_INPUT | MUX_MODE0) /* cam_d0.cam_d0 */
- OMAP3_CORE1_IOPAD(0x2116, PIN_INPUT | MUX_MODE0) /* cam_d1.cam_d1 */
- OMAP3_CORE1_IOPAD(0x2118, PIN_INPUT | MUX_MODE0) /* cam_d2.cam_d2 */
+ OMAP3_CORE1_IOPAD(0x2116, PIN_INPUT | MUX_MODE0) /* cam_d0.cam_d0 */
+ OMAP3_CORE1_IOPAD(0x2118, PIN_INPUT | MUX_MODE0) /* cam_d1.cam_d1 */
+ OMAP3_CORE1_IOPAD(0x211a, PIN_INPUT | MUX_MODE0) /* cam_d2.cam_d2 */
OMAP3_CORE1_IOPAD(0x211c, PIN_INPUT | MUX_MODE0) /* cam_d3.cam_d3 */
OMAP3_CORE1_IOPAD(0x211e, PIN_INPUT | MUX_MODE0) /* cam_d4.cam_d4 */
OMAP3_CORE1_IOPAD(0x2120, PIN_INPUT | MUX_MODE0) /* cam_d5.cam_d5 */
<GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_HIGH)>,
<GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_HIGH)>,
<GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_HIGH)>;
+ clock-frequency = <13000000>;
+ arm,cpu-registers-not-fw-configured;
};
watchdog: watchdog@10007000 {
simple-audio-card,bitclock-master = <&telephony_link_master>;
simple-audio-card,frame-master = <&telephony_link_master>;
simple-audio-card,format = "i2s";
-
+ simple-audio-card,bitclock-inversion;
+ simple-audio-card,frame-inversion;
simple-audio-card,cpu {
sound-dai = <&mcbsp4>;
};
/* Pandaboard Rev A4+ have external pullups on SCL & SDA */
&dss_hdmi_pins {
pinctrl-single,pins = <
- OMAP4_IOPAD(0x09a, PIN_INPUT_PULLUP | MUX_MODE0) /* hdmi_cec.hdmi_cec */
+ OMAP4_IOPAD(0x09a, PIN_INPUT | MUX_MODE0) /* hdmi_cec.hdmi_cec */
OMAP4_IOPAD(0x09c, PIN_INPUT | MUX_MODE0) /* hdmi_scl.hdmi_scl */
OMAP4_IOPAD(0x09e, PIN_INPUT | MUX_MODE0) /* hdmi_sda.hdmi_sda */
>;
/* PandaboardES has external pullups on SCL & SDA */
&dss_hdmi_pins {
pinctrl-single,pins = <
- OMAP4_IOPAD(0x09a, PIN_INPUT_PULLUP | MUX_MODE0) /* hdmi_cec.hdmi_cec */
+ OMAP4_IOPAD(0x09a, PIN_INPUT | MUX_MODE0) /* hdmi_cec.hdmi_cec */
OMAP4_IOPAD(0x09c, PIN_INPUT | MUX_MODE0) /* hdmi_scl.hdmi_scl */
OMAP4_IOPAD(0x09e, PIN_INPUT | MUX_MODE0) /* hdmi_sda.hdmi_sda */
>;
-#include <versatile-ab.dts>
+#include "versatile-ab.dts"
/ {
model = "ARM Versatile PB";
return ret;
}
-typedef void (*phys_reset_t)(unsigned long);
+typedef typeof(cpu_reset) phys_reset_t;
void mcpm_cpu_power_down(void)
{
* on the CPU.
*/
phys_reset = (phys_reset_t)(unsigned long)__pa_symbol(cpu_reset);
- phys_reset(__pa_symbol(mcpm_entry_point));
+ phys_reset(__pa_symbol(mcpm_entry_point), false);
/* should never get here */
BUG();
__mcpm_cpu_down(cpu, cluster);
phys_reset = (phys_reset_t)(unsigned long)__pa_symbol(cpu_reset);
- phys_reset(__pa_symbol(mcpm_entry_point));
+ phys_reset(__pa_symbol(mcpm_entry_point), false);
BUG();
}
--- /dev/null
+# CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_SYSVIPC=y
+CONFIG_NO_HZ_IDLE=y
+CONFIG_BSD_PROCESS_ACCT=y
+CONFIG_USER_NS=y
+CONFIG_RELAY=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_ARCH_MULTI_V4=y
+# CONFIG_ARCH_MULTI_V7 is not set
+CONFIG_ARCH_GEMINI=y
+CONFIG_PCI=y
+CONFIG_PREEMPT=y
+CONFIG_AEABI=y
+CONFIG_CMDLINE="console=ttyS0,115200n8"
+CONFIG_KEXEC=y
+CONFIG_BINFMT_MISC=y
+CONFIG_PM=y
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_DEVTMPFS=y
+CONFIG_MTD=y
+CONFIG_MTD_BLOCK=y
+CONFIG_MTD_CFI=y
+CONFIG_MTD_CFI_INTELEXT=y
+CONFIG_MTD_CFI_AMDSTD=y
+CONFIG_MTD_CFI_STAA=y
+CONFIG_MTD_PHYSMAP=y
+CONFIG_MTD_PHYSMAP_OF=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_SIZE=16384
+# CONFIG_SCSI_PROC_FS is not set
+CONFIG_BLK_DEV_SD=y
+# CONFIG_SCSI_LOWLEVEL is not set
+CONFIG_ATA=y
+CONFIG_INPUT_EVDEV=y
+CONFIG_KEYBOARD_GPIO=y
+# CONFIG_INPUT_MOUSE is not set
+# CONFIG_LEGACY_PTYS is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_NR_UARTS=1
+CONFIG_SERIAL_8250_RUNTIME_UARTS=1
+CONFIG_SERIAL_OF_PLATFORM=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+CONFIG_WATCHDOG=y
+CONFIG_GEMINI_WATCHDOG=y
+CONFIG_USB=y
+CONFIG_USB_MON=y
+CONFIG_USB_FOTG210_HCD=y
+CONFIG_USB_STORAGE=y
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
+CONFIG_LEDS_GPIO=y
+CONFIG_LEDS_TRIGGERS=y
+CONFIG_LEDS_TRIGGER_HEARTBEAT=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_GEMINI=y
+CONFIG_DMADEVICES=y
+# CONFIG_DNOTIFY is not set
+CONFIG_TMPFS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_ROMFS_FS=y
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_ISO8859_1=y
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+# CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_DEBUG_FS=y
#ifdef CONFIG_XEN
const struct dma_map_ops *dev_dma_ops;
#endif
- bool dma_coherent;
+ unsigned int dma_coherent:1;
+ unsigned int dma_ops_setup:1;
};
struct omap_device;
int kvm_handle_cp10_id(struct kvm_vcpu *vcpu, struct kvm_run *run);
int kvm_handle_cp_0_13_access(struct kvm_vcpu *vcpu, struct kvm_run *run);
int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run);
-int kvm_handle_cp14_access(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_handle_cp14_64(struct kvm_vcpu *vcpu, struct kvm_run *run);
int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run);
int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run);
#define pgprot_noncached(prot) (prot)
#define pgprot_writecombine(prot) (prot)
#define pgprot_dmacoherent(prot) (prot)
+#define pgprot_device(prot) (prot)
/*
#include <asm/vfp.h>
#include "../vfp/vfpinstr.h"
+#define CREATE_TRACE_POINTS
#include "trace.h"
#include "coproc.h"
return 1;
}
-int kvm_handle_cp14_access(struct kvm_vcpu *vcpu, struct kvm_run *run)
-{
- kvm_inject_undefined(vcpu);
- return 1;
-}
-
static void reset_mpidr(struct kvm_vcpu *vcpu, const struct coproc_reg *r)
{
/*
* must always support PMCCNTR (the cycle counter): we just RAZ/WI for
* all PM registers, which doesn't crash the guest kernel at least.
*/
-static bool pm_fake(struct kvm_vcpu *vcpu,
+static bool trap_raz_wi(struct kvm_vcpu *vcpu,
const struct coproc_params *p,
const struct coproc_reg *r)
{
return read_zero(vcpu, p);
}
-#define access_pmcr pm_fake
-#define access_pmcntenset pm_fake
-#define access_pmcntenclr pm_fake
-#define access_pmovsr pm_fake
-#define access_pmselr pm_fake
-#define access_pmceid0 pm_fake
-#define access_pmceid1 pm_fake
-#define access_pmccntr pm_fake
-#define access_pmxevtyper pm_fake
-#define access_pmxevcntr pm_fake
-#define access_pmuserenr pm_fake
-#define access_pmintenset pm_fake
-#define access_pmintenclr pm_fake
+#define access_pmcr trap_raz_wi
+#define access_pmcntenset trap_raz_wi
+#define access_pmcntenclr trap_raz_wi
+#define access_pmovsr trap_raz_wi
+#define access_pmselr trap_raz_wi
+#define access_pmceid0 trap_raz_wi
+#define access_pmceid1 trap_raz_wi
+#define access_pmccntr trap_raz_wi
+#define access_pmxevtyper trap_raz_wi
+#define access_pmxevcntr trap_raz_wi
+#define access_pmuserenr trap_raz_wi
+#define access_pmintenset trap_raz_wi
+#define access_pmintenclr trap_raz_wi
/* Architected CP15 registers.
* CRn denotes the primary register number, but is copied to the CRm in the
return 1;
}
-/**
- * kvm_handle_cp15_64 -- handles a mrrc/mcrr trap on a guest CP15 access
- * @vcpu: The VCPU pointer
- * @run: The kvm_run struct
- */
-int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static struct coproc_params decode_64bit_hsr(struct kvm_vcpu *vcpu)
{
struct coproc_params params;
params.Rt2 = (kvm_vcpu_get_hsr(vcpu) >> 10) & 0xf;
params.CRm = 0;
+ return params;
+}
+
+/**
+ * kvm_handle_cp15_64 -- handles a mrrc/mcrr trap on a guest CP15 access
+ * @vcpu: The VCPU pointer
+ * @run: The kvm_run struct
+ */
+int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+ struct coproc_params params = decode_64bit_hsr(vcpu);
+
return emulate_cp15(vcpu, ¶ms);
}
+/**
+ * kvm_handle_cp14_64 -- handles a mrrc/mcrr trap on a guest CP14 access
+ * @vcpu: The VCPU pointer
+ * @run: The kvm_run struct
+ */
+int kvm_handle_cp14_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+ struct coproc_params params = decode_64bit_hsr(vcpu);
+
+ /* raz_wi cp14 */
+ trap_raz_wi(vcpu, ¶ms, NULL);
+
+ /* handled */
+ kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+ return 1;
+}
+
static void reset_coproc_regs(struct kvm_vcpu *vcpu,
const struct coproc_reg *table, size_t num)
{
table[i].reset(vcpu, &table[i]);
}
-/**
- * kvm_handle_cp15_32 -- handles a mrc/mcr trap on a guest CP15 access
- * @vcpu: The VCPU pointer
- * @run: The kvm_run struct
- */
-int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static struct coproc_params decode_32bit_hsr(struct kvm_vcpu *vcpu)
{
struct coproc_params params;
params.Op2 = (kvm_vcpu_get_hsr(vcpu) >> 17) & 0x7;
params.Rt2 = 0;
+ return params;
+}
+
+/**
+ * kvm_handle_cp15_32 -- handles a mrc/mcr trap on a guest CP15 access
+ * @vcpu: The VCPU pointer
+ * @run: The kvm_run struct
+ */
+int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+ struct coproc_params params = decode_32bit_hsr(vcpu);
return emulate_cp15(vcpu, ¶ms);
}
+/**
+ * kvm_handle_cp14_32 -- handles a mrc/mcr trap on a guest CP14 access
+ * @vcpu: The VCPU pointer
+ * @run: The kvm_run struct
+ */
+int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+ struct coproc_params params = decode_32bit_hsr(vcpu);
+
+ /* raz_wi cp14 */
+ trap_raz_wi(vcpu, ¶ms, NULL);
+
+ /* handled */
+ kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+ return 1;
+}
+
/******************************************************************************
* Userspace API
*****************************************************************************/
[HSR_EC_WFI] = kvm_handle_wfx,
[HSR_EC_CP15_32] = kvm_handle_cp15_32,
[HSR_EC_CP15_64] = kvm_handle_cp15_64,
- [HSR_EC_CP14_MR] = kvm_handle_cp14_access,
+ [HSR_EC_CP14_MR] = kvm_handle_cp14_32,
[HSR_EC_CP14_LS] = kvm_handle_cp14_load_store,
- [HSR_EC_CP14_64] = kvm_handle_cp14_access,
+ [HSR_EC_CP14_64] = kvm_handle_cp14_64,
[HSR_EC_CP_0_13] = kvm_handle_cp_0_13_access,
[HSR_EC_CP10_ID] = kvm_handle_cp10_id,
[HSR_EC_HVC] = handle_hvc,
# Makefile for Kernel-based Virtual Machine module, HYP part
#
+ccflags-y += -fno-stack-protector
+
KVM=../../../../virt/kvm
obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v2-sr.o
write_sysreg(HSTR_T(15), HSTR);
write_sysreg(HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11), HCPTR);
val = read_sysreg(HDCR);
- write_sysreg(val | HDCR_TPM | HDCR_TPMCR, HDCR);
+ val |= HDCR_TPM | HDCR_TPMCR; /* trap performance monitors */
+ val |= HDCR_TDRA | HDCR_TDOSA | HDCR_TDA; /* trap debug regs */
+ write_sysreg(val, HDCR);
}
static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
@ - Write permission implies XN: disabled
@ - Instruction cache: enabled
@ - Data/Unified cache: enabled
- @ - Memory alignment checks: enabled
@ - MMU: enabled (this code must be run from an identity mapping)
mrc p15, 4, r0, c1, c0, 0 @ HSCR
ldr r2, =HSCTLR_MASK
mrc p15, 0, r1, c1, c0, 0 @ SCTLR
ldr r2, =(HSCTLR_EE | HSCTLR_FI | HSCTLR_I | HSCTLR_C)
and r1, r1, r2
- ARM( ldr r2, =(HSCTLR_M | HSCTLR_A) )
- THUMB( ldr r2, =(HSCTLR_M | HSCTLR_A | HSCTLR_TE) )
+ ARM( ldr r2, =(HSCTLR_M) )
+ THUMB( ldr r2, =(HSCTLR_M | HSCTLR_TE) )
orr r1, r1, r2
orr r0, r0, r1
mcr p15, 4, r0, c1, c0, 0 @ HSCR
-#if !defined(_TRACE_KVM_H) || defined(TRACE_HEADER_MULTI_READ)
-#define _TRACE_KVM_H
+#if !defined(_TRACE_ARM_KVM_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_ARM_KVM_H
#include <linux/tracepoint.h>
__entry->vcpu_pc, __entry->r0, __entry->imm)
);
-#endif /* _TRACE_KVM_H */
+#endif /* _TRACE_ARM_KVM_H */
#undef TRACE_INCLUDE_PATH
-#define TRACE_INCLUDE_PATH arch/arm/kvm
+#define TRACE_INCLUDE_PATH .
#undef TRACE_INCLUDE_FILE
#define TRACE_INCLUDE_FILE trace
menuconfig ARCH_AT91
bool "Atmel SoCs"
depends on ARCH_MULTI_V4T || ARCH_MULTI_V5 || ARCH_MULTI_V7
+ select ARM_CPU_SUSPEND if PM
select COMMON_CLK_AT91
select GPIOLIB
select PINCTRL
{ .idle = sama5d3_ddr_standby, .memctrl = AT91_MEMCTRL_DDRSDR},
};
-static const struct of_device_id const ramc_ids[] __initconst = {
+static const struct of_device_id ramc_ids[] __initconst = {
{ .compatible = "atmel,at91rm9200-sdramc", .data = &ramc_infos[0] },
{ .compatible = "atmel,at91sam9260-sdramc", .data = &ramc_infos[1] },
{ .compatible = "atmel,at91sam9g45-ddramc", .data = &ramc_infos[2] },
unsigned result;
};
-static const struct of_device_id const bcm_kona_smc_ids[] __initconst = {
+static const struct of_device_id bcm_kona_smc_ids[] __initconst = {
{.compatible = "brcm,kona-smc"},
{.compatible = "bcm,kona-smc"}, /* deprecated name */
{},
.power_off = csn3xxx_usb_power_off,
};
-static const struct of_dev_auxdata const cns3xxx_auxdata[] __initconst = {
+static const struct of_dev_auxdata cns3xxx_auxdata[] __initconst = {
{ "intel,usb-ehci", CNS3XXX_USB_BASE, "ehci-platform", &cns3xxx_usb_ehci_pdata },
{ "intel,usb-ohci", CNS3XXX_USB_OHCI_BASE, "ohci-platform", &cns3xxx_usb_ohci_pdata },
{ "cavium,cns3420-ahci", CNS3XXX_SATA2_BASE, "ahci", NULL },
davinci_sram_suspend = sram_alloc(davinci_cpu_suspend_sz, NULL);
if (!davinci_sram_suspend) {
pr_err("PM: cannot allocate SRAM memory\n");
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto no_sram_mem;
}
davinci_sram_push(davinci_sram_suspend, davinci_cpu_suspend,
suspend_set_ops(&davinci_pm_ops);
+ return 0;
+
+no_sram_mem:
+ iounmap(pm_config.ddrpsc_reg_base);
no_ddrpsc_mem:
iounmap(pm_config.ddrpll_reg_base);
no_ddrpll_mem:
extern const struct smp_operations omap4_smp_ops;
#endif
+extern u32 omap4_get_cpu1_ns_pa_addr(void);
+
#if defined(CONFIG_SMP) && defined(CONFIG_PM)
extern int omap4_mpuss_init(void);
extern int omap4_enter_lowpower(unsigned int cpu, unsigned int power_state);
extern int omap4_hotplug_cpu(unsigned int cpu, unsigned int power_state);
-extern u32 omap4_get_cpu1_ns_pa_addr(void);
#else
static inline int omap4_enter_lowpower(unsigned int cpu,
unsigned int power_state)
{}
#endif
-u32 omap4_get_cpu1_ns_pa_addr(void)
-{
- return old_cpu1_ns_pa_addr;
-}
-
/**
* omap4_enter_lowpower: OMAP4 MPUSS Low Power Entry Function
* The purpose of this function is to manage low power programming
#endif
+u32 omap4_get_cpu1_ns_pa_addr(void)
+{
+ return old_cpu1_ns_pa_addr;
+}
+
/*
* For kexec, we must set CPU1_WAKEUP_NS_PA_ADDR to point to
* current kernel's secondary_startup() early before
cpu1_startup_pa = readl_relaxed(cfg.wakeupgen_base +
OMAP_AUX_CORE_BOOT_1);
- cpu1_ns_pa_addr = omap4_get_cpu1_ns_pa_addr();
/* Did the configured secondary_startup() get overwritten? */
if (!omap4_smp_cpu1_startup_valid(cpu1_startup_pa))
* If omap4 or 5 has NS_PA_ADDR configured, CPU1 may be in a
* deeper idle state in WFI and will wake to an invalid address.
*/
- if ((soc_is_omap44xx() || soc_is_omap54xx()) &&
- !omap4_smp_cpu1_startup_valid(cpu1_ns_pa_addr))
- needs_reset = true;
+ if ((soc_is_omap44xx() || soc_is_omap54xx())) {
+ cpu1_ns_pa_addr = omap4_get_cpu1_ns_pa_addr();
+ if (!omap4_smp_cpu1_startup_valid(cpu1_ns_pa_addr))
+ needs_reset = true;
+ } else {
+ cpu1_ns_pa_addr = 0;
+ }
if (!needs_reset || !c->cpu1_rstctrl_va)
return;
};
#endif
-static const struct of_device_id const omap_prcm_dt_match_table[] __initconst = {
+static const struct of_device_id omap_prcm_dt_match_table[] __initconst = {
#ifdef CONFIG_SOC_AM33XX
{ .compatible = "ti,am3-prcm", .data = &am3_prm_data },
#endif
u8 hsscll_12;
};
-static const struct i2c_init_data const omap4_i2c_timing_data[] __initconst = {
+static const struct i2c_init_data omap4_i2c_timing_data[] __initconst = {
{
.load = 50,
.loadbits = 0x3,
setup_irq(irq, &spear_timer_irq);
}
-static const struct of_device_id const timer_of_match[] __initconst = {
+static const struct of_device_id timer_of_match[] __initconst = {
{ .compatible = "st,spear-timer", },
{ },
};
}
EXPORT_SYMBOL_GPL(arm_iommu_attach_device);
-static void __arm_iommu_detach_device(struct device *dev)
+/**
+ * arm_iommu_detach_device
+ * @dev: valid struct device pointer
+ *
+ * Detaches the provided device from a previously attached map.
+ * This voids the dma operations (dma_map_ops pointer)
+ */
+void arm_iommu_detach_device(struct device *dev)
{
struct dma_iommu_mapping *mapping;
iommu_detach_device(mapping->domain, dev);
kref_put(&mapping->kref, release_iommu_mapping);
to_dma_iommu_mapping(dev) = NULL;
+ set_dma_ops(dev, NULL);
pr_debug("Detached IOMMU controller from %s device.\n", dev_name(dev));
}
-
-/**
- * arm_iommu_detach_device
- * @dev: valid struct device pointer
- *
- * Detaches the provided device from a previously attached map.
- * This voids the dma operations (dma_map_ops pointer)
- */
-void arm_iommu_detach_device(struct device *dev)
-{
- __arm_iommu_detach_device(dev);
- set_dma_ops(dev, NULL);
-}
EXPORT_SYMBOL_GPL(arm_iommu_detach_device);
static const struct dma_map_ops *arm_get_iommu_dma_map_ops(bool coherent)
if (!mapping)
return;
- __arm_iommu_detach_device(dev);
+ arm_iommu_detach_device(dev);
arm_iommu_release_mapping(mapping);
}
dev->dma_ops = xen_dma_ops;
}
#endif
+ dev->archdata.dma_ops_setup = true;
}
void arch_teardown_dma_ops(struct device *dev)
{
+ if (!dev->archdata.dma_ops_setup)
+ return;
+
arm_teardown_iommu_dma_ops(dev);
}
def_bool y
depends on COMPAT && SYSVIPC
-config KEYS_COMPAT
- def_bool y
- depends on COMPAT && KEYS
-
endmenu
menu "Power management options"
select ARMADA_AP806_SYSCON
select ARMADA_CP110_SYSCON
select ARMADA_37XX_CLK
+ select GPIOLIB
+ select GPIOLIB_IRQCHIP
select MVEBU_ODMI
select MVEBU_PIC
+ select OF_GPIO
+ select PINCTRL
+ select PINCTRL_ARMADA_37XX
help
This enables support for Marvell EBU familly, including:
- Armada 3700 SoC Family
};
};
+ reg_sys_5v: regulator@0 {
+ compatible = "regulator-fixed";
+ regulator-name = "SYS_5V";
+ regulator-min-microvolt = <5000000>;
+ regulator-max-microvolt = <5000000>;
+ regulator-boot-on;
+ regulator-always-on;
+ };
+
+ reg_vdd_3v3: regulator@1 {
+ compatible = "regulator-fixed";
+ regulator-name = "VDD_3V3";
+ regulator-min-microvolt = <3300000>;
+ regulator-max-microvolt = <3300000>;
+ regulator-boot-on;
+ regulator-always-on;
+ vin-supply = <®_sys_5v>;
+ };
+
+ reg_5v_hub: regulator@2 {
+ compatible = "regulator-fixed";
+ regulator-name = "5V_HUB";
+ regulator-min-microvolt = <5000000>;
+ regulator-max-microvolt = <5000000>;
+ regulator-boot-on;
+ gpio = <&gpio0 7 0>;
+ regulator-always-on;
+ vin-supply = <®_sys_5v>;
+ };
+
+ wl1835_pwrseq: wl1835-pwrseq {
+ compatible = "mmc-pwrseq-simple";
+ /* WLAN_EN GPIO */
+ reset-gpios = <&gpio0 5 GPIO_ACTIVE_LOW>;
+ clocks = <&pmic>;
+ clock-names = "ext_clock";
+ power-off-delay-us = <10>;
+ };
+
soc {
spi0: spi@f7106000 {
status = "ok";
/* GPIO blocks 16 thru 19 do not appear to be routed to pins */
+ dwmmc_0: dwmmc0@f723d000 {
+ cap-mmc-highspeed;
+ non-removable;
+ bus-width = <0x8>;
+ vmmc-supply = <&ldo19>;
+ };
+
+ dwmmc_1: dwmmc1@f723e000 {
+ card-detect-delay = <200>;
+ cap-sd-highspeed;
+ sd-uhs-sdr12;
+ sd-uhs-sdr25;
+ sd-uhs-sdr50;
+ vqmmc-supply = <&ldo7>;
+ vmmc-supply = <&ldo10>;
+ bus-width = <0x4>;
+ disable-wp;
+ cd-gpios = <&gpio1 0 1>;
+ };
+
dwmmc_2: dwmmc2@f723f000 {
- ti,non-removable;
+ bus-width = <0x4>;
non-removable;
- /* WL_EN */
- vmmc-supply = <&wlan_en_reg>;
+ vmmc-supply = <®_vdd_3v3>;
+ mmc-pwrseq = <&wl1835_pwrseq>;
#address-cells = <0x1>;
#size-cells = <0x0>;
interrupts = <3 IRQ_TYPE_EDGE_RISING>;
};
};
-
- wlan_en_reg: regulator@1 {
- compatible = "regulator-fixed";
- regulator-name = "wlan-en-regulator";
- regulator-min-microvolt = <1800000>;
- regulator-max-microvolt = <1800000>;
- /* WLAN_EN GPIO */
- gpio = <&gpio0 5 0>;
- /* WLAN card specific delay */
- startup-delay-us = <70000>;
- enable-active-high;
- };
};
leds {
pmic: pmic@f8000000 {
compatible = "hisilicon,hi655x-pmic";
reg = <0x0 0xf8000000 0x0 0x1000>;
+ #clock-cells = <0>;
interrupt-controller;
#interrupt-cells = <2>;
pmic-gpios = <&gpio1 2 GPIO_ACTIVE_HIGH>;
status = "disabled";
};
- fixed_5v_hub: regulator@0 {
- compatible = "regulator-fixed";
- regulator-name = "fixed_5v_hub";
- regulator-min-microvolt = <5000000>;
- regulator-max-microvolt = <5000000>;
- regulator-boot-on;
- gpio = <&gpio0 7 0>;
- regulator-always-on;
- };
-
usb_phy: usbphy {
compatible = "hisilicon,hi6220-usb-phy";
#phy-cells = <0>;
- phy-supply = <&fixed_5v_hub>;
+ phy-supply = <®_5v_hub>;
hisilicon,peripheral-syscon = <&sys_ctrl>;
};
dwmmc_0: dwmmc0@f723d000 {
compatible = "hisilicon,hi6220-dw-mshc";
- num-slots = <0x1>;
- cap-mmc-highspeed;
- non-removable;
reg = <0x0 0xf723d000 0x0 0x1000>;
interrupts = <0x0 0x48 0x4>;
clocks = <&sys_ctrl 2>, <&sys_ctrl 1>;
clock-names = "ciu", "biu";
resets = <&sys_ctrl PERIPH_RSTDIS0_MMC0>;
reset-names = "reset";
- bus-width = <0x8>;
- vmmc-supply = <&ldo19>;
pinctrl-names = "default";
pinctrl-0 = <&emmc_pmx_func &emmc_clk_cfg_func
&emmc_cfg_func &emmc_rst_cfg_func>;
dwmmc_1: dwmmc1@f723e000 {
compatible = "hisilicon,hi6220-dw-mshc";
- num-slots = <0x1>;
- card-detect-delay = <200>;
hisilicon,peripheral-syscon = <&ao_ctrl>;
- cap-sd-highspeed;
- sd-uhs-sdr12;
- sd-uhs-sdr25;
- sd-uhs-sdr50;
reg = <0x0 0xf723e000 0x0 0x1000>;
interrupts = <0x0 0x49 0x4>;
#address-cells = <0x1>;
clock-names = "ciu", "biu";
resets = <&sys_ctrl PERIPH_RSTDIS0_MMC1>;
reset-names = "reset";
- vqmmc-supply = <&ldo7>;
- vmmc-supply = <&ldo10>;
- bus-width = <0x4>;
- disable-wp;
- cd-gpios = <&gpio1 0 1>;
pinctrl-names = "default", "idle";
pinctrl-0 = <&sd_pmx_func &sd_clk_cfg_func &sd_cfg_func>;
pinctrl-1 = <&sd_pmx_idle &sd_clk_cfg_idle &sd_cfg_idle>;
dwmmc_2: dwmmc2@f723f000 {
compatible = "hisilicon,hi6220-dw-mshc";
- num-slots = <0x1>;
reg = <0x0 0xf723f000 0x0 0x1000>;
interrupts = <0x0 0x4a 0x4>;
clocks = <&sys_ctrl HI6220_MMC2_CIUCLK>, <&sys_ctrl HI6220_MMC2_CLK>;
clock-names = "ciu", "biu";
resets = <&sys_ctrl PERIPH_RSTDIS0_MMC2>;
reset-names = "reset";
- bus-width = <0x4>;
- broken-cd;
pinctrl-names = "default", "idle";
pinctrl-0 = <&sdio_pmx_func &sdio_clk_cfg_func &sdio_cfg_func>;
pinctrl-1 = <&sdio_pmx_idle &sdio_clk_cfg_idle &sdio_cfg_idle>;
+++ /dev/null
-../../../../arm/boot/dts
\ No newline at end of file
+++ /dev/null
-..
\ No newline at end of file
+++ /dev/null
-../../../../../include/dt-bindings
\ No newline at end of file
};
&i2c0 {
+ pinctrl-names = "default";
+ pinctrl-0 = <&i2c1_pins>;
status = "okay";
gpio_exp: pca9555@22 {
&spi0 {
status = "okay";
+ pinctrl-names = "default";
+ pinctrl-0 = <&spi_quad_pins>;
m25p80@0 {
compatible = "jedec,spi-nor";
/* Exported on the micro USB connector CON32 through an FTDI */
&uart0 {
+ pinctrl-names = "default";
+ pinctrl-0 = <&uart1_pins>;
status = "okay";
};
};
ð0 {
+ pinctrl-names = "default";
+ pinctrl-0 = <&rgmii_pins>;
phy-mode = "rgmii-id";
phy = <&phy0>;
status = "okay";
#clock-cells = <1>;
};
- gpio1: gpio@13800 {
- compatible = "marvell,mvebu-gpio-3700",
+ pinctrl_nb: pinctrl@13800 {
+ compatible = "marvell,armada3710-nb-pinctrl",
"syscon", "simple-mfd";
- reg = <0x13800 0x500>;
+ reg = <0x13800 0x100>, <0x13C00 0x20>;
+ gpionb: gpio {
+ #gpio-cells = <2>;
+ gpio-ranges = <&pinctrl_nb 0 0 36>;
+ gpio-controller;
+ interrupts =
+ <GIC_SPI 51 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 56 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 57 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 58 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 152 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 153 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 154 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 155 IRQ_TYPE_LEVEL_HIGH>;
+
+ };
xtalclk: xtal-clk {
compatible = "marvell,armada-3700-xtal-clock";
clock-output-names = "xtal";
#clock-cells = <0>;
};
+
+ spi_quad_pins: spi-quad-pins {
+ groups = "spi_quad";
+ function = "spi";
+ };
+
+ i2c1_pins: i2c1-pins {
+ groups = "i2c1";
+ function = "i2c";
+ };
+
+ i2c2_pins: i2c2-pins {
+ groups = "i2c2";
+ function = "i2c";
+ };
+
+ uart1_pins: uart1-pins {
+ groups = "uart1";
+ function = "uart";
+ };
+
+ uart2_pins: uart2-pins {
+ groups = "uart2";
+ function = "uart";
+ };
+ };
+
+ pinctrl_sb: pinctrl@18800 {
+ compatible = "marvell,armada3710-sb-pinctrl",
+ "syscon", "simple-mfd";
+ reg = <0x18800 0x100>, <0x18C00 0x20>;
+ gpiosb: gpio {
+ #gpio-cells = <2>;
+ gpio-ranges = <&pinctrl_sb 0 0 29>;
+ gpio-controller;
+ interrupts =
+ <GIC_SPI 160 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 159 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 158 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 157 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 156 IRQ_TYPE_LEVEL_HIGH>;
+ };
+
+ rgmii_pins: mii-pins {
+ groups = "rgmii";
+ function = "mii";
+ };
+
};
eth0: ethernet@30000 {
cpm_crypto: crypto@800000 {
compatible = "inside-secure,safexcel-eip197";
reg = <0x800000 0x200000>;
- interrupts = <GIC_SPI 34 (IRQ_TYPE_EDGE_RISING
- | IRQ_TYPE_LEVEL_HIGH)>,
+ interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 56 IRQ_TYPE_LEVEL_HIGH>,
cps_crypto: crypto@800000 {
compatible = "inside-secure,safexcel-eip197";
reg = <0x800000 0x200000>;
- interrupts = <GIC_SPI 34 (IRQ_TYPE_EDGE_RISING
- | IRQ_TYPE_LEVEL_HIGH)>,
+ interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 278 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 279 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 280 IRQ_TYPE_LEVEL_HIGH>,
bus-width = <8>;
max-frequency = <50000000>;
cap-mmc-highspeed;
+ mediatek,hs200-cmd-int-delay=<26>;
+ mediatek,hs400-cmd-int-delay=<14>;
+ mediatek,hs400-cmd-resp-sel-rising;
vmmc-supply = <&mt6397_vemc_3v3_reg>;
vqmmc-supply = <&mt6397_vio18_reg>;
non-removable;
/dts-v1/;
#include "rk3399-gru.dtsi"
-#include <include/dt-bindings/input/linux-event-codes.h>
+#include <dt-bindings/input/linux-event-codes.h>
/*
* Kevin-specific things
CONFIG_JUMP_LABEL=y
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
# CONFIG_IOSCHED_DEADLINE is not set
CONFIG_ARCH_SUNXI=y
CONFIG_ARCH_ALPINE=y
CONFIG_ARCH_ZX=y
CONFIG_ARCH_ZYNQMP=y
CONFIG_PCI=y
-CONFIG_PCI_MSI=y
CONFIG_PCI_IOV=y
-CONFIG_PCI_AARDVARK=y
-CONFIG_PCIE_RCAR=y
-CONFIG_PCI_HOST_GENERIC=y
-CONFIG_PCI_XGENE=y
CONFIG_PCI_LAYERSCAPE=y
CONFIG_PCI_HISI=y
CONFIG_PCIE_QCOM=y
CONFIG_PCIE_ARMADA_8K=y
+CONFIG_PCI_AARDVARK=y
+CONFIG_PCIE_RCAR=y
+CONFIG_PCIE_ROCKCHIP=m
+CONFIG_PCI_HOST_GENERIC=y
+CONFIG_PCI_XGENE=y
CONFIG_ARM64_VA_BITS_48=y
CONFIG_SCHED_MC=y
CONFIG_NUMA=y
CONFIG_TRANSPARENT_HUGEPAGE=y
CONFIG_CMA=y
CONFIG_SECCOMP=y
-CONFIG_XEN=y
CONFIG_KEXEC=y
CONFIG_CRASH_DUMP=y
+CONFIG_XEN=y
# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
CONFIG_COMPAT=y
-CONFIG_CPU_IDLE=y
CONFIG_HIBERNATION=y
CONFIG_ARM_CPUIDLE=y
CONFIG_CPU_FREQ=y
CONFIG_BLK_DEV_LOOP=y
CONFIG_BLK_DEV_NBD=m
CONFIG_VIRTIO_BLK=y
-CONFIG_EEPROM_AT25=m
CONFIG_SRAM=y
+CONFIG_EEPROM_AT25=m
# CONFIG_SCSI_PROC_FS is not set
CONFIG_BLK_DEV_SD=y
CONFIG_SCSI_SAS_ATA=y
CONFIG_AHCI_MVEBU=y
CONFIG_AHCI_XGENE=y
CONFIG_AHCI_QORIQ=y
-CONFIG_SATA_RCAR=y
CONFIG_SATA_SIL24=y
+CONFIG_SATA_RCAR=y
CONFIG_PATA_PLATFORM=y
CONFIG_PATA_OF_PLATFORM=y
CONFIG_NETDEVICES=y
CONFIG_E1000E=y
CONFIG_IGB=y
CONFIG_IGBVF=y
-CONFIG_MVPP2=y
CONFIG_MVNETA=y
+CONFIG_MVPP2=y
CONFIG_SKY2=y
CONFIG_RAVB=y
CONFIG_SMC91X=y
CONFIG_SMSC911X=y
CONFIG_STMMAC_ETH=m
-CONFIG_REALTEK_PHY=m
+CONFIG_MDIO_BUS_MUX_MMIOREG=y
CONFIG_MESON_GXL_PHY=m
CONFIG_MICREL_PHY=y
-CONFIG_MDIO_BUS_MUX=y
-CONFIG_MDIO_BUS_MUX_MMIOREG=y
+CONFIG_REALTEK_PHY=m
CONFIG_USB_PEGASUS=m
CONFIG_USB_RTL8150=m
CONFIG_USB_RTL8152=m
CONFIG_WL18XX=m
CONFIG_WLCORE_SDIO=m
CONFIG_INPUT_EVDEV=y
+CONFIG_KEYBOARD_ADC=m
+CONFIG_KEYBOARD_CROS_EC=y
CONFIG_KEYBOARD_GPIO=y
CONFIG_INPUT_MISC=y
CONFIG_INPUT_PM8941_PWRKEY=y
CONFIG_SERIAL_OF_PLATFORM=y
CONFIG_SERIAL_AMBA_PL011=y
CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
+CONFIG_SERIAL_MESON=y
+CONFIG_SERIAL_MESON_CONSOLE=y
CONFIG_SERIAL_SAMSUNG=y
CONFIG_SERIAL_SAMSUNG_CONSOLE=y
CONFIG_SERIAL_TEGRA=y
CONFIG_SERIAL_SH_SCI=y
CONFIG_SERIAL_SH_SCI_NR_UARTS=11
CONFIG_SERIAL_SH_SCI_CONSOLE=y
-CONFIG_SERIAL_MESON=y
-CONFIG_SERIAL_MESON_CONSOLE=y
CONFIG_SERIAL_MSM=y
CONFIG_SERIAL_MSM_CONSOLE=y
CONFIG_SERIAL_XILINX_PS_UART=y
CONFIG_I2C_RCAR=y
CONFIG_I2C_CROS_EC_TUNNEL=y
CONFIG_SPI=y
-CONFIG_SPI_MESON_SPIFC=m
CONFIG_SPI_BCM2835=m
CONFIG_SPI_BCM2835AUX=m
+CONFIG_SPI_MESON_SPIFC=m
CONFIG_SPI_ORION=y
CONFIG_SPI_PL022=y
CONFIG_SPI_QUP=y
-CONFIG_SPI_SPIDEV=m
+CONFIG_SPI_ROCKCHIP=y
CONFIG_SPI_S3C64XX=y
+CONFIG_SPI_SPIDEV=m
CONFIG_SPMI=y
CONFIG_PINCTRL_SINGLE=y
CONFIG_PINCTRL_MAX77620=y
CONFIG_GPIO_PCA953X_IRQ=y
CONFIG_GPIO_MAX77620=y
CONFIG_POWER_RESET_MSM=y
-CONFIG_BATTERY_BQ27XXX=y
CONFIG_POWER_RESET_XGENE=y
CONFIG_POWER_RESET_SYSCON=y
+CONFIG_BATTERY_BQ27XXX=y
+CONFIG_SENSORS_ARM_SCPI=y
CONFIG_SENSORS_LM90=m
CONFIG_SENSORS_INA2XX=m
-CONFIG_SENSORS_ARM_SCPI=y
-CONFIG_THERMAL=y
-CONFIG_THERMAL_EMULATION=y
CONFIG_THERMAL_GOV_POWER_ALLOCATOR=y
CONFIG_CPU_THERMAL=y
-CONFIG_BCM2835_THERMAL=y
+CONFIG_THERMAL_EMULATION=y
CONFIG_EXYNOS_THERMAL=y
+CONFIG_ROCKCHIP_THERMAL=m
CONFIG_WATCHDOG=y
-CONFIG_BCM2835_WDT=y
-CONFIG_RENESAS_WDT=y
CONFIG_S3C2410_WATCHDOG=y
CONFIG_MESON_GXBB_WATCHDOG=m
CONFIG_MESON_WATCHDOG=m
+CONFIG_RENESAS_WDT=y
+CONFIG_BCM2835_WDT=y
+CONFIG_MFD_CROS_EC=y
+CONFIG_MFD_CROS_EC_I2C=y
+CONFIG_MFD_CROS_EC_SPI=y
CONFIG_MFD_EXYNOS_LPASS=m
+CONFIG_MFD_HI655X_PMIC=y
CONFIG_MFD_MAX77620=y
-CONFIG_MFD_RK808=y
CONFIG_MFD_SPMI_PMIC=y
+CONFIG_MFD_RK808=y
CONFIG_MFD_SEC_CORE=y
-CONFIG_MFD_HI655X_PMIC=y
-CONFIG_REGULATOR=y
-CONFIG_MFD_CROS_EC=y
-CONFIG_MFD_CROS_EC_I2C=y
+CONFIG_REGULATOR_FAN53555=y
CONFIG_REGULATOR_FIXED_VOLTAGE=y
CONFIG_REGULATOR_GPIO=y
CONFIG_REGULATOR_HI655X=y
CONFIG_DRM_EXYNOS_HDMI=y
CONFIG_DRM_EXYNOS_MIC=y
CONFIG_DRM_RCAR_DU=m
-CONFIG_DRM_RCAR_HDMI=y
CONFIG_DRM_RCAR_LVDS=y
CONFIG_DRM_RCAR_VSP=y
CONFIG_DRM_TEGRA=m
-CONFIG_DRM_VC4=m
CONFIG_DRM_PANEL_SIMPLE=m
CONFIG_DRM_I2C_ADV7511=m
+CONFIG_DRM_VC4=m
CONFIG_DRM_HISI_KIRIN=m
CONFIG_DRM_MESON=m
CONFIG_FB=y
CONFIG_SND=y
CONFIG_SND_SOC=y
CONFIG_SND_BCM2835_SOC_I2S=m
-CONFIG_SND_SOC_RCAR=y
CONFIG_SND_SOC_SAMSUNG=y
+CONFIG_SND_SOC_RCAR=y
CONFIG_SND_SOC_AK4613=y
CONFIG_USB=y
CONFIG_USB_OTG=y
CONFIG_USB_XHCI_HCD=y
-CONFIG_USB_XHCI_PLATFORM=y
-CONFIG_USB_XHCI_RCAR=y
-CONFIG_USB_EHCI_EXYNOS=y
CONFIG_USB_XHCI_TEGRA=y
CONFIG_USB_EHCI_HCD=y
CONFIG_USB_EHCI_MSM=y
+CONFIG_USB_EHCI_EXYNOS=y
CONFIG_USB_EHCI_HCD_PLATFORM=y
-CONFIG_USB_OHCI_EXYNOS=y
CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_OHCI_EXYNOS=y
CONFIG_USB_OHCI_HCD_PLATFORM=y
CONFIG_USB_RENESAS_USBHS=m
CONFIG_USB_STORAGE=y
-CONFIG_USB_DWC2=y
CONFIG_USB_DWC3=y
+CONFIG_USB_DWC2=y
CONFIG_USB_CHIPIDEA=y
CONFIG_USB_CHIPIDEA_UDC=y
CONFIG_USB_CHIPIDEA_HOST=y
CONFIG_USB_ISP1760=y
CONFIG_USB_HSIC_USB3503=y
CONFIG_USB_MSM_OTG=y
+CONFIG_USB_QCOM_8X16_PHY=y
CONFIG_USB_ULPI=y
CONFIG_USB_GADGET=y
CONFIG_USB_RENESAS_USBHS_UDC=m
CONFIG_MMC=y
CONFIG_MMC_BLOCK_MINORS=32
CONFIG_MMC_ARMMMCI=y
-CONFIG_MMC_MESON_GX=y
CONFIG_MMC_SDHCI=y
CONFIG_MMC_SDHCI_ACPI=y
CONFIG_MMC_SDHCI_PLTFM=y
CONFIG_MMC_SDHCI_OF_ESDHC=y
CONFIG_MMC_SDHCI_CADENCE=y
CONFIG_MMC_SDHCI_TEGRA=y
+CONFIG_MMC_MESON_GX=y
CONFIG_MMC_SDHCI_MSM=y
CONFIG_MMC_SPI=y
CONFIG_MMC_SDHI=y
CONFIG_MMC_DW_K3=y
CONFIG_MMC_DW_ROCKCHIP=y
CONFIG_MMC_SUNXI=y
-CONFIG_MMC_SDHCI_XENON=y
CONFIG_MMC_BCM2835=y
+CONFIG_MMC_SDHCI_XENON=y
CONFIG_NEW_LEDS=y
CONFIG_LEDS_CLASS=y
CONFIG_LEDS_GPIO=y
CONFIG_LEDS_PWM=y
CONFIG_LEDS_SYSCON=y
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
CONFIG_LEDS_TRIGGER_HEARTBEAT=y
CONFIG_LEDS_TRIGGER_CPU=y
+CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_MAX77686=y
+CONFIG_RTC_DRV_RK808=m
CONFIG_RTC_DRV_S5M=y
CONFIG_RTC_DRV_DS3232=y
CONFIG_RTC_DRV_EFI=y
+CONFIG_RTC_DRV_S3C=y
CONFIG_RTC_DRV_PL031=y
CONFIG_RTC_DRV_SUN6I=y
-CONFIG_RTC_DRV_RK808=m
CONFIG_RTC_DRV_TEGRA=y
CONFIG_RTC_DRV_XGENE=y
-CONFIG_RTC_DRV_S3C=y
CONFIG_DMADEVICES=y
+CONFIG_DMA_BCM2835=m
CONFIG_MV_XOR_V2=y
CONFIG_PL330_DMA=y
-CONFIG_DMA_BCM2835=m
CONFIG_TEGRA20_APB_DMA=y
CONFIG_QCOM_BAM_DMA=y
CONFIG_QCOM_HIDMA_MGMT=y
CONFIG_VIRTIO_MMIO=y
CONFIG_XEN_GNTDEV=y
CONFIG_XEN_GRANT_DEV_ALLOC=y
+CONFIG_COMMON_CLK_RK808=y
CONFIG_COMMON_CLK_SCPI=y
CONFIG_COMMON_CLK_CS2000_CP=y
CONFIG_COMMON_CLK_S2MPS11=y
-CONFIG_COMMON_CLK_PWM=y
-CONFIG_COMMON_CLK_RK808=y
CONFIG_CLK_QORIQ=y
+CONFIG_COMMON_CLK_PWM=y
CONFIG_COMMON_CLK_QCOM=y
+CONFIG_QCOM_CLK_SMD_RPM=y
CONFIG_MSM_GCC_8916=y
CONFIG_MSM_GCC_8994=y
CONFIG_MSM_MMCC_8996=y
CONFIG_HWSPINLOCK_QCOM=y
-CONFIG_MAILBOX=y
CONFIG_ARM_MHU=y
CONFIG_PLATFORM_MHU=y
CONFIG_BCM2835_MBOX=y
CONFIG_HI6220_MBOX=y
CONFIG_ARM_SMMU=y
CONFIG_ARM_SMMU_V3=y
+CONFIG_RPMSG_QCOM_SMD=y
CONFIG_RASPBERRYPI_POWER=y
CONFIG_QCOM_SMEM=y
-CONFIG_QCOM_SMD=y
CONFIG_QCOM_SMD_RPM=y
+CONFIG_QCOM_SMP2P=y
+CONFIG_QCOM_SMSM=y
CONFIG_ROCKCHIP_PM_DOMAINS=y
CONFIG_ARCH_TEGRA_132_SOC=y
CONFIG_ARCH_TEGRA_210_SOC=y
CONFIG_ARCH_TEGRA_186_SOC=y
CONFIG_EXTCON_USB_GPIO=y
+CONFIG_IIO=y
+CONFIG_EXYNOS_ADC=y
+CONFIG_ROCKCHIP_SARADC=m
CONFIG_PWM=y
CONFIG_PWM_BCM2835=m
+CONFIG_PWM_CROS_EC=m
+CONFIG_PWM_MESON=m
CONFIG_PWM_ROCKCHIP=y
+CONFIG_PWM_SAMSUNG=y
CONFIG_PWM_TEGRA=m
-CONFIG_PWM_MESON=m
-CONFIG_COMMON_RESET_HI6220=y
CONFIG_PHY_RCAR_GEN3_USB2=y
CONFIG_PHY_HI6220_USB=y
+CONFIG_PHY_SUN4I_USB=y
CONFIG_PHY_ROCKCHIP_INNO_USB2=y
CONFIG_PHY_ROCKCHIP_EMMC=y
-CONFIG_PHY_SUN4I_USB=y
+CONFIG_PHY_ROCKCHIP_PCIE=m
CONFIG_PHY_XGENE=y
CONFIG_PHY_TEGRA_XUSB=y
CONFIG_ARM_SCPI_PROTOCOL=y
-CONFIG_ACPI=y
-CONFIG_IIO=y
-CONFIG_EXYNOS_ADC=y
-CONFIG_PWM_SAMSUNG=y
CONFIG_RASPBERRYPI_FIRMWARE=y
+CONFIG_ACPI=y
CONFIG_EXT2_FS=y
CONFIG_EXT3_FS=y
CONFIG_EXT4_FS_POSIX_ACL=y
CONFIG_CUSE=m
CONFIG_OVERLAY_FS=m
CONFIG_VFAT_FS=y
-CONFIG_TMPFS=y
CONFIG_HUGETLBFS=y
CONFIG_CONFIGFS_FS=y
CONFIG_EFIVAR_FS=y
CONFIG_SECURITY=y
CONFIG_CRYPTO_ECHAINIV=y
CONFIG_CRYPTO_ANSI_CPRNG=y
-CONFIG_CRYPTO_DEV_SAFEXCEL=m
CONFIG_ARM64_CRYPTO=y
CONFIG_CRYPTO_SHA1_ARM64_CE=y
CONFIG_CRYPTO_SHA2_ARM64_CE=y
CONFIG_CRYPTO_GHASH_ARM64_CE=y
CONFIG_CRYPTO_AES_ARM64_CE_CCM=y
CONFIG_CRYPTO_AES_ARM64_CE_BLK=y
-# CONFIG_CRYPTO_AES_ARM64_NEON_BLK is not set
#define ACPI_MADT_GICC_LENGTH \
(acpi_gbl_FADT.header.revision < 6 ? 76 : 80)
-#define BAD_MADT_GICC_ENTRY(entry, end) \
- (!(entry) || (unsigned long)(entry) + sizeof(*(entry)) > (end) || \
- (entry)->header.length != ACPI_MADT_GICC_LENGTH)
+#define BAD_MADT_GICC_ENTRY(entry, end) \
+ (!(entry) || (entry)->header.length != ACPI_MADT_GICC_LENGTH || \
+ (unsigned long)(entry) + ACPI_MADT_GICC_LENGTH > (end))
/* Basic configuration for ACPI */
#ifdef CONFIG_ACPI
" st" #rel "xr" #sz "\t%w[tmp], %" #w "[new], %[v]\n" \
" cbnz %w[tmp], 1b\n" \
" " #mb "\n" \
- " mov %" #w "[oldval], %" #w "[old]\n" \
"2:" \
: [tmp] "=&r" (tmp), [oldval] "=&r" (oldval), \
[v] "+Q" (*(unsigned long *)ptr) \
extern DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
extern struct static_key_false cpu_hwcap_keys[ARM64_NCAPS];
+extern struct static_key_false arm64_const_caps_ready;
bool this_cpu_has_cap(unsigned int cap);
}
/* System capability check for constant caps */
-static inline bool cpus_have_const_cap(int num)
+static inline bool __cpus_have_const_cap(int num)
{
if (num >= ARM64_NCAPS)
return false;
return test_bit(num, cpu_hwcaps);
}
+static inline bool cpus_have_const_cap(int num)
+{
+ if (static_branch_likely(&arm64_const_caps_ready))
+ return __cpus_have_const_cap(num);
+ else
+ return cpus_have_cap(num);
+}
+
static inline void cpus_set_cap(unsigned int num)
{
if (num >= ARM64_NCAPS) {
num, ARM64_NCAPS);
} else {
__set_bit(num, cpu_hwcaps);
- static_branch_enable(&cpu_hwcap_keys[num]);
}
}
#include <linux/types.h>
#include <linux/kvm_types.h>
+#include <asm/cpufeature.h>
#include <asm/kvm.h>
#include <asm/kvm_asm.h>
#include <asm/kvm_mmio.h>
unsigned long vector_ptr)
{
/*
- * Call initialization code, and switch to the full blown
- * HYP code.
+ * Call initialization code, and switch to the full blown HYP code.
+ * If the cpucaps haven't been finalized yet, something has gone very
+ * wrong, and hyp will crash and burn when it uses any
+ * cpus_have_const_cap() wrapper.
*/
+ BUG_ON(!static_branch_likely(&arm64_const_caps_ready));
__kvm_call_hyp((void *)pgd_ptr, hyp_stack_ptr, vector_ptr);
}
#define SCTLR_ELx_A (1 << 1)
#define SCTLR_ELx_M 1
+#define SCTLR_EL2_RES1 ((1 << 4) | (1 << 5) | (1 << 11) | (1 << 16) | \
+ (1 << 16) | (1 << 18) | (1 << 22) | (1 << 23) | \
+ (1 << 28) | (1 << 29))
+
#define SCTLR_ELx_FLAGS (SCTLR_ELx_M | SCTLR_ELx_A | SCTLR_ELx_C | \
SCTLR_ELx_SA | SCTLR_ELx_I)
*/
void __init enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps)
{
- for (; caps->matches; caps++)
- if (caps->enable && cpus_have_cap(caps->capability))
+ for (; caps->matches; caps++) {
+ unsigned int num = caps->capability;
+
+ if (!cpus_have_cap(num))
+ continue;
+
+ /* Ensure cpus_have_const_cap(num) works */
+ static_branch_enable(&cpu_hwcap_keys[num]);
+
+ if (caps->enable) {
/*
* Use stop_machine() as it schedules the work allowing
* us to modify PSTATE, instead of on_each_cpu() which
* we return.
*/
stop_machine(caps->enable, NULL, cpu_online_mask);
+ }
+ }
}
/*
enable_cpu_capabilities(arm64_features);
}
+DEFINE_STATIC_KEY_FALSE(arm64_const_caps_ready);
+EXPORT_SYMBOL(arm64_const_caps_ready);
+
+static void __init mark_const_caps_ready(void)
+{
+ static_branch_enable(&arm64_const_caps_ready);
+}
+
/*
* Check if the current CPU has a given feature capability.
* Should be called from non-preemptible context.
/* Set the CPU feature capabilies */
setup_feature_capabilities();
enable_errata_workarounds();
+ mark_const_caps_ready();
setup_elf_hwcaps(arm64_elf_hwcaps);
if (system_supports_32bit_el0())
return NULL;
root_ops = kzalloc_node(sizeof(*root_ops), GFP_KERNEL, node);
- if (!root_ops)
+ if (!root_ops) {
+ kfree(ri);
return NULL;
+ }
ri->cfg = pci_acpi_setup_ecam_mapping(root);
if (!ri->cfg) {
if (attr->exclude_idle)
return -EPERM;
- if (is_kernel_in_hyp_mode() &&
- attr->exclude_kernel != attr->exclude_hv)
- return -EINVAL;
+
+ /*
+ * If we're running in hyp mode, then we *are* the hypervisor.
+ * Therefore we ignore exclude_hv in this configuration, since
+ * there's no hypervisor to sample anyway. This is consistent
+ * with other architectures (x86 and Power).
+ */
+ if (is_kernel_in_hyp_mode()) {
+ if (!attr->exclude_kernel)
+ config_base |= ARMV8_PMU_INCLUDE_EL2;
+ } else {
+ if (attr->exclude_kernel)
+ config_base |= ARMV8_PMU_EXCLUDE_EL1;
+ if (!attr->exclude_hv)
+ config_base |= ARMV8_PMU_INCLUDE_EL2;
+ }
if (attr->exclude_user)
config_base |= ARMV8_PMU_EXCLUDE_EL0;
- if (!is_kernel_in_hyp_mode() && attr->exclude_kernel)
- config_base |= ARMV8_PMU_EXCLUDE_EL1;
- if (!attr->exclude_hv)
- config_base |= ARMV8_PMU_INCLUDE_EL2;
/*
* Install the filter into config_base as this is used to
tlbi alle2
dsb sy
- mrs x4, sctlr_el2
- and x4, x4, #SCTLR_ELx_EE // preserve endianness of EL2
- ldr x5, =SCTLR_ELx_FLAGS
- orr x4, x4, x5
+ /*
+ * Preserve all the RES1 bits while setting the default flags,
+ * as well as the EE bit on BE. Drop the A flag since the compiler
+ * is allowed to generate unaligned accesses.
+ */
+ ldr x4, =(SCTLR_EL2_RES1 | (SCTLR_ELx_FLAGS & ~SCTLR_ELx_A))
+CPU_BE( orr x4, x4, #SCTLR_ELx_EE)
msr sctlr_el2, x4
isb
# Makefile for Kernel-based Virtual Machine module, HYP part
#
+ccflags-y += -fno-stack-protector
+
KVM=../../../../virt/kvm
obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v2-sr.o
* Here set VMCR.CTLR in ICC_CTLR_EL1 layout.
* The vgic_set_vmcr() will convert to ICH_VMCR layout.
*/
- vmcr.ctlr = val & ICC_CTLR_EL1_CBPR_MASK;
- vmcr.ctlr |= val & ICC_CTLR_EL1_EOImode_MASK;
+ vmcr.cbpr = (val & ICC_CTLR_EL1_CBPR_MASK) >> ICC_CTLR_EL1_CBPR_SHIFT;
+ vmcr.eoim = (val & ICC_CTLR_EL1_EOImode_MASK) >> ICC_CTLR_EL1_EOImode_SHIFT;
vgic_set_vmcr(vcpu, &vmcr);
} else {
val = 0;
* The VMCR.CTLR value is in ICC_CTLR_EL1 layout.
* Extract it directly using ICC_CTLR_EL1 reg definitions.
*/
- val |= vmcr.ctlr & ICC_CTLR_EL1_CBPR_MASK;
- val |= vmcr.ctlr & ICC_CTLR_EL1_EOImode_MASK;
+ val |= (vmcr.cbpr << ICC_CTLR_EL1_CBPR_SHIFT) & ICC_CTLR_EL1_CBPR_MASK;
+ val |= (vmcr.eoim << ICC_CTLR_EL1_EOImode_SHIFT) & ICC_CTLR_EL1_EOImode_MASK;
p->regval = val;
}
p->regval = 0;
vgic_get_vmcr(vcpu, &vmcr);
- if (!((vmcr.ctlr & ICH_VMCR_CBPR_MASK) >> ICH_VMCR_CBPR_SHIFT)) {
+ if (!vmcr.cbpr) {
if (p->is_write) {
vmcr.abpr = (p->regval & ICC_BPR1_EL1_MASK) >>
ICC_BPR1_EL1_SHIFT;
+++ /dev/null
-../../../../../include/dt-bindings
\ No newline at end of file
#define vxtime_lock() do {} while (0)
#define vxtime_unlock() do {} while (0)
+/* This attribute is used in include/linux/jiffies.h alongside with
+ * __cacheline_aligned_in_smp. It is assumed that __cacheline_aligned_in_smp
+ * for frv does not contain another section specification.
+ */
+#define __jiffy_arch_data __attribute__((__section__(".data")))
+
#endif
long uncleared;
while (count > PAGE_SIZE) {
- uncleared = __copy_to_user_hexagon(dest, &empty_zero_page,
- PAGE_SIZE);
+ uncleared = raw_copy_to_user(dest, &empty_zero_page, PAGE_SIZE);
if (uncleared)
return count - (PAGE_SIZE - uncleared);
count -= PAGE_SIZE;
dest += PAGE_SIZE;
}
if (count)
- count = __copy_to_user_hexagon(dest, &empty_zero_page, count);
+ count = raw_copy_to_user(dest, &empty_zero_page, count);
return count;
}
+++ /dev/null
-../../../../../include/dt-bindings
\ No newline at end of file
+++ /dev/null
-../../../../../include/dt-bindings
\ No newline at end of file
struct thread_info *ti = task_thread_info(p);
struct pt_regs *childregs, *regs = current_pt_regs();
unsigned long childksp;
- p->set_child_tid = p->clear_child_tid = NULL;
childksp = (unsigned long)task_stack_page(p) + THREAD_SIZE - 32;
top_of_kernel_stack = sp;
- p->set_child_tid = p->clear_child_tid = NULL;
-
/* Locate userspace context on stack... */
sp -= STACK_FRAME_OVERHEAD; /* redzone */
sp -= sizeof(struct pt_regs);
menu "Kernel options"
-config PPC_DT_CPU_FTRS
- bool "Device-tree based CPU feature discovery & setup"
- depends on PPC_BOOK3S_64
- default n
- help
- This enables code to use a new device tree binding for describing CPU
- compatibility and features. Saying Y here will attempt to use the new
- binding if the firmware provides it. Currently only the skiboot
- firmware provides this binding.
- If you're not sure say Y.
-
-config PPC_CPUFEATURES_ENABLE_UNKNOWN
- bool "cpufeatures pass through unknown features to guest/userspace"
- depends on PPC_DT_CPU_FTRS
- default y
-
config HIGHMEM
bool "High memory support"
depends on PPC32
source "security/Kconfig"
-config KEYS_COMPAT
- bool
- depends on COMPAT && KEYS
- default y
-
source "crypto/Kconfig"
config PPC_LIB_RHEAP
+++ /dev/null
-../../../../../include/dt-bindings
\ No newline at end of file
#define H_PTE_INDEX_SIZE 9
#define H_PMD_INDEX_SIZE 7
#define H_PUD_INDEX_SIZE 9
-#define H_PGD_INDEX_SIZE 12
+#define H_PGD_INDEX_SIZE 9
#ifndef __ASSEMBLY__
#define H_PTE_TABLE_SIZE (sizeof(pte_t) << H_PTE_INDEX_SIZE)
#define CPU_FTR_DAWR LONG_ASM_CONST(0x0400000000000000)
#define CPU_FTR_DABRX LONG_ASM_CONST(0x0800000000000000)
#define CPU_FTR_PMAO_BUG LONG_ASM_CONST(0x1000000000000000)
-#define CPU_FTR_SUBCORE LONG_ASM_CONST(0x2000000000000000)
#define CPU_FTR_POWER9_DD1 LONG_ASM_CONST(0x4000000000000000)
#ifndef __ASSEMBLY__
CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
CPU_FTR_ICSWX | CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \
- CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_SUBCORE)
+ CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP)
#define CPU_FTRS_POWER8E (CPU_FTRS_POWER8 | CPU_FTR_PMAO_BUG)
#define CPU_FTRS_POWER8_DD1 (CPU_FTRS_POWER8 & ~CPU_FTR_DBELL)
#define CPU_FTRS_POWER9 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
#include <asm-generic/module.h>
+#ifdef CC_USING_MPROFILE_KERNEL
+#define MODULE_ARCH_VERMAGIC "mprofile-kernel"
+#endif
+
#ifndef __powerpc64__
/*
* Thanks to Paul M for explaining this.
#define virt_to_pfn(kaddr) (__pa(kaddr) >> PAGE_SHIFT)
#define virt_to_page(kaddr) pfn_to_page(virt_to_pfn(kaddr))
#define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT)
+
+#ifdef CONFIG_PPC_BOOK3S_64
+/*
+ * On hash the vmalloc and other regions alias to the kernel region when passed
+ * through __pa(), which virt_to_pfn() uses. That means virt_addr_valid() can
+ * return true for some vmalloc addresses, which is incorrect. So explicitly
+ * check that the address is in the kernel region.
+ */
+#define virt_addr_valid(kaddr) (REGION_ID(kaddr) == KERNEL_REGION_ID && \
+ pfn_valid(virt_to_pfn(kaddr)))
+#else
#define virt_addr_valid(kaddr) pfn_valid(virt_to_pfn(kaddr))
+#endif
/*
* On Book-E parts we need __va to parse the device tree and we can't
#define TASK_SIZE_128TB (0x0000800000000000UL)
#define TASK_SIZE_512TB (0x0002000000000000UL)
-#ifdef CONFIG_PPC_BOOK3S_64
+/*
+ * For now 512TB is only supported with book3s and 64K linux page size.
+ */
+#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_64K_PAGES)
/*
* Max value currently used:
*/
-#define TASK_SIZE_USER64 TASK_SIZE_512TB
+#define TASK_SIZE_USER64 TASK_SIZE_512TB
+#define DEFAULT_MAP_WINDOW_USER64 TASK_SIZE_128TB
#else
-#define TASK_SIZE_USER64 TASK_SIZE_64TB
+#define TASK_SIZE_USER64 TASK_SIZE_64TB
+#define DEFAULT_MAP_WINDOW_USER64 TASK_SIZE_64TB
#endif
/*
* space during mmap's.
*/
#define TASK_UNMAPPED_BASE_USER32 (PAGE_ALIGN(TASK_SIZE_USER32 / 4))
-#define TASK_UNMAPPED_BASE_USER64 (PAGE_ALIGN(TASK_SIZE_128TB / 4))
+#define TASK_UNMAPPED_BASE_USER64 (PAGE_ALIGN(DEFAULT_MAP_WINDOW_USER64 / 4))
#define TASK_UNMAPPED_BASE ((is_32bit_task()) ? \
TASK_UNMAPPED_BASE_USER32 : TASK_UNMAPPED_BASE_USER64 )
* with 128TB and conditionally enable upto 512TB
*/
#ifdef CONFIG_PPC_BOOK3S_64
-#define DEFAULT_MAP_WINDOW ((is_32bit_task()) ? \
- TASK_SIZE_USER32 : TASK_SIZE_128TB)
+#define DEFAULT_MAP_WINDOW ((is_32bit_task()) ? \
+ TASK_SIZE_USER32 : DEFAULT_MAP_WINDOW_USER64)
#else
#define DEFAULT_MAP_WINDOW TASK_SIZE
#endif
#ifdef __powerpc64__
-#ifdef CONFIG_PPC_BOOK3S_64
-/* Limit stack to 128TB */
-#define STACK_TOP_USER64 TASK_SIZE_128TB
-#else
-#define STACK_TOP_USER64 TASK_SIZE_USER64
-#endif
-
+#define STACK_TOP_USER64 DEFAULT_MAP_WINDOW_USER64
#define STACK_TOP_USER32 TASK_SIZE_USER32
#define STACK_TOP (is_32bit_task() ? \
extern int sysfs_add_device_to_node(struct device *dev, int nid);
extern void sysfs_remove_device_from_node(struct device *dev, int nid);
+static inline int early_cpu_to_node(int cpu)
+{
+ int nid;
+
+ nid = numa_cpu_lookup_table[cpu];
+
+ /*
+ * Fall back to node 0 if nid is unset (it should be, except bugs).
+ * This allows callers to safely do NODE_DATA(early_cpu_to_node(cpu)).
+ */
+ return (nid < 0) ? 0 : nid;
+}
#else
+static inline int early_cpu_to_node(int cpu) { return 0; }
+
static inline void dump_numa_cpu_topology(void) {}
static inline int sysfs_add_device_to_node(struct device *dev, int nid)
#define PPC_FEATURE2_HTM_NOSC 0x01000000
#define PPC_FEATURE2_ARCH_3_00 0x00800000 /* ISA 3.00 */
#define PPC_FEATURE2_HAS_IEEE128 0x00400000 /* VSX IEEE Binary Float 128-bit */
+#define PPC_FEATURE2_DARN 0x00200000 /* darn random number insn */
+#define PPC_FEATURE2_SCV 0x00100000 /* scv syscall */
/*
* IMPORTANT!
#define COMMON_USER_POWER9 COMMON_USER_POWER8
#define COMMON_USER2_POWER9 (COMMON_USER2_POWER8 | \
PPC_FEATURE2_ARCH_3_00 | \
- PPC_FEATURE2_HAS_IEEE128)
+ PPC_FEATURE2_HAS_IEEE128 | \
+ PPC_FEATURE2_DARN )
#ifdef CONFIG_PPC_BOOK3E_64
#define COMMON_USER_BOOKE (COMMON_USER_PPC64 | PPC_FEATURE_BOOKE)
#include <linux/export.h>
#include <linux/init.h>
#include <linux/jump_label.h>
+#include <linux/libfdt.h>
#include <linux/memblock.h>
#include <linux/printk.h>
#include <linux/sched.h>
{"processor-control-facility", feat_enable_dbell, CPU_FTR_DBELL},
{"processor-control-facility-v3", feat_enable_dbell, CPU_FTR_DBELL},
{"processor-utilization-of-resources-register", feat_enable_purr, 0},
- {"subcore", feat_enable, CPU_FTR_SUBCORE},
{"no-execute", feat_enable, 0},
{"strong-access-ordering", feat_enable, CPU_FTR_SAO},
{"cache-inhibited-large-page", feat_enable_large_ci, 0},
{"wait-v3", feat_enable, 0},
};
-/* XXX: how to configure this? Default + boot time? */
-#ifdef CONFIG_PPC_CPUFEATURES_ENABLE_UNKNOWN
-#define CPU_FEATURE_ENABLE_UNKNOWN 1
-#else
-#define CPU_FEATURE_ENABLE_UNKNOWN 0
-#endif
+static bool __initdata using_dt_cpu_ftrs;
+static bool __initdata enable_unknown = true;
+
+static int __init dt_cpu_ftrs_parse(char *str)
+{
+ if (!str)
+ return 0;
+
+ if (!strcmp(str, "off"))
+ using_dt_cpu_ftrs = false;
+ else if (!strcmp(str, "known"))
+ enable_unknown = false;
+ else
+ return 1;
+
+ return 0;
+}
+early_param("dt_cpu_ftrs", dt_cpu_ftrs_parse);
static void __init cpufeatures_setup_start(u32 isa)
{
}
}
- if (!known && CPU_FEATURE_ENABLE_UNKNOWN) {
+ if (!known && enable_unknown) {
if (!feat_try_enable_unknown(f)) {
pr_info("not enabling: %s (unknown and unsupported by kernel)\n",
f->name);
cur_cpu_spec->cpu_features, cur_cpu_spec->mmu_features);
}
+static int __init disabled_on_cmdline(void)
+{
+ unsigned long root, chosen;
+ const char *p;
+
+ root = of_get_flat_dt_root();
+ chosen = of_get_flat_dt_subnode_by_name(root, "chosen");
+ if (chosen == -FDT_ERR_NOTFOUND)
+ return false;
+
+ p = of_get_flat_dt_prop(chosen, "bootargs", NULL);
+ if (!p)
+ return false;
+
+ if (strstr(p, "dt_cpu_ftrs=off"))
+ return true;
+
+ return false;
+}
+
static int __init fdt_find_cpu_features(unsigned long node, const char *uname,
int depth, void *data)
{
return 0;
}
-static bool __initdata using_dt_cpu_ftrs = false;
-
bool __init dt_cpu_ftrs_in_use(void)
{
return using_dt_cpu_ftrs;
bool __init dt_cpu_ftrs_init(void *fdt)
{
+ using_dt_cpu_ftrs = false;
+
/* Setup and verify the FDT, if it fails we just bail */
if (!early_init_dt_verify(fdt))
return false;
if (!of_scan_flat_dt(fdt_find_cpu_features, NULL))
return false;
+ if (disabled_on_cmdline())
+ return false;
+
cpufeatures_setup_cpu();
using_dt_cpu_ftrs = true;
void __init dt_cpu_ftrs_scan(void)
{
+ if (!using_dt_cpu_ftrs)
+ return;
+
of_scan_flat_dt(dt_cpu_ftrs_scan_callback, NULL);
}
* which needs to be restored from the stack.
*/
li r3, 1
- stb r0,PACA_NAPSTATELOST(r13)
+ stb r3,PACA_NAPSTATELOST(r13)
blr
/*
save_previous_kprobe(kcb);
set_current_kprobe(p, regs, kcb);
kprobes_inc_nmissed_count(p);
- prepare_singlestep(p, regs);
kcb->kprobe_status = KPROBE_REENTER;
if (p->ainsn.boostable >= 0) {
ret = try_to_emulate(p, regs);
if (ret > 0) {
restore_previous_kprobe(kcb);
+ preempt_enable_no_resched();
return 1;
}
}
+ prepare_singlestep(p, regs);
return 1;
} else {
if (*addr != BREAKPOINT_INSTRUCTION) {
if (!MSR_TM_SUSPENDED(mfmsr()))
return;
+ /*
+ * If we are in a transaction and FP is off then we can't have
+ * used FP inside that transaction. Hence the checkpointed
+ * state is the same as the live state. We need to copy the
+ * live state to the checkpointed state so that when the
+ * transaction is restored, the checkpointed state is correct
+ * and the aborted transaction sees the correct state. We use
+ * ckpt_regs.msr here as that's what tm_reclaim will use to
+ * determine if it's going to write the checkpointed state or
+ * not. So either this will write the checkpointed registers,
+ * or reclaim will. Similarly for VMX.
+ */
+ if ((thr->ckpt_regs.msr & MSR_FP) == 0)
+ memcpy(&thr->ckfp_state, &thr->fp_state,
+ sizeof(struct thread_fp_state));
+ if ((thr->ckpt_regs.msr & MSR_VEC) == 0)
+ memcpy(&thr->ckvr_state, &thr->vr_state,
+ sizeof(struct thread_vr_state));
+
giveup_all(container_of(thr, struct task_struct, thread));
tm_reclaim(thr, thr->ckpt_regs.msr, cause);
#ifdef CONFIG_VSX
current->thread.used_vsr = 0;
#endif
+ current->thread.load_fp = 0;
memset(¤t->thread.fp_state, 0, sizeof(current->thread.fp_state));
current->thread.fp_save_area = NULL;
#ifdef CONFIG_ALTIVEC
current->thread.vr_save_area = NULL;
current->thread.vrsave = 0;
current->thread.used_vr = 0;
+ current->thread.load_vec = 0;
#endif /* CONFIG_ALTIVEC */
#ifdef CONFIG_SPE
memset(current->thread.evr, 0, sizeof(current->thread.evr));
current->thread.tm_tfhar = 0;
current->thread.tm_texasr = 0;
current->thread.tm_tfiar = 0;
+ current->thread.load_tm = 0;
#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
}
EXPORT_SYMBOL(start_thread);
{ .pabyte = 0, .pabit = 3, .cpu_features = CPU_FTR_CTRL },
{ .pabyte = 0, .pabit = 6, .cpu_features = CPU_FTR_NOEXECUTE },
{ .pabyte = 1, .pabit = 2, .mmu_features = MMU_FTR_CI_LARGE_PAGE },
+#ifdef CONFIG_PPC_RADIX_MMU
{ .pabyte = 40, .pabit = 0, .mmu_features = MMU_FTR_TYPE_RADIX },
+#endif
{ .pabyte = 1, .pabit = 1, .invert = 1, .cpu_features = CPU_FTR_NODSISRALIGN },
{ .pabyte = 5, .pabit = 0, .cpu_features = CPU_FTR_REAL_LE,
.cpu_user_ftrs = PPC_FEATURE_TRUE_LE },
#ifdef CONFIG_PPC_MM_SLICES
#ifdef CONFIG_PPC64
- init_mm.context.addr_limit = TASK_SIZE_128TB;
+ init_mm.context.addr_limit = DEFAULT_MAP_WINDOW_USER64;
#else
#error "context.addr_limit not initialized."
#endif
static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
{
- return __alloc_bootmem_node(NODE_DATA(cpu_to_node(cpu)), size, align,
+ return __alloc_bootmem_node(NODE_DATA(early_cpu_to_node(cpu)), size, align,
__pa(MAX_DMA_ADDRESS));
}
static int pcpu_cpu_distance(unsigned int from, unsigned int to)
{
- if (cpu_to_node(from) == cpu_to_node(to))
+ if (early_cpu_to_node(from) == early_cpu_to_node(to))
return LOCAL_DISTANCE;
else
return REMOTE_DISTANCE;
select KVM_BOOK3S_64_HANDLER
select KVM
select KVM_BOOK3S_PR_POSSIBLE if !KVM_BOOK3S_HV_POSSIBLE
- select SPAPR_TCE_IOMMU if IOMMU_SUPPORT
+ select SPAPR_TCE_IOMMU if IOMMU_SUPPORT && (PPC_SERIES || PPC_POWERNV)
---help---
Support running unmodified book3s_64 and book3s_32 guest kernels
in virtual machines on book3s_64 host processors.
e500_emulate.o
kvm-objs-$(CONFIG_KVM_E500MC) := $(kvm-e500mc-objs)
-kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) := \
+kvm-book3s_64-builtin-objs-$(CONFIG_SPAPR_TCE_IOMMU) := \
book3s_64_vio_hv.o
kvm-pr-y := \
book3s_xics.o
kvm-book3s_64-objs-$(CONFIG_KVM_XIVE) += book3s_xive.o
+kvm-book3s_64-objs-$(CONFIG_SPAPR_TCE_IOMMU) += book3s_64_vio.o
kvm-book3s_64-module-objs := \
$(common-objs-y) \
book3s.o \
- book3s_64_vio.o \
book3s_rtas.o \
$(kvm-book3s_64-objs-y)
/* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
/* liobn, ioba, tce); */
+ /* For radix, we might be in virtual mode, so punt */
+ if (kvm_is_radix(vcpu->kvm))
+ return H_TOO_HARD;
+
stt = kvmppc_find_table(vcpu->kvm, liobn);
if (!stt)
return H_TOO_HARD;
bool prereg = false;
struct kvmppc_spapr_tce_iommu_table *stit;
+ /* For radix, we might be in virtual mode, so punt */
+ if (kvm_is_radix(vcpu->kvm))
+ return H_TOO_HARD;
+
stt = kvmppc_find_table(vcpu->kvm, liobn);
if (!stt)
return H_TOO_HARD;
long i, ret;
struct kvmppc_spapr_tce_iommu_table *stit;
+ /* For radix, we might be in virtual mode, so punt */
+ if (kvm_is_radix(vcpu->kvm))
+ return H_TOO_HARD;
+
stt = kvmppc_find_table(vcpu->kvm, liobn);
if (!stt)
return H_TOO_HARD;
return H_SUCCESS;
}
+/* This can be called in either virtual mode or real mode */
long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
unsigned long ioba)
{
long kvmppc_h_random(struct kvm_vcpu *vcpu)
{
- if (powernv_get_random_real_mode(&vcpu->arch.gpr[4]))
+ int r;
+
+ /* Only need to do the expensive mfmsr() on radix */
+ if (kvm_is_radix(vcpu->kvm) && (mfmsr() & MSR_IR))
+ r = powernv_get_random_long(&vcpu->arch.gpr[4]);
+ else
+ r = powernv_get_random_real_mode(&vcpu->arch.gpr[4]);
+ if (r)
return H_SUCCESS;
return H_HARDWARE;
pteg_addr = get_pteg_addr(vcpu, pte_index);
mutex_lock(&vcpu->kvm->arch.hpt_mutex);
- copy_from_user(pteg, (void __user *)pteg_addr, sizeof(pteg));
+ ret = H_FUNCTION;
+ if (copy_from_user(pteg, (void __user *)pteg_addr, sizeof(pteg)))
+ goto done;
hpte = pteg;
ret = H_PTEG_FULL;
hpte[0] = cpu_to_be64(kvmppc_get_gpr(vcpu, 6));
hpte[1] = cpu_to_be64(kvmppc_get_gpr(vcpu, 7));
pteg_addr += i * HPTE_SIZE;
- copy_to_user((void __user *)pteg_addr, hpte, HPTE_SIZE);
+ ret = H_FUNCTION;
+ if (copy_to_user((void __user *)pteg_addr, hpte, HPTE_SIZE))
+ goto done;
kvmppc_set_gpr(vcpu, 4, pte_index | i);
ret = H_SUCCESS;
pteg = get_pteg_addr(vcpu, pte_index);
mutex_lock(&vcpu->kvm->arch.hpt_mutex);
- copy_from_user(pte, (void __user *)pteg, sizeof(pte));
+ ret = H_FUNCTION;
+ if (copy_from_user(pte, (void __user *)pteg, sizeof(pte)))
+ goto done;
pte[0] = be64_to_cpu((__force __be64)pte[0]);
pte[1] = be64_to_cpu((__force __be64)pte[1]);
((flags & H_ANDCOND) && (pte[0] & avpn) != 0))
goto done;
- copy_to_user((void __user *)pteg, &v, sizeof(v));
+ ret = H_FUNCTION;
+ if (copy_to_user((void __user *)pteg, &v, sizeof(v)))
+ goto done;
rb = compute_tlbie_rb(pte[0], pte[1], pte_index);
vcpu->arch.mmu.tlbie(vcpu, rb, rb & 1 ? true : false);
}
pteg = get_pteg_addr(vcpu, tsh & H_BULK_REMOVE_PTEX);
- copy_from_user(pte, (void __user *)pteg, sizeof(pte));
+ if (copy_from_user(pte, (void __user *)pteg, sizeof(pte))) {
+ ret = H_FUNCTION;
+ break;
+ }
pte[0] = be64_to_cpu((__force __be64)pte[0]);
pte[1] = be64_to_cpu((__force __be64)pte[1]);
tsh |= H_BULK_REMOVE_NOT_FOUND;
} else {
/* Splat the pteg in (userland) hpt */
- copy_to_user((void __user *)pteg, &v, sizeof(v));
+ if (copy_to_user((void __user *)pteg, &v, sizeof(v))) {
+ ret = H_FUNCTION;
+ break;
+ }
rb = compute_tlbie_rb(pte[0], pte[1],
tsh & H_BULK_REMOVE_PTEX);
pteg = get_pteg_addr(vcpu, pte_index);
mutex_lock(&vcpu->kvm->arch.hpt_mutex);
- copy_from_user(pte, (void __user *)pteg, sizeof(pte));
+ ret = H_FUNCTION;
+ if (copy_from_user(pte, (void __user *)pteg, sizeof(pte)))
+ goto done;
pte[0] = be64_to_cpu((__force __be64)pte[0]);
pte[1] = be64_to_cpu((__force __be64)pte[1]);
vcpu->arch.mmu.tlbie(vcpu, rb, rb & 1 ? true : false);
pte[0] = (__force u64)cpu_to_be64(pte[0]);
pte[1] = (__force u64)cpu_to_be64(pte[1]);
- copy_to_user((void __user *)pteg, pte, sizeof(pte));
+ ret = H_FUNCTION;
+ if (copy_to_user((void __user *)pteg, pte, sizeof(pte)))
+ goto done;
ret = H_SUCCESS;
done:
return EMULATE_DONE;
}
-static int kvmppc_h_pr_put_tce(struct kvm_vcpu *vcpu)
+static int kvmppc_h_pr_logical_ci_load(struct kvm_vcpu *vcpu)
{
- unsigned long liobn = kvmppc_get_gpr(vcpu, 4);
- unsigned long ioba = kvmppc_get_gpr(vcpu, 5);
- unsigned long tce = kvmppc_get_gpr(vcpu, 6);
long rc;
- rc = kvmppc_h_put_tce(vcpu, liobn, ioba, tce);
+ rc = kvmppc_h_logical_ci_load(vcpu);
if (rc == H_TOO_HARD)
return EMULATE_FAIL;
kvmppc_set_gpr(vcpu, 3, rc);
return EMULATE_DONE;
}
-static int kvmppc_h_pr_logical_ci_load(struct kvm_vcpu *vcpu)
+static int kvmppc_h_pr_logical_ci_store(struct kvm_vcpu *vcpu)
{
long rc;
- rc = kvmppc_h_logical_ci_load(vcpu);
+ rc = kvmppc_h_logical_ci_store(vcpu);
if (rc == H_TOO_HARD)
return EMULATE_FAIL;
kvmppc_set_gpr(vcpu, 3, rc);
return EMULATE_DONE;
}
-static int kvmppc_h_pr_logical_ci_store(struct kvm_vcpu *vcpu)
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+static int kvmppc_h_pr_put_tce(struct kvm_vcpu *vcpu)
{
+ unsigned long liobn = kvmppc_get_gpr(vcpu, 4);
+ unsigned long ioba = kvmppc_get_gpr(vcpu, 5);
+ unsigned long tce = kvmppc_get_gpr(vcpu, 6);
long rc;
- rc = kvmppc_h_logical_ci_store(vcpu);
+ rc = kvmppc_h_put_tce(vcpu, liobn, ioba, tce);
if (rc == H_TOO_HARD)
return EMULATE_FAIL;
kvmppc_set_gpr(vcpu, 3, rc);
return EMULATE_DONE;
}
+#else /* CONFIG_SPAPR_TCE_IOMMU */
+static int kvmppc_h_pr_put_tce(struct kvm_vcpu *vcpu)
+{
+ return EMULATE_FAIL;
+}
+
+static int kvmppc_h_pr_put_tce_indirect(struct kvm_vcpu *vcpu)
+{
+ return EMULATE_FAIL;
+}
+
+static int kvmppc_h_pr_stuff_tce(struct kvm_vcpu *vcpu)
+{
+ return EMULATE_FAIL;
+}
+#endif /* CONFIG_SPAPR_TCE_IOMMU */
+
static int kvmppc_h_pr_xics_hcall(struct kvm_vcpu *vcpu, u32 cmd)
{
long rc = kvmppc_xics_hcall(vcpu, cmd);
r = kvm_vm_ioctl_enable_cap(kvm, &cap);
break;
}
-#ifdef CONFIG_PPC_BOOK3S_64
+#ifdef CONFIG_SPAPR_TCE_IOMMU
case KVM_CREATE_SPAPR_TCE_64: {
struct kvm_create_spapr_tce_64 create_tce_64;
r = kvm_vm_ioctl_create_spapr_tce(kvm, &create_tce_64);
goto out;
}
+#endif
+#ifdef CONFIG_PPC_BOOK3S_64
case KVM_PPC_GET_SMMU_INFO: {
struct kvm_ppc_smmu_info info;
struct kvm *kvm = filp->private_data;
*/
#include <linux/debugfs.h>
#include <linux/fs.h>
+#include <linux/hugetlb.h>
#include <linux/io.h>
#include <linux/mm.h>
#include <linux/sched.h>
for (i = 0; i < PTRS_PER_PMD; i++, pmd++) {
addr = start + i * PMD_SIZE;
- if (!pmd_none(*pmd))
+ if (!pmd_none(*pmd) && !pmd_huge(*pmd))
/* pmd exists */
walk_pte(st, pmd, addr);
else
for (i = 0; i < PTRS_PER_PUD; i++, pud++) {
addr = start + i * PUD_SIZE;
- if (!pud_none(*pud))
+ if (!pud_none(*pud) && !pud_huge(*pud))
/* pud exists */
walk_pmd(st, pud, addr);
else
*/
for (i = 0; i < PTRS_PER_PGD; i++, pgd++) {
addr = KERN_VIRT_START + i * PGDIR_SIZE;
- if (!pgd_none(*pgd))
+ if (!pgd_none(*pgd) && !pgd_huge(*pgd))
/* pgd exists */
walk_pud(st, pgd, addr);
else
* mm->context.addr_limit. Default to max task size so that we copy the
* default values to paca which will help us to handle slb miss early.
*/
- mm->context.addr_limit = TASK_SIZE_128TB;
+ mm->context.addr_limit = DEFAULT_MAP_WINDOW_USER64;
/*
* The old code would re-promote on fork, we don't do that when using
.name = "POWER9",
.n_counter = MAX_PMU_COUNTERS,
.add_fields = ISA207_ADD_FIELDS,
- .test_adder = ISA207_TEST_ADDER,
+ .test_adder = P9_DD1_TEST_ADDER,
.compute_mmcr = isa207_compute_mmcr,
.config_bhrb = power9_config_bhrb,
.bhrb_filter_map = power9_bhrb_filter_map,
.name = "POWER9",
.n_counter = MAX_PMU_COUNTERS,
.add_fields = ISA207_ADD_FIELDS,
- .test_adder = P9_DD1_TEST_ADDER,
+ .test_adder = ISA207_TEST_ADDER,
.compute_mmcr = isa207_compute_mmcr,
.config_bhrb = power9_config_bhrb,
.bhrb_filter_map = power9_bhrb_filter_map,
In case of doubt, say Y
+config PPC_DT_CPU_FTRS
+ bool "Device-tree based CPU feature discovery & setup"
+ depends on PPC_BOOK3S_64
+ default y
+ help
+ This enables code to use a new device tree binding for describing CPU
+ compatibility and features. Saying Y here will attempt to use the new
+ binding if the firmware provides it. Currently only the skiboot
+ firmware provides this binding.
+ If you're not sure say Y.
+
config UDBG_RTAS_CONSOLE
bool "RTAS based debug console"
depends on PPC_RTAS
(REGION_ID(ea) != USER_REGION_ID)) {
spin_unlock(&spu->register_lock);
- ret = hash_page(ea, _PAGE_PRESENT | _PAGE_READ, 0x300, dsisr);
+ ret = hash_page(ea,
+ _PAGE_PRESENT | _PAGE_READ | _PAGE_PRIVILEGED,
+ 0x300, dsisr);
spin_lock(&spu->register_lock);
if (!ret) {
skip = roundup(cprm->pos - total + sz, 4) - cprm->pos;
if (!dump_skip(cprm, skip))
goto Eio;
+
+ rc = 0;
out:
free_page((unsigned long)buf);
return rc;
void pnv_npu2_destroy_context(struct npu_context *npu_context,
struct pci_dev *gpdev)
{
- struct pnv_phb *nphb, *phb;
+ struct pnv_phb *nphb;
struct npu *npu;
struct pci_dev *npdev = pnv_pci_get_npu_dev(gpdev, 0);
struct device_node *nvlink_dn;
nphb = pci_bus_to_host(npdev->bus)->private_data;
npu = &nphb->npu;
- phb = pci_bus_to_host(gpdev->bus)->private_data;
nvlink_dn = of_parse_phandle(npdev->dev.of_node, "ibm,nvlink", 0);
if (WARN_ON(of_property_read_u32(nvlink_dn, "ibm,npu-link-index",
&nvlink_index)))
return;
npu_context->npdev[npu->index][nvlink_index] = NULL;
- opal_npu_destroy_context(phb->opal_id, npu_context->mm->context.id,
+ opal_npu_destroy_context(nphb->opal_id, npu_context->mm->context.id,
PCI_DEVID(gpdev->bus->number, gpdev->devfn));
kref_put(&npu_context->kref, pnv_npu2_release_context);
}
static int subcore_init(void)
{
- if (!cpu_has_feature(CPU_FTR_SUBCORE))
+ unsigned pvr_ver;
+
+ pvr_ver = PVR_VER(mfspr(SPRN_PVR));
+
+ if (pvr_ver != PVR_POWER8 &&
+ pvr_ver != PVR_POWER8E &&
+ pvr_ver != PVR_POWER8NVL)
return 0;
/*
for (i = 0; i < num_lmbs; i++) {
lmbs[i].base_addr = be64_to_cpu(lmbs[i].base_addr);
lmbs[i].drc_index = be32_to_cpu(lmbs[i].drc_index);
+ lmbs[i].aa_index = be32_to_cpu(lmbs[i].aa_index);
lmbs[i].flags = be32_to_cpu(lmbs[i].flags);
}
for (i = 0; i < num_lmbs; i++) {
lmbs[i].base_addr = cpu_to_be64(lmbs[i].base_addr);
lmbs[i].drc_index = cpu_to_be32(lmbs[i].drc_index);
+ lmbs[i].aa_index = cpu_to_be32(lmbs[i].aa_index);
lmbs[i].flags = cpu_to_be32(lmbs[i].flags);
}
static void u8_gpio_save_regs(struct of_mm_gpio_chip *mm_gc)
{
- struct u8_gpio_chip *u8_gc = gpiochip_get_data(&mm_gc->gc);
+ struct u8_gpio_chip *u8_gc =
+ container_of(mm_gc, struct u8_gpio_chip, mm_gc);
u8_gc->data = in_8(mm_gc->regs);
}
config SYSVIPC_COMPAT
def_bool y if COMPAT && SYSVIPC
-config KEYS_COMPAT
- def_bool y if COMPAT && KEYS
-
config SMP
def_bool y
prompt "Symmetric multi-processing support"
struct mutex ais_lock;
u8 simm;
u8 nimm;
- int ais_enabled;
};
struct kvm_hw_wp_info_arch {
struct kvm_s390_ais_req req;
int ret = 0;
- if (!fi->ais_enabled)
+ if (!test_kvm_facility(kvm, 72))
return -ENOTSUPP;
if (copy_from_user(&req, (void __user *)attr->addr, sizeof(req)))
};
int ret = 0;
- if (!fi->ais_enabled || !adapter->suppressible)
+ if (!test_kvm_facility(kvm, 72) || !adapter->suppressible)
return kvm_s390_inject_vm(kvm, &s390int);
mutex_lock(&fi->ais_lock);
} else {
set_kvm_facility(kvm->arch.model.fac_mask, 72);
set_kvm_facility(kvm->arch.model.fac_list, 72);
- kvm->arch.float_int.ais_enabled = 1;
r = 0;
}
mutex_unlock(&kvm->lock);
mutex_init(&kvm->arch.float_int.ais_lock);
kvm->arch.float_int.simm = 0;
kvm->arch.float_int.nimm = 0;
- kvm->arch.float_int.ais_enabled = 0;
spin_lock_init(&kvm->arch.float_int.lock);
for (i = 0; i < FIRQ_LIST_COUNT; i++)
INIT_LIST_HEAD(&kvm->arch.float_int.lists[i]);
int "Maximum number of CPUs"
depends on SMP
range 2 32 if SPARC32
- range 2 1024 if SPARC64
+ range 2 4096 if SPARC64
default 32 if SPARC32
- default 64 if SPARC64
+ default 4096 if SPARC64
source kernel/Kconfig.hz
depends on SPARC64 && SMP
config NODES_SHIFT
- int
- default "4"
+ int "Maximum NUMA Nodes (as a power of 2)"
+ range 4 5 if SPARC64
+ default "5"
depends on NEED_MULTIPLE_NODES
+ help
+ Specify the maximum number of NUMA Nodes available on the target
+ system. Increases memory reserved to accommodate various tables.
# Some NUMA nodes have memory ranges that span
# other nodes. Even though a pfn is valid and
depends on COMPAT && SYSVIPC
default y
-config KEYS_COMPAT
- def_bool y if COMPAT && KEYS
-
endmenu
source "net/Kconfig"
static inline int prepare_hugepage_range(struct file *file,
unsigned long addr, unsigned long len)
{
- if (len & ~HPAGE_MASK)
+ struct hstate *h = hstate_file(file);
+
+ if (len & ~huge_page_mask(h))
return -EINVAL;
- if (addr & ~HPAGE_MASK)
+ if (addr & ~huge_page_mask(h))
return -EINVAL;
return 0;
}
#define CTX_NR_MASK TAG_CONTEXT_BITS
#define CTX_HW_MASK (CTX_NR_MASK | CTX_PGSZ_MASK)
-#define CTX_FIRST_VERSION ((_AC(1,UL) << CTX_VERSION_SHIFT) + _AC(1,UL))
+#define CTX_FIRST_VERSION BIT(CTX_VERSION_SHIFT)
#define CTX_VALID(__ctx) \
(!(((__ctx.sparc64_ctx_val) ^ tlb_context_cache) & CTX_VERSION_MASK))
#define CTX_HWBITS(__ctx) ((__ctx.sparc64_ctx_val) & CTX_HW_MASK)
extern unsigned long tlb_context_cache;
extern unsigned long mmu_context_bmap[];
+DECLARE_PER_CPU(struct mm_struct *, per_cpu_secondary_mm);
void get_new_mmu_context(struct mm_struct *mm);
-#ifdef CONFIG_SMP
-void smp_new_mmu_context_version(void);
-#else
-#define smp_new_mmu_context_version() do { } while (0)
-#endif
-
int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
void destroy_context(struct mm_struct *mm);
static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, struct task_struct *tsk)
{
unsigned long ctx_valid, flags;
- int cpu;
+ int cpu = smp_processor_id();
+ per_cpu(per_cpu_secondary_mm, cpu) = mm;
if (unlikely(mm == &init_mm))
return;
* for the first time, we must flush that context out of the
* local TLB.
*/
- cpu = smp_processor_id();
if (!ctx_valid || !cpumask_test_cpu(cpu, mm_cpumask(mm))) {
cpumask_set_cpu(cpu, mm_cpumask(mm));
__flush_tlb_mm(CTX_HWBITS(mm->context),
}
#define deactivate_mm(tsk,mm) do { } while (0)
-
-/* Activate a new MM instance for the current task. */
-static inline void activate_mm(struct mm_struct *active_mm, struct mm_struct *mm)
-{
- unsigned long flags;
- int cpu;
-
- spin_lock_irqsave(&mm->context.lock, flags);
- if (!CTX_VALID(mm->context))
- get_new_mmu_context(mm);
- cpu = smp_processor_id();
- if (!cpumask_test_cpu(cpu, mm_cpumask(mm)))
- cpumask_set_cpu(cpu, mm_cpumask(mm));
-
- load_secondary_context(mm);
- __flush_tlb_mm(CTX_HWBITS(mm->context), SECONDARY_CONTEXT);
- tsb_context_switch(mm);
- spin_unlock_irqrestore(&mm->context.lock, flags);
-}
-
+#define activate_mm(active_mm, mm) switch_mm(active_mm, mm, NULL)
#endif /* !(__ASSEMBLY__) */
#endif /* !(__SPARC64_MMU_CONTEXT_H) */
* ZERO_PAGE is a global shared page that is always zero: used
* for zero-mapped memory areas etc..
*/
-extern unsigned long empty_zero_page;
+extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
-#define ZERO_PAGE(vaddr) (virt_to_page(&empty_zero_page))
+#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
/*
* In general all page table modifications should use the V8 atomic
#define PIL_SMP_CALL_FUNC 1
#define PIL_SMP_RECEIVE_SIGNAL 2
#define PIL_SMP_CAPTURE 3
-#define PIL_SMP_CTX_NEW_VERSION 4
#define PIL_DEVICE_IRQ 5
#define PIL_SMP_CALL_FUNC_SNGL 6
#define PIL_DEFERRED_PCR_WORK 7
*/
extern unsigned char boot_cpu_id;
-extern unsigned long empty_zero_page;
+extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
extern int serial_console;
static inline int con_is_present(void)
int compat_len;
u64 dev_no;
+ u64 id;
unsigned long channel_id;
pbuf.req.handle = cp->handle;
pbuf.req.major = 1;
pbuf.req.minor = 0;
- strcpy(pbuf.req.svc_id, cp->service_id);
+ strcpy(pbuf.id_buf, cp->service_id);
err = __ds_send(lp, &pbuf, msg_len);
if (err > 0)
if (unlikely(atomic_read(¤t->tracing_graph_pause)))
return parent + 8UL;
- if (ftrace_push_return_trace(parent, self_addr, &trace.depth,
- frame_pointer, NULL) == -EBUSY)
- return parent + 8UL;
-
trace.func = self_addr;
+ trace.depth = current->curr_ret_stack + 1;
/* Only trace if the calling function expects to */
- if (!ftrace_graph_entry(&trace)) {
- current->curr_ret_stack--;
+ if (!ftrace_graph_entry(&trace))
+ return parent + 8UL;
+
+ if (ftrace_push_return_trace(parent, self_addr, &trace.depth,
+ frame_pointer, NULL) == -EBUSY)
return parent + 8UL;
- }
return return_hooker;
}
{
#ifdef CONFIG_SMP
unsigned long page;
+ void *mondo, *p;
- BUILD_BUG_ON((NR_CPUS * sizeof(u16)) > (PAGE_SIZE - 64));
+ BUILD_BUG_ON((NR_CPUS * sizeof(u16)) > PAGE_SIZE);
+
+ /* Make sure mondo block is 64byte aligned */
+ p = kzalloc(127, GFP_KERNEL);
+ if (!p) {
+ prom_printf("SUN4V: Error, cannot allocate mondo block.\n");
+ prom_halt();
+ }
+ mondo = (void *)(((unsigned long)p + 63) & ~0x3f);
+ tb->cpu_mondo_block_pa = __pa(mondo);
page = get_zeroed_page(GFP_KERNEL);
if (!page) {
- prom_printf("SUN4V: Error, cannot allocate cpu mondo page.\n");
+ prom_printf("SUN4V: Error, cannot allocate cpu list page.\n");
prom_halt();
}
- tb->cpu_mondo_block_pa = __pa(page);
- tb->cpu_list_pa = __pa(page + 64);
+ tb->cpu_list_pa = __pa(page);
#endif
}
/* smp_64.c */
void __irq_entry smp_call_function_client(int irq, struct pt_regs *regs);
void __irq_entry smp_call_function_single_client(int irq, struct pt_regs *regs);
-void __irq_entry smp_new_mmu_context_version_client(int irq, struct pt_regs *regs);
void __irq_entry smp_penguin_jailcell(int irq, struct pt_regs *regs);
void __irq_entry smp_receive_signal_client(int irq, struct pt_regs *regs);
preempt_enable();
}
-void __irq_entry smp_new_mmu_context_version_client(int irq, struct pt_regs *regs)
-{
- struct mm_struct *mm;
- unsigned long flags;
-
- clear_softint(1 << irq);
-
- /* See if we need to allocate a new TLB context because
- * the version of the one we are using is now out of date.
- */
- mm = current->active_mm;
- if (unlikely(!mm || (mm == &init_mm)))
- return;
-
- spin_lock_irqsave(&mm->context.lock, flags);
-
- if (unlikely(!CTX_VALID(mm->context)))
- get_new_mmu_context(mm);
-
- spin_unlock_irqrestore(&mm->context.lock, flags);
-
- load_secondary_context(mm);
- __flush_tlb_mm(CTX_HWBITS(mm->context),
- SECONDARY_CONTEXT);
-}
-
-void smp_new_mmu_context_version(void)
-{
- smp_cross_call(&xcall_new_mmu_context_version, 0, 0, 0);
-}
-
#ifdef CONFIG_KGDB
void kgdb_roundup_cpus(unsigned long flags)
{
.type copy_tsb,#function
copy_tsb: /* %o0=old_tsb_base, %o1=old_tsb_size
* %o2=new_tsb_base, %o3=new_tsb_size
+ * %o4=page_size_shift
*/
sethi %uhi(TSB_PASS_BITS), %g7
srlx %o3, 4, %o3
- add %o0, %o1, %g1 /* end of old tsb */
+ add %o0, %o1, %o1 /* end of old tsb */
sllx %g7, 32, %g7
sub %o3, 1, %o3 /* %o3 == new tsb hash mask */
+ mov %o4, %g1 /* page_size_shift */
+
661: prefetcha [%o0] ASI_N, #one_read
.section .tsb_phys_patch, "ax"
.word 661b
/* This can definitely be computed faster... */
srlx %o0, 4, %o5 /* Build index */
and %o5, 511, %o5 /* Mask index */
- sllx %o5, PAGE_SHIFT, %o5 /* Put into vaddr position */
+ sllx %o5, %g1, %o5 /* Put into vaddr position */
or %o4, %o5, %o4 /* Full VADDR. */
- srlx %o4, PAGE_SHIFT, %o4 /* Shift down to create index */
+ srlx %o4, %g1, %o4 /* Shift down to create index */
and %o4, %o3, %o4 /* Mask with new_tsb_nents-1 */
sllx %o4, 4, %o4 /* Shift back up into tsb ent offset */
TSB_STORE(%o2 + %o4, %g2) /* Store TAG */
TSB_STORE(%o2 + %o4, %g3) /* Store TTE */
80: add %o0, 16, %o0
- cmp %o0, %g1
+ cmp %o0, %o1
bne,pt %xcc, 90b
nop
tl0_irq1: TRAP_IRQ(smp_call_function_client, 1)
tl0_irq2: TRAP_IRQ(smp_receive_signal_client, 2)
tl0_irq3: TRAP_IRQ(smp_penguin_jailcell, 3)
-tl0_irq4: TRAP_IRQ(smp_new_mmu_context_version_client, 4)
+tl0_irq4: BTRAP(0x44)
#else
tl0_irq1: BTRAP(0x41)
tl0_irq2: BTRAP(0x42)
if (!id) {
dev_set_name(&vdev->dev, "%s", bus_id_name);
vdev->dev_no = ~(u64)0;
+ vdev->id = ~(u64)0;
} else if (!cfg_handle) {
dev_set_name(&vdev->dev, "%s-%llu", bus_id_name, *id);
vdev->dev_no = *id;
+ vdev->id = ~(u64)0;
} else {
dev_set_name(&vdev->dev, "%s-%llu-%llu", bus_id_name,
*cfg_handle, *id);
vdev->dev_no = *cfg_handle;
+ vdev->id = *id;
}
vdev->dev.parent = parent;
(void) vio_create_one(hp, node, &root_vdev->dev);
}
+struct vio_md_node_query {
+ const char *type;
+ u64 dev_no;
+ u64 id;
+};
+
static int vio_md_node_match(struct device *dev, void *arg)
{
+ struct vio_md_node_query *query = (struct vio_md_node_query *) arg;
struct vio_dev *vdev = to_vio_dev(dev);
- if (vdev->mp == (u64) arg)
- return 1;
+ if (vdev->dev_no != query->dev_no)
+ return 0;
+ if (vdev->id != query->id)
+ return 0;
+ if (strcmp(vdev->type, query->type))
+ return 0;
- return 0;
+ return 1;
}
static void vio_remove(struct mdesc_handle *hp, u64 node)
{
+ const char *type;
+ const u64 *id, *cfg_handle;
+ u64 a;
+ struct vio_md_node_query query;
struct device *dev;
- dev = device_find_child(&root_vdev->dev, (void *) node,
+ type = mdesc_get_property(hp, node, "device-type", NULL);
+ if (!type) {
+ type = mdesc_get_property(hp, node, "name", NULL);
+ if (!type)
+ type = mdesc_node_name(hp, node);
+ }
+
+ query.type = type;
+
+ id = mdesc_get_property(hp, node, "id", NULL);
+ cfg_handle = NULL;
+ mdesc_for_each_arc(a, hp, node, MDESC_ARC_TYPE_BACK) {
+ u64 target;
+
+ target = mdesc_arc_target(hp, a);
+ cfg_handle = mdesc_get_property(hp, target,
+ "cfg-handle", NULL);
+ if (cfg_handle)
+ break;
+ }
+
+ if (!id) {
+ query.dev_no = ~(u64)0;
+ query.id = ~(u64)0;
+ } else if (!cfg_handle) {
+ query.dev_no = *id;
+ query.id = ~(u64)0;
+ } else {
+ query.dev_no = *cfg_handle;
+ query.id = *id;
+ }
+
+ dev = device_find_child(&root_vdev->dev, &query,
vio_md_node_match);
if (dev) {
printk(KERN_INFO "VIO: Removing device %s\n", dev_name(dev));
device_unregister(dev);
put_device(dev);
+ } else {
+ if (!id)
+ printk(KERN_ERR "VIO: Removed unknown %s node.\n",
+ type);
+ else if (!cfg_handle)
+ printk(KERN_ERR "VIO: Removed unknown %s node %llu.\n",
+ type, *id);
+ else
+ printk(KERN_ERR "VIO: Removed unknown %s node %llu-%llu.\n",
+ type, *cfg_handle, *id);
}
}
lib-$(CONFIG_SPARC64) += atomic_64.o
lib-$(CONFIG_SPARC32) += lshrdi3.o ashldi3.o
lib-$(CONFIG_SPARC32) += muldi3.o bitext.o cmpdi2.o
+lib-$(CONFIG_SPARC64) += multi3.o
lib-$(CONFIG_SPARC64) += copy_page.o clear_page.o bzero.o
lib-$(CONFIG_SPARC64) += csum_copy.o csum_copy_from_user.o csum_copy_to_user.o
--- /dev/null
+#include <linux/linkage.h>
+#include <asm/export.h>
+
+ .text
+ .align 4
+ENTRY(__multi3) /* %o0 = u, %o1 = v */
+ mov %o1, %g1
+ srl %o3, 0, %g4
+ mulx %g4, %g1, %o1
+ srlx %g1, 0x20, %g3
+ mulx %g3, %g4, %g5
+ sllx %g5, 0x20, %o5
+ srl %g1, 0, %g4
+ sub %o1, %o5, %o5
+ srlx %o5, 0x20, %o5
+ addcc %g5, %o5, %g5
+ srlx %o3, 0x20, %o5
+ mulx %g4, %o5, %g4
+ mulx %g3, %o5, %o5
+ sethi %hi(0x80000000), %g3
+ addcc %g5, %g4, %g5
+ srlx %g5, 0x20, %g5
+ add %g3, %g3, %g3
+ movcc %xcc, %g0, %g3
+ addcc %o5, %g5, %o5
+ sllx %g4, 0x20, %g4
+ add %o1, %g4, %o1
+ add %o5, %g3, %g2
+ mulx %g1, %o2, %g1
+ add %g1, %g2, %g1
+ mulx %o0, %o3, %o0
+ retl
+ add %g1, %o0, %o0
+ENDPROC(__multi3)
+EXPORT_SYMBOL(__multi3)
/* Saves us work later. */
- memset((void *)&empty_zero_page, 0, PAGE_SIZE);
+ memset((void *)empty_zero_page, 0, PAGE_SIZE);
i = last_valid_pfn >> ((20 - PAGE_SHIFT) + 5);
i += 1;
}
if ((hv_pgsz_mask & cpu_pgsz_mask) == 0U) {
- pr_warn("hugepagesz=%llu not supported by MMU.\n",
+ hugetlb_bad_size();
+ pr_err("hugepagesz=%llu not supported by MMU.\n",
hugepage_size);
goto out;
}
/* get_new_mmu_context() uses "cache + 1". */
DEFINE_SPINLOCK(ctx_alloc_lock);
-unsigned long tlb_context_cache = CTX_FIRST_VERSION - 1;
+unsigned long tlb_context_cache = CTX_FIRST_VERSION;
#define MAX_CTX_NR (1UL << CTX_NR_BITS)
#define CTX_BMAP_SLOTS BITS_TO_LONGS(MAX_CTX_NR)
DECLARE_BITMAP(mmu_context_bmap, MAX_CTX_NR);
+DEFINE_PER_CPU(struct mm_struct *, per_cpu_secondary_mm) = {0};
+
+static void mmu_context_wrap(void)
+{
+ unsigned long old_ver = tlb_context_cache & CTX_VERSION_MASK;
+ unsigned long new_ver, new_ctx, old_ctx;
+ struct mm_struct *mm;
+ int cpu;
+
+ bitmap_zero(mmu_context_bmap, 1 << CTX_NR_BITS);
+
+ /* Reserve kernel context */
+ set_bit(0, mmu_context_bmap);
+
+ new_ver = (tlb_context_cache & CTX_VERSION_MASK) + CTX_FIRST_VERSION;
+ if (unlikely(new_ver == 0))
+ new_ver = CTX_FIRST_VERSION;
+ tlb_context_cache = new_ver;
+
+ /*
+ * Make sure that any new mm that are added into per_cpu_secondary_mm,
+ * are going to go through get_new_mmu_context() path.
+ */
+ mb();
+
+ /*
+ * Updated versions to current on those CPUs that had valid secondary
+ * contexts
+ */
+ for_each_online_cpu(cpu) {
+ /*
+ * If a new mm is stored after we took this mm from the array,
+ * it will go into get_new_mmu_context() path, because we
+ * already bumped the version in tlb_context_cache.
+ */
+ mm = per_cpu(per_cpu_secondary_mm, cpu);
+
+ if (unlikely(!mm || mm == &init_mm))
+ continue;
+
+ old_ctx = mm->context.sparc64_ctx_val;
+ if (likely((old_ctx & CTX_VERSION_MASK) == old_ver)) {
+ new_ctx = (old_ctx & ~CTX_VERSION_MASK) | new_ver;
+ set_bit(new_ctx & CTX_NR_MASK, mmu_context_bmap);
+ mm->context.sparc64_ctx_val = new_ctx;
+ }
+ }
+}
/* Caller does TLB context flushing on local CPU if necessary.
* The caller also ensures that CTX_VALID(mm->context) is false.
{
unsigned long ctx, new_ctx;
unsigned long orig_pgsz_bits;
- int new_version;
spin_lock(&ctx_alloc_lock);
+retry:
+ /* wrap might have happened, test again if our context became valid */
+ if (unlikely(CTX_VALID(mm->context)))
+ goto out;
orig_pgsz_bits = (mm->context.sparc64_ctx_val & CTX_PGSZ_MASK);
ctx = (tlb_context_cache + 1) & CTX_NR_MASK;
new_ctx = find_next_zero_bit(mmu_context_bmap, 1 << CTX_NR_BITS, ctx);
- new_version = 0;
if (new_ctx >= (1 << CTX_NR_BITS)) {
new_ctx = find_next_zero_bit(mmu_context_bmap, ctx, 1);
if (new_ctx >= ctx) {
- int i;
- new_ctx = (tlb_context_cache & CTX_VERSION_MASK) +
- CTX_FIRST_VERSION;
- if (new_ctx == 1)
- new_ctx = CTX_FIRST_VERSION;
-
- /* Don't call memset, for 16 entries that's just
- * plain silly...
- */
- mmu_context_bmap[0] = 3;
- mmu_context_bmap[1] = 0;
- mmu_context_bmap[2] = 0;
- mmu_context_bmap[3] = 0;
- for (i = 4; i < CTX_BMAP_SLOTS; i += 4) {
- mmu_context_bmap[i + 0] = 0;
- mmu_context_bmap[i + 1] = 0;
- mmu_context_bmap[i + 2] = 0;
- mmu_context_bmap[i + 3] = 0;
- }
- new_version = 1;
- goto out;
+ mmu_context_wrap();
+ goto retry;
}
}
+ if (mm->context.sparc64_ctx_val)
+ cpumask_clear(mm_cpumask(mm));
mmu_context_bmap[new_ctx>>6] |= (1UL << (new_ctx & 63));
new_ctx |= (tlb_context_cache & CTX_VERSION_MASK);
-out:
tlb_context_cache = new_ctx;
mm->context.sparc64_ctx_val = new_ctx | orig_pgsz_bits;
+out:
spin_unlock(&ctx_alloc_lock);
-
- if (unlikely(new_version))
- smp_new_mmu_context_version();
}
static int numa_enabled = 1;
extern void copy_tsb(unsigned long old_tsb_base,
unsigned long old_tsb_size,
unsigned long new_tsb_base,
- unsigned long new_tsb_size);
+ unsigned long new_tsb_size,
+ unsigned long page_size_shift);
unsigned long old_tsb_base = (unsigned long) old_tsb;
unsigned long new_tsb_base = (unsigned long) new_tsb;
old_tsb_base = __pa(old_tsb_base);
new_tsb_base = __pa(new_tsb_base);
}
- copy_tsb(old_tsb_base, old_size, new_tsb_base, new_size);
+ copy_tsb(old_tsb_base, old_size, new_tsb_base, new_size,
+ tsb_index == MM_TSB_BASE ?
+ PAGE_SHIFT : REAL_HPAGE_SHIFT);
}
mm->context.tsb_block[tsb_index].tsb = new_tsb;
wr %g0, (1 << PIL_SMP_CAPTURE), %set_softint
retry
- .globl xcall_new_mmu_context_version
-xcall_new_mmu_context_version:
- wr %g0, (1 << PIL_SMP_CTX_NEW_VERSION), %set_softint
- retry
-
#ifdef CONFIG_KGDB
.globl xcall_kgdb_capture
xcall_kgdb_capture:
Management" code will be disabled if you say Y here.
See also <file:Documentation/x86/i386/IO-APIC.txt>,
- <file:Documentation/nmi_watchdog.txt> and the SMP-HOWTO available at
+ <file:Documentation/lockup-watchdogs.txt> and the SMP-HOWTO available at
<http://www.tldp.org/docs.html#howto>.
If you don't know what to do here, say N.
config SYSVIPC_COMPAT
def_bool y
depends on SYSVIPC
-
-config KEYS_COMPAT
- def_bool y
- depends on KEYS
endif
endmenu
# If '-Os' is enabled, disable it and print a warning.
ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
undefine CONFIG_CC_OPTIMIZE_FOR_SIZE
- $(warning Disabling CONFIG_CC_OPTIMIZE_FOR_SIZE. Your compiler does not have -mfentry so you cannot optimize for size with CONFIG_FUNCTION_GRAPH_TRACER.)
+ $(warning Disabling CONFIG_CC_OPTIMIZE_FOR_SIZE. Your compiler does not have -mfentry so you cannot optimize for size with CONFIG_FUNCTION_GRAPH_TRACER.)
endif
endif
quiet_cmd_check_data_rel = DATAREL $@
define cmd_check_data_rel
for obj in $(filter %.o,$^); do \
- readelf -S $$obj | grep -qF .rel.local && { \
+ ${CROSS_COMPILE}readelf -S $$obj | grep -qF .rel.local && { \
echo "error: $$obj has data relocations!" >&2; \
exit 1; \
} || true; \
jmp __switch_to
END(__switch_to_asm)
+/*
+ * The unwinder expects the last frame on the stack to always be at the same
+ * offset from the end of the page, which allows it to validate the stack.
+ * Calling schedule_tail() directly would break that convention because its an
+ * asmlinkage function so its argument has to be pushed on the stack. This
+ * wrapper creates a proper "end of stack" frame header before the call.
+ */
+ENTRY(schedule_tail_wrapper)
+ FRAME_BEGIN
+
+ pushl %eax
+ call schedule_tail
+ popl %eax
+
+ FRAME_END
+ ret
+ENDPROC(schedule_tail_wrapper)
/*
* A newly forked process directly context switches into this address.
*
* edi: kernel thread arg
*/
ENTRY(ret_from_fork)
- FRAME_BEGIN /* help unwinder find end of stack */
-
- /*
- * schedule_tail() is asmlinkage so we have to put its 'prev' argument
- * on the stack.
- */
- pushl %eax
- call schedule_tail
- popl %eax
+ call schedule_tail_wrapper
testl %ebx, %ebx
jnz 1f /* kernel threads are uncommon */
2:
/* When we fork, we trace the syscall return in the child, too. */
- leal FRAME_OFFSET(%esp), %eax
+ movl %esp, %eax
call syscall_return_slowpath
- FRAME_END
jmp restore_all
/* kernel thread */
#include <asm/smap.h>
#include <asm/pgtable_types.h>
#include <asm/export.h>
-#include <asm/frame.h>
#include <linux/err.h>
.code64
* r12: kernel thread arg
*/
ENTRY(ret_from_fork)
- FRAME_BEGIN /* help unwinder find end of stack */
movq %rax, %rdi
- call schedule_tail /* rdi: 'prev' task parameter */
+ call schedule_tail /* rdi: 'prev' task parameter */
- testq %rbx, %rbx /* from kernel_thread? */
- jnz 1f /* kernel threads are uncommon */
+ testq %rbx, %rbx /* from kernel_thread? */
+ jnz 1f /* kernel threads are uncommon */
2:
- leaq FRAME_OFFSET(%rsp),%rdi /* pt_regs pointer */
+ movq %rsp, %rdi
call syscall_return_slowpath /* returns with IRQs disabled */
TRACE_IRQS_ON /* user mode is traced as IRQS on */
SWAPGS
- FRAME_END
jmp restore_regs_and_iret
1:
#define KVM_PRIVATE_MEM_SLOTS 3
#define KVM_MEM_SLOTS_NUM (KVM_USER_MEM_SLOTS + KVM_PRIVATE_MEM_SLOTS)
-#define KVM_HALT_POLL_NS_DEFAULT 400000
+#define KVM_HALT_POLL_NS_DEFAULT 200000
#define KVM_IRQCHIP_NUM_PINS KVM_IOAPIC_NUM_PINS
#endif
int mce_available(struct cpuinfo_x86 *c);
+bool mce_is_memory_error(struct mce *m);
DECLARE_PER_CPU(unsigned, mce_exception_count);
DECLARE_PER_CPU(unsigned, mce_poll_count);
#define __get_user_asm_u64(x, ptr, retval, errret) \
({ \
__typeof__(ptr) __ptr = (ptr); \
- asm volatile(ASM_STAC "\n" \
+ asm volatile("\n" \
"1: movl %2,%%eax\n" \
"2: movl %3,%%edx\n" \
- "3: " ASM_CLAC "\n" \
+ "3:\n" \
".section .fixup,\"ax\"\n" \
"4: mov %4,%0\n" \
" xorl %%eax,%%eax\n" \
".previous\n" \
_ASM_EXTABLE(1b, 4b) \
_ASM_EXTABLE(2b, 4b) \
- : "=r" (retval), "=A"(x) \
+ : "=r" (retval), "=&A"(x) \
: "m" (__m(__ptr)), "m" __m(((u32 *)(__ptr)) + 1), \
"i" (errret), "0" (retval)); \
})
#define unsafe_put_user(x, ptr, err_label) \
do { \
int __pu_err; \
- __put_user_size((x), (ptr), sizeof(*(ptr)), __pu_err, -EFAULT); \
+ __typeof__(*(ptr)) __pu_val = (x); \
+ __put_user_size(__pu_val, (ptr), sizeof(*(ptr)), __pu_err, -EFAULT); \
if (unlikely(__pu_err)) goto err_label; \
} while (0)
#define unsafe_get_user(x, ptr, err_label) \
do { \
int __gu_err; \
- unsigned long __gu_val; \
+ __inttype(*(ptr)) __gu_val; \
__get_user_size(__gu_val, (ptr), sizeof(*(ptr)), __gu_err, -EFAULT); \
(x) = (__force __typeof__(*(ptr)))__gu_val; \
if (unlikely(__gu_err)) goto err_label; \
memcpy(insnbuf, replacement, a->replacementlen);
insnbuf_sz = a->replacementlen;
- /* 0xe8 is a relative jump; fix the offset. */
- if (*insnbuf == 0xe8 && a->replacementlen == 5) {
+ /*
+ * 0xe8 is a relative jump; fix the offset.
+ *
+ * Instruction length is checked before the opcode to avoid
+ * accessing uninitialized bytes for zero-length replacements.
+ */
+ if (a->replacementlen == 5 && *insnbuf == 0xe8) {
*(s32 *)(insnbuf + 1) += replacement - instr;
DPRINTK("Fix CALL offset: 0x%x, CALL 0x%lx",
*(s32 *)(insnbuf + 1),
break;
case 4: /* MediaGX/GXm or Geode GXM/GXLV/GX1 */
+ case 11: /* GX1 with inverted Device ID */
#ifdef CONFIG_PCI
{
u32 vendor, device;
return 1;
}
-static bool memory_error(struct mce *m)
+bool mce_is_memory_error(struct mce *m)
{
- struct cpuinfo_x86 *c = &boot_cpu_data;
-
- if (c->x86_vendor == X86_VENDOR_AMD) {
+ if (m->cpuvendor == X86_VENDOR_AMD) {
/* ErrCodeExt[20:16] */
u8 xec = (m->status >> 16) & 0x1f;
return (xec == 0x0 || xec == 0x8);
- } else if (c->x86_vendor == X86_VENDOR_INTEL) {
+ } else if (m->cpuvendor == X86_VENDOR_INTEL) {
/*
* Intel SDM Volume 3B - 15.9.2 Compound Error Codes
*
return false;
}
+EXPORT_SYMBOL_GPL(mce_is_memory_error);
static bool cec_add_mce(struct mce *m)
{
return false;
/* We eat only correctable DRAM errors with usable addresses. */
- if (memory_error(m) &&
+ if (mce_is_memory_error(m) &&
!(m->status & MCI_STATUS_UC) &&
mce_usable_address(m))
if (!cec_add_elem(m->addr >> PAGE_SHIFT))
severity = mce_severity(&m, mca_cfg.tolerant, NULL, false);
- if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m))
+ if (severity == MCE_DEFERRED_SEVERITY && mce_is_memory_error(&m))
if (m.status & MCI_STATUS_ADDRV)
m.severity = severity;
}
static enum ucode_state
-load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size);
+load_microcode_amd(bool save, u8 family, const u8 *data, size_t size);
int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax)
{
if (!desc.mc)
return -EINVAL;
- ret = load_microcode_amd(smp_processor_id(), x86_family(cpuid_1_eax),
- desc.data, desc.size);
+ ret = load_microcode_amd(true, x86_family(cpuid_1_eax), desc.data, desc.size);
if (ret != UCODE_OK)
return -EINVAL;
}
static enum ucode_state
-load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size)
+load_microcode_amd(bool save, u8 family, const u8 *data, size_t size)
{
enum ucode_state ret;
#ifdef CONFIG_X86_32
/* save BSP's matching patch for early load */
- if (cpu_data(cpu).cpu_index == boot_cpu_data.cpu_index) {
- struct ucode_patch *p = find_patch(cpu);
+ if (save) {
+ struct ucode_patch *p = find_patch(0);
if (p) {
memset(amd_ucode_patch, 0, PATCH_MAX_SIZE);
memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data),
{
char fw_name[36] = "amd-ucode/microcode_amd.bin";
struct cpuinfo_x86 *c = &cpu_data(cpu);
+ bool bsp = c->cpu_index == boot_cpu_data.cpu_index;
enum ucode_state ret = UCODE_NFOUND;
const struct firmware *fw;
/* reload ucode container only on the boot cpu */
- if (!refresh_fw || c->cpu_index != boot_cpu_data.cpu_index)
+ if (!refresh_fw || !bsp)
return UCODE_OK;
if (c->x86 >= 0x15)
goto fw_release;
}
- ret = load_microcode_amd(cpu, c->x86, fw->data, fw->size);
+ ret = load_microcode_amd(bsp, c->x86, fw->data, fw->size);
fw_release:
release_firmware(fw);
show_saved_mc();
+ /* initrd is going away, clear patch ptr. */
+ intel_ucode_patch = NULL;
+
return 0;
}
* Boot time FPU feature detection code:
*/
unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu;
+EXPORT_SYMBOL_GPL(mxcsr_feature_mask);
static void __init fpu__init_system_mxcsr(void)
{
{
return module_alloc(size);
}
-static inline void tramp_free(void *tramp)
+static inline void tramp_free(void *tramp, int size)
{
+ int npages = PAGE_ALIGN(size) >> PAGE_SHIFT;
+
+ set_memory_nx((unsigned long)tramp, npages);
+ set_memory_rw((unsigned long)tramp, npages);
module_memfree(tramp);
}
#else
{
return NULL;
}
-static inline void tramp_free(void *tramp) { }
+static inline void tramp_free(void *tramp, int size) { }
#endif
/* Defined as markers to the end of the ftrace default trampolines */
/* Copy ftrace_caller onto the trampoline memory */
ret = probe_kernel_read(trampoline, (void *)start_offset, size);
if (WARN_ON(ret < 0)) {
- tramp_free(trampoline);
+ tramp_free(trampoline, *tramp_size);
return 0;
}
/* Are we pointing to the reference? */
if (WARN_ON(memcmp(op_ptr.op, op_ref, 3) != 0)) {
- tramp_free(trampoline);
+ tramp_free(trampoline, *tramp_size);
return 0;
}
unsigned long offset;
unsigned long ip;
unsigned int size;
- int ret;
+ int ret, npages;
if (ops->trampoline) {
/*
*/
if (!(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP))
return;
+ npages = PAGE_ALIGN(ops->trampoline_size) >> PAGE_SHIFT;
+ set_memory_rw(ops->trampoline, npages);
} else {
ops->trampoline = create_trampoline(ops, &size);
if (!ops->trampoline)
return;
ops->trampoline_size = size;
+ npages = PAGE_ALIGN(size) >> PAGE_SHIFT;
}
offset = calc_trampoline_call_offset(ops->flags & FTRACE_OPS_FL_SAVE_REGS);
/* Do a safe modify in case the trampoline is executing */
new = ftrace_call_replace(ip, (unsigned long)func);
ret = update_ftrace_func(ip, new);
+ set_memory_ro(ops->trampoline, npages);
/* The update should never fail */
WARN_ON(ret);
if (!ops || !(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP))
return;
- tramp_free((void *)ops->trampoline);
+ tramp_free((void *)ops->trampoline, ops->trampoline_size);
ops->trampoline = 0;
}
#include <linux/ftrace.h>
#include <linux/frame.h>
#include <linux/kasan.h>
+#include <linux/moduleloader.h>
#include <asm/text-patching.h>
#include <asm/cacheflush.h>
}
}
+/* Recover page to RW mode before releasing it */
+void free_insn_page(void *page)
+{
+ set_memory_nx((unsigned long)page & PAGE_MASK, 1);
+ set_memory_rw((unsigned long)page & PAGE_MASK, 1);
+ module_memfree(page);
+}
+
static int arch_copy_kprobe(struct kprobe *p)
{
struct insn insn;
*/
rcu_irq_exit();
native_safe_halt();
- rcu_irq_enter();
local_irq_disable();
+ rcu_irq_enter();
}
}
if (!n.halted)
printk(KERN_DEFAULT "EIP: %pS\n", (void *)regs->ip);
printk(KERN_DEFAULT "EFLAGS: %08lx CPU: %d\n", regs->flags,
- smp_processor_id());
+ raw_smp_processor_id());
printk(KERN_DEFAULT "EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n",
regs->ax, regs->bx, regs->cx, regs->dx);
*/
x86_configure_nx();
- simple_udelay_calibration();
-
parse_early_param();
#ifdef CONFIG_MEMORY_HOTPLUG
*/
init_hypervisor_platform();
+ simple_udelay_calibration();
+
x86_init.resources.probe_roms();
/* after parse_early_param, so could debug it */
return (unsigned long *)task_pt_regs(state->task) - 2;
}
+static bool is_last_frame(struct unwind_state *state)
+{
+ return state->bp == last_frame(state);
+}
+
#ifdef CONFIG_X86_32
#define GCC_REALIGN_WORDS 3
#else
return last_frame(state) - GCC_REALIGN_WORDS;
}
-static bool is_last_task_frame(struct unwind_state *state)
+static bool is_last_aligned_frame(struct unwind_state *state)
{
unsigned long *last_bp = last_frame(state);
unsigned long *aligned_bp = last_aligned_frame(state);
/*
- * We have to check for the last task frame at two different locations
- * because gcc can occasionally decide to realign the stack pointer and
- * change the offset of the stack frame in the prologue of a function
- * called by head/entry code. Examples:
+ * GCC can occasionally decide to realign the stack pointer and change
+ * the offset of the stack frame in the prologue of a function called
+ * by head/entry code. Examples:
*
* <start_secondary>:
* push %edi
* push %rbp
* mov %rsp,%rbp
*
- * Note that after aligning the stack, it pushes a duplicate copy of
- * the return address before pushing the frame pointer.
+ * After aligning the stack, it pushes a duplicate copy of the return
+ * address before pushing the frame pointer.
+ */
+ return (state->bp == aligned_bp && *(aligned_bp + 1) == *(last_bp + 1));
+}
+
+static bool is_last_ftrace_frame(struct unwind_state *state)
+{
+ unsigned long *last_bp = last_frame(state);
+ unsigned long *last_ftrace_bp = last_bp - 3;
+
+ /*
+ * When unwinding from an ftrace handler of a function called by entry
+ * code, the stack layout of the last frame is:
+ *
+ * bp
+ * parent ret addr
+ * bp
+ * function ret addr
+ * parent ret addr
+ * pt_regs
+ * -----------------
*/
- return (state->bp == last_bp ||
- (state->bp == aligned_bp && *(aligned_bp+1) == *(last_bp+1)));
+ return (state->bp == last_ftrace_bp &&
+ *state->bp == *(state->bp + 2) &&
+ *(state->bp + 1) == *(state->bp + 4));
+}
+
+static bool is_last_task_frame(struct unwind_state *state)
+{
+ return is_last_frame(state) || is_last_aligned_frame(state) ||
+ is_last_ftrace_frame(state);
}
/*
static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i)
{
struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i];
- int j, nent = vcpu->arch.cpuid_nent;
+ struct kvm_cpuid_entry2 *ej;
+ int j = i;
+ int nent = vcpu->arch.cpuid_nent;
e->flags &= ~KVM_CPUID_FLAG_STATE_READ_NEXT;
/* when no next entry is found, the current entry[i] is reselected */
- for (j = i + 1; ; j = (j + 1) % nent) {
- struct kvm_cpuid_entry2 *ej = &vcpu->arch.cpuid_entries[j];
- if (ej->function == e->function) {
- ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
- return j;
- }
- }
- return 0; /* silence gcc, even though control never reaches here */
+ do {
+ j = (j + 1) % nent;
+ ej = &vcpu->arch.cpuid_entries[j];
+ } while (ej->function != e->function);
+
+ ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
+
+ return j;
}
/* find an entry with matching function, matching index (if needed), and that
static int check_svme(struct x86_emulate_ctxt *ctxt)
{
- u64 efer;
+ u64 efer = 0;
ctxt->ops->get_msr(ctxt, MSR_EFER, &efer);
static void cancel_hv_timer(struct kvm_lapic *apic)
{
+ preempt_disable();
kvm_x86_ops->cancel_hv_timer(apic->vcpu);
apic->lapic_timer.hv_timer_in_use = false;
+ preempt_enable();
}
static bool start_hv_timer(struct kvm_lapic *apic)
for (i = 0; i < KVM_APIC_LVT_NUM; i++)
kvm_lapic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED);
apic_update_lvtt(apic);
- if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_LINT0_REENABLED))
+ if (kvm_vcpu_is_reset_bsp(vcpu) &&
+ kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_LINT0_REENABLED))
kvm_lapic_set_reg(apic, APIC_LVT0,
SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT));
apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0));
return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
}
-static bool can_do_async_pf(struct kvm_vcpu *vcpu)
+bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu)
{
if (unlikely(!lapic_in_kernel(vcpu) ||
kvm_event_needs_reinjection(vcpu)))
return false;
+ if (is_guest_mode(vcpu))
+ return false;
+
return kvm_x86_ops->interrupt_allowed(vcpu);
}
if (!async)
return false; /* *pfn has correct page already */
- if (!prefault && can_do_async_pf(vcpu)) {
+ if (!prefault && kvm_can_do_async_pf(vcpu)) {
trace_kvm_try_async_get_page(gva, gfn);
if (kvm_find_async_pf_gfn(vcpu, gfn)) {
trace_kvm_async_pf_doublefault(gva, gfn);
void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu);
void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
bool accessed_dirty);
+bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu);
static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
{
pt_element_t pte;
pt_element_t __user *uninitialized_var(ptep_user);
gfn_t table_gfn;
- unsigned index, pt_access, pte_access, accessed_dirty, pte_pkey;
+ u64 pt_access, pte_access;
+ unsigned index, accessed_dirty, pte_pkey;
unsigned nested_access;
gpa_t pte_gpa;
bool have_ad;
int offset;
+ u64 walk_nx_mask = 0;
const int write_fault = access & PFERR_WRITE_MASK;
const int user_fault = access & PFERR_USER_MASK;
const int fetch_fault = access & PFERR_FETCH_MASK;
have_ad = PT_HAVE_ACCESSED_DIRTY(mmu);
#if PTTYPE == 64
+ walk_nx_mask = 1ULL << PT64_NX_SHIFT;
if (walker->level == PT32E_ROOT_LEVEL) {
pte = mmu->get_pdptr(vcpu, (addr >> 30) & 3);
trace_kvm_mmu_paging_element(pte, walker->level);
walker->max_level = walker->level;
ASSERT(!(is_long_mode(vcpu) && !is_pae(vcpu)));
- accessed_dirty = have_ad ? PT_GUEST_ACCESSED_MASK : 0;
-
/*
* FIXME: on Intel processors, loads of the PDPTE registers for PAE paging
* by the MOV to CR instruction are treated as reads and do not cause the
*/
nested_access = (have_ad ? PFERR_WRITE_MASK : 0) | PFERR_USER_MASK;
- pt_access = pte_access = ACC_ALL;
+ pte_access = ~0;
++walker->level;
do {
gfn_t real_gfn;
unsigned long host_addr;
- pt_access &= pte_access;
+ pt_access = pte_access;
--walker->level;
index = PT_INDEX(addr, walker->level);
trace_kvm_mmu_paging_element(pte, walker->level);
+ /*
+ * Inverting the NX it lets us AND it like other
+ * permission bits.
+ */
+ pte_access = pt_access & (pte ^ walk_nx_mask);
+
if (unlikely(!FNAME(is_present_gpte)(pte)))
goto error;
goto error;
}
- accessed_dirty &= pte;
- pte_access = pt_access & FNAME(gpte_access)(vcpu, pte);
-
walker->ptes[walker->level - 1] = pte;
} while (!is_last_gpte(mmu, walker->level, pte));
pte_pkey = FNAME(gpte_pkeys)(vcpu, pte);
- errcode = permission_fault(vcpu, mmu, pte_access, pte_pkey, access);
+ accessed_dirty = have_ad ? pte_access & PT_GUEST_ACCESSED_MASK : 0;
+
+ /* Convert to ACC_*_MASK flags for struct guest_walker. */
+ walker->pt_access = FNAME(gpte_access)(vcpu, pt_access ^ walk_nx_mask);
+ walker->pte_access = FNAME(gpte_access)(vcpu, pte_access ^ walk_nx_mask);
+ errcode = permission_fault(vcpu, mmu, walker->pte_access, pte_pkey, access);
if (unlikely(errcode))
goto error;
walker->gfn = real_gpa >> PAGE_SHIFT;
if (!write_fault)
- FNAME(protect_clean_gpte)(mmu, &pte_access, pte);
+ FNAME(protect_clean_gpte)(mmu, &walker->pte_access, pte);
else
/*
* On a write fault, fold the dirty bit into accessed_dirty.
goto retry_walk;
}
- walker->pt_access = pt_access;
- walker->pte_access = pte_access;
pgprintk("%s: pte %llx pte_access %x pt_access %x\n",
- __func__, (u64)pte, pte_access, pt_access);
+ __func__, (u64)pte, walker->pte_access, walker->pt_access);
return 1;
error:
*/
if (!(errcode & PFERR_RSVD_MASK)) {
vcpu->arch.exit_qualification &= 0x187;
- vcpu->arch.exit_qualification |= ((pt_access & pte) & 0x7) << 3;
+ vcpu->arch.exit_qualification |= (pte_access & 0x7) << 3;
}
#endif
walker->fault.address = addr;
((u64)1 << edx.split.bit_width_fixed) - 1;
}
- pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) |
+ pmu->global_ctrl = ((1ull << pmu->nr_arch_gp_counters) - 1) |
(((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED);
pmu->global_ctrl_mask = ~pmu->global_ctrl;
}
-static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu, int index)
+static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu,
+ unsigned int index)
{
u64 *avic_physical_id_table;
struct kvm_arch *vm_data = &vcpu->kvm->arch;
* AMD's VMCB does not have an explicit unusable field, so emulate it
* for cross vendor migration purposes by "not present"
*/
- var->unusable = !var->present || (var->type == 0);
+ var->unusable = !var->present;
switch (seg) {
case VCPU_SREG_TR:
*/
if (var->unusable)
var->db = 0;
+ /* This is symmetric with svm_set_segment() */
var->dpl = to_svm(vcpu)->vmcb->save.cpl;
break;
}
s->base = var->base;
s->limit = var->limit;
s->selector = var->selector;
- if (var->unusable)
- s->attrib = 0;
- else {
- s->attrib = (var->type & SVM_SELECTOR_TYPE_MASK);
- s->attrib |= (var->s & 1) << SVM_SELECTOR_S_SHIFT;
- s->attrib |= (var->dpl & 3) << SVM_SELECTOR_DPL_SHIFT;
- s->attrib |= (var->present & 1) << SVM_SELECTOR_P_SHIFT;
- s->attrib |= (var->avl & 1) << SVM_SELECTOR_AVL_SHIFT;
- s->attrib |= (var->l & 1) << SVM_SELECTOR_L_SHIFT;
- s->attrib |= (var->db & 1) << SVM_SELECTOR_DB_SHIFT;
- s->attrib |= (var->g & 1) << SVM_SELECTOR_G_SHIFT;
- }
+ s->attrib = (var->type & SVM_SELECTOR_TYPE_MASK);
+ s->attrib |= (var->s & 1) << SVM_SELECTOR_S_SHIFT;
+ s->attrib |= (var->dpl & 3) << SVM_SELECTOR_DPL_SHIFT;
+ s->attrib |= ((var->present & 1) && !var->unusable) << SVM_SELECTOR_P_SHIFT;
+ s->attrib |= (var->avl & 1) << SVM_SELECTOR_AVL_SHIFT;
+ s->attrib |= (var->l & 1) << SVM_SELECTOR_L_SHIFT;
+ s->attrib |= (var->db & 1) << SVM_SELECTOR_DB_SHIFT;
+ s->attrib |= (var->g & 1) << SVM_SELECTOR_G_SHIFT;
/*
* This is always accurate, except if SYSRET returned to a segment
* would entail passing the CPL to userspace and back.
*/
if (seg == VCPU_SREG_SS)
- svm->vmcb->save.cpl = (s->attrib >> SVM_SELECTOR_DPL_SHIFT) & 3;
+ /* This is symmetric with svm_get_segment() */
+ svm->vmcb->save.cpl = (var->dpl & 3);
mark_dirty(svm->vmcb, VMCB_SEG);
}
if (!(vmcs12->exception_bitmap & (1u << nr)))
return 0;
- nested_vmx_vmexit(vcpu, to_vmx(vcpu)->exit_reason,
+ nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
vmcs_read32(VM_EXIT_INTR_INFO),
vmcs_readl(EXIT_QUALIFICATION));
return 1;
enable_ept_ad_bits = 0;
}
- if (!cpu_has_vmx_ept_ad_bits())
+ if (!cpu_has_vmx_ept_ad_bits() || !enable_ept)
enable_ept_ad_bits = 0;
if (!cpu_has_vmx_unrestricted_guest())
return 0;
}
-/*
- * This function performs the various checks including
- * - if it's 4KB aligned
- * - No bits beyond the physical address width are set
- * - Returns 0 on success or else 1
- * (Intel SDM Section 30.3)
- */
-static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason,
- gpa_t *vmpointer)
+static int nested_vmx_get_vmptr(struct kvm_vcpu *vcpu, gpa_t *vmpointer)
{
gva_t gva;
- gpa_t vmptr;
struct x86_exception e;
- struct page *page;
- struct vcpu_vmx *vmx = to_vmx(vcpu);
- int maxphyaddr = cpuid_maxphyaddr(vcpu);
if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
vmcs_read32(VMX_INSTRUCTION_INFO), false, &gva))
return 1;
- if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr,
- sizeof(vmptr), &e)) {
+ if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, vmpointer,
+ sizeof(*vmpointer), &e)) {
kvm_inject_page_fault(vcpu, &e);
return 1;
}
- switch (exit_reason) {
- case EXIT_REASON_VMON:
- /*
- * SDM 3: 24.11.5
- * The first 4 bytes of VMXON region contain the supported
- * VMCS revision identifier
- *
- * Note - IA32_VMX_BASIC[48] will never be 1
- * for the nested case;
- * which replaces physical address width with 32
- *
- */
- if (!PAGE_ALIGNED(vmptr) || (vmptr >> maxphyaddr)) {
- nested_vmx_failInvalid(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
- }
-
- page = nested_get_page(vcpu, vmptr);
- if (page == NULL) {
- nested_vmx_failInvalid(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
- }
- if (*(u32 *)kmap(page) != VMCS12_REVISION) {
- kunmap(page);
- nested_release_page_clean(page);
- nested_vmx_failInvalid(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
- }
- kunmap(page);
- nested_release_page_clean(page);
- vmx->nested.vmxon_ptr = vmptr;
- break;
- case EXIT_REASON_VMCLEAR:
- if (!PAGE_ALIGNED(vmptr) || (vmptr >> maxphyaddr)) {
- nested_vmx_failValid(vcpu,
- VMXERR_VMCLEAR_INVALID_ADDRESS);
- return kvm_skip_emulated_instruction(vcpu);
- }
-
- if (vmptr == vmx->nested.vmxon_ptr) {
- nested_vmx_failValid(vcpu,
- VMXERR_VMCLEAR_VMXON_POINTER);
- return kvm_skip_emulated_instruction(vcpu);
- }
- break;
- case EXIT_REASON_VMPTRLD:
- if (!PAGE_ALIGNED(vmptr) || (vmptr >> maxphyaddr)) {
- nested_vmx_failValid(vcpu,
- VMXERR_VMPTRLD_INVALID_ADDRESS);
- return kvm_skip_emulated_instruction(vcpu);
- }
-
- if (vmptr == vmx->nested.vmxon_ptr) {
- nested_vmx_failValid(vcpu,
- VMXERR_VMPTRLD_VMXON_POINTER);
- return kvm_skip_emulated_instruction(vcpu);
- }
- break;
- default:
- return 1; /* shouldn't happen */
- }
-
- if (vmpointer)
- *vmpointer = vmptr;
return 0;
}
static int handle_vmon(struct kvm_vcpu *vcpu)
{
int ret;
+ gpa_t vmptr;
+ struct page *page;
struct vcpu_vmx *vmx = to_vmx(vcpu);
const u64 VMXON_NEEDED_FEATURES = FEATURE_CONTROL_LOCKED
| FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
return 1;
}
- if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMON, NULL))
+ if (nested_vmx_get_vmptr(vcpu, &vmptr))
return 1;
-
+
+ /*
+ * SDM 3: 24.11.5
+ * The first 4 bytes of VMXON region contain the supported
+ * VMCS revision identifier
+ *
+ * Note - IA32_VMX_BASIC[48] will never be 1 for the nested case;
+ * which replaces physical address width with 32
+ */
+ if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) {
+ nested_vmx_failInvalid(vcpu);
+ return kvm_skip_emulated_instruction(vcpu);
+ }
+
+ page = nested_get_page(vcpu, vmptr);
+ if (page == NULL) {
+ nested_vmx_failInvalid(vcpu);
+ return kvm_skip_emulated_instruction(vcpu);
+ }
+ if (*(u32 *)kmap(page) != VMCS12_REVISION) {
+ kunmap(page);
+ nested_release_page_clean(page);
+ nested_vmx_failInvalid(vcpu);
+ return kvm_skip_emulated_instruction(vcpu);
+ }
+ kunmap(page);
+ nested_release_page_clean(page);
+
+ vmx->nested.vmxon_ptr = vmptr;
ret = enter_vmx_operation(vcpu);
if (ret)
return ret;
if (!nested_vmx_check_permission(vcpu))
return 1;
- if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMCLEAR, &vmptr))
+ if (nested_vmx_get_vmptr(vcpu, &vmptr))
return 1;
+ if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) {
+ nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_INVALID_ADDRESS);
+ return kvm_skip_emulated_instruction(vcpu);
+ }
+
+ if (vmptr == vmx->nested.vmxon_ptr) {
+ nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_VMXON_POINTER);
+ return kvm_skip_emulated_instruction(vcpu);
+ }
+
if (vmptr == vmx->nested.current_vmptr)
nested_release_vmcs12(vmx);
if (!nested_vmx_check_permission(vcpu))
return 1;
- if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMPTRLD, &vmptr))
+ if (nested_vmx_get_vmptr(vcpu, &vmptr))
return 1;
+ if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) {
+ nested_vmx_failValid(vcpu, VMXERR_VMPTRLD_INVALID_ADDRESS);
+ return kvm_skip_emulated_instruction(vcpu);
+ }
+
+ if (vmptr == vmx->nested.vmxon_ptr) {
+ nested_vmx_failValid(vcpu, VMXERR_VMPTRLD_VMXON_POINTER);
+ return kvm_skip_emulated_instruction(vcpu);
+ }
+
if (vmx->nested.current_vmptr != vmptr) {
struct vmcs12 *new_vmcs12;
struct page *page;
{
unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
int cr = exit_qualification & 15;
- int reg = (exit_qualification >> 8) & 15;
- unsigned long val = kvm_register_readl(vcpu, reg);
+ int reg;
+ unsigned long val;
switch ((exit_qualification >> 4) & 3) {
case 0: /* mov to cr */
+ reg = (exit_qualification >> 8) & 15;
+ val = kvm_register_readl(vcpu, reg);
switch (cr) {
case 0:
if (vmcs12->cr0_guest_host_mask &
* lmsw can change bits 1..3 of cr0, and only set bit 0 of
* cr0. Other attempted changes are ignored, with no exit.
*/
+ val = (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f;
if (vmcs12->cr0_guest_host_mask & 0xe &
(val ^ vmcs12->cr0_read_shadow))
return true;
if (!nested_cpu_has_pml(vmcs12))
return 0;
- if (vmcs12->guest_pml_index > PML_ENTITY_NUM) {
+ if (vmcs12->guest_pml_index >= PML_ENTITY_NUM) {
vmx->nested.pml_full = true;
return 1;
}
{
struct kvm_arch *ka = &kvm->arch;
struct pvclock_vcpu_time_info hv_clock;
+ u64 ret;
spin_lock(&ka->pvclock_gtod_sync_lock);
if (!ka->use_master_clock) {
hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset;
spin_unlock(&ka->pvclock_gtod_sync_lock);
+ /* both __this_cpu_read() and rdtsc() should be on the same cpu */
+ get_cpu();
+
kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL,
&hv_clock.tsc_shift,
&hv_clock.tsc_to_system_mul);
- return __pvclock_read_cycles(&hv_clock, rdtsc());
+ ret = __pvclock_read_cycles(&hv_clock, rdtsc());
+
+ put_cpu();
+
+ return ret;
}
static void kvm_setup_pvclock_page(struct kvm_vcpu *v)
}
}
+#define XSAVE_MXCSR_OFFSET 24
+
static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
struct kvm_xsave *guest_xsave)
{
u64 xstate_bv =
*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)];
+ u32 mxcsr = *(u32 *)&guest_xsave->region[XSAVE_MXCSR_OFFSET / sizeof(u32)];
if (boot_cpu_has(X86_FEATURE_XSAVE)) {
/*
* CPUID leaf 0xD, index 0, EDX:EAX. This is for compatibility
* with old userspace.
*/
- if (xstate_bv & ~kvm_supported_xcr0())
+ if (xstate_bv & ~kvm_supported_xcr0() ||
+ mxcsr & ~mxcsr_feature_mask)
return -EINVAL;
load_xsave(vcpu, (u8 *)guest_xsave->region);
} else {
- if (xstate_bv & ~XFEATURE_MASK_FPSSE)
+ if (xstate_bv & ~XFEATURE_MASK_FPSSE ||
+ mxcsr & ~mxcsr_feature_mask)
return -EINVAL;
memcpy(&vcpu->arch.guest_fpu.state.fxsave,
guest_xsave->region, sizeof(struct fxregs_state));
static int kernel_pio(struct kvm_vcpu *vcpu, void *pd)
{
- /* TODO: String I/O for in kernel device */
- int r;
+ int r = 0, i;
- if (vcpu->arch.pio.in)
- r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port,
- vcpu->arch.pio.size, pd);
- else
- r = kvm_io_bus_write(vcpu, KVM_PIO_BUS,
- vcpu->arch.pio.port, vcpu->arch.pio.size,
- pd);
+ for (i = 0; i < vcpu->arch.pio.count; i++) {
+ if (vcpu->arch.pio.in)
+ r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port,
+ vcpu->arch.pio.size, pd);
+ else
+ r = kvm_io_bus_write(vcpu, KVM_PIO_BUS,
+ vcpu->arch.pio.port, vcpu->arch.pio.size,
+ pd);
+ if (r)
+ break;
+ pd += vcpu->arch.pio.size;
+ }
return r;
}
if (vcpu->arch.pio.count)
goto data_avail;
+ memset(vcpu->arch.pio_data, 0, size * count);
+
ret = emulator_pio_in_out(vcpu, size, port, val, count, true);
if (ret) {
data_avail:
if (var.unusable) {
memset(desc, 0, sizeof(*desc));
+ if (base3)
+ *base3 = 0;
return false;
}
if (vcpu->arch.pv.pv_unhalted)
return true;
- if (atomic_read(&vcpu->arch.nmi_queued))
+ if (kvm_test_request(KVM_REQ_NMI, vcpu) ||
+ (vcpu->arch.nmi_pending &&
+ kvm_x86_ops->nmi_allowed(vcpu)))
return true;
- if (kvm_test_request(KVM_REQ_SMI, vcpu))
+ if (kvm_test_request(KVM_REQ_SMI, vcpu) ||
+ (vcpu->arch.smi_pending && !is_smm(vcpu)))
return true;
if (kvm_arch_interrupt_allowed(vcpu) &&
if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED))
return true;
else
- return !kvm_event_needs_reinjection(vcpu) &&
- kvm_x86_ops->interrupt_allowed(vcpu);
+ return kvm_can_do_async_pf(vcpu);
}
void kvm_arch_start_assignment(struct kvm *kvm)
unsigned int i, level;
unsigned long addr;
- BUG_ON(irqs_disabled());
+ BUG_ON(irqs_disabled() && !early_boot_irqs_disabled);
WARN_ON(PAGE_ALIGN(start) != start);
on_each_cpu(__cpa_flush_range, NULL, 1);
/*
* We don't do virtual mode, since we don't do runtime services, on
- * non-native EFI
+ * non-native EFI. With efi=old_map, we don't do runtime services in
+ * kexec kernel because in the initial boot something else might
+ * have been mapped at these virtual addresses.
*/
- if (!efi_is_native()) {
+ if (!efi_is_native() || efi_enabled(EFI_OLD_MEMMAP)) {
efi_memmap_unmap();
clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
return;
pgd_t * __init efi_call_phys_prolog(void)
{
- unsigned long vaddress;
- pgd_t *save_pgd;
+ unsigned long vaddr, addr_pgd, addr_p4d, addr_pud;
+ pgd_t *save_pgd, *pgd_k, *pgd_efi;
+ p4d_t *p4d, *p4d_k, *p4d_efi;
+ pud_t *pud;
int pgd;
- int n_pgds;
+ int n_pgds, i, j;
if (!efi_enabled(EFI_OLD_MEMMAP)) {
save_pgd = (pgd_t *)read_cr3();
n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT), PGDIR_SIZE);
save_pgd = kmalloc_array(n_pgds, sizeof(*save_pgd), GFP_KERNEL);
+ /*
+ * Build 1:1 identity mapping for efi=old_map usage. Note that
+ * PAGE_OFFSET is PGDIR_SIZE aligned when KASLR is disabled, while
+ * it is PUD_SIZE ALIGNED with KASLR enabled. So for a given physical
+ * address X, the pud_index(X) != pud_index(__va(X)), we can only copy
+ * PUD entry of __va(X) to fill in pud entry of X to build 1:1 mapping.
+ * This means here we can only reuse the PMD tables of the direct mapping.
+ */
for (pgd = 0; pgd < n_pgds; pgd++) {
- save_pgd[pgd] = *pgd_offset_k(pgd * PGDIR_SIZE);
- vaddress = (unsigned long)__va(pgd * PGDIR_SIZE);
- set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), *pgd_offset_k(vaddress));
+ addr_pgd = (unsigned long)(pgd * PGDIR_SIZE);
+ vaddr = (unsigned long)__va(pgd * PGDIR_SIZE);
+ pgd_efi = pgd_offset_k(addr_pgd);
+ save_pgd[pgd] = *pgd_efi;
+
+ p4d = p4d_alloc(&init_mm, pgd_efi, addr_pgd);
+ if (!p4d) {
+ pr_err("Failed to allocate p4d table!\n");
+ goto out;
+ }
+
+ for (i = 0; i < PTRS_PER_P4D; i++) {
+ addr_p4d = addr_pgd + i * P4D_SIZE;
+ p4d_efi = p4d + p4d_index(addr_p4d);
+
+ pud = pud_alloc(&init_mm, p4d_efi, addr_p4d);
+ if (!pud) {
+ pr_err("Failed to allocate pud table!\n");
+ goto out;
+ }
+
+ for (j = 0; j < PTRS_PER_PUD; j++) {
+ addr_pud = addr_p4d + j * PUD_SIZE;
+
+ if (addr_pud > (max_pfn << PAGE_SHIFT))
+ break;
+
+ vaddr = (unsigned long)__va(addr_pud);
+
+ pgd_k = pgd_offset_k(vaddr);
+ p4d_k = p4d_offset(pgd_k, vaddr);
+ pud[j] = *pud_offset(p4d_k, vaddr);
+ }
+ }
}
out:
__flush_tlb_all();
/*
* After the lock is released, the original page table is restored.
*/
- int pgd_idx;
+ int pgd_idx, i;
int nr_pgds;
+ pgd_t *pgd;
+ p4d_t *p4d;
+ pud_t *pud;
if (!efi_enabled(EFI_OLD_MEMMAP)) {
write_cr3((unsigned long)save_pgd);
nr_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE);
- for (pgd_idx = 0; pgd_idx < nr_pgds; pgd_idx++)
+ for (pgd_idx = 0; pgd_idx < nr_pgds; pgd_idx++) {
+ pgd = pgd_offset_k(pgd_idx * PGDIR_SIZE);
set_pgd(pgd_offset_k(pgd_idx * PGDIR_SIZE), save_pgd[pgd_idx]);
+ if (!(pgd_val(*pgd) & _PAGE_PRESENT))
+ continue;
+
+ for (i = 0; i < PTRS_PER_P4D; i++) {
+ p4d = p4d_offset(pgd,
+ pgd_idx * PGDIR_SIZE + i * P4D_SIZE);
+
+ if (!(p4d_val(*p4d) & _PAGE_PRESENT))
+ continue;
+
+ pud = (pud_t *)p4d_page_vaddr(*p4d);
+ pud_free(&init_mm, pud);
+ }
+
+ p4d = (p4d_t *)pgd_page_vaddr(*pgd);
+ p4d_free(&init_mm, p4d);
+ }
+
kfree(save_pgd);
__flush_tlb_all();
free_bootmem_late(start, size);
}
+ if (!num_entries)
+ return;
+
new_size = efi.memmap.desc_size * num_entries;
new_phys = efi_memmap_alloc(num_entries);
if (!new_phys) {
struct xen_extraversion extra;
HYPERVISOR_xen_version(XENVER_extraversion, &extra);
- pr_info("Booting paravirtualized kernel %son %s\n",
- xen_feature(XENFEAT_auto_translated_physmap) ?
- "with PVH extensions " : "", pv_info.name);
+ pr_info("Booting paravirtualized kernel on %s\n", pv_info.name);
printk(KERN_INFO "Xen version: %d.%d%s%s\n",
version >> 16, version & 0xffff, extra.extraversion,
xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : "");
void xen_setup_shared_info(void)
{
- if (!xen_feature(XENFEAT_auto_translated_physmap)) {
- set_fixmap(FIX_PARAVIRT_BOOTMAP,
- xen_start_info->shared_info);
+ set_fixmap(FIX_PARAVIRT_BOOTMAP, xen_start_info->shared_info);
- HYPERVISOR_shared_info =
- (struct shared_info *)fix_to_virt(FIX_PARAVIRT_BOOTMAP);
- } else
- HYPERVISOR_shared_info =
- (struct shared_info *)__va(xen_start_info->shared_info);
+ HYPERVISOR_shared_info =
+ (struct shared_info *)fix_to_virt(FIX_PARAVIRT_BOOTMAP);
#ifndef CONFIG_SMP
/* In UP this is as good a place as any to set up shared info */
}
EXPORT_SYMBOL_GPL(arbitrary_virt_to_machine);
-void xen_flush_tlb_all(void)
+static void xen_flush_tlb_all(void)
{
struct mmuext_op *op;
struct multicall_space mcs;
pteval_t flags = val & PTE_FLAGS_MASK;
unsigned long mfn;
- if (!xen_feature(XENFEAT_auto_translated_physmap))
- mfn = __pfn_to_mfn(pfn);
- else
- mfn = pfn;
+ mfn = __pfn_to_mfn(pfn);
+
/*
* If there's no mfn for the pfn, then just create an
* empty non-present pte. Unfortunately this loses
limit--;
BUG_ON(limit >= FIXADDR_TOP);
- if (xen_feature(XENFEAT_auto_translated_physmap))
- return 0;
-
/*
* 64-bit has a great big hole in the middle of the address
* space, which contains the Xen mappings. On 32-bit these
static void __init xen_pagetable_p2m_setup(void)
{
- if (xen_feature(XENFEAT_auto_translated_physmap))
- return;
-
xen_vmalloc_p2m_tree();
#ifdef CONFIG_X86_64
xen_build_mfn_list_list();
/* Remap memory freed due to conflicts with E820 map */
- if (!xen_feature(XENFEAT_auto_translated_physmap))
- xen_remap_memory();
+ xen_remap_memory();
xen_setup_shared_info();
}
/* Zap identity mapping */
init_level4_pgt[0] = __pgd(0);
- if (!xen_feature(XENFEAT_auto_translated_physmap)) {
- /* Pre-constructed entries are in pfn, so convert to mfn */
- /* L4[272] -> level3_ident_pgt
- * L4[511] -> level3_kernel_pgt */
- convert_pfn_mfn(init_level4_pgt);
+ /* Pre-constructed entries are in pfn, so convert to mfn */
+ /* L4[272] -> level3_ident_pgt */
+ /* L4[511] -> level3_kernel_pgt */
+ convert_pfn_mfn(init_level4_pgt);
- /* L3_i[0] -> level2_ident_pgt */
- convert_pfn_mfn(level3_ident_pgt);
- /* L3_k[510] -> level2_kernel_pgt
- * L3_k[511] -> level2_fixmap_pgt */
- convert_pfn_mfn(level3_kernel_pgt);
+ /* L3_i[0] -> level2_ident_pgt */
+ convert_pfn_mfn(level3_ident_pgt);
+ /* L3_k[510] -> level2_kernel_pgt */
+ /* L3_k[511] -> level2_fixmap_pgt */
+ convert_pfn_mfn(level3_kernel_pgt);
+
+ /* L3_k[511][506] -> level1_fixmap_pgt */
+ convert_pfn_mfn(level2_fixmap_pgt);
- /* L3_k[511][506] -> level1_fixmap_pgt */
- convert_pfn_mfn(level2_fixmap_pgt);
- }
/* We get [511][511] and have Xen's version of level2_kernel_pgt */
l3 = m2v(pgd[pgd_index(__START_KERNEL_map)].pgd);
l2 = m2v(l3[pud_index(__START_KERNEL_map)].pud);
if (i && i < pgd_index(__START_KERNEL_map))
init_level4_pgt[i] = ((pgd_t *)xen_start_info->pt_base)[i];
- if (!xen_feature(XENFEAT_auto_translated_physmap)) {
- /* Make pagetable pieces RO */
- set_page_prot(init_level4_pgt, PAGE_KERNEL_RO);
- set_page_prot(level3_ident_pgt, PAGE_KERNEL_RO);
- set_page_prot(level3_kernel_pgt, PAGE_KERNEL_RO);
- set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO);
- set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO);
- set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
- set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO);
- set_page_prot(level1_fixmap_pgt, PAGE_KERNEL_RO);
-
- /* Pin down new L4 */
- pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE,
- PFN_DOWN(__pa_symbol(init_level4_pgt)));
-
- /* Unpin Xen-provided one */
- pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
+ /* Make pagetable pieces RO */
+ set_page_prot(init_level4_pgt, PAGE_KERNEL_RO);
+ set_page_prot(level3_ident_pgt, PAGE_KERNEL_RO);
+ set_page_prot(level3_kernel_pgt, PAGE_KERNEL_RO);
+ set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO);
+ set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO);
+ set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
+ set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO);
+ set_page_prot(level1_fixmap_pgt, PAGE_KERNEL_RO);
+
+ /* Pin down new L4 */
+ pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE,
+ PFN_DOWN(__pa_symbol(init_level4_pgt)));
+
+ /* Unpin Xen-provided one */
+ pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
- /*
- * At this stage there can be no user pgd, and no page
- * structure to attach it to, so make sure we just set kernel
- * pgd.
- */
- xen_mc_batch();
- __xen_write_cr3(true, __pa(init_level4_pgt));
- xen_mc_issue(PARAVIRT_LAZY_CPU);
- } else
- native_write_cr3(__pa(init_level4_pgt));
+ /*
+ * At this stage there can be no user pgd, and no page structure to
+ * attach it to, so make sure we just set kernel pgd.
+ */
+ xen_mc_batch();
+ __xen_write_cr3(true, __pa(init_level4_pgt));
+ xen_mc_issue(PARAVIRT_LAZY_CPU);
/* We can't that easily rip out L3 and L2, as the Xen pagetables are
* set out this way: [L4], [L1], [L2], [L3], [L1], [L1] ... for
static void __init xen_post_allocator_init(void)
{
- if (xen_feature(XENFEAT_auto_translated_physmap))
- return;
-
pv_mmu_ops.set_pte = xen_set_pte;
pv_mmu_ops.set_pmd = xen_set_pmd;
pv_mmu_ops.set_pud = xen_set_pud;
{
x86_init.paging.pagetable_init = xen_pagetable_init;
- if (xen_feature(XENFEAT_auto_translated_physmap))
- return;
-
pv_mmu_ops = xen_mmu_ops;
memset(dummy_mapping, 0xff, PAGE_SIZE);
* this function are redundant and can be ignored.
*/
- if (xen_feature(XENFEAT_auto_translated_physmap))
- return 0;
-
if (unlikely(order > MAX_CONTIG_ORDER))
return -ENOMEM;
int success;
unsigned long vstart;
- if (xen_feature(XENFEAT_auto_translated_physmap))
- return;
-
if (unlikely(order > MAX_CONTIG_ORDER))
return;
BFQG_FLAG_FNS(empty)
#undef BFQG_FLAG_FNS
-/* This should be called with the queue_lock held. */
+/* This should be called with the scheduler lock held. */
static void bfqg_stats_update_group_wait_time(struct bfqg_stats *stats)
{
unsigned long long now;
bfqg_stats_clear_waiting(stats);
}
-/* This should be called with the queue_lock held. */
+/* This should be called with the scheduler lock held. */
static void bfqg_stats_set_start_group_wait_time(struct bfq_group *bfqg,
struct bfq_group *curr_bfqg)
{
bfqg_stats_mark_waiting(stats);
}
-/* This should be called with the queue_lock held. */
+/* This should be called with the scheduler lock held. */
static void bfqg_stats_end_empty_time(struct bfqg_stats *stats)
{
unsigned long long now;
static void bfqg_get(struct bfq_group *bfqg)
{
- return blkg_get(bfqg_to_blkg(bfqg));
+ bfqg->ref++;
}
void bfqg_put(struct bfq_group *bfqg)
{
- return blkg_put(bfqg_to_blkg(bfqg));
+ bfqg->ref--;
+
+ if (bfqg->ref == 0)
+ kfree(bfqg);
+}
+
+static void bfqg_and_blkg_get(struct bfq_group *bfqg)
+{
+ /* see comments in bfq_bic_update_cgroup for why refcounting bfqg */
+ bfqg_get(bfqg);
+
+ blkg_get(bfqg_to_blkg(bfqg));
+}
+
+void bfqg_and_blkg_put(struct bfq_group *bfqg)
+{
+ bfqg_put(bfqg);
+
+ blkg_put(bfqg_to_blkg(bfqg));
}
void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
if (bfqq) {
bfqq->ioprio = bfqq->new_ioprio;
bfqq->ioprio_class = bfqq->new_ioprio_class;
- bfqg_get(bfqg);
+ /*
+ * Make sure that bfqg and its associated blkg do not
+ * disappear before entity.
+ */
+ bfqg_and_blkg_get(bfqg);
}
entity->parent = bfqg->my_entity; /* NULL for root group */
entity->sched_data = &bfqg->sched_data;
return NULL;
}
+ /* see comments in bfq_bic_update_cgroup for why refcounting */
+ bfqg_get(bfqg);
return &bfqg->pd;
}
struct bfq_group *bfqg = pd_to_bfqg(pd);
bfqg_stats_exit(&bfqg->stats);
- return kfree(bfqg);
+ bfqg_put(bfqg);
}
void bfq_pd_reset_stats(struct blkg_policy_data *pd)
* Move @bfqq to @bfqg, deactivating it from its old group and reactivating
* it on the new one. Avoid putting the entity on the old group idle tree.
*
- * Must be called under the queue lock; the cgroup owning @bfqg must
- * not disappear (by now this just means that we are called under
- * rcu_read_lock()).
+ * Must be called under the scheduler lock, to make sure that the blkg
+ * owning @bfqg does not disappear (see comments in
+ * bfq_bic_update_cgroup on guaranteeing the consistency of blkg
+ * objects).
*/
void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
struct bfq_group *bfqg)
bfq_deactivate_bfqq(bfqd, bfqq, false, false);
else if (entity->on_st)
bfq_put_idle_entity(bfq_entity_service_tree(entity), entity);
- bfqg_put(bfqq_group(bfqq));
+ bfqg_and_blkg_put(bfqq_group(bfqq));
- /*
- * Here we use a reference to bfqg. We don't need a refcounter
- * as the cgroup reference will not be dropped, so that its
- * destroy() callback will not be invoked.
- */
entity->parent = bfqg->my_entity;
entity->sched_data = &bfqg->sched_data;
- bfqg_get(bfqg);
+ /* pin down bfqg and its associated blkg */
+ bfqg_and_blkg_get(bfqg);
if (bfq_bfqq_busy(bfqq)) {
bfq_pos_tree_add_move(bfqd, bfqq);
* @bic: the bic to move.
* @blkcg: the blk-cgroup to move to.
*
- * Move bic to blkcg, assuming that bfqd->queue is locked; the caller
- * has to make sure that the reference to cgroup is valid across the call.
+ * Move bic to blkcg, assuming that bfqd->lock is held; which makes
+ * sure that the reference to cgroup is valid across the call (see
+ * comments in bfq_bic_update_cgroup on this issue)
*
* NOTE: an alternative approach might have been to store the current
* cgroup in bfqq and getting a reference to it, reducing the lookup
goto out;
bfqg = __bfq_bic_change_cgroup(bfqd, bic, bio_blkcg(bio));
+ /*
+ * Update blkg_path for bfq_log_* functions. We cache this
+ * path, and update it here, for the following
+ * reasons. Operations on blkg objects in blk-cgroup are
+ * protected with the request_queue lock, and not with the
+ * lock that protects the instances of this scheduler
+ * (bfqd->lock). This exposes BFQ to the following sort of
+ * race.
+ *
+ * The blkg_lookup performed in bfq_get_queue, protected
+ * through rcu, may happen to return the address of a copy of
+ * the original blkg. If this is the case, then the
+ * bfqg_and_blkg_get performed in bfq_get_queue, to pin down
+ * the blkg, is useless: it does not prevent blk-cgroup code
+ * from destroying both the original blkg and all objects
+ * directly or indirectly referred by the copy of the
+ * blkg.
+ *
+ * On the bright side, destroy operations on a blkg invoke, as
+ * a first step, hooks of the scheduler associated with the
+ * blkg. And these hooks are executed with bfqd->lock held for
+ * BFQ. As a consequence, for any blkg associated with the
+ * request queue this instance of the scheduler is attached
+ * to, we are guaranteed that such a blkg is not destroyed, and
+ * that all the pointers it contains are consistent, while we
+ * are holding bfqd->lock. A blkg_lookup performed with
+ * bfqd->lock held then returns a fully consistent blkg, which
+ * remains consistent until this lock is held.
+ *
+ * Thanks to the last fact, and to the fact that: (1) bfqg has
+ * been obtained through a blkg_lookup in the above
+ * assignment, and (2) bfqd->lock is being held, here we can
+ * safely use the policy data for the involved blkg (i.e., the
+ * field bfqg->pd) to get to the blkg associated with bfqg,
+ * and then we can safely use any field of blkg. After we
+ * release bfqd->lock, even just getting blkg through this
+ * bfqg may cause dangling references to be traversed, as
+ * bfqg->pd may not exist any more.
+ *
+ * In view of the above facts, here we cache, in the bfqg, any
+ * blkg data we may need for this bic, and for its associated
+ * bfq_queue. As of now, we need to cache only the path of the
+ * blkg, which is used in the bfq_log_* functions.
+ *
+ * Finally, note that bfqg itself needs to be protected from
+ * destruction on the blkg_free of the original blkg (which
+ * invokes bfq_pd_free). We use an additional private
+ * refcounter for bfqg, to let it disappear only after no
+ * bfq_queue refers to it any longer.
+ */
+ blkg_path(bfqg_to_blkg(bfqg), bfqg->blkg_path, sizeof(bfqg->blkg_path));
bic->blkcg_serial_nr = serial_nr;
out:
rcu_read_unlock();
* @bfqd: the device data structure with the root group.
* @bfqg: the group to move from.
* @st: the service tree with the entities.
- *
- * Needs queue_lock to be taken and reference to be valid over the call.
*/
static void bfq_reparent_active_entities(struct bfq_data *bfqd,
struct bfq_group *bfqg,
/*
* The idle tree may still contain bfq_queues belonging
* to exited task because they never migrated to a different
- * cgroup from the one being destroyed now. No one else
- * can access them so it's safe to act without any lock.
+ * cgroup from the one being destroyed now.
*/
bfq_flush_idle_tree(st);
kmem_cache_free(bfq_pool, bfqq);
#ifdef CONFIG_BFQ_GROUP_IOSCHED
- bfqg_put(bfqg);
+ bfqg_and_blkg_put(bfqg);
#endif
}
/* must be the first member */
struct blkg_policy_data pd;
+ /* cached path for this blkg (see comments in bfq_bic_update_cgroup) */
+ char blkg_path[128];
+
+ /* reference counter (see comments in bfq_bic_update_cgroup) */
+ int ref;
+
struct bfq_entity entity;
struct bfq_sched_data sched_data;
struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);
struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node);
-void bfqg_put(struct bfq_group *bfqg);
+void bfqg_and_blkg_put(struct bfq_group *bfqg);
#ifdef CONFIG_BFQ_GROUP_IOSCHED
extern struct cftype bfq_blkcg_legacy_files[];
struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
#define bfq_log_bfqq(bfqd, bfqq, fmt, args...) do { \
- char __pbuf[128]; \
- \
- blkg_path(bfqg_to_blkg(bfqq_group(bfqq)), __pbuf, sizeof(__pbuf)); \
- blk_add_trace_msg((bfqd)->queue, "bfq%d%c %s " fmt, (bfqq)->pid, \
+ blk_add_trace_msg((bfqd)->queue, "bfq%d%c %s " fmt, (bfqq)->pid,\
bfq_bfqq_sync((bfqq)) ? 'S' : 'A', \
- __pbuf, ##args); \
+ bfqq_group(bfqq)->blkg_path, ##args); \
} while (0)
-#define bfq_log_bfqg(bfqd, bfqg, fmt, args...) do { \
- char __pbuf[128]; \
- \
- blkg_path(bfqg_to_blkg(bfqg), __pbuf, sizeof(__pbuf)); \
- blk_add_trace_msg((bfqd)->queue, "%s " fmt, __pbuf, ##args); \
-} while (0)
+#define bfq_log_bfqg(bfqd, bfqg, fmt, args...) \
+ blk_add_trace_msg((bfqd)->queue, "%s " fmt, (bfqg)->blkg_path, ##args)
#else /* CONFIG_BFQ_GROUP_IOSCHED */
if (bio_op(bio) != REQ_OP_READ && bio_op(bio) != REQ_OP_WRITE)
return false;
+ if (!bio_sectors(bio))
+ return false;
+
/* Already protected? */
if (bio_integrity(bio))
return false;
blkcg_policy[i]->pd_free_fn(blkg->pd[i]);
if (blkg->blkcg != &blkcg_root)
- blk_exit_rl(&blkg->rl);
+ blk_exit_rl(blkg->q, &blkg->rl);
blkg_rwstat_exit(&blkg->stat_ios);
blkg_rwstat_exit(&blkg->stat_bytes);
if (!rl->rq_pool)
return -ENOMEM;
+ if (rl != &q->root_rl)
+ WARN_ON_ONCE(!blk_get_queue(q));
+
return 0;
}
-void blk_exit_rl(struct request_list *rl)
+void blk_exit_rl(struct request_queue *q, struct request_list *rl)
{
- if (rl->rq_pool)
+ if (rl->rq_pool) {
mempool_destroy(rl->rq_pool);
+ if (rl != &q->root_rl)
+ blk_put_queue(q);
+ }
}
struct request_queue *blk_alloc_queue(gfp_t gfp_mask)
}
EXPORT_SYMBOL(blk_mq_delay_kick_requeue_list);
-void blk_mq_abort_requeue_list(struct request_queue *q)
-{
- unsigned long flags;
- LIST_HEAD(rq_list);
-
- spin_lock_irqsave(&q->requeue_lock, flags);
- list_splice_init(&q->requeue_list, &rq_list);
- spin_unlock_irqrestore(&q->requeue_lock, flags);
-
- while (!list_empty(&rq_list)) {
- struct request *rq;
-
- rq = list_first_entry(&rq_list, struct request, queuelist);
- list_del_init(&rq->queuelist);
- blk_mq_end_request(rq, -EIO);
- }
-}
-EXPORT_SYMBOL(blk_mq_abort_requeue_list);
-
struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag)
{
if (tag < tags->nr_tags) {
return blk_tag_to_qc_t(rq->internal_tag, hctx->queue_num, true);
}
-static void __blk_mq_try_issue_directly(struct request *rq, blk_qc_t *cookie,
- bool may_sleep)
+static void __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
+ struct request *rq,
+ blk_qc_t *cookie, bool may_sleep)
{
struct request_queue *q = rq->q;
struct blk_mq_queue_data bd = {
.rq = rq,
.last = true,
};
- struct blk_mq_hw_ctx *hctx;
blk_qc_t new_cookie;
int ret;
+ bool run_queue = true;
+
+ if (blk_mq_hctx_stopped(hctx)) {
+ run_queue = false;
+ goto insert;
+ }
if (q->elevator)
goto insert;
- if (!blk_mq_get_driver_tag(rq, &hctx, false))
+ if (!blk_mq_get_driver_tag(rq, NULL, false))
goto insert;
new_cookie = request_to_qc_t(hctx, rq);
__blk_mq_requeue_request(rq);
insert:
- blk_mq_sched_insert_request(rq, false, true, false, may_sleep);
+ blk_mq_sched_insert_request(rq, false, run_queue, false, may_sleep);
}
static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
{
if (!(hctx->flags & BLK_MQ_F_BLOCKING)) {
rcu_read_lock();
- __blk_mq_try_issue_directly(rq, cookie, false);
+ __blk_mq_try_issue_directly(hctx, rq, cookie, false);
rcu_read_unlock();
} else {
unsigned int srcu_idx;
might_sleep();
srcu_idx = srcu_read_lock(&hctx->queue_rq_srcu);
- __blk_mq_try_issue_directly(rq, cookie, true);
+ __blk_mq_try_issue_directly(hctx, rq, cookie, true);
srcu_read_unlock(&hctx->queue_rq_srcu, srcu_idx);
}
}
blk_mq_put_ctx(data.ctx);
- if (same_queue_rq)
+ if (same_queue_rq) {
+ data.hctx = blk_mq_map_queue(q,
+ same_queue_rq->mq_ctx->cpu);
blk_mq_try_issue_directly(data.hctx, same_queue_rq,
&cookie);
+ }
} else if (q->nr_hw_queues > 1 && is_sync) {
blk_mq_put_ctx(data.ctx);
blk_mq_bio_to_request(rq, bio);
return ret;
}
-void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues)
+static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
+ int nr_hw_queues)
{
struct request_queue *q;
list_for_each_entry(q, &set->tag_list, tag_set_list)
blk_mq_unfreeze_queue(q);
}
+
+void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues)
+{
+ mutex_lock(&set->tag_list_lock);
+ __blk_mq_update_nr_hw_queues(set, nr_hw_queues);
+ mutex_unlock(&set->tag_list_lock);
+}
EXPORT_SYMBOL_GPL(blk_mq_update_nr_hw_queues);
/* Enable polling stats and return whether they were already enabled. */
blk_free_queue_stats(q->stats);
- blk_exit_rl(&q->root_rl);
+ blk_exit_rl(q, &q->root_rl);
if (q->queue_tags)
__blk_queue_free_tags(q);
goto unlock;
}
- if (q->mq_ops)
+ if (q->mq_ops) {
__blk_mq_register_dev(dev, q);
-
- blk_mq_debugfs_register(q);
+ blk_mq_debugfs_register(q);
+ }
kobject_uevent(&q->kobj, KOBJ_ADD);
#define DFL_THROTL_SLICE_HD (HZ / 10)
#define DFL_THROTL_SLICE_SSD (HZ / 50)
#define MAX_THROTL_SLICE (HZ)
-#define DFL_IDLE_THRESHOLD_SSD (1000L) /* 1 ms */
-#define DFL_IDLE_THRESHOLD_HD (100L * 1000) /* 100 ms */
#define MAX_IDLE_TIME (5L * 1000 * 1000) /* 5 s */
-/* default latency target is 0, eg, guarantee IO latency by default */
-#define DFL_LATENCY_TARGET (0)
+#define MIN_THROTL_BPS (320 * 1024)
+#define MIN_THROTL_IOPS (10)
+#define DFL_LATENCY_TARGET (-1L)
+#define DFL_IDLE_THRESHOLD (0)
+#define DFL_HD_BASELINE_LATENCY (4000L) /* 4ms */
+#define LATENCY_FILTERED_SSD (0)
+/*
+ * For HD, very small latency comes from sequential IO. Such IO is helpless to
+ * help determine if its IO is impacted by others, hence we ignore the IO
+ */
+#define LATENCY_FILTERED_HD (1000L) /* 1ms */
#define SKIP_LATENCY (((u64)1) << BLK_STAT_RES_SHIFT)
unsigned long last_check_time;
unsigned long latency_target; /* us */
+ unsigned long latency_target_conf; /* us */
/* When did we start a new slice */
unsigned long slice_start[2];
unsigned long slice_end[2];
unsigned long checked_last_finish_time; /* ns / 1024 */
unsigned long avg_idletime; /* ns / 1024 */
unsigned long idletime_threshold; /* us */
+ unsigned long idletime_threshold_conf; /* us */
unsigned int bio_cnt; /* total bios */
unsigned int bad_bio_cnt; /* bios exceeding latency threshold */
unsigned int limit_index;
bool limit_valid[LIMIT_CNT];
- unsigned long dft_idletime_threshold; /* us */
-
unsigned long low_upgrade_time;
unsigned long low_downgrade_time;
struct avg_latency_bucket avg_buckets[LATENCY_BUCKET_SIZE];
struct latency_bucket __percpu *latency_buckets;
unsigned long last_calculate_time;
+ unsigned long filtered_latency;
bool track_bio_latency;
};
td = tg->td;
ret = tg->bps[rw][td->limit_index];
- if (ret == 0 && td->limit_index == LIMIT_LOW)
- return tg->bps[rw][LIMIT_MAX];
+ if (ret == 0 && td->limit_index == LIMIT_LOW) {
+ /* intermediate node or iops isn't 0 */
+ if (!list_empty(&blkg->blkcg->css.children) ||
+ tg->iops[rw][td->limit_index])
+ return U64_MAX;
+ else
+ return MIN_THROTL_BPS;
+ }
if (td->limit_index == LIMIT_MAX && tg->bps[rw][LIMIT_LOW] &&
tg->bps[rw][LIMIT_LOW] != tg->bps[rw][LIMIT_MAX]) {
if (cgroup_subsys_on_dfl(io_cgrp_subsys) && !blkg->parent)
return UINT_MAX;
+
td = tg->td;
ret = tg->iops[rw][td->limit_index];
- if (ret == 0 && tg->td->limit_index == LIMIT_LOW)
- return tg->iops[rw][LIMIT_MAX];
+ if (ret == 0 && tg->td->limit_index == LIMIT_LOW) {
+ /* intermediate node or bps isn't 0 */
+ if (!list_empty(&blkg->blkcg->css.children) ||
+ tg->bps[rw][td->limit_index])
+ return UINT_MAX;
+ else
+ return MIN_THROTL_IOPS;
+ }
if (td->limit_index == LIMIT_MAX && tg->iops[rw][LIMIT_LOW] &&
tg->iops[rw][LIMIT_LOW] != tg->iops[rw][LIMIT_MAX]) {
/* LIMIT_LOW will have default value 0 */
tg->latency_target = DFL_LATENCY_TARGET;
+ tg->latency_target_conf = DFL_LATENCY_TARGET;
+ tg->idletime_threshold = DFL_IDLE_THRESHOLD;
+ tg->idletime_threshold_conf = DFL_IDLE_THRESHOLD;
return &tg->pd;
}
if (cgroup_subsys_on_dfl(io_cgrp_subsys) && blkg->parent)
sq->parent_sq = &blkg_to_tg(blkg->parent)->service_queue;
tg->td = td;
-
- tg->idletime_threshold = td->dft_idletime_threshold;
}
/*
static void throtl_schedule_pending_timer(struct throtl_service_queue *sq,
unsigned long expires)
{
- unsigned long max_expire = jiffies + 8 * sq_to_tg(sq)->td->throtl_slice;
+ unsigned long max_expire = jiffies + 8 * sq_to_td(sq)->throtl_slice;
/*
* Since we are adjusting the throttle limit dynamically, the sleep
return 0;
}
-static void tg_conf_updated(struct throtl_grp *tg)
+static void tg_conf_updated(struct throtl_grp *tg, bool global)
{
struct throtl_service_queue *sq = &tg->service_queue;
struct cgroup_subsys_state *pos_css;
* restrictions in the whole hierarchy and allows them to bypass
* blk-throttle.
*/
- blkg_for_each_descendant_pre(blkg, pos_css, tg_to_blkg(tg))
- tg_update_has_rules(blkg_to_tg(blkg));
+ blkg_for_each_descendant_pre(blkg, pos_css,
+ global ? tg->td->queue->root_blkg : tg_to_blkg(tg)) {
+ struct throtl_grp *this_tg = blkg_to_tg(blkg);
+ struct throtl_grp *parent_tg;
+
+ tg_update_has_rules(this_tg);
+ /* ignore root/second level */
+ if (!cgroup_subsys_on_dfl(io_cgrp_subsys) || !blkg->parent ||
+ !blkg->parent->parent)
+ continue;
+ parent_tg = blkg_to_tg(blkg->parent);
+ /*
+ * make sure all children has lower idle time threshold and
+ * higher latency target
+ */
+ this_tg->idletime_threshold = min(this_tg->idletime_threshold,
+ parent_tg->idletime_threshold);
+ this_tg->latency_target = max(this_tg->latency_target,
+ parent_tg->latency_target);
+ }
/*
* We're already holding queue_lock and know @tg is valid. Let's
else
*(unsigned int *)((void *)tg + of_cft(of)->private) = v;
- tg_conf_updated(tg);
+ tg_conf_updated(tg, false);
ret = 0;
out_finish:
blkg_conf_finish(&ctx);
tg->iops_conf[READ][off] == iops_dft &&
tg->iops_conf[WRITE][off] == iops_dft &&
(off != LIMIT_LOW ||
- (tg->idletime_threshold == tg->td->dft_idletime_threshold &&
- tg->latency_target == DFL_LATENCY_TARGET)))
+ (tg->idletime_threshold_conf == DFL_IDLE_THRESHOLD &&
+ tg->latency_target_conf == DFL_LATENCY_TARGET)))
return 0;
- if (tg->bps_conf[READ][off] != bps_dft)
+ if (tg->bps_conf[READ][off] != U64_MAX)
snprintf(bufs[0], sizeof(bufs[0]), "%llu",
tg->bps_conf[READ][off]);
- if (tg->bps_conf[WRITE][off] != bps_dft)
+ if (tg->bps_conf[WRITE][off] != U64_MAX)
snprintf(bufs[1], sizeof(bufs[1]), "%llu",
tg->bps_conf[WRITE][off]);
- if (tg->iops_conf[READ][off] != iops_dft)
+ if (tg->iops_conf[READ][off] != UINT_MAX)
snprintf(bufs[2], sizeof(bufs[2]), "%u",
tg->iops_conf[READ][off]);
- if (tg->iops_conf[WRITE][off] != iops_dft)
+ if (tg->iops_conf[WRITE][off] != UINT_MAX)
snprintf(bufs[3], sizeof(bufs[3]), "%u",
tg->iops_conf[WRITE][off]);
if (off == LIMIT_LOW) {
- if (tg->idletime_threshold == ULONG_MAX)
+ if (tg->idletime_threshold_conf == ULONG_MAX)
strcpy(idle_time, " idle=max");
else
snprintf(idle_time, sizeof(idle_time), " idle=%lu",
- tg->idletime_threshold);
+ tg->idletime_threshold_conf);
- if (tg->latency_target == ULONG_MAX)
+ if (tg->latency_target_conf == ULONG_MAX)
strcpy(latency_time, " latency=max");
else
snprintf(latency_time, sizeof(latency_time),
- " latency=%lu", tg->latency_target);
+ " latency=%lu", tg->latency_target_conf);
}
seq_printf(sf, "%s rbps=%s wbps=%s riops=%s wiops=%s%s%s\n",
v[2] = tg->iops_conf[READ][index];
v[3] = tg->iops_conf[WRITE][index];
- idle_time = tg->idletime_threshold;
- latency_time = tg->latency_target;
+ idle_time = tg->idletime_threshold_conf;
+ latency_time = tg->latency_target_conf;
while (true) {
char tok[27]; /* wiops=18446744073709551616 */
char *p;
tg->iops_conf[READ][LIMIT_MAX]);
tg->iops[WRITE][LIMIT_LOW] = min(tg->iops_conf[WRITE][LIMIT_LOW],
tg->iops_conf[WRITE][LIMIT_MAX]);
+ tg->idletime_threshold_conf = idle_time;
+ tg->latency_target_conf = latency_time;
+
+ /* force user to configure all settings for low limit */
+ if (!(tg->bps[READ][LIMIT_LOW] || tg->iops[READ][LIMIT_LOW] ||
+ tg->bps[WRITE][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW]) ||
+ tg->idletime_threshold_conf == DFL_IDLE_THRESHOLD ||
+ tg->latency_target_conf == DFL_LATENCY_TARGET) {
+ tg->bps[READ][LIMIT_LOW] = 0;
+ tg->bps[WRITE][LIMIT_LOW] = 0;
+ tg->iops[READ][LIMIT_LOW] = 0;
+ tg->iops[WRITE][LIMIT_LOW] = 0;
+ tg->idletime_threshold = DFL_IDLE_THRESHOLD;
+ tg->latency_target = DFL_LATENCY_TARGET;
+ } else if (index == LIMIT_LOW) {
+ tg->idletime_threshold = tg->idletime_threshold_conf;
+ tg->latency_target = tg->latency_target_conf;
+ }
- if (index == LIMIT_LOW) {
- blk_throtl_update_limit_valid(tg->td);
- if (tg->td->limit_valid[LIMIT_LOW])
+ blk_throtl_update_limit_valid(tg->td);
+ if (tg->td->limit_valid[LIMIT_LOW]) {
+ if (index == LIMIT_LOW)
tg->td->limit_index = LIMIT_LOW;
- tg->idletime_threshold = (idle_time == ULONG_MAX) ?
- ULONG_MAX : idle_time;
- tg->latency_target = (latency_time == ULONG_MAX) ?
- ULONG_MAX : latency_time;
- }
- tg_conf_updated(tg);
+ } else
+ tg->td->limit_index = LIMIT_MAX;
+ tg_conf_updated(tg, index == LIMIT_LOW &&
+ tg->td->limit_valid[LIMIT_LOW]);
ret = 0;
out_finish:
blkg_conf_finish(&ctx);
/*
* cgroup is idle if:
* - single idle is too long, longer than a fixed value (in case user
- * configure a too big threshold) or 4 times of slice
+ * configure a too big threshold) or 4 times of idletime threshold
* - average think time is more than threshold
* - IO latency is largely below threshold
*/
- unsigned long time = jiffies_to_usecs(4 * tg->td->throtl_slice);
-
- time = min_t(unsigned long, MAX_IDLE_TIME, time);
- return (ktime_get_ns() >> 10) - tg->last_finish_time > time ||
- tg->avg_idletime > tg->idletime_threshold ||
- (tg->latency_target && tg->bio_cnt &&
+ unsigned long time;
+ bool ret;
+
+ time = min_t(unsigned long, MAX_IDLE_TIME, 4 * tg->idletime_threshold);
+ ret = tg->latency_target == DFL_LATENCY_TARGET ||
+ tg->idletime_threshold == DFL_IDLE_THRESHOLD ||
+ (ktime_get_ns() >> 10) - tg->last_finish_time > time ||
+ tg->avg_idletime > tg->idletime_threshold ||
+ (tg->latency_target && tg->bio_cnt &&
tg->bad_bio_cnt * 5 < tg->bio_cnt);
+ throtl_log(&tg->service_queue,
+ "avg_idle=%ld, idle_threshold=%ld, bad_bio=%d, total_bio=%d, is_idle=%d, scale=%d",
+ tg->avg_idletime, tg->idletime_threshold, tg->bad_bio_cnt,
+ tg->bio_cnt, ret, tg->td->scale);
+ return ret;
}
static bool throtl_tg_can_upgrade(struct throtl_grp *tg)
struct cgroup_subsys_state *pos_css;
struct blkcg_gq *blkg;
+ throtl_log(&td->service_queue, "upgrade to max");
td->limit_index = LIMIT_MAX;
td->low_upgrade_time = jiffies;
td->scale = 0;
{
td->scale /= 2;
+ throtl_log(&td->service_queue, "downgrade, scale %d", td->scale);
if (td->scale) {
td->low_upgrade_time = jiffies - td->scale * td->throtl_slice;
return;
td->avg_buckets[i].valid = true;
last_latency = td->avg_buckets[i].latency;
}
+
+ for (i = 0; i < LATENCY_BUCKET_SIZE; i++)
+ throtl_log(&td->service_queue,
+ "Latency bucket %d: latency=%ld, valid=%d", i,
+ td->avg_buckets[i].latency, td->avg_buckets[i].valid);
}
#else
static inline void throtl_update_latency_buckets(struct throtl_data *td)
throtl_track_latency(tg->td, blk_stat_size(&bio->bi_issue_stat),
bio_op(bio), lat);
- if (tg->latency_target) {
+ if (tg->latency_target && lat >= tg->td->filtered_latency) {
int bucket;
unsigned int threshold;
void blk_throtl_register_queue(struct request_queue *q)
{
struct throtl_data *td;
- struct cgroup_subsys_state *pos_css;
- struct blkcg_gq *blkg;
+ int i;
td = q->td;
BUG_ON(!td);
if (blk_queue_nonrot(q)) {
td->throtl_slice = DFL_THROTL_SLICE_SSD;
- td->dft_idletime_threshold = DFL_IDLE_THRESHOLD_SSD;
+ td->filtered_latency = LATENCY_FILTERED_SSD;
} else {
td->throtl_slice = DFL_THROTL_SLICE_HD;
- td->dft_idletime_threshold = DFL_IDLE_THRESHOLD_HD;
+ td->filtered_latency = LATENCY_FILTERED_HD;
+ for (i = 0; i < LATENCY_BUCKET_SIZE; i++)
+ td->avg_buckets[i].latency = DFL_HD_BASELINE_LATENCY;
}
#ifndef CONFIG_BLK_DEV_THROTTLING_LOW
/* if no low limit, use previous default */
td->track_bio_latency = !q->mq_ops && !q->request_fn;
if (!td->track_bio_latency)
blk_stat_enable_accounting(q);
-
- /*
- * some tg are created before queue is fully initialized, eg, nonrot
- * isn't initialized yet
- */
- rcu_read_lock();
- blkg_for_each_descendant_post(blkg, pos_css, q->root_blkg) {
- struct throtl_grp *tg = blkg_to_tg(blkg);
-
- tg->idletime_threshold = td->dft_idletime_threshold;
- }
- rcu_read_unlock();
}
#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
int blk_init_rl(struct request_list *rl, struct request_queue *q,
gfp_t gfp_mask);
-void blk_exit_rl(struct request_list *rl);
+void blk_exit_rl(struct request_queue *q, struct request_list *rl);
void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
struct bio *bio);
void blk_queue_bypass_start(struct request_queue *q);
static const int cfq_hist_divisor = 4;
/*
- * offset from end of service tree
+ * offset from end of queue service tree for idle class
*/
#define CFQ_IDLE_DELAY (NSEC_PER_SEC / 5)
+/* offset from end of group service tree under time slice mode */
+#define CFQ_SLICE_MODE_GROUP_DELAY (NSEC_PER_SEC / 5)
+/* offset from end of group service under IOPS mode */
+#define CFQ_IOPS_MODE_GROUP_DELAY (HZ / 5)
/*
* below this threshold, we consider thinktime immediate
cfqg->vfraction = max_t(unsigned, vfr, 1);
}
+static inline u64 cfq_get_cfqg_vdisktime_delay(struct cfq_data *cfqd)
+{
+ if (!iops_mode(cfqd))
+ return CFQ_SLICE_MODE_GROUP_DELAY;
+ else
+ return CFQ_IOPS_MODE_GROUP_DELAY;
+}
+
static void
cfq_group_notify_queue_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
{
n = rb_last(&st->rb);
if (n) {
__cfqg = rb_entry_cfqg(n);
- cfqg->vdisktime = __cfqg->vdisktime + CFQ_IDLE_DELAY;
+ cfqg->vdisktime = __cfqg->vdisktime +
+ cfq_get_cfqg_vdisktime_delay(cfqd);
} else
cfqg->vdisktime = st->min_vdisktime;
cfq_group_service_tree_add(st, cfqg);
if (info) {
struct partition_meta_info *pinfo = alloc_part_info(disk);
- if (!pinfo)
+ if (!pinfo) {
+ err = -ENOMEM;
goto out_free_stats;
+ }
memcpy(pinfo, info, sizeof(*info));
p->info = pinfo;
}
continue;
bsd_start = le32_to_cpu(p->p_offset);
bsd_size = le32_to_cpu(p->p_size);
+ if (memcmp(flavour, "bsd\0", 4) == 0)
+ bsd_start += offset;
if (offset == bsd_start && size == bsd_size)
/* full parent partition, we have it already */
continue;
* signature and returns that to us.
*/
ret = crypto_akcipher_verify(req);
- if (ret == -EINPROGRESS) {
+ if ((ret == -EINPROGRESS) || (ret == -EBUSY)) {
wait_for_completion(&compl.completion);
ret = compl.err;
}
}
error:
- kfree(desc);
+ kzfree(desc);
error_no_desc:
crypto_free_shash(tfm);
kleave(" = %d", ret);
ret = pefile_digest_pe(pebuf, pelen, &ctx);
error:
- kfree(ctx.digest);
+ kzfree(ctx.digest);
return ret;
}
}
}
+ ret = -ENOMEM;
cert->pub->key = kmemdup(ctx->key, ctx->key_size, GFP_KERNEL);
if (!cert->pub->key)
goto error_decode;
break;
case -EINPROGRESS:
case -EBUSY:
- ret = wait_for_completion_interruptible(
- &drbg->ctr_completion);
- if (!ret && !drbg->ctr_async_err) {
+ wait_for_completion(&drbg->ctr_completion);
+ if (!drbg->ctr_async_err) {
reinit_completion(&drbg->ctr_completion);
break;
}
err = crypto_skcipher_encrypt(&data->req);
if (err == -EINPROGRESS || err == -EBUSY) {
- err = wait_for_completion_interruptible(
- &data->result.completion);
- if (!err)
- err = data->result.err;
+ wait_for_completion(&data->result.completion);
+ err = data->result.err;
}
if (err)
return 0;
}
+static int skcipher_setkey_unaligned(struct crypto_skcipher *tfm,
+ const u8 *key, unsigned int keylen)
+{
+ unsigned long alignmask = crypto_skcipher_alignmask(tfm);
+ struct skcipher_alg *cipher = crypto_skcipher_alg(tfm);
+ u8 *buffer, *alignbuffer;
+ unsigned long absize;
+ int ret;
+
+ absize = keylen + alignmask;
+ buffer = kmalloc(absize, GFP_ATOMIC);
+ if (!buffer)
+ return -ENOMEM;
+
+ alignbuffer = (u8 *)ALIGN((unsigned long)buffer, alignmask + 1);
+ memcpy(alignbuffer, key, keylen);
+ ret = cipher->setkey(tfm, alignbuffer, keylen);
+ kzfree(buffer);
+ return ret;
+}
+
+static int skcipher_setkey(struct crypto_skcipher *tfm, const u8 *key,
+ unsigned int keylen)
+{
+ struct skcipher_alg *cipher = crypto_skcipher_alg(tfm);
+ unsigned long alignmask = crypto_skcipher_alignmask(tfm);
+
+ if (keylen < cipher->min_keysize || keylen > cipher->max_keysize) {
+ crypto_skcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+ return -EINVAL;
+ }
+
+ if ((unsigned long)key & alignmask)
+ return skcipher_setkey_unaligned(tfm, key, keylen);
+
+ return cipher->setkey(tfm, key, keylen);
+}
+
static void crypto_skcipher_exit_tfm(struct crypto_tfm *tfm)
{
struct crypto_skcipher *skcipher = __crypto_skcipher_cast(tfm);
tfm->__crt_alg->cra_type == &crypto_givcipher_type)
return crypto_init_skcipher_ops_ablkcipher(tfm);
- skcipher->setkey = alg->setkey;
+ skcipher->setkey = skcipher_setkey;
skcipher->encrypt = alg->encrypt;
skcipher->decrypt = alg->decrypt;
skcipher->ivsize = alg->ivsize;
table_desc->validation_count++;
if (table_desc->validation_count == 0) {
- ACPI_ERROR((AE_INFO,
- "Table %p, Validation count is zero after increment\n",
- table_desc));
table_desc->validation_count--;
- return_ACPI_STATUS(AE_LIMIT);
}
*out_table = table_desc->pointer;
int ret = -ENODEV;
struct fwnode_handle *iort_fwnode;
- /*
- * If we already translated the fwspec there
- * is nothing left to do, return the iommu_ops.
- */
- ops = iort_fwspec_iommu_ops(dev->iommu_fwspec);
- if (ops)
- return ops;
-
if (node) {
iort_fwnode = iort_get_fwnode(node);
if (!iort_fwnode)
u32 streamid = 0;
int err;
+ /*
+ * If we already translated the fwspec there
+ * is nothing left to do, return the iommu_ops.
+ */
+ ops = iort_fwspec_iommu_ops(dev->iommu_fwspec);
+ if (ops)
+ return ops;
+
if (dev_is_pci(dev)) {
struct pci_bus *bus = to_pci_dev(dev)->bus;
u32 rid;
if (err)
ops = ERR_PTR(err);
+ /* Ignore all other errors apart from EPROBE_DEFER */
+ if (IS_ERR(ops) && (PTR_ERR(ops) != -EPROBE_DEFER)) {
+ dev_dbg(dev, "Adding to IOMMU failed: %ld\n", PTR_ERR(ops));
+ ops = NULL;
+ }
+
return ops;
}
if ((battery->state & ACPI_BATTERY_STATE_CRITICAL) ||
(test_bit(ACPI_BATTERY_ALARM_PRESENT, &battery->flags) &&
(battery->capacity_now <= battery->alarm)))
- pm_wakeup_hard_event(&battery->device->dev);
+ pm_wakeup_event(&battery->device->dev, 0);
return result;
}
#define ACPI_BUTTON_LID_INIT_IGNORE 0x00
#define ACPI_BUTTON_LID_INIT_OPEN 0x01
+#define ACPI_BUTTON_LID_INIT_METHOD 0x02
#define _COMPONENT ACPI_BUTTON_COMPONENT
ACPI_MODULE_NAME("button");
static BLOCKING_NOTIFIER_HEAD(acpi_lid_notifier);
static struct acpi_device *lid_device;
-static u8 lid_init_state = ACPI_BUTTON_LID_INIT_OPEN;
+static u8 lid_init_state = ACPI_BUTTON_LID_INIT_METHOD;
static unsigned long lid_report_interval __read_mostly = 500;
module_param(lid_report_interval, ulong, 0644);
}
if (state)
- pm_wakeup_hard_event(&device->dev);
+ pm_wakeup_event(&device->dev, 0);
ret = blocking_notifier_call_chain(&acpi_lid_notifier, state, device);
if (ret == NOTIFY_DONE)
case ACPI_BUTTON_LID_INIT_OPEN:
(void)acpi_lid_notify_state(device, 1);
break;
+ case ACPI_BUTTON_LID_INIT_METHOD:
+ (void)acpi_lid_update_state(device);
+ break;
case ACPI_BUTTON_LID_INIT_IGNORE:
default:
break;
} else {
int keycode;
- pm_wakeup_hard_event(&device->dev);
+ pm_wakeup_event(&device->dev, 0);
if (button->suspended)
break;
lid_device = device;
}
- device_init_wakeup(&device->dev, true);
printk(KERN_INFO PREFIX "%s [%s]\n", name, acpi_device_bid(device));
return 0;
if (!strncmp(val, "open", sizeof("open") - 1)) {
lid_init_state = ACPI_BUTTON_LID_INIT_OPEN;
pr_info("Notify initial lid state as open\n");
+ } else if (!strncmp(val, "method", sizeof("method") - 1)) {
+ lid_init_state = ACPI_BUTTON_LID_INIT_METHOD;
+ pr_info("Notify initial lid state with _LID return value\n");
} else if (!strncmp(val, "ignore", sizeof("ignore") - 1)) {
lid_init_state = ACPI_BUTTON_LID_INIT_IGNORE;
pr_info("Do not notify initial lid state\n");
switch (lid_init_state) {
case ACPI_BUTTON_LID_INIT_OPEN:
return sprintf(buffer, "open");
+ case ACPI_BUTTON_LID_INIT_METHOD:
+ return sprintf(buffer, "method");
case ACPI_BUTTON_LID_INIT_IGNORE:
return sprintf(buffer, "ignore");
default:
#include <linux/pm_qos.h>
#include <linux/pm_domain.h>
#include <linux/pm_runtime.h>
-#include <linux/suspend.h>
#include "internal.h"
mutex_lock(&acpi_pm_notifier_lock);
if (adev->wakeup.flags.notifier_present) {
- pm_wakeup_ws_event(adev->wakeup.ws, 0, true);
+ __pm_wakeup_event(adev->wakeup.ws, 0);
if (adev->wakeup.context.work.func)
queue_pm_work(&adev->wakeup.context.work);
}
struct nfit_spa *nfit_spa;
/* We only care about memory errors */
- if (!(mce->status & MCACOD))
+ if (!mce_is_memory_error(mce))
return NOTIFY_DONE;
/*
iort_set_dma_mask(dev);
iommu = iort_iommu_configure(dev);
- if (IS_ERR(iommu))
- return PTR_ERR(iommu);
+ if (IS_ERR(iommu) && PTR_ERR(iommu) == -EPROBE_DEFER)
+ return -EPROBE_DEFER;
size = max(dev->coherent_dma_mask, dev->coherent_dma_mask + 1);
/*
acpi_os_wait_events_complete();
if (acpi_sci_irq_valid())
enable_irq_wake(acpi_sci_irq);
-
return 0;
}
-static void acpi_freeze_wake(void)
-{
- /*
- * If IRQD_WAKEUP_ARMED is not set for the SCI at this point, it means
- * that the SCI has triggered while suspended, so cancel the wakeup in
- * case it has not been a wakeup event (the GPEs will be checked later).
- */
- if (acpi_sci_irq_valid() &&
- !irqd_is_wakeup_armed(irq_get_irq_data(acpi_sci_irq)))
- pm_system_cancel_wakeup();
-}
-
-static void acpi_freeze_sync(void)
-{
- /*
- * Process all pending events in case there are any wakeup ones.
- *
- * The EC driver uses the system workqueue, so that one needs to be
- * flushed too.
- */
- acpi_os_wait_events_complete();
- flush_scheduled_work();
-}
-
static void acpi_freeze_restore(void)
{
acpi_disable_wakeup_devices(ACPI_STATE_S0);
if (acpi_sci_irq_valid())
disable_irq_wake(acpi_sci_irq);
-
acpi_enable_all_runtime_gpes();
}
static const struct platform_freeze_ops acpi_freeze_ops = {
.begin = acpi_freeze_begin,
.prepare = acpi_freeze_prepare,
- .wake = acpi_freeze_wake,
- .sync = acpi_freeze_sync,
.restore = acpi_freeze_restore,
.end = acpi_freeze_end,
};
container_of(bin_attr, struct acpi_table_attr, attr);
struct acpi_table_header *table_header = NULL;
acpi_status status;
+ ssize_t rc;
status = acpi_get_table(table_attr->name, table_attr->instance,
&table_header);
if (ACPI_FAILURE(status))
return -ENODEV;
- return memory_read_from_buffer(buf, count, &offset,
- table_header, table_header->length);
+ rc = memory_read_from_buffer(buf, count, &offset, table_header,
+ table_header->length);
+ acpi_put_table(table_header);
+ return rc;
}
static int acpi_table_attr_init(struct kobject *tables_obj,
{}
#endif
+/*
+ * On the Acer Aspire Switch Alpha 12, sometimes all SATA ports are detected
+ * as DUMMY, or detected but eventually get a "link down" and never get up
+ * again. When this happens, CAP.NP may hold a value of 0x00 or 0x01, and the
+ * port_map may hold a value of 0x00.
+ *
+ * Overriding CAP.NP to 0x02 and the port_map to 0x7 will reveal all 3 ports
+ * and can significantly reduce the occurrence of the problem.
+ *
+ * https://bugzilla.kernel.org/show_bug.cgi?id=189471
+ */
+static void acer_sa5_271_workaround(struct ahci_host_priv *hpriv,
+ struct pci_dev *pdev)
+{
+ static const struct dmi_system_id sysids[] = {
+ {
+ .ident = "Acer Switch Alpha 12",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Switch SA5-271")
+ },
+ },
+ { }
+ };
+
+ if (dmi_check_system(sysids)) {
+ dev_info(&pdev->dev, "enabling Acer Switch Alpha 12 workaround\n");
+ if ((hpriv->saved_cap & 0xC734FF00) == 0xC734FF00) {
+ hpriv->port_map = 0x7;
+ hpriv->cap = 0xC734FF02;
+ }
+ }
+}
+
#ifdef CONFIG_ARM64
/*
* Due to ERRATA#22536, ThunderX needs to handle HOST_IRQ_STAT differently.
"online status unreliable, applying workaround\n");
}
+
+ /* Acer SA5-271 workaround modifies private_data */
+ acer_sa5_271_workaround(hpriv, pdev);
+
/* CAP.NP sometimes indicate the index of the last enabled
* port, at other times, that of the last possible port, so
* determining the maximum port number requires looking at
irq = platform_get_irq(pdev, 0);
if (irq <= 0) {
- dev_err(dev, "no irq\n");
- return -EINVAL;
+ if (irq != -EPROBE_DEFER)
+ dev_err(dev, "no irq\n");
+ return irq;
}
hpriv->irq = irq;
}
force_ent->port = simple_strtoul(id, &endp, 10);
- if (p == endp || *endp != '\0') {
+ if (id == endp || *endp != '\0') {
*reason = "invalid port/link";
return -EINVAL;
}
struct ata_host *host;
struct mv_host_priv *hpriv;
struct resource *res;
- void __iomem *mmio;
int n_ports = 0, irq = 0;
int rc;
int port;
* Get the register base first
*/
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- mmio = devm_ioremap_resource(&pdev->dev, res);
- if (IS_ERR(mmio))
- return PTR_ERR(mmio);
+ if (res == NULL)
+ return -EINVAL;
/* allocate host */
if (pdev->dev.of_node) {
hpriv->board_idx = chip_soc;
host->iomap = NULL;
- hpriv->base = mmio - SATAHC0_REG_BASE;
+ hpriv->base = devm_ioremap(&pdev->dev, res->start,
+ resource_size(res));
+ if (!hpriv->base)
+ return -ENOMEM;
+
+ hpriv->base -= SATAHC0_REG_BASE;
hpriv->clk = clk_get(&pdev->dev, NULL);
if (IS_ERR(hpriv->clk))
dev_err(&pdev->dev, "failed to get access to sata clock\n");
return PTR_ERR(priv->clk);
}
- clk_prepare_enable(priv->clk);
+
+ ret = clk_prepare_enable(priv->clk);
+ if (ret)
+ return ret;
host = ata_host_alloc(&pdev->dev, 1);
if (!host) {
struct ata_host *host = dev_get_drvdata(dev);
struct sata_rcar_priv *priv = host->private_data;
void __iomem *base = priv->base;
+ int ret;
- clk_prepare_enable(priv->clk);
+ ret = clk_prepare_enable(priv->clk);
+ if (ret)
+ return ret;
/* ack and mask */
iowrite32(0, base + SATAINTSTAT_REG);
{
struct ata_host *host = dev_get_drvdata(dev);
struct sata_rcar_priv *priv = host->private_data;
+ int ret;
- clk_prepare_enable(priv->clk);
+ ret = clk_prepare_enable(priv->clk);
+ if (ret)
+ return ret;
sata_rcar_setup_port(host);
if (async_error)
goto Complete;
+ if (pm_wakeup_pending()) {
+ async_error = -EBUSY;
+ goto Complete;
+ }
+
if (dev->power.syscore || dev->power.direct_complete)
goto Complete;
/* First wakeup IRQ seen by the kernel in the last cycle. */
unsigned int pm_wakeup_irq __read_mostly;
-/* If greater than 0 and the system is suspending, terminate the suspend. */
-static atomic_t pm_abort_suspend __read_mostly;
+/* If set and the system is suspending, terminate the suspend. */
+static bool pm_abort_suspend __read_mostly;
/*
* Combined counters of registered wakeup events and wakeup events in progress.
/**
* wakup_source_activate - Mark given wakeup source as active.
* @ws: Wakeup source to handle.
- * @hard: If set, abort suspends in progress and wake up from suspend-to-idle.
*
* Update the @ws' statistics and, if @ws has just been activated, notify the PM
* core of the event by incrementing the counter of of wakeup events being
* processed.
*/
-static void wakeup_source_activate(struct wakeup_source *ws, bool hard)
+static void wakeup_source_activate(struct wakeup_source *ws)
{
unsigned int cec;
"unregistered wakeup source\n"))
return;
- if (hard)
- pm_system_wakeup();
-
ws->active = true;
ws->active_count++;
ws->last_time = ktime_get();
ws->wakeup_count++;
if (!ws->active)
- wakeup_source_activate(ws, hard);
+ wakeup_source_activate(ws);
+
+ if (hard)
+ pm_system_wakeup();
}
/**
pm_print_active_wakeup_sources();
}
- return ret || atomic_read(&pm_abort_suspend) > 0;
+ return ret || pm_abort_suspend;
}
void pm_system_wakeup(void)
{
- atomic_inc(&pm_abort_suspend);
+ pm_abort_suspend = true;
freeze_wake();
}
EXPORT_SYMBOL_GPL(pm_system_wakeup);
-void pm_system_cancel_wakeup(void)
-{
- atomic_dec(&pm_abort_suspend);
-}
-
-void pm_wakeup_clear(bool reset)
+void pm_wakeup_clear(void)
{
+ pm_abort_suspend = false;
pm_wakeup_irq = 0;
- if (reset)
- atomic_set(&pm_abort_suspend, 0);
}
void pm_system_irq_wakeup(unsigned int irq_number)
}
/* still holds resource->req_lock */
-static int drbd_req_put_completion_ref(struct drbd_request *req, struct bio_and_error *m, int put)
+static void drbd_req_put_completion_ref(struct drbd_request *req, struct bio_and_error *m, int put)
{
struct drbd_device *device = req->device;
D_ASSERT(device, m || (req->rq_state & RQ_POSTPONED));
+ if (!put)
+ return;
+
if (!atomic_sub_and_test(put, &req->completion_ref))
- return 0;
+ return;
drbd_req_complete(req, m);
+ /* local completion may still come in later,
+ * we need to keep the req object around. */
+ if (req->rq_state & RQ_LOCAL_ABORTED)
+ return;
+
if (req->rq_state & RQ_POSTPONED) {
/* don't destroy the req object just yet,
* but queue it for retry */
drbd_restart_request(req);
- return 0;
+ return;
}
- return 1;
+ kref_put(&req->kref, drbd_req_destroy);
}
static void set_if_null_req_next(struct drbd_peer_device *peer_device, struct drbd_request *req)
if (req->i.waiting)
wake_up(&device->misc_wait);
- if (c_put) {
- if (drbd_req_put_completion_ref(req, m, c_put))
- kref_put(&req->kref, drbd_req_destroy);
- } else {
- kref_put(&req->kref, drbd_req_destroy);
- }
+ drbd_req_put_completion_ref(req, m, c_put);
+ kref_put(&req->kref, drbd_req_destroy);
}
static void drbd_report_io_error(struct drbd_device *device, struct drbd_request *req)
}
out:
- if (drbd_req_put_completion_ref(req, &m, 1))
- kref_put(&req->kref, drbd_req_destroy);
+ drbd_req_put_completion_ref(req, &m, 1);
spin_unlock_irq(&resource->req_lock);
/* Even though above is a kref_put(), this is safe.
*/
static int loop_flush(struct loop_device *lo)
{
+ /* loop not yet configured, no running thread, nothing to flush */
+ if (lo->lo_state != Lo_bound)
+ return 0;
return loop_switch(lo, NULL);
}
return -ENOSPC;
}
-/* Reset all properties of an NBD device */
-static void nbd_reset(struct nbd_device *nbd)
-{
- nbd->config = NULL;
- nbd->tag_set.timeout = 0;
- queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, nbd->disk->queue);
-}
-
static void nbd_bdev_reset(struct block_device *bdev)
{
if (bdev->bd_openers > 1)
}
kfree(config->socks);
}
- nbd_reset(nbd);
+ kfree(nbd->config);
+ nbd->config = NULL;
+
+ nbd->tag_set.timeout = 0;
+ queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, nbd->disk->queue);
mutex_unlock(&nbd->config_lock);
nbd_put(nbd);
disk->fops = &nbd_fops;
disk->private_data = nbd;
sprintf(disk->disk_name, "nbd%d", index);
- nbd_reset(nbd);
add_disk(disk);
nbd_total_devices++;
return index;
switch (req_op(rq)) {
case REQ_OP_DISCARD:
+ case REQ_OP_WRITE_ZEROES:
op_type = OBJ_OP_DISCARD;
break;
case REQ_OP_WRITE:
q->limits.discard_granularity = segment_size;
q->limits.discard_alignment = segment_size;
blk_queue_max_discard_sectors(q, segment_size / SECTOR_SIZE);
+ blk_queue_max_write_zeroes_sectors(q, segment_size / SECTOR_SIZE);
if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC))
q->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
dev_set_drvdata(&dev->dev, NULL);
- if (be->blkif)
+ if (be->blkif) {
xen_blkif_disconnect(be->blkif);
- /* Put the reference we set in xen_blkif_alloc(). */
- xen_blkif_put(be->blkif);
+ /* Put the reference we set in xen_blkif_alloc(). */
+ xen_blkif_put(be->blkif);
+ }
+
kfree(be->mode);
kfree(be);
return 0;
} else if (!strcmp(str, "auto")) {
parport_nr[0] = LP_PARPORT_AUTO;
} else if (!strcmp(str, "none")) {
- parport_nr[parport_ptr++] = LP_PARPORT_NONE;
+ if (parport_ptr < LP_NO)
+ parport_nr[parport_ptr++] = LP_PARPORT_NONE;
+ else
+ printk(KERN_INFO "lp: too many ports, %s ignored.\n",
+ str);
} else if (!strcmp(str, "reset")) {
reset = 1;
}
static int mmap_mem(struct file *file, struct vm_area_struct *vma)
{
size_t size = vma->vm_end - vma->vm_start;
+ phys_addr_t offset = (phys_addr_t)vma->vm_pgoff << PAGE_SHIFT;
+
+ /* It's illegal to wrap around the end of the physical address space. */
+ if (offset + (phys_addr_t)size - 1 < offset)
+ return -EINVAL;
if (!valid_mmap_phys_addr_range(vma->vm_pgoff, size))
return -EINVAL;
rc = write_sync_reg(SCR_HOST_TO_READER_START, dev);
if (rc <= 0) {
- DEBUGP(5, dev, "write_sync_reg c=%.2Zx\n", rc);
+ DEBUGP(5, dev, "write_sync_reg c=%.2zx\n", rc);
DEBUGP(2, dev, "<- cm4040_write (failed)\n");
if (rc == -ERESTARTSYS)
return rc;
for (i = 0; i < bytes_to_write; i++) {
rc = wait_for_bulk_out_ready(dev);
if (rc <= 0) {
- DEBUGP(5, dev, "wait_for_bulk_out_ready rc=%.2Zx\n",
+ DEBUGP(5, dev, "wait_for_bulk_out_ready rc=%.2zx\n",
rc);
DEBUGP(2, dev, "<- cm4040_write (failed)\n");
if (rc == -ERESTARTSYS)
rc = write_sync_reg(SCR_HOST_TO_READER_DONE, dev);
if (rc <= 0) {
- DEBUGP(5, dev, "write_sync_reg c=%.2Zx\n", rc);
+ DEBUGP(5, dev, "write_sync_reg c=%.2zx\n", rc);
DEBUGP(2, dev, "<- cm4040_write (failed)\n");
if (rc == -ERESTARTSYS)
return rc;
/*
* random.c -- A strong random number generator
*
+ * Copyright (C) 2017 Jason A. Donenfeld <Jason@zx2c4.com>. All
+ * Rights Reserved.
+ *
* Copyright Matt Mackall <mpm@selenic.com>, 2003, 2004, 2005
*
* Copyright Theodore Ts'o, 1994, 1995, 1996, 1997, 1998, 1999. All
static struct crng_state **crng_node_pool __read_mostly;
#endif
+static void invalidate_batched_entropy(void);
+
static void crng_initialize(struct crng_state *crng)
{
int i;
cp++; crng_init_cnt++; len--;
}
if (crng_init_cnt >= CRNG_INIT_CNT_THRESH) {
+ invalidate_batched_entropy();
crng_init = 1;
wake_up_interruptible(&crng_init_wait);
pr_notice("random: fast init done\n");
memzero_explicit(&buf, sizeof(buf));
crng->init_time = jiffies;
if (crng == &primary_crng && crng_init < 2) {
+ invalidate_batched_entropy();
crng_init = 2;
process_random_ready_list();
wake_up_interruptible(&crng_init_wait);
static __u32 get_reg(struct fast_pool *f, struct pt_regs *regs)
{
__u32 *ptr = (__u32 *) regs;
+ unsigned int idx;
if (regs == NULL)
return 0;
- if (f->reg_idx >= sizeof(struct pt_regs) / sizeof(__u32))
- f->reg_idx = 0;
- return *(ptr + f->reg_idx++);
+ idx = READ_ONCE(f->reg_idx);
+ if (idx >= sizeof(struct pt_regs) / sizeof(__u32))
+ idx = 0;
+ ptr += idx++;
+ WRITE_ONCE(f->reg_idx, idx);
+ return *ptr;
}
void add_interrupt_randomness(int irq, int irq_flags)
};
unsigned int position;
};
+static rwlock_t batched_entropy_reset_lock = __RW_LOCK_UNLOCKED(batched_entropy_reset_lock);
/*
* Get a random word for internal kernel use only. The quality of the random
u64 get_random_u64(void)
{
u64 ret;
+ bool use_lock = crng_init < 2;
+ unsigned long flags;
struct batched_entropy *batch;
#if BITS_PER_LONG == 64
#endif
batch = &get_cpu_var(batched_entropy_u64);
+ if (use_lock)
+ read_lock_irqsave(&batched_entropy_reset_lock, flags);
if (batch->position % ARRAY_SIZE(batch->entropy_u64) == 0) {
extract_crng((u8 *)batch->entropy_u64);
batch->position = 0;
}
ret = batch->entropy_u64[batch->position++];
+ if (use_lock)
+ read_unlock_irqrestore(&batched_entropy_reset_lock, flags);
put_cpu_var(batched_entropy_u64);
return ret;
}
u32 get_random_u32(void)
{
u32 ret;
+ bool use_lock = crng_init < 2;
+ unsigned long flags;
struct batched_entropy *batch;
if (arch_get_random_int(&ret))
return ret;
batch = &get_cpu_var(batched_entropy_u32);
+ if (use_lock)
+ read_lock_irqsave(&batched_entropy_reset_lock, flags);
if (batch->position % ARRAY_SIZE(batch->entropy_u32) == 0) {
extract_crng((u8 *)batch->entropy_u32);
batch->position = 0;
}
ret = batch->entropy_u32[batch->position++];
+ if (use_lock)
+ read_unlock_irqrestore(&batched_entropy_reset_lock, flags);
put_cpu_var(batched_entropy_u32);
return ret;
}
EXPORT_SYMBOL(get_random_u32);
+/* It's important to invalidate all potential batched entropy that might
+ * be stored before the crng is initialized, which we can do lazily by
+ * simply resetting the counter to zero so that it's re-extracted on the
+ * next usage. */
+static void invalidate_batched_entropy(void)
+{
+ int cpu;
+ unsigned long flags;
+
+ write_lock_irqsave(&batched_entropy_reset_lock, flags);
+ for_each_possible_cpu (cpu) {
+ per_cpu_ptr(&batched_entropy_u32, cpu)->position = 0;
+ per_cpu_ptr(&batched_entropy_u64, cpu)->position = 0;
+ }
+ write_unlock_irqrestore(&batched_entropy_reset_lock, flags);
+}
+
/**
* randomize_page - Generate a random, page aligned address
* @start: The smallest acceptable address the caller will take.
If in doubt, say N.
+config ARM_DB8500_CPUFREQ
+ tristate "ST-Ericsson DB8500 cpufreq" if COMPILE_TEST && !ARCH_U8500
+ default ARCH_U8500
+ depends on HAS_IOMEM
+ depends on !CPU_THERMAL || THERMAL
+ help
+ This adds the CPUFreq driver for ST-Ericsson Ux500 (DB8500) SoC
+ series.
+
config ARM_IMX6Q_CPUFREQ
tristate "Freescale i.MX6 cpufreq support"
depends on ARCH_MXC
obj-$(CONFIG_ARM_BRCMSTB_AVS_CPUFREQ) += brcmstb-avs-cpufreq.o
obj-$(CONFIG_ARCH_DAVINCI) += davinci-cpufreq.o
-obj-$(CONFIG_UX500_SOC_DB8500) += dbx500-cpufreq.o
+obj-$(CONFIG_ARM_DB8500_CPUFREQ) += dbx500-cpufreq.o
obj-$(CONFIG_ARM_EXYNOS5440_CPUFREQ) += exynos5440-cpufreq.o
obj-$(CONFIG_ARM_HIGHBANK_CPUFREQ) += highbank-cpufreq.o
obj-$(CONFIG_ARM_IMX6Q_CPUFREQ) += imx6q-cpufreq.o
if (!(cpufreq_driver->flags & CPUFREQ_STICKY) &&
list_empty(&cpufreq_policy_list)) {
/* if all ->init() calls failed, unregister */
+ ret = -ENODEV;
pr_debug("%s: No CPU initialized for driver %s\n", __func__,
driver_data->name);
goto err_if_unreg;
static int min_perf_pct_min(void)
{
struct cpudata *cpu = all_cpu_data[0];
+ int turbo_pstate = cpu->pstate.turbo_pstate;
- return DIV_ROUND_UP(cpu->pstate.min_pstate * 100,
- cpu->pstate.turbo_pstate);
+ return turbo_pstate ?
+ DIV_ROUND_UP(cpu->pstate.min_pstate * 100, turbo_pstate) : 0;
}
static s16 intel_pstate_get_epb(struct cpudata *cpu_data)
return PTR_ERR(priv.cpu_clk);
}
- clk_prepare_enable(priv.cpu_clk);
+ err = clk_prepare_enable(priv.cpu_clk);
+ if (err) {
+ dev_err(priv.dev, "Unable to prepare cpuclk\n");
+ return err;
+ }
+
kirkwood_freq_table[0].frequency = clk_get_rate(priv.cpu_clk) / 1000;
priv.ddr_clk = of_clk_get_by_name(np, "ddrclk");
goto out_cpu;
}
- clk_prepare_enable(priv.ddr_clk);
+ err = clk_prepare_enable(priv.ddr_clk);
+ if (err) {
+ dev_err(priv.dev, "Unable to prepare ddrclk\n");
+ goto out_cpu;
+ }
kirkwood_freq_table[1].frequency = clk_get_rate(priv.ddr_clk) / 1000;
priv.powersave_clk = of_clk_get_by_name(np, "powersave");
err = PTR_ERR(priv.powersave_clk);
goto out_ddr;
}
- clk_prepare_enable(priv.powersave_clk);
+ err = clk_prepare_enable(priv.powersave_clk);
+ if (err) {
+ dev_err(priv.dev, "Unable to prepare powersave clk\n");
+ goto out_ddr;
+ }
of_node_put(np);
np = NULL;
}
EXPORT_SYMBOL_GPL(dax_read_unlock);
+#ifdef CONFIG_BLOCK
int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size,
pgoff_t *pgoff)
{
return 0;
}
EXPORT_SYMBOL_GPL(__bdev_dax_supported);
+#endif
/**
* struct dax_device - anchor object for dax services
static struct inode *dax_alloc_inode(struct super_block *sb)
{
struct dax_device *dax_dev;
+ struct inode *inode;
dax_dev = kmem_cache_alloc(dax_cache, GFP_KERNEL);
- return &dax_dev->inode;
+ inode = &dax_dev->inode;
+ inode->i_rdev = 0;
+ return inode;
}
static struct dax_device *to_dax_dev(struct inode *inode)
kfree(dax_dev->host);
dax_dev->host = NULL;
- ida_simple_remove(&dax_minor_ida, MINOR(inode->i_rdev));
+ if (inode->i_rdev)
+ ida_simple_remove(&dax_minor_ida, MINOR(inode->i_rdev));
kmem_cache_free(dax_cache, dax_dev);
}
struct dax_device *dax_dev = _dax_dev;
struct inode *inode = &dax_dev->inode;
+ memset(dax_dev, 0, sizeof(*dax_dev));
inode_init_once(inode);
}
struct dma_device dma_dev;
bool m2m;
int (*hw_setup)(struct ep93xx_dma_chan *);
+ void (*hw_synchronize)(struct ep93xx_dma_chan *);
void (*hw_shutdown)(struct ep93xx_dma_chan *);
void (*hw_submit)(struct ep93xx_dma_chan *);
int (*hw_interrupt)(struct ep93xx_dma_chan *);
| M2P_CONTROL_ENABLE;
m2p_set_control(edmac, control);
+ edmac->buffer = 0;
+
return 0;
}
return (readl(edmac->regs + M2P_STATUS) >> 4) & 0x3;
}
-static void m2p_hw_shutdown(struct ep93xx_dma_chan *edmac)
+static void m2p_hw_synchronize(struct ep93xx_dma_chan *edmac)
{
+ unsigned long flags;
u32 control;
+ spin_lock_irqsave(&edmac->lock, flags);
control = readl(edmac->regs + M2P_CONTROL);
control &= ~(M2P_CONTROL_STALLINT | M2P_CONTROL_NFBINT);
m2p_set_control(edmac, control);
+ spin_unlock_irqrestore(&edmac->lock, flags);
while (m2p_channel_state(edmac) >= M2P_STATE_ON)
- cpu_relax();
+ schedule();
+}
+static void m2p_hw_shutdown(struct ep93xx_dma_chan *edmac)
+{
m2p_set_control(edmac, 0);
- while (m2p_channel_state(edmac) == M2P_STATE_STALL)
- cpu_relax();
+ while (m2p_channel_state(edmac) != M2P_STATE_IDLE)
+ dev_warn(chan2dev(edmac), "M2P: Not yet IDLE\n");
}
static void m2p_fill_desc(struct ep93xx_dma_chan *edmac)
return NULL;
}
+/**
+ * ep93xx_dma_synchronize - Synchronizes the termination of transfers to the
+ * current context.
+ * @chan: channel
+ *
+ * Synchronizes the DMA channel termination to the current context. When this
+ * function returns it is guaranteed that all transfers for previously issued
+ * descriptors have stopped and and it is safe to free the memory associated
+ * with them. Furthermore it is guaranteed that all complete callback functions
+ * for a previously submitted descriptor have finished running and it is safe to
+ * free resources accessed from within the complete callbacks.
+ */
+static void ep93xx_dma_synchronize(struct dma_chan *chan)
+{
+ struct ep93xx_dma_chan *edmac = to_ep93xx_dma_chan(chan);
+
+ if (edmac->edma->hw_synchronize)
+ edmac->edma->hw_synchronize(edmac);
+}
+
/**
* ep93xx_dma_terminate_all - terminate all transactions
* @chan: channel
dma_dev->device_prep_slave_sg = ep93xx_dma_prep_slave_sg;
dma_dev->device_prep_dma_cyclic = ep93xx_dma_prep_dma_cyclic;
dma_dev->device_config = ep93xx_dma_slave_config;
+ dma_dev->device_synchronize = ep93xx_dma_synchronize;
dma_dev->device_terminate_all = ep93xx_dma_terminate_all;
dma_dev->device_issue_pending = ep93xx_dma_issue_pending;
dma_dev->device_tx_status = ep93xx_dma_tx_status;
} else {
dma_cap_set(DMA_PRIVATE, dma_dev->cap_mask);
+ edma->hw_synchronize = m2p_hw_synchronize;
edma->hw_setup = m2p_hw_setup;
edma->hw_shutdown = m2p_hw_shutdown;
edma->hw_submit = m2p_hw_submit;
struct mv_xor_v2_sw_desc *sw_desq;
int desc_size;
unsigned int npendings;
+ unsigned int hw_queue_idx;
};
/**
}
}
-/*
- * Return the next available index in the DESQ.
- */
-static int mv_xor_v2_get_desq_write_ptr(struct mv_xor_v2_device *xor_dev)
-{
- /* read the index for the next available descriptor in the DESQ */
- u32 reg = readl(xor_dev->dma_base + MV_XOR_V2_DMA_DESQ_ALLOC_OFF);
-
- return ((reg >> MV_XOR_V2_DMA_DESQ_ALLOC_WRPTR_SHIFT)
- & MV_XOR_V2_DMA_DESQ_ALLOC_WRPTR_MASK);
-}
-
/*
* notify the engine of new descriptors, and update the available index.
*/
return MV_XOR_V2_EXT_DESC_SIZE;
}
-/*
- * Set the IMSG threshold
- */
-static inline
-void mv_xor_v2_set_imsg_thrd(struct mv_xor_v2_device *xor_dev, int thrd_val)
-{
- u32 reg;
-
- reg = readl(xor_dev->dma_base + MV_XOR_V2_DMA_IMSG_THRD_OFF);
-
- reg &= (~MV_XOR_V2_DMA_IMSG_THRD_MASK << MV_XOR_V2_DMA_IMSG_THRD_SHIFT);
- reg |= (thrd_val << MV_XOR_V2_DMA_IMSG_THRD_SHIFT);
-
- writel(reg, xor_dev->dma_base + MV_XOR_V2_DMA_IMSG_THRD_OFF);
-}
-
static irqreturn_t mv_xor_v2_interrupt_handler(int irq, void *data)
{
struct mv_xor_v2_device *xor_dev = data;
if (!ndescs)
return IRQ_NONE;
- /*
- * Update IMSG threshold, to disable new IMSG interrupts until
- * end of the tasklet
- */
- mv_xor_v2_set_imsg_thrd(xor_dev, MV_XOR_V2_DESC_NUM);
-
/* schedule a tasklet to handle descriptors callbacks */
tasklet_schedule(&xor_dev->irq_tasklet);
static dma_cookie_t
mv_xor_v2_tx_submit(struct dma_async_tx_descriptor *tx)
{
- int desq_ptr;
void *dest_hw_desc;
dma_cookie_t cookie;
struct mv_xor_v2_sw_desc *sw_desc =
spin_lock_bh(&xor_dev->lock);
cookie = dma_cookie_assign(tx);
- /* get the next available slot in the DESQ */
- desq_ptr = mv_xor_v2_get_desq_write_ptr(xor_dev);
-
/* copy the HW descriptor from the SW descriptor to the DESQ */
- dest_hw_desc = xor_dev->hw_desq_virt + desq_ptr;
+ dest_hw_desc = xor_dev->hw_desq_virt + xor_dev->hw_queue_idx;
memcpy(dest_hw_desc, &sw_desc->hw_desc, xor_dev->desc_size);
xor_dev->npendings++;
+ xor_dev->hw_queue_idx++;
+ if (xor_dev->hw_queue_idx >= MV_XOR_V2_DESC_NUM)
+ xor_dev->hw_queue_idx = 0;
spin_unlock_bh(&xor_dev->lock);
mv_xor_v2_prep_sw_desc(struct mv_xor_v2_device *xor_dev)
{
struct mv_xor_v2_sw_desc *sw_desc;
+ bool found = false;
/* Lock the channel */
spin_lock_bh(&xor_dev->lock);
return NULL;
}
- /* get a free SW descriptor from the SW DESQ */
- sw_desc = list_first_entry(&xor_dev->free_sw_desc,
- struct mv_xor_v2_sw_desc, free_list);
+ list_for_each_entry(sw_desc, &xor_dev->free_sw_desc, free_list) {
+ if (async_tx_test_ack(&sw_desc->async_tx)) {
+ found = true;
+ break;
+ }
+ }
+
+ if (!found) {
+ spin_unlock_bh(&xor_dev->lock);
+ return NULL;
+ }
+
list_del(&sw_desc->free_list);
/* Release the channel */
spin_unlock_bh(&xor_dev->lock);
- /* set the async tx descriptor */
- dma_async_tx_descriptor_init(&sw_desc->async_tx, &xor_dev->dmachan);
- sw_desc->async_tx.tx_submit = mv_xor_v2_tx_submit;
- async_tx_ack(&sw_desc->async_tx);
-
return sw_desc;
}
__func__, len, &src, &dest, flags);
sw_desc = mv_xor_v2_prep_sw_desc(xor_dev);
+ if (!sw_desc)
+ return NULL;
sw_desc->async_tx.flags = flags;
__func__, src_cnt, len, &dest, flags);
sw_desc = mv_xor_v2_prep_sw_desc(xor_dev);
+ if (!sw_desc)
+ return NULL;
sw_desc->async_tx.flags = flags;
container_of(chan, struct mv_xor_v2_device, dmachan);
sw_desc = mv_xor_v2_prep_sw_desc(xor_dev);
+ if (!sw_desc)
+ return NULL;
/* set the HW descriptor */
hw_descriptor = &sw_desc->hw_desc;
{
struct mv_xor_v2_device *xor_dev = (struct mv_xor_v2_device *) data;
int pending_ptr, num_of_pending, i;
- struct mv_xor_v2_descriptor *next_pending_hw_desc = NULL;
struct mv_xor_v2_sw_desc *next_pending_sw_desc = NULL;
dev_dbg(xor_dev->dmadev.dev, "%s %d\n", __func__, __LINE__);
/* get the pending descriptors parameters */
num_of_pending = mv_xor_v2_get_pending_params(xor_dev, &pending_ptr);
- /* next HW descriptor */
- next_pending_hw_desc = xor_dev->hw_desq_virt + pending_ptr;
-
/* loop over free descriptors */
for (i = 0; i < num_of_pending; i++) {
-
- if (pending_ptr > MV_XOR_V2_DESC_NUM)
- pending_ptr = 0;
-
- if (next_pending_sw_desc != NULL)
- next_pending_hw_desc++;
+ struct mv_xor_v2_descriptor *next_pending_hw_desc =
+ xor_dev->hw_desq_virt + pending_ptr;
/* get the SW descriptor related to the HW descriptor */
next_pending_sw_desc =
/* increment the next descriptor */
pending_ptr++;
+ if (pending_ptr >= MV_XOR_V2_DESC_NUM)
+ pending_ptr = 0;
}
if (num_of_pending != 0) {
/* free the descriptores */
mv_xor_v2_free_desc_from_desq(xor_dev, num_of_pending);
}
-
- /* Update IMSG threshold, to enable new IMSG interrupts */
- mv_xor_v2_set_imsg_thrd(xor_dev, 0);
}
/*
writel((xor_dev->hw_desq & 0xFFFF00000000) >> 32,
xor_dev->dma_base + MV_XOR_V2_DMA_DESQ_BAHR_OFF);
- /* enable the DMA engine */
- writel(0, xor_dev->dma_base + MV_XOR_V2_DMA_DESQ_STOP_OFF);
-
/*
* This is a temporary solution, until we activate the
* SMMU. Set the attributes for reading & writing data buffers
reg |= MV_XOR_V2_GLOB_PAUSE_AXI_TIME_DIS_VAL;
writel(reg, xor_dev->glob_base + MV_XOR_V2_GLOB_PAUSE);
+ /* enable the DMA engine */
+ writel(0, xor_dev->dma_base + MV_XOR_V2_DMA_DESQ_STOP_OFF);
+
return 0;
}
platform_set_drvdata(pdev, xor_dev);
+ ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(40));
+ if (ret)
+ return ret;
+
xor_dev->clk = devm_clk_get(&pdev->dev, NULL);
if (IS_ERR(xor_dev->clk) && PTR_ERR(xor_dev->clk) == -EPROBE_DEFER)
return -EPROBE_DEFER;
/* add all SW descriptors to the free list */
for (i = 0; i < MV_XOR_V2_DESC_NUM; i++) {
- xor_dev->sw_desq[i].idx = i;
- list_add(&xor_dev->sw_desq[i].free_list,
+ struct mv_xor_v2_sw_desc *sw_desc =
+ xor_dev->sw_desq + i;
+ sw_desc->idx = i;
+ dma_async_tx_descriptor_init(&sw_desc->async_tx,
+ &xor_dev->dmachan);
+ sw_desc->async_tx.tx_submit = mv_xor_v2_tx_submit;
+ async_tx_ack(&sw_desc->async_tx);
+
+ list_add(&sw_desc->free_list,
&xor_dev->free_sw_desc);
}
for (i = 0; i < AMBA_NR_IRQS; i++) {
irq = adev->irq[i];
- devm_free_irq(&adev->dev, irq, pl330);
+ if (irq)
+ devm_free_irq(&adev->dev, irq, pl330);
}
dma_async_device_unregister(&pl330->ddma);
if (desc->hwdescs.use) {
dptr = (rcar_dmac_chan_read(chan, RCAR_DMACHCRB) &
RCAR_DMACHCRB_DPTR_MASK) >> RCAR_DMACHCRB_DPTR_SHIFT;
+ if (dptr == 0)
+ dptr = desc->nchunks;
+ dptr--;
WARN_ON(dptr >= desc->nchunks);
} else {
running = desc->running;
#define USB_DMASWR 0x0008
#define USB_DMASWR_SWR (1 << 0)
#define USB_DMAOR 0x0060
-#define USB_DMAOR_AE (1 << 2)
+#define USB_DMAOR_AE (1 << 1)
#define USB_DMAOR_DME (1 << 0)
#define USB_DMASAR 0x0000
DEFINE_DMI_ATTR_WITH_SHOW(product_version, 0444, DMI_PRODUCT_VERSION);
DEFINE_DMI_ATTR_WITH_SHOW(product_serial, 0400, DMI_PRODUCT_SERIAL);
DEFINE_DMI_ATTR_WITH_SHOW(product_uuid, 0400, DMI_PRODUCT_UUID);
+DEFINE_DMI_ATTR_WITH_SHOW(product_family, 0400, DMI_PRODUCT_FAMILY);
DEFINE_DMI_ATTR_WITH_SHOW(board_vendor, 0444, DMI_BOARD_VENDOR);
DEFINE_DMI_ATTR_WITH_SHOW(board_name, 0444, DMI_BOARD_NAME);
DEFINE_DMI_ATTR_WITH_SHOW(board_version, 0444, DMI_BOARD_VERSION);
ADD_DMI_ATTR(product_version, DMI_PRODUCT_VERSION);
ADD_DMI_ATTR(product_serial, DMI_PRODUCT_SERIAL);
ADD_DMI_ATTR(product_uuid, DMI_PRODUCT_UUID);
+ ADD_DMI_ATTR(product_family, DMI_PRODUCT_FAMILY);
ADD_DMI_ATTR(board_vendor, DMI_BOARD_VENDOR);
ADD_DMI_ATTR(board_name, DMI_BOARD_NAME);
ADD_DMI_ATTR(board_version, DMI_BOARD_VERSION);
dmi_save_ident(dm, DMI_PRODUCT_VERSION, 6);
dmi_save_ident(dm, DMI_PRODUCT_SERIAL, 7);
dmi_save_uuid(dm, DMI_PRODUCT_UUID, 8);
+ dmi_save_ident(dm, DMI_PRODUCT_FAMILY, 26);
break;
case 2: /* Base Board Information */
dmi_save_ident(dm, DMI_BOARD_VENDOR, 4);
u32 size;
} __packed;
+static bool efi_bgrt_addr_valid(u64 addr)
+{
+ efi_memory_desc_t *md;
+
+ for_each_efi_memory_desc(md) {
+ u64 size;
+ u64 end;
+
+ if (md->type != EFI_BOOT_SERVICES_DATA)
+ continue;
+
+ size = md->num_pages << EFI_PAGE_SHIFT;
+ end = md->phys_addr + size;
+ if (addr >= md->phys_addr && addr < end)
+ return true;
+ }
+
+ return false;
+}
+
void __init efi_bgrt_init(struct acpi_table_header *table)
{
void *image;
if (acpi_disabled)
return;
+ if (!efi_enabled(EFI_MEMMAP))
+ return;
+
if (table->length < sizeof(bgrt_tab)) {
pr_notice("Ignoring BGRT: invalid length %u (expected %zu)\n",
table->length, sizeof(bgrt_tab));
goto out;
}
+ if (!efi_bgrt_addr_valid(bgrt->image_address)) {
+ pr_notice("Ignoring BGRT: invalid image address\n");
+ goto out;
+ }
image = early_memremap(bgrt->image_address, sizeof(bmp_header));
if (!image) {
pr_notice("Ignoring BGRT: failed to map image header memory\n");
if (sscanf(name, "dump-type%u-%u-%d-%lu-%c",
&record->type, &part, &cnt, &time, &data_type) == 5) {
record->id = generic_id(time, part, cnt);
+ record->part = part;
record->count = cnt;
record->time.tv_sec = time;
record->time.tv_nsec = 0;
} else if (sscanf(name, "dump-type%u-%u-%d-%lu",
&record->type, &part, &cnt, &time) == 4) {
record->id = generic_id(time, part, cnt);
+ record->part = part;
record->count = cnt;
record->time.tv_sec = time;
record->time.tv_nsec = 0;
* multiple logs, remains.
*/
record->id = generic_id(time, part, 0);
+ record->part = part;
record->count = 0;
record->time.tv_sec = time;
record->time.tv_nsec = 0;
efi_guid_t vendor = LINUX_EFI_CRASH_GUID;
int i, ret = 0;
+ record->time.tv_sec = get_seconds();
+ record->time.tv_nsec = 0;
+
+ record->id = generic_id(record->time.tv_sec, record->part,
+ record->count);
+
snprintf(name, sizeof(name), "dump-type%u-%u-%d-%lu-%c",
record->type, record->part, record->count,
- get_seconds(), record->compressed ? 'C' : 'D');
+ record->time.tv_sec, record->compressed ? 'C' : 'D');
for (i = 0; i < DUMP_NAME_LEN; i++)
efi_name[i] = name[i];
if (record->reason == KMSG_DUMP_OOPS)
efivar_run_worker();
- record->id = record->part;
return ret;
};
* holding multiple logs, remains.
*/
snprintf(name_old, sizeof(name_old), "dump-type%u-%u-%lu",
- ed->record->type, (unsigned int)ed->record->id,
+ ed->record->type, ed->record->part,
ed->record->time.tv_sec);
for (i = 0; i < DUMP_NAME_LEN; i++)
char name[DUMP_NAME_LEN];
efi_char16_t efi_name[DUMP_NAME_LEN];
int found, i;
- unsigned int part;
- do_div(record->id, 1000);
- part = do_div(record->id, 100);
snprintf(name, sizeof(name), "dump-type%u-%u-%d-%lu",
record->type, record->part, record->count,
record->time.tv_sec);
/* BIOS variables */
static const efi_guid_t efi_variable_guid = EFI_GLOBAL_VARIABLE_GUID;
-static const efi_char16_t const efi_SecureBoot_name[] = {
+static const efi_char16_t efi_SecureBoot_name[] = {
'S', 'e', 'c', 'u', 'r', 'e', 'B', 'o', 'o', 't', 0
};
-static const efi_char16_t const efi_SetupMode_name[] = {
+static const efi_char16_t efi_SetupMode_name[] = {
'S', 'e', 't', 'u', 'p', 'M', 'o', 'd', 'e', 0
};
return VPD_OK;
info = kzalloc(sizeof(*info), GFP_KERNEL);
- info->key = kzalloc(key_len + 1, GFP_KERNEL);
- if (!info->key)
+ if (!info)
return -ENOMEM;
+ info->key = kzalloc(key_len + 1, GFP_KERNEL);
+ if (!info->key) {
+ ret = -ENOMEM;
+ goto free_info;
+ }
memcpy(info->key, key, key_len);
info->value = value;
INIT_LIST_HEAD(&info->list);
- list_add_tail(&info->list, &sec->attribs);
ret = sysfs_create_bin_file(sec->kobj, &info->bin_attr);
- if (ret) {
- kfree(info->key);
- return ret;
- }
+ if (ret)
+ goto free_info_key;
+ list_add_tail(&info->list, &sec->attribs);
return 0;
+
+free_info_key:
+ kfree(info->key);
+free_info:
+ kfree(info);
+
+ return ret;
}
static void vpd_section_attrib_destroy(struct vpd_section *sec)
struct vpd_attrib_info *temp;
list_for_each_entry_safe(info, temp, &sec->attribs, list) {
- kfree(info->key);
sysfs_remove_bin_file(sec->kobj, &info->bin_attr);
+ kfree(info->key);
kfree(info);
}
}
{
if (sec->enabled) {
vpd_section_attrib_destroy(sec);
- kobject_del(sec->kobj);
+ kobject_put(sec->kobj);
sysfs_remove_bin_file(vpd_kobj, &sec->bin_attr);
kfree(sec->raw_name);
iounmap(sec->baseaddr);
{
vpd_section_destroy(&ro_vpd);
vpd_section_destroy(&rw_vpd);
- kobject_del(vpd_kobj);
+ kobject_put(vpd_kobj);
}
module_init(vpd_platform_init);
info->debug_buffer[info->debug_region_size] = 0;
info->d = debugfs_create_file(strncat(debug_name, dev_name(dev),
- sizeof(debug_name)),
+ sizeof(debug_name) -
+ sizeof("ti_sci_debug@")),
0444, NULL, info, &ti_sci_debug_fops);
if (IS_ERR(info->d))
return PTR_ERR(info->d);
int rc;
int i;
+ if (!gpio->clk)
+ return -EINVAL;
+
rc = usecs_to_cycles(gpio, usecs, &requested_cycles);
if (rc < 0) {
dev_warn(chip->parent, "Failed to convert %luus to cycles at %luHz: %d\n",
{
int reg;
- if (gpio == 94)
- return GPIOPANELCTL;
+ if (gpio >= CRYSTALCOVE_GPIO_NUM) {
+ /*
+ * Virtual GPIO called from ACPI, for now we only support
+ * the panel ctl.
+ */
+ switch (gpio) {
+ case 0x5e:
+ return GPIOPANELCTL;
+ default:
+ return -EOPNOTSUPP;
+ }
+ }
if (reg_type == CTRL_IN) {
if (gpio < 8)
static int crystalcove_gpio_dir_in(struct gpio_chip *chip, unsigned gpio)
{
struct crystalcove_gpio *cg = gpiochip_get_data(chip);
+ int reg = to_reg(gpio, CTRL_OUT);
- if (gpio > CRYSTALCOVE_VGPIO_NUM)
+ if (reg < 0)
return 0;
- return regmap_write(cg->regmap, to_reg(gpio, CTRL_OUT),
- CTLO_INPUT_SET);
+ return regmap_write(cg->regmap, reg, CTLO_INPUT_SET);
}
static int crystalcove_gpio_dir_out(struct gpio_chip *chip, unsigned gpio,
int value)
{
struct crystalcove_gpio *cg = gpiochip_get_data(chip);
+ int reg = to_reg(gpio, CTRL_OUT);
- if (gpio > CRYSTALCOVE_VGPIO_NUM)
+ if (reg < 0)
return 0;
- return regmap_write(cg->regmap, to_reg(gpio, CTRL_OUT),
- CTLO_OUTPUT_SET | value);
+ return regmap_write(cg->regmap, reg, CTLO_OUTPUT_SET | value);
}
static int crystalcove_gpio_get(struct gpio_chip *chip, unsigned gpio)
{
struct crystalcove_gpio *cg = gpiochip_get_data(chip);
- int ret;
unsigned int val;
+ int ret, reg = to_reg(gpio, CTRL_IN);
- if (gpio > CRYSTALCOVE_VGPIO_NUM)
+ if (reg < 0)
return 0;
- ret = regmap_read(cg->regmap, to_reg(gpio, CTRL_IN), &val);
+ ret = regmap_read(cg->regmap, reg, &val);
if (ret)
return ret;
unsigned gpio, int value)
{
struct crystalcove_gpio *cg = gpiochip_get_data(chip);
+ int reg = to_reg(gpio, CTRL_OUT);
- if (gpio > CRYSTALCOVE_VGPIO_NUM)
+ if (reg < 0)
return;
if (value)
- regmap_update_bits(cg->regmap, to_reg(gpio, CTRL_OUT), 1, 1);
+ regmap_update_bits(cg->regmap, reg, 1, 1);
else
- regmap_update_bits(cg->regmap, to_reg(gpio, CTRL_OUT), 1, 0);
+ regmap_update_bits(cg->regmap, reg, 1, 0);
}
static int crystalcove_irq_type(struct irq_data *data, unsigned type)
struct crystalcove_gpio *cg =
gpiochip_get_data(irq_data_get_irq_chip_data(data));
+ if (data->hwirq >= CRYSTALCOVE_GPIO_NUM)
+ return 0;
+
switch (type) {
case IRQ_TYPE_NONE:
cg->intcnt_value = CTLI_INTCNT_DIS;
struct crystalcove_gpio *cg =
gpiochip_get_data(irq_data_get_irq_chip_data(data));
- cg->set_irq_mask = false;
- cg->update |= UPDATE_IRQ_MASK;
+ if (data->hwirq < CRYSTALCOVE_GPIO_NUM) {
+ cg->set_irq_mask = false;
+ cg->update |= UPDATE_IRQ_MASK;
+ }
}
static void crystalcove_irq_mask(struct irq_data *data)
struct crystalcove_gpio *cg =
gpiochip_get_data(irq_data_get_irq_chip_data(data));
- cg->set_irq_mask = true;
- cg->update |= UPDATE_IRQ_MASK;
+ if (data->hwirq < CRYSTALCOVE_GPIO_NUM) {
+ cg->set_irq_mask = true;
+ cg->update |= UPDATE_IRQ_MASK;
+ }
}
static struct irq_chip crystalcove_irqchip = {
set = U32_MAX;
else
return -EINVAL;
- writel_relaxed(0, mvebu_gpioreg_blink_counter_select(mvchip));
+ writel_relaxed(set, mvebu_gpioreg_blink_counter_select(mvchip));
mvpwm = devm_kzalloc(dev, sizeof(struct mvebu_pwm), GFP_KERNEL);
if (!mvpwm)
mvpwm->chip.dev = dev;
mvpwm->chip.ops = &mvebu_pwm_ops;
mvpwm->chip.npwm = mvchip->chip.ngpio;
+ /*
+ * There may already be some PWM allocated, so we can't force
+ * mvpwm->chip.base to a fixed point like mvchip->chip.base.
+ * So, we let pwmchip_add() do the numbering and take the next free
+ * region.
+ */
+ mvpwm->chip.base = -1;
spin_lock_init(&mvpwm->lock);
void amdgpu_fbdev_restore_mode(struct amdgpu_device *adev)
{
- struct amdgpu_fbdev *afbdev = adev->mode_info.rfbdev;
+ struct amdgpu_fbdev *afbdev;
struct drm_fb_helper *fb_helper;
int ret;
+ if (!adev)
+ return;
+
+ afbdev = adev->mode_info.rfbdev;
+
if (!afbdev)
return;
mutex_unlock(&id_mgr->lock);
}
- if (gds_switch_needed) {
+ if (ring->funcs->emit_gds_switch && gds_switch_needed) {
id->gds_base = job->gds_base;
id->gds_size = job->gds_size;
id->gws_base = job->gws_base;
struct amdgpu_vm_id_manager *id_mgr = &adev->vm_manager.id_mgr[vmhub];
struct amdgpu_vm_id *id = &id_mgr->ids[vmid];
+ atomic64_set(&id->owner, 0);
id->gds_base = 0;
id->gds_size = 0;
id->gws_base = 0;
id->oa_size = 0;
}
+/**
+ * amdgpu_vm_reset_all_id - reset VMID to zero
+ *
+ * @adev: amdgpu device structure
+ *
+ * Reset VMID to force flush on next use
+ */
+void amdgpu_vm_reset_all_ids(struct amdgpu_device *adev)
+{
+ unsigned i, j;
+
+ for (i = 0; i < AMDGPU_MAX_VMHUBS; ++i) {
+ struct amdgpu_vm_id_manager *id_mgr =
+ &adev->vm_manager.id_mgr[i];
+
+ for (j = 1; j < id_mgr->num_ids; ++j)
+ amdgpu_vm_reset_id(adev, i, j);
+ }
+}
+
/**
* amdgpu_vm_bo_find - find the bo_va for a specific vm & bo
*
for (i = 0; i < AMDGPU_MAX_RINGS; ++i)
adev->vm_manager.seqno[i] = 0;
-
atomic_set(&adev->vm_manager.vm_pte_next_ring, 0);
atomic64_set(&adev->vm_manager.client_counter, 0);
spin_lock_init(&adev->vm_manager.prt_lock);
int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job);
void amdgpu_vm_reset_id(struct amdgpu_device *adev, unsigned vmhub,
unsigned vmid);
+void amdgpu_vm_reset_all_ids(struct amdgpu_device *adev);
int amdgpu_vm_update_directories(struct amdgpu_device *adev,
struct amdgpu_vm *vm);
int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
}
const struct ttm_mem_type_manager_func amdgpu_vram_mgr_func = {
- amdgpu_vram_mgr_init,
- amdgpu_vram_mgr_fini,
- amdgpu_vram_mgr_new,
- amdgpu_vram_mgr_del,
- amdgpu_vram_mgr_debug
+ .init = amdgpu_vram_mgr_init,
+ .takedown = amdgpu_vram_mgr_fini,
+ .get_node = amdgpu_vram_mgr_new,
+ .put_node = amdgpu_vram_mgr_del,
+ .debug = amdgpu_vram_mgr_debug
};
u32 vblank_time = amdgpu_dpm_get_vblank_time(adev);
u32 switch_limit = adev->mc.vram_type == AMDGPU_VRAM_TYPE_GDDR5 ? 450 : 300;
+ /* disable mclk switching if the refresh is >120Hz, even if the
+ * blanking period would allow it
+ */
+ if (amdgpu_dpm_get_vrefresh(adev) > 120)
+ return true;
+
if (vblank_time < switch_limit)
return true;
else
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- if (adev->vm_manager.enabled) {
- gmc_v6_0_vm_fini(adev);
- adev->vm_manager.enabled = false;
- }
gmc_v6_0_hw_fini(adev);
return 0;
if (r)
return r;
- if (!adev->vm_manager.enabled) {
- r = gmc_v6_0_vm_init(adev);
- if (r) {
- dev_err(adev->dev, "vm manager initialization failed (%d).\n", r);
- return r;
- }
- adev->vm_manager.enabled = true;
- }
+ amdgpu_vm_reset_all_ids(adev);
- return r;
+ return 0;
}
static bool gmc_v6_0_is_idle(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- if (adev->vm_manager.enabled) {
- gmc_v7_0_vm_fini(adev);
- adev->vm_manager.enabled = false;
- }
gmc_v7_0_hw_fini(adev);
return 0;
if (r)
return r;
- if (!adev->vm_manager.enabled) {
- r = gmc_v7_0_vm_init(adev);
- if (r) {
- dev_err(adev->dev, "vm manager initialization failed (%d).\n", r);
- return r;
- }
- adev->vm_manager.enabled = true;
- }
+ amdgpu_vm_reset_all_ids(adev);
- return r;
+ return 0;
}
static bool gmc_v7_0_is_idle(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- if (adev->vm_manager.enabled) {
- gmc_v8_0_vm_fini(adev);
- adev->vm_manager.enabled = false;
- }
gmc_v8_0_hw_fini(adev);
return 0;
if (r)
return r;
- if (!adev->vm_manager.enabled) {
- r = gmc_v8_0_vm_init(adev);
- if (r) {
- dev_err(adev->dev, "vm manager initialization failed (%d).\n", r);
- return r;
- }
- adev->vm_manager.enabled = true;
- }
+ amdgpu_vm_reset_all_ids(adev);
- return r;
+ return 0;
}
static bool gmc_v8_0_is_idle(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- if (adev->vm_manager.enabled) {
- gmc_v9_0_vm_fini(adev);
- adev->vm_manager.enabled = false;
- }
gmc_v9_0_hw_fini(adev);
return 0;
if (r)
return r;
- if (!adev->vm_manager.enabled) {
- r = gmc_v9_0_vm_init(adev);
- if (r) {
- dev_err(adev->dev,
- "vm manager initialization failed (%d).\n", r);
- return r;
- }
- adev->vm_manager.enabled = true;
- }
+ amdgpu_vm_reset_all_ids(adev);
- return r;
+ return 0;
}
static bool gmc_v9_0_is_idle(void *handle)
static uint64_t vce_v3_0_ring_get_rptr(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
+ u32 v;
+
+ mutex_lock(&adev->grbm_idx_mutex);
+ if (adev->vce.harvest_config == 0 ||
+ adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE1)
+ WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(0));
+ else if (adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE0)
+ WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(1));
if (ring == &adev->vce.ring[0])
- return RREG32(mmVCE_RB_RPTR);
+ v = RREG32(mmVCE_RB_RPTR);
else if (ring == &adev->vce.ring[1])
- return RREG32(mmVCE_RB_RPTR2);
+ v = RREG32(mmVCE_RB_RPTR2);
else
- return RREG32(mmVCE_RB_RPTR3);
+ v = RREG32(mmVCE_RB_RPTR3);
+
+ WREG32(mmGRBM_GFX_INDEX, mmGRBM_GFX_INDEX_DEFAULT);
+ mutex_unlock(&adev->grbm_idx_mutex);
+
+ return v;
}
/**
static uint64_t vce_v3_0_ring_get_wptr(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
+ u32 v;
+
+ mutex_lock(&adev->grbm_idx_mutex);
+ if (adev->vce.harvest_config == 0 ||
+ adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE1)
+ WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(0));
+ else if (adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE0)
+ WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(1));
if (ring == &adev->vce.ring[0])
- return RREG32(mmVCE_RB_WPTR);
+ v = RREG32(mmVCE_RB_WPTR);
else if (ring == &adev->vce.ring[1])
- return RREG32(mmVCE_RB_WPTR2);
+ v = RREG32(mmVCE_RB_WPTR2);
else
- return RREG32(mmVCE_RB_WPTR3);
+ v = RREG32(mmVCE_RB_WPTR3);
+
+ WREG32(mmGRBM_GFX_INDEX, mmGRBM_GFX_INDEX_DEFAULT);
+ mutex_unlock(&adev->grbm_idx_mutex);
+
+ return v;
}
/**
{
struct amdgpu_device *adev = ring->adev;
+ mutex_lock(&adev->grbm_idx_mutex);
+ if (adev->vce.harvest_config == 0 ||
+ adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE1)
+ WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(0));
+ else if (adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE0)
+ WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(1));
+
if (ring == &adev->vce.ring[0])
WREG32(mmVCE_RB_WPTR, lower_32_bits(ring->wptr));
else if (ring == &adev->vce.ring[1])
WREG32(mmVCE_RB_WPTR2, lower_32_bits(ring->wptr));
else
WREG32(mmVCE_RB_WPTR3, lower_32_bits(ring->wptr));
+
+ WREG32(mmGRBM_GFX_INDEX, mmGRBM_GFX_INDEX_DEFAULT);
+ mutex_unlock(&adev->grbm_idx_mutex);
}
static void vce_v3_0_override_vce_clock_gating(struct amdgpu_device *adev, bool override)
struct amdgpu_ring *ring;
int idx, r;
- ring = &adev->vce.ring[0];
- WREG32(mmVCE_RB_RPTR, lower_32_bits(ring->wptr));
- WREG32(mmVCE_RB_WPTR, lower_32_bits(ring->wptr));
- WREG32(mmVCE_RB_BASE_LO, ring->gpu_addr);
- WREG32(mmVCE_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
- WREG32(mmVCE_RB_SIZE, ring->ring_size / 4);
-
- ring = &adev->vce.ring[1];
- WREG32(mmVCE_RB_RPTR2, lower_32_bits(ring->wptr));
- WREG32(mmVCE_RB_WPTR2, lower_32_bits(ring->wptr));
- WREG32(mmVCE_RB_BASE_LO2, ring->gpu_addr);
- WREG32(mmVCE_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
- WREG32(mmVCE_RB_SIZE2, ring->ring_size / 4);
-
- ring = &adev->vce.ring[2];
- WREG32(mmVCE_RB_RPTR3, lower_32_bits(ring->wptr));
- WREG32(mmVCE_RB_WPTR3, lower_32_bits(ring->wptr));
- WREG32(mmVCE_RB_BASE_LO3, ring->gpu_addr);
- WREG32(mmVCE_RB_BASE_HI3, upper_32_bits(ring->gpu_addr));
- WREG32(mmVCE_RB_SIZE3, ring->ring_size / 4);
-
mutex_lock(&adev->grbm_idx_mutex);
for (idx = 0; idx < 2; ++idx) {
if (adev->vce.harvest_config & (1 << idx))
continue;
WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(idx));
+
+ /* Program instance 0 reg space for two instances or instance 0 case
+ program instance 1 reg space for only instance 1 available case */
+ if (idx != 1 || adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE0) {
+ ring = &adev->vce.ring[0];
+ WREG32(mmVCE_RB_RPTR, lower_32_bits(ring->wptr));
+ WREG32(mmVCE_RB_WPTR, lower_32_bits(ring->wptr));
+ WREG32(mmVCE_RB_BASE_LO, ring->gpu_addr);
+ WREG32(mmVCE_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
+ WREG32(mmVCE_RB_SIZE, ring->ring_size / 4);
+
+ ring = &adev->vce.ring[1];
+ WREG32(mmVCE_RB_RPTR2, lower_32_bits(ring->wptr));
+ WREG32(mmVCE_RB_WPTR2, lower_32_bits(ring->wptr));
+ WREG32(mmVCE_RB_BASE_LO2, ring->gpu_addr);
+ WREG32(mmVCE_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
+ WREG32(mmVCE_RB_SIZE2, ring->ring_size / 4);
+
+ ring = &adev->vce.ring[2];
+ WREG32(mmVCE_RB_RPTR3, lower_32_bits(ring->wptr));
+ WREG32(mmVCE_RB_WPTR3, lower_32_bits(ring->wptr));
+ WREG32(mmVCE_RB_BASE_LO3, ring->gpu_addr);
+ WREG32(mmVCE_RB_BASE_HI3, upper_32_bits(ring->gpu_addr));
+ WREG32(mmVCE_RB_SIZE3, ring->ring_size / 4);
+ }
+
vce_v3_0_mc_resume(adev, idx);
WREG32_FIELD(VCE_STATUS, JOB_BUSY, 1);
return sizeof(struct smu7_power_state);
}
+static int smu7_vblank_too_short(struct pp_hwmgr *hwmgr,
+ uint32_t vblank_time_us)
+{
+ struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
+ uint32_t switch_limit_us;
+
+ switch (hwmgr->chip_id) {
+ case CHIP_POLARIS10:
+ case CHIP_POLARIS11:
+ case CHIP_POLARIS12:
+ switch_limit_us = data->is_memory_gddr5 ? 190 : 150;
+ break;
+ default:
+ switch_limit_us = data->is_memory_gddr5 ? 450 : 150;
+ break;
+ }
+
+ if (vblank_time_us < switch_limit_us)
+ return true;
+ else
+ return false;
+}
static int smu7_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
struct pp_power_state *request_ps,
bool disable_mclk_switching;
bool disable_mclk_switching_for_frame_lock;
struct cgs_display_info info = {0};
+ struct cgs_mode_info mode_info = {0};
const struct phm_clock_and_voltage_limits *max_limits;
uint32_t i;
struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
int32_t count;
int32_t stable_pstate_sclk = 0, stable_pstate_mclk = 0;
+ info.mode_info = &mode_info;
data->battery_state = (PP_StateUILabel_Battery ==
request_ps->classification.ui_label);
cgs_get_active_displays_info(hwmgr->device, &info);
- /*TO DO result = PHM_CheckVBlankTime(hwmgr, &vblankTooShort);*/
-
minimum_clocks.engineClock = hwmgr->display_config.min_core_set_clock;
minimum_clocks.memoryClock = hwmgr->display_config.min_mem_set_clock;
PHM_PlatformCaps_DisableMclkSwitchingForFrameLock);
- disable_mclk_switching = (1 < info.display_count) ||
- disable_mclk_switching_for_frame_lock;
+ disable_mclk_switching = ((1 < info.display_count) ||
+ disable_mclk_switching_for_frame_lock ||
+ smu7_vblank_too_short(hwmgr, mode_info.vblank_time_us) ||
+ (mode_info.refresh_rate > 120));
sclk = smu7_ps->performance_levels[0].engine_clock;
mclk = smu7_ps->performance_levels[0].memory_clock;
enum pp_clock_type type, uint32_t mask)
{
struct vega10_hwmgr *data = (struct vega10_hwmgr *)(hwmgr->backend);
- uint32_t i;
+ int i;
if (hwmgr->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL)
return -EINVAL;
static struct phm_master_table_item
vega10_thermal_start_thermal_controller_master_list[] = {
- {NULL, tf_vega10_thermal_initialize},
- {NULL, tf_vega10_thermal_set_temperature_range},
- {NULL, tf_vega10_thermal_enable_alert},
+ { .tableFunction = tf_vega10_thermal_initialize },
+ { .tableFunction = tf_vega10_thermal_set_temperature_range },
+ { .tableFunction = tf_vega10_thermal_enable_alert },
/* We should restrict performance levels to low before we halt the SMC.
* On the other hand we are still in boot state when we do this
* so it would be pointless.
* If this assumption changes we have to revisit this table.
*/
- {NULL, tf_vega10_thermal_setup_fan_table},
- {NULL, tf_vega10_thermal_start_smc_fan_control},
- {NULL, NULL}
+ { .tableFunction = tf_vega10_thermal_setup_fan_table },
+ { .tableFunction = tf_vega10_thermal_start_smc_fan_control },
+ { }
};
static struct phm_master_table_header
static struct phm_master_table_item
vega10_thermal_set_temperature_range_master_list[] = {
- {NULL, tf_vega10_thermal_disable_alert},
- {NULL, tf_vega10_thermal_set_temperature_range},
- {NULL, tf_vega10_thermal_enable_alert},
- {NULL, NULL}
+ { .tableFunction = tf_vega10_thermal_disable_alert },
+ { .tableFunction = tf_vega10_thermal_set_temperature_range },
+ { .tableFunction = tf_vega10_thermal_enable_alert },
+ { }
};
struct phm_master_table_header
*/
#include <drm/drmP.h>
+#include <drm/drm_atomic.h>
#include <drm/drm_atomic_helper.h>
#include <drm/drm_crtc.h>
#include <drm/drm_crtc_helper.h>
static int hdlcd_plane_atomic_check(struct drm_plane *plane,
struct drm_plane_state *state)
{
- u32 src_w, src_h;
+ struct drm_rect clip = { 0 };
+ struct drm_crtc_state *crtc_state;
+ u32 src_h = state->src_h >> 16;
- src_w = state->src_w >> 16;
- src_h = state->src_h >> 16;
+ /* only the HDLCD_REG_FB_LINE_COUNT register has a limit */
+ if (src_h >= HDLCD_MAX_YRES) {
+ DRM_DEBUG_KMS("Invalid source width: %d\n", src_h);
+ return -EINVAL;
+ }
+
+ if (!state->fb || !state->crtc)
+ return 0;
- /* we can't do any scaling of the plane source */
- if ((src_w != state->crtc_w) || (src_h != state->crtc_h))
+ crtc_state = drm_atomic_get_existing_crtc_state(state->state,
+ state->crtc);
+ if (!crtc_state) {
+ DRM_DEBUG_KMS("Invalid crtc state\n");
return -EINVAL;
+ }
- return 0;
+ clip.x2 = crtc_state->adjusted_mode.hdisplay;
+ clip.y2 = crtc_state->adjusted_mode.vdisplay;
+
+ return drm_plane_helper_check_state(state, &clip,
+ DRM_PLANE_HELPER_NO_SCALING,
+ DRM_PLANE_HELPER_NO_SCALING,
+ false, true);
}
static void hdlcd_plane_atomic_update(struct drm_plane *plane,
struct drm_framebuffer *fb = plane->state->fb;
struct hdlcd_drm_private *hdlcd;
struct drm_gem_cma_object *gem;
- u32 src_w, src_h, dest_w, dest_h;
+ u32 src_x, src_y, dest_h;
dma_addr_t scanout_start;
if (!fb)
return;
- src_w = plane->state->src_w >> 16;
- src_h = plane->state->src_h >> 16;
- dest_w = plane->state->crtc_w;
- dest_h = plane->state->crtc_h;
+ src_x = plane->state->src.x1 >> 16;
+ src_y = plane->state->src.y1 >> 16;
+ dest_h = drm_rect_height(&plane->state->dst);
gem = drm_fb_cma_get_gem_obj(fb, 0);
+
scanout_start = gem->paddr + fb->offsets[0] +
- plane->state->crtc_y * fb->pitches[0] +
- plane->state->crtc_x *
- fb->format->cpp[0];
+ src_y * fb->pitches[0] +
+ src_x * fb->format->cpp[0];
hdlcd = plane->dev->dev_private;
hdlcd_write(hdlcd, HDLCD_REG_FB_LINE_LENGTH, fb->pitches[0]);
formats, ARRAY_SIZE(formats),
DRM_PLANE_TYPE_PRIMARY, NULL);
if (ret) {
- devm_kfree(drm->dev, plane);
return ERR_PTR(ret);
}
&hdlcd_crtc_funcs, NULL);
if (ret) {
hdlcd_plane_destroy(primary);
- devm_kfree(drm->dev, primary);
return ret;
}
.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
};
-static int atmel_hlcdc_attach_endpoint(struct drm_device *dev,
- const struct device_node *np)
+static int atmel_hlcdc_attach_endpoint(struct drm_device *dev, int endpoint)
{
struct atmel_hlcdc_dc *dc = dev->dev_private;
struct atmel_hlcdc_rgb_output *output;
struct drm_bridge *bridge;
int ret;
+ ret = drm_of_find_panel_or_bridge(dev->dev->of_node, 0, endpoint,
+ &panel, &bridge);
+ if (ret)
+ return ret;
+
output = devm_kzalloc(dev->dev, sizeof(*output), GFP_KERNEL);
if (!output)
return -EINVAL;
output->encoder.possible_crtcs = 0x1;
- ret = drm_of_find_panel_or_bridge(np, 0, 0, &panel, &bridge);
- if (ret)
- return ret;
-
if (panel) {
output->connector.dpms = DRM_MODE_DPMS_OFF;
output->connector.polled = DRM_CONNECTOR_POLL_CONNECT;
int atmel_hlcdc_create_outputs(struct drm_device *dev)
{
- struct device_node *remote;
- int ret = -ENODEV;
- int endpoint = 0;
-
- while (true) {
- /* Loop thru possible multiple connections to the output */
- remote = of_graph_get_remote_node(dev->dev->of_node, 0,
- endpoint++);
- if (!remote)
- break;
-
- ret = atmel_hlcdc_attach_endpoint(dev, remote);
- of_node_put(remote);
- if (ret)
- return ret;
- }
+ int endpoint, ret = 0;
+
+ for (endpoint = 0; !ret; endpoint++)
+ ret = atmel_hlcdc_attach_endpoint(dev, endpoint);
+
+ /* At least one device was successfully attached.*/
+ if (ret == -ENODEV && endpoint)
+ return 0;
return ret;
}
bool has_connectors =
!!new_crtc_state->connector_mask;
+ WARN_ON(!drm_modeset_is_locked(&crtc->mutex));
+
if (!drm_mode_equal(&old_crtc_state->mode, &new_crtc_state->mode)) {
DRM_DEBUG_ATOMIC("[CRTC:%d:%s] mode changed\n",
crtc->base.id, crtc->name);
for_each_oldnew_connector_in_state(state, connector, old_connector_state, new_connector_state, i) {
const struct drm_connector_helper_funcs *funcs = connector->helper_private;
+ WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex));
+
/*
* This only sets crtc->connectors_changed for routing changes,
* drivers must set crtc->connectors_changed themselves when
for_each_oldnew_plane_in_state(state, plane, old_plane_state, new_plane_state, i) {
const struct drm_plane_helper_funcs *funcs;
+ WARN_ON(!drm_modeset_is_locked(&plane->mutex));
+
funcs = plane->helper_private;
drm_atomic_helper_plane_changed(state, old_plane_state, new_plane_state, plane);
drm_modeset_acquire_init(&ctx, 0);
while (1) {
+ err = drm_modeset_lock_all_ctx(dev, &ctx);
+ if (err)
+ goto out;
+
err = drm_atomic_helper_commit_duplicated_state(state, &ctx);
+out:
if (err != -EDEADLK)
break;
return 0;
}
EXPORT_SYMBOL(drm_dp_stop_crc);
+
+struct dpcd_quirk {
+ u8 oui[3];
+ bool is_branch;
+ u32 quirks;
+};
+
+#define OUI(first, second, third) { (first), (second), (third) }
+
+static const struct dpcd_quirk dpcd_quirk_list[] = {
+ /* Analogix 7737 needs reduced M and N at HBR2 link rates */
+ { OUI(0x00, 0x22, 0xb9), true, BIT(DP_DPCD_QUIRK_LIMITED_M_N) },
+};
+
+#undef OUI
+
+/*
+ * Get a bit mask of DPCD quirks for the sink/branch device identified by
+ * ident. The quirk data is shared but it's up to the drivers to act on the
+ * data.
+ *
+ * For now, only the OUI (first three bytes) is used, but this may be extended
+ * to device identification string and hardware/firmware revisions later.
+ */
+static u32
+drm_dp_get_quirks(const struct drm_dp_dpcd_ident *ident, bool is_branch)
+{
+ const struct dpcd_quirk *quirk;
+ u32 quirks = 0;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(dpcd_quirk_list); i++) {
+ quirk = &dpcd_quirk_list[i];
+
+ if (quirk->is_branch != is_branch)
+ continue;
+
+ if (memcmp(quirk->oui, ident->oui, sizeof(ident->oui)) != 0)
+ continue;
+
+ quirks |= quirk->quirks;
+ }
+
+ return quirks;
+}
+
+/**
+ * drm_dp_read_desc - read sink/branch descriptor from DPCD
+ * @aux: DisplayPort AUX channel
+ * @desc: Device decriptor to fill from DPCD
+ * @is_branch: true for branch devices, false for sink devices
+ *
+ * Read DPCD 0x400 (sink) or 0x500 (branch) into @desc. Also debug log the
+ * identification.
+ *
+ * Returns 0 on success or a negative error code on failure.
+ */
+int drm_dp_read_desc(struct drm_dp_aux *aux, struct drm_dp_desc *desc,
+ bool is_branch)
+{
+ struct drm_dp_dpcd_ident *ident = &desc->ident;
+ unsigned int offset = is_branch ? DP_BRANCH_OUI : DP_SINK_OUI;
+ int ret, dev_id_len;
+
+ ret = drm_dp_dpcd_read(aux, offset, ident, sizeof(*ident));
+ if (ret < 0)
+ return ret;
+
+ desc->quirks = drm_dp_get_quirks(ident, is_branch);
+
+ dev_id_len = strnlen(ident->device_id, sizeof(ident->device_id));
+
+ DRM_DEBUG_KMS("DP %s: OUI %*phD dev-ID %*pE HW-rev %d.%d SW-rev %d.%d quirks 0x%04x\n",
+ is_branch ? "branch" : "sink",
+ (int)sizeof(ident->oui), ident->oui,
+ dev_id_len, ident->device_id,
+ ident->hw_rev >> 4, ident->hw_rev & 0xf,
+ ident->sw_major_rev, ident->sw_minor_rev,
+ desc->quirks);
+
+ return 0;
+}
+EXPORT_SYMBOL(drm_dp_read_desc);
void drm_unplug_dev(struct drm_device *dev)
{
/* for a USB device */
- drm_dev_unregister(dev);
+ if (drm_core_check_feature(dev, DRIVER_MODESET))
+ drm_modeset_unregister_all(dev);
+
+ drm_minor_unregister(dev, DRM_MINOR_PRIMARY);
+ drm_minor_unregister(dev, DRM_MINOR_RENDER);
+ drm_minor_unregister(dev, DRM_MINOR_CONTROL);
mutex_lock(&drm_global_mutex);
}
out:
- if (ret && crtc->funcs->page_flip_target)
- drm_crtc_vblank_put(crtc);
if (fb)
drm_framebuffer_put(fb);
if (crtc->primary->old_fb)
drm_modeset_drop_locks(&ctx);
drm_modeset_acquire_fini(&ctx);
+ if (ret && crtc->funcs->page_flip_target)
+ drm_crtc_vblank_put(crtc);
+
return ret;
}
/* initially, until copy_from_user() and bo lookup succeeds: */
submit->nr_bos = 0;
+ submit->fence = NULL;
ww_acquire_init(&submit->ticket, &reservation_ww_class);
}
}
ww_acquire_fini(&submit->ticket);
- dma_fence_put(submit->fence);
+ if (submit->fence)
+ dma_fence_put(submit->fence);
kfree(submit);
}
return ret;
}
-static void exynos_drm_preclose(struct drm_device *dev,
- struct drm_file *file)
-{
- exynos_drm_subdrv_close(dev, file);
-}
-
static void exynos_drm_postclose(struct drm_device *dev, struct drm_file *file)
{
+ exynos_drm_subdrv_close(dev, file);
kfree(file->driver_priv);
file->driver_priv = NULL;
}
.driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_PRIME
| DRIVER_ATOMIC | DRIVER_RENDER,
.open = exynos_drm_open,
- .preclose = exynos_drm_preclose,
.lastclose = exynos_drm_lastclose,
.postclose = exynos_drm_postclose,
.gem_free_object_unlocked = exynos_drm_gem_free_object,
* drm framework doesn't support multiple irq yet.
* we can refer to the crtc to current hardware interrupt occurred through
* this pipe value.
- * @enabled: if the crtc is enabled or not
- * @event: vblank event that is currently queued for flip
- * @wait_update: wait all pending planes updates to finish
- * @pending_update: number of pending plane updates in this crtc
* @ops: pointer to callbacks for exynos drm specific functionality
* @ctx: A pointer to the crtc's implementation specific context
+ * @pipe_clk: A pointer to the crtc's pipeline clock.
*/
struct exynos_drm_crtc {
struct drm_crtc base;
{
struct device *dev = dsi->dev;
struct device_node *node = dev->of_node;
- struct device_node *ep;
int ret;
ret = exynos_dsi_of_read_u32(node, "samsung,pll-clock-frequency",
if (ret < 0)
return ret;
- ep = of_graph_get_endpoint_by_regs(node, DSI_PORT_OUT, 0);
- if (!ep) {
- dev_err(dev, "no output port with endpoint specified\n");
- return -EINVAL;
- }
-
- ret = exynos_dsi_of_read_u32(ep, "samsung,burst-clock-frequency",
+ ret = exynos_dsi_of_read_u32(node, "samsung,burst-clock-frequency",
&dsi->burst_clk_rate);
if (ret < 0)
- goto end;
+ return ret;
- ret = exynos_dsi_of_read_u32(ep, "samsung,esc-clock-frequency",
+ ret = exynos_dsi_of_read_u32(node, "samsung,esc-clock-frequency",
&dsi->esc_clk_rate);
if (ret < 0)
- goto end;
-
- of_node_put(ep);
+ return ret;
dsi->bridge_node = of_graph_get_remote_node(node, DSI_PORT_OUT, 0);
if (!dsi->bridge_node)
return -EINVAL;
-end:
- of_node_put(ep);
-
- return ret;
+ return 0;
}
static int exynos_dsi_bind(struct device *dev, struct device *master,
static int exynos_dsi_remove(struct platform_device *pdev)
{
+ struct exynos_dsi *dsi = platform_get_drvdata(pdev);
+
+ of_node_put(dsi->bridge_node);
+
pm_runtime_disable(&pdev->dev);
component_del(&pdev->dev, &exynos_dsi_component_ops);
if (scan->type & DRM_MODE_TYPE_PREFERRED) {
mode_dev->panel_fixed_mode =
drm_mode_duplicate(dev, scan);
+ DRM_DEBUG_KMS("Using mode from DDC\n");
goto out; /* FIXME: check for quirks */
}
}
/* Failed to get EDID, what about VBT? do we need this? */
- if (mode_dev->vbt_mode)
+ if (dev_priv->lfp_lvds_vbt_mode) {
mode_dev->panel_fixed_mode =
- drm_mode_duplicate(dev, mode_dev->vbt_mode);
+ drm_mode_duplicate(dev, dev_priv->lfp_lvds_vbt_mode);
- if (!mode_dev->panel_fixed_mode)
- if (dev_priv->lfp_lvds_vbt_mode)
- mode_dev->panel_fixed_mode =
- drm_mode_duplicate(dev,
- dev_priv->lfp_lvds_vbt_mode);
+ if (mode_dev->panel_fixed_mode) {
+ mode_dev->panel_fixed_mode->type |=
+ DRM_MODE_TYPE_PREFERRED;
+ DRM_DEBUG_KMS("Using mode from VBT\n");
+ goto out;
+ }
+ }
/*
* If we didn't get EDID, try checking if the panel is already turned
if (mode_dev->panel_fixed_mode) {
mode_dev->panel_fixed_mode->type |=
DRM_MODE_TYPE_PREFERRED;
+ DRM_DEBUG_KMS("Using pre-programmed mode\n");
goto out; /* FIXME: check for quirks */
}
}
* Get the endpoint node. In our case, dsi has one output port1
* to which the external HDMI bridge is connected.
*/
- ret = drm_of_find_panel_or_bridge(np, 0, 0, NULL, &dsi->bridge);
+ ret = drm_of_find_panel_or_bridge(np, 1, 0, NULL, &dsi->bridge);
if (ret)
return ret;
vgpu_vreg(vgpu, ctx_status_ptr_reg) = ctx_status_ptr.dw;
}
+static void clean_workloads(struct intel_vgpu *vgpu, unsigned long engine_mask)
+{
+ struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
+ struct intel_engine_cs *engine;
+ struct intel_vgpu_workload *pos, *n;
+ unsigned int tmp;
+
+ /* free the unsubmited workloads in the queues. */
+ for_each_engine_masked(engine, dev_priv, engine_mask, tmp) {
+ list_for_each_entry_safe(pos, n,
+ &vgpu->workload_q_head[engine->id], list) {
+ list_del_init(&pos->list);
+ free_workload(pos);
+ }
+ }
+}
+
void intel_vgpu_clean_execlist(struct intel_vgpu *vgpu)
{
+ clean_workloads(vgpu, ALL_ENGINES);
kmem_cache_destroy(vgpu->workloads);
}
{
struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
struct intel_engine_cs *engine;
- struct intel_vgpu_workload *pos, *n;
unsigned int tmp;
- for_each_engine_masked(engine, dev_priv, engine_mask, tmp) {
- /* free the unsubmited workload in the queue */
- list_for_each_entry_safe(pos, n,
- &vgpu->workload_q_head[engine->id], list) {
- list_del_init(&pos->list);
- free_workload(pos);
- }
-
+ clean_workloads(vgpu, engine_mask);
+ for_each_engine_masked(engine, dev_priv, engine_mask, tmp)
init_vgpu_execlist(vgpu, engine->id);
- }
}
mode = vgpu_vreg(vgpu, offset);
if (GFX_MODE_BIT_SET_IN_MASK(mode, START_DMA)) {
- WARN_ONCE(1, "VM(%d): iGVT-g doesn't supporte GuC\n",
+ WARN_ONCE(1, "VM(%d): iGVT-g doesn't support GuC\n",
vgpu->id);
return 0;
}
void *p_data, unsigned int bytes)
{
struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
- i915_reg_t reg = {.reg = offset};
+ u32 v = *(u32 *)p_data;
+
+ if (!IS_SKYLAKE(dev_priv) && !IS_KABYLAKE(dev_priv))
+ return intel_vgpu_default_mmio_write(vgpu,
+ offset, p_data, bytes);
switch (offset) {
case 0x4ddc:
- vgpu_vreg(vgpu, offset) = 0x8000003c;
- /* WaCompressedResourceSamplerPbeMediaNewHashMode:skl */
- I915_WRITE(reg, vgpu_vreg(vgpu, offset));
+ /* bypass WaCompressedResourceSamplerPbeMediaNewHashMode */
+ vgpu_vreg(vgpu, offset) = v & ~(1 << 31);
break;
case 0x42080:
- vgpu_vreg(vgpu, offset) = 0x8000;
- /* WaCompressedResourceDisplayNewHashMode:skl */
- I915_WRITE(reg, vgpu_vreg(vgpu, offset));
+ /* bypass WaCompressedResourceDisplayNewHashMode */
+ vgpu_vreg(vgpu, offset) = v & ~(1 << 15);
+ break;
+ case 0xe194:
+ /* bypass WaCompressedResourceSamplerPbeMediaNewHashMode */
+ vgpu_vreg(vgpu, offset) = v & ~(1 << 8);
+ break;
+ case 0x7014:
+ /* bypass WaCompressedResourceSamplerPbeMediaNewHashMode */
+ vgpu_vreg(vgpu, offset) = v & ~(1 << 13);
break;
default:
return -EINVAL;
MMIO_DFH(GAM_ECOCHK, D_ALL, F_CMD_ACCESS, NULL, NULL);
MMIO_DFH(GEN7_COMMON_SLICE_CHICKEN1, D_ALL, F_MODE_MASK | F_CMD_ACCESS,
NULL, NULL);
- MMIO_DFH(COMMON_SLICE_CHICKEN2, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(COMMON_SLICE_CHICKEN2, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL,
+ skl_misc_ctl_write);
MMIO_DFH(0x9030, D_ALL, F_CMD_ACCESS, NULL, NULL);
MMIO_DFH(0x20a0, D_ALL, F_CMD_ACCESS, NULL, NULL);
MMIO_DFH(0x2420, D_ALL, F_CMD_ACCESS, NULL, NULL);
MMIO_D(0x6e570, D_BDW_PLUS);
MMIO_D(0x65f10, D_BDW_PLUS);
- MMIO_DFH(0xe194, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0xe194, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL,
+ skl_misc_ctl_write);
MMIO_DFH(0xe188, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
MMIO_DFH(HALF_SLICE_CHICKEN2, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
MMIO_DFH(0x2580, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
} else
v = mmio->value;
+ if (mmio->in_context)
+ continue;
+
I915_WRITE(mmio->reg, v);
POSTING_READ(mmio->reg);
struct vgpu_sched_data *vgpu_data;
ktime_t cur_time;
- /* no target to schedule */
- if (!scheduler->next_vgpu)
+ /* no need to schedule if next_vgpu is the same with current_vgpu,
+ * let scheduler chose next_vgpu again by setting it to NULL.
+ */
+ if (scheduler->next_vgpu == scheduler->current_vgpu) {
+ scheduler->next_vgpu = NULL;
return;
+ }
/*
* after the flag is set, workload dispatch thread will
goto out_fini;
pci_set_drvdata(pdev, &dev_priv->drm);
+ /*
+ * Disable the system suspend direct complete optimization, which can
+ * leave the device suspended skipping the driver's suspend handlers
+ * if the device was already runtime suspended. This is needed due to
+ * the difference in our runtime and system suspend sequence and
+ * becaue the HDA driver may require us to enable the audio power
+ * domain during system suspend.
+ */
+ pdev->dev_flags |= PCI_DEV_FLAGS_NEEDS_RESUME;
ret = i915_driver_init_early(dev_priv, ent);
if (ret < 0)
dev_priv->ipc_enabled = false;
- /* Everything is in place, we can now relax! */
- DRM_INFO("Initialized %s %d.%d.%d %s for %s on minor %d\n",
- driver.name, driver.major, driver.minor, driver.patchlevel,
- driver.date, pci_name(pdev), dev_priv->drm.primary->index);
if (IS_ENABLED(CONFIG_DRM_I915_DEBUG))
DRM_INFO("DRM_I915_DEBUG enabled\n");
if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
void intel_link_compute_m_n(int bpp, int nlanes,
int pixel_clock, int link_clock,
- struct intel_link_m_n *m_n);
+ struct intel_link_m_n *m_n,
+ bool reduce_m_n);
/* Interface history:
*
return false;
}
+static inline bool
+intel_ggtt_update_needs_vtd_wa(struct drm_i915_private *dev_priv)
+{
+#ifdef CONFIG_INTEL_IOMMU
+ if (IS_BROXTON(dev_priv) && intel_iommu_gfx_mapped)
+ return true;
+#endif
+ return false;
+}
+
int intel_sanitize_enable_ppgtt(struct drm_i915_private *dev_priv,
int enable_ppgtt);
{
int ret;
+ /* If the device is asleep, we have no requests outstanding */
+ if (!READ_ONCE(i915->gt.awake))
+ return 0;
+
if (flags & I915_WAIT_LOCKED) {
struct i915_gem_timeline *tl;
u32 pte_flags;
int ret;
- ret = vma->vm->allocate_va_range(vma->vm, vma->node.start, vma->size);
- if (ret)
- return ret;
+ if (!(vma->flags & I915_VMA_LOCAL_BIND)) {
+ ret = vma->vm->allocate_va_range(vma->vm, vma->node.start,
+ vma->size);
+ if (ret)
+ return ret;
+ }
vma->pages = vma->obj->mm.pages;
gen8_set_pte(>t_base[i], scratch_pte);
}
+static void bxt_vtd_ggtt_wa(struct i915_address_space *vm)
+{
+ struct drm_i915_private *dev_priv = vm->i915;
+
+ /*
+ * Make sure the internal GAM fifo has been cleared of all GTT
+ * writes before exiting stop_machine(). This guarantees that
+ * any aperture accesses waiting to start in another process
+ * cannot back up behind the GTT writes causing a hang.
+ * The register can be any arbitrary GAM register.
+ */
+ POSTING_READ(GFX_FLSH_CNTL_GEN6);
+}
+
+struct insert_page {
+ struct i915_address_space *vm;
+ dma_addr_t addr;
+ u64 offset;
+ enum i915_cache_level level;
+};
+
+static int bxt_vtd_ggtt_insert_page__cb(void *_arg)
+{
+ struct insert_page *arg = _arg;
+
+ gen8_ggtt_insert_page(arg->vm, arg->addr, arg->offset, arg->level, 0);
+ bxt_vtd_ggtt_wa(arg->vm);
+
+ return 0;
+}
+
+static void bxt_vtd_ggtt_insert_page__BKL(struct i915_address_space *vm,
+ dma_addr_t addr,
+ u64 offset,
+ enum i915_cache_level level,
+ u32 unused)
+{
+ struct insert_page arg = { vm, addr, offset, level };
+
+ stop_machine(bxt_vtd_ggtt_insert_page__cb, &arg, NULL);
+}
+
+struct insert_entries {
+ struct i915_address_space *vm;
+ struct sg_table *st;
+ u64 start;
+ enum i915_cache_level level;
+};
+
+static int bxt_vtd_ggtt_insert_entries__cb(void *_arg)
+{
+ struct insert_entries *arg = _arg;
+
+ gen8_ggtt_insert_entries(arg->vm, arg->st, arg->start, arg->level, 0);
+ bxt_vtd_ggtt_wa(arg->vm);
+
+ return 0;
+}
+
+static void bxt_vtd_ggtt_insert_entries__BKL(struct i915_address_space *vm,
+ struct sg_table *st,
+ u64 start,
+ enum i915_cache_level level,
+ u32 unused)
+{
+ struct insert_entries arg = { vm, st, start, level };
+
+ stop_machine(bxt_vtd_ggtt_insert_entries__cb, &arg, NULL);
+}
+
+struct clear_range {
+ struct i915_address_space *vm;
+ u64 start;
+ u64 length;
+};
+
+static int bxt_vtd_ggtt_clear_range__cb(void *_arg)
+{
+ struct clear_range *arg = _arg;
+
+ gen8_ggtt_clear_range(arg->vm, arg->start, arg->length);
+ bxt_vtd_ggtt_wa(arg->vm);
+
+ return 0;
+}
+
+static void bxt_vtd_ggtt_clear_range__BKL(struct i915_address_space *vm,
+ u64 start,
+ u64 length)
+{
+ struct clear_range arg = { vm, start, length };
+
+ stop_machine(bxt_vtd_ggtt_clear_range__cb, &arg, NULL);
+}
+
static void gen6_ggtt_clear_range(struct i915_address_space *vm,
u64 start, u64 length)
{
if (flags & I915_VMA_LOCAL_BIND) {
struct i915_hw_ppgtt *appgtt = i915->mm.aliasing_ppgtt;
- if (appgtt->base.allocate_va_range) {
+ if (!(vma->flags & I915_VMA_LOCAL_BIND) &&
+ appgtt->base.allocate_va_range) {
ret = appgtt->base.allocate_va_range(&appgtt->base,
vma->node.start,
- vma->node.size);
+ vma->size);
if (ret)
goto err_pages;
}
ggtt->base.insert_entries = gen8_ggtt_insert_entries;
+ /* Serialize GTT updates with aperture access on BXT if VT-d is on. */
+ if (intel_ggtt_update_needs_vtd_wa(dev_priv)) {
+ ggtt->base.insert_entries = bxt_vtd_ggtt_insert_entries__BKL;
+ ggtt->base.insert_page = bxt_vtd_ggtt_insert_page__BKL;
+ if (ggtt->base.clear_range != nop_clear_range)
+ ggtt->base.clear_range = bxt_vtd_ggtt_clear_range__BKL;
+ }
+
ggtt->invalidate = gen6_ggtt_invalidate;
return ggtt_probe_common(ggtt, size);
void i915_ggtt_disable_guc(struct drm_i915_private *i915)
{
- i915->ggtt.invalidate = gen6_ggtt_invalidate;
+ if (i915->ggtt.invalidate == guc_ggtt_invalidate)
+ i915->ggtt.invalidate = gen6_ggtt_invalidate;
}
void i915_gem_restore_gtt_mappings(struct drm_i915_private *dev_priv)
return;
mutex_unlock(&dev->struct_mutex);
-
- /* expedite the RCU grace period to free some request slabs */
- synchronize_rcu_expedited();
}
static bool any_vma_pinned(struct drm_i915_gem_object *obj)
I915_SHRINK_ACTIVE);
intel_runtime_pm_put(dev_priv);
- synchronize_rcu(); /* wait for our earlier RCU delayed slab frees */
-
return freed;
}
obj->mm.quirked = false;
}
if (!i915_gem_object_is_tiled(obj)) {
- GEM_BUG_ON(!obj->mm.quirked);
+ GEM_BUG_ON(obj->mm.quirked);
__i915_gem_object_pin_pages(obj);
obj->mm.quirked = true;
}
u32 pipestat_mask;
u32 enable_mask;
enum pipe pipe;
- u32 val;
pipestat_mask = PLANE_FLIP_DONE_INT_STATUS_VLV |
PIPE_CRC_DONE_INTERRUPT_STATUS;
enable_mask = I915_DISPLAY_PORT_INTERRUPT |
I915_DISPLAY_PIPE_A_EVENT_INTERRUPT |
- I915_DISPLAY_PIPE_B_EVENT_INTERRUPT;
+ I915_DISPLAY_PIPE_B_EVENT_INTERRUPT |
+ I915_LPE_PIPE_A_INTERRUPT |
+ I915_LPE_PIPE_B_INTERRUPT;
+
if (IS_CHERRYVIEW(dev_priv))
- enable_mask |= I915_DISPLAY_PIPE_C_EVENT_INTERRUPT;
+ enable_mask |= I915_DISPLAY_PIPE_C_EVENT_INTERRUPT |
+ I915_LPE_PIPE_C_INTERRUPT;
WARN_ON(dev_priv->irq_mask != ~0);
- val = (I915_LPE_PIPE_A_INTERRUPT |
- I915_LPE_PIPE_B_INTERRUPT |
- I915_LPE_PIPE_C_INTERRUPT);
-
- enable_mask |= val;
-
dev_priv->irq_mask = ~enable_mask;
GEN5_IRQ_INIT(VLV_, dev_priv->irq_mask, enable_mask);
static const struct intel_device_info intel_ironlake_m_info = {
GEN5_FEATURES,
.platform = INTEL_IRONLAKE,
- .is_mobile = 1,
+ .is_mobile = 1, .has_fbc = 1,
};
#define GEN6_FEATURES \
.has_hw_contexts = 1, \
.has_logical_ring_contexts = 1, \
.has_guc = 1, \
- .has_decoupled_mmio = 1, \
.has_aliasing_ppgtt = 1, \
.has_full_ppgtt = 1, \
.has_full_48bit_ppgtt = 1, \
#define CLKCFG_FSB_667 (3 << 0) /* hrawclk 166 */
#define CLKCFG_FSB_800 (2 << 0) /* hrawclk 200 */
#define CLKCFG_FSB_1067 (6 << 0) /* hrawclk 266 */
+#define CLKCFG_FSB_1067_ALT (0 << 0) /* hrawclk 266 */
#define CLKCFG_FSB_1333 (7 << 0) /* hrawclk 333 */
-/* Note, below two are guess */
-#define CLKCFG_FSB_1600 (4 << 0) /* hrawclk 400 */
-#define CLKCFG_FSB_1600_ALT (0 << 0) /* hrawclk 400 */
+/*
+ * Note that on at least on ELK the below value is reported for both
+ * 333 and 400 MHz BIOS FSB setting, but given that the gmch datasheet
+ * lists only 200/266/333 MHz FSB as supported let's decode it as 333 MHz.
+ */
+#define CLKCFG_FSB_1333_ALT (4 << 0) /* hrawclk 333 */
#define CLKCFG_FSB_MASK (7 << 0)
#define CLKCFG_MEM_533 (1 << 4)
#define CLKCFG_MEM_667 (2 << 4)
/* MIPI DSI registers */
-#define _MIPI_PORT(port, a, c) ((port) ? c : a) /* ports A and C only */
+#define _MIPI_PORT(port, a, c) (((port) == PORT_A) ? a : c) /* ports A and C only */
#define _MMIO_MIPI(port, a, c) _MMIO(_MIPI_PORT(port, a, c))
#define MIPIO_TXESC_CLK_DIV1 _MMIO(0x160004)
case CLKCFG_FSB_800:
return 200000;
case CLKCFG_FSB_1067:
+ case CLKCFG_FSB_1067_ALT:
return 266667;
case CLKCFG_FSB_1333:
+ case CLKCFG_FSB_1333_ALT:
return 333333;
- /* these two are just a guess; one of them might be right */
- case CLKCFG_FSB_1600:
- case CLKCFG_FSB_1600_ALT:
- return 400000;
default:
return 133333;
}
pipe_config->fdi_lanes = lane;
intel_link_compute_m_n(pipe_config->pipe_bpp, lane, fdi_dotclock,
- link_bw, &pipe_config->fdi_m_n);
+ link_bw, &pipe_config->fdi_m_n, false);
ret = ironlake_check_fdi_lanes(dev, intel_crtc->pipe, pipe_config);
if (ret == -EINVAL && pipe_config->pipe_bpp > 6*3) {
}
static void compute_m_n(unsigned int m, unsigned int n,
- uint32_t *ret_m, uint32_t *ret_n)
+ uint32_t *ret_m, uint32_t *ret_n,
+ bool reduce_m_n)
{
/*
* Reduce M/N as much as possible without loss in precision. Several DP
* values. The passed in values are more likely to have the least
* significant bits zero than M after rounding below, so do this first.
*/
- while ((m & 1) == 0 && (n & 1) == 0) {
- m >>= 1;
- n >>= 1;
+ if (reduce_m_n) {
+ while ((m & 1) == 0 && (n & 1) == 0) {
+ m >>= 1;
+ n >>= 1;
+ }
}
*ret_n = min_t(unsigned int, roundup_pow_of_two(n), DATA_LINK_N_MAX);
void
intel_link_compute_m_n(int bits_per_pixel, int nlanes,
int pixel_clock, int link_clock,
- struct intel_link_m_n *m_n)
+ struct intel_link_m_n *m_n,
+ bool reduce_m_n)
{
m_n->tu = 64;
compute_m_n(bits_per_pixel * pixel_clock,
link_clock * nlanes * 8,
- &m_n->gmch_m, &m_n->gmch_n);
+ &m_n->gmch_m, &m_n->gmch_n,
+ reduce_m_n);
compute_m_n(pixel_clock, link_clock,
- &m_n->link_m, &m_n->link_n);
+ &m_n->link_m, &m_n->link_n,
+ reduce_m_n);
}
static inline bool intel_panel_use_ssc(struct drm_i915_private *dev_priv)
* type. For DP ports it behaves like most other platforms, but on HDMI
* there's an extra 1 line difference. So we need to add two instead of
* one to the value.
+ *
+ * On VLV/CHV DSI the scanline counter would appear to increment
+ * approx. 1/3 of a scanline before start of vblank. Unfortunately
+ * that means we can't tell whether we're in vblank or not while
+ * we're on that particular line. We must still set scanline_offset
+ * to 1 so that the vblank timestamps come out correct when we query
+ * the scanline counter from within the vblank interrupt handler.
+ * However if queried just before the start of vblank we'll get an
+ * answer that's slightly in the future.
*/
if (IS_GEN2(dev_priv)) {
const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode;
DRM_DEBUG_KMS("common rates: %s\n", str);
}
-bool
-__intel_dp_read_desc(struct intel_dp *intel_dp, struct intel_dp_desc *desc)
-{
- u32 base = drm_dp_is_branch(intel_dp->dpcd) ? DP_BRANCH_OUI :
- DP_SINK_OUI;
-
- return drm_dp_dpcd_read(&intel_dp->aux, base, desc, sizeof(*desc)) ==
- sizeof(*desc);
-}
-
-bool intel_dp_read_desc(struct intel_dp *intel_dp)
-{
- struct intel_dp_desc *desc = &intel_dp->desc;
- bool oui_sup = intel_dp->dpcd[DP_DOWN_STREAM_PORT_COUNT] &
- DP_OUI_SUPPORT;
- int dev_id_len;
-
- if (!__intel_dp_read_desc(intel_dp, desc))
- return false;
-
- dev_id_len = strnlen(desc->device_id, sizeof(desc->device_id));
- DRM_DEBUG_KMS("DP %s: OUI %*phD%s dev-ID %*pE HW-rev %d.%d SW-rev %d.%d\n",
- drm_dp_is_branch(intel_dp->dpcd) ? "branch" : "sink",
- (int)sizeof(desc->oui), desc->oui, oui_sup ? "" : "(NS)",
- dev_id_len, desc->device_id,
- desc->hw_rev >> 4, desc->hw_rev & 0xf,
- desc->sw_major_rev, desc->sw_minor_rev);
-
- return true;
-}
-
static int rate_to_index(int find, const int *rates)
{
int i = 0;
int common_rates[DP_MAX_SUPPORTED_RATES] = {};
int common_len;
uint8_t link_bw, rate_select;
+ bool reduce_m_n = drm_dp_has_quirk(&intel_dp->desc,
+ DP_DPCD_QUIRK_LIMITED_M_N);
common_len = intel_dp_common_rates(intel_dp, common_rates);
intel_link_compute_m_n(bpp, lane_count,
adjusted_mode->crtc_clock,
pipe_config->port_clock,
- &pipe_config->dp_m_n);
+ &pipe_config->dp_m_n,
+ reduce_m_n);
if (intel_connector->panel.downclock_mode != NULL &&
dev_priv->drrs.type == SEAMLESS_DRRS_SUPPORT) {
intel_link_compute_m_n(bpp, lane_count,
intel_connector->panel.downclock_mode->clock,
pipe_config->port_clock,
- &pipe_config->dp_m2_n2);
+ &pipe_config->dp_m2_n2,
+ reduce_m_n);
}
/*
if (!intel_dp_read_dpcd(intel_dp))
return false;
- intel_dp_read_desc(intel_dp);
+ drm_dp_read_desc(&intel_dp->aux, &intel_dp->desc,
+ drm_dp_is_branch(intel_dp->dpcd));
if (intel_dp->dpcd[DP_DPCD_REV] >= 0x11)
dev_priv->no_aux_handshake = intel_dp->dpcd[DP_MAX_DOWNSPREAD] &
intel_dp_print_rates(intel_dp);
- intel_dp_read_desc(intel_dp);
+ drm_dp_read_desc(&intel_dp->aux, &intel_dp->desc,
+ drm_dp_is_branch(intel_dp->dpcd));
intel_dp_configure_mst(intel_dp);
int lane_count, slots;
const struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
int mst_pbn;
+ bool reduce_m_n = drm_dp_has_quirk(&intel_dp->desc,
+ DP_DPCD_QUIRK_LIMITED_M_N);
pipe_config->has_pch_encoder = false;
bpp = 24;
intel_link_compute_m_n(bpp, lane_count,
adjusted_mode->crtc_clock,
pipe_config->port_clock,
- &pipe_config->dp_m_n);
+ &pipe_config->dp_m_n,
+ reduce_m_n);
pipe_config->dp_m_n.tu = slots;
M2_N2
};
-struct intel_dp_desc {
- u8 oui[3];
- u8 device_id[6];
- u8 hw_rev;
- u8 sw_major_rev;
- u8 sw_minor_rev;
-} __packed;
-
struct intel_dp_compliance_data {
unsigned long edid;
uint8_t video_pattern;
/* Max link BW for the sink as per DPCD registers */
int max_sink_link_bw;
/* sink or branch descriptor */
- struct intel_dp_desc desc;
+ struct drm_dp_desc desc;
struct drm_dp_aux aux;
enum intel_display_power_domain aux_power_domain;
uint8_t train_set[4];
}
bool intel_dp_read_dpcd(struct intel_dp *intel_dp);
-bool __intel_dp_read_desc(struct intel_dp *intel_dp,
- struct intel_dp_desc *desc);
-bool intel_dp_read_desc(struct intel_dp *intel_dp);
int intel_dp_link_required(int pixel_clock, int bpp);
int intel_dp_max_data_rate(int max_link_clock, int max_lanes);
bool intel_digital_port_connected(struct drm_i915_private *dev_priv,
val |= (ULPS_STATE_ENTER | DEVICE_READY);
I915_WRITE(MIPI_DEVICE_READY(port), val);
- /* Wait for ULPS Not active */
+ /* Wait for ULPS active */
if (intel_wait_for_register(dev_priv,
- MIPI_CTRL(port), GLK_ULPS_NOT_ACTIVE,
- GLK_ULPS_NOT_ACTIVE, 20))
- DRM_ERROR("ULPS is still active\n");
+ MIPI_CTRL(port), GLK_ULPS_NOT_ACTIVE, 0, 20))
+ DRM_ERROR("ULPS not active\n");
/* Exit ULPS */
val = I915_READ(MIPI_DEVICE_READY(port));
return 0;
}
+static bool ring_is_idle(struct intel_engine_cs *engine)
+{
+ struct drm_i915_private *dev_priv = engine->i915;
+ bool idle = true;
+
+ intel_runtime_pm_get(dev_priv);
+
+ /* No bit for gen2, so assume the CS parser is idle */
+ if (INTEL_GEN(dev_priv) > 2 && !(I915_READ_MODE(engine) & MODE_IDLE))
+ idle = false;
+
+ intel_runtime_pm_put(dev_priv);
+
+ return idle;
+}
+
/**
* intel_engine_is_idle() - Report if the engine has finished process all work
* @engine: the intel_engine_cs
*/
bool intel_engine_is_idle(struct intel_engine_cs *engine)
{
- struct drm_i915_private *dev_priv = engine->i915;
-
/* Any inflight/incomplete requests? */
if (!i915_seqno_passed(intel_engine_get_seqno(engine),
intel_engine_last_submit(engine)))
return false;
/* Ring stopped? */
- if (INTEL_GEN(dev_priv) > 2 && !(I915_READ_MODE(engine) & MODE_IDLE))
+ if (!ring_is_idle(engine))
return false;
return true;
static void intel_fbc_get_plane_source_size(struct intel_fbc_state_cache *cache,
int *width, int *height)
{
- int w, h;
-
- if (drm_rotation_90_or_270(cache->plane.rotation)) {
- w = cache->plane.src_h;
- h = cache->plane.src_w;
- } else {
- w = cache->plane.src_w;
- h = cache->plane.src_h;
- }
-
if (width)
- *width = w;
+ *width = cache->plane.src_w;
if (height)
- *height = h;
+ *height = cache->plane.src_h;
}
static int intel_fbc_calculate_cfb_size(struct drm_i915_private *dev_priv,
cache->crtc.hsw_bdw_pixel_rate = crtc_state->pixel_rate;
cache->plane.rotation = plane_state->base.rotation;
+ /*
+ * Src coordinates are already rotated by 270 degrees for
+ * the 90/270 degree plane rotation cases (to match the
+ * GTT mapping), hence no need to account for rotation here.
+ */
cache->plane.src_w = drm_rect_width(&plane_state->base.src) >> 16;
cache->plane.src_h = drm_rect_height(&plane_state->base.src) >> 16;
cache->plane.visible = plane_state->base.visible;
#include <linux/acpi.h>
#include <linux/device.h>
#include <linux/pci.h>
+#include <linux/pm_runtime.h>
#include "i915_drv.h"
#include <linux/delay.h>
kfree(rsc);
+ pm_runtime_forbid(&platdev->dev);
+ pm_runtime_set_active(&platdev->dev);
+ pm_runtime_enable(&platdev->dev);
+
return platdev;
err:
static void lpe_audio_irq_unmask(struct irq_data *d)
{
- struct drm_i915_private *dev_priv = d->chip_data;
- unsigned long irqflags;
- u32 val = (I915_LPE_PIPE_A_INTERRUPT |
- I915_LPE_PIPE_B_INTERRUPT);
-
- if (IS_CHERRYVIEW(dev_priv))
- val |= I915_LPE_PIPE_C_INTERRUPT;
-
- spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
-
- dev_priv->irq_mask &= ~val;
- I915_WRITE(VLV_IIR, val);
- I915_WRITE(VLV_IIR, val);
- I915_WRITE(VLV_IMR, dev_priv->irq_mask);
- POSTING_READ(VLV_IMR);
-
- spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
}
static void lpe_audio_irq_mask(struct irq_data *d)
{
- struct drm_i915_private *dev_priv = d->chip_data;
- unsigned long irqflags;
- u32 val = (I915_LPE_PIPE_A_INTERRUPT |
- I915_LPE_PIPE_B_INTERRUPT);
-
- if (IS_CHERRYVIEW(dev_priv))
- val |= I915_LPE_PIPE_C_INTERRUPT;
-
- spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
-
- dev_priv->irq_mask |= val;
- I915_WRITE(VLV_IMR, dev_priv->irq_mask);
- I915_WRITE(VLV_IIR, val);
- I915_WRITE(VLV_IIR, val);
- POSTING_READ(VLV_IIR);
-
- spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
}
static struct irq_chip lpe_audio_irqchip = {
desc = irq_to_desc(dev_priv->lpe_audio.irq);
- lpe_audio_irq_mask(&desc->irq_data);
-
lpe_audio_platdev_destroy(dev_priv);
irq_free_desc(dev_priv->lpe_audio.irq);
ce->ring = ring;
ce->state = vma;
- ce->initialised = engine->init_context == NULL;
+ ce->initialised |= engine->init_context == NULL;
return 0;
return false;
}
- intel_dp_read_desc(dp);
+ drm_dp_read_desc(&dp->aux, &dp->desc, drm_dp_is_branch(dp->dpcd));
DRM_DEBUG_KMS("Success: LSPCON init\n");
return true;
struct drm_crtc_state *cstate;
struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
struct skl_wm_values *results = &intel_state->wm_results;
+ struct drm_device *dev = state->dev;
struct skl_pipe_wm *pipe_wm;
bool changed = false;
int ret, i;
+ /*
+ * When we distrust bios wm we always need to recompute to set the
+ * expected DDB allocations for each CRTC.
+ */
+ if (to_i915(dev)->wm.distrust_bios_wm)
+ changed = true;
+
/*
* If this transaction isn't actually touching any CRTC's, don't
* bother with watermark calculation. Note that if we pass this
*/
for_each_new_crtc_in_state(state, crtc, cstate, i)
changed = true;
+
if (!changed)
return 0;
}
/* PSR2 is restricted to work with panel resolutions upto 3200x2000 */
- if (intel_crtc->config->pipe_src_w > 3200 ||
- intel_crtc->config->pipe_src_h > 2000) {
+ if (dev_priv->psr.psr2_support &&
+ (intel_crtc->config->pipe_src_w > 3200 ||
+ intel_crtc->config->pipe_src_h > 2000)) {
dev_priv->psr.psr2_support = false;
return false;
}
*/
void intel_pipe_update_start(struct intel_crtc *crtc)
{
+ struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode;
long timeout = msecs_to_jiffies_timeout(1);
int scanline, min, max, vblank_start;
wait_queue_head_t *wq = drm_crtc_vblank_waitqueue(&crtc->base);
+ bool need_vlv_dsi_wa = (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) &&
+ intel_crtc_has_type(crtc->config, INTEL_OUTPUT_DSI);
DEFINE_WAIT(wait);
vblank_start = adjusted_mode->crtc_vblank_start;
drm_crtc_vblank_put(&crtc->base);
+ /*
+ * On VLV/CHV DSI the scanline counter would appear to
+ * increment approx. 1/3 of a scanline before start of vblank.
+ * The registers still get latched at start of vblank however.
+ * This means we must not write any registers on the first
+ * line of vblank (since not the whole line is actually in
+ * vblank). And unfortunately we can't use the interrupt to
+ * wait here since it will fire too soon. We could use the
+ * frame start interrupt instead since it will fire after the
+ * critical scanline, but that would require more changes
+ * in the interrupt code. So for now we'll just do the nasty
+ * thing and poll for the bad scanline to pass us by.
+ *
+ * FIXME figure out if BXT+ DSI suffers from this as well
+ */
+ while (need_vlv_dsi_wa && scanline == vblank_start)
+ scanline = intel_get_crtc_scanline(crtc);
+
crtc->debug.scanline_start = scanline;
crtc->debug.start_vbl_time = ktime_get();
crtc->debug.start_vbl_count = intel_crtc_get_vblank_counter(crtc);
* available in the work queue (note, the queue is shared,
* not per-engine). It is OK for this to be nonzero, but
* it should not be huge!
- * q_fail: failed to enqueue a work item. This should never happen,
- * because we check for space beforehand.
* b_fail: failed to ring the doorbell. This should never happen, unless
* somehow the hardware misbehaves, or maybe if the GuC firmware
* crashes? We probably need to reset the GPU to recover.
static int igt_ctx_exec(void *arg)
{
struct drm_i915_private *i915 = arg;
- struct drm_i915_gem_object *obj;
+ struct drm_i915_gem_object *obj = NULL;
struct drm_file *file;
IGT_TIMEOUT(end_time);
LIST_HEAD(objects);
}
for_each_engine(engine, i915, id) {
- if (dw == 0) {
+ if (!obj) {
obj = create_test_object(ctx, file, &objects);
if (IS_ERR(obj)) {
err = PTR_ERR(obj);
goto out_unlock;
}
- if (++dw == max_dwords(obj))
+ if (++dw == max_dwords(obj)) {
+ obj = NULL;
dw = 0;
+ }
ndwords++;
}
ncontexts++;
ret = drm_of_find_panel_or_bridge(child,
imx_ldb->lvds_mux ? 4 : 2, 0,
&channel->panel, &channel->bridge);
- if (ret)
+ if (ret && ret != -ENODEV)
return ret;
/* panel ddc only if there is no bridge */
#include <drm/drm_of.h>
#include <linux/clk.h>
#include <linux/component.h>
+#include <linux/iopoll.h>
#include <linux/irq.h>
#include <linux/of.h>
#include <linux/of_platform.h>
static void mtk_dsi_wait_for_idle(struct mtk_dsi *dsi)
{
- u32 timeout_ms = 500000; /* total 1s ~ 2s timeout */
-
- while (timeout_ms--) {
- if (!(readl(dsi->regs + DSI_INTSTA) & DSI_BUSY))
- break;
-
- usleep_range(2, 4);
- }
+ int ret;
+ u32 val;
- if (timeout_ms == 0) {
+ ret = readl_poll_timeout(dsi->regs + DSI_INTSTA, val, !(val & DSI_BUSY),
+ 4, 2000000);
+ if (ret) {
DRM_WARN("polling dsi wait not busy timeout!\n");
mtk_dsi_enable(dsi);
}
err = hdmi_vendor_infoframe_pack(&frame, buffer, sizeof(buffer));
- if (err) {
+ if (err < 0) {
dev_err(hdmi->dev, "Failed to pack vendor infoframe: %zd\n",
err);
return err;
.max_register = 0x1000,
};
-static int meson_drv_bind(struct device *dev)
+static int meson_drv_bind_master(struct device *dev, bool has_components)
{
struct platform_device *pdev = to_platform_device(dev);
struct meson_drm *priv;
if (ret)
goto free_drm;
- ret = component_bind_all(drm->dev, drm);
- if (ret) {
- dev_err(drm->dev, "Couldn't bind all components\n");
- goto free_drm;
+ if (has_components) {
+ ret = component_bind_all(drm->dev, drm);
+ if (ret) {
+ dev_err(drm->dev, "Couldn't bind all components\n");
+ goto free_drm;
+ }
}
ret = meson_plane_create(priv);
return ret;
}
+static int meson_drv_bind(struct device *dev)
+{
+ return meson_drv_bind_master(dev, true);
+}
+
static void meson_drv_unbind(struct device *dev)
{
struct drm_device *drm = dev_get_drvdata(dev);
count += meson_probe_remote(pdev, &match, np, remote);
}
+ if (count && !match)
+ return meson_drv_bind_master(&pdev->dev, false);
+
/* If some endpoints were found, initialize the nodes */
if (count) {
dev_info(&pdev->dev, "Queued %d outputs on vpu\n", count);
select QCOM_SCM
select SND_SOC_HDMI_CODEC if SND_SOC
select SYNC_FILE
+ select PM_OPP
default y
help
DRM/KMS driver for MSM/snapdragon.
return 0;
}
-static struct irq_domain_ops mdss_hw_irqdomain_ops = {
+static const struct irq_domain_ops mdss_hw_irqdomain_ops = {
.map = mdss_hw_irqdomain_map,
.xlate = irq_domain_xlate_onecell,
};
mdp5_state = kmemdup(to_mdp5_plane_state(plane->state),
sizeof(*mdp5_state), GFP_KERNEL);
+ if (!mdp5_state)
+ return NULL;
- if (mdp5_state && mdp5_state->base.fb)
- drm_framebuffer_reference(mdp5_state->base.fb);
+ __drm_atomic_helper_plane_duplicate_state(plane, &mdp5_state->base);
return &mdp5_state->base;
}
mdp5_pipe_release(state->state, old_hwpipe);
mdp5_pipe_release(state->state, old_right_hwpipe);
}
+ } else {
+ mdp5_pipe_release(state->state, mdp5_state->hwpipe);
+ mdp5_pipe_release(state->state, mdp5_state->r_hwpipe);
+ mdp5_state->hwpipe = mdp5_state->r_hwpipe = NULL;
}
return 0;
.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
.gem_prime_export = drm_gem_prime_export,
.gem_prime_import = drm_gem_prime_import,
+ .gem_prime_res_obj = msm_gem_prime_res_obj,
.gem_prime_pin = msm_gem_prime_pin,
.gem_prime_unpin = msm_gem_prime_unpin,
.gem_prime_get_sg_table = msm_gem_prime_get_sg_table,
void *msm_gem_prime_vmap(struct drm_gem_object *obj);
void msm_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr);
int msm_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma);
+struct reservation_object *msm_gem_prime_res_obj(struct drm_gem_object *obj);
struct drm_gem_object *msm_gem_prime_import_sg_table(struct drm_device *dev,
struct dma_buf_attachment *attach, struct sg_table *sg);
int msm_gem_prime_pin(struct drm_gem_object *obj);
}
struct msm_fence {
- struct msm_fence_context *fctx;
struct dma_fence base;
+ struct msm_fence_context *fctx;
};
static inline struct msm_fence *to_msm_fence(struct dma_fence *fence)
return fence_completed(f->fctx, f->base.seqno);
}
-static void msm_fence_release(struct dma_fence *fence)
-{
- struct msm_fence *f = to_msm_fence(fence);
- kfree_rcu(f, base.rcu);
-}
-
static const struct dma_fence_ops msm_fence_ops = {
.get_driver_name = msm_fence_get_driver_name,
.get_timeline_name = msm_fence_get_timeline_name,
.enable_signaling = msm_fence_enable_signaling,
.signaled = msm_fence_signaled,
.wait = dma_fence_default_wait,
- .release = msm_fence_release,
+ .release = dma_fence_free,
};
struct dma_fence *
struct msm_gem_object *msm_obj;
bool use_vram = false;
+ WARN_ON(!mutex_is_locked(&dev->struct_mutex));
+
switch (flags & MSM_BO_CACHE_MASK) {
case MSM_BO_UNCACHED:
case MSM_BO_CACHED:
size = PAGE_ALIGN(dmabuf->size);
+ /* Take mutex so we can modify the inactive list in msm_gem_new_impl */
+ mutex_lock(&dev->struct_mutex);
ret = msm_gem_new_impl(dev, size, MSM_BO_WC, dmabuf->resv, &obj);
+ mutex_unlock(&dev->struct_mutex);
+
if (ret)
goto fail;
if (!obj->import_attach)
msm_gem_put_pages(obj);
}
+
+struct reservation_object *msm_gem_prime_res_obj(struct drm_gem_object *obj)
+{
+ struct msm_gem_object *msm_obj = to_msm_bo(obj);
+
+ return msm_obj->resv;
+}
if (!in_fence)
return -EINVAL;
- /* TODO if we get an array-fence due to userspace merging multiple
- * fences, we need a way to determine if all the backing fences
- * are from our own context..
+ /*
+ * Wait if the fence is from a foreign context, or if the fence
+ * array contains any fence from a foreign context.
*/
-
- if (in_fence->context != gpu->fctx->context) {
+ if (!dma_fence_match_context(in_fence, gpu->fctx->context)) {
ret = dma_fence_wait(in_fence, true);
if (ret)
return ret;
goto out;
}
- if ((submit_cmd.size + submit_cmd.submit_offset) >=
- msm_obj->base.size) {
+ if (!submit_cmd.size ||
+ ((submit_cmd.size + submit_cmd.submit_offset) >
+ msm_obj->base.size)) {
DRM_ERROR("invalid cmdstream size: %u\n", submit_cmd.size);
ret = -EINVAL;
goto out;
gpu->grp_clks[i] = get_clock(dev, name);
/* Remember the key clocks that we need to control later */
- if (!strcmp(name, "core"))
+ if (!strcmp(name, "core") || !strcmp(name, "core_clk"))
gpu->core_clk = gpu->grp_clks[i];
- else if (!strcmp(name, "rbbmtimer"))
+ else if (!strcmp(name, "rbbmtimer") || !strcmp(name, "rbbmtimer_clk"))
gpu->rbbmtimer_clk = gpu->grp_clks[i];
++i;
struct nvkm_alarm {
struct list_head head;
+ struct list_head exec;
u64 timestamp;
void (*func)(struct nvkm_alarm *);
};
pm_runtime_get_sync(drm->dev->dev);
drm_helper_hpd_irq_event(drm->dev);
+ /* enable polling for external displays */
+ drm_kms_helper_poll_enable(drm->dev);
pm_runtime_mark_last_busy(drm->dev->dev);
pm_runtime_put_sync(drm->dev->dev);
if (ret)
return ret;
- /* enable polling for external displays */
- if (!dev->mode_config.poll_enabled)
- drm_kms_helper_poll_enable(dev);
-
/* enable hotplug interrupts */
list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
struct nouveau_connector *conn = nouveau_connector(connector);
module_param_named(modeset, nouveau_modeset, int, 0400);
MODULE_PARM_DESC(runpm, "disable (0), force enable (1), optimus only default (-1)");
-int nouveau_runtime_pm = -1;
+static int nouveau_runtime_pm = -1;
module_param_named(runpm, nouveau_runtime_pm, int, 0400);
static struct drm_driver driver_stub;
nouveau_fbcon_init(dev);
nouveau_led_init(dev);
- if (nouveau_runtime_pm != 0) {
+ if (nouveau_pmops_runtime()) {
pm_runtime_use_autosuspend(dev->dev);
pm_runtime_set_autosuspend_delay(dev->dev, 5000);
pm_runtime_set_active(dev->dev);
pm_runtime_allow(dev->dev);
pm_runtime_mark_last_busy(dev->dev);
pm_runtime_put(dev->dev);
+ } else {
+ /* enable polling for external displays */
+ drm_kms_helper_poll_enable(dev);
}
return 0;
{
struct nouveau_drm *drm = nouveau_drm(dev);
- if (nouveau_runtime_pm != 0) {
+ if (nouveau_pmops_runtime()) {
pm_runtime_get_sync(dev->dev);
pm_runtime_forbid(dev->dev);
}
return nouveau_do_resume(drm_dev, false);
}
+bool
+nouveau_pmops_runtime()
+{
+ if (nouveau_runtime_pm == -1)
+ return nouveau_is_optimus() || nouveau_is_v1_dsm();
+ return nouveau_runtime_pm == 1;
+}
+
static int
nouveau_pmops_runtime_suspend(struct device *dev)
{
struct drm_device *drm_dev = pci_get_drvdata(pdev);
int ret;
- if (nouveau_runtime_pm == 0) {
- pm_runtime_forbid(dev);
- return -EBUSY;
- }
-
- /* are we optimus enabled? */
- if (nouveau_runtime_pm == -1 && !nouveau_is_optimus() && !nouveau_is_v1_dsm()) {
- DRM_DEBUG_DRIVER("failing to power off - not optimus\n");
+ if (!nouveau_pmops_runtime()) {
pm_runtime_forbid(dev);
return -EBUSY;
}
struct nvif_device *device = &nouveau_drm(drm_dev)->client.device;
int ret;
- if (nouveau_runtime_pm == 0)
- return -EINVAL;
+ if (!nouveau_pmops_runtime()) {
+ pm_runtime_forbid(dev);
+ return -EBUSY;
+ }
pci_set_power_state(pdev, PCI_D0);
pci_restore_state(pdev);
ret = nouveau_do_resume(drm_dev, true);
- if (!drm_dev->mode_config.poll_enabled)
- drm_kms_helper_poll_enable(drm_dev);
-
/* do magic */
nvif_mask(&device->object, 0x088488, (1 << 25), (1 << 25));
vga_switcheroo_set_dynamic_switch(pdev, VGA_SWITCHEROO_ON);
struct nouveau_drm *drm = nouveau_drm(drm_dev);
struct drm_crtc *crtc;
- if (nouveau_runtime_pm == 0) {
- pm_runtime_forbid(dev);
- return -EBUSY;
- }
-
- /* are we optimus enabled? */
- if (nouveau_runtime_pm == -1 && !nouveau_is_optimus() && !nouveau_is_v1_dsm()) {
- DRM_DEBUG_DRIVER("failing to power off - not optimus\n");
+ if (!nouveau_pmops_runtime()) {
pm_runtime_forbid(dev);
return -EBUSY;
}
#include <nvif/object.h>
#include <nvif/device.h>
-extern int nouveau_runtime_pm;
-
struct nouveau_drm {
struct nouveau_cli client;
struct drm_device *dev;
int nouveau_pmops_suspend(struct device *);
int nouveau_pmops_resume(struct device *);
+bool nouveau_pmops_runtime(void);
#include <nvkm/core/tegra.h>
nouveau_vga_init(struct nouveau_drm *drm)
{
struct drm_device *dev = drm->dev;
- bool runtime = false;
+ bool runtime = nouveau_pmops_runtime();
/* only relevant for PCI devices */
if (!dev->pdev)
if (pci_is_thunderbolt_attached(dev->pdev))
return;
- if (nouveau_runtime_pm == 1)
- runtime = true;
- if ((nouveau_runtime_pm == -1) && (nouveau_is_optimus() || nouveau_is_v1_dsm()))
- runtime = true;
vga_switcheroo_register_client(dev->pdev, &nouveau_switcheroo_ops, runtime);
if (runtime && nouveau_is_v1_dsm() && !nouveau_is_optimus())
nouveau_vga_fini(struct nouveau_drm *drm)
{
struct drm_device *dev = drm->dev;
- bool runtime = false;
+ bool runtime = nouveau_pmops_runtime();
vga_client_register(dev->pdev, NULL, NULL, NULL);
if (pci_is_thunderbolt_attached(dev->pdev))
return;
- if (nouveau_runtime_pm == 1)
- runtime = true;
- if ((nouveau_runtime_pm == -1) && (nouveau_is_optimus() || nouveau_is_v1_dsm()))
- runtime = true;
-
vga_switcheroo_unregister_client(dev->pdev);
if (runtime && nouveau_is_v1_dsm() && !nouveau_is_optimus())
vga_switcheroo_fini_domain_pm_ops(drm->dev->dev);
asyc->set.dither = true;
}
} else {
- asyc->set.mask = ~0;
+ if (asyc)
+ asyc->set.mask = ~0;
asyh->set.mask = ~0;
}
case NVKM_MEM_TARGET_NCOH: target = 3; break;
default:
WARN_ON(1);
- return;
+ goto unlock;
}
nvkm_wr32(device, 0x002270, (nvkm_memory_addr(mem) >> 12) |
& 0x00100000),
msecs_to_jiffies(2000)) == 0)
nvkm_error(subdev, "runlist %d update timeout\n", runl);
+unlock:
mutex_unlock(&subdev->mutex);
}
ret = nvkm_firmware_get(subdev->device, f, &sig);
if (ret)
goto free_data;
+
img->sig = kmemdup(sig->data, sig->size, GFP_KERNEL);
if (!img->sig) {
ret = -ENOMEM;
img->ucode_data = ls_ucode_img_build(bl, code, data,
&img->ucode_desc);
if (IS_ERR(img->ucode_data)) {
+ kfree(img->sig);
ret = PTR_ERR(img->ucode_data);
- goto free_data;
+ goto free_sig;
}
img->ucode_size = img->ucode_desc.image_size;
/* Move to completed list. We'll drop the lock before
* executing the callback so it can reschedule itself.
*/
- list_move_tail(&alarm->head, &exec);
+ list_del_init(&alarm->head);
+ list_add(&alarm->exec, &exec);
}
/* Shut down interrupt if no more pending alarms. */
spin_unlock_irqrestore(&tmr->lock, flags);
/* Execute completed callbacks. */
- list_for_each_entry_safe(alarm, atemp, &exec, head) {
- list_del_init(&alarm->head);
+ list_for_each_entry_safe(alarm, atemp, &exec, exec) {
+ list_del(&alarm->exec);
alarm->func(alarm);
}
}
if (ret)
return;
- cmd = (struct qxl_cursor_cmd *) qxl_release_map(qdev, release);
-
if (fb != old_state->fb) {
obj = to_qxl_framebuffer(fb)->obj;
user_bo = gem_to_qxl_bo(obj);
qxl_bo_kunmap(cursor_bo);
qxl_bo_kunmap(user_bo);
+ cmd = (struct qxl_cursor_cmd *) qxl_release_map(qdev, release);
cmd->u.set.visible = 1;
cmd->u.set.shape = qxl_bo_physical_address(qdev,
cursor_bo, 0);
if (ret)
goto out_free_release;
+ cmd = (struct qxl_cursor_cmd *) qxl_release_map(qdev, release);
cmd->type = QXL_CURSOR_MOVE;
}
u32 vblank_time = r600_dpm_get_vblank_time(rdev);
u32 switch_limit = pi->mem_gddr5 ? 450 : 300;
+ /* disable mclk switching if the refresh is >120Hz, even if the
+ * blanking period would allow it
+ */
+ if (r600_dpm_get_vrefresh(rdev) > 120)
+ return true;
+
if (vblank_time < switch_limit)
return true;
else
WREG32(DC_HPD5_INT_CONTROL, tmp);
}
if (rdev->irq.stat_regs.cik.disp_int_cont5 & DC_HPD6_INTERRUPT) {
- tmp = RREG32(DC_HPD5_INT_CONTROL);
+ tmp = RREG32(DC_HPD6_INT_CONTROL);
tmp |= DC_HPDx_INT_ACK;
WREG32(DC_HPD6_INT_CONTROL, tmp);
}
WREG32(DC_HPD5_INT_CONTROL, tmp);
}
if (rdev->irq.stat_regs.cik.disp_int_cont5 & DC_HPD6_RX_INTERRUPT) {
- tmp = RREG32(DC_HPD5_INT_CONTROL);
+ tmp = RREG32(DC_HPD6_INT_CONTROL);
tmp |= DC_HPDx_RX_INT_ACK;
WREG32(DC_HPD6_INT_CONTROL, tmp);
}
WREG32(DC_HPD5_INT_CONTROL, tmp);
}
if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_INTERRUPT) {
- tmp = RREG32(DC_HPD5_INT_CONTROL);
+ tmp = RREG32(DC_HPD6_INT_CONTROL);
tmp |= DC_HPDx_INT_ACK;
WREG32(DC_HPD6_INT_CONTROL, tmp);
}
WREG32(DC_HPD5_INT_CONTROL, tmp);
}
if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_RX_INTERRUPT) {
- tmp = RREG32(DC_HPD5_INT_CONTROL);
+ tmp = RREG32(DC_HPD6_INT_CONTROL);
tmp |= DC_HPDx_RX_INT_ACK;
WREG32(DC_HPD6_INT_CONTROL, tmp);
}
WREG32(DC_HPD5_INT_CONTROL, tmp);
}
if (rdev->irq.stat_regs.r600.disp_int_cont2 & DC_HPD6_INTERRUPT) {
- tmp = RREG32(DC_HPD5_INT_CONTROL);
+ tmp = RREG32(DC_HPD6_INT_CONTROL);
tmp |= DC_HPDx_INT_ACK;
WREG32(DC_HPD6_INT_CONTROL, tmp);
}
if ((radeon_runtime_pm != 0) &&
radeon_has_atpx() &&
((flags & RADEON_IS_IGP) == 0) &&
- !pci_is_thunderbolt_attached(rdev->pdev))
+ !pci_is_thunderbolt_attached(dev->pdev))
flags |= RADEON_IS_PX;
/* radeon_device_init should report only fatal error
WREG32(DC_HPD5_INT_CONTROL, tmp);
}
if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_INTERRUPT) {
- tmp = RREG32(DC_HPD5_INT_CONTROL);
+ tmp = RREG32(DC_HPD6_INT_CONTROL);
tmp |= DC_HPDx_INT_ACK;
WREG32(DC_HPD6_INT_CONTROL, tmp);
}
WREG32(DC_HPD5_INT_CONTROL, tmp);
}
if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_RX_INTERRUPT) {
- tmp = RREG32(DC_HPD5_INT_CONTROL);
+ tmp = RREG32(DC_HPD6_INT_CONTROL);
tmp |= DC_HPDx_RX_INT_ACK;
WREG32(DC_HPD6_INT_CONTROL, tmp);
}
struct drm_connector_state *conn_state)
{
struct rockchip_crtc_state *s = to_rockchip_crtc_state(crtc_state);
- struct rockchip_dp_device *dp = to_dp(encoder);
- int ret;
/*
* The hardware IC designed that VOP must output the RGB10 video
s->output_mode = ROCKCHIP_OUT_MODE_AAAA;
s->output_type = DRM_MODE_CONNECTOR_eDP;
- if (dp->data->chip_type == RK3399_EDP) {
- /*
- * For RK3399, VOP Lit must code the out mode to RGB888,
- * VOP Big must code the out mode to RGB10.
- */
- ret = drm_of_encoder_active_endpoint_id(dp->dev->of_node,
- encoder);
- if (ret > 0)
- s->output_mode = ROCKCHIP_OUT_MODE_P888;
- }
return 0;
}
{
struct cdn_dp_device *dp = encoder_to_dp(encoder);
int ret, val;
- struct rockchip_crtc_state *state;
ret = drm_of_encoder_active_endpoint_id(dp->dev->of_node, encoder);
if (ret < 0) {
DRM_DEV_DEBUG_KMS(dp->dev, "vop %s output to cdn-dp\n",
(ret) ? "LIT" : "BIG");
- state = to_rockchip_crtc_state(encoder->crtc->state);
- if (ret) {
+ if (ret)
val = DP_SEL_VOP_LIT | (DP_SEL_VOP_LIT << 16);
- state->output_mode = ROCKCHIP_OUT_MODE_P888;
- } else {
+ else
val = DP_SEL_VOP_LIT << 16;
- state->output_mode = ROCKCHIP_OUT_MODE_AAAA;
- }
ret = cdn_dp_grf_write(dp, GRF_SOC_CON9, val);
if (ret)
static void vop_crtc_enable(struct drm_crtc *crtc)
{
struct vop *vop = to_vop(crtc);
+ const struct vop_data *vop_data = vop->data;
struct rockchip_crtc_state *s = to_rockchip_crtc_state(crtc->state);
struct drm_display_mode *adjusted_mode = &crtc->state->adjusted_mode;
u16 hsync_len = adjusted_mode->hsync_end - adjusted_mode->hsync_start;
DRM_DEV_ERROR(vop->dev, "unsupported connector_type [%d]\n",
s->output_type);
}
+
+ /*
+ * if vop is not support RGB10 output, need force RGB10 to RGB888.
+ */
+ if (s->output_mode == ROCKCHIP_OUT_MODE_AAAA &&
+ !(vop_data->feature & VOP_FEATURE_OUTPUT_RGB10))
+ s->output_mode = ROCKCHIP_OUT_MODE_P888;
VOP_CTRL_SET(vop, out_mode, s->output_mode);
VOP_CTRL_SET(vop, htotal_pw, (htotal << 16) | hsync_len);
const struct vop_intr *intr;
const struct vop_win_data *win;
unsigned int win_size;
+
+#define VOP_FEATURE_OUTPUT_RGB10 BIT(0)
+ u64 feature;
};
/* interrupt define */
static const struct vop_data rk3288_vop = {
.init_table = rk3288_init_reg_table,
.table_size = ARRAY_SIZE(rk3288_init_reg_table),
+ .feature = VOP_FEATURE_OUTPUT_RGB10,
.intr = &rk3288_vop_intr,
.ctrl = &rk3288_ctrl_data,
.win = rk3288_vop_win_data,
static const struct vop_data rk3399_vop_big = {
.init_table = rk3399_init_reg_table,
.table_size = ARRAY_SIZE(rk3399_init_reg_table),
+ .feature = VOP_FEATURE_OUTPUT_RGB10,
.intr = &rk3399_vop_intr,
.ctrl = &rk3399_ctrl_data,
/*
#include <drm/ttm/ttm_module.h>
#include "vmwgfx_fence.h"
-#define VMWGFX_DRIVER_DATE "20170221"
+#define VMWGFX_DRIVER_DATE "20170607"
#define VMWGFX_DRIVER_MAJOR 2
-#define VMWGFX_DRIVER_MINOR 12
+#define VMWGFX_DRIVER_MINOR 13
#define VMWGFX_DRIVER_PATCHLEVEL 0
#define VMWGFX_FILE_PAGE_OFFSET 0x00100000
#define VMWGFX_FIFO_STATIC_SIZE (1024*1024)
return fifo_state->static_buffer;
else {
fifo_state->dynamic_buffer = vmalloc(bytes);
+ if (!fifo_state->dynamic_buffer)
+ goto out_err;
return fifo_state->dynamic_buffer;
}
}
}
-
-/**
- * vmw_du_cursor_plane_update() - Update cursor image and location
- *
- * @plane: plane object to update
- * @crtc: owning CRTC of @plane
- * @fb: framebuffer to flip onto plane
- * @crtc_x: x offset of plane on crtc
- * @crtc_y: y offset of plane on crtc
- * @crtc_w: width of plane rectangle on crtc
- * @crtc_h: height of plane rectangle on crtc
- * @src_x: Not used
- * @src_y: Not used
- * @src_w: Not used
- * @src_h: Not used
- *
- *
- * RETURNS:
- * Zero on success, error code on failure
- */
-int vmw_du_cursor_plane_update(struct drm_plane *plane,
- struct drm_crtc *crtc,
- struct drm_framebuffer *fb,
- int crtc_x, int crtc_y,
- unsigned int crtc_w,
- unsigned int crtc_h,
- uint32_t src_x, uint32_t src_y,
- uint32_t src_w, uint32_t src_h)
-{
- struct vmw_private *dev_priv = vmw_priv(crtc->dev);
- struct vmw_display_unit *du = vmw_crtc_to_du(crtc);
- struct vmw_surface *surface = NULL;
- struct vmw_dma_buffer *dmabuf = NULL;
- s32 hotspot_x, hotspot_y;
- int ret;
-
- hotspot_x = du->hotspot_x + fb->hot_x;
- hotspot_y = du->hotspot_y + fb->hot_y;
-
- /* A lot of the code assumes this */
- if (crtc_w != 64 || crtc_h != 64) {
- ret = -EINVAL;
- goto out;
- }
-
- if (vmw_framebuffer_to_vfb(fb)->dmabuf)
- dmabuf = vmw_framebuffer_to_vfbd(fb)->buffer;
- else
- surface = vmw_framebuffer_to_vfbs(fb)->surface;
-
- if (surface && !surface->snooper.image) {
- DRM_ERROR("surface not suitable for cursor\n");
- ret = -EINVAL;
- goto out;
- }
-
- /* setup new image */
- ret = 0;
- if (surface) {
- /* vmw_user_surface_lookup takes one reference */
- du->cursor_surface = surface;
-
- du->cursor_age = du->cursor_surface->snooper.age;
-
- ret = vmw_cursor_update_image(dev_priv, surface->snooper.image,
- 64, 64, hotspot_x, hotspot_y);
- } else if (dmabuf) {
- /* vmw_user_surface_lookup takes one reference */
- du->cursor_dmabuf = dmabuf;
-
- ret = vmw_cursor_update_dmabuf(dev_priv, dmabuf, crtc_w, crtc_h,
- hotspot_x, hotspot_y);
- } else {
- vmw_cursor_update_position(dev_priv, false, 0, 0);
- goto out;
- }
-
- if (!ret) {
- du->cursor_x = crtc_x + du->set_gui_x;
- du->cursor_y = crtc_y + du->set_gui_y;
-
- vmw_cursor_update_position(dev_priv, true,
- du->cursor_x + hotspot_x,
- du->cursor_y + hotspot_y);
- }
-
-out:
- return ret;
-}
-
-
-int vmw_du_cursor_plane_disable(struct drm_plane *plane)
-{
- if (plane->fb) {
- drm_framebuffer_unreference(plane->fb);
- plane->fb = NULL;
- }
-
- return -EINVAL;
-}
-
-
void vmw_du_cursor_plane_destroy(struct drm_plane *plane)
{
vmw_cursor_update_position(plane->dev->dev_private, false, 0, 0);
}
-void
-vmw_du_cursor_plane_atomic_disable(struct drm_plane *plane,
- struct drm_plane_state *old_state)
-{
- struct drm_crtc *crtc = plane->state->crtc ?: old_state->crtc;
- struct vmw_private *dev_priv = vmw_priv(crtc->dev);
-
- drm_atomic_set_fb_for_plane(plane->state, NULL);
- vmw_cursor_update_position(dev_priv, false, 0, 0);
-}
-
-
void
vmw_du_cursor_plane_atomic_update(struct drm_plane *plane,
struct drm_plane_state *old_state)
*/
if (vmw_kms_srf_ok(dev_priv, mode_cmd->width, mode_cmd->height) &&
dmabuf && only_2d &&
+ mode_cmd->width > 64 && /* Don't create a proxy for cursor */
dev_priv->active_display_unit == vmw_du_screen_target) {
ret = vmw_create_dmabuf_proxy(dev_priv->dev, mode_cmd,
dmabuf, &surface);
u16 *r, u16 *g, u16 *b,
uint32_t size,
struct drm_modeset_acquire_ctx *ctx);
-int vmw_du_crtc_cursor_set2(struct drm_crtc *crtc, struct drm_file *file_priv,
- uint32_t handle, uint32_t width, uint32_t height,
- int32_t hot_x, int32_t hot_y);
-int vmw_du_crtc_cursor_move(struct drm_crtc *crtc, int x, int y);
int vmw_du_connector_set_property(struct drm_connector *connector,
struct drm_property *property,
uint64_t val);
/* Universal Plane Helpers */
void vmw_du_primary_plane_destroy(struct drm_plane *plane);
void vmw_du_cursor_plane_destroy(struct drm_plane *plane);
-int vmw_du_cursor_plane_disable(struct drm_plane *plane);
-int vmw_du_cursor_plane_update(struct drm_plane *plane,
- struct drm_crtc *crtc,
- struct drm_framebuffer *fb,
- int crtc_x, int crtc_y,
- unsigned int crtc_w,
- unsigned int crtc_h,
- uint32_t src_x, uint32_t src_y,
- uint32_t src_w, uint32_t src_h);
/* Atomic Helpers */
int vmw_du_primary_plane_atomic_check(struct drm_plane *plane,
struct drm_plane_state *state);
void vmw_du_cursor_plane_atomic_update(struct drm_plane *plane,
struct drm_plane_state *old_state);
-void vmw_du_cursor_plane_atomic_disable(struct drm_plane *plane,
- struct drm_plane_state *old_state);
int vmw_du_cursor_plane_prepare_fb(struct drm_plane *plane,
struct drm_plane_state *new_state);
void vmw_du_plane_cleanup_fb(struct drm_plane *plane,
* @right: Right side of bounding box.
* @top: Top side of bounding box.
* @bottom: Bottom side of bounding box.
+ * @fb_left: Left side of the framebuffer/content bounding box
+ * @fb_top: Top of the framebuffer/content bounding box
* @buf: DMA buffer when DMA-ing between buffer and screen targets.
* @sid: Surface ID when copying between surface and screen targets.
*/
struct vmw_kms_dirty base;
SVGA3dTransferType transfer;
s32 left, right, top, bottom;
+ s32 fb_left, fb_top;
u32 pitch;
union {
struct vmw_dma_buffer *buf;
*
* @dirty: The closure structure.
*
- * This function calculates the bounding box for all the incoming clips
+ * This function calculates the bounding box for all the incoming clips.
*/
static void vmw_stdu_dmabuf_cpu_clip(struct vmw_kms_dirty *dirty)
{
dirty->num_hits = 1;
- /* Calculate bounding box */
+ /* Calculate destination bounding box */
ddirty->left = min_t(s32, ddirty->left, dirty->unit_x1);
ddirty->top = min_t(s32, ddirty->top, dirty->unit_y1);
ddirty->right = max_t(s32, ddirty->right, dirty->unit_x2);
ddirty->bottom = max_t(s32, ddirty->bottom, dirty->unit_y2);
+
+ /*
+ * Calculate content bounding box. We only need the top-left
+ * coordinate because width and height will be the same as the
+ * destination bounding box above
+ */
+ ddirty->fb_left = min_t(s32, ddirty->fb_left, dirty->fb_x);
+ ddirty->fb_top = min_t(s32, ddirty->fb_top, dirty->fb_y);
}
/* Assume we are blitting from Host (display_srf) to Guest (dmabuf) */
src_pitch = stdu->display_srf->base_size.width * stdu->cpp;
src = ttm_kmap_obj_virtual(&stdu->host_map, ¬_used);
- src += dirty->unit_y1 * src_pitch + dirty->unit_x1 * stdu->cpp;
+ src += ddirty->top * src_pitch + ddirty->left * stdu->cpp;
dst_pitch = ddirty->pitch;
dst = ttm_kmap_obj_virtual(&stdu->guest_map, ¬_used);
- dst += dirty->fb_y * dst_pitch + dirty->fb_x * stdu->cpp;
+ dst += ddirty->fb_top * dst_pitch + ddirty->fb_left * stdu->cpp;
/* Figure out the real direction */
}
out_cleanup:
- ddirty->left = ddirty->top = S32_MAX;
+ ddirty->left = ddirty->top = ddirty->fb_left = ddirty->fb_top = S32_MAX;
ddirty->right = ddirty->bottom = S32_MIN;
}
SVGA3D_READ_HOST_VRAM;
ddirty.left = ddirty.top = S32_MAX;
ddirty.right = ddirty.bottom = S32_MIN;
+ ddirty.fb_left = ddirty.fb_top = S32_MAX;
ddirty.pitch = vfb->base.pitches[0];
ddirty.buf = buf;
ddirty.base.fifo_commit = vmw_stdu_dmabuf_fifo_commit;
DRM_ERROR("Failed to bind surface to STDU.\n");
else
crtc->primary->fb = plane->state->fb;
+
+ ret = vmw_stdu_update_st(dev_priv, stdu);
+
+ if (ret)
+ DRM_ERROR("Failed to update STDU.\n");
}
struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
int ret;
uint32_t size;
- uint32_t backup_handle;
+ uint32_t backup_handle = 0;
if (req->multisample_count != 0)
return -EINVAL;
+ if (req->mip_levels > DRM_VMW_MAX_MIP_LEVELS)
+ return -EINVAL;
+
if (unlikely(vmw_user_surface_size == 0))
vmw_user_surface_size = ttm_round_pot(sizeof(*user_srf)) +
128;
ret = vmw_user_dmabuf_lookup(tfile, req->buffer_handle,
&res->backup,
&user_srf->backup_base);
- if (ret == 0 && res->backup->base.num_pages * PAGE_SIZE <
- res->backup_size) {
- DRM_ERROR("Surface backup buffer is too small.\n");
- vmw_dmabuf_unreference(&res->backup);
- ret = -EINVAL;
- goto out_unlock;
+ if (ret == 0) {
+ if (res->backup->base.num_pages * PAGE_SIZE <
+ res->backup_size) {
+ DRM_ERROR("Surface backup buffer is too small.\n");
+ vmw_dmabuf_unreference(&res->backup);
+ ret = -EINVAL;
+ goto out_unlock;
+ } else {
+ backup_handle = req->buffer_handle;
+ }
}
} else if (req->drm_surface_flags & drm_vmw_surface_flag_create_buffer)
ret = vmw_user_dmabuf_alloc(dev_priv, tfile,
dev_priv->stdu_max_height);
if (size.width > max_width || size.height > max_height) {
- DRM_ERROR("%ux%u\n, exeeds max surface size %ux%u",
+ DRM_ERROR("%ux%u\n, exceeds max surface size %ux%u",
size.width, size.height,
max_width, max_height);
return -EINVAL;
config TEGRA_HOST1X
tristate "NVIDIA Tegra host1x driver"
depends on ARCH_TEGRA || (ARM && COMPILE_TEST)
+ select IOMMU_IOVA if IOMMU_SUPPORT
help
Driver for the NVIDIA Tegra host1x hardware.
spin_lock_irqsave(&ipu->lock, flags);
val = ipu_cm_read(ipu, IPU_CONF);
- if (vdi) {
+ if (vdi)
val |= IPU_CONF_IC_INPUT;
- } else {
+ else
val &= ~IPU_CONF_IC_INPUT;
- if (csi_id == 1)
- val |= IPU_CONF_CSI_SEL;
- else
- val &= ~IPU_CONF_CSI_SEL;
- }
+
+ if (csi_id == 1)
+ val |= IPU_CONF_CSI_SEL;
+ else
+ val &= ~IPU_CONF_CSI_SEL;
+
ipu_cm_write(ipu, val, IPU_CONF);
spin_unlock_irqrestore(&ipu->lock, flags);
if (pre->in_use)
return -EBUSY;
- clk_prepare_enable(pre->clk_axi);
-
/* first get the engine out of reset and remove clock gating */
writel(0, pre->regs + IPU_PRE_CTRL);
void ipu_pre_put(struct ipu_pre *pre)
{
- u32 val;
-
- val = IPU_PRE_CTRL_SFTRST | IPU_PRE_CTRL_CLKGATE;
- writel(val, pre->regs + IPU_PRE_CTRL);
-
- clk_disable_unprepare(pre->clk_axi);
+ writel(IPU_PRE_CTRL_SFTRST, pre->regs + IPU_PRE_CTRL);
pre->in_use = false;
}
if (!pre->buffer_virt)
return -ENOMEM;
+ clk_prepare_enable(pre->clk_axi);
+
pre->dev = dev;
platform_set_drvdata(pdev, pre);
mutex_lock(&ipu_pre_list_mutex);
available_pres--;
mutex_unlock(&ipu_pre_list_mutex);
+ clk_disable_unprepare(pre->clk_axi);
+
if (pre->buffer_virt)
gen_pool_free(pre->iram, (unsigned long)pre->buffer_virt,
IPU_PRE_MAX_WIDTH * IPU_PRE_NUM_SCANLINES * 4);
- Trio Linker Plus II
config HID_ELECOM
- tristate "ELECOM BM084 bluetooth mouse"
+ tristate "ELECOM HID devices"
depends on HID
---help---
- Support for the ELECOM BM084 (bluetooth mouse).
+ Support for ELECOM devices:
+ - BM084 Bluetooth Mouse
+ - DEFT Trackball (Wired and wireless)
config HID_ELO
tristate "ELO USB 4000/4500 touchscreen"
#define QUIRK_IS_MULTITOUCH BIT(3)
#define QUIRK_NO_CONSUMER_USAGES BIT(4)
#define QUIRK_USE_KBD_BACKLIGHT BIT(5)
+#define QUIRK_T100_KEYBOARD BIT(6)
#define I2C_KEYBOARD_QUIRKS (QUIRK_FIX_NOTEBOOK_REPORT | \
QUIRK_NO_INIT_REPORTS | \
drvdata->kbd_backlight->removed = true;
cancel_work_sync(&drvdata->kbd_backlight->work);
}
+
+ hid_hw_stop(hdev);
}
static __u8 *asus_report_fixup(struct hid_device *hdev, __u8 *rdesc,
hid_info(hdev, "Fixing up Asus notebook report descriptor\n");
rdesc[55] = 0xdd;
}
+ if (drvdata->quirks & QUIRK_T100_KEYBOARD &&
+ *rsize == 76 && rdesc[73] == 0x81 && rdesc[74] == 0x01) {
+ hid_info(hdev, "Fixing up Asus T100 keyb report descriptor\n");
+ rdesc[74] &= ~HID_MAIN_ITEM_CONSTANT;
+ }
+
return rdesc;
}
USB_DEVICE_ID_ASUSTEK_ROG_KEYBOARD1) },
{ HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK,
USB_DEVICE_ID_ASUSTEK_ROG_KEYBOARD2), QUIRK_USE_KBD_BACKLIGHT },
+ { HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK,
+ USB_DEVICE_ID_ASUSTEK_T100_KEYBOARD),
+ QUIRK_T100_KEYBOARD | QUIRK_NO_CONSUMER_USAGES },
{ }
};
MODULE_DEVICE_TABLE(hid, asus_devices);
{ HID_I2C_DEVICE(USB_VENDOR_ID_ASUSTEK, USB_DEVICE_ID_ASUSTEK_I2C_TOUCHPAD) },
{ HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK, USB_DEVICE_ID_ASUSTEK_ROG_KEYBOARD1) },
{ HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK, USB_DEVICE_ID_ASUSTEK_ROG_KEYBOARD2) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK, USB_DEVICE_ID_ASUSTEK_T100_KEYBOARD) },
{ HID_USB_DEVICE(USB_VENDOR_ID_AUREAL, USB_DEVICE_ID_AUREAL_W01RN) },
{ HID_USB_DEVICE(USB_VENDOR_ID_BELKIN, USB_DEVICE_ID_FLIP_KVM) },
{ HID_USB_DEVICE(USB_VENDOR_ID_BETOP_2185BFM, 0x2208) },
{ HID_USB_DEVICE(USB_VENDOR_ID_DREAM_CHEEKY, USB_DEVICE_ID_DREAM_CHEEKY_WN) },
{ HID_USB_DEVICE(USB_VENDOR_ID_DREAM_CHEEKY, USB_DEVICE_ID_DREAM_CHEEKY_FA) },
{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_BM084) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_DEFT_WIRED) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_DEFT_WIRELESS) },
{ HID_USB_DEVICE(USB_VENDOR_ID_ELO, 0x0009) },
{ HID_USB_DEVICE(USB_VENDOR_ID_ELO, 0x0030) },
{ HID_USB_DEVICE(USB_VENDOR_ID_ELO, USB_DEVICE_ID_ELO_ACCUTOUCH_2216) },
/*
- * HID driver for Elecom BM084 (bluetooth mouse).
- * Removes a non-existing horizontal wheel from
- * the HID descriptor.
- * (This module is based on "hid-ortek".)
- *
+ * HID driver for ELECOM devices.
* Copyright (c) 2010 Richard Nauber <Richard.Nauber@gmail.com>
+ * Copyright (c) 2016 Yuxuan Shui <yshuiv7@gmail.com>
+ * Copyright (c) 2017 Diego Elio Pettenò <flameeyes@flameeyes.eu>
*/
/*
static __u8 *elecom_report_fixup(struct hid_device *hdev, __u8 *rdesc,
unsigned int *rsize)
{
- if (*rsize >= 48 && rdesc[46] == 0x05 && rdesc[47] == 0x0c) {
- hid_info(hdev, "Fixing up Elecom BM084 report descriptor\n");
- rdesc[47] = 0x00;
+ switch (hdev->product) {
+ case USB_DEVICE_ID_ELECOM_BM084:
+ /* The BM084 Bluetooth mouse includes a non-existing horizontal
+ * wheel in the HID descriptor. */
+ if (*rsize >= 48 && rdesc[46] == 0x05 && rdesc[47] == 0x0c) {
+ hid_info(hdev, "Fixing up Elecom BM084 report descriptor\n");
+ rdesc[47] = 0x00;
+ }
+ break;
+ case USB_DEVICE_ID_ELECOM_DEFT_WIRED:
+ case USB_DEVICE_ID_ELECOM_DEFT_WIRELESS:
+ /* The DEFT trackball has eight buttons, but its descriptor only
+ * reports five, disabling the three Fn buttons on the top of
+ * the mouse.
+ *
+ * Apply the following diff to the descriptor:
+ *
+ * Collection (Physical), Collection (Physical),
+ * Report ID (1), Report ID (1),
+ * Report Count (5), -> Report Count (8),
+ * Report Size (1), Report Size (1),
+ * Usage Page (Button), Usage Page (Button),
+ * Usage Minimum (01h), Usage Minimum (01h),
+ * Usage Maximum (05h), -> Usage Maximum (08h),
+ * Logical Minimum (0), Logical Minimum (0),
+ * Logical Maximum (1), Logical Maximum (1),
+ * Input (Variable), Input (Variable),
+ * Report Count (1), -> Report Count (0),
+ * Report Size (3), Report Size (3),
+ * Input (Constant), Input (Constant),
+ * Report Size (16), Report Size (16),
+ * Report Count (2), Report Count (2),
+ * Usage Page (Desktop), Usage Page (Desktop),
+ * Usage (X), Usage (X),
+ * Usage (Y), Usage (Y),
+ * Logical Minimum (-32768), Logical Minimum (-32768),
+ * Logical Maximum (32767), Logical Maximum (32767),
+ * Input (Variable, Relative), Input (Variable, Relative),
+ * End Collection, End Collection,
+ */
+ if (*rsize == 213 && rdesc[13] == 5 && rdesc[21] == 5) {
+ hid_info(hdev, "Fixing up Elecom DEFT Fn buttons\n");
+ rdesc[13] = 8; /* Button/Variable Report Count */
+ rdesc[21] = 8; /* Button/Variable Usage Maximum */
+ rdesc[29] = 0; /* Button/Constant Report Count */
+ }
+ break;
}
return rdesc;
}
static const struct hid_device_id elecom_devices[] = {
- { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_BM084)},
+ { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_BM084) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_DEFT_WIRED) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_DEFT_WIRELESS) },
{ }
};
MODULE_DEVICE_TABLE(hid, elecom_devices);
#define USB_VENDOR_ID_ASUSTEK 0x0b05
#define USB_DEVICE_ID_ASUSTEK_LCM 0x1726
#define USB_DEVICE_ID_ASUSTEK_LCM2 0x175b
+#define USB_DEVICE_ID_ASUSTEK_T100_KEYBOARD 0x17e0
#define USB_DEVICE_ID_ASUSTEK_I2C_KEYBOARD 0x8585
#define USB_DEVICE_ID_ASUSTEK_I2C_TOUCHPAD 0x0101
#define USB_DEVICE_ID_ASUSTEK_ROG_KEYBOARD1 0x1854
#define USB_VENDOR_ID_ELECOM 0x056e
#define USB_DEVICE_ID_ELECOM_BM084 0x0061
+#define USB_DEVICE_ID_ELECOM_DEFT_WIRED 0x00fe
+#define USB_DEVICE_ID_ELECOM_DEFT_WIRELESS 0x00ff
#define USB_VENDOR_ID_DREAM_CHEEKY 0x1d34
#define USB_DEVICE_ID_DREAM_CHEEKY_WN 0x0004
if (input->id.product == USB_DEVICE_ID_APPLE_MAGICMOUSE) {
magicmouse_emit_buttons(msc, clicks & 3);
+ input_mt_report_pointer_emulation(input, true);
input_report_rel(input, REL_X, x);
input_report_rel(input, REL_Y, y);
} else { /* USB_DEVICE_ID_APPLE_MAGICTRACKPAD */
__clear_bit(BTN_RIGHT, input->keybit);
__clear_bit(BTN_MIDDLE, input->keybit);
__set_bit(BTN_MOUSE, input->keybit);
- __set_bit(BTN_TOOL_FINGER, input->keybit);
- __set_bit(BTN_TOOL_DOUBLETAP, input->keybit);
- __set_bit(BTN_TOOL_TRIPLETAP, input->keybit);
- __set_bit(BTN_TOOL_QUADTAP, input->keybit);
- __set_bit(BTN_TOOL_QUINTTAP, input->keybit);
- __set_bit(BTN_TOUCH, input->keybit);
- __set_bit(INPUT_PROP_POINTER, input->propbit);
__set_bit(INPUT_PROP_BUTTONPAD, input->propbit);
}
+ __set_bit(BTN_TOOL_FINGER, input->keybit);
+ __set_bit(BTN_TOOL_DOUBLETAP, input->keybit);
+ __set_bit(BTN_TOOL_TRIPLETAP, input->keybit);
+ __set_bit(BTN_TOOL_QUADTAP, input->keybit);
+ __set_bit(BTN_TOOL_QUINTTAP, input->keybit);
+ __set_bit(BTN_TOUCH, input->keybit);
+ __set_bit(INPUT_PROP_POINTER, input->propbit);
__set_bit(EV_ABS, input->evbit);
return 0;
}
+static void i2c_hid_acpi_fix_up_power(struct device *dev)
+{
+ acpi_handle handle = ACPI_HANDLE(dev);
+ struct acpi_device *adev;
+
+ if (handle && acpi_bus_get_device(handle, &adev) == 0)
+ acpi_device_fix_up_power(adev);
+}
+
static const struct acpi_device_id i2c_hid_acpi_match[] = {
{"ACPI0C50", 0 },
{"PNP0C50", 0 },
{
return -ENODEV;
}
+
+static inline void i2c_hid_acpi_fix_up_power(struct device *dev) {}
#endif
#ifdef CONFIG_OF
if (ret < 0)
goto err_regulator;
+ i2c_hid_acpi_fix_up_power(&client->dev);
+
pm_runtime_get_noresume(&client->dev);
pm_runtime_set_active(&client->dev);
pm_runtime_enable(&client->dev);
{
unsigned char *data = wacom->data;
- if (wacom->pen_input)
+ if (wacom->pen_input) {
dev_dbg(wacom->pen_input->dev.parent,
"%s: received report #%d\n", __func__, data[0]);
- else if (wacom->touch_input)
+
+ if (len == WACOM_PKGLEN_PENABLED ||
+ data[0] == WACOM_REPORT_PENABLED)
+ return wacom_tpc_pen(wacom);
+ }
+ else if (wacom->touch_input) {
dev_dbg(wacom->touch_input->dev.parent,
"%s: received report #%d\n", __func__, data[0]);
- switch (len) {
- case WACOM_PKGLEN_TPC1FG:
- return wacom_tpc_single_touch(wacom, len);
+ switch (len) {
+ case WACOM_PKGLEN_TPC1FG:
+ return wacom_tpc_single_touch(wacom, len);
- case WACOM_PKGLEN_TPC2FG:
- return wacom_tpc_mt_touch(wacom);
+ case WACOM_PKGLEN_TPC2FG:
+ return wacom_tpc_mt_touch(wacom);
- case WACOM_PKGLEN_PENABLED:
- return wacom_tpc_pen(wacom);
+ default:
+ switch (data[0]) {
+ case WACOM_REPORT_TPC1FG:
+ case WACOM_REPORT_TPCHID:
+ case WACOM_REPORT_TPCST:
+ case WACOM_REPORT_TPC1FGE:
+ return wacom_tpc_single_touch(wacom, len);
- default:
- switch (data[0]) {
- case WACOM_REPORT_TPC1FG:
- case WACOM_REPORT_TPCHID:
- case WACOM_REPORT_TPCST:
- case WACOM_REPORT_TPC1FGE:
- return wacom_tpc_single_touch(wacom, len);
-
- case WACOM_REPORT_TPCMT:
- case WACOM_REPORT_TPCMT2:
- return wacom_mt_touch(wacom);
+ case WACOM_REPORT_TPCMT:
+ case WACOM_REPORT_TPCMT2:
+ return wacom_mt_touch(wacom);
- case WACOM_REPORT_PENABLED:
- return wacom_tpc_pen(wacom);
+ }
}
}
config SENSORS_ASPEED
tristate "ASPEED AST2400/AST2500 PWM and Fan tach driver"
+ select REGMAP
help
This driver provides support for ASPEED AST2400/AST2500 PWM
and Fan Tacho controllers.
*/
#include <linux/clk.h>
+#include <linux/errno.h>
#include <linux/gpio/consumer.h>
#include <linux/delay.h>
#include <linux/hwmon.h>
return clk / (clk_unit * div_h * div_l * tacho_div * tacho_unit);
}
-static u32 aspeed_get_fan_tach_ch_rpm(struct aspeed_pwm_tacho_data *priv,
+static int aspeed_get_fan_tach_ch_rpm(struct aspeed_pwm_tacho_data *priv,
u8 fan_tach_ch)
{
u32 raw_data, tach_div, clk_source, sec, val;
msleep(sec);
regmap_read(priv->regmap, ASPEED_PTCR_RESULT, &val);
+ if (!(val & RESULT_STATUS_MASK))
+ return -ETIMEDOUT;
+
raw_data = val & RESULT_VALUE_MASK;
tach_div = priv->type_fan_tach_clock_division[type];
tach_div = 0x4 << (tach_div * 2);
{
struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
int index = sensor_attr->index;
- u32 rpm;
+ int rpm;
struct aspeed_pwm_tacho_data *priv = dev_get_drvdata(dev);
rpm = aspeed_get_fan_tach_ch_rpm(priv, index);
+ if (rpm < 0)
+ return rpm;
- return sprintf(buf, "%u\n", rpm);
+ return sprintf(buf, "%d\n", rpm);
}
static umode_t pwm_is_visible(struct kobject *kobj,
return a->mode;
}
-static SENSOR_DEVICE_ATTR(pwm0, 0644,
- show_pwm, set_pwm, 0);
static SENSOR_DEVICE_ATTR(pwm1, 0644,
- show_pwm, set_pwm, 1);
+ show_pwm, set_pwm, 0);
static SENSOR_DEVICE_ATTR(pwm2, 0644,
- show_pwm, set_pwm, 2);
+ show_pwm, set_pwm, 1);
static SENSOR_DEVICE_ATTR(pwm3, 0644,
- show_pwm, set_pwm, 3);
+ show_pwm, set_pwm, 2);
static SENSOR_DEVICE_ATTR(pwm4, 0644,
- show_pwm, set_pwm, 4);
+ show_pwm, set_pwm, 3);
static SENSOR_DEVICE_ATTR(pwm5, 0644,
- show_pwm, set_pwm, 5);
+ show_pwm, set_pwm, 4);
static SENSOR_DEVICE_ATTR(pwm6, 0644,
- show_pwm, set_pwm, 6);
+ show_pwm, set_pwm, 5);
static SENSOR_DEVICE_ATTR(pwm7, 0644,
+ show_pwm, set_pwm, 6);
+static SENSOR_DEVICE_ATTR(pwm8, 0644,
show_pwm, set_pwm, 7);
static struct attribute *pwm_dev_attrs[] = {
- &sensor_dev_attr_pwm0.dev_attr.attr,
&sensor_dev_attr_pwm1.dev_attr.attr,
&sensor_dev_attr_pwm2.dev_attr.attr,
&sensor_dev_attr_pwm3.dev_attr.attr,
&sensor_dev_attr_pwm5.dev_attr.attr,
&sensor_dev_attr_pwm6.dev_attr.attr,
&sensor_dev_attr_pwm7.dev_attr.attr,
+ &sensor_dev_attr_pwm8.dev_attr.attr,
NULL,
};
.is_visible = pwm_is_visible,
};
-static SENSOR_DEVICE_ATTR(fan0_input, 0444,
- show_rpm, NULL, 0);
static SENSOR_DEVICE_ATTR(fan1_input, 0444,
- show_rpm, NULL, 1);
+ show_rpm, NULL, 0);
static SENSOR_DEVICE_ATTR(fan2_input, 0444,
- show_rpm, NULL, 2);
+ show_rpm, NULL, 1);
static SENSOR_DEVICE_ATTR(fan3_input, 0444,
- show_rpm, NULL, 3);
+ show_rpm, NULL, 2);
static SENSOR_DEVICE_ATTR(fan4_input, 0444,
- show_rpm, NULL, 4);
+ show_rpm, NULL, 3);
static SENSOR_DEVICE_ATTR(fan5_input, 0444,
- show_rpm, NULL, 5);
+ show_rpm, NULL, 4);
static SENSOR_DEVICE_ATTR(fan6_input, 0444,
- show_rpm, NULL, 6);
+ show_rpm, NULL, 5);
static SENSOR_DEVICE_ATTR(fan7_input, 0444,
- show_rpm, NULL, 7);
+ show_rpm, NULL, 6);
static SENSOR_DEVICE_ATTR(fan8_input, 0444,
- show_rpm, NULL, 8);
+ show_rpm, NULL, 7);
static SENSOR_DEVICE_ATTR(fan9_input, 0444,
- show_rpm, NULL, 9);
+ show_rpm, NULL, 8);
static SENSOR_DEVICE_ATTR(fan10_input, 0444,
- show_rpm, NULL, 10);
+ show_rpm, NULL, 9);
static SENSOR_DEVICE_ATTR(fan11_input, 0444,
- show_rpm, NULL, 11);
+ show_rpm, NULL, 10);
static SENSOR_DEVICE_ATTR(fan12_input, 0444,
- show_rpm, NULL, 12);
+ show_rpm, NULL, 11);
static SENSOR_DEVICE_ATTR(fan13_input, 0444,
- show_rpm, NULL, 13);
+ show_rpm, NULL, 12);
static SENSOR_DEVICE_ATTR(fan14_input, 0444,
- show_rpm, NULL, 14);
+ show_rpm, NULL, 13);
static SENSOR_DEVICE_ATTR(fan15_input, 0444,
+ show_rpm, NULL, 14);
+static SENSOR_DEVICE_ATTR(fan16_input, 0444,
show_rpm, NULL, 15);
static struct attribute *fan_dev_attrs[] = {
- &sensor_dev_attr_fan0_input.dev_attr.attr,
&sensor_dev_attr_fan1_input.dev_attr.attr,
&sensor_dev_attr_fan2_input.dev_attr.attr,
&sensor_dev_attr_fan3_input.dev_attr.attr,
&sensor_dev_attr_fan13_input.dev_attr.attr,
&sensor_dev_attr_fan14_input.dev_attr.attr,
&sensor_dev_attr_fan15_input.dev_attr.attr,
+ &sensor_dev_attr_fan16_input.dev_attr.attr,
NULL
};
if (ret)
return ret;
}
- of_node_put(np);
priv->groups[0] = &pwm_dev_group;
priv->groups[1] = &fan_dev_group;
struct cpuinfo_x86 *c = &cpu_data(cpu);
struct platform_data *pdata;
+ /*
+ * Don't execute this on resume as the offline callback did
+ * not get executed on suspend.
+ */
+ if (cpuhp_tasks_frozen)
+ return 0;
+
/*
* CPUID.06H.EAX[0] indicates whether the CPU has thermal
* sensors. We check this bit only, all the early CPUs
struct temp_data *tdata;
int indx, target;
+ /*
+ * Don't execute this on suspend as the device remove locks
+ * up the machine.
+ */
+ if (cpuhp_tasks_frozen)
+ return 0;
+
/* If the physical CPU device does not exist, just return */
if (!pdev)
return 0;
static int dw_i2c_acpi_configure(struct platform_device *pdev)
{
struct dw_i2c_dev *dev = platform_get_drvdata(pdev);
+ u32 ss_ht = 0, fp_ht = 0, hs_ht = 0, fs_ht = 0;
acpi_handle handle = ACPI_HANDLE(&pdev->dev);
const struct acpi_device_id *id;
struct acpi_device *adev;
* Try to get SDA hold time and *CNT values from an ACPI method for
* selected speed modes.
*/
+ dw_i2c_acpi_params(pdev, "SSCN", &dev->ss_hcnt, &dev->ss_lcnt, &ss_ht);
+ dw_i2c_acpi_params(pdev, "FPCN", &dev->fp_hcnt, &dev->fp_lcnt, &fp_ht);
+ dw_i2c_acpi_params(pdev, "HSCN", &dev->hs_hcnt, &dev->hs_lcnt, &hs_ht);
+ dw_i2c_acpi_params(pdev, "FMCN", &dev->fs_hcnt, &dev->fs_lcnt, &fs_ht);
+
switch (dev->clk_freq) {
case 100000:
- dw_i2c_acpi_params(pdev, "SSCN", &dev->ss_hcnt, &dev->ss_lcnt,
- &dev->sda_hold_time);
+ dev->sda_hold_time = ss_ht;
break;
case 1000000:
- dw_i2c_acpi_params(pdev, "FPCN", &dev->fp_hcnt, &dev->fp_lcnt,
- &dev->sda_hold_time);
+ dev->sda_hold_time = fp_ht;
break;
case 3400000:
- dw_i2c_acpi_params(pdev, "HSCN", &dev->hs_hcnt, &dev->hs_lcnt,
- &dev->sda_hold_time);
+ dev->sda_hold_time = hs_ht;
break;
case 400000:
default:
- dw_i2c_acpi_params(pdev, "FMCN", &dev->fs_hcnt, &dev->fs_lcnt,
- &dev->sda_hold_time);
+ dev->sda_hold_time = fs_ht;
break;
}
rc = -EINVAL;
goto out;
}
- drv_data->irq = irq_of_parse_and_map(np, 0);
drv_data->rstc = devm_reset_control_get_optional(dev, NULL);
if (IS_ERR(drv_data->rstc)) {
if (!IS_ERR(drv_data->clk))
clk_prepare_enable(drv_data->clk);
+ drv_data->irq = platform_get_irq(pd, 0);
+
if (pdata) {
drv_data->freq_m = pdata->freq_m;
drv_data->freq_n = pdata->freq_n;
- drv_data->irq = platform_get_irq(pd, 0);
drv_data->adapter.timeout = msecs_to_jiffies(pdata->timeout);
drv_data->offload_enabled = false;
memcpy(&drv_data->reg_offsets, &mv64xxx_i2c_regs_mv64xxx, sizeof(drv_data->reg_offsets));
goto exit_clk;
}
if (drv_data->irq < 0) {
- rc = -ENXIO;
+ rc = drv_data->irq;
goto exit_reset;
}
int value, int index, void *data, int len)
{
struct i2c_tiny_usb *dev = (struct i2c_tiny_usb *)adapter->algo_data;
+ void *dmadata = kmalloc(len, GFP_KERNEL);
+ int ret;
+
+ if (!dmadata)
+ return -ENOMEM;
/* do control transfer */
- return usb_control_msg(dev->usb_dev, usb_rcvctrlpipe(dev->usb_dev, 0),
+ ret = usb_control_msg(dev->usb_dev, usb_rcvctrlpipe(dev->usb_dev, 0),
cmd, USB_TYPE_VENDOR | USB_RECIP_INTERFACE |
- USB_DIR_IN, value, index, data, len, 2000);
+ USB_DIR_IN, value, index, dmadata, len, 2000);
+
+ memcpy(data, dmadata, len);
+ kfree(dmadata);
+ return ret;
}
static int usb_write(struct i2c_adapter *adapter, int cmd,
int value, int index, void *data, int len)
{
struct i2c_tiny_usb *dev = (struct i2c_tiny_usb *)adapter->algo_data;
+ void *dmadata = kmemdup(data, len, GFP_KERNEL);
+ int ret;
+
+ if (!dmadata)
+ return -ENOMEM;
/* do control transfer */
- return usb_control_msg(dev->usb_dev, usb_sndctrlpipe(dev->usb_dev, 0),
+ ret = usb_control_msg(dev->usb_dev, usb_sndctrlpipe(dev->usb_dev, 0),
cmd, USB_TYPE_VENDOR | USB_RECIP_INTERFACE,
- value, index, data, len, 2000);
+ value, index, dmadata, len, 2000);
+
+ kfree(dmadata);
+ return ret;
}
static void i2c_tiny_usb_free(struct i2c_tiny_usb *dev)
adapter->class = I2C_CLASS_HWMON;
adapter->dev.parent = &pdev->dev;
adapter->dev.of_node = pdev->dev.of_node;
+ ACPI_COMPANION_SET(&adapter->dev, ACPI_COMPANION(&pdev->dev));
i2c_set_adapdata(adapter, ctx);
rc = i2c_add_adapter(adapter);
if (rc) {
if (force_nr) {
priv->adap.nr = force_nr;
ret = i2c_add_numbered_adapter(&priv->adap);
- dev_err(&parent->dev,
- "failed to add mux-adapter %u as bus %u (error=%d)\n",
- chan_id, force_nr, ret);
+ if (ret < 0) {
+ dev_err(&parent->dev,
+ "failed to add mux-adapter %u as bus %u (error=%d)\n",
+ chan_id, force_nr, ret);
+ goto err_free_priv;
+ }
} else {
ret = i2c_add_adapter(&priv->adap);
- dev_err(&parent->dev,
- "failed to add mux-adapter %u (error=%d)\n",
- chan_id, ret);
- }
- if (ret < 0) {
- kfree(priv);
- return ret;
+ if (ret < 0) {
+ dev_err(&parent->dev,
+ "failed to add mux-adapter %u (error=%d)\n",
+ chan_id, ret);
+ goto err_free_priv;
+ }
}
WARN(sysfs_create_link(&priv->adap.dev.kobj, &muxc->dev->kobj,
muxc->adapter[muxc->num_adapters++] = &priv->adap;
return 0;
+
+err_free_priv:
+ kfree(priv);
+ return ret;
}
EXPORT_SYMBOL_GPL(i2c_mux_add_adapter);
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
mux->data.reg_size = resource_size(res);
mux->data.reg = devm_ioremap_resource(&pdev->dev, res);
- if (IS_ERR(mux->data.reg))
- return PTR_ERR(mux->data.reg);
+ if (IS_ERR(mux->data.reg)) {
+ ret = PTR_ERR(mux->data.reg);
+ goto err_put_parent;
+ }
}
if (mux->data.reg_size != 4 && mux->data.reg_size != 2 &&
mux->data.reg_size != 1) {
dev_err(&pdev->dev, "Invalid register size\n");
- return -EINVAL;
+ ret = -EINVAL;
+ goto err_put_parent;
}
muxc = i2c_mux_alloc(parent, &pdev->dev, mux->data.n_values, 0, 0,
i2c_mux_reg_select, NULL);
- if (!muxc)
- return -ENOMEM;
+ if (!muxc) {
+ ret = -ENOMEM;
+ goto err_put_parent;
+ }
muxc->priv = mux;
platform_set_drvdata(pdev, muxc);
ret = i2c_mux_add_adapter(muxc, nr, mux->data.values[i], class);
if (ret)
- goto add_adapter_failed;
+ goto err_del_mux_adapters;
}
dev_dbg(&pdev->dev, "%d port mux on %s adapter\n",
return 0;
-add_adapter_failed:
+err_del_mux_adapters:
i2c_mux_del_adapters(muxc);
+err_put_parent:
+ i2c_put_adapter(parent);
return ret;
}
iproc_adc_dbg_reg(dev, adc_priv, IPROC_SOFT_BYPASS_DATA);
}
-static irqreturn_t iproc_adc_interrupt_handler(int irq, void *data)
+static irqreturn_t iproc_adc_interrupt_thread(int irq, void *data)
{
u32 channel_intr_status;
u32 intr_status;
return IRQ_NONE;
}
-static irqreturn_t iproc_adc_interrupt_thread(int irq, void *data)
+static irqreturn_t iproc_adc_interrupt_handler(int irq, void *data)
{
irqreturn_t retval = IRQ_NONE;
struct iproc_adc_priv *adc_priv;
adc_priv = iio_priv(indio_dev);
regmap_read(adc_priv->regmap, IPROC_INTERRUPT_STATUS, &intr_status);
- dev_dbg(&indio_dev->dev, "iproc_adc_interrupt_thread(),INTRPT_STS:%x\n",
+ dev_dbg(&indio_dev->dev, "iproc_adc_interrupt_handler(),INTRPT_STS:%x\n",
intr_status);
intr_channels = (intr_status & IPROC_ADC_INTR_MASK) >> IPROC_ADC_INTR;
}
ret = devm_request_threaded_irq(&pdev->dev, adc_priv->irqno,
- iproc_adc_interrupt_thread,
iproc_adc_interrupt_handler,
+ iproc_adc_interrupt_thread,
IRQF_SHARED, "iproc-adc", indio_dev);
if (ret) {
dev_err(&pdev->dev, "request_irq error %d\n", ret);
struct max9611_dev *max9611 = iio_priv(dev_to_iio_dev(dev));
unsigned int i, r;
- i = max9611->shunt_resistor_uohm / 1000;
- r = max9611->shunt_resistor_uohm % 1000;
+ i = max9611->shunt_resistor_uohm / 1000000;
+ r = max9611->shunt_resistor_uohm % 1000000;
- return sprintf(buf, "%u.%03u\n", i, r);
+ return sprintf(buf, "%u.%06u\n", i, r);
}
static IIO_DEVICE_ATTR(in_power_shunt_resistor, 0444,
int ret;
indio_dev = devm_iio_device_alloc(&client->dev, sizeof(*max9611));
- if (IS_ERR(indio_dev))
- return PTR_ERR(indio_dev);
+ if (!indio_dev)
+ return -ENOMEM;
i2c_set_clientdata(client, indio_dev);
bool no_irq;
/* prevents concurrent reads of temperature and ADC */
struct mutex mutex;
+ struct thermal_zone_device *tzd;
+ struct device *sensor_device;
};
#define SUN4I_GPADC_ADC_CHANNEL(_channel, _name) { \
{
struct sun4i_gpadc_iio *info = iio_priv(indio_dev);
const struct of_device_id *of_dev;
- struct thermal_zone_device *tzd;
struct resource *mem;
void __iomem *base;
int ret;
if (!IS_ENABLED(CONFIG_THERMAL_OF))
return 0;
- tzd = devm_thermal_zone_of_sensor_register(&pdev->dev, 0, info,
- &sun4i_ts_tz_ops);
- if (IS_ERR(tzd))
+ info->sensor_device = &pdev->dev;
+ info->tzd = thermal_zone_of_sensor_register(info->sensor_device, 0,
+ info, &sun4i_ts_tz_ops);
+ if (IS_ERR(info->tzd))
dev_err(&pdev->dev, "could not register thermal sensor: %ld\n",
- PTR_ERR(tzd));
+ PTR_ERR(info->tzd));
- return PTR_ERR_OR_ZERO(tzd);
+ return PTR_ERR_OR_ZERO(info->tzd);
}
static int sun4i_gpadc_probe_mfd(struct platform_device *pdev,
* of_node, and the device from this driver as third argument to
* return the temperature.
*/
- struct thermal_zone_device *tzd;
- tzd = devm_thermal_zone_of_sensor_register(pdev->dev.parent, 0,
- info,
- &sun4i_ts_tz_ops);
- if (IS_ERR(tzd)) {
+ info->sensor_device = pdev->dev.parent;
+ info->tzd = thermal_zone_of_sensor_register(info->sensor_device,
+ 0, info,
+ &sun4i_ts_tz_ops);
+ if (IS_ERR(info->tzd)) {
dev_err(&pdev->dev,
"could not register thermal sensor: %ld\n",
- PTR_ERR(tzd));
- return PTR_ERR(tzd);
+ PTR_ERR(info->tzd));
+ return PTR_ERR(info->tzd);
}
} else {
indio_dev->num_channels =
pm_runtime_put(&pdev->dev);
pm_runtime_disable(&pdev->dev);
- if (!info->no_irq && IS_ENABLED(CONFIG_THERMAL_OF))
+
+ if (!IS_ENABLED(CONFIG_THERMAL_OF))
+ return 0;
+
+ thermal_zone_of_sensor_unregister(info->sensor_device, info->tzd);
+
+ if (!info->no_irq)
iio_map_array_unregister(indio_dev);
return 0;
{ "sun6i-a31-gpadc-iio", (kernel_ulong_t)&sun6i_gpadc_data },
{ /* sentinel */ },
};
+MODULE_DEVICE_TABLE(platform, sun4i_gpadc_id);
static struct platform_driver sun4i_gpadc_driver = {
.driver = {
.probe = sun4i_gpadc_probe,
.remove = sun4i_gpadc_remove,
};
+MODULE_DEVICE_TABLE(of, sun4i_gpadc_of_id);
module_platform_driver(sun4i_gpadc_driver);
return -EINVAL;
}
- indio_dev = devm_iio_device_alloc(&pdev->dev, sizeof(*indio_dev));
+ indio_dev = devm_iio_device_alloc(&pdev->dev, sizeof(*adc_dev));
if (indio_dev == NULL) {
dev_err(&pdev->dev, "failed to allocate iio device\n");
return -ENOMEM;
return len;
out_trigger_put:
- iio_trigger_put(trig);
+ if (trig)
+ iio_trigger_put(trig);
return ret;
}
static const struct reg_field reg_field_it =
REG_FIELD(LTR501_ALS_MEAS_RATE, 3, 4);
static const struct reg_field reg_field_als_intr =
- REG_FIELD(LTR501_INTR, 0, 0);
-static const struct reg_field reg_field_ps_intr =
REG_FIELD(LTR501_INTR, 1, 1);
+static const struct reg_field reg_field_ps_intr =
+ REG_FIELD(LTR501_INTR, 0, 0);
static const struct reg_field reg_field_als_rate =
REG_FIELD(LTR501_ALS_MEAS_RATE, 0, 2);
static const struct reg_field reg_field_ps_rate =
#define AS3935_AFE_PWR_BIT BIT(0)
#define AS3935_INT 0x03
-#define AS3935_INT_MASK 0x07
+#define AS3935_INT_MASK 0x0f
#define AS3935_EVENT_INT BIT(3)
-#define AS3935_NOISE_INT BIT(1)
+#define AS3935_NOISE_INT BIT(0)
#define AS3935_DATA 0x07
#define AS3935_DATA_MASK 0x3F
st->buffer[0] = val & AS3935_DATA_MASK;
iio_push_to_buffers_with_timestamp(indio_dev, &st->buffer,
- pf->timestamp);
+ iio_get_time_ns(indio_dev));
err_read:
iio_trigger_notify_done(indio_dev->trig);
switch (val) {
case AS3935_EVENT_INT:
- iio_trigger_poll(st->trig);
+ iio_trigger_poll_chained(st->trig);
break;
case AS3935_NOISE_INT:
dev_warn(&st->spi->dev, "noise level is too high\n");
static void calibrate_as3935(struct as3935_state *st)
{
- mutex_lock(&st->lock);
-
/* mask disturber interrupt bit */
as3935_write(st, AS3935_INT, BIT(5));
mdelay(2);
as3935_write(st, AS3935_TUNE_CAP, (st->tune_cap / TUNE_CAP_DIV));
-
- mutex_unlock(&st->lock);
}
#ifdef CONFIG_PM_SLEEP
val &= ~AS3935_AFE_PWR_BIT;
ret = as3935_write(st, AS3935_AFE_GAIN, val);
+ calibrate_as3935(st);
+
err_resume:
mutex_unlock(&st->lock);
primary_path->packet_life_time =
cm_req_get_primary_local_ack_timeout(req_msg);
primary_path->packet_life_time -= (primary_path->packet_life_time > 0);
- sa_path_set_service_id(primary_path, req_msg->service_id);
+ primary_path->service_id = req_msg->service_id;
if (req_msg->alt_local_lid) {
alt_path->dgid = req_msg->alt_local_gid;
alt_path->packet_life_time =
cm_req_get_alt_local_ack_timeout(req_msg);
alt_path->packet_life_time -= (alt_path->packet_life_time > 0);
- sa_path_set_service_id(alt_path, req_msg->service_id);
+ alt_path->service_id = req_msg->service_id;
}
}
ib->sib_pkey = path->pkey;
ib->sib_flowinfo = path->flow_label;
memcpy(&ib->sib_addr, &path->sgid, 16);
- ib->sib_sid = sa_path_get_service_id(path);
+ ib->sib_sid = path->service_id;
ib->sib_scope_id = 0;
} else {
ib->sib_pkey = listen_ib->sib_pkey;
memcpy(&req->local_gid, &req_param->primary_path->sgid,
sizeof(req->local_gid));
req->has_gid = true;
- req->service_id =
- sa_path_get_service_id(req_param->primary_path);
+ req->service_id = req_param->primary_path->service_id;
req->pkey = be16_to_cpu(req_param->primary_path->pkey);
if (req->pkey != req_param->bth_pkey)
pr_warn_ratelimited("RDMA CMA: got different BTH P_Key (0x%x) and primary path P_Key (0x%x)\n"
struct rdma_route *rt;
const sa_family_t ss_family = listen_id->route.addr.src_addr.ss_family;
struct sa_path_rec *path = ib_event->param.req_rcvd.primary_path;
- const __be64 service_id = sa_path_get_service_id(path);
+ const __be64 service_id =
+ ib_event->param.req_rcvd.primary_path->service_id;
int ret;
id = rdma_create_id(listen_id->route.addr.dev_addr.net,
path_rec.pkey = cpu_to_be16(ib_addr_get_pkey(dev_addr));
path_rec.numb_path = 1;
path_rec.reversible = 1;
- sa_path_set_service_id(&path_rec,
- rdma_get_service_id(&id_priv->id,
- cma_dst_addr(id_priv)));
+ path_rec.service_id = rdma_get_service_id(&id_priv->id,
+ cma_dst_addr(id_priv));
comp_mask = IB_SA_PATH_REC_DGID | IB_SA_PATH_REC_SGID |
IB_SA_PATH_REC_PKEY | IB_SA_PATH_REC_NUMB_PATH |
int ib_sa_init(void);
void ib_sa_cleanup(void);
+int ibnl_init(void);
+void ibnl_cleanup(void);
+
+/**
+ * Check if there are any listeners to the netlink group
+ * @group: the netlink group ID
+ * Returns 0 on success or a negative for no listeners.
+ */
+int ibnl_chk_listeners(unsigned int group);
+
int ib_nl_handle_resolve_resp(struct sk_buff *skb,
struct netlink_callback *cb);
int ib_nl_handle_set_timeout(struct sk_buff *skb,
#include <net/net_namespace.h>
#include <net/sock.h>
#include <rdma/rdma_netlink.h>
+#include "core_priv.h"
struct ibnl_client {
struct list_head list;
return -1;
return 0;
}
-EXPORT_SYMBOL(ibnl_chk_listeners);
int ibnl_add_client(int index, int nops,
const struct ibnl_client_cbs cb_table[])
.field_name = "sa_path_rec:" #field
static const struct ib_field path_rec_table[] = {
- { PATH_REC_FIELD(ib.service_id),
+ { PATH_REC_FIELD(service_id),
.offset_words = 0,
.offset_bits = 0,
.size_bits = 64 },
.field_name = "sa_path_rec:" #field
static const struct ib_field opa_path_rec_table[] = {
- { OPA_PATH_REC_FIELD(opa.service_id),
+ { OPA_PATH_REC_FIELD(service_id),
.offset_words = 0,
.offset_bits = 0,
.size_bits = 64 },
/* Now build the attributes */
if (comp_mask & IB_SA_PATH_REC_SERVICE_ID) {
- val64 = be64_to_cpu(sa_path_get_service_id(sa_rec));
+ val64 = be64_to_cpu(sa_rec->service_id);
nla_put(skb, RDMA_NLA_F_MANDATORY | LS_NLA_TYPE_SERVICE_ID,
sizeof(val64), &val64);
}
for_each_sg(umem->sg_head.sgl, sg, umem->npages, i) {
page = sg_page(sg);
- if (umem->writable && dirty)
+ if (!PageDirty(page) && umem->writable && dirty)
set_page_dirty_lock(page);
put_page(page);
}
struct vm_area_struct *vma;
struct hstate *h;
+ down_read(&mm->mmap_sem);
vma = find_vma(mm, ib_umem_start(umem));
- if (!vma || !is_vm_hugetlb_page(vma))
+ if (!vma || !is_vm_hugetlb_page(vma)) {
+ up_read(&mm->mmap_sem);
return -EINVAL;
+ }
h = hstate_vma(vma);
umem->page_shift = huge_page_shift(h);
+ up_read(&mm->mmap_sem);
umem->hugetlb = 1;
} else {
umem->hugetlb = 0;
}
EXPORT_SYMBOL(ib_copy_qp_attr_to_user);
-void __ib_copy_path_rec_to_user(struct ib_user_path_rec *dst,
- struct sa_path_rec *src)
+static void __ib_copy_path_rec_to_user(struct ib_user_path_rec *dst,
+ struct sa_path_rec *src)
{
- memcpy(dst->dgid, src->dgid.raw, sizeof src->dgid);
- memcpy(dst->sgid, src->sgid.raw, sizeof src->sgid);
+ memcpy(dst->dgid, src->dgid.raw, sizeof(src->dgid));
+ memcpy(dst->sgid, src->sgid.raw, sizeof(src->sgid));
dst->dlid = htons(ntohl(sa_path_get_dlid(src)));
dst->slid = htons(ntohl(sa_path_get_slid(src)));
ep = *((struct c4iw_ep **)(skb->cb + 2 * sizeof(void *)));
release_ep_resources(ep);
+ kfree_skb(skb);
return 0;
}
ep = *((struct c4iw_ep **)(skb->cb + 2 * sizeof(void *)));
c4iw_put_ep(&ep->parent_ep->com);
release_ep_resources(ep);
+ kfree_skb(skb);
return 0;
}
pr_debug("%s rdev %p\n", __func__, rdev);
req->cmd = CPL_ABORT_NO_RST;
+ skb_get(skb);
ret = c4iw_ofld_send(rdev, skb);
if (ret) {
__state_set(&ep->com, DEAD);
queue_arp_failure_cpl(ep, skb, FAKE_CPL_PUT_EP_SAFE);
- }
+ } else
+ kfree_skb(skb);
}
static int send_flowc(struct c4iw_ep *ep)
goto reject;
}
- hdrs = sizeof(struct iphdr) + sizeof(struct tcphdr) +
+ hdrs = ((iptype == 4) ? sizeof(struct iphdr) : sizeof(struct ipv6hdr)) +
+ sizeof(struct tcphdr) +
((enable_tcp_timestamps && req->tcpopt.tstamp) ? 12 : 0);
if (peer_mss && child_ep->mtu > (peer_mss + hdrs))
child_ep->mtu = peer_mss + hdrs;
devp->rdev.lldi.sge_egrstatuspagesize);
devp->rdev.hw_queue.t4_eq_status_entries =
- devp->rdev.lldi.sge_ingpadboundary > 64 ? 2 : 1;
+ devp->rdev.lldi.sge_egrstatuspagesize / 64;
devp->rdev.hw_queue.t4_max_eq_size = 65520;
devp->rdev.hw_queue.t4_max_iq_size = 65520;
devp->rdev.hw_queue.t4_max_rq_size = 8192 -
}
}
-static void write_global_credit(struct hfi1_devdata *dd,
- u8 vau, u16 total, u16 shared)
+/*
+ * Set up allocation unit vaulue.
+ */
+void set_up_vau(struct hfi1_devdata *dd, u8 vau)
{
- write_csr(dd, SEND_CM_GLOBAL_CREDIT,
- ((u64)total <<
- SEND_CM_GLOBAL_CREDIT_TOTAL_CREDIT_LIMIT_SHIFT) |
- ((u64)shared <<
- SEND_CM_GLOBAL_CREDIT_SHARED_LIMIT_SHIFT) |
- ((u64)vau << SEND_CM_GLOBAL_CREDIT_AU_SHIFT));
+ u64 reg = read_csr(dd, SEND_CM_GLOBAL_CREDIT);
+
+ /* do not modify other values in the register */
+ reg &= ~SEND_CM_GLOBAL_CREDIT_AU_SMASK;
+ reg |= (u64)vau << SEND_CM_GLOBAL_CREDIT_AU_SHIFT;
+ write_csr(dd, SEND_CM_GLOBAL_CREDIT, reg);
}
/*
* Set up initial VL15 credits of the remote. Assumes the rest of
- * the CM credit registers are zero from a previous global or credit reset .
+ * the CM credit registers are zero from a previous global or credit reset.
+ * Shared limit for VL15 will always be 0.
*/
-void set_up_vl15(struct hfi1_devdata *dd, u8 vau, u16 vl15buf)
+void set_up_vl15(struct hfi1_devdata *dd, u16 vl15buf)
{
- /* leave shared count at zero for both global and VL15 */
- write_global_credit(dd, vau, vl15buf, 0);
+ u64 reg = read_csr(dd, SEND_CM_GLOBAL_CREDIT);
+
+ /* set initial values for total and shared credit limit */
+ reg &= ~(SEND_CM_GLOBAL_CREDIT_TOTAL_CREDIT_LIMIT_SMASK |
+ SEND_CM_GLOBAL_CREDIT_SHARED_LIMIT_SMASK);
+
+ /*
+ * Set total limit to be equal to VL15 credits.
+ * Leave shared limit at 0.
+ */
+ reg |= (u64)vl15buf << SEND_CM_GLOBAL_CREDIT_TOTAL_CREDIT_LIMIT_SHIFT;
+ write_csr(dd, SEND_CM_GLOBAL_CREDIT, reg);
write_csr(dd, SEND_CM_CREDIT_VL15, (u64)vl15buf
<< SEND_CM_CREDIT_VL15_DEDICATED_LIMIT_VL_SHIFT);
for (i = 0; i < TXE_NUM_DATA_VL; i++)
write_csr(dd, SEND_CM_CREDIT_VL + (8 * i), 0);
write_csr(dd, SEND_CM_CREDIT_VL15, 0);
- write_global_credit(dd, 0, 0, 0);
+ write_csr(dd, SEND_CM_GLOBAL_CREDIT, 0);
/* reset the CM block */
pio_send_control(dd, PSC_CM_RESET);
+ /* reset cached value */
+ dd->vl15buf_cached = 0;
}
/* convert a vCU to a CU */
{
struct hfi1_pportdata *ppd = container_of(work, struct hfi1_pportdata,
link_up_work);
+ struct hfi1_devdata *dd = ppd->dd;
+
set_link_state(ppd, HLS_UP_INIT);
/* cache the read of DC_LCB_STS_ROUND_TRIP_LTP_CNT */
- read_ltp_rtt(ppd->dd);
+ read_ltp_rtt(dd);
/*
* OPA specifies that certain counters are cleared on a transition
* to link up, so do that.
*/
- clear_linkup_counters(ppd->dd);
+ clear_linkup_counters(dd);
/*
* And (re)set link up default values.
*/
set_linkup_defaults(ppd);
+ /*
+ * Set VL15 credits. Use cached value from verify cap interrupt.
+ * In case of quick linkup or simulator, vl15 value will be set by
+ * handle_linkup_change. VerifyCap interrupt handler will not be
+ * called in those scenarios.
+ */
+ if (!(quick_linkup || dd->icode == ICODE_FUNCTIONAL_SIMULATOR))
+ set_up_vl15(dd, dd->vl15buf_cached);
+
/* enforce link speed enabled */
if ((ppd->link_speed_active & ppd->link_speed_enabled) == 0) {
/* oops - current speed is not enabled, bounce */
- dd_dev_err(ppd->dd,
+ dd_dev_err(dd,
"Link speed active 0x%x is outside enabled 0x%x, downing link\n",
ppd->link_speed_active, ppd->link_speed_enabled);
set_link_down_reason(ppd, OPA_LINKDOWN_REASON_SPEED_POLICY, 0,
*/
if (vau == 0)
vau = 1;
- set_up_vl15(dd, vau, vl15buf);
+ set_up_vau(dd, vau);
+
+ /*
+ * Set VL15 credits to 0 in global credit register. Cache remote VL15
+ * credits value and wait for link-up interrupt ot set it.
+ */
+ set_up_vl15(dd, 0);
+ dd->vl15buf_cached = vl15buf;
/* set up the LCB CRC mode */
crc_mask = ppd->port_crc_mode_enabled & partner_supported_crc;
#define SEND_CM_CTRL_FORCE_CREDIT_MODE_SMASK 0x8ull
#define SEND_CM_CTRL_RESETCSR 0x0000000000000020ull
#define SEND_CM_GLOBAL_CREDIT (TXE + 0x000000000508)
+#define SEND_CM_GLOBAL_CREDIT_AU_MASK 0x7ull
#define SEND_CM_GLOBAL_CREDIT_AU_SHIFT 16
+#define SEND_CM_GLOBAL_CREDIT_AU_SMASK 0x70000ull
#define SEND_CM_GLOBAL_CREDIT_RESETCSR 0x0000094000030000ull
#define SEND_CM_GLOBAL_CREDIT_SHARED_LIMIT_MASK 0xFFFFull
#define SEND_CM_GLOBAL_CREDIT_SHARED_LIMIT_SHIFT 0
/* initial vl15 credits to use */
u16 vl15_init;
+ /*
+ * Cached value for vl15buf, read during verify cap interrupt. VL15
+ * credits are to be kept at 0 and set when handling the link-up
+ * interrupt. This removes the possibility of receiving VL15 MAD
+ * packets before this HFI is ready.
+ */
+ u16 vl15buf_cached;
+
/* Misc small ints */
u8 n_krcv_queues;
u8 qos_shift;
int fm_get_table(struct hfi1_pportdata *ppd, int which, void *t);
int fm_set_table(struct hfi1_pportdata *ppd, int which, void *t);
-void set_up_vl15(struct hfi1_devdata *dd, u8 vau, u16 vl15buf);
+void set_up_vau(struct hfi1_devdata *dd, u8 vau);
+void set_up_vl15(struct hfi1_devdata *dd, u16 vl15buf);
void reset_link_credits(struct hfi1_devdata *dd);
void assign_remote_cm_au_table(struct hfi1_devdata *dd, u8 vcu);
* the remote values. Both sides must be using the values.
*/
if (quick_linkup || dd->icode == ICODE_FUNCTIONAL_SIMULATOR) {
- set_up_vl15(dd, dd->vau, dd->vl15_init);
+ set_up_vau(dd, dd->vau);
+ set_up_vl15(dd, dd->vl15_init);
assign_remote_cm_au_table(dd, dd->vcu);
}
/*
* Save BARs and command to rewrite after device reset.
*/
- dd->pcibar0 = addr;
- dd->pcibar1 = addr >> 32;
+ pci_read_config_dword(dd->pcidev, PCI_BASE_ADDRESS_0, &dd->pcibar0);
+ pci_read_config_dword(dd->pcidev, PCI_BASE_ADDRESS_1, &dd->pcibar1);
pci_read_config_dword(dd->pcidev, PCI_ROM_ADDRESS, &dd->pci_rom);
pci_read_config_word(dd->pcidev, PCI_COMMAND, &dd->pci_command);
pcie_capability_read_word(dd->pcidev, PCI_EXP_DEVCTL, &dd->pcie_devctl);
ret = hfi1_rvt_get_rwqe(qp, 1);
if (ret < 0)
goto nack_op_err;
- if (!ret)
+ if (!ret) {
+ /* peer will send again */
+ rvt_put_ss(&qp->r_sge);
goto rnr_nak;
+ }
wc.ex.imm_data = ohdr->u.rc.imm_data;
wc.wc_flags = IB_WC_WITH_IMM;
goto send_last;
};
static struct attribute *port_cc_default_attributes[] = {
- &cc_prescan_attr.attr
+ &cc_prescan_attr.attr,
+ NULL
};
static struct kobj_type port_cc_ktype = {
}
ctrl_ird |= IETF_PEER_TO_PEER;
- ctrl_ird |= IETF_FLPDU_ZERO_LEN;
switch (mpa_key) {
case MPA_KEY_REQUEST:
} else {
type = I40IW_CM_EVENT_CONNECTED;
cm_node->state = I40IW_CM_STATE_OFFLOADED;
- i40iw_send_ack(cm_node);
}
+ i40iw_send_ack(cm_node);
break;
default:
pr_err("%s wrong cm_node state =%d\n", __func__, cm_node->state);
struct i40iw_sc_dev *dev = vsi->dev;
struct i40iw_sc_qp *qp = NULL;
bool qs_handle_change = false;
- bool mss_change = false;
unsigned long flags;
u16 qs_handle;
int i;
- if (vsi->mss != l2params->mss) {
- mss_change = true;
- vsi->mss = l2params->mss;
- }
+ vsi->mss = l2params->mss;
i40iw_fill_qos_list(l2params->qs_handle_list);
for (i = 0; i < I40IW_MAX_USER_PRIORITY; i++) {
qs_handle = l2params->qs_handle_list[i];
if (vsi->qos[i].qs_handle != qs_handle)
qs_handle_change = true;
- else if (!mss_change)
- continue; /* no MSS nor qs handle change */
spin_lock_irqsave(&vsi->qos[i].lock, flags);
qp = i40iw_get_qp(&vsi->qos[i].qplist, qp);
while (qp) {
- if (mss_change)
- i40iw_qp_mss_modify(dev, qp);
if (qs_handle_change) {
qp->qs_handle = qs_handle;
/* issue cqp suspend command */
set_64bit_val(wqe,
8,
- LS_64(info->new_mss, I40IW_CQPSQ_QP_NEWMSS) |
LS_64(term_len, I40IW_CQPSQ_QP_TERMLEN));
set_64bit_val(wqe, 16, qp->hw_host_ctx_pa);
LS_64(info->cq_num_valid, I40IW_CQPSQ_QP_CQNUMVALID) |
LS_64(info->force_loopback, I40IW_CQPSQ_QP_FORCELOOPBACK) |
LS_64(qp->qp_type, I40IW_CQPSQ_QP_QPTYPE) |
- LS_64(info->mss_change, I40IW_CQPSQ_QP_MSSCHANGE) |
LS_64(info->static_rsrc, I40IW_CQPSQ_QP_STATRSRC) |
LS_64(info->remove_hash_idx, I40IW_CQPSQ_QP_REMOVEHASHENTRY) |
LS_64(term_actions, I40IW_CQPSQ_QP_TERMACT) |
status = i40iw_obj_aligned_mem(iwdev, &mem, I40IW_QUERY_FPM_BUF_SIZE,
I40IW_FPM_QUERY_BUF_ALIGNMENT_MASK);
if (status)
- goto exit;
+ goto error;
info.fpm_query_buf_pa = mem.pa;
info.fpm_query_buf = mem.va;
status = i40iw_obj_aligned_mem(iwdev, &mem, I40IW_COMMIT_FPM_BUF_SIZE,
I40IW_FPM_COMMIT_BUF_ALIGNMENT_MASK);
if (status)
- goto exit;
+ goto error;
info.fpm_commit_buf_pa = mem.pa;
info.fpm_commit_buf = mem.va;
info.hmc_fn_id = ldev->fid;
info.exception_lan_queue = 1;
info.vchnl_send = i40iw_virtchnl_send;
status = i40iw_device_init(&iwdev->sc_dev, &info);
-exit:
- if (status) {
- kfree(iwdev->hmc_info_mem);
- iwdev->hmc_info_mem = NULL;
- }
+
+ if (status)
+ goto error;
memset(&vsi_info, 0, sizeof(vsi_info));
vsi_info.dev = &iwdev->sc_dev;
vsi_info.back_vsi = (void *)iwdev;
memset(&stats_info, 0, sizeof(stats_info));
stats_info.fcn_id = ldev->fid;
stats_info.pestat = kzalloc(sizeof(*stats_info.pestat), GFP_KERNEL);
+ if (!stats_info.pestat) {
+ status = I40IW_ERR_NO_MEMORY;
+ goto error;
+ }
stats_info.stats_initialize = true;
if (stats_info.pestat)
i40iw_vsi_stats_init(&iwdev->vsi, &stats_info);
}
return status;
+error:
+ kfree(iwdev->hmc_info_mem);
+ iwdev->hmc_info_mem = NULL;
+ return status;
}
/**
struct i40iw_virtchnl_work_info *work_info, u32 iw_vf_idx);
void *i40iw_remove_head(struct list_head *list);
void i40iw_qp_suspend_resume(struct i40iw_sc_dev *dev, struct i40iw_sc_qp *qp, bool suspend);
-void i40iw_qp_mss_modify(struct i40iw_sc_dev *dev, struct i40iw_sc_qp *qp);
void i40iw_term_modify_qp(struct i40iw_sc_qp *qp, u8 next_state, u8 term, u8 term_len);
void i40iw_terminate_done(struct i40iw_sc_qp *qp, int timeout_occurred);
struct i40iw_modify_qp_info {
u64 rx_win0;
u64 rx_win1;
- u16 new_mss;
u8 next_iwarp_state;
u8 termlen;
bool ord_valid;
bool dont_send_term;
bool dont_send_fin;
bool cached_var_valid;
- bool mss_change;
bool force_loopback;
};
i40iw_pr_err("CQP-OP QP Suspend/Resume fail");
}
-/**
- * i40iw_qp_mss_modify - modify mss for qp
- * @dev: hardware control device structure
- * @qp: hardware control qp
- */
-void i40iw_qp_mss_modify(struct i40iw_sc_dev *dev, struct i40iw_sc_qp *qp)
-{
- struct i40iw_device *iwdev = (struct i40iw_device *)dev->back_dev;
- struct i40iw_qp *iwqp = (struct i40iw_qp *)qp->back_qp;
- struct i40iw_modify_qp_info info;
-
- memset(&info, 0, sizeof(info));
- info.mss_change = true;
- info.new_mss = qp->vsi->mss;
- i40iw_hw_modify_qp(iwdev, iwqp, &info, false);
-}
-
/**
* i40iw_term_modify_qp - modify qp for term message
* @qp: hardware control qp
if (!dev->vchnl_up)
return I40IW_ERR_NOT_READY;
if (vchnl_msg->iw_op_code == I40IW_VCHNL_OP_GET_VER) {
- if (vchnl_msg->iw_op_ver != I40IW_VCHNL_OP_GET_VER_V0)
- vchnl_pf_send_get_ver_resp(dev, vf_id, vchnl_msg);
- else
- vchnl_pf_send_get_ver_resp(dev, vf_id, vchnl_msg);
+ vchnl_pf_send_get_ver_resp(dev, vf_id, vchnl_msg);
return I40IW_SUCCESS;
}
for (iw_vf_idx = 0; iw_vf_idx < I40IW_MAX_PE_ENABLED_VF_COUNT; iw_vf_idx++) {
if (port < 0)
return;
ah.av.ib.port_pd = cpu_to_be32(port << 24 | (be32_to_cpu(ah.av.ib.port_pd) & 0xffffff));
+ ah.ibah.type = rdma_ah_find_type(&dev->ib_dev, port);
mlx4_ib_query_ah(&ah.ibah, &ah_attr);
if (rdma_ah_get_ah_flags(&ah_attr) & IB_AH_GRH)
return ret;
}
+static u8 mlx5_get_umr_fence(u8 umr_fence_cap)
+{
+ switch (umr_fence_cap) {
+ case MLX5_CAP_UMR_FENCE_NONE:
+ return MLX5_FENCE_MODE_NONE;
+ case MLX5_CAP_UMR_FENCE_SMALL:
+ return MLX5_FENCE_MODE_INITIATOR_SMALL;
+ default:
+ return MLX5_FENCE_MODE_STRONG_ORDERING;
+ }
+}
+
static int create_dev_resources(struct mlx5_ib_resources *devr)
{
struct ib_srq_init_attr attr;
mlx5_ib_internal_fill_odp_caps(dev);
+ dev->umr_fence = mlx5_get_umr_fence(MLX5_CAP_GEN(mdev, umr_fence));
+
if (MLX5_CAP_GEN(mdev, imaicl)) {
dev->ib_dev.alloc_mw = mlx5_ib_alloc_mw;
dev->ib_dev.dealloc_mw = mlx5_ib_dealloc_mw;
struct mlx5_ib_wq rq;
u8 sq_signal_bits;
- u8 fm_cache;
+ u8 next_fence;
struct mlx5_ib_wq sq;
/* serialize qp state modifications
struct mlx5_ib_port *port;
struct mlx5_sq_bfreg bfreg;
struct mlx5_sq_bfreg fp_bfreg;
+ u8 umr_fence;
};
static inline struct mlx5_ib_cq *to_mibcq(struct mlx5_core_cq *mcq)
}
}
-static u8 get_fence(u8 fence, struct ib_send_wr *wr)
-{
- if (unlikely(wr->opcode == IB_WR_LOCAL_INV &&
- wr->send_flags & IB_SEND_FENCE))
- return MLX5_FENCE_MODE_STRONG_ORDERING;
-
- if (unlikely(fence)) {
- if (wr->send_flags & IB_SEND_FENCE)
- return MLX5_FENCE_MODE_SMALL_AND_FENCE;
- else
- return fence;
- } else if (unlikely(wr->send_flags & IB_SEND_FENCE)) {
- return MLX5_FENCE_MODE_FENCE;
- }
-
- return 0;
-}
-
static int begin_wqe(struct mlx5_ib_qp *qp, void **seg,
struct mlx5_wqe_ctrl_seg **ctrl,
struct ib_send_wr *wr, unsigned *idx,
static void finish_wqe(struct mlx5_ib_qp *qp,
struct mlx5_wqe_ctrl_seg *ctrl,
u8 size, unsigned idx, u64 wr_id,
- int nreq, u8 fence, u8 next_fence,
- u32 mlx5_opcode)
+ int nreq, u8 fence, u32 mlx5_opcode)
{
u8 opmod = 0;
mlx5_opcode | ((u32)opmod << 24));
ctrl->qpn_ds = cpu_to_be32(size | (qp->trans_qp.base.mqp.qpn << 8));
ctrl->fm_ce_se |= fence;
- qp->fm_cache = next_fence;
if (unlikely(qp->wq_sig))
ctrl->signature = wq_sig(ctrl);
goto out;
}
- fence = qp->fm_cache;
num_sge = wr->num_sge;
if (unlikely(num_sge > qp->sq.max_gs)) {
mlx5_ib_warn(dev, "\n");
goto out;
}
+ if (wr->opcode == IB_WR_LOCAL_INV ||
+ wr->opcode == IB_WR_REG_MR) {
+ fence = dev->umr_fence;
+ next_fence = MLX5_FENCE_MODE_INITIATOR_SMALL;
+ } else if (wr->send_flags & IB_SEND_FENCE) {
+ if (qp->next_fence)
+ fence = MLX5_FENCE_MODE_SMALL_AND_FENCE;
+ else
+ fence = MLX5_FENCE_MODE_FENCE;
+ } else {
+ fence = qp->next_fence;
+ }
+
switch (ibqp->qp_type) {
case IB_QPT_XRC_INI:
xrc = seg;
goto out;
case IB_WR_LOCAL_INV:
- next_fence = MLX5_FENCE_MODE_INITIATOR_SMALL;
qp->sq.wr_data[idx] = IB_WR_LOCAL_INV;
ctrl->imm = cpu_to_be32(wr->ex.invalidate_rkey);
set_linv_wr(qp, &seg, &size);
break;
case IB_WR_REG_MR:
- next_fence = MLX5_FENCE_MODE_INITIATOR_SMALL;
qp->sq.wr_data[idx] = IB_WR_REG_MR;
ctrl->imm = cpu_to_be32(reg_wr(wr)->key);
err = set_reg_wr(qp, reg_wr(wr), &seg, &size);
goto out;
}
- finish_wqe(qp, ctrl, size, idx, wr->wr_id,
- nreq, get_fence(fence, wr),
- next_fence, MLX5_OPCODE_UMR);
+ finish_wqe(qp, ctrl, size, idx, wr->wr_id, nreq,
+ fence, MLX5_OPCODE_UMR);
/*
* SET_PSV WQEs are not signaled and solicited
* on error
goto out;
}
- finish_wqe(qp, ctrl, size, idx, wr->wr_id,
- nreq, get_fence(fence, wr),
- next_fence, MLX5_OPCODE_SET_PSV);
+ finish_wqe(qp, ctrl, size, idx, wr->wr_id, nreq,
+ fence, MLX5_OPCODE_SET_PSV);
err = begin_wqe(qp, &seg, &ctrl, wr,
&idx, &size, nreq);
if (err) {
goto out;
}
- next_fence = MLX5_FENCE_MODE_INITIATOR_SMALL;
err = set_psv_wr(&sig_handover_wr(wr)->sig_attrs->wire,
mr->sig->psv_wire.psv_idx, &seg,
&size);
goto out;
}
- finish_wqe(qp, ctrl, size, idx, wr->wr_id,
- nreq, get_fence(fence, wr),
- next_fence, MLX5_OPCODE_SET_PSV);
+ finish_wqe(qp, ctrl, size, idx, wr->wr_id, nreq,
+ fence, MLX5_OPCODE_SET_PSV);
+ qp->next_fence = MLX5_FENCE_MODE_INITIATOR_SMALL;
num_sge = 0;
goto skip_psv;
}
}
- finish_wqe(qp, ctrl, size, idx, wr->wr_id, nreq,
- get_fence(fence, wr), next_fence,
+ qp->next_fence = next_fence;
+ finish_wqe(qp, ctrl, size, idx, wr->wr_id, nreq, fence,
mlx5_ib_opcode[wr->opcode]);
skip_psv:
if (0)
ctrl_ord = cm_node->ord_size & IETF_NO_IRD_ORD;
}
ctrl_ird |= IETF_PEER_TO_PEER;
- ctrl_ird |= IETF_FLPDU_ZERO_LEN;
switch (mpa_key) {
case MPA_KEY_REQUEST:
type = NES_CM_EVENT_CONNECTED;
cm_node->state = NES_CM_STATE_TSA;
}
-
+ send_ack(cm_node, NULL);
break;
default:
WARN_ON(1);
return rc;
}
- vlan_id = rdma_vlan_dev_vlan_id(sgid_attr.ndev);
- if (vlan_id < VLAN_CFI_MASK)
- has_vlan = true;
- if (sgid_attr.ndev)
+ if (sgid_attr.ndev) {
+ vlan_id = rdma_vlan_dev_vlan_id(sgid_attr.ndev);
+ if (vlan_id < VLAN_CFI_MASK)
+ has_vlan = true;
+
dev_put(sgid_attr.ndev);
+ }
if (!memcmp(&sgid, &zgid, sizeof(sgid))) {
DP_ERR(dev, "gsi post send: GID not found GID index %d\n",
ret = qib_get_rwqe(qp, 1);
if (ret < 0)
goto nack_op_err;
- if (!ret)
+ if (!ret) {
+ rvt_put_ss(&qp->r_sge);
goto rnr_nak;
+ }
wc.ex.imm_data = ohdr->u.rc.imm_data;
hdrsize += 4;
wc.wc_flags = IB_WC_WITH_IMM;
static int ipoib_get_link_ksettings(struct net_device *netdev,
struct ethtool_link_ksettings *cmd)
{
- struct ipoib_dev_priv *priv = netdev_priv(netdev);
+ struct ipoib_dev_priv *priv = ipoib_priv(netdev);
struct ib_port_attr attr;
int ret, speed, width;
wait_for_completion(&priv->ntbl.deleted);
}
-void ipoib_dev_uninit_default(struct net_device *dev)
+static void ipoib_dev_uninit_default(struct net_device *dev)
{
struct ipoib_dev_priv *priv = ipoib_priv(dev);
ch->path.sgid = target->sgid;
ch->path.dgid = target->orig_dgid;
ch->path.pkey = target->pkey;
- sa_path_set_service_id(&ch->path, target->service_id);
+ ch->path.service_id = target->service_id;
return 0;
}
return 0;
err_qp:
- srp_destroy_qp(ch, qp);
+ ib_destroy_qp(qp);
err_send_cq:
ib_free_cq(send_cq);
/* led device */
touchkey->led_dev.name = TM2_TOUCHKEY_DEV_NAME;
touchkey->led_dev.brightness = LED_FULL;
- touchkey->led_dev.max_brightness = LED_FULL;
+ touchkey->led_dev.max_brightness = LED_ON;
touchkey->led_dev.brightness_set = tm2_touchkey_led_brightness_set;
error = devm_led_classdev_register(&client->dev, &touchkey->led_dev);
return 0;
}
+#ifdef CONFIG_ACPI
+static bool axp20x_pek_should_register_input(struct axp20x_pek *axp20x_pek,
+ struct platform_device *pdev)
+{
+ unsigned long long hrv = 0;
+ acpi_status status;
+
+ if (IS_ENABLED(CONFIG_INPUT_SOC_BUTTON_ARRAY) &&
+ axp20x_pek->axp20x->variant == AXP288_ID) {
+ status = acpi_evaluate_integer(ACPI_HANDLE(pdev->dev.parent),
+ "_HRV", NULL, &hrv);
+ if (ACPI_FAILURE(status))
+ dev_err(&pdev->dev, "Failed to get PMIC hardware revision\n");
+
+ /*
+ * On Cherry Trail platforms (hrv == 3), do not register the
+ * input device if there is an "INTCFD9" or "ACPI0011" gpio
+ * button ACPI device, as that handles the power button too,
+ * and otherwise we end up reporting all presses twice.
+ */
+ if (hrv == 3 && (acpi_dev_present("INTCFD9", NULL, -1) ||
+ acpi_dev_present("ACPI0011", NULL, -1)))
+ return false;
+
+ }
+
+ return true;
+}
+#else
+static bool axp20x_pek_should_register_input(struct axp20x_pek *axp20x_pek,
+ struct platform_device *pdev)
+{
+ return true;
+}
+#endif
+
static int axp20x_pek_probe(struct platform_device *pdev)
{
struct axp20x_pek *axp20x_pek;
axp20x_pek->axp20x = dev_get_drvdata(pdev->dev.parent);
- /*
- * Do not register the input device if there is an "INTCFD9"
- * gpio button ACPI device, that handles the power button too,
- * and otherwise we end up reporting all presses twice.
- */
- if (!acpi_dev_found("INTCFD9") ||
- !IS_ENABLED(CONFIG_INPUT_SOC_BUTTON_ARRAY)) {
+ if (axp20x_pek_should_register_input(axp20x_pek, pdev)) {
error = axp20x_pek_probe_input_device(axp20x_pek, pdev);
if (error)
return error;
struct completion *completion)
{
struct device *dev = &client->dev;
- long ret;
int error;
int len;
- u8 buffer[ETP_I2C_INF_LENGTH];
+ u8 buffer[ETP_I2C_REPORT_LEN];
+
+ len = i2c_master_recv(client, buffer, ETP_I2C_REPORT_LEN);
+ if (len != ETP_I2C_REPORT_LEN) {
+ error = len < 0 ? len : -EIO;
+ dev_warn(dev, "failed to read I2C data after FW WDT reset: %d (%d)\n",
+ error, len);
+ }
reinit_completion(completion);
enable_irq(client->irq);
error = elan_i2c_write_cmd(client, ETP_I2C_STAND_CMD, ETP_I2C_RESET);
- if (!error)
- ret = wait_for_completion_interruptible_timeout(completion,
- msecs_to_jiffies(300));
- disable_irq(client->irq);
-
if (error) {
dev_err(dev, "device reset failed: %d\n", error);
- return error;
- } else if (ret == 0) {
+ } else if (!wait_for_completion_timeout(completion,
+ msecs_to_jiffies(300))) {
dev_err(dev, "timeout waiting for device reset\n");
- return -ETIMEDOUT;
- } else if (ret < 0) {
- error = ret;
- dev_err(dev, "error waiting for device reset: %d\n", error);
- return error;
+ error = -ETIMEDOUT;
}
+ disable_irq(client->irq);
+
+ if (error)
+ return error;
+
len = i2c_master_recv(client, buffer, ETP_I2C_INF_LENGTH);
if (len != ETP_I2C_INF_LENGTH) {
error = len < 0 ? len : -EIO;
* Asus UX32VD 0x361f02 00, 15, 0e clickpad
* Avatar AVIU-145A2 0x361f00 ? clickpad
* Fujitsu LIFEBOOK E544 0x470f00 d0, 12, 09 2 hw buttons
+ * Fujitsu LIFEBOOK E546 0x470f00 50, 12, 09 2 hw buttons
* Fujitsu LIFEBOOK E547 0x470f00 50, 12, 09 2 hw buttons
* Fujitsu LIFEBOOK E554 0x570f01 40, 14, 0c 2 hw buttons
+ * Fujitsu LIFEBOOK E557 0x570f01 40, 14, 0c 2 hw buttons
* Fujitsu T725 0x470f01 05, 12, 09 2 hw buttons
* Fujitsu H730 0x570f00 c0, 14, 0c 3 hw buttons (**)
* Gigabyte U2442 0x450f01 58, 17, 0c 2 hw buttons
DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E544"),
},
},
+ {
+ /* Fujitsu LIFEBOOK E546 does not work with crc_enabled == 0 */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E546"),
+ },
+ },
{
/* Fujitsu LIFEBOOK E547 does not work with crc_enabled == 0 */
.matches = {
DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E556"),
},
},
+ {
+ /* Fujitsu LIFEBOOK E557 does not work with crc_enabled == 0 */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E557"),
+ },
+ },
{
/* Fujitsu LIFEBOOK U745 does not work with crc_enabled == 0 */
.matches = {
NULL
};
+static const char * const forcepad_pnp_ids[] = {
+ "SYN300D",
+ "SYN3014",
+ NULL
+};
+
/*
* Send a command to the synpatics touchpad by special commands
*/
{
int error;
+ memset(info, 0, sizeof(*info));
+
error = synaptics_identify(psmouse, info);
if (error)
return error;
{ }
};
-/* This list has been kindly provided by Synaptics. */
-static const char * const forcepad_pnp_ids[] = {
- "SYN300D",
- "SYN3014",
- NULL
-};
-
/*****************************************************************************
* Synaptics communications functions
****************************************************************************/
SYNAPTICS_INTERTOUCH_ON,
};
-static int synaptics_intertouch = SYNAPTICS_INTERTOUCH_NOT_SET;
+static int synaptics_intertouch = IS_ENABLED(CONFIG_RMI4_SMB) ?
+ SYNAPTICS_INTERTOUCH_NOT_SET : SYNAPTICS_INTERTOUCH_OFF;
module_param_named(synaptics_intertouch, synaptics_intertouch, int, 0644);
MODULE_PARM_DESC(synaptics_intertouch, "Use a secondary bus for the Synaptics device.");
if (synaptics_intertouch == SYNAPTICS_INTERTOUCH_NOT_SET) {
if (!psmouse_matches_pnp_id(psmouse, topbuttonpad_pnp_ids) &&
- !psmouse_matches_pnp_id(psmouse, smbus_pnp_ids))
+ !psmouse_matches_pnp_id(psmouse, smbus_pnp_ids)) {
+
+ if (!psmouse_matches_pnp_id(psmouse, forcepad_pnp_ids))
+ psmouse_info(psmouse,
+ "Your touchpad (%s) says it can support a different bus. "
+ "If i2c-hid and hid-rmi are not used, you might want to try setting psmouse.synaptics_intertouch to 1 and report this to linux-input@vger.kernel.org.\n",
+ psmouse->ps2dev.serio->firmware_id);
+
return -ENXIO;
+ }
}
psmouse_info(psmouse, "Trying to set up SMBus access\n");
}
if (SYN_CAP_INTERTOUCH(info.ext_cap_0c)) {
+ if ((!IS_ENABLED(CONFIG_RMI4_SMB) ||
+ !IS_ENABLED(CONFIG_MOUSE_PS2_SYNAPTICS_SMBUS)) &&
+ /* Forcepads need F21, which is not ready */
+ !psmouse_matches_pnp_id(psmouse, forcepad_pnp_ids)) {
+ psmouse_warn(psmouse,
+ "The touchpad can support a better bus than the too old PS/2 protocol. "
+ "Make sure MOUSE_PS2_SYNAPTICS_SMBUS and RMI4_SMB are enabled to get a better touchpad experience.\n");
+ }
+
error = synaptics_setup_intertouch(psmouse, &info, true);
if (!error)
return PSMOUSE_SYNAPTICS_SMBUS;
if (!serio)
return -ENOMEM;
- serio->id.type = SERIO_8042;
+ serio->id.type = SERIO_PS_PSTHRU;
serio->write = rmi_f03_pt_write;
serio->port_data = f03;
case MXT_TOUCH_KEYARRAY_T15:
case MXT_TOUCH_PROXIMITY_T23:
case MXT_TOUCH_PROXKEY_T52:
+ case MXT_TOUCH_MULTITOUCHSCREEN_T100:
case MXT_PROCI_GRIPFACE_T20:
case MXT_PROCG_NOISE_T22:
case MXT_PROCI_ONETOUCH_T24:
static EDT_ATTR(offset, S_IWUSR | S_IRUGO, WORK_REGISTER_OFFSET,
M09_REGISTER_OFFSET, 0, 31);
static EDT_ATTR(threshold, S_IWUSR | S_IRUGO, WORK_REGISTER_THRESHOLD,
- M09_REGISTER_THRESHOLD, 20, 80);
+ M09_REGISTER_THRESHOLD, 0, 80);
static EDT_ATTR(report_rate, S_IWUSR | S_IRUGO, WORK_REGISTER_REPORT_RATE,
NO_REGISTER, 3, 14);
{
struct i2c_client *client = to_i2c_client(dev);
+ disable_irq(client->irq);
silead_ts_set_power(client, SILEAD_POWER_OFF);
return 0;
}
return -ENODEV;
}
+ enable_irq(client->irq);
+
return 0;
}
dma_addr_t iova, size_t size)
{
struct iova_domain *iovad = &cookie->iovad;
- unsigned long shift = iova_shift(iovad);
/* The MSI case is only ever cleaning up its most recent allocation */
if (cookie->type == IOMMU_DMA_MSI_COOKIE)
cookie->msi_iova -= size;
else
- free_iova_fast(iovad, iova >> shift, size >> shift);
+ free_iova_fast(iovad, iova_pfn(iovad, iova),
+ size >> iova_shift(iovad));
}
static void __iommu_dma_unmap(struct iommu_domain *domain, dma_addr_t dma_addr,
{
struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
struct iommu_dma_cookie *cookie = domain->iova_cookie;
- struct iova_domain *iovad = &cookie->iovad;
- size_t iova_off = iova_offset(iovad, phys);
+ size_t iova_off = 0;
dma_addr_t iova;
- size = iova_align(iovad, size + iova_off);
+ if (cookie->type == IOMMU_DMA_IOVA_COOKIE) {
+ iova_off = iova_offset(&cookie->iovad, phys);
+ size = iova_align(&cookie->iovad, size + iova_off);
+ }
+
iova = iommu_dma_alloc_iova(domain, size, dma_get_mask(dev), dev);
if (!iova)
return DMA_ERROR_CODE;
if (context_copied(context)) {
u16 did_old = context_domain_id(context);
- if (did_old >= 0 && did_old < cap_ndoms(iommu->cap))
+ if (did_old >= 0 && did_old < cap_ndoms(iommu->cap)) {
iommu->flush.flush_context(iommu, did_old,
(((u16)bus) << 8) | devfn,
DMA_CCMD_MASK_NOBIT,
DMA_CCMD_DEVICE_INVL);
+ iommu->flush.flush_iotlb(iommu, did_old, 0, 0,
+ DMA_TLB_DSI_FLUSH);
+ }
}
pgd = domain->pgd;
#include <linux/clk.h>
#include <linux/component.h>
#include <linux/device.h>
+#include <linux/dma-mapping.h>
#include <linux/dma-iommu.h>
#include <linux/err.h>
#include <linux/interrupt.h>
ops = iommu_ops_from_fwnode(fwnode);
if ((ops && !ops->of_xlate) ||
+ !of_device_is_available(iommu_spec->np) ||
(!ops && !of_iommu_driver_present(iommu_spec->np)))
return NULL;
ops = ERR_PTR(err);
}
+ /* Ignore all other errors apart from EPROBE_DEFER */
+ if (IS_ERR(ops) && (PTR_ERR(ops) != -EPROBE_DEFER)) {
+ dev_dbg(dev, "Adding to IOMMU failed: %ld\n", PTR_ERR(ops));
+ ops = NULL;
+ }
+
return ops;
}
static inline void get_mbigen_clear_reg(irq_hw_number_t hwirq,
u32 *mask, u32 *addr)
{
- unsigned int ofst;
-
- hwirq -= RESERVED_IRQ_PER_MBIGEN_CHIP;
- ofst = hwirq / 32 * 4;
+ unsigned int ofst = (hwirq / 32) * 4;
*mask = 1 << (hwirq % 32);
*addr = ofst + REG_MBIGEN_CLEAR_OFFSET;
mgn_chip->pdev = pdev;
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- mgn_chip->base = devm_ioremap_resource(&pdev->dev, res);
- if (IS_ERR(mgn_chip->base))
- return PTR_ERR(mgn_chip->base);
+ if (!res)
+ return -EINVAL;
+
+ mgn_chip->base = devm_ioremap(&pdev->dev, res->start,
+ resource_size(res));
+ if (!mgn_chip->base) {
+ dev_err(&pdev->dev, "failed to ioremap %pR\n", res);
+ return -ENOMEM;
+ }
if (IS_ENABLED(CONFIG_OF) && pdev->dev.of_node)
err = mbigen_of_create_domain(pdev, mgn_chip);
id);
return NULL;
} else {
- rs = kzalloc(sizeof(struct ippp_ccp_reset_state), GFP_KERNEL);
+ rs = kzalloc(sizeof(struct ippp_ccp_reset_state), GFP_ATOMIC);
if (!rs)
return NULL;
rs->state = CCPResetIdle;
if (sk->sk_state != MISDN_BOUND)
continue;
if (!cskb)
- cskb = skb_copy(skb, GFP_KERNEL);
+ cskb = skb_copy(skb, GFP_ATOMIC);
if (!cskb) {
printk(KERN_WARNING "%s no skb\n", __func__);
break;
"slave address 0x%02x\n",
client->name, chip->bits, client->addr);
- if (!i2c_check_functionality(adapter, I2C_FUNC_I2C))
+ if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA))
return -EIO;
if (pdata) {
pr_debug(" magic: %08x\n", le32_to_cpu(sb->magic));
pr_debug(" version: %d\n", le32_to_cpu(sb->version));
pr_debug(" uuid: %08x.%08x.%08x.%08x\n",
- *(__u32 *)(sb->uuid+0),
- *(__u32 *)(sb->uuid+4),
- *(__u32 *)(sb->uuid+8),
- *(__u32 *)(sb->uuid+12));
+ le32_to_cpu(*(__u32 *)(sb->uuid+0)),
+ le32_to_cpu(*(__u32 *)(sb->uuid+4)),
+ le32_to_cpu(*(__u32 *)(sb->uuid+8)),
+ le32_to_cpu(*(__u32 *)(sb->uuid+12)));
pr_debug(" events: %llu\n",
(unsigned long long) le64_to_cpu(sb->events));
pr_debug("events cleared: %llu\n",
* Buffers are freed after this timeout
*/
static unsigned dm_bufio_max_age = DM_BUFIO_DEFAULT_AGE_SECS;
-static unsigned dm_bufio_retain_bytes = DM_BUFIO_DEFAULT_RETAIN_BYTES;
+static unsigned long dm_bufio_retain_bytes = DM_BUFIO_DEFAULT_RETAIN_BYTES;
static unsigned long dm_bufio_peak_allocated;
static unsigned long dm_bufio_allocated_kmem_cache;
{
struct dm_io_request io_req = {
.bi_op = REQ_OP_WRITE,
- .bi_op_flags = REQ_PREFLUSH,
+ .bi_op_flags = REQ_PREFLUSH | REQ_SYNC,
.mem.type = DM_IO_KMEM,
.mem.ptr.addr = NULL,
.client = c->dm_io,
return true;
}
-static unsigned get_retain_buffers(struct dm_bufio_client *c)
+static unsigned long get_retain_buffers(struct dm_bufio_client *c)
{
- unsigned retain_bytes = ACCESS_ONCE(dm_bufio_retain_bytes);
- return retain_bytes / c->block_size;
+ unsigned long retain_bytes = ACCESS_ONCE(dm_bufio_retain_bytes);
+ return retain_bytes >> (c->sectors_per_block_bits + SECTOR_SHIFT);
}
static unsigned long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan,
struct dm_buffer *b, *tmp;
unsigned long freed = 0;
unsigned long count = nr_to_scan;
- unsigned retain_target = get_retain_buffers(c);
+ unsigned long retain_target = get_retain_buffers(c);
for (l = 0; l < LIST_SIZE; l++) {
list_for_each_entry_safe_reverse(b, tmp, &c->lru[l], lru_list) {
static void __evict_old_buffers(struct dm_bufio_client *c, unsigned long age_hz)
{
struct dm_buffer *b, *tmp;
- unsigned retain_target = get_retain_buffers(c);
- unsigned count;
+ unsigned long retain_target = get_retain_buffers(c);
+ unsigned long count;
LIST_HEAD(write_list);
dm_bufio_lock(c);
module_param_named(max_age_seconds, dm_bufio_max_age, uint, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(max_age_seconds, "Max age of a buffer in seconds");
-module_param_named(retain_bytes, dm_bufio_retain_bytes, uint, S_IRUGO | S_IWUSR);
+module_param_named(retain_bytes, dm_bufio_retain_bytes, ulong, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(retain_bytes, "Try to keep at least this many bytes cached in memory");
module_param_named(peak_allocated_bytes, dm_bufio_peak_allocated, ulong, S_IRUGO | S_IWUSR);
{
struct background_tracker *b = kmalloc(sizeof(*b), GFP_KERNEL);
+ if (!b) {
+ DMERR("couldn't create background_tracker");
+ return NULL;
+ }
+
b->max_work = max_work;
atomic_set(&b->pending_promotes, 0);
atomic_set(&b->pending_writebacks, 0);
* Cache entries may not be populated. So we cannot rely on the
* size of the clean queue.
*/
- unsigned nr_clean;
-
if (idle) {
/*
* We'd like to clean everything.
return q_size(&mq->dirty) == 0u;
}
- nr_clean = from_cblock(mq->cache_size) - q_size(&mq->dirty);
- return (nr_clean + btracker_nr_writebacks_queued(mq->bg_work)) >=
- percent_to_target(mq, CLEAN_TARGET);
+ /*
+ * If we're busy we don't worry about cleaning at all.
+ */
+ return true;
}
-static bool free_target_met(struct smq_policy *mq, bool idle)
+static bool free_target_met(struct smq_policy *mq)
{
unsigned nr_free;
- if (!idle)
- return true;
-
nr_free = from_cblock(mq->cache_size) - mq->cache_alloc.nr_allocated;
return (nr_free + btracker_nr_demotions_queued(mq->bg_work)) >=
percent_to_target(mq, FREE_TARGET);
if (unlikely(WARN_ON_ONCE(!mq->migrations_allowed)))
return;
- e = q_peek(&mq->clean, mq->clean.nr_levels, true);
+ e = q_peek(&mq->clean, mq->clean.nr_levels / 2, true);
if (!e) {
- if (!clean_target_met(mq, false))
+ if (!clean_target_met(mq, true))
queue_writeback(mq);
return;
}
* We always claim to be 'idle' to ensure some demotions happen
* with continuous loads.
*/
- if (!free_target_met(mq, true))
+ if (!free_target_met(mq))
queue_demotion(mq);
return;
}
spin_lock_irqsave(&mq->lock, flags);
r = btracker_issue(mq->bg_work, result);
if (r == -ENODATA) {
- /* find some writeback work to do */
- if (mq->migrations_allowed && !free_target_met(mq, idle))
- queue_demotion(mq);
-
- else if (!clean_target_met(mq, idle))
+ if (!clean_target_met(mq, idle)) {
queue_writeback(mq);
-
- r = btracker_issue(mq->bg_work, result);
+ r = btracker_issue(mq->bg_work, result);
+ }
}
spin_unlock_irqrestore(&mq->lock, flags);
clear_pending(mq, e);
if (success) {
e->oblock = work->oblock;
+ e->level = NR_CACHE_LEVELS - 1;
push(mq, e);
// h, q, a
} else {
static void __iot_io_end(struct io_tracker *iot, sector_t len)
{
+ if (!len)
+ return;
+
iot->in_flight -= len;
if (!iot->in_flight)
iot->idle_time = jiffies;
spinlock_t invalidation_lock;
struct list_head invalidation_requests;
- struct io_tracker origin_tracker;
+ struct io_tracker tracker;
struct work_struct commit_ws;
struct batcher committer;
static bool accountable_bio(struct cache *cache, struct bio *bio)
{
- return ((bio->bi_bdev == cache->origin_dev->bdev) &&
- bio_op(bio) != REQ_OP_DISCARD);
+ return bio_op(bio) != REQ_OP_DISCARD;
}
static void accounted_begin(struct cache *cache, struct bio *bio)
if (accountable_bio(cache, bio)) {
pb->len = bio_sectors(bio);
- iot_io_begin(&cache->origin_tracker, pb->len);
+ iot_io_begin(&cache->tracker, pb->len);
}
}
size_t pb_data_size = get_per_bio_data_size(cache);
struct per_bio_data *pb = get_per_bio_data(bio, pb_data_size);
- iot_io_end(&cache->origin_tracker, pb->len);
+ iot_io_end(&cache->tracker, pb->len);
}
static void accounted_request(struct cache *cache, struct bio *bio)
enum busy {
IDLE,
- MODERATE,
BUSY
};
static enum busy spare_migration_bandwidth(struct cache *cache)
{
- bool idle = iot_idle_for(&cache->origin_tracker, HZ);
+ bool idle = iot_idle_for(&cache->tracker, HZ);
sector_t current_volume = (atomic_read(&cache->nr_io_migrations) + 1) *
cache->sectors_per_block;
- if (current_volume <= cache->migration_threshold)
- return idle ? IDLE : MODERATE;
+ if (idle && current_volume <= cache->migration_threshold)
+ return IDLE;
else
- return idle ? MODERATE : BUSY;
+ return BUSY;
}
static void inc_hit_counter(struct cache *cache, struct bio *bio)
for (;;) {
b = spare_migration_bandwidth(cache);
- if (b == BUSY)
- break;
r = policy_get_background_work(cache->policy, b == IDLE, &op);
if (r == -ENODATA)
batcher_init(&cache->committer, commit_op, cache,
issue_op, cache, cache->wq);
- iot_init(&cache->origin_tracker);
+ iot_init(&cache->tracker);
init_rwsem(&cache->background_work_lock);
prevent_background_work(cache);
cancel_delayed_work(&cache->waker);
flush_workqueue(cache->wq);
- WARN_ON(cache->origin_tracker.in_flight);
+ WARN_ON(cache->tracker.in_flight);
/*
* If it's a flush suspend there won't be any deferred bios, so this
for (i = 0; i < commit_sections; i++)
rw_section_mac(ic, commit_start + i, true);
}
- rw_journal(ic, REQ_OP_WRITE, REQ_FUA, commit_start, commit_sections, &io_comp);
+ rw_journal(ic, REQ_OP_WRITE, REQ_FUA | REQ_SYNC, commit_start,
+ commit_sections, &io_comp);
} else {
unsigned to_end;
io_comp.in_flight = (atomic_t)ATOMIC_INIT(2);
blk_queue_max_integrity_segments(disk->queue, UINT_MAX);
}
-/* FIXME: use new kvmalloc */
-static void *dm_integrity_kvmalloc(size_t size, gfp_t gfp)
-{
- void *ptr = NULL;
-
- if (size <= PAGE_SIZE)
- ptr = kmalloc(size, GFP_KERNEL | gfp);
- if (!ptr && size <= KMALLOC_MAX_SIZE)
- ptr = kmalloc(size, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY | gfp);
- if (!ptr)
- ptr = __vmalloc(size, GFP_KERNEL | gfp, PAGE_KERNEL);
-
- return ptr;
-}
-
static void dm_integrity_free_page_list(struct dm_integrity_c *ic, struct page_list *pl)
{
unsigned i;
struct page_list *pl;
unsigned i;
- pl = dm_integrity_kvmalloc(page_list_desc_size, __GFP_ZERO);
+ pl = kvmalloc(page_list_desc_size, GFP_KERNEL | __GFP_ZERO);
if (!pl)
return NULL;
struct scatterlist **sl;
unsigned i;
- sl = dm_integrity_kvmalloc(ic->journal_sections * sizeof(struct scatterlist *), __GFP_ZERO);
+ sl = kvmalloc(ic->journal_sections * sizeof(struct scatterlist *), GFP_KERNEL | __GFP_ZERO);
if (!sl)
return NULL;
n_pages = (end_index - start_index + 1);
- s = dm_integrity_kvmalloc(n_pages * sizeof(struct scatterlist), 0);
+ s = kvmalloc(n_pages * sizeof(struct scatterlist), GFP_KERNEL);
if (!s) {
dm_integrity_free_journal_scatterlist(ic, sl);
return NULL;
goto bad;
}
- sg = dm_integrity_kvmalloc((ic->journal_pages + 1) * sizeof(struct scatterlist), 0);
+ sg = kvmalloc((ic->journal_pages + 1) * sizeof(struct scatterlist), GFP_KERNEL);
if (!sg) {
*error = "Unable to allocate sg list";
r = -ENOMEM;
r = -ENOMEM;
goto bad;
}
- ic->sk_requests = dm_integrity_kvmalloc(ic->journal_sections * sizeof(struct skcipher_request *), __GFP_ZERO);
+ ic->sk_requests = kvmalloc(ic->journal_sections * sizeof(struct skcipher_request *), GFP_KERNEL | __GFP_ZERO);
if (!ic->sk_requests) {
*error = "Unable to allocate sk requests";
r = -ENOMEM;
r = -ENOMEM;
goto bad;
}
- ic->journal_tree = dm_integrity_kvmalloc(journal_tree_size, 0);
+ ic->journal_tree = kvmalloc(journal_tree_size, GFP_KERNEL);
if (!ic->journal_tree) {
*error = "Could not allocate memory for journal tree";
r = -ENOMEM;
}
/*
- * Try to avoid low memory issues when a device is suspended.
+ * Use __GFP_HIGH to avoid low memory issues when a device is
+ * suspended and the ioctl is needed to resume it.
* Use kmalloc() rather than vmalloc() when we can.
*/
dmi = NULL;
noio_flag = memalloc_noio_save();
- dmi = kvmalloc(param_kernel->data_size, GFP_KERNEL);
+ dmi = kvmalloc(param_kernel->data_size, GFP_KERNEL | __GFP_HIGH);
memalloc_noio_restore(noio_flag);
if (!dmi) {
* it has been invoked.
*/
#define dm_report_EIO(m) \
-({ \
+do { \
struct mapped_device *md = dm_table_get_md((m)->ti->table); \
\
pr_debug("%s: returning EIO; QIFNP = %d; SQIFNP = %d; DNFS = %d\n", \
test_bit(MPATHF_QUEUE_IF_NO_PATH, &(m)->flags), \
test_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &(m)->flags), \
dm_noflush_suspending((m)->ti)); \
- -EIO; \
-})
+} while (0)
/*
* Map cloned requests (request-based multipath)
if (!pgpath) {
if (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags))
return DM_MAPIO_DELAY_REQUEUE;
- return dm_report_EIO(m); /* Failed */
+ dm_report_EIO(m); /* Failed */
+ return DM_MAPIO_KILL;
} else if (test_bit(MPATHF_QUEUE_IO, &m->flags) ||
test_bit(MPATHF_PG_INIT_REQUIRED, &m->flags)) {
if (pg_init_all_paths(m))
if (!pgpath) {
if (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags))
return DM_MAPIO_REQUEUE;
- return dm_report_EIO(m);
+ dm_report_EIO(m);
+ return -EIO;
}
mpio->pgpath = pgpath;
if (atomic_read(&m->nr_valid_paths) == 0 &&
!test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) {
if (error == -EIO)
- error = dm_report_EIO(m);
+ dm_report_EIO(m);
/* complete with the original error */
r = DM_ENDIO_DONE;
}
fail_path(mpio->pgpath);
if (atomic_read(&m->nr_valid_paths) == 0 &&
- !test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags))
- return dm_report_EIO(m);
+ !test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) {
+ dm_report_EIO(m);
+ return -EIO;
+ }
/* Queue for the daemon to resubmit */
dm_bio_restore(get_bio_details_from_bio(clone), clone);
struct mirror *m;
struct dm_io_request io_req = {
.bi_op = REQ_OP_WRITE,
- .bi_op_flags = REQ_PREFLUSH,
+ .bi_op_flags = REQ_PREFLUSH | REQ_SYNC,
.mem.type = DM_IO_KMEM,
.mem.ptr.addr = NULL,
.client = ms->io_client,
case DM_MAPIO_KILL:
/* The target wants to complete the I/O */
dm_kill_unmapped_request(rq, -EIO);
+ break;
default:
DMWARN("unimplemented target map return value: %d", r);
BUG();
/*
* Commit exceptions to disk.
*/
- if (ps->valid && area_io(ps, REQ_OP_WRITE, REQ_PREFLUSH | REQ_FUA))
+ if (ps->valid && area_io(ps, REQ_OP_WRITE,
+ REQ_PREFLUSH | REQ_FUA | REQ_SYNC))
ps->valid = 0;
/*
if (r < 0)
return r;
- r = save_sm_roots(pmd);
+ r = dm_tm_pre_commit(pmd->tm);
if (r < 0)
return r;
- r = dm_tm_pre_commit(pmd->tm);
+ r = save_sm_roots(pmd);
if (r < 0)
return r;
return r;
}
- if (likely(v->version >= 1))
+ if (likely(v->salt_size && (v->version >= 1)))
r = verity_hash_update(v, req, v->salt, v->salt_size, res);
return r;
{
int r;
- if (unlikely(!v->version)) {
+ if (unlikely(v->salt_size && (!v->version))) {
r = verity_hash_update(v, req, v->salt, v->salt_size, res);
if (r < 0) {
bio_init(&md->flush_bio, NULL, 0);
md->flush_bio.bi_bdev = md->bdev;
- md->flush_bio.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
+ md->flush_bio.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH | REQ_SYNC;
dm_stats_init(&md->stats);
cmsg.raid_slot = cpu_to_le32(rdev->desc_nr);
lock_comm(cinfo, 1);
ret = __sendmsg(cinfo, &cmsg);
- if (ret)
+ if (ret) {
+ unlock_comm(cinfo);
return ret;
+ }
cinfo->no_new_dev_lockres->flags |= DLM_LKF_NOQUEUE;
ret = dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_EX);
cinfo->no_new_dev_lockres->flags &= ~DLM_LKF_NOQUEUE;
test_bit(FailFast, &rdev->flags) &&
!test_bit(LastDev, &rdev->flags))
ff = MD_FAILFAST;
- bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH | REQ_FUA | ff;
+ bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH | REQ_FUA | ff;
atomic_inc(&mddev->pending_writes);
submit_bio(bio);
static void no_op(struct percpu_ref *r) {}
+int mddev_init_writes_pending(struct mddev *mddev)
+{
+ if (mddev->writes_pending.percpu_count_ptr)
+ return 0;
+ if (percpu_ref_init(&mddev->writes_pending, no_op, 0, GFP_KERNEL) < 0)
+ return -ENOMEM;
+ /* We want to start with the refcount at zero */
+ percpu_ref_put(&mddev->writes_pending);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(mddev_init_writes_pending);
+
static int md_alloc(dev_t dev, char *name)
{
/*
blk_queue_make_request(mddev->queue, md_make_request);
blk_set_stacking_limits(&mddev->queue->limits);
- if (percpu_ref_init(&mddev->writes_pending, no_op, 0, GFP_KERNEL) < 0)
- goto abort;
- /* We want to start with the refcount at zero */
- percpu_ref_put(&mddev->writes_pending);
disk = alloc_disk(1 << shift);
if (!disk) {
blk_cleanup_queue(mddev->queue);
* may proceed without blocking. It is important to call this before
* attempting a GFP_KERNEL allocation while holding the mddev lock.
* Must be called with mddev_lock held.
- *
- * In the ->external case MD_SB_CHANGE_PENDING can not be cleared until mddev->lock
- * is dropped, so return -EAGAIN after notifying userspace.
*/
-int md_allow_write(struct mddev *mddev)
+void md_allow_write(struct mddev *mddev)
{
if (!mddev->pers)
- return 0;
+ return;
if (mddev->ro)
- return 0;
+ return;
if (!mddev->pers->sync_request)
- return 0;
+ return;
spin_lock(&mddev->lock);
if (mddev->in_sync) {
spin_unlock(&mddev->lock);
md_update_sb(mddev, 0);
sysfs_notify_dirent_safe(mddev->sysfs_state);
+ /* wait for the dirty state to be recorded in the metadata */
+ wait_event(mddev->sb_wait,
+ !test_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags) &&
+ !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));
} else
spin_unlock(&mddev->lock);
-
- if (test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags))
- return -EAGAIN;
- else
- return 0;
}
EXPORT_SYMBOL_GPL(md_allow_write);
extern void md_wakeup_thread(struct md_thread *thread);
extern void md_check_recovery(struct mddev *mddev);
extern void md_reap_sync_thread(struct mddev *mddev);
+extern int mddev_init_writes_pending(struct mddev *mddev);
extern void md_write_start(struct mddev *mddev, struct bio *bi);
extern void md_write_inc(struct mddev *mddev, struct bio *bi);
extern void md_write_end(struct mddev *mddev);
bool metadata_op);
extern void md_do_sync(struct md_thread *thread);
extern void md_new_event(struct mddev *mddev);
-extern int md_allow_write(struct mddev *mddev);
+extern void md_allow_write(struct mddev *mddev);
extern void md_wait_for_blocked_rdev(struct md_rdev *rdev, struct mddev *mddev);
extern void md_set_array_sectors(struct mddev *mddev, sector_t array_sectors);
extern int md_check_no_bitmap(struct mddev *mddev);
static int sm_disk_dec_block(struct dm_space_map *sm, dm_block_t b)
{
+ int r;
+ uint32_t old_count;
enum allocation_event ev;
struct sm_disk *smd = container_of(sm, struct sm_disk, sm);
- return sm_ll_dec(&smd->ll, b, &ev);
+ r = sm_ll_dec(&smd->ll, b, &ev);
+ if (!r && (ev == SM_FREE)) {
+ /*
+ * It's only free if it's also free in the last
+ * transaction.
+ */
+ r = sm_ll_lookup(&smd->old_ll, b, &old_count);
+ if (!r && !old_count)
+ smd->nr_allocated_this_transaction--;
+ }
+
+ return r;
}
static int sm_disk_new_block(struct dm_space_map *sm, dm_block_t *b)
blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors);
blk_queue_max_write_same_sectors(mddev->queue, mddev->chunk_sectors);
blk_queue_max_write_zeroes_sectors(mddev->queue, mddev->chunk_sectors);
- blk_queue_max_discard_sectors(mddev->queue, mddev->chunk_sectors);
+ blk_queue_max_discard_sectors(mddev->queue, UINT_MAX);
blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9);
blk_queue_io_opt(mddev->queue,
}
}
+static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)
+{
+ struct r0conf *conf = mddev->private;
+ struct strip_zone *zone;
+ sector_t start = bio->bi_iter.bi_sector;
+ sector_t end;
+ unsigned int stripe_size;
+ sector_t first_stripe_index, last_stripe_index;
+ sector_t start_disk_offset;
+ unsigned int start_disk_index;
+ sector_t end_disk_offset;
+ unsigned int end_disk_index;
+ unsigned int disk;
+
+ zone = find_zone(conf, &start);
+
+ if (bio_end_sector(bio) > zone->zone_end) {
+ struct bio *split = bio_split(bio,
+ zone->zone_end - bio->bi_iter.bi_sector, GFP_NOIO,
+ mddev->bio_set);
+ bio_chain(split, bio);
+ generic_make_request(bio);
+ bio = split;
+ end = zone->zone_end;
+ } else
+ end = bio_end_sector(bio);
+
+ if (zone != conf->strip_zone)
+ end = end - zone[-1].zone_end;
+
+ /* Now start and end is the offset in zone */
+ stripe_size = zone->nb_dev * mddev->chunk_sectors;
+
+ first_stripe_index = start;
+ sector_div(first_stripe_index, stripe_size);
+ last_stripe_index = end;
+ sector_div(last_stripe_index, stripe_size);
+
+ start_disk_index = (int)(start - first_stripe_index * stripe_size) /
+ mddev->chunk_sectors;
+ start_disk_offset = ((int)(start - first_stripe_index * stripe_size) %
+ mddev->chunk_sectors) +
+ first_stripe_index * mddev->chunk_sectors;
+ end_disk_index = (int)(end - last_stripe_index * stripe_size) /
+ mddev->chunk_sectors;
+ end_disk_offset = ((int)(end - last_stripe_index * stripe_size) %
+ mddev->chunk_sectors) +
+ last_stripe_index * mddev->chunk_sectors;
+
+ for (disk = 0; disk < zone->nb_dev; disk++) {
+ sector_t dev_start, dev_end;
+ struct bio *discard_bio = NULL;
+ struct md_rdev *rdev;
+
+ if (disk < start_disk_index)
+ dev_start = (first_stripe_index + 1) *
+ mddev->chunk_sectors;
+ else if (disk > start_disk_index)
+ dev_start = first_stripe_index * mddev->chunk_sectors;
+ else
+ dev_start = start_disk_offset;
+
+ if (disk < end_disk_index)
+ dev_end = (last_stripe_index + 1) * mddev->chunk_sectors;
+ else if (disk > end_disk_index)
+ dev_end = last_stripe_index * mddev->chunk_sectors;
+ else
+ dev_end = end_disk_offset;
+
+ if (dev_end <= dev_start)
+ continue;
+
+ rdev = conf->devlist[(zone - conf->strip_zone) *
+ conf->strip_zone[0].nb_dev + disk];
+ if (__blkdev_issue_discard(rdev->bdev,
+ dev_start + zone->dev_start + rdev->data_offset,
+ dev_end - dev_start, GFP_NOIO, 0, &discard_bio) ||
+ !discard_bio)
+ continue;
+ bio_chain(discard_bio, bio);
+ if (mddev->gendisk)
+ trace_block_bio_remap(bdev_get_queue(rdev->bdev),
+ discard_bio, disk_devt(mddev->gendisk),
+ bio->bi_iter.bi_sector);
+ generic_make_request(discard_bio);
+ }
+ bio_endio(bio);
+}
+
static void raid0_make_request(struct mddev *mddev, struct bio *bio)
{
struct strip_zone *zone;
return;
}
+ if (unlikely((bio_op(bio) == REQ_OP_DISCARD))) {
+ raid0_handle_discard(mddev, bio);
+ return;
+ }
+
bio_sector = bio->bi_iter.bi_sector;
sector = bio_sector;
chunk_sects = mddev->chunk_sectors;
bio->bi_iter.bi_sector = sector + zone->dev_start +
tmp_dev->data_offset;
- if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
- !blk_queue_discard(bdev_get_queue(bio->bi_bdev)))) {
- /* Just ignore it */
- bio_endio(bio);
- } else {
- if (mddev->gendisk)
- trace_block_bio_remap(bdev_get_queue(bio->bi_bdev),
- bio, disk_devt(mddev->gendisk),
- bio_sector);
- mddev_check_writesame(mddev, bio);
- mddev_check_write_zeroes(mddev, bio);
- generic_make_request(bio);
- }
+ if (mddev->gendisk)
+ trace_block_bio_remap(bdev_get_queue(bio->bi_bdev),
+ bio, disk_devt(mddev->gendisk),
+ bio_sector);
+ mddev_check_writesame(mddev, bio);
+ mddev_check_write_zeroes(mddev, bio);
+ generic_make_request(bio);
}
static void raid0_status(struct seq_file *seq, struct mddev *mddev)
break;
}
continue;
- } else
+ } else {
+ if ((sectors > best_good_sectors) && (best_disk >= 0))
+ best_disk = -1;
best_good_sectors = sectors;
+ }
if (best_disk >= 0)
/* At least two disks to choose from so failfast is OK */
plug = container_of(cb, struct raid1_plug_cb, cb);
else
plug = NULL;
- spin_lock_irqsave(&conf->device_lock, flags);
if (plug) {
bio_list_add(&plug->pending, mbio);
plug->pending_cnt++;
} else {
+ spin_lock_irqsave(&conf->device_lock, flags);
bio_list_add(&conf->pending_bio_list, mbio);
conf->pending_count++;
- }
- spin_unlock_irqrestore(&conf->device_lock, flags);
- if (!plug)
+ spin_unlock_irqrestore(&conf->device_lock, flags);
md_wakeup_thread(mddev->thread);
+ }
}
r1_bio_write_done(r1_bio);
mdname(mddev));
return -EIO;
}
+ if (mddev_init_writes_pending(mddev) < 0)
+ return -ENOMEM;
/*
* copy the already verified devices into our private RAID1
* bookkeeping area. [whatever we allocate in run(),
struct r1conf *conf = mddev->private;
int cnt, raid_disks;
unsigned long flags;
- int d, d2, err;
+ int d, d2;
/* Cannot change chunk_size, layout, or level */
if (mddev->chunk_sectors != mddev->new_chunk_sectors ||
return -EINVAL;
}
- if (!mddev_is_clustered(mddev)) {
- err = md_allow_write(mddev);
- if (err)
- return err;
- }
+ if (!mddev_is_clustered(mddev))
+ md_allow_write(mddev);
raid_disks = mddev->raid_disks + mddev->delta_disks;
plug = container_of(cb, struct raid10_plug_cb, cb);
else
plug = NULL;
- spin_lock_irqsave(&conf->device_lock, flags);
if (plug) {
bio_list_add(&plug->pending, mbio);
plug->pending_cnt++;
} else {
+ spin_lock_irqsave(&conf->device_lock, flags);
bio_list_add(&conf->pending_bio_list, mbio);
conf->pending_count++;
- }
- spin_unlock_irqrestore(&conf->device_lock, flags);
- if (!plug)
+ spin_unlock_irqrestore(&conf->device_lock, flags);
md_wakeup_thread(mddev->thread);
+ }
}
static void raid10_write_request(struct mddev *mddev, struct bio *bio,
int first = 1;
bool discard_supported = false;
+ if (mddev_init_writes_pending(mddev) < 0)
+ return -ENOMEM;
+
if (mddev->private == NULL) {
conf = setup_conf(mddev);
if (IS_ERR(conf))
#include "md.h"
#include "raid5.h"
#include "bitmap.h"
+#include "raid5-log.h"
/*
* metadata/data stored in disk with 4k size unit (a block) regardless
__r5l_set_io_unit_state(io, IO_UNIT_IO_START);
spin_unlock_irqrestore(&log->io_list_lock, flags);
+ /*
+ * In case of journal device failures, submit_bio will get error
+ * and calls endio, then active stripes will continue write
+ * process. Therefore, it is not necessary to check Faulty bit
+ * of journal device here.
+ *
+ * We can't check split_bio after current_bio is submitted. If
+ * io->split_bio is null, after current_bio is submitted, current_bio
+ * might already be completed and the io_unit is freed. We submit
+ * split_bio first to avoid the issue.
+ */
+ if (io->split_bio) {
+ if (io->has_flush)
+ io->split_bio->bi_opf |= REQ_PREFLUSH;
+ if (io->has_fua)
+ io->split_bio->bi_opf |= REQ_FUA;
+ submit_bio(io->split_bio);
+ }
+
if (io->has_flush)
io->current_bio->bi_opf |= REQ_PREFLUSH;
if (io->has_fua)
io->current_bio->bi_opf |= REQ_FUA;
submit_bio(io->current_bio);
-
- if (!io->split_bio)
- return;
-
- if (io->has_flush)
- io->split_bio->bi_opf |= REQ_PREFLUSH;
- if (io->has_fua)
- io->split_bio->bi_opf |= REQ_FUA;
- submit_bio(io->split_bio);
}
/* deferred io_unit will be dispatched here */
return;
pr_info("md/raid:%s: Disabling writeback cache for degraded array.\n",
mdname(mddev));
+
+ /* wait superblock change before suspend */
+ wait_event(mddev->sb_wait,
+ !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));
+
mddev_suspend(mddev);
log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_THROUGH;
mddev_resume(mddev);
mb->checksum = cpu_to_le32(crc32c_le(log->uuid_checksum,
mb, PAGE_SIZE));
if (!sync_page_io(log->rdev, pos, PAGE_SIZE, page, REQ_OP_WRITE,
- REQ_FUA, false)) {
+ REQ_SYNC | REQ_FUA, false)) {
__free_page(page);
return -EIO;
}
mb->checksum = cpu_to_le32(crc32c_le(log->uuid_checksum,
mb, PAGE_SIZE));
sync_page_io(log->rdev, ctx->pos, PAGE_SIZE, page,
- REQ_OP_WRITE, REQ_FUA, false);
+ REQ_OP_WRITE, REQ_SYNC | REQ_FUA, false);
sh->log_start = ctx->pos;
list_add_tail(&sh->r5c, &log->stripe_in_journal_list);
atomic_inc(&log->stripe_in_journal_count);
* When run in degraded mode, array is set to write-through mode.
* This check helps drain pending write safely in the transition to
* write-through mode.
+ *
+ * When a stripe is syncing, the write is also handled in write
+ * through mode.
*/
- if (s->failed) {
+ if (s->failed || test_bit(STRIPE_SYNCING, &sh->state)) {
r5c_make_stripe_write_out(sh);
return -EAGAIN;
}
}
r5l_append_flush_payload(log, sh->sector);
+ /* stripe is flused to raid disks, we can do resync now */
+ if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state))
+ set_bit(STRIPE_HANDLE, &sh->state);
}
int r5c_cache_data(struct r5l_log *log, struct stripe_head *sh)
return ret;
}
-void r5c_update_on_rdev_error(struct mddev *mddev)
+void r5c_update_on_rdev_error(struct mddev *mddev, struct md_rdev *rdev)
{
struct r5conf *conf = mddev->private;
struct r5l_log *log = conf->log;
if (!log)
return;
- if (raid5_calc_degraded(conf) > 0 &&
+ if ((raid5_calc_degraded(conf) > 0 ||
+ test_bit(Journal, &rdev->flags)) &&
conf->log->r5c_journal_mode == R5C_JOURNAL_MODE_WRITE_BACK)
schedule_work(&log->disable_writeback_work);
}
extern void r5c_check_stripe_cache_usage(struct r5conf *conf);
extern void r5c_check_cached_full_stripe(struct r5conf *conf);
extern struct md_sysfs_entry r5c_journal_mode;
-extern void r5c_update_on_rdev_error(struct mddev *mddev);
+extern void r5c_update_on_rdev_error(struct mddev *mddev,
+ struct md_rdev *rdev);
extern bool r5c_big_stripe_cached(struct r5conf *conf, sector_t sect);
extern struct dma_async_tx_descriptor *
pplhdr->checksum = cpu_to_le32(~crc32c_le(~0, pplhdr, PAGE_SIZE));
if (!sync_page_io(rdev, rdev->ppl.sector - rdev->data_offset,
- PPL_HEADER_SIZE, page, REQ_OP_WRITE | REQ_FUA, 0,
- false)) {
+ PPL_HEADER_SIZE, page, REQ_OP_WRITE | REQ_SYNC |
+ REQ_FUA, 0, false)) {
md_error(rdev->mddev, rdev);
ret = -EIO;
}
static inline void lock_all_device_hash_locks_irq(struct r5conf *conf)
{
int i;
- local_irq_disable();
- spin_lock(conf->hash_locks);
+ spin_lock_irq(conf->hash_locks);
for (i = 1; i < NR_STRIPE_HASH_LOCKS; i++)
spin_lock_nest_lock(conf->hash_locks + i, conf->hash_locks);
spin_lock(&conf->device_lock);
{
int i;
spin_unlock(&conf->device_lock);
- for (i = NR_STRIPE_HASH_LOCKS; i; i--)
- spin_unlock(conf->hash_locks + i - 1);
- local_irq_enable();
+ for (i = NR_STRIPE_HASH_LOCKS - 1; i; i--)
+ spin_unlock(conf->hash_locks + i);
+ spin_unlock_irq(conf->hash_locks);
}
/* Find first data disk in a raid6 stripe */
if (test_bit(R5_InJournal, &sh->dev[i].flags))
injournal++;
/*
- * When quiesce in r5c write back, set STRIPE_HANDLE for stripes with
- * data in journal, so they are not released to cached lists
+ * In the following cases, the stripe cannot be released to cached
+ * lists. Therefore, we make the stripe write out and set
+ * STRIPE_HANDLE:
+ * 1. when quiesce in r5c write back;
+ * 2. when resync is requested fot the stripe.
*/
- if (conf->quiesce && r5c_is_writeback(conf->log) &&
- !test_bit(STRIPE_HANDLE, &sh->state) && injournal != 0) {
+ if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state) ||
+ (conf->quiesce && r5c_is_writeback(conf->log) &&
+ !test_bit(STRIPE_HANDLE, &sh->state) && injournal != 0)) {
if (test_bit(STRIPE_R5C_CACHING, &sh->state))
r5c_make_stripe_write_out(sh);
set_bit(STRIPE_HANDLE, &sh->state);
static void lock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2)
{
- local_irq_disable();
if (sh1 > sh2) {
- spin_lock(&sh2->stripe_lock);
+ spin_lock_irq(&sh2->stripe_lock);
spin_lock_nested(&sh1->stripe_lock, 1);
} else {
- spin_lock(&sh1->stripe_lock);
+ spin_lock_irq(&sh1->stripe_lock);
spin_lock_nested(&sh2->stripe_lock, 1);
}
}
static void unlock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2)
{
spin_unlock(&sh1->stripe_lock);
- spin_unlock(&sh2->stripe_lock);
- local_irq_enable();
+ spin_unlock_irq(&sh2->stripe_lock);
}
/* Only freshly new full stripe normal write stripe can be added to a batch list */
struct stripe_head *osh, *nsh;
LIST_HEAD(newstripes);
struct disk_info *ndisks;
- int err;
+ int err = 0;
struct kmem_cache *sc;
int i;
int hash, cnt;
- err = md_allow_write(conf->mddev);
- if (err)
- return err;
+ md_allow_write(conf->mddev);
/* Step 1 */
sc = kmem_cache_create(conf->cache_name[1-conf->active_name],
bdevname(rdev->bdev, b),
mdname(mddev),
conf->raid_disks - mddev->degraded);
- r5c_update_on_rdev_error(mddev);
+ r5c_update_on_rdev_error(mddev, rdev);
}
/*
* When LOG_CRITICAL, stripes with injournal == 0 will be sent to
* no_space_stripes list.
*
+ * 3. during journal failure
+ * In journal failure, we try to flush all cached data to raid disks
+ * based on data in stripe cache. The array is read-only to upper
+ * layers, so we would skip all pending writes.
+ *
*/
static inline bool delay_towrite(struct r5conf *conf,
struct r5dev *dev,
if (test_bit(R5C_LOG_CRITICAL, &conf->cache_state) &&
s->injournal > 0)
return true;
+ /* case 3 above */
+ if (s->log_failed && s->injournal)
+ return true;
return false;
}
set_bit(STRIPE_INSYNC, &sh->state);
else {
atomic64_add(STRIPE_SECTORS, &conf->mddev->resync_mismatches);
- if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery))
+ if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery)) {
/* don't try to repair!! */
set_bit(STRIPE_INSYNC, &sh->state);
- else {
+ pr_warn_ratelimited("%s: mismatch sector in range "
+ "%llu-%llu\n", mdname(conf->mddev),
+ (unsigned long long) sh->sector,
+ (unsigned long long) sh->sector +
+ STRIPE_SECTORS);
+ } else {
sh->check_state = check_state_compute_run;
set_bit(STRIPE_COMPUTE_RUN, &sh->state);
set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request);
}
} else {
atomic64_add(STRIPE_SECTORS, &conf->mddev->resync_mismatches);
- if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery))
+ if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery)) {
/* don't try to repair!! */
set_bit(STRIPE_INSYNC, &sh->state);
- else {
+ pr_warn_ratelimited("%s: mismatch sector in range "
+ "%llu-%llu\n", mdname(conf->mddev),
+ (unsigned long long) sh->sector,
+ (unsigned long long) sh->sector +
+ STRIPE_SECTORS);
+ } else {
int *target = &sh->ops.target;
sh->ops.target = -1;
if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state) && !sh->batch_head) {
spin_lock(&sh->stripe_lock);
- /* Cannot process 'sync' concurrently with 'discard' */
- if (!test_bit(STRIPE_DISCARD, &sh->state) &&
+ /*
+ * Cannot process 'sync' concurrently with 'discard'.
+ * Flush data in r5cache before 'sync'.
+ */
+ if (!test_bit(STRIPE_R5C_PARTIAL_STRIPE, &sh->state) &&
+ !test_bit(STRIPE_R5C_FULL_STRIPE, &sh->state) &&
+ !test_bit(STRIPE_DISCARD, &sh->state) &&
test_and_clear_bit(STRIPE_SYNC_REQUESTED, &sh->state)) {
set_bit(STRIPE_SYNCING, &sh->state);
clear_bit(STRIPE_INSYNC, &sh->state);
" to_write=%d failed=%d failed_num=%d,%d\n",
s.locked, s.uptodate, s.to_read, s.to_write, s.failed,
s.failed_num[0], s.failed_num[1]);
- /* check if the array has lost more than max_degraded devices and,
+ /*
+ * check if the array has lost more than max_degraded devices and,
* if so, some requests might need to be failed.
+ *
+ * When journal device failed (log_failed), we will only process
+ * the stripe if there is data need write to raid disks
*/
- if (s.failed > conf->max_degraded || s.log_failed) {
+ if (s.failed > conf->max_degraded ||
+ (s.log_failed && s.injournal == 0)) {
sh->check_state = 0;
sh->reconstruct_state = 0;
break_stripe_batch_list(sh, 0);
struct stripe_head *sh, *tmp;
struct list_head *handle_list = NULL;
struct r5worker_group *wg;
- bool second_try = !r5c_is_writeback(conf->log);
- bool try_loprio = test_bit(R5C_LOG_TIGHT, &conf->cache_state);
+ bool second_try = !r5c_is_writeback(conf->log) &&
+ !r5l_log_disk_error(conf);
+ bool try_loprio = test_bit(R5C_LOG_TIGHT, &conf->cache_state) ||
+ r5l_log_disk_error(conf);
again:
wg = NULL;
raid5_set_cache_size(struct mddev *mddev, int size)
{
struct r5conf *conf = mddev->private;
- int err;
if (size <= 16 || size > 32768)
return -EINVAL;
;
mutex_unlock(&conf->cache_size_mutex);
-
- err = md_allow_write(mddev);
- if (err)
- return err;
+ md_allow_write(mddev);
mutex_lock(&conf->cache_size_mutex);
while (size > conf->max_nr_stripes)
long long min_offset_diff = 0;
int first = 1;
+ if (mddev_init_writes_pending(mddev) < 0)
+ return -ENOMEM;
+
if (mddev->recovery_cp != MaxSector)
pr_notice("md/raid:%s: not clean -- starting background reconstruction\n",
mdname(mddev));
* neilb: there is no locking about new writes here,
* so this cannot be safe.
*/
- if (atomic_read(&conf->active_stripes)) {
+ if (atomic_read(&conf->active_stripes) ||
+ atomic_read(&conf->r5c_cached_full_stripes) ||
+ atomic_read(&conf->r5c_cached_partial_stripes)) {
return -EBUSY;
}
log_exit(conf);
# Multimedia device configuration
#
+config CEC_CORE
+ tristate
+
+config CEC_NOTIFIER
+ bool
+
menuconfig MEDIA_SUPPORT
tristate "Multimedia support"
depends on HAS_IOMEM
media-objs := media-device.o media-devnode.o media-entity.o
-obj-$(CONFIG_CEC_CORE) += cec/
-
#
# I2C drivers should come before other drivers, otherwise they'll fail
# when compiled as builtin drivers
# There are both core and drivers at RC subtree - merge before drivers
obj-y += rc/
+obj-$(CONFIG_CEC_CORE) += cec/
+
#
# Finally, merge the drivers that require the core
#
-config CEC_CORE
- tristate
- depends on MEDIA_CEC_SUPPORT
- default y
-
-config MEDIA_CEC_NOTIFIER
- bool
-
config MEDIA_CEC_RC
bool "HDMI CEC RC integration"
depends on CEC_CORE && RC_CORE
---help---
Pass on CEC remote control messages to the RC framework.
-
-config MEDIA_CEC_DEBUG
- bool "HDMI CEC debugfs interface"
- depends on CEC_CORE && DEBUG_FS
- ---help---
- Turns on the DebugFS interface for CEC devices.
cec-objs := cec-core.o cec-adap.o cec-api.o cec-edid.o
-ifeq ($(CONFIG_MEDIA_CEC_NOTIFIER),y)
+ifeq ($(CONFIG_CEC_NOTIFIER),y)
cec-objs += cec-notifier.o
endif
WARN_ON(call_op(adap, adap_monitor_all_enable, 0));
}
-#ifdef CONFIG_MEDIA_CEC_DEBUG
+#ifdef CONFIG_DEBUG_FS
/*
* Log the current state of the CEC adapter.
* Very useful for debugging.
put_device(&devnode->dev);
}
-#ifdef CONFIG_MEDIA_CEC_NOTIFIER
+#ifdef CONFIG_CEC_NOTIFIER
static void cec_cec_notify(struct cec_adapter *adap, u16 pa)
{
cec_s_phys_addr(adap, pa, false);
}
dev_set_drvdata(&adap->devnode.dev, adap);
-#ifdef CONFIG_MEDIA_CEC_DEBUG
+#ifdef CONFIG_DEBUG_FS
if (!top_cec_dir)
return 0;
adap->rc = NULL;
#endif
debugfs_remove_recursive(adap->cec_dir);
-#ifdef CONFIG_MEDIA_CEC_NOTIFIER
+#ifdef CONFIG_CEC_NOTIFIER
if (adap->notifier)
cec_notifier_unregister(adap->notifier);
#endif
return ret;
}
-#ifdef CONFIG_MEDIA_CEC_DEBUG
+#ifdef CONFIG_DEBUG_FS
top_cec_dir = debugfs_create_dir("cec", NULL);
if (IS_ERR_OR_NULL(top_cec_dir)) {
pr_warn("cec: Failed to create debugfs cec dir\n");
config VIDEO_ADV7604_CEC
bool "Enable Analog Devices ADV7604 CEC support"
- depends on VIDEO_ADV7604 && CEC_CORE
+ depends on VIDEO_ADV7604
+ select CEC_CORE
---help---
When selected the adv7604 will support the optional
HDMI CEC feature.
config VIDEO_ADV7842_CEC
bool "Enable Analog Devices ADV7842 CEC support"
- depends on VIDEO_ADV7842 && CEC_CORE
+ depends on VIDEO_ADV7842
+ select CEC_CORE
---help---
When selected the adv7842 will support the optional
HDMI CEC feature.
config VIDEO_ADV7511_CEC
bool "Enable Analog Devices ADV7511 CEC support"
- depends on VIDEO_ADV7511 && CEC_CORE
+ depends on VIDEO_ADV7511
+ select CEC_CORE
---help---
When selected the adv7511 will support the optional
HDMI CEC feature.
config VIDEO_SAMSUNG_S5P_CEC
tristate "Samsung S5P CEC driver"
- depends on CEC_CORE && (PLAT_S5P || ARCH_EXYNOS || COMPILE_TEST)
- select MEDIA_CEC_NOTIFIER
+ depends on PLAT_S5P || ARCH_EXYNOS || COMPILE_TEST
+ select CEC_CORE
+ select CEC_NOTIFIER
---help---
This is a driver for Samsung S5P HDMI CEC interface. It uses the
generic CEC framework interface.
config VIDEO_STI_HDMI_CEC
tristate "STMicroelectronics STiH4xx HDMI CEC driver"
- depends on CEC_CORE && (ARCH_STI || COMPILE_TEST)
- select MEDIA_CEC_NOTIFIER
+ depends on ARCH_STI || COMPILE_TEST
+ select CEC_CORE
+ select CEC_NOTIFIER
---help---
This is a driver for STIH4xx HDMI CEC interface. It uses the
generic CEC framework interface.
}
static struct vdec_common_if vdec_h264_if = {
- vdec_h264_init,
- vdec_h264_decode,
- vdec_h264_get_param,
- vdec_h264_deinit,
+ .init = vdec_h264_init,
+ .decode = vdec_h264_decode,
+ .get_param = vdec_h264_get_param,
+ .deinit = vdec_h264_deinit,
};
struct vdec_common_if *get_h264_dec_comm_if(void);
}
static struct vdec_common_if vdec_vp8_if = {
- vdec_vp8_init,
- vdec_vp8_decode,
- vdec_vp8_get_param,
- vdec_vp8_deinit,
+ .init = vdec_vp8_init,
+ .decode = vdec_vp8_decode,
+ .get_param = vdec_vp8_get_param,
+ .deinit = vdec_vp8_deinit,
};
struct vdec_common_if *get_vp8_dec_comm_if(void);
}
static struct vdec_common_if vdec_vp9_if = {
- vdec_vp9_init,
- vdec_vp9_decode,
- vdec_vp9_get_param,
- vdec_vp9_deinit,
+ .init = vdec_vp9_init,
+ .decode = vdec_vp9_decode,
+ .get_param = vdec_vp9_get_param,
+ .deinit = vdec_vp9_deinit,
};
struct vdec_common_if *get_vp9_dec_comm_if(void);
config VIDEO_VIVID_CEC
bool "Enable CEC emulation support"
- depends on VIDEO_VIVID && CEC_CORE
+ depends on VIDEO_VIVID
+ select CEC_CORE
---help---
When selected the vivid module will emulate the optional
HDMI CEC feature.
*/
void ir_raw_event_handle(struct rc_dev *dev)
{
- if (!dev->raw)
+ if (!dev->raw || !dev->raw->thread)
return;
wake_up_process(dev->raw->thread);
{
int rc;
struct ir_raw_handler *handler;
+ struct task_struct *thread;
if (!dev)
return -EINVAL;
* because the event is coming from userspace
*/
if (dev->driver_type != RC_DRIVER_IR_RAW_TX) {
- dev->raw->thread = kthread_run(ir_raw_event_thread, dev->raw,
- "rc%u", dev->minor);
+ thread = kthread_run(ir_raw_event_thread, dev->raw, "rc%u",
+ dev->minor);
- if (IS_ERR(dev->raw->thread)) {
- rc = PTR_ERR(dev->raw->thread);
+ if (IS_ERR(thread)) {
+ rc = PTR_ERR(thread);
goto out;
}
+
+ dev->raw->thread = thread;
}
mutex_lock(&ir_raw_handler_lock);
config USB_PULSE8_CEC
tristate "Pulse Eight HDMI CEC"
- depends on USB_ACM && CEC_CORE
+ depends on USB_ACM
+ select CEC_CORE
select SERIO
select SERIO_SERPORT
---help---
config USB_RAINSHADOW_CEC
tristate "RainShadow Tech HDMI CEC"
- depends on USB_ACM && CEC_CORE
+ depends on USB_ACM
+ select CEC_CORE
select SERIO
select SERIO_SERPORT
---help---
while (true) {
unsigned long flags;
- bool exit_loop;
+ bool exit_loop = false;
char data;
spin_lock_irqsave(&rain->buf_lock, flags);
return of_platform_populate(np, NULL, NULL, dev);
}
-static int atmel_ebi_resume(struct device *dev)
+static __maybe_unused int atmel_ebi_resume(struct device *dev)
{
struct atmel_ebi *ebi = dev_get_drvdata(dev);
struct atmel_ebi_dev *ebid;
pr_info("gpmc cs%i access configuration:\n", cs);
GPMC_GET_RAW_BOOL(GPMC_CS_CONFIG1, 4, 4, "time-para-granularity");
GPMC_GET_RAW(GPMC_CS_CONFIG1, 8, 9, "mux-add-data");
- GPMC_GET_RAW_MAX(GPMC_CS_CONFIG1, 12, 13,
+ GPMC_GET_RAW_SHIFT_MAX(GPMC_CS_CONFIG1, 12, 13, 1,
GPMC_CONFIG1_DEVICESIZE_MAX, "device-width");
GPMC_GET_RAW(GPMC_CS_CONFIG1, 16, 17, "wait-pin");
GPMC_GET_RAW_BOOL(GPMC_CS_CONFIG1, 21, 21, "wait-on-write");
config PCI_ENDPOINT_TEST
depends on PCI
+ select CRC32
tristate "PCI Endpoint Test driver"
---help---
Enable this configuration option to enable the host side test driver
/* Do this outside the status_mutex to avoid a circular dependency with
* the locking in cxl_mmap_fault() */
- if (copy_from_user(&work, uwork,
- sizeof(struct cxl_ioctl_start_work))) {
- rc = -EFAULT;
- goto out;
- }
+ if (copy_from_user(&work, uwork, sizeof(work)))
+ return -EFAULT;
mutex_lock(&ctx->status_mutex);
if (ctx->status != OPENED) {
void cxl_native_release_psl_err_irq(struct cxl *adapter)
{
- if (adapter->native->err_virq != irq_find_mapping(NULL, adapter->native->err_hwirq))
+ if (adapter->native->err_virq == 0 ||
+ adapter->native->err_virq !=
+ irq_find_mapping(NULL, adapter->native->err_hwirq))
return;
cxl_p1_write(adapter, CXL_PSL_ErrIVTE, 0x0000000000000000);
cxl_unmap_irq(adapter->native->err_virq, adapter);
cxl_ops->release_one_irq(adapter, adapter->native->err_hwirq);
kfree(adapter->irq_name);
+ adapter->native->err_virq = 0;
}
int cxl_native_register_serr_irq(struct cxl_afu *afu)
void cxl_native_release_serr_irq(struct cxl_afu *afu)
{
- if (afu->serr_virq != irq_find_mapping(NULL, afu->serr_hwirq))
+ if (afu->serr_virq == 0 ||
+ afu->serr_virq != irq_find_mapping(NULL, afu->serr_hwirq))
return;
cxl_p1n_write(afu, CXL_PSL_SERR_An, 0x0000000000000000);
cxl_unmap_irq(afu->serr_virq, afu);
cxl_ops->release_one_irq(afu->adapter, afu->serr_hwirq);
kfree(afu->err_irq_name);
+ afu->serr_virq = 0;
}
int cxl_native_register_psl_irq(struct cxl_afu *afu)
void cxl_native_release_psl_irq(struct cxl_afu *afu)
{
- if (afu->native->psl_virq != irq_find_mapping(NULL, afu->native->psl_hwirq))
+ if (afu->native->psl_virq == 0 ||
+ afu->native->psl_virq !=
+ irq_find_mapping(NULL, afu->native->psl_hwirq))
return;
cxl_unmap_irq(afu->native->psl_virq, afu);
cxl_ops->release_one_irq(afu->adapter, afu->native->psl_hwirq);
kfree(afu->psl_irq_name);
+ afu->native->psl_virq = 0;
}
static void recover_psl_err(struct cxl_afu *afu, u64 errstat)
{
struct mei_cl_device *cldev = to_mei_cl_device(dev);
const uuid_le *uuid = mei_me_cl_uuid(cldev->me_cl);
+ u8 version = mei_me_cl_ver(cldev->me_cl);
- return scnprintf(buf, PAGE_SIZE, "mei:%s:%pUl:", cldev->name, uuid);
+ return scnprintf(buf, PAGE_SIZE, "mei:%s:%pUl:%02X:",
+ cldev->name, uuid, version);
}
static DEVICE_ATTR_RO(modalias);
xpc_send(short partid, int ch_number, u32 flags, void *payload,
u16 payload_size)
{
+ if (!xpc_interface.send)
+ return xpNotLoaded;
+
return xpc_interface.send(partid, ch_number, flags, payload,
payload_size);
}
xpc_send_notify(short partid, int ch_number, u32 flags, void *payload,
u16 payload_size, xpc_notify_func func, void *key)
{
+ if (!xpc_interface.send_notify)
+ return xpNotLoaded;
+
return xpc_interface.send_notify(partid, ch_number, flags, payload,
payload_size, func, key);
}
static inline void
xpc_received(short partid, int ch_number, void *payload)
{
- return xpc_interface.received(partid, ch_number, payload);
+ if (xpc_interface.received)
+ xpc_interface.received(partid, ch_number, payload);
}
static inline enum xp_retval
xpc_partid_to_nasids(short partid, void *nasids)
{
+ if (!xpc_interface.partid_to_nasids)
+ return xpNotLoaded;
+
return xpc_interface.partid_to_nasids(partid, nasids);
}
EXPORT_SYMBOL_GPL(xpc_registrations);
/*
- * Initialize the XPC interface to indicate that XPC isn't loaded.
+ * Initialize the XPC interface to NULL to indicate that XPC isn't loaded.
*/
-static enum xp_retval
-xpc_notloaded(void)
-{
- return xpNotLoaded;
-}
-
-struct xpc_interface xpc_interface = {
- (void (*)(int))xpc_notloaded,
- (void (*)(int))xpc_notloaded,
- (enum xp_retval(*)(short, int, u32, void *, u16))xpc_notloaded,
- (enum xp_retval(*)(short, int, u32, void *, u16, xpc_notify_func,
- void *))xpc_notloaded,
- (void (*)(short, int, void *))xpc_notloaded,
- (enum xp_retval(*)(short, void *))xpc_notloaded
-};
+struct xpc_interface xpc_interface = { };
EXPORT_SYMBOL_GPL(xpc_interface);
/*
void
xpc_clear_interface(void)
{
- xpc_interface.connect = (void (*)(int))xpc_notloaded;
- xpc_interface.disconnect = (void (*)(int))xpc_notloaded;
- xpc_interface.send = (enum xp_retval(*)(short, int, u32, void *, u16))
- xpc_notloaded;
- xpc_interface.send_notify = (enum xp_retval(*)(short, int, u32, void *,
- u16, xpc_notify_func,
- void *))xpc_notloaded;
- xpc_interface.received = (void (*)(short, int, void *))
- xpc_notloaded;
- xpc_interface.partid_to_nasids = (enum xp_retval(*)(short, void *))
- xpc_notloaded;
+ memset(&xpc_interface, 0, sizeof(xpc_interface));
}
EXPORT_SYMBOL_GPL(xpc_clear_interface);
mutex_unlock(®istration->mutex);
- xpc_interface.connect(ch_number);
+ if (xpc_interface.connect)
+ xpc_interface.connect(ch_number);
return xpSuccess;
}
registration->assigned_limit = 0;
registration->idle_limit = 0;
- xpc_interface.disconnect(ch_number);
+ if (xpc_interface.disconnect)
+ xpc_interface.disconnect(ch_number);
mutex_unlock(®istration->mutex);
struct mmc_pwrseq pwrseq;
bool clk_enabled;
u32 post_power_on_delay_ms;
+ u32 power_off_delay_us;
struct clk *ext_clk;
struct gpio_descs *reset_gpios;
};
mmc_pwrseq_simple_set_gpios_value(pwrseq, 1);
+ if (pwrseq->power_off_delay_us)
+ usleep_range(pwrseq->power_off_delay_us,
+ 2 * pwrseq->power_off_delay_us);
+
if (!IS_ERR(pwrseq->ext_clk) && pwrseq->clk_enabled) {
clk_disable_unprepare(pwrseq->ext_clk);
pwrseq->clk_enabled = false;
device_property_read_u32(dev, "post-power-on-delay-ms",
&pwrseq->post_power_on_delay_ms);
+ device_property_read_u32(dev, "power-off-delay-us",
+ &pwrseq->power_off_delay_us);
pwrseq->pwrseq.dev = dev;
pwrseq->pwrseq.ops = &mmc_pwrseq_simple_ops;
static void octeon_mmc_int_enable(struct cvm_mmc_host *host, u64 val)
{
writeq(val, host->base + MIO_EMM_INT(host));
- if (!host->dma_active || (host->dma_active && !host->has_ciu3))
+ if (!host->has_ciu3)
writeq(val, host->base + MIO_EMM_INT_EN(host));
}
}
host->global_pwr_gpiod = devm_gpiod_get_optional(&pdev->dev,
- "power-gpios",
+ "power",
GPIOD_OUT_HIGH);
if (IS_ERR(host->global_pwr_gpiod)) {
dev_err(&pdev->dev, "Invalid power GPIO\n");
if (ret) {
dev_err(&pdev->dev, "Error populating slots\n");
octeon_mmc_set_shared_power(host, 0);
- return ret;
+ goto error;
}
i++;
}
return 0;
+
+error:
+ for (i = 0; i < CAVIUM_MAX_MMC; i++) {
+ if (host->slot[i])
+ cvm_mmc_of_slot_remove(host->slot[i]);
+ if (host->slot_pdev[i])
+ of_platform_device_destroy(&host->slot_pdev[i]->dev, NULL);
+ }
+ return ret;
}
static int octeon_mmc_remove(struct platform_device *pdev)
return 0;
error:
+ for (i = 0; i < CAVIUM_MAX_MMC; i++) {
+ if (host->slot[i])
+ cvm_mmc_of_slot_remove(host->slot[i]);
+ if (host->slot_pdev[i])
+ of_platform_device_destroy(&host->slot_pdev[i]->dev, NULL);
+ }
clk_disable_unprepare(host->clk);
return ret;
}
cvm_mmc_reset_bus(slot);
if (host->global_pwr_gpiod)
host->set_shared_power(host, 0);
- else
+ else if (!IS_ERR(mmc->supply.vmmc))
mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, 0);
break;
case MMC_POWER_UP:
if (host->global_pwr_gpiod)
host->set_shared_power(host, 1);
- else
+ else if (!IS_ERR(mmc->supply.vmmc))
mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, ios->vdd);
break;
}
return -EINVAL;
}
- mmc->supply.vmmc = devm_regulator_get_optional(dev, "vmmc");
- if (IS_ERR(mmc->supply.vmmc)) {
- if (PTR_ERR(mmc->supply.vmmc) == -EPROBE_DEFER)
- return -EPROBE_DEFER;
- /*
- * Legacy Octeon firmware has no regulator entry, fall-back to
- * a hard-coded voltage to get a sane OCR.
- */
+ ret = mmc_regulator_get_supply(mmc);
+ if (ret == -EPROBE_DEFER)
+ return ret;
+ /*
+ * Legacy Octeon firmware has no regulator entry, fall-back to
+ * a hard-coded voltage to get a sane OCR.
+ */
+ if (IS_ERR(mmc->supply.vmmc))
mmc->ocr_avail = MMC_VDD_32_33 | MMC_VDD_33_34;
- } else {
- ret = mmc_regulator_get_ocrmask(mmc->supply.vmmc);
- if (ret > 0)
- mmc->ocr_avail = ret;
- }
/* Common MMC bindings */
ret = mmc_of_parse(mmc);
};
static const struct sdhci_pltfm_data sdhci_iproc_pltfm_data = {
- .quirks = SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK,
+ .quirks = SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK |
+ SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12,
.quirks2 = SDHCI_QUIRK2_ACMD23_BROKEN,
.ops = &sdhci_iproc_ops,
};
return ret;
}
-void xenon_clean_phy(struct sdhci_host *host)
-{
- struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
- struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host);
-
- kfree(priv->phy_params);
-}
-
static int xenon_add_phy(struct device_node *np, struct sdhci_host *host,
const char *phy_name)
{
if (ret)
return ret;
- ret = xenon_emmc_phy_parse_param_dt(host, np, priv->phy_params);
- if (ret)
- xenon_clean_phy(host);
-
- return ret;
+ return xenon_emmc_phy_parse_param_dt(host, np, priv->phy_params);
}
int xenon_phy_parse_dt(struct device_node *np, struct sdhci_host *host)
err = xenon_sdhc_prepare(host);
if (err)
- goto clean_phy_param;
+ goto err_clk;
err = sdhci_add_host(host);
if (err)
remove_sdhc:
xenon_sdhc_unprepare(host);
-clean_phy_param:
- xenon_clean_phy(host);
err_clk:
clk_disable_unprepare(pltfm_host->clk);
free_pltfm:
struct sdhci_host *host = platform_get_drvdata(pdev);
struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
- xenon_clean_phy(host);
-
sdhci_remove_host(host, 0);
xenon_sdhc_unprepare(host);
};
int xenon_phy_adj(struct sdhci_host *host, struct mmc_ios *ios);
-void xenon_clean_phy(struct sdhci_host *host);
int xenon_phy_parse_dt(struct device_node *np,
struct sdhci_host *host);
void xenon_soc_pad_ctrl(struct sdhci_host *host,
return 0;
}
-const struct mtd_ooblayout_ops nand_ooblayout_lp_hamming_ops = {
+static const struct mtd_ooblayout_ops nand_ooblayout_lp_hamming_ops = {
.ecc = nand_ooblayout_ecc_lp_hamming,
.free = nand_ooblayout_free_lp_hamming,
};
/* Initialize the ->data_interface field. */
ret = nand_init_data_interface(chip);
if (ret)
- return ret;
+ goto err_nand_init;
/*
* Setup the data interface correctly on the chip and controller side.
*/
ret = nand_setup_data_interface(chip);
if (ret)
- return ret;
+ goto err_nand_init;
nand_maf_id = chip->id.data[0];
nand_dev_id = chip->id.data[1];
mtd->size = i * chip->chipsize;
return 0;
+
+err_nand_init:
+ /* Free manufacturer priv data. */
+ nand_manufacturer_cleanup(chip);
+
+ return ret;
}
EXPORT_SYMBOL(nand_scan_ident);
/* New bad blocks should be marked in OOB, flash-based BBT, or both */
if (WARN_ON((chip->bbt_options & NAND_BBT_NO_OOB_BBM) &&
- !(chip->bbt_options & NAND_BBT_USE_FLASH)))
- return -EINVAL;
+ !(chip->bbt_options & NAND_BBT_USE_FLASH))) {
+ ret = -EINVAL;
+ goto err_ident;
+ }
if (invalid_ecc_page_accessors(chip)) {
pr_err("Invalid ECC page accessors setup\n");
- return -EINVAL;
+ ret = -EINVAL;
+ goto err_ident;
}
if (!(chip->options & NAND_OWN_BUFFERS)) {
nbuf = kzalloc(sizeof(*nbuf), GFP_KERNEL);
- if (!nbuf)
- return -ENOMEM;
+ if (!nbuf) {
+ ret = -ENOMEM;
+ goto err_ident;
+ }
nbuf->ecccalc = kmalloc(mtd->oobsize, GFP_KERNEL);
if (!nbuf->ecccalc) {
chip->buffers = nbuf;
} else {
- if (!chip->buffers)
- return -ENOMEM;
+ if (!chip->buffers) {
+ ret = -ENOMEM;
+ goto err_ident;
+ }
}
/* Set the internal oob buffer location, just after the page data */
return 0;
/* Build bad block table */
- return chip->scan_bbt(mtd);
+ ret = chip->scan_bbt(mtd);
+ if (ret)
+ goto err_free;
+ return 0;
+
err_free:
if (nbuf) {
kfree(nbuf->databuf);
kfree(nbuf->ecccalc);
kfree(nbuf);
}
+
+err_ident:
+ /* Clean up nand_scan_ident(). */
+
+ /* Free manufacturer priv data. */
+ nand_manufacturer_cleanup(chip);
+
return ret;
}
EXPORT_SYMBOL(nand_scan_tail);
* published by the Free Software Foundation.
*
*/
-#include <linux/module.h>
#include <linux/mtd/nand.h>
#include <linux/sizes.h>
case 7:
chip->ecc_strength_ds = 60;
break;
+ default:
+ WARN(1, "Could not decode ECC info");
+ chip->ecc_step_ds = 0;
}
}
} else {
* byte 1 for other packets in the page (PKT_N, for N > 0)
* ERR_COUNT_PKT_N is the max error count over all but the first packet.
*/
-#define DECODE_OK_PKT_0(v) ((v) & BIT(7))
-#define DECODE_OK_PKT_N(v) ((v) & BIT(15))
#define ERR_COUNT_PKT_0(v) (((v) >> 0) & 0x3f)
#define ERR_COUNT_PKT_N(v) (((v) >> 8) & 0x3f)
+#define DECODE_FAIL_PKT_0(v) (((v) & BIT(7)) == 0)
+#define DECODE_FAIL_PKT_N(v) (((v) & BIT(15)) == 0)
/* Offsets relative to pbus_base */
#define PBUS_CS_CTRL 0x83c
chip->ecc.strength);
if (res < 0)
mtd->ecc_stats.failed++;
+ else
+ mtd->ecc_stats.corrected += res;
bitflips = max(res, bitflips);
buf += pkt_size;
return bitflips;
}
-static int decode_error_report(struct tango_nfc *nfc)
+static int decode_error_report(struct nand_chip *chip)
{
u32 status, res;
+ struct mtd_info *mtd = nand_to_mtd(chip);
+ struct tango_nfc *nfc = to_tango_nfc(chip->controller);
status = readl_relaxed(nfc->reg_base + NFC_XFER_STATUS);
if (status & PAGE_IS_EMPTY)
res = readl_relaxed(nfc->mem_base + ERROR_REPORT);
- if (DECODE_OK_PKT_0(res) && DECODE_OK_PKT_N(res))
- return max(ERR_COUNT_PKT_0(res), ERR_COUNT_PKT_N(res));
+ if (DECODE_FAIL_PKT_0(res) || DECODE_FAIL_PKT_N(res))
+ return -EBADMSG;
+
+ /* ERR_COUNT_PKT_N is max, not sum, but that's all we have */
+ mtd->ecc_stats.corrected +=
+ ERR_COUNT_PKT_0(res) + ERR_COUNT_PKT_N(res);
- return -EBADMSG;
+ return max(ERR_COUNT_PKT_0(res), ERR_COUNT_PKT_N(res));
}
static void tango_dma_callback(void *arg)
if (err)
return err;
- res = decode_error_report(nfc);
+ res = decode_error_report(chip);
if (res < 0) {
chip->ecc.read_oob_raw(mtd, chip, page);
res = check_erased_page(chip, buf);
{ .compatible = "sigma,smp8758-nand" },
{ /* sentinel */ }
};
+MODULE_DEVICE_TABLE(of, tango_nand_ids);
static struct platform_driver tango_nand_driver = {
.probe = tango_nand_probe,
return -1;
ad_info->aggregator_id = aggregator->aggregator_identifier;
- ad_info->ports = aggregator->num_of_ports;
+ ad_info->ports = __agg_active_ports(aggregator);
ad_info->actor_key = aggregator->actor_oper_aggregator_key;
ad_info->partner_key = aggregator->partner_oper_aggregator_key;
ether_addr_copy(ad_info->partner_system,
bond_for_each_slave_rcu(bond, slave, iter) {
unsigned long trans_start = dev_trans_start(slave->dev);
+ slave->new_link = BOND_LINK_NOCHANGE;
+
if (slave->link != BOND_LINK_UP) {
if (bond_time_in_interval(bond, trans_start, 1) &&
bond_time_in_interval(bond, slave->last_rx, 1)) {
- slave->link = BOND_LINK_UP;
+ slave->new_link = BOND_LINK_UP;
slave_state_changed = 1;
/* primary_slave has no meaning in round-robin
if (!bond_time_in_interval(bond, trans_start, 2) ||
!bond_time_in_interval(bond, slave->last_rx, 2)) {
- slave->link = BOND_LINK_DOWN;
+ slave->new_link = BOND_LINK_DOWN;
slave_state_changed = 1;
if (slave->link_failure_count < UINT_MAX)
if (!rtnl_trylock())
goto re_arm;
+ bond_for_each_slave(bond, slave, iter) {
+ if (slave->new_link != BOND_LINK_NOCHANGE)
+ slave->link = slave->new_link;
+ }
+
if (slave_state_changed) {
bond_slave_state_change(bond);
if (BOND_MODE(bond) == BOND_MODE_XOR)
int arp_validate_value, fail_over_mac_value, primary_reselect_value, i;
struct bond_opt_value newval;
const struct bond_opt_value *valptr;
- int arp_all_targets_value;
+ int arp_all_targets_value = 0;
u16 ad_actor_sys_prio = 0;
u16 ad_user_port_key = 0;
- __be32 arp_target[BOND_MAX_ARP_TARGETS];
+ __be32 arp_target[BOND_MAX_ARP_TARGETS] = { 0 };
int arp_ip_count;
int bond_mode = BOND_MODE_ROUNDROBIN;
int xmit_hashtype = BOND_XMIT_POLICY_LAYER2;
arp_validate_value = 0;
}
- arp_all_targets_value = 0;
if (arp_all_targets) {
bond_opt_initstr(&newval, arp_all_targets);
valptr = bond_opt_parse(bond_opt_get(BOND_OPT_ARP_ALL_TARGETS),
return -EOPNOTSUPP;
}
-int mv88e6xxx_g2_pvt_write(struct mv88e6xxx_chip *chip, int src_dev,
- int src_port, u16 data)
+static inline int mv88e6xxx_g2_pvt_write(struct mv88e6xxx_chip *chip,
+ int src_dev, int src_port, u16 data)
{
return -EOPNOTSUPP;
}
-int mv88e6xxx_g2_misc_4_bit_port(struct mv88e6xxx_chip *chip)
+static inline int mv88e6xxx_g2_misc_4_bit_port(struct mv88e6xxx_chip *chip)
{
return -EOPNOTSUPP;
}
ret = ax_mii_init(dev);
if (ret)
- goto out_irq;
+ goto err_out;
ax_NS8390_init(dev, 0);
ret = register_netdev(dev);
if (ret)
- goto out_irq;
+ goto err_out;
netdev_info(dev, "%dbit, irq %d, %lx, MAC: %pM\n",
ei_local->word16 ? 16 : 8, dev->irq, dev->base_addr,
return 0;
- out_irq:
- /* cleanup irq */
- free_irq(dev->irq, dev);
err_out:
return ret;
}
struct xgbe_ring *ring,
struct xgbe_ring_data *rdata)
{
- int order, ret;
+ int ret;
if (!ring->rx_hdr_pa.pages) {
ret = xgbe_alloc_pages(pdata, &ring->rx_hdr_pa, GFP_ATOMIC, 0);
}
if (!ring->rx_buf_pa.pages) {
- order = max_t(int, PAGE_ALLOC_COSTLY_ORDER - 1, 0);
ret = xgbe_alloc_pages(pdata, &ring->rx_buf_pa, GFP_ATOMIC,
- order);
+ PAGE_ALLOC_COSTLY_ORDER);
if (ret)
return ret;
}
if (pci_set_dma_mask(pdev, DMA_BIT_MASK(32)) &&
pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32))) {
printk(KERN_ERR "atl2: No usable DMA configuration, aborting\n");
+ err = -EIO;
goto err_dma;
}
* pcibios_set_master to do the needed arch specific settings */
pci_set_master(pdev);
- err = -ENOMEM;
netdev = alloc_etherdev(sizeof(struct atl2_adapter));
- if (!netdev)
+ if (!netdev) {
+ err = -ENOMEM;
goto err_alloc_etherdev;
+ }
SET_NETDEV_DEV(netdev, &pdev->dev);
if (err)
goto err_sw_init;
- err = -EIO;
-
netdev->hw_features = NETIF_F_HW_VLAN_CTAG_RX;
netdev->features |= (NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX);
priv->num_rx_desc_words = params->num_rx_desc_words;
priv->irq0 = platform_get_irq(pdev, 0);
- if (!priv->is_lite)
+ if (!priv->is_lite) {
priv->irq1 = platform_get_irq(pdev, 1);
- priv->wol_irq = platform_get_irq(pdev, 2);
+ priv->wol_irq = platform_get_irq(pdev, 2);
+ } else {
+ priv->wol_irq = platform_get_irq(pdev, 1);
+ }
if (priv->irq0 <= 0 || (priv->irq1 <= 0 && !priv->is_lite)) {
dev_err(&pdev->dev, "invalid interrupts\n");
ret = -EINVAL;
}
/* select a non-FCoE queue */
- return fallback(dev, skb) % BNX2X_NUM_ETH_QUEUES(bp);
+ return fallback(dev, skb) % (BNX2X_NUM_ETH_QUEUES(bp) * bp->max_cos);
}
void bnx2x_set_num_queues(struct bnx2x *bp)
dev->min_mtu = ETH_ZLEN;
dev->max_mtu = BNXT_MAX_MTU;
- bnxt_dcb_init(bp);
-
#ifdef CONFIG_BNXT_SRIOV
init_waitqueue_head(&bp->sriov_cfg_wait);
#endif
bnxt_hwrm_func_qcfg(bp);
bnxt_hwrm_port_led_qcaps(bp);
bnxt_ethtool_init(bp);
+ bnxt_dcb_init(bp);
bnxt_set_rx_skb_mode(bp, false);
bnxt_set_tpa_flags(bp);
if ((mode & DCB_CAP_DCBX_VER_CEE) || !(mode & DCB_CAP_DCBX_VER_IEEE))
return 1;
- if ((mode & DCB_CAP_DCBX_HOST) && BNXT_VF(bp))
- return 1;
+ if (mode & DCB_CAP_DCBX_HOST) {
+ if (BNXT_VF(bp) || (bp->flags & BNXT_FLAG_FW_LLDP_AGENT))
+ return 1;
+ }
if (mode == bp->dcbx_cap)
return 0;
if (err)
goto irq_err;
}
+
+ mutex_lock(&uld_mutex);
enable_rx(adap);
t4_sge_start(adap);
t4_intr_enable(adap);
adap->flags |= FULL_INIT_DONE;
+ mutex_unlock(&uld_mutex);
+
notify_ulds(adap, CXGB4_STATE_UP);
#if IS_ENABLED(CONFIG_IPV6)
update_clip(adap);
{
int port;
+ if (pci_channel_offline(adap->pdev))
+ return;
+
/* Disable the SGE since ULDs are going to free resources that
* could be exposed to the adapter. RDMA MWs for example...
*/
spin_lock(&adap->stats_lock);
for_each_port(adap, i) {
struct net_device *dev = adap->port[i];
-
- netif_device_detach(dev);
- netif_carrier_off(dev);
+ if (dev) {
+ netif_device_detach(dev);
+ netif_carrier_off(dev);
+ }
}
spin_unlock(&adap->stats_lock);
disable_interrupts(adap);
rtnl_lock();
for_each_port(adap, i) {
struct net_device *dev = adap->port[i];
-
- if (netif_running(dev)) {
- link_start(dev);
- cxgb_set_rxmode(dev);
+ if (dev) {
+ if (netif_running(dev)) {
+ link_start(dev);
+ cxgb_set_rxmode(dev);
+ }
+ netif_device_attach(dev);
}
- netif_device_attach(dev);
}
rtnl_unlock();
}
*/
void t4_intr_disable(struct adapter *adapter)
{
- u32 whoami = t4_read_reg(adapter, PL_WHOAMI_A);
- u32 pf = CHELSIO_CHIP_VERSION(adapter->params.chip) <= CHELSIO_T5 ?
+ u32 whoami, pf;
+
+ if (pci_channel_offline(adapter->pdev))
+ return;
+
+ whoami = t4_read_reg(adapter, PL_WHOAMI_A);
+ pf = CHELSIO_CHIP_VERSION(adapter->params.chip) <= CHELSIO_T5 ?
SOURCEPF_G(whoami) : T6_SOURCEPF_G(whoami);
t4_write_reg(adapter, MYPF_REG(PL_PF_INT_ENABLE_A), 0);
#define T4FW_VERSION_MAJOR 0x01
#define T4FW_VERSION_MINOR 0x10
-#define T4FW_VERSION_MICRO 0x21
+#define T4FW_VERSION_MICRO 0x2D
#define T4FW_VERSION_BUILD 0x00
#define T4FW_MIN_VERSION_MAJOR 0x01
#define T5FW_VERSION_MAJOR 0x01
#define T5FW_VERSION_MINOR 0x10
-#define T5FW_VERSION_MICRO 0x21
+#define T5FW_VERSION_MICRO 0x2D
#define T5FW_VERSION_BUILD 0x00
#define T5FW_MIN_VERSION_MAJOR 0x00
#define T6FW_VERSION_MAJOR 0x01
#define T6FW_VERSION_MINOR 0x10
-#define T6FW_VERSION_MICRO 0x21
+#define T6FW_VERSION_MICRO 0x2D
#define T6FW_VERSION_BUILD 0x00
#define T6FW_MIN_VERSION_MAJOR 0x00
struct be_adapter *adapter = netdev_priv(dev);
u8 l4_hdr = 0;
- /* The code below restricts offload features for some tunneled packets.
+ /* The code below restricts offload features for some tunneled and
+ * Q-in-Q packets.
* Offload features for normal (non tunnel) packets are unchanged.
*/
+ features = vlan_features_check(skb, features);
if (!skb->encapsulation ||
!(adapter->flags & BE_FLAGS_VXLAN_OFFLOADS))
return features;
if (ret)
return ret;
+ napi_enable(&priv->napi);
+
ethoc_init_ring(priv, dev->mem_start);
ethoc_reset(priv);
priv->old_duplex = -1;
phy_start(dev->phydev);
- napi_enable(&priv->napi);
if (netif_msg_ifup(priv)) {
dev_info(&dev->dev, "I/O: %08lx Memory: %08lx-%08lx\n",
return 0;
}
+static const struct of_device_id ftmac100_of_ids[] = {
+ { .compatible = "andestech,atmac100" },
+ { }
+};
+
static struct platform_driver ftmac100_driver = {
.probe = ftmac100_probe,
.remove = ftmac100_remove,
.driver = {
.name = DRV_NAME,
+ .of_match_table = ftmac100_of_ids
},
};
MODULE_AUTHOR("Po-Yu Chuang <ratbert@faraday-tech.com>");
MODULE_DESCRIPTION("FTMAC100 driver");
MODULE_LICENSE("GPL");
+MODULE_DEVICE_TABLE(of, ftmac100_of_ids);
{
int err, phy_reset;
bool active_high = false;
- int msec = 1;
+ int msec = 1, phy_post_delay = 0;
struct device_node *np = pdev->dev.of_node;
if (!np)
else if (!gpio_is_valid(phy_reset))
return 0;
+ err = of_property_read_u32(np, "phy-reset-post-delay", &phy_post_delay);
+ /* valid reset duration should be less than 1s */
+ if (!err && phy_post_delay > 1000)
+ return -EINVAL;
+
active_high = of_property_read_bool(np, "phy-reset-active-high");
err = devm_gpio_request_one(&pdev->dev, phy_reset,
gpio_set_value_cansleep(phy_reset, !active_high);
+ if (!phy_post_delay)
+ return 0;
+
+ if (phy_post_delay > 20)
+ msleep(phy_post_delay);
+ else
+ usleep_range(phy_post_delay * 1000,
+ phy_post_delay * 1000 + 1000);
+
return 0;
}
#else /* CONFIG_OF */
{
const struct of_device_id *id =
of_match_device(fsl_pq_mdio_match, &pdev->dev);
- const struct fsl_pq_mdio_data *data = id->data;
+ const struct fsl_pq_mdio_data *data;
struct device_node *np = pdev->dev.of_node;
struct resource res;
struct device_node *tbi;
struct mii_bus *new_bus;
int err;
+ if (!id) {
+ dev_err(&pdev->dev, "Failed to match device\n");
+ return -ENODEV;
+ }
+
+ data = id->data;
+
dev_dbg(&pdev->dev, "found %s compatible node\n", id->compatible);
new_bus = mdiobus_alloc_size(sizeof(*priv));
static const char ibmvnic_driver_name[] = "ibmvnic";
static const char ibmvnic_driver_string[] = "IBM System i/p Virtual NIC Driver";
-MODULE_AUTHOR("Santiago Leon <santi_leon@yahoo.com>");
+MODULE_AUTHOR("Santiago Leon");
MODULE_DESCRIPTION("IBM System i/p Virtual NIC Driver");
MODULE_LICENSE("GPL");
MODULE_VERSION(IBMVNIC_DRIVER_VERSION);
**/
void i40e_service_event_schedule(struct i40e_pf *pf)
{
- if (!test_bit(__I40E_VSI_DOWN, pf->state) &&
+ if (!test_bit(__I40E_DOWN, pf->state) &&
!test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state))
queue_work(i40e_wq, &pf->service_task);
}
* this is not a performance path and napi_schedule()
* can deal with rescheduling.
*/
- if (!test_bit(__I40E_VSI_DOWN, pf->state))
+ if (!test_bit(__I40E_DOWN, pf->state))
napi_schedule_irqoff(&q_vector->napi);
}
enable_intr:
/* re-enable interrupt causes */
wr32(hw, I40E_PFINT_ICR0_ENA, ena_mask);
- if (!test_bit(__I40E_VSI_DOWN, pf->state)) {
+ if (!test_bit(__I40E_DOWN, pf->state)) {
i40e_service_event_schedule(pf);
i40e_irq_dynamic_enable_icr0(pf, false);
}
{
/* if interface is down do nothing */
- if (test_bit(__I40E_VSI_DOWN, pf->state))
+ if (test_bit(__I40E_DOWN, pf->state))
return;
if (test_bit(__I40E_FD_FLUSH_REQUESTED, pf->state))
int i;
/* if interface is down do nothing */
- if (test_bit(__I40E_VSI_DOWN, pf->state) ||
+ if (test_bit(__I40E_DOWN, pf->state) ||
test_bit(__I40E_CONFIG_BUSY, pf->state))
return;
reset_flags |= BIT(__I40E_GLOBAL_RESET_REQUESTED);
clear_bit(__I40E_GLOBAL_RESET_REQUESTED, pf->state);
}
- if (test_bit(__I40E_VSI_DOWN_REQUESTED, pf->state)) {
- reset_flags |= BIT(__I40E_VSI_DOWN_REQUESTED);
- clear_bit(__I40E_VSI_DOWN_REQUESTED, pf->state);
+ if (test_bit(__I40E_DOWN_REQUESTED, pf->state)) {
+ reset_flags |= BIT(__I40E_DOWN_REQUESTED);
+ clear_bit(__I40E_DOWN_REQUESTED, pf->state);
}
/* If there's a recovery already waiting, it takes
/* If we're already down or resetting, just bail */
if (reset_flags &&
- !test_bit(__I40E_VSI_DOWN, pf->state) &&
+ !test_bit(__I40E_DOWN, pf->state) &&
!test_bit(__I40E_CONFIG_BUSY, pf->state)) {
rtnl_lock();
i40e_do_reset(pf, reset_flags, true);
u32 val;
int v;
- if (test_bit(__I40E_VSI_DOWN, pf->state))
+ if (test_bit(__I40E_DOWN, pf->state))
goto clear_recovery;
dev_dbg(&pf->pdev->dev, "Rebuilding internal switch\n");
return -ENODEV;
}
if (vsi == pf->vsi[pf->lan_vsi] &&
- !test_bit(__I40E_VSI_DOWN, pf->state)) {
+ !test_bit(__I40E_DOWN, pf->state)) {
dev_info(&pf->pdev->dev, "Can't remove PF VSI\n");
return -ENODEV;
}
}
pf->next_vsi = 0;
pf->pdev = pdev;
- set_bit(__I40E_VSI_DOWN, pf->state);
+ set_bit(__I40E_DOWN, pf->state);
hw = &pf->hw;
hw->back = pf;
* before setting up the misc vector or we get a race and the vector
* ends up disabled forever.
*/
- clear_bit(__I40E_VSI_DOWN, pf->state);
+ clear_bit(__I40E_DOWN, pf->state);
/* In case of MSIX we are going to setup the misc vector right here
* to handle admin queue events etc. In case of legacy and MSI
/* Unwind what we've done if something failed in the setup */
err_vsis:
- set_bit(__I40E_VSI_DOWN, pf->state);
+ set_bit(__I40E_DOWN, pf->state);
i40e_clear_interrupt_scheme(pf);
kfree(pf->vsi);
err_switch_setup:
/* no more scheduling of any task */
set_bit(__I40E_SUSPENDED, pf->state);
- set_bit(__I40E_VSI_DOWN, pf->state);
+ set_bit(__I40E_DOWN, pf->state);
if (pf->service_timer.data)
del_timer_sync(&pf->service_timer);
if (pf->service_task.func)
struct i40e_hw *hw = &pf->hw;
set_bit(__I40E_SUSPENDED, pf->state);
- set_bit(__I40E_VSI_DOWN, pf->state);
+ set_bit(__I40E_DOWN, pf->state);
rtnl_lock();
i40e_prep_for_reset(pf, true);
rtnl_unlock();
int retval = 0;
set_bit(__I40E_SUSPENDED, pf->state);
- set_bit(__I40E_VSI_DOWN, pf->state);
+ set_bit(__I40E_DOWN, pf->state);
if (pf->wol_en && (pf->flags & I40E_FLAG_WOL_MC_MAGIC_PKT_WAKE))
i40e_enable_mc_magic_wake(pf);
/* handling the reset will rebuild the device state */
if (test_and_clear_bit(__I40E_SUSPENDED, pf->state)) {
- clear_bit(__I40E_VSI_DOWN, pf->state);
+ clear_bit(__I40E_DOWN, pf->state);
rtnl_lock();
i40e_reset_and_rebuild(pf, false, true);
rtnl_unlock();
#if (PAGE_SIZE < 8192)
unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2;
#else
- unsigned int truesize = SKB_DATA_ALIGN(size);
+ unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) +
+ SKB_DATA_ALIGN(I40E_SKB_PAD + size);
#endif
struct sk_buff *skb;
#if (PAGE_SIZE < 8192)
unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2;
#else
- unsigned int truesize = SKB_DATA_ALIGN(size);
+ unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) +
+ SKB_DATA_ALIGN(I40E_SKB_PAD + size);
#endif
struct sk_buff *skb;
qpn = priv->drop_qp.qpn;
else if (cmd->fs.ring_cookie & EN_ETHTOOL_QP_ATTACH) {
qpn = cmd->fs.ring_cookie & (EN_ETHTOOL_QP_ATTACH - 1);
- if (qpn < priv->rss_map.base_qpn ||
- qpn >= priv->rss_map.base_qpn + priv->rx_ring_num) {
- en_warn(priv, "rxnfc: QP (0x%x) doesn't exist\n", qpn);
- return -EINVAL;
- }
} else {
if (cmd->fs.ring_cookie >= priv->rx_ring_num) {
en_warn(priv, "rxnfc: RX ring (%llu) doesn't exist\n",
#include <linux/etherdevice.h>
#include <linux/mlx4/cmd.h>
+#include <linux/mlx4/qp.h>
#include <linux/export.h>
#include "mlx4.h"
if (IS_ERR(mailbox))
return PTR_ERR(mailbox);
+ if (!mlx4_qp_lookup(dev, rule->qpn)) {
+ mlx4_err_rule(dev, "QP doesn't exist\n", rule);
+ ret = -EINVAL;
+ goto out;
+ }
+
trans_rule_ctrl_to_hw(rule, mailbox->buf);
size += sizeof(struct mlx4_net_trans_rule_hw_ctrl);
list_for_each_entry(cur, &rule->list, list) {
ret = parse_trans_rule(dev, cur, mailbox->buf + size);
- if (ret < 0) {
- mlx4_free_cmd_mailbox(dev, mailbox);
- return ret;
- }
+ if (ret < 0)
+ goto out;
+
size += ret;
}
}
}
+out:
mlx4_free_cmd_mailbox(dev, mailbox);
return ret;
__mlx4_qp_free_icm(dev, qpn);
}
+struct mlx4_qp *mlx4_qp_lookup(struct mlx4_dev *dev, u32 qpn)
+{
+ struct mlx4_qp_table *qp_table = &mlx4_priv(dev)->qp_table;
+ struct mlx4_qp *qp;
+
+ spin_lock(&qp_table->lock);
+
+ qp = __mlx4_qp_lookup(dev, qpn);
+
+ spin_unlock(&qp_table->lock);
+ return qp;
+}
+
int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp, gfp_t gfp)
{
struct mlx4_priv *priv = mlx4_priv(dev);
}
if (attr & MLX4_UPDATE_QP_QOS_VPORT) {
+ if (!(dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_QOS_VPP)) {
+ mlx4_warn(dev, "Granular QoS per VF is not enabled\n");
+ err = -EOPNOTSUPP;
+ goto out;
+ }
+
qp_mask |= 1ULL << MLX4_UPD_QP_MASK_QOS_VPP;
cmd->qp_context.qos_vport = params->qos_vport;
}
mutex_unlock(&priv->mfunc.master.res_tracker.slave_list[slave].mutex);
}
+static void update_qos_vpp(struct mlx4_update_qp_context *ctx,
+ struct mlx4_vf_immed_vlan_work *work)
+{
+ ctx->qp_mask |= cpu_to_be64(1ULL << MLX4_UPD_QP_MASK_QOS_VPP);
+ ctx->qp_context.qos_vport = work->qos_vport;
+}
+
void mlx4_vf_immed_vlan_work_handler(struct work_struct *_work)
{
struct mlx4_vf_immed_vlan_work *work =
qp->sched_queue & 0xC7;
upd_context->qp_context.pri_path.sched_queue |=
((work->qos & 0x7) << 3);
- upd_context->qp_mask |=
- cpu_to_be64(1ULL <<
- MLX4_UPD_QP_MASK_QOS_VPP);
- upd_context->qp_context.qos_vport =
- work->qos_vport;
+
+ if (dev->caps.flags2 &
+ MLX4_DEV_CAP_FLAG2_QOS_VPP)
+ update_qos_vpp(upd_context, work);
}
err = mlx4_cmd(dev, mailbox->dma,
config MLX5_CORE_EN
bool "Mellanox Technologies ConnectX-4 Ethernet support"
- depends on NETDEVICES && ETHERNET && PCI && MLX5_CORE
+ depends on NETDEVICES && ETHERNET && INET && PCI && MLX5_CORE
depends on IPV6=y || IPV6=n || MLX5_CORE=m
imply PTP_1588_CLOCK
default n
mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n",
mlx5_command_str(msg_to_opcode(ent->in)),
msg_to_opcode(ent->in));
- mlx5_cmd_comp_handler(dev, 1UL << ent->idx);
+ mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
}
static void cmd_work_handler(struct work_struct *work)
}
cmd->ent_arr[ent->idx] = ent;
+ set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state);
lay = get_inst(cmd, ent->idx);
ent->lay = lay;
memset(lay, 0, sizeof(*lay));
if (ent->callback)
schedule_delayed_work(&ent->cb_timeout_work, cb_timeout);
+ /* Skip sending command to fw if internal error */
+ if (pci_channel_offline(dev->pdev) ||
+ dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
+ u8 status = 0;
+ u32 drv_synd;
+
+ ent->ret = mlx5_internal_err_ret_value(dev, msg_to_opcode(ent->in), &drv_synd, &status);
+ MLX5_SET(mbox_out, ent->out, status, status);
+ MLX5_SET(mbox_out, ent->out, syndrome, drv_synd);
+
+ mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
+ return;
+ }
+
/* ring doorbell after the descriptor is valid */
mlx5_core_dbg(dev, "writing 0x%x to command doorbell\n", 1 << ent->idx);
wmb();
poll_timeout(ent);
/* make sure we read the descriptor after ownership is SW */
rmb();
- mlx5_cmd_comp_handler(dev, 1UL << ent->idx);
+ mlx5_cmd_comp_handler(dev, 1UL << ent->idx, (ent->ret == -ETIMEDOUT));
}
}
wait_for_completion(&ent->done);
} else if (!wait_for_completion_timeout(&ent->done, timeout)) {
ent->ret = -ETIMEDOUT;
- mlx5_cmd_comp_handler(dev, 1UL << ent->idx);
+ mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
}
err = ent->ret;
}
}
-void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec)
+void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced)
{
struct mlx5_cmd *cmd = &dev->cmd;
struct mlx5_cmd_work_ent *ent;
struct semaphore *sem;
ent = cmd->ent_arr[i];
+
+ /* if we already completed the command, ignore it */
+ if (!test_and_clear_bit(MLX5_CMD_ENT_STATE_PENDING_COMP,
+ &ent->state)) {
+ /* only real completion can free the cmd slot */
+ if (!forced) {
+ mlx5_core_err(dev, "Command completion arrived after timeout (entry idx = %d).\n",
+ ent->idx);
+ free_ent(cmd, ent->idx);
+ }
+ continue;
+ }
+
if (ent->callback)
cancel_delayed_work(&ent->cb_timeout_work);
if (ent->page_queue)
mlx5_core_dbg(dev, "command completed. ret 0x%x, delivery status %s(0x%x)\n",
ent->ret, deliv_status_to_str(ent->status), ent->status);
}
- free_ent(cmd, ent->idx);
+
+ /* only real completion will free the entry slot */
+ if (!forced)
+ free_ent(cmd, ent->idx);
if (ent->callback) {
ds = ent->ts2 - ent->ts1;
#define MLX5_IB_GRH_BYTES 40
#define MLX5_IPOIB_ENCAP_LEN 4
#define MLX5_GID_SIZE 16
+#define MLX5_IPOIB_PSEUDO_LEN 20
+#define MLX5_IPOIB_HARD_LEN (MLX5_IPOIB_PSEUDO_LEN + MLX5_IPOIB_ENCAP_LEN)
static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq,
struct mlx5_cqe64 *cqe,
struct sk_buff *skb)
{
struct net_device *netdev = rq->netdev;
+ char *pseudo_header;
u8 *dgid;
u8 g;
if (likely(netdev->features & NETIF_F_RXHASH))
mlx5e_skb_set_hash(cqe, skb);
+ /* 20 bytes of ipoib header and 4 for encap existing */
+ pseudo_header = skb_push(skb, MLX5_IPOIB_PSEUDO_LEN);
+ memset(pseudo_header, 0, MLX5_IPOIB_PSEUDO_LEN);
skb_reset_mac_header(skb);
- skb_pull(skb, MLX5_IPOIB_ENCAP_LEN);
+ skb_pull(skb, MLX5_IPOIB_HARD_LEN);
skb->dev = netdev;
#include <net/tc_act/tc_vlan.h>
#include <net/tc_act/tc_tunnel_key.h>
#include <net/tc_act/tc_pedit.h>
+#include <net/tc_act/tc_csum.h>
#include <net/vxlan.h>
#include <net/arp.h>
#include "en.h"
if (e->flags & MLX5_ENCAP_ENTRY_VALID)
mlx5_encap_dealloc(priv->mdev, e->encap_id);
- hlist_del_rcu(&e->encap_hlist);
+ hash_del_rcu(&e->encap_hlist);
kfree(e->encap_header);
kfree(e);
}
struct mlx5e_tc_flow_parse_attr *parse_attr)
{
struct pedit_headers *set_masks, *add_masks, *set_vals, *add_vals;
- int i, action_size, nactions, max_actions, first, last;
+ int i, action_size, nactions, max_actions, first, last, first_z;
void *s_masks_p, *a_masks_p, *vals_p;
- u32 s_mask, a_mask, val;
struct mlx5_fields *f;
u8 cmd, field_bsize;
+ u32 s_mask, a_mask;
unsigned long mask;
void *action;
for (i = 0; i < ARRAY_SIZE(fields); i++) {
f = &fields[i];
/* avoid seeing bits set from previous iterations */
- s_mask = a_mask = mask = val = 0;
+ s_mask = 0;
+ a_mask = 0;
s_masks_p = (void *)set_masks + f->offset;
a_masks_p = (void *)add_masks + f->offset;
memset(a_masks_p, 0, f->size);
}
- memcpy(&val, vals_p, f->size);
-
field_bsize = f->size * BITS_PER_BYTE;
+
+ first_z = find_first_zero_bit(&mask, field_bsize);
first = find_first_bit(&mask, field_bsize);
last = find_last_bit(&mask, field_bsize);
- if (first > 0 || last != (field_bsize - 1)) {
+ if (first > 0 || last != (field_bsize - 1) || first_z < last) {
printk(KERN_WARNING "mlx5: partial rewrite (mask %lx) is currently not offloaded\n",
mask);
return -EOPNOTSUPP;
}
if (field_bsize == 32)
- MLX5_SET(set_action_in, action, data, ntohl(val));
+ MLX5_SET(set_action_in, action, data, ntohl(*(__be32 *)vals_p));
else if (field_bsize == 16)
- MLX5_SET(set_action_in, action, data, ntohs(val));
+ MLX5_SET(set_action_in, action, data, ntohs(*(__be16 *)vals_p));
else if (field_bsize == 8)
- MLX5_SET(set_action_in, action, data, val);
+ MLX5_SET(set_action_in, action, data, *(u8 *)vals_p);
action += action_size;
nactions++;
return err;
}
+static bool csum_offload_supported(struct mlx5e_priv *priv, u32 action, u32 update_flags)
+{
+ u32 prot_flags = TCA_CSUM_UPDATE_FLAG_IPV4HDR | TCA_CSUM_UPDATE_FLAG_TCP |
+ TCA_CSUM_UPDATE_FLAG_UDP;
+
+ /* The HW recalcs checksums only if re-writing headers */
+ if (!(action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)) {
+ netdev_warn(priv->netdev,
+ "TC csum action is only offloaded with pedit\n");
+ return false;
+ }
+
+ if (update_flags & ~prot_flags) {
+ netdev_warn(priv->netdev,
+ "can't offload TC csum action for some header/s - flags %#x\n",
+ update_flags);
+ return false;
+ }
+
+ return true;
+}
+
static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
struct mlx5e_tc_flow_parse_attr *parse_attr,
struct mlx5e_tc_flow *flow)
continue;
}
+ if (is_tcf_csum(a)) {
+ if (csum_offload_supported(priv, attr->action,
+ tcf_csum_update_flags(a)))
+ continue;
+
+ return -EOPNOTSUPP;
+ }
+
if (is_tcf_skbedit_mark(a)) {
u32 mark = tcf_skbedit_mark(a);
continue;
}
+ if (is_tcf_csum(a)) {
+ if (csum_offload_supported(priv, attr->action,
+ tcf_csum_update_flags(a)))
+ continue;
+
+ return -EOPNOTSUPP;
+ }
+
if (is_tcf_mirred_egress_redirect(a)) {
int ifindex = tcf_mirred_ifindex(a);
struct net_device *out_dev, *encap_dev = NULL;
break;
case MLX5_EVENT_TYPE_CMD:
- mlx5_cmd_comp_handler(dev, be32_to_cpu(eqe->data.cmd.vector));
+ mlx5_cmd_comp_handler(dev, be32_to_cpu(eqe->data.cmd.vector), false);
break;
case MLX5_EVENT_TYPE_PORT_CHANGE:
spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags);
mlx5_core_dbg(dev, "vector 0x%llx\n", vector);
- mlx5_cmd_comp_handler(dev, vector);
+ mlx5_cmd_comp_handler(dev, vector, true);
return;
no_trig:
struct mlx5_priv *priv = &mdev->priv;
struct msix_entry *msix = priv->msix_arr;
int irq = msix[i + MLX5_EQ_VEC_COMP_BASE].vector;
- int err;
if (!zalloc_cpumask_var(&priv->irq_info[i].mask, GFP_KERNEL)) {
mlx5_core_warn(mdev, "zalloc_cpumask_var failed");
cpumask_set_cpu(cpumask_local_spread(i, priv->numa_node),
priv->irq_info[i].mask);
- err = irq_set_affinity_hint(irq, priv->irq_info[i].mask);
- if (err) {
- mlx5_core_warn(mdev, "irq_set_affinity_hint failed,irq 0x%.4x",
- irq);
- goto err_clear_mask;
- }
+ if (IS_ENABLED(CONFIG_SMP) &&
+ irq_set_affinity_hint(irq, priv->irq_info[i].mask))
+ mlx5_core_warn(mdev, "irq_set_affinity_hint failed, irq 0x%.4x", irq);
return 0;
-
-err_clear_mask:
- free_cpumask_var(priv->irq_info[i].mask);
- return err;
}
static void mlx5_irq_clear_affinity_hint(struct mlx5_core_dev *mdev, int i)
entry->counter_valid = false;
entry->counter = 0;
+ entry->index = mlxsw_sp_rif_index(rif);
+
if (!counters_enabled)
return 0;
- entry->index = mlxsw_sp_rif_index(rif);
err = mlxsw_sp_rif_counter_value_get(mlxsw_sp, rif,
MLXSW_SP_RIF_COUNTER_EGRESS,
&cnt);
{
unsigned int *p_counter_index;
+ if (!mlxsw_sp_rif_counter_valid_get(rif, dir))
+ return;
+
p_counter_index = mlxsw_sp_rif_p_counter_get(rif, dir);
if (WARN_ON(!p_counter_index))
return;
err = mlxsw_sp_port_fdb_uc_op(mlxsw_sp, local_port, mac, fid,
adding, true);
if (err) {
- if (net_ratelimit())
- netdev_err(mlxsw_sp_port->dev, "Failed to set FDB entry\n");
+ dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to set FDB entry\n");
return;
}
err = mlxsw_sp_port_fdb_uc_lag_op(mlxsw_sp, lag_id, mac, fid, lag_vid,
adding, true);
if (err) {
- if (net_ratelimit())
- netdev_err(mlxsw_sp_port->dev, "Failed to set FDB entry\n");
+ dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to set FDB entry\n");
return;
}
qed_get_protocol_stats_iscsi(cdev, &stats->iscsi_stats);
break;
default:
- DP_ERR(cdev, "Invalid protocol type = %d\n", type);
+ DP_VERBOSE(cdev, QED_MSG_SP,
+ "Invalid protocol type = %d\n", type);
return;
}
}
u32 (*get_cap_size)(void *, int);
void (*set_sys_info)(void *, int, u32);
void (*store_cap_mask)(void *, u32);
+ bool (*encap_rx_offload) (struct qlcnic_adapter *adapter);
+ bool (*encap_tx_offload) (struct qlcnic_adapter *adapter);
};
extern struct qlcnic_nic_template qlcnic_vf_ops;
-static inline bool qlcnic_encap_tx_offload(struct qlcnic_adapter *adapter)
+static inline bool qlcnic_83xx_encap_tx_offload(struct qlcnic_adapter *adapter)
{
return adapter->ahw->extra_capability[0] &
QLCNIC_83XX_FW_CAPAB_ENCAP_TX_OFFLOAD;
}
-static inline bool qlcnic_encap_rx_offload(struct qlcnic_adapter *adapter)
+static inline bool qlcnic_83xx_encap_rx_offload(struct qlcnic_adapter *adapter)
{
return adapter->ahw->extra_capability[0] &
QLCNIC_83XX_FW_CAPAB_ENCAP_RX_OFFLOAD;
}
+static inline bool qlcnic_82xx_encap_tx_offload(struct qlcnic_adapter *adapter)
+{
+ return false;
+}
+
+static inline bool qlcnic_82xx_encap_rx_offload(struct qlcnic_adapter *adapter)
+{
+ return false;
+}
+
+static inline bool qlcnic_encap_rx_offload(struct qlcnic_adapter *adapter)
+{
+ return adapter->ahw->hw_ops->encap_rx_offload(adapter);
+}
+
+static inline bool qlcnic_encap_tx_offload(struct qlcnic_adapter *adapter)
+{
+ return adapter->ahw->hw_ops->encap_tx_offload(adapter);
+}
+
static inline int qlcnic_start_firmware(struct qlcnic_adapter *adapter)
{
return adapter->nic_ops->start_firmware(adapter);
.get_cap_size = qlcnic_83xx_get_cap_size,
.set_sys_info = qlcnic_83xx_set_sys_info,
.store_cap_mask = qlcnic_83xx_store_cap_mask,
+ .encap_rx_offload = qlcnic_83xx_encap_rx_offload,
+ .encap_tx_offload = qlcnic_83xx_encap_tx_offload,
};
static struct qlcnic_nic_template qlcnic_83xx_ops = {
}
return -EIO;
}
- usleep_range(1000, 1500);
+ udelay(1200);
}
if (id_reg)
.get_cap_size = qlcnic_82xx_get_cap_size,
.set_sys_info = qlcnic_82xx_set_sys_info,
.store_cap_mask = qlcnic_82xx_store_cap_mask,
+ .encap_rx_offload = qlcnic_82xx_encap_rx_offload,
+ .encap_tx_offload = qlcnic_82xx_encap_tx_offload,
};
static int qlcnic_check_multi_tx_capability(struct qlcnic_adapter *adapter)
.free_mac_list = qlcnic_sriov_vf_free_mac_list,
.enable_sds_intr = qlcnic_83xx_enable_sds_intr,
.disable_sds_intr = qlcnic_83xx_disable_sds_intr,
+ .encap_rx_offload = qlcnic_83xx_encap_rx_offload,
+ .encap_tx_offload = qlcnic_83xx_encap_tx_offload,
};
static struct qlcnic_nic_template qlcnic_sriov_vf_ops = {
emac_mac_config(adpt);
emac_mac_rx_descs_refill(adpt, &adpt->rx_q);
- adpt->phydev->irq = PHY_IGNORE_INTERRUPT;
+ adpt->phydev->irq = PHY_POLL;
ret = phy_connect_direct(netdev, adpt->phydev, emac_adjust_link,
PHY_INTERFACE_MODE_SGMII);
if (ret) {
/* Qualcomm Technologies, Inc. EMAC PHY Controller driver.
*/
-#include <linux/module.h>
-#include <linux/of.h>
-#include <linux/of_net.h>
#include <linux/of_mdio.h>
#include <linux/phy.h>
#include <linux/iopoll.h>
#include <linux/acpi.h>
#include "emac.h"
-#include "emac-mac.h"
/* EMAC base register offsets */
#define EMAC_MDIO_CTRL 0x001414
#define MDIO_WAIT_TIMES 1000
-#define EMAC_LINK_SPEED_DEFAULT (\
- EMAC_LINK_SPEED_10_HALF |\
- EMAC_LINK_SPEED_10_FULL |\
- EMAC_LINK_SPEED_100_HALF |\
- EMAC_LINK_SPEED_100_FULL |\
- EMAC_LINK_SPEED_1GB_FULL)
-
-/**
- * emac_phy_mdio_autopoll_disable() - disable mdio autopoll
- * @adpt: the emac adapter
- *
- * The autopoll feature takes over the MDIO bus. In order for
- * the PHY driver to be able to talk to the PHY over the MDIO
- * bus, we need to temporarily disable the autopoll feature.
- */
-static int emac_phy_mdio_autopoll_disable(struct emac_adapter *adpt)
-{
- u32 val;
-
- /* disable autopoll */
- emac_reg_update32(adpt->base + EMAC_MDIO_CTRL, MDIO_AP_EN, 0);
-
- /* wait for any mdio polling to complete */
- if (!readl_poll_timeout(adpt->base + EMAC_MDIO_CTRL, val,
- !(val & MDIO_BUSY), 100, MDIO_WAIT_TIMES * 100))
- return 0;
-
- /* failed to disable; ensure it is enabled before returning */
- emac_reg_update32(adpt->base + EMAC_MDIO_CTRL, 0, MDIO_AP_EN);
-
- return -EBUSY;
-}
-
-/**
- * emac_phy_mdio_autopoll_disable() - disable mdio autopoll
- * @adpt: the emac adapter
- *
- * The EMAC has the ability to poll the external PHY on the MDIO
- * bus for link state changes. This eliminates the need for the
- * driver to poll the phy. If if the link state does change,
- * the EMAC issues an interrupt on behalf of the PHY.
- */
-static void emac_phy_mdio_autopoll_enable(struct emac_adapter *adpt)
-{
- emac_reg_update32(adpt->base + EMAC_MDIO_CTRL, 0, MDIO_AP_EN);
-}
-
static int emac_mdio_read(struct mii_bus *bus, int addr, int regnum)
{
struct emac_adapter *adpt = bus->priv;
u32 reg;
- int ret;
-
- ret = emac_phy_mdio_autopoll_disable(adpt);
- if (ret)
- return ret;
emac_reg_update32(adpt->base + EMAC_PHY_STS, PHY_ADDR_BMSK,
(addr << PHY_ADDR_SHFT));
if (readl_poll_timeout(adpt->base + EMAC_MDIO_CTRL, reg,
!(reg & (MDIO_START | MDIO_BUSY)),
100, MDIO_WAIT_TIMES * 100))
- ret = -EIO;
- else
- ret = (reg >> MDIO_DATA_SHFT) & MDIO_DATA_BMSK;
+ return -EIO;
- emac_phy_mdio_autopoll_enable(adpt);
-
- return ret;
+ return (reg >> MDIO_DATA_SHFT) & MDIO_DATA_BMSK;
}
static int emac_mdio_write(struct mii_bus *bus, int addr, int regnum, u16 val)
{
struct emac_adapter *adpt = bus->priv;
u32 reg;
- int ret;
-
- ret = emac_phy_mdio_autopoll_disable(adpt);
- if (ret)
- return ret;
emac_reg_update32(adpt->base + EMAC_PHY_STS, PHY_ADDR_BMSK,
(addr << PHY_ADDR_SHFT));
if (readl_poll_timeout(adpt->base + EMAC_MDIO_CTRL, reg,
!(reg & (MDIO_START | MDIO_BUSY)), 100,
MDIO_WAIT_TIMES * 100))
- ret = -EIO;
+ return -EIO;
- emac_phy_mdio_autopoll_enable(adpt);
-
- return ret;
+ return 0;
}
/* Configure the MDIO bus and connect the external PHY */
#define DMAR_DLY_CNT_DEF 15
#define DMAW_DLY_CNT_DEF 4
-#define IMR_NORMAL_MASK (\
- ISR_ERROR |\
- ISR_GPHY_LINK |\
- ISR_TX_PKT |\
- GPHY_WAKEUP_INT)
-
-#define IMR_EXTENDED_MASK (\
- SW_MAN_INT |\
- ISR_OVER |\
- ISR_ERROR |\
- ISR_GPHY_LINK |\
- ISR_TX_PKT |\
- GPHY_WAKEUP_INT)
+#define IMR_NORMAL_MASK (ISR_ERROR | ISR_OVER | ISR_TX_PKT)
#define ISR_TX_PKT (\
TX_PKT_INT |\
TX_PKT_INT2 |\
TX_PKT_INT3)
-#define ISR_GPHY_LINK (\
- GPHY_LINK_UP_INT |\
- GPHY_LINK_DOWN_INT)
-
#define ISR_OVER (\
RFD0_UR_INT |\
RFD1_UR_INT |\
if (status & ISR_OVER)
net_warn_ratelimited("warning: TX/RX overflow\n");
- /* link event */
- if (status & ISR_GPHY_LINK)
- phy_mac_interrupt(adpt->phydev, !!(status & GPHY_LINK_UP_INT));
-
exit:
/* enable the interrupt */
writel(irq->mask, adpt->base + EMAC_INT_MASK);
int ring_size;
int i;
- /* Free RX skb ringbuffer */
- if (priv->rx_skb[q]) {
- for (i = 0; i < priv->num_rx_ring[q]; i++)
- dev_kfree_skb(priv->rx_skb[q][i]);
- }
- kfree(priv->rx_skb[q]);
- priv->rx_skb[q] = NULL;
-
- /* Free aligned TX buffers */
- kfree(priv->tx_align[q]);
- priv->tx_align[q] = NULL;
-
if (priv->rx_ring[q]) {
for (i = 0; i < priv->num_rx_ring[q]; i++) {
struct ravb_ex_rx_desc *desc = &priv->rx_ring[q][i];
priv->tx_ring[q] = NULL;
}
+ /* Free RX skb ringbuffer */
+ if (priv->rx_skb[q]) {
+ for (i = 0; i < priv->num_rx_ring[q]; i++)
+ dev_kfree_skb(priv->rx_skb[q][i]);
+ }
+ kfree(priv->rx_skb[q]);
+ priv->rx_skb[q] = NULL;
+
+ /* Free aligned TX buffers */
+ kfree(priv->tx_align[q]);
+ priv->tx_align[q] = NULL;
+
/* Free TX skb ringbuffer.
* SKBs are freed by ravb_tx_free() call above.
*/
/* MDIO bus init */
ret = sh_mdio_init(mdp, pd);
if (ret) {
- dev_err(&ndev->dev, "failed to initialise MDIO\n");
+ if (ret != -EPROBE_DEFER)
+ dev_err(&pdev->dev, "MDIO init failed: %d\n", ret);
goto out_release;
}
#define TSE_PCS_CONTROL_AN_EN_MASK BIT(12)
#define TSE_PCS_CONTROL_REG 0x00
#define TSE_PCS_CONTROL_RESTART_AN_MASK BIT(9)
+#define TSE_PCS_CTRL_AUTONEG_SGMII 0x1140
#define TSE_PCS_IF_MODE_REG 0x28
#define TSE_PCS_LINK_TIMER_0_REG 0x24
#define TSE_PCS_LINK_TIMER_1_REG 0x26
#define TSE_PCS_SW_RESET_TIMEOUT 100
#define TSE_PCS_USE_SGMII_AN_MASK BIT(1)
#define TSE_PCS_USE_SGMII_ENA BIT(0)
+#define TSE_PCS_IF_USE_SGMII 0x03
#define SGMII_ADAPTER_CTRL_REG 0x00
#define SGMII_ADAPTER_DISABLE 0x0001
{
int ret = 0;
- writew(TSE_PCS_USE_SGMII_ENA, base + TSE_PCS_IF_MODE_REG);
+ writew(TSE_PCS_IF_USE_SGMII, base + TSE_PCS_IF_MODE_REG);
+
+ writew(TSE_PCS_CTRL_AUTONEG_SGMII, base + TSE_PCS_CONTROL_REG);
writew(TSE_PCS_SGMII_LINK_TIMER_0, base + TSE_PCS_LINK_TIMER_0_REG);
writew(TSE_PCS_SGMII_LINK_TIMER_1, base + TSE_PCS_LINK_TIMER_1_REG);
u32 rx_count = priv->plat->rx_queues_to_use;
unsigned int bfsize = 0;
int ret = -ENOMEM;
- u32 queue;
+ int queue;
int i;
if (priv->hw->mode->set_16kib_bfsize)
priv->hw->desc->prepare_tso_tx_desc(desc, 0, buff_size,
0, 1,
- (last_segment) && (buff_size < TSO_MAX_BUFF_SIZE),
+ (last_segment) && (tmp_len <= TSO_MAX_BUFF_SIZE),
0, 0);
tmp_len -= TSO_MAX_BUFF_SIZE;
int i, csum_insertion = 0, is_jumbo = 0;
u32 queue = skb_get_queue_mapping(skb);
int nfrags = skb_shinfo(skb)->nr_frags;
- unsigned int entry, first_entry;
+ int entry;
+ unsigned int first_entry;
struct dma_desc *desc, *first;
struct stmmac_tx_queue *tx_q;
unsigned int enh_desc;
/* make enough headroom for basic scenario */
encap_len = GENEVE_BASE_HLEN + ETH_HLEN;
- if (ip_tunnel_info_af(info) == AF_INET) {
+ if (!metadata && ip_tunnel_info_af(info) == AF_INET) {
encap_len += sizeof(struct iphdr);
dev->max_mtu -= sizeof(struct iphdr);
} else {
if (nla_put_u32(skb, IFLA_GENEVE_ID, vni))
goto nla_put_failure;
- if (ip_tunnel_info_af(info) == AF_INET) {
+ if (rtnl_dereference(geneve->sock4)) {
if (nla_put_in_addr(skb, IFLA_GENEVE_REMOTE,
info->key.u.ipv4.dst))
goto nla_put_failure;
!!(info->key.tun_flags & TUNNEL_CSUM)))
goto nla_put_failure;
+ }
+
#if IS_ENABLED(CONFIG_IPV6)
- } else {
+ if (rtnl_dereference(geneve->sock6)) {
if (nla_put_in6_addr(skb, IFLA_GENEVE_REMOTE6,
&info->key.u.ipv6.dst))
goto nla_put_failure;
if (nla_put_u8(skb, IFLA_GENEVE_UDP_ZERO_CSUM6_RX,
!geneve->use_udp6_rx_checksums))
goto nla_put_failure;
-#endif
}
+#endif
if (nla_put_u8(skb, IFLA_GENEVE_TTL, info->key.ttl) ||
nla_put_u8(skb, IFLA_GENEVE_TOS, info->key.tos) ||
/* Check if there's an existing gtpX device to configure */
dev = dev_get_by_index_rcu(net, nla_get_u32(nla[GTPA_LINK]));
- if (dev->netdev_ops == >p_netdev_ops)
+ if (dev && dev->netdev_ops == >p_netdev_ops)
gtp = netdev_priv(dev);
put_net(net);
case HDLCDRVCTL_CALIBRATE:
if(!capable(CAP_SYS_RAWIO))
return -EPERM;
+ if (s->par.bitrate <= 0)
+ return -EINVAL;
if (bi.data.calibrate > INT_MAX / s->par.bitrate)
return -EINVAL;
s->hdlctx.calibrate = bi.data.calibrate * s->par.bitrate / 16;
config MDIO_OCTEON
tristate "Octeon and some ThunderX SOCs MDIO buses"
depends on 64BIT
- depends on HAS_IOMEM
+ depends on HAS_IOMEM && OF_MDIO
select MDIO_CAVIUM
help
This module provides a driver for the Octeon and ThunderX MDIO
{
int err;
- /* The Marvell PHY has an errata which requires
- * that certain registers get written in order
- * to restart autonegotiation */
- err = phy_write(phydev, MII_BMCR, BMCR_RESET);
-
- if (err < 0)
- return err;
-
- err = phy_write(phydev, 0x1d, 0x1f);
- if (err < 0)
- return err;
-
- err = phy_write(phydev, 0x1e, 0x200c);
- if (err < 0)
- return err;
-
- err = phy_write(phydev, 0x1d, 0x5);
- if (err < 0)
- return err;
-
- err = phy_write(phydev, 0x1e, 0);
- if (err < 0)
- return err;
-
- err = phy_write(phydev, 0x1e, 0x100);
- if (err < 0)
- return err;
-
err = marvell_set_polarity(phydev, phydev->mdix_ctrl);
if (err < 0)
return err;
return 0;
}
+static int m88e1101_config_aneg(struct phy_device *phydev)
+{
+ int err;
+
+ /* This Marvell PHY has an errata which requires
+ * that certain registers get written in order
+ * to restart autonegotiation
+ */
+ err = phy_write(phydev, MII_BMCR, BMCR_RESET);
+
+ if (err < 0)
+ return err;
+
+ err = phy_write(phydev, 0x1d, 0x1f);
+ if (err < 0)
+ return err;
+
+ err = phy_write(phydev, 0x1e, 0x200c);
+ if (err < 0)
+ return err;
+
+ err = phy_write(phydev, 0x1d, 0x5);
+ if (err < 0)
+ return err;
+
+ err = phy_write(phydev, 0x1e, 0);
+ if (err < 0)
+ return err;
+
+ err = phy_write(phydev, 0x1e, 0x100);
+ if (err < 0)
+ return err;
+
+ return marvell_config_aneg(phydev);
+}
+
static int m88e1111_config_aneg(struct phy_device *phydev)
{
int err;
if (adv < 0)
return adv;
- lpa &= adv;
-
if (status & MII_M1011_PHY_STATUS_FULLDUPLEX)
phydev->duplex = DUPLEX_FULL;
else
.flags = PHY_HAS_INTERRUPT,
.probe = marvell_probe,
.config_init = &marvell_config_init,
- .config_aneg = &marvell_config_aneg,
+ .config_aneg = &m88e1101_config_aneg,
.read_status = &genphy_read_status,
.ack_interrupt = &marvell_ack_interrupt,
.config_intr = &marvell_config_intr,
return 0;
}
+static int mdio_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+ int rc;
+
+ /* Some devices have extra OF data and an OF-style MODALIAS */
+ rc = of_device_uevent_modalias(dev, env);
+ if (rc != -ENODEV)
+ return rc;
+
+ return 0;
+}
+
#ifdef CONFIG_PM
static int mdio_bus_suspend(struct device *dev)
{
struct bus_type mdio_bus_type = {
.name = "mdio_bus",
.match = mdio_bus_match,
+ .uevent = mdio_uevent,
.pm = MDIO_BUS_PM_OPS,
};
EXPORT_SYMBOL(mdio_bus_type);
return ret;
}
-static int kszphy_config_init(struct phy_device *phydev)
+/* Some config bits need to be set again on resume, handle them here. */
+static int kszphy_config_reset(struct phy_device *phydev)
{
struct kszphy_priv *priv = phydev->priv;
- const struct kszphy_type *type;
int ret;
- if (!priv)
- return 0;
-
- type = priv->type;
-
- if (type->has_broadcast_disable)
- kszphy_broadcast_disable(phydev);
-
- if (type->has_nand_tree_disable)
- kszphy_nand_tree_disable(phydev);
-
if (priv->rmii_ref_clk_sel) {
ret = kszphy_rmii_clk_sel(phydev, priv->rmii_ref_clk_sel_val);
if (ret) {
}
if (priv->led_mode >= 0)
- kszphy_setup_led(phydev, type->led_mode_reg, priv->led_mode);
+ kszphy_setup_led(phydev, priv->type->led_mode_reg, priv->led_mode);
return 0;
}
+static int kszphy_config_init(struct phy_device *phydev)
+{
+ struct kszphy_priv *priv = phydev->priv;
+ const struct kszphy_type *type;
+
+ if (!priv)
+ return 0;
+
+ type = priv->type;
+
+ if (type->has_broadcast_disable)
+ kszphy_broadcast_disable(phydev);
+
+ if (type->has_nand_tree_disable)
+ kszphy_nand_tree_disable(phydev);
+
+ return kszphy_config_reset(phydev);
+}
+
static int ksz8041_config_init(struct phy_device *phydev)
{
struct device_node *of_node = phydev->mdio.dev.of_node;
static int kszphy_resume(struct phy_device *phydev)
{
+ int ret;
+
genphy_resume(phydev);
+ ret = kszphy_config_reset(phydev);
+ if (ret)
+ return ret;
+
/* Enable PHY Interrupts */
if (phy_interrupt_is_valid(phydev)) {
phydev->interrupts = PHY_INTERRUPT_ENABLED;
* phy_lookup_setting - lookup a PHY setting
* @speed: speed to match
* @duplex: duplex to match
- * @feature: allowed link modes
+ * @features: allowed link modes
* @exact: an exact match is required
*
* Search the settings array for a setting that matches the speed and
return -ENODEV;
}
+ return 0;
+
+bad_desc:
+ dev_info(&dev->udev->dev, "bad CDC descriptors\n");
+ return -ENODEV;
+}
+EXPORT_SYMBOL_GPL(usbnet_generic_cdc_bind);
+
+
+/* like usbnet_generic_cdc_bind() but handles filter initialization
+ * correctly
+ */
+int usbnet_ether_cdc_bind(struct usbnet *dev, struct usb_interface *intf)
+{
+ int rv;
+
+ rv = usbnet_generic_cdc_bind(dev, intf);
+ if (rv < 0)
+ goto bail_out;
+
/* Some devices don't initialise properly. In particular
* the packet filter is not reset. There are devices that
* don't do reset all the way. So the packet filter should
*/
usbnet_cdc_update_filter(dev);
- return 0;
-
-bad_desc:
- dev_info(&dev->udev->dev, "bad CDC descriptors\n");
- return -ENODEV;
+bail_out:
+ return rv;
}
-EXPORT_SYMBOL_GPL(usbnet_generic_cdc_bind);
+EXPORT_SYMBOL_GPL(usbnet_ether_cdc_bind);
void usbnet_cdc_unbind(struct usbnet *dev, struct usb_interface *intf)
{
BUILD_BUG_ON((sizeof(((struct usbnet *)0)->data)
< sizeof(struct cdc_state)));
- status = usbnet_generic_cdc_bind(dev, intf);
+ status = usbnet_ether_cdc_bind(dev, intf);
if (status < 0)
return status;
{QMI_FIXED_INTF(0x1199, 0x9071, 10)}, /* Sierra Wireless MC74xx */
{QMI_FIXED_INTF(0x1199, 0x9079, 8)}, /* Sierra Wireless EM74xx */
{QMI_FIXED_INTF(0x1199, 0x9079, 10)}, /* Sierra Wireless EM74xx */
+ {QMI_FIXED_INTF(0x1199, 0x907b, 8)}, /* Sierra Wireless EM74xx */
+ {QMI_FIXED_INTF(0x1199, 0x907b, 10)}, /* Sierra Wireless EM74xx */
{QMI_FIXED_INTF(0x1bbb, 0x011e, 4)}, /* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */
{QMI_FIXED_INTF(0x1bbb, 0x0203, 2)}, /* Alcatel L800MA */
{QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */
if (ret < 0)
return ret;
- if (features & NETIF_F_HW_CSUM)
+ if (features & NETIF_F_IP_CSUM)
read_buf |= Tx_COE_EN_;
else
read_buf &= ~Tx_COE_EN_;
spin_lock_init(&pdata->mac_cr_lock);
+ /* LAN95xx devices do not alter the computed checksum of 0 to 0xffff.
+ * RFC 2460, ipv6 UDP calculated checksum yields a result of zero must
+ * be changed to 0xffff. RFC 768, ipv4 UDP computed checksum is zero,
+ * it is transmitted as all ones. The zero transmitted checksum means
+ * transmitter generated no checksum. Hence, enable csum offload only
+ * for ipv4 packets.
+ */
if (DEFAULT_TX_CSUM_ENABLE)
- dev->net->features |= NETIF_F_HW_CSUM;
+ dev->net->features |= NETIF_F_IP_CSUM;
if (DEFAULT_RX_CSUM_ENABLE)
dev->net->features |= NETIF_F_RXCSUM;
- dev->net->hw_features = NETIF_F_HW_CSUM | NETIF_F_RXCSUM;
+ dev->net->hw_features = NETIF_F_IP_CSUM | NETIF_F_RXCSUM;
smsc95xx_init_mac_address(dev);
unsigned int len;
len = hdr_len + clamp_t(unsigned int, ewma_pkt_len_read(avg_pkt_len),
- rq->min_buf_len - hdr_len, PAGE_SIZE - hdr_len);
+ rq->min_buf_len, PAGE_SIZE - hdr_len);
return ALIGN(len, L1_CACHE_BYTES);
}
.ndo_poll_controller = virtnet_netpoll,
#endif
.ndo_xdp = virtnet_xdp,
+ .ndo_features_check = passthru_features_check,
};
static void virtnet_config_changed_work(struct work_struct *work)
unsigned int buf_len = hdr_len + ETH_HLEN + VLAN_HLEN + packet_len;
unsigned int min_buf_len = DIV_ROUND_UP(buf_len, rq_size);
- return max(min_buf_len, hdr_len);
+ return max(max(min_buf_len, hdr_len) - hdr_len,
+ (unsigned int)GOOD_PACKET_LEN);
}
static int virtnet_find_vqs(struct virtnet_info *vi)
static int vxlan_sock_add(struct vxlan_dev *vxlan);
+static void vxlan_vs_del_dev(struct vxlan_dev *vxlan);
+
/* per-network namespace private data for this module */
struct vxlan_net {
struct list_head vxlan_list;
call_rcu(&f->rcu, vxlan_fdb_free);
}
+static void vxlan_dst_free(struct rcu_head *head)
+{
+ struct vxlan_rdst *rd = container_of(head, struct vxlan_rdst, rcu);
+
+ dst_cache_destroy(&rd->dst_cache);
+ kfree(rd);
+}
+
+static void vxlan_fdb_dst_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f,
+ struct vxlan_rdst *rd)
+{
+ list_del_rcu(&rd->list);
+ vxlan_fdb_notify(vxlan, f, rd, RTM_DELNEIGH);
+ call_rcu(&rd->rcu, vxlan_dst_free);
+}
+
static int vxlan_fdb_parse(struct nlattr *tb[], struct vxlan_dev *vxlan,
union vxlan_addr *ip, __be16 *port, __be32 *src_vni,
__be32 *vni, u32 *ifindex)
* otherwise destroy the fdb entry
*/
if (rd && !list_is_singular(&f->remotes)) {
- list_del_rcu(&rd->list);
- vxlan_fdb_notify(vxlan, f, rd, RTM_DELNEIGH);
- kfree_rcu(rd, rcu);
+ vxlan_fdb_dst_destroy(vxlan, f, rd);
goto out;
}
rcu_assign_pointer(vxlan->vn4_sock, NULL);
synchronize_net();
+ vxlan_vs_del_dev(vxlan);
+
if (__vxlan_sock_release_prep(sock4)) {
udp_tunnel_sock_release(sock4->sock);
kfree(sock4);
mod_timer(&vxlan->age_timer, next_timer);
}
+static void vxlan_vs_del_dev(struct vxlan_dev *vxlan)
+{
+ struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
+
+ spin_lock(&vn->sock_lock);
+ hlist_del_init_rcu(&vxlan->hlist);
+ spin_unlock(&vn->sock_lock);
+}
+
static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan)
{
struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
static void vxlan_dellink(struct net_device *dev, struct list_head *head)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
- struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
vxlan_flush(vxlan, true);
- spin_lock(&vn->sock_lock);
- if (!hlist_unhashed(&vxlan->hlist))
- hlist_del_rcu(&vxlan->hlist);
- spin_unlock(&vn->sock_lock);
-
gro_cells_destroy(&vxlan->gro_cells);
list_del(&vxlan->next);
unregister_netdevice_queue(dev, head);
qcom_smem_state_put(wcn->tx_enable_state);
qcom_smem_state_put(wcn->tx_rings_empty_state);
+ rpmsg_destroy_ept(wcn->smd_channel);
+
iounmap(wcn->dxe_base);
iounmap(wcn->ccu_base);
/* otherwise, set txglomalign */
value = sdiodev->settings->bus.sdio.sd_sgentry_align;
/* SDIO ADMA requires at least 32 bit alignment */
- value = max_t(u32, value, 4);
+ value = max_t(u32, value, ALIGNMENT);
err = brcmf_iovar_data_set(dev, "bus:txglomalign", &value,
sizeof(u32));
}
/* Lowest firmware API version supported */
#define IWL7260_UCODE_API_MIN 17
#define IWL7265_UCODE_API_MIN 17
-#define IWL7265D_UCODE_API_MIN 17
-#define IWL3168_UCODE_API_MIN 20
+#define IWL7265D_UCODE_API_MIN 22
+#define IWL3168_UCODE_API_MIN 22
/* NVM versions */
#define IWL7260_NVM_VERSION 0x0a1d
#define IWL8265_UCODE_API_MAX 30
/* Lowest firmware API version supported */
-#define IWL8000_UCODE_API_MIN 17
-#define IWL8265_UCODE_API_MIN 20
+#define IWL8000_UCODE_API_MIN 22
+#define IWL8265_UCODE_API_MIN 22
/* NVM versions */
#define IWL8000_NVM_VERSION 0x0a1d
#define MON_DMARB_RD_DATA_ADDR (0xa03c5c)
#define DBGC_IN_SAMPLE (0xa03c00)
+#define DBGC_OUT_CTRL (0xa03c0c)
/* enable the ID buf for read */
#define WFPM_PS_CTL_CLR 0xA0300C
/* Bit 1-3: LQ command color. Used to match responses to LQ commands */
#define LQ_FLAG_COLOR_POS 1
#define LQ_FLAG_COLOR_MSK (7 << LQ_FLAG_COLOR_POS)
+#define LQ_FLAG_COLOR_GET(_f) (((_f) & LQ_FLAG_COLOR_MSK) >>\
+ LQ_FLAG_COLOR_POS)
+#define LQ_FLAGS_COLOR_INC(_c) ((((_c) + 1) << LQ_FLAG_COLOR_POS) &\
+ LQ_FLAG_COLOR_MSK)
+#define LQ_FLAG_COLOR_SET(_f, _c) ((_c) | ((_f) & ~LQ_FLAG_COLOR_MSK))
/* Bit 4-5: Tx RTS BW Signalling
* (0) No RTS BW signalling
* bit-7 invalid rate indication
*/
#define TX_RES_INIT_RATE_INDEX_MSK 0x0f
+#define TX_RES_RATE_TABLE_COLOR_POS 4
#define TX_RES_RATE_TABLE_COLOR_MSK 0x70
#define TX_RES_INV_RATE_INDEX_MSK 0x80
+#define TX_RES_RATE_TABLE_COL_GET(_f) (((_f) & TX_RES_RATE_TABLE_COLOR_MSK) >>\
+ TX_RES_RATE_TABLE_COLOR_POS)
#define IWL_MVM_TX_RES_GET_TID(_ra_tid) ((_ra_tid) & 0x0f)
#define IWL_MVM_TX_RES_GET_RA(_ra_tid) ((_ra_tid) >> 4)
return 0;
}
-static inline void iwl_mvm_restart_early_start(struct iwl_mvm *mvm)
-{
- if (mvm->cfg->device_family == IWL_DEVICE_FAMILY_7000)
- iwl_clear_bits_prph(mvm->trans, MON_BUFF_SAMPLE_CTL, 0x100);
- else
- iwl_write_prph(mvm->trans, DBGC_IN_SAMPLE, 1);
-}
-
int iwl_mvm_start_fw_dbg_conf(struct iwl_mvm *mvm, u8 conf_id)
{
u8 *ptr;
/* EARLY START - firmware's configuration is hard coded */
if ((!mvm->fw->dbg_conf_tlv[conf_id] ||
!mvm->fw->dbg_conf_tlv[conf_id]->num_of_hcmds) &&
- conf_id == FW_DBG_START_FROM_ALIVE) {
- iwl_mvm_restart_early_start(mvm);
+ conf_id == FW_DBG_START_FROM_ALIVE)
return 0;
- }
if (!mvm->fw->dbg_conf_tlv[conf_id])
return -EINVAL;
struct iwl_mac_beacon_cmd_v6 beacon_cmd_v6;
struct iwl_mac_beacon_cmd_v7 beacon_cmd;
} u = {};
- struct iwl_mac_beacon_cmd beacon_cmd;
+ struct iwl_mac_beacon_cmd beacon_cmd = {};
struct ieee80211_tx_info *info;
u32 beacon_skb_len;
u32 rate, tx_flags;
*/
static inline u32 iwl_mvm_flushable_queues(struct iwl_mvm *mvm)
{
+ u32 cmd_queue = iwl_mvm_is_dqa_supported(mvm) ? IWL_MVM_DQA_CMD_QUEUE :
+ IWL_MVM_CMD_QUEUE;
+
return ((BIT(mvm->cfg->base_params->num_of_queues) - 1) &
- ~BIT(IWL_MVM_CMD_QUEUE));
+ ~BIT(cmd_queue));
}
static inline
if (!iwl_mvm_has_new_tx_api(mvm))
iwl_free_fw_paging(mvm);
mvm->ucode_loaded = false;
+ mvm->fw_dbg_conf = FW_DBG_INVALID;
iwl_trans_stop_device(mvm->trans);
}
mutex_lock(&mvm->mutex);
- /* stop recording */
if (mvm->cfg->device_family == IWL_DEVICE_FAMILY_7000) {
+ /* stop recording */
iwl_set_bits_prph(mvm->trans, MON_BUFF_SAMPLE_CTL, 0x100);
+
+ iwl_mvm_fw_error_dump(mvm);
+
+ /* start recording again if the firmware is not crashed */
+ if (!test_bit(STATUS_FW_ERROR, &mvm->trans->status) &&
+ mvm->fw->dbg_dest_tlv)
+ iwl_clear_bits_prph(mvm->trans,
+ MON_BUFF_SAMPLE_CTL, 0x100);
} else {
+ u32 in_sample = iwl_read_prph(mvm->trans, DBGC_IN_SAMPLE);
+ u32 out_ctrl = iwl_read_prph(mvm->trans, DBGC_OUT_CTRL);
+
+ /* stop recording */
iwl_write_prph(mvm->trans, DBGC_IN_SAMPLE, 0);
- /* wait before we collect the data till the DBGC stop */
udelay(100);
- }
+ iwl_write_prph(mvm->trans, DBGC_OUT_CTRL, 0);
+ /* wait before we collect the data till the DBGC stop */
+ udelay(500);
- iwl_mvm_fw_error_dump(mvm);
+ iwl_mvm_fw_error_dump(mvm);
- /* start recording again if the firmware is not crashed */
- WARN_ON_ONCE((!test_bit(STATUS_FW_ERROR, &mvm->trans->status)) &&
- mvm->fw->dbg_dest_tlv &&
- iwl_mvm_start_fw_dbg_conf(mvm, mvm->fw_dbg_conf));
+ /* start recording again if the firmware is not crashed */
+ if (!test_bit(STATUS_FW_ERROR, &mvm->trans->status) &&
+ mvm->fw->dbg_dest_tlv) {
+ iwl_write_prph(mvm->trans, DBGC_IN_SAMPLE, in_sample);
+ iwl_write_prph(mvm->trans, DBGC_OUT_CTRL, out_ctrl);
+ }
+ }
mutex_unlock(&mvm->mutex);
*
* Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
- * Copyright(c) 2016 Intel Deutschland GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of version 2 of the GNU General Public License as
rs_get_lower_rate_in_column(lq_sta, rate);
}
-/* Check if both rates are identical
- * allow_ant_mismatch enables matching a SISO rate on ANT_A or ANT_B
- * with a rate indicating STBC/BFER and ANT_AB.
- */
-static inline bool rs_rate_equal(struct rs_rate *a,
- struct rs_rate *b,
- bool allow_ant_mismatch)
-
-{
- bool ant_match = (a->ant == b->ant) && (a->stbc == b->stbc) &&
- (a->bfer == b->bfer);
-
- if (allow_ant_mismatch) {
- if (a->stbc || a->bfer) {
- WARN_ONCE(a->ant != ANT_AB, "stbc %d bfer %d ant %d",
- a->stbc, a->bfer, a->ant);
- ant_match |= (b->ant == ANT_A || b->ant == ANT_B);
- } else if (b->stbc || b->bfer) {
- WARN_ONCE(b->ant != ANT_AB, "stbc %d bfer %d ant %d",
- b->stbc, b->bfer, b->ant);
- ant_match |= (a->ant == ANT_A || a->ant == ANT_B);
- }
- }
-
- return (a->type == b->type) && (a->bw == b->bw) && (a->sgi == b->sgi) &&
- (a->ldpc == b->ldpc) && (a->index == b->index) && ant_match;
-}
-
/* Check if both rates share the same column */
static inline bool rs_rate_column_match(struct rs_rate *a,
struct rs_rate *b)
u32 lq_hwrate;
struct rs_rate lq_rate, tx_resp_rate;
struct iwl_scale_tbl_info *curr_tbl, *other_tbl, *tmp_tbl;
- u8 reduced_txp = (uintptr_t)info->status.status_driver_data[0];
+ u32 tlc_info = (uintptr_t)info->status.status_driver_data[0];
+ u8 reduced_txp = tlc_info & RS_DRV_DATA_TXP_MSK;
+ u8 lq_color = RS_DRV_DATA_LQ_COLOR_GET(tlc_info);
u32 tx_resp_hwrate = (uintptr_t)info->status.status_driver_data[1];
struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
struct iwl_lq_sta *lq_sta = &mvmsta->lq_sta;
- bool allow_ant_mismatch = fw_has_api(&mvm->fw->ucode_capa,
- IWL_UCODE_TLV_API_LQ_SS_PARAMS);
/* Treat uninitialized rate scaling data same as non-existing. */
if (!lq_sta) {
rs_rate_from_ucode_rate(lq_hwrate, info->band, &lq_rate);
/* Here we actually compare this rate to the latest LQ command */
- if (!rs_rate_equal(&tx_resp_rate, &lq_rate, allow_ant_mismatch)) {
+ if (lq_color != LQ_FLAG_COLOR_GET(table->flags)) {
IWL_DEBUG_RATE(mvm,
- "initial tx resp rate 0x%x does not match 0x%x\n",
- tx_resp_hwrate, lq_hwrate);
+ "tx resp color 0x%x does not match 0x%x\n",
+ lq_color, LQ_FLAG_COLOR_GET(table->flags));
/*
* Since rates mis-match, the last LQ command may have failed.
u8 valid_tx_ant = 0;
struct iwl_lq_cmd *lq_cmd = &lq_sta->lq;
bool toggle_ant = false;
+ u32 color;
memcpy(&rate, initial_rate, sizeof(rate));
num_rates, num_retries, valid_tx_ant,
toggle_ant);
+ /* update the color of the LQ command (as a counter at bits 1-3) */
+ color = LQ_FLAGS_COLOR_INC(LQ_FLAG_COLOR_GET(lq_cmd->flags));
+ lq_cmd->flags = LQ_FLAG_COLOR_SET(lq_cmd->flags, color);
}
struct rs_bfer_active_iter_data {
*
* Copyright(c) 2003 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2015 Intel Mobile Communications GmbH
+ * Copyright(c) 2017 Intel Deutschland GmbH
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of version 2 of the GNU General Public License as
} pers;
};
+/* ieee80211_tx_info's status_driver_data[0] is packed with lq color and txp
+ * Note, it's iwlmvm <-> mac80211 interface.
+ * bits 0-7: reduced tx power
+ * bits 8-10: LQ command's color
+ */
+#define RS_DRV_DATA_TXP_MSK 0xff
+#define RS_DRV_DATA_LQ_COLOR_POS 8
+#define RS_DRV_DATA_LQ_COLOR_MSK (7 << RS_DRV_DATA_LQ_COLOR_POS)
+#define RS_DRV_DATA_LQ_COLOR_GET(_f) (((_f) & RS_DRV_DATA_LQ_COLOR_MSK) >>\
+ RS_DRV_DATA_LQ_COLOR_POS)
+#define RS_DRV_DATA_PACK(_c, _p) ((void *)(uintptr_t)\
+ (((uintptr_t)_p) |\
+ ((_c) << RS_DRV_DATA_LQ_COLOR_POS)))
+
/* Initialize station's rate scaling information after adding station */
void iwl_mvm_rs_rate_init(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
enum nl80211_band band, bool init);
if (!iwl_mvm_is_dqa_supported(mvm))
return 0;
- if (WARN_ON(vif->type != NL80211_IFTYPE_AP))
+ if (WARN_ON(vif->type != NL80211_IFTYPE_AP &&
+ vif->type != NL80211_IFTYPE_ADHOC))
return -ENOTSUPP;
/*
mvmvif->cab_queue = queue;
} else if (!fw_has_api(&mvm->fw->ucode_capa,
IWL_UCODE_TLV_API_STA_TYPE)) {
+ /*
+ * In IBSS, ieee80211_check_queues() sets the cab_queue to be
+ * invalid, so make sure we use the queue we want.
+ * Note that this is done here as we want to avoid making DQA
+ * changes in mac80211 layer.
+ */
+ if (vif->type == NL80211_IFTYPE_ADHOC) {
+ vif->cab_queue = IWL_MVM_DQA_GCAST_QUEUE;
+ mvmvif->cab_queue = vif->cab_queue;
+ }
iwl_mvm_enable_txq(mvm, vif->cab_queue, vif->cab_queue, 0,
&cfg, timeout);
}
/* Get the station from the mvm local station table */
mvm_sta = iwl_mvm_get_key_sta(mvm, vif, sta);
- if (!mvm_sta) {
- IWL_ERR(mvm, "Failed to find station\n");
- return -EINVAL;
- }
- sta_id = mvm_sta->sta_id;
+ if (mvm_sta)
+ sta_id = mvm_sta->sta_id;
IWL_DEBUG_WEP(mvm, "mvm remove dynamic key: idx=%d sta=%d\n",
keyconf->keyidx, sta_id);
- if (keyconf->cipher == WLAN_CIPHER_SUITE_AES_CMAC ||
- keyconf->cipher == WLAN_CIPHER_SUITE_BIP_GMAC_128 ||
- keyconf->cipher == WLAN_CIPHER_SUITE_BIP_GMAC_256)
+ if (mvm_sta && (keyconf->cipher == WLAN_CIPHER_SUITE_AES_CMAC ||
+ keyconf->cipher == WLAN_CIPHER_SUITE_BIP_GMAC_128 ||
+ keyconf->cipher == WLAN_CIPHER_SUITE_BIP_GMAC_256))
return iwl_mvm_send_sta_igtk(mvm, keyconf, sta_id, true);
if (!__test_and_clear_bit(keyconf->hw_key_idx, mvm->fw_key_table)) {
* This is basically (last acked packet++).
* @rate_n_flags: Rate at which Tx was attempted. Holds the data between the
* Tx response (TX_CMD), and the block ack notification (COMPRESSED_BA).
+ * @lq_color: the color of the LQ command as it appears in tx response.
* @amsdu_in_ampdu_allowed: true if A-MSDU in A-MPDU is allowed.
* @state: state of the BA agreement establishment / tear down.
* @txq_id: Tx queue used by the BA session / DQA
u16 next_reclaimed;
/* The rest is Tx AGG related */
u32 rate_n_flags;
+ u8 lq_color;
bool amsdu_in_ampdu_allowed;
enum iwl_mvm_agg_state state;
u16 txq_id;
struct iwl_mvm *mvm = (struct iwl_mvm *)(cdev->devdata);
int ret;
- if (!mvm->ucode_loaded || !(mvm->cur_ucode == IWL_UCODE_REGULAR))
- return -EIO;
-
mutex_lock(&mvm->mutex);
+ if (!mvm->ucode_loaded || !(mvm->cur_ucode == IWL_UCODE_REGULAR)) {
+ ret = -EIO;
+ goto unlock;
+ }
+
if (new_state >= ARRAY_SIZE(iwl_mvm_cdev_budgets)) {
ret = -EINVAL;
goto unlock;
struct iwl_mvm_sta *mvmsta;
struct sk_buff_head skbs;
u8 skb_freed = 0;
+ u8 lq_color;
u16 next_reclaimed, seq_ctl;
bool is_ndp = false;
info->status.tx_time =
le16_to_cpu(tx_resp->wireless_media_time);
BUILD_BUG_ON(ARRAY_SIZE(info->status.status_driver_data) < 1);
+ lq_color = TX_RES_RATE_TABLE_COL_GET(tx_resp->tlc_info);
info->status.status_driver_data[0] =
- (void *)(uintptr_t)tx_resp->reduced_tpc;
+ RS_DRV_DATA_PACK(lq_color, tx_resp->reduced_tpc);
ieee80211_tx_status(mvm->hw, skb);
}
le32_to_cpu(tx_resp->initial_rate);
mvmsta->tid_data[tid].tx_time =
le16_to_cpu(tx_resp->wireless_media_time);
+ mvmsta->tid_data[tid].lq_color =
+ (tx_resp->tlc_info & TX_RES_RATE_TABLE_COLOR_MSK) >>
+ TX_RES_RATE_TABLE_COLOR_POS;
}
rcu_read_unlock();
iwl_mvm_check_ratid_empty(mvm, sta, tid);
freed = 0;
+
+ /* pack lq color from tid_data along the reduced txp */
+ ba_info->status.status_driver_data[0] =
+ RS_DRV_DATA_PACK(tid_data->lq_color,
+ ba_info->status.status_driver_data[0]);
ba_info->status.status_driver_data[1] = (void *)(uintptr_t)rate;
skb_queue_walk(&reclaimed_skbs, skb) {
#ifdef CONFIG_PM_SLEEP
static int iwl_trans_pcie_suspend(struct iwl_trans *trans)
{
- if (trans->runtime_pm_mode == IWL_PLAT_PM_MODE_D0I3)
+ if (trans->runtime_pm_mode == IWL_PLAT_PM_MODE_D0I3 &&
+ (trans->system_pm_mode == IWL_PLAT_PM_MODE_D0I3))
return iwl_pci_fw_enter_d0i3(trans);
return 0;
static void iwl_trans_pcie_resume(struct iwl_trans *trans)
{
- if (trans->runtime_pm_mode == IWL_PLAT_PM_MODE_D0I3)
+ if (trans->runtime_pm_mode == IWL_PLAT_PM_MODE_D0I3 &&
+ (trans->system_pm_mode == IWL_PLAT_PM_MODE_D0I3))
iwl_pci_fw_exit_d0i3(trans);
}
#endif /* CONFIG_PM_SLEEP */
if (WARN_ON(iwl_rx_packet_payload_len(hcmd.resp_pkt) != sizeof(*rsp))) {
ret = -EINVAL;
- goto error;
+ goto error_free_resp;
}
rsp = (void *)hcmd.resp_pkt->data;
if (qid > ARRAY_SIZE(trans_pcie->txq)) {
WARN_ONCE(1, "queue index %d unsupported", qid);
ret = -EIO;
- goto error;
+ goto error_free_resp;
}
if (test_and_set_bit(qid, trans_pcie->queue_used)) {
WARN_ONCE(1, "queue %d already used", qid);
ret = -EIO;
- goto error;
+ goto error_free_resp;
}
txq->id = qid;
(txq->write_ptr) | (qid << 16));
IWL_DEBUG_TX_QUEUES(trans, "Activate queue %d\n", qid);
+ iwl_free_resp(&hcmd);
return qid;
+error_free_resp:
+ iwl_free_resp(&hcmd);
error:
iwl_pcie_gen2_txq_free_memory(trans, txq);
return ret;
static int nvme_char_major;
module_param(nvme_char_major, int, 0);
-static unsigned long default_ps_max_latency_us = 25000;
+static unsigned long default_ps_max_latency_us = 100000;
module_param(default_ps_max_latency_us, ulong, 0644);
MODULE_PARM_DESC(default_ps_max_latency_us,
"max power saving latency for new devices; use PM QOS to change per device");
}
#ifdef CONFIG_BLK_DEV_INTEGRITY
+static void nvme_prep_integrity(struct gendisk *disk, struct nvme_id_ns *id,
+ u16 bs)
+{
+ struct nvme_ns *ns = disk->private_data;
+ u16 old_ms = ns->ms;
+ u8 pi_type = 0;
+
+ ns->ms = le16_to_cpu(id->lbaf[id->flbas & NVME_NS_FLBAS_LBA_MASK].ms);
+ ns->ext = ns->ms && (id->flbas & NVME_NS_FLBAS_META_EXT);
+
+ /* PI implementation requires metadata equal t10 pi tuple size */
+ if (ns->ms == sizeof(struct t10_pi_tuple))
+ pi_type = id->dps & NVME_NS_DPS_PI_MASK;
+
+ if (blk_get_integrity(disk) &&
+ (ns->pi_type != pi_type || ns->ms != old_ms ||
+ bs != queue_logical_block_size(disk->queue) ||
+ (ns->ms && ns->ext)))
+ blk_integrity_unregister(disk);
+
+ ns->pi_type = pi_type;
+}
+
static void nvme_init_integrity(struct nvme_ns *ns)
{
struct blk_integrity integrity;
blk_queue_max_integrity_segments(ns->queue, 1);
}
#else
+static void nvme_prep_integrity(struct gendisk *disk, struct nvme_id_ns *id,
+ u16 bs)
+{
+}
static void nvme_init_integrity(struct nvme_ns *ns)
{
}
static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
{
struct nvme_ns *ns = disk->private_data;
- u8 lbaf, pi_type;
- u16 old_ms;
- unsigned short bs;
-
- old_ms = ns->ms;
- lbaf = id->flbas & NVME_NS_FLBAS_LBA_MASK;
- ns->lba_shift = id->lbaf[lbaf].ds;
- ns->ms = le16_to_cpu(id->lbaf[lbaf].ms);
- ns->ext = ns->ms && (id->flbas & NVME_NS_FLBAS_META_EXT);
+ u16 bs;
/*
* If identify namespace failed, use default 512 byte block size so
* block layer can use before failing read/write for 0 capacity.
*/
+ ns->lba_shift = id->lbaf[id->flbas & NVME_NS_FLBAS_LBA_MASK].ds;
if (ns->lba_shift == 0)
ns->lba_shift = 9;
bs = 1 << ns->lba_shift;
- /* XXX: PI implementation requires metadata equal t10 pi tuple size */
- pi_type = ns->ms == sizeof(struct t10_pi_tuple) ?
- id->dps & NVME_NS_DPS_PI_MASK : 0;
blk_mq_freeze_queue(disk->queue);
- if (blk_get_integrity(disk) && (ns->pi_type != pi_type ||
- ns->ms != old_ms ||
- bs != queue_logical_block_size(disk->queue) ||
- (ns->ms && ns->ext)))
- blk_integrity_unregister(disk);
- ns->pi_type = pi_type;
+ if (ns->ctrl->ops->flags & NVME_F_METADATA_SUPPORTED)
+ nvme_prep_integrity(disk, id, bs);
blk_queue_logical_block_size(ns->queue, bs);
-
if (ns->ms && !blk_get_integrity(disk) && !ns->ext)
nvme_init_integrity(ns);
if (ns->ms && !(ns->ms == 8 && ns->pi_type) && !blk_get_integrity(disk))
* transitioning between power states. Therefore, when running
* in any given state, we will enter the next lower-power
* non-operational state after waiting 50 * (enlat + exlat)
- * microseconds, as long as that state's total latency is under
+ * microseconds, as long as that state's exit latency is under
* the requested maximum latency.
*
* We will not autonomously enter any non-operational state for
* lowest-power state, not the number of states.
*/
for (state = (int)ctrl->npss; state >= 0; state--) {
- u64 total_latency_us, transition_ms;
+ u64 total_latency_us, exit_latency_us, transition_ms;
if (target)
table->entries[state] = target;
NVME_PS_FLAGS_NON_OP_STATE))
continue;
- total_latency_us =
- (u64)le32_to_cpu(ctrl->psd[state].entry_lat) +
- + le32_to_cpu(ctrl->psd[state].exit_lat);
- if (total_latency_us > ctrl->ps_max_latency_us)
+ exit_latency_us =
+ (u64)le32_to_cpu(ctrl->psd[state].exit_lat);
+ if (exit_latency_us > ctrl->ps_max_latency_us)
continue;
+ total_latency_us =
+ exit_latency_us +
+ le32_to_cpu(ctrl->psd[state].entry_lat);
+
/*
* This state is good. Use it as the APST idle
* target for higher power states.
}
memcpy(ctrl->psd, id->psd, sizeof(ctrl->psd));
- if (ctrl->ops->is_fabrics) {
+ if (ctrl->ops->flags & NVME_F_FABRICS) {
ctrl->icdoff = le16_to_cpu(id->icdoff);
ctrl->ioccsz = le32_to_cpu(id->ioccsz);
ctrl->iorcsz = le32_to_cpu(id->iorcsz);
if (ns->ndev)
nvme_nvm_unregister_sysfs(ns);
del_gendisk(ns->disk);
- blk_mq_abort_requeue_list(ns->queue);
blk_cleanup_queue(ns->queue);
}
struct nvme_ns *ns;
mutex_lock(&ctrl->namespaces_mutex);
+
+ /* Forcibly start all queues to avoid having stuck requests */
+ blk_mq_start_hw_queues(ctrl->admin_q);
+
list_for_each_entry(ns, &ctrl->namespaces, list) {
/*
* Revalidating a dead namespace sets capacity to 0. This will
continue;
revalidate_disk(ns->disk);
blk_set_queue_dying(ns->queue);
- blk_mq_abort_requeue_list(ns->queue);
- blk_mq_start_stopped_hw_queues(ns->queue, true);
+
+ /*
+ * Forcibly start all queues to avoid having stuck requests.
+ * Note that we must ensure the queues are not stopped
+ * when the final removal happens.
+ */
+ blk_mq_start_hw_queues(ns->queue);
+
+ /* draining requests in requeue list */
+ blk_mq_kick_requeue_list(ns->queue);
}
mutex_unlock(&ctrl->namespaces_mutex);
}
#define NVMEFC_QUEUE_DELAY 3 /* ms units */
-#define NVME_FC_MAX_CONNECT_ATTEMPTS 1
-
struct nvme_fc_queue {
struct nvme_fc_ctrl *ctrl;
struct device *dev;
struct work_struct delete_work;
struct work_struct reset_work;
struct delayed_work connect_work;
- int reconnect_delay;
- int connect_attempts;
struct kref ref;
u32 flags;
/* *********************** NVME Ctrl Routines **************************** */
static void __nvme_fc_final_op_cleanup(struct request *rq);
+static void nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg);
static int
nvme_fc_reinit_request(void *data, struct request *rq)
struct nvme_command *sqe = &op->cmd_iu.sqe;
__le16 status = cpu_to_le16(NVME_SC_SUCCESS << 1);
union nvme_result result;
- bool complete_rq;
+ bool complete_rq, terminate_assoc = true;
/*
* WARNING:
* fabricate a CQE, the following fields will not be set as they
* are not referenced:
* cqe.sqid, cqe.sqhd, cqe.command_id
+ *
+ * Failure or error of an individual i/o, in a transport
+ * detected fashion unrelated to the nvme completion status,
+ * potentially cause the initiator and target sides to get out
+ * of sync on SQ head/tail (aka outstanding io count allowed).
+ * Per FC-NVME spec, failure of an individual command requires
+ * the connection to be terminated, which in turn requires the
+ * association to be terminated.
*/
fc_dma_sync_single_for_cpu(ctrl->lport->dev, op->fcp_req.rspdma,
goto done;
}
+ terminate_assoc = false;
+
done:
if (op->flags & FCOP_FLAGS_AEN) {
nvme_complete_async_event(&queue->ctrl->ctrl, status, &result);
atomic_set(&op->state, FCPOP_STATE_IDLE);
op->flags = FCOP_FLAGS_AEN; /* clear other flags */
nvme_fc_ctrl_put(ctrl);
- return;
+ goto check_error;
}
complete_rq = __nvme_fc_fcpop_chk_teardowns(ctrl, op);
if (!complete_rq) {
if (unlikely(op->flags & FCOP_FLAGS_TERMIO)) {
- status = cpu_to_le16(NVME_SC_ABORT_REQ);
+ status = cpu_to_le16(NVME_SC_ABORT_REQ << 1);
if (blk_queue_dying(rq->q))
- status |= cpu_to_le16(NVME_SC_DNR);
+ status |= cpu_to_le16(NVME_SC_DNR << 1);
}
nvme_end_request(rq, status, result);
} else
__nvme_fc_final_op_cleanup(rq);
+
+check_error:
+ if (terminate_assoc)
+ nvme_fc_error_recovery(ctrl, "transport detected io error");
}
static int
dev_warn(ctrl->ctrl.device,
"NVME-FC{%d}: transport association error detected: %s\n",
ctrl->cnum, errmsg);
- dev_info(ctrl->ctrl.device,
+ dev_warn(ctrl->ctrl.device,
"NVME-FC{%d}: resetting controller\n", ctrl->cnum);
+ /* stop the queues on error, cleanup is in reset thread */
+ if (ctrl->queue_count > 1)
+ nvme_stop_queues(&ctrl->ctrl);
+
if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RECONNECTING)) {
dev_err(ctrl->ctrl.device,
"NVME-FC{%d}: error_recovery: Couldn't change state "
if (!opts->nr_io_queues)
return 0;
- dev_info(ctrl->ctrl.device, "creating %d I/O queues.\n",
- opts->nr_io_queues);
-
nvme_fc_init_io_queues(ctrl);
memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set));
if (ctrl->queue_count == 1)
return 0;
- dev_info(ctrl->ctrl.device, "Recreating %d I/O queues.\n",
- opts->nr_io_queues);
-
nvme_fc_init_io_queues(ctrl);
ret = blk_mq_reinit_tagset(&ctrl->tag_set);
int ret;
bool changed;
- ctrl->connect_attempts++;
+ ++ctrl->ctrl.opts->nr_reconnects;
/*
* Create the admin queue
changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
WARN_ON_ONCE(!changed);
- ctrl->connect_attempts = 0;
-
- kref_get(&ctrl->ctrl.kref);
+ ctrl->ctrl.opts->nr_reconnects = 0;
if (ctrl->queue_count > 1) {
nvme_start_queues(&ctrl->ctrl);
/*
* tear down the controller
- * This will result in the last reference on the nvme ctrl to
- * expire, calling the transport nvme_fc_nvme_ctrl_freed() callback.
- * From there, the transport will tear down it's logical queues and
- * association.
+ * After the last reference on the nvme ctrl is removed,
+ * the transport nvme_fc_nvme_ctrl_freed() callback will be
+ * invoked. From there, the transport will tear down it's
+ * logical queues and association.
*/
nvme_uninit_ctrl(&ctrl->ctrl);
nvme_put_ctrl(&ctrl->ctrl);
}
-static int
-__nvme_fc_del_ctrl(struct nvme_fc_ctrl *ctrl)
+static bool
+__nvme_fc_schedule_delete_work(struct nvme_fc_ctrl *ctrl)
{
if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING))
- return -EBUSY;
+ return true;
if (!queue_work(nvme_fc_wq, &ctrl->delete_work))
- return -EBUSY;
+ return true;
- return 0;
+ return false;
+}
+
+static int
+__nvme_fc_del_ctrl(struct nvme_fc_ctrl *ctrl)
+{
+ return __nvme_fc_schedule_delete_work(ctrl) ? -EBUSY : 0;
}
/*
return ret;
}
+static void
+nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status)
+{
+ /* If we are resetting/deleting then do nothing */
+ if (ctrl->ctrl.state != NVME_CTRL_RECONNECTING) {
+ WARN_ON_ONCE(ctrl->ctrl.state == NVME_CTRL_NEW ||
+ ctrl->ctrl.state == NVME_CTRL_LIVE);
+ return;
+ }
+
+ dev_info(ctrl->ctrl.device,
+ "NVME-FC{%d}: reset: Reconnect attempt failed (%d)\n",
+ ctrl->cnum, status);
+
+ if (nvmf_should_reconnect(&ctrl->ctrl)) {
+ dev_info(ctrl->ctrl.device,
+ "NVME-FC{%d}: Reconnect attempt in %d seconds.\n",
+ ctrl->cnum, ctrl->ctrl.opts->reconnect_delay);
+ queue_delayed_work(nvme_fc_wq, &ctrl->connect_work,
+ ctrl->ctrl.opts->reconnect_delay * HZ);
+ } else {
+ dev_warn(ctrl->ctrl.device,
+ "NVME-FC{%d}: Max reconnect attempts (%d) "
+ "reached. Removing controller\n",
+ ctrl->cnum, ctrl->ctrl.opts->nr_reconnects);
+ WARN_ON(__nvme_fc_schedule_delete_work(ctrl));
+ }
+}
+
static void
nvme_fc_reset_ctrl_work(struct work_struct *work)
{
nvme_fc_delete_association(ctrl);
ret = nvme_fc_create_association(ctrl);
- if (ret) {
- dev_warn(ctrl->ctrl.device,
- "NVME-FC{%d}: reset: Reconnect attempt failed (%d)\n",
- ctrl->cnum, ret);
- if (ctrl->connect_attempts >= NVME_FC_MAX_CONNECT_ATTEMPTS) {
- dev_warn(ctrl->ctrl.device,
- "NVME-FC{%d}: Max reconnect attempts (%d) "
- "reached. Removing controller\n",
- ctrl->cnum, ctrl->connect_attempts);
-
- if (!nvme_change_ctrl_state(&ctrl->ctrl,
- NVME_CTRL_DELETING)) {
- dev_err(ctrl->ctrl.device,
- "NVME-FC{%d}: failed to change state "
- "to DELETING\n", ctrl->cnum);
- return;
- }
-
- WARN_ON(!queue_work(nvme_fc_wq, &ctrl->delete_work));
- return;
- }
-
- dev_warn(ctrl->ctrl.device,
- "NVME-FC{%d}: Reconnect attempt in %d seconds.\n",
- ctrl->cnum, ctrl->reconnect_delay);
- queue_delayed_work(nvme_fc_wq, &ctrl->connect_work,
- ctrl->reconnect_delay * HZ);
- } else
+ if (ret)
+ nvme_fc_reconnect_or_delete(ctrl, ret);
+ else
dev_info(ctrl->ctrl.device,
"NVME-FC{%d}: controller reset complete\n", ctrl->cnum);
}
{
struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
- dev_warn(ctrl->ctrl.device,
+ dev_info(ctrl->ctrl.device,
"NVME-FC{%d}: admin requested controller reset\n", ctrl->cnum);
if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RESETTING))
static const struct nvme_ctrl_ops nvme_fc_ctrl_ops = {
.name = "fc",
.module = THIS_MODULE,
- .is_fabrics = true,
+ .flags = NVME_F_FABRICS,
.reg_read32 = nvmf_reg_read32,
.reg_read64 = nvmf_reg_read64,
.reg_write32 = nvmf_reg_write32,
struct nvme_fc_ctrl, connect_work);
ret = nvme_fc_create_association(ctrl);
- if (ret) {
- dev_warn(ctrl->ctrl.device,
- "NVME-FC{%d}: Reconnect attempt failed (%d)\n",
- ctrl->cnum, ret);
- if (ctrl->connect_attempts >= NVME_FC_MAX_CONNECT_ATTEMPTS) {
- dev_warn(ctrl->ctrl.device,
- "NVME-FC{%d}: Max reconnect attempts (%d) "
- "reached. Removing controller\n",
- ctrl->cnum, ctrl->connect_attempts);
-
- if (!nvme_change_ctrl_state(&ctrl->ctrl,
- NVME_CTRL_DELETING)) {
- dev_err(ctrl->ctrl.device,
- "NVME-FC{%d}: failed to change state "
- "to DELETING\n", ctrl->cnum);
- return;
- }
-
- WARN_ON(!queue_work(nvme_fc_wq, &ctrl->delete_work));
- return;
- }
-
- dev_warn(ctrl->ctrl.device,
- "NVME-FC{%d}: Reconnect attempt in %d seconds.\n",
- ctrl->cnum, ctrl->reconnect_delay);
- queue_delayed_work(nvme_fc_wq, &ctrl->connect_work,
- ctrl->reconnect_delay * HZ);
- } else
+ if (ret)
+ nvme_fc_reconnect_or_delete(ctrl, ret);
+ else
dev_info(ctrl->ctrl.device,
"NVME-FC{%d}: controller reconnect complete\n",
ctrl->cnum);
unsigned long flags;
int ret, idx;
+ if (!(rport->remoteport.port_role &
+ (FC_PORT_ROLE_NVME_DISCOVERY | FC_PORT_ROLE_NVME_TARGET))) {
+ ret = -EBADR;
+ goto out_fail;
+ }
+
ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL);
if (!ctrl) {
ret = -ENOMEM;
INIT_WORK(&ctrl->delete_work, nvme_fc_delete_ctrl_work);
INIT_WORK(&ctrl->reset_work, nvme_fc_reset_ctrl_work);
INIT_DELAYED_WORK(&ctrl->connect_work, nvme_fc_connect_ctrl_work);
- ctrl->reconnect_delay = opts->reconnect_delay;
spin_lock_init(&ctrl->lock);
/* io queue count */
return ERR_PTR(ret);
}
+ kref_get(&ctrl->ctrl.kref);
+
dev_info(ctrl->ctrl.device,
"NVME-FC{%d}: new ctrl: NQN \"%s\"\n",
ctrl->cnum, ctrl->ctrl.opts->subsysnqn);
static struct nvmf_transport_ops nvme_fc_transport = {
.name = "fc",
.required_opts = NVMF_OPT_TRADDR | NVMF_OPT_HOST_TRADDR,
- .allowed_opts = NVMF_OPT_RECONNECT_DELAY,
+ .allowed_opts = NVMF_OPT_RECONNECT_DELAY | NVMF_OPT_CTRL_LOSS_TMO,
.create_ctrl = nvme_fc_create_ctrl,
};
struct nvme_ctrl_ops {
const char *name;
struct module *module;
- bool is_fabrics;
+ unsigned int flags;
+#define NVME_F_FABRICS (1 << 0)
+#define NVME_F_METADATA_SUPPORTED (1 << 1)
int (*reg_read32)(struct nvme_ctrl *ctrl, u32 off, u32 *val);
int (*reg_write32)(struct nvme_ctrl *ctrl, u32 off, u32 val);
int (*reg_read64)(struct nvme_ctrl *ctrl, u32 off, u64 *val);
c.dbbuf.prp2 = cpu_to_le64(dev->dbbuf_eis_dma_addr);
if (nvme_submit_sync_cmd(dev->ctrl.admin_q, &c, NULL, 0)) {
- dev_warn(dev->dev, "unable to set dbbuf\n");
+ dev_warn(dev->ctrl.device, "unable to set dbbuf\n");
/* Free memory and continue on */
nvme_dbbuf_dma_free(dev);
}
bool nssro = dev->subsystem && (csts & NVME_CSTS_NSSRO);
/* If there is a reset ongoing, we shouldn't reset again. */
- if (work_busy(&dev->reset_work))
+ if (dev->ctrl.state == NVME_CTRL_RESETTING)
return false;
/* We shouldn't reset unless the controller is on fatal error state
result = pci_read_config_word(to_pci_dev(dev->dev), PCI_STATUS,
&pci_status);
if (result == PCIBIOS_SUCCESSFUL)
- dev_warn(dev->dev,
+ dev_warn(dev->ctrl.device,
"controller is down; will reset: CSTS=0x%x, PCI_STATUS=0x%hx\n",
csts, pci_status);
else
- dev_warn(dev->dev,
+ dev_warn(dev->ctrl.device,
"controller is down; will reset: CSTS=0x%x, PCI_STATUS read failed (%d)\n",
csts, result);
}
if (dev->cmb) {
iounmap(dev->cmb);
dev->cmb = NULL;
+ if (dev->cmbsz) {
+ sysfs_remove_file_from_group(&dev->ctrl.device->kobj,
+ &dev_attr_cmb.attr, NULL);
+ dev->cmbsz = 0;
+ }
}
}
*/
if (pdev->vendor == PCI_VENDOR_ID_APPLE && pdev->device == 0x2001) {
dev->q_depth = 2;
- dev_warn(dev->dev, "detected Apple NVMe controller, set "
- "queue depth=%u to work around controller resets\n",
+ dev_warn(dev->ctrl.device, "detected Apple NVMe controller, "
+ "set queue depth=%u to work around controller resets\n",
dev->q_depth);
}
if (dev->cmbsz) {
if (sysfs_add_file_to_group(&dev->ctrl.device->kobj,
&dev_attr_cmb.attr, NULL))
- dev_warn(dev->dev,
+ dev_warn(dev->ctrl.device,
"failed to add sysfs attribute for CMB\n");
}
}
{
struct pci_dev *pdev = to_pci_dev(dev->dev);
+ nvme_release_cmb(dev);
pci_free_irq_vectors(pdev);
if (pci_is_enabled(pdev)) {
bool was_suspend = !!(dev->ctrl.ctrl_config & NVME_CC_SHN_NORMAL);
int result = -ENODEV;
- if (WARN_ON(dev->ctrl.state == NVME_CTRL_RESETTING))
+ if (WARN_ON(dev->ctrl.state != NVME_CTRL_RESETTING))
goto out;
/*
if (dev->ctrl.ctrl_config & NVME_CC_ENABLE)
nvme_dev_disable(dev, false);
- if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RESETTING))
- goto out;
-
result = nvme_pci_enable(dev);
if (result)
goto out;
{
if (!dev->ctrl.admin_q || blk_queue_dying(dev->ctrl.admin_q))
return -ENODEV;
- if (work_busy(&dev->reset_work))
- return -ENODEV;
+ if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RESETTING))
+ return -EBUSY;
if (!queue_work(nvme_workq, &dev->reset_work))
return -EBUSY;
return 0;
static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
.name = "pcie",
.module = THIS_MODULE,
+ .flags = NVME_F_METADATA_SUPPORTED,
.reg_read32 = nvme_pci_reg_read32,
.reg_write32 = nvme_pci_reg_write32,
.reg_read64 = nvme_pci_reg_read64,
if (result)
goto release_pools;
+ nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RESETTING);
dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev));
queue_work(nvme_workq, &dev->reset_work);
nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING);
+ cancel_work_sync(&dev->reset_work);
pci_set_drvdata(pdev, NULL);
if (!pci_device_is_present(pdev)) {
nvme_dev_disable(dev, true);
nvme_dev_remove_admin(dev);
nvme_free_queues(dev, 0);
- nvme_release_cmb(dev);
nvme_release_prp_pools(dev);
nvme_dev_unmap(dev);
nvme_put_ctrl(&dev->ctrl);
{ PCI_VDEVICE(INTEL, 0x0a54),
.driver_data = NVME_QUIRK_STRIPE_SIZE |
NVME_QUIRK_DEALLOCATE_ZEROES, },
+ { PCI_VDEVICE(INTEL, 0xf1a5), /* Intel 600P/P3100 */
+ .driver_data = NVME_QUIRK_NO_DEEPEST_PS },
{ PCI_VDEVICE(INTEL, 0x5845), /* Qemu emulated controller */
.driver_data = NVME_QUIRK_IDENTIFY_CNS, },
{ PCI_DEVICE(0x1c58, 0x0003), /* HGST adapter */
if (ret)
goto requeue;
- blk_mq_start_stopped_hw_queues(ctrl->ctrl.admin_q, true);
-
ret = nvmf_connect_admin_queue(&ctrl->ctrl);
if (ret)
- goto stop_admin_q;
+ goto requeue;
set_bit(NVME_RDMA_Q_LIVE, &ctrl->queues[0].flags);
ret = nvme_enable_ctrl(&ctrl->ctrl, ctrl->cap);
if (ret)
- goto stop_admin_q;
+ goto requeue;
nvme_start_keep_alive(&ctrl->ctrl);
if (ctrl->queue_count > 1) {
ret = nvme_rdma_init_io_queues(ctrl);
if (ret)
- goto stop_admin_q;
+ goto requeue;
ret = nvme_rdma_connect_io_queues(ctrl);
if (ret)
- goto stop_admin_q;
+ goto requeue;
}
changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
ctrl->ctrl.opts->nr_reconnects = 0;
if (ctrl->queue_count > 1) {
- nvme_start_queues(&ctrl->ctrl);
nvme_queue_scan(&ctrl->ctrl);
nvme_queue_async_events(&ctrl->ctrl);
}
return;
-stop_admin_q:
- blk_mq_stop_hw_queues(ctrl->ctrl.admin_q);
requeue:
dev_info(ctrl->ctrl.device, "Failed reconnect attempt %d\n",
ctrl->ctrl.opts->nr_reconnects);
blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
nvme_cancel_request, &ctrl->ctrl);
+ /*
+ * queues are not a live anymore, so restart the queues to fail fast
+ * new IO
+ */
+ blk_mq_start_stopped_hw_queues(ctrl->ctrl.admin_q, true);
+ nvme_start_queues(&ctrl->ctrl);
+
nvme_rdma_reconnect_or_remove(ctrl);
}
nvme_rdma_wr_error(cq, wc, "SEND");
}
+static inline int nvme_rdma_queue_sig_limit(struct nvme_rdma_queue *queue)
+{
+ int sig_limit;
+
+ /*
+ * We signal completion every queue depth/2 and also handle the
+ * degenerated case of a device with queue_depth=1, where we
+ * would need to signal every message.
+ */
+ sig_limit = max(queue->queue_size / 2, 1);
+ return (++queue->sig_count % sig_limit) == 0;
+}
+
static int nvme_rdma_post_send(struct nvme_rdma_queue *queue,
struct nvme_rdma_qe *qe, struct ib_sge *sge, u32 num_sge,
struct ib_send_wr *first, bool flush)
* Would have been way to obvious to handle this in hardware or
* at least the RDMA stack..
*
- * This messy and racy code sniplet is copy and pasted from the iSER
- * initiator, and the magic '32' comes from there as well.
- *
* Always signal the flushes. The magic request used for the flush
* sequencer is not allocated in our driver's tagset and it's
* triggered to be freed by blk_cleanup_queue(). So we need to
* embedded in request's payload, is not freed when __ib_process_cq()
* calls wr_cqe->done().
*/
- if ((++queue->sig_count % 32) == 0 || flush)
+ if (nvme_rdma_queue_sig_limit(queue) || flush)
wr.send_flags |= IB_SEND_SIGNALED;
if (first)
/*
* We cannot accept any other command until the Connect command has completed.
*/
-static inline bool nvme_rdma_queue_is_ready(struct nvme_rdma_queue *queue,
+static inline int nvme_rdma_queue_is_ready(struct nvme_rdma_queue *queue,
struct request *rq)
{
if (unlikely(!test_bit(NVME_RDMA_Q_LIVE, &queue->flags))) {
if (!blk_rq_is_passthrough(rq) ||
cmd->common.opcode != nvme_fabrics_command ||
- cmd->fabrics.fctype != nvme_fabrics_type_connect)
- return false;
+ cmd->fabrics.fctype != nvme_fabrics_type_connect) {
+ /*
+ * reconnecting state means transport disruption, which
+ * can take a long time and even might fail permanently,
+ * so we can't let incoming I/O be requeued forever.
+ * fail it fast to allow upper layers a chance to
+ * failover.
+ */
+ if (queue->ctrl->ctrl.state == NVME_CTRL_RECONNECTING)
+ return -EIO;
+ else
+ return -EAGAIN;
+ }
}
- return true;
+ return 0;
}
static int nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
WARN_ON_ONCE(rq->tag < 0);
- if (!nvme_rdma_queue_is_ready(queue, rq))
- return BLK_MQ_RQ_QUEUE_BUSY;
+ ret = nvme_rdma_queue_is_ready(queue, rq);
+ if (unlikely(ret))
+ goto err;
dev = queue->device->dev;
ib_dma_sync_single_for_cpu(dev, sqe->dma,
static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = {
.name = "rdma",
.module = THIS_MODULE,
- .is_fabrics = true,
+ .flags = NVME_F_FABRICS,
.reg_read32 = nvmf_reg_read32,
.reg_read64 = nvmf_reg_read64,
.reg_write32 = nvmf_reg_write32,
}
EXPORT_SYMBOL_GPL(nvmet_req_init);
+void nvmet_req_uninit(struct nvmet_req *req)
+{
+ percpu_ref_put(&req->sq->ref);
+}
+EXPORT_SYMBOL_GPL(nvmet_req_uninit);
+
static inline bool nvmet_cc_en(u32 cc)
{
return cc & 0x1;
{
int cpu, idx, cnt;
- if (!(tgtport->ops->target_features &
- NVMET_FCTGTFEAT_NEEDS_CMD_CPUSCHED) ||
- tgtport->ops->max_hw_queues == 1)
+ if (tgtport->ops->max_hw_queues == 1)
return WORK_CPU_UNBOUND;
/* Simple cpu selection based on qid modulo active cpu count */
.dma_boundary = FCLOOP_DMABOUND_4G,
/* optional features */
.target_features = NVMET_FCTGTFEAT_CMD_IN_ISR |
- NVMET_FCTGTFEAT_NEEDS_CMD_CPUSCHED |
NVMET_FCTGTFEAT_OPDONE_IN_ISR,
/* sizes of additional private data for data structures */
.target_priv_sz = sizeof(struct fcloop_tport),
static const struct nvme_ctrl_ops nvme_loop_ctrl_ops = {
.name = "loop",
.module = THIS_MODULE,
- .is_fabrics = true,
+ .flags = NVME_F_FABRICS,
.reg_read32 = nvmf_reg_read32,
.reg_read64 = nvmf_reg_read64,
.reg_write32 = nvmf_reg_write32,
bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
struct nvmet_sq *sq, struct nvmet_fabrics_ops *ops);
+void nvmet_req_uninit(struct nvmet_req *req);
void nvmet_req_complete(struct nvmet_req *req, u16 status);
void nvmet_cq_setup(struct nvmet_ctrl *ctrl, struct nvmet_cq *cq, u16 qid,
rsp->n_rdma = 0;
if (unlikely(wc->status != IB_WC_SUCCESS)) {
+ nvmet_req_uninit(&rsp->req);
nvmet_rdma_release_rsp(rsp);
if (wc->status != IB_WC_WR_FLUSH_ERR) {
pr_info("RDMA READ for CQE 0x%p failed with status %s (%d).\n",
coherent ? " " : " not ");
iommu = of_iommu_configure(dev, np);
- if (IS_ERR(iommu))
- return PTR_ERR(iommu);
+ if (IS_ERR(iommu) && PTR_ERR(iommu) == -EPROBE_DEFER)
+ return -EPROBE_DEFER;
dev_dbg(dev, "device is%sbehind an iommu\n",
iommu ? " " : " not ");
/* Allocate memory for the expanded device tree */
mem = dt_alloc(size + 4, __alignof__(struct device_node));
+ if (!mem)
+ return NULL;
+
memset(mem, 0, size);
*(__be32 *)(mem + size) = cpu_to_be32(0xdeadbeef);
const struct of_device_id *i;
for (i = __reservedmem_of_table; i < &__rmem_of_table_sentinel; i++) {
- int const (*initfn)(struct reserved_mem *rmem) = i->data;
+ reservedmem_of_init_fn initfn = i->data;
const char *compat = i->compatible;
if (!of_flat_dt_is_compatible(rmem->fdt_node, compat))
arch_initcall_sync(of_platform_default_populate_init);
#endif
-static int of_platform_device_destroy(struct device *dev, void *data)
+int of_platform_device_destroy(struct device *dev, void *data)
{
/* Do not touch devices not populated from the device tree */
if (!dev->of_node || !of_node_check_flag(dev->of_node, OF_POPULATED))
of_node_clear_flag(dev->of_node, OF_POPULATED_BUS);
return 0;
}
+EXPORT_SYMBOL_GPL(of_platform_device_destroy);
/**
* of_platform_depopulate() - Remove devices populated from device tree
static int imx6q_pcie_abort_handler(unsigned long addr,
unsigned int fsr, struct pt_regs *regs)
{
- return 0;
+ unsigned long pc = instruction_pointer(regs);
+ unsigned long instr = *(unsigned long *)pc;
+ int reg = (instr >> 12) & 15;
+
+ /*
+ * If the instruction being executed was a read,
+ * make it look like it read all-ones.
+ */
+ if ((instr & 0x0c100000) == 0x04100000) {
+ unsigned long val;
+
+ if (instr & 0x00400000)
+ val = 255;
+ else
+ val = -1;
+
+ regs->uregs[reg] = val;
+ regs->ARM_pc += 4;
+ return 0;
+ }
+
+ if ((instr & 0x0e100090) == 0x00100090) {
+ regs->uregs[reg] = -1;
+ regs->ARM_pc += 4;
+ return 0;
+ }
+
+ return 1;
}
static void imx6_pcie_assert_core_reset(struct imx6_pcie *imx6_pcie)
* we can install the handler here without risking it
* accessing some uninitialized driver state.
*/
- hook_fault_code(16 + 6, imx6q_pcie_abort_handler, SIGBUS, 0,
- "imprecise external abort");
+ hook_fault_code(8, imx6q_pcie_abort_handler, SIGBUS, 0,
+ "external abort on non-linefetch");
return platform_driver_register(&imx6_pcie_driver);
}
config PCI_ENDPOINT
bool "PCI Endpoint Support"
+ depends on HAS_DMA
help
Enable this configuration option to support configurable PCI
endpoint. This should be enabled if the platform has a PCI
if (!pm_runtime_suspended(dev)
|| pci_target_state(pci_dev) != pci_dev->current_state
- || platform_pci_need_resume(pci_dev))
+ || platform_pci_need_resume(pci_dev)
+ || (pci_dev->dev_flags & PCI_DEV_FLAGS_NEEDS_RESUME))
return false;
/*
cdev = &stdev->cdev;
cdev_init(cdev, &switchtec_fops);
cdev->owner = THIS_MODULE;
- cdev->kobj.parent = &dev->kobj;
return stdev;
stdev->mmio_sys_info = stdev->mmio + SWITCHTEC_GAS_SYS_INFO_OFFSET;
stdev->mmio_flash_info = stdev->mmio + SWITCHTEC_GAS_FLASH_INFO_OFFSET;
stdev->mmio_ntb = stdev->mmio + SWITCHTEC_GAS_NTB_OFFSET;
- stdev->partition = ioread8(&stdev->mmio_ntb->partition_id);
+ stdev->partition = ioread8(&stdev->mmio_sys_info->partition_id);
stdev->partition_count = ioread8(&stdev->mmio_ntb->partition_count);
stdev->mmio_part_cfg_all = stdev->mmio + SWITCHTEC_GAS_PART_CFG_OFFSET;
stdev->mmio_part_cfg = &stdev->mmio_part_cfg_all[stdev->partition];
stdev->mmio_pff_csr = stdev->mmio + SWITCHTEC_GAS_PFF_CSR_OFFSET;
+ if (stdev->partition_count < 1)
+ stdev->partition_count = 1;
+
init_pff(stdev);
pci_set_drvdata(pdev, stdev);
SWITCHTEC_EVENT_EN_IRQ,
&stdev->mmio_part_cfg->mrpc_comp_hdr);
- rc = cdev_add(&stdev->cdev, stdev->dev.devt, 1);
- if (rc)
- goto err_put;
-
- rc = device_add(&stdev->dev);
+ rc = cdev_device_add(&stdev->cdev, &stdev->dev);
if (rc)
goto err_devadd;
return 0;
err_devadd:
- cdev_del(&stdev->cdev);
stdev_kill(stdev);
err_put:
ida_simple_remove(&switchtec_minor_ida, MINOR(stdev->dev.devt));
pci_set_drvdata(pdev, NULL);
- device_del(&stdev->dev);
- cdev_del(&stdev->cdev);
+ cdev_device_del(&stdev->cdev, &stdev->dev);
ida_simple_remove(&switchtec_minor_ida, MINOR(stdev->dev.devt));
dev_info(&stdev->dev, "unregistered.\n");
return -EINVAL;
gsi = gicc->performance_interrupt;
+
+ /*
+ * Per the ACPI spec, the MADT cannot describe a PMU that doesn't
+ * have an interrupt. QEMU advertises this by using a GSI of zero,
+ * which is not known to be valid on any hardware despite being
+ * valid per the spec. Take the pragmatic approach and reject a
+ * GSI of zero for now.
+ */
+ if (!gsi)
+ return 0;
+
if (gicc->flags & ACPI_MADT_PERFORMANCE_IRQ_MODE)
trigger = ACPI_EDGE_SENSITIVE;
else
int num = qmp->cfg->num_vregs;
int i;
- qmp->vregs = devm_kcalloc(dev, num, sizeof(qmp->vregs), GFP_KERNEL);
+ qmp->vregs = devm_kcalloc(dev, num, sizeof(*qmp->vregs), GFP_KERNEL);
if (!qmp->vregs)
return -ENOMEM;
* Resources are indexed as: tx -> 0; rx -> 1; pcs -> 2.
*/
qphy->tx = of_iomap(np, 0);
- if (IS_ERR(qphy->tx))
- return PTR_ERR(qphy->tx);
+ if (!qphy->tx)
+ return -ENOMEM;
qphy->rx = of_iomap(np, 1);
- if (IS_ERR(qphy->rx))
- return PTR_ERR(qphy->rx);
+ if (!qphy->rx)
+ return -ENOMEM;
qphy->pcs = of_iomap(np, 2);
- if (IS_ERR(qphy->pcs))
- return PTR_ERR(qphy->pcs);
+ if (!qphy->pcs)
+ return -ENOMEM;
/*
* Get PHY's Pipe clock, if any. USB3 and PCIe are PIPE3
* pinctrl_generic_free_groups() - removes all pin groups
* @pctldev: pin controller device
*
- * Note that the caller must take care of locking.
+ * Note that the caller must take care of locking. The pinctrl groups
+ * are allocated with devm_kzalloc() so no need to free them here.
*/
static void pinctrl_generic_free_groups(struct pinctrl_dev *pctldev)
{
struct radix_tree_iter iter;
- struct group_desc *group;
- unsigned long *indices;
void **slot;
- int i = 0;
-
- indices = devm_kzalloc(pctldev->dev, sizeof(*indices) *
- pctldev->num_groups, GFP_KERNEL);
- if (!indices)
- return;
radix_tree_for_each_slot(slot, &pctldev->pin_group_tree, &iter, 0)
- indices[i++] = iter.index;
-
- for (i = 0; i < pctldev->num_groups; i++) {
- group = radix_tree_lookup(&pctldev->pin_group_tree,
- indices[i]);
- radix_tree_delete(&pctldev->pin_group_tree, indices[i]);
- devm_kfree(pctldev->dev, group);
- }
+ radix_tree_delete(&pctldev->pin_group_tree, iter.index);
pctldev->num_groups = 0;
}
return 0;
}
+static void mxs_pinctrl_rmwl(u32 value, u32 mask, u8 shift, void __iomem *reg)
+{
+ u32 tmp;
+
+ tmp = readl(reg);
+ tmp &= ~(mask << shift);
+ tmp |= value << shift;
+ writel(tmp, reg);
+}
+
static int mxs_pinctrl_set_mux(struct pinctrl_dev *pctldev, unsigned selector,
unsigned group)
{
reg += bank * 0x20 + pin / 16 * 0x10;
shift = pin % 16 * 2;
- writel(0x3 << shift, reg + CLR);
- writel(g->muxsel[i] << shift, reg + SET);
+ mxs_pinctrl_rmwl(g->muxsel[i], 0x3, shift, reg);
}
return 0;
/* mA */
if (config & MA_PRESENT) {
shift = pin % 8 * 4;
- writel(0x3 << shift, reg + CLR);
- writel(ma << shift, reg + SET);
+ mxs_pinctrl_rmwl(ma, 0x3, shift, reg);
}
/* vol */
* is not listed below.
*/
static const struct dmi_system_id chv_no_valid_mask[] = {
+ /* See https://bugzilla.kernel.org/show_bug.cgi?id=194945 */
{
- /* See https://bugzilla.kernel.org/show_bug.cgi?id=194945 */
- .ident = "Acer Chromebook (CYAN)",
+ .ident = "Intel_Strago based Chromebooks (All models)",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"),
- DMI_MATCH(DMI_PRODUCT_NAME, "Edgar"),
- DMI_MATCH(DMI_BIOS_DATE, "05/21/2016"),
+ DMI_MATCH(DMI_PRODUCT_FAMILY, "Intel_Strago"),
},
- }
+ },
+ {
+ .ident = "Acer Chromebook R11 (Cyan)",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Cyan"),
+ },
+ },
+ {
+ .ident = "Samsung Chromebook 3 (Celes)",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Celes"),
+ },
+ },
+ {}
};
static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq)
PCONFDUMP(PIN_CONFIG_BIAS_PULL_PIN_DEFAULT,
"input bias pull to pin specific state", NULL, false),
PCONFDUMP(PIN_CONFIG_BIAS_PULL_UP, "input bias pull up", NULL, false),
- PCONFDUMP(PIN_CONFIG_BIDIRECTIONAL, "bi-directional pin operations", NULL, false),
PCONFDUMP(PIN_CONFIG_DRIVE_OPEN_DRAIN, "output drive open drain", NULL, false),
PCONFDUMP(PIN_CONFIG_DRIVE_OPEN_SOURCE, "output drive open source", NULL, false),
PCONFDUMP(PIN_CONFIG_DRIVE_PUSH_PULL, "output drive push pull", NULL, false),
{ "bias-pull-up", PIN_CONFIG_BIAS_PULL_UP, 1 },
{ "bias-pull-pin-default", PIN_CONFIG_BIAS_PULL_PIN_DEFAULT, 1 },
{ "bias-pull-down", PIN_CONFIG_BIAS_PULL_DOWN, 1 },
- { "bi-directional", PIN_CONFIG_BIDIRECTIONAL, 1 },
{ "drive-open-drain", PIN_CONFIG_DRIVE_OPEN_DRAIN, 0 },
{ "drive-open-source", PIN_CONFIG_DRIVE_OPEN_SOURCE, 0 },
{ "drive-push-pull", PIN_CONFIG_DRIVE_PUSH_PULL, 0 },
{ "input-schmitt-enable", PIN_CONFIG_INPUT_SCHMITT_ENABLE, 1 },
{ "low-power-disable", PIN_CONFIG_LOW_POWER_MODE, 0 },
{ "low-power-enable", PIN_CONFIG_LOW_POWER_MODE, 1 },
- { "output-enable", PIN_CONFIG_OUTPUT, 1, },
{ "output-high", PIN_CONFIG_OUTPUT, 1, },
{ "output-low", PIN_CONFIG_OUTPUT, 0, },
{ "power-source", PIN_CONFIG_POWER_SOURCE, 0 },
* pinmux_generic_free_functions() - removes all functions
* @pctldev: pin controller device
*
- * Note that the caller must take care of locking.
+ * Note that the caller must take care of locking. The pinctrl
+ * functions are allocated with devm_kzalloc() so no need to free
+ * them here.
*/
void pinmux_generic_free_functions(struct pinctrl_dev *pctldev)
{
struct radix_tree_iter iter;
- struct function_desc *function;
- unsigned long *indices;
void **slot;
- int i = 0;
-
- indices = devm_kzalloc(pctldev->dev, sizeof(*indices) *
- pctldev->num_functions, GFP_KERNEL);
- if (!indices)
- return;
radix_tree_for_each_slot(slot, &pctldev->pin_function_tree, &iter, 0)
- indices[i++] = iter.index;
-
- for (i = 0; i < pctldev->num_functions; i++) {
- function = radix_tree_lookup(&pctldev->pin_function_tree,
- indices[i]);
- radix_tree_delete(&pctldev->pin_function_tree, indices[i]);
- devm_kfree(pctldev->dev, function);
- }
+ radix_tree_delete(&pctldev->pin_function_tree, iter.index);
pctldev->num_functions = 0;
}
SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 18),
SUNXI_FUNCTION(0x0, "gpio_in"),
SUNXI_FUNCTION(0x1, "gpio_out"),
- SUNXI_FUNCTION(0x3, "owa")), /* DOUT */
+ SUNXI_FUNCTION(0x3, "spdif")), /* DOUT */
SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 19),
SUNXI_FUNCTION(0x0, "gpio_in"),
SUNXI_FUNCTION(0x1, "gpio_out")),
/* Reallocate the array */
u32 new_capacity = 2 * dev->pipes_capacity;
struct goldfish_pipe **pipes =
- kcalloc(new_capacity, sizeof(*pipes), GFP_KERNEL);
+ kcalloc(new_capacity, sizeof(*pipes), GFP_ATOMIC);
if (!pipes)
return -ENOMEM;
memcpy(pipes, dev->pipes, sizeof(*pipes) * dev->pipes_capacity);
power_zone->id = result;
idr_init(&power_zone->idr);
+ result = -ENOMEM;
power_zone->name = kstrdup(name, GFP_KERNEL);
if (!power_zone->name)
goto err_name_alloc;
}
postcore_initcall(hi6220_reset_init);
+
+MODULE_LICENSE("GPL v2");
}
spin_unlock_irqrestore(&rtc_lock, flags);
- pm_wakeup_event(dev, 0);
+ pm_wakeup_hard_event(dev);
acpi_clear_event(ACPI_EVENT_RTC);
acpi_disable_event(ACPI_EVENT_RTC, 0);
return ACPI_INTERRUPT_HANDLED;
struct bnx2fc_cmd_mgr *cmd_mgr;
spinlock_t hba_lock;
struct mutex hba_mutex;
+ struct mutex hba_stats_mutex;
unsigned long adapter_state;
#define ADAPTER_STATE_UP 0
#define ADAPTER_STATE_GOING_DOWN 1
if (!fw_stats)
return NULL;
+ mutex_lock(&hba->hba_stats_mutex);
+
bnx2fc_stats = fc_get_host_stats(shost);
init_completion(&hba->stat_req_done);
if (bnx2fc_send_stat_req(hba))
- return bnx2fc_stats;
+ goto unlock_stats_mutex;
rc = wait_for_completion_timeout(&hba->stat_req_done, (2 * HZ));
if (!rc) {
BNX2FC_HBA_DBG(lport, "FW stat req timed out\n");
- return bnx2fc_stats;
+ goto unlock_stats_mutex;
}
BNX2FC_STATS(hba, rx_stat2, fc_crc_cnt);
bnx2fc_stats->invalid_crc_count += hba->bfw_stats.fc_crc_cnt;
memcpy(&hba->prev_stats, hba->stats_buffer,
sizeof(struct fcoe_statistics_params));
+
+unlock_stats_mutex:
+ mutex_unlock(&hba->hba_stats_mutex);
return bnx2fc_stats;
}
}
spin_lock_init(&hba->hba_lock);
mutex_init(&hba->hba_mutex);
+ mutex_init(&hba->hba_stats_mutex);
hba->cnic = cnic;
goto bye;
}
- mempool_free(mbp, hw->mb_mempool);
if (finicsum != cfcsum) {
csio_warn(hw,
"Config File checksum mismatch: csum=%#x, computed=%#x\n",
rv = csio_hw_validate_caps(hw, mbp);
if (rv != 0)
goto bye;
+
+ mempool_free(mbp, hw->mb_mempool);
+ mbp = NULL;
+
/*
* Note that we're operating with parameters
* not supplied by the driver, rather than from hard-wired
cxgbi_sock_put(csk);
}
csk->dst = NULL;
- csk->cdev = NULL;
}
static int init_act_open(struct cxgbi_sock *csk)
log_debug(1 << CXGBI_DBG_SOCK, "csk 0x%p,%u,0x%lx,%u.\n",
csk, (csk)->state, (csk)->flags, (csk)->tid);
spin_lock_bh(&csk->lock);
- dst_confirm(csk->dst);
+ if (csk->dst)
+ dst_confirm(csk->dst);
data_lost = skb_queue_len(&csk->receive_queue);
__skb_queue_purge(&csk->receive_queue);
}
if (close_req) {
- if (data_lost)
+ if (!cxgbi_sock_flag(csk, CTPF_LOGOUT_RSP_RCVD) ||
+ data_lost)
csk->cdev->csk_send_abort_req(csk);
else
csk->cdev->csk_send_close_req(csk);
cxgbi_ulp_extra_len(cxgbi_skcb_ulp_mode(skb));
skb = next;
}
-done:
+
if (likely(skb_queue_len(&csk->write_queue)))
cdev->csk_push_tx_frames(csk, 1);
+done:
spin_unlock_bh(&csk->lock);
return copied;
}
}
-static int skb_read_pdu_bhs(struct iscsi_conn *conn, struct sk_buff *skb)
+static int
+skb_read_pdu_bhs(struct cxgbi_sock *csk, struct iscsi_conn *conn,
+ struct sk_buff *skb)
{
struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
+ int err;
log_debug(1 << CXGBI_DBG_PDU_RX,
"conn 0x%p, skb 0x%p, len %u, flag 0x%lx.\n",
}
}
- return read_pdu_skb(conn, skb, 0, 0);
+ err = read_pdu_skb(conn, skb, 0, 0);
+ if (likely(err >= 0)) {
+ struct iscsi_hdr *hdr = (struct iscsi_hdr *)skb->data;
+ u8 opcode = hdr->opcode & ISCSI_OPCODE_MASK;
+
+ if (unlikely(opcode == ISCSI_OP_LOGOUT_RSP))
+ cxgbi_sock_set_flag(csk, CTPF_LOGOUT_RSP_RCVD);
+ }
+
+ return err;
}
static int skb_read_pdu_data(struct iscsi_conn *conn, struct sk_buff *lskb,
cxgbi_skcb_rx_pdulen(skb));
if (cxgbi_skcb_test_flag(skb, SKCBF_RX_COALESCED)) {
- err = skb_read_pdu_bhs(conn, skb);
+ err = skb_read_pdu_bhs(csk, conn, skb);
if (err < 0) {
pr_err("coalesced bhs, csk 0x%p, skb 0x%p,%u, "
"f 0x%lx, plen %u.\n",
cxgbi_skcb_flags(skb),
cxgbi_skcb_rx_pdulen(skb));
} else {
- err = skb_read_pdu_bhs(conn, skb);
+ err = skb_read_pdu_bhs(csk, conn, skb);
if (err < 0) {
pr_err("bhs, csk 0x%p, skb 0x%p,%u, "
"f 0x%lx, plen %u.\n",
tcp_task->dd_data = tdata;
task->hdr = NULL;
+ if (tdata->skb) {
+ kfree_skb(tdata->skb);
+ tdata->skb = NULL;
+ }
+
if (SKB_MAX_HEAD(cdev->skb_tx_rsvd) > (512 * MAX_SKB_FRAGS) &&
(opcode == ISCSI_OP_SCSI_DATA_OUT ||
(opcode == ISCSI_OP_SCSI_CMD &&
return -ENOMEM;
}
+ skb_get(tdata->skb);
skb_reserve(tdata->skb, cdev->skb_tx_rsvd);
task->hdr = (struct iscsi_hdr *)tdata->skb->data;
task->hdr_max = SKB_TX_ISCSI_PDU_HEADER_MAX; /* BHS + AHS */
unsigned int datalen;
int err;
- if (!skb) {
+ if (!skb || cxgbi_skcb_test_flag(skb, SKCBF_TX_DONE)) {
log_debug(1 << CXGBI_DBG_ISCSI | 1 << CXGBI_DBG_PDU_TX,
- "task 0x%p, skb NULL.\n", task);
+ "task 0x%p, skb 0x%p\n", task, skb);
return 0;
}
}
datalen = skb->data_len;
- tdata->skb = NULL;
/* write ppod first if using ofldq to write ppod */
if (ttinfo->flags & CXGBI_PPOD_INFO_FLAG_VALID) {
pdulen += ISCSI_DIGEST_SIZE;
task->conn->txdata_octets += pdulen;
+ cxgbi_skcb_set_flag(skb, SKCBF_TX_DONE);
return 0;
}
"task 0x%p, skb 0x%p, len %u/%u, %d EAGAIN.\n",
task, skb, skb->len, skb->data_len, err);
/* reset skb to send when we are called again */
- tdata->skb = skb;
return err;
}
"itt 0x%x, skb 0x%p, len %u/%u, xmit err %d.\n",
task->itt, skb, skb->len, skb->data_len, err);
- kfree_skb(skb);
+ __kfree_skb(tdata->skb);
+ tdata->skb = NULL;
iscsi_conn_printk(KERN_ERR, task->conn, "xmit err %d.\n", err);
iscsi_conn_failure(task->conn, ISCSI_ERR_XMIT_FAILED);
tcp_task->dd_data = NULL;
/* never reached the xmit task callout */
- if (tdata->skb)
- __kfree_skb(tdata->skb);
+ if (tdata->skb) {
+ kfree_skb(tdata->skb);
+ tdata->skb = NULL;
+ }
task_release_itt(task, task->hdr_itt);
memset(tdata, 0, sizeof(*tdata));
static int __init libcxgbi_init_module(void)
{
pr_info("%s", version);
+
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, cb) <
+ sizeof(struct cxgbi_skb_cb));
return 0;
}
CTPF_HAS_ATID, /* reserved atid */
CTPF_HAS_TID, /* reserved hw tid */
CTPF_OFFLOAD_DOWN, /* offload function off */
+ CTPF_LOGOUT_RSP_RCVD, /* received logout response */
};
struct cxgbi_skb_rx_cb {
};
struct cxgbi_skb_tx_cb {
- void *l2t;
+ void *handle;
+ void *arp_err_handler;
struct sk_buff *wr_next;
};
SKCBF_TX_NEED_HDR, /* packet needs a header */
SKCBF_TX_MEM_WRITE, /* memory write */
SKCBF_TX_FLAG_COMPL, /* wr completion flag */
+ SKCBF_TX_DONE, /* skb tx done */
SKCBF_RX_COALESCED, /* received whole pdu */
SKCBF_RX_HDR, /* received pdu header */
SKCBF_RX_DATA, /* received pdu payload */
};
struct cxgbi_skb_cb {
- unsigned char ulp_mode;
- unsigned long flags;
- unsigned int seq;
union {
struct cxgbi_skb_rx_cb rx;
struct cxgbi_skb_tx_cb tx;
};
+ unsigned char ulp_mode;
+ unsigned long flags;
+ unsigned int seq;
};
#define CXGBI_SKB_CB(skb) ((struct cxgbi_skb_cb *)&((skb)->cb[0]))
cxgbi_skcb_tx_wr_next(skb) = NULL;
/*
* We want to take an extra reference since both us and the driver
- * need to free the packet before it's really freed. We know there's
- * just one user currently so we use atomic_set rather than skb_get
- * to avoid the atomic op.
+ * need to free the packet before it's really freed.
*/
- atomic_set(&skb->users, 2);
+ skb_get(skb);
if (!csk->wr_pending_head)
csk->wr_pending_head = skb;
config CXLFLASH
tristate "Support for IBM CAPI Flash"
depends on PCI && SCSI && CXL && EEH
+ select IRQ_POLL
default m
help
Allows CAPI Accelerated IO to Flash
struct list_head *list,
unsigned char *cdb)
{
- struct scsi_device *sdev = ctlr->ms_sdev;
- struct rdac_dh_data *h = sdev->handler_data;
struct rdac_mode_common *common;
unsigned data_size;
struct rdac_queue_data *qdata;
u8 *lun_table;
- if (h->ctlr->use_ms10) {
+ if (ctlr->use_ms10) {
struct rdac_pg_expanded *rdac_pg;
data_size = sizeof(struct rdac_pg_expanded);
- rdac_pg = &h->ctlr->mode_select.expanded;
+ rdac_pg = &ctlr->mode_select.expanded;
memset(rdac_pg, 0, data_size);
common = &rdac_pg->common;
rdac_pg->page_code = RDAC_PAGE_CODE_REDUNDANT_CONTROLLER + 0x40;
struct rdac_pg_legacy *rdac_pg;
data_size = sizeof(struct rdac_pg_legacy);
- rdac_pg = &h->ctlr->mode_select.legacy;
+ rdac_pg = &ctlr->mode_select.legacy;
memset(rdac_pg, 0, data_size);
common = &rdac_pg->common;
rdac_pg->page_code = RDAC_PAGE_CODE_REDUNDANT_CONTROLLER;
}
/* Prepare the command. */
- if (h->ctlr->use_ms10) {
+ if (ctlr->use_ms10) {
cdb[0] = MODE_SELECT_10;
cdb[7] = data_size >> 8;
cdb[8] = data_size & 0xff;
cmd = list_first_entry_or_null(&vscsi->free_cmd,
struct ibmvscsis_cmd, list);
if (cmd) {
+ if (cmd->abort_cmd)
+ cmd->abort_cmd = NULL;
cmd->flags &= ~(DELAY_SEND);
list_del(&cmd->list);
cmd->iue = iue;
if (cmd->abort_cmd) {
retry = true;
cmd->abort_cmd->flags &= ~(DELAY_SEND);
+ cmd->abort_cmd = NULL;
}
/*
list_del(&cmd->list);
ibmvscsis_free_cmd_resources(vscsi,
cmd);
+ /*
+ * With a successfully aborted op
+ * through LIO we want to increment the
+ * the vscsi credit so that when we dont
+ * send a rsp to the original scsi abort
+ * op (h_send_crq), but the tm rsp to
+ * the abort is sent, the credit is
+ * correctly sent with the abort tm rsp.
+ * We would need 1 for the abort tm rsp
+ * and 1 credit for the aborted scsi op.
+ * Thus we need to increment here.
+ * Also we want to increment the credit
+ * here because we want to make sure
+ * cmd is actually released first
+ * otherwise the client will think it
+ * it can send a new cmd, and we could
+ * find ourselves short of cmd elements.
+ */
+ vscsi->credit += 1;
} else {
iue = cmd->iue;
rsp->opcode = SRP_RSP;
- if (vscsi->credit > 0 && vscsi->state == SRP_PROCESSING)
- rsp->req_lim_delta = cpu_to_be32(vscsi->credit);
- else
- rsp->req_lim_delta = cpu_to_be32(1 + vscsi->credit);
+ rsp->req_lim_delta = cpu_to_be32(1 + vscsi->credit);
rsp->tag = cmd->rsp.tag;
rsp->flags = 0;
* can_queue. Eventually we will hit the point where we run
* on all reserved structs.
*/
-static void fc_fcp_can_queue_ramp_down(struct fc_lport *lport)
+static bool fc_fcp_can_queue_ramp_down(struct fc_lport *lport)
{
struct fc_fcp_internal *si = fc_get_scsi_internal(lport);
unsigned long flags;
int can_queue;
+ bool changed = false;
spin_lock_irqsave(lport->host->host_lock, flags);
if (!can_queue)
can_queue = 1;
lport->host->can_queue = can_queue;
+ changed = true;
unlock:
spin_unlock_irqrestore(lport->host->host_lock, flags);
+ return changed;
}
/*
if (!fc_fcp_lport_queue_ready(lport)) {
if (lport->qfull) {
- fc_fcp_can_queue_ramp_down(lport);
- shost_printk(KERN_ERR, lport->host,
- "libfc: queue full, "
- "reducing can_queue to %d.\n",
- lport->host->can_queue);
+ if (fc_fcp_can_queue_ramp_down(lport))
+ shost_printk(KERN_ERR, lport->host,
+ "libfc: queue full, "
+ "reducing can_queue to %d.\n",
+ lport->host->can_queue);
}
rc = SCSI_MLQUEUE_HOST_BUSY;
goto out;
fp = fc_frame_alloc(lport, sizeof(*rtv));
if (!fp) {
rjt_data.reason = ELS_RJT_UNAB;
- rjt_data.reason = ELS_EXPL_INSUF_RES;
+ rjt_data.explan = ELS_EXPL_INSUF_RES;
fc_seq_els_rsp_send(in_fp, ELS_LS_RJT, &rjt_data);
goto drop;
}
uint32_t buffer_tag; /* used for tagged queue ring */
};
+struct lpfc_nvmet_ctxbuf {
+ struct list_head list;
+ struct lpfc_nvmet_rcv_ctx *context;
+ struct lpfc_iocbq *iocbq;
+ struct lpfc_sglq *sglq;
+};
+
struct lpfc_dma_pool {
struct lpfc_dmabuf *elements;
uint32_t max_count;
struct lpfc_dmabuf dbuf;
uint16_t total_size;
uint16_t bytes_recv;
- void *context;
- struct lpfc_iocbq *iocbq;
- struct lpfc_sglq *sglq;
+ uint16_t idx;
struct lpfc_queue *hrq; /* ptr to associated Header RQ */
struct lpfc_queue *drq; /* ptr to associated Data RQ */
};
/* INIT_LINK mailbox command */
#define LS_NPIV_FAB_SUPPORTED 0x2 /* Fabric supports NPIV */
#define LS_IGNORE_ERATT 0x4 /* intr handler should ignore ERATT */
+#define LS_MDS_LINK_DOWN 0x8 /* MDS Diagnostics Link Down */
+#define LS_MDS_LOOPBACK 0x16 /* MDS Diagnostics Link Up (Loopback) */
uint32_t hba_flag; /* hba generic flags */
#define HBA_ERATT_HANDLED 0x1 /* This flag is set when eratt handled */
uint32_t cfg_nvme_oas;
uint32_t cfg_nvme_io_channel;
uint32_t cfg_nvmet_mrq;
- uint32_t cfg_nvmet_mrq_post;
uint32_t cfg_enable_nvmet;
uint32_t cfg_nvme_enable_fb;
uint32_t cfg_nvmet_fb_size;
struct pci_pool *lpfc_mbuf_pool;
struct pci_pool *lpfc_hrb_pool; /* header receive buffer pool */
struct pci_pool *lpfc_drb_pool; /* data receive buffer pool */
+ struct pci_pool *lpfc_nvmet_drb_pool; /* data receive buffer pool */
struct pci_pool *lpfc_hbq_pool; /* SLI3 hbq buffer pool */
struct pci_pool *txrdy_payload_pool;
struct lpfc_dma_pool lpfc_mbuf_safety_pool;
static inline struct lpfc_sli_ring *
lpfc_phba_elsring(struct lpfc_hba *phba)
{
- if (phba->sli_rev == LPFC_SLI_REV4)
- return phba->sli4_hba.els_wq->pring;
+ if (phba->sli_rev == LPFC_SLI_REV4) {
+ if (phba->sli4_hba.els_wq)
+ return phba->sli4_hba.els_wq->pring;
+ else
+ return NULL;
+ }
return &phba->sli.sli3_ring[LPFC_ELS_RING];
}
#define LPFC_MIN_DEVLOSS_TMO 1
#define LPFC_MAX_DEVLOSS_TMO 255
-#define LPFC_DEF_MRQ_POST 256
-#define LPFC_MIN_MRQ_POST 32
-#define LPFC_MAX_MRQ_POST 512
+#define LPFC_DEF_MRQ_POST 512
+#define LPFC_MIN_MRQ_POST 512
+#define LPFC_MAX_MRQ_POST 2048
/*
* Write key size should be multiple of 4. If write key is changed
atomic_read(&tgtp->xmt_ls_rsp_error));
len += snprintf(buf+len, PAGE_SIZE-len,
- "FCP: Rcv %08x Drop %08x\n",
+ "FCP: Rcv %08x Release %08x Drop %08x\n",
atomic_read(&tgtp->rcv_fcp_cmd_in),
+ atomic_read(&tgtp->xmt_fcp_release),
atomic_read(&tgtp->rcv_fcp_cmd_drop));
if (atomic_read(&tgtp->rcv_fcp_cmd_in) !=
}
len += snprintf(buf+len, PAGE_SIZE-len,
- "FCP Rsp: RD %08x rsp %08x WR %08x rsp %08x\n",
+ "FCP Rsp: RD %08x rsp %08x WR %08x rsp %08x "
+ "drop %08x\n",
atomic_read(&tgtp->xmt_fcp_read),
atomic_read(&tgtp->xmt_fcp_read_rsp),
atomic_read(&tgtp->xmt_fcp_write),
- atomic_read(&tgtp->xmt_fcp_rsp));
-
- len += snprintf(buf+len, PAGE_SIZE-len,
- "FCP Rsp: abort %08x drop %08x\n",
- atomic_read(&tgtp->xmt_fcp_abort),
+ atomic_read(&tgtp->xmt_fcp_rsp),
atomic_read(&tgtp->xmt_fcp_drop));
len += snprintf(buf+len, PAGE_SIZE-len,
atomic_read(&tgtp->xmt_fcp_rsp_drop));
len += snprintf(buf+len, PAGE_SIZE-len,
- "ABORT: Xmt %08x Err %08x Cmpl %08x",
+ "ABORT: Xmt %08x Cmpl %08x\n",
+ atomic_read(&tgtp->xmt_fcp_abort),
+ atomic_read(&tgtp->xmt_fcp_abort_cmpl));
+
+ len += snprintf(buf + len, PAGE_SIZE - len,
+ "ABORT: Sol %08x Usol %08x Err %08x Cmpl %08x",
+ atomic_read(&tgtp->xmt_abort_sol),
+ atomic_read(&tgtp->xmt_abort_unsol),
atomic_read(&tgtp->xmt_abort_rsp),
- atomic_read(&tgtp->xmt_abort_rsp_error),
- atomic_read(&tgtp->xmt_abort_cmpl));
+ atomic_read(&tgtp->xmt_abort_rsp_error));
+
+ len += snprintf(buf + len, PAGE_SIZE - len,
+ "IO_CTX: %08x outstanding %08x total %x",
+ phba->sli4_hba.nvmet_ctx_cnt,
+ phba->sli4_hba.nvmet_io_wait_cnt,
+ phba->sli4_hba.nvmet_io_wait_total);
len += snprintf(buf+len, PAGE_SIZE-len, "\n");
return len;
1, 1, 16,
"Specify number of RQ pairs for processing NVMET cmds");
-/*
- * lpfc_nvmet_mrq_post: Specify number buffers to post on every MRQ
- *
- */
-LPFC_ATTR_R(nvmet_mrq_post, LPFC_DEF_MRQ_POST,
- LPFC_MIN_MRQ_POST, LPFC_MAX_MRQ_POST,
- "Specify number of buffers to post on every MRQ");
-
/*
* lpfc_enable_fc4_type: Defines what FC4 types are supported.
* Supported Values: 1 - register just FCP
&dev_attr_lpfc_suppress_rsp,
&dev_attr_lpfc_nvme_io_channel,
&dev_attr_lpfc_nvmet_mrq,
- &dev_attr_lpfc_nvmet_mrq_post,
&dev_attr_lpfc_nvme_enable_fb,
&dev_attr_lpfc_nvmet_fb_size,
&dev_attr_lpfc_enable_bg,
lpfc_enable_fc4_type_init(phba, lpfc_enable_fc4_type);
lpfc_nvmet_mrq_init(phba, lpfc_nvmet_mrq);
- lpfc_nvmet_mrq_post_init(phba, lpfc_nvmet_mrq_post);
/* Initialize first burst. Target vs Initiator are different. */
lpfc_nvme_enable_fb_init(phba, lpfc_nvme_enable_fb);
/* Not NVME Target mode. Turn off Target parameters. */
phba->nvmet_support = 0;
phba->cfg_nvmet_mrq = 0;
- phba->cfg_nvmet_mrq_post = 0;
phba->cfg_nvmet_fb_size = 0;
}
void lpfc_cancel_all_vport_retry_delay_timer(struct lpfc_hba *);
void lpfc_retry_pport_discovery(struct lpfc_hba *);
void lpfc_release_rpi(struct lpfc_hba *, struct lpfc_vport *, uint16_t);
+int lpfc_init_iocb_list(struct lpfc_hba *phba, int cnt);
+void lpfc_free_iocb_list(struct lpfc_hba *phba);
+int lpfc_post_rq_buffer(struct lpfc_hba *phba, struct lpfc_queue *hrq,
+ struct lpfc_queue *drq, int count, int idx);
void lpfc_mbx_cmpl_local_config_link(struct lpfc_hba *, LPFC_MBOXQ_t *);
void lpfc_mbx_cmpl_reg_login(struct lpfc_hba *, LPFC_MBOXQ_t *);
void lpfc_do_scr_ns_plogi(struct lpfc_hba *, struct lpfc_vport *);
int lpfc_check_sparm(struct lpfc_vport *, struct lpfc_nodelist *,
struct serv_parm *, uint32_t, int);
-int lpfc_els_abort(struct lpfc_hba *, struct lpfc_nodelist *);
+void lpfc_els_abort(struct lpfc_hba *, struct lpfc_nodelist *);
void lpfc_more_plogi(struct lpfc_vport *);
void lpfc_more_adisc(struct lpfc_vport *);
void lpfc_end_rscn(struct lpfc_vport *);
void lpfc_sli4_rb_free(struct lpfc_hba *, struct hbq_dmabuf *);
struct rqb_dmabuf *lpfc_sli4_nvmet_alloc(struct lpfc_hba *phba);
void lpfc_sli4_nvmet_free(struct lpfc_hba *phba, struct rqb_dmabuf *dmab);
-void lpfc_nvmet_rq_post(struct lpfc_hba *phba, struct lpfc_nvmet_rcv_ctx *ctxp,
- struct lpfc_dmabuf *mp);
+void lpfc_nvmet_ctxbuf_post(struct lpfc_hba *phba,
+ struct lpfc_nvmet_ctxbuf *ctxp);
int lpfc_nvmet_rcv_unsol_abort(struct lpfc_vport *vport,
struct fc_frame_header *fc_hdr);
void lpfc_sli4_build_dflt_fcf_record(struct lpfc_hba *, struct fcf_record *,
uint16_t);
int lpfc_sli4_rq_put(struct lpfc_queue *hq, struct lpfc_queue *dq,
struct lpfc_rqe *hrqe, struct lpfc_rqe *drqe);
-int lpfc_post_rq_buffer(struct lpfc_hba *phba, struct lpfc_queue *hq,
- struct lpfc_queue *dq, int count);
int lpfc_free_rq_buffer(struct lpfc_hba *phba, struct lpfc_queue *hq);
void lpfc_unregister_fcf(struct lpfc_hba *);
void lpfc_unregister_fcf_rescan(struct lpfc_hba *);
void lpfc_sli4_clear_fcf_rr_bmask(struct lpfc_hba *);
int lpfc_mem_alloc(struct lpfc_hba *, int align);
+int lpfc_nvmet_mem_alloc(struct lpfc_hba *phba);
int lpfc_mem_alloc_active_rrq_pool_s4(struct lpfc_hba *);
void lpfc_mem_free(struct lpfc_hba *);
void lpfc_mem_free_all(struct lpfc_hba *);
void lpfc_reset_barrier(struct lpfc_hba *);
int lpfc_sli_brdready(struct lpfc_hba *, uint32_t);
int lpfc_sli_brdkill(struct lpfc_hba *);
+int lpfc_sli_chipset_init(struct lpfc_hba *phba);
int lpfc_sli_brdreset(struct lpfc_hba *);
int lpfc_sli_brdrestart(struct lpfc_hba *);
int lpfc_sli_hba_setup(struct lpfc_hba *);
NLP_EVT_DEVICE_RECOVERY);
spin_lock_irq(shost->host_lock);
ndlp->nlp_flag &= ~NLP_NVMET_RECOV;
- spin_lock_irq(shost->host_lock);
+ spin_unlock_irq(shost->host_lock);
}
}
ndlp, did, ndlp->nlp_fc4_type,
FC_TYPE_FCP, FC_TYPE_NVME);
ndlp->nlp_prev_state = NLP_STE_REG_LOGIN_ISSUE;
+
+ lpfc_nlp_set_state(vport, ndlp, NLP_STE_PRLI_ISSUE);
+ lpfc_issue_els_prli(vport, ndlp, 0);
}
- lpfc_nlp_set_state(vport, ndlp, NLP_STE_PRLI_ISSUE);
- lpfc_issue_els_prli(vport, ndlp, 0);
} else
lpfc_printf_vlog(vport, KERN_ERR, LOG_DISCOVERY,
"3065 GFT_ID failed x%08x\n", irsp->ulpStatus);
ae->un.AttrTypes[3] = 0x02; /* Type 1 - ELS */
ae->un.AttrTypes[2] = 0x01; /* Type 8 - FCP */
+ ae->un.AttrTypes[6] = 0x01; /* Type 40 - NVME */
ae->un.AttrTypes[7] = 0x01; /* Type 32 - CT */
size = FOURBYTES + 32;
ad->AttrLen = cpu_to_be16(size);
atomic_read(&tgtp->xmt_fcp_write),
atomic_read(&tgtp->xmt_fcp_rsp));
- len += snprintf(buf + len, size - len,
- "FCP Rsp: abort %08x drop %08x\n",
- atomic_read(&tgtp->xmt_fcp_abort),
- atomic_read(&tgtp->xmt_fcp_drop));
-
len += snprintf(buf + len, size - len,
"FCP Rsp Cmpl: %08x err %08x drop %08x\n",
atomic_read(&tgtp->xmt_fcp_rsp_cmpl),
atomic_read(&tgtp->xmt_fcp_rsp_drop));
len += snprintf(buf + len, size - len,
- "ABORT: Xmt %08x Err %08x Cmpl %08x",
+ "ABORT: Xmt %08x Cmpl %08x\n",
+ atomic_read(&tgtp->xmt_fcp_abort),
+ atomic_read(&tgtp->xmt_fcp_abort_cmpl));
+
+ len += snprintf(buf + len, size - len,
+ "ABORT: Sol %08x Usol %08x Err %08x Cmpl %08x",
+ atomic_read(&tgtp->xmt_abort_sol),
+ atomic_read(&tgtp->xmt_abort_unsol),
atomic_read(&tgtp->xmt_abort_rsp),
- atomic_read(&tgtp->xmt_abort_rsp_error),
- atomic_read(&tgtp->xmt_abort_cmpl));
+ atomic_read(&tgtp->xmt_abort_rsp_error));
len += snprintf(buf + len, size - len, "\n");
}
spin_unlock(&phba->sli4_hba.abts_nvme_buf_list_lock);
}
+
+ len += snprintf(buf + len, size - len,
+ "IO_CTX: %08x outstanding %08x total %08x\n",
+ phba->sli4_hba.nvmet_ctx_cnt,
+ phba->sli4_hba.nvmet_io_wait_cnt,
+ phba->sli4_hba.nvmet_io_wait_total);
} else {
if (!(phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME))
return len;
atomic_set(&tgtp->rcv_ls_req_out, 0);
atomic_set(&tgtp->rcv_ls_req_drop, 0);
atomic_set(&tgtp->xmt_ls_abort, 0);
+ atomic_set(&tgtp->xmt_ls_abort_cmpl, 0);
atomic_set(&tgtp->xmt_ls_rsp, 0);
atomic_set(&tgtp->xmt_ls_drop, 0);
atomic_set(&tgtp->xmt_ls_rsp_error, 0);
atomic_set(&tgtp->rcv_fcp_cmd_in, 0);
atomic_set(&tgtp->rcv_fcp_cmd_out, 0);
atomic_set(&tgtp->rcv_fcp_cmd_drop, 0);
- atomic_set(&tgtp->xmt_fcp_abort, 0);
atomic_set(&tgtp->xmt_fcp_drop, 0);
atomic_set(&tgtp->xmt_fcp_read_rsp, 0);
atomic_set(&tgtp->xmt_fcp_read, 0);
atomic_set(&tgtp->xmt_fcp_write, 0);
atomic_set(&tgtp->xmt_fcp_rsp, 0);
+ atomic_set(&tgtp->xmt_fcp_release, 0);
atomic_set(&tgtp->xmt_fcp_rsp_cmpl, 0);
atomic_set(&tgtp->xmt_fcp_rsp_error, 0);
atomic_set(&tgtp->xmt_fcp_rsp_drop, 0);
+ atomic_set(&tgtp->xmt_fcp_abort, 0);
+ atomic_set(&tgtp->xmt_fcp_abort_cmpl, 0);
+ atomic_set(&tgtp->xmt_abort_sol, 0);
+ atomic_set(&tgtp->xmt_abort_unsol, 0);
atomic_set(&tgtp->xmt_abort_rsp, 0);
atomic_set(&tgtp->xmt_abort_rsp_error, 0);
- atomic_set(&tgtp->xmt_abort_cmpl, 0);
}
return nbytes;
}
qp->assoc_qid, qp->q_cnt_1,
(unsigned long long)qp->q_cnt_4);
len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
- "\t\tWQID[%02d], QE-CNT[%04d], QE-SIZE[%04d], "
- "HOST-IDX[%04d], PORT-IDX[%04d]",
+ "\t\tWQID[%02d], QE-CNT[%04d], QE-SZ[%04d], "
+ "HST-IDX[%04d], PRT-IDX[%04d], PST[%03d]",
qp->queue_id, qp->entry_count,
qp->entry_size, qp->host_index,
- qp->hba_index);
+ qp->hba_index, qp->entry_repost);
len += snprintf(pbuffer + len,
LPFC_QUE_INFO_GET_BUF_SIZE - len, "\n");
return len;
qp->assoc_qid, qp->q_cnt_1, qp->q_cnt_2,
qp->q_cnt_3, (unsigned long long)qp->q_cnt_4);
len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
- "\tCQID[%02d], QE-CNT[%04d], QE-SIZE[%04d], "
- "HOST-IDX[%04d], PORT-IDX[%04d]",
+ "\tCQID[%02d], QE-CNT[%04d], QE-SZ[%04d], "
+ "HST-IDX[%04d], PRT-IDX[%04d], PST[%03d]",
qp->queue_id, qp->entry_count,
qp->entry_size, qp->host_index,
- qp->hba_index);
+ qp->hba_index, qp->entry_repost);
len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len, "\n");
"\t\t%s RQ info: ", rqtype);
len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
"AssocCQID[%02d]: RQ-STAT[nopost:x%x nobuf:x%x "
- "trunc:x%x rcv:x%llx]\n",
+ "posted:x%x rcv:x%llx]\n",
qp->assoc_qid, qp->q_cnt_1, qp->q_cnt_2,
qp->q_cnt_3, (unsigned long long)qp->q_cnt_4);
len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
- "\t\tHQID[%02d], QE-CNT[%04d], QE-SIZE[%04d], "
- "HOST-IDX[%04d], PORT-IDX[%04d]\n",
+ "\t\tHQID[%02d], QE-CNT[%04d], QE-SZ[%04d], "
+ "HST-IDX[%04d], PRT-IDX[%04d], PST[%03d]\n",
qp->queue_id, qp->entry_count, qp->entry_size,
- qp->host_index, qp->hba_index);
+ qp->host_index, qp->hba_index, qp->entry_repost);
len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
- "\t\tDQID[%02d], QE-CNT[%04d], QE-SIZE[%04d], "
- "HOST-IDX[%04d], PORT-IDX[%04d]\n",
+ "\t\tDQID[%02d], QE-CNT[%04d], QE-SZ[%04d], "
+ "HST-IDX[%04d], PRT-IDX[%04d], PST[%03d]\n",
datqp->queue_id, datqp->entry_count,
datqp->entry_size, datqp->host_index,
- datqp->hba_index);
+ datqp->hba_index, datqp->entry_repost);
return len;
}
eqtype, qp->q_cnt_1, qp->q_cnt_2, qp->q_cnt_3,
(unsigned long long)qp->q_cnt_4);
len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
- "EQID[%02d], QE-CNT[%04d], QE-SIZE[%04d], "
- "HOST-IDX[%04d], PORT-IDX[%04d]",
+ "EQID[%02d], QE-CNT[%04d], QE-SZ[%04d], "
+ "HST-IDX[%04d], PRT-IDX[%04d], PST[%03d]",
qp->queue_id, qp->entry_count, qp->entry_size,
- qp->host_index, qp->hba_index);
+ qp->host_index, qp->hba_index, qp->entry_repost);
len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len, "\n");
return len;
atomic_dec(&lpfc_debugfs_hba_count);
}
- debugfs_remove(lpfc_debugfs_root); /* lpfc */
- lpfc_debugfs_root = NULL;
+ if (atomic_read(&lpfc_debugfs_hba_count) == 0) {
+ debugfs_remove(lpfc_debugfs_root); /* lpfc */
+ lpfc_debugfs_root = NULL;
+ }
}
#endif
return;
#define NLP_FCP_INITIATOR 0x10 /* entry is an FCP Initiator */
#define NLP_NVME_TARGET 0x20 /* entry is a NVME Target */
#define NLP_NVME_INITIATOR 0x40 /* entry is a NVME Initiator */
+#define NLP_NVME_DISCOVERY 0x80 /* entry has NVME disc srvc */
uint16_t nlp_fc4_type; /* FC types node supports. */
/* Assigned from GID_FF, only
irsp->ulpStatus, irsp->un.ulpWord[4],
irsp->ulpTimeout);
+
+ /* If this is not a loop open failure, bail out */
+ if (!(irsp->ulpStatus == IOSTAT_LOCAL_REJECT &&
+ ((irsp->un.ulpWord[4] & IOERR_PARAM_MASK) ==
+ IOERR_LOOP_OPEN_FAILURE)))
+ goto flogifail;
+
/* FLOGI failed, so there is no fabric */
spin_lock_irq(shost->host_lock);
vport->fc_flag &= ~(FC_FABRIC | FC_PUBLIC_LOOP);
if (irsp->ulpStatus) {
/* Check for retry */
+ ndlp->fc4_prli_sent--;
if (lpfc_els_retry(phba, cmdiocb, rspiocb)) {
/* ELS command is being retried */
- ndlp->fc4_prli_sent--;
goto out;
}
+
/* PRLI failed */
lpfc_printf_vlog(vport, KERN_ERR, LOG_ELS,
- "2754 PRLI failure DID:%06X Status:x%x/x%x\n",
+ "2754 PRLI failure DID:%06X Status:x%x/x%x, "
+ "data: x%x\n",
ndlp->nlp_DID, irsp->ulpStatus,
- irsp->un.ulpWord[4]);
+ irsp->un.ulpWord[4], ndlp->fc4_prli_sent);
+
/* Do not call DSM for lpfc_els_abort'ed ELS cmds */
if (lpfc_error_lost_link(irsp))
goto out;
*/
spin_lock_irq(&phba->hbalock);
pring = lpfc_phba_elsring(phba);
+
+ /* Bail out if we've no ELS wq, like in PCI error recovery case. */
+ if (unlikely(!pring)) {
+ spin_unlock_irq(&phba->hbalock);
+ return;
+ }
+
if (phba->sli_rev == LPFC_SLI_REV4)
spin_lock(&pring->ring_lock);
lpfc_do_scr_ns_plogi(phba, vport);
goto out;
fdisc_failed:
- if (vport->fc_vport->vport_state != FC_VPORT_NO_FABRIC_RSCS)
+ if (vport->fc_vport &&
+ (vport->fc_vport->vport_state != FC_VPORT_NO_FABRIC_RSCS))
lpfc_vport_set_state(vport, FC_VPORT_FAILED);
/* Cancel discovery timer */
lpfc_can_disctmo(vport);
pring = lpfc_phba_elsring(phba);
status = (ha_copy & (HA_RXMASK << (4*LPFC_ELS_RING)));
status >>= (4*LPFC_ELS_RING);
- if ((status & HA_RXMASK) ||
- (pring->flag & LPFC_DEFERRED_RING_EVENT) ||
- (phba->hba_flag & HBA_SP_QUEUE_EVT)) {
+ if (pring && (status & HA_RXMASK ||
+ pring->flag & LPFC_DEFERRED_RING_EVENT ||
+ phba->hba_flag & HBA_SP_QUEUE_EVT)) {
if (pring->flag & LPFC_STOP_IOCB_EVENT) {
pring->flag |= LPFC_DEFERRED_RING_EVENT;
/* Set the lpfc data pending flag */
set_bit(LPFC_DATA_READY, &phba->data_flags);
} else {
- if (phba->link_state >= LPFC_LINK_UP) {
+ if (phba->link_state >= LPFC_LINK_UP ||
+ phba->link_flag & LS_MDS_LOOPBACK) {
pring->flag &= ~LPFC_DEFERRED_RING_EVENT;
lpfc_sli_handle_slow_ring_event(phba, pring,
(status &
#define LPFC_HDR_BUF_SIZE 128
#define LPFC_DATA_BUF_SIZE 2048
+#define LPFC_NVMET_DATA_BUF_SIZE 128
struct rq_context {
uint32_t word0;
#define lpfc_rq_context_rqe_count_SHIFT 16 /* Version 0 Only */
};
#define TXRDY_PAYLOAD_LEN 12
+#define CMD_SEND_FRAME 0xE1
+
+struct send_frame_wqe {
+ struct ulp_bde64 bde; /* words 0-2 */
+ uint32_t frame_len; /* word 3 */
+ uint32_t fc_hdr_wd0; /* word 4 */
+ uint32_t fc_hdr_wd1; /* word 5 */
+ struct wqe_common wqe_com; /* words 6-11 */
+ uint32_t fc_hdr_wd2; /* word 12 */
+ uint32_t fc_hdr_wd3; /* word 13 */
+ uint32_t fc_hdr_wd4; /* word 14 */
+ uint32_t fc_hdr_wd5; /* word 15 */
+};
union lpfc_wqe {
uint32_t words[16];
struct fcp_trsp64_wqe fcp_trsp;
struct fcp_tsend64_wqe fcp_tsend;
struct fcp_treceive64_wqe fcp_treceive;
-
+ struct send_frame_wqe send_frame;
};
union lpfc_wqe128 {
list_for_each_entry_safe(ctxp, ctxp_next, &nvmet_aborts, list) {
ctxp->flag &= ~(LPFC_NVMET_XBUSY | LPFC_NVMET_ABORT_OP);
- lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
+ lpfc_nvmet_ctxbuf_post(phba, ctxp->ctxbuf);
}
}
{
struct lpfc_sglq *sglq_entry = NULL, *sglq_entry_next = NULL;
uint16_t i, lxri, xri_cnt, els_xri_cnt;
- uint16_t nvmet_xri_cnt, tot_cnt;
+ uint16_t nvmet_xri_cnt;
LIST_HEAD(nvmet_sgl_list);
int rc;
* update on pci function's nvmet xri-sgl list
*/
els_xri_cnt = lpfc_sli4_get_els_iocb_cnt(phba);
- nvmet_xri_cnt = phba->cfg_nvmet_mrq * phba->cfg_nvmet_mrq_post;
- tot_cnt = phba->sli4_hba.max_cfg_param.max_xri - els_xri_cnt;
- if (nvmet_xri_cnt > tot_cnt) {
- phba->cfg_nvmet_mrq_post = tot_cnt / phba->cfg_nvmet_mrq;
- nvmet_xri_cnt = phba->cfg_nvmet_mrq * phba->cfg_nvmet_mrq_post;
- lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
- "6301 NVMET post-sgl count changed to %d\n",
- phba->cfg_nvmet_mrq_post);
- }
+
+ /* For NVMET, ALL remaining XRIs are dedicated for IO processing */
+ nvmet_xri_cnt = phba->sli4_hba.max_cfg_param.max_xri - els_xri_cnt;
if (nvmet_xri_cnt > phba->sli4_hba.nvmet_xri_cnt) {
/* els xri-sgl expanded */
LPFC_MBOXQ_t *mboxq;
MAILBOX_t *mb;
+ if (phba->sli_rev < LPFC_SLI_REV4) {
+ /* Reset the port first */
+ lpfc_sli_brdrestart(phba);
+ rc = lpfc_sli_chipset_init(phba);
+ if (rc)
+ return (uint64_t)-1;
+ }
mboxq = (LPFC_MBOXQ_t *) mempool_alloc(phba->mbox_mem_pool,
GFP_KERNEL);
pmb->vport = phba->pport;
if (phba->sli4_hba.link_state.status != LPFC_FC_LA_TYPE_LINK_UP) {
+ phba->link_flag &= ~(LS_MDS_LINK_DOWN | LS_MDS_LOOPBACK);
+
+ switch (phba->sli4_hba.link_state.status) {
+ case LPFC_FC_LA_TYPE_MDS_LINK_DOWN:
+ phba->link_flag |= LS_MDS_LINK_DOWN;
+ break;
+ case LPFC_FC_LA_TYPE_MDS_LOOPBACK:
+ phba->link_flag |= LS_MDS_LOOPBACK;
+ break;
+ default:
+ break;
+ }
+
/* Parse and translate status field */
mb = &pmb->u.mb;
mb->mbxStatus = lpfc_sli4_parse_latt_fault(phba,
spin_lock_init(&phba->sli4_hba.abts_nvme_buf_list_lock);
INIT_LIST_HEAD(&phba->sli4_hba.lpfc_abts_nvme_buf_list);
INIT_LIST_HEAD(&phba->sli4_hba.lpfc_abts_nvmet_ctx_list);
+ INIT_LIST_HEAD(&phba->sli4_hba.lpfc_nvmet_ctx_list);
+ INIT_LIST_HEAD(&phba->sli4_hba.lpfc_nvmet_io_wait_list);
+
/* Fast-path XRI aborted CQ Event work queue list */
INIT_LIST_HEAD(&phba->sli4_hba.sp_nvme_xri_aborted_work_queue);
}
/* This abort list used by worker thread */
spin_lock_init(&phba->sli4_hba.sgl_list_lock);
spin_lock_init(&phba->sli4_hba.nvmet_io_lock);
+ spin_lock_init(&phba->sli4_hba.nvmet_io_wait_lock);
/*
* Initialize driver internal slow-path work queues
for (i = 0; i < lpfc_enable_nvmet_cnt; i++) {
if (wwn == lpfc_enable_nvmet[i]) {
#if (IS_ENABLED(CONFIG_NVME_TARGET_FC))
+ if (lpfc_nvmet_mem_alloc(phba))
+ break;
+
+ phba->nvmet_support = 1; /* a match */
+
lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
"6017 NVME Target %016llx\n",
wwn);
- phba->nvmet_support = 1; /* a match */
#else
lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
"6021 Can't enable NVME Target."
" NVME_TARGET_FC infrastructure"
" is not in kernel\n");
#endif
+ break;
}
}
}
*
* This routine is invoked to free the driver's IOCB list and memory.
**/
-static void
+void
lpfc_free_iocb_list(struct lpfc_hba *phba)
{
struct lpfc_iocbq *iocbq_entry = NULL, *iocbq_next = NULL;
* 0 - successful
* other values - error
**/
-static int
+int
lpfc_init_iocb_list(struct lpfc_hba *phba, int iocb_count)
{
struct lpfc_iocbq *iocbq_entry = NULL;
uint16_t rpi_limit, curr_rpi_range;
struct lpfc_dmabuf *dmabuf;
struct lpfc_rpi_hdr *rpi_hdr;
- uint32_t rpi_count;
/*
* If the SLI4 port supports extents, posting the rpi header isn't
return NULL;
/* The limit on the logical index is just the max_rpi count. */
- rpi_limit = phba->sli4_hba.max_cfg_param.rpi_base +
- phba->sli4_hba.max_cfg_param.max_rpi - 1;
+ rpi_limit = phba->sli4_hba.max_cfg_param.max_rpi;
spin_lock_irq(&phba->hbalock);
/*
curr_rpi_range = phba->sli4_hba.next_rpi;
spin_unlock_irq(&phba->hbalock);
- /*
- * The port has a limited number of rpis. The increment here
- * is LPFC_RPI_HDR_COUNT - 1 to account for the starting value
- * and to allow the full max_rpi range per port.
- */
- if ((curr_rpi_range + (LPFC_RPI_HDR_COUNT - 1)) > rpi_limit)
- rpi_count = rpi_limit - curr_rpi_range;
- else
- rpi_count = LPFC_RPI_HDR_COUNT;
-
- if (!rpi_count)
+ /* Reached full RPI range */
+ if (curr_rpi_range == rpi_limit)
return NULL;
+
/*
* First allocate the protocol header region for the port. The
* port expects a 4KB DMA-mapped memory region that is 4K aligned.
/* The rpi_hdr stores the logical index only. */
rpi_hdr->start_rpi = curr_rpi_range;
+ rpi_hdr->next_rpi = phba->sli4_hba.next_rpi + LPFC_RPI_HDR_COUNT;
list_add_tail(&rpi_hdr->list, &phba->sli4_hba.lpfc_rpi_hdr_list);
- /*
- * The next_rpi stores the next logical module-64 rpi value used
- * to post physical rpis in subsequent rpi postings.
- */
- phba->sli4_hba.next_rpi += rpi_count;
spin_unlock_irq(&phba->hbalock);
return rpi_hdr;
/* Create NVMET Receive Queue for header */
qdesc = lpfc_sli4_queue_alloc(phba,
phba->sli4_hba.rq_esize,
- phba->sli4_hba.rq_ecount);
+ LPFC_NVMET_RQE_DEF_COUNT);
if (!qdesc) {
lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
"3146 Failed allocate "
/* Create NVMET Receive Queue for data */
qdesc = lpfc_sli4_queue_alloc(phba,
phba->sli4_hba.rq_esize,
- phba->sli4_hba.rq_ecount);
+ LPFC_NVMET_RQE_DEF_COUNT);
if (!qdesc) {
lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
"3156 Failed allocate "
INIT_LIST_HEAD(&phba->sli4_hba.lpfc_wq_list);
}
-int
-lpfc_post_rq_buffer(struct lpfc_hba *phba, struct lpfc_queue *hrq,
- struct lpfc_queue *drq, int count)
-{
- int rc, i;
- struct lpfc_rqe hrqe;
- struct lpfc_rqe drqe;
- struct lpfc_rqb *rqbp;
- struct rqb_dmabuf *rqb_buffer;
- LIST_HEAD(rqb_buf_list);
-
- rqbp = hrq->rqbp;
- for (i = 0; i < count; i++) {
- rqb_buffer = (rqbp->rqb_alloc_buffer)(phba);
- if (!rqb_buffer)
- break;
- rqb_buffer->hrq = hrq;
- rqb_buffer->drq = drq;
- list_add_tail(&rqb_buffer->hbuf.list, &rqb_buf_list);
- }
- while (!list_empty(&rqb_buf_list)) {
- list_remove_head(&rqb_buf_list, rqb_buffer, struct rqb_dmabuf,
- hbuf.list);
-
- hrqe.address_lo = putPaddrLow(rqb_buffer->hbuf.phys);
- hrqe.address_hi = putPaddrHigh(rqb_buffer->hbuf.phys);
- drqe.address_lo = putPaddrLow(rqb_buffer->dbuf.phys);
- drqe.address_hi = putPaddrHigh(rqb_buffer->dbuf.phys);
- rc = lpfc_sli4_rq_put(hrq, drq, &hrqe, &drqe);
- if (rc < 0) {
- (rqbp->rqb_free_buffer)(phba, rqb_buffer);
- } else {
- list_add_tail(&rqb_buffer->hbuf.list,
- &rqbp->rqb_buffer_list);
- rqbp->buffer_count++;
- }
- }
- return 1;
-}
-
int
lpfc_free_rq_buffer(struct lpfc_hba *phba, struct lpfc_queue *rq)
{
goto out_destroy;
}
- lpfc_rq_adjust_repost(phba, phba->sli4_hba.hdr_rq, LPFC_ELS_HBQ);
- lpfc_rq_adjust_repost(phba, phba->sli4_hba.dat_rq, LPFC_ELS_HBQ);
-
rc = lpfc_rq_create(phba, phba->sli4_hba.hdr_rq, phba->sli4_hba.dat_rq,
phba->sli4_hba.els_cq, LPFC_USOL);
if (rc) {
lpfc_wq_destroy(phba, phba->sli4_hba.nvmels_wq);
/* Unset ELS work queue */
- if (phba->sli4_hba.els_cq)
+ if (phba->sli4_hba.els_wq)
lpfc_wq_destroy(phba, phba->sli4_hba.els_wq);
/* Unset unsolicited receive queue */
struct lpfc_hba *phba;
struct lpfc_vport *vport = NULL;
struct Scsi_Host *shost = NULL;
- int error, cnt;
+ int error;
uint32_t cfg_mode, intr_mode;
/* Allocate memory for HBA structure */
goto out_unset_pci_mem_s4;
}
- cnt = phba->cfg_iocb_cnt * 1024;
- if (phba->nvmet_support)
- cnt += phba->cfg_nvmet_mrq_post * phba->cfg_nvmet_mrq;
-
- /* Initialize and populate the iocb list per host */
- lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
- "2821 initialize iocb list %d total %d\n",
- phba->cfg_iocb_cnt, cnt);
- error = lpfc_init_iocb_list(phba, cnt);
-
- if (error) {
- lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
- "1413 Failed to initialize iocb list.\n");
- goto out_unset_driver_resource_s4;
- }
-
INIT_LIST_HEAD(&phba->active_rrq_list);
INIT_LIST_HEAD(&phba->fcf.fcf_pri_list);
if (error) {
lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
"1414 Failed to set up driver resource.\n");
- goto out_free_iocb_list;
+ goto out_unset_driver_resource_s4;
}
/* Get the default values for Model Name and Description */
lpfc_destroy_shost(phba);
out_unset_driver_resource:
lpfc_unset_driver_resource_phase2(phba);
-out_free_iocb_list:
- lpfc_free_iocb_list(phba);
out_unset_driver_resource_s4:
lpfc_sli4_driver_resource_unset(phba);
out_unset_pci_mem_s4:
return -ENOMEM;
}
+int
+lpfc_nvmet_mem_alloc(struct lpfc_hba *phba)
+{
+ phba->lpfc_nvmet_drb_pool =
+ pci_pool_create("lpfc_nvmet_drb_pool",
+ phba->pcidev, LPFC_NVMET_DATA_BUF_SIZE,
+ SGL_ALIGN_SZ, 0);
+ if (!phba->lpfc_nvmet_drb_pool) {
+ lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+ "6024 Can't enable NVME Target - no memory\n");
+ return -ENOMEM;
+ }
+ return 0;
+}
+
/**
* lpfc_mem_free - Frees memory allocated by lpfc_mem_alloc
* @phba: HBA to free memory for
/* Free HBQ pools */
lpfc_sli_hbqbuf_free_all(phba);
+ if (phba->lpfc_nvmet_drb_pool)
+ pci_pool_destroy(phba->lpfc_nvmet_drb_pool);
+ phba->lpfc_nvmet_drb_pool = NULL;
if (phba->lpfc_drb_pool)
pci_pool_destroy(phba->lpfc_drb_pool);
phba->lpfc_drb_pool = NULL;
lpfc_sli4_nvmet_alloc(struct lpfc_hba *phba)
{
struct rqb_dmabuf *dma_buf;
- struct lpfc_iocbq *nvmewqe;
- union lpfc_wqe128 *wqe;
dma_buf = kzalloc(sizeof(struct rqb_dmabuf), GFP_KERNEL);
if (!dma_buf)
kfree(dma_buf);
return NULL;
}
- dma_buf->dbuf.virt = pci_pool_alloc(phba->lpfc_drb_pool, GFP_KERNEL,
- &dma_buf->dbuf.phys);
+ dma_buf->dbuf.virt = pci_pool_alloc(phba->lpfc_nvmet_drb_pool,
+ GFP_KERNEL, &dma_buf->dbuf.phys);
if (!dma_buf->dbuf.virt) {
pci_pool_free(phba->lpfc_hrb_pool, dma_buf->hbuf.virt,
dma_buf->hbuf.phys);
kfree(dma_buf);
return NULL;
}
- dma_buf->total_size = LPFC_DATA_BUF_SIZE;
-
- dma_buf->context = kzalloc(sizeof(struct lpfc_nvmet_rcv_ctx),
- GFP_KERNEL);
- if (!dma_buf->context) {
- pci_pool_free(phba->lpfc_drb_pool, dma_buf->dbuf.virt,
- dma_buf->dbuf.phys);
- pci_pool_free(phba->lpfc_hrb_pool, dma_buf->hbuf.virt,
- dma_buf->hbuf.phys);
- kfree(dma_buf);
- return NULL;
- }
-
- dma_buf->iocbq = lpfc_sli_get_iocbq(phba);
- if (!dma_buf->iocbq) {
- kfree(dma_buf->context);
- pci_pool_free(phba->lpfc_drb_pool, dma_buf->dbuf.virt,
- dma_buf->dbuf.phys);
- pci_pool_free(phba->lpfc_hrb_pool, dma_buf->hbuf.virt,
- dma_buf->hbuf.phys);
- kfree(dma_buf);
- lpfc_printf_log(phba, KERN_ERR, LOG_NVME,
- "2621 Ran out of nvmet iocb/WQEs\n");
- return NULL;
- }
- dma_buf->iocbq->iocb_flag = LPFC_IO_NVMET;
- nvmewqe = dma_buf->iocbq;
- wqe = (union lpfc_wqe128 *)&nvmewqe->wqe;
- /* Initialize WQE */
- memset(wqe, 0, sizeof(union lpfc_wqe));
- /* Word 7 */
- bf_set(wqe_ct, &wqe->generic.wqe_com, SLI4_CT_RPI);
- bf_set(wqe_class, &wqe->generic.wqe_com, CLASS3);
- bf_set(wqe_pu, &wqe->generic.wqe_com, 1);
- /* Word 10 */
- bf_set(wqe_nvme, &wqe->fcp_tsend.wqe_com, 1);
- bf_set(wqe_ebde_cnt, &wqe->generic.wqe_com, 0);
- bf_set(wqe_qosd, &wqe->generic.wqe_com, 0);
-
- dma_buf->iocbq->context1 = NULL;
- spin_lock(&phba->sli4_hba.sgl_list_lock);
- dma_buf->sglq = __lpfc_sli_get_nvmet_sglq(phba, dma_buf->iocbq);
- spin_unlock(&phba->sli4_hba.sgl_list_lock);
- if (!dma_buf->sglq) {
- lpfc_sli_release_iocbq(phba, dma_buf->iocbq);
- kfree(dma_buf->context);
- pci_pool_free(phba->lpfc_drb_pool, dma_buf->dbuf.virt,
- dma_buf->dbuf.phys);
- pci_pool_free(phba->lpfc_hrb_pool, dma_buf->hbuf.virt,
- dma_buf->hbuf.phys);
- kfree(dma_buf);
- lpfc_printf_log(phba, KERN_ERR, LOG_NVME,
- "6132 Ran out of nvmet XRIs\n");
- return NULL;
- }
+ dma_buf->total_size = LPFC_NVMET_DATA_BUF_SIZE;
return dma_buf;
}
void
lpfc_sli4_nvmet_free(struct lpfc_hba *phba, struct rqb_dmabuf *dmab)
{
- unsigned long flags;
-
- __lpfc_clear_active_sglq(phba, dmab->sglq->sli4_lxritag);
- dmab->sglq->state = SGL_FREED;
- dmab->sglq->ndlp = NULL;
-
- spin_lock_irqsave(&phba->sli4_hba.sgl_list_lock, flags);
- list_add_tail(&dmab->sglq->list, &phba->sli4_hba.lpfc_nvmet_sgl_list);
- spin_unlock_irqrestore(&phba->sli4_hba.sgl_list_lock, flags);
-
- lpfc_sli_release_iocbq(phba, dmab->iocbq);
- kfree(dmab->context);
pci_pool_free(phba->lpfc_hrb_pool, dmab->hbuf.virt, dmab->hbuf.phys);
- pci_pool_free(phba->lpfc_drb_pool, dmab->dbuf.virt, dmab->dbuf.phys);
+ pci_pool_free(phba->lpfc_nvmet_drb_pool,
+ dmab->dbuf.virt, dmab->dbuf.phys);
kfree(dmab);
}
rc = lpfc_sli4_rq_put(rqb_entry->hrq, rqb_entry->drq, &hrqe, &drqe);
if (rc < 0) {
(rqbp->rqb_free_buffer)(phba, rqb_entry);
+ lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+ "6409 Cannot post to RQ %d: %x %x\n",
+ rqb_entry->hrq->queue_id,
+ rqb_entry->hrq->host_index,
+ rqb_entry->hrq->hba_index);
} else {
list_add_tail(&rqb_entry->hbuf.list, &rqbp->rqb_buffer_list);
rqbp->buffer_count++;
* associated with a LPFC_NODELIST entry. This
* routine effectively results in a "software abort".
*/
-int
+void
lpfc_els_abort(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp)
{
LIST_HEAD(abort_list);
pring = lpfc_phba_elsring(phba);
+ /* In case of error recovery path, we might have a NULL pring here */
+ if (!pring)
+ return;
+
/* Abort outstanding I/O on NPort <nlp_DID> */
lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_DISCOVERY,
"2819 Abort outstanding I/O on NPort x%x "
IOSTAT_LOCAL_REJECT, IOERR_SLI_ABORTED);
lpfc_cancel_retry_delay_tmo(phba->pport, ndlp);
- return 0;
}
static int
/* Target driver cannot solicit NVME FB. */
if (bf_get_be32(prli_tgt, nvpr)) {
+ /* Complete the nvme target roles. The transport
+ * needs to know if the rport is capable of
+ * discovery in addition to its role.
+ */
ndlp->nlp_type |= NLP_NVME_TARGET;
+ if (bf_get_be32(prli_disc, nvpr))
+ ndlp->nlp_type |= NLP_NVME_DISCOVERY;
if ((bf_get_be32(prli_fba, nvpr) == 1) &&
(bf_get_be32(prli_fb_sz, nvpr) > 0) &&
(phba->cfg_nvme_enable_fb) &&
}
/**
- * lpfc_nvmet_rq_post - Repost a NVMET RQ DMA buffer and clean up context
+ * lpfc_nvmet_ctxbuf_post - Repost a NVMET RQ DMA buffer and clean up context
* @phba: HBA buffer is associated with
* @ctxp: context to clean up
* @mp: Buffer to free
* Returns: None
**/
void
-lpfc_nvmet_rq_post(struct lpfc_hba *phba, struct lpfc_nvmet_rcv_ctx *ctxp,
- struct lpfc_dmabuf *mp)
+lpfc_nvmet_ctxbuf_post(struct lpfc_hba *phba, struct lpfc_nvmet_ctxbuf *ctx_buf)
{
- if (ctxp) {
- if (ctxp->flag)
- lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
- "6314 rq_post ctx xri x%x flag x%x\n",
- ctxp->oxid, ctxp->flag);
-
- if (ctxp->txrdy) {
- pci_pool_free(phba->txrdy_payload_pool, ctxp->txrdy,
- ctxp->txrdy_phys);
- ctxp->txrdy = NULL;
- ctxp->txrdy_phys = 0;
+#if (IS_ENABLED(CONFIG_NVME_TARGET_FC))
+ struct lpfc_nvmet_rcv_ctx *ctxp = ctx_buf->context;
+ struct lpfc_nvmet_tgtport *tgtp;
+ struct fc_frame_header *fc_hdr;
+ struct rqb_dmabuf *nvmebuf;
+ struct lpfc_dmabuf *hbufp;
+ uint32_t *payload;
+ uint32_t size, oxid, sid, rc;
+ unsigned long iflag;
+
+ if (ctxp->txrdy) {
+ pci_pool_free(phba->txrdy_payload_pool, ctxp->txrdy,
+ ctxp->txrdy_phys);
+ ctxp->txrdy = NULL;
+ ctxp->txrdy_phys = 0;
+ }
+ ctxp->state = LPFC_NVMET_STE_FREE;
+
+ spin_lock_irqsave(&phba->sli4_hba.nvmet_io_wait_lock, iflag);
+ if (phba->sli4_hba.nvmet_io_wait_cnt) {
+ hbufp = &nvmebuf->hbuf;
+ list_remove_head(&phba->sli4_hba.lpfc_nvmet_io_wait_list,
+ nvmebuf, struct rqb_dmabuf,
+ hbuf.list);
+ phba->sli4_hba.nvmet_io_wait_cnt--;
+ spin_unlock_irqrestore(&phba->sli4_hba.nvmet_io_wait_lock,
+ iflag);
+
+ fc_hdr = (struct fc_frame_header *)(nvmebuf->hbuf.virt);
+ oxid = be16_to_cpu(fc_hdr->fh_ox_id);
+ tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
+ payload = (uint32_t *)(nvmebuf->dbuf.virt);
+ size = nvmebuf->bytes_recv;
+ sid = sli4_sid_from_fc_hdr(fc_hdr);
+
+ ctxp = (struct lpfc_nvmet_rcv_ctx *)ctx_buf->context;
+ memset(ctxp, 0, sizeof(ctxp->ctx));
+ ctxp->wqeq = NULL;
+ ctxp->txrdy = NULL;
+ ctxp->offset = 0;
+ ctxp->phba = phba;
+ ctxp->size = size;
+ ctxp->oxid = oxid;
+ ctxp->sid = sid;
+ ctxp->state = LPFC_NVMET_STE_RCV;
+ ctxp->entry_cnt = 1;
+ ctxp->flag = 0;
+ ctxp->ctxbuf = ctx_buf;
+ spin_lock_init(&ctxp->ctxlock);
+
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+ if (phba->ktime_on) {
+ ctxp->ts_cmd_nvme = ktime_get_ns();
+ ctxp->ts_isr_cmd = ctxp->ts_cmd_nvme;
+ ctxp->ts_nvme_data = 0;
+ ctxp->ts_data_wqput = 0;
+ ctxp->ts_isr_data = 0;
+ ctxp->ts_data_nvme = 0;
+ ctxp->ts_nvme_status = 0;
+ ctxp->ts_status_wqput = 0;
+ ctxp->ts_isr_status = 0;
+ ctxp->ts_status_nvme = 0;
}
- ctxp->state = LPFC_NVMET_STE_FREE;
+#endif
+ atomic_inc(&tgtp->rcv_fcp_cmd_in);
+ /*
+ * The calling sequence should be:
+ * nvmet_fc_rcv_fcp_req->lpfc_nvmet_xmt_fcp_op/cmp- req->done
+ * lpfc_nvmet_xmt_fcp_op_cmp should free the allocated ctxp.
+ * When we return from nvmet_fc_rcv_fcp_req, all relevant info
+ * the NVME command / FC header is stored.
+ * A buffer has already been reposted for this IO, so just free
+ * the nvmebuf.
+ */
+ rc = nvmet_fc_rcv_fcp_req(phba->targetport, &ctxp->ctx.fcp_req,
+ payload, size);
+
+ /* Process FCP command */
+ if (rc == 0) {
+ atomic_inc(&tgtp->rcv_fcp_cmd_out);
+ nvmebuf->hrq->rqbp->rqb_free_buffer(phba, nvmebuf);
+ return;
+ }
+
+ atomic_inc(&tgtp->rcv_fcp_cmd_drop);
+ lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+ "2582 FCP Drop IO x%x: err x%x: x%x x%x x%x\n",
+ ctxp->oxid, rc,
+ atomic_read(&tgtp->rcv_fcp_cmd_in),
+ atomic_read(&tgtp->rcv_fcp_cmd_out),
+ atomic_read(&tgtp->xmt_fcp_release));
+
+ lpfc_nvmet_defer_release(phba, ctxp);
+ lpfc_nvmet_unsol_fcp_issue_abort(phba, ctxp, sid, oxid);
+ nvmebuf->hrq->rqbp->rqb_free_buffer(phba, nvmebuf);
+ return;
}
- lpfc_rq_buf_free(phba, mp);
+ spin_unlock_irqrestore(&phba->sli4_hba.nvmet_io_wait_lock, iflag);
+
+ spin_lock_irqsave(&phba->sli4_hba.nvmet_io_lock, iflag);
+ list_add_tail(&ctx_buf->list,
+ &phba->sli4_hba.lpfc_nvmet_ctx_list);
+ phba->sli4_hba.nvmet_ctx_cnt++;
+ spin_unlock_irqrestore(&phba->sli4_hba.nvmet_io_lock, iflag);
+#endif
}
#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
"6150 LS Drop IO x%x: Prep\n",
ctxp->oxid);
lpfc_in_buf_free(phba, &nvmebuf->dbuf);
+ atomic_inc(&nvmep->xmt_ls_abort);
lpfc_nvmet_unsol_ls_issue_abort(phba, ctxp,
ctxp->sid, ctxp->oxid);
return -ENOMEM;
lpfc_nlp_put(nvmewqeq->context1);
lpfc_in_buf_free(phba, &nvmebuf->dbuf);
+ atomic_inc(&nvmep->xmt_ls_abort);
lpfc_nvmet_unsol_ls_issue_abort(phba, ctxp, ctxp->sid, ctxp->oxid);
return -ENXIO;
}
lpfc_nvmeio_data(phba, "NVMET FCP CMND: xri x%x op x%x len x%x\n",
ctxp->oxid, rsp->op, rsp->rsplen);
+ ctxp->flag |= LPFC_NVMET_IO_INP;
rc = lpfc_sli4_issue_wqe(phba, LPFC_FCP_RING, nvmewqeq);
if (rc == WQE_SUCCESS) {
- ctxp->flag |= LPFC_NVMET_IO_INP;
#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
if (!phba->ktime_on)
return 0;
lpfc_nvmet_xmt_fcp_release(struct nvmet_fc_target_port *tgtport,
struct nvmefc_tgt_fcp_req *rsp)
{
+ struct lpfc_nvmet_tgtport *lpfc_nvmep = tgtport->private;
struct lpfc_nvmet_rcv_ctx *ctxp =
container_of(rsp, struct lpfc_nvmet_rcv_ctx, ctx.fcp_req);
struct lpfc_hba *phba = ctxp->phba;
}
spin_unlock_irqrestore(&ctxp->ctxlock, flags);
- lpfc_nvmeio_data(phba, "NVMET FCP FREE: xri x%x ste %d\n", ctxp->oxid,
- ctxp->state, 0);
+ lpfc_nvmeio_data(phba, "NVMET FCP FREE: xri x%x ste %d abt %d\n", ctxp->oxid,
+ ctxp->state, aborting);
+
+ atomic_inc(&lpfc_nvmep->xmt_fcp_release);
if (aborting)
return;
- lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
+ lpfc_nvmet_ctxbuf_post(phba, ctxp->ctxbuf);
}
static struct nvmet_fc_target_template lpfc_tgttemplate = {
.target_priv_sz = sizeof(struct lpfc_nvmet_tgtport),
};
+void
+lpfc_nvmet_cleanup_io_context(struct lpfc_hba *phba)
+{
+ struct lpfc_nvmet_ctxbuf *ctx_buf, *next_ctx_buf;
+ unsigned long flags;
+
+ list_for_each_entry_safe(
+ ctx_buf, next_ctx_buf,
+ &phba->sli4_hba.lpfc_nvmet_ctx_list, list) {
+ spin_lock_irqsave(
+ &phba->sli4_hba.abts_nvme_buf_list_lock, flags);
+ list_del_init(&ctx_buf->list);
+ spin_unlock_irqrestore(
+ &phba->sli4_hba.abts_nvme_buf_list_lock, flags);
+ __lpfc_clear_active_sglq(phba,
+ ctx_buf->sglq->sli4_lxritag);
+ ctx_buf->sglq->state = SGL_FREED;
+ ctx_buf->sglq->ndlp = NULL;
+
+ spin_lock_irqsave(&phba->sli4_hba.sgl_list_lock, flags);
+ list_add_tail(&ctx_buf->sglq->list,
+ &phba->sli4_hba.lpfc_nvmet_sgl_list);
+ spin_unlock_irqrestore(&phba->sli4_hba.sgl_list_lock,
+ flags);
+
+ lpfc_sli_release_iocbq(phba, ctx_buf->iocbq);
+ kfree(ctx_buf->context);
+ }
+}
+
+int
+lpfc_nvmet_setup_io_context(struct lpfc_hba *phba)
+{
+ struct lpfc_nvmet_ctxbuf *ctx_buf;
+ struct lpfc_iocbq *nvmewqe;
+ union lpfc_wqe128 *wqe;
+ int i;
+
+ lpfc_printf_log(phba, KERN_INFO, LOG_NVME,
+ "6403 Allocate NVMET resources for %d XRIs\n",
+ phba->sli4_hba.nvmet_xri_cnt);
+
+ /* For all nvmet xris, allocate resources needed to process a
+ * received command on a per xri basis.
+ */
+ for (i = 0; i < phba->sli4_hba.nvmet_xri_cnt; i++) {
+ ctx_buf = kzalloc(sizeof(*ctx_buf), GFP_KERNEL);
+ if (!ctx_buf) {
+ lpfc_printf_log(phba, KERN_ERR, LOG_NVME,
+ "6404 Ran out of memory for NVMET\n");
+ return -ENOMEM;
+ }
+
+ ctx_buf->context = kzalloc(sizeof(*ctx_buf->context),
+ GFP_KERNEL);
+ if (!ctx_buf->context) {
+ kfree(ctx_buf);
+ lpfc_printf_log(phba, KERN_ERR, LOG_NVME,
+ "6405 Ran out of NVMET "
+ "context memory\n");
+ return -ENOMEM;
+ }
+ ctx_buf->context->ctxbuf = ctx_buf;
+
+ ctx_buf->iocbq = lpfc_sli_get_iocbq(phba);
+ if (!ctx_buf->iocbq) {
+ kfree(ctx_buf->context);
+ kfree(ctx_buf);
+ lpfc_printf_log(phba, KERN_ERR, LOG_NVME,
+ "6406 Ran out of NVMET iocb/WQEs\n");
+ return -ENOMEM;
+ }
+ ctx_buf->iocbq->iocb_flag = LPFC_IO_NVMET;
+ nvmewqe = ctx_buf->iocbq;
+ wqe = (union lpfc_wqe128 *)&nvmewqe->wqe;
+ /* Initialize WQE */
+ memset(wqe, 0, sizeof(union lpfc_wqe));
+ /* Word 7 */
+ bf_set(wqe_ct, &wqe->generic.wqe_com, SLI4_CT_RPI);
+ bf_set(wqe_class, &wqe->generic.wqe_com, CLASS3);
+ bf_set(wqe_pu, &wqe->generic.wqe_com, 1);
+ /* Word 10 */
+ bf_set(wqe_nvme, &wqe->fcp_tsend.wqe_com, 1);
+ bf_set(wqe_ebde_cnt, &wqe->generic.wqe_com, 0);
+ bf_set(wqe_qosd, &wqe->generic.wqe_com, 0);
+
+ ctx_buf->iocbq->context1 = NULL;
+ spin_lock(&phba->sli4_hba.sgl_list_lock);
+ ctx_buf->sglq = __lpfc_sli_get_nvmet_sglq(phba, ctx_buf->iocbq);
+ spin_unlock(&phba->sli4_hba.sgl_list_lock);
+ if (!ctx_buf->sglq) {
+ lpfc_sli_release_iocbq(phba, ctx_buf->iocbq);
+ kfree(ctx_buf->context);
+ kfree(ctx_buf);
+ lpfc_printf_log(phba, KERN_ERR, LOG_NVME,
+ "6407 Ran out of NVMET XRIs\n");
+ return -ENOMEM;
+ }
+ spin_lock(&phba->sli4_hba.nvmet_io_lock);
+ list_add_tail(&ctx_buf->list,
+ &phba->sli4_hba.lpfc_nvmet_ctx_list);
+ spin_unlock(&phba->sli4_hba.nvmet_io_lock);
+ }
+ phba->sli4_hba.nvmet_ctx_cnt = phba->sli4_hba.nvmet_xri_cnt;
+ return 0;
+}
+
int
lpfc_nvmet_create_targetport(struct lpfc_hba *phba)
{
struct lpfc_vport *vport = phba->pport;
struct lpfc_nvmet_tgtport *tgtp;
struct nvmet_fc_port_info pinfo;
- int error = 0;
+ int error;
if (phba->targetport)
return 0;
+ error = lpfc_nvmet_setup_io_context(phba);
+ if (error)
+ return error;
+
memset(&pinfo, 0, sizeof(struct nvmet_fc_port_info));
pinfo.node_name = wwn_to_u64(vport->fc_nodename.u.wwn);
pinfo.port_name = wwn_to_u64(vport->fc_portname.u.wwn);
lpfc_tgttemplate.max_sgl_segments = phba->cfg_nvme_seg_cnt + 1;
lpfc_tgttemplate.max_hw_queues = phba->cfg_nvme_io_channel;
lpfc_tgttemplate.target_features = NVMET_FCTGTFEAT_READDATA_RSP |
- NVMET_FCTGTFEAT_NEEDS_CMD_CPUSCHED |
NVMET_FCTGTFEAT_CMD_IN_ISR |
NVMET_FCTGTFEAT_OPDONE_IN_ISR;
&phba->pcidev->dev,
&phba->targetport);
#else
- error = -ENOMEM;
+ error = -ENOENT;
#endif
if (error) {
lpfc_printf_log(phba, KERN_ERR, LOG_NVME_DISC,
"6025 Cannot register NVME targetport "
"x%x\n", error);
phba->targetport = NULL;
+
+ lpfc_nvmet_cleanup_io_context(phba);
+
} else {
tgtp = (struct lpfc_nvmet_tgtport *)
phba->targetport->private;
atomic_set(&tgtp->rcv_ls_req_out, 0);
atomic_set(&tgtp->rcv_ls_req_drop, 0);
atomic_set(&tgtp->xmt_ls_abort, 0);
+ atomic_set(&tgtp->xmt_ls_abort_cmpl, 0);
atomic_set(&tgtp->xmt_ls_rsp, 0);
atomic_set(&tgtp->xmt_ls_drop, 0);
atomic_set(&tgtp->xmt_ls_rsp_error, 0);
atomic_set(&tgtp->rcv_fcp_cmd_in, 0);
atomic_set(&tgtp->rcv_fcp_cmd_out, 0);
atomic_set(&tgtp->rcv_fcp_cmd_drop, 0);
- atomic_set(&tgtp->xmt_fcp_abort, 0);
atomic_set(&tgtp->xmt_fcp_drop, 0);
atomic_set(&tgtp->xmt_fcp_read_rsp, 0);
atomic_set(&tgtp->xmt_fcp_read, 0);
atomic_set(&tgtp->xmt_fcp_write, 0);
atomic_set(&tgtp->xmt_fcp_rsp, 0);
+ atomic_set(&tgtp->xmt_fcp_release, 0);
atomic_set(&tgtp->xmt_fcp_rsp_cmpl, 0);
atomic_set(&tgtp->xmt_fcp_rsp_error, 0);
atomic_set(&tgtp->xmt_fcp_rsp_drop, 0);
+ atomic_set(&tgtp->xmt_fcp_abort, 0);
+ atomic_set(&tgtp->xmt_fcp_abort_cmpl, 0);
+ atomic_set(&tgtp->xmt_abort_unsol, 0);
+ atomic_set(&tgtp->xmt_abort_sol, 0);
atomic_set(&tgtp->xmt_abort_rsp, 0);
atomic_set(&tgtp->xmt_abort_rsp_error, 0);
- atomic_set(&tgtp->xmt_abort_cmpl, 0);
}
return error;
}
list_for_each_entry_safe(ctxp, next_ctxp,
&phba->sli4_hba.lpfc_abts_nvmet_ctx_list,
list) {
- if (ctxp->rqb_buffer->sglq->sli4_xritag != xri)
+ if (ctxp->ctxbuf->sglq->sli4_xritag != xri)
continue;
/* Check if we already received a free context call
(ndlp->nlp_state == NLP_STE_UNMAPPED_NODE ||
ndlp->nlp_state == NLP_STE_MAPPED_NODE)) {
lpfc_set_rrq_active(phba, ndlp,
- ctxp->rqb_buffer->sglq->sli4_lxritag,
+ ctxp->ctxbuf->sglq->sli4_lxritag,
rxid, 1);
lpfc_sli4_abts_err_handler(phba, ndlp, axri);
}
"6318 XB aborted %x flg x%x (%x)\n",
ctxp->oxid, ctxp->flag, released);
if (released)
- lpfc_nvmet_rq_post(phba, ctxp,
- &ctxp->rqb_buffer->hbuf);
+ lpfc_nvmet_ctxbuf_post(phba, ctxp->ctxbuf);
+
if (rrq_empty)
lpfc_worker_wake_up(phba);
return;
list_for_each_entry_safe(ctxp, next_ctxp,
&phba->sli4_hba.lpfc_abts_nvmet_ctx_list,
list) {
- if (ctxp->rqb_buffer->sglq->sli4_xritag != xri)
+ if (ctxp->ctxbuf->sglq->sli4_xritag != xri)
continue;
spin_unlock(&phba->sli4_hba.abts_nvme_buf_list_lock);
init_completion(&tgtp->tport_unreg_done);
nvmet_fc_unregister_targetport(phba->targetport);
wait_for_completion_timeout(&tgtp->tport_unreg_done, 5);
+ lpfc_nvmet_cleanup_io_context(phba);
}
phba->targetport = NULL;
#endif
oxid = 0;
size = 0;
sid = 0;
+ ctxp = NULL;
goto dropit;
}
struct lpfc_nvmet_rcv_ctx *ctxp;
struct lpfc_nvmet_tgtport *tgtp;
struct fc_frame_header *fc_hdr;
+ struct lpfc_nvmet_ctxbuf *ctx_buf;
uint32_t *payload;
- uint32_t size, oxid, sid, rc;
+ uint32_t size, oxid, sid, rc, qno;
+ unsigned long iflag;
#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
uint32_t id;
#endif
+ ctx_buf = NULL;
if (!nvmebuf || !phba->targetport) {
lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
- "6157 FCP Drop IO\n");
+ "6157 NVMET FCP Drop IO\n");
oxid = 0;
size = 0;
sid = 0;
+ ctxp = NULL;
goto dropit;
}
+ spin_lock_irqsave(&phba->sli4_hba.nvmet_io_lock, iflag);
+ if (phba->sli4_hba.nvmet_ctx_cnt) {
+ list_remove_head(&phba->sli4_hba.lpfc_nvmet_ctx_list,
+ ctx_buf, struct lpfc_nvmet_ctxbuf, list);
+ phba->sli4_hba.nvmet_ctx_cnt--;
+ }
+ spin_unlock_irqrestore(&phba->sli4_hba.nvmet_io_lock, iflag);
- tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
- payload = (uint32_t *)(nvmebuf->dbuf.virt);
fc_hdr = (struct fc_frame_header *)(nvmebuf->hbuf.virt);
- size = nvmebuf->bytes_recv;
oxid = be16_to_cpu(fc_hdr->fh_ox_id);
- sid = sli4_sid_from_fc_hdr(fc_hdr);
+ size = nvmebuf->bytes_recv;
- ctxp = (struct lpfc_nvmet_rcv_ctx *)nvmebuf->context;
- if (ctxp == NULL) {
- atomic_inc(&tgtp->rcv_fcp_cmd_drop);
- lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
- "6158 FCP Drop IO x%x: Alloc\n",
- oxid);
- lpfc_nvmet_rq_post(phba, NULL, &nvmebuf->hbuf);
- /* Cannot send ABTS without context */
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+ if (phba->cpucheck_on & LPFC_CHECK_NVMET_RCV) {
+ id = smp_processor_id();
+ if (id < LPFC_CHECK_CPU_CNT)
+ phba->cpucheck_rcv_io[id]++;
+ }
+#endif
+
+ lpfc_nvmeio_data(phba, "NVMET FCP RCV: xri x%x sz %d CPU %02x\n",
+ oxid, size, smp_processor_id());
+
+ if (!ctx_buf) {
+ /* Queue this NVME IO to process later */
+ spin_lock_irqsave(&phba->sli4_hba.nvmet_io_wait_lock, iflag);
+ list_add_tail(&nvmebuf->hbuf.list,
+ &phba->sli4_hba.lpfc_nvmet_io_wait_list);
+ phba->sli4_hba.nvmet_io_wait_cnt++;
+ phba->sli4_hba.nvmet_io_wait_total++;
+ spin_unlock_irqrestore(&phba->sli4_hba.nvmet_io_wait_lock,
+ iflag);
+
+ /* Post a brand new DMA buffer to RQ */
+ qno = nvmebuf->idx;
+ lpfc_post_rq_buffer(
+ phba, phba->sli4_hba.nvmet_mrq_hdr[qno],
+ phba->sli4_hba.nvmet_mrq_data[qno], 1, qno);
return;
}
+
+ tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
+ payload = (uint32_t *)(nvmebuf->dbuf.virt);
+ sid = sli4_sid_from_fc_hdr(fc_hdr);
+
+ ctxp = (struct lpfc_nvmet_rcv_ctx *)ctx_buf->context;
memset(ctxp, 0, sizeof(ctxp->ctx));
ctxp->wqeq = NULL;
ctxp->txrdy = NULL;
ctxp->oxid = oxid;
ctxp->sid = sid;
ctxp->state = LPFC_NVMET_STE_RCV;
- ctxp->rqb_buffer = nvmebuf;
ctxp->entry_cnt = 1;
ctxp->flag = 0;
+ ctxp->ctxbuf = ctx_buf;
spin_lock_init(&ctxp->ctxlock);
#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
ctxp->ts_isr_status = 0;
ctxp->ts_status_nvme = 0;
}
-
- if (phba->cpucheck_on & LPFC_CHECK_NVMET_RCV) {
- id = smp_processor_id();
- if (id < LPFC_CHECK_CPU_CNT)
- phba->cpucheck_rcv_io[id]++;
- }
#endif
- lpfc_nvmeio_data(phba, "NVMET FCP RCV: xri x%x sz %d CPU %02x\n",
- oxid, size, smp_processor_id());
-
atomic_inc(&tgtp->rcv_fcp_cmd_in);
/*
* The calling sequence should be:
* nvmet_fc_rcv_fcp_req -> lpfc_nvmet_xmt_fcp_op/cmp -> req->done
* lpfc_nvmet_xmt_fcp_op_cmp should free the allocated ctxp.
+ * When we return from nvmet_fc_rcv_fcp_req, all relevant info in
+ * the NVME command / FC header is stored, so we are free to repost
+ * the buffer.
*/
rc = nvmet_fc_rcv_fcp_req(phba->targetport, &ctxp->ctx.fcp_req,
payload, size);
/* Process FCP command */
if (rc == 0) {
atomic_inc(&tgtp->rcv_fcp_cmd_out);
+ lpfc_rq_buf_free(phba, &nvmebuf->hbuf); /* repost */
return;
}
atomic_inc(&tgtp->rcv_fcp_cmd_drop);
lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
- "6159 FCP Drop IO x%x: err x%x\n",
- ctxp->oxid, rc);
+ "6159 FCP Drop IO x%x: err x%x: x%x x%x x%x\n",
+ ctxp->oxid, rc,
+ atomic_read(&tgtp->rcv_fcp_cmd_in),
+ atomic_read(&tgtp->rcv_fcp_cmd_out),
+ atomic_read(&tgtp->xmt_fcp_release));
dropit:
lpfc_nvmeio_data(phba, "NVMET FCP DROP: xri x%x sz %d from %06x\n",
oxid, size, sid);
if (oxid) {
+ lpfc_nvmet_defer_release(phba, ctxp);
lpfc_nvmet_unsol_fcp_issue_abort(phba, ctxp, sid, oxid);
+ lpfc_rq_buf_free(phba, &nvmebuf->hbuf); /* repost */
return;
}
- if (nvmebuf) {
- nvmebuf->iocbq->hba_wqidx = 0;
- /* We assume a rcv'ed cmd ALWAYs fits into 1 buffer */
- lpfc_nvmet_rq_post(phba, NULL, &nvmebuf->hbuf);
- }
+ if (ctx_buf)
+ lpfc_nvmet_ctxbuf_post(phba, ctx_buf);
+
+ if (nvmebuf)
+ lpfc_rq_buf_free(phba, &nvmebuf->hbuf); /* repost */
#endif
}
uint64_t isr_timestamp)
{
if (phba->nvmet_support == 0) {
- lpfc_nvmet_rq_post(phba, NULL, &nvmebuf->hbuf);
+ lpfc_rq_buf_free(phba, &nvmebuf->hbuf);
return;
}
lpfc_nvmet_unsol_fcp_buffer(phba, pring, nvmebuf,
nvmewqe = ctxp->wqeq;
if (nvmewqe == NULL) {
/* Allocate buffer for command wqe */
- nvmewqe = ctxp->rqb_buffer->iocbq;
+ nvmewqe = ctxp->ctxbuf->iocbq;
if (nvmewqe == NULL) {
lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
"6110 lpfc_nvmet_prep_fcp_wqe: No "
return NULL;
}
- sgl = (struct sli4_sge *)ctxp->rqb_buffer->sglq->sgl;
+ sgl = (struct sli4_sge *)ctxp->ctxbuf->sglq->sgl;
switch (rsp->op) {
case NVMET_FCOP_READDATA:
case NVMET_FCOP_READDATA_RSP:
result = wcqe->parameter;
tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
- atomic_inc(&tgtp->xmt_abort_cmpl);
+ if (ctxp->flag & LPFC_NVMET_ABORT_OP)
+ atomic_inc(&tgtp->xmt_fcp_abort_cmpl);
ctxp->state = LPFC_NVMET_STE_DONE;
}
ctxp->flag &= ~LPFC_NVMET_ABORT_OP;
spin_unlock_irqrestore(&ctxp->ctxlock, flags);
+ atomic_inc(&tgtp->xmt_abort_rsp);
lpfc_printf_log(phba, KERN_ERR, LOG_NVME_ABTS,
"6165 ABORT cmpl: xri x%x flg x%x (%d) "
wcqe->word0, wcqe->total_data_placed,
result, wcqe->word3);
+ cmdwqe->context2 = NULL;
+ cmdwqe->context3 = NULL;
/*
* if transport has released ctx, then can reuse it. Otherwise,
* will be recycled by transport release call.
*/
if (released)
- lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
+ lpfc_nvmet_ctxbuf_post(phba, ctxp->ctxbuf);
- cmdwqe->context2 = NULL;
- cmdwqe->context3 = NULL;
+ /* This is the iocbq for the abort, not the command */
lpfc_sli_release_iocbq(phba, cmdwqe);
/* Since iaab/iaar are NOT set, there is no work left.
result = wcqe->parameter;
tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
- atomic_inc(&tgtp->xmt_abort_cmpl);
+ if (ctxp->flag & LPFC_NVMET_ABORT_OP)
+ atomic_inc(&tgtp->xmt_fcp_abort_cmpl);
if (!ctxp) {
/* if context is clear, related io alrady complete */
}
ctxp->flag &= ~LPFC_NVMET_ABORT_OP;
spin_unlock_irqrestore(&ctxp->ctxlock, flags);
+ atomic_inc(&tgtp->xmt_abort_rsp);
lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
"6316 ABTS cmpl xri x%x flg x%x (%x) "
ctxp->oxid, ctxp->flag, released,
wcqe->word0, wcqe->total_data_placed,
result, wcqe->word3);
+
+ cmdwqe->context2 = NULL;
+ cmdwqe->context3 = NULL;
/*
* if transport has released ctx, then can reuse it. Otherwise,
* will be recycled by transport release call.
*/
if (released)
- lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
-
- cmdwqe->context2 = NULL;
- cmdwqe->context3 = NULL;
+ lpfc_nvmet_ctxbuf_post(phba, ctxp->ctxbuf);
/* Since iaab/iaar are NOT set, there is no work left.
* For LPFC_NVMET_XBUSY, lpfc_sli4_nvmet_xri_aborted
result = wcqe->parameter;
tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
- atomic_inc(&tgtp->xmt_abort_cmpl);
+ atomic_inc(&tgtp->xmt_ls_abort_cmpl);
lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
"6083 Abort cmpl: ctx %p WCQE: %08x %08x %08x %08x\n",
sid, xri, ctxp->wqeq->sli4_xritag);
tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
- if (!ctxp->wqeq) {
- ctxp->wqeq = ctxp->rqb_buffer->iocbq;
- ctxp->wqeq->hba_wqidx = 0;
- }
ndlp = lpfc_findnode_did(phba->pport, sid);
if (!ndlp || !NLP_CHK_NODE_ACT(ndlp) ||
tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
if (!ctxp->wqeq) {
- ctxp->wqeq = ctxp->rqb_buffer->iocbq;
+ ctxp->wqeq = ctxp->ctxbuf->iocbq;
ctxp->wqeq->hba_wqidx = 0;
}
/* Issue ABTS for this WQE based on iotag */
ctxp->abort_wqeq = lpfc_sli_get_iocbq(phba);
if (!ctxp->abort_wqeq) {
+ atomic_inc(&tgtp->xmt_abort_rsp_error);
lpfc_printf_log(phba, KERN_WARNING, LOG_NVME_ABTS,
"6161 ABORT failed: No wqeqs: "
"xri: x%x\n", ctxp->oxid);
/* driver queued commands are in process of being flushed */
if (phba->hba_flag & HBA_NVME_IOQ_FLUSH) {
spin_unlock_irqrestore(&phba->hbalock, flags);
+ atomic_inc(&tgtp->xmt_abort_rsp_error);
lpfc_printf_log(phba, KERN_ERR, LOG_NVME,
"6163 Driver in reset cleanup - flushing "
"NVME Req now. hba_flag x%x oxid x%x\n",
/* Outstanding abort is in progress */
if (abts_wqeq->iocb_flag & LPFC_DRIVER_ABORTED) {
spin_unlock_irqrestore(&phba->hbalock, flags);
+ atomic_inc(&tgtp->xmt_abort_rsp_error);
lpfc_printf_log(phba, KERN_ERR, LOG_NVME,
"6164 Outstanding NVME I/O Abort Request "
"still pending on oxid x%x\n",
abts_wqeq->context2 = ctxp;
rc = lpfc_sli4_issue_wqe(phba, LPFC_FCP_RING, abts_wqeq);
spin_unlock_irqrestore(&phba->hbalock, flags);
- if (rc == WQE_SUCCESS)
+ if (rc == WQE_SUCCESS) {
+ atomic_inc(&tgtp->xmt_abort_sol);
return 0;
+ }
+ atomic_inc(&tgtp->xmt_abort_rsp_error);
ctxp->flag &= ~LPFC_NVMET_ABORT_OP;
lpfc_sli_release_iocbq(phba, abts_wqeq);
lpfc_printf_log(phba, KERN_ERR, LOG_NVME_ABTS,
tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
if (!ctxp->wqeq) {
- ctxp->wqeq = ctxp->rqb_buffer->iocbq;
+ ctxp->wqeq = ctxp->ctxbuf->iocbq;
ctxp->wqeq->hba_wqidx = 0;
}
rc = lpfc_sli4_issue_wqe(phba, LPFC_FCP_RING, abts_wqeq);
spin_unlock_irqrestore(&phba->hbalock, flags);
if (rc == WQE_SUCCESS) {
- atomic_inc(&tgtp->xmt_abort_rsp);
return 0;
}
aerr:
+ atomic_inc(&tgtp->xmt_abort_rsp_error);
ctxp->flag &= ~LPFC_NVMET_ABORT_OP;
atomic_inc(&tgtp->xmt_abort_rsp_error);
lpfc_printf_log(phba, KERN_WARNING, LOG_NVME_ABTS,
}
abts_wqeq = ctxp->wqeq;
wqe_abts = &abts_wqeq->wqe;
+
lpfc_nvmet_unsol_issue_abort(phba, ctxp, sid, xri);
spin_lock_irqsave(&phba->hbalock, flags);
rc = lpfc_sli4_issue_wqe(phba, LPFC_ELS_RING, abts_wqeq);
spin_unlock_irqrestore(&phba->hbalock, flags);
if (rc == WQE_SUCCESS) {
- atomic_inc(&tgtp->xmt_abort_rsp);
+ atomic_inc(&tgtp->xmt_abort_unsol);
return 0;
}
********************************************************************/
#define LPFC_NVMET_DEFAULT_SEGS (64 + 1) /* 256K IOs */
+#define LPFC_NVMET_RQE_DEF_COUNT 512
#define LPFC_NVMET_SUCCESS_LEN 12
/* Used for NVME Target */
atomic_t rcv_ls_req_out;
atomic_t rcv_ls_req_drop;
atomic_t xmt_ls_abort;
+ atomic_t xmt_ls_abort_cmpl;
/* Stats counters - lpfc_nvmet_xmt_ls_rsp */
atomic_t xmt_ls_rsp;
atomic_t rcv_fcp_cmd_in;
atomic_t rcv_fcp_cmd_out;
atomic_t rcv_fcp_cmd_drop;
+ atomic_t xmt_fcp_release;
/* Stats counters - lpfc_nvmet_xmt_fcp_op */
- atomic_t xmt_fcp_abort;
atomic_t xmt_fcp_drop;
atomic_t xmt_fcp_read_rsp;
atomic_t xmt_fcp_read;
atomic_t xmt_fcp_rsp_drop;
- /* Stats counters - lpfc_nvmet_unsol_issue_abort */
+ /* Stats counters - lpfc_nvmet_xmt_fcp_abort */
+ atomic_t xmt_fcp_abort;
+ atomic_t xmt_fcp_abort_cmpl;
+ atomic_t xmt_abort_sol;
+ atomic_t xmt_abort_unsol;
atomic_t xmt_abort_rsp;
atomic_t xmt_abort_rsp_error;
-
- /* Stats counters - lpfc_nvmet_xmt_abort_cmp */
- atomic_t xmt_abort_cmpl;
};
struct lpfc_nvmet_rcv_ctx {
#define LPFC_NVMET_CTX_RLS 0x8 /* ctx free requested */
#define LPFC_NVMET_ABTS_RCV 0x10 /* ABTS received on exchange */
struct rqb_dmabuf *rqb_buffer;
+ struct lpfc_nvmet_ctxbuf *ctxbuf;
#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
uint64_t ts_isr_cmd;
struct lpfc_iocbq *);
static void lpfc_sli4_send_seq_to_ulp(struct lpfc_vport *,
struct hbq_dmabuf *);
+static void lpfc_sli4_handle_mds_loopback(struct lpfc_vport *vport,
+ struct hbq_dmabuf *dmabuf);
static int lpfc_sli4_fp_handle_cqe(struct lpfc_hba *, struct lpfc_queue *,
struct lpfc_cqe *);
static int lpfc_sli4_post_sgl_list(struct lpfc_hba *, struct list_head *,
if (unlikely(!hq) || unlikely(!dq))
return -ENOMEM;
put_index = hq->host_index;
- temp_hrqe = hq->qe[hq->host_index].rqe;
+ temp_hrqe = hq->qe[put_index].rqe;
temp_drqe = dq->qe[dq->host_index].rqe;
if (hq->type != LPFC_HRQ || dq->type != LPFC_DRQ)
return -EINVAL;
- if (hq->host_index != dq->host_index)
+ if (put_index != dq->host_index)
return -EINVAL;
/* If the host has not yet processed the next entry then we are done */
- if (((hq->host_index + 1) % hq->entry_count) == hq->hba_index)
+ if (((put_index + 1) % hq->entry_count) == hq->hba_index)
return -EBUSY;
lpfc_sli_pcimem_bcopy(hrqe, temp_hrqe, hq->entry_size);
lpfc_sli_pcimem_bcopy(drqe, temp_drqe, dq->entry_size);
/* Update the host index to point to the next slot */
- hq->host_index = ((hq->host_index + 1) % hq->entry_count);
+ hq->host_index = ((put_index + 1) % hq->entry_count);
dq->host_index = ((dq->host_index + 1) % dq->entry_count);
+ hq->RQ_buf_posted++;
/* Ring The Header Receive Queue Doorbell */
if (!(hq->host_index % hq->entry_repost)) {
/* Reset HBA */
lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
"0325 Reset HBA Data: x%x x%x\n",
- phba->pport->port_state, psli->sli_flag);
+ (phba->pport) ? phba->pport->port_state : 0,
+ psli->sli_flag);
/* perform board reset */
phba->fc_eventTag = 0;
phba->link_events = 0;
- phba->pport->fc_myDID = 0;
- phba->pport->fc_prevDID = 0;
+ if (phba->pport) {
+ phba->pport->fc_myDID = 0;
+ phba->pport->fc_prevDID = 0;
+ }
/* Turn off parity checking and serr during the physical reset */
pci_read_config_word(phba->pcidev, PCI_COMMAND, &cfg_value);
/* Restart HBA */
lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
"0337 Restart HBA Data: x%x x%x\n",
- phba->pport->port_state, psli->sli_flag);
+ (phba->pport) ? phba->pport->port_state : 0,
+ psli->sli_flag);
word0 = 0;
mb = (MAILBOX_t *) &word0;
readl(to_slim); /* flush */
/* Only skip post after fc_ffinit is completed */
- if (phba->pport->port_state)
+ if (phba->pport && phba->pport->port_state)
word0 = 1; /* This is really setting up word1 */
else
word0 = 0; /* This is really setting up word1 */
readl(to_slim); /* flush */
lpfc_sli_brdreset(phba);
- phba->pport->stopped = 0;
+ if (phba->pport)
+ phba->pport->stopped = 0;
phba->link_state = LPFC_INIT_START;
phba->hba_flag = 0;
spin_unlock_irq(&phba->hbalock);
* iteration, the function will restart the HBA again. The function returns
* zero if HBA successfully restarted else returns negative error code.
**/
-static int
+int
lpfc_sli_chipset_init(struct lpfc_hba *phba)
{
uint32_t status, i = 0;
bf_set(lpfc_mbx_set_feature_mds,
&mbox->u.mqe.un.set_feature, 1);
bf_set(lpfc_mbx_set_feature_mds_deep_loopbk,
- &mbox->u.mqe.un.set_feature, 0);
+ &mbox->u.mqe.un.set_feature, 1);
mbox->u.mqe.un.set_feature.feature = LPFC_SET_MDS_DIAGS;
mbox->u.mqe.un.set_feature.param_len = 8;
break;
(phba->hba_flag & HBA_FCOE_MODE) ? "FCoE" : "FC");
}
+int
+lpfc_post_rq_buffer(struct lpfc_hba *phba, struct lpfc_queue *hrq,
+ struct lpfc_queue *drq, int count, int idx)
+{
+ int rc, i;
+ struct lpfc_rqe hrqe;
+ struct lpfc_rqe drqe;
+ struct lpfc_rqb *rqbp;
+ struct rqb_dmabuf *rqb_buffer;
+ LIST_HEAD(rqb_buf_list);
+
+ rqbp = hrq->rqbp;
+ for (i = 0; i < count; i++) {
+ /* IF RQ is already full, don't bother */
+ if (rqbp->buffer_count + i >= rqbp->entry_count - 1)
+ break;
+ rqb_buffer = rqbp->rqb_alloc_buffer(phba);
+ if (!rqb_buffer)
+ break;
+ rqb_buffer->hrq = hrq;
+ rqb_buffer->drq = drq;
+ rqb_buffer->idx = idx;
+ list_add_tail(&rqb_buffer->hbuf.list, &rqb_buf_list);
+ }
+ while (!list_empty(&rqb_buf_list)) {
+ list_remove_head(&rqb_buf_list, rqb_buffer, struct rqb_dmabuf,
+ hbuf.list);
+
+ hrqe.address_lo = putPaddrLow(rqb_buffer->hbuf.phys);
+ hrqe.address_hi = putPaddrHigh(rqb_buffer->hbuf.phys);
+ drqe.address_lo = putPaddrLow(rqb_buffer->dbuf.phys);
+ drqe.address_hi = putPaddrHigh(rqb_buffer->dbuf.phys);
+ rc = lpfc_sli4_rq_put(hrq, drq, &hrqe, &drqe);
+ if (rc < 0) {
+ rqbp->rqb_free_buffer(phba, rqb_buffer);
+ } else {
+ list_add_tail(&rqb_buffer->hbuf.list,
+ &rqbp->rqb_buffer_list);
+ rqbp->buffer_count++;
+ }
+ }
+ return 1;
+}
+
/**
* lpfc_sli4_hba_setup - SLI4 device initialization PCI function
* @phba: Pointer to HBA context object.
int
lpfc_sli4_hba_setup(struct lpfc_hba *phba)
{
- int rc, i;
+ int rc, i, cnt;
LPFC_MBOXQ_t *mboxq;
struct lpfc_mqe *mqe;
uint8_t *vpd;
goto out_destroy_queue;
}
phba->sli4_hba.nvmet_xri_cnt = rc;
+
+ cnt = phba->cfg_iocb_cnt * 1024;
+ /* We need 1 iocbq for every SGL, for IO processing */
+ cnt += phba->sli4_hba.nvmet_xri_cnt;
+ /* Initialize and populate the iocb list per host */
+ lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
+ "2821 initialize iocb list %d total %d\n",
+ phba->cfg_iocb_cnt, cnt);
+ rc = lpfc_init_iocb_list(phba, cnt);
+ if (rc) {
+ lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+ "1413 Failed to init iocb list.\n");
+ goto out_destroy_queue;
+ }
+
lpfc_nvmet_create_targetport(phba);
} else {
/* update host scsi xri-sgl sizes and mappings */
"and mapping: %d\n", rc);
goto out_destroy_queue;
}
+
+ cnt = phba->cfg_iocb_cnt * 1024;
+ /* Initialize and populate the iocb list per host */
+ lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
+ "2820 initialize iocb list %d total %d\n",
+ phba->cfg_iocb_cnt, cnt);
+ rc = lpfc_init_iocb_list(phba, cnt);
+ if (rc) {
+ lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+ "6301 Failed to init iocb list.\n");
+ goto out_destroy_queue;
+ }
}
if (phba->nvmet_support && phba->cfg_nvmet_mrq) {
-
/* Post initial buffers to all RQs created */
for (i = 0; i < phba->cfg_nvmet_mrq; i++) {
rqbp = phba->sli4_hba.nvmet_mrq_hdr[i]->rqbp;
INIT_LIST_HEAD(&rqbp->rqb_buffer_list);
rqbp->rqb_alloc_buffer = lpfc_sli4_nvmet_alloc;
rqbp->rqb_free_buffer = lpfc_sli4_nvmet_free;
- rqbp->entry_count = 256;
+ rqbp->entry_count = LPFC_NVMET_RQE_DEF_COUNT;
rqbp->buffer_count = 0;
- /* Divide by 4 and round down to multiple of 16 */
- rc = (phba->cfg_nvmet_mrq_post >> 2) & 0xfff8;
- phba->sli4_hba.nvmet_mrq_hdr[i]->entry_repost = rc;
- phba->sli4_hba.nvmet_mrq_data[i]->entry_repost = rc;
-
lpfc_post_rq_buffer(
phba, phba->sli4_hba.nvmet_mrq_hdr[i],
phba->sli4_hba.nvmet_mrq_data[i],
- phba->cfg_nvmet_mrq_post);
+ LPFC_NVMET_RQE_DEF_COUNT, i);
}
}
/* Unset all the queues set up in this routine when error out */
lpfc_sli4_queue_unset(phba);
out_destroy_queue:
+ lpfc_free_iocb_list(phba);
lpfc_sli4_queue_destroy(phba);
out_stop_timers:
lpfc_stop_hba_timers(phba);
memset(wqe, 0, sizeof(union lpfc_wqe128));
/* Some of the fields are in the right position already */
memcpy(wqe, &iocbq->iocb, sizeof(union lpfc_wqe));
- wqe->generic.wqe_com.word7 = 0; /* The ct field has moved so reset */
- wqe->generic.wqe_com.word10 = 0;
+ if (iocbq->iocb.ulpCommand != CMD_SEND_FRAME) {
+ /* The ct field has moved so reset */
+ wqe->generic.wqe_com.word7 = 0;
+ wqe->generic.wqe_com.word10 = 0;
+ }
abort_tag = (uint32_t) iocbq->iotag;
xritag = iocbq->sli4_xritag;
}
break;
+ case CMD_SEND_FRAME:
+ bf_set(wqe_xri_tag, &wqe->generic.wqe_com, xritag);
+ bf_set(wqe_reqtag, &wqe->generic.wqe_com, iocbq->iotag);
+ return 0;
case CMD_XRI_ABORTED_CX:
case CMD_CREATE_XRI_CR: /* Do we expect to use this? */
case CMD_IOCB_FCP_IBIDIR64_CR: /* bidirectional xfer */
struct fc_frame_header *fc_hdr;
struct lpfc_queue *hrq = phba->sli4_hba.hdr_rq;
struct lpfc_queue *drq = phba->sli4_hba.dat_rq;
+ struct lpfc_nvmet_tgtport *tgtp;
struct hbq_dmabuf *dma_buf;
uint32_t status, rq_id;
unsigned long iflags;
case FC_STATUS_RQ_BUF_LEN_EXCEEDED:
lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
"2537 Receive Frame Truncated!!\n");
- hrq->RQ_buf_trunc++;
case FC_STATUS_RQ_SUCCESS:
lpfc_sli4_rq_release(hrq, drq);
spin_lock_irqsave(&phba->hbalock, iflags);
goto out;
}
hrq->RQ_rcv_buf++;
+ hrq->RQ_buf_posted--;
memcpy(&dma_buf->cq_event.cqe.rcqe_cmpl, rcqe, sizeof(*rcqe));
/* If a NVME LS event (type 0x28), treat it as Fast path */
spin_unlock_irqrestore(&phba->hbalock, iflags);
workposted = true;
break;
- case FC_STATUS_INSUFF_BUF_NEED_BUF:
case FC_STATUS_INSUFF_BUF_FRM_DISC:
+ if (phba->nvmet_support) {
+ tgtp = phba->targetport->private;
+ lpfc_printf_log(phba, KERN_ERR, LOG_SLI | LOG_NVME,
+ "6402 RQE Error x%x, posted %d err_cnt "
+ "%d: %x %x %x\n",
+ status, hrq->RQ_buf_posted,
+ hrq->RQ_no_posted_buf,
+ atomic_read(&tgtp->rcv_fcp_cmd_in),
+ atomic_read(&tgtp->rcv_fcp_cmd_out),
+ atomic_read(&tgtp->xmt_fcp_release));
+ }
+ /* fallthrough */
+
+ case FC_STATUS_INSUFF_BUF_NEED_BUF:
hrq->RQ_no_posted_buf++;
/* Post more buffers if possible */
spin_lock_irqsave(&phba->hbalock, iflags);
while ((cqe = lpfc_sli4_cq_get(cq))) {
workposted |= lpfc_sli4_sp_handle_mcqe(phba, cqe);
if (!(++ecount % cq->entry_repost))
- lpfc_sli4_cq_release(cq, LPFC_QUEUE_NOARM);
+ break;
cq->CQ_mbox++;
}
break;
workposted |= lpfc_sli4_sp_handle_cqe(phba, cq,
cqe);
if (!(++ecount % cq->entry_repost))
- lpfc_sli4_cq_release(cq, LPFC_QUEUE_NOARM);
+ break;
}
/* Track the max number of CQEs processed in 1 EQ */
struct lpfc_queue *drq;
struct rqb_dmabuf *dma_buf;
struct fc_frame_header *fc_hdr;
+ struct lpfc_nvmet_tgtport *tgtp;
uint32_t status, rq_id;
unsigned long iflags;
uint32_t fctl, idx;
case FC_STATUS_RQ_BUF_LEN_EXCEEDED:
lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
"6126 Receive Frame Truncated!!\n");
- hrq->RQ_buf_trunc++;
- break;
case FC_STATUS_RQ_SUCCESS:
lpfc_sli4_rq_release(hrq, drq);
spin_lock_irqsave(&phba->hbalock, iflags);
}
spin_unlock_irqrestore(&phba->hbalock, iflags);
hrq->RQ_rcv_buf++;
+ hrq->RQ_buf_posted--;
fc_hdr = (struct fc_frame_header *)dma_buf->hbuf.virt;
/* Just some basic sanity checks on FCP Command frame */
drop:
lpfc_in_buf_free(phba, &dma_buf->dbuf);
break;
- case FC_STATUS_INSUFF_BUF_NEED_BUF:
case FC_STATUS_INSUFF_BUF_FRM_DISC:
+ if (phba->nvmet_support) {
+ tgtp = phba->targetport->private;
+ lpfc_printf_log(phba, KERN_ERR, LOG_SLI | LOG_NVME,
+ "6401 RQE Error x%x, posted %d err_cnt "
+ "%d: %x %x %x\n",
+ status, hrq->RQ_buf_posted,
+ hrq->RQ_no_posted_buf,
+ atomic_read(&tgtp->rcv_fcp_cmd_in),
+ atomic_read(&tgtp->rcv_fcp_cmd_out),
+ atomic_read(&tgtp->xmt_fcp_release));
+ }
+ /* fallthrough */
+
+ case FC_STATUS_INSUFF_BUF_NEED_BUF:
hrq->RQ_no_posted_buf++;
/* Post more buffers if possible */
- spin_lock_irqsave(&phba->hbalock, iflags);
- phba->hba_flag |= HBA_POST_RECEIVE_BUFFER;
- spin_unlock_irqrestore(&phba->hbalock, iflags);
- workposted = true;
break;
}
out:
while ((cqe = lpfc_sli4_cq_get(cq))) {
workposted |= lpfc_sli4_fp_handle_cqe(phba, cq, cqe);
if (!(++ecount % cq->entry_repost))
- lpfc_sli4_cq_release(cq, LPFC_QUEUE_NOARM);
+ break;
}
/* Track the max number of CQEs processed in 1 EQ */
while ((cqe = lpfc_sli4_cq_get(cq))) {
workposted |= lpfc_sli4_fp_handle_cqe(phba, cq, cqe);
if (!(++ecount % cq->entry_repost))
- lpfc_sli4_cq_release(cq, LPFC_QUEUE_NOARM);
+ break;
}
/* Track the max number of CQEs processed in 1 EQ */
while ((eqe = lpfc_sli4_eq_get(eq))) {
lpfc_sli4_fof_handle_eqe(phba, eqe);
if (!(++ecount % eq->entry_repost))
- lpfc_sli4_eq_release(eq, LPFC_QUEUE_NOARM);
+ break;
eq->EQ_processed++;
}
lpfc_sli4_hba_handle_eqe(phba, eqe, hba_eqidx);
if (!(++ecount % fpeq->entry_repost))
- lpfc_sli4_eq_release(fpeq, LPFC_QUEUE_NOARM);
+ break;
fpeq->EQ_processed++;
}
}
queue->entry_size = entry_size;
queue->entry_count = entry_count;
-
- /*
- * entry_repost is calculated based on the number of entries in the
- * queue. This works out except for RQs. If buffers are NOT initially
- * posted for every RQE, entry_repost should be adjusted accordingly.
- */
- queue->entry_repost = (entry_count >> 3);
- if (queue->entry_repost < LPFC_QUEUE_MIN_REPOST)
- queue->entry_repost = LPFC_QUEUE_MIN_REPOST;
queue->phba = phba;
+ /* entry_repost will be set during q creation */
+
return queue;
out_fail:
lpfc_sli4_queue_free(queue);
status = -ENXIO;
eq->host_index = 0;
eq->hba_index = 0;
+ eq->entry_repost = LPFC_EQ_REPOST;
mempool_free(mbox, phba->mbox_mem_pool);
return status;
default:
lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
"0361 Unsupported CQ count: "
- "entry cnt %d sz %d pg cnt %d repost %d\n",
+ "entry cnt %d sz %d pg cnt %d\n",
cq->entry_count, cq->entry_size,
- cq->page_count, cq->entry_repost);
+ cq->page_count);
if (cq->entry_count < 256) {
status = -EINVAL;
goto out;
cq->assoc_qid = eq->queue_id;
cq->host_index = 0;
cq->hba_index = 0;
+ cq->entry_repost = LPFC_CQ_REPOST;
out:
mempool_free(mbox, phba->mbox_mem_pool);
cq->assoc_qid = eq->queue_id;
cq->host_index = 0;
cq->hba_index = 0;
+ cq->entry_repost = LPFC_CQ_REPOST;
rc = 0;
list_for_each_entry(dmabuf, &cq->page_list, list) {
mq->subtype = subtype;
mq->host_index = 0;
mq->hba_index = 0;
+ mq->entry_repost = LPFC_MQ_REPOST;
/* link the mq onto the parent cq child list */
list_add_tail(&mq->list, &cq->child_list);
return status;
}
-/**
- * lpfc_rq_adjust_repost - Adjust entry_repost for an RQ
- * @phba: HBA structure that indicates port to create a queue on.
- * @rq: The queue structure to use for the receive queue.
- * @qno: The associated HBQ number
- *
- *
- * For SLI4 we need to adjust the RQ repost value based on
- * the number of buffers that are initially posted to the RQ.
- */
-void
-lpfc_rq_adjust_repost(struct lpfc_hba *phba, struct lpfc_queue *rq, int qno)
-{
- uint32_t cnt;
-
- /* sanity check on queue memory */
- if (!rq)
- return;
- cnt = lpfc_hbq_defs[qno]->entry_count;
-
- /* Recalc repost for RQs based on buffers initially posted */
- cnt = (cnt >> 3);
- if (cnt < LPFC_QUEUE_MIN_REPOST)
- cnt = LPFC_QUEUE_MIN_REPOST;
-
- rq->entry_repost = cnt;
-}
-
/**
* lpfc_rq_create - Create a Receive Queue on the HBA
* @phba: HBA structure that indicates port to create a queue on.
hrq->subtype = subtype;
hrq->host_index = 0;
hrq->hba_index = 0;
+ hrq->entry_repost = LPFC_RQ_REPOST;
/* now create the data queue */
lpfc_sli4_config(phba, mbox, LPFC_MBOX_SUBSYSTEM_FCOE,
if (phba->sli4_hba.pc_sli4_params.rqv == LPFC_Q_CREATE_VERSION_1) {
bf_set(lpfc_rq_context_rqe_count_1,
&rq_create->u.request.context, hrq->entry_count);
- rq_create->u.request.context.buffer_size = LPFC_DATA_BUF_SIZE;
+ if (subtype == LPFC_NVMET)
+ rq_create->u.request.context.buffer_size =
+ LPFC_NVMET_DATA_BUF_SIZE;
+ else
+ rq_create->u.request.context.buffer_size =
+ LPFC_DATA_BUF_SIZE;
bf_set(lpfc_rq_context_rqe_size, &rq_create->u.request.context,
LPFC_RQE_SIZE_8);
bf_set(lpfc_rq_context_page_size, &rq_create->u.request.context,
LPFC_RQ_RING_SIZE_4096);
break;
}
- bf_set(lpfc_rq_context_buf_size, &rq_create->u.request.context,
- LPFC_DATA_BUF_SIZE);
+ if (subtype == LPFC_NVMET)
+ bf_set(lpfc_rq_context_buf_size,
+ &rq_create->u.request.context,
+ LPFC_NVMET_DATA_BUF_SIZE);
+ else
+ bf_set(lpfc_rq_context_buf_size,
+ &rq_create->u.request.context,
+ LPFC_DATA_BUF_SIZE);
}
bf_set(lpfc_rq_context_cq_id, &rq_create->u.request.context,
cq->queue_id);
drq->subtype = subtype;
drq->host_index = 0;
drq->hba_index = 0;
+ drq->entry_repost = LPFC_RQ_REPOST;
/* link the header and data RQs onto the parent cq child list */
list_add_tail(&hrq->list, &cq->child_list);
cq->queue_id);
bf_set(lpfc_rq_context_data_size,
&rq_create->u.request.context,
- LPFC_DATA_BUF_SIZE);
+ LPFC_NVMET_DATA_BUF_SIZE);
bf_set(lpfc_rq_context_hdr_size,
&rq_create->u.request.context,
LPFC_HDR_BUF_SIZE);
hrq->subtype = subtype;
hrq->host_index = 0;
hrq->hba_index = 0;
+ hrq->entry_repost = LPFC_RQ_REPOST;
drq->db_format = LPFC_DB_RING_FORMAT;
drq->db_regaddr = phba->sli4_hba.RQDBregaddr;
drq->subtype = subtype;
drq->host_index = 0;
drq->hba_index = 0;
+ drq->entry_repost = LPFC_RQ_REPOST;
list_add_tail(&hrq->list, &cq->child_list);
list_add_tail(&drq->list, &cq->child_list);
struct fc_vft_header *fc_vft_hdr;
uint32_t *header = (uint32_t *) fc_hdr;
+#define FC_RCTL_MDS_DIAGS 0xF4
+
switch (fc_hdr->fh_r_ctl) {
case FC_RCTL_DD_UNCAT: /* uncategorized information */
case FC_RCTL_DD_SOL_DATA: /* solicited data */
case FC_RCTL_F_BSY: /* fabric busy to data frame */
case FC_RCTL_F_BSYL: /* fabric busy to link control frame */
case FC_RCTL_LCR: /* link credit reset */
+ case FC_RCTL_MDS_DIAGS: /* MDS Diagnostics */
case FC_RCTL_END: /* end */
break;
case FC_RCTL_VFTH: /* Virtual Fabric tagging Header */
default:
goto drop;
}
+
+#define FC_TYPE_VENDOR_UNIQUE 0xFF
+
switch (fc_hdr->fh_type) {
case FC_TYPE_BLS:
case FC_TYPE_ELS:
case FC_TYPE_FCP:
case FC_TYPE_CT:
case FC_TYPE_NVME:
+ case FC_TYPE_VENDOR_UNIQUE:
break;
case FC_TYPE_IP:
case FC_TYPE_ILS:
lpfc_printf_log(phba, KERN_INFO, LOG_ELS,
"2538 Received frame rctl:%s (x%x), type:%s (x%x), "
"frame Data:%08x %08x %08x %08x %08x %08x %08x\n",
+ (fc_hdr->fh_r_ctl == FC_RCTL_MDS_DIAGS) ? "MDS Diags" :
lpfc_rctl_names[fc_hdr->fh_r_ctl], fc_hdr->fh_r_ctl,
- lpfc_type_names[fc_hdr->fh_type], fc_hdr->fh_type,
- be32_to_cpu(header[0]), be32_to_cpu(header[1]),
- be32_to_cpu(header[2]), be32_to_cpu(header[3]),
- be32_to_cpu(header[4]), be32_to_cpu(header[5]),
- be32_to_cpu(header[6]));
+ (fc_hdr->fh_type == FC_TYPE_VENDOR_UNIQUE) ?
+ "Vendor Unique" : lpfc_type_names[fc_hdr->fh_type],
+ fc_hdr->fh_type, be32_to_cpu(header[0]),
+ be32_to_cpu(header[1]), be32_to_cpu(header[2]),
+ be32_to_cpu(header[3]), be32_to_cpu(header[4]),
+ be32_to_cpu(header[5]), be32_to_cpu(header[6]));
return 0;
drop:
lpfc_printf_log(phba, KERN_WARNING, LOG_ELS,
lpfc_sli_release_iocbq(phba, iocbq);
}
+static void
+lpfc_sli4_mds_loopback_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
+ struct lpfc_iocbq *rspiocb)
+{
+ struct lpfc_dmabuf *pcmd = cmdiocb->context2;
+
+ if (pcmd && pcmd->virt)
+ pci_pool_free(phba->lpfc_drb_pool, pcmd->virt, pcmd->phys);
+ kfree(pcmd);
+ lpfc_sli_release_iocbq(phba, cmdiocb);
+}
+
+static void
+lpfc_sli4_handle_mds_loopback(struct lpfc_vport *vport,
+ struct hbq_dmabuf *dmabuf)
+{
+ struct fc_frame_header *fc_hdr;
+ struct lpfc_hba *phba = vport->phba;
+ struct lpfc_iocbq *iocbq = NULL;
+ union lpfc_wqe *wqe;
+ struct lpfc_dmabuf *pcmd = NULL;
+ uint32_t frame_len;
+ int rc;
+
+ fc_hdr = (struct fc_frame_header *)dmabuf->hbuf.virt;
+ frame_len = bf_get(lpfc_rcqe_length, &dmabuf->cq_event.cqe.rcqe_cmpl);
+
+ /* Send the received frame back */
+ iocbq = lpfc_sli_get_iocbq(phba);
+ if (!iocbq)
+ goto exit;
+
+ /* Allocate buffer for command payload */
+ pcmd = kmalloc(sizeof(struct lpfc_dmabuf), GFP_KERNEL);
+ if (pcmd)
+ pcmd->virt = pci_pool_alloc(phba->lpfc_drb_pool, GFP_KERNEL,
+ &pcmd->phys);
+ if (!pcmd || !pcmd->virt)
+ goto exit;
+
+ INIT_LIST_HEAD(&pcmd->list);
+
+ /* copyin the payload */
+ memcpy(pcmd->virt, dmabuf->dbuf.virt, frame_len);
+
+ /* fill in BDE's for command */
+ iocbq->iocb.un.xseq64.bdl.addrHigh = putPaddrHigh(pcmd->phys);
+ iocbq->iocb.un.xseq64.bdl.addrLow = putPaddrLow(pcmd->phys);
+ iocbq->iocb.un.xseq64.bdl.bdeFlags = BUFF_TYPE_BDE_64;
+ iocbq->iocb.un.xseq64.bdl.bdeSize = frame_len;
+
+ iocbq->context2 = pcmd;
+ iocbq->vport = vport;
+ iocbq->iocb_flag &= ~LPFC_FIP_ELS_ID_MASK;
+ iocbq->iocb_flag |= LPFC_USE_FCPWQIDX;
+
+ /*
+ * Setup rest of the iocb as though it were a WQE
+ * Build the SEND_FRAME WQE
+ */
+ wqe = (union lpfc_wqe *)&iocbq->iocb;
+
+ wqe->send_frame.frame_len = frame_len;
+ wqe->send_frame.fc_hdr_wd0 = be32_to_cpu(*((uint32_t *)fc_hdr));
+ wqe->send_frame.fc_hdr_wd1 = be32_to_cpu(*((uint32_t *)fc_hdr + 1));
+ wqe->send_frame.fc_hdr_wd2 = be32_to_cpu(*((uint32_t *)fc_hdr + 2));
+ wqe->send_frame.fc_hdr_wd3 = be32_to_cpu(*((uint32_t *)fc_hdr + 3));
+ wqe->send_frame.fc_hdr_wd4 = be32_to_cpu(*((uint32_t *)fc_hdr + 4));
+ wqe->send_frame.fc_hdr_wd5 = be32_to_cpu(*((uint32_t *)fc_hdr + 5));
+
+ iocbq->iocb.ulpCommand = CMD_SEND_FRAME;
+ iocbq->iocb.ulpLe = 1;
+ iocbq->iocb_cmpl = lpfc_sli4_mds_loopback_cmpl;
+ rc = lpfc_sli_issue_iocb(phba, LPFC_ELS_RING, iocbq, 0);
+ if (rc == IOCB_ERROR)
+ goto exit;
+
+ lpfc_in_buf_free(phba, &dmabuf->dbuf);
+ return;
+
+exit:
+ lpfc_printf_log(phba, KERN_WARNING, LOG_SLI,
+ "2023 Unable to process MDS loopback frame\n");
+ if (pcmd && pcmd->virt)
+ pci_pool_free(phba->lpfc_drb_pool, pcmd->virt, pcmd->phys);
+ kfree(pcmd);
+ lpfc_sli_release_iocbq(phba, iocbq);
+ lpfc_in_buf_free(phba, &dmabuf->dbuf);
+}
+
/**
* lpfc_sli4_handle_received_buffer - Handle received buffers from firmware
* @phba: Pointer to HBA context object.
fcfi = bf_get(lpfc_rcqe_fcf_id,
&dmabuf->cq_event.cqe.rcqe_cmpl);
+ if (fc_hdr->fh_r_ctl == 0xF4 && fc_hdr->fh_type == 0xFF) {
+ vport = phba->pport;
+ /* Handle MDS Loopback frames */
+ lpfc_sli4_handle_mds_loopback(vport, dmabuf);
+ return;
+ }
+
/* d_id this frame is directed to */
did = sli4_did_from_fc_hdr(fc_hdr);
"status x%x add_status x%x, mbx status x%x\n",
shdr_status, shdr_add_status, rc);
rc = -ENXIO;
+ } else {
+ /*
+ * The next_rpi stores the next logical module-64 rpi value used
+ * to post physical rpis in subsequent rpi postings.
+ */
+ spin_lock_irq(&phba->hbalock);
+ phba->sli4_hba.next_rpi = rpi_page->next_rpi;
+ spin_unlock_irq(&phba->hbalock);
}
return rc;
}
spin_lock_irqsave(&pring->ring_lock, iflags);
ctxp = pwqe->context2;
- sglq = ctxp->rqb_buffer->sglq;
+ sglq = ctxp->ctxbuf->sglq;
if (pwqe->sli4_xritag == NO_XRI) {
pwqe->sli4_lxritag = sglq->sli4_lxritag;
pwqe->sli4_xritag = sglq->sli4_xritag;
#define LPFC_XRI_EXCH_BUSY_WAIT_TMO 10000
#define LPFC_XRI_EXCH_BUSY_WAIT_T1 10
#define LPFC_XRI_EXCH_BUSY_WAIT_T2 30000
-#define LPFC_RELEASE_NOTIFICATION_INTERVAL 32
#define LPFC_RPI_LOW_WATER_MARK 10
#define LPFC_UNREG_FCF 1
uint32_t entry_count; /* Number of entries to support on the queue */
uint32_t entry_size; /* Size of each queue entry. */
uint32_t entry_repost; /* Count of entries before doorbell is rung */
-#define LPFC_QUEUE_MIN_REPOST 8
+#define LPFC_EQ_REPOST 8
+#define LPFC_MQ_REPOST 8
+#define LPFC_CQ_REPOST 64
+#define LPFC_RQ_REPOST 64
+#define LPFC_RELEASE_NOTIFICATION_INTERVAL 32 /* For WQs */
uint32_t queue_id; /* Queue ID assigned by the hardware */
uint32_t assoc_qid; /* Queue ID associated with, for CQ/WQ/MQ */
uint32_t page_count; /* Number of pages allocated for this queue */
/* defines for RQ stats */
#define RQ_no_posted_buf q_cnt_1
#define RQ_no_buf_found q_cnt_2
-#define RQ_buf_trunc q_cnt_3
+#define RQ_buf_posted q_cnt_3
#define RQ_rcv_buf q_cnt_4
uint64_t isr_timestamp;
uint16_t scsi_xri_start;
uint16_t els_xri_cnt;
uint16_t nvmet_xri_cnt;
+ uint16_t nvmet_ctx_cnt;
+ uint16_t nvmet_io_wait_cnt;
+ uint16_t nvmet_io_wait_total;
struct list_head lpfc_els_sgl_list;
struct list_head lpfc_abts_els_sgl_list;
struct list_head lpfc_nvmet_sgl_list;
struct list_head lpfc_abts_nvmet_ctx_list;
struct list_head lpfc_abts_scsi_buf_list;
struct list_head lpfc_abts_nvme_buf_list;
+ struct list_head lpfc_nvmet_ctx_list;
+ struct list_head lpfc_nvmet_io_wait_list;
struct lpfc_sglq **lpfc_sglq_active_list;
struct list_head lpfc_rpi_hdr_list;
unsigned long *rpi_bmask;
spinlock_t abts_scsi_buf_list_lock; /* list of aborted SCSI IOs */
spinlock_t sgl_list_lock; /* list of aborted els IOs */
spinlock_t nvmet_io_lock;
+ spinlock_t nvmet_io_wait_lock; /* IOs waiting for ctx resources */
uint32_t physical_port;
/* CPU to vector mapping information */
uint16_t num_online_cpu;
uint16_t num_present_cpu;
uint16_t curr_disp_cpu;
-
- uint16_t nvmet_mrq_post_idx;
};
enum lpfc_sge_type {
struct lpfc_dmabuf *dmabuf;
uint32_t page_count;
uint32_t start_rpi;
+ uint16_t next_rpi;
};
struct lpfc_rsrc_blks {
int lpfc_mrq_create(struct lpfc_hba *phba, struct lpfc_queue **hrqp,
struct lpfc_queue **drqp, struct lpfc_queue **cqp,
uint32_t subtype);
-void lpfc_rq_adjust_repost(struct lpfc_hba *, struct lpfc_queue *, int);
int lpfc_eq_destroy(struct lpfc_hba *, struct lpfc_queue *);
int lpfc_cq_destroy(struct lpfc_hba *, struct lpfc_queue *);
int lpfc_mq_destroy(struct lpfc_hba *, struct lpfc_queue *);
* included with this package. *
*******************************************************************/
-#define LPFC_DRIVER_VERSION "11.2.0.12"
+#define LPFC_DRIVER_VERSION "11.2.0.14"
#define LPFC_DRIVER_NAME "lpfc"
/* Used for SLI 2/3 */
pmcraid_err("couldn't build passthrough ioadls\n");
goto out_free_cmd;
}
- } else if (request_size < 0) {
- rc = -EINVAL;
- goto out_free_cmd;
}
/* If data is being written into the device, copy the data from user
uint16_t task_id;
uint32_t port_id; /* Remote port fabric ID */
int lun;
- char op; /* SCSI CDB */
+ unsigned char op; /* SCSI CDB */
uint8_t lba[4];
unsigned int bufflen; /* SCSI buffer length */
unsigned int sg_count; /* Number of SG elements */
did = fcport->rdata->ids.port_id;
sid = fcport->sid;
- __fc_fill_fc_hdr(fc_hdr, FC_RCTL_ELS_REQ, sid, did,
+ __fc_fill_fc_hdr(fc_hdr, FC_RCTL_ELS_REQ, did, sid,
FC_TYPE_ELS, FC_FC_FIRST_SEQ | FC_FC_END_SEQ |
FC_FC_SEQ_INIT, 0);
slowpath_params.drv_minor = QEDF_DRIVER_MINOR_VER;
slowpath_params.drv_rev = QEDF_DRIVER_REV_VER;
slowpath_params.drv_eng = QEDF_DRIVER_ENG_VER;
- memcpy(slowpath_params.name, "qedf", QED_DRV_VER_STR_SIZE);
+ strncpy(slowpath_params.name, "qedf", QED_DRV_VER_STR_SIZE);
rc = qed_ops->common->slowpath_start(qedf->cdev, &slowpath_params);
if (rc) {
QEDF_ERR(&(qedf->dbg_ctx), "Cannot start slowpath.\n");
#define QEDI_MAX_ISCSI_TASK 4096
#define QEDI_MAX_TASK_NUM 0x0FFF
#define QEDI_MAX_ISCSI_CONNS_PER_HBA 1024
-#define QEDI_ISCSI_MAX_BDS_PER_CMD 256 /* Firmware max BDs is 256 */
+#define QEDI_ISCSI_MAX_BDS_PER_CMD 255 /* Firmware max BDs is 255 */
#define MAX_OUSTANDING_TASKS_PER_CON 1024
#define QEDI_MAX_BD_LEN 0xffff
#define QEDI_PAGE_MASK (~((QEDI_PAGE_SIZE) - 1))
#define QEDI_PAGE_SIZE 4096
+#define QEDI_HW_DMA_BOUNDARY 0xfff
#define QEDI_PATH_HANDLE 0xFE0000000UL
struct qedi_uio_ctrl {
tmf_hdr = (struct iscsi_tm *)mtask->hdr;
qedi_cmd = (struct qedi_cmd *)mtask->dd_data;
ep = qedi_conn->ep;
+ if (!ep)
+ return -ENODEV;
tid = qedi_get_task_idx(qedi);
if (tid == -1)
.this_id = -1,
.sg_tablesize = QEDI_ISCSI_MAX_BDS_PER_CMD,
.max_sectors = 0xffff,
+ .dma_boundary = QEDI_HW_DMA_BOUNDARY,
.cmd_per_lun = 128,
.use_clustering = ENABLE_CLUSTERING,
.shost_attrs = qedi_shost_attrs,
iscsi_cid = (u32)path_data->handle;
qedi_ep = qedi->ep_tbl[iscsi_cid];
- QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+ QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
"iscsi_cid=0x%x, qedi_ep=%p\n", iscsi_cid, qedi_ep);
+ if (!qedi_ep) {
+ ret = -EINVAL;
+ goto set_path_exit;
+ }
if (!is_valid_ether_addr(&path_data->mac_addr[0])) {
QEDI_NOTICE(&qedi->dbg_ctx, "dst mac NOT VALID\n");
static void __qedi_free_uio_rings(struct qedi_uio_dev *udev)
{
+ if (udev->uctrl) {
+ free_page((unsigned long)udev->uctrl);
+ udev->uctrl = NULL;
+ }
+
if (udev->ll2_ring) {
free_page((unsigned long)udev->ll2_ring);
udev->ll2_ring = NULL;
__qedi_free_uio_rings(udev);
pci_dev_put(udev->pdev);
- kfree(udev->uctrl);
kfree(udev);
}
if (udev->ll2_ring || udev->ll2_buf)
return rc;
+ /* Memory for control area. */
+ udev->uctrl = (void *)get_zeroed_page(GFP_KERNEL);
+ if (!udev->uctrl)
+ return -ENOMEM;
+
/* Allocating memory for LL2 ring */
udev->ll2_ring_size = QEDI_PAGE_SIZE;
udev->ll2_ring = (void *)get_zeroed_page(GFP_KERNEL | __GFP_COMP);
static int qedi_alloc_uio_rings(struct qedi_ctx *qedi)
{
struct qedi_uio_dev *udev = NULL;
- struct qedi_uio_ctrl *uctrl = NULL;
int rc = 0;
list_for_each_entry(udev, &qedi_udev_list, list) {
goto err_udev;
}
- uctrl = kzalloc(sizeof(*uctrl), GFP_KERNEL);
- if (!uctrl) {
- rc = -ENOMEM;
- goto err_uctrl;
- }
-
udev->uio_dev = -1;
udev->qedi = qedi;
udev->pdev = qedi->pdev;
- udev->uctrl = uctrl;
rc = __qedi_alloc_uio_rings(udev);
if (rc)
- goto err_uio_rings;
+ goto err_uctrl;
list_add(&udev->list, &qedi_udev_list);
udev->rx_pkt = udev->ll2_buf + LL2_SINGLE_BUF_SIZE;
return 0;
- err_uio_rings:
- kfree(uctrl);
err_uctrl:
kfree(udev);
err_udev:
qedi->pf_params.iscsi_pf_params.num_uhq_pages_in_ring = num_sq_pages;
qedi->pf_params.iscsi_pf_params.num_queues = qedi->num_queues;
qedi->pf_params.iscsi_pf_params.debug_mode = qedi_fw_debug;
+ qedi->pf_params.iscsi_pf_params.two_msl_timer = 4000;
+ qedi->pf_params.iscsi_pf_params.max_fin_rt = 2;
for (log_page_size = 0 ; log_page_size < 32 ; log_page_size++) {
if ((1 << log_page_size) == PAGE_SIZE)
return -EIO;
}
+ memset(&elreq, 0, sizeof(elreq));
+
elreq.req_sg_cnt = dma_map_sg(&ha->pdev->dev,
bsg_job->request_payload.sg_list, bsg_job->request_payload.sg_cnt,
DMA_TO_DEVICE);
if (atomic_read(&vha->loop_state) == LOOP_READY &&
(ha->current_topology == ISP_CFG_F ||
- ((IS_QLA81XX(ha) || IS_QLA8031(ha) || IS_QLA8044(ha)) &&
- le32_to_cpu(*(uint32_t *)req_data) == ELS_OPCODE_BYTE
- && req_data_len == MAX_ELS_FRAME_PAYLOAD)) &&
- elreq.options == EXTERNAL_LOOPBACK) {
+ (le32_to_cpu(*(uint32_t *)req_data) == ELS_OPCODE_BYTE &&
+ req_data_len == MAX_ELS_FRAME_PAYLOAD)) &&
+ elreq.options == EXTERNAL_LOOPBACK) {
type = "FC_BSG_HST_VENDOR_ECHO_DIAG";
ql_dbg(ql_dbg_user, vha, 0x701e,
"BSG request type: %s.\n", type);
/* Mailbox registers. */
mbx_reg = ®->mailbox0;
- for (cnt = 0; cnt < sizeof(fw->mailbox_reg) / 2; cnt++, dmp_reg++)
+ for (cnt = 0; cnt < sizeof(fw->mailbox_reg) / 2; cnt++, mbx_reg++)
fw->mailbox_reg[cnt] = htons(RD_REG_WORD(mbx_reg));
/* Transfer sequence registers. */
/* Mailbox registers. */
mbx_reg = ®->mailbox0;
- for (cnt = 0; cnt < sizeof(fw->mailbox_reg) / 2; cnt++, dmp_reg++)
+ for (cnt = 0; cnt < sizeof(fw->mailbox_reg) / 2; cnt++, mbx_reg++)
fw->mailbox_reg[cnt] = htons(RD_REG_WORD(mbx_reg));
/* Transfer sequence registers. */
uint8_t max_req_queues;
uint8_t max_rsp_queues;
uint8_t max_qpairs;
+ uint8_t num_qpairs;
struct qla_qpair *base_qpair;
struct qla_npiv_entry *npiv_info;
uint16_t nvram_npiv_size;
/* Assign available que pair id */
mutex_lock(&ha->mq_lock);
qpair_id = find_first_zero_bit(ha->qpair_qid_map, ha->max_qpairs);
- if (qpair_id >= ha->max_qpairs) {
+ if (ha->num_qpairs >= ha->max_qpairs) {
mutex_unlock(&ha->mq_lock);
ql_log(ql_log_warn, vha, 0x0183,
"No resources to create additional q pair.\n");
goto fail_qid_map;
}
+ ha->num_qpairs++;
set_bit(qpair_id, ha->qpair_qid_map);
ha->queue_pair_map[qpair_id] = qpair;
qpair->id = qpair_id;
fail_msix:
ha->queue_pair_map[qpair_id] = NULL;
clear_bit(qpair_id, ha->qpair_qid_map);
+ ha->num_qpairs--;
mutex_unlock(&ha->mq_lock);
fail_qid_map:
kfree(qpair);
mutex_lock(&ha->mq_lock);
ha->queue_pair_map[qpair->id] = NULL;
clear_bit(qpair->id, ha->qpair_qid_map);
+ ha->num_qpairs--;
list_del(&qpair->qp_list_elem);
if (list_empty(&vha->qp_list))
vha->flags.qpairs_available = 0;
}
static inline void
-qla2x00_clean_dsd_pool(struct qla_hw_data *ha, srb_t *sp,
- struct qla_tgt_cmd *tc)
+qla2x00_clean_dsd_pool(struct qla_hw_data *ha, struct crc_context *ctx)
{
- struct dsd_dma *dsd_ptr, *tdsd_ptr;
- struct crc_context *ctx;
-
- if (sp)
- ctx = (struct crc_context *)GET_CMD_CTX_SP(sp);
- else if (tc)
- ctx = (struct crc_context *)tc->ctx;
- else {
- BUG();
- return;
- }
+ struct dsd_dma *dsd, *tdsd;
/* clean up allocated prev pool */
- list_for_each_entry_safe(dsd_ptr, tdsd_ptr,
- &ctx->dsd_list, list) {
- dma_pool_free(ha->dl_dma_pool, dsd_ptr->dsd_addr,
- dsd_ptr->dsd_list_dma);
- list_del(&dsd_ptr->list);
- kfree(dsd_ptr);
+ list_for_each_entry_safe(dsd, tdsd, &ctx->dsd_list, list) {
+ dma_pool_free(ha->dl_dma_pool, dsd->dsd_addr,
+ dsd->dsd_list_dma);
+ list_del(&dsd->list);
+ kfree(dsd);
}
INIT_LIST_HEAD(&ctx->dsd_list);
}
}
/* Enable MSI-X vector for response queue update for queue 0 */
- if (IS_QLA83XX(ha) || IS_QLA27XX(ha)) {
+ if (IS_QLA25XX(ha) || IS_QLA83XX(ha) || IS_QLA27XX(ha)) {
if (ha->msixbase && ha->mqiobase &&
(ha->max_rsp_queues > 1 || ha->max_req_queues > 1 ||
ql2xmqsupport))
qlt_update_host_map(vha, id);
}
- fc_host_port_name(vha->host) =
- wwn_to_u64(vha->port_name);
-
- if (qla_ini_mode_enabled(vha))
- ql_dbg(ql_dbg_mbx, vha, 0x1018,
- "FA-WWN portname %016llx (%x)\n",
- fc_host_port_name(vha->host),
- rptid_entry->vp_status);
-
set_bit(REGISTER_FC4_NEEDED, &vha->dpc_flags);
set_bit(REGISTER_FDMI_NEEDED, &vha->dpc_flags);
} else {
memset(mcp->mb, 0 , sizeof(mcp->mb));
mcp->mb[0] = MBC_DIAGNOSTIC_ECHO;
- mcp->mb[1] = mreq->options | BIT_6; /* BIT_6 specifies 64bit address */
+ /* BIT_6 specifies 64bit address */
+ mcp->mb[1] = mreq->options | BIT_15 | BIT_6;
if (IS_CNA_CAPABLE(ha)) {
- mcp->mb[1] |= BIT_15;
mcp->mb[2] = vha->fcoe_fcf_idx;
}
mcp->mb[16] = LSW(mreq->rcv_dma);
sp->flags &= ~SRB_CRC_PROT_DMA_VALID;
}
+ if (!ctx)
+ goto end;
+
if (sp->flags & SRB_CRC_CTX_DSD_VALID) {
/* List assured to be having elements */
- qla2x00_clean_dsd_pool(ha, sp, NULL);
+ qla2x00_clean_dsd_pool(ha, ctx);
sp->flags &= ~SRB_CRC_CTX_DSD_VALID;
}
if (sp->flags & SRB_CRC_CTX_DMA_VALID) {
- dma_pool_free(ha->dl_dma_pool, ctx,
- ((struct crc_context *)ctx)->crc_ctx_dma);
+ struct crc_context *ctx0 = ctx;
+
+ dma_pool_free(ha->dl_dma_pool, ctx0, ctx0->crc_ctx_dma);
sp->flags &= ~SRB_CRC_CTX_DMA_VALID;
}
if (sp->flags & SRB_FCP_CMND_DMA_VALID) {
- struct ct6_dsd *ctx1 = (struct ct6_dsd *)ctx;
+ struct ct6_dsd *ctx1 = ctx;
dma_pool_free(ha->fcp_cmnd_dma_pool, ctx1->fcp_cmnd,
- ctx1->fcp_cmnd_dma);
+ ctx1->fcp_cmnd_dma);
list_splice(&ctx1->dsd_list, &ha->gbl_dsd_list);
ha->gbl_dsd_inuse -= ctx1->dsd_use_cnt;
ha->gbl_dsd_avail += ctx1->dsd_use_cnt;
mempool_free(ctx1, ha->ctx_mempool);
}
+end:
CMD_SP(cmd) = NULL;
qla2x00_rel_sp(sp);
}
sp->flags &= ~SRB_CRC_PROT_DMA_VALID;
}
+ if (!ctx)
+ goto end;
+
if (sp->flags & SRB_CRC_CTX_DSD_VALID) {
/* List assured to be having elements */
- qla2x00_clean_dsd_pool(ha, sp, NULL);
+ qla2x00_clean_dsd_pool(ha, ctx);
sp->flags &= ~SRB_CRC_CTX_DSD_VALID;
}
if (sp->flags & SRB_CRC_CTX_DMA_VALID) {
- dma_pool_free(ha->dl_dma_pool, ctx,
- ((struct crc_context *)ctx)->crc_ctx_dma);
+ struct crc_context *ctx0 = ctx;
+
+ dma_pool_free(ha->dl_dma_pool, ctx, ctx0->crc_ctx_dma);
sp->flags &= ~SRB_CRC_CTX_DMA_VALID;
}
if (sp->flags & SRB_FCP_CMND_DMA_VALID) {
- struct ct6_dsd *ctx1 = (struct ct6_dsd *)ctx;
-
+ struct ct6_dsd *ctx1 = ctx;
dma_pool_free(ha->fcp_cmnd_dma_pool, ctx1->fcp_cmnd,
ctx1->fcp_cmnd_dma);
list_splice(&ctx1->dsd_list, &ha->gbl_dsd_list);
ha->gbl_dsd_avail += ctx1->dsd_use_cnt;
mempool_free(ctx1, ha->ctx_mempool);
}
-
+end:
CMD_SP(cmd) = NULL;
qla2xxx_rel_qpair_sp(sp->qpair, sp);
}
void
qla2x00_abort_all_cmds(scsi_qla_host_t *vha, int res)
{
- int que, cnt;
+ int que, cnt, status;
unsigned long flags;
srb_t *sp;
struct qla_hw_data *ha = vha->hw;
*/
sp_get(sp);
spin_unlock_irqrestore(&ha->hardware_lock, flags);
- qla2xxx_eh_abort(GET_CMD_SP(sp));
+ status = qla2xxx_eh_abort(GET_CMD_SP(sp));
spin_lock_irqsave(&ha->hardware_lock, flags);
+ /* Get rid of extra reference if immediate exit
+ * from ql2xxx_eh_abort */
+ if (status == FAILED && (qla2x00_isp_reg_stat(ha)))
+ atomic_dec(&sp->ref_count);
}
req->outstanding_cmds[cnt] = NULL;
sp->done(sp, res);
if (mem_only) {
if (pci_enable_device_mem(pdev))
- goto probe_out;
+ return ret;
} else {
if (pci_enable_device(pdev))
- goto probe_out;
+ return ret;
}
/* This may fail but that's ok */
if (!ha) {
ql_log_pci(ql_log_fatal, pdev, 0x0009,
"Unable to allocate memory for ha.\n");
- goto probe_out;
+ goto disable_device;
}
ql_dbg_pci(ql_dbg_init, pdev, 0x000a,
"Memory allocated for ha=%p.\n", ha);
pci_release_selected_regions(ha->pdev, ha->bars);
kfree(ha);
-probe_out:
+disable_device:
pci_disable_device(pdev);
return ret;
}
pci_unmap_sg(ha->pdev, cmd->prot_sg, cmd->prot_sg_cnt,
cmd->dma_data_direction);
+ if (!cmd->ctx)
+ return;
+
if (cmd->ctx_dsd_alloced)
- qla2x00_clean_dsd_pool(ha, NULL, cmd);
+ qla2x00_clean_dsd_pool(ha, cmd->ctx);
- if (cmd->ctx)
- dma_pool_free(ha->dl_dma_pool, cmd->ctx, cmd->ctx->crc_ctx_dma);
+ dma_pool_free(ha->dl_dma_pool, cmd->ctx, cmd->ctx->crc_ctx_dma);
}
static int qlt_check_reserve_free_req(struct scsi_qla_host *vha,
goto done;
}
- if (end <= start || start == 0 || end == 0) {
+ if (end < start || start == 0 || end == 0) {
ql_dbg(ql_dbg_misc, vha, 0xd023,
"%s: unusable range (start=%x end=%x)\n", __func__,
ent->t262.end_addr, ent->t262.start_addr);
struct scsi_device *sdev;
list_for_each_entry(sdev, &shost->__devices, siblings) {
+ if (sdev->sdev_state == SDEV_DEL)
+ continue;
if (sdev->channel == channel && sdev->id == id &&
sdev->lun ==lun)
return sdev;
arr[4] = SDEBUG_LONG_INQ_SZ - 5;
arr[5] = (int)have_dif_prot; /* PROTECT bit */
if (sdebug_vpd_use_hostno == 0)
- arr[5] = 0x10; /* claim: implicit TGPS */
+ arr[5] |= 0x10; /* claim: implicit TPGS */
arr[6] = 0x10; /* claim: MultiP */
/* arr[6] |= 0x40; ... claim: EncServ (enclosure services) */
arr[7] = 0xa; /* claim: LINKED + CMDQUE */
#include <scsi/scsi_driver.h>
#include <scsi/scsi_eh.h>
#include <scsi/scsi_host.h>
+#include <scsi/scsi_transport.h> /* __scsi_init_queue() */
#include <scsi/scsi_dh.h>
#include <trace/events/scsi.h>
/* zero out the cmd, except for the embedded scsi_request */
memset((char *)cmd + sizeof(cmd->req), 0,
- sizeof(*cmd) - sizeof(cmd->req));
+ sizeof(*cmd) - sizeof(cmd->req) + shost->hostt->cmd_size);
req->special = cmd;
struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
u64 sector = blk_rq_pos(rq) >> (ilog2(sdp->sector_size) - 9);
u32 nr_sectors = blk_rq_sectors(rq) >> (ilog2(sdp->sector_size) - 9);
+ int ret;
if (!(rq->cmd_flags & REQ_NOUNMAP)) {
switch (sdkp->zeroing_mode) {
case SD_ZERO_WS16_UNMAP:
- return sd_setup_write_same16_cmnd(cmd, true);
+ ret = sd_setup_write_same16_cmnd(cmd, true);
+ goto out;
case SD_ZERO_WS10_UNMAP:
- return sd_setup_write_same10_cmnd(cmd, true);
+ ret = sd_setup_write_same10_cmnd(cmd, true);
+ goto out;
}
}
if (sdp->no_write_same)
return BLKPREP_INVALID;
+
if (sdkp->ws16 || sector > 0xffffffff || nr_sectors > 0xffff)
- return sd_setup_write_same16_cmnd(cmd, false);
- return sd_setup_write_same10_cmnd(cmd, false);
+ ret = sd_setup_write_same16_cmnd(cmd, false);
+ else
+ ret = sd_setup_write_same10_cmnd(cmd, false);
+
+out:
+ if (sd_is_zoned(sdkp) && ret == BLKPREP_OK)
+ return sd_zbc_write_lock_zone(cmd);
+
+ return ret;
}
static void sd_config_write_same(struct scsi_disk *sdkp)
rq->__data_len = sdp->sector_size;
ret = scsi_init_io(cmd);
rq->__data_len = nr_bytes;
+
+ if (sd_is_zoned(sdkp) && ret != BLKPREP_OK)
+ sd_zbc_write_unlock_zone(cmd);
+
return ret;
}
return retval;
}
-static int sd_sync_cache(struct scsi_disk *sdkp)
+static int sd_sync_cache(struct scsi_disk *sdkp, struct scsi_sense_hdr *sshdr)
{
int retries, res;
struct scsi_device *sdp = sdkp->device;
const int timeout = sdp->request_queue->rq_timeout
* SD_FLUSH_TIMEOUT_MULTIPLIER;
- struct scsi_sense_hdr sshdr;
+ struct scsi_sense_hdr my_sshdr;
if (!scsi_device_online(sdp))
return -ENODEV;
+ /* caller might not be interested in sense, but we need it */
+ if (!sshdr)
+ sshdr = &my_sshdr;
+
for (retries = 3; retries > 0; --retries) {
unsigned char cmd[10] = { 0 };
* Leave the rest of the command zero to indicate
* flush everything.
*/
- res = scsi_execute(sdp, cmd, DMA_NONE, NULL, 0, NULL, &sshdr,
+ res = scsi_execute(sdp, cmd, DMA_NONE, NULL, 0, NULL, sshdr,
timeout, SD_MAX_RETRIES, 0, RQF_PM, NULL);
if (res == 0)
break;
sd_print_result(sdkp, "Synchronize Cache(10) failed", res);
if (driver_byte(res) & DRIVER_SENSE)
- sd_print_sense_hdr(sdkp, &sshdr);
+ sd_print_sense_hdr(sdkp, sshdr);
+
/* we need to evaluate the error return */
- if (scsi_sense_valid(&sshdr) &&
- (sshdr.asc == 0x3a || /* medium not present */
- sshdr.asc == 0x20)) /* invalid command */
+ if (scsi_sense_valid(sshdr) &&
+ (sshdr->asc == 0x3a || /* medium not present */
+ sshdr->asc == 0x20)) /* invalid command */
/* this is no error here */
return 0;
if (sdkp->WCE && sdkp->media_present) {
sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n");
- sd_sync_cache(sdkp);
+ sd_sync_cache(sdkp, NULL);
}
if (system_state != SYSTEM_RESTART && sdkp->device->manage_start_stop) {
static int sd_suspend_common(struct device *dev, bool ignore_stop_errors)
{
struct scsi_disk *sdkp = dev_get_drvdata(dev);
+ struct scsi_sense_hdr sshdr;
int ret = 0;
if (!sdkp) /* E.g.: runtime suspend following sd_remove() */
if (sdkp->WCE && sdkp->media_present) {
sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n");
- ret = sd_sync_cache(sdkp);
+ ret = sd_sync_cache(sdkp, &sshdr);
+
if (ret) {
/* ignore OFFLINE device */
if (ret == -ENODEV)
- ret = 0;
- goto done;
+ return 0;
+
+ if (!scsi_sense_valid(&sshdr) ||
+ sshdr.sense_key != ILLEGAL_REQUEST)
+ return ret;
+
+ /*
+ * sshdr.sense_key == ILLEGAL_REQUEST means this drive
+ * doesn't support sync. There's not much to do and
+ * suspend shouldn't fail.
+ */
+ ret = 0;
}
}
ret = 0;
}
-done:
return ret;
}
if ((1 == resp->done) && (!resp->sg_io_owned) &&
((-1 == pack_id) || (resp->header.pack_id == pack_id))) {
resp->done = 2; /* guard against other readers */
- break;
+ write_unlock_irqrestore(&sfp->rq_list_lock, iflags);
+ return resp;
}
}
write_unlock_irqrestore(&sfp->rq_list_lock, iflags);
- return resp;
+ return NULL;
}
/* always adds to end of list */
ufshcd_add_spm_lvl_sysfs_nodes(hba);
}
+static inline void ufshcd_remove_sysfs_nodes(struct ufs_hba *hba)
+{
+ device_remove_file(hba->dev, &hba->rpm_lvl_attr);
+ device_remove_file(hba->dev, &hba->spm_lvl_attr);
+}
+
/**
* ufshcd_shutdown - shutdown routine
* @hba: per adapter instance
*/
void ufshcd_remove(struct ufs_hba *hba)
{
+ ufshcd_remove_sysfs_nodes(hba);
scsi_remove_host(hba->host);
/* disable interrupts */
ufshcd_disable_intr(hba, hba->intr_mask);
{ .compatible = "brcm,bcm7420-sun-top-ctrl", },
{ .compatible = "brcm,bcm7425-sun-top-ctrl", },
{ .compatible = "brcm,bcm7429-sun-top-ctrl", },
- { .compatible = "brcm,bcm7425-sun-top-ctrl", },
+ { .compatible = "brcm,bcm7435-sun-top-ctrl", },
{ .compatible = "brcm,brcmstb-sun-top-ctrl", },
{ }
};
config IMX7_PM_DOMAINS
bool "i.MX7 PM domains"
- select PM_GENERIC_DOMAINS
depends on SOC_IMX7D || (COMPILE_TEST && OF)
+ depends on PM
+ select PM_GENERIC_DOMAINS
default y if SOC_IMX7D
endmenu
+++ /dev/null
-Ion Memory Manager
-
-Ion is a memory manager that allows for sharing of buffers via dma-buf.
-Ion allows for different types of allocation via an abstraction called
-a 'heap'. A heap represents a specific type of memory. Each heap has
-a different type. There can be multiple instances of the same heap
-type.
-
-Specific heap instances are tied to heap IDs. Heap IDs are not to be specified
-in the devicetree.
-
-Required properties for Ion
-
-- compatible: "linux,ion" PLUS a compatible property for the device
-
-All child nodes of a linux,ion node are interpreted as heaps
-
-required properties for heaps
-
-- compatible: compatible string for a heap type PLUS a compatible property
-for the specific instance of the heap. Current heap types
--- linux,ion-heap-system
--- linux,ion-heap-system-contig
--- linux,ion-heap-carveout
--- linux,ion-heap-chunk
--- linux,ion-heap-dma
--- linux,ion-heap-custom
-
-Optional properties
-- memory-region: A phandle to a memory region. Required for DMA heap type
-(see reserved-memory.txt for details on the reservation)
-
-Example:
-
- ion {
- compatbile = "hisilicon,ion", "linux,ion";
-
- ion-system-heap {
- compatbile = "hisilicon,system-heap", "linux,ion-heap-system"
- };
-
- ion-camera-region {
- compatible = "hisilicon,camera-heap", "linux,ion-heap-dma"
- memory-region = <&camera_region>;
- };
-
- ion-fb-region {
- compatbile = "hisilicon,fb-heap", "linux,ion-heap-dma"
- memory-region = <&fb_region>;
- };
- }
config CRYPTO_DEV_CCREE
tristate "Support for ARM TrustZone CryptoCell C7XX family of Crypto accelerators"
- depends on CRYPTO_HW && OF && HAS_DMA
+ depends on CRYPTO && CRYPTO_HW && OF && HAS_DMA
default n
select CRYPTO_HASH
select CRYPTO_BLKCIPHER
uint32_t nents, lbytes;
nents = ssi_buffer_mgr_get_sgl_nents(sg, end, &lbytes, NULL);
- sg_copy_buffer(sg, nents, (void *)dest, (end - to_skip), 0, (direct == SSI_SG_TO_BUF));
+ sg_copy_buffer(sg, nents, (void *)dest, (end - to_skip + 1), to_skip,
+ (direct == SSI_SG_TO_BUF));
}
static inline int ssi_buffer_mgr_render_buff_to_mlli(
rc = ssi_power_mgr_runtime_get(&drvdata->plat_dev->dev);
if (rc != 0) {
SSI_LOG_ERR("ssi_power_mgr_runtime_get returned %x\n",rc);
- spin_unlock_bh(&req_mgr_h->hw_lock);
return rc;
}
#endif
config FSL_DPAA2_ETH
tristate "Freescale DPAA2 Ethernet"
depends on FSL_DPAA2 && FSL_MC_DPIO
+ depends on NETDEVICES && ETHERNET
---help---
Ethernet driver for Freescale DPAA2 SoCs, using the
Freescale MC bus driver
size_t lmmk_size;
size_t lum_size;
int rc;
- mm_segment_t seg;
if (!lsm)
return -ENODATA;
- /*
- * "Switch to kernel segment" to allow copying from kernel space by
- * copy_{to,from}_user().
- */
- seg = get_fs();
- set_fs(KERNEL_DS);
-
if (lsm->lsm_magic != LOV_MAGIC_V1 && lsm->lsm_magic != LOV_MAGIC_V3) {
CERROR("bad LSM MAGIC: 0x%08X != 0x%08X nor 0x%08X\n",
lsm->lsm_magic, LOV_MAGIC_V1, LOV_MAGIC_V3);
out_free:
kvfree(lmmk);
out:
- set_fs(seg);
return rc;
}
obj-$(CONFIG_VIDEO_LM3554) += lm3554.o
-ccflags-y += -Werror
-
ov8858_driver-objs := ../ov8858.o dw9718.o vcm.o
obj-$(CONFIG_VIDEO_OV8858) += ov8858_driver.o
-
-ccflags-y += -Werror
obj-$(CONFIG_VIDEO_OV5693) += ov5693.o
-
-ccflags-y += -Werror
DEFINES += -DATOMISP_POSTFIX=\"css2400b0_v21\" -DISP2400B0
DEFINES += -DSYSTEM_hive_isp_css_2400_system -DISP2400
-ccflags-y += $(INCLUDES) $(DEFINES) -fno-common -Werror
+ccflags-y += $(INCLUDES) $(DEFINES) -fno-common
switch (variable) {
case HW_VAR_BSSID:
- rtl92e_writel(dev, BSSIDR, ((u32 *)(val))[0]);
- rtl92e_writew(dev, BSSIDR+2, ((u16 *)(val+2))[0]);
+ /* BSSIDR 2 byte alignment */
+ rtl92e_writew(dev, BSSIDR, *(u16 *)val);
+ rtl92e_writel(dev, BSSIDR + 2, *(u32 *)(val + 2));
break;
case HW_VAR_MEDIA_STATUS:
struct r8192_priv *priv = rtllib_priv(dev);
RT_TRACE(COMP_INIT, "===========>%s()\n", __func__);
- curCR = rtl92e_readl(dev, EPROM_CMD);
+ curCR = rtl92e_readw(dev, EPROM_CMD);
RT_TRACE(COMP_INIT, "read from Reg Cmd9346CR(%x):%x\n", EPROM_CMD,
curCR);
priv->epromtype = (curCR & EPROM_CMD_9356SEL) ? EEPROM_93C56 :
rtl92e_config_rate(dev, &rate_config);
priv->dot11CurrentPreambleMode = PREAMBLE_AUTO;
priv->basic_rate = rate_config &= 0x15f;
- rtl92e_writel(dev, BSSIDR, ((u32 *)net->bssid)[0]);
- rtl92e_writew(dev, BSSIDR+4, ((u16 *)net->bssid)[2]);
+ rtl92e_writew(dev, BSSIDR, *(u16 *)net->bssid);
+ rtl92e_writel(dev, BSSIDR + 2, *(u32 *)(net->bssid + 2));
if (priv->rtllib->iw_mode == IW_MODE_ADHOC) {
rtl92e_writew(dev, ATIMWND, 2);
struct cb_desc *cb_desc, struct sk_buff *skb)
{
struct r8192_priv *priv = rtllib_priv(dev);
- dma_addr_t mapping = pci_map_single(priv->pdev, skb->data, skb->len,
- PCI_DMA_TODEVICE);
+ dma_addr_t mapping;
struct tx_fwinfo_8190pci *pTxFwInfo;
pTxFwInfo = (struct tx_fwinfo_8190pci *)skb->data;
pTxFwInfo->Short = _rtl92e_query_is_short(pTxFwInfo->TxHT,
pTxFwInfo->TxRate, cb_desc);
- if (pci_dma_mapping_error(priv->pdev, mapping))
- netdev_err(dev, "%s(): DMA Mapping error\n", __func__);
if (cb_desc->bAMPDUEnable) {
pTxFwInfo->AllowAggregation = 1;
pTxFwInfo->RxMF = cb_desc->ampdu_factor;
}
memset((u8 *)pdesc, 0, 12);
+
+ mapping = pci_map_single(priv->pdev, skb->data, skb->len,
+ PCI_DMA_TODEVICE);
+ if (pci_dma_mapping_error(priv->pdev, mapping)) {
+ netdev_err(dev, "%s(): DMA Mapping error\n", __func__);
+ return;
+ }
+
pdesc->LINIP = 0;
pdesc->CmdInit = 1;
pdesc->Offset = sizeof(struct tx_fwinfo_8190pci) + 8;
pTsCommonInfo->TClasNum = TCLAS_Num;
}
-static bool IsACValid(unsigned int tid)
-{
- return tid < 7;
-}
-
bool GetTs(struct rtllib_device *ieee, struct ts_common_info **ppTS,
u8 *Addr, u8 TID, enum tr_select TxRxSelect, bool bAddNewTs)
{
if (ieee->current_network.qos_data.supported == 0) {
UP = 0;
} else {
- if (!IsACValid(TID)) {
- netdev_warn(ieee->dev, "%s(): TID(%d) is not valid\n",
- __func__, TID);
- return false;
- }
-
switch (TID) {
case 0:
case 3:
case 7:
UP = 7;
break;
+ default:
+ netdev_warn(ieee->dev, "%s(): TID(%d) is not valid\n",
+ __func__, TID);
+ return false;
}
}
pwdev_priv->power_mgmt = true;
else
pwdev_priv->power_mgmt = false;
- kfree((u8 *)wdev);
return ret;
#define FUSB302_RESUME_RETRY 10
#define FUSB302_RESUME_RETRY_SLEEP 50
-static int fusb302_i2c_write(struct fusb302_chip *chip,
- u8 address, u8 data)
+
+static bool fusb302_is_suspended(struct fusb302_chip *chip)
{
int retry_cnt;
- int ret = 0;
- atomic_set(&chip->i2c_busy, 1);
for (retry_cnt = 0; retry_cnt < FUSB302_RESUME_RETRY; retry_cnt++) {
if (atomic_read(&chip->pm_suspend)) {
- pr_err("fusb302_i2c: pm suspend, retry %d/%d\n",
- retry_cnt + 1, FUSB302_RESUME_RETRY);
+ dev_err(chip->dev, "i2c: pm suspend, retry %d/%d\n",
+ retry_cnt + 1, FUSB302_RESUME_RETRY);
msleep(FUSB302_RESUME_RETRY_SLEEP);
} else {
- break;
+ return false;
}
}
+
+ return true;
+}
+
+static int fusb302_i2c_write(struct fusb302_chip *chip,
+ u8 address, u8 data)
+{
+ int ret = 0;
+
+ atomic_set(&chip->i2c_busy, 1);
+
+ if (fusb302_is_suspended(chip)) {
+ atomic_set(&chip->i2c_busy, 0);
+ return -ETIMEDOUT;
+ }
+
ret = i2c_smbus_write_byte_data(chip->i2c_client, address, data);
if (ret < 0)
fusb302_log(chip, "cannot write 0x%02x to 0x%02x, ret=%d",
static int fusb302_i2c_block_write(struct fusb302_chip *chip, u8 address,
u8 length, const u8 *data)
{
- int retry_cnt;
int ret = 0;
if (length <= 0)
return ret;
atomic_set(&chip->i2c_busy, 1);
- for (retry_cnt = 0; retry_cnt < FUSB302_RESUME_RETRY; retry_cnt++) {
- if (atomic_read(&chip->pm_suspend)) {
- pr_err("fusb302_i2c: pm suspend, retry %d/%d\n",
- retry_cnt + 1, FUSB302_RESUME_RETRY);
- msleep(FUSB302_RESUME_RETRY_SLEEP);
- } else {
- break;
- }
+
+ if (fusb302_is_suspended(chip)) {
+ atomic_set(&chip->i2c_busy, 0);
+ return -ETIMEDOUT;
}
+
ret = i2c_smbus_write_i2c_block_data(chip->i2c_client, address,
length, data);
if (ret < 0)
static int fusb302_i2c_read(struct fusb302_chip *chip,
u8 address, u8 *data)
{
- int retry_cnt;
int ret = 0;
atomic_set(&chip->i2c_busy, 1);
- for (retry_cnt = 0; retry_cnt < FUSB302_RESUME_RETRY; retry_cnt++) {
- if (atomic_read(&chip->pm_suspend)) {
- pr_err("fusb302_i2c: pm suspend, retry %d/%d\n",
- retry_cnt + 1, FUSB302_RESUME_RETRY);
- msleep(FUSB302_RESUME_RETRY_SLEEP);
- } else {
- break;
- }
+
+ if (fusb302_is_suspended(chip)) {
+ atomic_set(&chip->i2c_busy, 0);
+ return -ETIMEDOUT;
}
+
ret = i2c_smbus_read_byte_data(chip->i2c_client, address);
*data = (u8)ret;
if (ret < 0)
static int fusb302_i2c_block_read(struct fusb302_chip *chip, u8 address,
u8 length, u8 *data)
{
- int retry_cnt;
int ret = 0;
if (length <= 0)
return ret;
atomic_set(&chip->i2c_busy, 1);
- for (retry_cnt = 0; retry_cnt < FUSB302_RESUME_RETRY; retry_cnt++) {
- if (atomic_read(&chip->pm_suspend)) {
- pr_err("fusb302_i2c: pm suspend, retry %d/%d\n",
- retry_cnt + 1, FUSB302_RESUME_RETRY);
- msleep(FUSB302_RESUME_RETRY_SLEEP);
- } else {
- break;
- }
+
+ if (fusb302_is_suspended(chip)) {
+ atomic_set(&chip->i2c_busy, 0);
+ return -ETIMEDOUT;
}
+
ret = i2c_smbus_read_i2c_block_data(chip->i2c_client, address,
length, data);
if (ret < 0) {
fusb302_log(chip, "cannot block read 0x%02x, len=%d, ret=%d",
address, length, ret);
- return ret;
+ goto done;
}
if (ret != length) {
fusb302_log(chip, "only read %d/%d bytes from 0x%02x",
ret, length, address);
- return -EIO;
+ ret = -EIO;
}
+
+done:
atomic_set(&chip->i2c_busy, 0);
return ret;
ret = fusb302_i2c_read(chip, FUSB_REG_STATUS0, &data);
if (ret < 0)
return ret;
- chip->vbus_present = !!(FUSB_REG_STATUS0 & FUSB_REG_STATUS0_VBUSOK);
+ chip->vbus_present = !!(data & FUSB_REG_STATUS0_VBUSOK);
ret = fusb302_i2c_read(chip, FUSB_REG_DEVICE_ID, &data);
if (ret < 0)
return ret;
buf[pos++] = FUSB302_TKN_SYNC1;
buf[pos++] = FUSB302_TKN_SYNC2;
- len = pd_header_cnt(msg->header) * 4;
+ len = pd_header_cnt_le(msg->header) * 4;
/* plug 2 for header */
len += 2;
if (len > 0x1F) {
(u8 *)&msg->header);
if (ret < 0)
return ret;
- len = pd_header_cnt(msg->header) * 4;
+ len = pd_header_cnt_le(msg->header) * 4;
/* add 4 to length to include the CRC */
if (len > PD_MAX_PAYLOAD * 4) {
fusb302_log(chip, "PD message too long %d", len);
if (ret < 0) {
fusb302_log(chip,
"cannot set GPIO Int_N to input, ret=%d", ret);
- gpio_free(chip->gpio_int_n);
return ret;
}
ret = gpio_to_irq(chip->gpio_int_n);
if (ret < 0) {
fusb302_log(chip,
"cannot request IRQ for GPIO Int_N, ret=%d", ret);
- gpio_free(chip->gpio_int_n);
return ret;
}
chip->gpio_int_n_irq = ret;
{.compatible = "fcs,fusb302"},
{},
};
+MODULE_DEVICE_TABLE(of, fusb302_dt_match);
static const struct i2c_device_id fusb302_i2c_device_id[] = {
{"typec_fusb302", 0},
{},
};
+MODULE_DEVICE_TABLE(i2c, fusb302_i2c_device_id);
static const struct dev_pm_ops fusb302_pm_ops = {
.suspend = fusb302_pm_suspend,
return pd_header_type(le16_to_cpu(header));
}
+static inline unsigned int pd_header_msgid(u16 header)
+{
+ return (header >> PD_HEADER_ID_SHIFT) & PD_HEADER_ID_MASK;
+}
+
+static inline unsigned int pd_header_msgid_le(__le16 header)
+{
+ return pd_header_msgid(le16_to_cpu(header));
+}
+
#define PD_MAX_PAYLOAD 7
struct pd_message {
* VDM object is minimum of VDM header + 6 additional data objects.
*/
+#define VDO_MAX_OBJECTS 6
+#define VDO_MAX_SIZE (VDO_MAX_OBJECTS + 1)
+
/*
* VDM header
* ----------
* <5> :: reserved (SVDM), command type (UVDM)
* <4:0> :: command
*/
-#define VDO_MAX_SIZE 7
#define VDO(vid, type, custom) \
(((vid) << 16) | \
((type) << 15) | \
.max_register = 0x7F, /* 0x80 .. 0xFF are vendor defined */
};
-const struct tcpc_config tcpci_tcpc_config = {
+static const struct tcpc_config tcpci_tcpc_config = {
.type = TYPEC_PORT_DFP,
.default_role = TYPEC_SINK,
};
unsigned int hard_reset_count;
bool pd_capable;
bool explicit_contract;
+ unsigned int rx_msgid;
/* Partner capabilities/requests */
u32 sink_request;
unsigned int nr_src_pdo;
u32 snk_pdo[PDO_MAX_OBJECTS];
unsigned int nr_snk_pdo;
+ u32 snk_vdo[VDO_MAX_OBJECTS];
+ unsigned int nr_snk_vdo;
unsigned int max_snk_mv;
unsigned int max_snk_ma;
struct pd_mode_data *modep;
int rlen = 0;
u16 svid;
+ int i;
tcpm_log(port, "Rx VDM cmd 0x%x type %d cmd %d len %d",
p0, cmd_type, cmd, cnt);
case CMDT_INIT:
switch (cmd) {
case CMD_DISCOVER_IDENT:
+ /* 6.4.4.3.1: Only respond as UFP (device) */
+ if (port->data_role == TYPEC_DEVICE &&
+ port->nr_snk_vdo) {
+ for (i = 0; i < port->nr_snk_vdo; i++)
+ response[i + 1]
+ = cpu_to_le32(port->snk_vdo[i]);
+ rlen = port->nr_snk_vdo + 1;
+ }
break;
case CMD_DISCOVER_SVID:
break;
break;
case SOFT_RESET_SEND:
port->message_id = 0;
+ port->rx_msgid = -1;
if (port->pwr_role == TYPEC_SOURCE)
next_state = SRC_SEND_CAPABILITIES;
else
port->attached);
if (port->attached) {
+ enum pd_ctrl_msg_type type = pd_header_type_le(msg->header);
+ unsigned int msgid = pd_header_msgid_le(msg->header);
+
+ /*
+ * USB PD standard, 6.6.1.2:
+ * "... if MessageID value in a received Message is the
+ * same as the stored value, the receiver shall return a
+ * GoodCRC Message with that MessageID value and drop
+ * the Message (this is a retry of an already received
+ * Message). Note: this shall not apply to the Soft_Reset
+ * Message which always has a MessageID value of zero."
+ */
+ if (msgid == port->rx_msgid && type != PD_CTRL_SOFT_RESET)
+ goto done;
+ port->rx_msgid = msgid;
+
/*
* If both ends believe to be DFP/host, we have a data role
* mismatch.
}
}
+done:
mutex_unlock(&port->lock);
kfree(event);
}
}
ma = min(ma, port->max_snk_ma);
- /* XXX: Any other flags need to be set? */
- flags = 0;
+ flags = RDO_USB_COMM | RDO_NO_SUSPEND;
/* Set mismatch bit if offered power is less than operating power */
mw = ma * mv / 1000;
port->attached = false;
port->pd_capable = false;
+ /*
+ * First Rx ID should be 0; set this to a sentinel of -1 so that
+ * we can check tcpm_pd_rx_handler() if we had seen it before.
+ */
+ port->rx_msgid = -1;
+
port->tcpc->set_pd_rx(port->tcpc, false);
tcpm_init_vbus(port); /* also disables charging */
tcpm_init_vconn(port);
port->pwr_opmode = TYPEC_PWR_MODE_USB;
port->caps_count = 0;
port->message_id = 0;
+ port->rx_msgid = -1;
port->explicit_contract = false;
tcpm_set_state(port, SRC_SEND_CAPABILITIES, 0);
break;
typec_set_pwr_opmode(port->typec_port, TYPEC_PWR_MODE_USB);
port->pwr_opmode = TYPEC_PWR_MODE_USB;
port->message_id = 0;
+ port->rx_msgid = -1;
port->explicit_contract = false;
tcpm_set_state(port, SNK_DISCOVERY, 0);
break;
/* Soft_Reset states */
case SOFT_RESET:
port->message_id = 0;
+ port->rx_msgid = -1;
tcpm_pd_send_control(port, PD_CTRL_ACCEPT);
if (port->pwr_role == TYPEC_SOURCE)
tcpm_set_state(port, SRC_SEND_CAPABILITIES, 0);
break;
case SOFT_RESET_SEND:
port->message_id = 0;
+ port->rx_msgid = -1;
if (tcpm_pd_send_control(port, PD_CTRL_SOFT_RESET))
tcpm_set_state_cond(port, hard_reset_state(port), 0);
else
break;
case PR_SWAP_SRC_SNK_SOURCE_OFF:
tcpm_set_cc(port, TYPEC_CC_RD);
+ /*
+ * USB-PD standard, 6.2.1.4, Port Power Role:
+ * "During the Power Role Swap Sequence, for the initial Source
+ * Port, the Port Power Role field shall be set to Sink in the
+ * PS_RDY Message indicating that the initial Source’s power
+ * supply is turned off"
+ */
+ tcpm_set_pwr_role(port, TYPEC_SINK);
if (tcpm_pd_send_control(port, PD_CTRL_PS_RDY)) {
tcpm_set_state(port, ERROR_RECOVERY, 0);
break;
tcpm_set_state_cond(port, SNK_UNATTACHED, PD_T_PS_SOURCE_ON);
break;
case PR_SWAP_SRC_SNK_SINK_ON:
- tcpm_set_pwr_role(port, TYPEC_SINK);
tcpm_swap_complete(port, 0);
tcpm_set_state(port, SNK_STARTUP, 0);
break;
case PR_SWAP_SNK_SRC_SOURCE_ON:
tcpm_set_cc(port, tcpm_rp_cc(port));
tcpm_set_vbus(port, true);
- tcpm_pd_send_control(port, PD_CTRL_PS_RDY);
+ /*
+ * USB PD standard, 6.2.1.4:
+ * "Subsequent Messages initiated by the Policy Engine,
+ * such as the PS_RDY Message sent to indicate that Vbus
+ * is ready, will have the Port Power Role field set to
+ * Source."
+ */
tcpm_set_pwr_role(port, TYPEC_SOURCE);
+ tcpm_pd_send_control(port, PD_CTRL_PS_RDY);
tcpm_swap_complete(port, 0);
tcpm_set_state(port, SRC_STARTUP, 0);
break;
return nr_pdo;
}
+static int tcpm_copy_vdos(u32 *dest_vdo, const u32 *src_vdo,
+ unsigned int nr_vdo)
+{
+ unsigned int i;
+
+ if (nr_vdo > VDO_MAX_OBJECTS)
+ nr_vdo = VDO_MAX_OBJECTS;
+
+ for (i = 0; i < nr_vdo; i++)
+ dest_vdo[i] = src_vdo[i];
+
+ return nr_vdo;
+}
+
void tcpm_update_source_capabilities(struct tcpm_port *port, const u32 *pdo,
unsigned int nr_pdo)
{
tcpc->config->nr_src_pdo);
port->nr_snk_pdo = tcpm_copy_pdos(port->snk_pdo, tcpc->config->snk_pdo,
tcpc->config->nr_snk_pdo);
+ port->nr_snk_vdo = tcpm_copy_vdos(port->snk_vdo, tcpc->config->snk_vdo,
+ tcpc->config->nr_snk_vdo);
port->max_snk_mv = tcpc->config->max_snk_mv;
port->max_snk_ma = tcpc->config->max_snk_ma;
const u32 *snk_pdo;
unsigned int nr_snk_pdo;
+ const u32 *snk_vdo;
+ unsigned int nr_snk_vdo;
+
unsigned int max_snk_mv;
unsigned int max_snk_ma;
unsigned int max_snk_mw;
*/
sg_init_table(scatterlist, num_pages);
/* Now set the pages for each scatterlist */
- for (i = 0; i < num_pages; i++)
- sg_set_page(scatterlist + i, pages[i], PAGE_SIZE, 0);
+ for (i = 0; i < num_pages; i++) {
+ unsigned int len = PAGE_SIZE - offset;
+
+ if (len > count)
+ len = count;
+ sg_set_page(scatterlist + i, pages[i], len, offset);
+ offset = 0;
+ count -= len;
+ }
dma_buffers = dma_map_sg(g_dev,
scatterlist,
u32 addr = sg_dma_address(sg);
/* Note: addrs is the address + page_count - 1
- * The firmware expects the block to be page
+ * The firmware expects blocks after the first to be page-
* aligned and a multiple of the page size
*/
WARN_ON(len == 0);
- WARN_ON(len & ~PAGE_MASK);
- WARN_ON(addr & ~PAGE_MASK);
+ WARN_ON(i && (i != (dma_buffers - 1)) && (len & ~PAGE_MASK));
+ WARN_ON(i && (addr & ~PAGE_MASK));
if (k > 0 &&
- ((addrs[k - 1] & PAGE_MASK) |
- ((addrs[k - 1] & ~PAGE_MASK) + 1) << PAGE_SHIFT)
- == addr) {
- addrs[k - 1] += (len >> PAGE_SHIFT);
- } else {
- addrs[k++] = addr | ((len >> PAGE_SHIFT) - 1);
- }
+ ((addrs[k - 1] & PAGE_MASK) +
+ (((addrs[k - 1] & ~PAGE_MASK) + 1) << PAGE_SHIFT))
+ == (addr & PAGE_MASK))
+ addrs[k - 1] += ((len + PAGE_SIZE - 1) >> PAGE_SHIFT);
+ else
+ addrs[k++] = (addr & PAGE_MASK) |
+ (((len + PAGE_SIZE - 1) >> PAGE_SHIFT) - 1);
}
/* Partial cache lines (fragments) require special measures */
{
int ret = 0;
struct iscsi_conn *conn = arg;
+ bool conn_freed = false;
+
/*
* Allow ourselves to be interrupted by SIGINT so that a
* connection recovery / failure event can be triggered externally.
goto transport_err;
ret = iscsit_handle_response_queue(conn);
- if (ret == 1)
+ if (ret == 1) {
goto get_immediate;
- else if (ret == -ECONNRESET)
+ } else if (ret == -ECONNRESET) {
+ conn_freed = true;
goto out;
- else if (ret < 0)
+ } else if (ret < 0) {
goto transport_err;
+ }
}
transport_err:
* responsible for cleaning up the early connection failure.
*/
if (conn->conn_state != TARG_CONN_STATE_IN_LOGIN)
- iscsit_take_action_for_connection_exit(conn);
+ iscsit_take_action_for_connection_exit(conn, &conn_freed);
out:
+ if (!conn_freed) {
+ while (!kthread_should_stop()) {
+ msleep(100);
+ }
+ }
return 0;
}
{
int rc;
struct iscsi_conn *conn = arg;
+ bool conn_freed = false;
/*
* Allow ourselves to be interrupted by SIGINT so that a
*/
rc = wait_for_completion_interruptible(&conn->rx_login_comp);
if (rc < 0 || iscsi_target_check_conn_state(conn))
- return 0;
+ goto out;
if (!conn->conn_transport->iscsit_get_rx_pdu)
return 0;
if (!signal_pending(current))
atomic_set(&conn->transport_failed, 1);
- iscsit_take_action_for_connection_exit(conn);
+ iscsit_take_action_for_connection_exit(conn, &conn_freed);
+
+out:
+ if (!conn_freed) {
+ while (!kthread_should_stop()) {
+ msleep(100);
+ }
+ }
+
return 0;
}
}
}
-void iscsit_take_action_for_connection_exit(struct iscsi_conn *conn)
+void iscsit_take_action_for_connection_exit(struct iscsi_conn *conn, bool *conn_freed)
{
+ *conn_freed = false;
+
spin_lock_bh(&conn->state_lock);
if (atomic_read(&conn->connection_exit)) {
spin_unlock_bh(&conn->state_lock);
if (conn->conn_state == TARG_CONN_STATE_IN_LOGOUT) {
spin_unlock_bh(&conn->state_lock);
iscsit_close_connection(conn);
+ *conn_freed = true;
return;
}
spin_unlock_bh(&conn->state_lock);
iscsit_handle_connection_cleanup(conn);
+ *conn_freed = true;
}
extern void iscsit_connection_reinstatement_rcfr(struct iscsi_conn *);
extern void iscsit_cause_connection_reinstatement(struct iscsi_conn *, int);
extern void iscsit_fall_back_to_erl0(struct iscsi_session *);
-extern void iscsit_take_action_for_connection_exit(struct iscsi_conn *);
+extern void iscsit_take_action_for_connection_exit(struct iscsi_conn *, bool *);
#endif /*** ISCSI_TARGET_ERL0_H ***/
break;
}
+ while (!kthread_should_stop()) {
+ msleep(100);
+ }
+
return 0;
}
static int iscsi_target_do_login(struct iscsi_conn *, struct iscsi_login *);
-static bool iscsi_target_sk_state_check(struct sock *sk)
+static bool __iscsi_target_sk_check_close(struct sock *sk)
{
if (sk->sk_state == TCP_CLOSE_WAIT || sk->sk_state == TCP_CLOSE) {
- pr_debug("iscsi_target_sk_state_check: TCP_CLOSE_WAIT|TCP_CLOSE,"
+ pr_debug("__iscsi_target_sk_check_close: TCP_CLOSE_WAIT|TCP_CLOSE,"
"returning FALSE\n");
- return false;
+ return true;
}
- return true;
+ return false;
+}
+
+static bool iscsi_target_sk_check_close(struct iscsi_conn *conn)
+{
+ bool state = false;
+
+ if (conn->sock) {
+ struct sock *sk = conn->sock->sk;
+
+ read_lock_bh(&sk->sk_callback_lock);
+ state = (__iscsi_target_sk_check_close(sk) ||
+ test_bit(LOGIN_FLAGS_CLOSED, &conn->login_flags));
+ read_unlock_bh(&sk->sk_callback_lock);
+ }
+ return state;
+}
+
+static bool iscsi_target_sk_check_flag(struct iscsi_conn *conn, unsigned int flag)
+{
+ bool state = false;
+
+ if (conn->sock) {
+ struct sock *sk = conn->sock->sk;
+
+ read_lock_bh(&sk->sk_callback_lock);
+ state = test_bit(flag, &conn->login_flags);
+ read_unlock_bh(&sk->sk_callback_lock);
+ }
+ return state;
+}
+
+static bool iscsi_target_sk_check_and_clear(struct iscsi_conn *conn, unsigned int flag)
+{
+ bool state = false;
+
+ if (conn->sock) {
+ struct sock *sk = conn->sock->sk;
+
+ write_lock_bh(&sk->sk_callback_lock);
+ state = (__iscsi_target_sk_check_close(sk) ||
+ test_bit(LOGIN_FLAGS_CLOSED, &conn->login_flags));
+ if (!state)
+ clear_bit(flag, &conn->login_flags);
+ write_unlock_bh(&sk->sk_callback_lock);
+ }
+ return state;
}
static void iscsi_target_login_drop(struct iscsi_conn *conn, struct iscsi_login *login)
pr_debug("entering iscsi_target_do_login_rx, conn: %p, %s:%d\n",
conn, current->comm, current->pid);
+ /*
+ * If iscsi_target_do_login_rx() has been invoked by ->sk_data_ready()
+ * before initial PDU processing in iscsi_target_start_negotiation()
+ * has completed, go ahead and retry until it's cleared.
+ *
+ * Otherwise if the TCP connection drops while this is occuring,
+ * iscsi_target_start_negotiation() will detect the failure, call
+ * cancel_delayed_work_sync(&conn->login_work), and cleanup the
+ * remaining iscsi connection resources from iscsi_np process context.
+ */
+ if (iscsi_target_sk_check_flag(conn, LOGIN_FLAGS_INITIAL_PDU)) {
+ schedule_delayed_work(&conn->login_work, msecs_to_jiffies(10));
+ return;
+ }
spin_lock(&tpg->tpg_state_lock);
state = (tpg->tpg_state == TPG_STATE_ACTIVE);
if (!state) {
pr_debug("iscsi_target_do_login_rx: tpg_state != TPG_STATE_ACTIVE\n");
- iscsi_target_restore_sock_callbacks(conn);
- iscsi_target_login_drop(conn, login);
- iscsit_deaccess_np(np, tpg, tpg_np);
- return;
+ goto err;
}
- if (conn->sock) {
- struct sock *sk = conn->sock->sk;
-
- read_lock_bh(&sk->sk_callback_lock);
- state = iscsi_target_sk_state_check(sk);
- read_unlock_bh(&sk->sk_callback_lock);
-
- if (!state) {
- pr_debug("iscsi_target_do_login_rx, TCP state CLOSE\n");
- iscsi_target_restore_sock_callbacks(conn);
- iscsi_target_login_drop(conn, login);
- iscsit_deaccess_np(np, tpg, tpg_np);
- return;
- }
+ if (iscsi_target_sk_check_close(conn)) {
+ pr_debug("iscsi_target_do_login_rx, TCP state CLOSE\n");
+ goto err;
}
conn->login_kworker = current;
flush_signals(current);
conn->login_kworker = NULL;
- if (rc < 0) {
- iscsi_target_restore_sock_callbacks(conn);
- iscsi_target_login_drop(conn, login);
- iscsit_deaccess_np(np, tpg, tpg_np);
- return;
- }
+ if (rc < 0)
+ goto err;
pr_debug("iscsi_target_do_login_rx after rx_login_io, %p, %s:%d\n",
conn, current->comm, current->pid);
rc = iscsi_target_do_login(conn, login);
if (rc < 0) {
- iscsi_target_restore_sock_callbacks(conn);
- iscsi_target_login_drop(conn, login);
- iscsit_deaccess_np(np, tpg, tpg_np);
+ goto err;
} else if (!rc) {
- if (conn->sock) {
- struct sock *sk = conn->sock->sk;
-
- write_lock_bh(&sk->sk_callback_lock);
- clear_bit(LOGIN_FLAGS_READ_ACTIVE, &conn->login_flags);
- write_unlock_bh(&sk->sk_callback_lock);
- }
+ if (iscsi_target_sk_check_and_clear(conn, LOGIN_FLAGS_READ_ACTIVE))
+ goto err;
} else if (rc == 1) {
iscsi_target_nego_release(conn);
iscsi_post_login_handler(np, conn, zero_tsih);
iscsit_deaccess_np(np, tpg, tpg_np);
}
+ return;
+
+err:
+ iscsi_target_restore_sock_callbacks(conn);
+ iscsi_target_login_drop(conn, login);
+ iscsit_deaccess_np(np, tpg, tpg_np);
}
static void iscsi_target_do_cleanup(struct work_struct *work)
orig_state_change(sk);
return;
}
+ state = __iscsi_target_sk_check_close(sk);
+ pr_debug("__iscsi_target_sk_close_change: state: %d\n", state);
+
if (test_bit(LOGIN_FLAGS_READ_ACTIVE, &conn->login_flags)) {
pr_debug("Got LOGIN_FLAGS_READ_ACTIVE=1 sk_state_change"
" conn: %p\n", conn);
+ if (state)
+ set_bit(LOGIN_FLAGS_CLOSED, &conn->login_flags);
write_unlock_bh(&sk->sk_callback_lock);
orig_state_change(sk);
return;
}
- if (test_and_set_bit(LOGIN_FLAGS_CLOSED, &conn->login_flags)) {
+ if (test_bit(LOGIN_FLAGS_CLOSED, &conn->login_flags)) {
pr_debug("Got LOGIN_FLAGS_CLOSED=1 sk_state_change conn: %p\n",
conn);
write_unlock_bh(&sk->sk_callback_lock);
orig_state_change(sk);
return;
}
+ /*
+ * If the TCP connection has dropped, go ahead and set LOGIN_FLAGS_CLOSED,
+ * but only queue conn->login_work -> iscsi_target_do_login_rx()
+ * processing if LOGIN_FLAGS_INITIAL_PDU has already been cleared.
+ *
+ * When iscsi_target_do_login_rx() runs, iscsi_target_sk_check_close()
+ * will detect the dropped TCP connection from delayed workqueue context.
+ *
+ * If LOGIN_FLAGS_INITIAL_PDU is still set, which means the initial
+ * iscsi_target_start_negotiation() is running, iscsi_target_do_login()
+ * via iscsi_target_sk_check_close() or iscsi_target_start_negotiation()
+ * via iscsi_target_sk_check_and_clear() is responsible for detecting the
+ * dropped TCP connection in iscsi_np process context, and cleaning up
+ * the remaining iscsi connection resources.
+ */
+ if (state) {
+ pr_debug("iscsi_target_sk_state_change got failed state\n");
+ set_bit(LOGIN_FLAGS_CLOSED, &conn->login_flags);
+ state = test_bit(LOGIN_FLAGS_INITIAL_PDU, &conn->login_flags);
+ write_unlock_bh(&sk->sk_callback_lock);
- state = iscsi_target_sk_state_check(sk);
- write_unlock_bh(&sk->sk_callback_lock);
-
- pr_debug("iscsi_target_sk_state_change: state: %d\n", state);
+ orig_state_change(sk);
- if (!state) {
- pr_debug("iscsi_target_sk_state_change got failed state\n");
- schedule_delayed_work(&conn->login_cleanup_work, 0);
+ if (!state)
+ schedule_delayed_work(&conn->login_work, 0);
return;
}
+ write_unlock_bh(&sk->sk_callback_lock);
+
orig_state_change(sk);
}
if (iscsi_target_handle_csg_one(conn, login) < 0)
return -1;
if (login_rsp->flags & ISCSI_FLAG_LOGIN_TRANSIT) {
+ /*
+ * Check to make sure the TCP connection has not
+ * dropped asynchronously while session reinstatement
+ * was occuring in this kthread context, before
+ * transitioning to full feature phase operation.
+ */
+ if (iscsi_target_sk_check_close(conn))
+ return -1;
+
login->tsih = conn->sess->tsih;
login->login_complete = 1;
iscsi_target_restore_sock_callbacks(conn);
break;
}
- if (conn->sock) {
- struct sock *sk = conn->sock->sk;
- bool state;
-
- read_lock_bh(&sk->sk_callback_lock);
- state = iscsi_target_sk_state_check(sk);
- read_unlock_bh(&sk->sk_callback_lock);
-
- if (!state) {
- pr_debug("iscsi_target_do_login() failed state for"
- " conn: %p\n", conn);
- return -1;
- }
- }
-
return 0;
}
write_lock_bh(&sk->sk_callback_lock);
set_bit(LOGIN_FLAGS_READY, &conn->login_flags);
+ set_bit(LOGIN_FLAGS_INITIAL_PDU, &conn->login_flags);
write_unlock_bh(&sk->sk_callback_lock);
}
-
+ /*
+ * If iscsi_target_do_login returns zero to signal more PDU
+ * exchanges are required to complete the login, go ahead and
+ * clear LOGIN_FLAGS_INITIAL_PDU but only if the TCP connection
+ * is still active.
+ *
+ * Otherwise if TCP connection dropped asynchronously, go ahead
+ * and perform connection cleanup now.
+ */
ret = iscsi_target_do_login(conn, login);
+ if (!ret && iscsi_target_sk_check_and_clear(conn, LOGIN_FLAGS_INITIAL_PDU))
+ ret = -1;
+
if (ret < 0) {
cancel_delayed_work_sync(&conn->login_work);
cancel_delayed_work_sync(&conn->login_cleanup_work);
if (cmd->unknown_data_length) {
cmd->data_length = size;
} else if (size != cmd->data_length) {
- pr_warn("TARGET_CORE[%s]: Expected Transfer Length:"
+ pr_warn_ratelimited("TARGET_CORE[%s]: Expected Transfer Length:"
" %u does not match SCSI CDB Length: %u for SAM Opcode:"
" 0x%02x\n", cmd->se_tfo->get_fabric_name(),
cmd->data_length, size, cmd->t_task_cdb[0]);
- if (cmd->data_direction == DMA_TO_DEVICE &&
- cmd->se_cmd_flags & SCF_SCSI_DATA_CDB) {
- pr_err("Rejecting underflow/overflow WRITE data\n");
- return TCM_INVALID_CDB_FIELD;
+ if (cmd->data_direction == DMA_TO_DEVICE) {
+ if (cmd->se_cmd_flags & SCF_SCSI_DATA_CDB) {
+ pr_err_ratelimited("Rejecting underflow/overflow"
+ " for WRITE data CDB\n");
+ return TCM_INVALID_CDB_FIELD;
+ }
+ /*
+ * Some fabric drivers like iscsi-target still expect to
+ * always reject overflow writes. Reject this case until
+ * full fabric driver level support for overflow writes
+ * is introduced tree-wide.
+ */
+ if (size > cmd->data_length) {
+ pr_err_ratelimited("Rejecting overflow for"
+ " WRITE control CDB\n");
+ return TCM_INVALID_CDB_FIELD;
+ }
}
/*
* Reject READ_* or WRITE_* with overflow/underflow for
struct tcmu_dev {
struct list_head node;
-
+ struct kref kref;
struct se_device se_dev;
char *name;
udev = kzalloc(sizeof(struct tcmu_dev), GFP_KERNEL);
if (!udev)
return NULL;
+ kref_init(&udev->kref);
udev->name = kstrdup(name, GFP_KERNEL);
if (!udev->name) {
return 0;
}
+static void tcmu_dev_call_rcu(struct rcu_head *p)
+{
+ struct se_device *dev = container_of(p, struct se_device, rcu_head);
+ struct tcmu_dev *udev = TCMU_DEV(dev);
+
+ kfree(udev->uio_info.name);
+ kfree(udev->name);
+ kfree(udev);
+}
+
+static void tcmu_dev_kref_release(struct kref *kref)
+{
+ struct tcmu_dev *udev = container_of(kref, struct tcmu_dev, kref);
+ struct se_device *dev = &udev->se_dev;
+
+ call_rcu(&dev->rcu_head, tcmu_dev_call_rcu);
+}
+
static int tcmu_release(struct uio_info *info, struct inode *inode)
{
struct tcmu_dev *udev = container_of(info, struct tcmu_dev, uio_info);
clear_bit(TCMU_DEV_BIT_OPEN, &udev->flags);
pr_debug("close\n");
-
+ /* release ref from configure */
+ kref_put(&udev->kref, tcmu_dev_kref_release);
return 0;
}
dev->dev_attrib.hw_max_sectors = 128;
dev->dev_attrib.hw_queue_depth = 128;
+ /*
+ * Get a ref incase userspace does a close on the uio device before
+ * LIO has initiated tcmu_free_device.
+ */
+ kref_get(&udev->kref);
+
ret = tcmu_netlink_event(TCMU_CMD_ADDED_DEVICE, udev->uio_info.name,
udev->uio_info.uio_dev->minor);
if (ret)
return 0;
err_netlink:
+ kref_put(&udev->kref, tcmu_dev_kref_release);
uio_unregister_device(&udev->uio_info);
err_register:
vfree(udev->mb_addr);
err_vzalloc:
kfree(info->name);
+ info->name = NULL;
return ret;
}
return -EINVAL;
}
-static void tcmu_dev_call_rcu(struct rcu_head *p)
-{
- struct se_device *dev = container_of(p, struct se_device, rcu_head);
- struct tcmu_dev *udev = TCMU_DEV(dev);
-
- kfree(udev);
-}
-
static bool tcmu_dev_configured(struct tcmu_dev *udev)
{
return udev->uio_info.uio_dev ? true : false;
udev->uio_info.uio_dev->minor);
uio_unregister_device(&udev->uio_info);
- kfree(udev->uio_info.name);
- kfree(udev->name);
}
- call_rcu(&dev->rcu_head, tcmu_dev_call_rcu);
+
+ /* release ref from init */
+ kref_put(&udev->kref, tcmu_dev_kref_release);
}
enum {
# Generic Trusted Execution Environment Configuration
config TEE
tristate "Trusted Execution Environment support"
+ depends on HAVE_ARM_SMCCC || COMPILE_TEST
select DMA_SHARED_BUFFER
select GENERIC_ALLOCATOR
help
config BCM_NS_THERMAL
tristate "Northstar thermal driver"
depends on ARCH_BCM_IPROC || COMPILE_TEST
+ default y if ARCH_BCM_IPROC
help
- Northstar is a family of SoCs that includes e.g. BCM4708, BCM47081,
- BCM4709 and BCM47094. It contains DMU (Device Management Unit) block
- with a thermal sensor that allows checking CPU temperature. This
- driver provides support for it.
+ Support for the Northstar and Northstar Plus family of SoCs (e.g.
+ BCM4708, BCM4709, BCM5301x, BCM95852X, etc). It contains DMU (Device
+ Management Unit) block with a thermal sensor that allows checking CPU
+ temperature.
static int qoriq_tmu_probe(struct platform_device *pdev)
{
int ret;
- const struct thermal_trip *trip;
struct qoriq_tmu_data *data;
struct device_node *np = pdev->dev.of_node;
u32 site = 0;
goto err_tmu;
}
- trip = of_thermal_get_trip_points(data->tz);
-
/* Enable monitoring */
site |= 0x1 << (15 - data->sensor_id);
tmu_write(data, site | TMR_ME | TMR_ALPF, &data->regs->tmr);
* This may be called from any critical situation to trigger a system shutdown
* after a known period of time. By default this is not scheduled.
*/
-void thermal_emergency_poweroff(void)
+static void thermal_emergency_poweroff(void)
{
int poweroff_delay_ms = CONFIG_THERMAL_EMERGENCY_POWEROFF_DELAY_MS;
/*
}
/**
- * ti_bandgap_set_continous_mode() - One time enabling of continuous mode
+ * ti_bandgap_set_continuous_mode() - One time enabling of continuous mode
* @bgp: pointer to struct ti_bandgap
*
* Call this function only if HAS(MODE_CONFIG) is set. As this driver may
}
bgp = devm_kzalloc(&pdev->dev, sizeof(*bgp), GFP_KERNEL);
- if (!bgp) {
- dev_err(&pdev->dev, "Unable to allocate mem for driver ref\n");
+ if (!bgp)
return ERR_PTR(-ENOMEM);
- }
of_id = of_match_device(of_ti_bandgap_match, &pdev->dev);
if (of_id)
bgp->conf = of_id->data;
/* register shadow for context save and restore */
- bgp->regval = devm_kzalloc(&pdev->dev, sizeof(*bgp->regval) *
- bgp->conf->sensor_count, GFP_KERNEL);
- if (!bgp->regval) {
- dev_err(&pdev->dev, "Unable to allocate mem for driver ref\n");
+ bgp->regval = devm_kcalloc(&pdev->dev, bgp->conf->sensor_count,
+ sizeof(*bgp->regval), GFP_KERNEL);
+ if (!bgp->regval)
return ERR_PTR(-ENOMEM);
- }
i = 0;
do {
ehv_bc_driver = alloc_tty_driver(count);
if (!ehv_bc_driver) {
ret = -ENOMEM;
- goto error;
+ goto err_free_bcs;
}
ehv_bc_driver->driver_name = "ehv-bc";
ret = tty_register_driver(ehv_bc_driver);
if (ret) {
pr_err("ehv-bc: could not register tty driver (ret=%i)\n", ret);
- goto error;
+ goto err_put_tty_driver;
}
ret = platform_driver_register(&ehv_bc_tty_driver);
if (ret) {
pr_err("ehv-bc: could not register platform driver (ret=%i)\n",
ret);
- goto error;
+ goto err_deregister_tty_driver;
}
return 0;
-error:
- if (ehv_bc_driver) {
- tty_unregister_driver(ehv_bc_driver);
- put_tty_driver(ehv_bc_driver);
- }
-
+err_deregister_tty_driver:
+ tty_unregister_driver(ehv_bc_driver);
+err_put_tty_driver:
+ put_tty_driver(ehv_bc_driver);
+err_free_bcs:
kfree(bcs);
return ret;
}
EXPORT_SYMBOL_GPL(serdev_device_write_wakeup);
+int serdev_device_write_buf(struct serdev_device *serdev,
+ const unsigned char *buf, size_t count)
+{
+ struct serdev_controller *ctrl = serdev->ctrl;
+
+ if (!ctrl || !ctrl->ops->write_buf)
+ return -EINVAL;
+
+ return ctrl->ops->write_buf(ctrl, buf, count);
+}
+EXPORT_SYMBOL_GPL(serdev_device_write_buf);
+
int serdev_device_write(struct serdev_device *serdev,
const unsigned char *buf, size_t count,
unsigned long timeout)
return PTR_ERR(tty);
serport->tty = tty;
- serport->port->client_ops = &client_ops;
- serport->port->client_data = ctrl;
-
if (tty->ops->open)
tty->ops->open(serport->tty, NULL);
else
struct device *parent,
struct tty_driver *drv, int idx)
{
+ const struct tty_port_client_operations *old_ops;
struct serdev_controller *ctrl;
struct serport *serport;
int ret;
ctrl->ops = &ctrl_ops;
+ old_ops = port->client_ops;
+ port->client_ops = &client_ops;
+ port->client_data = ctrl;
+
ret = serdev_controller_add(ctrl);
if (ret)
- goto err_controller_put;
+ goto err_reset_data;
dev_info(&ctrl->dev, "tty port %s%d registered\n", drv->name, idx);
return &ctrl->dev;
-err_controller_put:
+err_reset_data:
+ port->client_data = NULL;
+ port->client_ops = old_ops;
serdev_controller_put(ctrl);
+
return ERR_PTR(ret);
}
-void serdev_tty_port_unregister(struct tty_port *port)
+int serdev_tty_port_unregister(struct tty_port *port)
{
struct serdev_controller *ctrl = port->client_data;
struct serport *serport = serdev_controller_get_drvdata(ctrl);
if (!serport)
- return;
+ return -ENODEV;
serdev_controller_remove(ctrl);
port->client_ops = NULL;
port->client_data = NULL;
serdev_controller_put(ctrl);
+
+ return 0;
}
/*
* These are definitions for the Exar XR17V35X and XR17(C|D)15X
*/
+#define UART_EXAR_INT0 0x80
#define UART_EXAR_SLEEP 0x8b /* Sleep mode */
#define UART_EXAR_DVID 0x8d /* Device identification */
/*
* Check if the device is a Fintek F81216A
*/
- if (port->type == PORT_16550A)
+ if (port->type == PORT_16550A && port->iotype == UPIO_PORT)
fintek_8250_probe(up);
if (up->capabilities != old_capabilities) {
static int exar_handle_irq(struct uart_port *port)
{
unsigned int iir = serial_port_in(port, UART_IIR);
- int ret;
+ int ret = 0;
- ret = serial8250_handle_irq(port, iir);
+ if (((port->type == PORT_XR17V35X) || (port->type == PORT_XR17D15X)) &&
+ serial_port_in(port, UART_EXAR_INT0) != 0)
+ ret = 1;
- if ((port->type == PORT_XR17V35X) ||
- (port->type == PORT_XR17D15X)) {
- serial_port_in(port, 0x80);
- serial_port_in(port, 0x81);
- serial_port_in(port, 0x82);
- serial_port_in(port, 0x83);
- }
+ ret |= serial8250_handle_irq(port, iir);
return ret;
}
serial_port_in(port, UART_RX);
serial_port_in(port, UART_IIR);
serial_port_in(port, UART_MSR);
+ if ((port->type == PORT_XR17V35X) || (port->type == PORT_XR17D15X))
+ serial_port_in(port, UART_EXAR_INT0);
/*
* At this point, there's no way the LSR could still be 0xff;
serial_port_in(port, UART_RX);
serial_port_in(port, UART_IIR);
serial_port_in(port, UART_MSR);
+ if ((port->type == PORT_XR17V35X) || (port->type == PORT_XR17D15X))
+ serial_port_in(port, UART_EXAR_INT0);
up->lsr_saved_flags = 0;
up->msr_saved_flags = 0;
port = &altera_jtaguart_ports[i].port;
uart_remove_one_port(&altera_jtaguart_driver, port);
+ iounmap(port->membase);
return 0;
}
if (port) {
uart_remove_one_port(&altera_uart_driver, port);
port->mapbase = 0;
+ iounmap(port->membase);
}
return 0;
#define UARTn_FRAME 0x04
#define UARTn_FRAME_DATABITS__MASK 0x000f
#define UARTn_FRAME_DATABITS(n) ((n) - 3)
+#define UARTn_FRAME_PARITY__MASK 0x0300
#define UARTn_FRAME_PARITY_NONE 0x0000
#define UARTn_FRAME_PARITY_EVEN 0x0200
#define UARTn_FRAME_PARITY_ODD 0x0300
16 * (4 + (clkdiv >> 6)));
frame = efm32_uart_read32(efm_port, UARTn_FRAME);
- if (frame & UARTn_FRAME_PARITY_ODD)
+ switch (frame & UARTn_FRAME_PARITY__MASK) {
+ case UARTn_FRAME_PARITY_ODD:
*parity = 'o';
- else if (frame & UARTn_FRAME_PARITY_EVEN)
+ break;
+ case UARTn_FRAME_PARITY_EVEN:
*parity = 'e';
- else
+ break;
+ default:
*parity = 'n';
+ }
*bits = (frame & UARTn_FRAME_DATABITS__MASK) -
UARTn_FRAME_DATABITS(4) + 4;
static void __exit ifx_spi_exit(void)
{
/* unregister */
+ spi_unregister_driver(&ifx_spi_driver);
tty_unregister_driver(tty_drv);
put_tty_driver(tty_drv);
- spi_unregister_driver(&ifx_spi_driver);
unregister_reboot_notifier(&ifx_modem_reboot_notifier_block);
}
* and DCD (when they are outputs) or enables the respective
* irqs. So set this bit early, i.e. before requesting irqs.
*/
- writel(UFCR_DCEDTE, sport->port.membase + UFCR);
+ reg = readl(sport->port.membase + UFCR);
+ if (!(reg & UFCR_DCEDTE))
+ writel(reg | UFCR_DCEDTE, sport->port.membase + UFCR);
/*
* Disable UCR3_RI and UCR3_DCD irqs. They are also not
sport->port.membase + UCR3);
} else {
- writel(0, sport->port.membase + UFCR);
+ unsigned long ucr3 = UCR3_DSR;
+
+ reg = readl(sport->port.membase + UFCR);
+ if (reg & UFCR_DCEDTE)
+ writel(reg & ~UFCR_DCEDTE, sport->port.membase + UFCR);
+
+ if (!is_imx1_uart(sport))
+ ucr3 |= IMX21_UCR3_RXDMUXSEL | UCR3_ADNIMP;
+ writel(ucr3, sport->port.membase + UCR3);
}
clk_disable_unprepare(sport->clk_ipg);
mutex_lock(&port->mutex);
tty_dev = device_find_child(uport->dev, &match, serial_match_port);
- if (device_may_wakeup(tty_dev)) {
+ if (tty_dev && device_may_wakeup(tty_dev)) {
if (!enable_irq_wake(uport->irq))
uport->irq_wake = 1;
put_device(tty_dev);
* Register the port whether it's detected or not. This allows
* setserial to be used to alter this port's parameters.
*/
- tty_dev = tty_port_register_device_attr(port, drv->tty_driver,
+ tty_dev = tty_port_register_device_attr_serdev(port, drv->tty_driver,
uport->line, uport->dev, port, uport->tty_groups);
if (likely(!IS_ERR(tty_dev))) {
device_set_wakeup_capable(tty_dev, 1);
/*
* Remove the devices from the tty layer
*/
- tty_unregister_device(drv->tty_driver, uport->line);
+ tty_port_unregister_device(port, drv->tty_driver, uport->line);
tty = tty_port_tty_get(port);
if (tty) {
struct tty_driver *driver, unsigned index,
struct device *device, void *drvdata,
const struct attribute_group **attr_grp)
+{
+ tty_port_link_device(port, driver, index);
+ return tty_register_device_attr(driver, index, device, drvdata,
+ attr_grp);
+}
+EXPORT_SYMBOL_GPL(tty_port_register_device_attr);
+
+/**
+ * tty_port_register_device_attr_serdev - register tty or serdev device
+ * @port: tty_port of the device
+ * @driver: tty_driver for this device
+ * @index: index of the tty
+ * @device: parent if exists, otherwise NULL
+ * @drvdata: driver data for the device
+ * @attr_grp: attribute group for the device
+ *
+ * Register a serdev or tty device depending on if the parent device has any
+ * defined serdev clients or not.
+ */
+struct device *tty_port_register_device_attr_serdev(struct tty_port *port,
+ struct tty_driver *driver, unsigned index,
+ struct device *device, void *drvdata,
+ const struct attribute_group **attr_grp)
{
struct device *dev;
tty_port_link_device(port, driver, index);
dev = serdev_tty_port_register(port, device, driver, index);
- if (PTR_ERR(dev) != -ENODEV)
+ if (PTR_ERR(dev) != -ENODEV) {
/* Skip creating cdev if we registered a serdev device */
return dev;
+ }
return tty_register_device_attr(driver, index, device, drvdata,
attr_grp);
}
-EXPORT_SYMBOL_GPL(tty_port_register_device_attr);
+EXPORT_SYMBOL_GPL(tty_port_register_device_attr_serdev);
+
+/**
+ * tty_port_register_device_serdev - register tty or serdev device
+ * @port: tty_port of the device
+ * @driver: tty_driver for this device
+ * @index: index of the tty
+ * @device: parent if exists, otherwise NULL
+ *
+ * Register a serdev or tty device depending on if the parent device has any
+ * defined serdev clients or not.
+ */
+struct device *tty_port_register_device_serdev(struct tty_port *port,
+ struct tty_driver *driver, unsigned index,
+ struct device *device)
+{
+ return tty_port_register_device_attr_serdev(port, driver, index,
+ device, NULL, NULL);
+}
+EXPORT_SYMBOL_GPL(tty_port_register_device_serdev);
+
+/**
+ * tty_port_unregister_device - deregister a tty or serdev device
+ * @port: tty_port of the device
+ * @driver: tty_driver for this device
+ * @index: index of the tty
+ *
+ * If a tty or serdev device is registered with a call to
+ * tty_port_register_device_serdev() then this function must be called when
+ * the device is gone.
+ */
+void tty_port_unregister_device(struct tty_port *port,
+ struct tty_driver *driver, unsigned index)
+{
+ int ret;
+
+ ret = serdev_tty_port_unregister(port);
+ if (ret == 0)
+ return;
+
+ tty_unregister_device(driver, index);
+}
+EXPORT_SYMBOL_GPL(tty_port_unregister_device);
int tty_port_alloc_xmit_buf(struct tty_port *port)
{
/* check if last port ref was dropped before tty release */
if (WARN_ON(port->itty))
return;
-
- serdev_tty_port_unregister(port);
-
if (port->xmit_buf)
free_page((unsigned long)port->xmit_buf);
tty_port_destroy(port);
map = kzalloc(sizeof(*map), GFP_KERNEL);
if (!map) {
ret = -ENOMEM;
- goto err_map_kobj;
+ goto err_map;
}
kobject_init(&map->kobj, &map_attr_type);
map->mem = mem;
goto err_map_kobj;
ret = kobject_uevent(&map->kobj, KOBJ_ADD);
if (ret)
- goto err_map;
+ goto err_map_kobj;
}
for (pi = 0; pi < MAX_UIO_PORT_REGIONS; pi++) {
portio = kzalloc(sizeof(*portio), GFP_KERNEL);
if (!portio) {
ret = -ENOMEM;
- goto err_portio_kobj;
+ goto err_portio;
}
kobject_init(&portio->kobj, &portio_attr_type);
portio->port = port;
goto err_portio_kobj;
ret = kobject_uevent(&portio->kobj, KOBJ_ADD);
if (ret)
- goto err_portio;
+ goto err_portio_kobj;
}
return 0;
{
struct ci_hdrc *ci = dev_get_drvdata(dev);
- return sprintf(buf, "%s\n", ci_role(ci)->name);
+ if (ci->role != CI_ROLE_END)
+ return sprintf(buf, "%s\n", ci_role(ci)->name);
+
+ return 0;
}
static ssize_t ci_role_store(struct device *dev,
{
struct ci_hdrc *ci = s->private;
- seq_printf(s, "%s\n", ci_role(ci)->name);
+ if (ci->role != CI_ROLE_END)
+ seq_printf(s, "%s\n", ci_role(ci)->name);
return 0;
}
int ci_hdrc_gadget_init(struct ci_hdrc *ci)
{
struct ci_role_driver *rdrv;
+ int ret;
if (!hw_read(ci, CAP_DCCPARAMS, DCCPARAMS_DC))
return -ENXIO;
rdrv->stop = udc_id_switch_for_host;
rdrv->irq = udc_irq;
rdrv->name = "gadget";
- ci->roles[CI_ROLE_GADGET] = rdrv;
- return udc_start(ci);
+ ret = udc_start(ci);
+ if (!ret)
+ ci->roles[CI_ROLE_GADGET] = rdrv;
+
+ return ret;
}
const struct usbmisc_ops *ops;
};
+static inline bool is_imx53_usbmisc(struct imx_usbmisc_data *data);
+
static int usbmisc_imx25_init(struct imx_usbmisc_data *data)
{
struct imx_usbmisc *usbmisc = dev_get_drvdata(data->dev);
val = readl(reg) | MX53_USB_UHx_CTRL_WAKE_UP_EN
| MX53_USB_UHx_CTRL_ULPI_INT_EN;
writel(val, reg);
- /* Disable internal 60Mhz clock */
- reg = usbmisc->base + MX53_USB_CLKONOFF_CTRL_OFFSET;
- val = readl(reg) | MX53_USB_CLKONOFF_CTRL_H2_INT60CKOFF;
- writel(val, reg);
+ if (is_imx53_usbmisc(data)) {
+ /* Disable internal 60Mhz clock */
+ reg = usbmisc->base +
+ MX53_USB_CLKONOFF_CTRL_OFFSET;
+ val = readl(reg) |
+ MX53_USB_CLKONOFF_CTRL_H2_INT60CKOFF;
+ writel(val, reg);
+ }
+
}
if (data->disable_oc) {
reg = usbmisc->base + MX53_USB_UH2_CTRL_OFFSET;
val = readl(reg) | MX53_USB_UHx_CTRL_WAKE_UP_EN
| MX53_USB_UHx_CTRL_ULPI_INT_EN;
writel(val, reg);
- /* Disable internal 60Mhz clock */
- reg = usbmisc->base + MX53_USB_CLKONOFF_CTRL_OFFSET;
- val = readl(reg) | MX53_USB_CLKONOFF_CTRL_H3_INT60CKOFF;
- writel(val, reg);
+
+ if (is_imx53_usbmisc(data)) {
+ /* Disable internal 60Mhz clock */
+ reg = usbmisc->base +
+ MX53_USB_CLKONOFF_CTRL_OFFSET;
+ val = readl(reg) |
+ MX53_USB_CLKONOFF_CTRL_H3_INT60CKOFF;
+ writel(val, reg);
+ }
}
if (data->disable_oc) {
reg = usbmisc->base + MX53_USB_UH3_CTRL_OFFSET;
.init = usbmisc_imx27_init,
};
+static const struct usbmisc_ops imx51_usbmisc_ops = {
+ .init = usbmisc_imx53_init,
+};
+
static const struct usbmisc_ops imx53_usbmisc_ops = {
.init = usbmisc_imx53_init,
};
.set_wakeup = usbmisc_imx7d_set_wakeup,
};
+static inline bool is_imx53_usbmisc(struct imx_usbmisc_data *data)
+{
+ struct imx_usbmisc *usbmisc = dev_get_drvdata(data->dev);
+
+ return usbmisc->ops == &imx53_usbmisc_ops;
+}
+
int imx_usbmisc_init(struct imx_usbmisc_data *data)
{
struct imx_usbmisc *usbmisc;
},
{
.compatible = "fsl,imx51-usbmisc",
- .data = &imx53_usbmisc_ops,
+ .data = &imx51_usbmisc_ops,
},
{
.compatible = "fsl,imx53-usbmisc",
if (userurb) { /* Async */
if (when == SUBMIT)
- dev_info(&udev->dev, "userurb %p, ep%d %s-%s, "
+ dev_info(&udev->dev, "userurb %pK, ep%d %s-%s, "
"length %u\n",
userurb, ep, t, d, length);
else
- dev_info(&udev->dev, "userurb %p, ep%d %s-%s, "
+ dev_info(&udev->dev, "userurb %pK, ep%d %s-%s, "
"actual_length %u status %d\n",
userurb, ep, t, d, length,
timeout_or_status);
if (as) {
int retval;
- snoop(&ps->dev->dev, "reap %p\n", as->userurb);
+ snoop(&ps->dev->dev, "reap %pK\n", as->userurb);
retval = processcompl(as, (void __user * __user *)arg);
free_async(as);
return retval;
as = async_getcompleted(ps);
if (as) {
- snoop(&ps->dev->dev, "reap %p\n", as->userurb);
+ snoop(&ps->dev->dev, "reap %pK\n", as->userurb);
retval = processcompl(as, (void __user * __user *)arg);
free_async(as);
} else {
if (as) {
int retval;
- snoop(&ps->dev->dev, "reap %p\n", as->userurb);
+ snoop(&ps->dev->dev, "reap %pK\n", as->userurb);
retval = processcompl_compat(as, (void __user * __user *)arg);
free_async(as);
return retval;
as = async_getcompleted(ps);
if (as) {
- snoop(&ps->dev->dev, "reap %p\n", as->userurb);
+ snoop(&ps->dev->dev, "reap %pK\n", as->userurb);
retval = processcompl_compat(as, (void __user * __user *)arg);
free_async(as);
} else {
#endif
case USBDEVFS_DISCARDURB:
- snoop(&dev->dev, "%s: DISCARDURB %p\n", __func__, p);
+ snoop(&dev->dev, "%s: DISCARDURB %pK\n", __func__, p);
ret = proc_unlinkurb(ps, p);
break;
if (retval == 0)
retval = -EINPROGRESS;
else if (retval != -EIDRM && retval != -EBUSY)
- dev_dbg(&udev->dev, "hcd_unlink_urb %p fail %d\n",
+ dev_dbg(&udev->dev, "hcd_unlink_urb %pK fail %d\n",
urb, retval);
usb_put_dev(udev);
}
/* kick hcd */
unlink1(hcd, urb, -ESHUTDOWN);
dev_dbg (hcd->self.controller,
- "shutdown urb %p ep%d%s%s\n",
+ "shutdown urb %pK ep%d%s%s\n",
urb, usb_endpoint_num(&ep->desc),
is_in ? "in" : "out",
({ char *s;
hcd->bandwidth_mutex = kmalloc(sizeof(*hcd->bandwidth_mutex),
GFP_KERNEL);
if (!hcd->bandwidth_mutex) {
+ kfree(hcd->address0_mutex);
kfree(hcd);
dev_dbg(dev, "hcd bandwidth mutex alloc failed\n");
return NULL;
}
/* USB 2.0 spec Section 11.24.4.5 */
-static int get_hub_descriptor(struct usb_device *hdev, void *data)
+static int get_hub_descriptor(struct usb_device *hdev,
+ struct usb_hub_descriptor *desc)
{
int i, ret, size;
unsigned dtype;
for (i = 0; i < 3; i++) {
ret = usb_control_msg(hdev, usb_rcvctrlpipe(hdev, 0),
USB_REQ_GET_DESCRIPTOR, USB_DIR_IN | USB_RT_HUB,
- dtype << 8, 0, data, size,
+ dtype << 8, 0, desc, size,
USB_CTRL_GET_TIMEOUT);
- if (ret >= (USB_DT_HUB_NONVAR_SIZE + 2))
+ if (hub_is_superspeed(hdev)) {
+ if (ret == size)
+ return ret;
+ } else if (ret >= USB_DT_HUB_NONVAR_SIZE + 2) {
+ /* Make sure we have the DeviceRemovable field. */
+ size = USB_DT_HUB_NONVAR_SIZE + desc->bNbrPorts / 8 + 1;
+ if (ret < size)
+ return -EMSGSIZE;
return ret;
+ }
}
return -EINVAL;
}
}
mutex_init(&hub->status_mutex);
- hub->descriptor = kmalloc(sizeof(*hub->descriptor), GFP_KERNEL);
+ hub->descriptor = kzalloc(sizeof(*hub->descriptor), GFP_KERNEL);
if (!hub->descriptor) {
ret = -ENOMEM;
goto fail;
/* Request the entire hub descriptor.
* hub->descriptor can handle USB_MAXCHILDREN ports,
- * but the hub can/will return fewer bytes here.
+ * but a (non-SS) hub can/will return fewer bytes here.
*/
ret = get_hub_descriptor(hdev, hub->descriptor);
if (ret < 0) {
message = "can't read hub descriptor";
goto fail;
- } else if (hub->descriptor->bNbrPorts > USB_MAXCHILDREN) {
+ }
+
+ maxchild = USB_MAXCHILDREN;
+ if (hub_is_superspeed(hdev))
+ maxchild = min_t(unsigned, maxchild, USB_SS_MAXPORTS);
+
+ if (hub->descriptor->bNbrPorts > maxchild) {
message = "hub has too many ports!";
ret = -ENODEV;
goto fail;
*
* Find the companion device from platform bus.
*
+ * Takes a reference to the returned struct device which needs to be dropped
+ * after use.
+ *
* Return: On success, a pointer to the companion device, %NULL on failure.
*/
struct device *usb_of_get_companion_dev(struct device *dev)
if (!urb || !urb->complete)
return -EINVAL;
if (urb->hcpriv) {
- WARN_ONCE(1, "URB %p submitted while active\n", urb);
+ WARN_ONCE(1, "URB %pK submitted while active\n", urb);
return -EBUSY;
}
{ .compatible = "lantiq,xrx200-usb", .data = dwc2_set_ltq_params },
{ .compatible = "snps,dwc2" },
{ .compatible = "samsung,s3c6400-hsotg" },
+ { .compatible = "amlogic,meson8-usb",
+ .data = dwc2_set_amlogic_params },
{ .compatible = "amlogic,meson8b-usb",
.data = dwc2_set_amlogic_params },
{ .compatible = "amlogic,meson-gxbb-usb",
return PTR_ERR(kdwc->usbss);
kdwc->clk = devm_clk_get(kdwc->dev, "usb");
+ if (IS_ERR(kdwc->clk)) {
+ dev_err(kdwc->dev, "unable to get usb clock\n");
+ return PTR_ERR(kdwc->clk);
+ }
error = clk_prepare_enable(kdwc->clk);
if (error < 0) {
#define PCI_DEVICE_ID_INTEL_APL 0x5aaa
#define PCI_DEVICE_ID_INTEL_KBP 0xa2b0
#define PCI_DEVICE_ID_INTEL_GLK 0x31aa
+#define PCI_DEVICE_ID_INTEL_CNPLP 0x9dee
+#define PCI_DEVICE_ID_INTEL_CNPH 0xa36e
#define PCI_INTEL_BXT_DSM_UUID "732b85d5-b7a7-4a1b-9ba0-4bbd00ffd511"
#define PCI_INTEL_BXT_FUNC_PMU_PWR 4
{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_APL), },
{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBP), },
{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_GLK), },
+ { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CNPLP), },
+ { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CNPH), },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_NL_USB), },
{ } /* Terminating Entry */
};
__dwc3_gadget_start_isoc(dwc, dep, cur_uf);
dep->flags &= ~DWC3_EP_PENDING_REQUEST;
}
+ return 0;
}
- return 0;
+
+ if ((dep->flags & DWC3_EP_BUSY) &&
+ !(dep->flags & DWC3_EP_MISSED_ISOC)) {
+ WARN_ON_ONCE(!dep->resource_index);
+ ret = __dwc3_gadget_kick_transfer(dep,
+ dep->resource_index);
+ }
+
+ goto out;
}
if (!dwc3_calc_trbs_left(dep))
return 0;
ret = __dwc3_gadget_kick_transfer(dep, 0);
+out:
if (ret == -EBUSY)
ret = 0;
return IRQ_HANDLED;
}
+ /*
+ * With PCIe legacy interrupt, test shows that top-half irq handler can
+ * be called again after HW interrupt deassertion. Check if bottom-half
+ * irq event handler completes before caching new event to prevent
+ * losing events.
+ */
+ if (evt->flags & DWC3_EVENT_PENDING)
+ return IRQ_HANDLED;
+
count = dwc3_readl(dwc->regs, DWC3_GEVNTCOUNT(0));
count &= DWC3_GEVNTCOUNT_MASK;
if (!count)
ep->ep->driver_data = ep;
ep->ep->desc = ds;
- comp_desc = (struct usb_ss_ep_comp_descriptor *)(ds +
- USB_DT_ENDPOINT_SIZE);
- ep->ep->maxburst = comp_desc->bMaxBurst + 1;
-
- if (needs_comp_desc)
+ if (needs_comp_desc) {
+ comp_desc = (struct usb_ss_ep_comp_descriptor *)(ds +
+ USB_DT_ENDPOINT_SIZE);
+ ep->ep->maxburst = comp_desc->bMaxBurst + 1;
ep->ep->comp_desc = comp_desc;
+ }
ret = usb_ep_enable(ep->ep);
if (likely(!ret)) {
/* Caller must hold fsg->lock */
static void wakeup_thread(struct fsg_common *common)
{
- smp_wmb(); /* ensure the write of bh->state is complete */
+ /*
+ * Ensure the reading of thread_wakeup_needed
+ * and the writing of bh->state are completed
+ */
+ smp_mb();
/* Tell the main thread that something has happened */
common->thread_wakeup_needed = 1;
if (common->thread_task)
}
__set_current_state(TASK_RUNNING);
common->thread_wakeup_needed = 0;
- smp_rmb(); /* ensure the latest bh->state is visible */
+
+ /*
+ * Ensure the writing of thread_wakeup_needed
+ * and the reading of bh->state are completed
+ */
+ smp_mb();
return rc;
}
struct gscons_info *info = &gscons_info;
unregister_console(&gserial_cons);
- if (info->console_thread != NULL)
+ if (!IS_ERR_OR_NULL(info->console_thread))
kthread_stop(info->console_thread);
gs_buf_free(&info->con_buf);
}
HUB_CHAR_COMMON_OCPM);
desc->bNbrPorts = 1;
desc->u.ss.bHubHdrDecLat = 0x04; /* Worst case: 0.4 micro sec*/
- desc->u.ss.DeviceRemovable = 0xffff;
+ desc->u.ss.DeviceRemovable = 0;
}
static inline void hub_descriptor(struct usb_hub_descriptor *desc)
HUB_CHAR_INDV_PORT_LPSM |
HUB_CHAR_COMMON_OCPM);
desc->bNbrPorts = 1;
- desc->u.hs.DeviceRemovable[0] = 0xff;
- desc->u.hs.DeviceRemovable[1] = 0xff;
+ desc->u.hs.DeviceRemovable[0] = 0;
+ desc->u.hs.DeviceRemovable[1] = 0xff; /* PortPwrCtrlMask */
}
static int dummy_hub_control(
{
usb3_disconnect(usb3);
usb3_write(usb3, 0, USB3_P0_INT_ENA);
- usb3_write(usb3, 0, USB3_PN_INT_ENA);
usb3_write(usb3, 0, USB3_USB_OTG_INT_ENA);
usb3_write(usb3, 0, USB3_USB_INT_ENA_1);
usb3_write(usb3, 0, USB3_USB_INT_ENA_2);
struct renesas_usb3_request *usb3_req,
int status)
{
- usb3_pn_stop(usb3);
+ unsigned long flags;
+
+ spin_lock_irqsave(&usb3->lock, flags);
+ if (usb3_pn_change(usb3, usb3_ep->num))
+ usb3_pn_stop(usb3);
+ spin_unlock_irqrestore(&usb3->lock, flags);
+
usb3_disable_pipe_irq(usb3, usb3_ep->num);
usb3_request_done(usb3_ep, usb3_req, status);
{
struct renesas_usb3_ep *usb3_ep = usb3_get_ep(usb3, num);
struct renesas_usb3_request *usb3_req = usb3_get_request(usb3_ep);
+ bool done = false;
if (!usb3_req)
return;
+ spin_lock(&usb3->lock);
+ if (usb3_pn_change(usb3, num))
+ goto out;
+
if (usb3_ep->dir_in) {
/* Do not stop the IN pipe here to detect LSTTR interrupt */
if (!usb3_write_pipe(usb3_ep, usb3_req, USB3_PN_WRITE))
usb3_clear_bit(usb3, PN_INT_BFRDY, USB3_PN_INT_ENA);
} else {
if (!usb3_read_pipe(usb3_ep, usb3_req, USB3_PN_READ))
- usb3_request_done_pipen(usb3, usb3_ep, usb3_req, 0);
+ done = true;
}
+
+out:
+ /* need to unlock because usb3_request_done_pipen() locks it */
+ spin_unlock(&usb3->lock);
+
+ if (done)
+ usb3_request_done_pipen(usb3, usb3_ep, usb3_req, 0);
}
static void usb3_irq_epc_pipen(struct renesas_usb3 *usb3, int num)
{
u32 pn_int_sta;
- if (usb3_pn_change(usb3, num) < 0)
+ spin_lock(&usb3->lock);
+ if (usb3_pn_change(usb3, num) < 0) {
+ spin_unlock(&usb3->lock);
return;
+ }
pn_int_sta = usb3_read(usb3, USB3_PN_INT_STA);
pn_int_sta &= usb3_read(usb3, USB3_PN_INT_ENA);
usb3_write(usb3, pn_int_sta, USB3_PN_INT_STA);
+ spin_unlock(&usb3->lock);
if (pn_int_sta & PN_INT_LSTTR)
usb3_irq_epc_pipen_lsttr(usb3, num);
if (pn_int_sta & PN_INT_BFRDY)
spin_lock_irqsave(&usb3->lock, flags);
if (!usb3_pn_change(usb3, usb3_ep->num)) {
+ usb3_write(usb3, 0, USB3_PN_INT_ENA);
usb3_write(usb3, 0, USB3_PN_RAMMAP);
usb3_clear_bit(usb3, PN_CON_EN, USB3_PN_CON);
}
/* hook up the driver */
usb3->driver = driver;
+ pm_runtime_enable(usb3_to_dev(usb3));
+ pm_runtime_get_sync(usb3_to_dev(usb3));
+
renesas_usb3_init_controller(usb3);
return 0;
static int renesas_usb3_stop(struct usb_gadget *gadget)
{
struct renesas_usb3 *usb3 = gadget_to_renesas_usb3(gadget);
- unsigned long flags;
- spin_lock_irqsave(&usb3->lock, flags);
usb3->softconnect = false;
usb3->gadget.speed = USB_SPEED_UNKNOWN;
usb3->driver = NULL;
renesas_usb3_stop_controller(usb3);
- spin_unlock_irqrestore(&usb3->lock, flags);
+
+ pm_runtime_put(usb3_to_dev(usb3));
+ pm_runtime_disable(usb3_to_dev(usb3));
return 0;
}
device_remove_file(&pdev->dev, &dev_attr_role);
- pm_runtime_put(&pdev->dev);
- pm_runtime_disable(&pdev->dev);
-
usb_del_gadget_udc(&usb3->gadget);
__renesas_usb3_ep_free_request(usb3->ep0_req);
usb3->workaround_for_vbus = priv->workaround_for_vbus;
- pm_runtime_enable(&pdev->dev);
- pm_runtime_get_sync(&pdev->dev);
-
dev_info(&pdev->dev, "probed\n");
return 0;
}
companion_dev = usb_of_get_companion_dev(hcd->self.controller);
- if (companion_dev)
+ if (companion_dev) {
device_pm_wait_for_dev(hcd->self.controller, companion_dev);
+ put_device(companion_dev);
+ }
ehci_resume(hcd, priv->reset_on_resume);
return 0;
time = 30;
break;
default:
- time = 300;
+ time = 50;
break;
}
pipe = td->pipe;
pipe_stop(r8a66597, pipe);
+ /* Select a different address or endpoint */
new_td = td;
do {
list_move_tail(&new_td->queue,
new_td = td;
break;
}
- } while (td != new_td && td->address == new_td->address);
+ } while (td != new_td && td->address == new_td->address &&
+ td->pipe->info.epnum == new_td->pipe->info.epnum);
start_transfer(r8a66597, new_td);
wait_for_completion(cmd->completion);
if (cmd->status == COMP_COMMAND_ABORTED ||
- cmd->status == COMP_STOPPED) {
+ cmd->status == COMP_COMMAND_RING_STOPPED) {
xhci_warn(xhci, "Timeout while waiting for stop endpoint command\n");
ret = -ETIME;
}
}
if (max_packet) {
- seg->bounce_buf = kzalloc(max_packet, flags | GFP_DMA);
+ seg->bounce_buf = kzalloc(max_packet, flags);
if (!seg->bounce_buf) {
dma_pool_free(xhci->segment_pool, seg->trbs, dma);
kfree(seg);
xhci->dcbaa->dev_context_ptrs[0] = cpu_to_le64(xhci->scratchpad->sp_dma);
for (i = 0; i < num_sp; i++) {
dma_addr_t dma;
- void *buf = dma_alloc_coherent(dev, xhci->page_size, &dma,
+ void *buf = dma_zalloc_coherent(dev, xhci->page_size, &dma,
flags);
if (!buf)
goto fail_sp4;
/* Place limits on the number of roothub ports so that the hub
* descriptors aren't longer than the USB core will allocate.
*/
- if (xhci->num_usb3_ports > 15) {
+ if (xhci->num_usb3_ports > USB_SS_MAXPORTS) {
xhci_dbg_trace(xhci, trace_xhci_dbg_init,
- "Limiting USB 3.0 roothub ports to 15.");
- xhci->num_usb3_ports = 15;
+ "Limiting USB 3.0 roothub ports to %u.",
+ USB_SS_MAXPORTS);
+ xhci->num_usb3_ports = USB_SS_MAXPORTS;
}
if (xhci->num_usb2_ports > USB_MAXCHILDREN) {
xhci_dbg_trace(xhci, trace_xhci_dbg_init,
#define PCI_DEVICE_ID_INTEL_BROXTON_M_XHCI 0x0aa8
#define PCI_DEVICE_ID_INTEL_BROXTON_B_XHCI 0x1aa8
#define PCI_DEVICE_ID_INTEL_APL_XHCI 0x5aa8
+#define PCI_DEVICE_ID_INTEL_DNV_XHCI 0x19d0
static const char hcd_name[] = "xhci_hcd";
pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI ||
pdev->device == PCI_DEVICE_ID_INTEL_BROXTON_M_XHCI ||
pdev->device == PCI_DEVICE_ID_INTEL_BROXTON_B_XHCI ||
- pdev->device == PCI_DEVICE_ID_INTEL_APL_XHCI)) {
+ pdev->device == PCI_DEVICE_ID_INTEL_APL_XHCI ||
+ pdev->device == PCI_DEVICE_ID_INTEL_DNV_XHCI)) {
xhci->quirks |= XHCI_PME_STUCK_QUIRK;
}
if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
}
if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
(pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI ||
- pdev->device == PCI_DEVICE_ID_INTEL_APL_XHCI))
+ pdev->device == PCI_DEVICE_ID_INTEL_APL_XHCI ||
+ pdev->device == PCI_DEVICE_ID_INTEL_DNV_XHCI))
xhci->quirks |= XHCI_MISSING_CAS;
if (pdev->vendor == PCI_VENDOR_ID_ETRON &&
irq = platform_get_irq(pdev, 0);
if (irq < 0)
- return -ENODEV;
+ return irq;
/*
* sysdev must point to a device that is known to the system firmware
if (i_cmd->status != COMP_COMMAND_ABORTED)
continue;
- i_cmd->status = COMP_STOPPED;
+ i_cmd->status = COMP_COMMAND_RING_STOPPED;
xhci_dbg(xhci, "Turn aborted command %p to no-op\n",
i_cmd->command_trb);
xhci_urb_free_priv(urb_priv);
usb_hcd_unlink_urb_from_ep(hcd, urb);
spin_unlock(&xhci->lock);
- usb_hcd_giveback_urb(hcd, urb, status);
trace_xhci_urb_giveback(urb);
+ usb_hcd_giveback_urb(hcd, urb, status);
spin_lock(&xhci->lock);
}
cmd_comp_code = GET_COMP_CODE(le32_to_cpu(event->status));
/* If CMD ring stopped we own the trbs between enqueue and dequeue */
- if (cmd_comp_code == COMP_STOPPED) {
+ if (cmd_comp_code == COMP_COMMAND_RING_STOPPED) {
complete_all(&xhci->cmd_ring_stop_completion);
return;
}
break;
case TRB_CMD_NOOP:
/* Is this an aborted command turned to NO-OP? */
- if (cmd->status == COMP_STOPPED)
- cmd_comp_code = COMP_STOPPED;
+ if (cmd->status == COMP_COMMAND_RING_STOPPED)
+ cmd_comp_code = COMP_COMMAND_RING_STOPPED;
break;
case TRB_RESET_EP:
WARN_ON(slot_id != TRB_TO_SLOT_ID(
struct xhci_hcd *xhci = hcd_to_xhci(hcd);
union xhci_trb *event_ring_deq;
irqreturn_t ret = IRQ_NONE;
+ unsigned long flags;
dma_addr_t deq;
u64 temp_64;
u32 status;
- spin_lock(&xhci->lock);
+ spin_lock_irqsave(&xhci->lock, flags);
/* Check if the xHC generated the interrupt, or the irq is shared */
status = readl(&xhci->op_regs->status);
if (status == ~(u32)0) {
*/
status |= STS_EINT;
writel(status, &xhci->op_regs->status);
- /* FIXME when MSI-X is supported and there are multiple vectors */
- /* Clear the MSI-X event interrupt status */
- if (hcd->irq) {
+ if (!hcd->msi_enabled) {
u32 irq_pending;
- /* Acknowledge the PCI interrupt */
irq_pending = readl(&xhci->ir_set->irq_pending);
irq_pending |= IMAN_IP;
writel(irq_pending, &xhci->ir_set->irq_pending);
ret = IRQ_HANDLED;
out:
- spin_unlock(&xhci->lock);
+ spin_unlock_irqrestore(&xhci->lock, flags);
return ret;
}
/* fall back to msi*/
ret = xhci_setup_msi(xhci);
- if (!ret)
- /* hcd->irq is 0, we have MSI */
+ if (!ret) {
+ hcd->msi_enabled = 1;
return 0;
+ }
if (!pdev->irq) {
xhci_err(xhci, "No msi-x/msi found and no IRQ in BIOS\n");
switch (*cmd_status) {
case COMP_COMMAND_ABORTED:
- case COMP_STOPPED:
+ case COMP_COMMAND_RING_STOPPED:
xhci_warn(xhci, "Timeout while waiting for configure endpoint command\n");
ret = -ETIME;
break;
switch (*cmd_status) {
case COMP_COMMAND_ABORTED:
- case COMP_STOPPED:
+ case COMP_COMMAND_RING_STOPPED:
xhci_warn(xhci, "Timeout while waiting for evaluate context command\n");
ret = -ETIME;
break;
ret = reset_device_cmd->status;
switch (ret) {
case COMP_COMMAND_ABORTED:
- case COMP_STOPPED:
+ case COMP_COMMAND_RING_STOPPED:
xhci_warn(xhci, "Timeout waiting for reset device command\n");
ret = -ETIME;
goto command_cleanup;
*/
switch (command->status) {
case COMP_COMMAND_ABORTED:
- case COMP_STOPPED:
+ case COMP_COMMAND_RING_STOPPED:
xhci_warn(xhci, "Timeout while waiting for setup device command\n");
ret = -ETIME;
break;
dev->in_ep = in_ep;
- if (udev->descriptor.idVendor != ALEA_VENDOR_ID)
+ if (le16_to_cpu(udev->descriptor.idVendor) != ALEA_VENDOR_ID)
dev->reads_started = 1;
dev->size = size;
info.revision = le16_to_cpu(dev->udev->descriptor.bcdDevice);
/* 0==UNKNOWN, 1==LOW(usb1.1) ,2=FULL(usb1.1), 3=HIGH(usb2.0) */
- info.speed = le16_to_cpu(dev->udev->speed);
+ info.speed = dev->udev->speed;
info.if_num = dev->interface->cur_altsetting->desc.bInterfaceNumber;
info.report_size = dev->report_size;
USB_MAJOR, dev->minor);
exit:
+ kfree(get_version_reply);
return retval;
error:
mutex_unlock(&sisusb->lock);
- return 1;
+ return true;
}
/* Interface routine */
dsps_mod_timer_optional(glue);
break;
case OTG_STATE_A_WAIT_BCON:
+ /* keep VBUS on for host-only mode */
+ if (musb->port_mode == MUSB_PORT_MODE_HOST) {
+ dsps_mod_timer_optional(glue);
+ break;
+ }
musb_writeb(musb->mregs, MUSB_DEVCTL, 0);
skip_session = 1;
/* fall */
int ret;
struct usb_hcd *hcd = musb->hcd;
- MUSB_HST_MODE(musb);
- musb->xceiv->otg->default_a = 1;
- musb->xceiv->otg->state = OTG_STATE_A_IDLE;
-
+ if (musb->port_mode == MUSB_PORT_MODE_HOST) {
+ MUSB_HST_MODE(musb);
+ musb->xceiv->otg->default_a = 1;
+ musb->xceiv->otg->state = OTG_STATE_A_IDLE;
+ }
otg_set_host(musb->xceiv->otg, &hcd->self);
hcd->self.otg_port = 1;
musb->xceiv->otg->host = &hcd->self;
u32 dma_remaining;
int src_burst, dst_burst;
u16 csr;
+ u32 psize;
int ch;
s8 dmareq;
s8 sync_dev;
if (chdat->tx) {
/* Send transfer_packet_sz packets at a time */
- musb_writel(ep_conf, TUSB_EP_MAX_PACKET_SIZE_OFFSET,
- chdat->transfer_packet_sz);
+ psize = musb_readl(ep_conf, TUSB_EP_MAX_PACKET_SIZE_OFFSET);
+ psize &= ~0x7ff;
+ psize |= chdat->transfer_packet_sz;
+ musb_writel(ep_conf, TUSB_EP_MAX_PACKET_SIZE_OFFSET, psize);
musb_writel(ep_conf, TUSB_EP_TX_OFFSET,
TUSB_EP_CONFIG_XFR_SIZE(chdat->transfer_len));
} else {
/* Receive transfer_packet_sz packets at a time */
- musb_writel(ep_conf, TUSB_EP_MAX_PACKET_SIZE_OFFSET,
- chdat->transfer_packet_sz << 16);
+ psize = musb_readl(ep_conf, TUSB_EP_MAX_PACKET_SIZE_OFFSET);
+ psize &= ~(0x7ff << 16);
+ psize |= (chdat->transfer_packet_sz << 16);
+ musb_writel(ep_conf, TUSB_EP_MAX_PACKET_SIZE_OFFSET, psize);
musb_writel(ep_conf, TUSB_EP_RX_OFFSET,
TUSB_EP_CONFIG_XFR_SIZE(chdat->transfer_len));
{ USB_DEVICE(FTDI_VID, FTDI_PROPOX_ISPCABLEIII_PID) },
{ USB_DEVICE(FTDI_VID, CYBER_CORTEX_AV_PID),
.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
- { USB_DEVICE(OLIMEX_VID, OLIMEX_ARM_USB_OCD_PID),
- .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
- { USB_DEVICE(OLIMEX_VID, OLIMEX_ARM_USB_OCD_H_PID),
- .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
+ { USB_DEVICE_INTERFACE_NUMBER(OLIMEX_VID, OLIMEX_ARM_USB_OCD_PID, 1) },
+ { USB_DEVICE_INTERFACE_NUMBER(OLIMEX_VID, OLIMEX_ARM_USB_OCD_H_PID, 1) },
+ { USB_DEVICE_INTERFACE_NUMBER(OLIMEX_VID, OLIMEX_ARM_USB_TINY_PID, 1) },
+ { USB_DEVICE_INTERFACE_NUMBER(OLIMEX_VID, OLIMEX_ARM_USB_TINY_H_PID, 1) },
{ USB_DEVICE(FIC_VID, FIC_NEO1973_DEBUG_PID),
.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
{ USB_DEVICE(FTDI_VID, FTDI_OOCDLINK_PID),
(new_serial.flags & ASYNC_FLAGS));
priv->custom_divisor = new_serial.custom_divisor;
+check_and_exit:
write_latency_timer(port);
-check_and_exit:
if ((old_priv.flags & ASYNC_SPD_MASK) !=
(priv->flags & ASYNC_SPD_MASK)) {
if ((priv->flags & ASYNC_SPD_MASK) == ASYNC_SPD_HI)
/* Olimex */
#define OLIMEX_VID 0x15BA
#define OLIMEX_ARM_USB_OCD_PID 0x0003
+#define OLIMEX_ARM_USB_TINY_PID 0x0004
+#define OLIMEX_ARM_USB_TINY_H_PID 0x002a
#define OLIMEX_ARM_USB_OCD_H_PID 0x002b
/*
if (!baud) {
/* pick a default, any default... */
baud = 9600;
- } else
+ } else {
+ /* Avoid a zero divisor. */
+ baud = min(baud, 461550);
tty_encode_baud_rate(tty, baud, baud);
+ }
edge_port->baud_rate = baud;
config->wBaudRate = (__u16)((461550L + baud/2) / baud);
static int ir_startup(struct usb_serial *serial)
{
struct usb_irda_cs_descriptor *irda_desc;
+ int rates;
irda_desc = irda_usb_find_class_desc(serial, 0);
if (!irda_desc) {
return -ENODEV;
}
+ rates = le16_to_cpu(irda_desc->wBaudRate);
+
dev_dbg(&serial->dev->dev,
"%s - Baud rates supported:%s%s%s%s%s%s%s%s%s\n",
__func__,
- (irda_desc->wBaudRate & USB_IRDA_BR_2400) ? " 2400" : "",
- (irda_desc->wBaudRate & USB_IRDA_BR_9600) ? " 9600" : "",
- (irda_desc->wBaudRate & USB_IRDA_BR_19200) ? " 19200" : "",
- (irda_desc->wBaudRate & USB_IRDA_BR_38400) ? " 38400" : "",
- (irda_desc->wBaudRate & USB_IRDA_BR_57600) ? " 57600" : "",
- (irda_desc->wBaudRate & USB_IRDA_BR_115200) ? " 115200" : "",
- (irda_desc->wBaudRate & USB_IRDA_BR_576000) ? " 576000" : "",
- (irda_desc->wBaudRate & USB_IRDA_BR_1152000) ? " 1152000" : "",
- (irda_desc->wBaudRate & USB_IRDA_BR_4000000) ? " 4000000" : "");
+ (rates & USB_IRDA_BR_2400) ? " 2400" : "",
+ (rates & USB_IRDA_BR_9600) ? " 9600" : "",
+ (rates & USB_IRDA_BR_19200) ? " 19200" : "",
+ (rates & USB_IRDA_BR_38400) ? " 38400" : "",
+ (rates & USB_IRDA_BR_57600) ? " 57600" : "",
+ (rates & USB_IRDA_BR_115200) ? " 115200" : "",
+ (rates & USB_IRDA_BR_576000) ? " 576000" : "",
+ (rates & USB_IRDA_BR_1152000) ? " 1152000" : "",
+ (rates & USB_IRDA_BR_4000000) ? " 4000000" : "");
switch (irda_desc->bmAdditionalBOFs) {
case USB_IRDA_AB_48:
return -ENOMEM;
divisor = mct_u232_calculate_baud_rate(serial, value, &speed);
- put_unaligned_le32(cpu_to_le32(divisor), buf);
+ put_unaligned_le32(divisor, buf);
rc = usb_control_msg(serial->dev, usb_sndctrlpipe(serial->dev, 0),
MCT_U232_SET_BAUD_RATE_REQUEST,
MCT_U232_SET_REQUEST_TYPE,
#define TELIT_PRODUCT_LE922_USBCFG0 0x1042
#define TELIT_PRODUCT_LE922_USBCFG3 0x1043
#define TELIT_PRODUCT_LE922_USBCFG5 0x1045
+#define TELIT_PRODUCT_ME910 0x1100
#define TELIT_PRODUCT_LE920 0x1200
#define TELIT_PRODUCT_LE910 0x1201
#define TELIT_PRODUCT_LE910_USBCFG4 0x1206
.reserved = BIT(5) | BIT(6),
};
+static const struct option_blacklist_info telit_me910_blacklist = {
+ .sendsetup = BIT(0),
+ .reserved = BIT(1) | BIT(3),
+};
+
static const struct option_blacklist_info telit_le910_blacklist = {
.sendsetup = BIT(0),
.reserved = BIT(1) | BIT(2),
.driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg3 },
{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG5, 0xff),
.driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg0 },
+ { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910),
+ .driver_info = (kernel_ulong_t)&telit_me910_blacklist },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910),
.driver_info = (kernel_ulong_t)&telit_le910_blacklist },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910_USBCFG4),
{DEVICE_SWI(0x1199, 0x9071)}, /* Sierra Wireless MC74xx */
{DEVICE_SWI(0x1199, 0x9078)}, /* Sierra Wireless EM74xx */
{DEVICE_SWI(0x1199, 0x9079)}, /* Sierra Wireless EM74xx */
+ {DEVICE_SWI(0x1199, 0x907a)}, /* Sierra Wireless EM74xx QDL */
+ {DEVICE_SWI(0x1199, 0x907b)}, /* Sierra Wireless EM74xx */
{DEVICE_SWI(0x413c, 0x81a2)}, /* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card */
{DEVICE_SWI(0x413c, 0x81a3)}, /* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card */
{DEVICE_SWI(0x413c, 0x81a4)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */
#define SD_BLOCK_LEN 9
struct ene_ub6250_info {
+
+ /* I/O bounce buffer */
+ u8 *bbuf;
+
/* for 6250 code */
struct SD_STATUS SD_Status;
struct MS_STATUS MS_Status;
static void ene_ub6250_info_destructor(void *extra)
{
+ struct ene_ub6250_info *info = (struct ene_ub6250_info *) extra;
+
if (!extra)
return;
+ kfree(info->bbuf);
}
static int ene_send_scsi_cmd(struct us_data *us, u8 fDir, void *buf, int use_sg)
u8 PageNum, u32 *PageBuf, struct ms_lib_type_extdat *ExtraDat)
{
struct bulk_cb_wrap *bcb = (struct bulk_cb_wrap *) us->iobuf;
+ struct ene_ub6250_info *info = (struct ene_ub6250_info *) us->extra;
+ u8 *bbuf = info->bbuf;
int result;
- u8 ExtBuf[4];
u32 bn = PhyBlockAddr * 0x20 + PageNum;
result = ene_load_bincode(us, MS_RW_PATTERN);
bcb->CDB[2] = (unsigned char)(PhyBlockAddr>>16);
bcb->CDB[6] = 0x01;
- result = ene_send_scsi_cmd(us, FDIR_READ, &ExtBuf, 0);
+ result = ene_send_scsi_cmd(us, FDIR_READ, bbuf, 0);
if (result != USB_STOR_XFER_GOOD)
return USB_STOR_TRANSPORT_ERROR;
ExtraDat->status0 = 0x10; /* Not yet,fireware support */
ExtraDat->status1 = 0x00; /* Not yet,fireware support */
- ExtraDat->ovrflg = ExtBuf[0];
- ExtraDat->mngflg = ExtBuf[1];
- ExtraDat->logadr = memstick_logaddr(ExtBuf[2], ExtBuf[3]);
+ ExtraDat->ovrflg = bbuf[0];
+ ExtraDat->mngflg = bbuf[1];
+ ExtraDat->logadr = memstick_logaddr(bbuf[2], bbuf[3]);
return USB_STOR_TRANSPORT_GOOD;
}
u8 PageNum, struct ms_lib_type_extdat *ExtraDat)
{
struct bulk_cb_wrap *bcb = (struct bulk_cb_wrap *) us->iobuf;
+ struct ene_ub6250_info *info = (struct ene_ub6250_info *) us->extra;
+ u8 *bbuf = info->bbuf;
int result;
- u8 ExtBuf[4];
memset(bcb, 0, sizeof(struct bulk_cb_wrap));
bcb->Signature = cpu_to_le32(US_BULK_CB_SIGN);
bcb->CDB[2] = (unsigned char)(PhyBlock>>16);
bcb->CDB[6] = 0x01;
- result = ene_send_scsi_cmd(us, FDIR_READ, &ExtBuf, 0);
+ result = ene_send_scsi_cmd(us, FDIR_READ, bbuf, 0);
if (result != USB_STOR_XFER_GOOD)
return USB_STOR_TRANSPORT_ERROR;
ExtraDat->intr = 0x80; /* Not yet, waiting for fireware support */
ExtraDat->status0 = 0x10; /* Not yet, waiting for fireware support */
ExtraDat->status1 = 0x00; /* Not yet, waiting for fireware support */
- ExtraDat->ovrflg = ExtBuf[0];
- ExtraDat->mngflg = ExtBuf[1];
- ExtraDat->logadr = memstick_logaddr(ExtBuf[2], ExtBuf[3]);
+ ExtraDat->ovrflg = bbuf[0];
+ ExtraDat->mngflg = bbuf[1];
+ ExtraDat->logadr = memstick_logaddr(bbuf[2], bbuf[3]);
return USB_STOR_TRANSPORT_GOOD;
}
u16 PhyBlock, newblk, i;
u16 LogStart, LogEnde;
struct ms_lib_type_extdat extdat;
- u8 buf[0x200];
u32 count = 0, index = 0;
struct ene_ub6250_info *info = (struct ene_ub6250_info *) us->extra;
+ u8 *bbuf = info->bbuf;
for (PhyBlock = 0; PhyBlock < info->MS_Lib.NumberOfPhyBlock;) {
ms_lib_phy_to_log_range(PhyBlock, &LogStart, &LogEnde);
}
if (count == PhyBlock) {
- ms_lib_read_extrablock(us, PhyBlock, 0, 0x80, &buf);
+ ms_lib_read_extrablock(us, PhyBlock, 0, 0x80,
+ bbuf);
count += 0x80;
}
index = (PhyBlock % 0x80) * 4;
- extdat.ovrflg = buf[index];
- extdat.mngflg = buf[index+1];
- extdat.logadr = memstick_logaddr(buf[index+2], buf[index+3]);
+ extdat.ovrflg = bbuf[index];
+ extdat.mngflg = bbuf[index+1];
+ extdat.logadr = memstick_logaddr(bbuf[index+2],
+ bbuf[index+3]);
if ((extdat.ovrflg & MS_REG_OVR_BKST) != MS_REG_OVR_BKST_OK) {
ms_lib_setacquired_errorblock(us, PhyBlock);
{
struct bulk_cb_wrap *bcb = (struct bulk_cb_wrap *) us->iobuf;
int result;
- u8 buf[0x200];
u16 MSP_BlockSize, MSP_UserAreaBlocks;
struct ene_ub6250_info *info = (struct ene_ub6250_info *) us->extra;
+ u8 *bbuf = info->bbuf;
printk(KERN_INFO "transport --- ENE_MSInit\n");
bcb->CDB[0] = 0xF1;
bcb->CDB[1] = 0x01;
- result = ene_send_scsi_cmd(us, FDIR_READ, &buf, 0);
+ result = ene_send_scsi_cmd(us, FDIR_READ, bbuf, 0);
if (result != USB_STOR_XFER_GOOD) {
printk(KERN_ERR "Execution MS Init Code Fail !!\n");
return USB_STOR_TRANSPORT_ERROR;
}
/* the same part to test ENE */
- info->MS_Status = *(struct MS_STATUS *)&buf[0];
+ info->MS_Status = *(struct MS_STATUS *) bbuf;
if (info->MS_Status.Insert && info->MS_Status.Ready) {
printk(KERN_INFO "Insert = %x\n", info->MS_Status.Insert);
printk(KERN_INFO "IsMSPHG = %x\n", info->MS_Status.IsMSPHG);
printk(KERN_INFO "WtP= %x\n", info->MS_Status.WtP);
if (info->MS_Status.IsMSPro) {
- MSP_BlockSize = (buf[6] << 8) | buf[7];
- MSP_UserAreaBlocks = (buf[10] << 8) | buf[11];
+ MSP_BlockSize = (bbuf[6] << 8) | bbuf[7];
+ MSP_UserAreaBlocks = (bbuf[10] << 8) | bbuf[11];
info->MSP_TotalBlock = MSP_BlockSize * MSP_UserAreaBlocks;
} else {
ms_card_init(us); /* Card is MS (to ms.c)*/
}
usb_stor_dbg(us, "MS Init Code OK !!\n");
} else {
- usb_stor_dbg(us, "MS Card Not Ready --- %x\n", buf[0]);
+ usb_stor_dbg(us, "MS Card Not Ready --- %x\n", bbuf[0]);
return USB_STOR_TRANSPORT_ERROR;
}
static int ene_sd_init(struct us_data *us)
{
int result;
- u8 buf[0x200];
struct bulk_cb_wrap *bcb = (struct bulk_cb_wrap *) us->iobuf;
struct ene_ub6250_info *info = (struct ene_ub6250_info *) us->extra;
+ u8 *bbuf = info->bbuf;
usb_stor_dbg(us, "transport --- ENE_SDInit\n");
/* SD Init Part-1 */
bcb->Flags = US_BULK_FLAG_IN;
bcb->CDB[0] = 0xF1;
- result = ene_send_scsi_cmd(us, FDIR_READ, &buf, 0);
+ result = ene_send_scsi_cmd(us, FDIR_READ, bbuf, 0);
if (result != USB_STOR_XFER_GOOD) {
usb_stor_dbg(us, "Execution SD Init Code Fail !!\n");
return USB_STOR_TRANSPORT_ERROR;
}
- info->SD_Status = *(struct SD_STATUS *)&buf[0];
+ info->SD_Status = *(struct SD_STATUS *) bbuf;
if (info->SD_Status.Insert && info->SD_Status.Ready) {
struct SD_STATUS *s = &info->SD_Status;
- ene_get_card_status(us, (unsigned char *)&buf);
+ ene_get_card_status(us, bbuf);
usb_stor_dbg(us, "Insert = %x\n", s->Insert);
usb_stor_dbg(us, "Ready = %x\n", s->Ready);
usb_stor_dbg(us, "IsMMC = %x\n", s->IsMMC);
usb_stor_dbg(us, "HiSpeed = %x\n", s->HiSpeed);
usb_stor_dbg(us, "WtP = %x\n", s->WtP);
} else {
- usb_stor_dbg(us, "SD Card Not Ready --- %x\n", buf[0]);
+ usb_stor_dbg(us, "SD Card Not Ready --- %x\n", bbuf[0]);
return USB_STOR_TRANSPORT_ERROR;
}
return USB_STOR_TRANSPORT_GOOD;
static int ene_init(struct us_data *us)
{
int result;
- u8 misc_reg03 = 0;
+ u8 misc_reg03;
struct ene_ub6250_info *info = (struct ene_ub6250_info *)(us->extra);
+ u8 *bbuf = info->bbuf;
- result = ene_get_card_type(us, REG_CARD_STATUS, &misc_reg03);
+ result = ene_get_card_type(us, REG_CARD_STATUS, bbuf);
if (result != USB_STOR_XFER_GOOD)
return USB_STOR_TRANSPORT_ERROR;
+ misc_reg03 = bbuf[0];
if (misc_reg03 & 0x01) {
if (!info->SD_Status.Ready) {
result = ene_sd_init(us);
const struct usb_device_id *id)
{
int result;
- u8 misc_reg03 = 0;
+ u8 misc_reg03;
struct us_data *us;
+ struct ene_ub6250_info *info;
result = usb_stor_probe1(&us, intf, id,
(id - ene_ub6250_usb_ids) + ene_ub6250_unusual_dev_list,
return result;
/* FIXME: where should the code alloc extra buf ? */
- if (!us->extra) {
- us->extra = kzalloc(sizeof(struct ene_ub6250_info), GFP_KERNEL);
- if (!us->extra)
- return -ENOMEM;
- us->extra_destructor = ene_ub6250_info_destructor;
+ us->extra = kzalloc(sizeof(struct ene_ub6250_info), GFP_KERNEL);
+ if (!us->extra)
+ return -ENOMEM;
+ us->extra_destructor = ene_ub6250_info_destructor;
+
+ info = (struct ene_ub6250_info *)(us->extra);
+ info->bbuf = kmalloc(512, GFP_KERNEL);
+ if (!info->bbuf) {
+ kfree(us->extra);
+ return -ENOMEM;
}
us->transport_name = "ene_ub6250";
return result;
/* probe card type */
- result = ene_get_card_type(us, REG_CARD_STATUS, &misc_reg03);
+ result = ene_get_card_type(us, REG_CARD_STATUS, info->bbuf);
if (result != USB_STOR_XFER_GOOD) {
usb_stor_disconnect(intf);
return USB_STOR_TRANSPORT_ERROR;
}
+ misc_reg03 = info->bbuf[0];
if (!(misc_reg03 & 0x01)) {
pr_info("ums_eneub6250: This driver only supports SD/MS cards. "
"It does not support SM cards.\n");
static inline void hub_descriptor(struct usb_hub_descriptor *desc)
{
+ int width;
+
memset(desc, 0, sizeof(*desc));
desc->bDescriptorType = USB_DT_HUB;
- desc->bDescLength = 9;
desc->wHubCharacteristics = cpu_to_le16(
HUB_CHAR_INDV_PORT_LPSM | HUB_CHAR_COMMON_OCPM);
+
desc->bNbrPorts = VHCI_HC_PORTS;
- desc->u.hs.DeviceRemovable[0] = 0xff;
- desc->u.hs.DeviceRemovable[1] = 0xff;
+ BUILD_BUG_ON(VHCI_HC_PORTS > USB_MAXCHILDREN);
+ width = desc->bNbrPorts / 8 + 1;
+ desc->bDescLength = USB_DT_HUB_NONVAR_SIZE + 2 * width;
+ memset(&desc->u.hs.DeviceRemovable[0], 0, width);
+ memset(&desc->u.hs.DeviceRemovable[width], 0xff, width);
}
static int vhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
static
int i1480_usb_probe(struct usb_interface *iface, const struct usb_device_id *id)
{
+ struct usb_device *udev = interface_to_usbdev(iface);
struct i1480_usb *i1480_usb;
struct i1480 *i1480;
struct device *dev = &iface->dev;
iface->cur_altsetting->desc.bInterfaceNumber);
goto error;
}
- if (iface->num_altsetting > 1
- && interface_to_usbdev(iface)->descriptor.idProduct == 0xbabe) {
+ if (iface->num_altsetting > 1 &&
+ le16_to_cpu(udev->descriptor.idProduct) == 0xbabe) {
/* Need altsetting #1 [HW QUIRK] or EP1 won't work */
result = usb_set_interface(interface_to_usbdev(iface), 0, 1);
if (result < 0)
config ORION_WATCHDOG
tristate "Orion watchdog"
- depends on ARCH_ORION5X || ARCH_DOVE || MACH_DOVE || ARCH_MVEBU || COMPILE_TEST
+ depends on ARCH_ORION5X || ARCH_DOVE || MACH_DOVE || ARCH_MVEBU || (COMPILE_TEST && !ARCH_EBSA110)
depends on ARM
select WATCHDOG_CORE
help
if (!wdt)
return -ENOMEM;
+ spin_lock_init(&wdt->lock);
+
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
wdt->base = devm_ioremap_resource(dev, res);
if (IS_ERR(wdt->base))
return ret;
}
- spin_lock_init(&wdt->lock);
platform_set_drvdata(pdev, wdt);
watchdog_set_drvdata(&bcm_kona_wdt_wdd, wdt);
bcm_kona_wdt_wdd.parent = &pdev->dev;
/* Counter maximum value */
#define CDNS_WDT_COUNTER_MAX 0xFFF
-static int wdt_timeout = CDNS_WDT_DEFAULT_TIMEOUT;
+static int wdt_timeout;
static int nowayout = WATCHDOG_NOWAYOUT;
module_param(wdt_timeout, int, 0);
iTCO_vendor_pre_keepalive(p->smi_res, wd_dev->timeout);
+ /* Reset the timeout status bit so that the timer
+ * needs to count down twice again before rebooting */
+ outw(0x0008, TCO1_STS(p)); /* write 1 to clear bit */
+
/* Reload the timer by writing to the TCO Timer Counter register */
- if (p->iTCO_version >= 2) {
+ if (p->iTCO_version >= 2)
outw(0x01, TCO_RLD(p));
- } else if (p->iTCO_version == 1) {
- /* Reset the timeout status bit so that the timer
- * needs to count down twice again before rebooting */
- outw(0x0008, TCO1_STS(p)); /* write 1 to clear bit */
-
+ else if (p->iTCO_version == 1)
outb(0x01, TCO_RLD(p));
- }
spin_unlock(&p->io_lock);
return 0;
unsigned char val8;
unsigned int tmrval;
- tmrval = seconds_to_ticks(p, t);
-
- /* For TCO v1 the timer counts down twice before rebooting */
- if (p->iTCO_version == 1)
- tmrval /= 2;
+ /* The timer counts down twice before rebooting */
+ tmrval = seconds_to_ticks(p, t) / 2;
/* from the specs: */
/* "Values of 0h-3h are ignored and should not be attempted" */
spin_lock(&p->io_lock);
val16 = inw(TCO_RLD(p));
val16 &= 0x3ff;
+ if (!(inw(TCO1_STS(p)) & 0x0008))
+ val16 += (inw(TCOv2_TMR(p)) & 0x3ff);
spin_unlock(&p->io_lock);
time_left = ticks_to_seconds(p, val16);
return -ENODEV;
}
+ if (iface_desc->desc.bNumEndpoints < 1)
+ return -ENODEV;
+
/* check out the endpoint: it has to be Interrupt & IN */
endpoint = &iface_desc->endpoint[0].desc;
* Licensed under GPLv2.
*/
+#include <linux/delay.h>
#include <linux/interrupt.h>
#include <linux/io.h>
#include <linux/kernel.h>
struct watchdog_device wdd;
void __iomem *reg_base;
u32 mr;
+ unsigned long last_ping;
};
static int wdt_timeout = WDT_DEFAULT_TIMEOUT;
"Watchdog cannot be stopped once started (default="
__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
+#define wdt_enabled (!(wdt->mr & AT91_WDT_WDDIS))
+
#define wdt_read(wdt, field) \
readl_relaxed((wdt)->reg_base + (field))
-#define wdt_write(wtd, field, val) \
- writel_relaxed((val), (wdt)->reg_base + (field))
+/* 4 slow clock periods is 4/32768 = 122.07µs*/
+#define WDT_DELAY usecs_to_jiffies(123)
+
+static void wdt_write(struct sama5d4_wdt *wdt, u32 field, u32 val)
+{
+ /*
+ * WDT_CR and WDT_MR must not be modified within three slow clock
+ * periods following a restart of the watchdog performed by a write
+ * access in WDT_CR.
+ */
+ while (time_before(jiffies, wdt->last_ping + WDT_DELAY))
+ usleep_range(30, 125);
+ writel_relaxed(val, wdt->reg_base + field);
+ wdt->last_ping = jiffies;
+}
+
+static void wdt_write_nosleep(struct sama5d4_wdt *wdt, u32 field, u32 val)
+{
+ if (time_before(jiffies, wdt->last_ping + WDT_DELAY))
+ udelay(123);
+ writel_relaxed(val, wdt->reg_base + field);
+ wdt->last_ping = jiffies;
+}
static int sama5d4_wdt_start(struct watchdog_device *wdd)
{
wdt->mr &= ~AT91_WDT_WDD;
wdt->mr |= AT91_WDT_SET_WDV(value);
wdt->mr |= AT91_WDT_SET_WDD(value);
- wdt_write(wdt, AT91_WDT_MR, wdt->mr);
+
+ /*
+ * WDDIS has to be 0 when updating WDD/WDV. The datasheet states: When
+ * setting the WDDIS bit, and while it is set, the fields WDV and WDD
+ * must not be modified.
+ * If the watchdog is enabled, then the timeout can be updated. Else,
+ * wait that the user enables it.
+ */
+ if (wdt_enabled)
+ wdt_write(wdt, AT91_WDT_MR, wdt->mr & ~AT91_WDT_WDDIS);
wdd->timeout = timeout;
static int sama5d4_wdt_init(struct sama5d4_wdt *wdt)
{
- struct watchdog_device *wdd = &wdt->wdd;
- u32 value = WDT_SEC2TICKS(wdd->timeout);
u32 reg;
-
/*
- * Because the fields WDV and WDD must not be modified when the WDDIS
- * bit is set, so clear the WDDIS bit before writing the WDT_MR.
+ * When booting and resuming, the bootloader may have changed the
+ * watchdog configuration.
+ * If the watchdog is already running, we can safely update it.
+ * Else, we have to disable it properly.
*/
- reg = wdt_read(wdt, AT91_WDT_MR);
- reg &= ~AT91_WDT_WDDIS;
- wdt_write(wdt, AT91_WDT_MR, reg);
-
- wdt->mr |= AT91_WDT_SET_WDD(value);
- wdt->mr |= AT91_WDT_SET_WDV(value);
-
- wdt_write(wdt, AT91_WDT_MR, wdt->mr);
-
+ if (wdt_enabled) {
+ wdt_write_nosleep(wdt, AT91_WDT_MR, wdt->mr);
+ } else {
+ reg = wdt_read(wdt, AT91_WDT_MR);
+ if (!(reg & AT91_WDT_WDDIS))
+ wdt_write_nosleep(wdt, AT91_WDT_MR,
+ reg | AT91_WDT_WDDIS);
+ }
return 0;
}
struct resource *res;
void __iomem *regs;
u32 irq = 0;
+ u32 timeout;
int ret;
wdt = devm_kzalloc(&pdev->dev, sizeof(*wdt), GFP_KERNEL);
wdd->ops = &sama5d4_wdt_ops;
wdd->min_timeout = MIN_WDT_TIMEOUT;
wdd->max_timeout = MAX_WDT_TIMEOUT;
+ wdt->last_ping = jiffies;
watchdog_set_drvdata(wdd, wdt);
return ret;
}
+ timeout = WDT_SEC2TICKS(wdd->timeout);
+
+ wdt->mr |= AT91_WDT_SET_WDD(timeout);
+ wdt->mr |= AT91_WDT_SET_WDV(timeout);
+
ret = sama5d4_wdt_init(wdt);
if (ret)
return ret;
{
struct sama5d4_wdt *wdt = dev_get_drvdata(dev);
- wdt_write(wdt, AT91_WDT_MR, wdt->mr & ~AT91_WDT_WDDIS);
- if (wdt->mr & AT91_WDT_WDDIS)
- wdt_write(wdt, AT91_WDT_MR, wdt->mr);
+ sama5d4_wdt_init(wdt);
return 0;
}
pr_crit("Would Reboot\n");
#else
pr_crit("Initiating system reboot\n");
- emergency_restart(NULL);
+ emergency_restart();
#endif
#else
pr_crit("Reset in 5ms\n");
base = platform_get_resource(pdev, IORESOURCE_MEM, 0);
wdt->reg_base = devm_ioremap_resource(dev, base);
- if (IS_ERR(wdt->reg_base)) {
- dev_err(dev, "ioremap failed\n");
+ if (IS_ERR(wdt->reg_base))
return PTR_ERR(wdt->reg_base);
- }
zx2967_wdt_reset_sysctrl(dev);
st->global_error = 1;
}
}
- st->va += PAGE_SIZE * nr;
- st->index += nr;
+ st->va += XEN_PAGE_SIZE * nr;
+ st->index += nr / XEN_PFN_PER_PAGE;
return 0;
}
static inline u64 btrfs_calc_trans_metadata_size(struct btrfs_fs_info *fs_info,
unsigned num_items)
{
- return fs_info->nodesize * BTRFS_MAX_LEVEL * 2 * num_items;
+ return (u64)fs_info->nodesize * BTRFS_MAX_LEVEL * 2 * num_items;
}
/*
static inline u64 btrfs_calc_trunc_metadata_size(struct btrfs_fs_info *fs_info,
unsigned num_items)
{
- return fs_info->nodesize * BTRFS_MAX_LEVEL * num_items;
+ return (u64)fs_info->nodesize * BTRFS_MAX_LEVEL * num_items;
}
int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans,
if (btrfs_dir_name_len(leaf, dir_item) > namelen) {
btrfs_crit(fs_info, "invalid dir item name len: %u",
- (unsigned)btrfs_dir_data_len(leaf, dir_item));
+ (unsigned)btrfs_dir_name_len(leaf, dir_item));
return 1;
}
* we fua the first super. The others we allow
* to go down lazy.
*/
- if (i == 0)
- ret = btrfsic_submit_bh(REQ_OP_WRITE, REQ_FUA, bh);
- else
+ if (i == 0) {
+ ret = btrfsic_submit_bh(REQ_OP_WRITE,
+ REQ_SYNC | REQ_FUA, bh);
+ } else {
ret = btrfsic_submit_bh(REQ_OP_WRITE, REQ_SYNC, bh);
+ }
if (ret)
errors++;
}
bio->bi_end_io = btrfs_end_empty_barrier;
bio->bi_bdev = device->bdev;
- bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
+ bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH;
init_completion(&device->flush_wait);
bio->bi_private = &device->flush_wait;
device->flush_bio = bio;
info->space_info_kobj, "%s",
alloc_name(found->flags));
if (ret) {
+ percpu_counter_destroy(&found->total_bytes_pinned);
kfree(found);
return ret;
}
spin_unlock(&delayed_rsv->lock);
commit:
- trans = btrfs_join_transaction(fs_info->fs_root);
+ trans = btrfs_join_transaction(fs_info->extent_root);
if (IS_ERR(trans))
return -ENOSPC;
struct btrfs_space_info *space_info, u64 num_bytes,
u64 orig_bytes, int state)
{
- struct btrfs_root *root = fs_info->fs_root;
+ struct btrfs_root *root = fs_info->extent_root;
struct btrfs_trans_handle *trans;
int nr;
int ret = 0;
int flush_state = FLUSH_DELAYED_ITEMS_NR;
spin_lock(&space_info->lock);
- to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info->fs_root,
+ to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info->extent_root,
space_info);
if (!to_reclaim) {
spin_unlock(&space_info->lock);
if (!uptodate) {
ClearPageUptodate(page);
SetPageError(page);
- ret = ret < 0 ? ret : -EIO;
+ ret = err < 0 ? err : -EIO;
mapping_set_error(page->mapping, ret);
}
}
return NULL;
}
+/*
+ * To cache previous fiemap extent
+ *
+ * Will be used for merging fiemap extent
+ */
+struct fiemap_cache {
+ u64 offset;
+ u64 phys;
+ u64 len;
+ u32 flags;
+ bool cached;
+};
+
+/*
+ * Helper to submit fiemap extent.
+ *
+ * Will try to merge current fiemap extent specified by @offset, @phys,
+ * @len and @flags with cached one.
+ * And only when we fails to merge, cached one will be submitted as
+ * fiemap extent.
+ *
+ * Return value is the same as fiemap_fill_next_extent().
+ */
+static int emit_fiemap_extent(struct fiemap_extent_info *fieinfo,
+ struct fiemap_cache *cache,
+ u64 offset, u64 phys, u64 len, u32 flags)
+{
+ int ret = 0;
+
+ if (!cache->cached)
+ goto assign;
+
+ /*
+ * Sanity check, extent_fiemap() should have ensured that new
+ * fiemap extent won't overlap with cahced one.
+ * Not recoverable.
+ *
+ * NOTE: Physical address can overlap, due to compression
+ */
+ if (cache->offset + cache->len > offset) {
+ WARN_ON(1);
+ return -EINVAL;
+ }
+
+ /*
+ * Only merges fiemap extents if
+ * 1) Their logical addresses are continuous
+ *
+ * 2) Their physical addresses are continuous
+ * So truly compressed (physical size smaller than logical size)
+ * extents won't get merged with each other
+ *
+ * 3) Share same flags except FIEMAP_EXTENT_LAST
+ * So regular extent won't get merged with prealloc extent
+ */
+ if (cache->offset + cache->len == offset &&
+ cache->phys + cache->len == phys &&
+ (cache->flags & ~FIEMAP_EXTENT_LAST) ==
+ (flags & ~FIEMAP_EXTENT_LAST)) {
+ cache->len += len;
+ cache->flags |= flags;
+ goto try_submit_last;
+ }
+
+ /* Not mergeable, need to submit cached one */
+ ret = fiemap_fill_next_extent(fieinfo, cache->offset, cache->phys,
+ cache->len, cache->flags);
+ cache->cached = false;
+ if (ret)
+ return ret;
+assign:
+ cache->cached = true;
+ cache->offset = offset;
+ cache->phys = phys;
+ cache->len = len;
+ cache->flags = flags;
+try_submit_last:
+ if (cache->flags & FIEMAP_EXTENT_LAST) {
+ ret = fiemap_fill_next_extent(fieinfo, cache->offset,
+ cache->phys, cache->len, cache->flags);
+ cache->cached = false;
+ }
+ return ret;
+}
+
+/*
+ * Sanity check for fiemap cache
+ *
+ * All fiemap cache should be submitted by emit_fiemap_extent()
+ * Iteration should be terminated either by last fiemap extent or
+ * fieinfo->fi_extents_max.
+ * So no cached fiemap should exist.
+ */
+static int check_fiemap_cache(struct btrfs_fs_info *fs_info,
+ struct fiemap_extent_info *fieinfo,
+ struct fiemap_cache *cache)
+{
+ int ret;
+
+ if (!cache->cached)
+ return 0;
+
+ /* Small and recoverbale problem, only to info developer */
+#ifdef CONFIG_BTRFS_DEBUG
+ WARN_ON(1);
+#endif
+ btrfs_warn(fs_info,
+ "unhandled fiemap cache detected: offset=%llu phys=%llu len=%llu flags=0x%x",
+ cache->offset, cache->phys, cache->len, cache->flags);
+ ret = fiemap_fill_next_extent(fieinfo, cache->offset, cache->phys,
+ cache->len, cache->flags);
+ cache->cached = false;
+ if (ret > 0)
+ ret = 0;
+ return ret;
+}
+
int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
__u64 start, __u64 len, get_extent_t *get_extent)
{
struct extent_state *cached_state = NULL;
struct btrfs_path *path;
struct btrfs_root *root = BTRFS_I(inode)->root;
+ struct fiemap_cache cache = { 0 };
int end = 0;
u64 em_start = 0;
u64 em_len = 0;
flags |= FIEMAP_EXTENT_LAST;
end = 1;
}
- ret = fiemap_fill_next_extent(fieinfo, em_start, disko,
- em_len, flags);
+ ret = emit_fiemap_extent(fieinfo, &cache, em_start, disko,
+ em_len, flags);
if (ret) {
if (ret == 1)
ret = 0;
}
}
out_free:
+ if (!ret)
+ ret = check_fiemap_cache(root->fs_info, fieinfo, &cache);
free_extent_map(em);
out:
btrfs_free_path(path);
ret = test_range_bit(io_tree, ordered_extent->file_offset,
ordered_extent->file_offset + ordered_extent->len - 1,
- EXTENT_DEFRAG, 1, cached_state);
+ EXTENT_DEFRAG, 0, cached_state);
if (ret) {
u64 last_snapshot = btrfs_root_last_snapshot(&root->root_item);
if (0 && last_snapshot >= BTRFS_I(inode)->generation)
int found = false;
void **pagep = NULL;
struct page *page = NULL;
- int start_idx;
- int end_idx;
+ unsigned long start_idx;
+ unsigned long end_idx;
start_idx = start >> PAGE_SHIFT;
}
size = i_size_read(inode);
- if (!(mode & FALLOC_FL_KEEP_SIZE))
+ if (!(mode & FALLOC_FL_KEEP_SIZE)) {
endoff = offset + length;
+ ret = inode_newsize_ok(inode, endoff);
+ if (ret)
+ goto unlock;
+ }
if (fi->fmode & CEPH_FILE_MODE_LAZY)
want = CEPH_CAP_FILE_BUFFER | CEPH_CAP_FILE_LAZYIO;
goto out;
}
+ /*
+ * It is possible, particularly with mixed reads & writes to private
+ * mappings, that we have raced with a PMD fault that overlaps with
+ * the PTE we need to set up. If so just return and the fault will be
+ * retried.
+ */
+ if (pmd_trans_huge(*vmf->pmd) || pmd_devmap(*vmf->pmd)) {
+ vmf_ret = VM_FAULT_NOPAGE;
+ goto unlock_entry;
+ }
+
/*
* Note that we don't bother to use iomap_apply here: DAX required
* the file system block size to be equal the page size, which means
if (IS_ERR(entry))
goto fallback;
+ /*
+ * It is possible, particularly with mixed reads & writes to private
+ * mappings, that we have raced with a PTE fault that overlaps with
+ * the PMD we need to set up. If so just return and the fault will be
+ * retried.
+ */
+ if (!pmd_none(*vmf->pmd) && !pmd_trans_huge(*vmf->pmd) &&
+ !pmd_devmap(*vmf->pmd)) {
+ result = 0;
+ goto unlock_entry;
+ }
+
/*
* Note that we don't use iomap_apply here. We aren't doing I/O, only
* setting up a mapping, so really we're using iomap_begin() as a way
iomap->bdev = bdev;
iomap->offset = (u64)first_block << blkbits;
if (blk_queue_dax(bdev->bd_queue))
- iomap->dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
+ iomap->dax_dev = fs_dax_get_by_host(bdev->bd_disk->disk_name);
else
iomap->dax_dev = NULL;
ext2_iomap_end(struct inode *inode, loff_t offset, loff_t length,
ssize_t written, unsigned flags, struct iomap *iomap)
{
- put_dax(iomap->dax_dev);
+ fs_put_dax(iomap->dax_dev);
if (iomap->type == IOMAP_MAPPED &&
written < length &&
(flags & IOMAP_WRITE))
* Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de>
*/
+#include <linux/quotaops.h>
#include "ext4_jbd2.h"
#include "ext4.h"
#include "xattr.h"
handle_t *handle;
int error, retries = 0;
+ error = dquot_initialize(inode);
+ if (error)
+ return error;
retry:
handle = ext4_journal_start(inode, EXT4_HT_XATTR,
ext4_jbd2_credits_xattr(inode));
int buf_size,
struct inode *dir,
struct ext4_filename *fname,
- const struct qstr *d_name,
unsigned int offset,
struct ext4_dir_entry_2 **res_dir);
extern int ext4_generic_delete_entry(handle_t *handle,
int *has_inline_data);
extern struct buffer_head *ext4_find_inline_entry(struct inode *dir,
struct ext4_filename *fname,
- const struct qstr *d_name,
struct ext4_dir_entry_2 **res_dir,
int *has_inline_data);
extern int ext4_delete_inline_entry(handle_t *handle,
struct ext4_sb_info *sbi;
struct ext4_extent_header *eh;
struct ext4_map_blocks split_map;
- struct ext4_extent zero_ex;
+ struct ext4_extent zero_ex1, zero_ex2;
struct ext4_extent *ex, *abut_ex;
ext4_lblk_t ee_block, eof_block;
unsigned int ee_len, depth, map_len = map->m_len;
int allocated = 0, max_zeroout = 0;
int err = 0;
- int split_flag = 0;
+ int split_flag = EXT4_EXT_DATA_VALID2;
ext_debug("ext4_ext_convert_to_initialized: inode %lu, logical"
"block %llu, max_blocks %u\n", inode->i_ino,
ex = path[depth].p_ext;
ee_block = le32_to_cpu(ex->ee_block);
ee_len = ext4_ext_get_actual_len(ex);
- zero_ex.ee_len = 0;
+ zero_ex1.ee_len = 0;
+ zero_ex2.ee_len = 0;
trace_ext4_ext_convert_to_initialized_enter(inode, map, ex);
if (ext4_encrypted_inode(inode))
max_zeroout = 0;
- /* If extent is less than s_max_zeroout_kb, zeroout directly */
- if (max_zeroout && (ee_len <= max_zeroout)) {
- err = ext4_ext_zeroout(inode, ex);
- if (err)
- goto out;
- zero_ex.ee_block = ex->ee_block;
- zero_ex.ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex));
- ext4_ext_store_pblock(&zero_ex, ext4_ext_pblock(ex));
-
- err = ext4_ext_get_access(handle, inode, path + depth);
- if (err)
- goto out;
- ext4_ext_mark_initialized(ex);
- ext4_ext_try_to_merge(handle, inode, path, ex);
- err = ext4_ext_dirty(handle, inode, path + path->p_depth);
- goto out;
- }
-
/*
- * four cases:
+ * five cases:
* 1. split the extent into three extents.
- * 2. split the extent into two extents, zeroout the first half.
- * 3. split the extent into two extents, zeroout the second half.
+ * 2. split the extent into two extents, zeroout the head of the first
+ * extent.
+ * 3. split the extent into two extents, zeroout the tail of the second
+ * extent.
* 4. split the extent into two extents with out zeroout.
+ * 5. no splitting needed, just possibly zeroout the head and / or the
+ * tail of the extent.
*/
split_map.m_lblk = map->m_lblk;
split_map.m_len = map->m_len;
- if (max_zeroout && (allocated > map->m_len)) {
+ if (max_zeroout && (allocated > split_map.m_len)) {
if (allocated <= max_zeroout) {
- /* case 3 */
- zero_ex.ee_block =
- cpu_to_le32(map->m_lblk);
- zero_ex.ee_len = cpu_to_le16(allocated);
- ext4_ext_store_pblock(&zero_ex,
- ext4_ext_pblock(ex) + map->m_lblk - ee_block);
- err = ext4_ext_zeroout(inode, &zero_ex);
+ /* case 3 or 5 */
+ zero_ex1.ee_block =
+ cpu_to_le32(split_map.m_lblk +
+ split_map.m_len);
+ zero_ex1.ee_len =
+ cpu_to_le16(allocated - split_map.m_len);
+ ext4_ext_store_pblock(&zero_ex1,
+ ext4_ext_pblock(ex) + split_map.m_lblk +
+ split_map.m_len - ee_block);
+ err = ext4_ext_zeroout(inode, &zero_ex1);
if (err)
goto out;
- split_map.m_lblk = map->m_lblk;
split_map.m_len = allocated;
- } else if (map->m_lblk - ee_block + map->m_len < max_zeroout) {
- /* case 2 */
- if (map->m_lblk != ee_block) {
- zero_ex.ee_block = ex->ee_block;
- zero_ex.ee_len = cpu_to_le16(map->m_lblk -
+ }
+ if (split_map.m_lblk - ee_block + split_map.m_len <
+ max_zeroout) {
+ /* case 2 or 5 */
+ if (split_map.m_lblk != ee_block) {
+ zero_ex2.ee_block = ex->ee_block;
+ zero_ex2.ee_len = cpu_to_le16(split_map.m_lblk -
ee_block);
- ext4_ext_store_pblock(&zero_ex,
+ ext4_ext_store_pblock(&zero_ex2,
ext4_ext_pblock(ex));
- err = ext4_ext_zeroout(inode, &zero_ex);
+ err = ext4_ext_zeroout(inode, &zero_ex2);
if (err)
goto out;
}
+ split_map.m_len += split_map.m_lblk - ee_block;
split_map.m_lblk = ee_block;
- split_map.m_len = map->m_lblk - ee_block + map->m_len;
allocated = map->m_len;
}
}
err = 0;
out:
/* If we have gotten a failure, don't zero out status tree */
- if (!err)
- err = ext4_zeroout_es(inode, &zero_ex);
+ if (!err) {
+ err = ext4_zeroout_es(inode, &zero_ex1);
+ if (!err)
+ err = ext4_zeroout_es(inode, &zero_ex2);
+ }
return err ? err : allocated;
}
/* Zero out partial block at the edges of the range */
ret = ext4_zero_partial_blocks(handle, inode, offset, len);
+ if (ret >= 0)
+ ext4_update_inode_fsync_trans(handle, inode, 1);
if (file->f_flags & O_SYNC)
ext4_handle_sync(handle);
ext4_handle_sync(handle);
inode->i_mtime = inode->i_ctime = current_time(inode);
ext4_mark_inode_dirty(handle, inode);
+ ext4_update_inode_fsync_trans(handle, inode, 1);
out_stop:
ext4_journal_stop(handle);
up_write(&EXT4_I(inode)->i_data_sem);
if (IS_SYNC(inode))
ext4_handle_sync(handle);
+ if (ret >= 0)
+ ext4_update_inode_fsync_trans(handle, inode, 1);
out_stop:
ext4_journal_stop(handle);
endoff = (loff_t)end_blk << blkbits;
index = startoff >> PAGE_SHIFT;
- end = endoff >> PAGE_SHIFT;
+ end = (endoff - 1) >> PAGE_SHIFT;
pagevec_init(&pvec, 0);
do {
int i, num;
unsigned long nr_pages;
- num = min_t(pgoff_t, end - index, PAGEVEC_SIZE);
+ num = min_t(pgoff_t, end - index, PAGEVEC_SIZE - 1) + 1;
nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index,
(pgoff_t)num);
- if (nr_pages == 0) {
- if (whence == SEEK_DATA)
- break;
-
- BUG_ON(whence != SEEK_HOLE);
- /*
- * If this is the first time to go into the loop and
- * offset is not beyond the end offset, it will be a
- * hole at this offset
- */
- if (lastoff == startoff || lastoff < endoff)
- found = 1;
- break;
- }
-
- /*
- * If this is the first time to go into the loop and
- * offset is smaller than the first page offset, it will be a
- * hole at this offset.
- */
- if (lastoff == startoff && whence == SEEK_HOLE &&
- lastoff < page_offset(pvec.pages[0])) {
- found = 1;
+ if (nr_pages == 0)
break;
- }
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
struct buffer_head *bh, *head;
/*
- * If the current offset is not beyond the end of given
- * range, it will be a hole.
+ * If current offset is smaller than the page offset,
+ * there is a hole at this offset.
*/
- if (lastoff < endoff && whence == SEEK_HOLE &&
- page->index > end) {
+ if (whence == SEEK_HOLE && lastoff < endoff &&
+ lastoff < page_offset(pvec.pages[i])) {
found = 1;
*offset = lastoff;
goto out;
}
+ if (page->index > end)
+ goto out;
+
lock_page(page);
if (unlikely(page->mapping != inode->i_mapping)) {
unlock_page(page);
}
- /*
- * The no. of pages is less than our desired, that would be a
- * hole in there.
- */
- if (nr_pages < num && whence == SEEK_HOLE) {
- found = 1;
- *offset = lastoff;
+ /* The no. of pages is less than our desired, we are done. */
+ if (nr_pages < num)
break;
- }
index = pvec.pages[i - 1]->index + 1;
pagevec_release(&pvec);
} while (index <= end);
+ if (whence == SEEK_HOLE && lastoff < endoff) {
+ found = 1;
+ *offset = lastoff;
+ }
out:
pagevec_release(&pvec);
return found;
struct buffer_head *ext4_find_inline_entry(struct inode *dir,
struct ext4_filename *fname,
- const struct qstr *d_name,
struct ext4_dir_entry_2 **res_dir,
int *has_inline_data)
{
EXT4_INLINE_DOTDOT_SIZE;
inline_size = EXT4_MIN_INLINE_DATA_SIZE - EXT4_INLINE_DOTDOT_SIZE;
ret = ext4_search_dir(iloc.bh, inline_start, inline_size,
- dir, fname, d_name, 0, res_dir);
+ dir, fname, 0, res_dir);
if (ret == 1)
goto out_find;
if (ret < 0)
inline_size = ext4_get_inline_size(dir) - EXT4_MIN_INLINE_DATA_SIZE;
ret = ext4_search_dir(iloc.bh, inline_start, inline_size,
- dir, fname, d_name, 0, res_dir);
+ dir, fname, 0, res_dir);
if (ret == 1)
goto out_find;
static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page)
{
int len;
- loff_t size = i_size_read(mpd->inode);
+ loff_t size;
int err;
BUG_ON(page->index != mpd->first_page);
+ clear_page_dirty_for_io(page);
+ /*
+ * We have to be very careful here! Nothing protects writeback path
+ * against i_size changes and the page can be writeably mapped into
+ * page tables. So an application can be growing i_size and writing
+ * data through mmap while writeback runs. clear_page_dirty_for_io()
+ * write-protects our page in page tables and the page cannot get
+ * written to again until we release page lock. So only after
+ * clear_page_dirty_for_io() we are safe to sample i_size for
+ * ext4_bio_write_page() to zero-out tail of the written page. We rely
+ * on the barrier provided by TestClearPageDirty in
+ * clear_page_dirty_for_io() to make sure i_size is really sampled only
+ * after page tables are updated.
+ */
+ size = i_size_read(mpd->inode);
if (page->index == size >> PAGE_SHIFT)
len = size & ~PAGE_MASK;
else
len = PAGE_SIZE;
- clear_page_dirty_for_io(page);
err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc, false);
if (!err)
mpd->wbc->nr_to_write--;
bdev = inode->i_sb->s_bdev;
iomap->bdev = bdev;
if (blk_queue_dax(bdev->bd_queue))
- iomap->dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
+ iomap->dax_dev = fs_dax_get_by_host(bdev->bd_disk->disk_name);
else
iomap->dax_dev = NULL;
iomap->offset = first_block << blkbits;
int blkbits = inode->i_blkbits;
bool truncate = false;
- put_dax(iomap->dax_dev);
+ fs_put_dax(iomap->dax_dev);
if (!(flags & IOMAP_WRITE) || (flags & IOMAP_FAULT))
return 0;
get_block_func = ext4_dio_get_block_unwritten_async;
dio_flags = DIO_LOCKING;
}
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
- BUG_ON(ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode));
-#endif
ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter,
get_block_func, ext4_end_io_dio, NULL,
dio_flags);
*/
inode_lock_shared(inode);
ret = filemap_write_and_wait_range(mapping, iocb->ki_pos,
- iocb->ki_pos + count);
+ iocb->ki_pos + count - 1);
if (ret)
goto out_unlock;
ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
inode->i_mtime = inode->i_ctime = current_time(inode);
ext4_mark_inode_dirty(handle, inode);
+ if (ret >= 0)
+ ext4_update_inode_fsync_trans(handle, inode, 1);
out_stop:
ext4_journal_stop(handle);
out_dio:
/* No extended attributes present */
if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR) ||
header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)) {
- memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE, 0,
- new_extra_isize);
+ memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE +
+ EXT4_I(inode)->i_extra_isize, 0,
+ new_extra_isize - EXT4_I(inode)->i_extra_isize);
EXT4_I(inode)->i_extra_isize = new_extra_isize;
return 0;
}
err = ext4_mb_load_buddy(sb, group, &e4b);
if (err) {
- ext4_error(sb, "Error loading buddy information for %u", group);
+ ext4_warning(sb, "Error %d loading buddy information for %u",
+ err, group);
put_bh(bitmap_bh);
return 0;
}
BUG_ON(pa->pa_type != MB_INODE_PA);
group = ext4_get_group_number(sb, pa->pa_pstart);
- err = ext4_mb_load_buddy(sb, group, &e4b);
+ err = ext4_mb_load_buddy_gfp(sb, group, &e4b,
+ GFP_NOFS|__GFP_NOFAIL);
if (err) {
- ext4_error(sb, "Error loading buddy information for %u",
- group);
+ ext4_error(sb, "Error %d loading buddy information for %u",
+ err, group);
continue;
}
spin_unlock(&lg->lg_prealloc_lock);
list_for_each_entry_safe(pa, tmp, &discard_list, u.pa_tmp_list) {
+ int err;
group = ext4_get_group_number(sb, pa->pa_pstart);
- if (ext4_mb_load_buddy(sb, group, &e4b)) {
- ext4_error(sb, "Error loading buddy information for %u",
- group);
+ err = ext4_mb_load_buddy_gfp(sb, group, &e4b,
+ GFP_NOFS|__GFP_NOFAIL);
+ if (err) {
+ ext4_error(sb, "Error %d loading buddy information for %u",
+ err, group);
continue;
}
ext4_lock_group(sb, group);
ret = ext4_mb_load_buddy(sb, group, &e4b);
if (ret) {
- ext4_error(sb, "Error in loading buddy "
- "information for %u", group);
+ ext4_warning(sb, "Error %d loading buddy information for %u",
+ ret, group);
return ret;
}
bitmap = e4b.bd_bitmap;
static inline int search_dirblock(struct buffer_head *bh,
struct inode *dir,
struct ext4_filename *fname,
- const struct qstr *d_name,
unsigned int offset,
struct ext4_dir_entry_2 **res_dir)
{
return ext4_search_dir(bh, bh->b_data, dir->i_sb->s_blocksize, dir,
- fname, d_name, offset, res_dir);
+ fname, offset, res_dir);
}
/*
*/
int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size,
struct inode *dir, struct ext4_filename *fname,
- const struct qstr *d_name,
unsigned int offset, struct ext4_dir_entry_2 **res_dir)
{
struct ext4_dir_entry_2 * de;
if (ext4_has_inline_data(dir)) {
int has_inline_data = 1;
- ret = ext4_find_inline_entry(dir, &fname, d_name, res_dir,
+ ret = ext4_find_inline_entry(dir, &fname, res_dir,
&has_inline_data);
if (has_inline_data) {
if (inlined)
goto next;
}
set_buffer_verified(bh);
- i = search_dirblock(bh, dir, &fname, d_name,
+ i = search_dirblock(bh, dir, &fname,
block << EXT4_BLOCK_SIZE_BITS(sb), res_dir);
if (i == 1) {
EXT4_I(dir)->i_dir_start_lookup = block;
{
struct super_block * sb = dir->i_sb;
struct dx_frame frames[2], *frame;
- const struct qstr *d_name = fname->usr_fname;
struct buffer_head *bh;
ext4_lblk_t block;
int retval;
if (IS_ERR(bh))
goto errout;
- retval = search_dirblock(bh, dir, fname, d_name,
+ retval = search_dirblock(bh, dir, fname,
block << EXT4_BLOCK_SIZE_BITS(sb),
res_dir);
if (retval == 1)
bh = NULL;
errout:
- dxtrace(printk(KERN_DEBUG "%s not found\n", d_name->name));
+ dxtrace(printk(KERN_DEBUG "%s not found\n", fname->usr_fname->name));
success:
dx_release(frames);
return bh;
{
int type;
- if (ext4_has_feature_quota(sb)) {
- dquot_disable(sb, -1,
- DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);
- } else {
- /* Use our quota_off function to clear inode flags etc. */
- for (type = 0; type < EXT4_MAXQUOTAS; type++)
- ext4_quota_off(sb, type);
- }
+ /* Use our quota_off function to clear inode flags etc. */
+ for (type = 0; type < EXT4_MAXQUOTAS; type++)
+ ext4_quota_off(sb, type);
}
#else
static inline void ext4_quota_off_umount(struct super_block *sb)
return res;
}
+ res = dquot_initialize(inode);
+ if (res)
+ return res;
retry:
handle = ext4_journal_start(inode, EXT4_HT_MISC,
ext4_jbd2_credits_xattr(inode));
goto out;
err = dquot_quota_off(sb, type);
- if (err)
+ if (err || ext4_has_feature_quota(sb))
goto out_put;
inode_lock(inode);
out_unlock:
inode_unlock(inode);
out_put:
+ lockdep_set_quota_inode(inode, I_DATA_SEM_NORMAL);
iput(inode);
return err;
out:
else {
u32 ref;
+ WARN_ON_ONCE(dquot_initialize_needed(inode));
+
/* The old block is released after updating
the inode. */
error = dquot_alloc_block(inode,
/* We need to allocate a new block */
ext4_fsblk_t goal, block;
+ WARN_ON_ONCE(dquot_initialize_needed(inode));
+
goal = ext4_group_first_block_no(sb,
EXT4_I(inode)->i_block_group);
return -EINVAL;
if (strlen(name) > 255)
return -ERANGE;
+
ext4_write_lock_xattr(inode, &no_expand);
error = ext4_reserve_inode_write(handle, inode, &is.iloc);
int error, retries = 0;
int credits = ext4_jbd2_credits_xattr(inode);
+ error = dquot_initialize(inode);
+ if (error)
+ return error;
retry:
handle = ext4_journal_start(inode, EXT4_HT_XATTR, credits);
if (IS_ERR(handle)) {
int err;
char *suffix = "";
- if (sb->s_bdev)
+ if (sb->s_bdev) {
suffix = "-fuseblk";
+ /*
+ * sb->s_bdi points to blkdev's bdi however we want to redirect
+ * it to our private bdi...
+ */
+ bdi_put(sb->s_bdi);
+ sb->s_bdi = &noop_backing_dev_info;
+ }
err = super_setup_bdi_name(sb, "%u:%u%s", MAJOR(fc->dev),
MINOR(fc->dev), suffix);
if (err)
struct gfs2_log_header *lh;
unsigned int tail;
u32 hash;
- int op_flags = REQ_PREFLUSH | REQ_FUA | REQ_META;
+ int op_flags = REQ_PREFLUSH | REQ_FUA | REQ_META | REQ_SYNC;
struct page *page = mempool_alloc(gfs2_page_pool, GFP_NOIO);
enum gfs2_freeze_state state = atomic_read(&sdp->sd_freeze_state);
lh = page_address(page);
rwsem_release(&journal->j_trans_commit_map, 1, _THIS_IP_);
handle->h_buffer_credits = nblocks;
+ /*
+ * Restore the original nofs context because the journal restart
+ * is basically the same thing as journal stop and start.
+ * start_this_handle will start a new nofs context.
+ */
+ memalloc_nofs_restore(handle->saved_alloc_context);
ret = start_this_handle(journal, handle, gfp_mask);
return ret;
}
goto out_err_free;
/* fh */
+ rc = -EIO;
p = xdr_inline_decode(&stream, 4);
if (!p)
goto out_err_free;
bool nfs_auth_info_match(const struct nfs_auth_info *, rpc_authflavor_t);
struct dentry *nfs_try_mount(int, const char *, struct nfs_mount_info *,
struct nfs_subversion *);
-void nfs_initialise_sb(struct super_block *);
int nfs_set_sb_security(struct super_block *, struct dentry *, struct nfs_mount_info *);
int nfs_clone_sb_security(struct super_block *, struct dentry *, struct nfs_mount_info *);
struct dentry *nfs_fs_mount_common(struct nfs_server *, int, const char *,
extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio);
/* super.c */
-void nfs_clone_super(struct super_block *, struct nfs_mount_info *);
void nfs_umount_begin(struct super_block *);
int nfs_statfs(struct dentry *, struct kstatfs *);
int nfs_show_options(struct seq_file *, struct dentry *);
devname = nfs_devname(dentry, page, PAGE_SIZE);
if (IS_ERR(devname))
- mnt = (struct vfsmount *)devname;
+ mnt = ERR_CAST(devname);
else
mnt = nfs_do_clone_mount(NFS_SB(dentry->d_sb), devname, &mountdata);
if (status)
goto out;
- if (!nfs_write_verifier_cmp(&res->write_res.verifier.verifier,
+ if (nfs_write_verifier_cmp(&res->write_res.verifier.verifier,
&res->commit_res.verf->verifier)) {
status = -EAGAIN;
goto out;
*/
nfs4_schedule_path_down_recovery(pos);
default:
- spin_lock(&nn->nfs_client_lock);
goto out;
}
}
EXPORT_SYMBOL_GPL(pnfs_generic_pg_check_layout);
+/*
+ * Check for any intersection between the request and the pgio->pg_lseg,
+ * and if none, put this pgio->pg_lseg away.
+ */
+static void
+pnfs_generic_pg_check_range(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
+{
+ if (pgio->pg_lseg && !pnfs_lseg_request_intersecting(pgio->pg_lseg, req)) {
+ pnfs_put_lseg(pgio->pg_lseg);
+ pgio->pg_lseg = NULL;
+ }
+}
+
void
pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
{
u64 rd_size = req->wb_bytes;
pnfs_generic_pg_check_layout(pgio);
+ pnfs_generic_pg_check_range(pgio, req);
if (pgio->pg_lseg == NULL) {
if (pgio->pg_dreq == NULL)
rd_size = i_size_read(pgio->pg_inode) - req_offset(req);
struct nfs_page *req, u64 wb_size)
{
pnfs_generic_pg_check_layout(pgio);
+ pnfs_generic_pg_check_range(pgio, req);
if (pgio->pg_lseg == NULL) {
pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
req->wb_context,
seg_end = pnfs_end_offset(pgio->pg_lseg->pls_range.offset,
pgio->pg_lseg->pls_range.length);
req_start = req_offset(req);
- WARN_ON_ONCE(req_start >= seg_end);
+
/* start of request is past the last byte of this segment */
- if (req_start >= seg_end) {
- /* reference the new lseg */
- if (pgio->pg_ops->pg_cleanup)
- pgio->pg_ops->pg_cleanup(pgio);
- if (pgio->pg_ops->pg_init)
- pgio->pg_ops->pg_init(pgio, req);
+ if (req_start >= seg_end)
return 0;
- }
/* adjust 'size' iff there are fewer bytes left in the
* segment than what nfs_generic_pg_test returned */
return pnfs_is_range_intersecting(l1->offset, end1, l2->offset, end2);
}
+static inline bool
+pnfs_lseg_request_intersecting(struct pnfs_layout_segment *lseg, struct nfs_page *req)
+{
+ u64 seg_last = pnfs_end_offset(lseg->pls_range.offset, lseg->pls_range.length);
+ u64 req_last = req_offset(req) + req->wb_bytes;
+
+ return pnfs_is_range_intersecting(lseg->pls_range.offset, seg_last,
+ req_offset(req), req_last);
+}
+
extern unsigned int layoutstats_timer;
#ifdef NFS_DEBUG
/*
* Initialise the common bits of the superblock
*/
-inline void nfs_initialise_sb(struct super_block *sb)
+static void nfs_initialise_sb(struct super_block *sb)
{
struct nfs_server *server = NFS_SB(sb);
/*
* Finish setting up a cloned NFS2/3/4 superblock
*/
-void nfs_clone_super(struct super_block *sb, struct nfs_mount_info *mount_info)
+static void nfs_clone_super(struct super_block *sb,
+ struct nfs_mount_info *mount_info)
{
const struct super_block *old_sb = mount_info->cloned->sb;
struct nfs_server *server = NFS_SB(sb);
if (!p)
return 0;
p = xdr_decode_hyper(p, &args->offset);
- args->count = ntohl(*p++);
-
- if (!xdr_argsize_check(rqstp, p))
- return 0;
+ args->count = ntohl(*p++);
len = min(args->count, max_blocksize);
/* set up the kvec */
v++;
}
args->vlen = v;
- return 1;
+ return xdr_argsize_check(rqstp, p);
}
int
p = decode_fh(p, &args->fh);
if (!p)
return 0;
- if (!xdr_argsize_check(rqstp, p))
- return 0;
args->buffer = page_address(*(rqstp->rq_next_page++));
- return 1;
+ return xdr_argsize_check(rqstp, p);
}
int
args->verf = p; p += 2;
args->dircount = ~0;
args->count = ntohl(*p++);
-
- if (!xdr_argsize_check(rqstp, p))
- return 0;
-
args->count = min_t(u32, args->count, PAGE_SIZE);
args->buffer = page_address(*(rqstp->rq_next_page++));
- return 1;
+ return xdr_argsize_check(rqstp, p);
}
int
args->dircount = ntohl(*p++);
args->count = ntohl(*p++);
- if (!xdr_argsize_check(rqstp, p))
- return 0;
-
len = args->count = min(args->count, max_blocksize);
while (len > 0) {
struct page *p = *(rqstp->rq_next_page++);
args->buffer = page_address(p);
len -= PAGE_SIZE;
}
- return 1;
+
+ return xdr_argsize_check(rqstp, p);
}
int
opdesc->op_get_currentstateid(cstate, &op->u);
op->status = opdesc->op_func(rqstp, cstate, &op->u);
+ /* Only from SEQUENCE */
+ if (cstate->status == nfserr_replay_cache) {
+ dprintk("%s NFS4.1 replay from cache\n", __func__);
+ status = op->status;
+ goto out;
+ }
if (!op->status) {
if (opdesc->op_set_currentstateid)
opdesc->op_set_currentstateid(cstate, &op->u);
if (need_wrongsec_check(rqstp))
op->status = check_nfsd_access(current_fh->fh_export, rqstp);
}
-
encode_op:
- /* Only from SEQUENCE */
- if (cstate->status == nfserr_replay_cache) {
- dprintk("%s NFS4.1 replay from cache\n", __func__);
- status = op->status;
- goto out;
- }
if (op->status == nfserr_replay_me) {
op->replay = &cstate->replay_owner->so_replay;
nfsd4_encode_replay(&resp->xdr, op);
len = args->count = ntohl(*p++);
p++; /* totalcount - unused */
- if (!xdr_argsize_check(rqstp, p))
- return 0;
-
len = min_t(unsigned int, len, NFSSVC_MAXBLKSIZE_V2);
/* set up somewhere to store response.
v++;
}
args->vlen = v;
- return 1;
+ return xdr_argsize_check(rqstp, p);
}
int
p = decode_fh(p, &args->fh);
if (!p)
return 0;
- if (!xdr_argsize_check(rqstp, p))
- return 0;
args->buffer = page_address(*(rqstp->rq_next_page++));
- return 1;
+ return xdr_argsize_check(rqstp, p);
}
int
args->cookie = ntohl(*p++);
args->count = ntohl(*p++);
args->count = min_t(u32, args->count, PAGE_SIZE);
- if (!xdr_argsize_check(rqstp, p))
- return 0;
args->buffer = page_address(*(rqstp->rq_next_page++));
- return 1;
+ return xdr_argsize_check(rqstp, p);
}
/*
PTR_ERR(dent_inode));
kfree(name);
/* Return the error code. */
- return (struct dentry *)dent_inode;
+ return ERR_CAST(dent_inode);
}
/* It is guaranteed that @name is no longer allocated at this point. */
if (MREF_ERR(mref) == -ENOENT) {
if (IS_ERR(inode)) {
mlog_errno(PTR_ERR(inode));
- result = (void *)inode;
+ result = ERR_CAST(inode);
goto bail;
}
config OVERLAY_FS
tristate "Overlay filesystem support"
+ select EXPORTFS
help
An overlay filesystem combines two filesystems - an 'upper' filesystem
and a 'lower' filesystem. When a name exists in both filesystems, the
return PTR_ERR(fh);
}
- err = ovl_do_setxattr(upper, OVL_XATTR_ORIGIN, fh, fh ? fh->len : 0, 0);
+ /*
+ * Do not fail when upper doesn't support xattrs.
+ */
+ err = ovl_check_setxattr(dentry, upper, OVL_XATTR_ORIGIN, fh,
+ fh ? fh->len : 0, 0);
kfree(fh);
return err;
if (tmpfile)
temp = ovl_do_tmpfile(upperdir, stat->mode);
else
- temp = ovl_lookup_temp(workdir, dentry);
- err = PTR_ERR(temp);
- if (IS_ERR(temp))
- goto out1;
-
+ temp = ovl_lookup_temp(workdir);
err = 0;
- if (!tmpfile)
+ if (IS_ERR(temp)) {
+ err = PTR_ERR(temp);
+ temp = NULL;
+ }
+
+ if (!err && !tmpfile)
err = ovl_create_real(wdir, temp, &cattr, NULL, true);
if (new_creds) {
ovl_path_upper(parent, &parentpath);
upperdir = parentpath.dentry;
+ /* Mark parent "impure" because it may now contain non-pure upper */
+ err = ovl_set_impure(parent, upperdir);
+ if (err)
+ return err;
+
err = vfs_getattr(&parentpath, &pstat,
STATX_ATIME | STATX_MTIME, AT_STATX_SYNC_AS_STAT);
if (err)
}
}
-struct dentry *ovl_lookup_temp(struct dentry *workdir, struct dentry *dentry)
+struct dentry *ovl_lookup_temp(struct dentry *workdir)
{
struct dentry *temp;
char name[20];
struct dentry *whiteout;
struct inode *wdir = workdir->d_inode;
- whiteout = ovl_lookup_temp(workdir, dentry);
+ whiteout = ovl_lookup_temp(workdir);
if (IS_ERR(whiteout))
return whiteout;
return err;
}
-static int ovl_set_opaque(struct dentry *dentry, struct dentry *upperdentry)
+static int ovl_set_opaque_xerr(struct dentry *dentry, struct dentry *upper,
+ int xerr)
{
int err;
- err = ovl_do_setxattr(upperdentry, OVL_XATTR_OPAQUE, "y", 1, 0);
+ err = ovl_check_setxattr(dentry, upper, OVL_XATTR_OPAQUE, "y", 1, xerr);
if (!err)
ovl_dentry_set_opaque(dentry);
return err;
}
+static int ovl_set_opaque(struct dentry *dentry, struct dentry *upperdentry)
+{
+ /*
+ * Fail with -EIO when trying to create opaque dir and upper doesn't
+ * support xattrs. ovl_rename() calls ovl_set_opaque_xerr(-EXDEV) to
+ * return a specific error for noxattr case.
+ */
+ return ovl_set_opaque_xerr(dentry, upperdentry, -EIO);
+}
+
/* Common operations required to be done after creation of file on upper */
static void ovl_instantiate(struct dentry *dentry, struct inode *inode,
struct dentry *newdentry, bool hardlink)
return OVL_TYPE_MERGE(ovl_path_type(dentry));
}
+static bool ovl_type_origin(struct dentry *dentry)
+{
+ return OVL_TYPE_ORIGIN(ovl_path_type(dentry));
+}
+
static int ovl_create_upper(struct dentry *dentry, struct inode *inode,
struct cattr *attr, struct dentry *hardlink)
{
if (upper->d_parent->d_inode != udir)
goto out_unlock;
- opaquedir = ovl_lookup_temp(workdir, dentry);
+ opaquedir = ovl_lookup_temp(workdir);
err = PTR_ERR(opaquedir);
if (IS_ERR(opaquedir))
goto out_unlock;
if (err)
goto out;
- newdentry = ovl_lookup_temp(workdir, dentry);
+ newdentry = ovl_lookup_temp(workdir);
err = PTR_ERR(newdentry);
if (IS_ERR(newdentry))
goto out_unlock;
if (IS_ERR(redirect))
return PTR_ERR(redirect);
- err = ovl_do_setxattr(ovl_dentry_upper(dentry), OVL_XATTR_REDIRECT,
- redirect, strlen(redirect), 0);
+ err = ovl_check_setxattr(dentry, ovl_dentry_upper(dentry),
+ OVL_XATTR_REDIRECT,
+ redirect, strlen(redirect), -EXDEV);
if (!err) {
spin_lock(&dentry->d_lock);
ovl_dentry_set_redirect(dentry, redirect);
spin_unlock(&dentry->d_lock);
} else {
kfree(redirect);
- if (err == -EOPNOTSUPP)
- ovl_clear_redirect_dir(dentry->d_sb);
- else
- pr_warn_ratelimited("overlay: failed to set redirect (%i)\n", err);
+ pr_warn_ratelimited("overlay: failed to set redirect (%i)\n", err);
/* Fall back to userspace copy-up */
err = -EXDEV;
}
old_upperdir = ovl_dentry_upper(old->d_parent);
new_upperdir = ovl_dentry_upper(new->d_parent);
+ if (!samedir) {
+ /*
+ * When moving a merge dir or non-dir with copy up origin into
+ * a new parent, we are marking the new parent dir "impure".
+ * When ovl_iterate() iterates an "impure" upper dir, it will
+ * lookup the origin inodes of the entries to fill d_ino.
+ */
+ if (ovl_type_origin(old)) {
+ err = ovl_set_impure(new->d_parent, new_upperdir);
+ if (err)
+ goto out_revert_creds;
+ }
+ if (!overwrite && ovl_type_origin(new)) {
+ err = ovl_set_impure(old->d_parent, old_upperdir);
+ if (err)
+ goto out_revert_creds;
+ }
+ }
+
trap = lock_rename(new_upperdir, old_upperdir);
olddentry = lookup_one_len(old->d_name.name, old_upperdir,
if (ovl_type_merge_or_lower(old))
err = ovl_set_redirect(old, samedir);
else if (!old_opaque && ovl_type_merge(new->d_parent))
- err = ovl_set_opaque(old, olddentry);
+ err = ovl_set_opaque_xerr(old, olddentry, -EXDEV);
if (err)
goto out_dput;
}
if (ovl_type_merge_or_lower(new))
err = ovl_set_redirect(new, samedir);
else if (!new_opaque && ovl_type_merge(old->d_parent))
- err = ovl_set_opaque(new, newdentry);
+ err = ovl_set_opaque_xerr(new, newdentry, -EXDEV);
if (err)
goto out_dput;
}
return res;
}
+static bool ovl_can_list(const char *s)
+{
+ /* List all non-trusted xatts */
+ if (strncmp(s, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) != 0)
+ return true;
+
+ /* Never list trusted.overlay, list other trusted for superuser only */
+ return !ovl_is_private_xattr(s) && capable(CAP_SYS_ADMIN);
+}
+
ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size)
{
struct dentry *realdentry = ovl_dentry_real(dentry);
return -EIO;
len -= slen;
- if (ovl_is_private_xattr(s)) {
+ if (!ovl_can_list(s)) {
res -= slen;
memmove(s, s + slen, len);
} else {
static bool ovl_is_opaquedir(struct dentry *dentry)
{
- int res;
- char val;
-
- if (!d_is_dir(dentry))
- return false;
-
- res = vfs_getxattr(dentry, OVL_XATTR_OPAQUE, &val, 1);
- if (res == 1 && val == 'y')
- return true;
-
- return false;
+ return ovl_check_dir_xattr(dentry, OVL_XATTR_OPAQUE);
}
static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d,
unsigned int ctr = 0;
struct inode *inode = NULL;
bool upperopaque = false;
+ bool upperimpure = false;
char *upperredirect = NULL;
struct dentry *this;
unsigned int i;
poe = roe;
}
upperopaque = d.opaque;
+ if (upperdentry && d.is_dir)
+ upperimpure = ovl_is_impuredir(upperdentry);
}
if (!d.stop && poe->numlower) {
revert_creds(old_cred);
oe->opaque = upperopaque;
+ oe->impure = upperimpure;
oe->redirect = upperredirect;
oe->__upperdentry = upperdentry;
memcpy(oe->lowerstack, stack, sizeof(struct path) * ctr);
#define OVL_XATTR_OPAQUE OVL_XATTR_PREFIX "opaque"
#define OVL_XATTR_REDIRECT OVL_XATTR_PREFIX "redirect"
#define OVL_XATTR_ORIGIN OVL_XATTR_PREFIX "origin"
+#define OVL_XATTR_IMPURE OVL_XATTR_PREFIX "impure"
/*
* The tuple (fh,uuid) is a universal unique identifier for a copy up origin,
struct ovl_dir_cache *ovl_dir_cache(struct dentry *dentry);
void ovl_set_dir_cache(struct dentry *dentry, struct ovl_dir_cache *cache);
bool ovl_dentry_is_opaque(struct dentry *dentry);
+bool ovl_dentry_is_impure(struct dentry *dentry);
bool ovl_dentry_is_whiteout(struct dentry *dentry);
void ovl_dentry_set_opaque(struct dentry *dentry);
bool ovl_redirect_dir(struct super_block *sb);
-void ovl_clear_redirect_dir(struct super_block *sb);
const char *ovl_dentry_get_redirect(struct dentry *dentry);
void ovl_dentry_set_redirect(struct dentry *dentry, const char *redirect);
void ovl_dentry_update(struct dentry *dentry, struct dentry *upperdentry);
struct file *ovl_path_open(struct path *path, int flags);
int ovl_copy_up_start(struct dentry *dentry);
void ovl_copy_up_end(struct dentry *dentry);
+bool ovl_check_dir_xattr(struct dentry *dentry, const char *name);
+int ovl_check_setxattr(struct dentry *dentry, struct dentry *upperdentry,
+ const char *name, const void *value, size_t size,
+ int xerr);
+int ovl_set_impure(struct dentry *dentry, struct dentry *upperdentry);
+
+static inline bool ovl_is_impuredir(struct dentry *dentry)
+{
+ return ovl_check_dir_xattr(dentry, OVL_XATTR_IMPURE);
+}
+
/* namei.c */
int ovl_path_next(int idx, struct dentry *dentry, struct path *path);
/* dir.c */
extern const struct inode_operations ovl_dir_inode_operations;
-struct dentry *ovl_lookup_temp(struct dentry *workdir, struct dentry *dentry);
+struct dentry *ovl_lookup_temp(struct dentry *workdir);
struct cattr {
dev_t rdev;
umode_t mode;
/* creds of process who forced instantiation of super block */
const struct cred *creator_cred;
bool tmpfile;
+ bool noxattr;
wait_queue_head_t copyup_wq;
/* sb common to all layers */
struct super_block *same_sb;
u64 version;
const char *redirect;
bool opaque;
+ bool impure;
bool copying;
};
struct rcu_head rcu;
dput(temp);
else
pr_warn("overlayfs: upper fs does not support tmpfile.\n");
+
+ /*
+ * Check if upper/work fs supports trusted.overlay.*
+ * xattr
+ */
+ err = ovl_do_setxattr(ufs->workdir, OVL_XATTR_OPAQUE,
+ "0", 1, 0);
+ if (err) {
+ ufs->noxattr = true;
+ pr_warn("overlayfs: upper fs does not support xattr.\n");
+ } else {
+ vfs_removexattr(ufs->workdir, OVL_XATTR_OPAQUE);
+ }
}
}
path_put(&workpath);
kfree(lowertmp);
- oe->__upperdentry = upperpath.dentry;
+ if (upperpath.dentry) {
+ oe->__upperdentry = upperpath.dentry;
+ oe->impure = ovl_is_impuredir(upperpath.dentry);
+ }
for (i = 0; i < numlower; i++) {
oe->lowerstack[i].dentry = stack[i].dentry;
oe->lowerstack[i].mnt = ufs->lower_mnt[i];
return oe->opaque;
}
+bool ovl_dentry_is_impure(struct dentry *dentry)
+{
+ struct ovl_entry *oe = dentry->d_fsdata;
+
+ return oe->impure;
+}
+
bool ovl_dentry_is_whiteout(struct dentry *dentry)
{
return !dentry->d_inode && ovl_dentry_is_opaque(dentry);
{
struct ovl_fs *ofs = sb->s_fs_info;
- return ofs->config.redirect_dir;
-}
-
-void ovl_clear_redirect_dir(struct super_block *sb)
-{
- struct ovl_fs *ofs = sb->s_fs_info;
-
- ofs->config.redirect_dir = false;
+ return ofs->config.redirect_dir && !ofs->noxattr;
}
const char *ovl_dentry_get_redirect(struct dentry *dentry)
wake_up_locked(&ofs->copyup_wq);
spin_unlock(&ofs->copyup_wq.lock);
}
+
+bool ovl_check_dir_xattr(struct dentry *dentry, const char *name)
+{
+ int res;
+ char val;
+
+ if (!d_is_dir(dentry))
+ return false;
+
+ res = vfs_getxattr(dentry, name, &val, 1);
+ if (res == 1 && val == 'y')
+ return true;
+
+ return false;
+}
+
+int ovl_check_setxattr(struct dentry *dentry, struct dentry *upperdentry,
+ const char *name, const void *value, size_t size,
+ int xerr)
+{
+ int err;
+ struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
+
+ if (ofs->noxattr)
+ return xerr;
+
+ err = ovl_do_setxattr(upperdentry, name, value, size, 0);
+
+ if (err == -EOPNOTSUPP) {
+ pr_warn("overlayfs: cannot set %s xattr on upper\n", name);
+ ofs->noxattr = true;
+ return xerr;
+ }
+
+ return err;
+}
+
+int ovl_set_impure(struct dentry *dentry, struct dentry *upperdentry)
+{
+ int err;
+ struct ovl_entry *oe = dentry->d_fsdata;
+
+ if (oe->impure)
+ return 0;
+
+ /*
+ * Do not fail when upper doesn't support xattrs.
+ * Upper inodes won't have origin nor redirect xattr anyway.
+ */
+ err = ovl_check_setxattr(dentry, upperdentry, OVL_XATTR_IMPURE,
+ "y", 1, 0);
+ if (!err)
+ oe->impure = true;
+
+ return err;
+}
if (!mmget_not_zero(mm))
goto free;
- flags = write ? FOLL_WRITE : 0;
+ flags = FOLL_FORCE | (write ? FOLL_WRITE : 0);
while (count > 0) {
int this_len = min_t(int, count, PAGE_SIZE);
}
EXPORT_SYMBOL(dquot_initialize);
+bool dquot_initialize_needed(struct inode *inode)
+{
+ struct dquot **dquots;
+ int i;
+
+ if (!dquot_active(inode))
+ return false;
+
+ dquots = i_dquot(inode);
+ for (i = 0; i < MAXQUOTAS; i++)
+ if (!dquots[i] && sb_has_quota_active(inode->i_sb, i))
+ return true;
+ return false;
+}
+EXPORT_SYMBOL(dquot_initialize_needed);
+
/*
* Release all quotas referenced by inode.
*
depth = reiserfs_write_unlock_nested(s);
if (reiserfs_barrier_flush(s))
__sync_dirty_buffer(jl->j_commit_bh,
- REQ_PREFLUSH | REQ_FUA);
+ REQ_SYNC | REQ_PREFLUSH | REQ_FUA);
else
sync_dirty_buffer(jl->j_commit_bh);
reiserfs_write_lock_nested(s, depth);
if (reiserfs_barrier_flush(sb))
__sync_dirty_buffer(journal->j_header_bh,
- REQ_PREFLUSH | REQ_FUA);
+ REQ_SYNC | REQ_PREFLUSH | REQ_FUA);
else
sync_dirty_buffer(journal->j_header_bh);
inode->i_bytes -= 512;
}
}
+EXPORT_SYMBOL(__inode_add_bytes);
void inode_add_bytes(struct inode *inode, loff_t bytes)
{
ufs_error (sb, "ufs_free_fragments",
"bit already cleared for fragment %u", i);
}
-
+
+ inode_sub_bytes(inode, count << uspi->s_fshift);
fs32_add(sb, &ucg->cg_cs.cs_nffree, count);
uspi->cs_total.cs_nffree += count;
fs32_add(sb, &UFS_SB(sb)->fs_cs(cgno).cs_nffree, count);
ufs_error(sb, "ufs_free_blocks", "freeing free fragment");
}
ubh_setblock(UCPI_UBH(ucpi), ucpi->c_freeoff, blkno);
+ inode_sub_bytes(inode, uspi->s_fpb << uspi->s_fshift);
if ((UFS_SB(sb)->s_flags & UFS_CG_MASK) == UFS_CG_44BSD)
ufs_clusteracct (sb, ucpi, blkno, 1);
return 0;
}
+static bool try_add_frags(struct inode *inode, unsigned frags)
+{
+ unsigned size = frags * i_blocksize(inode);
+ spin_lock(&inode->i_lock);
+ __inode_add_bytes(inode, size);
+ if (unlikely((u32)inode->i_blocks != inode->i_blocks)) {
+ __inode_sub_bytes(inode, size);
+ spin_unlock(&inode->i_lock);
+ return false;
+ }
+ spin_unlock(&inode->i_lock);
+ return true;
+}
+
static u64 ufs_add_fragments(struct inode *inode, u64 fragment,
unsigned oldcount, unsigned newcount)
{
for (i = oldcount; i < newcount; i++)
if (ubh_isclr (UCPI_UBH(ucpi), ucpi->c_freeoff, fragno + i))
return 0;
+
+ if (!try_add_frags(inode, count))
+ return 0;
/*
* Block can be extended
*/
ubh_setbit (UCPI_UBH(ucpi), ucpi->c_freeoff, goal + i);
i = uspi->s_fpb - count;
+ inode_sub_bytes(inode, i << uspi->s_fshift);
fs32_add(sb, &ucg->cg_cs.cs_nffree, i);
uspi->cs_total.cs_nffree += i;
fs32_add(sb, &UFS_SB(sb)->fs_cs(cgno).cs_nffree, i);
result = ufs_bitmap_search (sb, ucpi, goal, allocsize);
if (result == INVBLOCK)
return 0;
+ if (!try_add_frags(inode, count))
+ return 0;
for (i = 0; i < count; i++)
ubh_clrbit (UCPI_UBH(ucpi), ucpi->c_freeoff, result + i);
return INVBLOCK;
ucpi->c_rotor = result;
gotit:
+ if (!try_add_frags(inode, uspi->s_fpb))
+ return 0;
blkno = ufs_fragstoblks(result);
ubh_clrblock (UCPI_UBH(ucpi), ucpi->c_freeoff, blkno);
if ((UFS_SB(sb)->s_flags & UFS_CG_MASK) == UFS_CG_44BSD)
p = ufs_get_direct_data_ptr(uspi, ufsi, block);
tmp = ufs_new_fragments(inode, p, lastfrag, ufs_data_ptr_to_cpu(sb, p),
- new_size, err, locked_page);
+ new_size - (lastfrag & uspi->s_fpbmask), err,
+ locked_page);
return tmp != 0;
}
goal += uspi->s_fpb;
}
tmp = ufs_new_fragments(inode, p, ufs_blknum(new_fragment),
- goal, uspi->s_fpb, err, locked_page);
+ goal, nfrags, err, locked_page);
if (!tmp) {
*err = -ENOSPC;
if (!create) {
phys64 = ufs_frag_map(inode, offsets, depth);
- goto out;
+ if (phys64)
+ map_bh(bh_result, sb, phys64 + frag);
+ return 0;
}
/* This code entered only while writing ....? */
truncate_inode_pages_final(&inode->i_data);
if (want_delete) {
inode->i_size = 0;
- if (inode->i_blocks)
+ if (inode->i_blocks &&
+ (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+ S_ISLNK(inode->i_mode)))
ufs_truncate_blocks(inode);
+ ufs_update_inode(inode, inode_needs_sync(inode));
}
invalidate_inode_buffers(inode);
return err;
}
-static void __ufs_truncate_blocks(struct inode *inode)
+static void ufs_truncate_blocks(struct inode *inode)
{
struct ufs_inode_info *ufsi = UFS_I(inode);
struct super_block *sb = inode->i_sb;
truncate_setsize(inode, size);
- __ufs_truncate_blocks(inode);
+ ufs_truncate_blocks(inode);
inode->i_mtime = inode->i_ctime = current_time(inode);
mark_inode_dirty(inode);
out:
return err;
}
-static void ufs_truncate_blocks(struct inode *inode)
-{
- if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
- S_ISLNK(inode->i_mode)))
- return;
- if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
- return;
- __ufs_truncate_blocks(inode);
-}
-
int ufs_setattr(struct dentry *dentry, struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
return;
}
+static u64 ufs_max_bytes(struct super_block *sb)
+{
+ struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi;
+ int bits = uspi->s_apbshift;
+ u64 res;
+
+ if (bits > 21)
+ res = ~0ULL;
+ else
+ res = UFS_NDADDR + (1LL << bits) + (1LL << (2*bits)) +
+ (1LL << (3*bits));
+
+ if (res >= (MAX_LFS_FILESIZE >> uspi->s_bshift))
+ return MAX_LFS_FILESIZE;
+ return res << uspi->s_bshift;
+}
+
static int ufs_fill_super(struct super_block *sb, void *data, int silent)
{
struct ufs_sb_info * sbi;
uspi->s_dirblksize = UFS_SECTOR_SIZE;
super_block_offset=UFS_SBLOCK;
- /* Keep 2Gig file limit. Some UFS variants need to override
- this but as I don't know which I'll let those in the know loosen
- the rules */
+ sb->s_maxbytes = MAX_LFS_FILESIZE;
+
switch (sbi->s_mount_opt & UFS_MOUNT_UFSTYPE) {
case UFS_MOUNT_UFSTYPE_44BSD:
UFSD("ufstype=44bsd\n");
"fast symlink size (%u)\n", uspi->s_maxsymlinklen);
uspi->s_maxsymlinklen = maxsymlen;
}
+ sb->s_maxbytes = ufs_max_bytes(sb);
sb->s_max_links = UFS_LINK_MAX;
inode = ufs_iget(sb, UFS_ROOTINO);
static inline int _ubh_isblockset_(struct ufs_sb_private_info * uspi,
struct ufs_buffer_head * ubh, unsigned begin, unsigned block)
{
+ u8 mask;
switch (uspi->s_fpb) {
case 8:
return (*ubh_get_addr (ubh, begin + block) == 0xff);
case 4:
- return (*ubh_get_addr (ubh, begin + (block >> 1)) == (0x0f << ((block & 0x01) << 2)));
+ mask = 0x0f << ((block & 0x01) << 2);
+ return (*ubh_get_addr (ubh, begin + (block >> 1)) & mask) == mask;
case 2:
- return (*ubh_get_addr (ubh, begin + (block >> 2)) == (0x03 << ((block & 0x03) << 1)));
+ mask = 0x03 << ((block & 0x03) << 1);
+ return (*ubh_get_addr (ubh, begin + (block >> 2)) & mask) == mask;
case 1:
- return (*ubh_get_addr (ubh, begin + (block >> 3)) == (0x01 << (block & 0x07)));
+ mask = 0x01 << (block & 0x07);
+ return (*ubh_get_addr (ubh, begin + (block >> 3)) & mask) == mask;
}
return 0;
}
xfs_bmbt_rec_t *frp;
xfs_fsblock_t nextbno;
xfs_extnum_t num_recs;
- xfs_extnum_t start;
num_recs = xfs_btree_get_numrecs(block);
if (unlikely(i + num_recs > room)) {
* Copy records into the extent records.
*/
frp = XFS_BMBT_REC_ADDR(mp, block, 1);
- start = i;
for (j = 0; j < num_recs; j++, i++, frp++) {
xfs_bmbt_rec_host_t *trp = xfs_iext_get_ext(ifp, i);
trp->l0 = be64_to_cpu(frp->l0);
}
temp = xfs_bmap_worst_indlen(bma->ip, temp);
temp2 = xfs_bmap_worst_indlen(bma->ip, temp2);
- diff = (int)(temp + temp2 - startblockval(PREV.br_startblock) -
- (bma->cur ? bma->cur->bc_private.b.allocated : 0));
+ diff = (int)(temp + temp2 -
+ (startblockval(PREV.br_startblock) -
+ (bma->cur ?
+ bma->cur->bc_private.b.allocated : 0)));
if (diff > 0) {
error = xfs_mod_fdblocks(bma->ip->i_mount,
-((int64_t)diff), false);
temp = da_new;
if (bma->cur)
temp += bma->cur->bc_private.b.allocated;
- ASSERT(temp <= da_old);
if (temp < da_old)
xfs_mod_fdblocks(bma->ip->i_mount,
(int64_t)(da_old - temp), false);
xfs_btree_readahead_ptr(cur, ptr, 1);
/* save for the next iteration of the loop */
- lptr = *ptr;
+ xfs_btree_copy_ptrs(cur, &lptr, ptr, 1);
}
/* for each buffer in the level */
if (mp->m_sb.sb_agblocks >= XFS_REFC_COW_START)
return -EOPNOTSUPP;
- error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp);
+ INIT_LIST_HEAD(&debris);
+
+ /*
+ * In this first part, we use an empty transaction to gather up
+ * all the leftover CoW extents so that we can subsequently
+ * delete them. The empty transaction is used to avoid
+ * a buffer lock deadlock if there happens to be a loop in the
+ * refcountbt because we're allowed to re-grab a buffer that is
+ * already attached to our transaction. When we're done
+ * recording the CoW debris we cancel the (empty) transaction
+ * and everything goes away cleanly.
+ */
+ error = xfs_trans_alloc_empty(mp, &tp);
if (error)
return error;
- cur = xfs_refcountbt_init_cursor(mp, NULL, agbp, agno, NULL);
+
+ error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp);
+ if (error)
+ goto out_trans;
+ cur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno, NULL);
/* Find all the leftover CoW staging extents. */
- INIT_LIST_HEAD(&debris);
memset(&low, 0, sizeof(low));
memset(&high, 0, sizeof(high));
low.rc.rc_startblock = XFS_REFC_COW_START;
if (error)
goto out_cursor;
xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
- xfs_buf_relse(agbp);
+ xfs_trans_brelse(tp, agbp);
+ xfs_trans_cancel(tp);
/* Now iterate the list to free the leftovers */
- list_for_each_entry(rr, &debris, rr_list) {
+ list_for_each_entry_safe(rr, n, &debris, rr_list) {
/* Set up transaction. */
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, 0, 0, 0, &tp);
if (error)
error = xfs_trans_commit(tp);
if (error)
goto out_free;
+
+ list_del(&rr->rr_list);
+ kmem_free(rr);
}
+ return error;
+out_defer:
+ xfs_defer_cancel(&dfops);
+out_trans:
+ xfs_trans_cancel(tp);
out_free:
/* Free the leftover list */
list_for_each_entry_safe(rr, n, &debris, rr_list) {
out_cursor:
xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
- xfs_buf_relse(agbp);
- goto out_free;
-
-out_defer:
- xfs_defer_cancel(&dfops);
- xfs_trans_cancel(tp);
- goto out_free;
+ xfs_trans_brelse(tp, agbp);
+ goto out_trans;
}
}
break;
default:
+ /* Local format data forks report no extents. */
+ if (ip->i_d.di_format == XFS_DINODE_FMT_LOCAL) {
+ bmv->bmv_entries = 0;
+ return 0;
+ }
if (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS &&
- ip->i_d.di_format != XFS_DINODE_FMT_BTREE &&
- ip->i_d.di_format != XFS_DINODE_FMT_LOCAL)
+ ip->i_d.di_format != XFS_DINODE_FMT_BTREE)
return -EINVAL;
if (xfs_get_extsz_hint(ip) ||
* extents.
*/
if (map[i].br_startblock == DELAYSTARTBLOCK &&
- map[i].br_startoff <= XFS_B_TO_FSB(mp, XFS_ISIZE(ip)))
+ map[i].br_startoff < XFS_B_TO_FSB(mp, XFS_ISIZE(ip)))
ASSERT((iflags & BMV_IF_DELALLOC) != 0);
if (map[i].br_startblock == HOLESTARTBLOCK &&
xfs_buf_ioacct_inc(
struct xfs_buf *bp)
{
- if (bp->b_flags & (XBF_NO_IOACCT|_XBF_IN_FLIGHT))
+ if (bp->b_flags & XBF_NO_IOACCT)
return;
ASSERT(bp->b_flags & XBF_ASYNC);
- bp->b_flags |= _XBF_IN_FLIGHT;
- percpu_counter_inc(&bp->b_target->bt_io_count);
+ spin_lock(&bp->b_lock);
+ if (!(bp->b_state & XFS_BSTATE_IN_FLIGHT)) {
+ bp->b_state |= XFS_BSTATE_IN_FLIGHT;
+ percpu_counter_inc(&bp->b_target->bt_io_count);
+ }
+ spin_unlock(&bp->b_lock);
}
/*
* freed and unaccount from the buftarg.
*/
static inline void
-xfs_buf_ioacct_dec(
+__xfs_buf_ioacct_dec(
struct xfs_buf *bp)
{
- if (!(bp->b_flags & _XBF_IN_FLIGHT))
- return;
+ ASSERT(spin_is_locked(&bp->b_lock));
- bp->b_flags &= ~_XBF_IN_FLIGHT;
- percpu_counter_dec(&bp->b_target->bt_io_count);
+ if (bp->b_state & XFS_BSTATE_IN_FLIGHT) {
+ bp->b_state &= ~XFS_BSTATE_IN_FLIGHT;
+ percpu_counter_dec(&bp->b_target->bt_io_count);
+ }
+}
+
+static inline void
+xfs_buf_ioacct_dec(
+ struct xfs_buf *bp)
+{
+ spin_lock(&bp->b_lock);
+ __xfs_buf_ioacct_dec(bp);
+ spin_unlock(&bp->b_lock);
}
/*
* unaccounted (released to LRU) before that occurs. Drop in-flight
* status now to preserve accounting consistency.
*/
- xfs_buf_ioacct_dec(bp);
-
spin_lock(&bp->b_lock);
+ __xfs_buf_ioacct_dec(bp);
+
atomic_set(&bp->b_lru_ref, 0);
if (!(bp->b_state & XFS_BSTATE_DISPOSE) &&
(list_lru_del(&bp->b_target->bt_lru, &bp->b_lru)))
* ensures the decrement occurs only once per-buf.
*/
if ((atomic_read(&bp->b_hold) == 1) && !list_empty(&bp->b_lru))
- xfs_buf_ioacct_dec(bp);
+ __xfs_buf_ioacct_dec(bp);
goto out_unlock;
}
/* the last reference has been dropped ... */
- xfs_buf_ioacct_dec(bp);
+ __xfs_buf_ioacct_dec(bp);
if (!(bp->b_flags & XBF_STALE) && atomic_read(&bp->b_lru_ref)) {
/*
* If the buffer is added to the LRU take a new reference to the
#define _XBF_KMEM (1 << 21)/* backed by heap memory */
#define _XBF_DELWRI_Q (1 << 22)/* buffer on a delwri queue */
#define _XBF_COMPOUND (1 << 23)/* compound buffer */
-#define _XBF_IN_FLIGHT (1 << 25) /* I/O in flight, for accounting purposes */
typedef unsigned int xfs_buf_flags_t;
{ _XBF_PAGES, "PAGES" }, \
{ _XBF_KMEM, "KMEM" }, \
{ _XBF_DELWRI_Q, "DELWRI_Q" }, \
- { _XBF_COMPOUND, "COMPOUND" }, \
- { _XBF_IN_FLIGHT, "IN_FLIGHT" }
+ { _XBF_COMPOUND, "COMPOUND" }
/*
* Internal state flags.
*/
#define XFS_BSTATE_DISPOSE (1 << 0) /* buffer being discarded */
+#define XFS_BSTATE_IN_FLIGHT (1 << 1) /* I/O in flight */
/*
* The xfs_buftarg contains 2 notions of "sector size" -
index = startoff >> PAGE_SHIFT;
endoff = XFS_FSB_TO_B(mp, map->br_startoff + map->br_blockcount);
- end = endoff >> PAGE_SHIFT;
+ end = (endoff - 1) >> PAGE_SHIFT;
do {
int want;
unsigned nr_pages;
unsigned int i;
- want = min_t(pgoff_t, end - index, PAGEVEC_SIZE);
+ want = min_t(pgoff_t, end - index, PAGEVEC_SIZE - 1) + 1;
nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index,
want);
- /*
- * No page mapped into given range. If we are searching holes
- * and if this is the first time we got into the loop, it means
- * that the given offset is landed in a hole, return it.
- *
- * If we have already stepped through some block buffers to find
- * holes but they all contains data. In this case, the last
- * offset is already updated and pointed to the end of the last
- * mapped page, if it does not reach the endpoint to search,
- * that means there should be a hole between them.
- */
- if (nr_pages == 0) {
- /* Data search found nothing */
- if (type == DATA_OFF)
- break;
-
- ASSERT(type == HOLE_OFF);
- if (lastoff == startoff || lastoff < endoff) {
- found = true;
- *offset = lastoff;
- }
- break;
- }
-
- /*
- * At lease we found one page. If this is the first time we
- * step into the loop, and if the first page index offset is
- * greater than the given search offset, a hole was found.
- */
- if (type == HOLE_OFF && lastoff == startoff &&
- lastoff < page_offset(pvec.pages[0])) {
- found = true;
+ if (nr_pages == 0)
break;
- }
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
* file mapping. However, page->index will not change
* because we have a reference on the page.
*
- * Searching done if the page index is out of range.
- * If the current offset is not reaches the end of
- * the specified search range, there should be a hole
- * between them.
+ * If current page offset is beyond where we've ended,
+ * we've found a hole.
*/
- if (page->index > end) {
- if (type == HOLE_OFF && lastoff < endoff) {
- *offset = lastoff;
- found = true;
- }
+ if (type == HOLE_OFF && lastoff < endoff &&
+ lastoff < page_offset(pvec.pages[i])) {
+ found = true;
+ *offset = lastoff;
goto out;
}
+ /* Searching done if the page index is out of range. */
+ if (page->index > end)
+ goto out;
lock_page(page);
/*
/*
* The number of returned pages less than our desired, search
- * done. In this case, nothing was found for searching data,
- * but we found a hole behind the last offset.
+ * done.
*/
- if (nr_pages < want) {
- if (type == HOLE_OFF) {
- *offset = lastoff;
- found = true;
- }
+ if (nr_pages < want)
break;
- }
index = pvec.pages[i - 1]->index + 1;
pagevec_release(&pvec);
} while (index <= end);
+ /* No page at lastoff and we are not done - we found a hole. */
+ if (type == HOLE_OFF && lastoff < endoff) {
+ *offset = lastoff;
+ found = true;
+ }
out:
pagevec_release(&pvec);
return found;
struct xfs_fsmap dkeys[2]; /* per-dev keys */
struct xfs_getfsmap_dev handlers[XFS_GETFSMAP_DEVS];
struct xfs_getfsmap_info info = { NULL };
+ bool use_rmap;
int i;
int error = 0;
!xfs_getfsmap_is_valid_device(mp, &head->fmh_keys[1]))
return -EINVAL;
+ use_rmap = capable(CAP_SYS_ADMIN) &&
+ xfs_sb_version_hasrmapbt(&mp->m_sb);
head->fmh_entries = 0;
/* Set up our device handlers. */
memset(handlers, 0, sizeof(handlers));
handlers[0].dev = new_encode_dev(mp->m_ddev_targp->bt_dev);
- if (xfs_sb_version_hasrmapbt(&mp->m_sb))
+ if (use_rmap)
handlers[0].fn = xfs_getfsmap_datadev_rmapbt;
else
handlers[0].fn = xfs_getfsmap_datadev_bnobt;
/* optionally associate a dax device with the iomap bdev */
bdev = iomap->bdev;
if (blk_queue_dax(bdev->bd_queue))
- iomap->dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
+ iomap->dax_dev = fs_dax_get_by_host(bdev->bd_disk->disk_name);
else
iomap->dax_dev = NULL;
unsigned flags,
struct iomap *iomap)
{
- put_dax(iomap->dax_dev);
+ fs_put_dax(iomap->dax_dev);
if ((flags & IOMAP_WRITE) && iomap->type == IOMAP_DELALLOC)
return xfs_file_iomap_end_delalloc(XFS_I(inode), offset,
length, written, iomap);
int drm_dp_start_crc(struct drm_dp_aux *aux, struct drm_crtc *crtc);
int drm_dp_stop_crc(struct drm_dp_aux *aux);
+struct drm_dp_dpcd_ident {
+ u8 oui[3];
+ u8 device_id[6];
+ u8 hw_rev;
+ u8 sw_major_rev;
+ u8 sw_minor_rev;
+} __packed;
+
+/**
+ * struct drm_dp_desc - DP branch/sink device descriptor
+ * @ident: DP device identification from DPCD 0x400 (sink) or 0x500 (branch).
+ * @quirks: Quirks; use drm_dp_has_quirk() to query for the quirks.
+ */
+struct drm_dp_desc {
+ struct drm_dp_dpcd_ident ident;
+ u32 quirks;
+};
+
+int drm_dp_read_desc(struct drm_dp_aux *aux, struct drm_dp_desc *desc,
+ bool is_branch);
+
+/**
+ * enum drm_dp_quirk - Display Port sink/branch device specific quirks
+ *
+ * Display Port sink and branch devices in the wild have a variety of bugs, try
+ * to collect them here. The quirks are shared, but it's up to the drivers to
+ * implement workarounds for them.
+ */
+enum drm_dp_quirk {
+ /**
+ * @DP_DPCD_QUIRK_LIMITED_M_N:
+ *
+ * The device requires main link attributes Mvid and Nvid to be limited
+ * to 16 bits.
+ */
+ DP_DPCD_QUIRK_LIMITED_M_N,
+};
+
+/**
+ * drm_dp_has_quirk() - does the DP device have a specific quirk
+ * @desc: Device decriptor filled by drm_dp_read_desc()
+ * @quirk: Quirk to query for
+ *
+ * Return true if DP device identified by @desc has @quirk.
+ */
+static inline bool
+drm_dp_has_quirk(const struct drm_dp_desc *desc, enum drm_dp_quirk quirk)
+{
+ return desc->quirks & BIT(quirk);
+}
+
#endif /* _DRM_DP_HELPER_H_ */
/* either a GICv2 CPU interface */
gpa_t vgic_cpu_base;
/* or a number of GICv3 redistributor regions */
- gpa_t vgic_redist_base;
+ struct {
+ gpa_t vgic_redist_base;
+ gpa_t vgic_redist_free_offset;
+ };
};
/* distributor enabled */
bool kick_requeue_list);
void blk_mq_kick_requeue_list(struct request_queue *q);
void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs);
-void blk_mq_abort_requeue_list(struct request_queue *q);
void blk_mq_complete_request(struct request *rq);
bool blk_mq_queue_stopped(struct request_queue *q);
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/string.h>
+
#ifdef CONFIG_CEPH_LIB_PRETTYDEBUG
/*
*/
# if defined(DEBUG) || defined(CONFIG_DYNAMIC_DEBUG)
-extern const char *ceph_file_part(const char *s, int len);
# define dout(fmt, ...) \
pr_debug("%.*s %12.12s:%-4d : " fmt, \
8 - (int)sizeof(KBUILD_MODNAME), " ", \
- ceph_file_part(__FILE__, sizeof(__FILE__)), \
- __LINE__, ##__VA_ARGS__)
+ kbasename(__FILE__), __LINE__, ##__VA_ARGS__)
# else
/* faux printk call just to see any compiler warnings. */
# define dout(fmt, ...) do { \
CSS_ONLINE = (1 << 1), /* between ->css_online() and ->css_offline() */
CSS_RELEASED = (1 << 2), /* refcnt reached zero, released */
CSS_VISIBLE = (1 << 3), /* css is visible to userland */
+ CSS_DYING = (1 << 4), /* css is dying */
};
/* bits in struct cgroup flags field */
return true;
}
+/**
+ * css_is_dying - test whether the specified css is dying
+ * @css: target css
+ *
+ * Test whether @css is in the process of offlining or already offline. In
+ * most cases, ->css_online() and ->css_offline() callbacks should be
+ * enough; however, the actual offline operations are RCU delayed and this
+ * test returns %true also when @css is scheduled to be offlined.
+ *
+ * This is useful, for example, when the use case requires synchronous
+ * behavior with respect to cgroup removal. cgroup removal schedules css
+ * offlining but the css can seem alive while the operation is being
+ * delayed. If the delay affects user visible semantics, this test can be
+ * used to resolve the situation.
+ */
+static inline bool css_is_dying(struct cgroup_subsys_state *css)
+{
+ return !(css->flags & CSS_NO_REF) && percpu_ref_is_dying(&css->refcnt);
+}
+
/**
* css_put - put a css reference
* @css: target css
* with any version that can compile the kernel
*/
#define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__)
+
+/*
+ * GCC does not warn about unused static inline functions for
+ * -Wunused-function. This turns out to avoid the need for complex #ifdef
+ * directives. Suppress the warning in clang as well.
+ */
+#undef inline
+#define inline inline __attribute__((unused)) notrace
void **, pfn_t *);
};
+#if IS_ENABLED(CONFIG_DAX)
+struct dax_device *dax_get_by_host(const char *host);
+void put_dax(struct dax_device *dax_dev);
+#else
+static inline struct dax_device *dax_get_by_host(const char *host)
+{
+ return NULL;
+}
+
+static inline void put_dax(struct dax_device *dax_dev)
+{
+}
+#endif
+
int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff);
#if IS_ENABLED(CONFIG_FS_DAX)
int __bdev_dax_supported(struct super_block *sb, int blocksize);
{
return __bdev_dax_supported(sb, blocksize);
}
+
+static inline struct dax_device *fs_dax_get_by_host(const char *host)
+{
+ return dax_get_by_host(host);
+}
+
+static inline void fs_put_dax(struct dax_device *dax_dev)
+{
+ put_dax(dax_dev);
+}
+
#else
static inline int bdev_dax_supported(struct super_block *sb, int blocksize)
{
return -EOPNOTSUPP;
}
-#endif
-#if IS_ENABLED(CONFIG_DAX)
-struct dax_device *dax_get_by_host(const char *host);
-void put_dax(struct dax_device *dax_dev);
-#else
-static inline struct dax_device *dax_get_by_host(const char *host)
+static inline struct dax_device *fs_dax_get_by_host(const char *host)
{
return NULL;
}
-static inline void put_dax(struct dax_device *dax_dev)
+static inline void fs_put_dax(struct dax_device *dax_dev)
{
}
#endif
struct iommu_domain;
struct msi_msg;
+struct device;
static inline int iommu_dma_init(void)
{
#endif
/* managed by elevator core */
- char icq_cache_name[ELV_NAME_MAX + 5]; /* elvname + "_io_cq" */
+ char icq_cache_name[ELV_NAME_MAX + 6]; /* elvname + "_io_cq" */
struct list_head list;
};
.off = OFF, \
.imm = IMM })
+/* Unconditional jumps, goto pc + off16 */
+
+#define BPF_JMP_A(OFF) \
+ ((struct bpf_insn) { \
+ .code = BPF_JMP | BPF_JA, \
+ .dst_reg = 0, \
+ .src_reg = 0, \
+ .off = OFF, \
+ .imm = 0 })
+
/* Function call */
#define BPF_EMIT_CALL(FUNC) \
#define ___GFP_WRITE 0x800000u
#define ___GFP_KSWAPD_RECLAIM 0x1000000u
#ifdef CONFIG_LOCKDEP
-#define ___GFP_NOLOCKDEP 0x4000000u
+#define ___GFP_NOLOCKDEP 0x2000000u
#else
#define ___GFP_NOLOCKDEP 0
#endif
.flags = _flags, \
}
+#ifdef CONFIG_GPIOLIB
void gpiod_add_lookup_table(struct gpiod_lookup_table *table);
void gpiod_remove_lookup_table(struct gpiod_lookup_table *table);
+#else
+static inline
+void gpiod_add_lookup_table(struct gpiod_lookup_table *table) {}
+static inline
+void gpiod_remove_lookup_table(struct gpiod_lookup_table *table) {}
+#endif
#endif /* __LINUX_GPIO_MACHINE_H */
static inline netdev_features_t vlan_features_check(const struct sk_buff *skb,
netdev_features_t features)
{
- if (skb_vlan_tagged_multi(skb))
- features = netdev_intersect_features(features,
- NETIF_F_SG |
- NETIF_F_HIGHDMA |
- NETIF_F_FRAGLIST |
- NETIF_F_HW_CSUM |
- NETIF_F_HW_VLAN_CTAG_TX |
- NETIF_F_HW_VLAN_STAG_TX);
+ if (skb_vlan_tagged_multi(skb)) {
+ /* In the case of multi-tagged packets, use a direct mask
+ * instead of using netdev_interesect_features(), to make
+ * sure that only devices supporting NETIF_F_HW_CSUM will
+ * have checksum offloading support.
+ */
+ features &= NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_HW_CSUM |
+ NETIF_F_FRAGLIST | NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_HW_VLAN_STAG_TX;
+ }
return features;
}
#define ICH_HCR_EN (1 << 0)
#define ICH_HCR_UIE (1 << 1)
+#define ICH_VMCR_ACK_CTL_SHIFT 2
+#define ICH_VMCR_ACK_CTL_MASK (1 << ICH_VMCR_ACK_CTL_SHIFT)
+#define ICH_VMCR_FIQ_EN_SHIFT 3
+#define ICH_VMCR_FIQ_EN_MASK (1 << ICH_VMCR_FIQ_EN_SHIFT)
#define ICH_VMCR_CBPR_SHIFT 4
#define ICH_VMCR_CBPR_MASK (1 << ICH_VMCR_CBPR_SHIFT)
#define ICH_VMCR_EOIM_SHIFT 9
#define GICC_ENABLE 0x1
#define GICC_INT_PRI_THRESHOLD 0xf0
-#define GIC_CPU_CTRL_EOImodeNS (1 << 9)
+#define GIC_CPU_CTRL_EnableGrp0_SHIFT 0
+#define GIC_CPU_CTRL_EnableGrp0 (1 << GIC_CPU_CTRL_EnableGrp0_SHIFT)
+#define GIC_CPU_CTRL_EnableGrp1_SHIFT 1
+#define GIC_CPU_CTRL_EnableGrp1 (1 << GIC_CPU_CTRL_EnableGrp1_SHIFT)
+#define GIC_CPU_CTRL_AckCtl_SHIFT 2
+#define GIC_CPU_CTRL_AckCtl (1 << GIC_CPU_CTRL_AckCtl_SHIFT)
+#define GIC_CPU_CTRL_FIQEn_SHIFT 3
+#define GIC_CPU_CTRL_FIQEn (1 << GIC_CPU_CTRL_FIQEn_SHIFT)
+#define GIC_CPU_CTRL_CBPR_SHIFT 4
+#define GIC_CPU_CTRL_CBPR (1 << GIC_CPU_CTRL_CBPR_SHIFT)
+#define GIC_CPU_CTRL_EOImodeNS_SHIFT 9
+#define GIC_CPU_CTRL_EOImodeNS (1 << GIC_CPU_CTRL_EOImodeNS_SHIFT)
#define GICC_IAR_INT_ID_MASK 0x3ff
#define GICC_INT_SPURIOUS 1023
#define GICH_LR_EOI (1 << 19)
#define GICH_LR_HW (1 << 31)
-#define GICH_VMCR_CTRL_SHIFT 0
-#define GICH_VMCR_CTRL_MASK (0x21f << GICH_VMCR_CTRL_SHIFT)
+#define GICH_VMCR_ENABLE_GRP0_SHIFT 0
+#define GICH_VMCR_ENABLE_GRP0_MASK (1 << GICH_VMCR_ENABLE_GRP0_SHIFT)
+#define GICH_VMCR_ENABLE_GRP1_SHIFT 1
+#define GICH_VMCR_ENABLE_GRP1_MASK (1 << GICH_VMCR_ENABLE_GRP1_SHIFT)
+#define GICH_VMCR_ACK_CTL_SHIFT 2
+#define GICH_VMCR_ACK_CTL_MASK (1 << GICH_VMCR_ACK_CTL_SHIFT)
+#define GICH_VMCR_FIQ_EN_SHIFT 3
+#define GICH_VMCR_FIQ_EN_MASK (1 << GICH_VMCR_FIQ_EN_SHIFT)
+#define GICH_VMCR_CBPR_SHIFT 4
+#define GICH_VMCR_CBPR_MASK (1 << GICH_VMCR_CBPR_SHIFT)
+#define GICH_VMCR_EOI_MODE_SHIFT 9
+#define GICH_VMCR_EOI_MODE_MASK (1 << GICH_VMCR_EOI_MODE_SHIFT)
+
#define GICH_VMCR_PRIMASK_SHIFT 27
#define GICH_VMCR_PRIMASK_MASK (0x1f << GICH_VMCR_PRIMASK_SHIFT)
#define GICH_VMCR_BINPOINT_SHIFT 21
/* TICK_USEC is the time between ticks in usec assuming fake USER_HZ */
#define TICK_USEC ((1000000UL + USER_HZ/2) / USER_HZ)
+#ifndef __jiffy_arch_data
+#define __jiffy_arch_data
+#endif
+
/*
* The 64-bit value is not atomic - you MUST NOT read it
* without sampling the sequence number in jiffies_lock.
* get_jiffies_64() will do this for you as appropriate.
*/
extern u64 __cacheline_aligned_in_smp jiffies_64;
-extern unsigned long volatile __cacheline_aligned_in_smp jiffies;
+extern unsigned long volatile __cacheline_aligned_in_smp __jiffy_arch_data jiffies;
#if (BITS_PER_LONG < 64)
u64 get_jiffies_64(void);
#ifdef KEY_DEBUGGING
unsigned magic;
#define KEY_DEBUG_MAGIC 0x18273645u
-#define KEY_DEBUG_MAGIC_X 0xf8e9dacbu
#endif
unsigned long flags; /* status flags (change with bitops) */
int write, void __user *buffer,
size_t *length, loff_t *ppos);
#endif
+extern void wait_for_kprobe_optimizer(void);
+#else
+static inline void wait_for_kprobe_optimizer(void) { }
#endif /* CONFIG_OPTPROBES */
#ifdef CONFIG_KPROBES_ON_FTRACE
extern void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
}
#endif
+extern unsigned long memblock_reserved_memory_within(phys_addr_t start_addr,
+ phys_addr_t end_addr);
#else
static inline phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align)
{
return 0;
}
+static inline unsigned long memblock_reserved_memory_within(phys_addr_t start_addr,
+ phys_addr_t end_addr)
+{
+ return 0;
+}
+
#endif /* CONFIG_HAVE_MEMBLOCK */
#endif /* __KERNEL__ */
u16 rate_val;
};
+struct mlx4_qp *mlx4_qp_lookup(struct mlx4_dev *dev, u32 qpn);
int mlx4_update_qp(struct mlx4_dev *dev, u32 qpn,
enum mlx4_update_qp_attr attr,
struct mlx4_update_qp_params *params);
};
enum {
- CQE_RSS_HTYPE_IP = 0x3 << 6,
- CQE_RSS_HTYPE_L4 = 0x3 << 2,
+ CQE_RSS_HTYPE_IP = 0x3 << 2,
+ /* cqe->rss_hash_type[3:2] - IP destination selected for hash
+ * (00 = none, 01 = IPv4, 10 = IPv6, 11 = Reserved)
+ */
+ CQE_RSS_HTYPE_L4 = 0x3 << 6,
+ /* cqe->rss_hash_type[7:6] - L4 destination selected for hash
+ * (00 = none, 01 = TCP. 10 = UDP, 11 = IPSEC.SPI
+ */
};
enum {
typedef void (*mlx5_cmd_cbk_t)(int status, void *context);
+enum {
+ MLX5_CMD_ENT_STATE_PENDING_COMP,
+};
+
struct mlx5_cmd_work_ent {
+ unsigned long state;
struct mlx5_cmd_msg *in;
struct mlx5_cmd_msg *out;
void *uout;
void mlx5_rsc_event(struct mlx5_core_dev *dev, u32 rsn, int event_type);
void mlx5_srq_event(struct mlx5_core_dev *dev, u32 srqn, int event_type);
struct mlx5_core_srq *mlx5_core_get_srq(struct mlx5_core_dev *dev, u32 srqn);
-void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec);
+void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced);
void mlx5_cq_event(struct mlx5_core_dev *dev, u32 cqn, int event_type);
int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
int nent, u64 mask, const char *name,
MLX5_CAP_PORT_TYPE_ETH = 0x1,
};
+enum {
+ MLX5_CAP_UMR_FENCE_STRONG = 0x0,
+ MLX5_CAP_UMR_FENCE_SMALL = 0x1,
+ MLX5_CAP_UMR_FENCE_NONE = 0x2,
+};
+
struct mlx5_ifc_cmd_hca_cap_bits {
u8 reserved_at_0[0x80];
u8 reserved_at_202[0x1];
u8 ipoib_enhanced_offloads[0x1];
u8 ipoib_basic_offloads[0x1];
- u8 reserved_at_205[0xa];
+ u8 reserved_at_205[0x5];
+ u8 umr_fence[0x2];
+ u8 reserved_at_20c[0x3];
u8 drain_sigerr[0x1];
u8 cmdif_checksum[0x2];
u8 sigerr_cqe[0x1];
#define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */
#define FOLL_COW 0x4000 /* internal GUP flag */
+static inline int vm_fault_to_errno(int vm_fault, int foll_flags)
+{
+ if (vm_fault & VM_FAULT_OOM)
+ return -ENOMEM;
+ if (vm_fault & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE))
+ return (foll_flags & FOLL_HWPOISON) ? -EHWPOISON : -EFAULT;
+ if (vm_fault & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV))
+ return -EFAULT;
+ return 0;
+}
+
typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
void *data);
extern int apply_to_page_range(struct mm_struct *mm, unsigned long address,
* is the first PFN that needs to be initialised.
*/
unsigned long first_deferred_pfn;
+ unsigned long static_init_size;
#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
DMI_PRODUCT_VERSION,
DMI_PRODUCT_SERIAL,
DMI_PRODUCT_UUID,
+ DMI_PRODUCT_FAMILY,
DMI_BOARD_VENDOR,
DMI_BOARD_NAME,
DMI_BOARD_VERSION,
int xt_target_to_user(const struct xt_entry_target *t,
struct xt_entry_target __user *u);
int xt_data_to_user(void __user *dst, const void *src,
- int usersize, int size);
+ int usersize, int size, int aligned_size);
void *xt_copy_counters_from_user(const void __user *user, unsigned int len,
struct xt_counters_info *info, bool compat);
/* True if the target is not a standard target */
#define INVALID_TARGET (info->target < -NUM_STANDARD_TARGETS || info->target >= 0)
+static inline bool ebt_invalid_target(int target)
+{
+ return (target < -NUM_STANDARD_TARGETS || target >= 0);
+}
+
#endif
/* FC Port role bitmask - can merge with FC Port Roles in fc transport */
#define FC_PORT_ROLE_NVME_INITIATOR 0x10
-#define FC_PORT_ROLE_NVME_TARGET 0x11
-#define FC_PORT_ROLE_NVME_DISCOVERY 0x12
+#define FC_PORT_ROLE_NVME_TARGET 0x20
+#define FC_PORT_ROLE_NVME_DISCOVERY 0x40
/**
* sequence in one LLDD operation. Errors during Data
* sequence transmit must not allow RSP sequence to be sent.
*/
- NVMET_FCTGTFEAT_NEEDS_CMD_CPUSCHED = (1 << 1),
- /* Bit 1: When 0, the LLDD will deliver FCP CMD
- * on the CPU it should be affinitized to. Thus work will
- * be scheduled on the cpu received on. When 1, the LLDD
- * may not deliver the CMD on the CPU it should be worked
- * on. The transport should pick a cpu to schedule the work
- * on.
- */
- NVMET_FCTGTFEAT_CMD_IN_ISR = (1 << 2),
+ NVMET_FCTGTFEAT_CMD_IN_ISR = (1 << 1),
/* Bit 2: When 0, the LLDD is calling the cmd rcv handler
* in a non-isr context, allowing the transport to finish
* op completion in the calling context. When 1, the LLDD
* requiring the transport to transition to a workqueue
* for op completion.
*/
- NVMET_FCTGTFEAT_OPDONE_IN_ISR = (1 << 3),
+ NVMET_FCTGTFEAT_OPDONE_IN_ISR = (1 << 2),
/* Bit 3: When 0, the LLDD is calling the op done handler
* in a non-isr context, allowing the transport to finish
* op completion in the calling context. When 1, the LLDD
#include <linux/ioport.h>
#include <linux/of.h>
-typedef int const (*of_irq_init_cb_t)(struct device_node *, struct device_node *);
+typedef int (*of_irq_init_cb_t)(struct device_node *, struct device_node *);
/*
* Workarounds only applied to 32bit powermac machines
const char *bus_id,
struct device *parent);
+extern int of_platform_device_destroy(struct device *dev, void *data);
extern int of_platform_bus_probe(struct device_node *root,
const struct of_device_id *matches,
struct device *parent);
PCI_DEV_FLAGS_BRIDGE_XLATE_ROOT = (__force pci_dev_flags_t) (1 << 9),
/* Do not use FLR even if device advertises PCI_AF_CAP */
PCI_DEV_FLAGS_NO_FLR_RESET = (__force pci_dev_flags_t) (1 << 10),
+ /*
+ * Resume before calling the driver's system suspend hooks, disabling
+ * the direct_complete optimization.
+ */
+ PCI_DEV_FLAGS_NEEDS_RESUME = (__force pci_dev_flags_t) (1 << 11),
};
enum pci_irq_reroute_variant {
unsigned int max_vecs, unsigned int flags,
const struct irq_affinity *aff_desc)
{
- if (min_vecs > 1)
- return -EINVAL;
- return 1;
+ if ((flags & PCI_IRQ_LEGACY) && min_vecs == 1 && dev->irq)
+ return 1;
+ return -ENOSPC;
}
static inline void pci_free_irq_vectors(struct pci_dev *dev)
* @PIN_CONFIG_BIAS_PULL_UP: the pin will be pulled up (usually with high
* impedance to VDD). If the argument is != 0 pull-up is enabled,
* if it is 0, pull-up is total, i.e. the pin is connected to VDD.
- * @PIN_CONFIG_BIDIRECTIONAL: the pin will be configured to allow simultaneous
- * input and output operations.
* @PIN_CONFIG_DRIVE_OPEN_DRAIN: the pin will be driven with open drain (open
* collector) which means it is usually wired with other output ports
* which are then pulled up with an external resistor. Setting this
PIN_CONFIG_BIAS_PULL_DOWN,
PIN_CONFIG_BIAS_PULL_PIN_DEFAULT,
PIN_CONFIG_BIAS_PULL_UP,
- PIN_CONFIG_BIDIRECTIONAL,
PIN_CONFIG_DRIVE_OPEN_DRAIN,
PIN_CONFIG_DRIVE_OPEN_SOURCE,
PIN_CONFIG_DRIVE_PUSH_PULL,
unsigned long addr, unsigned long data);
extern void ptrace_notify(int exit_code);
extern void __ptrace_link(struct task_struct *child,
- struct task_struct *new_parent);
+ struct task_struct *new_parent,
+ const struct cred *ptracer_cred);
extern void __ptrace_unlink(struct task_struct *child);
extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead);
#define PTRACE_MODE_READ 0x01
if (unlikely(ptrace) && current->ptrace) {
child->ptrace = current->ptrace;
- __ptrace_link(child, current->parent);
+ __ptrace_link(child, current->parent, current->ptracer_cred);
if (child->ptrace & PT_SEIZED)
task_set_jobctl_pending(child, JOBCTL_TRAP_STOP);
set_tsk_thread_flag(child, TIF_SIGPENDING);
}
+ else
+ child->ptracer_cred = NULL;
}
/**
void inode_reclaim_rsv_space(struct inode *inode, qsize_t number);
int dquot_initialize(struct inode *inode);
+bool dquot_initialize_needed(struct inode *inode);
void dquot_drop(struct inode *inode);
struct dquot *dqget(struct super_block *sb, struct kqid qid);
static inline struct dquot *dqgrab(struct dquot *dquot)
return 0;
}
+static inline bool dquot_initialize_needed(struct inode *inode)
+{
+ return false;
+}
+
static inline void dquot_drop(struct inode *inode)
{
}
void serdev_device_close(struct serdev_device *);
unsigned int serdev_device_set_baudrate(struct serdev_device *, unsigned int);
void serdev_device_set_flow_control(struct serdev_device *, bool);
+int serdev_device_write_buf(struct serdev_device *, const unsigned char *, size_t);
void serdev_device_wait_until_sent(struct serdev_device *, long);
int serdev_device_get_tiocm(struct serdev_device *);
int serdev_device_set_tiocm(struct serdev_device *, int, int);
return 0;
}
static inline void serdev_device_set_flow_control(struct serdev_device *sdev, bool enable) {}
+static inline int serdev_device_write_buf(struct serdev_device *serdev,
+ const unsigned char *buf,
+ size_t count)
+{
+ return -ENODEV;
+}
static inline void serdev_device_wait_until_sent(struct serdev_device *sdev, long timeout) {}
static inline int serdev_device_get_tiocm(struct serdev_device *serdev)
{
struct device *serdev_tty_port_register(struct tty_port *port,
struct device *parent,
struct tty_driver *drv, int idx);
-void serdev_tty_port_unregister(struct tty_port *port);
+int serdev_tty_port_unregister(struct tty_port *port);
#else
static inline struct device *serdev_tty_port_register(struct tty_port *port,
struct device *parent,
{
return ERR_PTR(-ENODEV);
}
-static inline void serdev_tty_port_unregister(struct tty_port *port) {}
-#endif /* CONFIG_SERIAL_DEV_CTRL_TTYPORT */
-
-static inline int serdev_device_write_buf(struct serdev_device *serdev,
- const unsigned char *data,
- size_t count)
+static inline int serdev_tty_port_unregister(struct tty_port *port)
{
- return serdev_device_write(serdev, data, count, 0);
+ return -ENODEV;
}
+#endif /* CONFIG_SERIAL_DEV_CTRL_TTYPORT */
#endif /*_LINUX_SERDEV_H */
#ifndef __LINUX_SOC_RENESAS_RCAR_RST_H__
#define __LINUX_SOC_RENESAS_RCAR_RST_H__
+#if defined(CONFIG_ARCH_RCAR_GEN1) || defined(CONFIG_ARCH_RCAR_GEN2) || \
+ defined(CONFIG_ARCH_R8A7795) || defined(CONFIG_ARCH_R8A7796)
int rcar_rst_read_mode_pins(u32 *mode);
+#else
+static inline int rcar_rst_read_mode_pins(u32 *mode) { return -ENODEV; }
+#endif
#endif /* __LINUX_SOC_RENESAS_RCAR_RST_H__ */
{
int retval;
- preempt_disable();
retval = __srcu_read_lock(sp);
- preempt_enable();
rcu_lock_acquire(&(sp)->dep_map);
return retval;
}
{
char *cp = (char *)p;
struct kvec *vec = &rqstp->rq_arg.head[0];
- return cp == (char *)vec->iov_base + vec->iov_len;
+ return cp >= (char*)vec->iov_base
+ && cp <= (char*)vec->iov_base + vec->iov_len;
}
static inline int
struct platform_freeze_ops {
int (*begin)(void);
int (*prepare)(void);
- void (*wake)(void);
- void (*sync)(void);
void (*restore)(void);
void (*end)(void);
};
extern bool pm_wakeup_pending(void);
extern void pm_system_wakeup(void);
-extern void pm_system_cancel_wakeup(void);
-extern void pm_wakeup_clear(bool reset);
+extern void pm_wakeup_clear(void);
extern void pm_system_irq_wakeup(unsigned int irq_number);
extern bool pm_get_wakeup_count(unsigned int *count, bool block);
extern bool pm_save_wakeup_count(unsigned int count);
static inline bool pm_wakeup_pending(void) { return false; }
static inline void pm_system_wakeup(void) {}
-static inline void pm_wakeup_clear(bool reset) {}
+static inline void pm_wakeup_clear(void) {}
static inline void pm_system_irq_wakeup(unsigned int irq_number) {}
static inline void lock_system_sleep(void) {}
struct tty_driver *driver, unsigned index,
struct device *device, void *drvdata,
const struct attribute_group **attr_grp);
+extern struct device *tty_port_register_device_serdev(struct tty_port *port,
+ struct tty_driver *driver, unsigned index,
+ struct device *device);
+extern struct device *tty_port_register_device_attr_serdev(struct tty_port *port,
+ struct tty_driver *driver, unsigned index,
+ struct device *device, void *drvdata,
+ const struct attribute_group **attr_grp);
+extern void tty_port_unregister_device(struct tty_port *port,
+ struct tty_driver *driver, unsigned index);
extern int tty_port_alloc_xmit_buf(struct tty_port *port);
extern void tty_port_free_xmit_buf(struct tty_port *port);
extern void tty_port_destroy(struct tty_port *port);
unsigned rh_registered:1;/* is root hub registered? */
unsigned rh_pollable:1; /* may we poll the root hub? */
unsigned msix_enabled:1; /* driver has MSI-X enabled? */
+ unsigned msi_enabled:1; /* driver has MSI enabled? */
unsigned remove_phy:1; /* auto-remove USB phy */
/* The next flag is a stopgap, to be removed when all the HCDs
};
extern int usbnet_generic_cdc_bind(struct usbnet *, struct usb_interface *);
+extern int usbnet_ether_cdc_bind(struct usbnet *dev, struct usb_interface *intf);
extern int usbnet_cdc_bind(struct usbnet *, struct usb_interface *);
extern void usbnet_cdc_unbind(struct usbnet *, struct usb_interface *);
extern void usbnet_cdc_status(struct usbnet *, struct urb *);
struct cec_adapter;
struct cec_notifier;
-#ifdef CONFIG_MEDIA_CEC_NOTIFIER
+#if IS_REACHABLE(CONFIG_CEC_CORE) && IS_ENABLED(CONFIG_CEC_NOTIFIER)
/**
* cec_notifier_get - find or create a new cec_notifier for the given device.
bool passthrough;
struct cec_log_addrs log_addrs;
-#ifdef CONFIG_MEDIA_CEC_NOTIFIER
+#ifdef CONFIG_CEC_NOTIFIER
struct cec_notifier *notifier;
#endif
*/
int cec_phys_addr_validate(u16 phys_addr, u16 *parent, u16 *port);
-#ifdef CONFIG_MEDIA_CEC_NOTIFIER
+#ifdef CONFIG_CEC_NOTIFIER
void cec_register_cec_notifier(struct cec_adapter *adap,
struct cec_notifier *notifier);
#endif
};
};
+struct dst_metrics {
+ u32 metrics[RTAX_MAX];
+ atomic_t refcnt;
+};
+extern const struct dst_metrics dst_default_metrics;
+
u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old);
-extern const u32 dst_default_metrics[];
#define DST_METRICS_READ_ONLY 0x1UL
+#define DST_METRICS_REFCOUNTED 0x2UL
#define DST_METRICS_FLAGS 0x3UL
#define __DST_METRICS_PTR(Y) \
((u32 *)((Y) & ~DST_METRICS_FLAGS))
__be32 fib_prefsrc;
u32 fib_tb_id;
u32 fib_priority;
- u32 *fib_metrics;
-#define fib_mtu fib_metrics[RTAX_MTU-1]
-#define fib_window fib_metrics[RTAX_WINDOW-1]
-#define fib_rtt fib_metrics[RTAX_RTT-1]
-#define fib_advmss fib_metrics[RTAX_ADVMSS-1]
+ struct dst_metrics *fib_metrics;
+#define fib_mtu fib_metrics->metrics[RTAX_MTU-1]
+#define fib_window fib_metrics->metrics[RTAX_WINDOW-1]
+#define fib_rtt fib_metrics->metrics[RTAX_RTT-1]
+#define fib_advmss fib_metrics->metrics[RTAX_ADVMSS-1]
int fib_nhs;
#ifdef CONFIG_IP_ROUTE_MULTIPATH
int fib_weight;
*/
extern const struct proto_ops inet6_stream_ops;
extern const struct proto_ops inet6_dgram_ops;
+extern const struct proto_ops inet6_sockraw_ops;
struct group_source_req;
struct group_filter;
#ifndef _NF_CONNTRACK_HELPER_H
#define _NF_CONNTRACK_HELPER_H
+#include <linux/refcount.h>
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_extend.h>
#include <net/netfilter/nf_conntrack_expect.h>
struct hlist_node hnode; /* Internal use. */
char name[NF_CT_HELPER_NAME_LEN]; /* name of the module */
+ refcount_t refcnt;
struct module *me; /* pointer to self */
const struct nf_conntrack_expect_policy *expect_policy;
struct nf_conntrack_helper *nf_conntrack_helper_try_module_get(const char *name,
u16 l3num,
u8 protonum);
+void nf_conntrack_helper_put(struct nf_conntrack_helper *helper);
+
void nf_ct_helper_init(struct nf_conntrack_helper *helper,
u16 l3num, u16 protonum, const char *name,
u16 default_port, u16 spec_port, u32 id,
int nft_data_init(const struct nft_ctx *ctx,
struct nft_data *data, unsigned int size,
struct nft_data_desc *desc, const struct nlattr *nla);
-void nft_data_uninit(const struct nft_data *data, enum nft_data_types type);
+void nft_data_release(const struct nft_data *data, enum nft_data_types type);
int nft_data_dump(struct sk_buff *skb, int attr, const struct nft_data *data,
enum nft_data_types type, unsigned int len);
#include <linux/types.h>
#include <net/act_api.h>
+#include <linux/tc_act/tc_csum.h>
struct tcf_csum {
struct tc_action common;
};
#define to_tcf_csum(a) ((struct tcf_csum *)a)
+static inline bool is_tcf_csum(const struct tc_action *a)
+{
+#ifdef CONFIG_NET_CLS_ACT
+ if (a->ops && a->ops->type == TCA_ACT_CSUM)
+ return true;
+#endif
+ return false;
+}
+
+static inline u32 tcf_csum_update_flags(const struct tc_action *a)
+{
+ return to_tcf_csum(a)->update_flags;
+}
+
#endif /* __NET_TC_CSUM_H */
void (*cwnd_event)(struct sock *sk, enum tcp_ca_event ev);
/* call when ack arrives (optional) */
void (*in_ack_event)(struct sock *sk, u32 flags);
- /* new value of cwnd after loss (optional) */
+ /* new value of cwnd after loss (required) */
u32 (*undo_cwnd)(struct sock *sk);
/* hook for packet ack accounting (optional) */
void (*pkts_acked)(struct sock *sk, const struct ack_sample *sample);
/* sysctl_net_x25.c */
#ifdef CONFIG_SYSCTL
-void x25_register_sysctl(void);
+int x25_register_sysctl(void);
void x25_unregister_sysctl(void);
#else
-static inline void x25_register_sysctl(void) {};
+static inline int x25_register_sysctl(void) { return 0; };
static inline void x25_unregister_sysctl(void) {};
#endif /* CONFIG_SYSCTL */
struct flow_cache_object flo;
struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX];
int num_pols, num_xfrms;
-#ifdef CONFIG_XFRM_SUB_POLICY
- struct flowi *origin;
- struct xfrm_selector *partner;
-#endif
u32 xfrm_genid;
u32 policy_genid;
u32 route_mtu_cached;
dst_release(xdst->route);
if (likely(xdst->u.dst.xfrm))
xfrm_state_put(xdst->u.dst.xfrm);
-#ifdef CONFIG_XFRM_SUB_POLICY
- kfree(xdst->origin);
- xdst->origin = NULL;
- kfree(xdst->partner);
- xdst->partner = NULL;
-#endif
}
#endif
};
struct sa_path_rec_ib {
- __be64 service_id;
__be16 dlid;
__be16 slid;
u8 raw_traffic;
};
struct sa_path_rec_opa {
- __be64 service_id;
__be32 dlid;
__be32 slid;
u8 raw_traffic;
struct sa_path_rec {
union ib_gid dgid;
union ib_gid sgid;
+ __be64 service_id;
/* reserved */
__be32 flow_label;
u8 hop_limit;
ib->ib.dlid = htons(ntohl(opa->opa.dlid));
ib->ib.slid = htons(ntohl(opa->opa.slid));
}
- ib->ib.service_id = opa->opa.service_id;
+ ib->service_id = opa->service_id;
ib->ib.raw_traffic = opa->opa.raw_traffic;
}
}
opa->opa.slid = slid;
opa->opa.dlid = dlid;
- opa->opa.service_id = ib->ib.service_id;
+ opa->service_id = ib->service_id;
opa->opa.raw_traffic = ib->ib.raw_traffic;
}
(rec->rec_type == SA_PATH_REC_TYPE_ROCE_V2));
}
-static inline void sa_path_set_service_id(struct sa_path_rec *rec,
- __be64 service_id)
-{
- if (rec->rec_type == SA_PATH_REC_TYPE_IB)
- rec->ib.service_id = service_id;
- else if (rec->rec_type == SA_PATH_REC_TYPE_OPA)
- rec->opa.service_id = service_id;
-}
-
static inline void sa_path_set_slid(struct sa_path_rec *rec, __be32 slid)
{
if (rec->rec_type == SA_PATH_REC_TYPE_IB)
rec->opa.raw_traffic = raw_traffic;
}
-static inline __be64 sa_path_get_service_id(struct sa_path_rec *rec)
-{
- if (rec->rec_type == SA_PATH_REC_TYPE_IB)
- return rec->ib.service_id;
- else if (rec->rec_type == SA_PATH_REC_TYPE_OPA)
- return rec->opa.service_id;
- return 0;
-}
-
static inline __be32 sa_path_get_slid(struct sa_path_rec *rec)
{
if (rec->rec_type == SA_PATH_REC_TYPE_IB)
struct module *module;
};
-int ibnl_init(void);
-void ibnl_cleanup(void);
-
/**
* Add a a client to the list of IB netlink exporters.
* @index: Index of the added client
int ibnl_multicast(struct sk_buff *skb, struct nlmsghdr *nlh,
unsigned int group, gfp_t flags);
-/**
- * Check if there are any listeners to the netlink group
- * @group: the netlink group ID
- * Returns 0 on success or a negative for no listeners.
- */
-int ibnl_chk_listeners(unsigned int group);
-
#endif /* _RDMA_NETLINK_H */
#define LOGIN_FLAGS_READ_ACTIVE 1
#define LOGIN_FLAGS_CLOSED 2
#define LOGIN_FLAGS_READY 4
+#define LOGIN_FLAGS_INITIAL_PDU 8
unsigned long login_flags;
struct delayed_work login_work;
struct delayed_work login_cleanup_work;
};
struct keyctl_kdf_params {
- char *hashname;
- char *otherinfo;
+ char __user *hashname;
+ char __user *otherinfo;
__u32 otherinfolen;
__u32 __spare[8];
};
*/
#define USB_MAXCHILDREN 31
+/* See USB 3.1 spec Table 10-5 */
+#define USB_SS_MAXPORTS 15
+
/*
* Hub request types
*/
array->map.key_size = attr->key_size;
array->map.value_size = attr->value_size;
array->map.max_entries = attr->max_entries;
+ array->map.map_flags = attr->map_flags;
array->elem_size = elem_size;
if (!percpu)
trie->map.key_size = attr->key_size;
trie->map.value_size = attr->value_size;
trie->map.max_entries = attr->max_entries;
+ trie->map.map_flags = attr->map_flags;
trie->data_size = attr->key_size -
offsetof(struct bpf_lpm_trie_key, data);
trie->max_prefixlen = trie->data_size * 8;
smap->map.key_size = attr->key_size;
smap->map.value_size = value_size;
smap->map.max_entries = attr->max_entries;
+ smap->map.map_flags = attr->map_flags;
smap->n_buckets = n_buckets;
smap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
struct bpf_verifier_stack_elem *next;
};
-#define BPF_COMPLEXITY_LIMIT_INSNS 65536
+#define BPF_COMPLEXITY_LIMIT_INSNS 98304
#define BPF_COMPLEXITY_LIMIT_STACK 1024
#define BPF_MAP_PTR_POISON ((void *)0xeB9F + POISON_POINTER_DELTA)
BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5
};
+static void mark_reg_not_init(struct bpf_reg_state *regs, u32 regno)
+{
+ BUG_ON(regno >= MAX_BPF_REG);
+
+ memset(®s[regno], 0, sizeof(regs[regno]));
+ regs[regno].type = NOT_INIT;
+ regs[regno].min_value = BPF_REGISTER_MIN_RANGE;
+ regs[regno].max_value = BPF_REGISTER_MAX_RANGE;
+}
+
static void init_reg_state(struct bpf_reg_state *regs)
{
int i;
- for (i = 0; i < MAX_BPF_REG; i++) {
- regs[i].type = NOT_INIT;
- regs[i].imm = 0;
- regs[i].min_value = BPF_REGISTER_MIN_RANGE;
- regs[i].max_value = BPF_REGISTER_MAX_RANGE;
- regs[i].min_align = 0;
- regs[i].aux_off = 0;
- regs[i].aux_off_align = 0;
- }
+ for (i = 0; i < MAX_BPF_REG; i++)
+ mark_reg_not_init(regs, i);
/* frame pointer */
regs[BPF_REG_FP].type = FRAME_PTR;
reg_off += reg->aux_off;
}
- /* skb->data is NET_IP_ALIGN-ed, but for strict alignment checking
- * we force this to 2 which is universally what architectures use
- * when they don't set CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS.
+ /* For platforms that do not have a Kconfig enabling
+ * CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS the value of
+ * NET_IP_ALIGN is universally set to '2'. And on platforms
+ * that do set CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS, we get
+ * to this code only in strict mode where we want to emulate
+ * the NET_IP_ALIGN==2 checking. Therefore use an
+ * unconditional IP align value of '2'.
*/
- ip_align = strict ? 2 : NET_IP_ALIGN;
+ ip_align = 2;
if ((ip_align + reg_off + off) % size != 0) {
verbose("misaligned packet access off %d+%d+%d size %d\n",
ip_align, reg_off, off, size);
{
bool strict = env->strict_alignment;
- if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
- strict = true;
-
switch (reg->type) {
case PTR_TO_PACKET:
return check_pkt_ptr_alignment(reg, off, size, strict);
struct bpf_verifier_state *state = &env->cur_state;
const struct bpf_func_proto *fn = NULL;
struct bpf_reg_state *regs = state->regs;
- struct bpf_reg_state *reg;
struct bpf_call_arg_meta meta;
bool changes_data;
int i, err;
}
/* reset caller saved regs */
- for (i = 0; i < CALLER_SAVED_REGS; i++) {
- reg = regs + caller_saved[i];
- reg->type = NOT_INIT;
- reg->imm = 0;
- }
+ for (i = 0; i < CALLER_SAVED_REGS; i++)
+ mark_reg_not_init(regs, caller_saved[i]);
/* update return register */
if (fn->ret_type == RET_INTEGER) {
{
struct bpf_reg_state *regs = env->cur_state.regs;
u8 mode = BPF_MODE(insn->code);
- struct bpf_reg_state *reg;
int i, err;
if (!may_access_skb(env->prog->type)) {
}
/* reset caller saved regs to unreadable */
- for (i = 0; i < CALLER_SAVED_REGS; i++) {
- reg = regs + caller_saved[i];
- reg->type = NOT_INIT;
- reg->imm = 0;
- }
+ for (i = 0; i < CALLER_SAVED_REGS; i++)
+ mark_reg_not_init(regs, caller_saved[i]);
/* mark destination R0 register as readable, since it contains
* the value fetched from the packet
env->explored_states[t + 1] = STATE_LIST_MARK;
} else {
/* conditional jump with two edges */
+ env->explored_states[t] = STATE_LIST_MARK;
ret = push_insn(t, t + 1, FALLTHROUGH, env);
if (ret == 1)
goto peek_stack;
/* the following conditions reduce the number of explored insns
* from ~140k to ~80k for ultra large programs that use a lot of ptr_to_packet
*/
-static bool compare_ptrs_to_packet(struct bpf_reg_state *old,
+static bool compare_ptrs_to_packet(struct bpf_verifier_env *env,
+ struct bpf_reg_state *old,
struct bpf_reg_state *cur)
{
if (old->id != cur->id)
* 'if (R4 > data_end)' and all further insn were already good with r=20,
* so they will be good with r=30 and we can prune the search.
*/
- if (old->off <= cur->off &&
+ if (!env->strict_alignment && old->off <= cur->off &&
old->off >= old->range && cur->off >= cur->range)
return true;
rcur->type != NOT_INIT))
continue;
+ /* Don't care about the reg->id in this case. */
+ if (rold->type == PTR_TO_MAP_VALUE_OR_NULL &&
+ rcur->type == PTR_TO_MAP_VALUE_OR_NULL &&
+ rold->map_ptr == rcur->map_ptr)
+ continue;
+
if (rold->type == PTR_TO_PACKET && rcur->type == PTR_TO_PACKET &&
- compare_ptrs_to_packet(rold, rcur))
+ compare_ptrs_to_packet(env, rold, rcur))
continue;
return false;
goto process_bpf_exit;
}
+ if (need_resched())
+ cond_resched();
+
if (log_level > 1 || (log_level && do_print_state)) {
if (log_level > 1)
verbose("%d:", insn_idx);
} else {
log_level = 0;
}
- if (attr->prog_flags & BPF_F_STRICT_ALIGNMENT)
+
+ env->strict_alignment = !!(attr->prog_flags & BPF_F_STRICT_ALIGNMENT);
+ if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
env->strict_alignment = true;
- else
- env->strict_alignment = false;
ret = replace_map_fd_with_map_ptr(env);
if (ret < 0)
mutex_lock(&bpf_verifier_lock);
log_level = 0;
+
env->strict_alignment = false;
+ if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
+ env->strict_alignment = true;
env->explored_states = kcalloc(env->prog->len,
sizeof(struct bpf_verifier_state_list *),
{
lockdep_assert_held(&cgroup_mutex);
+ if (css->flags & CSS_DYING)
+ return;
+
+ css->flags |= CSS_DYING;
+
/*
* This must happen before css is disassociated with its cgroup.
* See seq_css() for details.
} cpuset_flagbits_t;
/* convenient tests for these bits */
-static inline bool is_cpuset_online(const struct cpuset *cs)
+static inline bool is_cpuset_online(struct cpuset *cs)
{
- return test_bit(CS_ONLINE, &cs->flags);
+ return test_bit(CS_ONLINE, &cs->flags) && !css_is_dying(&cs->css);
}
static inline int is_cpu_exclusive(const struct cpuset *cs)
ret = !sp->name || sp->cant_stop ? -EINVAL : 0;
mutex_unlock(&cpuhp_state_mutex);
if (ret)
- return ret;
+ goto out;
if (st->state < target)
ret = do_cpu_up(dev->id, target);
else
ret = do_cpu_down(dev->id, target);
-
+out:
unlock_device_hotplug();
return ret ? ret : count;
}
return __perf_event_account_interrupt(event, 1);
}
+static bool sample_is_allowed(struct perf_event *event, struct pt_regs *regs)
+{
+ /*
+ * Due to interrupt latency (AKA "skid"), we may enter the
+ * kernel before taking an overflow, even if the PMU is only
+ * counting user events.
+ * To avoid leaking information to userspace, we must always
+ * reject kernel samples when exclude_kernel is set.
+ */
+ if (event->attr.exclude_kernel && !user_mode(regs))
+ return false;
+
+ return true;
+}
+
/*
* Generic event overflow handling, sampling.
*/
ret = __perf_event_account_interrupt(event, throttle);
+ /*
+ * For security, drop the skid kernel samples if necessary.
+ */
+ if (!sample_is_allowed(event, regs))
+ return ret;
+
/*
* XXX event_limit might not quite work as expected on inherited
* events
if (!p)
goto fork_out;
+ /*
+ * This _must_ happen before we call free_task(), i.e. before we jump
+ * to any of the bad_fork_* labels. This is to avoid freeing
+ * p->set_child_tid which is (ab)used as a kthread's data pointer for
+ * kernel threads (PF_KTHREAD).
+ */
+ p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
+ /*
+ * Clear TID on mm_release()?
+ */
+ p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr : NULL;
+
ftrace_graph_init_task(p);
rt_mutex_init_task(p);
}
}
- p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
- /*
- * Clear TID on mm_release()?
- */
- p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr : NULL;
#ifdef CONFIG_BLOCK
p->plug = NULL;
#endif
*/
recalc_sigpending();
if (signal_pending(current)) {
- spin_unlock(¤t->sighand->siglock);
- write_unlock_irq(&tasklist_lock);
retval = -ERESTARTNOINTR;
goto bad_fork_cancel_cgroup;
}
+ if (unlikely(!(ns_of_pid(pid)->nr_hashed & PIDNS_HASH_ADDING))) {
+ retval = -ENOMEM;
+ goto bad_fork_cancel_cgroup;
+ }
if (likely(p->pid)) {
ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace);
return p;
bad_fork_cancel_cgroup:
+ spin_unlock(¤t->sighand->siglock);
+ write_unlock_irq(&tasklist_lock);
cgroup_cancel_fork(p);
bad_fork_free_pid:
cgroup_threadgroup_change_end(current);
if (!desc)
return;
- __irq_do_set_handler(desc, handle, 1, NULL);
desc->irq_common_data.handler_data = data;
+ __irq_do_set_handler(desc, handle, 1, NULL);
irq_put_desc_busunlock(desc, flags);
}
return module_alloc(PAGE_SIZE);
}
-static void free_insn_page(void *page)
+void __weak free_insn_page(void *page)
{
module_memfree(page);
}
}
/* Wait for completing optimization and unoptimization */
-static void wait_for_kprobe_optimizer(void)
+void wait_for_kprobe_optimizer(void)
{
mutex_lock(&kprobe_mutex);
* The vaddr this probe is installed will soon
* be vfreed buy not synced to disk. Hence,
* disarming the breakpoint isn't needed.
+ *
+ * Note, this will also move any optimized probes
+ * that are pending to be removed from their
+ * corresponding lists to the freeing_list and
+ * will not be touched by the delayed
+ * kprobe_optimizer work handler.
*/
kill_kprobe(p);
}
depends on SYSFS
depends on KALLSYMS_ALL
depends on HAVE_LIVEPATCH
+ depends on !TRIM_UNUSED_KSYMS
help
Say Y here if you want to support kernel live patching.
This option has no runtime impact until a kernel "patch"
int ret;
raw_spin_lock_irq(&lock->wait_lock);
-
- set_current_state(TASK_INTERRUPTIBLE);
-
/* sleep on the mutex */
+ set_current_state(TASK_INTERRUPTIBLE);
ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter);
-
+ /*
+ * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
+ * have to fix that up.
+ */
+ fixup_rt_mutex_waiters(lock);
raw_spin_unlock_irq(&lock->wait_lock);
return ret;
bool cleanup = false;
raw_spin_lock_irq(&lock->wait_lock);
+ /*
+ * Do an unconditional try-lock, this deals with the lock stealing
+ * state where __rt_mutex_futex_unlock() -> mark_wakeup_next_waiter()
+ * sets a NULL owner.
+ *
+ * We're not interested in the return value, because the subsequent
+ * test on rt_mutex_owner() will infer that. If the trylock succeeded,
+ * we will own the lock and it will have removed the waiter. If we
+ * failed the trylock, we're still not owner and we need to remove
+ * ourselves.
+ */
+ try_to_take_rt_mutex(lock, current, waiter);
/*
* Unless we're the owner; we're still enqueued on the wait_list.
* So check if we became owner, if not, take us off the wait_list.
*/
if (rt_mutex_owner(lock) != current) {
remove_waiter(lock, waiter);
- fixup_rt_mutex_waiters(lock);
cleanup = true;
}
-
/*
* try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
* have to fix that up.
* if reparented.
*/
for (;;) {
- set_current_state(TASK_UNINTERRUPTIBLE);
+ set_current_state(TASK_INTERRUPTIBLE);
if (pid_ns->nr_hashed == init_pids)
break;
schedule();
if (!pm_freezing)
atomic_inc(&system_freezing_cnt);
- pm_wakeup_clear(true);
+ pm_wakeup_clear();
pr_info("Freezing user space processes ... ");
pm_freezing = true;
error = try_to_freeze_tasks(true);
* Numbers of normal and highmem page frames allocated for hibernation image
* before suspending devices.
*/
-unsigned int alloc_normal, alloc_highmem;
+static unsigned int alloc_normal, alloc_highmem;
/*
* Memory bitmap used for marking saveable pages (during hibernation) or
* hibernation image pages (during restore)
static void freeze_enter(void)
{
- trace_suspend_resume(TPS("machine_suspend"), PM_SUSPEND_FREEZE, true);
-
spin_lock_irq(&suspend_freeze_lock);
if (pm_wakeup_pending())
goto out;
out:
suspend_freeze_state = FREEZE_STATE_NONE;
spin_unlock_irq(&suspend_freeze_lock);
-
- trace_suspend_resume(TPS("machine_suspend"), PM_SUSPEND_FREEZE, false);
-}
-
-static void s2idle_loop(void)
-{
- do {
- freeze_enter();
-
- if (freeze_ops && freeze_ops->wake)
- freeze_ops->wake();
-
- dpm_resume_noirq(PMSG_RESUME);
- if (freeze_ops && freeze_ops->sync)
- freeze_ops->sync();
-
- if (pm_wakeup_pending())
- break;
-
- pm_wakeup_clear(false);
- } while (!dpm_suspend_noirq(PMSG_SUSPEND));
}
void freeze_wake(void)
* all the devices are suspended.
*/
if (state == PM_SUSPEND_FREEZE) {
- s2idle_loop();
- goto Platform_early_resume;
+ trace_suspend_resume(TPS("machine_suspend"), state, true);
+ freeze_enter();
+ trace_suspend_resume(TPS("machine_suspend"), state, false);
+ goto Platform_wake;
}
error = disable_nonboot_cpus();
#define MAX_CMDLINECONSOLES 8
static struct console_cmdline console_cmdline[MAX_CMDLINECONSOLES];
-static int console_cmdline_cnt;
static int preferred_console = -1;
int console_set_on_cmdline;
* See if this tty is not yet registered, and
* if we have a slot free.
*/
- for (i = 0, c = console_cmdline; i < console_cmdline_cnt; i++, c++) {
+ for (i = 0, c = console_cmdline;
+ i < MAX_CMDLINECONSOLES && c->name[0];
+ i++, c++) {
if (strcmp(c->name, name) == 0 && c->index == idx) {
- if (brl_options)
- return 0;
-
- /*
- * Maintain an invariant that will help to find if
- * the matching console is preferred, see
- * register_console():
- *
- * The last non-braille console is always
- * the preferred one.
- */
- if (i != console_cmdline_cnt - 1)
- swap(console_cmdline[i],
- console_cmdline[console_cmdline_cnt - 1]);
-
- preferred_console = console_cmdline_cnt - 1;
-
+ if (!brl_options)
+ preferred_console = i;
return 0;
}
}
braille_set_options(c, brl_options);
c->index = idx;
- console_cmdline_cnt++;
return 0;
}
/*
}
/*
- * See if this console matches one we selected on the command line.
- *
- * There may be several entries in the console_cmdline array matching
- * with the same console, one with newcon->match(), another by
- * name/index:
- *
- * pl011,mmio,0x87e024000000,115200 -- added from SPCR
- * ttyAMA0 -- added from command line
- *
- * Traverse the console_cmdline array in reverse order to be
- * sure that if this console is preferred then it will be the first
- * matching entry. We use the invariant that is maintained in
- * __add_preferred_console().
+ * See if this console matches one we selected on
+ * the command line.
*/
- for (i = console_cmdline_cnt - 1; i >= 0; i--) {
- c = console_cmdline + i;
-
+ for (i = 0, c = console_cmdline;
+ i < MAX_CMDLINECONSOLES && c->name[0];
+ i++, c++) {
if (!newcon->match ||
newcon->match(newcon, c->name, c->index, c->options) != 0) {
/* default matching */
}
+void __ptrace_link(struct task_struct *child, struct task_struct *new_parent,
+ const struct cred *ptracer_cred)
+{
+ BUG_ON(!list_empty(&child->ptrace_entry));
+ list_add(&child->ptrace_entry, &new_parent->ptraced);
+ child->parent = new_parent;
+ child->ptracer_cred = get_cred(ptracer_cred);
+}
+
/*
* ptrace a task: make the debugger its new parent and
* move it to the ptrace list.
*
* Must be called with the tasklist lock write-held.
*/
-void __ptrace_link(struct task_struct *child, struct task_struct *new_parent)
+static void ptrace_link(struct task_struct *child, struct task_struct *new_parent)
{
- BUG_ON(!list_empty(&child->ptrace_entry));
- list_add(&child->ptrace_entry, &new_parent->ptraced);
- child->parent = new_parent;
rcu_read_lock();
- child->ptracer_cred = get_cred(__task_cred(new_parent));
+ __ptrace_link(child, new_parent, __task_cred(new_parent));
rcu_read_unlock();
}
flags |= PT_SEIZED;
task->ptrace = flags;
- __ptrace_link(task, current);
+ ptrace_link(task, current);
/* SEIZE doesn't trap tracee on attach */
if (!seize)
*/
if (!ret && !(current->real_parent->flags & PF_EXITING)) {
current->ptrace = PT_PTRACED;
- __ptrace_link(current, current->real_parent);
+ ptrace_link(current, current->real_parent);
}
}
write_unlock_irq(&tasklist_lock);
/*
* Counts the new reader in the appropriate per-CPU element of the
- * srcu_struct. Must be called from process context.
+ * srcu_struct.
* Returns an index that must be passed to the matching srcu_read_unlock().
*/
int __srcu_read_lock(struct srcu_struct *sp)
int idx;
idx = READ_ONCE(sp->completed) & 0x1;
- __this_cpu_inc(sp->per_cpu_ref->lock_count[idx]);
+ this_cpu_inc(sp->per_cpu_ref->lock_count[idx]);
smp_mb(); /* B */ /* Avoid leaking the critical section. */
return idx;
}
* Removes the count for the old reader from the appropriate per-CPU
* element of the srcu_struct. Note that this may well be a different
* CPU than that which was incremented by the corresponding srcu_read_lock().
- * Must be called from process context.
*/
void __srcu_read_unlock(struct srcu_struct *sp, int idx)
{
/*
* Counts the new reader in the appropriate per-CPU element of the
- * srcu_struct. Must be called from process context.
- * Returns an index that must be passed to the matching srcu_read_unlock().
+ * srcu_struct. Can be invoked from irq/bh handlers, but the matching
+ * __srcu_read_unlock() must be in the same handler instance. Returns an
+ * index that must be passed to the matching srcu_read_unlock().
*/
int __srcu_read_lock(struct srcu_struct *sp)
{
/*
* Removes the count for the old reader from the appropriate element of
- * the srcu_struct. Must be called from process context.
+ * the srcu_struct.
*/
void __srcu_read_unlock(struct srcu_struct *sp, int idx)
{
/*
* Counts the new reader in the appropriate per-CPU element of the
- * srcu_struct. Must be called from process context.
+ * srcu_struct.
* Returns an index that must be passed to the matching srcu_read_unlock().
*/
int __srcu_read_lock(struct srcu_struct *sp)
int idx;
idx = READ_ONCE(sp->srcu_idx) & 0x1;
- __this_cpu_inc(sp->sda->srcu_lock_count[idx]);
+ this_cpu_inc(sp->sda->srcu_lock_count[idx]);
smp_mb(); /* B */ /* Avoid leaking the critical section. */
return idx;
}
* Removes the count for the old reader from the appropriate per-CPU
* element of the srcu_struct. Note that this may well be a different
* CPU than that which was incremented by the corresponding srcu_read_lock().
- * Must be called from process context.
*/
void __srcu_read_unlock(struct srcu_struct *sp, int idx)
{
}
EXPORT_SYMBOL(schedule);
+/*
+ * synchronize_rcu_tasks() makes sure that no task is stuck in preempted
+ * state (have scheduled out non-voluntarily) by making sure that all
+ * tasks have either left the run queue or have gone into user space.
+ * As idle tasks do not do either, they must not ever be preempted
+ * (schedule out non-voluntarily).
+ *
+ * schedule_idle() is similar to schedule_preempt_disable() except that it
+ * never enables preemption because it does not call sched_submit_work().
+ */
+void __sched schedule_idle(void)
+{
+ /*
+ * As this skips calling sched_submit_work(), which the idle task does
+ * regardless because that function is a nop when the task is in a
+ * TASK_RUNNING state, make sure this isn't used someplace that the
+ * current task can be in any other state. Note, idle is always in the
+ * TASK_RUNNING state.
+ */
+ WARN_ON_ONCE(current->state);
+ do {
+ __schedule(false);
+ } while (need_resched());
+}
+
#ifdef CONFIG_CONTEXT_TRACKING
asmlinkage __visible void __sched schedule_user(void)
{
sugov_update_commit(sg_policy, time, next_f);
}
-static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu)
+static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
{
struct sugov_policy *sg_policy = sg_cpu->sg_policy;
struct cpufreq_policy *policy = sg_policy->policy;
- u64 last_freq_update_time = sg_policy->last_freq_update_time;
unsigned long util = 0, max = 1;
unsigned int j;
* enough, don't take the CPU into account as it probably is
* idle now (and clear iowait_boost for it).
*/
- delta_ns = last_freq_update_time - j_sg_cpu->last_update;
+ delta_ns = time - j_sg_cpu->last_update;
if (delta_ns > TICK_NSEC) {
j_sg_cpu->iowait_boost = 0;
continue;
if (flags & SCHED_CPUFREQ_RT_DL)
next_f = sg_policy->policy->cpuinfo.max_freq;
else
- next_f = sugov_next_freq_shared(sg_cpu);
+ next_f = sugov_next_freq_shared(sg_cpu, time);
sugov_update_commit(sg_policy, time, next_f);
}
smp_mb__after_atomic();
sched_ttwu_pending();
- schedule_preempt_disabled();
+ schedule_idle();
if (unlikely(klp_patch_pending(current)))
klp_update_patch_state(current);
}
#endif
+extern void schedule_idle(void);
+
extern void sysrq_sched_debug_show(void);
extern void sched_init_granularity(void);
extern void update_max_interval(void);
* At the hard limit, we just die.
* No need to calculate anything else now.
*/
- pr_info("CPU Watchdog Timeout (hard): %s[%d]\n",
- tsk->comm, task_pid_nr(tsk));
+ if (print_fatal_signals) {
+ pr_info("CPU Watchdog Timeout (hard): %s[%d]\n",
+ tsk->comm, task_pid_nr(tsk));
+ }
__group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk);
return;
}
soft += USEC_PER_SEC;
sig->rlim[RLIMIT_RTTIME].rlim_cur = soft;
}
- pr_info("RT Watchdog Timeout (soft): %s[%d]\n",
- tsk->comm, task_pid_nr(tsk));
+ if (print_fatal_signals) {
+ pr_info("RT Watchdog Timeout (soft): %s[%d]\n",
+ tsk->comm, task_pid_nr(tsk));
+ }
__group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk);
}
}
* At the hard limit, we just die.
* No need to calculate anything else now.
*/
- pr_info("RT Watchdog Timeout (hard): %s[%d]\n",
- tsk->comm, task_pid_nr(tsk));
+ if (print_fatal_signals) {
+ pr_info("RT Watchdog Timeout (hard): %s[%d]\n",
+ tsk->comm, task_pid_nr(tsk));
+ }
__group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk);
return;
}
/*
* At the soft limit, send a SIGXCPU every second.
*/
- pr_info("CPU Watchdog Timeout (soft): %s[%d]\n",
- tsk->comm, task_pid_nr(tsk));
+ if (print_fatal_signals) {
+ pr_info("CPU Watchdog Timeout (soft): %s[%d]\n",
+ tsk->comm, task_pid_nr(tsk));
+ }
__group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk);
if (soft < hard) {
soft++;
goto out;
if (attr == &dev_attr_act_mask) {
- if (sscanf(buf, "%llx", &value) != 1) {
+ if (kstrtoull(buf, 0, &value)) {
/* Assume it is a list of trace category names */
ret = blk_trace_str2mask(buf);
if (ret < 0)
goto out;
value = ret;
}
- } else if (sscanf(buf, "%llu", &value) != 1)
+ } else if (kstrtoull(buf, 0, &value))
goto out;
ret = -ENXIO;
int i, ret = -ENODEV;
int size;
- if (glob && (strcmp(glob, "*") == 0 || !strlen(glob)))
+ if (!glob || !strlen(glob) || !strcmp(glob, "*"))
func_g.search = NULL;
- else if (glob) {
+ else {
int not;
func_g.type = filter_parse_regex(glob, strlen(glob),
return ret;
}
+void clear_ftrace_function_probes(struct trace_array *tr)
+{
+ struct ftrace_func_probe *probe, *n;
+
+ list_for_each_entry_safe(probe, n, &tr->func_probes, list)
+ unregister_ftrace_function_probe_func(NULL, tr, probe->probe_ops);
+}
+
static LIST_HEAD(ftrace_commands);
static DEFINE_MUTEX(ftrace_cmd_mutex);
}
out:
- kfree(fgd->new_hash);
+ free_ftrace_hash(fgd->new_hash);
kfree(fgd);
return ret;
return 0;
}
-early_initcall(init_trace_selftests);
+core_initcall(init_trace_selftests);
#else
static inline int run_tracer_selftest(struct tracer *type)
{
void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
int pc)
{
- __ftrace_trace_stack(tr->trace_buffer.buffer, flags, skip, pc, NULL);
+ struct ring_buffer *buffer = tr->trace_buffer.buffer;
+
+ if (rcu_is_watching()) {
+ __ftrace_trace_stack(buffer, flags, skip, pc, NULL);
+ return;
+ }
+
+ /*
+ * When an NMI triggers, RCU is enabled via rcu_nmi_enter(),
+ * but if the above rcu_is_watching() failed, then the NMI
+ * triggered someplace critical, and rcu_irq_enter() should
+ * not be called from NMI.
+ */
+ if (unlikely(in_nmi()))
+ return;
+
+ /*
+ * It is possible that a function is being traced in a
+ * location that RCU is not watching. A call to
+ * rcu_irq_enter() will make sure that it is, but there's
+ * a few internal rcu functions that could be traced
+ * where that wont work either. In those cases, we just
+ * do nothing.
+ */
+ if (unlikely(rcu_irq_enter_disabled()))
+ return;
+
+ rcu_irq_enter_irqson();
+ __ftrace_trace_stack(buffer, flags, skip, pc, NULL);
+ rcu_irq_exit_irqson();
}
/**
}
tracing_set_nop(tr);
+ clear_ftrace_function_probes(tr);
event_trace_del_tracer(tr);
ftrace_clear_pids(tr);
ftrace_destroy_function_files(tr);
extern int
unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr,
struct ftrace_probe_ops *ops);
+extern void clear_ftrace_function_probes(struct trace_array *tr);
int register_ftrace_command(struct ftrace_func_command *cmd);
int unregister_ftrace_command(struct ftrace_func_command *cmd);
{
return -EINVAL;
}
+static inline void clear_ftrace_function_probes(struct trace_array *tr)
+{
+}
+
/*
* The ops parameter passed in is usually undefined.
* This must be a macro.
end:
release_all_trace_kprobes();
+ /*
+ * Wait for the optimizer work to finish. Otherwise it might fiddle
+ * with probes in already freed __init text.
+ */
+ wait_for_kprobe_optimizer();
if (warn)
pr_cont("NG: Some tests are failed. Please check them.\n");
else
{ },
{ { 0, 1 } },
},
+ {
+ "JMP_JSGE_K: Signed jump: value walk 1",
+ .u.insns_int = {
+ BPF_ALU32_IMM(BPF_MOV, R0, 0),
+ BPF_LD_IMM64(R1, -3),
+ BPF_JMP_IMM(BPF_JSGE, R1, 0, 6),
+ BPF_ALU64_IMM(BPF_ADD, R1, 1),
+ BPF_JMP_IMM(BPF_JSGE, R1, 0, 4),
+ BPF_ALU64_IMM(BPF_ADD, R1, 1),
+ BPF_JMP_IMM(BPF_JSGE, R1, 0, 2),
+ BPF_ALU64_IMM(BPF_ADD, R1, 1),
+ BPF_JMP_IMM(BPF_JSGE, R1, 0, 1),
+ BPF_EXIT_INSN(), /* bad exit */
+ BPF_ALU32_IMM(BPF_MOV, R0, 1), /* good exit */
+ BPF_EXIT_INSN(),
+ },
+ INTERNAL,
+ { },
+ { { 0, 1 } },
+ },
+ {
+ "JMP_JSGE_K: Signed jump: value walk 2",
+ .u.insns_int = {
+ BPF_ALU32_IMM(BPF_MOV, R0, 0),
+ BPF_LD_IMM64(R1, -3),
+ BPF_JMP_IMM(BPF_JSGE, R1, 0, 4),
+ BPF_ALU64_IMM(BPF_ADD, R1, 2),
+ BPF_JMP_IMM(BPF_JSGE, R1, 0, 2),
+ BPF_ALU64_IMM(BPF_ADD, R1, 2),
+ BPF_JMP_IMM(BPF_JSGE, R1, 0, 1),
+ BPF_EXIT_INSN(), /* bad exit */
+ BPF_ALU32_IMM(BPF_MOV, R0, 1), /* good exit */
+ BPF_EXIT_INSN(),
+ },
+ INTERNAL,
+ { },
+ { { 0, 1 } },
+ },
/* BPF_JMP | BPF_JGT | BPF_K */
{
"JMP_JGT_K: if (3 > 2) return 1",
ret = handle_mm_fault(vma, address, fault_flags);
if (ret & VM_FAULT_ERROR) {
- if (ret & VM_FAULT_OOM)
- return -ENOMEM;
- if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE))
- return *flags & FOLL_HWPOISON ? -EHWPOISON : -EFAULT;
- if (ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV))
- return -EFAULT;
+ int err = vm_fault_to_errno(ret, *flags);
+
+ if (err)
+ return err;
BUG();
}
ret = handle_mm_fault(vma, address, fault_flags);
major |= ret & VM_FAULT_MAJOR;
if (ret & VM_FAULT_ERROR) {
- if (ret & VM_FAULT_OOM)
- return -ENOMEM;
- if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE))
- return -EHWPOISON;
- if (ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV))
- return -EFAULT;
+ int err = vm_fault_to_errno(ret, 0);
+
+ if (err)
+ return err;
BUG();
}
}
ret = hugetlb_fault(mm, vma, vaddr, fault_flags);
if (ret & VM_FAULT_ERROR) {
+ int err = vm_fault_to_errno(ret, flags);
+
+ if (err)
+ return err;
+
remainder = 0;
break;
}
goto out;
if (PageTransCompound(page)) {
- err = split_huge_page(page);
- if (err)
+ if (split_huge_page(page))
goto out_unlock;
}
}
}
+extern unsigned long __init_memblock
+memblock_reserved_memory_within(phys_addr_t start_addr, phys_addr_t end_addr)
+{
+ struct memblock_region *rgn;
+ unsigned long size = 0;
+ int idx;
+
+ for_each_memblock_type((&memblock.reserved), rgn) {
+ phys_addr_t start, end;
+
+ if (rgn->base + rgn->size < start_addr)
+ continue;
+ if (rgn->base > end_addr)
+ continue;
+
+ start = rgn->base;
+ end = start + rgn->size;
+ size += end - start;
+ }
+
+ return size;
+}
+
void __init_memblock __memblock_dump_all(void)
{
pr_info("MEMBLOCK configuration:\n");
if (ret) {
pr_info("soft offline: %#lx: migration failed %d, type %lx (%pGp)\n",
pfn, ret, page->flags, &page->flags);
- /*
- * We know that soft_offline_huge_page() tries to migrate
- * only one hugepage pointed to by hpage, so we need not
- * run through the pagelist here.
- */
- putback_active_hugepage(hpage);
+ if (!list_empty(&pagelist))
+ putback_movable_pages(&pagelist);
if (ret > 0)
ret = -EIO;
} else {
return ret;
}
+/*
+ * The ordering of these checks is important for pmds with _PAGE_DEVMAP set.
+ * If we check pmd_trans_unstable() first we will trip the bad_pmd() check
+ * inside of pmd_none_or_trans_huge_or_clear_bad(). This will end up correctly
+ * returning 1 but not before it spams dmesg with the pmd_clear_bad() output.
+ */
+static int pmd_devmap_trans_unstable(pmd_t *pmd)
+{
+ return pmd_devmap(*pmd) || pmd_trans_unstable(pmd);
+}
+
static int pte_alloc_one_map(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
map_pte:
/*
* If a huge pmd materialized under us just retry later. Use
- * pmd_trans_unstable() instead of pmd_trans_huge() to ensure the pmd
- * didn't become pmd_trans_huge under us and then back to pmd_none, as
- * a result of MADV_DONTNEED running immediately after a huge pmd fault
- * in a different thread of this mm, in turn leading to a misleading
- * pmd_trans_huge() retval. All we have to ensure is that it is a
- * regular pmd that we can walk with pte_offset_map() and we can do that
- * through an atomic read in C, which is what pmd_trans_unstable()
- * provides.
+ * pmd_trans_unstable() via pmd_devmap_trans_unstable() instead of
+ * pmd_trans_huge() to ensure the pmd didn't become pmd_trans_huge
+ * under us and then back to pmd_none, as a result of MADV_DONTNEED
+ * running immediately after a huge pmd fault in a different thread of
+ * this mm, in turn leading to a misleading pmd_trans_huge() retval.
+ * All we have to ensure is that it is a regular pmd that we can walk
+ * with pte_offset_map() and we can do that through an atomic read in
+ * C, which is what pmd_trans_unstable() provides.
*/
- if (pmd_trans_unstable(vmf->pmd) || pmd_devmap(*vmf->pmd))
+ if (pmd_devmap_trans_unstable(vmf->pmd))
return VM_FAULT_NOPAGE;
+ /*
+ * At this point we know that our vmf->pmd points to a page of ptes
+ * and it cannot become pmd_none(), pmd_devmap() or pmd_trans_huge()
+ * for the duration of the fault. If a racing MADV_DONTNEED runs and
+ * we zap the ptes pointed to by our vmf->pmd, the vmf->ptl will still
+ * be valid and we will re-check to make sure the vmf->pte isn't
+ * pte_none() under vmf->ptl protection when we return to
+ * alloc_set_pte().
+ */
vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
&vmf->ptl);
return 0;
vmf->pte = NULL;
} else {
/* See comment in pte_alloc_one_map() */
- if (pmd_trans_unstable(vmf->pmd) || pmd_devmap(*vmf->pmd))
+ if (pmd_devmap_trans_unstable(vmf->pmd))
return 0;
/*
* A regular pmd is established and it can't morph into a huge
{
int i;
int nr = pagevec_count(pvec);
- int delta_munlocked;
+ int delta_munlocked = -nr;
struct pagevec pvec_putback;
int pgrescued = 0;
continue;
else
__munlock_isolation_failed(page);
+ } else {
+ delta_munlocked++;
}
/*
pagevec_add(&pvec_putback, pvec->pages[i]);
pvec->pages[i] = NULL;
}
- delta_munlocked = -nr + pagevec_count(&pvec_putback);
__mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
spin_unlock_irq(zone_lru_lock(zone));
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
static inline void reset_deferred_meminit(pg_data_t *pgdat)
{
+ unsigned long max_initialise;
+ unsigned long reserved_lowmem;
+
+ /*
+ * Initialise at least 2G of a node but also take into account that
+ * two large system hashes that can take up 1GB for 0.25TB/node.
+ */
+ max_initialise = max(2UL << (30 - PAGE_SHIFT),
+ (pgdat->node_spanned_pages >> 8));
+
+ /*
+ * Compensate the all the memblock reservations (e.g. crash kernel)
+ * from the initial estimation to make sure we will initialize enough
+ * memory to boot.
+ */
+ reserved_lowmem = memblock_reserved_memory_within(pgdat->node_start_pfn,
+ pgdat->node_start_pfn + max_initialise);
+ max_initialise += reserved_lowmem;
+
+ pgdat->static_init_size = min(max_initialise, pgdat->node_spanned_pages);
pgdat->first_deferred_pfn = ULONG_MAX;
}
unsigned long pfn, unsigned long zone_end,
unsigned long *nr_initialised)
{
- unsigned long max_initialise;
-
/* Always populate low zones for address-contrained allocations */
if (zone_end < pgdat_end_pfn(pgdat))
return true;
- /*
- * Initialise at least 2G of a node but also take into account that
- * two large system hashes that can take up 1GB for 0.25TB/node.
- */
- max_initialise = max(2UL << (30 - PAGE_SHIFT),
- (pgdat->node_spanned_pages >> 8));
-
(*nr_initialised)++;
- if ((*nr_initialised > max_initialise) &&
+ if ((*nr_initialised > pgdat->static_init_size) &&
(pfn & (PAGES_PER_SECTION - 1)) == 0) {
pgdat->first_deferred_pfn = pfn;
return false;
goto got_pg;
/* Avoid allocations with no watermarks from looping endlessly */
- if (test_thread_flag(TIF_MEMDIE))
+ if (test_thread_flag(TIF_MEMDIE) &&
+ (alloc_flags == ALLOC_NO_WATERMARKS ||
+ (gfp_mask & __GFP_NOMEMALLOC)))
goto nopage;
/* Retry as long as the OOM killer is making progress */
/* pg_data_t should be reset to zero when it's allocated */
WARN_ON(pgdat->nr_zones || pgdat->kswapd_classzone_idx);
- reset_deferred_meminit(pgdat);
pgdat->node_id = nid;
pgdat->node_start_pfn = node_start_pfn;
pgdat->per_cpu_nodestats = NULL;
(unsigned long)pgdat->node_mem_map);
#endif
+ reset_deferred_meminit(pgdat);
free_area_init_core(pgdat);
}
char mbuf[64];
char *buf;
struct slab_attribute *attr = to_slab_attr(slab_attrs[i]);
+ ssize_t len;
if (!attr || !attr->store || !attr->show)
continue;
buf = buffer;
}
- attr->show(root_cache, buf);
- attr->store(s, buf, strlen(buf));
+ len = attr->show(root_cache, buf);
+ if (len > 0)
+ attr->store(s, buf, len);
}
if (buffer)
WARN_ON_ONCE((flags & GFP_KERNEL) != GFP_KERNEL);
/*
- * Make sure that larger requests are not too disruptive - no OOM
- * killer and no allocation failure warnings as we have a fallback
+ * We want to attempt a large physically contiguous block first because
+ * it is less likely to fragment multiple larger blocks and therefore
+ * contribute to a long term fragmentation less than vmalloc fallback.
+ * However make sure that larger requests are not too disruptive - no
+ * OOM killer and no allocation failure warnings as we have a fallback.
*/
if (size > PAGE_SIZE) {
kmalloc_flags |= __GFP_NOWARN;
goto error_xenbus;
}
priv->tag = xenbus_read(xbt, dev->nodename, "tag", NULL);
- if (!priv->tag) {
- ret = -EINVAL;
+ if (IS_ERR(priv->tag)) {
+ ret = PTR_ERR(priv->tag);
goto error_xenbus;
}
ret = xenbus_transaction_end(xbt, 0);
.otherend_changed = xen_9pfs_front_changed,
};
-int p9_trans_xen_init(void)
+static int p9_trans_xen_init(void)
{
if (!xen_domain())
return -ENODEV;
}
module_init(p9_trans_xen_init);
-void p9_trans_xen_exit(void)
+static void p9_trans_xen_exit(void)
{
v9fs_unregister_trans(&p9_xen_trans);
return xenbus_unregister_driver(&xen_9pfs_front_driver);
err = 0;
switch (nla_type(attr)) {
case IFLA_BRIDGE_VLAN_TUNNEL_INFO:
- if (!(p->flags & BR_VLAN_TUNNEL))
+ if (!p || !(p->flags & BR_VLAN_TUNNEL))
return -EINVAL;
err = br_parse_vlan_tunnel_info(attr, &tinfo_curr);
if (err)
return -EPROTONOSUPPORT;
}
}
+
+ if (data[IFLA_BR_VLAN_DEFAULT_PVID]) {
+ __u16 defpvid = nla_get_u16(data[IFLA_BR_VLAN_DEFAULT_PVID]);
+
+ if (defpvid >= VLAN_VID_MASK)
+ return -EINVAL;
+ }
#endif
return 0;
br_debug(br, "using kernel STP\n");
/* To start timers on any ports left in blocking */
+ if (br->dev->flags & IFF_UP)
+ mod_timer(&br->hello_timer, jiffies + br->hello_time);
br_port_state_selection(br);
}
if (br->dev->flags & IFF_UP) {
br_config_bpdu_generation(br);
- if (br->stp_enabled != BR_USER_STP)
+ if (br->stp_enabled == BR_KERNEL_STP)
mod_timer(&br->hello_timer,
round_jiffies(jiffies + br->hello_time));
}
if (e->ethproto != htons(ETH_P_ARP) ||
e->invflags & EBT_IPROTO)
return -EINVAL;
+ if (ebt_invalid_target(info->target))
+ return -EINVAL;
+
return 0;
}
strlcpy(name, _name, sizeof(name));
if (copy_to_user(um, name, EBT_FUNCTION_MAXNAMELEN) ||
put_user(datasize, (int __user *)(um + EBT_FUNCTION_MAXNAMELEN)) ||
- xt_data_to_user(um + entrysize, data, usersize, datasize))
+ xt_data_to_user(um + entrysize, data, usersize, datasize,
+ XT_ALIGN(datasize)))
return -EFAULT;
return 0;
if (match->compat_to_user(cm->data, m->data))
return -EFAULT;
} else {
- if (xt_data_to_user(cm->data, m->data, match->usersize, msize))
+ if (xt_data_to_user(cm->data, m->data, match->usersize, msize,
+ COMPAT_XT_ALIGN(msize)))
return -EFAULT;
}
if (target->compat_to_user(cm->data, t->data))
return -EFAULT;
} else {
- if (xt_data_to_user(cm->data, t->data, target->usersize, tsize))
+ if (xt_data_to_user(cm->data, t->data, target->usersize, tsize,
+ COMPAT_XT_ALIGN(tsize)))
return -EFAULT;
}
struct timespec validity;
void *tp, *tpend;
void **ptp;
- struct ceph_crypto_key new_session_key;
+ struct ceph_crypto_key new_session_key = { 0 };
struct ceph_buffer *new_ticket_blob;
unsigned long new_expires, new_renew_after;
u64 new_secret_id;
dout(" ticket blob is %d bytes\n", dlen);
ceph_decode_need(ptp, tpend, 1 + sizeof(u64), bad);
blob_struct_v = ceph_decode_8(ptp);
+ if (blob_struct_v != 1)
+ goto bad;
+
new_secret_id = ceph_decode_64(ptp);
ret = ceph_decode_buffer(&new_ticket_blob, ptp, tpend);
if (ret)
type, ceph_entity_type_name(type), th->secret_id,
(int)th->ticket_blob->vec.iov_len);
xi->have_keys |= th->service;
-
-out:
- return ret;
+ return 0;
bad:
ret = -EINVAL;
- goto out;
+out:
+ ceph_crypto_key_destroy(&new_session_key);
+ return ret;
}
static int ceph_x_proc_ticket_reply(struct ceph_auth_client *ac,
module_param_cb(supported_features, ¶m_ops_supported_features, NULL,
S_IRUGO);
-/*
- * find filename portion of a path (/foo/bar/baz -> baz)
- */
-const char *ceph_file_part(const char *s, int len)
-{
- const char *e = s + len;
-
- while (e != s && *(e-1) != '/')
- e--;
- return e;
-}
-EXPORT_SYMBOL(ceph_file_part);
-
const char *ceph_msg_type_name(int type)
{
switch (type) {
* Returns true if the result moves the cursor on to the next piece
* of the data item.
*/
-static bool ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor,
- size_t bytes)
+static void ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor,
+ size_t bytes)
{
bool new_piece;
new_piece = true;
}
cursor->need_crc = new_piece;
-
- return new_piece;
}
static size_t sizeof_footer(struct ceph_connection *con)
size_t page_offset;
size_t length;
bool last_piece;
- bool need_crc;
int ret;
page = ceph_msg_data_next(cursor, &page_offset, &length,
}
if (do_datacrc && cursor->need_crc)
crc = ceph_crc32c_page(crc, page, page_offset, length);
- need_crc = ceph_msg_data_advance(cursor, (size_t)ret);
+ ceph_msg_data_advance(cursor, (size_t)ret);
}
dout("%s %p msg %p done\n", __func__, con, msg);
struct ceph_msg *m;
u64 ack = le64_to_cpu(con->in_temp_ack);
u64 seq;
+ bool reconnect = (con->in_tag == CEPH_MSGR_TAG_SEQ);
+ struct list_head *list = reconnect ? &con->out_queue : &con->out_sent;
- while (!list_empty(&con->out_sent)) {
- m = list_first_entry(&con->out_sent, struct ceph_msg,
- list_head);
+ /*
+ * In the reconnect case, con_fault() has requeued messages
+ * in out_sent. We should cleanup old messages according to
+ * the reconnect seq.
+ */
+ while (!list_empty(list)) {
+ m = list_first_entry(list, struct ceph_msg, list_head);
+ if (reconnect && m->needs_out_seq)
+ break;
seq = le64_to_cpu(m->hdr.seq);
if (seq > ack)
break;
m->ack_stamp = jiffies;
ceph_msg_remove(m);
}
+
prepare_read_tag(con);
}
if (do_datacrc)
crc = ceph_crc32c_page(crc, page, page_offset, ret);
- (void) ceph_msg_data_advance(cursor, (size_t)ret);
+ ceph_msg_data_advance(cursor, (size_t)ret);
}
if (do_datacrc)
con->in_data_crc = crc;
int i, err = -EINVAL;
struct ceph_fsid fsid;
u32 epoch, num_mon;
- u16 version;
u32 len;
ceph_decode_32_safe(&p, end, len, bad);
ceph_decode_need(&p, end, len, bad);
dout("monmap_decode %p %p len %d\n", p, end, (int)(end-p));
-
- ceph_decode_16_safe(&p, end, version, bad);
+ p += sizeof(u16); /* skip version */
ceph_decode_need(&p, end, sizeof(fsid) + 2*sizeof(u32), bad);
ceph_decode_copy(&p, &fsid, sizeof(fsid));
u32 yes;
struct crush_rule *r;
+ err = -EINVAL;
ceph_decode_32_safe(p, end, yes, bad);
if (!yes) {
dout("crush_decode NO rule %d off %x %p to %p\n",
hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq,
&devlink_nl_family, NLM_F_MULTI, cmd);
- if (!hdr)
+ if (!hdr) {
+ nlmsg_free(skb);
return -EMSGSIZE;
+ }
if (devlink_nl_put_handle(skb, devlink))
goto nla_put_failure;
hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq,
&devlink_nl_family, NLM_F_MULTI, cmd);
- if (!hdr)
+ if (!hdr) {
+ nlmsg_free(skb);
return -EMSGSIZE;
+ }
if (devlink_nl_put_handle(skb, devlink))
goto nla_put_failure;
}
EXPORT_SYMBOL(dst_discard_out);
-const u32 dst_default_metrics[RTAX_MAX + 1] = {
+const struct dst_metrics dst_default_metrics = {
/* This initializer is needed to force linker to place this variable
* into const section. Otherwise it might end into bss section.
* We really want to avoid false sharing on this variable, and catch
* any writes on it.
*/
- [RTAX_MAX] = 0xdeadbeef,
+ .refcnt = ATOMIC_INIT(1),
};
void dst_init(struct dst_entry *dst, struct dst_ops *ops,
if (dev)
dev_hold(dev);
dst->ops = ops;
- dst_init_metrics(dst, dst_default_metrics, true);
+ dst_init_metrics(dst, dst_default_metrics.metrics, true);
dst->expires = 0UL;
dst->path = dst;
dst->from = NULL;
u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old)
{
- u32 *p = kmalloc(sizeof(u32) * RTAX_MAX, GFP_ATOMIC);
+ struct dst_metrics *p = kmalloc(sizeof(*p), GFP_ATOMIC);
if (p) {
- u32 *old_p = __DST_METRICS_PTR(old);
+ struct dst_metrics *old_p = (struct dst_metrics *)__DST_METRICS_PTR(old);
unsigned long prev, new;
- memcpy(p, old_p, sizeof(u32) * RTAX_MAX);
+ atomic_set(&p->refcnt, 1);
+ memcpy(p->metrics, old_p->metrics, sizeof(p->metrics));
new = (unsigned long) p;
prev = cmpxchg(&dst->_metrics, old, new);
if (prev != old) {
kfree(p);
- p = __DST_METRICS_PTR(prev);
+ p = (struct dst_metrics *)__DST_METRICS_PTR(prev);
if (prev & DST_METRICS_READ_ONLY)
p = NULL;
+ } else if (prev & DST_METRICS_REFCOUNTED) {
+ if (atomic_dec_and_test(&old_p->refcnt))
+ kfree(old_p);
}
}
- return p;
+ BUILD_BUG_ON(offsetof(struct dst_metrics, metrics) != 0);
+ return (u32 *)p;
}
EXPORT_SYMBOL(dst_cow_metrics_generic);
{
unsigned long prev, new;
- new = ((unsigned long) dst_default_metrics) | DST_METRICS_READ_ONLY;
+ new = ((unsigned long) &dst_default_metrics) | DST_METRICS_READ_ONLY;
prev = cmpxchg(&dst->_metrics, old, new);
if (prev == old)
kfree(__DST_METRICS_PTR(old));
func == bpf_skb_change_head ||
func == bpf_skb_change_tail ||
func == bpf_skb_pull_data ||
+ func == bpf_clone_redirect ||
func == bpf_l3_csum_replace ||
func == bpf_l4_csum_replace ||
func == bpf_xdp_adjust_head)
lladdr = neigh->ha;
}
- if (new & NUD_CONNECTED)
- neigh->confirmed = jiffies;
- neigh->updated = jiffies;
-
/* If entry was valid and address is not changed,
do not change entry state, if new one is STALE.
*/
}
}
+ /* Update timestamps only once we know we will make a change to the
+ * neighbour entry. Otherwise we risk to move the locktime window with
+ * noop updates and ignore relevant ARP updates.
+ */
+ if (new != old || lladdr != neigh->ha) {
+ if (new & NUD_CONNECTED)
+ neigh->confirmed = jiffies;
+ neigh->updated = jiffies;
+ }
+
if (new != old) {
neigh_del_timer(neigh);
if (new & NUD_PROBE)
goto out;
}
+static int __net_init net_defaults_init_net(struct net *net)
+{
+ net->core.sysctl_somaxconn = SOMAXCONN;
+ return 0;
+}
+
+static struct pernet_operations net_defaults_ops = {
+ .init = net_defaults_init_net,
+};
+
+static __init int net_defaults_init(void)
+{
+ if (register_pernet_subsys(&net_defaults_ops))
+ panic("Cannot initialize net default settings");
+
+ return 0;
+}
+
+core_initcall(net_defaults_init);
#ifdef CONFIG_NET_NS
static struct ucounts *inc_net_namespaces(struct user_namespace *ns)
cb->nlh->nlmsg_seq, 0,
flags,
ext_filter_mask);
- /* If we ran out of room on the first message,
- * we're in trouble
- */
- WARN_ON((err == -EMSGSIZE) && (skb->len == 0));
- if (err < 0)
- goto out;
+ if (err < 0) {
+ if (likely(skb->len))
+ goto out;
+
+ goto out_err;
+ }
nl_dump_check_consistent(cb, nlmsg_hdr(skb));
cont:
}
}
out:
+ err = skb->len;
+out_err:
cb->args[1] = idx;
cb->args[0] = h;
- return skb->len;
+ return err;
}
int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len,
int err = 0;
int fidx = 0;
- if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb,
- IFLA_MAX, ifla_policy, NULL) == 0) {
+ err = nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb,
+ IFLA_MAX, ifla_policy, NULL);
+ if (err < 0) {
+ return -EINVAL;
+ } else if (err == 0) {
if (tb[IFLA_MASTER])
br_idx = nla_get_u32(tb[IFLA_MASTER]);
}
err = br_dev->netdev_ops->ndo_bridge_getlink(
skb, portid, seq, dev,
filter_mask, NLM_F_MULTI);
- if (err < 0 && err != -EOPNOTSUPP)
- break;
+ if (err < 0 && err != -EOPNOTSUPP) {
+ if (likely(skb->len))
+ break;
+
+ goto out_err;
+ }
}
idx++;
}
seq, dev,
filter_mask,
NLM_F_MULTI);
- if (err < 0 && err != -EOPNOTSUPP)
- break;
+ if (err < 0 && err != -EOPNOTSUPP) {
+ if (likely(skb->len))
+ break;
+
+ goto out_err;
+ }
}
idx++;
}
}
+ err = skb->len;
+out_err:
rcu_read_unlock();
cb->args[0] = idx;
- return skb->len;
+ return err;
}
static inline size_t bridge_nlmsg_size(void)
spin_lock_irqsave(&q->lock, flags);
skb = __skb_dequeue(q);
- if (skb && (skb_next = skb_peek(q)))
+ if (skb && (skb_next = skb_peek(q))) {
icmp_next = is_icmp_err_skb(skb_next);
+ if (icmp_next)
+ sk->sk_err = SKB_EXT_ERR(skb_next)->ee.ee_origin;
+ }
spin_unlock_irqrestore(&q->lock, flags);
if (is_icmp_err_skb(skb) && !icmp_next)
#include <trace/events/sock.h>
-#ifdef CONFIG_INET
#include <net/tcp.h>
-#endif
-
#include <net/busy_poll.h>
static DEFINE_MUTEX(proto_list_mutex);
{
struct ctl_table *tbl;
- net->core.sysctl_somaxconn = SOMAXCONN;
-
tbl = netns_core_table;
if (!net_eq(net, &init_net)) {
tbl = kmemdup(tbl, sizeof(netns_core_table), GFP_KERNEL);
return 0;
}
+#ifdef CONFIG_PM_SLEEP
+int dsa_switch_suspend(struct dsa_switch *ds)
+{
+ int i, ret = 0;
+
+ /* Suspend slave network devices */
+ for (i = 0; i < ds->num_ports; i++) {
+ if (!dsa_is_port_initialized(ds, i))
+ continue;
+
+ ret = dsa_slave_suspend(ds->ports[i].netdev);
+ if (ret)
+ return ret;
+ }
+
+ if (ds->ops->suspend)
+ ret = ds->ops->suspend(ds);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(dsa_switch_suspend);
+
+int dsa_switch_resume(struct dsa_switch *ds)
+{
+ int i, ret = 0;
+
+ if (ds->ops->resume)
+ ret = ds->ops->resume(ds);
+
+ if (ret)
+ return ret;
+
+ /* Resume slave network devices */
+ for (i = 0; i < ds->num_ports; i++) {
+ if (!dsa_is_port_initialized(ds, i))
+ continue;
+
+ ret = dsa_slave_resume(ds->ports[i].netdev);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(dsa_switch_resume);
+#endif
+
static struct packet_type dsa_pack_type __read_mostly = {
.type = cpu_to_be16(ETH_P_XDSA),
.func = dsa_switch_rcv,
dsa_ds_unapply(dst, ds);
}
- if (dst->cpu_switch)
+ if (dst->cpu_switch) {
dsa_cpu_port_ethtool_restore(dst->cpu_switch);
+ dst->cpu_switch = NULL;
+ }
pr_info("DSA: tree %d unapplied\n", dst->tree);
dst->applied = false;
dsa_switch_unregister_notifier(ds);
}
-#ifdef CONFIG_PM_SLEEP
-int dsa_switch_suspend(struct dsa_switch *ds)
-{
- int i, ret = 0;
-
- /* Suspend slave network devices */
- for (i = 0; i < ds->num_ports; i++) {
- if (!dsa_is_port_initialized(ds, i))
- continue;
-
- ret = dsa_slave_suspend(ds->ports[i].netdev);
- if (ret)
- return ret;
- }
-
- if (ds->ops->suspend)
- ret = ds->ops->suspend(ds);
-
- return ret;
-}
-EXPORT_SYMBOL_GPL(dsa_switch_suspend);
-
-int dsa_switch_resume(struct dsa_switch *ds)
-{
- int i, ret = 0;
-
- if (ds->ops->resume)
- ret = ds->ops->resume(ds);
-
- if (ret)
- return ret;
-
- /* Resume slave network devices */
- for (i = 0; i < ds->num_ports; i++) {
- if (!dsa_is_port_initialized(ds, i))
- continue;
-
- ret = dsa_slave_resume(ds->ports[i].netdev);
- if (ret)
- return ret;
- }
-
- return 0;
-}
-EXPORT_SYMBOL_GPL(dsa_switch_resume);
-#endif
-
/* platform driver init and cleanup *****************************************/
static int dev_is_class(struct device *dev, void *class)
{
.type = SOCK_DGRAM,
.protocol = IPPROTO_ICMP,
.prot = &ping_prot,
- .ops = &inet_dgram_ops,
+ .ops = &inet_sockraw_ops,
.flags = INET_PROTOSW_REUSE,
},
}
EXPORT_SYMBOL(arp_xmit);
+static bool arp_is_garp(struct net *net, struct net_device *dev,
+ int *addr_type, __be16 ar_op,
+ __be32 sip, __be32 tip,
+ unsigned char *sha, unsigned char *tha)
+{
+ bool is_garp = tip == sip;
+
+ /* Gratuitous ARP _replies_ also require target hwaddr to be
+ * the same as source.
+ */
+ if (is_garp && ar_op == htons(ARPOP_REPLY))
+ is_garp =
+ /* IPv4 over IEEE 1394 doesn't provide target
+ * hardware address field in its ARP payload.
+ */
+ tha &&
+ !memcmp(tha, sha, dev->addr_len);
+
+ if (is_garp) {
+ *addr_type = inet_addr_type_dev_table(net, dev, sip);
+ if (*addr_type != RTN_UNICAST)
+ is_garp = false;
+ }
+ return is_garp;
+}
+
/*
* Process an arp request.
*/
unsigned char *arp_ptr;
struct rtable *rt;
unsigned char *sha;
+ unsigned char *tha = NULL;
__be32 sip, tip;
u16 dev_type = dev->type;
int addr_type;
break;
#endif
default:
+ tha = arp_ptr;
arp_ptr += dev->addr_len;
}
memcpy(&tip, arp_ptr, 4);
n = __neigh_lookup(&arp_tbl, &sip, dev, 0);
- if (IN_DEV_ARP_ACCEPT(in_dev)) {
- unsigned int addr_type = inet_addr_type_dev_table(net, dev, sip);
+ addr_type = -1;
+ if (n || IN_DEV_ARP_ACCEPT(in_dev)) {
+ is_garp = arp_is_garp(net, dev, &addr_type, arp->ar_op,
+ sip, tip, sha, tha);
+ }
+ if (IN_DEV_ARP_ACCEPT(in_dev)) {
/* Unsolicited ARP is not accepted by default.
It is possible, that this option should be enabled for some
devices (strip is candidate)
*/
- is_garp = arp->ar_op == htons(ARPOP_REQUEST) && tip == sip &&
- addr_type == RTN_UNICAST;
-
if (!n &&
- ((arp->ar_op == htons(ARPOP_REPLY) &&
- addr_type == RTN_UNICAST) || is_garp))
+ (is_garp ||
+ (arp->ar_op == htons(ARPOP_REPLY) &&
+ (addr_type == RTN_UNICAST ||
+ (addr_type < 0 &&
+ /* postpone calculation to as late as possible */
+ inet_addr_type_dev_table(net, dev, sip) ==
+ RTN_UNICAST)))))
n = __neigh_lookup(&arp_tbl, &sip, dev, 1);
}
u8 *tail;
u8 *vaddr;
int nfrags;
+ int esph_offset;
struct page *page;
struct sk_buff *trailer;
int tailen = esp->tailen;
}
cow:
+ esph_offset = (unsigned char *)esp->esph - skb_transport_header(skb);
+
nfrags = skb_cow_data(skb, tailen, &trailer);
if (nfrags < 0)
goto out;
tail = skb_tail_pointer(trailer);
- esp->esph = ip_esp_hdr(skb);
+ esp->esph = (struct ip_esp_hdr *)(skb_transport_header(skb) + esph_offset);
skip_cow:
esp_output_fill_trailer(tail, esp->tfclen, esp->plen, esp->proto);
unsigned int e = 0, s_e;
struct fib_table *tb;
struct hlist_head *head;
- int dumped = 0;
+ int dumped = 0, err;
if (nlmsg_len(cb->nlh) >= sizeof(struct rtmsg) &&
((struct rtmsg *) nlmsg_data(cb->nlh))->rtm_flags & RTM_F_CLONED)
if (dumped)
memset(&cb->args[2], 0, sizeof(cb->args) -
2 * sizeof(cb->args[0]));
- if (fib_table_dump(tb, skb, cb) < 0)
- goto out;
+ err = fib_table_dump(tb, skb, cb);
+ if (err < 0) {
+ if (likely(skb->len))
+ goto out;
+
+ goto out_err;
+ }
dumped = 1;
next:
e++;
}
}
out:
+ err = skb->len;
+out_err:
rcu_read_unlock();
cb->args[1] = e;
cb->args[0] = h;
- return skb->len;
+ return err;
}
/* Prepare and feed intra-kernel routing request.
static void free_fib_info_rcu(struct rcu_head *head)
{
struct fib_info *fi = container_of(head, struct fib_info, rcu);
+ struct dst_metrics *m;
change_nexthops(fi) {
if (nexthop_nh->nh_dev)
rt_fibinfo_free(&nexthop_nh->nh_rth_input);
} endfor_nexthops(fi);
- if (fi->fib_metrics != (u32 *) dst_default_metrics)
- kfree(fi->fib_metrics);
+ m = fi->fib_metrics;
+ if (m != &dst_default_metrics && atomic_dec_and_test(&m->refcnt))
+ kfree(m);
kfree(fi);
}
val = 255;
if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK))
return -EINVAL;
- fi->fib_metrics[type - 1] = val;
+ fi->fib_metrics->metrics[type - 1] = val;
}
if (ecn_ca)
- fi->fib_metrics[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA;
+ fi->fib_metrics->metrics[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA;
return 0;
}
goto failure;
fib_info_cnt++;
if (cfg->fc_mx) {
- fi->fib_metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
+ fi->fib_metrics = kzalloc(sizeof(*fi->fib_metrics), GFP_KERNEL);
if (!fi->fib_metrics)
goto failure;
+ atomic_set(&fi->fib_metrics->refcnt, 1);
} else
- fi->fib_metrics = (u32 *) dst_default_metrics;
+ fi->fib_metrics = (struct dst_metrics *)&dst_default_metrics;
fi->fib_net = net;
fi->fib_protocol = cfg->fc_protocol;
if (fi->fib_priority &&
nla_put_u32(skb, RTA_PRIORITY, fi->fib_priority))
goto nla_put_failure;
- if (rtnetlink_put_metrics(skb, fi->fib_metrics) < 0)
+ if (rtnetlink_put_metrics(skb, fi->fib_metrics->metrics) < 0)
goto nla_put_failure;
if (fi->fib_prefsrc &&
/* rcu_read_lock is hold by caller */
hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) {
+ int err;
+
if (i < s_i) {
i++;
continue;
continue;
}
- if (fib_dump_info(skb, NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq,
- RTM_NEWROUTE,
- tb->tb_id,
- fa->fa_type,
- xkey,
- KEYLENGTH - fa->fa_slen,
- fa->fa_tos,
- fa->fa_info, NLM_F_MULTI) < 0) {
+ err = fib_dump_info(skb, NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq, RTM_NEWROUTE,
+ tb->tb_id, fa->fa_type,
+ xkey, KEYLENGTH - fa->fa_slen,
+ fa->fa_tos, fa->fa_info, NLM_F_MULTI);
+ if (err < 0) {
cb->args[4] = i;
- return -1;
+ return err;
}
i++;
}
t_key key = cb->args[3];
while ((l = leaf_walk_rcu(&tp, key)) != NULL) {
- if (fn_trie_dump_leaf(l, tb, skb, cb) < 0) {
+ int err;
+
+ err = fn_trie_dump_leaf(l, tb, skb, cb);
+ if (err < 0) {
cb->args[3] = key;
cb->args[2] = count;
- return -1;
+ return err;
}
++count;
struct net *net = dev_net(skb->dev);
int local = skb_rtable(skb)->rt_flags & RTCF_LOCAL;
struct mr_table *mrt;
+ struct net_device *dev;
+
+ /* skb->dev passed in is the loX master dev for vrfs.
+ * As there are no vifs associated with loopback devices,
+ * get the proper interface that does have a vif associated with it.
+ */
+ dev = skb->dev;
+ if (netif_is_l3_master(skb->dev)) {
+ dev = dev_get_by_index_rcu(net, IPCB(skb)->iif);
+ if (!dev) {
+ kfree_skb(skb);
+ return -ENODEV;
+ }
+ }
/* Packet is looped back after forward, it should not be
* forwarded second time, but still can be delivered locally.
/* already under rcu_read_lock() */
cache = ipmr_cache_find(mrt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr);
if (!cache) {
- int vif = ipmr_find_vif(mrt, skb->dev);
+ int vif = ipmr_find_vif(mrt, dev);
if (vif >= 0)
cache = ipmr_cache_find_any(mrt, ip_hdr(skb)->daddr,
}
read_lock(&mrt_lock);
- vif = ipmr_find_vif(mrt, skb->dev);
+ vif = ipmr_find_vif(mrt, dev);
if (vif >= 0) {
int err2 = ipmr_cache_unresolved(mrt, vif, skb);
read_unlock(&mrt_lock);
static void ipv4_dst_destroy(struct dst_entry *dst)
{
+ struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst);
struct rtable *rt = (struct rtable *) dst;
+ if (p != &dst_default_metrics && atomic_dec_and_test(&p->refcnt))
+ kfree(p);
+
if (!list_empty(&rt->rt_uncached)) {
struct uncached_list *ul = rt->rt_uncached_list;
rt->rt_gateway = nh->nh_gw;
rt->rt_uses_gateway = 1;
}
- dst_init_metrics(&rt->dst, fi->fib_metrics, true);
+ dst_init_metrics(&rt->dst, fi->fib_metrics->metrics, true);
+ if (fi->fib_metrics != &dst_default_metrics) {
+ rt->dst._metrics |= DST_METRICS_REFCOUNTED;
+ atomic_inc(&fi->fib_metrics->refcnt);
+ }
#ifdef CONFIG_IP_ROUTE_CLASSID
rt->dst.tclassid = nh->nh_tclassid;
#endif
{
struct tcp_sock *tp = tcp_sk(sk);
struct inet_sock *inet = inet_sk(sk);
+ struct sockaddr *uaddr = msg->msg_name;
int err, flags;
- if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE))
+ if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) ||
+ (uaddr && msg->msg_namelen >= sizeof(uaddr->sa_family) &&
+ uaddr->sa_family == AF_UNSPEC))
return -EOPNOTSUPP;
if (tp->fastopen_req)
return -EALREADY; /* Another Fast Open is in progress */
}
}
flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0;
- err = __inet_stream_connect(sk->sk_socket, msg->msg_name,
+ err = __inet_stream_connect(sk->sk_socket, uaddr,
msg->msg_namelen, flags, 1);
/* fastopen_req could already be freed in __inet_stream_connect
* if the connection times out or gets rst
tcp_set_ca_state(sk, TCP_CA_Open);
tcp_clear_retrans(tp);
inet_csk_delack_init(sk);
+ /* Initialize rcv_mss to TCP_MIN_MSS to avoid division by 0
+ * issue in __tcp_select_window()
+ */
+ icsk->icsk_ack.rcv_mss = TCP_MIN_MSS;
tcp_init_send_head(sk);
memset(&tp->rx_opt, 0, sizeof(tp->rx_opt));
__sk_dst_reset(sk);
return 0;
}
-static int tcp_repair_options_est(struct tcp_sock *tp,
+static int tcp_repair_options_est(struct sock *sk,
struct tcp_repair_opt __user *optbuf, unsigned int len)
{
+ struct tcp_sock *tp = tcp_sk(sk);
struct tcp_repair_opt opt;
while (len >= sizeof(opt)) {
switch (opt.opt_code) {
case TCPOPT_MSS:
tp->rx_opt.mss_clamp = opt.opt_val;
+ tcp_mtup_init(sk);
break;
case TCPOPT_WINDOW:
{
if (!tp->repair)
err = -EINVAL;
else if (sk->sk_state == TCP_ESTABLISHED)
- err = tcp_repair_options_est(tp,
+ err = tcp_repair_options_est(sk,
(struct tcp_repair_opt __user *)optval,
optlen);
else
{
const struct inet_connection_sock *icsk = inet_csk(sk);
+ tcp_sk(sk)->prior_ssthresh = 0;
if (icsk->icsk_ca_ops->init)
icsk->icsk_ca_ops->init(sk);
if (tcp_ca_needs_ecn(sk))
int delta;
/* Non-retransmitted hole got filled? That's reordering */
- if (reord < prior_fackets)
+ if (reord < prior_fackets && reord <= tp->fackets_out)
tcp_update_reordering(sk, tp->fackets_out - reord, 0);
delta = tcp_is_fack(tp) ? pkts_acked :
udp_lib_rehash(sk, new_hash);
}
-int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
int rc;
* Note that in the success and error cases, the skb is assumed to
* have either been requeued or freed.
*/
-int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
struct udp_sock *up = udp_sk(sk);
int is_udplite = IS_UDPLITE(sk);
int flags, int *addr_len);
int udp_sendpage(struct sock *sk, struct page *page, int offset, size_t size,
int flags);
-int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
void udp_destroy_sock(struct sock *sk);
#ifdef CONFIG_PROC_FS
struct ipv6hdr *ip6_hdr;
struct ipv6_opt_hdr *hop;
unsigned char buf[CALIPSO_MAX_BUFFER];
- int len_delta, new_end, pad;
+ int len_delta, new_end, pad, payload;
unsigned int start, end;
ip6_hdr = ipv6_hdr(skb);
if (ret_val < 0)
return ret_val;
+ ip6_hdr = ipv6_hdr(skb); /* Reset as skb_cow() may have moved it */
+
if (len_delta) {
if (len_delta > 0)
skb_push(skb, len_delta);
sizeof(*ip6_hdr) + start);
skb_reset_network_header(skb);
ip6_hdr = ipv6_hdr(skb);
+ payload = ntohs(ip6_hdr->payload_len);
+ ip6_hdr->payload_len = htons(payload + len_delta);
}
hop = (struct ipv6_opt_hdr *)(ip6_hdr + 1);
memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
- dsfield = ipv4_get_dsfield(iph);
-
if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
- fl6.flowlabel |= htonl((__u32)iph->tos << IPV6_TCLASS_SHIFT)
- & IPV6_TCLASS_MASK;
+ dsfield = ipv4_get_dsfield(iph);
+ else
+ dsfield = ip6_tclass(t->parms.flowinfo);
if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
fl6.flowi6_mark = skb->mark;
else
memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
- dsfield = ipv6_get_dsfield(ipv6h);
if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
- fl6.flowlabel |= (*(__be32 *) ipv6h & IPV6_TCLASS_MASK);
+ dsfield = ipv6_get_dsfield(ipv6h);
+ else
+ dsfield = ip6_tclass(t->parms.flowinfo);
+
if (t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL)
fl6.flowlabel |= ip6_flowlabel(ipv6h);
if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
const struct net_offload *ops;
int proto;
struct frag_hdr *fptr;
- unsigned int unfrag_ip6hlen;
unsigned int payload_len;
u8 *prevhdr;
int offset = 0;
skb->network_header = (u8 *)ipv6h - skb->head;
if (udpfrag) {
- unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr);
- fptr = (struct frag_hdr *)((u8 *)ipv6h + unfrag_ip6hlen);
+ int err = ip6_find_1stfragopt(skb, &prevhdr);
+ if (err < 0) {
+ kfree_skb_list(segs);
+ return ERR_PTR(err);
+ }
+ fptr = (struct frag_hdr *)((u8 *)ipv6h + err);
fptr->frag_off = htons(offset);
if (skb->next)
fptr->frag_off |= htons(IP6_MF);
int ptr, offset = 0, err = 0;
u8 *prevhdr, nexthdr = 0;
- hlen = ip6_find_1stfragopt(skb, &prevhdr);
+ err = ip6_find_1stfragopt(skb, &prevhdr);
+ if (err < 0)
+ goto fail;
+ hlen = err;
nexthdr = *prevhdr;
mtu = ip6_skb_dst_mtu(skb);
*/
alloclen += sizeof(struct frag_hdr);
+ copy = datalen - transhdrlen - fraggap;
+ if (copy < 0) {
+ err = -EINVAL;
+ goto error;
+ }
if (transhdrlen) {
skb = sock_alloc_send_skb(sk,
alloclen + hh_len,
data += fraggap;
pskb_trim_unique(skb_prev, maxfraglen);
}
- copy = datalen - transhdrlen - fraggap;
-
- if (copy < 0) {
- err = -EINVAL;
- kfree_skb(skb);
- goto error;
- } else if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) {
+ if (copy > 0 &&
+ getfrag(from, data + transhdrlen, offset,
+ copy, fraggap, skb) < 0) {
err = -EFAULT;
kfree_skb(skb);
goto error;
if (!dst) {
route_lookup:
+ /* add dsfield to flowlabel for route lookup */
+ fl6->flowlabel = ip6_make_flowinfo(dsfield, fl6->flowlabel);
+
dst = ip6_route_output(net, NULL, fl6);
if (dst->error)
skb_push(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
ipv6h = ipv6_hdr(skb);
- ip6_flow_hdr(ipv6h, INET_ECN_encapsulate(0, dsfield),
+ ip6_flow_hdr(ipv6h, dsfield,
ip6_make_flowlabel(net, skb, fl6->flowlabel, true, fl6));
ipv6h->hop_limit = hop_limit;
ipv6h->nexthdr = proto;
if (tproto != IPPROTO_IPIP && tproto != 0)
return -1;
- dsfield = ipv4_get_dsfield(iph);
-
if (t->parms.collect_md) {
struct ip_tunnel_info *tun_info;
const struct ip_tunnel_key *key;
fl6.flowi6_proto = IPPROTO_IPIP;
fl6.daddr = key->u.ipv6.dst;
fl6.flowlabel = key->label;
+ dsfield = ip6_tclass(key->label);
} else {
if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
encap_limit = t->parms.encap_limit;
fl6.flowi6_proto = IPPROTO_IPIP;
if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
- fl6.flowlabel |= htonl((__u32)iph->tos << IPV6_TCLASS_SHIFT)
- & IPV6_TCLASS_MASK;
+ dsfield = ipv4_get_dsfield(iph);
+ else
+ dsfield = ip6_tclass(t->parms.flowinfo);
if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
fl6.flowi6_mark = skb->mark;
else
if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
return -1;
+ dsfield = INET_ECN_encapsulate(dsfield, ipv4_get_dsfield(iph));
+
skb_set_inner_ipproto(skb, IPPROTO_IPIP);
err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu,
ip6_tnl_addr_conflict(t, ipv6h))
return -1;
- dsfield = ipv6_get_dsfield(ipv6h);
-
if (t->parms.collect_md) {
struct ip_tunnel_info *tun_info;
const struct ip_tunnel_key *key;
fl6.flowi6_proto = IPPROTO_IPV6;
fl6.daddr = key->u.ipv6.dst;
fl6.flowlabel = key->label;
+ dsfield = ip6_tclass(key->label);
} else {
offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb));
/* ip6_tnl_parse_tlv_enc_lim() might have reallocated skb->head */
fl6.flowi6_proto = IPPROTO_IPV6;
if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
- fl6.flowlabel |= (*(__be32 *)ipv6h & IPV6_TCLASS_MASK);
+ dsfield = ipv6_get_dsfield(ipv6h);
+ else
+ dsfield = ip6_tclass(t->parms.flowinfo);
if (t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL)
fl6.flowlabel |= ip6_flowlabel(ipv6h);
if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
return -1;
+ dsfield = INET_ECN_encapsulate(dsfield, ipv6_get_dsfield(ipv6h));
+
skb_set_inner_ipproto(skb, IPPROTO_IPV6);
err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu,
int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
{
u16 offset = sizeof(struct ipv6hdr);
- struct ipv6_opt_hdr *exthdr =
- (struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1);
unsigned int packet_len = skb_tail_pointer(skb) -
skb_network_header(skb);
int found_rhdr = 0;
*nexthdr = &ipv6_hdr(skb)->nexthdr;
- while (offset + 1 <= packet_len) {
+ while (offset <= packet_len) {
+ struct ipv6_opt_hdr *exthdr;
switch (**nexthdr) {
return offset;
}
- offset += ipv6_optlen(exthdr);
- *nexthdr = &exthdr->nexthdr;
+ if (offset + sizeof(struct ipv6_opt_hdr) > packet_len)
+ return -EINVAL;
+
exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) +
offset);
+ offset += ipv6_optlen(exthdr);
+ *nexthdr = &exthdr->nexthdr;
}
- return offset;
+ return -EINVAL;
}
EXPORT_SYMBOL(ip6_find_1stfragopt);
.type = SOCK_DGRAM,
.protocol = IPPROTO_ICMPV6,
.prot = &pingv6_prot,
- .ops = &inet6_dgram_ops,
+ .ops = &inet6_sockraw_ops,
.flags = INET_PROTOSW_REUSE,
};
#endif /* CONFIG_PROC_FS */
/* Same as inet6_dgram_ops, sans udp_poll. */
-static const struct proto_ops inet6_sockraw_ops = {
+const struct proto_ops inet6_sockraw_ops = {
.family = PF_INET6,
.owner = THIS_MODULE,
.release = inet6_release,
return;
}
-int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
int rc;
}
EXPORT_SYMBOL(udpv6_encap_enable);
-int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
struct udp_sock *up = udp_sk(sk);
int is_udplite = IS_UDPLITE(sk);
int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len);
int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
int flags, int *addr_len);
-int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
void udpv6_destroy_sock(struct sock *sk);
#ifdef CONFIG_PROC_FS
u8 frag_hdr_sz = sizeof(struct frag_hdr);
__wsum csum;
int tnl_hlen;
+ int err;
mss = skb_shinfo(skb)->gso_size;
if (unlikely(skb->len <= mss))
/* Find the unfragmentable header and shift it left by frag_hdr_sz
* bytes to insert fragment header.
*/
- unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr);
+ err = ip6_find_1stfragopt(skb, &prevhdr);
+ if (err < 0)
+ return ERR_PTR(err);
+ unfrag_ip6hlen = err;
nexthdr = *prevhdr;
*prevhdr = NEXTHDR_FRAGMENT;
unfrag_len = (skb_network_header(skb) - skb_mac_header(skb)) +
iph = ipv6_hdr(skb);
hdr_len = x->type->hdr_offset(x, skb, &prevhdr);
+ if (hdr_len < 0)
+ return hdr_len;
skb_set_mac_header(skb, (prevhdr - x->props.header_len) - skb->data);
skb_set_network_header(skb, -x->props.header_len);
skb->transport_header = skb->network_header + hdr_len;
skb_set_inner_transport_header(skb, skb_transport_offset(skb));
hdr_len = x->type->hdr_offset(x, skb, &prevhdr);
+ if (hdr_len < 0)
+ return hdr_len;
skb_set_mac_header(skb, (prevhdr - x->props.header_len) - skb->data);
skb_set_network_header(skb, -x->props.header_len);
skb->transport_header = skb->network_header + hdr_len;
p += pol->sadb_x_policy_len*8;
sec_ctx = (struct sadb_x_sec_ctx *)p;
if (len < pol->sadb_x_policy_len*8 +
- sec_ctx->sadb_x_sec_len) {
+ sec_ctx->sadb_x_sec_len*8) {
*dir = -EINVAL;
goto out;
}
int rc = -EINVAL;
dprintk("%s: binding %02X\n", __func__, addr->sllc_sap);
+
+ lock_sock(sk);
if (unlikely(!sock_flag(sk, SOCK_ZAPPED) || addrlen != sizeof(*addr)))
goto out;
rc = -EAFNOSUPPORT;
out_put:
llc_sap_put(sap);
out:
+ release_sock(sk);
return rc;
}
* Copyright 2006-2007 Jiri Benc <jbenc@suse.cz>
* Copyright 2007, Michael Wu <flamingice@sourmilk.net>
* Copyright 2007-2010, Intel Corporation
- * Copyright(c) 2015 Intel Deutschland GmbH
+ * Copyright(c) 2015-2017 Intel Deutschland GmbH
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
ieee80211_agg_start_txq(sta, tid, true);
}
-void ieee80211_start_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u16 tid)
+void ieee80211_start_tx_ba_cb(struct sta_info *sta, int tid,
+ struct tid_ampdu_tx *tid_tx)
{
- struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
+ struct ieee80211_sub_if_data *sdata = sta->sdata;
struct ieee80211_local *local = sdata->local;
- struct sta_info *sta;
- struct tid_ampdu_tx *tid_tx;
- trace_api_start_tx_ba_cb(sdata, ra, tid);
+ if (WARN_ON(test_and_set_bit(HT_AGG_STATE_DRV_READY, &tid_tx->state)))
+ return;
+
+ if (test_bit(HT_AGG_STATE_RESPONSE_RECEIVED, &tid_tx->state))
+ ieee80211_agg_tx_operational(local, sta, tid);
+}
+
+static struct tid_ampdu_tx *
+ieee80211_lookup_tid_tx(struct ieee80211_sub_if_data *sdata,
+ const u8 *ra, u16 tid, struct sta_info **sta)
+{
+ struct tid_ampdu_tx *tid_tx;
if (tid >= IEEE80211_NUM_TIDS) {
ht_dbg(sdata, "Bad TID value: tid = %d (>= %d)\n",
tid, IEEE80211_NUM_TIDS);
- return;
+ return NULL;
}
- mutex_lock(&local->sta_mtx);
- sta = sta_info_get_bss(sdata, ra);
- if (!sta) {
- mutex_unlock(&local->sta_mtx);
+ *sta = sta_info_get_bss(sdata, ra);
+ if (!*sta) {
ht_dbg(sdata, "Could not find station: %pM\n", ra);
- return;
+ return NULL;
}
- mutex_lock(&sta->ampdu_mlme.mtx);
- tid_tx = rcu_dereference_protected_tid_tx(sta, tid);
+ tid_tx = rcu_dereference((*sta)->ampdu_mlme.tid_tx[tid]);
- if (WARN_ON(!tid_tx)) {
+ if (WARN_ON(!tid_tx))
ht_dbg(sdata, "addBA was not requested!\n");
- goto unlock;
- }
- if (WARN_ON(test_and_set_bit(HT_AGG_STATE_DRV_READY, &tid_tx->state)))
- goto unlock;
-
- if (test_bit(HT_AGG_STATE_RESPONSE_RECEIVED, &tid_tx->state))
- ieee80211_agg_tx_operational(local, sta, tid);
-
- unlock:
- mutex_unlock(&sta->ampdu_mlme.mtx);
- mutex_unlock(&local->sta_mtx);
+ return tid_tx;
}
void ieee80211_start_tx_ba_cb_irqsafe(struct ieee80211_vif *vif,
{
struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
struct ieee80211_local *local = sdata->local;
- struct ieee80211_ra_tid *ra_tid;
- struct sk_buff *skb = dev_alloc_skb(0);
+ struct sta_info *sta;
+ struct tid_ampdu_tx *tid_tx;
- if (unlikely(!skb))
- return;
+ trace_api_start_tx_ba_cb(sdata, ra, tid);
- ra_tid = (struct ieee80211_ra_tid *) &skb->cb;
- memcpy(&ra_tid->ra, ra, ETH_ALEN);
- ra_tid->tid = tid;
+ rcu_read_lock();
+ tid_tx = ieee80211_lookup_tid_tx(sdata, ra, tid, &sta);
+ if (!tid_tx)
+ goto out;
- skb->pkt_type = IEEE80211_SDATA_QUEUE_AGG_START;
- skb_queue_tail(&sdata->skb_queue, skb);
- ieee80211_queue_work(&local->hw, &sdata->work);
+ set_bit(HT_AGG_STATE_START_CB, &tid_tx->state);
+ ieee80211_queue_work(&local->hw, &sta->ampdu_mlme.work);
+ out:
+ rcu_read_unlock();
}
EXPORT_SYMBOL(ieee80211_start_tx_ba_cb_irqsafe);
}
EXPORT_SYMBOL(ieee80211_stop_tx_ba_session);
-void ieee80211_stop_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u8 tid)
+void ieee80211_stop_tx_ba_cb(struct sta_info *sta, int tid,
+ struct tid_ampdu_tx *tid_tx)
{
- struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
- struct ieee80211_local *local = sdata->local;
- struct sta_info *sta;
- struct tid_ampdu_tx *tid_tx;
+ struct ieee80211_sub_if_data *sdata = sta->sdata;
bool send_delba = false;
- trace_api_stop_tx_ba_cb(sdata, ra, tid);
-
- if (tid >= IEEE80211_NUM_TIDS) {
- ht_dbg(sdata, "Bad TID value: tid = %d (>= %d)\n",
- tid, IEEE80211_NUM_TIDS);
- return;
- }
-
- ht_dbg(sdata, "Stopping Tx BA session for %pM tid %d\n", ra, tid);
-
- mutex_lock(&local->sta_mtx);
-
- sta = sta_info_get_bss(sdata, ra);
- if (!sta) {
- ht_dbg(sdata, "Could not find station: %pM\n", ra);
- goto unlock;
- }
+ ht_dbg(sdata, "Stopping Tx BA session for %pM tid %d\n",
+ sta->sta.addr, tid);
- mutex_lock(&sta->ampdu_mlme.mtx);
spin_lock_bh(&sta->lock);
- tid_tx = rcu_dereference_protected_tid_tx(sta, tid);
- if (!tid_tx || !test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state)) {
+ if (!test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state)) {
ht_dbg(sdata,
"unexpected callback to A-MPDU stop for %pM tid %d\n",
sta->sta.addr, tid);
spin_unlock_bh(&sta->lock);
if (send_delba)
- ieee80211_send_delba(sdata, ra, tid,
+ ieee80211_send_delba(sdata, sta->sta.addr, tid,
WLAN_BACK_INITIATOR, WLAN_REASON_QSTA_NOT_USE);
-
- mutex_unlock(&sta->ampdu_mlme.mtx);
- unlock:
- mutex_unlock(&local->sta_mtx);
}
void ieee80211_stop_tx_ba_cb_irqsafe(struct ieee80211_vif *vif,
{
struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
struct ieee80211_local *local = sdata->local;
- struct ieee80211_ra_tid *ra_tid;
- struct sk_buff *skb = dev_alloc_skb(0);
+ struct sta_info *sta;
+ struct tid_ampdu_tx *tid_tx;
- if (unlikely(!skb))
- return;
+ trace_api_stop_tx_ba_cb(sdata, ra, tid);
- ra_tid = (struct ieee80211_ra_tid *) &skb->cb;
- memcpy(&ra_tid->ra, ra, ETH_ALEN);
- ra_tid->tid = tid;
+ rcu_read_lock();
+ tid_tx = ieee80211_lookup_tid_tx(sdata, ra, tid, &sta);
+ if (!tid_tx)
+ goto out;
- skb->pkt_type = IEEE80211_SDATA_QUEUE_AGG_STOP;
- skb_queue_tail(&sdata->skb_queue, skb);
- ieee80211_queue_work(&local->hw, &sdata->work);
+ set_bit(HT_AGG_STATE_STOP_CB, &tid_tx->state);
+ ieee80211_queue_work(&local->hw, &sta->ampdu_mlme.work);
+ out:
+ rcu_read_unlock();
}
EXPORT_SYMBOL(ieee80211_stop_tx_ba_cb_irqsafe);
* Copyright 2006-2007 Jiri Benc <jbenc@suse.cz>
* Copyright 2007, Michael Wu <flamingice@sourmilk.net>
* Copyright 2007-2010, Intel Corporation
+ * Copyright 2017 Intel Deutschland GmbH
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
{
int i;
- cancel_work_sync(&sta->ampdu_mlme.work);
-
for (i = 0; i < IEEE80211_NUM_TIDS; i++) {
__ieee80211_stop_tx_ba_session(sta, i, reason);
__ieee80211_stop_rx_ba_session(sta, i, WLAN_BACK_RECIPIENT,
reason != AGG_STOP_DESTROY_STA &&
reason != AGG_STOP_PEER_REQUEST);
}
+
+ /* stopping might queue the work again - so cancel only afterwards */
+ cancel_work_sync(&sta->ampdu_mlme.work);
}
void ieee80211_ba_session_work(struct work_struct *work)
spin_unlock_bh(&sta->lock);
tid_tx = rcu_dereference_protected_tid_tx(sta, tid);
- if (tid_tx && test_and_clear_bit(HT_AGG_STATE_WANT_STOP,
- &tid_tx->state))
+ if (!tid_tx)
+ continue;
+
+ if (test_and_clear_bit(HT_AGG_STATE_START_CB, &tid_tx->state))
+ ieee80211_start_tx_ba_cb(sta, tid, tid_tx);
+ if (test_and_clear_bit(HT_AGG_STATE_WANT_STOP, &tid_tx->state))
___ieee80211_stop_tx_ba_session(sta, tid,
AGG_STOP_LOCAL_REQUEST);
+ if (test_and_clear_bit(HT_AGG_STATE_STOP_CB, &tid_tx->state))
+ ieee80211_stop_tx_ba_cb(sta, tid, tid_tx);
}
mutex_unlock(&sta->ampdu_mlme.mtx);
}
enum sdata_queue_type {
IEEE80211_SDATA_QUEUE_TYPE_FRAME = 0,
- IEEE80211_SDATA_QUEUE_AGG_START = 1,
- IEEE80211_SDATA_QUEUE_AGG_STOP = 2,
IEEE80211_SDATA_QUEUE_RX_AGG_START = 3,
IEEE80211_SDATA_QUEUE_RX_AGG_STOP = 4,
};
return local->hw.wiphy->bands[band];
}
-/* this struct represents 802.11n's RA/TID combination */
-struct ieee80211_ra_tid {
- u8 ra[ETH_ALEN];
- u16 tid;
-};
-
/* this struct holds the value parsing from channel switch IE */
struct ieee80211_csa_ie {
struct cfg80211_chan_def chandef;
enum ieee80211_agg_stop_reason reason);
int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid,
enum ieee80211_agg_stop_reason reason);
-void ieee80211_start_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u16 tid);
-void ieee80211_stop_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u8 tid);
+void ieee80211_start_tx_ba_cb(struct sta_info *sta, int tid,
+ struct tid_ampdu_tx *tid_tx);
+void ieee80211_stop_tx_ba_cb(struct sta_info *sta, int tid,
+ struct tid_ampdu_tx *tid_tx);
void ieee80211_ba_session_work(struct work_struct *work);
void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid);
void ieee80211_release_reorder_timeout(struct sta_info *sta, int tid);
struct ieee80211_local *local = sdata->local;
struct sk_buff *skb;
struct sta_info *sta;
- struct ieee80211_ra_tid *ra_tid;
struct ieee80211_rx_agg *rx_agg;
if (!ieee80211_sdata_running(sdata))
while ((skb = skb_dequeue(&sdata->skb_queue))) {
struct ieee80211_mgmt *mgmt = (void *)skb->data;
- if (skb->pkt_type == IEEE80211_SDATA_QUEUE_AGG_START) {
- ra_tid = (void *)&skb->cb;
- ieee80211_start_tx_ba_cb(&sdata->vif, ra_tid->ra,
- ra_tid->tid);
- } else if (skb->pkt_type == IEEE80211_SDATA_QUEUE_AGG_STOP) {
- ra_tid = (void *)&skb->cb;
- ieee80211_stop_tx_ba_cb(&sdata->vif, ra_tid->ra,
- ra_tid->tid);
- } else if (skb->pkt_type == IEEE80211_SDATA_QUEUE_RX_AGG_START) {
+ if (skb->pkt_type == IEEE80211_SDATA_QUEUE_RX_AGG_START) {
rx_agg = (void *)&skb->cb;
mutex_lock(&local->sta_mtx);
sta = sta_info_get_bss(sdata, rx_agg->addr);
if (is_multicast_ether_addr(hdr->addr1)) {
mpp_addr = hdr->addr3;
proxied_addr = mesh_hdr->eaddr1;
- } else if (mesh_hdr->flags & MESH_FLAGS_AE_A5_A6) {
+ } else if ((mesh_hdr->flags & MESH_FLAGS_AE) ==
+ MESH_FLAGS_AE_A5_A6) {
/* has_a4 already checked in ieee80211_rx_mesh_check */
mpp_addr = hdr->addr4;
proxied_addr = mesh_hdr->eaddr2;
struct ieee80211_sta_rx_stats *cpurxs;
cpurxs = per_cpu_ptr(sta->pcpu_rx_stats, cpu);
- sinfo->rx_packets += cpurxs->dropped;
+ sinfo->rx_dropped_misc += cpurxs->dropped;
}
}
#define HT_AGG_STATE_STOPPING 3
#define HT_AGG_STATE_WANT_START 4
#define HT_AGG_STATE_WANT_STOP 5
+#define HT_AGG_STATE_START_CB 6
+#define HT_AGG_STATE_STOP_CB 7
enum ieee80211_agg_stop_reason {
AGG_STOP_DECLINED,
continue;
alive++;
nh_flags &= ~flags;
- WRITE_ONCE(nh->nh_flags, flags);
+ WRITE_ONCE(nh->nh_flags, nh_flags);
} endfor_nexthops(rt);
WRITE_ONCE(rt->rt_nhn_alive, alive);
{
unsigned int verdict = NF_DROP;
- if (IP_VS_FWD_METHOD(cp) != 0) {
- pr_err("shouldn't reach here, because the box is on the "
- "half connection in the tun/dr module.\n");
- }
+ if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ)
+ goto ignore_cp;
/* Ensure the checksum is correct */
if (!skb_csum_unnecessary(skb) && ip_vs_checksum_complete(skb, ihl)) {
ip_vs_notrack(skb);
else
ip_vs_update_conntrack(skb, cp, 0);
+
+ignore_cp:
verdict = NF_ACCEPT;
out:
*/
cp = pp->conn_out_get(ipvs, af, skb, &iph);
- if (likely(cp))
+ if (likely(cp)) {
+ if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ)
+ goto ignore_cp;
return handle_response(af, skb, pd, cp, &iph, hooknum);
+ }
/* Check for real-server-started requests */
if (atomic_read(&ipvs->conn_out_counter)) {
}
}
}
+
+out:
IP_VS_DBG_PKT(12, af, pp, skb, iph.off,
"ip_vs_out: packet continues traversal as normal");
return NF_ACCEPT;
+
+ignore_cp:
+ __ip_vs_conn_put(cp);
+ goto out;
}
/*
#endif
if (h != NULL && !try_module_get(h->me))
h = NULL;
+ if (h != NULL && !refcount_inc_not_zero(&h->refcnt)) {
+ module_put(h->me);
+ h = NULL;
+ }
rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(nf_conntrack_helper_try_module_get);
+void nf_conntrack_helper_put(struct nf_conntrack_helper *helper)
+{
+ refcount_dec(&helper->refcnt);
+ module_put(helper->me);
+}
+EXPORT_SYMBOL_GPL(nf_conntrack_helper_put);
+
struct nf_conn_help *
nf_ct_helper_ext_add(struct nf_conn *ct,
struct nf_conntrack_helper *helper, gfp_t gfp)
}
}
}
+ refcount_set(&me->refcnt, 1);
hlist_add_head_rcu(&me->hnode, &nf_ct_helper_hash[h]);
nf_ct_helper_count++;
out:
#include <net/netfilter/nf_conntrack_zones.h>
#include <net/netfilter/nf_conntrack_timestamp.h>
#include <net/netfilter/nf_conntrack_labels.h>
+#include <net/netfilter/nf_conntrack_seqadj.h>
+#include <net/netfilter/nf_conntrack_synproxy.h>
#ifdef CONFIG_NF_NAT_NEEDED
#include <net/netfilter/nf_nat_core.h>
#include <net/netfilter/nf_nat_l4proto.h>
}
out:
local_bh_enable();
- if (last)
+ if (last) {
+ /* nf ct hash resize happened, now clear the leftover. */
+ if ((struct nf_conn *)cb->args[1] == last)
+ cb->args[1] = 0;
+
nf_ct_put(last);
+ }
while (i) {
i--;
static int
ctnetlink_parse_tuple(const struct nlattr * const cda[],
- struct nf_conntrack_tuple *tuple,
- enum ctattr_type type, u_int8_t l3num,
- struct nf_conntrack_zone *zone)
+ struct nf_conntrack_tuple *tuple, u32 type,
+ u_int8_t l3num, struct nf_conntrack_zone *zone)
{
struct nlattr *tb[CTA_TUPLE_MAX+1];
int err;
nf_ct_tstamp_ext_add(ct, GFP_ATOMIC);
nf_ct_ecache_ext_add(ct, 0, 0, GFP_ATOMIC);
nf_ct_labels_ext_add(ct);
+ nfct_seqadj_ext_add(ct);
+ nfct_synproxy_ext_add(ct);
/* we must add conntrack extensions before confirmation. */
ct->status |= IPS_CONFIRMED;
static int ctnetlink_exp_dump_tuple(struct sk_buff *skb,
const struct nf_conntrack_tuple *tuple,
- enum ctattr_expect type)
+ u32 type)
{
struct nlattr *nest_parms;
u8 pf, unsigned int hooknum)
{
const struct sctphdr *sh;
- struct sctphdr _sctph;
const char *logmsg;
- sh = skb_header_pointer(skb, dataoff, sizeof(_sctph), &_sctph);
- if (!sh) {
+ if (skb->len < dataoff + sizeof(struct sctphdr)) {
logmsg = "nf_ct_sctp: short packet ";
goto out_invalid;
}
if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING &&
skb->ip_summed == CHECKSUM_NONE) {
+ if (!skb_make_writable(skb, dataoff + sizeof(struct sctphdr))) {
+ logmsg = "nf_ct_sctp: failed to read header ";
+ goto out_invalid;
+ }
+ sh = (const struct sctphdr *)(skb->data + dataoff);
if (sh->checksum != sctp_compute_cksum(skb, dataoff)) {
logmsg = "nf_ct_sctp: bad CRC ";
goto out_invalid;
{
struct nf_conntrack_tuple curr_tuple, new_tuple;
+ /* Can't setup nat info for confirmed ct. */
+ if (nf_ct_is_confirmed(ct))
+ return NF_ACCEPT;
+
NF_CT_ASSERT(maniptype == NF_NAT_MANIP_SRC ||
maniptype == NF_NAT_MANIP_DST);
BUG_ON(nf_nat_initialized(ct, maniptype));
* Else, when the conntrack is destoyed, nf_nat_cleanup_conntrack()
* will delete entry from already-freed table.
*/
- ct->status &= ~IPS_NAT_DONE_MASK;
+ clear_bit(IPS_SRC_NAT_DONE_BIT, &ct->status);
rhltable_remove(&nf_nat_bysource_table, &ct->nat_bysource,
nf_nat_bysource_params);
return nf_tables_fill_setelem(args->skb, set, elem);
}
+struct nft_set_dump_ctx {
+ const struct nft_set *set;
+ struct nft_ctx ctx;
+};
+
static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
{
+ struct nft_set_dump_ctx *dump_ctx = cb->data;
struct net *net = sock_net(skb->sk);
- u8 genmask = nft_genmask_cur(net);
+ struct nft_af_info *afi;
+ struct nft_table *table;
struct nft_set *set;
struct nft_set_dump_args args;
- struct nft_ctx ctx;
- struct nlattr *nla[NFTA_SET_ELEM_LIST_MAX + 1];
+ bool set_found = false;
struct nfgenmsg *nfmsg;
struct nlmsghdr *nlh;
struct nlattr *nest;
u32 portid, seq;
- int event, err;
+ int event;
- err = nlmsg_parse(cb->nlh, sizeof(struct nfgenmsg), nla,
- NFTA_SET_ELEM_LIST_MAX, nft_set_elem_list_policy,
- NULL);
- if (err < 0)
- return err;
+ rcu_read_lock();
+ list_for_each_entry_rcu(afi, &net->nft.af_info, list) {
+ if (afi != dump_ctx->ctx.afi)
+ continue;
- err = nft_ctx_init_from_elemattr(&ctx, net, cb->skb, cb->nlh,
- (void *)nla, genmask);
- if (err < 0)
- return err;
+ list_for_each_entry_rcu(table, &afi->tables, list) {
+ if (table != dump_ctx->ctx.table)
+ continue;
- set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET],
- genmask);
- if (IS_ERR(set))
- return PTR_ERR(set);
+ list_for_each_entry_rcu(set, &table->sets, list) {
+ if (set == dump_ctx->set) {
+ set_found = true;
+ break;
+ }
+ }
+ break;
+ }
+ break;
+ }
+
+ if (!set_found) {
+ rcu_read_unlock();
+ return -ENOENT;
+ }
event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, NFT_MSG_NEWSETELEM);
portid = NETLINK_CB(cb->skb).portid;
goto nla_put_failure;
nfmsg = nlmsg_data(nlh);
- nfmsg->nfgen_family = ctx.afi->family;
+ nfmsg->nfgen_family = afi->family;
nfmsg->version = NFNETLINK_V0;
- nfmsg->res_id = htons(ctx.net->nft.base_seq & 0xffff);
+ nfmsg->res_id = htons(net->nft.base_seq & 0xffff);
- if (nla_put_string(skb, NFTA_SET_ELEM_LIST_TABLE, ctx.table->name))
+ if (nla_put_string(skb, NFTA_SET_ELEM_LIST_TABLE, table->name))
goto nla_put_failure;
if (nla_put_string(skb, NFTA_SET_ELEM_LIST_SET, set->name))
goto nla_put_failure;
args.cb = cb;
args.skb = skb;
- args.iter.genmask = nft_genmask_cur(ctx.net);
+ args.iter.genmask = nft_genmask_cur(net);
args.iter.skip = cb->args[0];
args.iter.count = 0;
args.iter.err = 0;
args.iter.fn = nf_tables_dump_setelem;
- set->ops->walk(&ctx, set, &args.iter);
+ set->ops->walk(&dump_ctx->ctx, set, &args.iter);
+ rcu_read_unlock();
nla_nest_end(skb, nest);
nlmsg_end(skb, nlh);
return skb->len;
nla_put_failure:
+ rcu_read_unlock();
return -ENOSPC;
}
+static int nf_tables_dump_set_done(struct netlink_callback *cb)
+{
+ kfree(cb->data);
+ return 0;
+}
+
static int nf_tables_getsetelem(struct net *net, struct sock *nlsk,
struct sk_buff *skb, const struct nlmsghdr *nlh,
const struct nlattr * const nla[])
if (nlh->nlmsg_flags & NLM_F_DUMP) {
struct netlink_dump_control c = {
.dump = nf_tables_dump_set,
+ .done = nf_tables_dump_set_done,
};
+ struct nft_set_dump_ctx *dump_ctx;
+
+ dump_ctx = kmalloc(sizeof(*dump_ctx), GFP_KERNEL);
+ if (!dump_ctx)
+ return -ENOMEM;
+
+ dump_ctx->set = set;
+ dump_ctx->ctx = ctx;
+
+ c.data = dump_ctx;
return netlink_dump_start(nlsk, skb, nlh, &c);
}
return -EOPNOTSUPP;
{
struct nft_set_ext *ext = nft_set_elem_ext(set, elem);
- nft_data_uninit(nft_set_ext_key(ext), NFT_DATA_VALUE);
+ nft_data_release(nft_set_ext_key(ext), NFT_DATA_VALUE);
if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA))
- nft_data_uninit(nft_set_ext_data(ext), set->dtype);
+ nft_data_release(nft_set_ext_data(ext), set->dtype);
if (destroy_expr && nft_set_ext_exists(ext, NFT_SET_EXT_EXPR))
nf_tables_expr_destroy(NULL, nft_set_ext_expr(ext));
if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF))
}
EXPORT_SYMBOL_GPL(nft_set_elem_destroy);
+/* Only called from commit path, nft_set_elem_deactivate() already deals with
+ * the refcounting from the preparation phase.
+ */
+static void nf_tables_set_elem_destroy(const struct nft_set *set, void *elem)
+{
+ struct nft_set_ext *ext = nft_set_elem_ext(set, elem);
+
+ if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPR))
+ nf_tables_expr_destroy(NULL, nft_set_ext_expr(ext));
+ kfree(elem);
+}
+
static int nft_setelem_parse_flags(const struct nft_set *set,
const struct nlattr *attr, u32 *flags)
{
kfree(elem.priv);
err3:
if (nla[NFTA_SET_ELEM_DATA] != NULL)
- nft_data_uninit(&data, d2.type);
+ nft_data_release(&data, d2.type);
err2:
- nft_data_uninit(&elem.key.val, d1.type);
+ nft_data_release(&elem.key.val, d1.type);
err1:
return err;
}
return err;
}
+/**
+ * nft_data_hold - hold a nft_data item
+ *
+ * @data: struct nft_data to release
+ * @type: type of data
+ *
+ * Hold a nft_data item. NFT_DATA_VALUE types can be silently discarded,
+ * NFT_DATA_VERDICT bumps the reference to chains in case of NFT_JUMP and
+ * NFT_GOTO verdicts. This function must be called on active data objects
+ * from the second phase of the commit protocol.
+ */
+static void nft_data_hold(const struct nft_data *data, enum nft_data_types type)
+{
+ if (type == NFT_DATA_VERDICT) {
+ switch (data->verdict.code) {
+ case NFT_JUMP:
+ case NFT_GOTO:
+ data->verdict.chain->use++;
+ break;
+ }
+ }
+}
+
+static void nft_set_elem_activate(const struct net *net,
+ const struct nft_set *set,
+ struct nft_set_elem *elem)
+{
+ const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
+
+ if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA))
+ nft_data_hold(nft_set_ext_data(ext), set->dtype);
+ if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF))
+ (*nft_set_ext_obj(ext))->use++;
+}
+
+static void nft_set_elem_deactivate(const struct net *net,
+ const struct nft_set *set,
+ struct nft_set_elem *elem)
+{
+ const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
+
+ if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA))
+ nft_data_release(nft_set_ext_data(ext), set->dtype);
+ if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF))
+ (*nft_set_ext_obj(ext))->use--;
+}
+
static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set,
const struct nlattr *attr)
{
kfree(elem.priv);
elem.priv = priv;
+ nft_set_elem_deactivate(ctx->net, set, &elem);
+
nft_trans_elem(trans) = elem;
list_add_tail(&trans->list, &ctx->net->nft.commit_list);
return 0;
err3:
kfree(elem.priv);
err2:
- nft_data_uninit(&elem.key.val, desc.type);
+ nft_data_release(&elem.key.val, desc.type);
err1:
return err;
}
nft_set_destroy(nft_trans_set(trans));
break;
case NFT_MSG_DELSETELEM:
- nft_set_elem_destroy(nft_trans_elem_set(trans),
- nft_trans_elem(trans).priv, true);
+ nf_tables_set_elem_destroy(nft_trans_elem_set(trans),
+ nft_trans_elem(trans).priv);
break;
case NFT_MSG_DELOBJ:
nft_obj_destroy(nft_trans_obj(trans));
case NFT_MSG_DELSETELEM:
te = (struct nft_trans_elem *)trans->data;
+ nft_set_elem_activate(net, te->set, &te->elem);
te->set->ops->activate(net, te->set, &te->elem);
te->set->ndeact--;
EXPORT_SYMBOL_GPL(nft_data_init);
/**
- * nft_data_uninit - release a nft_data item
+ * nft_data_release - release a nft_data item
*
* @data: struct nft_data to release
* @type: type of data
* Release a nft_data item. NFT_DATA_VALUE types can be silently discarded,
* all others need to be released by calling this function.
*/
-void nft_data_uninit(const struct nft_data *data, enum nft_data_types type)
+void nft_data_release(const struct nft_data *data, enum nft_data_types type)
{
if (type < NFT_DATA_VERDICT)
return;
WARN_ON(1);
}
}
-EXPORT_SYMBOL_GPL(nft_data_uninit);
+EXPORT_SYMBOL_GPL(nft_data_release);
int nft_data_dump(struct sk_buff *skb, int attr, const struct nft_data *data,
enum nft_data_types type, unsigned int len)
tuple_set = true;
}
+ ret = -ENOENT;
list_for_each_entry_safe(nlcth, n, &nfnl_cthelper_list, list) {
cur = &nlcth->helper;
j++;
tuple.dst.protonum != cur->tuple.dst.protonum))
continue;
- found = true;
- nf_conntrack_helper_unregister(cur);
- kfree(cur->expect_policy);
+ if (refcount_dec_if_one(&cur->refcnt)) {
+ found = true;
+ nf_conntrack_helper_unregister(cur);
+ kfree(cur->expect_policy);
- list_del(&nlcth->list);
- kfree(nlcth);
+ list_del(&nlcth->list);
+ kfree(nlcth);
+ } else {
+ ret = -EBUSY;
+ }
}
/* Make sure we return success if we flush and there is no helpers */
- return (found || j == 0) ? 0 : -ENOENT;
+ return (found || j == 0) ? 0 : ret;
}
static const struct nla_policy nfnl_cthelper_policy[NFCTH_MAX+1] = {
tb[NFTA_BITWISE_MASK]);
if (err < 0)
return err;
- if (d1.len != priv->len)
- return -EINVAL;
+ if (d1.len != priv->len) {
+ err = -EINVAL;
+ goto err1;
+ }
err = nft_data_init(NULL, &priv->xor, sizeof(priv->xor), &d2,
tb[NFTA_BITWISE_XOR]);
if (err < 0)
- return err;
- if (d2.len != priv->len)
- return -EINVAL;
+ goto err1;
+ if (d2.len != priv->len) {
+ err = -EINVAL;
+ goto err2;
+ }
return 0;
+err2:
+ nft_data_release(&priv->xor, d2.type);
+err1:
+ nft_data_release(&priv->mask, d1.type);
+ return err;
}
static int nft_bitwise_dump(struct sk_buff *skb, const struct nft_expr *expr)
if (err < 0)
return ERR_PTR(err);
+ if (desc.type != NFT_DATA_VALUE) {
+ err = -EINVAL;
+ goto err1;
+ }
+
if (desc.len <= sizeof(u32) && op == NFT_CMP_EQ)
return &nft_cmp_fast_ops;
- else
- return &nft_cmp_ops;
+
+ return &nft_cmp_ops;
+err1:
+ nft_data_release(&data, desc.type);
+ return ERR_PTR(-EINVAL);
}
struct nft_expr_type nft_cmp_type __read_mostly = {
struct nft_ct_helper_obj *priv = nft_obj_data(obj);
if (priv->helper4)
- module_put(priv->helper4->me);
+ nf_conntrack_helper_put(priv->helper4);
if (priv->helper6)
- module_put(priv->helper6->me);
+ nf_conntrack_helper_put(priv->helper6);
}
static void nft_ct_helper_obj_eval(struct nft_object *obj,
return 0;
err1:
- nft_data_uninit(&priv->data, desc.type);
+ nft_data_release(&priv->data, desc.type);
return err;
}
const struct nft_expr *expr)
{
const struct nft_immediate_expr *priv = nft_expr_priv(expr);
- return nft_data_uninit(&priv->data, nft_dreg_to_type(priv->dreg));
+
+ return nft_data_release(&priv->data, nft_dreg_to_type(priv->dreg));
}
static int nft_immediate_dump(struct sk_buff *skb, const struct nft_expr *expr)
priv->len = desc_from.len;
return 0;
err2:
- nft_data_uninit(&priv->data_to, desc_to.type);
+ nft_data_release(&priv->data_to, desc_to.type);
err1:
- nft_data_uninit(&priv->data_from, desc_from.type);
+ nft_data_release(&priv->data_from, desc_from.type);
return err;
}
struct nft_set_elem elem;
int err;
- err = rhashtable_walk_init(&priv->ht, &hti, GFP_KERNEL);
+ err = rhashtable_walk_init(&priv->ht, &hti, GFP_ATOMIC);
iter->err = err;
if (err)
return;
else if (d > 0)
p = &parent->rb_right;
else {
- if (nft_set_elem_active(&rbe->ext, genmask)) {
- if (nft_rbtree_interval_end(rbe) &&
- !nft_rbtree_interval_end(new))
- p = &parent->rb_left;
- else if (!nft_rbtree_interval_end(rbe) &&
- nft_rbtree_interval_end(new))
- p = &parent->rb_right;
- else {
- *ext = &rbe->ext;
- return -EEXIST;
- }
+ if (nft_rbtree_interval_end(rbe) &&
+ !nft_rbtree_interval_end(new)) {
+ p = &parent->rb_left;
+ } else if (!nft_rbtree_interval_end(rbe) &&
+ nft_rbtree_interval_end(new)) {
+ p = &parent->rb_right;
+ } else if (nft_set_elem_active(&rbe->ext, genmask)) {
+ *ext = &rbe->ext;
+ return -EEXIST;
+ } else {
+ p = &parent->rb_left;
}
}
}
&U->u.user.revision, K->u.kernel.TYPE->revision)
int xt_data_to_user(void __user *dst, const void *src,
- int usersize, int size)
+ int usersize, int size, int aligned_size)
{
usersize = usersize ? : size;
if (copy_to_user(dst, src, usersize))
return -EFAULT;
- if (usersize != size && clear_user(dst + usersize, size - usersize))
+ if (usersize != aligned_size &&
+ clear_user(dst + usersize, aligned_size - usersize))
return -EFAULT;
return 0;
}
EXPORT_SYMBOL_GPL(xt_data_to_user);
-#define XT_DATA_TO_USER(U, K, TYPE, C_SIZE) \
+#define XT_DATA_TO_USER(U, K, TYPE) \
xt_data_to_user(U->data, K->data, \
K->u.kernel.TYPE->usersize, \
- C_SIZE ? : K->u.kernel.TYPE->TYPE##size)
+ K->u.kernel.TYPE->TYPE##size, \
+ XT_ALIGN(K->u.kernel.TYPE->TYPE##size))
int xt_match_to_user(const struct xt_entry_match *m,
struct xt_entry_match __user *u)
{
return XT_OBJ_TO_USER(u, m, match, 0) ||
- XT_DATA_TO_USER(u, m, match, 0);
+ XT_DATA_TO_USER(u, m, match);
}
EXPORT_SYMBOL_GPL(xt_match_to_user);
struct xt_entry_target __user *u)
{
return XT_OBJ_TO_USER(u, t, target, 0) ||
- XT_DATA_TO_USER(u, t, target, 0);
+ XT_DATA_TO_USER(u, t, target);
}
EXPORT_SYMBOL_GPL(xt_target_to_user);
}
EXPORT_SYMBOL_GPL(xt_compat_match_from_user);
+#define COMPAT_XT_DATA_TO_USER(U, K, TYPE, C_SIZE) \
+ xt_data_to_user(U->data, K->data, \
+ K->u.kernel.TYPE->usersize, \
+ C_SIZE, \
+ COMPAT_XT_ALIGN(C_SIZE))
+
int xt_compat_match_to_user(const struct xt_entry_match *m,
void __user **dstptr, unsigned int *size)
{
if (match->compat_to_user((void __user *)cm->data, m->data))
return -EFAULT;
} else {
- if (XT_DATA_TO_USER(cm, m, match, msize - sizeof(*cm)))
+ if (COMPAT_XT_DATA_TO_USER(cm, m, match, msize - sizeof(*cm)))
return -EFAULT;
}
if (target->compat_to_user((void __user *)ct->data, t->data))
return -EFAULT;
} else {
- if (XT_DATA_TO_USER(ct, t, target, tsize - sizeof(*ct)))
+ if (COMPAT_XT_DATA_TO_USER(ct, t, target, tsize - sizeof(*ct)))
return -EFAULT;
}
help = nf_ct_helper_ext_add(ct, helper, GFP_KERNEL);
if (help == NULL) {
- module_put(helper->me);
+ nf_conntrack_helper_put(helper);
return -ENOMEM;
}
err4:
help = nfct_help(ct);
if (help)
- module_put(help->helper->me);
+ nf_conntrack_helper_put(help->helper);
err3:
nf_ct_tmpl_free(ct);
err2:
if (ct) {
help = nfct_help(ct);
if (help)
- module_put(help->helper->me);
+ nf_conntrack_helper_put(help->helper);
nf_ct_netns_put(par->net, par->family);
#include <asm/cacheflush.h>
#include <linux/hash.h>
#include <linux/genetlink.h>
+#include <linux/net_namespace.h>
#include <net/net_namespace.h>
#include <net/sock.h>
goto out;
}
NETLINK_CB(p->skb2).nsid = peernet2id(sock_net(sk), p->net);
- NETLINK_CB(p->skb2).nsid_is_set = true;
+ if (NETLINK_CB(p->skb2).nsid != NETNSA_NSID_NOT_ASSIGNED)
+ NETLINK_CB(p->skb2).nsid_is_set = true;
val = netlink_broadcast_deliver(sk, p->skb2);
if (val < 0) {
netlink_overrun(sk);
help = nf_ct_helper_ext_add(info->ct, helper, GFP_KERNEL);
if (!help) {
- module_put(helper->me);
+ nf_conntrack_helper_put(helper);
return -ENOMEM;
}
static void __ovs_ct_free_action(struct ovs_conntrack_info *ct_info)
{
if (ct_info->helper)
- module_put(ct_info->helper->me);
+ nf_conntrack_helper_put(ct_info->helper);
if (ct_info->ct)
nf_ct_tmpl_free(ct_info->ct);
}
*arg = (unsigned long) head;
rcu_assign_pointer(tp->root, new);
- call_rcu(&head->rcu, mall_destroy_rcu);
return 0;
err_replace_hw_filter:
asoc->ctsn_ack_point = asoc->next_tsn - 1;
asoc->adv_peer_ack_point = asoc->ctsn_ack_point;
- if (!asoc->stream) {
+
+ if (sctp_state(asoc, COOKIE_WAIT)) {
+ sctp_stream_free(asoc->stream);
asoc->stream = new->stream;
new->stream = NULL;
}
struct sctp_association **app,
struct sctp_transport **tpp)
{
+ struct sctp_init_chunk *chunkhdr, _chunkhdr;
union sctp_addr saddr;
union sctp_addr daddr;
struct sctp_af *af;
struct sock *sk = NULL;
struct sctp_association *asoc;
struct sctp_transport *transport = NULL;
- struct sctp_init_chunk *chunkhdr;
__u32 vtag = ntohl(sctphdr->vtag);
- int len = skb->len - ((void *)sctphdr - (void *)skb->data);
*app = NULL; *tpp = NULL;
* discard the packet.
*/
if (vtag == 0) {
- chunkhdr = (void *)sctphdr + sizeof(struct sctphdr);
- if (len < sizeof(struct sctphdr) + sizeof(sctp_chunkhdr_t)
- + sizeof(__be32) ||
+ /* chunk header + first 4 octects of init header */
+ chunkhdr = skb_header_pointer(skb, skb_transport_offset(skb) +
+ sizeof(struct sctphdr),
+ sizeof(struct sctp_chunkhdr) +
+ sizeof(__be32), &_chunkhdr);
+ if (!chunkhdr ||
chunkhdr->chunk_hdr.type != SCTP_CID_INIT ||
- ntohl(chunkhdr->init_hdr.init_tag) != asoc->c.my_vtag) {
+ ntohl(chunkhdr->init_hdr.init_tag) != asoc->c.my_vtag)
goto out;
- }
+
} else if (vtag != asoc->c.peer_vtag) {
goto out;
}
newnp = inet6_sk(newsk);
memcpy(newnp, np, sizeof(struct ipv6_pinfo));
+ newnp->ipv6_mc_list = NULL;
+ newnp->ipv6_ac_list = NULL;
+ newnp->ipv6_fl_list = NULL;
rcu_read_lock();
opt = rcu_dereference(np->opt);
* stream sequence number shall be set to 0.
*/
- /* Allocate storage for the negotiated streams if it is not a temporary
- * association.
- */
- if (!asoc->temp) {
- if (sctp_stream_init(asoc, gfp))
- goto clean_up;
+ if (sctp_stream_init(asoc, gfp))
+ goto clean_up;
- if (sctp_assoc_set_id(asoc, gfp))
- goto clean_up;
- }
+ if (!asoc->temp && sctp_assoc_set_id(asoc, gfp))
+ goto clean_up;
/* ADDIP Section 4.1 ASCONF Chunk Procedures
*
}
}
+ /* Set temp so that it won't be added into hashtable */
+ new_asoc->temp = 1;
+
/* Compare the tie_tag in cookie with the verification tag of
* current association.
*/
The Linux implementation of the SMC-R solution is designed as
a separate socket family SMC.
+ Warning: SMC will expose all memory for remote reads and writes
+ once a connection is established. Don't enable this option except
+ for tightly controlled lab environment.
+
Select this option if you want to run SMC socket applications
config SMC_DIAG
memcpy(&cclc.lcl.mac, &link->smcibdev->mac[link->ibport - 1], ETH_ALEN);
hton24(cclc.qpn, link->roce_qp->qp_num);
cclc.rmb_rkey =
- htonl(conn->rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey);
+ htonl(conn->rmb_desc->rkey[SMC_SINGLE_LINK]);
cclc.conn_idx = 1; /* for now: 1 RMB = 1 RMBE */
cclc.rmbe_alert_token = htonl(conn->alert_token_local);
cclc.qp_mtu = min(link->path_mtu, link->peer_mtu);
memcpy(&aclc.lcl.mac, link->smcibdev->mac[link->ibport - 1], ETH_ALEN);
hton24(aclc.qpn, link->roce_qp->qp_num);
aclc.rmb_rkey =
- htonl(conn->rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey);
+ htonl(conn->rmb_desc->rkey[SMC_SINGLE_LINK]);
aclc.conn_idx = 1; /* as long as 1 RMB = 1 RMBE */
aclc.rmbe_alert_token = htonl(conn->alert_token_local);
aclc.qp_mtu = link->path_mtu;
rmb_desc = NULL;
continue; /* if mapping failed, try smaller one */
}
- rc = smc_ib_get_memory_region(lgr->lnk[SMC_SINGLE_LINK].roce_pd,
- IB_ACCESS_REMOTE_WRITE |
- IB_ACCESS_LOCAL_WRITE,
- &rmb_desc->mr_rx[SMC_SINGLE_LINK]);
- if (rc) {
- smc_ib_buf_unmap(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
- tmp_bufsize, rmb_desc,
- DMA_FROM_DEVICE);
- kfree(rmb_desc->cpu_addr);
- kfree(rmb_desc);
- rmb_desc = NULL;
- continue;
- }
+ rmb_desc->rkey[SMC_SINGLE_LINK] =
+ lgr->lnk[SMC_SINGLE_LINK].roce_pd->unsafe_global_rkey;
rmb_desc->used = 1;
write_lock_bh(&lgr->rmbs_lock);
list_add(&rmb_desc->list,
for (i = 0; i < SMC_RMBS_PER_LGR_MAX; i++) {
if ((lgr->rtokens[i][SMC_SINGLE_LINK].rkey == rkey) &&
+ (lgr->rtokens[i][SMC_SINGLE_LINK].dma_addr == dma_addr) &&
test_bit(i, lgr->rtokens_used_mask)) {
conn->rtoken_idx = i;
return 0;
u64 dma_addr[SMC_LINKS_PER_LGR_MAX];
/* mapped address of buffer */
void *cpu_addr; /* virtual address of buffer */
- struct ib_mr *mr_rx[SMC_LINKS_PER_LGR_MAX];
+ u32 rkey[SMC_LINKS_PER_LGR_MAX];
/* for rmb only:
* rkey provided to peer
*/
* identifier
*/
-int smc_ib_get_memory_region(struct ib_pd *pd, int access_flags,
- struct ib_mr **mr)
-{
- int rc;
-
- if (*mr)
- return 0; /* already done */
-
- /* obtain unique key -
- * next invocation of get_dma_mr returns a different key!
- */
- *mr = pd->device->get_dma_mr(pd, access_flags);
- rc = PTR_ERR_OR_ZERO(*mr);
- if (IS_ERR(*mr))
- *mr = NULL;
- return rc;
-}
-
static int smc_ib_modify_qp_init(struct smc_link *lnk)
{
struct ib_qp_attr qp_attr;
{
int rc;
- lnk->roce_pd = ib_alloc_pd(lnk->smcibdev->ibdev, 0);
+ lnk->roce_pd = ib_alloc_pd(lnk->smcibdev->ibdev,
+ IB_PD_UNSAFE_GLOBAL_RKEY);
rc = PTR_ERR_OR_ZERO(lnk->roce_pd);
if (IS_ERR(lnk->roce_pd))
lnk->roce_pd = NULL;
int smc_ib_create_protection_domain(struct smc_link *lnk);
void smc_ib_destroy_queue_pair(struct smc_link *lnk);
int smc_ib_create_queue_pair(struct smc_link *lnk);
-int smc_ib_get_memory_region(struct ib_pd *pd, int access_flags,
- struct ib_mr **mr);
int smc_ib_ready_link(struct smc_link *lnk);
int smc_ib_modify_qp_rts(struct smc_link *lnk);
int smc_ib_modify_qp_reset(struct smc_link *lnk);
for (i = 0; i < (reqs << 1); i++) {
rqst = kzalloc(sizeof(*rqst), GFP_KERNEL);
- if (!rqst) {
- pr_err("RPC: %s: Failed to create bc rpc_rqst\n",
- __func__);
+ if (!rqst)
goto out_free;
- }
+
dprintk("RPC: %s: new rqst %p\n", __func__, rqst);
rqst->rq_xprt = &r_xprt->rx_xprt;
case -ENETUNREACH:
case -EADDRINUSE:
case -ENOBUFS:
- /* retry with existing socket, after a delay */
+ /*
+ * xs_tcp_force_close() wakes tasks with -EIO.
+ * We need to wake them first to ensure the
+ * correct error code.
+ */
+ xprt_wake_pending_tasks(xprt, status);
xs_tcp_force_close(xprt);
goto out;
}
long timeout;
int err;
struct vsock_transport_send_notify_data send_data;
-
- DEFINE_WAIT(wait);
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
sk = sock->sk;
vsk = vsock_sk(sk);
if (err < 0)
goto out;
-
while (total_written < len) {
ssize_t written;
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+ add_wait_queue(sk_sleep(sk), &wait);
while (vsock_stream_has_space(vsk) == 0 &&
sk->sk_err == 0 &&
!(sk->sk_shutdown & SEND_SHUTDOWN) &&
/* Don't wait for non-blocking sockets. */
if (timeout == 0) {
err = -EAGAIN;
- finish_wait(sk_sleep(sk), &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
goto out_err;
}
err = transport->notify_send_pre_block(vsk, &send_data);
if (err < 0) {
- finish_wait(sk_sleep(sk), &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
goto out_err;
}
release_sock(sk);
- timeout = schedule_timeout(timeout);
+ timeout = wait_woken(&wait, TASK_INTERRUPTIBLE, timeout);
lock_sock(sk);
if (signal_pending(current)) {
err = sock_intr_errno(timeout);
- finish_wait(sk_sleep(sk), &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
goto out_err;
} else if (timeout == 0) {
err = -EAGAIN;
- finish_wait(sk_sleep(sk), &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
goto out_err;
}
-
- prepare_to_wait(sk_sleep(sk), &wait,
- TASK_INTERRUPTIBLE);
}
- finish_wait(sk_sleep(sk), &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
/* These checks occur both as part of and after the loop
* conditional since we need to check before and after
{
struct cfg80211_sched_scan_request *pos;
- ASSERT_RTNL();
+ WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held());
- list_for_each_entry(pos, &rdev->sched_scan_req_list, list) {
+ list_for_each_entry_rcu(pos, &rdev->sched_scan_req_list, list) {
if (pos->reqid == reqid)
return pos;
}
trace_cfg80211_sched_scan_results(wiphy, reqid);
/* ignore if we're not scanning */
- rtnl_lock();
+ rcu_read_lock();
request = cfg80211_find_sched_scan_req(rdev, reqid);
if (request) {
request->report_results = true;
queue_work(cfg80211_wq, &rdev->sched_scan_res_wk);
}
- rtnl_unlock();
+ rcu_read_unlock();
}
EXPORT_SYMBOL(cfg80211_sched_scan_results);
if (iftype == NL80211_IFTYPE_MESH_POINT)
skb_copy_bits(skb, hdrlen, &mesh_flags, 1);
+ mesh_flags &= MESH_FLAGS_AE;
+
switch (hdr->frame_control &
cpu_to_le16(IEEE80211_FCTL_TODS | IEEE80211_FCTL_FROMDS)) {
case cpu_to_le16(IEEE80211_FCTL_TODS):
iftype != NL80211_IFTYPE_STATION))
return -1;
if (iftype == NL80211_IFTYPE_MESH_POINT) {
- if (mesh_flags & MESH_FLAGS_AE_A4)
+ if (mesh_flags == MESH_FLAGS_AE_A4)
return -1;
- if (mesh_flags & MESH_FLAGS_AE_A5_A6) {
+ if (mesh_flags == MESH_FLAGS_AE_A5_A6) {
skb_copy_bits(skb, hdrlen +
offsetof(struct ieee80211s_hdr, eaddr1),
tmp.h_dest, 2 * ETH_ALEN);
ether_addr_equal(tmp.h_source, addr)))
return -1;
if (iftype == NL80211_IFTYPE_MESH_POINT) {
- if (mesh_flags & MESH_FLAGS_AE_A5_A6)
+ if (mesh_flags == MESH_FLAGS_AE_A5_A6)
return -1;
- if (mesh_flags & MESH_FLAGS_AE_A4)
+ if (mesh_flags == MESH_FLAGS_AE_A4)
skb_copy_bits(skb, hdrlen +
offsetof(struct ieee80211s_hdr, eaddr1),
tmp.h_source, ETH_ALEN);
static int __init x25_init(void)
{
- int rc = proto_register(&x25_proto, 0);
+ int rc;
- if (rc != 0)
+ rc = proto_register(&x25_proto, 0);
+ if (rc)
goto out;
rc = sock_register(&x25_family_ops);
- if (rc != 0)
+ if (rc)
goto out_proto;
dev_add_pack(&x25_packet_type);
rc = register_netdevice_notifier(&x25_dev_notifier);
- if (rc != 0)
+ if (rc)
goto out_sock;
- pr_info("Linux Version 0.2\n");
+ rc = x25_register_sysctl();
+ if (rc)
+ goto out_dev;
- x25_register_sysctl();
rc = x25_proc_init();
- if (rc != 0)
- goto out_dev;
+ if (rc)
+ goto out_sysctl;
+
+ pr_info("Linux Version 0.2\n");
+
out:
return rc;
+out_sysctl:
+ x25_unregister_sysctl();
out_dev:
unregister_netdevice_notifier(&x25_dev_notifier);
out_sock:
+ dev_remove_pack(&x25_packet_type);
sock_unregister(AF_X25);
out_proto:
proto_unregister(&x25_proto);
{ },
};
-void __init x25_register_sysctl(void)
+int __init x25_register_sysctl(void)
{
x25_table_header = register_net_sysctl(&init_net, "net/x25", x25_table);
+ if (!x25_table_header)
+ return -ENOMEM;
+ return 0;
}
void x25_unregister_sysctl(void)
static int xfrm_dev_down(struct net_device *dev)
{
- if (dev->hw_features & NETIF_F_HW_ESP)
+ if (dev->features & NETIF_F_HW_ESP)
xfrm_dev_state_flush(dev_net(dev), dev, true);
xfrm_garbage_collect(dev_net(dev));
goto out;
}
-#ifdef CONFIG_XFRM_SUB_POLICY
-static int xfrm_dst_alloc_copy(void **target, const void *src, int size)
-{
- if (!*target) {
- *target = kmalloc(size, GFP_ATOMIC);
- if (!*target)
- return -ENOMEM;
- }
-
- memcpy(*target, src, size);
- return 0;
-}
-#endif
-
-static int xfrm_dst_update_parent(struct dst_entry *dst,
- const struct xfrm_selector *sel)
-{
-#ifdef CONFIG_XFRM_SUB_POLICY
- struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
- return xfrm_dst_alloc_copy((void **)&(xdst->partner),
- sel, sizeof(*sel));
-#else
- return 0;
-#endif
-}
-
-static int xfrm_dst_update_origin(struct dst_entry *dst,
- const struct flowi *fl)
-{
-#ifdef CONFIG_XFRM_SUB_POLICY
- struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
- return xfrm_dst_alloc_copy((void **)&(xdst->origin), fl, sizeof(*fl));
-#else
- return 0;
-#endif
-}
-
static int xfrm_expand_policies(const struct flowi *fl, u16 family,
struct xfrm_policy **pols,
int *num_pols, int *num_xfrms)
xdst = (struct xfrm_dst *)dst;
xdst->num_xfrms = err;
- if (num_pols > 1)
- err = xfrm_dst_update_parent(dst, &pols[1]->selector);
- else
- err = xfrm_dst_update_origin(dst, fl);
- if (unlikely(err)) {
- dst_free(dst);
- XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLECHECKERROR);
- return ERR_PTR(err);
- }
-
xdst->num_pols = num_pols;
memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols);
xdst->policy_genid = atomic_read(&pols[0]->genid);
x->curlft.add_time = orig->curlft.add_time;
x->km.state = orig->km.state;
x->km.seq = orig->km.seq;
+ x->replay = orig->replay;
+ x->preplay = orig->preplay;
return x;
#
# ==========================================================================
+PHONY := __headers
+__headers:
+
+include scripts/Kbuild.include
+
+srcdir := $(srctree)/$(obj)
+subdirs := $(patsubst $(srcdir)/%/.,%,$(wildcard $(srcdir)/*/.))
+# caller may set destination dir (when installing to asm/)
+_dst := $(if $(dst),$(dst),$(obj))
+
+# Recursion
+__headers: $(subdirs)
+
+.PHONY: $(subdirs)
+$(subdirs):
+ $(Q)$(MAKE) $(hdr-inst)=$(obj)/$@ dst=$(_dst)/$@
+
+# Skip header install/check for include/uapi and arch/$(hdr-arch)/include/uapi.
+# We have only sub-directories there.
+skip-inst := $(if $(filter %/uapi,$(obj)),1)
+
+ifeq ($(skip-inst),)
+
# generated header directory
gen := $(if $(gen),$(gen),$(subst include/,include/generated/,$(obj)))
kbuild-file := $(srctree)/$(obj)/Kbuild
-include $(kbuild-file)
-# called may set destination dir (when installing to asm/)
-_dst := $(if $(dst),$(dst),$(obj))
-
old-kbuild-file := $(srctree)/$(subst uapi/,,$(obj))/Kbuild
ifneq ($(wildcard $(old-kbuild-file)),)
include $(old-kbuild-file)
endif
-include scripts/Kbuild.include
-
installdir := $(INSTALL_HDR_PATH)/$(subst uapi/,,$(_dst))
-srcdir := $(srctree)/$(obj)
gendir := $(objtree)/$(gen)
-subdirs := $(patsubst $(srcdir)/%/.,%,$(wildcard $(srcdir)/*/.))
header-files := $(notdir $(wildcard $(srcdir)/*.h))
header-files += $(notdir $(wildcard $(srcdir)/*.agh))
header-files := $(filter-out $(no-export-headers), $(header-files))
$(PERL) $< $(INSTALL_HDR_PATH)/include $(SRCARCH); \
touch $@
-PHONY += __headersinst __headerscheck
-
ifndef HDRCHECK
# Rules for installing headers
-__headersinst: $(subdirs) $(install-file)
+__headers: $(install-file)
@:
targets += $(install-file)
$(call if_changed,install)
else
-__headerscheck: $(subdirs) $(check-file)
+__headers: $(check-file)
@:
targets += $(check-file)
endif
-# Recursion
-.PHONY: $(subdirs)
-$(subdirs):
- $(Q)$(MAKE) $(hdr-inst)=$(obj)/$@ dst=$(_dst)/$@
-
targets := $(wildcard $(sort $(targets)))
cmd_files := $(wildcard \
$(foreach f,$(targets),$(dir $(f)).$(notdir $(f)).cmd))
include $(cmd_files)
endif
+endif # skip-inst
+
.PHONY: $(PHONY)
PHONY += FORCE
FORCE: ;
dtc_cpp_flags = -Wp,-MD,$(depfile).pre.tmp -nostdinc \
-I$(srctree)/arch/$(SRCARCH)/boot/dts \
- -I$(srctree)/arch/$(SRCARCH)/boot/dts/include \
+ -I$(srctree)/scripts/dtc/include-prefixes \
-I$(srctree)/drivers/of/testcase-data \
-undef -D__DTS__
while (size--)
reg = (reg << 32) | fdt32_to_cpu(*(cells++));
- snprintf(unit_addr, sizeof(unit_addr), "%lx", reg);
+ snprintf(unit_addr, sizeof(unit_addr), "%zx", reg);
if (!streq(unitname, unit_addr))
FAIL(c, dti, "Node %s simple-bus unit address format error, expected \"%s\"",
node->fullpath, unit_addr);
--- /dev/null
+../../../arch/arc/boot/dts
\ No newline at end of file
--- /dev/null
+../../../arch/arm/boot/dts
\ No newline at end of file
--- /dev/null
+../../../arch/arm64/boot/dts
\ No newline at end of file
--- /dev/null
+../../../arch/c6x/boot/dts
\ No newline at end of file
--- /dev/null
+../../../arch/cris/boot/dts
\ No newline at end of file
--- /dev/null
+../../../include/dt-bindings
\ No newline at end of file
--- /dev/null
+../../../arch/h8300/boot/dts
\ No newline at end of file
--- /dev/null
+../../../arch/metag/boot/dts
\ No newline at end of file
--- /dev/null
+../../../arch/microblaze/boot/dts
\ No newline at end of file
--- /dev/null
+../../../arch/mips/boot/dts
\ No newline at end of file
--- /dev/null
+../../../arch/nios2/boot/dts
\ No newline at end of file
--- /dev/null
+../../../arch/openrisc/boot/dts
\ No newline at end of file
--- /dev/null
+../../../arch/powerpc/boot/dts
\ No newline at end of file
--- /dev/null
+../../../arch/sh/boot/dts
\ No newline at end of file
--- /dev/null
+../../../arch/xtensa/boot/dts
\ No newline at end of file
super(LxDmesg, self).__init__("lx-dmesg", gdb.COMMAND_DATA)
def invoke(self, arg, from_tty):
- log_buf_addr = int(str(gdb.parse_and_eval("log_buf")).split()[0], 16)
- log_first_idx = int(gdb.parse_and_eval("log_first_idx"))
- log_next_idx = int(gdb.parse_and_eval("log_next_idx"))
- log_buf_len = int(gdb.parse_and_eval("log_buf_len"))
+ log_buf_addr = int(str(gdb.parse_and_eval(
+ "'printk.c'::log_buf")).split()[0], 16)
+ log_first_idx = int(gdb.parse_and_eval("'printk.c'::log_first_idx"))
+ log_next_idx = int(gdb.parse_and_eval("'printk.c'::log_next_idx"))
+ log_buf_len = int(gdb.parse_and_eval("'printk.c'::log_buf_len"))
inf = gdb.inferiors()[0]
start = log_buf_addr + log_first_idx
If you are unsure as to whether this is required, answer N.
+config KEYS_COMPAT
+ def_bool y
+ depends on COMPAT && KEYS
+
config PERSISTENT_KEYRINGS
bool "Enable register of persistent per-UID keyrings"
depends on KEYS
config KEY_DH_OPERATIONS
bool "Diffie-Hellman operations on retained keys"
depends on KEYS
- select MPILIB
select CRYPTO
select CRYPTO_HASH
+ select CRYPTO_DH
help
This option provides support for calculating Diffie-Hellman
public keys and shared secrets using values stored as keys
* 2 of the License, or (at your option) any later version.
*/
-#include <linux/mpi.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
+#include <linux/scatterlist.h>
#include <linux/crypto.h>
#include <crypto/hash.h>
+#include <crypto/kpp.h>
+#include <crypto/dh.h>
#include <keys/user-type.h>
#include "internal.h"
-/*
- * Public key or shared secret generation function [RFC2631 sec 2.1.1]
- *
- * ya = g^xa mod p;
- * or
- * ZZ = yb^xa mod p;
- *
- * where xa is the local private key, ya is the local public key, g is
- * the generator, p is the prime, yb is the remote public key, and ZZ
- * is the shared secret.
- *
- * Both are the same calculation, so g or yb are the "base" and ya or
- * ZZ are the "result".
- */
-static int do_dh(MPI result, MPI base, MPI xa, MPI p)
-{
- return mpi_powm(result, base, xa, p);
-}
-
-static ssize_t mpi_from_key(key_serial_t keyid, size_t maxlen, MPI *mpi)
+static ssize_t dh_data_from_key(key_serial_t keyid, void **data)
{
struct key *key;
key_ref_t key_ref;
status = key_validate(key);
if (status == 0) {
const struct user_key_payload *payload;
+ uint8_t *duplicate;
payload = user_key_payload_locked(key);
- if (maxlen == 0) {
- *mpi = NULL;
+ duplicate = kmemdup(payload->data, payload->datalen,
+ GFP_KERNEL);
+ if (duplicate) {
+ *data = duplicate;
ret = payload->datalen;
- } else if (payload->datalen <= maxlen) {
- *mpi = mpi_read_raw_data(payload->data,
- payload->datalen);
- if (*mpi)
- ret = payload->datalen;
} else {
- ret = -EINVAL;
+ ret = -ENOMEM;
}
}
up_read(&key->sem);
return ret;
}
+static void dh_free_data(struct dh *dh)
+{
+ kzfree(dh->key);
+ kzfree(dh->p);
+ kzfree(dh->g);
+}
+
+struct dh_completion {
+ struct completion completion;
+ int err;
+};
+
+static void dh_crypto_done(struct crypto_async_request *req, int err)
+{
+ struct dh_completion *compl = req->data;
+
+ if (err == -EINPROGRESS)
+ return;
+
+ compl->err = err;
+ complete(&compl->completion);
+}
+
struct kdf_sdesc {
struct shash_desc shash;
char ctx[];
struct crypto_shash *tfm;
struct kdf_sdesc *sdesc;
int size;
+ int err;
/* allocate synchronous hash */
tfm = crypto_alloc_shash(hashname, 0, 0);
return PTR_ERR(tfm);
}
+ err = -EINVAL;
+ if (crypto_shash_digestsize(tfm) == 0)
+ goto out_free_tfm;
+
+ err = -ENOMEM;
size = sizeof(struct shash_desc) + crypto_shash_descsize(tfm);
sdesc = kmalloc(size, GFP_KERNEL);
if (!sdesc)
- return -ENOMEM;
+ goto out_free_tfm;
sdesc->shash.tfm = tfm;
sdesc->shash.flags = 0x0;
*sdesc_ret = sdesc;
return 0;
+
+out_free_tfm:
+ crypto_free_shash(tfm);
+ return err;
}
static void kdf_dealloc(struct kdf_sdesc *sdesc)
kzfree(sdesc);
}
-/* convert 32 bit integer into its string representation */
-static inline void crypto_kw_cpu_to_be32(u32 val, u8 *buf)
-{
- __be32 *a = (__be32 *)buf;
-
- *a = cpu_to_be32(val);
-}
-
/*
* Implementation of the KDF in counter mode according to SP800-108 section 5.1
* as well as SP800-56A section 5.8.1 (Single-step KDF).
* 5.8.1.2).
*/
static int kdf_ctr(struct kdf_sdesc *sdesc, const u8 *src, unsigned int slen,
- u8 *dst, unsigned int dlen)
+ u8 *dst, unsigned int dlen, unsigned int zlen)
{
struct shash_desc *desc = &sdesc->shash;
unsigned int h = crypto_shash_digestsize(desc->tfm);
int err = 0;
u8 *dst_orig = dst;
- u32 i = 1;
- u8 iteration[sizeof(u32)];
+ __be32 counter = cpu_to_be32(1);
while (dlen) {
err = crypto_shash_init(desc);
if (err)
goto err;
- crypto_kw_cpu_to_be32(i, iteration);
- err = crypto_shash_update(desc, iteration, sizeof(u32));
+ err = crypto_shash_update(desc, (u8 *)&counter, sizeof(__be32));
if (err)
goto err;
+ if (zlen && h) {
+ u8 tmpbuffer[h];
+ size_t chunk = min_t(size_t, zlen, h);
+ memset(tmpbuffer, 0, chunk);
+
+ do {
+ err = crypto_shash_update(desc, tmpbuffer,
+ chunk);
+ if (err)
+ goto err;
+
+ zlen -= chunk;
+ chunk = min_t(size_t, zlen, h);
+ } while (zlen);
+ }
+
if (src && slen) {
err = crypto_shash_update(desc, src, slen);
if (err)
dlen -= h;
dst += h;
- i++;
+ counter = cpu_to_be32(be32_to_cpu(counter) + 1);
}
}
static int keyctl_dh_compute_kdf(struct kdf_sdesc *sdesc,
char __user *buffer, size_t buflen,
- uint8_t *kbuf, size_t kbuflen)
+ uint8_t *kbuf, size_t kbuflen, size_t lzero)
{
uint8_t *outbuf = NULL;
int ret;
goto err;
}
- ret = kdf_ctr(sdesc, kbuf, kbuflen, outbuf, buflen);
+ ret = kdf_ctr(sdesc, kbuf, kbuflen, outbuf, buflen, lzero);
if (ret)
goto err;
struct keyctl_kdf_params *kdfcopy)
{
long ret;
- MPI base, private, prime, result;
- unsigned nbytes;
+ ssize_t dlen;
+ int secretlen;
+ int outlen;
struct keyctl_dh_params pcopy;
- uint8_t *kbuf;
- ssize_t keylen;
- size_t resultlen;
+ struct dh dh_inputs;
+ struct scatterlist outsg;
+ struct dh_completion compl;
+ struct crypto_kpp *tfm;
+ struct kpp_request *req;
+ uint8_t *secret;
+ uint8_t *outbuf;
struct kdf_sdesc *sdesc = NULL;
if (!params || (!buffer && buflen)) {
ret = -EINVAL;
- goto out;
+ goto out1;
}
if (copy_from_user(&pcopy, params, sizeof(pcopy)) != 0) {
ret = -EFAULT;
- goto out;
+ goto out1;
}
if (kdfcopy) {
if (buflen > KEYCTL_KDF_MAX_OUTPUT_LEN ||
kdfcopy->otherinfolen > KEYCTL_KDF_MAX_OI_LEN) {
ret = -EMSGSIZE;
- goto out;
+ goto out1;
}
/* get KDF name string */
hashname = strndup_user(kdfcopy->hashname, CRYPTO_MAX_ALG_NAME);
if (IS_ERR(hashname)) {
ret = PTR_ERR(hashname);
- goto out;
+ goto out1;
}
/* allocate KDF from the kernel crypto API */
ret = kdf_alloc(&sdesc, hashname);
kfree(hashname);
if (ret)
- goto out;
+ goto out1;
}
- /*
- * If the caller requests postprocessing with a KDF, allow an
- * arbitrary output buffer size since the KDF ensures proper truncation.
- */
- keylen = mpi_from_key(pcopy.prime, kdfcopy ? SIZE_MAX : buflen, &prime);
- if (keylen < 0 || !prime) {
- /* buflen == 0 may be used to query the required buffer size,
- * which is the prime key length.
- */
- ret = keylen;
- goto out;
+ memset(&dh_inputs, 0, sizeof(dh_inputs));
+
+ dlen = dh_data_from_key(pcopy.prime, &dh_inputs.p);
+ if (dlen < 0) {
+ ret = dlen;
+ goto out1;
+ }
+ dh_inputs.p_size = dlen;
+
+ dlen = dh_data_from_key(pcopy.base, &dh_inputs.g);
+ if (dlen < 0) {
+ ret = dlen;
+ goto out2;
}
+ dh_inputs.g_size = dlen;
- /* The result is never longer than the prime */
- resultlen = keylen;
+ dlen = dh_data_from_key(pcopy.private, &dh_inputs.key);
+ if (dlen < 0) {
+ ret = dlen;
+ goto out2;
+ }
+ dh_inputs.key_size = dlen;
- keylen = mpi_from_key(pcopy.base, SIZE_MAX, &base);
- if (keylen < 0 || !base) {
- ret = keylen;
- goto error1;
+ secretlen = crypto_dh_key_len(&dh_inputs);
+ secret = kmalloc(secretlen, GFP_KERNEL);
+ if (!secret) {
+ ret = -ENOMEM;
+ goto out2;
}
+ ret = crypto_dh_encode_key(secret, secretlen, &dh_inputs);
+ if (ret)
+ goto out3;
- keylen = mpi_from_key(pcopy.private, SIZE_MAX, &private);
- if (keylen < 0 || !private) {
- ret = keylen;
- goto error2;
+ tfm = crypto_alloc_kpp("dh", CRYPTO_ALG_TYPE_KPP, 0);
+ if (IS_ERR(tfm)) {
+ ret = PTR_ERR(tfm);
+ goto out3;
+ }
+
+ ret = crypto_kpp_set_secret(tfm, secret, secretlen);
+ if (ret)
+ goto out4;
+
+ outlen = crypto_kpp_maxsize(tfm);
+
+ if (!kdfcopy) {
+ /*
+ * When not using a KDF, buflen 0 is used to read the
+ * required buffer length
+ */
+ if (buflen == 0) {
+ ret = outlen;
+ goto out4;
+ } else if (outlen > buflen) {
+ ret = -EOVERFLOW;
+ goto out4;
+ }
}
- result = mpi_alloc(0);
- if (!result) {
+ outbuf = kzalloc(kdfcopy ? (outlen + kdfcopy->otherinfolen) : outlen,
+ GFP_KERNEL);
+ if (!outbuf) {
ret = -ENOMEM;
- goto error3;
+ goto out4;
}
- /* allocate space for DH shared secret and SP800-56A otherinfo */
- kbuf = kmalloc(kdfcopy ? (resultlen + kdfcopy->otherinfolen) : resultlen,
- GFP_KERNEL);
- if (!kbuf) {
+ sg_init_one(&outsg, outbuf, outlen);
+
+ req = kpp_request_alloc(tfm, GFP_KERNEL);
+ if (!req) {
ret = -ENOMEM;
- goto error4;
+ goto out5;
}
+ kpp_request_set_input(req, NULL, 0);
+ kpp_request_set_output(req, &outsg, outlen);
+ init_completion(&compl.completion);
+ kpp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG |
+ CRYPTO_TFM_REQ_MAY_SLEEP,
+ dh_crypto_done, &compl);
+
/*
- * Concatenate SP800-56A otherinfo past DH shared secret -- the
- * input to the KDF is (DH shared secret || otherinfo)
+ * For DH, generate_public_key and generate_shared_secret are
+ * the same calculation
*/
- if (kdfcopy && kdfcopy->otherinfo &&
- copy_from_user(kbuf + resultlen, kdfcopy->otherinfo,
- kdfcopy->otherinfolen) != 0) {
- ret = -EFAULT;
- goto error5;
+ ret = crypto_kpp_generate_public_key(req);
+ if (ret == -EINPROGRESS) {
+ wait_for_completion(&compl.completion);
+ ret = compl.err;
+ if (ret)
+ goto out6;
}
- ret = do_dh(result, base, private, prime);
- if (ret)
- goto error5;
-
- ret = mpi_read_buffer(result, kbuf, resultlen, &nbytes, NULL);
- if (ret != 0)
- goto error5;
-
if (kdfcopy) {
- ret = keyctl_dh_compute_kdf(sdesc, buffer, buflen, kbuf,
- resultlen + kdfcopy->otherinfolen);
- } else {
- ret = nbytes;
- if (copy_to_user(buffer, kbuf, nbytes) != 0)
+ /*
+ * Concatenate SP800-56A otherinfo past DH shared secret -- the
+ * input to the KDF is (DH shared secret || otherinfo)
+ */
+ if (copy_from_user(outbuf + req->dst_len, kdfcopy->otherinfo,
+ kdfcopy->otherinfolen) != 0) {
ret = -EFAULT;
+ goto out6;
+ }
+
+ ret = keyctl_dh_compute_kdf(sdesc, buffer, buflen, outbuf,
+ req->dst_len + kdfcopy->otherinfolen,
+ outlen - req->dst_len);
+ } else if (copy_to_user(buffer, outbuf, req->dst_len) == 0) {
+ ret = req->dst_len;
+ } else {
+ ret = -EFAULT;
}
-error5:
- kzfree(kbuf);
-error4:
- mpi_free(result);
-error3:
- mpi_free(private);
-error2:
- mpi_free(base);
-error1:
- mpi_free(prime);
-out:
+out6:
+ kpp_request_free(req);
+out5:
+ kzfree(outbuf);
+out4:
+ crypto_free_kpp(tfm);
+out3:
+ kzfree(secret);
+out2:
+ dh_free_data(&dh_inputs);
+out1:
kdf_dealloc(sdesc);
return ret;
}
#include <linux/scatterlist.h>
#include <linux/ctype.h>
#include <crypto/aes.h>
+#include <crypto/algapi.h>
#include <crypto/hash.h>
#include <crypto/sha.h>
#include <crypto/skcipher.h>
#define MAX_DATA_SIZE 4096
#define MIN_DATA_SIZE 20
-struct sdesc {
- struct shash_desc shash;
- char ctx[];
-};
-
-static struct crypto_shash *hashalg;
-static struct crypto_shash *hmacalg;
+static struct crypto_shash *hash_tfm;
enum {
Opt_err = -1, Opt_new, Opt_load, Opt_update
*/
static int valid_master_desc(const char *new_desc, const char *orig_desc)
{
- if (!memcmp(new_desc, KEY_TRUSTED_PREFIX, KEY_TRUSTED_PREFIX_LEN)) {
- if (strlen(new_desc) == KEY_TRUSTED_PREFIX_LEN)
- goto out;
- if (orig_desc)
- if (memcmp(new_desc, orig_desc, KEY_TRUSTED_PREFIX_LEN))
- goto out;
- } else if (!memcmp(new_desc, KEY_USER_PREFIX, KEY_USER_PREFIX_LEN)) {
- if (strlen(new_desc) == KEY_USER_PREFIX_LEN)
- goto out;
- if (orig_desc)
- if (memcmp(new_desc, orig_desc, KEY_USER_PREFIX_LEN))
- goto out;
- } else
- goto out;
+ int prefix_len;
+
+ if (!strncmp(new_desc, KEY_TRUSTED_PREFIX, KEY_TRUSTED_PREFIX_LEN))
+ prefix_len = KEY_TRUSTED_PREFIX_LEN;
+ else if (!strncmp(new_desc, KEY_USER_PREFIX, KEY_USER_PREFIX_LEN))
+ prefix_len = KEY_USER_PREFIX_LEN;
+ else
+ return -EINVAL;
+
+ if (!new_desc[prefix_len])
+ return -EINVAL;
+
+ if (orig_desc && strncmp(new_desc, orig_desc, prefix_len))
+ return -EINVAL;
+
return 0;
-out:
- return -EINVAL;
}
/*
return ukey;
}
-static struct sdesc *alloc_sdesc(struct crypto_shash *alg)
-{
- struct sdesc *sdesc;
- int size;
-
- size = sizeof(struct shash_desc) + crypto_shash_descsize(alg);
- sdesc = kmalloc(size, GFP_KERNEL);
- if (!sdesc)
- return ERR_PTR(-ENOMEM);
- sdesc->shash.tfm = alg;
- sdesc->shash.flags = 0x0;
- return sdesc;
-}
-
-static int calc_hmac(u8 *digest, const u8 *key, unsigned int keylen,
+static int calc_hash(struct crypto_shash *tfm, u8 *digest,
const u8 *buf, unsigned int buflen)
{
- struct sdesc *sdesc;
- int ret;
+ SHASH_DESC_ON_STACK(desc, tfm);
+ int err;
- sdesc = alloc_sdesc(hmacalg);
- if (IS_ERR(sdesc)) {
- pr_info("encrypted_key: can't alloc %s\n", hmac_alg);
- return PTR_ERR(sdesc);
- }
+ desc->tfm = tfm;
+ desc->flags = 0;
- ret = crypto_shash_setkey(hmacalg, key, keylen);
- if (!ret)
- ret = crypto_shash_digest(&sdesc->shash, buf, buflen, digest);
- kfree(sdesc);
- return ret;
+ err = crypto_shash_digest(desc, buf, buflen, digest);
+ shash_desc_zero(desc);
+ return err;
}
-static int calc_hash(u8 *digest, const u8 *buf, unsigned int buflen)
+static int calc_hmac(u8 *digest, const u8 *key, unsigned int keylen,
+ const u8 *buf, unsigned int buflen)
{
- struct sdesc *sdesc;
- int ret;
+ struct crypto_shash *tfm;
+ int err;
- sdesc = alloc_sdesc(hashalg);
- if (IS_ERR(sdesc)) {
- pr_info("encrypted_key: can't alloc %s\n", hash_alg);
- return PTR_ERR(sdesc);
+ tfm = crypto_alloc_shash(hmac_alg, 0, CRYPTO_ALG_ASYNC);
+ if (IS_ERR(tfm)) {
+ pr_err("encrypted_key: can't alloc %s transform: %ld\n",
+ hmac_alg, PTR_ERR(tfm));
+ return PTR_ERR(tfm);
}
- ret = crypto_shash_digest(&sdesc->shash, buf, buflen, digest);
- kfree(sdesc);
- return ret;
+ err = crypto_shash_setkey(tfm, key, keylen);
+ if (!err)
+ err = calc_hash(tfm, digest, buf, buflen);
+ crypto_free_shash(tfm);
+ return err;
}
enum derived_key_type { ENC_KEY, AUTH_KEY };
derived_buf_len = HASH_SIZE;
derived_buf = kzalloc(derived_buf_len, GFP_KERNEL);
- if (!derived_buf) {
- pr_err("encrypted_key: out of memory\n");
+ if (!derived_buf)
return -ENOMEM;
- }
+
if (key_type)
strcpy(derived_buf, "AUTH_KEY");
else
memcpy(derived_buf + strlen(derived_buf) + 1, master_key,
master_keylen);
- ret = calc_hash(derived_key, derived_buf, derived_buf_len);
- kfree(derived_buf);
+ ret = calc_hash(hash_tfm, derived_key, derived_buf, derived_buf_len);
+ kzfree(derived_buf);
return ret;
}
struct skcipher_request *req;
unsigned int encrypted_datalen;
u8 iv[AES_BLOCK_SIZE];
- unsigned int padlen;
- char pad[16];
int ret;
encrypted_datalen = roundup(epayload->decrypted_datalen, blksize);
- padlen = encrypted_datalen - epayload->decrypted_datalen;
req = init_skcipher_req(derived_key, derived_keylen);
ret = PTR_ERR(req);
goto out;
dump_decrypted_data(epayload);
- memset(pad, 0, sizeof pad);
sg_init_table(sg_in, 2);
sg_set_buf(&sg_in[0], epayload->decrypted_data,
epayload->decrypted_datalen);
- sg_set_buf(&sg_in[1], pad, padlen);
+ sg_set_page(&sg_in[1], ZERO_PAGE(0), AES_BLOCK_SIZE, 0);
sg_init_table(sg_out, 1);
sg_set_buf(sg_out, epayload->encrypted_data, encrypted_datalen);
if (!ret)
dump_hmac(NULL, digest, HASH_SIZE);
out:
+ memzero_explicit(derived_key, sizeof(derived_key));
return ret;
}
ret = calc_hmac(digest, derived_key, sizeof derived_key, p, len);
if (ret < 0)
goto out;
- ret = memcmp(digest, epayload->format + epayload->datablob_len,
- sizeof digest);
+ ret = crypto_memneq(digest, epayload->format + epayload->datablob_len,
+ sizeof(digest));
if (ret) {
ret = -EINVAL;
dump_hmac("datablob",
dump_hmac("calc", digest, HASH_SIZE);
}
out:
+ memzero_explicit(derived_key, sizeof(derived_key));
return ret;
}
struct skcipher_request *req;
unsigned int encrypted_datalen;
u8 iv[AES_BLOCK_SIZE];
- char pad[16];
+ u8 *pad;
int ret;
+ /* Throwaway buffer to hold the unused zero padding at the end */
+ pad = kmalloc(AES_BLOCK_SIZE, GFP_KERNEL);
+ if (!pad)
+ return -ENOMEM;
+
encrypted_datalen = roundup(epayload->decrypted_datalen, blksize);
req = init_skcipher_req(derived_key, derived_keylen);
ret = PTR_ERR(req);
goto out;
dump_encrypted_data(epayload, encrypted_datalen);
- memset(pad, 0, sizeof pad);
sg_init_table(sg_in, 1);
sg_init_table(sg_out, 2);
sg_set_buf(sg_in, epayload->encrypted_data, encrypted_datalen);
sg_set_buf(&sg_out[0], epayload->decrypted_data,
epayload->decrypted_datalen);
- sg_set_buf(&sg_out[1], pad, sizeof pad);
+ sg_set_buf(&sg_out[1], pad, AES_BLOCK_SIZE);
memcpy(iv, epayload->iv, sizeof(iv));
skcipher_request_set_crypt(req, sg_in, sg_out, encrypted_datalen, iv);
goto out;
dump_decrypted_data(epayload);
out:
+ kfree(pad);
return ret;
}
out:
up_read(&mkey->sem);
key_put(mkey);
+ memzero_explicit(derived_key, sizeof(derived_key));
return ret;
}
ret = encrypted_init(epayload, key->description, format, master_desc,
decrypted_datalen, hex_encoded_iv);
if (ret < 0) {
- kfree(epayload);
+ kzfree(epayload);
goto out;
}
rcu_assign_keypointer(key, epayload);
out:
- kfree(datablob);
+ kzfree(datablob);
return ret;
}
struct encrypted_key_payload *epayload;
epayload = container_of(rcu, struct encrypted_key_payload, rcu);
- memset(epayload->decrypted_data, 0, epayload->decrypted_datalen);
- kfree(epayload);
+ kzfree(epayload);
}
/*
rcu_assign_keypointer(key, new_epayload);
call_rcu(&epayload->rcu, encrypted_rcu_free);
out:
- kfree(buf);
+ kzfree(buf);
return ret;
}
up_read(&mkey->sem);
key_put(mkey);
+ memzero_explicit(derived_key, sizeof(derived_key));
if (copy_to_user(buffer, ascii_buf, asciiblob_len) != 0)
ret = -EFAULT;
- kfree(ascii_buf);
+ kzfree(ascii_buf);
return asciiblob_len;
out:
up_read(&mkey->sem);
key_put(mkey);
+ memzero_explicit(derived_key, sizeof(derived_key));
return ret;
}
/*
- * encrypted_destroy - before freeing the key, clear the decrypted data
- *
- * Before freeing the key, clear the memory containing the decrypted
- * key data.
+ * encrypted_destroy - clear and free the key's payload
*/
static void encrypted_destroy(struct key *key)
{
- struct encrypted_key_payload *epayload = key->payload.data[0];
-
- if (!epayload)
- return;
-
- memzero_explicit(epayload->decrypted_data, epayload->decrypted_datalen);
- kfree(key->payload.data[0]);
+ kzfree(key->payload.data[0]);
}
struct key_type key_type_encrypted = {
};
EXPORT_SYMBOL_GPL(key_type_encrypted);
-static void encrypted_shash_release(void)
-{
- if (hashalg)
- crypto_free_shash(hashalg);
- if (hmacalg)
- crypto_free_shash(hmacalg);
-}
-
-static int __init encrypted_shash_alloc(void)
+static int __init init_encrypted(void)
{
int ret;
- hmacalg = crypto_alloc_shash(hmac_alg, 0, CRYPTO_ALG_ASYNC);
- if (IS_ERR(hmacalg)) {
- pr_info("encrypted_key: could not allocate crypto %s\n",
- hmac_alg);
- return PTR_ERR(hmacalg);
- }
-
- hashalg = crypto_alloc_shash(hash_alg, 0, CRYPTO_ALG_ASYNC);
- if (IS_ERR(hashalg)) {
- pr_info("encrypted_key: could not allocate crypto %s\n",
- hash_alg);
- ret = PTR_ERR(hashalg);
- goto hashalg_fail;
+ hash_tfm = crypto_alloc_shash(hash_alg, 0, CRYPTO_ALG_ASYNC);
+ if (IS_ERR(hash_tfm)) {
+ pr_err("encrypted_key: can't allocate %s transform: %ld\n",
+ hash_alg, PTR_ERR(hash_tfm));
+ return PTR_ERR(hash_tfm);
}
- return 0;
-
-hashalg_fail:
- crypto_free_shash(hmacalg);
- return ret;
-}
-
-static int __init init_encrypted(void)
-{
- int ret;
-
- ret = encrypted_shash_alloc();
- if (ret < 0)
- return ret;
ret = aes_get_sizes();
if (ret < 0)
goto out;
goto out;
return 0;
out:
- encrypted_shash_release();
+ crypto_free_shash(hash_tfm);
return ret;
}
static void __exit cleanup_encrypted(void)
{
- encrypted_shash_release();
+ crypto_free_shash(hash_tfm);
unregister_key_type(&key_type_encrypted);
}
kfree(key->description);
-#ifdef KEY_DEBUGGING
- key->magic = KEY_DEBUG_MAGIC_X;
-#endif
+ memzero_explicit(key, sizeof(*key));
kmem_cache_free(key_jar, key);
}
}
goto error;
found:
- /* pretend it doesn't exist if it is awaiting deletion */
- if (refcount_read(&key->usage) == 0)
- goto not_found;
-
- /* this races with key_put(), but that doesn't matter since key_put()
- * doesn't actually change the key
+ /* A key is allowed to be looked up only if someone still owns a
+ * reference to it - otherwise it's awaiting the gc.
*/
- __key_get(key);
+ if (!refcount_inc_not_zero(&key->usage))
+ goto not_found;
error:
spin_unlock(&key_serial_lock);
/* the key must be writable */
ret = key_permission(key_ref, KEY_NEED_WRITE);
if (ret < 0)
- goto error;
+ return ret;
/* attempt to update it if supported */
- ret = -EOPNOTSUPP;
if (!key->type->update)
- goto error;
+ return -EOPNOTSUPP;
memset(&prep, 0, sizeof(prep));
prep.data = payload;
/* pull the payload in if one was supplied */
payload = NULL;
- if (_payload) {
+ if (plen) {
ret = -ENOMEM;
payload = kvmalloc(plen, GFP_KERNEL);
if (!payload)
key_ref_put(keyring_ref);
error3:
- kvfree(payload);
+ if (payload) {
+ memzero_explicit(payload, plen);
+ kvfree(payload);
+ }
error2:
kfree(description);
error:
/* pull the payload in if one was supplied */
payload = NULL;
- if (_payload) {
+ if (plen) {
ret = -ENOMEM;
payload = kmalloc(plen, GFP_KERNEL);
if (!payload)
key_ref_put(key_ref);
error2:
- kfree(payload);
+ kzfree(payload);
error:
return ret;
}
keyctl_change_reqkey_auth(NULL);
error2:
- kvfree(payload);
+ if (payload) {
+ memzero_explicit(payload, plen);
+ kvfree(payload);
+ }
error:
return ret;
}
* Non-keyrings avoid the leftmost branch of the root entirely (root
* slots 1-15).
*/
- ptr = ACCESS_ONCE(keyring->keys.root);
+ ptr = READ_ONCE(keyring->keys.root);
if (!ptr)
goto not_this_keyring;
if ((shortcut->index_key[0] & ASSOC_ARRAY_FAN_MASK) != 0)
goto not_this_keyring;
- ptr = ACCESS_ONCE(shortcut->next_node);
+ ptr = READ_ONCE(shortcut->next_node);
node = assoc_array_ptr_to_node(ptr);
goto begin_node;
}
if (assoc_array_ptr_is_shortcut(ptr)) {
shortcut = assoc_array_ptr_to_shortcut(ptr);
smp_read_barrier_depends();
- ptr = ACCESS_ONCE(shortcut->next_node);
+ ptr = READ_ONCE(shortcut->next_node);
BUG_ON(!assoc_array_ptr_is_node(ptr));
}
node = assoc_array_ptr_to_node(ptr);
ascend_to_node:
/* Go through the slots in a node */
for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) {
- ptr = ACCESS_ONCE(node->slots[slot]);
+ ptr = READ_ONCE(node->slots[slot]);
if (assoc_array_ptr_is_meta(ptr) && node->back_pointer)
goto descend_to_node;
/* We've dealt with all the slots in the current node, so now we need
* to ascend to the parent and continue processing there.
*/
- ptr = ACCESS_ONCE(node->back_pointer);
+ ptr = READ_ONCE(node->back_pointer);
slot = node->parent_slot;
if (ptr && assoc_array_ptr_is_shortcut(ptr)) {
shortcut = assoc_array_ptr_to_shortcut(ptr);
smp_read_barrier_depends();
- ptr = ACCESS_ONCE(shortcut->back_pointer);
+ ptr = READ_ONCE(shortcut->back_pointer);
slot = shortcut->parent_slot;
}
if (!ptr)
ret = PTR_ERR(keyring);
goto error2;
} else if (keyring == new->session_keyring) {
- key_put(keyring);
ret = 0;
- goto error2;
+ goto error3;
}
/* we've got a keyring - now to install it */
ret = install_session_keyring_to_cred(new, keyring);
if (ret < 0)
- goto error2;
+ goto error3;
commit_creds(new);
mutex_unlock(&key_session_mutex);
okay:
return ret;
+error3:
+ key_put(keyring);
error2:
mutex_unlock(&key_session_mutex);
error:
}
ret = crypto_shash_digest(&sdesc->shash, data, datalen, digest);
- kfree(sdesc);
+ kzfree(sdesc);
return ret;
}
if (!ret)
ret = crypto_shash_final(&sdesc->shash, digest);
out:
- kfree(sdesc);
+ kzfree(sdesc);
return ret;
}
paramdigest, TPM_NONCE_SIZE, h1,
TPM_NONCE_SIZE, h2, 1, &c, 0, 0);
out:
- kfree(sdesc);
+ kzfree(sdesc);
return ret;
}
if (memcmp(testhmac, authdata, SHA1_DIGEST_SIZE))
ret = -EINVAL;
out:
- kfree(sdesc);
+ kzfree(sdesc);
return ret;
}
if (memcmp(testhmac2, authdata2, SHA1_DIGEST_SIZE))
ret = -EINVAL;
out:
- kfree(sdesc);
+ kzfree(sdesc);
return ret;
}
*bloblen = storedsize;
}
out:
- kfree(td);
+ kzfree(td);
return ret;
}
if (ret < 0)
pr_info("trusted_key: srkseal failed (%d)\n", ret);
- kfree(tb);
+ kzfree(tb);
return ret;
}
/* pull migratable flag out of sealed key */
p->migratable = p->key[--p->key_len];
- kfree(tb);
+ kzfree(tb);
return ret;
}
if (!ret && options->pcrlock)
ret = pcrlock(options->pcrlock);
out:
- kfree(datablob);
- kfree(options);
+ kzfree(datablob);
+ kzfree(options);
if (!ret)
rcu_assign_keypointer(key, payload);
else
- kfree(payload);
+ kzfree(payload);
return ret;
}
struct trusted_key_payload *p;
p = container_of(rcu, struct trusted_key_payload, rcu);
- memset(p->key, 0, p->key_len);
- kfree(p);
+ kzfree(p);
}
/*
ret = datablob_parse(datablob, new_p, new_o);
if (ret != Opt_update) {
ret = -EINVAL;
- kfree(new_p);
+ kzfree(new_p);
goto out;
}
if (!new_o->keyhandle) {
ret = -EINVAL;
- kfree(new_p);
+ kzfree(new_p);
goto out;
}
ret = key_seal(new_p, new_o);
if (ret < 0) {
pr_info("trusted_key: key_seal failed (%d)\n", ret);
- kfree(new_p);
+ kzfree(new_p);
goto out;
}
if (new_o->pcrlock) {
ret = pcrlock(new_o->pcrlock);
if (ret < 0) {
pr_info("trusted_key: pcrlock failed (%d)\n", ret);
- kfree(new_p);
+ kzfree(new_p);
goto out;
}
}
rcu_assign_keypointer(key, new_p);
call_rcu(&p->rcu, trusted_rcu_free);
out:
- kfree(datablob);
- kfree(new_o);
+ kzfree(datablob);
+ kzfree(new_o);
return ret;
}
for (i = 0; i < p->blob_len; i++)
bufp = hex_byte_pack(bufp, p->blob[i]);
if ((copy_to_user(buffer, ascii_buf, 2 * p->blob_len)) != 0) {
- kfree(ascii_buf);
+ kzfree(ascii_buf);
return -EFAULT;
}
- kfree(ascii_buf);
+ kzfree(ascii_buf);
return 2 * p->blob_len;
}
/*
- * trusted_destroy - before freeing the key, clear the decrypted data
+ * trusted_destroy - clear and free the key's payload
*/
static void trusted_destroy(struct key *key)
{
- struct trusted_key_payload *p = key->payload.data[0];
-
- if (!p)
- return;
- memset(p->key, 0, p->key_len);
- kfree(key->payload.data[0]);
+ kzfree(key->payload.data[0]);
}
struct key_type key_type_trusted = {
*/
void user_free_preparse(struct key_preparsed_payload *prep)
{
- kfree(prep->payload.data[0]);
+ kzfree(prep->payload.data[0]);
}
EXPORT_SYMBOL_GPL(user_free_preparse);
+static void user_free_payload_rcu(struct rcu_head *head)
+{
+ struct user_key_payload *payload;
+
+ payload = container_of(head, struct user_key_payload, rcu);
+ kzfree(payload);
+}
+
/*
* update a user defined key
* - the key's semaphore is write-locked
prep->payload.data[0] = NULL;
if (zap)
- kfree_rcu(zap, rcu);
+ call_rcu(&zap->rcu, user_free_payload_rcu);
return ret;
}
EXPORT_SYMBOL_GPL(user_update);
if (upayload) {
rcu_assign_keypointer(key, NULL);
- kfree_rcu(upayload, rcu);
+ call_rcu(&upayload->rcu, user_free_payload_rcu);
}
}
{
struct user_key_payload *upayload = key->payload.data[0];
- kfree(upayload);
+ kzfree(upayload);
}
EXPORT_SYMBOL_GPL(user_destroy);
if (err < 0)
goto __err;
+ tu->qhead = tu->qtail = tu->qused = 0;
kfree(tu->queue);
tu->queue = NULL;
kfree(tu->tqueue);
tu = file->private_data;
unit = tu->tread ? sizeof(struct snd_timer_tread) : sizeof(struct snd_timer_read);
+ mutex_lock(&tu->ioctl_lock);
spin_lock_irq(&tu->qlock);
while ((long)count - result >= unit) {
while (!tu->qused) {
add_wait_queue(&tu->qchange_sleep, &wait);
spin_unlock_irq(&tu->qlock);
+ mutex_unlock(&tu->ioctl_lock);
schedule();
+ mutex_lock(&tu->ioctl_lock);
spin_lock_irq(&tu->qlock);
remove_wait_queue(&tu->qchange_sleep, &wait);
tu->qused--;
spin_unlock_irq(&tu->qlock);
- mutex_lock(&tu->ioctl_lock);
if (tu->tread) {
if (copy_to_user(buffer, &tu->tqueue[qhead],
sizeof(struct snd_timer_tread)))
sizeof(struct snd_timer_read)))
err = -EFAULT;
}
- mutex_unlock(&tu->ioctl_lock);
spin_lock_irq(&tu->qlock);
if (err < 0)
}
_error:
spin_unlock_irq(&tu->qlock);
+ mutex_unlock(&tu->ioctl_lock);
return result > 0 ? result : err;
}
SND_PCI_QUIRK(0x106b, 0x4a00, "Macbook 5,2", ALC889_FIXUP_MBA11_VREF),
SND_PCI_QUIRK(0x1071, 0x8258, "Evesham Voyaeger", ALC882_FIXUP_EAPD),
- SND_PCI_QUIRK(0x1462, 0x7350, "MSI-7350", ALC889_FIXUP_CD),
- SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3),
SND_PCI_QUIRK(0x1458, 0xa002, "Gigabyte EP45-DS3/Z87X-UD3H", ALC889_FIXUP_FRONT_HP_NO_PRESENCE),
SND_PCI_QUIRK(0x1458, 0xa0b8, "Gigabyte AZ370-Gaming", ALC1220_FIXUP_GB_DUAL_CODECS),
+ SND_PCI_QUIRK(0x1462, 0x7350, "MSI-7350", ALC889_FIXUP_CD),
+ SND_PCI_QUIRK(0x1462, 0xda57, "MSI Z270-Gaming", ALC1220_FIXUP_GB_DUAL_CODECS),
+ SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3),
SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", ALC882_FIXUP_ABIT_AW9D_MAX),
SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC882_FIXUP_EAPD),
SND_PCI_QUIRK(0x161f, 0x2054, "Medion laptop", ALC883_FIXUP_EAPD),
{.id = ALC883_FIXUP_ACER_EAPD, .name = "acer-aspire"},
{.id = ALC882_FIXUP_INV_DMIC, .name = "inv-dmic"},
{.id = ALC882_FIXUP_NO_PRIMARY_HP, .name = "no-primary-hp"},
+ {.id = ALC1220_FIXUP_GB_DUAL_CODECS, .name = "dual-codecs"},
{}
};
SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
SND_PCI_QUIRK(0x1043, 0x10c0, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC),
+ SND_PCI_QUIRK(0x1043, 0x10d0, "ASUS X540LA/X540LJ", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1043, 0x115d, "Asus 1015E", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
+ SND_PCI_QUIRK(0x1043, 0x11c0, "ASUS X556UR", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1043, 0x1290, "ASUS X441SA", ALC233_FIXUP_EAPD_COEF_AND_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1043, 0x12a0, "ASUS X441UV", ALC233_FIXUP_EAPD_COEF_AND_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1043, 0x12f0, "ASUS X541UV", ALC256_FIXUP_ASUS_MIC),
SND_PCI_QUIRK(0x1043, 0x12e0, "ASUS X541SA", ALC256_FIXUP_ASUS_MIC),
SND_PCI_QUIRK(0x1043, 0x13b0, "ASUS Z550SA", ALC256_FIXUP_ASUS_MIC),
SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A),
SND_PCI_QUIRK(0x1043, 0x16e3, "ASUS UX50", ALC269_FIXUP_STEREO_DMIC),
SND_PCI_QUIRK(0x1043, 0x1a13, "Asus G73Jw", ALC269_FIXUP_ASUS_G73JW),
+ SND_PCI_QUIRK(0x1043, 0x1a30, "ASUS X705UD", ALC256_FIXUP_ASUS_MIC),
SND_PCI_QUIRK(0x1043, 0x1b13, "Asus U41SV", ALC269_FIXUP_INV_DMIC),
- SND_PCI_QUIRK(0x1043, 0x1c23, "Asus X55U", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
- SND_PCI_QUIRK(0x1043, 0x10d0, "ASUS X540LA/X540LJ", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
- SND_PCI_QUIRK(0x1043, 0x11c0, "ASUS X556UR", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
- SND_PCI_QUIRK(0x1043, 0x1290, "ASUS X441SA", ALC233_FIXUP_EAPD_COEF_AND_MIC_NO_PRESENCE),
- SND_PCI_QUIRK(0x1043, 0x12a0, "ASUS X441UV", ALC233_FIXUP_EAPD_COEF_AND_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1043, 0x1c23, "Asus X55U", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
SND_PCI_QUIRK(0x1043, 0x1ccd, "ASUS X555UB", ALC256_FIXUP_ASUS_MIC),
SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2),
SND_PCI_QUIRK(0x1043, 0x831a, "ASUS P901", ALC269_FIXUP_STEREO_DMIC),
{.id = ALC292_FIXUP_TPT440_DOCK, .name = "tpt440-dock"},
{.id = ALC292_FIXUP_TPT440, .name = "tpt440"},
{.id = ALC292_FIXUP_TPT460, .name = "tpt460"},
+ {.id = ALC233_FIXUP_LENOVO_MULTI_CODECS, .name = "dual-codecs"},
{}
};
#define ALC225_STANDARD_PINS \
break;
case 0x10ec0225:
case 0x10ec0295:
+ spec->codec_variant = ALC269_TYPE_ALC225;
+ break;
case 0x10ec0299:
spec->codec_variant = ALC269_TYPE_ALC225;
+ spec->gen.mixer_nid = 0; /* no loopback on ALC299 */
break;
case 0x10ec0234:
case 0x10ec0274:
{.id = ALC662_FIXUP_ASUS_MODE8, .name = "asus-mode8"},
{.id = ALC662_FIXUP_INV_DMIC, .name = "inv-dmic"},
{.id = ALC668_FIXUP_DELL_MIC_NO_PRESENCE, .name = "dell-headset-multi"},
+ {.id = ALC662_FIXUP_LENOVO_MULTI_CODECS, .name = "dual-codecs"},
{}
};
"Dell Inspiron 1501", STAC_9200_DELL_M26),
SND_PCI_QUIRK(PCI_VENDOR_ID_DELL, 0x01f6,
"unknown Dell", STAC_9200_DELL_M26),
+ SND_PCI_QUIRK(PCI_VENDOR_ID_DELL, 0x0201,
+ "Dell Latitude D430", STAC_9200_DELL_M22),
/* Panasonic */
SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-74", STAC_9200_PANASONIC),
/* Gateway machines needs EAPD to be set on resume */
return 0;
}
+static int atmel_classd_codec_resume(struct snd_soc_codec *codec)
+{
+ struct snd_soc_card *card = snd_soc_codec_get_drvdata(codec);
+ struct atmel_classd *dd = snd_soc_card_get_drvdata(card);
+
+ return regcache_sync(dd->regmap);
+}
+
static struct regmap *atmel_classd_codec_get_remap(struct device *dev)
{
return dev_get_regmap(dev, NULL);
static struct snd_soc_codec_driver soc_codec_dev_classd = {
.probe = atmel_classd_codec_probe,
+ .resume = atmel_classd_codec_resume,
.get_regmap = atmel_classd_codec_get_remap,
.component_driver = {
.controls = atmel_classd_snd_controls,
++i;
msleep(50);
}
- } while ((i < DA7213_SRM_CHECK_RETRIES) & (!srm_lock));
+ } while ((i < DA7213_SRM_CHECK_RETRIES) && (!srm_lock));
if (!srm_lock)
dev_warn(codec->dev, "SRM failed to lock\n");
DMI_MATCH(DMI_PRODUCT_NAME, "Kabylake Client platform")
}
},
+ {
+ .ident = "Thinkpad Helix 2nd",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad Helix 2nd")
+ }
+ },
{ }
};
if (ret < 0)
return ret;
- ret = asoc_simple_card_init_mic(rtd->card, &priv->hp_jack, PREFIX);
+ ret = asoc_simple_card_init_mic(rtd->card, &priv->mic_jack, PREFIX);
if (ret < 0)
return ret;
u32 reply = header.primary & IPC_GLB_REPLY_STATUS_MASK;
u64 *ipc_header = (u64 *)(&header);
struct skl_sst *skl = container_of(ipc, struct skl_sst, ipc);
+ unsigned long flags;
+ spin_lock_irqsave(&ipc->dsp->spinlock, flags);
msg = skl_ipc_reply_get_msg(ipc, *ipc_header);
+ spin_unlock_irqrestore(&ipc->dsp->spinlock, flags);
if (msg == NULL) {
dev_dbg(ipc->dev, "ipc: rx list is empty\n");
return;
}
}
+ spin_lock_irqsave(&ipc->dsp->spinlock, flags);
list_del(&msg->list);
sst_ipc_tx_msg_reply_complete(ipc, msg);
+ spin_unlock_irqrestore(&ipc->dsp->spinlock, flags);
}
irqreturn_t skl_dsp_irq_thread_handler(int irq, void *context)
if (ret < 0)
return ret;
- tkn_count += ret;
+ tkn_count = ret;
tuple_size += tkn_count *
sizeof(struct snd_soc_tplg_vendor_string_elem);
struct skl *skl = ebus_to_skl(ebus);
struct hdac_bus *bus = ebus_to_hbus(ebus);
- skl->init_failed = 1; /* to be sure */
+ skl->init_done = 0; /* to be sure */
snd_hdac_ext_stop_streams(ebus);
snd_hdac_ext_bus_exit(ebus);
+ cancel_work_sync(&skl->probe_work);
if (IS_ENABLED(CONFIG_SND_SOC_HDAC_HDMI))
snd_hdac_i915_exit(&ebus->bus);
+
return 0;
}
.get_response = snd_hdac_bus_get_response,
};
+static int skl_i915_init(struct hdac_bus *bus)
+{
+ int err;
+
+ /*
+ * The HDMI codec is in GPU so we need to ensure that it is powered
+ * up and ready for probe
+ */
+ err = snd_hdac_i915_init(bus);
+ if (err < 0)
+ return err;
+
+ err = snd_hdac_display_power(bus, true);
+ if (err < 0)
+ dev_err(bus->dev, "Cannot turn on display power on i915\n");
+
+ return err;
+}
+
+static void skl_probe_work(struct work_struct *work)
+{
+ struct skl *skl = container_of(work, struct skl, probe_work);
+ struct hdac_ext_bus *ebus = &skl->ebus;
+ struct hdac_bus *bus = ebus_to_hbus(ebus);
+ struct hdac_ext_link *hlink = NULL;
+ int err;
+
+ if (IS_ENABLED(CONFIG_SND_SOC_HDAC_HDMI)) {
+ err = skl_i915_init(bus);
+ if (err < 0)
+ return;
+ }
+
+ err = skl_init_chip(bus, true);
+ if (err < 0) {
+ dev_err(bus->dev, "Init chip failed with err: %d\n", err);
+ goto out_err;
+ }
+
+ /* codec detection */
+ if (!bus->codec_mask)
+ dev_info(bus->dev, "no hda codecs found!\n");
+
+ /* create codec instances */
+ err = skl_codec_create(ebus);
+ if (err < 0)
+ goto out_err;
+
+ if (IS_ENABLED(CONFIG_SND_SOC_HDAC_HDMI)) {
+ err = snd_hdac_display_power(bus, false);
+ if (err < 0) {
+ dev_err(bus->dev, "Cannot turn off display power on i915\n");
+ return;
+ }
+ }
+
+ /* register platform dai and controls */
+ err = skl_platform_register(bus->dev);
+ if (err < 0)
+ return;
+ /*
+ * we are done probing so decrement link counts
+ */
+ list_for_each_entry(hlink, &ebus->hlink_list, list)
+ snd_hdac_ext_bus_link_put(ebus, hlink);
+
+ /* configure PM */
+ pm_runtime_put_noidle(bus->dev);
+ pm_runtime_allow(bus->dev);
+ skl->init_done = 1;
+
+ return;
+
+out_err:
+ if (IS_ENABLED(CONFIG_SND_SOC_HDAC_HDMI))
+ err = snd_hdac_display_power(bus, false);
+}
+
/*
* constructor
*/
snd_hdac_ext_bus_init(ebus, &pci->dev, &bus_core_ops, io_ops);
ebus->bus.use_posbuf = 1;
skl->pci = pci;
+ INIT_WORK(&skl->probe_work, skl_probe_work);
ebus->bus.bdl_pos_adj = 0;
return 0;
}
-static int skl_i915_init(struct hdac_bus *bus)
-{
- int err;
-
- /*
- * The HDMI codec is in GPU so we need to ensure that it is powered
- * up and ready for probe
- */
- err = snd_hdac_i915_init(bus);
- if (err < 0)
- return err;
-
- err = snd_hdac_display_power(bus, true);
- if (err < 0) {
- dev_err(bus->dev, "Cannot turn on display power on i915\n");
- return err;
- }
-
- return err;
-}
-
static int skl_first_init(struct hdac_ext_bus *ebus)
{
struct skl *skl = ebus_to_skl(ebus);
/* initialize chip */
skl_init_pci(skl);
- if (IS_ENABLED(CONFIG_SND_SOC_HDAC_HDMI)) {
- err = skl_i915_init(bus);
- if (err < 0)
- return err;
- }
-
- skl_init_chip(bus, true);
-
- /* codec detection */
- if (!bus->codec_mask) {
- dev_info(bus->dev, "no hda codecs found!\n");
- }
-
- return 0;
+ return skl_init_chip(bus, true);
}
static int skl_probe(struct pci_dev *pci,
struct skl *skl;
struct hdac_ext_bus *ebus = NULL;
struct hdac_bus *bus = NULL;
- struct hdac_ext_link *hlink = NULL;
int err;
/* we use ext core ops, so provide NULL for ops here */
if (skl->nhlt == NULL) {
err = -ENODEV;
- goto out_display_power_off;
+ goto out_free;
}
err = skl_nhlt_create_sysfs(skl);
if (bus->mlcap)
snd_hdac_ext_bus_get_ml_capabilities(ebus);
+ snd_hdac_bus_stop_chip(bus);
+
/* create device for soc dmic */
err = skl_dmic_device_register(skl);
if (err < 0)
goto out_dsp_free;
- /* register platform dai and controls */
- err = skl_platform_register(bus->dev);
- if (err < 0)
- goto out_dmic_free;
-
- /* create codec instances */
- err = skl_codec_create(ebus);
- if (err < 0)
- goto out_unregister;
-
- if (IS_ENABLED(CONFIG_SND_SOC_HDAC_HDMI)) {
- err = snd_hdac_display_power(bus, false);
- if (err < 0) {
- dev_err(bus->dev, "Cannot turn off display power on i915\n");
- return err;
- }
- }
-
- /*
- * we are done probling so decrement link counts
- */
- list_for_each_entry(hlink, &ebus->hlink_list, list)
- snd_hdac_ext_bus_link_put(ebus, hlink);
-
- /* configure PM */
- pm_runtime_put_noidle(bus->dev);
- pm_runtime_allow(bus->dev);
+ schedule_work(&skl->probe_work);
return 0;
-out_unregister:
- skl_platform_unregister(bus->dev);
-out_dmic_free:
- skl_dmic_device_unregister(skl);
out_dsp_free:
skl_free_dsp(skl);
out_mach_free:
skl_machine_device_unregister(skl);
out_nhlt_free:
skl_nhlt_free(skl->nhlt);
-out_display_power_off:
- if (IS_ENABLED(CONFIG_SND_SOC_HDAC_HDMI))
- snd_hdac_display_power(bus, false);
out_free:
- skl->init_failed = 1;
skl_free(ebus);
return err;
skl = ebus_to_skl(ebus);
- if (skl->init_failed)
+ if (!skl->init_done)
return;
snd_hdac_ext_stop_streams(ebus);
struct hdac_ext_bus ebus;
struct pci_dev *pci;
- unsigned int init_failed:1; /* delayed init failed */
+ unsigned int init_done:1; /* delayed init status */
struct platform_device *dmic_dev;
struct platform_device *i2s_dev;
struct snd_soc_platform *platform;
const struct firmware *tplg;
int supend_active;
+
+ struct work_struct probe_work;
};
#define skl_to_ebus(s) (&(s)->ebus)
rbga = rbgx;
adg->rbga_rate_for_441khz = rate / div;
ckr |= brg_table[i] << 20;
- if (req_441kHz_rate)
+ if (req_441kHz_rate &&
+ !(adg_mode_flags(adg) & AUDIO_OUT_48))
parent_clk_name = __clk_get_name(clk);
}
}
rbgb = rbgx;
adg->rbgb_rate_for_48khz = rate / div;
ckr |= brg_table[i] << 16;
- if (req_48kHz_rate)
+ if (req_48kHz_rate &&
+ (adg_mode_flags(adg) & AUDIO_OUT_48))
parent_clk_name = __clk_get_name(clk);
}
}
dev_dbg(dev, "ctu/mix path = 0x%08x", data);
rsnd_mod_write(mod, CMD_ROUTE_SLCT, data);
+ rsnd_mod_write(mod, CMD_BUSIF_MODE, rsnd_get_busif_shift(io, mod) | 1);
rsnd_mod_write(mod, CMD_BUSIF_DALIGN, rsnd_get_dalign(mod, io));
rsnd_adg_set_cmd_timsel_gen2(mod, io);
return 0x76543210;
}
+u32 rsnd_get_busif_shift(struct rsnd_dai_stream *io, struct rsnd_mod *mod)
+{
+ enum rsnd_mod_type playback_mods[] = {
+ RSND_MOD_SRC,
+ RSND_MOD_CMD,
+ RSND_MOD_SSIU,
+ };
+ enum rsnd_mod_type capture_mods[] = {
+ RSND_MOD_CMD,
+ RSND_MOD_SRC,
+ RSND_MOD_SSIU,
+ };
+ struct snd_pcm_runtime *runtime = rsnd_io_to_runtime(io);
+ struct rsnd_mod *tmod = NULL;
+ enum rsnd_mod_type *mods =
+ rsnd_io_is_play(io) ?
+ playback_mods : capture_mods;
+ int i;
+
+ /*
+ * This is needed for 24bit data
+ * We need to shift 8bit
+ *
+ * Linux 24bit data is located as 0x00******
+ * HW 24bit data is located as 0x******00
+ *
+ */
+ switch (runtime->sample_bits) {
+ case 16:
+ return 0;
+ case 32:
+ break;
+ }
+
+ for (i = 0; i < ARRAY_SIZE(playback_mods); i++) {
+ tmod = rsnd_io_to_mod(io, mods[i]);
+ if (tmod)
+ break;
+ }
+
+ if (tmod != mod)
+ return 0;
+
+ if (rsnd_io_is_play(io))
+ return (0 << 20) | /* shift to Left */
+ (8 << 16); /* 8bit */
+ else
+ return (1 << 20) | /* shift to Right */
+ (8 << 16); /* 8bit */
+}
+
/*
* rsnd_dai functions
*/
RSND_GEN_M_REG(SRC_ROUTE_MODE0, 0xc, 0x20),
RSND_GEN_M_REG(SRC_CTRL, 0x10, 0x20),
RSND_GEN_M_REG(SRC_INT_ENABLE0, 0x18, 0x20),
+ RSND_GEN_M_REG(CMD_BUSIF_MODE, 0x184, 0x20),
RSND_GEN_M_REG(CMD_BUSIF_DALIGN,0x188, 0x20),
RSND_GEN_M_REG(CMD_ROUTE_SLCT, 0x18c, 0x20),
RSND_GEN_M_REG(CMD_CTRL, 0x190, 0x20),
RSND_REG_SCU_SYS_INT_EN0,
RSND_REG_SCU_SYS_INT_EN1,
RSND_REG_CMD_CTRL,
+ RSND_REG_CMD_BUSIF_MODE,
RSND_REG_CMD_BUSIF_DALIGN,
RSND_REG_CMD_ROUTE_SLCT,
RSND_REG_CMDOUT_TIMSEL,
u32 mask, u32 data);
u32 rsnd_get_adinr_bit(struct rsnd_mod *mod, struct rsnd_dai_stream *io);
u32 rsnd_get_dalign(struct rsnd_mod *mod, struct rsnd_dai_stream *io);
+u32 rsnd_get_busif_shift(struct rsnd_dai_stream *io, struct rsnd_mod *mod);
/*
* R-Car DMA
struct rsnd_priv *priv = rsnd_mod_to_priv(mod);
struct device *dev = rsnd_priv_to_dev(priv);
struct snd_pcm_runtime *runtime = rsnd_io_to_runtime(io);
+ int is_play = rsnd_io_is_play(io);
int use_src = 0;
u32 fin, fout;
u32 ifscr, fsrate, adinr;
u32 cr, route;
u32 bsdsr, bsisr;
+ u32 i_busif, o_busif, tmp;
uint ratio;
if (!runtime)
break;
}
+ /* BUSIF_MODE */
+ tmp = rsnd_get_busif_shift(io, mod);
+ i_busif = ( is_play ? tmp : 0) | 1;
+ o_busif = (!is_play ? tmp : 0) | 1;
+
rsnd_mod_write(mod, SRC_ROUTE_MODE0, route);
rsnd_mod_write(mod, SRC_SRCIR, 1); /* initialize */
rsnd_mod_write(mod, SRC_BSISR, bsisr);
rsnd_mod_write(mod, SRC_SRCIR, 0); /* cancel initialize */
- rsnd_mod_write(mod, SRC_I_BUSIF_MODE, 1);
- rsnd_mod_write(mod, SRC_O_BUSIF_MODE, 1);
+ rsnd_mod_write(mod, SRC_I_BUSIF_MODE, i_busif);
+ rsnd_mod_write(mod, SRC_O_BUSIF_MODE, o_busif);
+
rsnd_mod_write(mod, SRC_BUSIF_DALIGN, rsnd_get_dalign(mod, io));
rsnd_adg_set_src_timesel_gen2(mod, io, fin, fout);
* always use 32bit system word.
* see also rsnd_ssi_master_clk_enable()
*/
- cr_own = FORCE | SWL_32 | PDTA;
+ cr_own = FORCE | SWL_32;
if (rdai->bit_clk_inv)
cr_own |= SCKP;
struct snd_pcm_runtime *runtime = rsnd_io_to_runtime(io);
u32 *buf = (u32 *)(runtime->dma_area +
rsnd_dai_pointer_offset(io, 0));
+ int shift = 0;
+
+ switch (runtime->sample_bits) {
+ case 32:
+ shift = 8;
+ break;
+ }
/*
* 8/16/32 data can be assesse to TDR/RDR register
* see rsnd_ssi_init()
*/
if (rsnd_io_is_play(io))
- rsnd_mod_write(mod, SSITDR, *buf);
+ rsnd_mod_write(mod, SSITDR, (*buf) << shift);
else
- *buf = rsnd_mod_read(mod, SSIRDR);
+ *buf = (rsnd_mod_read(mod, SSIRDR) >> shift);
elapsed = rsnd_dai_pointer_update(io, sizeof(*buf));
}
struct rsnd_priv *priv)
{
struct rsnd_ssi *ssi = rsnd_mod_to_ssi(mod);
+ struct rsnd_mod *ssi_parent_mod = rsnd_io_to_mod_ssip(io);
+
+ /* Do nothing for SSI parent mod */
+ if (ssi_parent_mod == mod)
+ return 0;
/* PIO will request IRQ again */
free_irq(ssi->irq, mod);
(rsnd_io_is_play(io) ?
rsnd_runtime_channel_after_ctu(io) :
rsnd_runtime_channel_original(io)));
- rsnd_mod_write(mod, SSI_BUSIF_MODE, 1);
+ rsnd_mod_write(mod, SSI_BUSIF_MODE,
+ rsnd_get_busif_shift(io, mod) | 1);
rsnd_mod_write(mod, SSI_BUSIF_DALIGN,
rsnd_get_dalign(mod, io));
}
list_for_each_entry(rtd, &card->rtd_list, list)
flush_delayed_work(&rtd->delayed_work);
+ /* free the ALSA card at first; this syncs with pending operations */
+ snd_card_free(card->snd_card);
+
/* remove and free each DAI */
soc_remove_dai_links(card);
soc_remove_pcm_runtimes(card);
if (card->remove)
card->remove(card);
- snd_card_free(card->snd_card);
return 0;
-
}
/* removes a socdev */
struct snd_usb_audio *chip = elem->head.mixer->chip;
struct snd_us16x08_meter_store *store = elem->private_data;
u8 meter_urb[64];
- char tmp[sizeof(mix_init_msg2)] = {0};
switch (kcontrol->private_value) {
- case 0:
- snd_us16x08_send_urb(chip, (char *)mix_init_msg1,
- sizeof(mix_init_msg1));
+ case 0: {
+ char tmp[sizeof(mix_init_msg1)];
+
+ memcpy(tmp, mix_init_msg1, sizeof(mix_init_msg1));
+ snd_us16x08_send_urb(chip, tmp, 4);
snd_us16x08_recv_urb(chip, meter_urb,
sizeof(meter_urb));
kcontrol->private_value++;
break;
+ }
case 1:
snd_us16x08_recv_urb(chip, meter_urb,
sizeof(meter_urb));
sizeof(meter_urb));
kcontrol->private_value++;
break;
- case 3:
+ case 3: {
+ char tmp[sizeof(mix_init_msg2)];
+
memcpy(tmp, mix_init_msg2, sizeof(mix_init_msg2));
tmp[2] = snd_get_meter_comp_index(store);
- snd_us16x08_send_urb(chip, tmp, sizeof(mix_init_msg2));
+ snd_us16x08_send_urb(chip, tmp, 10);
snd_us16x08_recv_urb(chip, meter_urb,
sizeof(meter_urb));
kcontrol->private_value = 0;
break;
}
+ }
for (set = 0; set < 6; set++)
get_meter_levels_from_urb(set, store, meter_urb);
.control_id = SND_US16X08_ID_EQLOWMIDWIDTH,
.type = USB_MIXER_U8,
.num_channels = 16,
- .name = "EQ MidQLow Q",
+ .name = "EQ MidLow Q",
},
{ /* EQ mid high gain */
.kcontrol_new = &snd_us16x08_eq_gain_ctl,
/* Amanero Combo384 USB interface with native DSD support */
case USB_ID(0x16d0, 0x071a):
if (fp->altsetting == 2) {
- switch (chip->dev->descriptor.bcdDevice) {
+ switch (le16_to_cpu(chip->dev->descriptor.bcdDevice)) {
case 0x199:
return SNDRV_PCM_FMTBIT_DSD_U32_LE;
case 0x19b:
pdata->notify_pending = false;
spin_unlock_irq(&pdata->lpe_audio_slock);
- /* runtime PM isn't enabled as default, since it won't save much on
- * BYT/CHT devices; user who want the runtime PM should adjust the
- * power/ontrol and power/autosuspend_delay_ms sysfs entries instead
- */
pm_runtime_use_autosuspend(&pdev->dev);
pm_runtime_mark_last_busy(&pdev->dev);
pm_runtime_set_active(&pdev->dev);
#define __KVM_HAVE_IRQ_LINE
#define __KVM_HAVE_READONLY_MEM
+#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
+
#define KVM_REG_SIZE(id) \
(1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
};
struct kvm_sync_regs {
+ /* Used with KVM_CAP_ARM_USER_IRQ */
+ __u64 device_irq_level;
};
struct kvm_arch_memory_slot {
#define KVM_DEV_ARM_VGIC_GRP_REDIST_REGS 5
#define KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS 6
#define KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO 7
+#define KVM_DEV_ARM_VGIC_GRP_ITS_REGS 8
#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT 10
#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK \
(0x3fffffULL << KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT)
#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK 0x3ff
#define VGIC_LEVEL_INFO_LINE_LEVEL 0
-#define KVM_DEV_ARM_VGIC_CTRL_INIT 0
+#define KVM_DEV_ARM_VGIC_CTRL_INIT 0
+#define KVM_DEV_ARM_ITS_SAVE_TABLES 1
+#define KVM_DEV_ARM_ITS_RESTORE_TABLES 2
+#define KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES 3
/* KVM_IRQ_LINE irq field index values */
#define KVM_ARM_IRQ_TYPE_SHIFT 24
#define __KVM_HAVE_IRQ_LINE
#define __KVM_HAVE_READONLY_MEM
+#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
+
#define KVM_REG_SIZE(id) \
(1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
#define KVM_GUESTDBG_USE_HW (1 << 17)
struct kvm_sync_regs {
+ /* Used with KVM_CAP_ARM_USER_IRQ */
+ __u64 device_irq_level;
};
struct kvm_arch_memory_slot {
#define KVM_DEV_ARM_VGIC_GRP_REDIST_REGS 5
#define KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS 6
#define KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO 7
+#define KVM_DEV_ARM_VGIC_GRP_ITS_REGS 8
#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT 10
#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK \
(0x3fffffULL << KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT)
#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK 0x3ff
#define VGIC_LEVEL_INFO_LINE_LEVEL 0
-#define KVM_DEV_ARM_VGIC_CTRL_INIT 0
+#define KVM_DEV_ARM_VGIC_CTRL_INIT 0
+#define KVM_DEV_ARM_ITS_SAVE_TABLES 1
+#define KVM_DEV_ARM_ITS_RESTORE_TABLES 2
+#define KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES 3
/* Device Control API on vcpu fd */
#define KVM_ARM_VCPU_PMU_V3_CTRL 0
#define __KVM_HAVE_IRQ_LINE
#define __KVM_HAVE_GUEST_DEBUG
+/* Not always available, but if it is, this is the correct offset. */
+#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
+
struct kvm_regs {
__u64 pc;
__u64 cr;
#define KVM_DEV_FLIC_ADAPTER_REGISTER 6
#define KVM_DEV_FLIC_ADAPTER_MODIFY 7
#define KVM_DEV_FLIC_CLEAR_IO_IRQ 8
+#define KVM_DEV_FLIC_AISM 9
+#define KVM_DEV_FLIC_AIRQ_INJECT 10
/*
* We can have up to 4*64k pending subchannels + 8 adapter interrupts,
* as well as up to ASYNC_PF_PER_VCPU*KVM_MAX_VCPUS pfault done interrupts.
__u8 isc;
__u8 maskable;
__u8 swap;
- __u8 pad;
+ __u8 flags;
+};
+
+#define KVM_S390_ADAPTER_SUPPRESSIBLE 0x01
+
+struct kvm_s390_ais_req {
+ __u8 isc;
+ __u16 mode;
};
#define KVM_S390_IO_ADAPTER_MASK 1
#define KVM_S390_VM_CPU_FEAT_CMMA 10
#define KVM_S390_VM_CPU_FEAT_PFMFI 11
#define KVM_S390_VM_CPU_FEAT_SIGPIF 12
+#define KVM_S390_VM_CPU_FEAT_KSS 13
struct kvm_s390_vm_cpu_feat {
__u64 feat[16];
};
#define KVM_SYNC_VRS (1UL << 6)
#define KVM_SYNC_RICCB (1UL << 7)
#define KVM_SYNC_FPRS (1UL << 8)
+#define KVM_SYNC_GSCB (1UL << 9)
+/* length and alignment of the sdnx as a power of two */
+#define SDNXC 8
+#define SDNXL (1UL << SDNXC)
/* definition of registers in kvm_run */
struct kvm_sync_regs {
__u64 prefix; /* prefix register */
};
__u8 reserved[512]; /* for future vector expansion */
__u32 fpc; /* valid on KVM_SYNC_VRS or KVM_SYNC_FPRS */
- __u8 padding[52]; /* riccb needs to be 64byte aligned */
+ __u8 padding1[52]; /* riccb needs to be 64byte aligned */
__u8 riccb[64]; /* runtime instrumentation controls block */
+ __u8 padding2[192]; /* sdnx needs to be 256byte aligned */
+ union {
+ __u8 sdnx[SDNXL]; /* state description annex */
+ struct {
+ __u64 reserved1[2];
+ __u64 gscb[4];
+ };
+ };
};
#define KVM_REG_S390_TODPR (KVM_REG_S390 | KVM_REG_SIZE_U32 | 0x1)
#define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */
#define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */
+
/* Virtualization flags: Linux defined, word 8 */
#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */
#define X86_FEATURE_VNMI ( 8*32+ 1) /* Intel Virtual NMI */
# define DISABLE_OSPKE (1<<(X86_FEATURE_OSPKE & 31))
#endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */
+#ifdef CONFIG_X86_5LEVEL
+# define DISABLE_LA57 0
+#else
+# define DISABLE_LA57 (1<<(X86_FEATURE_LA57 & 31))
+#endif
+
/*
* Make sure to add features to the correct mask
*/
#define DISABLED_MASK13 0
#define DISABLED_MASK14 0
#define DISABLED_MASK15 0
-#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE)
+#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57)
#define DISABLED_MASK17 0
#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
# define NEED_MOVBE 0
#endif
+#ifdef CONFIG_X86_5LEVEL
+# define NEED_LA57 (1<<(X86_FEATURE_LA57 & 31))
+#else
+# define NEED_LA57 0
+#endif
+
#ifdef CONFIG_X86_64
#ifdef CONFIG_PARAVIRT
/* Paravirtualized systems may not have PSE or PGE available */
#define REQUIRED_MASK13 0
#define REQUIRED_MASK14 0
#define REQUIRED_MASK15 0
-#define REQUIRED_MASK16 0
+#define REQUIRED_MASK16 (NEED_LA57)
#define REQUIRED_MASK17 0
#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
#include <linux/types.h>
#include <linux/ioctl.h>
+#define KVM_PIO_PAGE_OFFSET 1
+#define KVM_COALESCED_MMIO_PAGE_OFFSET 2
+
#define DE_VECTOR 0
#define DB_VECTOR 1
#define BP_VECTOR 3
#define EXIT_REASON_WBINVD 54
#define EXIT_REASON_XSETBV 55
#define EXIT_REASON_APIC_WRITE 56
+#define EXIT_REASON_RDRAND 57
#define EXIT_REASON_INVPCID 58
+#define EXIT_REASON_VMFUNC 59
+#define EXIT_REASON_ENCLS 60
+#define EXIT_REASON_RDSEED 61
#define EXIT_REASON_PML_FULL 62
#define EXIT_REASON_XSAVES 63
#define EXIT_REASON_XRSTORS 64
{ EXIT_REASON_TASK_SWITCH, "TASK_SWITCH" }, \
{ EXIT_REASON_CPUID, "CPUID" }, \
{ EXIT_REASON_HLT, "HLT" }, \
+ { EXIT_REASON_INVD, "INVD" }, \
{ EXIT_REASON_INVLPG, "INVLPG" }, \
{ EXIT_REASON_RDPMC, "RDPMC" }, \
{ EXIT_REASON_RDTSC, "RDTSC" }, \
{ EXIT_REASON_IO_INSTRUCTION, "IO_INSTRUCTION" }, \
{ EXIT_REASON_MSR_READ, "MSR_READ" }, \
{ EXIT_REASON_MSR_WRITE, "MSR_WRITE" }, \
+ { EXIT_REASON_INVALID_STATE, "INVALID_STATE" }, \
+ { EXIT_REASON_MSR_LOAD_FAIL, "MSR_LOAD_FAIL" }, \
{ EXIT_REASON_MWAIT_INSTRUCTION, "MWAIT_INSTRUCTION" }, \
{ EXIT_REASON_MONITOR_TRAP_FLAG, "MONITOR_TRAP_FLAG" }, \
{ EXIT_REASON_MONITOR_INSTRUCTION, "MONITOR_INSTRUCTION" }, \
{ EXIT_REASON_MCE_DURING_VMENTRY, "MCE_DURING_VMENTRY" }, \
{ EXIT_REASON_TPR_BELOW_THRESHOLD, "TPR_BELOW_THRESHOLD" }, \
{ EXIT_REASON_APIC_ACCESS, "APIC_ACCESS" }, \
- { EXIT_REASON_GDTR_IDTR, "GDTR_IDTR" }, \
- { EXIT_REASON_LDTR_TR, "LDTR_TR" }, \
+ { EXIT_REASON_EOI_INDUCED, "EOI_INDUCED" }, \
+ { EXIT_REASON_GDTR_IDTR, "GDTR_IDTR" }, \
+ { EXIT_REASON_LDTR_TR, "LDTR_TR" }, \
{ EXIT_REASON_EPT_VIOLATION, "EPT_VIOLATION" }, \
{ EXIT_REASON_EPT_MISCONFIG, "EPT_MISCONFIG" }, \
{ EXIT_REASON_INVEPT, "INVEPT" }, \
+ { EXIT_REASON_RDTSCP, "RDTSCP" }, \
{ EXIT_REASON_PREEMPTION_TIMER, "PREEMPTION_TIMER" }, \
+ { EXIT_REASON_INVVPID, "INVVPID" }, \
{ EXIT_REASON_WBINVD, "WBINVD" }, \
+ { EXIT_REASON_XSETBV, "XSETBV" }, \
{ EXIT_REASON_APIC_WRITE, "APIC_WRITE" }, \
- { EXIT_REASON_EOI_INDUCED, "EOI_INDUCED" }, \
- { EXIT_REASON_INVALID_STATE, "INVALID_STATE" }, \
- { EXIT_REASON_MSR_LOAD_FAIL, "MSR_LOAD_FAIL" }, \
- { EXIT_REASON_INVD, "INVD" }, \
- { EXIT_REASON_INVVPID, "INVVPID" }, \
+ { EXIT_REASON_RDRAND, "RDRAND" }, \
{ EXIT_REASON_INVPCID, "INVPCID" }, \
+ { EXIT_REASON_VMFUNC, "VMFUNC" }, \
+ { EXIT_REASON_ENCLS, "ENCLS" }, \
+ { EXIT_REASON_RDSEED, "RDSEED" }, \
+ { EXIT_REASON_PML_FULL, "PML_FULL" }, \
{ EXIT_REASON_XSAVES, "XSAVES" }, \
{ EXIT_REASON_XRSTORS, "XRSTORS" }
.off = OFF, \
.imm = IMM })
+/* Unconditional jumps, goto pc + off16 */
+
+#define BPF_JMP_A(OFF) \
+ ((struct bpf_insn) { \
+ .code = BPF_JMP | BPF_JA, \
+ .dst_reg = 0, \
+ .src_reg = 0, \
+ .off = OFF, \
+ .imm = 0 })
+
/* Function call */
#define BPF_EMIT_CALL(FUNC) \
* tv_sec holds the number of seconds before (negative) or after (positive)
* 00:00:00 1st January 1970 UTC.
*
- * tv_nsec holds a number of nanoseconds before (0..-999,999,999 if tv_sec is
- * negative) or after (0..999,999,999 if tv_sec is positive) the tv_sec time.
- *
- * Note that if both tv_sec and tv_nsec are non-zero, then the two values must
- * either be both positive or both negative.
+ * tv_nsec holds a number of nanoseconds (0..999,999,999) after the tv_sec time.
*
* __reserved is held in case we need a yet finer resolution.
*/
struct statx_timestamp {
__s64 tv_sec;
- __s32 tv_nsec;
+ __u32 tv_nsec;
__s32 __reserved;
};
or
./perf probe --add='schedule:12 cpu'
- this will add one or more probes which has the name start with "schedule".
+Add one or more probes which has the name start with "schedule".
- Add probes on lines in schedule() function which calls update_rq_clock().
+ ./perf probe schedule*
+ or
+ ./perf probe --add='schedule*'
+
+Add probes on lines in schedule() function which calls update_rq_clock().
./perf probe 'schedule;update_rq_clock*'
or
When perf script is invoked using a trace script, a user-defined
'handler function' is called for each event in the trace. If there's
no handler function defined for a given event type, the event is
-ignored (or passed to a 'trace_handled' function, see below) and the
+ignored (or passed to a 'trace_unhandled' function, see below) and the
next event is processed.
Most of the event's field values are passed as arguments to the
print "id=%d, args=%s\n" % \
(id, args),
-def trace_unhandled(event_name, context, common_cpu, common_secs, common_nsecs,
- common_pid, common_comm):
- print_header(event_name, common_cpu, common_secs, common_nsecs,
- common_pid, common_comm)
+def trace_unhandled(event_name, context, event_fields_dict):
+ print ' '.join(['%s=%s'%(k,str(v))for k,v in sorted(event_fields_dict.items())])
def print_header(event_name, cpu, secs, nsecs, pid, comm):
print "%-20s %5u %05u.%09u %8u %-20s " % \
process can be generalized to any tracepoint or set of tracepoints
you're interested in - basically find the tracepoint(s) you're
interested in by looking at the list of available events shown by
-'perf list' and/or look in /sys/kernel/debug/tracing events for
+'perf list' and/or look in /sys/kernel/debug/tracing/events/ for
detailed event and field info, record the corresponding trace data
using 'perf record', passing it the list of interesting events,
generate a skeleton script using 'perf script -g python' and modify the
scripts listed by the 'perf script -l' command e.g.:
----
-root@tropicana:~# perf script -l
+# perf script -l
List of available trace scripts:
wakeup-latency system-wide min/max/avg wakeup latency
rw-by-file <comm> r/w activity for a program, by file
----
# ls -al kernel-source/tools/perf/scripts/python
-
-root@tropicana:/home/trz/src/tip# ls -al tools/perf/scripts/python
total 32
drwxr-xr-x 4 trz trz 4096 2010-01-26 22:30 .
drwxr-xr-x 4 trz trz 4096 2010-01-26 22:29 ..
should show a new entry for your script:
----
-root@tropicana:~# perf script -l
+# perf script -l
List of available trace scripts:
wakeup-latency system-wide min/max/avg wakeup latency
rw-by-file <comm> r/w activity for a program, by file
When perf script is invoked using a trace script, a user-defined
'handler function' is called for each event in the trace. If there's
no handler function defined for a given event type, the event is
-ignored (or passed to a 'trace_handled' function, see below) and the
+ignored (or passed to a 'trace_unhandled' function, see below) and the
next event is processed.
Most of the event's field values are passed as arguments to the
gives scripts a chance to do setup tasks:
----
-def trace_begin:
+def trace_begin():
pass
----
as display results:
----
-def trace_end:
+def trace_end():
pass
----
of common arguments are passed into it:
----
-def trace_unhandled(event_name, context, common_cpu, common_secs,
- common_nsecs, common_pid, common_comm):
+def trace_unhandled(event_name, context, event_fields_dict):
pass
----
Set the maximum number of program blocks to print with brstackasm for
each sample.
+--inline::
+ If a callgraph address belongs to an inlined function, the inline stack
+ will be printed. Each entry has function name and file/line.
+
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-script-perl[1],
const char *const powerpc_triplets[] = {
"powerpc-unknown-linux-gnu-",
+ "powerpc-linux-gnu-",
"powerpc64-unknown-linux-gnu-",
"powerpc64-linux-gnu-",
"powerpc64le-linux-gnu-",
"Enable kernel symbol demangling"),
OPT_STRING(0, "time", &script.time_str, "str",
"Time span of interest (start,stop)"),
+ OPT_BOOLEAN(0, "inline", &symbol_conf.inline_name,
+ "Show inline function"),
OPT_END()
};
const char * const script_subcommands[] = { "record", "report", NULL };
static void print_footer(void)
{
FILE *output = stat_config.output;
+ int n;
if (!null_run)
fprintf(output, "\n");
}
fprintf(output, "\n\n");
- if (print_free_counters_hint)
+ if (print_free_counters_hint &&
+ sysctl__read_int("kernel/nmi_watchdog", &n) >= 0 &&
+ n > 0)
fprintf(output,
"Some events weren't counted. Try disabling the NMI watchdog:\n"
" echo 0 > /proc/sys/kernel/nmi_watchdog\n"
{ .name = "mlockall", .errmsg = true,
.arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
{ .name = "mmap", .hexret = true,
+/* The standard mmap maps to old_mmap on s390x */
+#if defined(__s390x__)
+ .alias = "old_mmap",
+#endif
.arg_scnprintf = { [0] = SCA_HEX, /* addr */
[2] = SCA_MMAP_PROT, /* prot */
[3] = SCA_MMAP_FLAGS, /* flags */ }, },
return count1 == 1 && overflows == 3 && count2 == 3 && overflows_2 == 3 && count3 == 2 ?
TEST_OK : TEST_FAIL;
}
+
+bool test__bp_signal_is_supported(void)
+{
+/*
+ * The powerpc so far does not have support to even create
+ * instruction breakpoint using the perf event interface.
+ * Once it's there we can release this.
+ */
+#ifdef __powerpc__
+ return false;
+#else
+ return true;
+#endif
+}
{
.desc = "Breakpoint overflow signal handler",
.func = test__bp_signal,
+ .is_supported = test__bp_signal_is_supported,
},
{
.desc = "Breakpoint overflow sampling",
.func = test__bp_signal_overflow,
+ .is_supported = test__bp_signal_is_supported,
},
{
.desc = "Number of exit events of a simple workload",
if (!perf_test__matches(t, curr, argc, argv))
continue;
+ if (t->is_supported && !t->is_supported()) {
+ pr_debug("%2d: %-*s: Disabled\n", i, width, t->desc);
+ continue;
+ }
+
pr_info("%2d: %-*s:", i, width, t->desc);
if (intlist__find(skiplist, i)) {
unsigned char buf2[BUFSZ];
size_t ret_len;
u64 objdump_addr;
+ const char *objdump_name;
+ char decomp_name[KMOD_DECOMP_LEN];
int ret;
pr_debug("Reading object code for memory address: %#"PRIx64"\n", addr);
state->done[state->done_cnt++] = al.map->start;
}
+ objdump_name = al.map->dso->long_name;
+ if (dso__needs_decompress(al.map->dso)) {
+ if (dso__decompress_kmodule_path(al.map->dso, objdump_name,
+ decomp_name,
+ sizeof(decomp_name)) < 0) {
+ pr_debug("decompression failed\n");
+ return -1;
+ }
+
+ objdump_name = decomp_name;
+ }
+
/* Read the object code using objdump */
objdump_addr = map__rip_2objdump(al.map, al.addr);
- ret = read_via_objdump(al.map->dso->long_name, objdump_addr, buf2, len);
+ ret = read_via_objdump(objdump_name, objdump_addr, buf2, len);
+
+ if (dso__needs_decompress(al.map->dso))
+ unlink(objdump_name);
+
if (ret > 0) {
/*
* The kernel maps are inaccurate - assume objdump is right in
int (*get_nr)(void);
const char *(*get_desc)(int subtest);
} subtest;
+ bool (*is_supported)(void);
};
/* Tests */
int test__clang_subtest_get_nr(void);
int test__unit_number__scnprint(int subtest);
+bool test__bp_signal_is_supported(void);
+
#if defined(__arm__) || defined(__aarch64__)
#ifdef HAVE_DWARF_UNWIND_SUPPORT
struct thread;
return 0;
ret = b->callchain->max_depth - a->callchain->max_depth;
+ if (callchain_param.order == ORDER_CALLER)
+ ret = -ret;
}
return ret;
}
const char *s = strchr(ops->raw, '+');
const char *c = strchr(ops->raw, ',');
- if (c++ != NULL)
+ /*
+ * skip over possible up to 2 operands to get to address, e.g.:
+ * tbnz w0, #26, ffff0000083cd190 <security_file_permission+0xd0>
+ */
+ if (c++ != NULL) {
ops->target.addr = strtoull(c, NULL, 16);
- else
+ if (!ops->target.addr) {
+ c = strchr(c, ',');
+ if (c++ != NULL)
+ ops->target.addr = strtoull(c, NULL, 16);
+ }
+ } else {
ops->target.addr = strtoull(ops->raw, NULL, 16);
+ }
if (s++ != NULL) {
ops->target.offset = strtoull(s, NULL, 16);
static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
struct ins_operands *ops)
{
+ const char *c = strchr(ops->raw, ',');
+
if (!ops->target.addr || ops->target.offset < 0)
return ins__raw_scnprintf(ins, bf, size, ops);
- return scnprintf(bf, size, "%-6.6s %" PRIx64, ins->name, ops->target.offset);
+ if (c != NULL) {
+ const char *c2 = strchr(c + 1, ',');
+
+ /* check for 3-op insn */
+ if (c2 != NULL)
+ c = c2;
+ c++;
+
+ /* mirror arch objdump's space-after-comma style */
+ if (*c == ' ')
+ c++;
+ }
+
+ return scnprintf(bf, size, "%-6.6s %.*s%" PRIx64,
+ ins->name, c ? c - ops->raw : 0, ops->raw,
+ ops->target.offset);
}
static struct ins_ops jump_ops = {
char linkname[PATH_MAX];
char *build_id_filename;
char *build_id_path = NULL;
+ char *pos;
if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS &&
!dso__is_kcore(dso))
if (!build_id_path)
return -1;
- dirname(build_id_path);
+ /*
+ * old style build-id cache has name of XX/XXXXXXX.. while
+ * new style has XX/XXXXXXX../{elf,kallsyms,vdso}.
+ * extract the build-id part of dirname in the new style only.
+ */
+ pos = strrchr(build_id_path, '/');
+ if (pos && strlen(pos) < SBUILD_ID_SIZE - 2)
+ dirname(build_id_path);
if (dso__is_kcore(dso) ||
readlink(build_id_path, linkname, sizeof(linkname)) < 0 ||
sizeof(symfs_filename));
}
} else if (dso__needs_decompress(dso)) {
- char tmp[PATH_MAX];
- struct kmod_path m;
- int fd;
- bool ret;
-
- if (kmod_path__parse_ext(&m, symfs_filename))
- goto out;
-
- snprintf(tmp, PATH_MAX, "/tmp/perf-kmod-XXXXXX");
-
- fd = mkstemp(tmp);
- if (fd < 0) {
- free(m.ext);
- goto out;
- }
-
- ret = decompress_to_file(m.ext, symfs_filename, fd);
-
- if (ret)
- pr_err("Cannot decompress %s %s\n", m.ext, symfs_filename);
-
- free(m.ext);
- close(fd);
+ char tmp[KMOD_DECOMP_LEN];
- if (!ret)
+ if (dso__decompress_kmodule_path(dso, symfs_filename,
+ tmp, sizeof(tmp)) < 0)
goto out;
strcpy(symfs_filename, tmp);
snprintf(command, sizeof(command),
"%s %s%s --start-address=0x%016" PRIx64
" --stop-address=0x%016" PRIx64
- " -l -d %s %s -C %s 2>/dev/null|grep -v %s:|expand",
+ " -l -d %s %s -C \"%s\" 2>/dev/null|grep -v \"%s:\"|expand",
objdump_path ? objdump_path : "objdump",
disassembler_style ? "-M " : "",
disassembler_style ? disassembler_style : "",
return bf;
}
-bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size)
-{
- char *id_name = NULL, *ch;
- struct stat sb;
- char sbuild_id[SBUILD_ID_SIZE];
-
- if (!dso->has_build_id)
- goto err;
-
- build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
- id_name = build_id_cache__linkname(sbuild_id, NULL, 0);
- if (!id_name)
- goto err;
- if (access(id_name, F_OK))
- goto err;
- if (lstat(id_name, &sb) == -1)
- goto err;
- if ((size_t)sb.st_size > size - 1)
- goto err;
- if (readlink(id_name, bf, size - 1) < 0)
- goto err;
-
- bf[sb.st_size] = '\0';
-
- /*
- * link should be:
- * ../../lib/modules/4.4.0-rc4/kernel/net/ipv4/netfilter/nf_nat_ipv4.ko/a09fe3eb3147dafa4e3b31dbd6257e4d696bdc92
- */
- ch = strrchr(bf, '/');
- if (!ch)
- goto err;
- if (ch - 3 < bf)
- goto err;
-
- free(id_name);
- return strncmp(".ko", ch - 3, 3) == 0;
-err:
- pr_err("Invalid build id: %s\n", id_name ? :
- dso->long_name ? :
- dso->short_name ? :
- "[unknown]");
- free(id_name);
- return false;
-}
-
#define dsos__for_each_with_build_id(pos, head) \
list_for_each_entry(pos, head, node) \
if (!pos->has_build_id) \
size_t size);
char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size);
-bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size);
int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event,
struct perf_sample *sample, struct perf_evsel *evsel,
static enum match_result match_chain_srcline(struct callchain_cursor_node *node,
struct callchain_list *cnode)
{
- char *left = get_srcline(cnode->ms.map->dso,
+ char *left = NULL;
+ char *right = NULL;
+ enum match_result ret = MATCH_EQ;
+ int cmp;
+
+ if (cnode->ms.map)
+ left = get_srcline(cnode->ms.map->dso,
map__rip_2objdump(cnode->ms.map, cnode->ip),
cnode->ms.sym, true, false);
- char *right = get_srcline(node->map->dso,
+ if (node->map)
+ right = get_srcline(node->map->dso,
map__rip_2objdump(node->map, node->ip),
node->sym, true, false);
- enum match_result ret = MATCH_EQ;
- int cmp;
if (left && right)
cmp = strcmp(left, right);
dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP;
}
+static int decompress_kmodule(struct dso *dso, const char *name, char *tmpbuf)
+{
+ int fd = -1;
+ struct kmod_path m;
+
+ if (!dso__needs_decompress(dso))
+ return -1;
+
+ if (kmod_path__parse_ext(&m, dso->long_name))
+ return -1;
+
+ if (!m.comp)
+ goto out;
+
+ fd = mkstemp(tmpbuf);
+ if (fd < 0) {
+ dso->load_errno = errno;
+ goto out;
+ }
+
+ if (!decompress_to_file(m.ext, name, fd)) {
+ dso->load_errno = DSO_LOAD_ERRNO__DECOMPRESSION_FAILURE;
+ close(fd);
+ fd = -1;
+ }
+
+out:
+ free(m.ext);
+ return fd;
+}
+
+int dso__decompress_kmodule_fd(struct dso *dso, const char *name)
+{
+ char tmpbuf[] = KMOD_DECOMP_NAME;
+ int fd;
+
+ fd = decompress_kmodule(dso, name, tmpbuf);
+ unlink(tmpbuf);
+ return fd;
+}
+
+int dso__decompress_kmodule_path(struct dso *dso, const char *name,
+ char *pathname, size_t len)
+{
+ char tmpbuf[] = KMOD_DECOMP_NAME;
+ int fd;
+
+ fd = decompress_kmodule(dso, name, tmpbuf);
+ if (fd < 0) {
+ unlink(tmpbuf);
+ return -1;
+ }
+
+ strncpy(pathname, tmpbuf, len);
+ close(fd);
+ return 0;
+}
+
/*
* Parses kernel module specified in @path and updates
* @m argument like:
return 0;
}
+void dso__set_module_info(struct dso *dso, struct kmod_path *m,
+ struct machine *machine)
+{
+ if (machine__is_host(machine))
+ dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE;
+ else
+ dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE;
+
+ /* _KMODULE_COMP should be next to _KMODULE */
+ if (m->kmod && m->comp)
+ dso->symtab_type++;
+
+ dso__set_short_name(dso, strdup(m->name), true);
+}
+
/*
* Global list of open DSOs and the counter.
*/
static int __open_dso(struct dso *dso, struct machine *machine)
{
- int fd;
+ int fd = -EINVAL;
char *root_dir = (char *)"";
char *name = malloc(PATH_MAX);
root_dir = machine->root_dir;
if (dso__read_binary_type_filename(dso, dso->binary_type,
- root_dir, name, PATH_MAX)) {
- free(name);
- return -EINVAL;
- }
+ root_dir, name, PATH_MAX))
+ goto out;
if (!is_regular_file(name))
- return -EINVAL;
+ goto out;
+
+ if (dso__needs_decompress(dso)) {
+ char newpath[KMOD_DECOMP_LEN];
+ size_t len = sizeof(newpath);
+
+ if (dso__decompress_kmodule_path(dso, name, newpath, len) < 0) {
+ fd = -dso->load_errno;
+ goto out;
+ }
+
+ strcpy(name, newpath);
+ }
fd = do_open(name);
+
+ if (dso__needs_decompress(dso))
+ unlink(name);
+
+out:
free(name);
return fd;
}
bool is_kernel_module(const char *pathname, int cpumode);
bool decompress_to_file(const char *ext, const char *filename, int output_fd);
bool dso__needs_decompress(struct dso *dso);
+int dso__decompress_kmodule_fd(struct dso *dso, const char *name);
+int dso__decompress_kmodule_path(struct dso *dso, const char *name,
+ char *pathname, size_t len);
+
+#define KMOD_DECOMP_NAME "/tmp/perf-kmod-XXXXXX"
+#define KMOD_DECOMP_LEN sizeof(KMOD_DECOMP_NAME)
struct kmod_path {
char *name;
#define kmod_path__parse_name(__m, __p) __kmod_path__parse(__m, __p, true , false)
#define kmod_path__parse_ext(__m, __p) __kmod_path__parse(__m, __p, false, true)
+void dso__set_module_info(struct dso *dso, struct kmod_path *m,
+ struct machine *machine);
+
/*
* The dso__data_* external interface provides following functions:
* dso__data_get_fd
#include "map.h"
#include "strlist.h"
#include "symbol.h"
+#include "srcline.h"
static int comma_fprintf(FILE *fp, bool *first, const char *fmt, ...)
{
if (!print_oneline)
printed += fprintf(fp, "\n");
+ if (symbol_conf.inline_name && node->map) {
+ struct inline_node *inode;
+
+ addr = map__rip_2objdump(node->map, node->ip),
+ inode = dso__parse_addr_inlines(node->map->dso, addr);
+
+ if (inode) {
+ struct inline_list *ilist;
+
+ list_for_each_entry(ilist, &inode->val, list) {
+ if (print_arrow)
+ printed += fprintf(fp, " <-");
+
+ /* IP is same, just skip it */
+ if (print_ip)
+ printed += fprintf(fp, "%c%16s",
+ s, "");
+ if (print_sym)
+ printed += fprintf(fp, " %s",
+ ilist->funcname);
+ if (print_srcline)
+ printed += fprintf(fp, "\n %s:%d",
+ ilist->filename,
+ ilist->line_nr);
+ if (!print_oneline)
+ printed += fprintf(fp, "\n");
+ }
+
+ inline_node__delete(inode);
+ }
+ }
+
if (symbol_conf.bt_stop_list &&
node->sym &&
strlist__has_entry(symbol_conf.bt_stop_list,
dso__set_build_id(dso, &bev->build_id);
- if (!is_kernel_module(filename, cpumode))
- dso->kernel = dso_type;
+ if (dso_type != DSO_TYPE_USER) {
+ struct kmod_path m = { .name = NULL, };
+
+ if (!kmod_path__parse_name(&m, filename) && m.kmod)
+ dso__set_module_info(dso, &m, machine);
+ else
+ dso->kernel = dso_type;
+
+ free(m.name);
+ }
build_id__sprintf(dso->build_id, sizeof(dso->build_id),
sbuild_id);
if (dso == NULL)
goto out_unlock;
- if (machine__is_host(machine))
- dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE;
- else
- dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE;
-
- /* _KMODULE_COMP should be next to _KMODULE */
- if (m->kmod && m->comp)
- dso->symtab_type++;
-
- dso__set_short_name(dso, strdup(m->name), true);
+ dso__set_module_info(dso, m, machine);
dso__set_long_name(dso, strdup(filename), true);
}
fprintf(ofp, "# be retrieved using Python functions of the form "
"common_*(context).\n");
- fprintf(ofp, "# See the perf-trace-python Documentation for the list "
+ fprintf(ofp, "# See the perf-script-python Documentation for the list "
"of available functions.\n\n");
fprintf(ofp, "import os\n");
}
}
- list_add_tail(&ilist->list, &node->val);
+ if (callchain_param.order == ORDER_CALLEE)
+ list_add_tail(&ilist->list, &node->val);
+ else
+ list_add(&ilist->list, &node->val);
return 0;
}
#define MAX_INLINE_NEST 1024
-static void inline_list__reverse(struct inline_node *node)
+static int inline_list__append_dso_a2l(struct dso *dso,
+ struct inline_node *node)
{
- struct inline_list *ilist, *n;
+ struct a2l_data *a2l = dso->a2l;
+ char *funcname = a2l->funcname ? strdup(a2l->funcname) : NULL;
+ char *filename = a2l->filename ? strdup(a2l->filename) : NULL;
- list_for_each_entry_safe_reverse(ilist, n, &node->val, list)
- list_move_tail(&ilist->list, &node->val);
+ return inline_list__append(filename, funcname, a2l->line, node, dso);
}
static int addr2line(const char *dso_name, u64 addr,
bfd_map_over_sections(a2l->abfd, find_address_in_section, a2l);
- if (a2l->found && unwind_inlines) {
+ if (!a2l->found)
+ return 0;
+
+ if (unwind_inlines) {
int cnt = 0;
+ if (node && inline_list__append_dso_a2l(dso, node))
+ return 0;
+
while (bfd_find_inliner_info(a2l->abfd, &a2l->filename,
&a2l->funcname, &a2l->line) &&
cnt++ < MAX_INLINE_NEST) {
if (node != NULL) {
- if (inline_list__append(strdup(a2l->filename),
- strdup(a2l->funcname),
- a2l->line, node,
- dso) != 0)
+ if (inline_list__append_dso_a2l(dso, node))
return 0;
+ // found at least one inline frame
+ ret = 1;
}
}
+ }
- if ((node != NULL) &&
- (callchain_param.order != ORDER_CALLEE)) {
- inline_list__reverse(node);
- }
+ if (file) {
+ *file = a2l->filename ? strdup(a2l->filename) : NULL;
+ ret = *file ? 1 : 0;
}
- if (a2l->found && a2l->filename) {
- *file = strdup(a2l->filename);
+ if (line)
*line = a2l->line;
- if (*file)
- ret = 1;
- }
-
return ret;
}
static struct inline_node *addr2inlines(const char *dso_name, u64 addr,
struct dso *dso)
{
- char *file = NULL;
- unsigned int line = 0;
struct inline_node *node;
node = zalloc(sizeof(*node));
INIT_LIST_HEAD(&node->val);
node->addr = addr;
- if (!addr2line(dso_name, addr, &file, &line, dso, TRUE, node))
+ if (!addr2line(dso_name, addr, NULL, NULL, dso, TRUE, node))
goto out_free_inline_node;
if (list_empty(&node->val))
return 0;
}
-static int decompress_kmodule(struct dso *dso, const char *name,
- enum dso_binary_type type)
-{
- int fd = -1;
- char tmpbuf[] = "/tmp/perf-kmod-XXXXXX";
- struct kmod_path m;
-
- if (type != DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP &&
- type != DSO_BINARY_TYPE__GUEST_KMODULE_COMP &&
- type != DSO_BINARY_TYPE__BUILD_ID_CACHE)
- return -1;
-
- if (type == DSO_BINARY_TYPE__BUILD_ID_CACHE)
- name = dso->long_name;
-
- if (kmod_path__parse_ext(&m, name) || !m.comp)
- return -1;
-
- fd = mkstemp(tmpbuf);
- if (fd < 0) {
- dso->load_errno = errno;
- goto out;
- }
-
- if (!decompress_to_file(m.ext, name, fd)) {
- dso->load_errno = DSO_LOAD_ERRNO__DECOMPRESSION_FAILURE;
- close(fd);
- fd = -1;
- }
-
- unlink(tmpbuf);
-
-out:
- free(m.ext);
- return fd;
-}
-
bool symsrc__possibly_runtime(struct symsrc *ss)
{
return ss->dynsym || ss->opdsec;
int fd;
if (dso__needs_decompress(dso)) {
- fd = decompress_kmodule(dso, name, type);
+ fd = dso__decompress_kmodule_fd(dso, name);
if (fd < 0)
return -1;
+
+ type = dso->symtab_type;
} else {
fd = open(name, O_RDONLY);
if (fd < 0) {
if (!runtime_ss && syms_ss)
runtime_ss = syms_ss;
- if (syms_ss && syms_ss->type == DSO_BINARY_TYPE__BUILD_ID_CACHE)
- if (dso__build_id_is_kmod(dso, name, PATH_MAX))
- kmod = true;
-
if (syms_ss)
ret = dso__load_sym(dso, map, syms_ss, runtime_ss, kmod);
else
return 0;
mod = dwfl_addrmodule(ui->dwfl, ip);
+ if (mod) {
+ Dwarf_Addr s;
+
+ dwfl_module_info(mod, NULL, &s, NULL, NULL, NULL, NULL, NULL);
+ if (s != al->map->start)
+ mod = 0;
+ }
+
if (!mod)
mod = dwfl_report_elf(ui->dwfl, dso->short_name,
dso->long_name, -1, al->map->start,
{
struct unwind_info *ui = arg;
Dwarf_Addr pc;
+ bool isactivation;
- if (!dwfl_frame_pc(state, &pc, NULL)) {
+ if (!dwfl_frame_pc(state, &pc, &isactivation)) {
pr_err("%s", dwfl_errmsg(-1));
return DWARF_CB_ABORT;
}
+ if (!isactivation)
+ --pc;
+
return entry(pc, ui) || !(--ui->max_stack) ?
DWARF_CB_ABORT : DWARF_CB_OK;
}
err = dwfl_getthread_frames(ui->dwfl, thread->tid, frame_callback, ui);
- if (err && !ui->max_stack)
+ if (err && ui->max_stack != max_stack)
err = 0;
/*
while (!ret && (unw_step(&c) > 0) && i < max_stack) {
unw_get_reg(&c, UNW_REG_IP, &ips[i]);
+
+ /*
+ * Decrement the IP for any non-activation frames.
+ * this is required to properly find the srcline
+ * for caller frames.
+ * See also the documentation for dwfl_frame_pc(),
+ * which this code tries to replicate.
+ */
+ if (unw_is_signal_frame(&c) <= 0)
+ --ips[i];
+
++i;
}
--- /dev/null
+acpidbg
+acpidump
+ec
+include
#include <asm-generic/int-ll64.h>
+/* copied from linux:include/uapi/linux/types.h */
+#define __bitwise
+typedef __u16 __bitwise __le16;
+typedef __u16 __bitwise __be16;
+typedef __u32 __bitwise __le32;
+typedef __u32 __bitwise __be32;
+typedef __u64 __bitwise __le64;
+typedef __u64 __bitwise __be64;
+
+typedef __u16 __bitwise __sum16;
+typedef __u32 __bitwise __wsum;
+
+#define __aligned_u64 __u64 __attribute__((aligned(8)))
+#define __aligned_be64 __be64 __attribute__((aligned(8)))
+#define __aligned_le64 __le64 __attribute__((aligned(8)))
+
#endif /* _UAPI_LINUX_TYPES_H */
* License as published by the Free Software Foundation.
*/
#include <stddef.h>
+#include <string.h>
#include <linux/bpf.h>
#include <linux/if_ether.h>
#include <linux/if_packet.h>
#define MAX_NR_MAPS 4
#define F_NEEDS_EFFICIENT_UNALIGNED_ACCESS (1 << 0)
+#define F_LOAD_WITH_STRICT_ALIGNMENT (1 << 1)
struct bpf_test {
const char *descr;
.result = REJECT,
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
},
+ {
+ "direct packet access: test17 (pruning, alignment)",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ offsetof(struct __sk_buff, data)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ offsetof(struct __sk_buff, data_end)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
+ offsetof(struct __sk_buff, mark)),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 14),
+ BPF_JMP_IMM(BPF_JGT, BPF_REG_7, 1, 4),
+ BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
+ BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, -4),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
+ BPF_JMP_A(-6),
+ },
+ .errstr = "misaligned packet access off 2+15+-4 size 4",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .flags = F_LOAD_WITH_STRICT_ALIGNMENT,
+ },
{
"helper access to packet: test1, valid packet_ptr range",
.insns = {
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_SCHED_CLS
},
+ {
+ "alu ops on ptr_to_map_value_or_null, 1",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_1, 10),
+ BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_0),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 2),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+ BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map1 = { 4 },
+ .errstr = "R4 invalid mem access",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS
+ },
+ {
+ "alu ops on ptr_to_map_value_or_null, 2",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_1, 10),
+ BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_4, -1),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+ BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map1 = { 4 },
+ .errstr = "R4 invalid mem access",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS
+ },
+ {
+ "alu ops on ptr_to_map_value_or_null, 3",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_1, 10),
+ BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_0),
+ BPF_ALU64_IMM(BPF_LSH, BPF_REG_4, 1),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+ BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map1 = { 4 },
+ .errstr = "R4 invalid mem access",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS
+ },
{
"invalid memory access with multiple map_lookup_elem calls",
.insns = {
.fixup_map_in_map = { 3 },
.errstr = "R1 type=map_value_or_null expected=map_ptr",
.result = REJECT,
- }
+ },
+ {
+ "ld_abs: check calling conv, r1",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_MOV64_IMM(BPF_REG_1, 0),
+ BPF_LD_ABS(BPF_W, -0x200000),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R1 !read_ok",
+ .result = REJECT,
+ },
+ {
+ "ld_abs: check calling conv, r2",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_MOV64_IMM(BPF_REG_2, 0),
+ BPF_LD_ABS(BPF_W, -0x200000),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R2 !read_ok",
+ .result = REJECT,
+ },
+ {
+ "ld_abs: check calling conv, r3",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_MOV64_IMM(BPF_REG_3, 0),
+ BPF_LD_ABS(BPF_W, -0x200000),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_3),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R3 !read_ok",
+ .result = REJECT,
+ },
+ {
+ "ld_abs: check calling conv, r4",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_MOV64_IMM(BPF_REG_4, 0),
+ BPF_LD_ABS(BPF_W, -0x200000),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_4),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R4 !read_ok",
+ .result = REJECT,
+ },
+ {
+ "ld_abs: check calling conv, r5",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_MOV64_IMM(BPF_REG_5, 0),
+ BPF_LD_ABS(BPF_W, -0x200000),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_5),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R5 !read_ok",
+ .result = REJECT,
+ },
+ {
+ "ld_abs: check calling conv, r7",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_MOV64_IMM(BPF_REG_7, 0),
+ BPF_LD_ABS(BPF_W, -0x200000),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_7),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ },
+ {
+ "ld_ind: check calling conv, r1",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_MOV64_IMM(BPF_REG_1, 1),
+ BPF_LD_IND(BPF_W, BPF_REG_1, -0x200000),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R1 !read_ok",
+ .result = REJECT,
+ },
+ {
+ "ld_ind: check calling conv, r2",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_MOV64_IMM(BPF_REG_2, 1),
+ BPF_LD_IND(BPF_W, BPF_REG_2, -0x200000),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R2 !read_ok",
+ .result = REJECT,
+ },
+ {
+ "ld_ind: check calling conv, r3",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_MOV64_IMM(BPF_REG_3, 1),
+ BPF_LD_IND(BPF_W, BPF_REG_3, -0x200000),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_3),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R3 !read_ok",
+ .result = REJECT,
+ },
+ {
+ "ld_ind: check calling conv, r4",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_MOV64_IMM(BPF_REG_4, 1),
+ BPF_LD_IND(BPF_W, BPF_REG_4, -0x200000),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_4),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R4 !read_ok",
+ .result = REJECT,
+ },
+ {
+ "ld_ind: check calling conv, r5",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_MOV64_IMM(BPF_REG_5, 1),
+ BPF_LD_IND(BPF_W, BPF_REG_5, -0x200000),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_5),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R5 !read_ok",
+ .result = REJECT,
+ },
+ {
+ "ld_ind: check calling conv, r7",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_MOV64_IMM(BPF_REG_7, 1),
+ BPF_LD_IND(BPF_W, BPF_REG_7, -0x200000),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_7),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ },
};
static int probe_filter_length(const struct bpf_insn *fp)
do_test_fixup(test, prog, map_fds);
- fd_prog = bpf_load_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER,
- prog, prog_len, "GPL", 0, bpf_vlog,
- sizeof(bpf_vlog));
+ fd_prog = bpf_verify_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER,
+ prog, prog_len, test->flags & F_LOAD_WITH_STRICT_ALIGNMENT,
+ "GPL", 0, bpf_vlog, sizeof(bpf_vlog));
expected_ret = unpriv && test->result_unpriv != UNDEF ?
test->result_unpriv : test->result;
;;
--verbose|-v|-vv)
VERBOSE=$((VERBOSE + 1))
- [ $1 == '-vv' ] && VERBOSE=$((VERBOSE + 1))
+ [ $1 = '-vv' ] && VERBOSE=$((VERBOSE + 1))
shift 1
;;
--debug|-d)
e=`cat $EVENT_ENABLE`
if [ "$e" != $val ]; then
echo "Expected $val but found $e"
- exit -1
+ exit 1
fi
}
echo > set_ftrace_filter
grep -v '^#' set_ftrace_filter | while read t; do
tr=`echo $t | cut -d: -f2`
- if [ "$tr" == "" ]; then
+ if [ "$tr" = "" ]; then
continue
fi
- if [ $tr == "enable_event" -o $tr == "disable_event" ]; then
+ if [ $tr = "enable_event" -o $tr = "disable_event" ]; then
tr=`echo $t | cut -d: -f1-4`
limit=`echo $t | cut -d: -f5`
else
if [ -d foo ]; then
fail "foo still exists"
fi
-exit 0
-
+mkdir foo
+echo "schedule:enable_event:sched:sched_switch" > foo/set_ftrace_filter
+rmdir foo
+if [ -d foo ]; then
+ fail "foo still exists"
+fi
instance_slam() {
--- /dev/null
+#!/bin/sh
+# description: Register/unregister many kprobe events
+
+# ftrace fentry skip size depends on the machine architecture.
+# Currently HAVE_KPROBES_ON_FTRACE defined on x86 and powerpc
+case `uname -m` in
+ x86_64|i[3456]86) OFFS=5;;
+ ppc*) OFFS=4;;
+ *) OFFS=0;;
+esac
+
+echo "Setup up to 256 kprobes"
+grep t /proc/kallsyms | cut -f3 -d" " | grep -v .*\\..* | \
+head -n 256 | while read i; do echo p ${i}+${OFFS} ; done > kprobe_events ||:
+
+echo 1 > events/kprobes/enable
+echo 0 > events/kprobes/enable
+echo > kprobe_events
+echo "Waiting for unoptimizing & freeing"
+sleep 5
+echo "Done"
tm-signal-context-chk-gpr
tm-signal-context-chk-vmx
tm-signal-context-chk-vsx
+tm-vmx-unavail
tm-signal-context-chk-vmx tm-signal-context-chk-vsx
TEST_GEN_PROGS := tm-resched-dscr tm-syscall tm-signal-msr-resv tm-signal-stack \
- tm-vmxcopy tm-fork tm-tar tm-tmspr $(SIGNAL_CONTEXT_CHK_TESTS)
+ tm-vmxcopy tm-fork tm-tar tm-tmspr tm-vmx-unavail \
+ $(SIGNAL_CONTEXT_CHK_TESTS)
include ../../lib.mk
$(OUTPUT)/tm-syscall: tm-syscall-asm.S
$(OUTPUT)/tm-syscall: CFLAGS += -I../../../../../usr/include
$(OUTPUT)/tm-tmspr: CFLAGS += -pthread
+$(OUTPUT)/tm-vmx-unavail: CFLAGS += -pthread -m64
SIGNAL_CONTEXT_CHK_TESTS := $(patsubst %,$(OUTPUT)/%,$(SIGNAL_CONTEXT_CHK_TESTS))
$(SIGNAL_CONTEXT_CHK_TESTS): tm-signal.S
printf("Check DSCR TM context switch: ");
fflush(stdout);
for (;;) {
- rv = 1;
asm __volatile__ (
/* set a known value into the DSCR */
"ld 3, %[dscr1];"
"mtspr %[sprn_dscr], 3;"
+ "li %[rv], 1;"
/* start and suspend a transaction */
"tbegin.;"
"beq 1f;"
--- /dev/null
+/*
+ * Copyright 2017, Michael Neuling, IBM Corp.
+ * Licensed under GPLv2.
+ * Original: Breno Leitao <brenohl@br.ibm.com> &
+ * Gustavo Bueno Romero <gromero@br.ibm.com>
+ * Edited: Michael Neuling
+ *
+ * Force VMX unavailable during a transaction and see if it corrupts
+ * the checkpointed VMX register state after the abort.
+ */
+
+#include <inttypes.h>
+#include <htmintrin.h>
+#include <string.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <pthread.h>
+#include <sys/mman.h>
+#include <unistd.h>
+#include <pthread.h>
+
+#include "tm.h"
+#include "utils.h"
+
+int passed;
+
+void *worker(void *unused)
+{
+ __int128 vmx0;
+ uint64_t texasr;
+
+ asm goto (
+ "li 3, 1;" /* Stick non-zero value in VMX0 */
+ "std 3, 0(%[vmx0_ptr]);"
+ "lvx 0, 0, %[vmx0_ptr];"
+
+ /* Wait here a bit so we get scheduled out 255 times */
+ "lis 3, 0x3fff;"
+ "1: ;"
+ "addi 3, 3, -1;"
+ "cmpdi 3, 0;"
+ "bne 1b;"
+
+ /* Kernel will hopefully turn VMX off now */
+
+ "tbegin. ;"
+ "beq failure;"
+
+ /* Cause VMX unavail. Any VMX instruction */
+ "vaddcuw 0,0,0;"
+
+ "tend. ;"
+ "b %l[success];"
+
+ /* Check VMX0 sanity after abort */
+ "failure: ;"
+ "lvx 1, 0, %[vmx0_ptr];"
+ "vcmpequb. 2, 0, 1;"
+ "bc 4, 24, %l[value_mismatch];"
+ "b %l[value_match];"
+ :
+ : [vmx0_ptr] "r"(&vmx0)
+ : "r3"
+ : success, value_match, value_mismatch
+ );
+
+ /* HTM aborted and VMX0 is corrupted */
+value_mismatch:
+ texasr = __builtin_get_texasr();
+
+ printf("\n\n==============\n\n");
+ printf("Failure with error: %lx\n", _TEXASR_FAILURE_CODE(texasr));
+ printf("Summary error : %lx\n", _TEXASR_FAILURE_SUMMARY(texasr));
+ printf("TFIAR exact : %lx\n\n", _TEXASR_TFIAR_EXACT(texasr));
+
+ passed = 0;
+ return NULL;
+
+ /* HTM aborted but VMX0 is correct */
+value_match:
+// printf("!");
+ return NULL;
+
+success:
+// printf(".");
+ return NULL;
+}
+
+int tm_vmx_unavail_test()
+{
+ int threads;
+ pthread_t *thread;
+
+ SKIP_IF(!have_htm());
+
+ passed = 1;
+
+ threads = sysconf(_SC_NPROCESSORS_ONLN) * 4;
+ thread = malloc(sizeof(pthread_t)*threads);
+ if (!thread)
+ return EXIT_FAILURE;
+
+ for (uint64_t i = 0; i < threads; i++)
+ pthread_create(&thread[i], NULL, &worker, NULL);
+
+ for (uint64_t i = 0; i < threads; i++)
+ pthread_join(thread[i], NULL);
+
+ free(thread);
+
+ return passed ? EXIT_SUCCESS : EXIT_FAILURE;
+}
+
+
+int main(int argc, char **argv)
+{
+ return test_harness(tm_vmx_unavail_test, "tm_vmx_unavail_test");
+}
endchoice
config INITRAMFS_COMPRESSION
+ depends on INITRAMFS_SOURCE!=""
string
default "" if INITRAMFS_COMPRESSION_NONE
default ".gz" if INITRAMFS_COMPRESSION_GZIP
#include <asm/kvm_hyp.h>
#define vtr_to_max_lr_idx(v) ((v) & 0xf)
-#define vtr_to_nr_pri_bits(v) (((u32)(v) >> 29) + 1)
+#define vtr_to_nr_pre_bits(v) ((((u32)(v) >> 26) & 7) + 1)
static u64 __hyp_text __gic_v3_get_lr(unsigned int lr)
{
if (used_lrs) {
int i;
- u32 nr_pri_bits;
+ u32 nr_pre_bits;
cpu_if->vgic_elrsr = read_gicreg(ICH_ELSR_EL2);
write_gicreg(0, ICH_HCR_EL2);
val = read_gicreg(ICH_VTR_EL2);
- nr_pri_bits = vtr_to_nr_pri_bits(val);
+ nr_pre_bits = vtr_to_nr_pre_bits(val);
for (i = 0; i < used_lrs; i++) {
if (cpu_if->vgic_elrsr & (1 << i))
__gic_v3_set_lr(0, i);
}
- switch (nr_pri_bits) {
+ switch (nr_pre_bits) {
case 7:
cpu_if->vgic_ap0r[3] = read_gicreg(ICH_AP0R3_EL2);
cpu_if->vgic_ap0r[2] = read_gicreg(ICH_AP0R2_EL2);
cpu_if->vgic_ap0r[0] = read_gicreg(ICH_AP0R0_EL2);
}
- switch (nr_pri_bits) {
+ switch (nr_pre_bits) {
case 7:
cpu_if->vgic_ap1r[3] = read_gicreg(ICH_AP1R3_EL2);
cpu_if->vgic_ap1r[2] = read_gicreg(ICH_AP1R2_EL2);
struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
u64 used_lrs = vcpu->arch.vgic_cpu.used_lrs;
u64 val;
- u32 nr_pri_bits;
+ u32 nr_pre_bits;
int i;
/*
}
val = read_gicreg(ICH_VTR_EL2);
- nr_pri_bits = vtr_to_nr_pri_bits(val);
+ nr_pre_bits = vtr_to_nr_pre_bits(val);
if (used_lrs) {
write_gicreg(cpu_if->vgic_hcr, ICH_HCR_EL2);
- switch (nr_pri_bits) {
+ switch (nr_pre_bits) {
case 7:
write_gicreg(cpu_if->vgic_ap0r[3], ICH_AP0R3_EL2);
write_gicreg(cpu_if->vgic_ap0r[2], ICH_AP0R2_EL2);
write_gicreg(cpu_if->vgic_ap0r[0], ICH_AP0R0_EL2);
}
- switch (nr_pri_bits) {
+ switch (nr_pre_bits) {
case 7:
write_gicreg(cpu_if->vgic_ap1r[3], ICH_AP1R3_EL2);
write_gicreg(cpu_if->vgic_ap1r[2], ICH_AP1R2_EL2);
assert_spin_locked(&kvm->mmu_lock);
pgd = kvm->arch.pgd + stage2_pgd_index(addr);
do {
+ /*
+ * Make sure the page table is still active, as another thread
+ * could have possibly freed the page table, while we released
+ * the lock.
+ */
+ if (!READ_ONCE(kvm->arch.pgd))
+ break;
next = stage2_pgd_addr_end(addr, end);
if (!stage2_pgd_none(*pgd))
unmap_stage2_puds(kvm, pgd, addr, next);
* Walks the level-1 page table pointed to by kvm->arch.pgd and frees all
* underlying level-2 and level-3 tables before freeing the actual level-1 table
* and setting the struct pointer to NULL.
- *
- * Note we don't need locking here as this is only called when the VM is
- * destroyed, which can only be done once.
*/
void kvm_free_stage2_pgd(struct kvm *kvm)
{
- if (kvm->arch.pgd == NULL)
- return;
+ void *pgd = NULL;
spin_lock(&kvm->mmu_lock);
- unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE);
+ if (kvm->arch.pgd) {
+ unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE);
+ pgd = READ_ONCE(kvm->arch.pgd);
+ kvm->arch.pgd = NULL;
+ }
spin_unlock(&kvm->mmu_lock);
/* Free the HW pgd, one page at a time */
- free_pages_exact(kvm->arch.pgd, S2_PGD_SIZE);
- kvm->arch.pgd = NULL;
+ if (pgd)
+ free_pages_exact(pgd, S2_PGD_SIZE);
}
static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
pmd_t *pmd;
pud = stage2_get_pud(kvm, cache, addr);
+ if (!pud)
+ return NULL;
+
if (stage2_pud_none(*pud)) {
if (!cache)
return NULL;
* large. Otherwise, we may see kernel panics with
* CONFIG_DETECT_HUNG_TASK, CONFIG_LOCKUP_DETECTOR,
* CONFIG_LOCKDEP. Additionally, holding the lock too long
- * will also starve other vCPUs.
+ * will also starve other vCPUs. We have to also make sure
+ * that the page tables are not freed while we released
+ * the lock.
*/
- if (need_resched() || spin_needbreak(&kvm->mmu_lock))
- cond_resched_lock(&kvm->mmu_lock);
-
+ cond_resched_lock(&kvm->mmu_lock);
+ if (!READ_ONCE(kvm->arch.pgd))
+ break;
next = stage2_pgd_addr_end(addr, end);
if (stage2_pgd_present(*pgd))
stage2_wp_puds(pgd, addr, next);
* If we are creating a VCPU with a GICv3 we must also register the
* KVM io device for the redistributor that belongs to this VCPU.
*/
- if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)
+ if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) {
+ mutex_lock(&vcpu->kvm->lock);
ret = vgic_register_redist_iodev(vcpu);
+ mutex_unlock(&vcpu->kvm->lock);
+ }
return ret;
}
switch (addr & 0xff) {
case GIC_CPU_CTRL:
- val = vmcr.ctlr;
+ val = vmcr.grpen0 << GIC_CPU_CTRL_EnableGrp0_SHIFT;
+ val |= vmcr.grpen1 << GIC_CPU_CTRL_EnableGrp1_SHIFT;
+ val |= vmcr.ackctl << GIC_CPU_CTRL_AckCtl_SHIFT;
+ val |= vmcr.fiqen << GIC_CPU_CTRL_FIQEn_SHIFT;
+ val |= vmcr.cbpr << GIC_CPU_CTRL_CBPR_SHIFT;
+ val |= vmcr.eoim << GIC_CPU_CTRL_EOImodeNS_SHIFT;
+
break;
case GIC_CPU_PRIMASK:
/*
switch (addr & 0xff) {
case GIC_CPU_CTRL:
- vmcr.ctlr = val;
+ vmcr.grpen0 = !!(val & GIC_CPU_CTRL_EnableGrp0);
+ vmcr.grpen1 = !!(val & GIC_CPU_CTRL_EnableGrp1);
+ vmcr.ackctl = !!(val & GIC_CPU_CTRL_AckCtl);
+ vmcr.fiqen = !!(val & GIC_CPU_CTRL_FIQEn);
+ vmcr.cbpr = !!(val & GIC_CPU_CTRL_CBPR);
+ vmcr.eoim = !!(val & GIC_CPU_CTRL_EOImodeNS);
+
break;
case GIC_CPU_PRIMASK:
/*
if (!vgic_v3_check_base(kvm))
return -EINVAL;
- rd_base = vgic->vgic_redist_base + kvm_vcpu_get_idx(vcpu) * SZ_64K * 2;
+ rd_base = vgic->vgic_redist_base + vgic->vgic_redist_free_offset;
sgi_base = rd_base + SZ_64K;
kvm_iodevice_init(&rd_dev->dev, &kvm_io_gic_ops);
mutex_lock(&kvm->slots_lock);
ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, sgi_base,
SZ_64K, &sgi_dev->dev);
- mutex_unlock(&kvm->slots_lock);
- if (ret)
+ if (ret) {
kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS,
&rd_dev->dev);
+ goto out;
+ }
+ vgic->vgic_redist_free_offset += 2 * SZ_64K;
+out:
+ mutex_unlock(&kvm->slots_lock);
return ret;
}
if (ret) {
/* The current c failed, so we start with the previous one. */
+ mutex_lock(&kvm->slots_lock);
for (c--; c >= 0; c--) {
vcpu = kvm_get_vcpu(kvm, c);
vgic_unregister_redist_iodev(vcpu);
}
+ mutex_unlock(&kvm->slots_lock);
}
return ret;
if (irq->hw) {
val |= GICH_LR_HW;
val |= irq->hwintid << GICH_LR_PHYSID_CPUID_SHIFT;
+ /*
+ * Never set pending+active on a HW interrupt, as the
+ * pending state is kept at the physical distributor
+ * level.
+ */
+ if (irq->active && irq_is_pending(irq))
+ val &= ~GICH_LR_PENDING_BIT;
} else {
if (irq->config == VGIC_CONFIG_LEVEL)
val |= GICH_LR_EOI;
struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
u32 vmcr;
- vmcr = (vmcrp->ctlr << GICH_VMCR_CTRL_SHIFT) & GICH_VMCR_CTRL_MASK;
+ vmcr = (vmcrp->grpen0 << GICH_VMCR_ENABLE_GRP0_SHIFT) &
+ GICH_VMCR_ENABLE_GRP0_MASK;
+ vmcr |= (vmcrp->grpen1 << GICH_VMCR_ENABLE_GRP1_SHIFT) &
+ GICH_VMCR_ENABLE_GRP1_MASK;
+ vmcr |= (vmcrp->ackctl << GICH_VMCR_ACK_CTL_SHIFT) &
+ GICH_VMCR_ACK_CTL_MASK;
+ vmcr |= (vmcrp->fiqen << GICH_VMCR_FIQ_EN_SHIFT) &
+ GICH_VMCR_FIQ_EN_MASK;
+ vmcr |= (vmcrp->cbpr << GICH_VMCR_CBPR_SHIFT) &
+ GICH_VMCR_CBPR_MASK;
+ vmcr |= (vmcrp->eoim << GICH_VMCR_EOI_MODE_SHIFT) &
+ GICH_VMCR_EOI_MODE_MASK;
vmcr |= (vmcrp->abpr << GICH_VMCR_ALIAS_BINPOINT_SHIFT) &
GICH_VMCR_ALIAS_BINPOINT_MASK;
vmcr |= (vmcrp->bpr << GICH_VMCR_BINPOINT_SHIFT) &
vmcr = cpu_if->vgic_vmcr;
- vmcrp->ctlr = (vmcr & GICH_VMCR_CTRL_MASK) >>
- GICH_VMCR_CTRL_SHIFT;
+ vmcrp->grpen0 = (vmcr & GICH_VMCR_ENABLE_GRP0_MASK) >>
+ GICH_VMCR_ENABLE_GRP0_SHIFT;
+ vmcrp->grpen1 = (vmcr & GICH_VMCR_ENABLE_GRP1_MASK) >>
+ GICH_VMCR_ENABLE_GRP1_SHIFT;
+ vmcrp->ackctl = (vmcr & GICH_VMCR_ACK_CTL_MASK) >>
+ GICH_VMCR_ACK_CTL_SHIFT;
+ vmcrp->fiqen = (vmcr & GICH_VMCR_FIQ_EN_MASK) >>
+ GICH_VMCR_FIQ_EN_SHIFT;
+ vmcrp->cbpr = (vmcr & GICH_VMCR_CBPR_MASK) >>
+ GICH_VMCR_CBPR_SHIFT;
+ vmcrp->eoim = (vmcr & GICH_VMCR_EOI_MODE_MASK) >>
+ GICH_VMCR_EOI_MODE_SHIFT;
+
vmcrp->abpr = (vmcr & GICH_VMCR_ALIAS_BINPOINT_MASK) >>
GICH_VMCR_ALIAS_BINPOINT_SHIFT;
vmcrp->bpr = (vmcr & GICH_VMCR_BINPOINT_MASK) >>
if (irq->hw) {
val |= ICH_LR_HW;
val |= ((u64)irq->hwintid) << ICH_LR_PHYS_ID_SHIFT;
+ /*
+ * Never set pending+active on a HW interrupt, as the
+ * pending state is kept at the physical distributor
+ * level.
+ */
+ if (irq->active && irq_is_pending(irq))
+ val &= ~ICH_LR_PENDING_BIT;
} else {
if (irq->config == VGIC_CONFIG_LEVEL)
val |= ICH_LR_EOI;
void vgic_v3_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
{
struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
+ u32 model = vcpu->kvm->arch.vgic.vgic_model;
u32 vmcr;
- /*
- * Ignore the FIQen bit, because GIC emulation always implies
- * SRE=1 which means the vFIQEn bit is also RES1.
- */
- vmcr = ((vmcrp->ctlr >> ICC_CTLR_EL1_EOImode_SHIFT) <<
- ICH_VMCR_EOIM_SHIFT) & ICH_VMCR_EOIM_MASK;
- vmcr |= (vmcrp->ctlr << ICH_VMCR_CBPR_SHIFT) & ICH_VMCR_CBPR_MASK;
+ if (model == KVM_DEV_TYPE_ARM_VGIC_V2) {
+ vmcr = (vmcrp->ackctl << ICH_VMCR_ACK_CTL_SHIFT) &
+ ICH_VMCR_ACK_CTL_MASK;
+ vmcr |= (vmcrp->fiqen << ICH_VMCR_FIQ_EN_SHIFT) &
+ ICH_VMCR_FIQ_EN_MASK;
+ } else {
+ /*
+ * When emulating GICv3 on GICv3 with SRE=1 on the
+ * VFIQEn bit is RES1 and the VAckCtl bit is RES0.
+ */
+ vmcr = ICH_VMCR_FIQ_EN_MASK;
+ }
+
+ vmcr |= (vmcrp->cbpr << ICH_VMCR_CBPR_SHIFT) & ICH_VMCR_CBPR_MASK;
+ vmcr |= (vmcrp->eoim << ICH_VMCR_EOIM_SHIFT) & ICH_VMCR_EOIM_MASK;
vmcr |= (vmcrp->abpr << ICH_VMCR_BPR1_SHIFT) & ICH_VMCR_BPR1_MASK;
vmcr |= (vmcrp->bpr << ICH_VMCR_BPR0_SHIFT) & ICH_VMCR_BPR0_MASK;
vmcr |= (vmcrp->pmr << ICH_VMCR_PMR_SHIFT) & ICH_VMCR_PMR_MASK;
void vgic_v3_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
{
struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
+ u32 model = vcpu->kvm->arch.vgic.vgic_model;
u32 vmcr;
vmcr = cpu_if->vgic_vmcr;
- /*
- * Ignore the FIQen bit, because GIC emulation always implies
- * SRE=1 which means the vFIQEn bit is also RES1.
- */
- vmcrp->ctlr = ((vmcr >> ICH_VMCR_EOIM_SHIFT) <<
- ICC_CTLR_EL1_EOImode_SHIFT) & ICC_CTLR_EL1_EOImode_MASK;
- vmcrp->ctlr |= (vmcr & ICH_VMCR_CBPR_MASK) >> ICH_VMCR_CBPR_SHIFT;
+ if (model == KVM_DEV_TYPE_ARM_VGIC_V2) {
+ vmcrp->ackctl = (vmcr & ICH_VMCR_ACK_CTL_MASK) >>
+ ICH_VMCR_ACK_CTL_SHIFT;
+ vmcrp->fiqen = (vmcr & ICH_VMCR_FIQ_EN_MASK) >>
+ ICH_VMCR_FIQ_EN_SHIFT;
+ } else {
+ /*
+ * When emulating GICv3 on GICv3 with SRE=1 on the
+ * VFIQEn bit is RES1 and the VAckCtl bit is RES0.
+ */
+ vmcrp->fiqen = 1;
+ vmcrp->ackctl = 0;
+ }
+
+ vmcrp->cbpr = (vmcr & ICH_VMCR_CBPR_MASK) >> ICH_VMCR_CBPR_SHIFT;
+ vmcrp->eoim = (vmcr & ICH_VMCR_EOIM_MASK) >> ICH_VMCR_EOIM_SHIFT;
vmcrp->abpr = (vmcr & ICH_VMCR_BPR1_MASK) >> ICH_VMCR_BPR1_SHIFT;
vmcrp->bpr = (vmcr & ICH_VMCR_BPR0_MASK) >> ICH_VMCR_BPR0_SHIFT;
vmcrp->pmr = (vmcr & ICH_VMCR_PMR_MASK) >> ICH_VMCR_PMR_SHIFT;
* registers regardless of the hardware backed GIC used.
*/
struct vgic_vmcr {
- u32 ctlr;
+ u32 grpen0;
+ u32 grpen1;
+
+ u32 ackctl;
+ u32 fiqen;
+ u32 cbpr;
+ u32 eoim;
+
u32 abpr;
u32 bpr;
u32 pmr; /* Priority mask field in the GICC_PMR and
* ICC_PMR_EL1 priority field format */
- /* Below member variable are valid only for GICv3 */
- u32 grpen0;
- u32 grpen1;
};
struct vgic_reg_attr {