diff options
302 files changed, 3629 insertions, 1663 deletions
diff --git a/Documentation/admin-guide/pm/cpuidle.rst b/Documentation/admin-guide/pm/cpuidle.rst index 106379e2619f..9c58b35a81cb 100644 --- a/Documentation/admin-guide/pm/cpuidle.rst +++ b/Documentation/admin-guide/pm/cpuidle.rst @@ -155,14 +155,14 @@ governor uses that information depends on what algorithm is implemented by it and that is the primary reason for having more than one governor in the ``CPUIdle`` subsystem. -There are two ``CPUIdle`` governors available, ``menu`` and ``ladder``. Which -of them is used depends on the configuration of the kernel and in particular on -whether or not the scheduler tick can be `stopped by the idle -loop <idle-cpus-and-tick_>`_. It is possible to change the governor at run time -if the ``cpuidle_sysfs_switch`` command line parameter has been passed to the -kernel, but that is not safe in general, so it should not be done on production -systems (that may change in the future, though). The name of the ``CPUIdle`` -governor currently used by the kernel can be read from the +There are three ``CPUIdle`` governors available, ``menu``, `TEO <teo-gov_>`_ +and ``ladder``. Which of them is used by default depends on the configuration +of the kernel and in particular on whether or not the scheduler tick can be +`stopped by the idle loop <idle-cpus-and-tick_>`_. It is possible to change the +governor at run time if the ``cpuidle_sysfs_switch`` command line parameter has +been passed to the kernel, but that is not safe in general, so it should not be +done on production systems (that may change in the future, though). The name of +the ``CPUIdle`` governor currently used by the kernel can be read from the :file:`current_governor_ro` (or :file:`current_governor` if ``cpuidle_sysfs_switch`` is present in the kernel command line) file under :file:`/sys/devices/system/cpu/cpuidle/` in ``sysfs``. @@ -256,6 +256,8 @@ the ``menu`` governor by default and if it is not tickless, the default ``CPUIdle`` governor on it will be ``ladder``. +.. _menu-gov: + The ``menu`` Governor ===================== @@ -333,6 +335,92 @@ that time, the governor may need to select a shallower state with a suitable target residency. +.. _teo-gov: + +The Timer Events Oriented (TEO) Governor +======================================== + +The timer events oriented (TEO) governor is an alternative ``CPUIdle`` governor +for tickless systems. It follows the same basic strategy as the ``menu`` `one +<menu-gov_>`_: it always tries to find the deepest idle state suitable for the +given conditions. However, it applies a different approach to that problem. + +First, it does not use sleep length correction factors, but instead it attempts +to correlate the observed idle duration values with the available idle states +and use that information to pick up the idle state that is most likely to +"match" the upcoming CPU idle interval. Second, it does not take the tasks +that were running on the given CPU in the past and are waiting on some I/O +operations to complete now at all (there is no guarantee that they will run on +the same CPU when they become runnable again) and the pattern detection code in +it avoids taking timer wakeups into account. It also only uses idle duration +values less than the current time till the closest timer (with the scheduler +tick excluded) for that purpose. + +Like in the ``menu`` governor `case <menu-gov_>`_, the first step is to obtain +the *sleep length*, which is the time until the closest timer event with the +assumption that the scheduler tick will be stopped (that also is the upper bound +on the time until the next CPU wakeup). That value is then used to preselect an +idle state on the basis of three metrics maintained for each idle state provided +by the ``CPUIdle`` driver: ``hits``, ``misses`` and ``early_hits``. + +The ``hits`` and ``misses`` metrics measure the likelihood that a given idle +state will "match" the observed (post-wakeup) idle duration if it "matches" the +sleep length. They both are subject to decay (after a CPU wakeup) every time +the target residency of the idle state corresponding to them is less than or +equal to the sleep length and the target residency of the next idle state is +greater than the sleep length (that is, when the idle state corresponding to +them "matches" the sleep length). The ``hits`` metric is increased if the +former condition is satisfied and the target residency of the given idle state +is less than or equal to the observed idle duration and the target residency of +the next idle state is greater than the observed idle duration at the same time +(that is, it is increased when the given idle state "matches" both the sleep +length and the observed idle duration). In turn, the ``misses`` metric is +increased when the given idle state "matches" the sleep length only and the +observed idle duration is too short for its target residency. + +The ``early_hits`` metric measures the likelihood that a given idle state will +"match" the observed (post-wakeup) idle duration if it does not "match" the +sleep length. It is subject to decay on every CPU wakeup and it is increased +when the idle state corresponding to it "matches" the observed (post-wakeup) +idle duration and the target residency of the next idle state is less than or +equal to the sleep length (i.e. the idle state "matching" the sleep length is +deeper than the given one). + +The governor walks the list of idle states provided by the ``CPUIdle`` driver +and finds the last (deepest) one with the target residency less than or equal +to the sleep length. Then, the ``hits`` and ``misses`` metrics of that idle +state are compared with each other and it is preselected if the ``hits`` one is +greater (which means that that idle state is likely to "match" the observed idle +duration after CPU wakeup). If the ``misses`` one is greater, the governor +preselects the shallower idle state with the maximum ``early_hits`` metric +(or if there are multiple shallower idle states with equal ``early_hits`` +metric which also is the maximum, the shallowest of them will be preselected). +[If there is a wakeup latency constraint coming from the `PM QoS framework +<cpu-pm-qos_>`_ which is hit before reaching the deepest idle state with the +target residency within the sleep length, the deepest idle state with the exit +latency within the constraint is preselected without consulting the ``hits``, +``misses`` and ``early_hits`` metrics.] + +Next, the governor takes several idle duration values observed most recently +into consideration and if at least a half of them are greater than or equal to +the target residency of the preselected idle state, that idle state becomes the +final candidate to ask for. Otherwise, the average of the most recent idle +duration values below the target residency of the preselected idle state is +computed and the governor walks the idle states shallower than the preselected +one and finds the deepest of them with the target residency within that average. +That idle state is then taken as the final candidate to ask for. + +Still, at this point the governor may need to refine the idle state selection if +it has not decided to `stop the scheduler tick <idle-cpus-and-tick_>`_. That +generally happens if the target residency of the idle state selected so far is +less than the tick period and the tick has not been stopped already (in a +previous iteration of the idle loop). Then, like in the ``menu`` governor +`case <menu-gov_>`_, the sleep length used in the previous computations may not +reflect the real time until the closest timer event and if it really is greater +than that time, a shallower state with a suitable target residency may need to +be selected. + + .. _idle-states-representation: Representation of Idle States diff --git a/Documentation/cpuidle/driver.txt b/Documentation/cpuidle/driver.txt deleted file mode 100644 index 1b0d81d92583..000000000000 --- a/Documentation/cpuidle/driver.txt +++ /dev/null @@ -1,37 +0,0 @@ - - - Supporting multiple CPU idle levels in kernel - - cpuidle drivers - - - - -cpuidle driver hooks into the cpuidle infrastructure and handles the -architecture/platform dependent part of CPU idle states. Driver -provides the platform idle state detection capability and also -has mechanisms in place to support actual entry-exit into CPU idle states. - -cpuidle driver initializes the cpuidle_device structure for each CPU device -and registers with cpuidle using cpuidle_register_device. - -If all the idle states are the same, the wrapper function cpuidle_register -could be used instead. - -It can also support the dynamic changes (like battery <-> AC), by using -cpuidle_pause_and_lock, cpuidle_disable_device and cpuidle_enable_device, -cpuidle_resume_and_unlock. - -Interfaces: -extern int cpuidle_register(struct cpuidle_driver *drv, - const struct cpumask *const coupled_cpus); -extern int cpuidle_unregister(struct cpuidle_driver *drv); -extern int cpuidle_register_driver(struct cpuidle_driver *drv); -extern void cpuidle_unregister_driver(struct cpuidle_driver *drv); -extern int cpuidle_register_device(struct cpuidle_device *dev); -extern void cpuidle_unregister_device(struct cpuidle_device *dev); - -extern void cpuidle_pause_and_lock(void); -extern void cpuidle_resume_and_unlock(void); -extern int cpuidle_enable_device(struct cpuidle_device *dev); -extern void cpuidle_disable_device(struct cpuidle_device *dev); diff --git a/Documentation/cpuidle/governor.txt b/Documentation/cpuidle/governor.txt deleted file mode 100644 index d9020f5e847b..000000000000 --- a/Documentation/cpuidle/governor.txt +++ /dev/null @@ -1,28 +0,0 @@ - - - - Supporting multiple CPU idle levels in kernel - - cpuidle governors - - - - -cpuidle governor is policy routine that decides what idle state to enter at -any given time. cpuidle core uses different callbacks to the governor. - -* enable() to enable governor for a particular device -* disable() to disable governor for a particular device -* select() to select an idle state to enter -* reflect() called after returning from the idle state, which can be used - by the governor for some record keeping. - -More than one governor can be registered at the same time and -users can switch between drivers using /sysfs interface (when enabled). -More than one governor part is supported for developers to easily experiment -with different governors. By default, most optimal governor based on your -kernel configuration and platform will be selected by cpuidle. - -Interfaces: -extern int cpuidle_register_governor(struct cpuidle_governor *gov); -struct cpuidle_governor diff --git a/Documentation/driver-api/pm/cpuidle.rst b/Documentation/driver-api/pm/cpuidle.rst new file mode 100644 index 000000000000..5842ab621a58 --- /dev/null +++ b/Documentation/driver-api/pm/cpuidle.rst @@ -0,0 +1,282 @@ +.. |struct cpuidle_governor| replace:: :c:type:`struct cpuidle_governor <cpuidle_governor>` +.. |struct cpuidle_device| replace:: :c:type:`struct cpuidle_device <cpuidle_device>` +.. |struct cpuidle_driver| replace:: :c:type:`struct cpuidle_driver <cpuidle_driver>` +.. |struct cpuidle_state| replace:: :c:type:`struct cpuidle_state <cpuidle_state>` + +======================== +CPU Idle Time Management +======================== + +:: + + Copyright (c) 2019 Intel Corp., Rafael J. Wysocki <rafael.j.wysocki@intel.com> + + +CPU Idle Time Management Subsystem +================================== + +Every time one of the logical CPUs in the system (the entities that appear to +fetch and execute instructions: hardware threads, if present, or processor +cores) is idle after an interrupt or equivalent wakeup event, which means that +there are no tasks to run on it except for the special "idle" task associated +with it, there is an opportunity to save energy for the processor that it +belongs to. That can be done by making the idle logical CPU stop fetching +instructions from memory and putting some of the processor's functional units +depended on by it into an idle state in which they will draw less power. + +However, there may be multiple different idle states that can be used in such a +situation in principle, so it may be necessary to find the most suitable one +(from the kernel perspective) and ask the processor to use (or "enter") that +particular idle state. That is the role of the CPU idle time management +subsystem in the kernel, called ``CPUIdle``. + +The design of ``CPUIdle`` is modular and based on the code duplication avoidance +principle, so the generic code that in principle need not depend on the hardware +or platform design details in it is separate from the code that interacts with +the hardware. It generally is divided into three categories of functional +units: *governors* responsible for selecting idle states to ask the processor +to enter, *drivers* that pass the governors' decisions on to the hardware and +the *core* providing a common framework for them. + + +CPU Idle Time Governors +======================= + +A CPU idle time (``CPUIdle``) governor is a bundle of policy code invoked when +one of the logical CPUs in the system turns out to be idle. Its role is to +select an idle state to ask the processor to enter in order to save some energy. + +``CPUIdle`` governors are generic and each of them can be used on any hardware +platform that the Linux kernel can run on. For this reason, data structures +operated on by them cannot depend on any hardware architecture or platform +design details as well. + +The governor itself is represented by a |struct cpuidle_governor| object +containing four callback pointers, :c:member:`enable`, :c:member:`disable`, +:c:member:`select`, :c:member:`reflect`, a :c:member:`rating` field described +below, and a name (string) used for identifying it. + +For the governor to be available at all, that object needs to be registered +with the ``CPUIdle`` core by calling :c:func:`cpuidle_register_governor()` with +a pointer to it passed as the argument. If successful, that causes the core to +add the governor to the global list of available governors and, if it is the +only one in the list (that is, the list was empty before) or the value of its +:c:member:`rating` field is greater than the value of that field for the +governor currently in use, or the name of the new governor was passed to the +kernel as the value of the ``cpuidle.governor=`` command line parameter, the new +governor will be used from that point on (there can be only one ``CPUIdle`` +governor in use at a time). Also, if ``cpuidle_sysfs_switch`` is passed to the +kernel in the command line, user space can choose the ``CPUIdle`` governor to +use at run time via ``sysfs``. + +Once registered, ``CPUIdle`` governors cannot be unregistered, so it is not +practical to put them into loadable kernel modules. + +The interface between ``CPUIdle`` governors and the core consists of four +callbacks: + +:c:member:`enable` + :: + + int (*enable) (struct cpuidle_driver *drv, struct cpuidle_device *dev); + + The role of this callback is to prepare the governor for handling the + (logical) CPU represented by the |struct cpuidle_device| object pointed + to by the ``dev`` argument. The |struct cpuidle_driver| object pointed + to by the ``drv`` argument represents the ``CPUIdle`` driver to be used + with that CPU (among other things, it should contain the list of + |struct cpuidle_state| objects representing idle states that the + processor holding the given CPU can be asked to enter). + + It may fail, in which case it is expected to return a negative error + code, and that causes the kernel to run the architecture-specific + default code for idle CPUs on the CPU in question instead of ``CPUIdle`` + until the ``->enable()`` governor callback is invoked for that CPU + again. + +:c:member:`disable` + :: + + void (*disable) (struct cpuidle_driver *drv, struct cpuidle_device *dev); + + Called to make the governor stop handling the (logical) CPU represented + by the |struct cpuidle_device| object pointed to by the ``dev`` + argument. + + It is expected to reverse any changes made by the ``->enable()`` + callback when it was last invoked for the target CPU, free all memory + allocated by that callback and so on. + +:c:member:`select` + :: + + int (*select) (struct cpuidle_driver *drv, struct cpuidle_device *dev, + bool *stop_tick); + + Called to select an idle state for the processor holding the (logical) + CPU represented by the |struct cpuidle_device| object pointed to by the + ``dev`` argument. + + The list of idle states to take into consideration is represented by the + :c:member:`states` array of |struct cpuidle_state| objects held by the + |struct cpuidle_driver| object pointed to by the ``drv`` argument (which + represents the ``CPUIdle`` driver to be used with the CPU at hand). The + value returned by this callback is interpreted as an index into that + array (unless it is a negative error code). + + The ``stop_tick`` argument is used to indicate whether or not to stop + the scheduler tick before asking the processor to enter the selected + idle state. When the ``bool`` variable pointed to by it (which is set + to ``true`` before invoking this callback) is cleared to ``false``, the + processor will be asked to enter the selected idle state without + stopping the scheduler tick on the given CPU (if the tick has been + stopped on that CPU already, however, it will not be restarted before + asking the processor to enter the idle state). + + This callback is mandatory (i.e. the :c:member:`select` callback pointer + in |struct cpuidle_governor| must not be ``NULL`` for the registration + of the governor to succeed). + +:c:member:`reflect` + :: + + void (*reflect) (struct cpuidle_device *dev, int index); + + Called to allow the governor to evaluate the accuracy of the idle state + selection made by the ``->select()`` callback (when it was invoked last + time) and possibly use the result of that to improve the accuracy of + idle state selections in the future. + +In addition, ``CPUIdle`` governors are required to take power management +quality of service (PM QoS) constraints on the processor wakeup latency into +account when selecting idle states. In order to obtain the current effective +PM QoS wakeup latency constraint for a given CPU, a ``CPUIdle`` governor is +expected to pass the number of the CPU to +:c:func:`cpuidle_governor_latency_req()`. Then, the governor's ``->select()`` +callback must not return the index of an indle state whose +:c:member:`exit_latency` value is greater than the number returned by that +function. + + +CPU Idle Time Management Drivers +================================ + +CPU idle time management (``CPUIdle``) drivers provide an interface between the +other parts of ``CPUIdle`` and the hardware. + +First of all, a ``CPUIdle`` driver has to populate the :c:member:`states` array +of |struct cpuidle_state| objects included in the |struct cpuidle_driver| object +representing it. Going forward this array will represent the list of available +idle states that the processor hardware can be asked to enter shared by all of +the logical CPUs handled by the given driver. + +The entries in the :c:member:`states` array are expected to be sorted by the +value of the :c:member:`target_residency` field in |struct cpuidle_state| in +the ascending order (that is, index 0 should correspond to the idle state with +the minimum value of :c:member:`target_residency`). [Since the +:c:member:`target_residency` value is expected to reflect the "depth" of the +idle state represented by the |struct cpuidle_state| object holding it, this +sorting order should be the same as the ascending sorting order by the idle +state "depth".] + +Three fields in |struct cpuidle_state| are used by the existing ``CPUIdle`` +governors for computations related to idle state selection: + +:c:member:`target_residency` + Minimum time to spend in this idle state including the time needed to + enter it (which may be substantial) to save more energy than could + be saved by staying in a shallower idle state for the same amount of + time, in microseconds. + +:c:member:`exit_latency` + Maximum time it will take a CPU asking the processor to enter this idle + state to start executing the first instruction after a wakeup from it, + in microseconds. + +:c:member:`flags` + Flags representing idle state properties. Currently, governors only use + the ``CPUIDLE_FLAG_POLLING`` flag which is set if the given object + does not represent a real idle state, but an interface to a software + "loop" that can be used in order to avoid asking the processor to enter + any idle state at all. [There are other flags used by the ``CPUIdle`` + core in special situations.] + +The :c:member:`enter` callback pointer in |struct cpuidle_state|, which must not +be ``NULL``, points to the routine to execute in order to ask the processor to +enter this particular idle state: + +:: + + void (*enter) (struct cpuidle_device *dev, struct cpuidle_driver *drv, + int index); + +The first two arguments of it point to the |struct cpuidle_device| object +representing the logical CPU running this callback and the +|struct cpuidle_driver| object representing the driver itself, respectively, +and the last one is an index of the |struct cpuidle_state| entry in the driver's +:c:member:`states` array representing the idle state to ask the processor to +enter. + +The analogous ``->enter_s2idle()`` callback in |struct cpuidle_state| is used +only for implementing the suspend-to-idle system-wide power management feature. +The difference between in and ``->enter()`` is that it must not re-enable +interrupts at any point (even temporarily) or attempt to change the states of +clock event devices, which the ``->enter()`` callback may do sometimes. + +Once the :c:member:`states` array has been populated, the number of valid +entries in it has to be stored in the :c:member:`state_count` field of the +|struct cpuidle_driver| object representing the driver. Moreover, if any +entries in the :c:member:`states` array represent "coupled" idle states (that +is, idle states that can only be asked for if multiple related logical CPUs are +idle), the :c:member:`safe_state_index` field in |struct cpuidle_driver| needs +to be the index of an idle state that is not "coupled" (that is, one that can be +asked for if only one logical CPU is idle). + +In addition to that, if the given ``CPUIdle`` driver is only going to handle a +subset of logical CPUs in the system, the :c:member:`cpumask` field in its +|struct cpuidle_driver| object must point to the set (mask) of CPUs that will be +handled by it. + +A ``CPUIdle`` driver can only be used after it has been registered. If there +are no "coupled" idle state entries in the driver's :c:member:`states` array, +that can be accomplished by passing the driver's |struct cpuidle_driver| object +to :c:func:`cpuidle_register_driver()`. Otherwise, :c:func:`cpuidle_register()` +should be used for this purpose. + +However, it also is necessary to register |struct cpuidle_device| objects for +all of the logical CPUs to be handled by the given ``CPUIdle`` driver with the +help of :c:func:`cpuidle_register_device()` after the driver has been registered +and :c:func:`cpuidle_register_driver()`, unlike :c:func:`cpuidle_register()`, +does not do that automatically. For this reason, the drivers that use +:c:func:`cpuidle_register_driver()` to register themselves must also take care +of registering the |struct cpuidle_device| objects as needed, so it is generally +recommended to use :c:func:`cpuidle_register()` for ``CPUIdle`` driver +registration in all cases. + +The registration of a |struct cpuidle_device| object causes the ``CPUIdle`` +``sysfs`` interface to be created and the governor's ``->enable()`` callback to +be invoked for the logical CPU represented by it, so it must take place after +registering the driver that will handle the CPU in question. + +``CPUIdle`` drivers and |struct cpuidle_device| objects can be unregistered +when they are not necessary any more which allows some resources associated with +them to be released. Due to dependencies between them, all of the +|struct cpuidle_device| objects representing CPUs handled by the given +``CPUIdle`` driver must be unregistered, with the help of +:c:func:`cpuidle_unregister_device()`, before calling +:c:func:`cpuidle_unregister_driver()` to unregister the driver. Alternatively, +:c:func:`cpuidle_unregister()` can be called to unregister a ``CPUIdle`` driver +along with all of the |struct cpuidle_device| objects representing CPUs handled +by it. + +``CPUIdle`` drivers can respond to runtime system configuration changes that +lead to modifications of the list of available processor idle states (which can +happen, for example, when the system's power source is switched from AC to +battery or the other way around). Upon a notification of such a change, +a ``CPUIdle`` driver is expected to call :c:func:`cpuidle_pause_and_lock()` to +turn ``CPUIdle`` off temporarily and then :c:func:`cpuidle_disable_device()` for +all of the |struct cpuidle_device| objects representing CPUs affected by that +change. Next, it can update its :c:member:`states` array in accordance with +the new configuration of the system, call :c:func:`cpuidle_enable_device()` for +all of the relevant |struct cpuidle_device| objects and invoke +:c:func:`cpuidle_resume_and_unlock()` to allow ``CPUIdle`` to be used again. diff --git a/Documentation/driver-api/pm/index.rst b/Documentation/driver-api/pm/index.rst index 2f6d0e9cf6b7..56975c6bc789 100644 --- a/Documentation/driver-api/pm/index.rst +++ b/Documentation/driver-api/pm/index.rst @@ -1,9 +1,10 @@ -======================= -Device Power Management -======================= +=============================== +CPU and Device Power Management +=============================== .. toctree:: + cpuidle devices notifiers types diff --git a/Documentation/networking/operstates.txt b/Documentation/networking/operstates.txt index 355c6d8ef8ad..b203d1334822 100644 --- a/Documentation/networking/operstates.txt +++ b/Documentation/networking/operstates.txt @@ -22,8 +22,9 @@ and changeable from userspace under certain rules. 2. Querying from userspace Both admin and operational state can be queried via the netlink -operation RTM_GETLINK. It is also possible to subscribe to RTMGRP_LINK -to be notified of updates. This is important for setting from userspace. +operation RTM_GETLINK. It is also possible to subscribe to RTNLGRP_LINK +to be notified of updates while the interface is admin up. This is +important for setting from userspace. These values contain interface state: @@ -101,8 +102,9 @@ because some driver controlled protocol establishment has to complete. Corresponding functions are netif_dormant_on() to set the flag, netif_dormant_off() to clear it and netif_dormant() to query. -On device allocation, networking core sets the flags equivalent to -netif_carrier_ok() and !netif_dormant(). +On device allocation, both flags __LINK_STATE_NOCARRIER and +__LINK_STATE_DORMANT are cleared, so the effective state is equivalent +to netif_carrier_ok() and !netif_dormant(). Whenever the driver CHANGES one of these flags, a workqueue event is @@ -133,11 +135,11 @@ netif_carrier_ok() && !netif_dormant() is set by the driver. Afterwards, the userspace application can set IFLA_OPERSTATE to IF_OPER_DORMANT or IF_OPER_UP as long as the driver does not set netif_carrier_off() or netif_dormant_on(). Changes made by userspace -are multicasted on the netlink group RTMGRP_LINK. +are multicasted on the netlink group RTNLGRP_LINK. So basically a 802.1X supplicant interacts with the kernel like this: --subscribe to RTMGRP_LINK +-subscribe to RTNLGRP_LINK -set IFLA_LINKMODE to 1 via RTM_SETLINK -query RTM_GETLINK once to get initial state -if initial flags are not (IFF_LOWER_UP && !IFF_DORMANT), wait until diff --git a/Documentation/sysctl/fs.txt b/Documentation/sysctl/fs.txt index 58649bd4fcfc..ebc679bcb2dc 100644 --- a/Documentation/sysctl/fs.txt +++ b/Documentation/sysctl/fs.txt @@ -80,7 +80,9 @@ nonzero when shrink_dcache_pages() has been called and the dcache isn't pruned yet. nr_negative shows the number of unused dentries that are also -negative dentries which do not mapped to actual files. +negative dentries which do not map to any files. Instead, +they help speeding up rejection of non-existing files provided +by the users. ============================================================== diff --git a/MAINTAINERS b/MAINTAINERS index 9919840d54cd..d8db9ad441c3 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1737,6 +1737,7 @@ F: arch/arm/configs/mvebu_*_defconfig F: arch/arm/mach-mvebu/ F: arch/arm64/boot/dts/marvell/armada* F: drivers/cpufreq/armada-37xx-cpufreq.c +F: drivers/cpufreq/armada-8k-cpufreq.c F: drivers/cpufreq/mvebu-cpufreq.c F: drivers/irqchip/irq-armada-370-xp.c F: drivers/irqchip/irq-mvebu-* @@ -3961,7 +3962,7 @@ M: Viresh Kumar <viresh.kumar@linaro.org> L: linux-pm@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git -T: git git://git.linaro.org/people/vireshk/linux.git (For ARM Updates) +T: git git://git.kernel.org/pub/scm/linux/kernel/git/vireshk/pm.git (For ARM Updates) B: https://bugzilla.kernel.org F: Documentation/admin-guide/pm/cpufreq.rst F: Documentation/admin-guide/pm/intel_pstate.rst @@ -4021,6 +4022,7 @@ S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git B: https://bugzilla.kernel.org F: Documentation/admin-guide/pm/cpuidle.rst +F: Documentation/driver-api/pm/cpuidle.rst F: drivers/cpuidle/* F: include/linux/cpuidle.h @@ -6151,7 +6153,7 @@ FREESCALE SOC SOUND DRIVERS M: Timur Tabi <timur@kernel.org> M: Nicolin Chen <nicoleotsuka@gmail.com> M: Xiubo Li <Xiubo.Lee@gmail.com> -R: Fabio Estevam <fabio.estevam@nxp.com> +R: Fabio Estevam <festevam@gmail.com> L: alsa-devel@alsa-project.org (moderated for non-subscribers) L: linuxppc-dev@lists.ozlabs.org S: Maintained @@ -10898,7 +10900,7 @@ F: include/linux/nvmem-consumer.h F: include/linux/nvmem-provider.h NXP SGTL5000 DRIVER -M: Fabio Estevam <fabio.estevam@nxp.com> +M: Fabio Estevam <festevam@gmail.com> L: alsa-devel@alsa-project.org (moderated for non-subscribers) S: Maintained F: Documentation/devicetree/bindings/sound/sgtl5000.txt @@ -12604,11 +12606,11 @@ F: Documentation/media/v4l-drivers/qcom_camss.rst F: drivers/media/platform/qcom/camss/ QUALCOMM CPUFREQ DRIVER MSM8996/APQ8096 -M: Ilia Lin <ilia.lin@gmail.com> -L: linux-pm@vger.kernel.org -S: Maintained -F: Documentation/devicetree/bindings/opp/kryo-cpufreq.txt -F: drivers/cpufreq/qcom-cpufreq-kryo.c +M: Ilia Lin <ilia.lin@kernel.org> +L: linux-pm@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/opp/kryo-cpufreq.txt +F: drivers/cpufreq/qcom-cpufreq-kryo.c QUALCOMM EMAC GIGABIT ETHERNET DRIVER M: Timur Tabi <timur@kernel.org> @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 0 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = -rc7 NAME = Shy Crocodile # *DOCUMENTATION* diff --git a/arch/alpha/include/asm/irq.h b/arch/alpha/include/asm/irq.h index 4d17cacd1462..432402c8e47f 100644 --- a/arch/alpha/include/asm/irq.h +++ b/arch/alpha/include/asm/irq.h @@ -56,15 +56,15 @@ #elif defined(CONFIG_ALPHA_DP264) || \ defined(CONFIG_ALPHA_LYNX) || \ - defined(CONFIG_ALPHA_SHARK) || \ - defined(CONFIG_ALPHA_EIGER) + defined(CONFIG_ALPHA_SHARK) # define NR_IRQS 64 #elif defined(CONFIG_ALPHA_TITAN) #define NR_IRQS 80 #elif defined(CONFIG_ALPHA_RAWHIDE) || \ - defined(CONFIG_ALPHA_TAKARA) + defined(CONFIG_ALPHA_TAKARA) || \ + defined(CONFIG_ALPHA_EIGER) # define NR_IRQS 128 #elif defined(CONFIG_ALPHA_WILDFIRE) diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index d73dc473fbb9..188fc9256baf 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -78,7 +78,7 @@ __load_new_mm_context(struct mm_struct *next_mm) /* Macro for exception fixup code to access integer registers. */ #define dpf_reg(r) \ (((unsigned long *)regs)[(r) <= 8 ? (r) : (r) <= 15 ? (r)-16 : \ - (r) <= 18 ? (r)+8 : (r)-10]) + (r) <= 18 ? (r)+10 : (r)-10]) asmlinkage void do_page_fault(unsigned long address, unsigned long mmcsr, diff --git a/arch/arm/boot/dts/omap4-droid4-xt894.dts b/arch/arm/boot/dts/omap4-droid4-xt894.dts index 04758a2a87f0..67d77eee9433 100644 --- a/arch/arm/boot/dts/omap4-droid4-xt894.dts +++ b/arch/arm/boot/dts/omap4-droid4-xt894.dts @@ -644,6 +644,17 @@ }; }; +/* Configure pwm clock source for timers 8 & 9 */ +&timer8 { + assigned-clocks = <&abe_clkctrl OMAP4_TIMER8_CLKCTRL 24>; + assigned-clock-parents = <&sys_clkin_ck>; +}; + +&timer9 { + assigned-clocks = <&l4_per_clkctrl OMAP4_TIMER9_CLKCTRL 24>; + assigned-clock-parents = <&sys_clkin_ck>; +}; + /* * As uart1 is wired to mdm6600 with rts and cts, we can use the cts pin for * uart1 wakeirq. diff --git a/arch/arm/boot/dts/omap5-board-common.dtsi b/arch/arm/boot/dts/omap5-board-common.dtsi index bc853ebeda22..61a06f6add3c 100644 --- a/arch/arm/boot/dts/omap5-board-common.dtsi +++ b/arch/arm/boot/dts/omap5-board-common.dtsi @@ -317,7 +317,8 @@ palmas_sys_nirq_pins: pinmux_palmas_sys_nirq_pins { pinctrl-single,pins = < - OMAP5_IOPAD(0x068, PIN_INPUT_PULLUP | MUX_MODE0) /* sys_nirq1 */ + /* sys_nirq1 is pulled down as the SoC is inverting it for GIC */ + OMAP5_IOPAD(0x068, PIN_INPUT_PULLUP | MUX_MODE0) >; }; @@ -385,7 +386,8 @@ palmas: palmas@48 { compatible = "ti,palmas"; - interrupts = <GIC_SPI 7 IRQ_TYPE_NONE>; /* IRQ_SYS_1N */ + /* sys_nirq/ext_sys_irq pins get inverted at mpuss wakeupgen */ + interrupts = <GIC_SPI 7 IRQ_TYPE_LEVEL_LOW>; reg = <0x48>; interrupt-controller; #interrupt-cells = <2>; @@ -651,7 +653,8 @@ pinctrl-names = "default"; pinctrl-0 = <&twl6040_pins>; - interrupts = <GIC_SPI 119 IRQ_TYPE_NONE>; /* IRQ_SYS_2N cascaded to gic */ + /* sys_nirq/ext_sys_irq pins get inverted at mpuss wakeupgen */ + interrupts = <GIC_SPI 119 IRQ_TYPE_LEVEL_LOW>; /* audpwron gpio defined in the board specific dts */ diff --git a/arch/arm/boot/dts/omap5-cm-t54.dts b/arch/arm/boot/dts/omap5-cm-t54.dts index 5e21fb430a65..e78d3718f145 100644 --- a/arch/arm/boot/dts/omap5-cm-t54.dts +++ b/arch/arm/boot/dts/omap5-cm-t54.dts @@ -181,6 +181,13 @@ OMAP5_IOPAD(0x0042, PIN_INPUT_PULLDOWN | MUX_MODE6) /* llib_wakereqin.gpio1_wk15 */ >; }; + + palmas_sys_nirq_pins: pinmux_palmas_sys_nirq_pins { + pinctrl-single,pins = < + /* sys_nirq1 is pulled down as the SoC is inverting it for GIC */ + OMAP5_IOPAD(0x068, PIN_INPUT_PULLUP | MUX_MODE0) + >; + }; }; &omap5_pmx_core { @@ -414,8 +421,11 @@ palmas: palmas@48 { compatible = "ti,palmas"; - interrupts = <GIC_SPI 7 IRQ_TYPE_NONE>; /* IRQ_SYS_1N */ reg = <0x48>; + pinctrl-0 = <&palmas_sys_nirq_pins>; + pinctrl-names = "default"; + /* sys_nirq/ext_sys_irq pins get inverted at mpuss wakeupgen */ + interrupts = <GIC_SPI 7 IRQ_TYPE_LEVEL_LOW>; interrupt-controller; #interrupt-cells = <2>; ti,system-power-controller; diff --git a/arch/arm/boot/dts/rk3188.dtsi b/arch/arm/boot/dts/rk3188.dtsi index 4acb501dd3f8..3ed49898f4b2 100644 --- a/arch/arm/boot/dts/rk3188.dtsi +++ b/arch/arm/boot/dts/rk3188.dtsi @@ -719,7 +719,6 @@ pm_qos = <&qos_lcdc0>, <&qos_lcdc1>, <&qos_cif0>, - <&qos_cif1>, <&qos_ipp>, <&qos_rga>; }; diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index ca56537b61bc..50e89869178a 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -48,6 +48,7 @@ #define KVM_REQ_SLEEP \ KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_IRQ_PENDING KVM_ARCH_REQ(1) +#define KVM_REQ_VCPU_RESET KVM_ARCH_REQ(2) DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use); @@ -147,6 +148,13 @@ struct kvm_cpu_context { typedef struct kvm_cpu_context kvm_cpu_context_t; +struct vcpu_reset_state { + unsigned long pc; + unsigned long r0; + bool be; + bool reset; +}; + struct kvm_vcpu_arch { struct kvm_cpu_context ctxt; @@ -186,6 +194,8 @@ struct kvm_vcpu_arch { /* Cache some mmu pages needed inside spinlock regions */ struct kvm_mmu_memory_cache mmu_page_cache; + struct vcpu_reset_state reset_state; + /* Detect first run of a vcpu */ bool has_run_once; }; diff --git a/arch/arm/include/asm/stage2_pgtable.h b/arch/arm/include/asm/stage2_pgtable.h index c4b1d4fb1797..de2089501b8b 100644 --- a/arch/arm/include/asm/stage2_pgtable.h +++ b/arch/arm/include/asm/stage2_pgtable.h @@ -76,4 +76,9 @@ static inline bool kvm_stage2_has_pud(struct kvm *kvm) #define S2_PMD_MASK PMD_MASK #define S2_PMD_SIZE PMD_SIZE +static inline bool kvm_stage2_has_pmd(struct kvm *kvm) +{ + return true; +} + #endif /* __ARM_S2_PGTABLE_H_ */ diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c index 222c1635bc7a..e8bd288fd5be 100644 --- a/arch/arm/kvm/coproc.c +++ b/arch/arm/kvm/coproc.c @@ -1450,6 +1450,6 @@ void kvm_reset_coprocs(struct kvm_vcpu *vcpu) reset_coproc_regs(vcpu, table, num); for (num = 1; num < NR_CP15_REGS; num++) - if (vcpu_cp15(vcpu, num) == 0x42424242) - panic("Didn't reset vcpu_cp15(vcpu, %zi)", num); + WARN(vcpu_cp15(vcpu, num) == 0x42424242, + "Didn't reset vcpu_cp15(vcpu, %zi)", num); } diff --git a/arch/arm/kvm/reset.c b/arch/arm/kvm/reset.c index 5ed0c3ee33d6..e53327912adc 100644 --- a/arch/arm/kvm/reset.c +++ b/arch/arm/kvm/reset.c @@ -26,6 +26,7 @@ #include <asm/cputype.h> #include <asm/kvm_arm.h> #include <asm/kvm_coproc.h> +#include <asm/kvm_emulate.h> #include <kvm/arm_arch_timer.h> @@ -69,6 +70,29 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) /* Reset CP15 registers */ kvm_reset_coprocs(vcpu); + /* + * Additional reset state handling that PSCI may have imposed on us. + * Must be done after all the sys_reg reset. + */ + if (READ_ONCE(vcpu->arch.reset_state.reset)) { + unsigned long target_pc = vcpu->arch.reset_state.pc; + + /* Gracefully handle Thumb2 entry point */ + if (target_pc & 1) { + target_pc &= ~1UL; + vcpu_set_thumb(vcpu); + } + + /* Propagate caller endianness */ + if (vcpu->arch.reset_state.be) + kvm_vcpu_set_be(vcpu); + + *vcpu_pc(vcpu) = target_pc; + vcpu_set_reg(vcpu, 0, vcpu->arch.reset_state.r0); + + vcpu->arch.reset_state.reset = false; + } + /* Reset arch_timer context */ return kvm_timer_vcpu_reset(vcpu); } diff --git a/arch/arm/mach-davinci/da850.c b/arch/arm/mach-davinci/da850.c index e7b78df2bfef..a02ff431ba47 100644 --- a/arch/arm/mach-davinci/da850.c +++ b/arch/arm/mach-davinci/da850.c @@ -21,6 +21,7 @@ #include <linux/mfd/da8xx-cfgchip.h> #include <linux/platform_data/clk-da8xx-cfgchip.h> #include <linux/platform_data/clk-davinci-pll.h> +#include <linux/platform_data/davinci-cpufreq.h> #include <linux/platform_data/gpio-davinci.h> #include <linux/platform_device.h> #include <linux/regmap.h> @@ -29,7 +30,6 @@ #include <asm/mach/map.h> #include <mach/common.h> -#include <mach/cpufreq.h> #include <mach/cputype.h> #include <mach/da8xx.h> #include <mach/irqs.h> diff --git a/arch/arm/mach-davinci/include/mach/cpufreq.h b/arch/arm/mach-davinci/include/mach/cpufreq.h deleted file mode 100644 index 3c089cfb6cd6..000000000000 --- a/arch/arm/mach-davinci/include/mach/cpufreq.h +++ /dev/null @@ -1,26 +0,0 @@ -/* - * TI DaVinci CPUFreq platform support. - * - * Copyright (C) 2009 Texas Instruments, Inc. http://www.ti.com/ - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation version 2. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether express or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - */ -#ifndef _MACH_DAVINCI_CPUFREQ_H -#define _MACH_DAVINCI_CPUFREQ_H - -#include <linux/cpufreq.h> - -struct davinci_cpufreq_config { - struct cpufreq_frequency_table *freq_table; - int (*set_voltage) (unsigned int index); - int (*init) (void); -}; - -#endif diff --git a/arch/arm/mach-omap2/cpuidle44xx.c b/arch/arm/mach-omap2/cpuidle44xx.c index a8b291f00109..dae514c8276a 100644 --- a/arch/arm/mach-omap2/cpuidle44xx.c +++ b/arch/arm/mach-omap2/cpuidle44xx.c @@ -152,6 +152,10 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev, mpuss_can_lose_context = (cx->mpu_state == PWRDM_POWER_RET) && (cx->mpu_logic_state == PWRDM_POWER_OFF); + /* Enter broadcast mode for periodic timers */ + tick_broadcast_enable(); + + /* Enter broadcast mode for one-shot timers */ tick_broadcast_enter(); /* @@ -218,15 +222,6 @@ fail: return index; } -/* - * For each cpu, setup the broadcast timer because local timers - * stops for the states above C1. - */ -static void omap_setup_broadcast_timer(void *arg) -{ - tick_broadcast_enable(); -} - static struct cpuidle_driver omap4_idle_driver = { .name = "omap4_idle", .owner = THIS_MODULE, @@ -319,8 +314,5 @@ int __init omap4_idle_init(void) if (!cpu_clkdm[0] || !cpu_clkdm[1]) return -ENODEV; - /* Configure the broadcast timer on each cpu */ - on_each_cpu(omap_setup_broadcast_timer, NULL, 1); - return cpuidle_register(idle_driver, cpu_online_mask); } diff --git a/arch/arm/mach-omap2/display.c b/arch/arm/mach-omap2/display.c index f86b72d1d59e..1444b4b4bd9f 100644 --- a/arch/arm/mach-omap2/display.c +++ b/arch/arm/mach-omap2/display.c @@ -83,6 +83,7 @@ static int omap4_dsi_mux_pads(int dsi_id, unsigned lanes) u32 enable_mask, enable_shift; u32 pipd_mask, pipd_shift; u32 reg; + int ret; if (dsi_id == 0) { enable_mask = OMAP4_DSI1_LANEENABLE_MASK; @@ -98,7 +99,11 @@ static int omap4_dsi_mux_pads(int dsi_id, unsigned lanes) return -ENODEV; } - regmap_read(omap4_dsi_mux_syscon, OMAP4_DSIPHY_SYSCON_OFFSET, ®); + ret = regmap_read(omap4_dsi_mux_syscon, + OMAP4_DSIPHY_SYSCON_OFFSET, + ®); + if (ret) + return ret; reg &= ~enable_mask; reg &= ~pipd_mask; diff --git a/arch/arm/mach-omap2/omap-wakeupgen.c b/arch/arm/mach-omap2/omap-wakeupgen.c index fc5fb776a710..17558be4bf0a 100644 --- a/arch/arm/mach-omap2/omap-wakeupgen.c +++ b/arch/arm/mach-omap2/omap-wakeupgen.c @@ -50,6 +50,9 @@ #define OMAP4_NR_BANKS 4 #define OMAP4_NR_IRQS 128 +#define SYS_NIRQ1_EXT_SYS_IRQ_1 7 +#define SYS_NIRQ2_EXT_SYS_IRQ_2 119 + static void __iomem *wakeupgen_base; static void __iomem *sar_base; static DEFINE_RAW_SPINLOCK(wakeupgen_lock); @@ -153,6 +156,37 @@ static void wakeupgen_unmask(struct irq_data *d) irq_chip_unmask_parent(d); } +/* + * The sys_nirq pins bypass peripheral modules and are wired directly + * to MPUSS wakeupgen. They get automatically inverted for GIC. + */ +static int wakeupgen_irq_set_type(struct irq_data *d, unsigned int type) +{ + bool inverted = false; + + switch (type) { + case IRQ_TYPE_LEVEL_LOW: + type &= ~IRQ_TYPE_LEVEL_MASK; + type |= IRQ_TYPE_LEVEL_HIGH; + inverted = true; + break; + case IRQ_TYPE_EDGE_FALLING: + type &= ~IRQ_TYPE_EDGE_BOTH; + type |= IRQ_TYPE_EDGE_RISING; + inverted = true; + break; + default: + break; + } + + if (inverted && d->hwirq != SYS_NIRQ1_EXT_SYS_IRQ_1 && + d->hwirq != SYS_NIRQ2_EXT_SYS_IRQ_2) + pr_warn("wakeupgen: irq%li polarity inverted in dts\n", + d->hwirq); + + return irq_chip_set_type_parent(d, type); +} + #ifdef CONFIG_HOTPLUG_CPU static DEFINE_PER_CPU(u32 [MAX_NR_REG_BANKS], irqmasks); @@ -446,7 +480,7 @@ static struct irq_chip wakeupgen_chip = { .irq_mask = wakeupgen_mask, .irq_unmask = wakeupgen_unmask, .irq_retrigger = irq_chip_retrigger_hierarchy, - .irq_set_type = irq_chip_set_type_parent, + .irq_set_type = wakeupgen_irq_set_type, .flags = IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MASK_ON_SUSPEND, #ifdef CONFIG_SMP .irq_set_affinity = irq_chip_set_affinity_parent, diff --git a/arch/arm64/boot/dts/freescale/imx8mq-evk.dts b/arch/arm64/boot/dts/freescale/imx8mq-evk.dts index 64acccc4bfcb..f74b13aa5aa5 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mq-evk.dts @@ -227,34 +227,34 @@ pinctrl_usdhc1_100mhz: usdhc1-100grp { fsl,pins = < - MX8MQ_IOMUXC_SD1_CLK_USDHC1_CLK 0x85 - MX8MQ_IOMUXC_SD1_CMD_USDHC1_CMD 0xc5 - MX8MQ_IOMUXC_SD1_DATA0_USDHC1_DATA0 0xc5 - MX8MQ_IOMUXC_SD1_DATA1_USDHC1_DATA1 0xc5 - MX8MQ_IOMUXC_SD1_DATA2_USDHC1_DATA2 0xc5 - MX8MQ_IOMUXC_SD1_DATA3_USDHC1_DATA3 0xc5 - MX8MQ_IOMUXC_SD1_DATA4_USDHC1_DATA4 0xc5 - MX8MQ_IOMUXC_SD1_DATA5_USDHC1_DATA5 0xc5 - MX8MQ_IOMUXC_SD1_DATA6_USDHC1_DATA6 0xc5 - MX8MQ_IOMUXC_SD1_DATA7_USDHC1_DATA7 0xc5 - MX8MQ_IOMUXC_SD1_STROBE_USDHC1_STROBE 0x85 + MX8MQ_IOMUXC_SD1_CLK_USDHC1_CLK 0x8d + MX8MQ_IOMUXC_SD1_CMD_USDHC1_CMD 0xcd + MX8MQ_IOMUXC_SD1_DATA0_USDHC1_DATA0 0xcd + MX8MQ_IOMUXC_SD1_DATA1_USDHC1_DATA1 0xcd + MX8MQ_IOMUXC_SD1_DATA2_USDHC1_DATA2 0xcd + MX8MQ_IOMUXC_SD1_DATA3_USDHC1_DATA3 0xcd + MX8MQ_IOMUXC_SD1_DATA4_USDHC1_DATA4 0xcd + MX8MQ_IOMUXC_SD1_DATA5_USDHC1_DATA5 0xcd + MX8MQ_IOMUXC_SD1_DATA6_USDHC1_DATA6 0xcd + MX8MQ_IOMUXC_SD1_DATA7_USDHC1_DATA7 0xcd + MX8MQ_IOMUXC_SD1_STROBE_USDHC1_STROBE 0x8d MX8MQ_IOMUXC_SD1_RESET_B_USDHC1_RESET_B 0xc1 >; }; pinctrl_usdhc1_200mhz: usdhc1-200grp { fsl,pins = < - MX8MQ_IOMUXC_SD1_CLK_USDHC1_CLK 0x87 - MX8MQ_IOMUXC_SD1_CMD_USDHC1_CMD 0xc7 - MX8MQ_IOMUXC_SD1_DATA0_USDHC1_DATA0 0xc7 - MX8MQ_IOMUXC_SD1_DATA1_USDHC1_DATA1 0xc7 - MX8MQ_IOMUXC_SD1_DATA2_USDHC1_DATA2 0xc7 - MX8MQ_IOMUXC_SD1_DATA3_USDHC1_DATA3 0xc7 - MX8MQ_IOMUXC_SD1_DATA4_USDHC1_DATA4 0xc7 - MX8MQ_IOMUXC_SD1_DATA5_USDHC1_DATA5 0xc7 - MX8MQ_IOMUXC_SD1_DATA6_USDHC1_DATA6 0xc7 - MX8MQ_IOMUXC_SD1_DATA7_USDHC1_DATA7 0xc7 - MX8MQ_IOMUXC_SD1_STROBE_USDHC1_STROBE 0x87 + MX8MQ_IOMUXC_SD1_CLK_USDHC1_CLK 0x9f + MX8MQ_IOMUXC_SD1_CMD_USDHC1_CMD 0xdf + MX8MQ_IOMUXC_SD1_DATA0_USDHC1_DATA0 0xdf + MX8MQ_IOMUXC_SD1_DATA1_USDHC1_DATA1 0xdf + MX8MQ_IOMUXC_SD1_DATA2_USDHC1_DATA2 0xdf + MX8MQ_IOMUXC_SD1_DATA3_USDHC1_DATA3 0xdf + MX8MQ_IOMUXC_SD1_DATA4_USDHC1_DATA4 0xdf + MX8MQ_IOMUXC_SD1_DATA5_USDHC1_DATA5 0xdf + MX8MQ_IOMUXC_SD1_DATA6_USDHC1_DATA6 0xdf + MX8MQ_IOMUXC_SD1_DATA7_USDHC1_DATA7 0xdf + MX8MQ_IOMUXC_SD1_STROBE_USDHC1_STROBE 0x9f MX8MQ_IOMUXC_SD1_RESET_B_USDHC1_RESET_B 0xc1 >; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq.dtsi index 8e9d6d5ed7b2..b6d31499fb43 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq.dtsi @@ -360,6 +360,8 @@ <&clk IMX8MQ_CLK_NAND_USDHC_BUS>, <&clk IMX8MQ_CLK_USDHC1_ROOT>; clock-names = "ipg", "ahb", "per"; + assigned-clocks = <&clk IMX8MQ_CLK_USDHC1>; + assigned-clock-rates = <400000000>; fsl,tuning-start-tap = <20>; fsl,tuning-step = <2>; bus-width = <4>; diff --git a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts index bd937d68ca3b..040b36ef0dd2 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts @@ -40,6 +40,7 @@ pinctrl-0 = <&usb30_host_drv>; regulator-name = "vcc_host_5v"; regulator-always-on; + regulator-boot-on; vin-supply = <&vcc_sys>; }; @@ -51,6 +52,7 @@ pinctrl-0 = <&usb20_host_drv>; regulator-name = "vcc_host1_5v"; regulator-always-on; + regulator-boot-on; vin-supply = <&vcc_sys>; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-bob.dts b/arch/arm64/boot/dts/rockchip/rk3399-gru-bob.dts index 1ee0dc0d9f10..d1cf404b8708 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-gru-bob.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-bob.dts @@ -22,7 +22,7 @@ backlight = <&backlight>; power-supply = <&pp3300_disp>; - ports { + port { panel_in_edp: endpoint { remote-endpoint = <&edp_out_panel>; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts b/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts index 81e73103fa78..15e254a77391 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts @@ -43,7 +43,7 @@ backlight = <&backlight>; power-supply = <&pp3300_disp>; - ports { + port { panel_in_edp: endpoint { remote-endpoint = <&edp_out_panel>; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-sapphire-excavator.dts b/arch/arm64/boot/dts/rockchip/rk3399-sapphire-excavator.dts index 0b8f1edbd746..b48a63c3efc3 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-sapphire-excavator.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-sapphire-excavator.dts @@ -91,7 +91,7 @@ pinctrl-0 = <&lcd_panel_reset>; power-supply = <&vcc3v3_s0>; - ports { + port { panel_in_edp: endpoint { remote-endpoint = <&edp_out_panel>; }; diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 7732d0ba4e60..da3fc7324d68 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -48,6 +48,7 @@ #define KVM_REQ_SLEEP \ KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_IRQ_PENDING KVM_ARCH_REQ(1) +#define KVM_REQ_VCPU_RESET KVM_ARCH_REQ(2) DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use); @@ -208,6 +209,13 @@ struct kvm_cpu_context { typedef struct kvm_cpu_context kvm_cpu_context_t; +struct vcpu_reset_state { + unsigned long pc; + unsigned long r0; + bool be; + bool reset; +}; + struct kvm_vcpu_arch { struct kvm_cpu_context ctxt; @@ -297,6 +305,9 @@ struct kvm_vcpu_arch { /* Virtual SError ESR to restore when HCR_EL2.VSE is set */ u64 vsesr_el2; + /* Additional reset state */ + struct vcpu_reset_state reset_state; + /* True when deferrable sysregs are loaded on the physical CPU, * see kvm_vcpu_load_sysregs and kvm_vcpu_put_sysregs. */ bool sysregs_loaded_on_cpu; diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index e1ec947e7c0c..0c656850eeea 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -332,6 +332,17 @@ static inline void *phys_to_virt(phys_addr_t x) #define virt_addr_valid(kaddr) \ (_virt_addr_is_linear(kaddr) && _virt_addr_valid(kaddr)) +/* + * Given that the GIC architecture permits ITS implementations that can only be + * configured with a LPI table address once, GICv3 systems with many CPUs may + * end up reserving a lot of different regions after a kexec for their LPI + * tables (one per CPU), as we are forced to reuse the same memory after kexec + * (and thus reserve it persistently with EFI beforehand) + */ +#if defined(CONFIG_EFI) && defined(CONFIG_ARM_GIC_V3_ITS) +# define INIT_MEMBLOCK_RESERVED_REGIONS (INIT_MEMBLOCK_REGIONS + NR_CPUS + 1) +#endif + #include <asm-generic/memory_model.h> #endif diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 4b0e1231625c..d09ec76f08cf 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -313,7 +313,6 @@ void __init setup_arch(char **cmdline_p) arm64_memblock_init(); paging_init(); - efi_apply_persistent_mem_reservations(); acpi_table_upgrade(); diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index b0b1478094b4..421ebf6f7086 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -23,6 +23,7 @@ #include <kvm/arm_psci.h> #include <asm/cpufeature.h> +#include <asm/kprobes.h> #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_host.h> @@ -107,6 +108,7 @@ static void activate_traps_vhe(struct kvm_vcpu *vcpu) write_sysreg(kvm_get_hyp_vector(), vbar_el1); } +NOKPROBE_SYMBOL(activate_traps_vhe); static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu) { @@ -154,6 +156,7 @@ static void deactivate_traps_vhe(void) write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1); write_sysreg(vectors, vbar_el1); } +NOKPROBE_SYMBOL(deactivate_traps_vhe); static void __hyp_text __deactivate_traps_nvhe(void) { @@ -513,6 +516,7 @@ int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) return exit_code; } +NOKPROBE_SYMBOL(kvm_vcpu_run_vhe); /* Switch to the guest for legacy non-VHE systems */ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu) @@ -620,6 +624,7 @@ static void __hyp_call_panic_vhe(u64 spsr, u64 elr, u64 par, read_sysreg_el2(esr), read_sysreg_el2(far), read_sysreg(hpfar_el2), par, vcpu); } +NOKPROBE_SYMBOL(__hyp_call_panic_vhe); void __hyp_text __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt) { diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c index 68d6f7c3b237..b426e2cf973c 100644 --- a/arch/arm64/kvm/hyp/sysreg-sr.c +++ b/arch/arm64/kvm/hyp/sysreg-sr.c @@ -18,6 +18,7 @@ #include <linux/compiler.h> #include <linux/kvm_host.h> +#include <asm/kprobes.h> #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_hyp.h> @@ -98,12 +99,14 @@ void sysreg_save_host_state_vhe(struct kvm_cpu_context *ctxt) { __sysreg_save_common_state(ctxt); } +NOKPROBE_SYMBOL(sysreg_save_host_state_vhe); void sysreg_save_guest_state_vhe(struct kvm_cpu_context *ctxt) { __sysreg_save_common_state(ctxt); __sysreg_save_el2_return_state(ctxt); } +NOKPROBE_SYMBOL(sysreg_save_guest_state_vhe); static void __hyp_text __sysreg_restore_common_state(struct kvm_cpu_context *ctxt) { @@ -188,12 +191,14 @@ void sysreg_restore_host_state_vhe(struct kvm_cpu_context *ctxt) { __sysreg_restore_common_state(ctxt); } +NOKPROBE_SYMBOL(sysreg_restore_host_state_vhe); void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt) { __sysreg_restore_common_state(ctxt); __sysreg_restore_el2_return_state(ctxt); } +NOKPROBE_SYMBOL(sysreg_restore_guest_state_vhe); void __hyp_text __sysreg32_save_state(struct kvm_vcpu *vcpu) { diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index b72a3dd56204..f16a5f8ff2b4 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -32,6 +32,7 @@ #include <asm/kvm_arm.h> #include <asm/kvm_asm.h> #include <asm/kvm_coproc.h> +#include <asm/kvm_emulate.h> #include <asm/kvm_mmu.h> /* Maximum phys_shift supported for any VM on this host */ @@ -105,16 +106,33 @@ int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext) * This function finds the right table above and sets the registers on * the virtual CPU struct to their architecturally defined reset * values. + * + * Note: This function can be called from two paths: The KVM_ARM_VCPU_INIT + * ioctl or as part of handling a request issued by another VCPU in the PSCI + * handling code. In the first case, the VCPU will not be loaded, and in the + * second case the VCPU will be loaded. Because this function operates purely + * on the memory-backed valus of system registers, we want to do a full put if + * we were loaded (handling a request) and load the values back at the end of + * the function. Otherwise we leave the state alone. In both cases, we + * disable preemption around the vcpu reset as we would otherwise race with + * preempt notifiers which also call put/load. */ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) { const struct kvm_regs *cpu_reset; + int ret = -EINVAL; + bool loaded; + + preempt_disable(); + loaded = (vcpu->cpu != -1); + if (loaded) + kvm_arch_vcpu_put(vcpu); switch (vcpu->arch.target) { default: if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) { if (!cpu_has_32bit_el1()) - return -EINVAL; + goto out; cpu_reset = &default_regs_reset32; } else { cpu_reset = &default_regs_reset; @@ -129,6 +147,29 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) /* Reset system registers */ kvm_reset_sys_regs(vcpu); + /* + * Additional reset state handling that PSCI may have imposed on us. + * Must be done after all the sys_reg reset. + */ + if (vcpu->arch.reset_state.reset) { + unsigned long target_pc = vcpu->arch.reset_state.pc; + + /* Gracefully handle Thumb2 entry point */ + if (vcpu_mode_is_32bit(vcpu) && (target_pc & 1)) { + target_pc &= ~1UL; + vcpu_set_thumb(vcpu); + } + + /* Propagate caller endianness */ + if (vcpu->arch.reset_state.be) + kvm_vcpu_set_be(vcpu); + + *vcpu_pc(vcpu) = target_pc; + vcpu_set_reg(vcpu, 0, vcpu->arch.reset_state.r0); + + vcpu->arch.reset_state.reset = false; + } + /* Reset PMU */ kvm_pmu_vcpu_reset(vcpu); @@ -137,7 +178,12 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) vcpu->arch.workaround_flags |= VCPU_WORKAROUND_2_FLAG; /* Reset timer */ - return kvm_timer_vcpu_reset(vcpu); + ret = kvm_timer_vcpu_reset(vcpu); +out: + if (loaded) + kvm_arch_vcpu_load(vcpu, smp_processor_id()); + preempt_enable(); + return ret; } void kvm_set_ipa_limit(void) diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index e3e37228ae4e..c936aa40c3f4 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -314,12 +314,29 @@ static bool trap_raz_wi(struct kvm_vcpu *vcpu, return read_zero(vcpu, p); } -static bool trap_undef(struct kvm_vcpu *vcpu, - struct sys_reg_params *p, - const struct sys_reg_desc *r) +/* + * ARMv8.1 mandates at least a trivial LORegion implementation, where all the + * RW registers are RES0 (which we can implement as RAZ/WI). On an ARMv8.0 + * system, these registers should UNDEF. LORID_EL1 being a RO register, we + * treat it separately. + */ +static bool trap_loregion(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) { - kvm_inject_undefined(vcpu); - return false; + u64 val = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); + u32 sr = sys_reg((u32)r->Op0, (u32)r->Op1, + (u32)r->CRn, (u32)r->CRm, (u32)r->Op2); + + if (!(val & (0xfUL << ID_AA64MMFR1_LOR_SHIFT))) { + kvm_inject_undefined(vcpu); + return false; + } + + if (p->is_write && sr == SYS_LORID_EL1) + return write_to_read_only(vcpu, p, r); + + return trap_raz_wi(vcpu, p, r); } static bool trap_oslsr_el1(struct kvm_vcpu *vcpu, @@ -1048,11 +1065,6 @@ static u64 read_id_reg(struct sys_reg_desc const *r, bool raz) if (val & ptrauth_mask) kvm_debug("ptrauth unsupported for guests, suppressing\n"); val &= ~ptrauth_mask; - } else if (id == SYS_ID_AA64MMFR1_EL1) { - if (val & (0xfUL << ID_AA64MMFR1_LOR_SHIFT)) - kvm_debug("LORegions unsupported for guests, suppressing\n"); - - val &= ~(0xfUL << ID_AA64MMFR1_LOR_SHIFT); } return val; @@ -1338,11 +1350,11 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_MAIR_EL1), access_vm_reg, reset_unknown, MAIR_EL1 }, { SYS_DESC(SYS_AMAIR_EL1), access_vm_reg, reset_amair_el1, AMAIR_EL1 }, - { SYS_DESC(SYS_LORSA_EL1), trap_undef }, - { SYS_DESC(SYS_LOREA_EL1), trap_undef }, - { SYS_DESC(SYS_LORN_EL1), trap_undef }, - { SYS_DESC(SYS_LORC_EL1), trap_undef }, - { SYS_DESC(SYS_LORID_EL1), trap_undef }, + { SYS_DESC(SYS_LORSA_EL1), trap_loregion }, + { SYS_DESC(SYS_LOREA_EL1), trap_loregion }, + { SYS_DESC(SYS_LORN_EL1), trap_loregion }, + { SYS_DESC(SYS_LORC_EL1), trap_loregion }, + { SYS_DESC(SYS_LORID_EL1), trap_loregion }, { SYS_DESC(SYS_VBAR_EL1), NULL, reset_val, VBAR_EL1, 0 }, { SYS_DESC(SYS_DISR_EL1), NULL, reset_val, DISR_EL1, 0 }, @@ -2596,7 +2608,9 @@ void kvm_reset_sys_regs(struct kvm_vcpu *vcpu) table = get_target_table(vcpu->arch.target, true, &num); reset_sys_reg_descs(vcpu, table, num); - for (num = 1; num < NR_SYS_REGS; num++) - if (__vcpu_sys_reg(vcpu, num) == 0x4242424242424242) - panic("Didn't reset __vcpu_sys_reg(%zi)", num); + for (num = 1; num < NR_SYS_REGS; num++) { + if (WARN(__vcpu_sys_reg(vcpu, num) == 0x4242424242424242, + "Didn't reset __vcpu_sys_reg(%zi)\n", num)) + break; + } } diff --git a/arch/csky/include/asm/pgtable.h b/arch/csky/include/asm/pgtable.h index edfcbb25fd9f..dcea277c09ae 100644 --- a/arch/csky/include/asm/pgtable.h +++ b/arch/csky/include/asm/pgtable.h @@ -45,8 +45,8 @@ ((pte_t *)page_address(pmd_page(*(dir))) + __pte_offset_t(address)) #define pmd_page(pmd) (pfn_to_page(pmd_phys(pmd) >> PAGE_SHIFT)) #define pte_clear(mm, addr, ptep) set_pte((ptep), \ - (((unsigned int)addr&0x80000000)?__pte(1):__pte(0))) -#define pte_none(pte) (!(pte_val(pte)&0xfffffffe)) + (((unsigned int) addr & PAGE_OFFSET) ? __pte(_PAGE_GLOBAL) : __pte(0))) +#define pte_none(pte) (!(pte_val(pte) & ~_PAGE_GLOBAL)) #define pte_present(pte) (pte_val(pte) & _PAGE_PRESENT) #define pte_pfn(x) ((unsigned long)((x).pte_low >> PAGE_SHIFT)) #define pfn_pte(pfn, prot) __pte(((unsigned long long)(pfn) << PAGE_SHIFT) \ @@ -241,6 +241,11 @@ static inline pte_t pte_mkyoung(pte_t pte) #define pgd_index(address) ((address) >> PGDIR_SHIFT) +#define __HAVE_PHYS_MEM_ACCESS_PROT +struct file; +extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, + unsigned long size, pgprot_t vma_prot); + /* * Macro to make mark a page protection value as "uncacheable". Note * that "protection" is really a misnomer here as the protection value diff --git a/arch/csky/include/asm/processor.h b/arch/csky/include/asm/processor.h index 8f454810514f..21e0bd5293dd 100644 --- a/arch/csky/include/asm/processor.h +++ b/arch/csky/include/asm/processor.h @@ -49,7 +49,7 @@ struct thread_struct { }; #define INIT_THREAD { \ - .ksp = (unsigned long) init_thread_union.stack + THREAD_SIZE, \ + .ksp = sizeof(init_stack) + (unsigned long) &init_stack, \ .sr = DEFAULT_PSR_VALUE, \ } @@ -95,7 +95,7 @@ unsigned long get_wchan(struct task_struct *p); #define KSTK_ESP(tsk) (task_pt_regs(tsk)->usp) #define task_pt_regs(p) \ - ((struct pt_regs *)(THREAD_SIZE + p->stack) - 1) + ((struct pt_regs *)(THREAD_SIZE + task_stack_page(p)) - 1) #define cpu_relax() barrier() diff --git a/arch/csky/kernel/dumpstack.c b/arch/csky/kernel/dumpstack.c index 659253e9989c..d67f9777cfd9 100644 --- a/arch/csky/kernel/dumpstack.c +++ b/arch/csky/kernel/dumpstack.c @@ -38,7 +38,11 @@ void show_stack(struct task_struct *task, unsigned long *stack) if (task) stack = (unsigned long *)thread_saved_fp(task); else +#ifdef CONFIG_STACKTRACE + asm volatile("mov %0, r8\n":"=r"(stack)::"memory"); +#else stack = (unsigned long *)&stack; +#endif } show_trace(stack); diff --git a/arch/csky/kernel/ptrace.c b/arch/csky/kernel/ptrace.c index 57f1afe19a52..f2f12fff36f7 100644 --- a/arch/csky/kernel/ptrace.c +++ b/arch/csky/kernel/ptrace.c @@ -8,6 +8,7 @@ #include <linux/ptrace.h> #include <linux/regset.h> #include <linux/sched.h> +#include <linux/sched/task_stack.h> #include <linux/signal.h> #include <linux/smp.h> #include <linux/uaccess.h> @@ -159,7 +160,7 @@ static int fpr_set(struct task_struct *target, static const struct user_regset csky_regsets[] = { [REGSET_GPR] = { .core_note_type = NT_PRSTATUS, - .n = ELF_NGREG, + .n = sizeof(struct pt_regs) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), .get = &gpr_get, diff --git a/arch/csky/kernel/smp.c b/arch/csky/kernel/smp.c index ddc4dd79f282..b07a534b3062 100644 --- a/arch/csky/kernel/smp.c +++ b/arch/csky/kernel/smp.c @@ -160,7 +160,8 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle) { unsigned long mask = 1 << cpu; - secondary_stack = (unsigned int)tidle->stack + THREAD_SIZE - 8; + secondary_stack = + (unsigned int) task_stack_page(tidle) + THREAD_SIZE - 8; secondary_hint = mfcr("cr31"); secondary_ccr = mfcr("cr18"); diff --git a/arch/csky/mm/ioremap.c b/arch/csky/mm/ioremap.c index cb7c03e5cd21..8473b6bdf512 100644 --- a/arch/csky/mm/ioremap.c +++ b/arch/csky/mm/ioremap.c @@ -46,3 +46,17 @@ void iounmap(void __iomem *addr) vunmap((void *)((unsigned long)addr & PAGE_MASK)); } EXPORT_SYMBOL(iounmap); + +pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, + unsigned long size, pgprot_t vma_prot) +{ + if (!pfn_valid(pfn)) { + vma_prot.pgprot |= _PAGE_SO; + return pgprot_noncached(vma_prot); + } else if (file->f_flags & O_SYNC) { + return pgprot_noncached(vma_prot); + } + + return vma_prot; +} +EXPORT_SYMBOL(phys_mem_access_prot); diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index c9bfe526ca9d..d8c8d7c9df15 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -904,7 +904,7 @@ static inline int pud_none(pud_t pud) static inline int pud_present(pud_t pud) { - return (pud_raw(pud) & cpu_to_be64(_PAGE_PRESENT)); + return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PRESENT)); } extern struct page *pud_page(pud_t pud); @@ -951,7 +951,7 @@ static inline int pgd_none(pgd_t pgd) static inline int pgd_present(pgd_t pgd) { - return (pgd_raw(pgd) & cpu_to_be64(_PAGE_PRESENT)); + return !!(pgd_raw(pgd) & cpu_to_be64(_PAGE_PRESENT)); } static inline pte_t pgd_pte(pgd_t pgd) diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h index 2fa2942be221..470755cb7558 100644 --- a/arch/riscv/include/asm/pgtable-bits.h +++ b/arch/riscv/include/asm/pgtable-bits.h @@ -35,6 +35,12 @@ #define _PAGE_SPECIAL _PAGE_SOFT #define _PAGE_TABLE _PAGE_PRESENT +/* + * _PAGE_PROT_NONE is set on not-present pages (and ignored by the hardware) to + * distinguish them from swapped out pages + */ +#define _PAGE_PROT_NONE _PAGE_READ + #define _PAGE_PFN_SHIFT 10 /* Set of bits to preserve across pte_modify() */ diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 16301966d65b..a8179a8c1491 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -44,7 +44,7 @@ /* Page protection bits */ #define _PAGE_BASE (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_USER) -#define PAGE_NONE __pgprot(0) +#define PAGE_NONE __pgprot(_PAGE_PROT_NONE) #define PAGE_READ __pgprot(_PAGE_BASE | _PAGE_READ) #define PAGE_WRITE __pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_WRITE) #define PAGE_EXEC __pgprot(_PAGE_BASE | _PAGE_EXEC) @@ -98,7 +98,7 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; static inline int pmd_present(pmd_t pmd) { - return (pmd_val(pmd) & _PAGE_PRESENT); + return (pmd_val(pmd) & (_PAGE_PRESENT | _PAGE_PROT_NONE)); } static inline int pmd_none(pmd_t pmd) @@ -178,7 +178,7 @@ static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long addr) static inline int pte_present(pte_t pte) { - return (pte_val(pte) & _PAGE_PRESENT); + return (pte_val(pte) & (_PAGE_PRESENT | _PAGE_PROT_NONE)); } static inline int pte_none(pte_t pte) @@ -380,7 +380,7 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma, * * Format of swap PTE: * bit 0: _PAGE_PRESENT (zero) - * bit 1: reserved for future use (zero) + * bit 1: _PAGE_PROT_NONE (zero) * bits 2 to 6: swap type * bits 7 to XLEN-1: swap offset */ diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S index 1e1395d63dab..65df1dfdc303 100644 --- a/arch/riscv/kernel/vmlinux.lds.S +++ b/arch/riscv/kernel/vmlinux.lds.S @@ -18,8 +18,6 @@ #include <asm/cache.h> #include <asm/thread_info.h> -#define MAX_BYTES_PER_LONG 0x10 - OUTPUT_ARCH(riscv) ENTRY(_start) @@ -76,6 +74,8 @@ SECTIONS *(.sbss*) } + BSS_SECTION(PAGE_SIZE, PAGE_SIZE, 0) + EXCEPTION_TABLE(0x10) NOTES @@ -83,10 +83,6 @@ SECTIONS *(.rel.dyn*) } - BSS_SECTION(MAX_BYTES_PER_LONG, - MAX_BYTES_PER_LONG, - MAX_BYTES_PER_LONG) - _end = .; STABS_DEBUG diff --git a/arch/s390/kernel/swsusp.S b/arch/s390/kernel/swsusp.S index 537f97fde37f..b6796e616812 100644 --- a/arch/s390/kernel/swsusp.S +++ b/arch/s390/kernel/swsusp.S @@ -30,10 +30,10 @@ .section .text ENTRY(swsusp_arch_suspend) lg %r1,__LC_NODAT_STACK - aghi %r1,-STACK_FRAME_OVERHEAD stmg %r6,%r15,__SF_GPRS(%r1) + aghi %r1,-STACK_FRAME_OVERHEAD stg %r15,__SF_BACKCHAIN(%r1) - lgr %r1,%r15 + lgr %r15,%r1 /* Store FPU registers */ brasl %r14,save_fpu_regs diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index a966d7bfac57..4266a4de3160 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -382,7 +382,9 @@ static void zpci_irq_handler(struct airq_struct *airq) if (ai == -1UL) break; inc_irq_stat(IRQIO_MSI); + airq_iv_lock(aibv, ai); generic_handle_irq(airq_iv_get_data(aibv, ai)); + airq_iv_unlock(aibv, ai); } } } @@ -408,7 +410,7 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) zdev->aisb = aisb; /* Create adapter interrupt vector */ - zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA); + zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | AIRQ_IV_BITLOCK); if (!zdev->aibv) return -ENOMEM; diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 374a19712e20..b684f0294f35 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2278,6 +2278,19 @@ void perf_check_microcode(void) x86_pmu.check_microcode(); } +static int x86_pmu_check_period(struct perf_event *event, u64 value) +{ + if (x86_pmu.check_period && x86_pmu.check_period(event, value)) + return -EINVAL; + + if (value && x86_pmu.limit_period) { + if (x86_pmu.limit_period(event, value) > value) + return -EINVAL; + } + + return 0; +} + static struct pmu pmu = { .pmu_enable = x86_pmu_enable, .pmu_disable = x86_pmu_disable, @@ -2302,6 +2315,7 @@ static struct pmu pmu = { .event_idx = x86_pmu_event_idx, .sched_task = x86_pmu_sched_task, .task_ctx_size = sizeof(struct x86_perf_task_context), + .check_period = x86_pmu_check_period, }; void arch_perf_update_userpage(struct perf_event *event, diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index daafb893449b..730978dff63f 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3587,6 +3587,11 @@ static void intel_pmu_sched_task(struct perf_event_context *ctx, intel_pmu_lbr_sched_task(ctx, sched_in); } +static int intel_pmu_check_period(struct perf_event *event, u64 value) +{ + return intel_pmu_has_bts_period(event, value) ? -EINVAL : 0; +} + PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63"); PMU_FORMAT_ATTR(ldlat, "config1:0-15"); @@ -3667,6 +3672,8 @@ static __initconst const struct x86_pmu core_pmu = { .cpu_starting = intel_pmu_cpu_starting, .cpu_dying = intel_pmu_cpu_dying, .cpu_dead = intel_pmu_cpu_dead, + + .check_period = intel_pmu_check_period, }; static struct attribute *intel_pmu_attrs[]; @@ -3711,6 +3718,8 @@ static __initconst const struct x86_pmu intel_pmu = { .guest_get_msrs = intel_guest_get_msrs, .sched_task = intel_pmu_sched_task, + + .check_period = intel_pmu_check_period, }; static __init void intel_clovertown_quirk(void) diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 78d7b7031bfc..d46fd6754d92 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -646,6 +646,11 @@ struct x86_pmu { * Intel host/guest support (KVM) */ struct perf_guest_switch_msr *(*guest_get_msrs)(int *nr); + + /* + * Check period value for PERF_EVENT_IOC_PERIOD ioctl. + */ + int (*check_period) (struct perf_event *event, u64 period); }; struct x86_perf_task_context { @@ -857,7 +862,7 @@ static inline int amd_pmu_init(void) #ifdef CONFIG_CPU_SUP_INTEL -static inline bool intel_pmu_has_bts(struct perf_event *event) +static inline bool intel_pmu_has_bts_period(struct perf_event *event, u64 period) { struct hw_perf_event *hwc = &event->hw; unsigned int hw_event, bts_event; @@ -868,7 +873,14 @@ static inline bool intel_pmu_has_bts(struct perf_event *event) hw_event = hwc->config & INTEL_ARCH_EVENT_MASK; bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS); - return hw_event == bts_event && hwc->sample_period == 1; + return hw_event == bts_event && period == 1; +} + +static inline bool intel_pmu_has_bts(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + return intel_pmu_has_bts_period(event, hwc->sample_period); } int intel_pmu_save_and_restart(struct perf_event *event); diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index f65b78d32f5e..7dbbe9ffda17 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -51,7 +51,7 @@ static unsigned long get_dr(int n) /* * fill in the user structure for a core dump.. */ -static void dump_thread32(struct pt_regs *regs, struct user32 *dump) +static void fill_dump(struct pt_regs *regs, struct user32 *dump) { u32 fs, gs; memset(dump, 0, sizeof(*dump)); @@ -157,10 +157,12 @@ static int aout_core_dump(struct coredump_params *cprm) fs = get_fs(); set_fs(KERNEL_DS); has_dumped = 1; + + fill_dump(cprm->regs, &dump); + strncpy(dump.u_comm, current->comm, sizeof(current->comm)); dump.u_ar0 = offsetof(struct user32, regs); dump.signal = cprm->siginfo->si_signo; - dump_thread32(cprm->regs, &dump); /* * If the size of the dump file exceeds the rlimit, then see diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index d9a9993af882..9f15384c504a 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -52,6 +52,8 @@ #define INTEL_FAM6_CANNONLAKE_MOBILE 0x66 +#define INTEL_FAM6_ICELAKE_MOBILE 0x7E + /* "Small Core" Processors (Atom) */ #define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */ diff --git a/arch/x86/include/asm/uv/bios.h b/arch/x86/include/asm/uv/bios.h index e652a7cc6186..3f697a9e3f59 100644 --- a/arch/x86/include/asm/uv/bios.h +++ b/arch/x86/include/asm/uv/bios.h @@ -48,7 +48,8 @@ enum { BIOS_STATUS_SUCCESS = 0, BIOS_STATUS_UNIMPLEMENTED = -ENOSYS, BIOS_STATUS_EINVAL = -EINVAL, - BIOS_STATUS_UNAVAIL = -EBUSY + BIOS_STATUS_UNAVAIL = -EBUSY, + BIOS_STATUS_ABORT = -EINTR, }; /* Address map parameters */ @@ -167,4 +168,9 @@ extern long system_serial_number; extern struct kobject *sgi_uv_kobj; /* /sys/firmware/sgi_uv */ +/* + * EFI runtime lock; cf. firmware/efi/runtime-wrappers.c for details + */ +extern struct semaphore __efi_uv_runtime_lock; + #endif /* _ASM_X86_UV_BIOS_H */ diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index d8ea4ebd79e7..d737a51a53ca 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -2473,6 +2473,10 @@ static int nested_check_vm_execution_controls(struct kvm_vcpu *vcpu, (nested_cpu_has_vpid(vmcs12) && !vmcs12->virtual_processor_id)) return -EINVAL; + if (!nested_cpu_has_preemption_timer(vmcs12) && + nested_cpu_has_save_preemption_timer(vmcs12)) + return -EINVAL; + if (nested_cpu_has_ept(vmcs12) && !valid_ept_address(vcpu, vmcs12->ept_pointer)) return -EINVAL; @@ -5557,9 +5561,11 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps, * secondary cpu-based controls. Do not include those that * depend on CPUID bits, they are added later by vmx_cpuid_update. */ - rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2, - msrs->secondary_ctls_low, - msrs->secondary_ctls_high); + if (msrs->procbased_ctls_high & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) + rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2, + msrs->secondary_ctls_low, + msrs->secondary_ctls_high); + msrs->secondary_ctls_low = 0; msrs->secondary_ctls_high &= SECONDARY_EXEC_DESC | diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 95d618045001..30a6bcd735ec 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -863,7 +863,8 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, if (!entry_only) j = find_msr(&m->host, msr); - if (i == NR_AUTOLOAD_MSRS || j == NR_AUTOLOAD_MSRS) { + if ((i < 0 && m->guest.nr == NR_AUTOLOAD_MSRS) || + (j < 0 && m->host.nr == NR_AUTOLOAD_MSRS)) { printk_once(KERN_WARNING "Not enough msr switch entries. " "Can't add msr %x\n", msr); return; @@ -1193,21 +1194,6 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu) return; - /* - * First handle the simple case where no cmpxchg is necessary; just - * allow posting non-urgent interrupts. - * - * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change - * PI.NDST: pi_post_block will do it for us and the wakeup_handler - * expects the VCPU to be on the blocked_vcpu_list that matches - * PI.NDST. - */ - if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR || - vcpu->cpu == cpu) { - pi_clear_sn(pi_desc); - return; - } - /* The full case. */ do { old.control = new.control = pi_desc->control; @@ -1222,6 +1208,17 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) new.sn = 0; } while (cmpxchg64(&pi_desc->control, old.control, new.control) != old.control); + + /* + * Clear SN before reading the bitmap. The VT-d firmware + * writes the bitmap and reads SN atomically (5.2.3 in the + * spec), so it doesn't really have a memory barrier that + * pairs with this, but we cannot do that and we need one. + */ + smp_mb__after_atomic(); + + if (!bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS)) + pi_set_on(pi_desc); } /* diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 99328954c2fc..0ac0a64c7790 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -337,16 +337,16 @@ static inline int pi_test_and_set_pir(int vector, struct pi_desc *pi_desc) return test_and_set_bit(vector, (unsigned long *)pi_desc->pir); } -static inline void pi_clear_sn(struct pi_desc *pi_desc) +static inline void pi_set_sn(struct pi_desc *pi_desc) { - return clear_bit(POSTED_INTR_SN, + return set_bit(POSTED_INTR_SN, (unsigned long *)&pi_desc->control); } -static inline void pi_set_sn(struct pi_desc *pi_desc) +static inline void pi_set_on(struct pi_desc *pi_desc) { - return set_bit(POSTED_INTR_SN, - (unsigned long *)&pi_desc->control); + set_bit(POSTED_INTR_ON, + (unsigned long *)&pi_desc->control); } static inline void pi_clear_on(struct pi_desc *pi_desc) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e67ecf25e690..941f932373d0 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7801,7 +7801,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * 1) We should set ->mode before checking ->requests. Please see * the comment in kvm_vcpu_exiting_guest_mode(). * - * 2) For APICv, we should set ->mode before checking PIR.ON. This + * 2) For APICv, we should set ->mode before checking PID.ON. This * pairs with the memory barrier implicit in pi_test_and_set_on * (see vmx_deliver_posted_interrupt). * diff --git a/arch/x86/platform/uv/bios_uv.c b/arch/x86/platform/uv/bios_uv.c index 4a6a5a26c582..eb33432f2f24 100644 --- a/arch/x86/platform/uv/bios_uv.c +++ b/arch/x86/platform/uv/bios_uv.c @@ -29,7 +29,8 @@ struct uv_systab *uv_systab; -s64 uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, u64 a4, u64 a5) +static s64 __uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, + u64 a4, u64 a5) { struct uv_systab *tab = uv_systab; s64 ret; @@ -51,6 +52,19 @@ s64 uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, u64 a4, u64 a5) return ret; } + +s64 uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, u64 a4, u64 a5) +{ + s64 ret; + + if (down_interruptible(&__efi_uv_runtime_lock)) + return BIOS_STATUS_ABORT; + + ret = __uv_bios_call(which, a1, a2, a3, a4, a5); + up(&__efi_uv_runtime_lock); + + return ret; +} EXPORT_SYMBOL_GPL(uv_bios_call); s64 uv_bios_call_irqsave(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, @@ -59,10 +73,15 @@ s64 uv_bios_call_irqsave(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, unsigned long bios_flags; s64 ret; + if (down_interruptible(&__efi_uv_runtime_lock)) + return BIOS_STATUS_ABORT; + local_irq_save(bios_flags); - ret = uv_bios_call(which, a1, a2, a3, a4, a5); + ret = __uv_bios_call(which, a1, a2, a3, a4, a5); local_irq_restore(bios_flags); + up(&__efi_uv_runtime_lock); + return ret; } diff --git a/block/blk-mq.c b/block/blk-mq.c index 8f5b533764ca..9437a5eb07cf 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -737,12 +737,20 @@ static void blk_mq_requeue_work(struct work_struct *work) spin_unlock_irq(&q->requeue_lock); list_for_each_entry_safe(rq, next, &rq_list, queuelist) { - if (!(rq->rq_flags & RQF_SOFTBARRIER)) + if (!(rq->rq_flags & (RQF_SOFTBARRIER | RQF_DONTPREP))) continue; rq->rq_flags &= ~RQF_SOFTBARRIER; list_del_init(&rq->queuelist); - blk_mq_sched_insert_request(rq, true, false, false); + /* + * If RQF_DONTPREP, rq has contained some driver specific + * data, so insert it to hctx dispatch list to avoid any + * merge. + */ + if (rq->rq_flags & RQF_DONTPREP) + blk_mq_request_bypass_insert(rq, false); + else + blk_mq_sched_insert_request(rq, true, false, false); } while (!list_empty(&rq_list)) { diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index 217a782c3e55..1b207fca1420 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -1051,6 +1051,48 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val) } /** + * cppc_get_desired_perf - Get the value of desired performance register. + * @cpunum: CPU from which to get desired performance. + * @desired_perf: address of a variable to store the returned desired performance + * + * Return: 0 for success, -EIO otherwise. + */ +int cppc_get_desired_perf(int cpunum, u64 *desired_perf) +{ + struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpunum); + int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpunum); + struct cpc_register_resource *desired_reg; + struct cppc_pcc_data *pcc_ss_data = NULL; + + desired_reg = &cpc_desc->cpc_regs[DESIRED_PERF]; + + if (CPC_IN_PCC(desired_reg)) { + int ret = 0; + + if (pcc_ss_id < 0) + return -EIO; + + pcc_ss_data = pcc_data[pcc_ss_id]; + + down_write(&pcc_ss_data->pcc_lock); + + if (send_pcc_cmd(pcc_ss_id, CMD_READ) >= 0) + cpc_read(cpunum, desired_reg, desired_perf); + else + ret = -EIO; + + up_write(&pcc_ss_data->pcc_lock); + + return ret; + } + + cpc_read(cpunum, desired_reg, desired_perf); + + return 0; +} +EXPORT_SYMBOL_GPL(cppc_get_desired_perf); + +/** * cppc_get_perf_caps - Get a CPUs performance capabilities. * @cpunum: CPU from which to get capabilities info. * @perf_caps: ptr to cppc_perf_caps. See cppc_acpi.h diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index b2131c4ea124..98d4ec5bf450 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -282,6 +282,13 @@ static int acpi_processor_get_power_info_fadt(struct acpi_processor *pr) pr->power.states[ACPI_STATE_C2].address, pr->power.states[ACPI_STATE_C3].address)); + snprintf(pr->power.states[ACPI_STATE_C2].desc, + ACPI_CX_DESC_LEN, "ACPI P_LVL2 IOPORT 0x%x", + pr->power.states[ACPI_STATE_C2].address); + snprintf(pr->power.states[ACPI_STATE_C3].desc, + ACPI_CX_DESC_LEN, "ACPI P_LVL3 IOPORT 0x%x", + pr->power.states[ACPI_STATE_C3].address); + return 0; } diff --git a/drivers/auxdisplay/ht16k33.c b/drivers/auxdisplay/ht16k33.c index a43276c76fc6..21393ec3b9a4 100644 --- a/drivers/auxdisplay/ht16k33.c +++ b/drivers/auxdisplay/ht16k33.c @@ -509,7 +509,7 @@ static int ht16k33_remove(struct i2c_client *client) struct ht16k33_priv *priv = i2c_get_clientdata(client); struct ht16k33_fbdev *fbdev = &priv->fbdev; - cancel_delayed_work(&fbdev->work); + cancel_delayed_work_sync(&fbdev->work); unregister_framebuffer(fbdev->info); framebuffer_release(fbdev->info); free_page((unsigned long) fbdev->buffer); diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index eb9443d5bae1..6ce93a52bf3f 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -427,6 +427,7 @@ __cpu_device_create(struct device *parent, void *drvdata, dev->parent = parent; dev->groups = groups; dev->release = device_create_release; + device_set_pm_not_required(dev); dev_set_drvdata(dev, drvdata); retval = kobject_set_name_vargs(&dev->kobj, fmt, args); diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c index 5a42ae4078c2..365ad751ce0f 100644 --- a/drivers/base/power/clock_ops.c +++ b/drivers/base/power/clock_ops.c @@ -65,10 +65,15 @@ static void pm_clk_acquire(struct device *dev, struct pm_clock_entry *ce) if (IS_ERR(ce->clk)) { ce->status = PCE_STATUS_ERROR; } else { - clk_prepare(ce->clk); - ce->status = PCE_STATUS_ACQUIRED; - dev_dbg(dev, "Clock %pC con_id %s managed by runtime PM.\n", - ce->clk, ce->con_id); + if (clk_prepare(ce->clk)) { + ce->status = PCE_STATUS_ERROR; + dev_err(dev, "clk_prepare() failed\n"); + } else { + ce->status = PCE_STATUS_ACQUIRED; + dev_dbg(dev, + "Clock %pC con_id %s managed by runtime PM.\n", + ce->clk, ce->con_id); + } } } diff --git a/drivers/base/power/common.c b/drivers/base/power/common.c index b413951c6abc..22aedb28aad7 100644 --- a/drivers/base/power/common.c +++ b/drivers/base/power/common.c @@ -160,7 +160,7 @@ EXPORT_SYMBOL_GPL(dev_pm_domain_attach_by_id); * For a detailed function description, see dev_pm_domain_attach_by_id(). */ struct device *dev_pm_domain_attach_by_name(struct device *dev, - char *name) + const char *name) { if (dev->pm_domain) return ERR_PTR(-EEXIST); diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 500de1dee967..2c334c01fc43 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -2483,7 +2483,7 @@ EXPORT_SYMBOL_GPL(genpd_dev_pm_attach_by_id); * power-domain-names DT property. For further description see * genpd_dev_pm_attach_by_id(). */ -struct device *genpd_dev_pm_attach_by_name(struct device *dev, char *name) +struct device *genpd_dev_pm_attach_by_name(struct device *dev, const char *name) { int index; @@ -2948,18 +2948,11 @@ static int __init genpd_debug_init(void) genpd_debugfs_dir = debugfs_create_dir("pm_genpd", NULL); - if (!genpd_debugfs_dir) - return -ENOMEM; - - d = debugfs_create_file("pm_genpd_summary", S_IRUGO, - genpd_debugfs_dir, NULL, &summary_fops); - if (!d) - return -ENOMEM; + debugfs_create_file("pm_genpd_summary", S_IRUGO, genpd_debugfs_dir, + NULL, &summary_fops); list_for_each_entry(genpd, &gpd_list, gpd_list_node) { d = debugfs_create_dir(genpd->name, genpd_debugfs_dir); - if (!d) - return -ENOMEM; debugfs_create_file("current_state", 0444, d, genpd, &status_fops); diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index 0992e67e862b..893ae464bfd6 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -124,6 +124,10 @@ void device_pm_unlock(void) */ void device_pm_add(struct device *dev) { + /* Skip PM setup/initialization. */ + if (device_pm_not_required(dev)) + return; + pr_debug("PM: Adding info for %s:%s\n", dev->bus ? dev->bus->name : "No Bus", dev_name(dev)); device_pm_check_callbacks(dev); @@ -142,6 +146,9 @@ void device_pm_add(struct device *dev) */ void device_pm_remove(struct device *dev) { + if (device_pm_not_required(dev)) + return; + pr_debug("PM: Removing info for %s:%s\n", dev->bus ? dev->bus->name : "No Bus", dev_name(dev)); complete_all(&dev->power.completion); @@ -1741,8 +1748,10 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) if (dev->power.direct_complete) { if (pm_runtime_status_suspended(dev)) { pm_runtime_disable(dev); - if (pm_runtime_status_suspended(dev)) + if (pm_runtime_status_suspended(dev)) { + pm_dev_dbg(dev, state, "direct-complete "); goto Complete; + } pm_runtime_enable(dev); } diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 0ea2139c50d8..78937c45278c 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -66,20 +66,30 @@ static int rpm_suspend(struct device *dev, int rpmflags); */ void update_pm_runtime_accounting(struct device *dev) { - unsigned long now = jiffies; - unsigned long delta; + u64 now, last, delta; - delta = now - dev->power.accounting_timestamp; + if (dev->power.disable_depth > 0) + return; + + last = dev->power.accounting_timestamp; + now = ktime_get_mono_fast_ns(); dev->power.accounting_timestamp = now; - if (dev->power.disable_depth > 0) + /* + * Because ktime_get_mono_fast_ns() is not monotonic during + * timekeeping updates, ensure that 'now' is after the last saved + * timesptamp. + */ + if (now < last) return; + delta = now - last; + if (dev->power.runtime_status == RPM_SUSPENDED) - dev->power.suspended_jiffies += delta; + dev->power.suspended_time += delta; else - dev->power.active_jiffies += delta; + dev->power.active_time += delta; } static void __update_runtime_status(struct device *dev, enum rpm_status status) @@ -88,6 +98,22 @@ static void __update_runtime_status(struct device *dev, enum rpm_status status) dev->power.runtime_status = status; } +u64 pm_runtime_suspended_time(struct device *dev) +{ + u64 time; + unsigned long flags; + + spin_lock_irqsave(&dev->power.lock, flags); + + update_pm_runtime_accounting(dev); + time = dev->power.suspended_time; + + spin_unlock_irqrestore(&dev->power.lock, flags); + + return time; +} +EXPORT_SYMBOL_GPL(pm_runtime_suspended_time); + /** * pm_runtime_deactivate_timer - Deactivate given device's suspend timer. * @dev: Device to handle. @@ -95,7 +121,7 @@ static void __update_runtime_status(struct device *dev, enum rpm_status status) static void pm_runtime_deactivate_timer(struct device *dev) { if (dev->power.timer_expires > 0) { - hrtimer_cancel(&dev->power.suspend_timer); + hrtimer_try_to_cancel(&dev->power.suspend_timer); dev->power.timer_expires = 0; } } @@ -129,24 +155,21 @@ static void pm_runtime_cancel_pending(struct device *dev) u64 pm_runtime_autosuspend_expiration(struct device *dev) { int autosuspend_delay; - u64 last_busy, expires = 0; - u64 now = ktime_get_mono_fast_ns(); + u64 expires; if (!dev->power.use_autosuspend) - goto out; + return 0; autosuspend_delay = READ_ONCE(dev->power.autosuspend_delay); if (autosuspend_delay < 0) - goto out; - - last_busy = READ_ONCE(dev->power.last_busy); + return 0; - expires = last_busy + (u64)autosuspend_delay * NSEC_PER_MSEC; - if (expires <= now) - expires = 0; /* Already expired. */ + expires = READ_ONCE(dev->power.last_busy); + expires += (u64)autosuspend_delay * NSEC_PER_MSEC; + if (expires > ktime_get_mono_fast_ns()) + return expires; /* Expires in the future */ - out: - return expires; + return 0; } EXPORT_SYMBOL_GPL(pm_runtime_autosuspend_expiration); @@ -1276,6 +1299,9 @@ void __pm_runtime_disable(struct device *dev, bool check_resume) pm_runtime_put_noidle(dev); } + /* Update time accounting before disabling PM-runtime. */ + update_pm_runtime_accounting(dev); + if (!dev->power.disable_depth++) __pm_runtime_barrier(dev); @@ -1294,10 +1320,15 @@ void pm_runtime_enable(struct device *dev) spin_lock_irqsave(&dev->power.lock, flags); - if (dev->power.disable_depth > 0) + if (dev->power.disable_depth > 0) { dev->power.disable_depth--; - else + + /* About to enable runtime pm, set accounting_timestamp to now */ + if (!dev->power.disable_depth) + dev->power.accounting_timestamp = ktime_get_mono_fast_ns(); + } else { dev_warn(dev, "Unbalanced %s!\n", __func__); + } WARN(!dev->power.disable_depth && dev->power.runtime_status == RPM_SUSPENDED && @@ -1494,7 +1525,6 @@ void pm_runtime_init(struct device *dev) dev->power.request_pending = false; dev->power.request = RPM_REQ_NONE; dev->power.deferred_resume = false; - dev->power.accounting_timestamp = jiffies; INIT_WORK(&dev->power.work, pm_runtime_work); dev->power.timer_expires = 0; diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c index d713738ce796..c6bf76124184 100644 --- a/drivers/base/power/sysfs.c +++ b/drivers/base/power/sysfs.c @@ -125,9 +125,12 @@ static ssize_t runtime_active_time_show(struct device *dev, struct device_attribute *attr, char *buf) { int ret; + u64 tmp; spin_lock_irq(&dev->power.lock); update_pm_runtime_accounting(dev); - ret = sprintf(buf, "%i\n", jiffies_to_msecs(dev->power.active_jiffies)); + tmp = dev->power.active_time; + do_div(tmp, NSEC_PER_MSEC); + ret = sprintf(buf, "%llu\n", tmp); spin_unlock_irq(&dev->power.lock); return ret; } @@ -138,10 +141,12 @@ static ssize_t runtime_suspended_time_show(struct device *dev, struct device_attribute *attr, char *buf) { int ret; + u64 tmp; spin_lock_irq(&dev->power.lock); update_pm_runtime_accounting(dev); - ret = sprintf(buf, "%i\n", - jiffies_to_msecs(dev->power.suspended_jiffies)); + tmp = dev->power.suspended_time; + do_div(tmp, NSEC_PER_MSEC); + ret = sprintf(buf, "%llu\n", tmp); spin_unlock_irq(&dev->power.lock); return ret; } @@ -648,6 +653,10 @@ int dpm_sysfs_add(struct device *dev) { int rc; + /* No need to create PM sysfs if explicitly disabled. */ + if (device_pm_not_required(dev)) + return 0; + rc = sysfs_create_group(&dev->kobj, &pm_attr_group); if (rc) return rc; @@ -727,6 +736,8 @@ void rpm_sysfs_remove(struct device *dev) void dpm_sysfs_remove(struct device *dev) { + if (device_pm_not_required(dev)) + return; sysfs_unmerge_group(&dev->kobj, &pm_qos_latency_tolerance_attr_group); dev_pm_qos_constraints_destroy(dev); rpm_sysfs_remove(dev); diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c index 5fa1898755a3..f1fee72ed970 100644 --- a/drivers/base/power/wakeup.c +++ b/drivers/base/power/wakeup.c @@ -783,7 +783,7 @@ void pm_wakeup_ws_event(struct wakeup_source *ws, unsigned int msec, bool hard) EXPORT_SYMBOL_GPL(pm_wakeup_ws_event); /** - * pm_wakeup_event - Notify the PM core of a wakeup event. + * pm_wakeup_dev_event - Notify the PM core of a wakeup event. * @dev: Device the wakeup event is related to. * @msec: Anticipated event processing time (in milliseconds). * @hard: If set, abort suspends in progress and wake up from suspend-to-idle. diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 6f2856c6d0f2..55481b40df9a 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -4075,7 +4075,7 @@ static unsigned int floppy_check_events(struct gendisk *disk, if (time_after(jiffies, UDRS->last_checked + UDP->checkfreq)) { if (lock_fdc(drive)) - return -EINTR; + return 0; poll_drive(false, 0); process_fd_request(); } diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index f94d33525771..d299ec79e4c3 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -781,12 +781,12 @@ static const struct sysc_revision_quirk sysc_revision_quirks[] = { SYSC_QUIRK("smartreflex", 0, -1, 0x38, -1, 0x00000000, 0xffffffff, SYSC_QUIRK_LEGACY_IDLE), SYSC_QUIRK("timer", 0, 0, 0x10, 0x14, 0x00000015, 0xffffffff, - SYSC_QUIRK_LEGACY_IDLE), + 0), /* Some timers on omap4 and later */ SYSC_QUIRK("timer", 0, 0, 0x10, -1, 0x50002100, 0xffffffff, - SYSC_QUIRK_LEGACY_IDLE), + 0), SYSC_QUIRK("timer", 0, 0, 0x10, -1, 0x4fff1301, 0xffff00ff, - SYSC_QUIRK_LEGACY_IDLE), + 0), SYSC_QUIRK("uart", 0, 0x50, 0x54, 0x58, 0x00000052, 0xffffffff, SYSC_QUIRK_LEGACY_IDLE), /* Uarts on omap4 and later */ diff --git a/drivers/clocksource/timer-ti-dm.c b/drivers/clocksource/timer-ti-dm.c index 595124074821..c364027638e1 100644 --- a/drivers/clocksource/timer-ti-dm.c +++ b/drivers/clocksource/timer-ti-dm.c @@ -154,6 +154,10 @@ static int omap_dm_timer_of_set_source(struct omap_dm_timer *timer) if (IS_ERR(parent)) return -ENODEV; + /* Bail out if both clocks point to fck */ + if (clk_is_match(parent, timer->fclk)) + return 0; + ret = clk_set_parent(timer->fclk, parent); if (ret < 0) pr_err("%s: failed to set parent\n", __func__); @@ -864,7 +868,6 @@ static int omap_dm_timer_probe(struct platform_device *pdev) timer->pdev = pdev; pm_runtime_enable(dev); - pm_runtime_irq_safe(dev); if (!timer->reserved) { ret = pm_runtime_get_sync(dev); diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig index 608af20a3494..b22e6bba71f1 100644 --- a/drivers/cpufreq/Kconfig +++ b/drivers/cpufreq/Kconfig @@ -207,8 +207,6 @@ comment "CPU frequency scaling drivers" config CPUFREQ_DT tristate "Generic DT based cpufreq driver" depends on HAVE_CLK && OF - # if CPU_THERMAL is on and THERMAL=m, CPUFREQ_DT cannot be =y: - depends on !CPU_THERMAL || THERMAL select CPUFREQ_DT_PLATDEV select PM_OPP help @@ -327,7 +325,6 @@ endif config QORIQ_CPUFREQ tristate "CPU frequency scaling driver for Freescale QorIQ SoCs" depends on OF && COMMON_CLK && (PPC_E500MC || ARM || ARM64) - depends on !CPU_THERMAL || THERMAL select CLK_QORIQ help This adds the CPUFreq driver support for Freescale QorIQ SoCs diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index 688f10227793..f08bb0075316 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -25,12 +25,21 @@ config ARM_ARMADA_37XX_CPUFREQ This adds the CPUFreq driver support for Marvell Armada 37xx SoCs. The Armada 37xx PMU supports 4 frequency and VDD levels. +config ARM_ARMADA_8K_CPUFREQ + tristate "Armada 8K CPUFreq driver" + depends on ARCH_MVEBU && CPUFREQ_DT + help + This enables the CPUFreq driver support for Marvell + Armada8k SOCs. + Armada8K device has the AP806 which supports scaling + to any full integer divider. + + If in doubt, say N. + # big LITTLE core layer and glue drivers config ARM_BIG_LITTLE_CPUFREQ tristate "Generic ARM big LITTLE CPUfreq driver" depends on ARM_CPU_TOPOLOGY && HAVE_CLK - # if CPU_THERMAL is on and THERMAL=m, ARM_BIT_LITTLE_CPUFREQ cannot be =y - depends on !CPU_THERMAL || THERMAL select PM_OPP help This enables the Generic CPUfreq driver for ARM big.LITTLE platforms. @@ -38,7 +47,6 @@ config ARM_BIG_LITTLE_CPUFREQ config ARM_SCPI_CPUFREQ tristate "SCPI based CPUfreq driver" depends on ARM_SCPI_PROTOCOL && COMMON_CLK_SCPI - depends on !CPU_THERMAL || THERMAL help This adds the CPUfreq driver support for ARM platforms using SCPI protocol for CPU power management. @@ -93,7 +101,6 @@ config ARM_KIRKWOOD_CPUFREQ config ARM_MEDIATEK_CPUFREQ tristate "CPU Frequency scaling support for MediaTek SoCs" depends on ARCH_MEDIATEK && REGULATOR - depends on !CPU_THERMAL || THERMAL select PM_OPP help This adds the CPUFreq driver support for MediaTek SoCs. @@ -233,7 +240,6 @@ config ARM_SA1110_CPUFREQ config ARM_SCMI_CPUFREQ tristate "SCMI based CPUfreq driver" depends on ARM_SCMI_PROTOCOL || COMPILE_TEST - depends on !CPU_THERMAL || THERMAL select PM_OPP help This adds the CPUfreq driver support for ARM platforms using SCMI diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile index 08c071be2491..689b26c6f949 100644 --- a/drivers/cpufreq/Makefile +++ b/drivers/cpufreq/Makefile @@ -50,6 +50,7 @@ obj-$(CONFIG_X86_SFI_CPUFREQ) += sfi-cpufreq.o obj-$(CONFIG_ARM_BIG_LITTLE_CPUFREQ) += arm_big_little.o obj-$(CONFIG_ARM_ARMADA_37XX_CPUFREQ) += armada-37xx-cpufreq.o +obj-$(CONFIG_ARM_ARMADA_8K_CPUFREQ) += armada-8k-cpufreq.o obj-$(CONFIG_ARM_BRCMSTB_AVS_CPUFREQ) += brcmstb-avs-cpufreq.o obj-$(CONFIG_ACPI_CPPC_CPUFREQ) += cppc_cpufreq.o obj-$(CONFIG_ARCH_DAVINCI) += davinci-cpufreq.o diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index d62fd374d5c7..c72258a44ba4 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -916,8 +916,10 @@ static void __init acpi_cpufreq_boost_init(void) { int ret; - if (!(boot_cpu_has(X86_FEATURE_CPB) || boot_cpu_has(X86_FEATURE_IDA))) + if (!(boot_cpu_has(X86_FEATURE_CPB) || boot_cpu_has(X86_FEATURE_IDA))) { + pr_debug("Boost capabilities not present in the processor\n"); return; + } acpi_cpufreq_driver.set_boost = set_boost; acpi_cpufreq_driver.boost_enabled = boost_state(0); diff --git a/drivers/cpufreq/armada-8k-cpufreq.c b/drivers/cpufreq/armada-8k-cpufreq.c new file mode 100644 index 000000000000..b3f4bd647e9b --- /dev/null +++ b/drivers/cpufreq/armada-8k-cpufreq.c @@ -0,0 +1,206 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * CPUFreq support for Armada 8K + * + * Copyright (C) 2018 Marvell + * + * Omri Itach <omrii@marvell.com> + * Gregory Clement <gregory.clement@bootlin.com> + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/clk.h> +#include <linux/cpu.h> +#include <linux/err.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/platform_device.h> +#include <linux/pm_opp.h> +#include <linux/slab.h> + +/* + * Setup the opps list with the divider for the max frequency, that + * will be filled at runtime. + */ +static const int opps_div[] __initconst = {1, 2, 3, 4}; + +static struct platform_device *armada_8k_pdev; + +struct freq_table { + struct device *cpu_dev; + unsigned int freq[ARRAY_SIZE(opps_div)]; +}; + +/* If the CPUs share the same clock, then they are in the same cluster. */ +static void __init armada_8k_get_sharing_cpus(struct clk *cur_clk, + struct cpumask *cpumask) +{ + int cpu; + + for_each_possible_cpu(cpu) { + struct device *cpu_dev; + struct clk *clk; + + cpu_dev = get_cpu_device(cpu); + if (!cpu_dev) { + pr_warn("Failed to get cpu%d device\n", cpu); + continue; + } + + clk = clk_get(cpu_dev, 0); + if (IS_ERR(clk)) { + pr_warn("Cannot get clock for CPU %d\n", cpu); + } else { + if (clk_is_match(clk, cur_clk)) + cpumask_set_cpu(cpu, cpumask); + + clk_put(clk); + } + } +} + +static int __init armada_8k_add_opp(struct clk *clk, struct device *cpu_dev, + struct freq_table *freq_tables, + int opps_index) +{ + unsigned int cur_frequency; + unsigned int freq; + int i, ret; + + /* Get nominal (current) CPU frequency. */ + cur_frequency = clk_get_rate(clk); + if (!cur_frequency) { + dev_err(cpu_dev, "Failed to get clock rate for this CPU\n"); + return -EINVAL; + } + + freq_tables[opps_index].cpu_dev = cpu_dev; + + for (i = 0; i < ARRAY_SIZE(opps_div); i++) { + freq = cur_frequency / opps_div[i]; + + ret = dev_pm_opp_add(cpu_dev, freq, 0); + if (ret) + return ret; + + freq_tables[opps_index].freq[i] = freq; + } + + return 0; +} + +static void armada_8k_cpufreq_free_table(struct freq_table *freq_tables) +{ + int opps_index, nb_cpus = num_possible_cpus(); + + for (opps_index = 0 ; opps_index <= nb_cpus; opps_index++) { + int i; + + /* If cpu_dev is NULL then we reached the end of the array */ + if (!freq_tables[opps_index].cpu_dev) + break; + + for (i = 0; i < ARRAY_SIZE(opps_div); i++) { + /* + * A 0Hz frequency is not valid, this meant + * that it was not yet initialized so there is + * no more opp to free + */ + if (freq_tables[opps_index].freq[i] == 0) + break; + + dev_pm_opp_remove(freq_tables[opps_index].cpu_dev, + freq_tables[opps_index].freq[i]); + } + } + + kfree(freq_tables); +} + +static int __init armada_8k_cpufreq_init(void) +{ + int ret = 0, opps_index = 0, cpu, nb_cpus; + struct freq_table *freq_tables; + struct device_node *node; + struct cpumask cpus; + + node = of_find_compatible_node(NULL, NULL, "marvell,ap806-cpu-clock"); + if (!node || !of_device_is_available(node)) { + of_node_put(node); + return -ENODEV; + } + + nb_cpus = num_possible_cpus(); + freq_tables = kcalloc(nb_cpus, sizeof(*freq_tables), GFP_KERNEL); + cpumask_copy(&cpus, cpu_possible_mask); + + /* + * For each CPU, this loop registers the operating points + * supported (which are the nominal CPU frequency and full integer + * divisions of it). + */ + for_each_cpu(cpu, &cpus) { + struct cpumask shared_cpus; + struct device *cpu_dev; + struct clk *clk; + + cpu_dev = get_cpu_device(cpu); + + if (!cpu_dev) { + pr_err("Cannot get CPU %d\n", cpu); + continue; + } + + clk = clk_get(cpu_dev, 0); + + if (IS_ERR(clk)) { + pr_err("Cannot get clock for CPU %d\n", cpu); + ret = PTR_ERR(clk); + goto remove_opp; + } + + ret = armada_8k_add_opp(clk, cpu_dev, freq_tables, opps_index); + if (ret) { + clk_put(clk); + goto remove_opp; + } + + opps_index++; + cpumask_clear(&shared_cpus); + armada_8k_get_sharing_cpus(clk, &shared_cpus); + dev_pm_opp_set_sharing_cpus(cpu_dev, &shared_cpus); + cpumask_andnot(&cpus, &cpus, &shared_cpus); + clk_put(clk); + } + + armada_8k_pdev = platform_device_register_simple("cpufreq-dt", -1, + NULL, 0); + ret = PTR_ERR_OR_ZERO(armada_8k_pdev); + if (ret) + goto remove_opp; + + platform_set_drvdata(armada_8k_pdev, freq_tables); + + return 0; + +remove_opp: + armada_8k_cpufreq_free_table(freq_tables); + return ret; +} +module_init(armada_8k_cpufreq_init); + +static void __exit armada_8k_cpufreq_exit(void) +{ + struct freq_table *freq_tables = platform_get_drvdata(armada_8k_pdev); + + platform_device_unregister(armada_8k_pdev); + armada_8k_cpufreq_free_table(freq_tables); +} +module_exit(armada_8k_cpufreq_exit); + +MODULE_AUTHOR("Gregory Clement <gregory.clement@bootlin.com>"); +MODULE_DESCRIPTION("Armada 8K cpufreq driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c index fd25c21cee72..2ae978d27e61 100644 --- a/drivers/cpufreq/cppc_cpufreq.c +++ b/drivers/cpufreq/cppc_cpufreq.c @@ -42,6 +42,66 @@ */ static struct cppc_cpudata **all_cpu_data; +struct cppc_workaround_oem_info { + char oem_id[ACPI_OEM_ID_SIZE +1]; + char oem_table_id[ACPI_OEM_TABLE_ID_SIZE + 1]; + u32 oem_revision; +}; + +static bool apply_hisi_workaround; + +static struct cppc_workaround_oem_info wa_info[] = { + { + .oem_id = "HISI ", + .oem_table_id = "HIP07 ", + .oem_revision = 0, + }, { + .oem_id = "HISI ", + .oem_table_id = "HIP08 ", + .oem_revision = 0, + } +}; + +static unsigned int cppc_cpufreq_perf_to_khz(struct cppc_cpudata *cpu, + unsigned int perf); + +/* + * HISI platform does not support delivered performance counter and + * reference performance counter. It can calculate the performance using the + * platform specific mechanism. We reuse the desired performance register to + * store the real performance calculated by the platform. + */ +static unsigned int hisi_cppc_cpufreq_get_rate(unsigned int cpunum) +{ + struct cppc_cpudata *cpudata = all_cpu_data[cpunum]; + u64 desired_perf; + int ret; + + ret = cppc_get_desired_perf(cpunum, &desired_perf); + if (ret < 0) + return -EIO; + + return cppc_cpufreq_perf_to_khz(cpudata, desired_perf); +} + +static void cppc_check_hisi_workaround(void) +{ + struct acpi_table_header *tbl; + acpi_status status = AE_OK; + int i; + + status = acpi_get_table(ACPI_SIG_PCCT, 0, &tbl); + if (ACPI_FAILURE(status) || !tbl) + return; + + for (i = 0; i < ARRAY_SIZE(wa_info); i++) { + if (!memcmp(wa_info[i].oem_id, tbl->oem_id, ACPI_OEM_ID_SIZE) && + !memcmp(wa_info[i].oem_table_id, tbl->oem_table_id, ACPI_OEM_TABLE_ID_SIZE) && + wa_info[i].oem_revision == tbl->oem_revision) + apply_hisi_workaround = true; + } +} + /* Callback function used to retrieve the max frequency from DMI */ static void cppc_find_dmi_mhz(const struct dmi_header *dm, void *private) { @@ -334,6 +394,9 @@ static unsigned int cppc_cpufreq_get_rate(unsigned int cpunum) struct cppc_cpudata *cpu = all_cpu_data[cpunum]; int ret; + if (apply_hisi_workaround) + return hisi_cppc_cpufreq_get_rate(cpunum); + ret = cppc_get_perf_ctrs(cpunum, &fb_ctrs_t0); if (ret) return ret; @@ -386,6 +449,8 @@ static int __init cppc_cpufreq_init(void) goto out; } + cppc_check_hisi_workaround(); + ret = cpufreq_register_driver(&cppc_cpufreq_driver); if (ret) goto out; diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c index d74e0402512a..bde28878725b 100644 --- a/drivers/cpufreq/cpufreq-dt.c +++ b/drivers/cpufreq/cpufreq-dt.c @@ -13,7 +13,6 @@ #include <linux/clk.h> #include <linux/cpu.h> -#include <linux/cpu_cooling.h> #include <linux/cpufreq.h> #include <linux/cpumask.h> #include <linux/err.h> @@ -30,7 +29,6 @@ struct private_data { struct opp_table *opp_table; struct device *cpu_dev; - struct thermal_cooling_device *cdev; const char *reg_name; bool have_static_opps; }; @@ -299,11 +297,25 @@ out_put_clk: return ret; } +static int cpufreq_online(struct cpufreq_policy *policy) +{ + /* We did light-weight tear down earlier, nothing to do here */ + return 0; +} + +static int cpufreq_offline(struct cpufreq_policy *policy) +{ + /* + * Preserve policy->driver_data and don't free resources on light-weight + * tear down. + */ + return 0; +} + static int cpufreq_exit(struct cpufreq_policy *policy) { struct private_data *priv = policy->driver_data; - cpufreq_cooling_unregister(priv->cdev); dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table); if (priv->have_static_opps) dev_pm_opp_of_cpumask_remove_table(policy->related_cpus); @@ -316,21 +328,16 @@ static int cpufreq_exit(struct cpufreq_policy *policy) return 0; } -static void cpufreq_ready(struct cpufreq_policy *policy) -{ - struct private_data *priv = policy->driver_data; - - priv->cdev = of_cpufreq_cooling_register(policy); -} - static struct cpufreq_driver dt_cpufreq_driver = { - .flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK, + .flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK | + CPUFREQ_IS_COOLING_DEV, .verify = cpufreq_generic_frequency_table_verify, .target_index = set_target, .get = cpufreq_generic_get, .init = cpufreq_init, .exit = cpufreq_exit, - .ready = cpufreq_ready, + .online = cpufreq_online, + .offline = cpufreq_offline, .name = "cpufreq-dt", .attr = cpufreq_dt_attr, .suspend = cpufreq_generic_suspend, diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index e35a886e00bc..0e626b00053b 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -19,6 +19,7 @@ #include <linux/cpu.h> #include <linux/cpufreq.h> +#include <linux/cpu_cooling.h> #include <linux/delay.h> #include <linux/device.h> #include <linux/init.h> @@ -545,13 +546,13 @@ EXPORT_SYMBOL_GPL(cpufreq_policy_transition_delay_us); * SYSFS INTERFACE * *********************************************************************/ static ssize_t show_boost(struct kobject *kobj, - struct attribute *attr, char *buf) + struct kobj_attribute *attr, char *buf) { return sprintf(buf, "%d\n", cpufreq_driver->boost_enabled); } -static ssize_t store_boost(struct kobject *kobj, struct attribute *attr, - const char *buf, size_t count) +static ssize_t store_boost(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count) { int ret, enable; @@ -1200,28 +1201,39 @@ static int cpufreq_online(unsigned int cpu) return -ENOMEM; } - cpumask_copy(policy->cpus, cpumask_of(cpu)); + if (!new_policy && cpufreq_driver->online) { + ret = cpufreq_driver->online(policy); + if (ret) { + pr_debug("%s: %d: initialization failed\n", __func__, + __LINE__); + goto out_exit_policy; + } - /* call driver. From then on the cpufreq must be able - * to accept all calls to ->verify and ->setpolicy for this CPU - */ - ret = cpufreq_driver->init(policy); - if (ret) { - pr_debug("initialization failed\n"); - goto out_free_policy; - } + /* Recover policy->cpus using related_cpus */ + cpumask_copy(policy->cpus, policy->related_cpus); + } else { + cpumask_copy(policy->cpus, cpumask_of(cpu)); - ret = cpufreq_table_validate_and_sort(policy); - if (ret) - goto out_exit_policy; + /* + * Call driver. From then on the cpufreq must be able + * to accept all calls to ->verify and ->setpolicy for this CPU. + */ + ret = cpufreq_driver->init(policy); + if (ret) { + pr_debug("%s: %d: initialization failed\n", __func__, + __LINE__); + goto out_free_policy; + } - down_write(&policy->rwsem); + ret = cpufreq_table_validate_and_sort(policy); + if (ret) + goto out_exit_policy; - if (new_policy) { /* related_cpus should at least include policy->cpus. */ cpumask_copy(policy->related_cpus, policy->cpus); } + down_write(&policy->rwsem); /* * affected cpus must always be the one, which are online. We aren't * managing offline cpus here. @@ -1305,8 +1317,6 @@ static int cpufreq_online(unsigned int cpu) if (ret) { pr_err("%s: Failed to initialize policy for cpu: %d (%d)\n", __func__, cpu, ret); - /* cpufreq_policy_free() will notify based on this */ - new_policy = false; goto out_destroy_policy; } @@ -1318,6 +1328,10 @@ static int cpufreq_online(unsigned int cpu) if (cpufreq_driver->ready) cpufreq_driver->ready(policy); + if (IS_ENABLED(CONFIG_CPU_THERMAL) && + cpufreq_driver->flags & CPUFREQ_IS_COOLING_DEV) + policy->cdev = of_cpufreq_cooling_register(policy); + pr_debug("initialization complete\n"); return 0; @@ -1405,6 +1419,12 @@ static int cpufreq_offline(unsigned int cpu) goto unlock; } + if (IS_ENABLED(CONFIG_CPU_THERMAL) && + cpufreq_driver->flags & CPUFREQ_IS_COOLING_DEV) { + cpufreq_cooling_unregister(policy->cdev); + policy->cdev = NULL; + } + if (cpufreq_driver->stop_cpu) cpufreq_driver->stop_cpu(policy); @@ -1412,11 +1432,12 @@ static int cpufreq_offline(unsigned int cpu) cpufreq_exit_governor(policy); /* - * Perform the ->exit() even during light-weight tear-down, - * since this is a core component, and is essential for the - * subsequent light-weight ->init() to succeed. + * Perform the ->offline() during light-weight tear-down, as + * that allows fast recovery when the CPU comes back. */ - if (cpufreq_driver->exit) { + if (cpufreq_driver->offline) { + cpufreq_driver->offline(policy); + } else if (cpufreq_driver->exit) { cpufreq_driver->exit(policy); policy->freq_table = NULL; } @@ -1445,8 +1466,13 @@ static void cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif) cpumask_clear_cpu(cpu, policy->real_cpus); remove_cpu_dev_symlink(policy, dev); - if (cpumask_empty(policy->real_cpus)) + if (cpumask_empty(policy->real_cpus)) { + /* We did light-weight exit earlier, do full tear down now */ + if (cpufreq_driver->offline) + cpufreq_driver->exit(policy); + cpufreq_policy_free(policy); + } } /** @@ -2192,12 +2218,25 @@ int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu) } EXPORT_SYMBOL(cpufreq_get_policy); -/* - * policy : current policy. - * new_policy: policy to be set. +/** + * cpufreq_set_policy - Modify cpufreq policy parameters. + * @policy: Policy object to modify. + * @new_policy: New policy data. + * + * Pass @new_policy to the cpufreq driver's ->verify() callback, run the + * installed policy notifiers for it with the CPUFREQ_ADJUST value, pass it to + * the driver's ->verify() callback again and run the notifiers for it again + * with the CPUFREQ_NOTIFY value. Next, copy the min and max parameters + * of @new_policy to @policy and either invoke the driver's ->setpolicy() + * callback (if present) or carry out a governor update for @policy. That is, + * run the current governor's ->limits() callback (if the governor field in + * @new_policy points to the same object as the one in @policy) or replace the + * governor for @policy with the new one stored in @new_policy. + * + * The cpuinfo part of @policy is not updated by this function. */ static int cpufreq_set_policy(struct cpufreq_policy *policy, - struct cpufreq_policy *new_policy) + struct cpufreq_policy *new_policy) { struct cpufreq_governor *old_gov; int ret; @@ -2247,11 +2286,11 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy, if (cpufreq_driver->setpolicy) { policy->policy = new_policy->policy; pr_debug("setting range\n"); - return cpufreq_driver->setpolicy(new_policy); + return cpufreq_driver->setpolicy(policy); } if (new_policy->governor == policy->governor) { - pr_debug("cpufreq: governor limits update\n"); + pr_debug("governor limits update\n"); cpufreq_governor_limits(policy); return 0; } @@ -2272,7 +2311,7 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy, if (!ret) { ret = cpufreq_start_governor(policy); if (!ret) { - pr_debug("cpufreq: governor change\n"); + pr_debug("governor change\n"); sched_cpufreq_governor_change(policy, old_gov); return 0; } @@ -2293,11 +2332,14 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy, } /** - * cpufreq_update_policy - re-evaluate an existing cpufreq policy - * @cpu: CPU which shall be re-evaluated + * cpufreq_update_policy - Re-evaluate an existing cpufreq policy. + * @cpu: CPU to re-evaluate the policy for. * - * Useful for policy notifiers which have different necessities - * at different times. + * Update the current frequency for the cpufreq policy of @cpu and use + * cpufreq_set_policy() to re-apply the min and max limits saved in the + * user_policy sub-structure of that policy, which triggers the evaluation + * of policy notifiers and the cpufreq driver's ->verify() callback for the + * policy in question, among other things. */ void cpufreq_update_policy(unsigned int cpu) { @@ -2312,23 +2354,18 @@ void cpufreq_update_policy(unsigned int cpu) if (policy_is_inactive(policy)) goto unlock; - pr_debug("updating policy for CPU %u\n", cpu); - memcpy(&new_policy, policy, sizeof(*policy)); - new_policy.min = policy->user_policy.min; - new_policy.max = policy->user_policy.max; - /* * BIOS might change freq behind our back * -> ask driver for current freq and notify governors about a change */ - if (cpufreq_driver->get && !cpufreq_driver->setpolicy) { - if (cpufreq_suspended) - goto unlock; + if (cpufreq_driver->get && !cpufreq_driver->setpolicy && + (cpufreq_suspended || WARN_ON(!cpufreq_update_current_freq(policy)))) + goto unlock; - new_policy.cur = cpufreq_update_current_freq(policy); - if (WARN_ON(!new_policy.cur)) - goto unlock; - } + pr_debug("updating policy for CPU %u\n", cpu); + memcpy(&new_policy, policy, sizeof(*policy)); + new_policy.min = policy->user_policy.min; + new_policy.max = policy->user_policy.max; cpufreq_set_policy(policy, &new_policy); @@ -2479,7 +2516,8 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) driver_data->target) || (driver_data->setpolicy && (driver_data->target_index || driver_data->target)) || - (!!driver_data->get_intermediate != !!driver_data->target_intermediate)) + (!driver_data->get_intermediate != !driver_data->target_intermediate) || + (!driver_data->online != !driver_data->offline)) return -EINVAL; pr_debug("trying to register driver %s\n", driver_data->name); diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c index 1572129844a5..e2db5581489a 100644 --- a/drivers/cpufreq/cpufreq_stats.c +++ b/drivers/cpufreq/cpufreq_stats.c @@ -31,26 +31,27 @@ static void cpufreq_stats_update(struct cpufreq_stats *stats) { unsigned long long cur_time = get_jiffies_64(); - spin_lock(&cpufreq_stats_lock); stats->time_in_state[stats->last_index] += cur_time - stats->last_time; stats->last_time = cur_time; - spin_unlock(&cpufreq_stats_lock); } static void cpufreq_stats_clear_table(struct cpufreq_stats *stats) { unsigned int count = stats->max_state; + spin_lock(&cpufreq_stats_lock); memset(stats->time_in_state, 0, count * sizeof(u64)); memset(stats->trans_table, 0, count * count * sizeof(int)); stats->last_time = get_jiffies_64(); stats->total_trans = 0; + spin_unlock(&cpufreq_stats_lock); } static ssize_t show_total_trans(struct cpufreq_policy *policy, char *buf) { return sprintf(buf, "%d\n", policy->stats->total_trans); } +cpufreq_freq_attr_ro(total_trans); static ssize_t show_time_in_state(struct cpufreq_policy *policy, char *buf) { @@ -61,7 +62,10 @@ static ssize_t show_time_in_state(struct cpufreq_policy *policy, char *buf) if (policy->fast_switch_enabled) return 0; + spin_lock(&cpufreq_stats_lock); cpufreq_stats_update(stats); + spin_unlock(&cpufreq_stats_lock); + for (i = 0; i < stats->state_num; i++) { len += sprintf(buf + len, "%u %llu\n", stats->freq_table[i], (unsigned long long) @@ -69,6 +73,7 @@ static ssize_t show_time_in_state(struct cpufreq_policy *policy, char *buf) } return len; } +cpufreq_freq_attr_ro(time_in_state); static ssize_t store_reset(struct cpufreq_policy *policy, const char *buf, size_t count) @@ -77,6 +82,7 @@ static ssize_t store_reset(struct cpufreq_policy *policy, const char *buf, cpufreq_stats_clear_table(policy->stats); return count; } +cpufreq_freq_attr_wo(reset); static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf) { @@ -126,10 +132,6 @@ static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf) } cpufreq_freq_attr_ro(trans_table); -cpufreq_freq_attr_ro(total_trans); -cpufreq_freq_attr_ro(time_in_state); -cpufreq_freq_attr_wo(reset); - static struct attribute *default_attrs[] = { &total_trans.attr, &time_in_state.attr, @@ -240,9 +242,11 @@ void cpufreq_stats_record_transition(struct cpufreq_policy *policy, if (old_index == -1 || new_index == -1 || old_index == new_index) return; + spin_lock(&cpufreq_stats_lock); cpufreq_stats_update(stats); stats->last_index = new_index; stats->trans_table[old_index * stats->max_state + new_index]++; stats->total_trans++; + spin_unlock(&cpufreq_stats_lock); } diff --git a/drivers/cpufreq/davinci-cpufreq.c b/drivers/cpufreq/davinci-cpufreq.c index d54a27c99121..940fe85db97a 100644 --- a/drivers/cpufreq/davinci-cpufreq.c +++ b/drivers/cpufreq/davinci-cpufreq.c @@ -23,13 +23,10 @@ #include <linux/init.h> #include <linux/err.h> #include <linux/clk.h> +#include <linux/platform_data/davinci-cpufreq.h> #include <linux/platform_device.h> #include <linux/export.h> -#include <mach/hardware.h> -#include <mach/cpufreq.h> -#include <mach/common.h> - struct davinci_cpufreq { struct device *dev; struct clk *armclk; diff --git a/drivers/cpufreq/e_powersaver.c b/drivers/cpufreq/e_powersaver.c index 60bea302abbe..2d3ef208dd70 100644 --- a/drivers/cpufreq/e_powersaver.c +++ b/drivers/cpufreq/e_powersaver.c @@ -323,9 +323,8 @@ static int eps_cpu_init(struct cpufreq_policy *policy) states = 2; /* Allocate private data and frequency table for current cpu */ - centaur = kzalloc(sizeof(*centaur) - + (states + 1) * sizeof(struct cpufreq_frequency_table), - GFP_KERNEL); + centaur = kzalloc(struct_size(centaur, freq_table, states + 1), + GFP_KERNEL); if (!centaur) return -ENOMEM; eps_cpu[0] = centaur; diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c index 73bfd5bc3087..a4ff09f91c8f 100644 --- a/drivers/cpufreq/imx6q-cpufreq.c +++ b/drivers/cpufreq/imx6q-cpufreq.c @@ -9,7 +9,6 @@ #include <linux/clk.h> #include <linux/cpu.h> #include <linux/cpufreq.h> -#include <linux/cpu_cooling.h> #include <linux/err.h> #include <linux/module.h> #include <linux/nvmem-consumer.h> @@ -52,7 +51,6 @@ static struct clk_bulk_data clks[] = { }; static struct device *cpu_dev; -static struct thermal_cooling_device *cdev; static bool free_opp; static struct cpufreq_frequency_table *freq_table; static unsigned int max_freq; @@ -193,16 +191,6 @@ static int imx6q_set_target(struct cpufreq_policy *policy, unsigned int index) return 0; } -static void imx6q_cpufreq_ready(struct cpufreq_policy *policy) -{ - cdev = of_cpufreq_cooling_register(policy); - - if (!cdev) - dev_err(cpu_dev, - "running cpufreq without cooling device: %ld\n", - PTR_ERR(cdev)); -} - static int imx6q_cpufreq_init(struct cpufreq_policy *policy) { int ret; @@ -215,22 +203,14 @@ static int imx6q_cpufreq_init(struct cpufreq_policy *policy) return ret; } -static int imx6q_cpufreq_exit(struct cpufreq_policy *policy) -{ - cpufreq_cooling_unregister(cdev); - - return 0; -} - static struct cpufreq_driver imx6q_cpufreq_driver = { - .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK, + .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK | + CPUFREQ_IS_COOLING_DEV, .verify = cpufreq_generic_frequency_table_verify, .target_index = imx6q_set_target, .get = cpufreq_generic_get, .init = imx6q_cpufreq_init, - .exit = imx6q_cpufreq_exit, .name = "imx6q-cpufreq", - .ready = imx6q_cpufreq_ready, .attr = cpufreq_generic_attr, .suspend = cpufreq_generic_suspend, }; diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index dd66decf2087..002f5169d4eb 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -50,6 +50,8 @@ #define int_tofp(X) ((int64_t)(X) << FRAC_BITS) #define fp_toint(X) ((X) >> FRAC_BITS) +#define ONE_EIGHTH_FP ((int64_t)1 << (FRAC_BITS - 3)) + #define EXT_BITS 6 #define EXT_FRAC_BITS (EXT_BITS + FRAC_BITS) #define fp_ext_toint(X) ((X) >> EXT_FRAC_BITS) @@ -895,7 +897,7 @@ static void intel_pstate_update_policies(void) /************************** sysfs begin ************************/ #define show_one(file_name, object) \ static ssize_t show_##file_name \ - (struct kobject *kobj, struct attribute *attr, char *buf) \ + (struct kobject *kobj, struct kobj_attribute *attr, char *buf) \ { \ return sprintf(buf, "%u\n", global.object); \ } @@ -904,7 +906,7 @@ static ssize_t intel_pstate_show_status(char *buf); static int intel_pstate_update_status(const char *buf, size_t size); static ssize_t show_status(struct kobject *kobj, - struct attribute *attr, char *buf) + struct kobj_attribute *attr, char *buf) { ssize_t ret; @@ -915,7 +917,7 @@ static ssize_t show_status(struct kobject *kobj, return ret; } -static ssize_t store_status(struct kobject *a, struct attribute *b, +static ssize_t store_status(struct kobject *a, struct kobj_attribute *b, const char *buf, size_t count) { char *p = memchr(buf, '\n', count); @@ -929,7 +931,7 @@ static ssize_t store_status(struct kobject *a, struct attribute *b, } static ssize_t show_turbo_pct(struct kobject *kobj, - struct attribute *attr, char *buf) + struct kobj_attribute *attr, char *buf) { struct cpudata *cpu; int total, no_turbo, turbo_pct; @@ -955,7 +957,7 @@ static ssize_t show_turbo_pct(struct kobject *kobj, } static ssize_t show_num_pstates(struct kobject *kobj, - struct attribute *attr, char *buf) + struct kobj_attribute *attr, char *buf) { struct cpudata *cpu; int total; @@ -976,7 +978,7 @@ static ssize_t show_num_pstates(struct kobject *kobj, } static ssize_t show_no_turbo(struct kobject *kobj, - struct attribute *attr, char *buf) + struct kobj_attribute *attr, char *buf) { ssize_t ret; @@ -998,7 +1000,7 @@ static ssize_t show_no_turbo(struct kobject *kobj, return ret; } -static ssize_t store_no_turbo(struct kobject *a, struct attribute *b, +static ssize_t store_no_turbo(struct kobject *a, struct kobj_attribute *b, const char *buf, size_t count) { unsigned int input; @@ -1045,7 +1047,7 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b, return count; } -static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b, +static ssize_t store_max_perf_pct(struct kobject *a, struct kobj_attribute *b, const char *buf, size_t count) { unsigned int input; @@ -1075,7 +1077,7 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b, return count; } -static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b, +static ssize_t store_min_perf_pct(struct kobject *a, struct kobj_attribute *b, const char *buf, size_t count) { unsigned int input; @@ -1107,12 +1109,13 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b, } static ssize_t show_hwp_dynamic_boost(struct kobject *kobj, - struct attribute *attr, char *buf) + struct kobj_attribute *attr, char *buf) { return sprintf(buf, "%u\n", hwp_boost); } -static ssize_t store_hwp_dynamic_boost(struct kobject *a, struct attribute *b, +static ssize_t store_hwp_dynamic_boost(struct kobject *a, + struct kobj_attribute *b, const char *buf, size_t count) { unsigned int input; @@ -1444,12 +1447,6 @@ static int knl_get_turbo_pstate(void) return ret; } -static int intel_pstate_get_base_pstate(struct cpudata *cpu) -{ - return global.no_turbo || global.turbo_disabled ? - cpu->pstate.max_pstate : cpu->pstate.turbo_pstate; -} - static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate) { trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu); @@ -1470,11 +1467,9 @@ static void intel_pstate_set_min_pstate(struct cpudata *cpu) static void intel_pstate_max_within_limits(struct cpudata *cpu) { - int pstate; + int pstate = max(cpu->pstate.min_pstate, cpu->max_perf_ratio); update_turbo_state(); - pstate = intel_pstate_get_base_pstate(cpu); - pstate = max(cpu->pstate.min_pstate, cpu->max_perf_ratio); intel_pstate_set_pstate(cpu, pstate); } @@ -1678,17 +1673,14 @@ static inline int32_t get_avg_pstate(struct cpudata *cpu) static inline int32_t get_target_pstate(struct cpudata *cpu) { struct sample *sample = &cpu->sample; - int32_t busy_frac, boost; + int32_t busy_frac; int target, avg_pstate; busy_frac = div_fp(sample->mperf << cpu->aperf_mperf_shift, sample->tsc); - boost = cpu->iowait_boost; - cpu->iowait_boost >>= 1; - - if (busy_frac < boost) - busy_frac = boost; + if (busy_frac < cpu->iowait_boost) + busy_frac = cpu->iowait_boost; sample->busy_scaled = busy_frac * 100; @@ -1715,11 +1707,9 @@ static inline int32_t get_target_pstate(struct cpudata *cpu) static int intel_pstate_prepare_request(struct cpudata *cpu, int pstate) { - int max_pstate = intel_pstate_get_base_pstate(cpu); - int min_pstate; + int min_pstate = max(cpu->pstate.min_pstate, cpu->min_perf_ratio); + int max_pstate = max(min_pstate, cpu->max_perf_ratio); - min_pstate = max(cpu->pstate.min_pstate, cpu->min_perf_ratio); - max_pstate = max(min_pstate, cpu->max_perf_ratio); return clamp_t(int, pstate, min_pstate, max_pstate); } @@ -1767,29 +1757,30 @@ static void intel_pstate_update_util(struct update_util_data *data, u64 time, if (smp_processor_id() != cpu->cpu) return; + delta_ns = time - cpu->last_update; if (flags & SCHED_CPUFREQ_IOWAIT) { - cpu->iowait_boost = int_tofp(1); - cpu->last_update = time; - /* - * The last time the busy was 100% so P-state was max anyway - * so avoid overhead of computation. - */ - if (fp_toint(cpu->sample.busy_scaled) == 100) - return; - - goto set_pstate; + /* Start over if the CPU may have been idle. */ + if (delta_ns > TICK_NSEC) { + cpu->iowait_boost = ONE_EIGHTH_FP; + } else if (cpu->iowait_boost) { + cpu->iowait_boost <<= 1; + if (cpu->iowait_boost > int_tofp(1)) + cpu->iowait_boost = int_tofp(1); + } else { + cpu->iowait_boost = ONE_EIGHTH_FP; + } } else if (cpu->iowait_boost) { /* Clear iowait_boost if the CPU may have been idle. */ - delta_ns = time - cpu->last_update; if (delta_ns > TICK_NSEC) cpu->iowait_boost = 0; + else + cpu->iowait_boost >>= 1; } cpu->last_update = time; delta_ns = time - cpu->sample.time; if ((s64)delta_ns < INTEL_PSTATE_SAMPLING_INTERVAL) return; -set_pstate: if (intel_pstate_sample(cpu, time)) intel_pstate_adjust_pstate(cpu); } @@ -1976,7 +1967,8 @@ static void intel_pstate_update_perf_limits(struct cpufreq_policy *policy, if (hwp_active) { intel_pstate_get_hwp_max(cpu->cpu, &turbo_max, &max_state); } else { - max_state = intel_pstate_get_base_pstate(cpu); + max_state = global.no_turbo || global.turbo_disabled ? + cpu->pstate.max_pstate : cpu->pstate.turbo_pstate; turbo_max = cpu->pstate.turbo_pstate; } @@ -2475,6 +2467,7 @@ static bool __init intel_pstate_no_acpi_pss(void) kfree(pss); } + pr_debug("ACPI _PSS not found\n"); return true; } @@ -2485,9 +2478,14 @@ static bool __init intel_pstate_no_acpi_pcch(void) status = acpi_get_handle(NULL, "\\_SB", &handle); if (ACPI_FAILURE(status)) - return true; + goto not_found; + + if (acpi_has_method(handle, "PCCH")) + return false; - return !acpi_has_method(handle, "PCCH"); +not_found: + pr_debug("ACPI PCCH not found\n"); + return true; } static bool __init intel_pstate_has_acpi_ppc(void) @@ -2502,6 +2500,7 @@ static bool __init intel_pstate_has_acpi_ppc(void) if (acpi_has_method(pr->handle, "_PPC")) return true; } + pr_debug("ACPI _PPC not found\n"); return false; } @@ -2539,8 +2538,10 @@ static bool __init intel_pstate_platform_pwr_mgmt_exists(void) id = x86_match_cpu(intel_pstate_cpu_oob_ids); if (id) { rdmsrl(MSR_MISC_PWR_MGMT, misc_pwr); - if ( misc_pwr & (1 << 8)) + if (misc_pwr & (1 << 8)) { + pr_debug("Bit 8 in the MISC_PWR_MGMT MSR set\n"); return true; + } } idx = acpi_match_platform_list(plat_info); @@ -2606,22 +2607,28 @@ static int __init intel_pstate_init(void) } } else { id = x86_match_cpu(intel_pstate_cpu_ids); - if (!id) + if (!id) { + pr_info("CPU ID not supported\n"); return -ENODEV; + } copy_cpu_funcs((struct pstate_funcs *)id->driver_data); } - if (intel_pstate_msrs_not_valid()) + if (intel_pstate_msrs_not_valid()) { + pr_info("Invalid MSRs\n"); return -ENODEV; + } hwp_cpu_matched: /* * The Intel pstate driver will be ignored if the platform * firmware has its own power management modes. */ - if (intel_pstate_platform_pwr_mgmt_exists()) + if (intel_pstate_platform_pwr_mgmt_exists()) { + pr_info("P-states controlled by the platform\n"); return -ENODEV; + } if (!hwp_active && hwp_only) return -ENOTSUPP; diff --git a/drivers/cpufreq/longhaul.c b/drivers/cpufreq/longhaul.c index 279bd9e9fa95..fb546e0d0356 100644 --- a/drivers/cpufreq/longhaul.c +++ b/drivers/cpufreq/longhaul.c @@ -851,7 +851,7 @@ static int longhaul_cpu_init(struct cpufreq_policy *policy) case TYPE_POWERSAVER: pr_cont("Powersaver supported\n"); break; - }; + } /* Doesn't hurt */ longhaul_setup_southbridge(); diff --git a/drivers/cpufreq/mediatek-cpufreq.c b/drivers/cpufreq/mediatek-cpufreq.c index 5250df762814..48e9829274c6 100644 --- a/drivers/cpufreq/mediatek-cpufreq.c +++ b/drivers/cpufreq/mediatek-cpufreq.c @@ -14,7 +14,6 @@ #include <linux/clk.h> #include <linux/cpu.h> -#include <linux/cpu_cooling.h> #include <linux/cpufreq.h> #include <linux/cpumask.h> #include <linux/module.h> @@ -48,7 +47,6 @@ struct mtk_cpu_dvfs_info { struct regulator *sram_reg; struct clk *cpu_clk; struct clk *inter_clk; - struct thermal_cooling_device *cdev; struct list_head list_head; int intermediate_voltage; bool need_voltage_tracking; @@ -307,13 +305,6 @@ static int mtk_cpufreq_set_target(struct cpufreq_policy *policy, #define DYNAMIC_POWER "dynamic-power-coefficient" -static void mtk_cpufreq_ready(struct cpufreq_policy *policy) -{ - struct mtk_cpu_dvfs_info *info = policy->driver_data; - - info->cdev = of_cpufreq_cooling_register(policy); -} - static int mtk_cpu_dvfs_info_init(struct mtk_cpu_dvfs_info *info, int cpu) { struct device *cpu_dev; @@ -474,7 +465,6 @@ static int mtk_cpufreq_exit(struct cpufreq_policy *policy) { struct mtk_cpu_dvfs_info *info = policy->driver_data; - cpufreq_cooling_unregister(info->cdev); dev_pm_opp_free_cpufreq_table(info->cpu_dev, &policy->freq_table); return 0; @@ -482,13 +472,13 @@ static int mtk_cpufreq_exit(struct cpufreq_policy *policy) static struct cpufreq_driver mtk_cpufreq_driver = { .flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK | - CPUFREQ_HAVE_GOVERNOR_PER_POLICY, + CPUFREQ_HAVE_GOVERNOR_PER_POLICY | + CPUFREQ_IS_COOLING_DEV, .verify = cpufreq_generic_frequency_table_verify, .target_index = mtk_cpufreq_set_target, .get = cpufreq_generic_get, .init = mtk_cpufreq_init, .exit = mtk_cpufreq_exit, - .ready = mtk_cpufreq_ready, .name = "mtk-cpufreq", .attr = cpufreq_generic_attr, }; diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c index 099a849396f6..1e5e64643c3a 100644 --- a/drivers/cpufreq/pcc-cpufreq.c +++ b/drivers/cpufreq/pcc-cpufreq.c @@ -268,7 +268,7 @@ static int pcc_get_offset(int cpu) if (!pccp || pccp->type != ACPI_TYPE_PACKAGE) { ret = -ENODEV; goto out_free; - }; + } offset = &(pccp->package.elements[0]); if (!offset || offset->type != ACPI_TYPE_INTEGER) { diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c index 7e7ad3879c4e..d2230812fa4b 100644 --- a/drivers/cpufreq/powernv-cpufreq.c +++ b/drivers/cpufreq/powernv-cpufreq.c @@ -244,6 +244,7 @@ static int init_powernv_pstates(void) u32 len_ids, len_freqs; u32 pstate_min, pstate_max, pstate_nominal; u32 pstate_turbo, pstate_ultra_turbo; + int rc = -ENODEV; power_mgt = of_find_node_by_path("/ibm,opal/power-mgt"); if (!power_mgt) { @@ -327,8 +328,11 @@ next: powernv_freqs[i].frequency = freq * 1000; /* kHz */ powernv_freqs[i].driver_data = id & 0xFF; - revmap_data = (struct pstate_idx_revmap_data *) - kmalloc(sizeof(*revmap_data), GFP_KERNEL); + revmap_data = kmalloc(sizeof(*revmap_data), GFP_KERNEL); + if (!revmap_data) { + rc = -ENOMEM; + goto out; + } revmap_data->pstate_id = id & 0xFF; revmap_data->cpufreq_table_idx = i; @@ -357,7 +361,7 @@ next: return 0; out: of_node_put(power_mgt); - return -ENODEV; + return rc; } /* Returns the CPU frequency corresponding to the pstate_id. */ diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c index d83939a1b3d4..4b0b50403901 100644 --- a/drivers/cpufreq/qcom-cpufreq-hw.c +++ b/drivers/cpufreq/qcom-cpufreq-hw.c @@ -10,18 +10,21 @@ #include <linux/module.h> #include <linux/of_address.h> #include <linux/of_platform.h> +#include <linux/pm_opp.h> #include <linux/slab.h> #define LUT_MAX_ENTRIES 40U #define LUT_SRC GENMASK(31, 30) #define LUT_L_VAL GENMASK(7, 0) #define LUT_CORE_COUNT GENMASK(18, 16) +#define LUT_VOLT GENMASK(11, 0) #define LUT_ROW_SIZE 32 #define CLK_HW_DIV 2 /* Register offsets */ #define REG_ENABLE 0x0 -#define REG_LUT_TABLE 0x110 +#define REG_FREQ_LUT 0x110 +#define REG_VOLT_LUT 0x114 #define REG_PERF_STATE 0x920 static unsigned long cpu_hw_rate, xo_rate; @@ -70,11 +73,12 @@ static unsigned int qcom_cpufreq_hw_fast_switch(struct cpufreq_policy *policy, return policy->freq_table[index].frequency; } -static int qcom_cpufreq_hw_read_lut(struct device *dev, +static int qcom_cpufreq_hw_read_lut(struct device *cpu_dev, struct cpufreq_policy *policy, void __iomem *base) { u32 data, src, lval, i, core_count, prev_cc = 0, prev_freq = 0, freq; + u32 volt; unsigned int max_cores = cpumask_weight(policy->cpus); struct cpufreq_frequency_table *table; @@ -83,23 +87,28 @@ static int qcom_cpufreq_hw_read_lut(struct device *dev, return -ENOMEM; for (i = 0; i < LUT_MAX_ENTRIES; i++) { - data = readl_relaxed(base + REG_LUT_TABLE + i * LUT_ROW_SIZE); + data = readl_relaxed(base + REG_FREQ_LUT + + i * LUT_ROW_SIZE); src = FIELD_GET(LUT_SRC, data); lval = FIELD_GET(LUT_L_VAL, data); core_count = FIELD_GET(LUT_CORE_COUNT, data); + data = readl_relaxed(base + REG_VOLT_LUT + + i * LUT_ROW_SIZE); + volt = FIELD_GET(LUT_VOLT, data) * 1000; + if (src) freq = xo_rate * lval / 1000; else freq = cpu_hw_rate / 1000; - /* Ignore boosts in the middle of the table */ - if (core_count != max_cores) { - table[i].frequency = CPUFREQ_ENTRY_INVALID; - } else { + if (freq != prev_freq && core_count == max_cores) { table[i].frequency = freq; - dev_dbg(dev, "index=%d freq=%d, core_count %d\n", i, + dev_pm_opp_add(cpu_dev, freq * 1000, volt); + dev_dbg(cpu_dev, "index=%d freq=%d, core_count %d\n", i, freq, core_count); + } else { + table[i].frequency = CPUFREQ_ENTRY_INVALID; } /* @@ -116,6 +125,7 @@ static int qcom_cpufreq_hw_read_lut(struct device *dev, if (prev_cc != max_cores) { prev->frequency = prev_freq; prev->flags = CPUFREQ_BOOST_FREQ; + dev_pm_opp_add(cpu_dev, prev_freq * 1000, volt); } break; @@ -127,6 +137,7 @@ static int qcom_cpufreq_hw_read_lut(struct device *dev, table[i].frequency = CPUFREQ_TABLE_END; policy->freq_table = table; + dev_pm_opp_set_sharing_cpus(cpu_dev, policy->cpus); return 0; } @@ -159,10 +170,18 @@ static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy) struct device *dev = &global_pdev->dev; struct of_phandle_args args; struct device_node *cpu_np; + struct device *cpu_dev; struct resource *res; void __iomem *base; int ret, index; + cpu_dev = get_cpu_device(policy->cpu); + if (!cpu_dev) { + pr_err("%s: failed to get cpu%d device\n", __func__, + policy->cpu); + return -ENODEV; + } + cpu_np = of_cpu_device_node_get(policy->cpu); if (!cpu_np) return -EINVAL; @@ -199,12 +218,21 @@ static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy) policy->driver_data = base + REG_PERF_STATE; - ret = qcom_cpufreq_hw_read_lut(dev, policy, base); + ret = qcom_cpufreq_hw_read_lut(cpu_dev, policy, base); if (ret) { dev_err(dev, "Domain-%d failed to read LUT\n", index); goto error; } + ret = dev_pm_opp_get_opp_count(cpu_dev); + if (ret <= 0) { + dev_err(cpu_dev, "Failed to add OPPs\n"); + ret = -ENODEV; + goto error; + } + + dev_pm_opp_of_register_em(policy->cpus); + policy->fast_switch_possible = true; return 0; @@ -215,8 +243,10 @@ error: static int qcom_cpufreq_hw_cpu_exit(struct cpufreq_policy *policy) { + struct device *cpu_dev = get_cpu_device(policy->cpu); void __iomem *base = policy->driver_data - REG_PERF_STATE; + dev_pm_opp_remove_all_dynamic(cpu_dev); kfree(policy->freq_table); devm_iounmap(&global_pdev->dev, base); @@ -231,7 +261,8 @@ static struct freq_attr *qcom_cpufreq_hw_attr[] = { static struct cpufreq_driver cpufreq_qcom_hw_driver = { .flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK | - CPUFREQ_HAVE_GOVERNOR_PER_POLICY, + CPUFREQ_HAVE_GOVERNOR_PER_POLICY | + CPUFREQ_IS_COOLING_DEV, .verify = cpufreq_generic_frequency_table_verify, .target_index = qcom_cpufreq_hw_target_index, .get = qcom_cpufreq_hw_get, @@ -296,7 +327,7 @@ static int __init qcom_cpufreq_hw_init(void) { return platform_driver_register(&qcom_cpufreq_hw_driver); } -subsys_initcall(qcom_cpufreq_hw_init); +device_initcall(qcom_cpufreq_hw_init); static void __exit qcom_cpufreq_hw_exit(void) { diff --git a/drivers/cpufreq/qcom-cpufreq-kryo.c b/drivers/cpufreq/qcom-cpufreq-kryo.c index 2a3675c24032..dd64dcf89c74 100644 --- a/drivers/cpufreq/qcom-cpufreq-kryo.c +++ b/drivers/cpufreq/qcom-cpufreq-kryo.c @@ -42,7 +42,7 @@ enum _msm8996_version { NUM_OF_MSM8996_VERSIONS, }; -struct platform_device *cpufreq_dt_pdev, *kryo_cpufreq_pdev; +static struct platform_device *cpufreq_dt_pdev, *kryo_cpufreq_pdev; static enum _msm8996_version qcom_cpufreq_kryo_get_msm_id(void) { @@ -75,7 +75,7 @@ static enum _msm8996_version qcom_cpufreq_kryo_get_msm_id(void) static int qcom_cpufreq_kryo_probe(struct platform_device *pdev) { - struct opp_table *opp_tables[NR_CPUS] = {0}; + struct opp_table **opp_tables; enum _msm8996_version msm8996_version; struct nvmem_cell *speedbin_nvmem; struct device_node *np; @@ -133,6 +133,10 @@ static int qcom_cpufreq_kryo_probe(struct platform_device *pdev) } kfree(speedbin); + opp_tables = kcalloc(num_possible_cpus(), sizeof(*opp_tables), GFP_KERNEL); + if (!opp_tables) + return -ENOMEM; + for_each_possible_cpu(cpu) { cpu_dev = get_cpu_device(cpu); if (NULL == cpu_dev) { @@ -151,8 +155,10 @@ static int qcom_cpufreq_kryo_probe(struct platform_device *pdev) cpufreq_dt_pdev = platform_device_register_simple("cpufreq-dt", -1, NULL, 0); - if (!IS_ERR(cpufreq_dt_pdev)) + if (!IS_ERR(cpufreq_dt_pdev)) { + platform_set_drvdata(pdev, opp_tables); return 0; + } ret = PTR_ERR(cpufreq_dt_pdev); dev_err(cpu_dev, "Failed to register platform device\n"); @@ -163,13 +169,23 @@ free_opp: break; dev_pm_opp_put_supported_hw(opp_tables[cpu]); } + kfree(opp_tables); return ret; } static int qcom_cpufreq_kryo_remove(struct platform_device *pdev) { + struct opp_table **opp_tables = platform_get_drvdata(pdev); + unsigned int cpu; + platform_device_unregister(cpufreq_dt_pdev); + + for_each_possible_cpu(cpu) + dev_pm_opp_put_supported_hw(opp_tables[cpu]); + + kfree(opp_tables); + return 0; } diff --git a/drivers/cpufreq/qoriq-cpufreq.c b/drivers/cpufreq/qoriq-cpufreq.c index 3d773f64b4df..4295e5476264 100644 --- a/drivers/cpufreq/qoriq-cpufreq.c +++ b/drivers/cpufreq/qoriq-cpufreq.c @@ -13,7 +13,6 @@ #include <linux/clk.h> #include <linux/clk-provider.h> #include <linux/cpufreq.h> -#include <linux/cpu_cooling.h> #include <linux/errno.h> #include <linux/init.h> #include <linux/kernel.h> @@ -31,7 +30,6 @@ struct cpu_data { struct clk **pclk; struct cpufreq_frequency_table *table; - struct thermal_cooling_device *cdev; }; /* @@ -239,7 +237,6 @@ static int qoriq_cpufreq_cpu_exit(struct cpufreq_policy *policy) { struct cpu_data *data = policy->driver_data; - cpufreq_cooling_unregister(data->cdev); kfree(data->pclk); kfree(data->table); kfree(data); @@ -258,23 +255,15 @@ static int qoriq_cpufreq_target(struct cpufreq_policy *policy, return clk_set_parent(policy->clk, parent); } - -static void qoriq_cpufreq_ready(struct cpufreq_policy *policy) -{ - struct cpu_data *cpud = policy->driver_data; - - cpud->cdev = of_cpufreq_cooling_register(policy); -} - static struct cpufreq_driver qoriq_cpufreq_driver = { .name = "qoriq_cpufreq", - .flags = CPUFREQ_CONST_LOOPS, + .flags = CPUFREQ_CONST_LOOPS | + CPUFREQ_IS_COOLING_DEV, .init = qoriq_cpufreq_cpu_init, .exit = qoriq_cpufreq_cpu_exit, .verify = cpufreq_generic_frequency_table_verify, .target_index = qoriq_cpufreq_target, .get = cpufreq_generic_get, - .ready = qoriq_cpufreq_ready, .attr = cpufreq_generic_attr, }; diff --git a/drivers/cpufreq/s5pv210-cpufreq.c b/drivers/cpufreq/s5pv210-cpufreq.c index dbecd7667db2..5b4289460bc9 100644 --- a/drivers/cpufreq/s5pv210-cpufreq.c +++ b/drivers/cpufreq/s5pv210-cpufreq.c @@ -584,7 +584,7 @@ static struct notifier_block s5pv210_cpufreq_reboot_notifier = { static int s5pv210_cpufreq_probe(struct platform_device *pdev) { struct device_node *np; - int id; + int id, result = 0; /* * HACK: This is a temporary workaround to get access to clock @@ -594,18 +594,39 @@ static int s5pv210_cpufreq_probe(struct platform_device *pdev) * this whole driver as soon as S5PV210 gets migrated to use * cpufreq-dt driver. */ + arm_regulator = regulator_get(NULL, "vddarm"); + if (IS_ERR(arm_regulator)) { + if (PTR_ERR(arm_regulator) == -EPROBE_DEFER) + pr_debug("vddarm regulator not ready, defer\n"); + else + pr_err("failed to get regulator vddarm\n"); + return PTR_ERR(arm_regulator); + } + + int_regulator = regulator_get(NULL, "vddint"); + if (IS_ERR(int_regulator)) { + if (PTR_ERR(int_regulator) == -EPROBE_DEFER) + pr_debug("vddint regulator not ready, defer\n"); + else + pr_err("failed to get regulator vddint\n"); + result = PTR_ERR(int_regulator); + goto err_int_regulator; + } + np = of_find_compatible_node(NULL, NULL, "samsung,s5pv210-clock"); if (!np) { pr_err("%s: failed to find clock controller DT node\n", __func__); - return -ENODEV; + result = -ENODEV; + goto err_clock; } clk_base = of_iomap(np, 0); of_node_put(np); if (!clk_base) { pr_err("%s: failed to map clock registers\n", __func__); - return -EFAULT; + result = -EFAULT; + goto err_clock; } for_each_compatible_node(np, NULL, "samsung,s5pv210-dmc") { @@ -614,7 +635,8 @@ static int s5pv210_cpufreq_probe(struct platform_device *pdev) pr_err("%s: failed to get alias of dmc node '%pOFn'\n", __func__, np); of_node_put(np); - return id; + result = id; + goto err_clk_base; } dmc_base[id] = of_iomap(np, 0); @@ -622,33 +644,40 @@ static int s5pv210_cpufreq_probe(struct platform_device *pdev) pr_err("%s: failed to map dmc%d registers\n", __func__, id); of_node_put(np); - return -EFAULT; + result = -EFAULT; + goto err_dmc; } } for (id = 0; id < ARRAY_SIZE(dmc_base); ++id) { if (!dmc_base[id]) { pr_err("%s: failed to find dmc%d node\n", __func__, id); - return -ENODEV; + result = -ENODEV; + goto err_dmc; } } - arm_regulator = regulator_get(NULL, "vddarm"); - if (IS_ERR(arm_regulator)) { - pr_err("failed to get regulator vddarm\n"); - return PTR_ERR(arm_regulator); - } - - int_regulator = regulator_get(NULL, "vddint"); - if (IS_ERR(int_regulator)) { - pr_err("failed to get regulator vddint\n"); - regulator_put(arm_regulator); - return PTR_ERR(int_regulator); - } - register_reboot_notifier(&s5pv210_cpufreq_reboot_notifier); return cpufreq_register_driver(&s5pv210_driver); + +err_dmc: + for (id = 0; id < ARRAY_SIZE(dmc_base); ++id) + if (dmc_base[id]) { + iounmap(dmc_base[id]); + dmc_base[id] = NULL; + } + +err_clk_base: + iounmap(clk_base); + +err_clock: + regulator_put(int_regulator); + +err_int_regulator: + regulator_put(arm_regulator); + + return result; } static struct platform_driver s5pv210_cpufreq_platdrv = { diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c index 0d87e1433296..e6182c89df79 100644 --- a/drivers/cpufreq/scmi-cpufreq.c +++ b/drivers/cpufreq/scmi-cpufreq.c @@ -11,7 +11,6 @@ #include <linux/cpu.h> #include <linux/cpufreq.h> #include <linux/cpumask.h> -#include <linux/cpu_cooling.h> #include <linux/energy_model.h> #include <linux/export.h> #include <linux/module.h> @@ -23,7 +22,6 @@ struct scmi_data { int domain_id; struct device *cpu_dev; - struct thermal_cooling_device *cdev; }; static const struct scmi_handle *handle; @@ -218,25 +216,18 @@ static int scmi_cpufreq_exit(struct cpufreq_policy *policy) { struct scmi_data *priv = policy->driver_data; - cpufreq_cooling_unregister(priv->cdev); dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table); - kfree(priv); dev_pm_opp_remove_all_dynamic(priv->cpu_dev); + kfree(priv); return 0; } -static void scmi_cpufreq_ready(struct cpufreq_policy *policy) -{ - struct scmi_data *priv = policy->driver_data; - - priv->cdev = of_cpufreq_cooling_register(policy); -} - static struct cpufreq_driver scmi_cpufreq_driver = { .name = "scmi", .flags = CPUFREQ_STICKY | CPUFREQ_HAVE_GOVERNOR_PER_POLICY | - CPUFREQ_NEED_INITIAL_FREQ_CHECK, + CPUFREQ_NEED_INITIAL_FREQ_CHECK | + CPUFREQ_IS_COOLING_DEV, .verify = cpufreq_generic_frequency_table_verify, .attr = cpufreq_generic_attr, .target_index = scmi_cpufreq_set_target, @@ -244,7 +235,6 @@ static struct cpufreq_driver scmi_cpufreq_driver = { .get = scmi_cpufreq_get_rate, .init = scmi_cpufreq_init, .exit = scmi_cpufreq_exit, - .ready = scmi_cpufreq_ready, }; static int scmi_cpufreq_probe(struct scmi_device *sdev) diff --git a/drivers/cpufreq/scpi-cpufreq.c b/drivers/cpufreq/scpi-cpufreq.c index b279f94d82f7..3f49427766b8 100644 --- a/drivers/cpufreq/scpi-cpufreq.c +++ b/drivers/cpufreq/scpi-cpufreq.c @@ -22,7 +22,6 @@ #include <linux/cpu.h> #include <linux/cpufreq.h> #include <linux/cpumask.h> -#include <linux/cpu_cooling.h> #include <linux/export.h> #include <linux/module.h> #include <linux/of_platform.h> @@ -34,7 +33,6 @@ struct scpi_data { struct clk *clk; struct device *cpu_dev; - struct thermal_cooling_device *cdev; }; static struct scpi_ops *scpi_ops; @@ -189,7 +187,6 @@ static int scpi_cpufreq_exit(struct cpufreq_policy *policy) { struct scpi_data *priv = policy->driver_data; - cpufreq_cooling_unregister(priv->cdev); clk_put(priv->clk); dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table); kfree(priv); @@ -198,23 +195,16 @@ static int scpi_cpufreq_exit(struct cpufreq_policy *policy) return 0; } -static void scpi_cpufreq_ready(struct cpufreq_policy *policy) -{ - struct scpi_data *priv = policy->driver_data; - - priv->cdev = of_cpufreq_cooling_register(policy); -} - static struct cpufreq_driver scpi_cpufreq_driver = { .name = "scpi-cpufreq", .flags = CPUFREQ_STICKY | CPUFREQ_HAVE_GOVERNOR_PER_POLICY | - CPUFREQ_NEED_INITIAL_FREQ_CHECK, + CPUFREQ_NEED_INITIAL_FREQ_CHECK | + CPUFREQ_IS_COOLING_DEV, .verify = cpufreq_generic_frequency_table_verify, .attr = cpufreq_generic_attr, .get = scpi_cpufreq_get_rate, .init = scpi_cpufreq_init, .exit = scpi_cpufreq_exit, - .ready = scpi_cpufreq_ready, .target_index = scpi_cpufreq_set_target, }; diff --git a/drivers/cpufreq/speedstep-ich.c b/drivers/cpufreq/speedstep-ich.c index fbbcb88db061..5d8a09b82efb 100644 --- a/drivers/cpufreq/speedstep-ich.c +++ b/drivers/cpufreq/speedstep-ich.c @@ -243,8 +243,7 @@ static unsigned int speedstep_get(unsigned int cpu) unsigned int speed; /* You're supposed to ensure CPU is online. */ - if (smp_call_function_single(cpu, get_freq_data, &speed, 1) != 0) - BUG(); + BUG_ON(smp_call_function_single(cpu, get_freq_data, &speed, 1)); pr_debug("detected %u kHz as current frequency\n", speed); return speed; diff --git a/drivers/cpufreq/tegra124-cpufreq.c b/drivers/cpufreq/tegra124-cpufreq.c index 43530254201a..4bb154f6c54c 100644 --- a/drivers/cpufreq/tegra124-cpufreq.c +++ b/drivers/cpufreq/tegra124-cpufreq.c @@ -134,6 +134,8 @@ static int tegra124_cpufreq_probe(struct platform_device *pdev) platform_set_drvdata(pdev, priv); + of_node_put(np); + return 0; out_switch_to_pllx: diff --git a/drivers/cpuidle/Kconfig b/drivers/cpuidle/Kconfig index 7e48eb5bf0a7..8caccbbd7353 100644 --- a/drivers/cpuidle/Kconfig +++ b/drivers/cpuidle/Kconfig @@ -4,7 +4,7 @@ config CPU_IDLE bool "CPU idle PM support" default y if ACPI || PPC_PSERIES select CPU_IDLE_GOV_LADDER if (!NO_HZ && !NO_HZ_IDLE) - select CPU_IDLE_GOV_MENU if (NO_HZ || NO_HZ_IDLE) + select CPU_IDLE_GOV_MENU if (NO_HZ || NO_HZ_IDLE) && !CPU_IDLE_GOV_TEO help CPU idle is a generic framework for supporting software-controlled idle processor power management. It includes modular cross-platform @@ -23,6 +23,15 @@ config CPU_IDLE_GOV_LADDER config CPU_IDLE_GOV_MENU bool "Menu governor (for tickless system)" +config CPU_IDLE_GOV_TEO + bool "Timer events oriented (TEO) governor (for tickless systems)" + help + This governor implements a simplified idle state selection method + focused on timer events and does not do any interactivity boosting. + + Some workloads benefit from using it and it generally should be safe + to use. Say Y here if you are not happy with the alternatives. + config DT_IDLE_STATES bool diff --git a/drivers/cpuidle/dt_idle_states.c b/drivers/cpuidle/dt_idle_states.c index 53342b7f1010..add9569636b5 100644 --- a/drivers/cpuidle/dt_idle_states.c +++ b/drivers/cpuidle/dt_idle_states.c @@ -22,16 +22,12 @@ #include "dt_idle_states.h" static int init_state_node(struct cpuidle_state *idle_state, - const struct of_device_id *matches, + const struct of_device_id *match_id, struct device_node *state_node) { int err; - const struct of_device_id *match_id; const char *desc; - match_id = of_match_node(matches, state_node); - if (!match_id) - return -ENODEV; /* * CPUidle drivers are expected to initialize the const void *data * pointer of the passed in struct of_device_id array to the idle @@ -160,6 +156,7 @@ int dt_init_idle_driver(struct cpuidle_driver *drv, { struct cpuidle_state *idle_state; struct device_node *state_node, *cpu_node; + const struct of_device_id *match_id; int i, err = 0; const cpumask_t *cpumask; unsigned int state_idx = start_idx; @@ -180,6 +177,12 @@ int dt_init_idle_driver(struct cpuidle_driver *drv, if (!state_node) break; + match_id = of_match_node(matches, state_node); + if (!match_id) { + err = -ENODEV; + break; + } + if (!of_device_is_available(state_node)) { of_node_put(state_node); continue; @@ -198,7 +201,7 @@ int dt_init_idle_driver(struct cpuidle_driver *drv, } idle_state = &drv->states[state_idx++]; - err = init_state_node(idle_state, matches, state_node); + err = init_state_node(idle_state, match_id, state_node); if (err) { pr_err("Parsing idle state node %pOF failed with err %d\n", state_node, err); diff --git a/drivers/cpuidle/governors/Makefile b/drivers/cpuidle/governors/Makefile index 1b512722689f..4d8aff5248a8 100644 --- a/drivers/cpuidle/governors/Makefile +++ b/drivers/cpuidle/governors/Makefile @@ -4,3 +4,4 @@ obj-$(CONFIG_CPU_IDLE_GOV_LADDER) += ladder.o obj-$(CONFIG_CPU_IDLE_GOV_MENU) += menu.o +obj-$(CONFIG_CPU_IDLE_GOV_TEO) += teo.o diff --git a/drivers/cpuidle/governors/teo.c b/drivers/cpuidle/governors/teo.c new file mode 100644 index 000000000000..7d05efdbd3c6 --- /dev/null +++ b/drivers/cpuidle/governors/teo.c @@ -0,0 +1,444 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Timer events oriented CPU idle governor + * + * Copyright (C) 2018 Intel Corporation + * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com> + * + * The idea of this governor is based on the observation that on many systems + * timer events are two or more orders of magnitude more frequent than any + * other interrupts, so they are likely to be the most significant source of CPU + * wakeups from idle states. Moreover, information about what happened in the + * (relatively recent) past can be used to estimate whether or not the deepest + * idle state with target residency within the time to the closest timer is + * likely to be suitable for the upcoming idle time of the CPU and, if not, then + * which of the shallower idle states to choose. + * + * Of course, non-timer wakeup sources are more important in some use cases and + * they can be covered by taking a few most recent idle time intervals of the + * CPU into account. However, even in that case it is not necessary to consider + * idle duration values greater than the time till the closest timer, as the + * patterns that they may belong to produce average values close enough to + * the time till the closest timer (sleep length) anyway. + * + * Thus this governor estimates whether or not the upcoming idle time of the CPU + * is likely to be significantly shorter than the sleep length and selects an + * idle state for it in accordance with that, as follows: + * + * - Find an idle state on the basis of the sleep length and state statistics + * collected over time: + * + * o Find the deepest idle state whose target residency is less than or equal + * to the sleep length. + * + * o Select it if it matched both the sleep length and the observed idle + * duration in the past more often than it matched the sleep length alone + * (i.e. the observed idle duration was significantly shorter than the sleep + * length matched by it). + * + * o Otherwise, select the shallower state with the greatest matched "early" + * wakeups metric. + * + * - If the majority of the most recent idle duration values are below the + * target residency of the idle state selected so far, use those values to + * compute the new expected idle duration and find an idle state matching it + * (which has to be shallower than the one selected so far). + */ + +#include <linux/cpuidle.h> +#include <linux/jiffies.h> +#include <linux/kernel.h> +#include <linux/sched/clock.h> +#include <linux/tick.h> + +/* + * The PULSE value is added to metrics when they grow and the DECAY_SHIFT value + * is used for decreasing metrics on a regular basis. + */ +#define PULSE 1024 +#define DECAY_SHIFT 3 + +/* + * Number of the most recent idle duration values to take into consideration for + * the detection of wakeup patterns. + */ +#define INTERVALS 8 + +/** + * struct teo_idle_state - Idle state data used by the TEO cpuidle governor. + * @early_hits: "Early" CPU wakeups "matching" this state. + * @hits: "On time" CPU wakeups "matching" this state. + * @misses: CPU wakeups "missing" this state. + * + * A CPU wakeup is "matched" by a given idle state if the idle duration measured + * after the wakeup is between the target residency of that state and the target + * residency of the next one (or if this is the deepest available idle state, it + * "matches" a CPU wakeup when the measured idle duration is at least equal to + * its target residency). + * + * Also, from the TEO governor perspective, a CPU wakeup from idle is "early" if + * it occurs significantly earlier than the closest expected timer event (that + * is, early enough to match an idle state shallower than the one matching the + * time till the closest timer event). Otherwise, the wakeup is "on time", or + * it is a "hit". + * + * A "miss" occurs when the given state doesn't match the wakeup, but it matches + * the time till the closest timer event used for idle state selection. + */ +struct teo_idle_state { + unsigned int early_hits; + unsigned int hits; + unsigned int misses; +}; + +/** + * struct teo_cpu - CPU data used by the TEO cpuidle governor. + * @time_span_ns: Time between idle state selection and post-wakeup update. + * @sleep_length_ns: Time till the closest timer event (at the selection time). + * @states: Idle states data corresponding to this CPU. + * @last_state: Idle state entered by the CPU last time. + * @interval_idx: Index of the most recent saved idle interval. + * @intervals: Saved idle duration values. + */ +struct teo_cpu { + u64 time_span_ns; + u64 sleep_length_ns; + struct teo_idle_state states[CPUIDLE_STATE_MAX]; + int last_state; + int interval_idx; + unsigned int intervals[INTERVALS]; +}; + +static DEFINE_PER_CPU(struct teo_cpu, teo_cpus); + +/** + * teo_update - Update CPU data after wakeup. + * @drv: cpuidle driver containing state data. + * @dev: Target CPU. + */ +static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) +{ + struct teo_cpu *cpu_data = per_cpu_ptr(&teo_cpus, dev->cpu); + unsigned int sleep_length_us = ktime_to_us(cpu_data->sleep_length_ns); + int i, idx_hit = -1, idx_timer = -1; + unsigned int measured_us; + + if (cpu_data->time_span_ns >= cpu_data->sleep_length_ns) { + /* + * One of the safety nets has triggered or this was a timer + * wakeup (or equivalent). + */ + measured_us = sleep_length_us; + } else { + unsigned int lat = drv->states[cpu_data->last_state].exit_latency; + + measured_us = ktime_to_us(cpu_data->time_span_ns); + /* + * The delay between the wakeup and the first instruction + * executed by the CPU is not likely to be worst-case every + * time, so take 1/2 of the exit latency as a very rough + * approximation of the average of it. + */ + if (measured_us >= lat) + measured_us -= lat / 2; + else + measured_us /= 2; + } + + /* + * Decay the "early hits" metric for all of the states and find the + * states matching the sleep length and the measured idle duration. + */ + for (i = 0; i < drv->state_count; i++) { + unsigned int early_hits = cpu_data->states[i].early_hits; + + cpu_data->states[i].early_hits -= early_hits >> DECAY_SHIFT; + + if (drv->states[i].target_residency <= sleep_length_us) { + idx_timer = i; + if (drv->states[i].target_residency <= measured_us) + idx_hit = i; + } + } + + /* + * Update the "hits" and "misses" data for the state matching the sleep + * length. If it matches the measured idle duration too, this is a hit, + * so increase the "hits" metric for it then. Otherwise, this is a + * miss, so increase the "misses" metric for it. In the latter case + * also increase the "early hits" metric for the state that actually + * matches the measured idle duration. + */ + if (idx_timer >= 0) { + unsigned int hits = cpu_data->states[idx_timer].hits; + unsigned int misses = cpu_data->states[idx_timer].misses; + + hits -= hits >> DECAY_SHIFT; + misses -= misses >> DECAY_SHIFT; + + if (idx_timer > idx_hit) { + misses += PULSE; + if (idx_hit >= 0) + cpu_data->states[idx_hit].early_hits += PULSE; + } else { + hits += PULSE; + } + + cpu_data->states[idx_timer].misses = misses; + cpu_data->states[idx_timer].hits = hits; + } + + /* + * If the total time span between idle state selection and the "reflect" + * callback is greater than or equal to the sleep length determined at + * the idle state selection time, the wakeup is likely to be due to a + * timer event. + */ + if (cpu_data->time_span_ns >= cpu_data->sleep_length_ns) + measured_us = UINT_MAX; + + /* + * Save idle duration values corresponding to non-timer wakeups for + * pattern detection. + */ + cpu_data->intervals[cpu_data->interval_idx++] = measured_us; + if (cpu_data->interval_idx > INTERVALS) + cpu_data->interval_idx = 0; +} + +/** + * teo_find_shallower_state - Find shallower idle state matching given duration. + * @drv: cpuidle driver containing state data. + * @dev: Target CPU. + * @state_idx: Index of the capping idle state. + * @duration_us: Idle duration value to match. + */ +static int teo_find_shallower_state(struct cpuidle_driver *drv, + struct cpuidle_device *dev, int state_idx, + unsigned int duration_us) +{ + int i; + + for (i = state_idx - 1; i >= 0; i--) { + if (drv->states[i].disabled || dev->states_usage[i].disable) + continue; + + state_idx = i; + if (drv->states[i].target_residency <= duration_us) + break; + } + return state_idx; +} + +/** + * teo_select - Selects the next idle state to enter. + * @drv: cpuidle driver containing state data. + * @dev: Target CPU. + * @stop_tick: Indication on whether or not to stop the scheduler tick. + */ +static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, + bool *stop_tick) +{ + struct teo_cpu *cpu_data = per_cpu_ptr(&teo_cpus, dev->cpu); + int latency_req = cpuidle_governor_latency_req(dev->cpu); + unsigned int duration_us, count; + int max_early_idx, idx, i; + ktime_t delta_tick; + + if (cpu_data->last_state >= 0) { + teo_update(drv, dev); + cpu_data->last_state = -1; + } + + cpu_data->time_span_ns = local_clock(); + + cpu_data->sleep_length_ns = tick_nohz_get_sleep_length(&delta_tick); + duration_us = ktime_to_us(cpu_data->sleep_length_ns); + + count = 0; + max_early_idx = -1; + idx = -1; + + for (i = 0; i < drv->state_count; i++) { + struct cpuidle_state *s = &drv->states[i]; + struct cpuidle_state_usage *su = &dev->states_usage[i]; + + if (s->disabled || su->disable) { + /* + * If the "early hits" metric of a disabled state is + * greater than the current maximum, it should be taken + * into account, because it would be a mistake to select + * a deeper state with lower "early hits" metric. The + * index cannot be changed to point to it, however, so + * just increase the max count alone and let the index + * still point to a shallower idle state. + */ + if (max_early_idx >= 0 && + count < cpu_data->states[i].early_hits) + count = cpu_data->states[i].early_hits; + + continue; + } + + if (idx < 0) + idx = i; /* first enabled state */ + + if (s->target_residency > duration_us) + break; + + if (s->exit_latency > latency_req) { + /* + * If we break out of the loop for latency reasons, use + * the target residency of the selected state as the + * expected idle duration to avoid stopping the tick + * as long as that target residency is low enough. + */ + duration_us = drv->states[idx].target_residency; + goto refine; + } + + idx = i; + + if (count < cpu_data->states[i].early_hits && + !(tick_nohz_tick_stopped() && + drv->states[i].target_residency < TICK_USEC)) { + count = cpu_data->states[i].early_hits; + max_early_idx = i; + } + } + + /* + * If the "hits" metric of the idle state matching the sleep length is + * greater than its "misses" metric, that is the one to use. Otherwise, + * it is more likely that one of the shallower states will match the + * idle duration observed after wakeup, so take the one with the maximum + * "early hits" metric, but if that cannot be determined, just use the + * state selected so far. + */ + if (cpu_data->states[idx].hits <= cpu_data->states[idx].misses && + max_early_idx >= 0) { + idx = max_early_idx; + duration_us = drv->states[idx].target_residency; + } + +refine: + if (idx < 0) { + idx = 0; /* No states enabled. Must use 0. */ + } else if (idx > 0) { + u64 sum = 0; + + count = 0; + + /* + * Count and sum the most recent idle duration values less than + * the target residency of the state selected so far, find the + * max. + */ + for (i = 0; i < INTERVALS; i++) { + unsigned int val = cpu_data->intervals[i]; + + if (val >= drv->states[idx].target_residency) + continue; + + count++; + sum += val; + } + + /* + * Give up unless the majority of the most recent idle duration + * values are in the interesting range. + */ + if (count > INTERVALS / 2) { + unsigned int avg_us = div64_u64(sum, count); + + /* + * Avoid spending too much time in an idle state that + * would be too shallow. + */ + if (!(tick_nohz_tick_stopped() && avg_us < TICK_USEC)) { + idx = teo_find_shallower_state(drv, dev, idx, avg_us); + duration_us = avg_us; + } + } + } + + /* + * Don't stop the tick if the selected state is a polling one or if the + * expected idle duration is shorter than the tick period length. + */ + if (((drv->states[idx].flags & CPUIDLE_FLAG_POLLING) || + duration_us < TICK_USEC) && !tick_nohz_tick_stopped()) { + unsigned int delta_tick_us = ktime_to_us(delta_tick); + + *stop_tick = false; + + /* + * The tick is not going to be stopped, so if the target + * residency of the state to be returned is not within the time + * till the closest timer including the tick, try to correct + * that. + */ + if (idx > 0 && drv->states[idx].target_residency > delta_tick_us) + idx = teo_find_shallower_state(drv, dev, idx, delta_tick_us); + } + + return idx; +} + +/** + * teo_reflect - Note that governor data for the CPU need to be updated. + * @dev: Target CPU. + * @state: Entered state. + */ +static void teo_reflect(struct cpuidle_device *dev, int state) +{ + struct teo_cpu *cpu_data = per_cpu_ptr(&teo_cpus, dev->cpu); + + cpu_data->last_state = state; + /* + * If the wakeup was not "natural", but triggered by one of the safety + * nets, assume that the CPU might have been idle for the entire sleep + * length time. + */ + if (dev->poll_time_limit || + (tick_nohz_idle_got_tick() && cpu_data->sleep_length_ns > TICK_NSEC)) { + dev->poll_time_limit = false; + cpu_data->time_span_ns = cpu_data->sleep_length_ns; + } else { + cpu_data->time_span_ns = local_clock() - cpu_data->time_span_ns; + } +} + +/** + * teo_enable_device - Initialize the governor's data for the target CPU. + * @drv: cpuidle driver (not used). + * @dev: Target CPU. + */ +static int teo_enable_device(struct cpuidle_driver *drv, + struct cpuidle_device *dev) +{ + struct teo_cpu *cpu_data = per_cpu_ptr(&teo_cpus, dev->cpu); + int i; + + memset(cpu_data, 0, sizeof(*cpu_data)); + + for (i = 0; i < INTERVALS; i++) + cpu_data->intervals[i] = UINT_MAX; + + return 0; +} + +static struct cpuidle_governor teo_governor = { + .name = "teo", + .rating = 19, + .enable = teo_enable_device, + .select = teo_select, + .reflect = teo_reflect, +}; + +static int __init teo_governor_init(void) +{ + return cpuidle_register_governor(&teo_governor); +} + +postcore_initcall(teo_governor_init); diff --git a/drivers/crypto/ccree/cc_driver.c b/drivers/crypto/ccree/cc_driver.c index 8ada308d72ee..b0125ad65825 100644 --- a/drivers/crypto/ccree/cc_driver.c +++ b/drivers/crypto/ccree/cc_driver.c @@ -380,7 +380,7 @@ static int init_cc_resources(struct platform_device *plat_dev) rc = cc_ivgen_init(new_drvdata); if (rc) { dev_err(dev, "cc_ivgen_init failed\n"); - goto post_power_mgr_err; + goto post_buf_mgr_err; } /* Allocate crypto algs */ @@ -403,6 +403,9 @@ static int init_cc_resources(struct platform_device *plat_dev) goto post_hash_err; } + /* All set, we can allow autosuspend */ + cc_pm_go(new_drvdata); + /* If we got here and FIPS mode is enabled * it means all FIPS test passed, so let TEE * know we're good. @@ -417,8 +420,6 @@ post_cipher_err: cc_cipher_free(new_drvdata); post_ivgen_err: cc_ivgen_fini(new_drvdata); -post_power_mgr_err: - cc_pm_fini(new_drvdata); post_buf_mgr_err: cc_buffer_mgr_fini(new_drvdata); post_req_mgr_err: diff --git a/drivers/crypto/ccree/cc_pm.c b/drivers/crypto/ccree/cc_pm.c index d990f472e89f..6ff7e75ad90e 100644 --- a/drivers/crypto/ccree/cc_pm.c +++ b/drivers/crypto/ccree/cc_pm.c @@ -100,20 +100,19 @@ int cc_pm_put_suspend(struct device *dev) int cc_pm_init(struct cc_drvdata *drvdata) { - int rc = 0; struct device *dev = drvdata_to_dev(drvdata); /* must be before the enabling to avoid resdundent suspending */ pm_runtime_set_autosuspend_delay(dev, CC_SUSPEND_TIMEOUT); pm_runtime_use_autosuspend(dev); /* activate the PM module */ - rc = pm_runtime_set_active(dev); - if (rc) - return rc; - /* enable the PM module*/ - pm_runtime_enable(dev); + return pm_runtime_set_active(dev); +} - return rc; +/* enable the PM module*/ +void cc_pm_go(struct cc_drvdata *drvdata) +{ + pm_runtime_enable(drvdata_to_dev(drvdata)); } void cc_pm_fini(struct cc_drvdata *drvdata) diff --git a/drivers/crypto/ccree/cc_pm.h b/drivers/crypto/ccree/cc_pm.h index 020a5403c58b..f62624357020 100644 --- a/drivers/crypto/ccree/cc_pm.h +++ b/drivers/crypto/ccree/cc_pm.h @@ -16,6 +16,7 @@ extern const struct dev_pm_ops ccree_pm; int cc_pm_init(struct cc_drvdata *drvdata); +void cc_pm_go(struct cc_drvdata *drvdata); void cc_pm_fini(struct cc_drvdata *drvdata); int cc_pm_suspend(struct device *dev); int cc_pm_resume(struct device *dev); @@ -29,6 +30,8 @@ static inline int cc_pm_init(struct cc_drvdata *drvdata) return 0; } +static void cc_pm_go(struct cc_drvdata *drvdata) {} + static inline void cc_pm_fini(struct cc_drvdata *drvdata) {} static inline int cc_pm_suspend(struct device *dev) diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 4c46ff6f2242..55b77c576c42 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -592,11 +592,7 @@ int __init efi_config_parse_tables(void *config_tables, int count, int sz, early_memunmap(tbl, sizeof(*tbl)); } - return 0; -} -int __init efi_apply_persistent_mem_reservations(void) -{ if (efi.mem_reserve != EFI_INVALID_TABLE_ADDR) { unsigned long prsv = efi.mem_reserve; diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c index eee42d5e25ee..c037c6c5d0b7 100644 --- a/drivers/firmware/efi/libstub/arm-stub.c +++ b/drivers/firmware/efi/libstub/arm-stub.c @@ -75,9 +75,6 @@ void install_memreserve_table(efi_system_table_t *sys_table_arg) efi_guid_t memreserve_table_guid = LINUX_EFI_MEMRESERVE_TABLE_GUID; efi_status_t status; - if (IS_ENABLED(CONFIG_ARM)) - return; - status = efi_call_early(allocate_pool, EFI_LOADER_DATA, sizeof(*rsv), (void **)&rsv); if (status != EFI_SUCCESS) { diff --git a/drivers/firmware/efi/runtime-wrappers.c b/drivers/firmware/efi/runtime-wrappers.c index 8903b9ccfc2b..e2abfdb5cee6 100644 --- a/drivers/firmware/efi/runtime-wrappers.c +++ b/drivers/firmware/efi/runtime-wrappers.c @@ -147,6 +147,13 @@ void efi_call_virt_check_flags(unsigned long flags, const char *call) static DEFINE_SEMAPHORE(efi_runtime_lock); /* + * Expose the EFI runtime lock to the UV platform + */ +#ifdef CONFIG_X86_UV +extern struct semaphore __efi_uv_runtime_lock __alias(efi_runtime_lock); +#endif + +/* * Calls the appropriate efi_runtime_service() with the appropriate * arguments. * diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 8fab0d637ee5..3a9b48b227ac 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -90,8 +90,10 @@ static int psp_sw_fini(void *handle) adev->psp.sos_fw = NULL; release_firmware(adev->psp.asd_fw); adev->psp.asd_fw = NULL; - release_firmware(adev->psp.ta_fw); - adev->psp.ta_fw = NULL; + if (adev->psp.ta_fw) { + release_firmware(adev->psp.ta_fw); + adev->psp.ta_fw = NULL; + } return 0; } @@ -435,6 +437,9 @@ static int psp_xgmi_initialize(struct psp_context *psp) struct ta_xgmi_shared_memory *xgmi_cmd; int ret; + if (!psp->adev->psp.ta_fw) + return -ENOENT; + if (!psp->xgmi_context.initialized) { ret = psp_xgmi_init_shared_buf(psp); if (ret) diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c index 0c6e7f9b143f..189fcb004579 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c @@ -152,18 +152,22 @@ static int psp_v11_0_init_microcode(struct psp_context *psp) snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ta.bin", chip_name); err = request_firmware(&adev->psp.ta_fw, fw_name, adev->dev); - if (err) - goto out2; - - err = amdgpu_ucode_validate(adev->psp.ta_fw); - if (err) - goto out2; - - ta_hdr = (const struct ta_firmware_header_v1_0 *)adev->psp.ta_fw->data; - adev->psp.ta_xgmi_ucode_version = le32_to_cpu(ta_hdr->ta_xgmi_ucode_version); - adev->psp.ta_xgmi_ucode_size = le32_to_cpu(ta_hdr->ta_xgmi_size_bytes); - adev->psp.ta_xgmi_start_addr = (uint8_t *)ta_hdr + - le32_to_cpu(ta_hdr->header.ucode_array_offset_bytes); + if (err) { + release_firmware(adev->psp.ta_fw); + adev->psp.ta_fw = NULL; + dev_info(adev->dev, + "psp v11.0: Failed to load firmware \"%s\"\n", fw_name); + } else { + err = amdgpu_ucode_validate(adev->psp.ta_fw); + if (err) + goto out2; + + ta_hdr = (const struct ta_firmware_header_v1_0 *)adev->psp.ta_fw->data; + adev->psp.ta_xgmi_ucode_version = le32_to_cpu(ta_hdr->ta_xgmi_ucode_version); + adev->psp.ta_xgmi_ucode_size = le32_to_cpu(ta_hdr->ta_xgmi_size_bytes); + adev->psp.ta_xgmi_start_addr = (uint8_t *)ta_hdr + + le32_to_cpu(ta_hdr->header.ucode_array_offset_bytes); + } return 0; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c index 9a7ac58eb18e..ddd75a4d8ba5 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c @@ -671,6 +671,25 @@ static ssize_t dp_phy_test_pattern_debugfs_write(struct file *f, const char __us return bytes_from_user; } +/* + * Returns the min and max vrr vfreq through the connector's debugfs file. + * Example usage: cat /sys/kernel/debug/dri/0/DP-1/vrr_range + */ +static int vrr_range_show(struct seq_file *m, void *data) +{ + struct drm_connector *connector = m->private; + struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); + + if (connector->status != connector_status_connected) + return -ENODEV; + + seq_printf(m, "Min: %u\n", (unsigned int)aconnector->min_vfreq); + seq_printf(m, "Max: %u\n", (unsigned int)aconnector->max_vfreq); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(vrr_range); + static const struct file_operations dp_link_settings_debugfs_fops = { .owner = THIS_MODULE, .read = dp_link_settings_read, @@ -697,7 +716,8 @@ static const struct { } dp_debugfs_entries[] = { {"link_settings", &dp_link_settings_debugfs_fops}, {"phy_settings", &dp_phy_settings_debugfs_fop}, - {"test_pattern", &dp_phy_test_pattern_fops} + {"test_pattern", &dp_phy_test_pattern_fops}, + {"vrr_range", &vrr_range_fops} }; int connector_debugfs_init(struct amdgpu_dm_connector *connector) diff --git a/drivers/gpu/drm/drm_lease.c b/drivers/gpu/drm/drm_lease.c index 99cba8ea5d82..5df1256618cc 100644 --- a/drivers/gpu/drm/drm_lease.c +++ b/drivers/gpu/drm/drm_lease.c @@ -528,7 +528,8 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev, object_count = cl->object_count; - object_ids = memdup_user(u64_to_user_ptr(cl->object_ids), object_count * sizeof(__u32)); + object_ids = memdup_user(u64_to_user_ptr(cl->object_ids), + array_size(object_count, sizeof(__u32))); if (IS_ERR(object_ids)) return PTR_ERR(object_ids); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 216f52b744a6..c882ea94172c 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1824,6 +1824,16 @@ i915_gem_sw_finish_ioctl(struct drm_device *dev, void *data, return 0; } +static inline bool +__vma_matches(struct vm_area_struct *vma, struct file *filp, + unsigned long addr, unsigned long size) +{ + if (vma->vm_file != filp) + return false; + + return vma->vm_start == addr && (vma->vm_end - vma->vm_start) == size; +} + /** * i915_gem_mmap_ioctl - Maps the contents of an object, returning the address * it is mapped to. @@ -1882,7 +1892,7 @@ i915_gem_mmap_ioctl(struct drm_device *dev, void *data, return -EINTR; } vma = find_vma(mm, addr); - if (vma) + if (vma && __vma_matches(vma, obj->base.filp, addr, args->size)) vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags)); else diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index d6c8f8fdfda5..cf7c66bb3ed9 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -5,6 +5,7 @@ */ #include <linux/irq.h> +#include <linux/pm_runtime.h> #include "i915_pmu.h" #include "intel_ringbuffer.h" #include "i915_drv.h" @@ -478,7 +479,6 @@ static u64 get_rc6(struct drm_i915_private *i915) * counter value. */ spin_lock_irqsave(&i915->pmu.lock, flags); - spin_lock(&kdev->power.lock); /* * After the above branch intel_runtime_pm_get_if_in_use failed @@ -491,16 +491,13 @@ static u64 get_rc6(struct drm_i915_private *i915) * suspended and if not we cannot do better than report the last * known RC6 value. */ - if (kdev->power.runtime_status == RPM_SUSPENDED) { - if (!i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur) - i915->pmu.suspended_jiffies_last = - kdev->power.suspended_jiffies; + if (pm_runtime_status_suspended(kdev)) { + val = pm_runtime_suspended_time(kdev); - val = kdev->power.suspended_jiffies - - i915->pmu.suspended_jiffies_last; - val += jiffies - kdev->power.accounting_timestamp; + if (!i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur) + i915->pmu.suspended_time_last = val; - val = jiffies_to_nsecs(val); + val -= i915->pmu.suspended_time_last; val += i915->pmu.sample[__I915_SAMPLE_RC6].cur; i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur = val; @@ -510,7 +507,6 @@ static u64 get_rc6(struct drm_i915_private *i915) val = i915->pmu.sample[__I915_SAMPLE_RC6].cur; } - spin_unlock(&kdev->power.lock); spin_unlock_irqrestore(&i915->pmu.lock, flags); } @@ -594,7 +590,8 @@ static void i915_pmu_enable(struct perf_event *event) * Update the bitmask of enabled events and increment * the event reference counter. */ - GEM_BUG_ON(bit >= I915_PMU_MASK_BITS); + BUILD_BUG_ON(ARRAY_SIZE(i915->pmu.enable_count) != I915_PMU_MASK_BITS); + GEM_BUG_ON(bit >= ARRAY_SIZE(i915->pmu.enable_count)); GEM_BUG_ON(i915->pmu.enable_count[bit] == ~0); i915->pmu.enable |= BIT_ULL(bit); i915->pmu.enable_count[bit]++; @@ -615,11 +612,16 @@ static void i915_pmu_enable(struct perf_event *event) engine = intel_engine_lookup_user(i915, engine_event_class(event), engine_event_instance(event)); - GEM_BUG_ON(!engine); - engine->pmu.enable |= BIT(sample); - GEM_BUG_ON(sample >= I915_PMU_SAMPLE_BITS); + BUILD_BUG_ON(ARRAY_SIZE(engine->pmu.enable_count) != + I915_ENGINE_SAMPLE_COUNT); + BUILD_BUG_ON(ARRAY_SIZE(engine->pmu.sample) != + I915_ENGINE_SAMPLE_COUNT); + GEM_BUG_ON(sample >= ARRAY_SIZE(engine->pmu.enable_count)); + GEM_BUG_ON(sample >= ARRAY_SIZE(engine->pmu.sample)); GEM_BUG_ON(engine->pmu.enable_count[sample] == ~0); + + engine->pmu.enable |= BIT(sample); engine->pmu.enable_count[sample]++; } @@ -649,9 +651,11 @@ static void i915_pmu_disable(struct perf_event *event) engine = intel_engine_lookup_user(i915, engine_event_class(event), engine_event_instance(event)); - GEM_BUG_ON(!engine); - GEM_BUG_ON(sample >= I915_PMU_SAMPLE_BITS); + + GEM_BUG_ON(sample >= ARRAY_SIZE(engine->pmu.enable_count)); + GEM_BUG_ON(sample >= ARRAY_SIZE(engine->pmu.sample)); GEM_BUG_ON(engine->pmu.enable_count[sample] == 0); + /* * Decrement the reference count and clear the enabled * bitmask when the last listener on an event goes away. @@ -660,7 +664,7 @@ static void i915_pmu_disable(struct perf_event *event) engine->pmu.enable &= ~BIT(sample); } - GEM_BUG_ON(bit >= I915_PMU_MASK_BITS); + GEM_BUG_ON(bit >= ARRAY_SIZE(i915->pmu.enable_count)); GEM_BUG_ON(i915->pmu.enable_count[bit] == 0); /* * Decrement the reference count and clear the enabled diff --git a/drivers/gpu/drm/i915/i915_pmu.h b/drivers/gpu/drm/i915/i915_pmu.h index 7f164ca3db12..4fc4f2478301 100644 --- a/drivers/gpu/drm/i915/i915_pmu.h +++ b/drivers/gpu/drm/i915/i915_pmu.h @@ -31,6 +31,8 @@ enum { ((1 << I915_PMU_SAMPLE_BITS) + \ (I915_PMU_LAST + 1 - __I915_PMU_OTHER(0))) +#define I915_ENGINE_SAMPLE_COUNT (I915_SAMPLE_SEMA + 1) + struct i915_pmu_sample { u64 cur; }; @@ -95,9 +97,9 @@ struct i915_pmu { */ struct i915_pmu_sample sample[__I915_NUM_PMU_SAMPLERS]; /** - * @suspended_jiffies_last: Cached suspend time from PM core. + * @suspended_time_last: Cached suspend time from PM core. */ - unsigned long suspended_jiffies_last; + u64 suspended_time_last; /** * @i915_attr: Memory block holding device attributes. */ diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 0a7d60509ca7..067054cf4a86 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -1790,7 +1790,7 @@ enum i915_power_well_id { #define _CNL_PORT_TX_C_LN0_OFFSET 0x162C40 #define _CNL_PORT_TX_D_LN0_OFFSET 0x162E40 #define _CNL_PORT_TX_F_LN0_OFFSET 0x162840 -#define _CNL_PORT_TX_DW_GRP(port, dw) (_PICK((port), \ +#define _CNL_PORT_TX_DW_GRP(dw, port) (_PICK((port), \ _CNL_PORT_TX_AE_GRP_OFFSET, \ _CNL_PORT_TX_B_GRP_OFFSET, \ _CNL_PORT_TX_B_GRP_OFFSET, \ @@ -1798,7 +1798,7 @@ enum i915_power_well_id { _CNL_PORT_TX_AE_GRP_OFFSET, \ _CNL_PORT_TX_F_GRP_OFFSET) + \ 4 * (dw)) -#define _CNL_PORT_TX_DW_LN0(port, dw) (_PICK((port), \ +#define _CNL_PORT_TX_DW_LN0(dw, port) (_PICK((port), \ _CNL_PORT_TX_AE_LN0_OFFSET, \ _CNL_PORT_TX_B_LN0_OFFSET, \ _CNL_PORT_TX_B_LN0_OFFSET, \ @@ -1834,9 +1834,9 @@ enum i915_power_well_id { #define _CNL_PORT_TX_DW4_LN0_AE 0x162450 #define _CNL_PORT_TX_DW4_LN1_AE 0x1624D0 -#define CNL_PORT_TX_DW4_GRP(port) _MMIO(_CNL_PORT_TX_DW_GRP((port), 4)) -#define CNL_PORT_TX_DW4_LN0(port) _MMIO(_CNL_PORT_TX_DW_LN0((port), 4)) -#define CNL_PORT_TX_DW4_LN(port, ln) _MMIO(_CNL_PORT_TX_DW_LN0((port), 4) + \ +#define CNL_PORT_TX_DW4_GRP(port) _MMIO(_CNL_PORT_TX_DW_GRP(4, (port))) +#define CNL_PORT_TX_DW4_LN0(port) _MMIO(_CNL_PORT_TX_DW_LN0(4, (port))) +#define CNL_PORT_TX_DW4_LN(port, ln) _MMIO(_CNL_PORT_TX_DW_LN0(4, (port)) + \ ((ln) * (_CNL_PORT_TX_DW4_LN1_AE - \ _CNL_PORT_TX_DW4_LN0_AE))) #define ICL_PORT_TX_DW4_AUX(port) _MMIO(_ICL_PORT_TX_DW_AUX(4, port)) @@ -1864,8 +1864,12 @@ enum i915_power_well_id { #define RTERM_SELECT(x) ((x) << 3) #define RTERM_SELECT_MASK (0x7 << 3) -#define CNL_PORT_TX_DW7_GRP(port) _MMIO(_CNL_PORT_TX_DW_GRP((port), 7)) -#define CNL_PORT_TX_DW7_LN0(port) _MMIO(_CNL_PORT_TX_DW_LN0((port), 7)) +#define CNL_PORT_TX_DW7_GRP(port) _MMIO(_CNL_PORT_TX_DW_GRP(7, (port))) +#define CNL_PORT_TX_DW7_LN0(port) _MMIO(_CNL_PORT_TX_DW_LN0(7, (port))) +#define ICL_PORT_TX_DW7_AUX(port) _MMIO(_ICL_PORT_TX_DW_AUX(7, port)) +#define ICL_PORT_TX_DW7_GRP(port) _MMIO(_ICL_PORT_TX_DW_GRP(7, port)) +#define ICL_PORT_TX_DW7_LN0(port) _MMIO(_ICL_PORT_TX_DW_LN(7, 0, port)) +#define ICL_PORT_TX_DW7_LN(port, ln) _MMIO(_ICL_PORT_TX_DW_LN(7, ln, port)) #define N_SCALAR(x) ((x) << 24) #define N_SCALAR_MASK (0x7F << 24) diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index 4079050f9d6c..7edce1b7b348 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -494,103 +494,58 @@ static const struct cnl_ddi_buf_trans cnl_ddi_translations_edp_1_05V[] = { { 0x2, 0x7F, 0x3F, 0x00, 0x00 }, /* 400 400 0.0 */ }; -struct icl_combo_phy_ddi_buf_trans { - u32 dw2_swing_select; - u32 dw2_swing_scalar; - u32 dw4_scaling; -}; - -/* Voltage Swing Programming for VccIO 0.85V for DP */ -static const struct icl_combo_phy_ddi_buf_trans icl_combo_phy_ddi_translations_dp_hdmi_0_85V[] = { - /* Voltage mV db */ - { 0x2, 0x98, 0x0018 }, /* 400 0.0 */ - { 0x2, 0x98, 0x3015 }, /* 400 3.5 */ - { 0x2, 0x98, 0x6012 }, /* 400 6.0 */ - { 0x2, 0x98, 0x900F }, /* 400 9.5 */ - { 0xB, 0x70, 0x0018 }, /* 600 0.0 */ - { 0xB, 0x70, 0x3015 }, /* 600 3.5 */ - { 0xB, 0x70, 0x6012 }, /* 600 6.0 */ - { 0x5, 0x00, 0x0018 }, /* 800 0.0 */ - { 0x5, 0x00, 0x3015 }, /* 800 3.5 */ - { 0x6, 0x98, 0x0018 }, /* 1200 0.0 */ -}; - -/* FIXME - After table is updated in Bspec */ -/* Voltage Swing Programming for VccIO 0.85V for eDP */ -static const struct icl_combo_phy_ddi_buf_trans icl_combo_phy_ddi_translations_edp_0_85V[] = { - /* Voltage mV db */ - { 0x0, 0x00, 0x00 }, /* 200 0.0 */ - { 0x0, 0x00, 0x00 }, /* 200 1.5 */ - { 0x0, 0x00, 0x00 }, /* 200 4.0 */ - { 0x0, 0x00, 0x00 }, /* 200 6.0 */ - { 0x0, 0x00, 0x00 }, /* 250 0.0 */ - { 0x0, 0x00, 0x00 }, /* 250 1.5 */ - { 0x0, 0x00, 0x00 }, /* 250 4.0 */ - { 0x0, 0x00, 0x00 }, /* 300 0.0 */ - { 0x0, 0x00, 0x00 }, /* 300 1.5 */ - { 0x0, 0x00, 0x00 }, /* 350 0.0 */ -}; - -/* Voltage Swing Programming for VccIO 0.95V for DP */ -static const struct icl_combo_phy_ddi_buf_trans icl_combo_phy_ddi_translations_dp_hdmi_0_95V[] = { - /* Voltage mV db */ - { 0x2, 0x98, 0x0018 }, /* 400 0.0 */ - { 0x2, 0x98, 0x3015 }, /* 400 3.5 */ - { 0x2, 0x98, 0x6012 }, /* 400 6.0 */ - { 0x2, 0x98, 0x900F }, /* 400 9.5 */ - { 0x4, 0x98, 0x0018 }, /* 600 0.0 */ - { 0x4, 0x98, 0x3015 }, /* 600 3.5 */ - { 0x4, 0x98, 0x6012 }, /* 600 6.0 */ - { 0x5, 0x76, 0x0018 }, /* 800 0.0 */ - { 0x5, 0x76, 0x3015 }, /* 800 3.5 */ - { 0x6, 0x98, 0x0018 }, /* 1200 0.0 */ +/* icl_combo_phy_ddi_translations */ +static const struct cnl_ddi_buf_trans icl_combo_phy_ddi_translations_dp_hbr2[] = { + /* NT mV Trans mV db */ + { 0xA, 0x35, 0x3F, 0x00, 0x00 }, /* 350 350 0.0 */ + { 0xA, 0x4F, 0x37, 0x00, 0x08 }, /* 350 500 3.1 */ + { 0xC, 0x71, 0x2F, 0x00, 0x10 }, /* 350 700 6.0 */ + { 0x6, 0x7F, 0x2B, 0x00, 0x14 }, /* 350 900 8.2 */ + { 0xA, 0x4C, 0x3F, 0x00, 0x00 }, /* 500 500 0.0 */ + { 0xC, 0x73, 0x34, 0x00, 0x0B }, /* 500 700 2.9 */ + { 0x6, 0x7F, 0x2F, 0x00, 0x10 }, /* 500 900 5.1 */ + { 0xC, 0x6C, 0x3C, 0x00, 0x03 }, /* 650 700 0.6 */ + { 0x6, 0x7F, 0x35, 0x00, 0x0A }, /* 600 900 3.5 */ + { 0x6, 0x7F, 0x3F, 0x00, 0x00 }, /* 900 900 0.0 */ }; -/* FIXME - After table is updated in Bspec */ -/* Voltage Swing Programming for VccIO 0.95V for eDP */ -static const struct icl_combo_phy_ddi_buf_trans icl_combo_phy_ddi_translations_edp_0_95V[] = { - /* Voltage mV db */ - { 0x0, 0x00, 0x00 }, /* 200 0.0 */ - { 0x0, 0x00, 0x00 }, /* 200 1.5 */ - { 0x0, 0x00, 0x00 }, /* 200 4.0 */ - { 0x0, 0x00, 0x00 }, /* 200 6.0 */ - { 0x0, 0x00, 0x00 }, /* 250 0.0 */ - { 0x0, 0x00, 0x00 }, /* 250 1.5 */ - { 0x0, 0x00, 0x00 }, /* 250 4.0 */ - { 0x0, 0x00, 0x00 }, /* 300 0.0 */ - { 0x0, 0x00, 0x00 }, /* 300 1.5 */ - { 0x0, 0x00, 0x00 }, /* 350 0.0 */ +static const struct cnl_ddi_buf_trans icl_combo_phy_ddi_translations_edp_hbr2[] = { + /* NT mV Trans mV db */ + { 0x0, 0x7F, 0x3F, 0x00, 0x00 }, /* 200 200 0.0 */ + { 0x8, 0x7F, 0x38, 0x00, 0x07 }, /* 200 250 1.9 */ + { 0x1, 0x7F, 0x33, 0x00, 0x0C }, /* 200 300 3.5 */ + { 0x9, 0x7F, 0x31, 0x00, 0x0E }, /* 200 350 4.9 */ + { 0x8, 0x7F, 0x3F, 0x00, 0x00 }, /* 250 250 0.0 */ + { 0x1, 0x7F, 0x38, 0x00, 0x07 }, /* 250 300 1.6 */ + { 0x9, 0x7F, 0x35, 0x00, 0x0A }, /* 250 350 2.9 */ + { 0x1, 0x7F, 0x3F, 0x00, 0x00 }, /* 300 300 0.0 */ + { 0x9, 0x7F, 0x38, 0x00, 0x07 }, /* 300 350 1.3 */ + { 0x9, 0x7F, 0x3F, 0x00, 0x00 }, /* 350 350 0.0 */ }; -/* Voltage Swing Programming for VccIO 1.05V for DP */ -static const struct icl_combo_phy_ddi_buf_trans icl_combo_phy_ddi_translations_dp_hdmi_1_05V[] = { - /* Voltage mV db */ - { 0x2, 0x98, 0x0018 }, /* 400 0.0 */ - { 0x2, 0x98, 0x3015 }, /* 400 3.5 */ - { 0x2, 0x98, 0x6012 }, /* 400 6.0 */ - { 0x2, 0x98, 0x900F }, /* 400 9.5 */ - { 0x4, 0x98, 0x0018 }, /* 600 0.0 */ - { 0x4, 0x98, 0x3015 }, /* 600 3.5 */ - { 0x4, 0x98, 0x6012 }, /* 600 6.0 */ - { 0x5, 0x71, 0x0018 }, /* 800 0.0 */ - { 0x5, 0x71, 0x3015 }, /* 800 3.5 */ - { 0x6, 0x98, 0x0018 }, /* 1200 0.0 */ +static const struct cnl_ddi_buf_trans icl_combo_phy_ddi_translations_edp_hbr3[] = { + /* NT mV Trans mV db */ + { 0xA, 0x35, 0x3F, 0x00, 0x00 }, /* 350 350 0.0 */ + { 0xA, 0x4F, 0x37, 0x00, 0x08 }, /* 350 500 3.1 */ + { 0xC, 0x71, 0x2F, 0x00, 0x10 }, /* 350 700 6.0 */ + { 0x6, 0x7F, 0x2B, 0x00, 0x14 }, /* 350 900 8.2 */ + { 0xA, 0x4C, 0x3F, 0x00, 0x00 }, /* 500 500 0.0 */ + { 0xC, 0x73, 0x34, 0x00, 0x0B }, /* 500 700 2.9 */ + { 0x6, 0x7F, 0x2F, 0x00, 0x10 }, /* 500 900 5.1 */ + { 0xC, 0x6C, 0x3C, 0x00, 0x03 }, /* 650 700 0.6 */ + { 0x6, 0x7F, 0x35, 0x00, 0x0A }, /* 600 900 3.5 */ + { 0x6, 0x7F, 0x3F, 0x00, 0x00 }, /* 900 900 0.0 */ }; -/* FIXME - After table is updated in Bspec */ -/* Voltage Swing Programming for VccIO 1.05V for eDP */ -static const struct icl_combo_phy_ddi_buf_trans icl_combo_phy_ddi_translations_edp_1_05V[] = { - /* Voltage mV db */ - { 0x0, 0x00, 0x00 }, /* 200 0.0 */ - { 0x0, 0x00, 0x00 }, /* 200 1.5 */ - { 0x0, 0x00, 0x00 }, /* 200 4.0 */ - { 0x0, 0x00, 0x00 }, /* 200 6.0 */ - { 0x0, 0x00, 0x00 }, /* 250 0.0 */ - { 0x0, 0x00, 0x00 }, /* 250 1.5 */ - { 0x0, 0x00, 0x00 }, /* 250 4.0 */ - { 0x0, 0x00, 0x00 }, /* 300 0.0 */ - { 0x0, 0x00, 0x00 }, /* 300 1.5 */ - { 0x0, 0x00, 0x00 }, /* 350 0.0 */ +static const struct cnl_ddi_buf_trans icl_combo_phy_ddi_translations_hdmi[] = { + /* NT mV Trans mV db */ + { 0xA, 0x60, 0x3F, 0x00, 0x00 }, /* 450 450 0.0 */ + { 0xB, 0x73, 0x36, 0x00, 0x09 }, /* 450 650 3.2 */ + { 0x6, 0x7F, 0x31, 0x00, 0x0E }, /* 450 850 5.5 */ + { 0xB, 0x73, 0x3F, 0x00, 0x00 }, /* 650 650 0.0 ALS */ + { 0x6, 0x7F, 0x37, 0x00, 0x08 }, /* 650 850 2.3 */ + { 0x6, 0x7F, 0x3F, 0x00, 0x00 }, /* 850 850 0.0 */ + { 0x6, 0x7F, 0x35, 0x00, 0x0A }, /* 600 850 3.0 */ }; struct icl_mg_phy_ddi_buf_trans { @@ -871,43 +826,23 @@ cnl_get_buf_trans_edp(struct drm_i915_private *dev_priv, int *n_entries) } } -static const struct icl_combo_phy_ddi_buf_trans * +static const struct cnl_ddi_buf_trans * icl_get_combo_buf_trans(struct drm_i915_private *dev_priv, enum port port, - int type, int *n_entries) + int type, int rate, int *n_entries) { - u32 voltage = I915_READ(ICL_PORT_COMP_DW3(port)) & VOLTAGE_INFO_MASK; - - if (type == INTEL_OUTPUT_EDP && dev_priv->vbt.edp.low_vswing) { - switch (voltage) { - case VOLTAGE_INFO_0_85V: - *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_0_85V); - return icl_combo_phy_ddi_translations_edp_0_85V; - case VOLTAGE_INFO_0_95V: - *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_0_95V); - return icl_combo_phy_ddi_translations_edp_0_95V; - case VOLTAGE_INFO_1_05V: - *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_1_05V); - return icl_combo_phy_ddi_translations_edp_1_05V; - default: - MISSING_CASE(voltage); - return NULL; - } - } else { - switch (voltage) { - case VOLTAGE_INFO_0_85V: - *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_dp_hdmi_0_85V); - return icl_combo_phy_ddi_translations_dp_hdmi_0_85V; - case VOLTAGE_INFO_0_95V: - *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_dp_hdmi_0_95V); - return icl_combo_phy_ddi_translations_dp_hdmi_0_95V; - case VOLTAGE_INFO_1_05V: - *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_dp_hdmi_1_05V); - return icl_combo_phy_ddi_translations_dp_hdmi_1_05V; - default: - MISSING_CASE(voltage); - return NULL; - } + if (type == INTEL_OUTPUT_HDMI) { + *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_hdmi); + return icl_combo_phy_ddi_translations_hdmi; + } else if (rate > 540000 && type == INTEL_OUTPUT_EDP) { + *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_hbr3); + return icl_combo_phy_ddi_translations_edp_hbr3; + } else if (type == INTEL_OUTPUT_EDP && dev_priv->vbt.edp.low_vswing) { + *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_hbr2); + return icl_combo_phy_ddi_translations_edp_hbr2; } + + *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_dp_hbr2); + return icl_combo_phy_ddi_translations_dp_hbr2; } static int intel_ddi_hdmi_level(struct drm_i915_private *dev_priv, enum port port) @@ -918,8 +853,8 @@ static int intel_ddi_hdmi_level(struct drm_i915_private *dev_priv, enum port por if (IS_ICELAKE(dev_priv)) { if (intel_port_is_combophy(dev_priv, port)) - icl_get_combo_buf_trans(dev_priv, port, - INTEL_OUTPUT_HDMI, &n_entries); + icl_get_combo_buf_trans(dev_priv, port, INTEL_OUTPUT_HDMI, + 0, &n_entries); else n_entries = ARRAY_SIZE(icl_mg_phy_ddi_translations); default_entry = n_entries - 1; @@ -2275,13 +2210,14 @@ static void bxt_ddi_vswing_sequence(struct intel_encoder *encoder, u8 intel_ddi_dp_voltage_max(struct intel_encoder *encoder) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base); enum port port = encoder->port; int n_entries; if (IS_ICELAKE(dev_priv)) { if (intel_port_is_combophy(dev_priv, port)) icl_get_combo_buf_trans(dev_priv, port, encoder->type, - &n_entries); + intel_dp->link_rate, &n_entries); else n_entries = ARRAY_SIZE(icl_mg_phy_ddi_translations); } else if (IS_CANNONLAKE(dev_priv)) { @@ -2462,14 +2398,15 @@ static void cnl_ddi_vswing_sequence(struct intel_encoder *encoder, } static void icl_ddi_combo_vswing_program(struct drm_i915_private *dev_priv, - u32 level, enum port port, int type) + u32 level, enum port port, int type, + int rate) { - const struct icl_combo_phy_ddi_buf_trans *ddi_translations = NULL; + const struct cnl_ddi_buf_trans *ddi_translations = NULL; u32 n_entries, val; int ln; ddi_translations = icl_get_combo_buf_trans(dev_priv, port, type, - &n_entries); + rate, &n_entries); if (!ddi_translations) return; @@ -2478,34 +2415,23 @@ static void icl_ddi_combo_vswing_program(struct drm_i915_private *dev_priv, level = n_entries - 1; } - /* Set PORT_TX_DW5 Rterm Sel to 110b. */ + /* Set PORT_TX_DW5 */ val = I915_READ(ICL_PORT_TX_DW5_LN0(port)); - val &= ~RTERM_SELECT_MASK; + val &= ~(SCALING_MODE_SEL_MASK | RTERM_SELECT_MASK | + TAP2_DISABLE | TAP3_DISABLE); + val |= SCALING_MODE_SEL(0x2); val |= RTERM_SELECT(0x6); - I915_WRITE(ICL_PORT_TX_DW5_GRP(port), val); - - /* Program PORT_TX_DW5 */ - val = I915_READ(ICL_PORT_TX_DW5_LN0(port)); - /* Set DisableTap2 and DisableTap3 if MIPI DSI - * Clear DisableTap2 and DisableTap3 for all other Ports - */ - if (type == INTEL_OUTPUT_DSI) { - val |= TAP2_DISABLE; - val |= TAP3_DISABLE; - } else { - val &= ~TAP2_DISABLE; - val &= ~TAP3_DISABLE; - } + val |= TAP3_DISABLE; I915_WRITE(ICL_PORT_TX_DW5_GRP(port), val); /* Program PORT_TX_DW2 */ val = I915_READ(ICL_PORT_TX_DW2_LN0(port)); val &= ~(SWING_SEL_LOWER_MASK | SWING_SEL_UPPER_MASK | RCOMP_SCALAR_MASK); - val |= SWING_SEL_UPPER(ddi_translations[level].dw2_swing_select); - val |= SWING_SEL_LOWER(ddi_translations[level].dw2_swing_select); + val |= SWING_SEL_UPPER(ddi_translations[level].dw2_swing_sel); + val |= SWING_SEL_LOWER(ddi_translations[level].dw2_swing_sel); /* Program Rcomp scalar for every table entry */ - val |= RCOMP_SCALAR(ddi_translations[level].dw2_swing_scalar); + val |= RCOMP_SCALAR(0x98); I915_WRITE(ICL_PORT_TX_DW2_GRP(port), val); /* Program PORT_TX_DW4 */ @@ -2514,9 +2440,17 @@ static void icl_ddi_combo_vswing_program(struct drm_i915_private *dev_priv, val = I915_READ(ICL_PORT_TX_DW4_LN(port, ln)); val &= ~(POST_CURSOR_1_MASK | POST_CURSOR_2_MASK | CURSOR_COEFF_MASK); - val |= ddi_translations[level].dw4_scaling; + val |= POST_CURSOR_1(ddi_translations[level].dw4_post_cursor_1); + val |= POST_CURSOR_2(ddi_translations[level].dw4_post_cursor_2); + val |= CURSOR_COEFF(ddi_translations[level].dw4_cursor_coeff); I915_WRITE(ICL_PORT_TX_DW4_LN(port, ln), val); } + + /* Program PORT_TX_DW7 */ + val = I915_READ(ICL_PORT_TX_DW7_LN0(port)); + val &= ~N_SCALAR_MASK; + val |= N_SCALAR(ddi_translations[level].dw7_n_scalar); + I915_WRITE(ICL_PORT_TX_DW7_GRP(port), val); } static void icl_combo_phy_ddi_vswing_sequence(struct intel_encoder *encoder, @@ -2581,7 +2515,7 @@ static void icl_combo_phy_ddi_vswing_sequence(struct intel_encoder *encoder, I915_WRITE(ICL_PORT_TX_DW5_GRP(port), val); /* 5. Program swing and de-emphasis */ - icl_ddi_combo_vswing_program(dev_priv, level, port, type); + icl_ddi_combo_vswing_program(dev_priv, level, port, type, rate); /* 6. Set training enable to trigger update */ val = I915_READ(ICL_PORT_TX_DW5_LN0(port)); diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index fdd2cbc56fa3..22a74608c6e4 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -304,9 +304,11 @@ static int cnl_max_source_rate(struct intel_dp *intel_dp) static int icl_max_source_rate(struct intel_dp *intel_dp) { struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); + struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev); enum port port = dig_port->base.port; - if (port == PORT_B) + if (intel_port_is_combophy(dev_priv, port) && + !intel_dp_is_edp(intel_dp)) return 540000; return 810000; diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index f94a04b4ad87..e9ddeaf05a14 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -209,6 +209,16 @@ struct intel_fbdev { unsigned long vma_flags; async_cookie_t cookie; int preferred_bpp; + + /* Whether or not fbdev hpd processing is temporarily suspended */ + bool hpd_suspended : 1; + /* Set when a hotplug was received while HPD processing was + * suspended + */ + bool hpd_waiting : 1; + + /* Protects hpd_suspended */ + struct mutex hpd_lock; }; struct intel_encoder { diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c index fb5bb5b32a60..7f365ac0b549 100644 --- a/drivers/gpu/drm/i915/intel_fbdev.c +++ b/drivers/gpu/drm/i915/intel_fbdev.c @@ -679,6 +679,7 @@ int intel_fbdev_init(struct drm_device *dev) if (ifbdev == NULL) return -ENOMEM; + mutex_init(&ifbdev->hpd_lock); drm_fb_helper_prepare(dev, &ifbdev->helper, &intel_fb_helper_funcs); if (!intel_fbdev_init_bios(dev, ifbdev)) @@ -752,6 +753,26 @@ void intel_fbdev_fini(struct drm_i915_private *dev_priv) intel_fbdev_destroy(ifbdev); } +/* Suspends/resumes fbdev processing of incoming HPD events. When resuming HPD + * processing, fbdev will perform a full connector reprobe if a hotplug event + * was received while HPD was suspended. + */ +static void intel_fbdev_hpd_set_suspend(struct intel_fbdev *ifbdev, int state) +{ + bool send_hpd = false; + + mutex_lock(&ifbdev->hpd_lock); + ifbdev->hpd_suspended = state == FBINFO_STATE_SUSPENDED; + send_hpd = !ifbdev->hpd_suspended && ifbdev->hpd_waiting; + ifbdev->hpd_waiting = false; + mutex_unlock(&ifbdev->hpd_lock); + + if (send_hpd) { + DRM_DEBUG_KMS("Handling delayed fbcon HPD event\n"); + drm_fb_helper_hotplug_event(&ifbdev->helper); + } +} + void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous) { struct drm_i915_private *dev_priv = to_i915(dev); @@ -773,6 +794,7 @@ void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous */ if (state != FBINFO_STATE_RUNNING) flush_work(&dev_priv->fbdev_suspend_work); + console_lock(); } else { /* @@ -800,17 +822,26 @@ void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous drm_fb_helper_set_suspend(&ifbdev->helper, state); console_unlock(); + + intel_fbdev_hpd_set_suspend(ifbdev, state); } void intel_fbdev_output_poll_changed(struct drm_device *dev) { struct intel_fbdev *ifbdev = to_i915(dev)->fbdev; + bool send_hpd; if (!ifbdev) return; intel_fbdev_sync(ifbdev); - if (ifbdev->vma || ifbdev->helper.deferred_setup) + + mutex_lock(&ifbdev->hpd_lock); + send_hpd = !ifbdev->hpd_suspended; + ifbdev->hpd_waiting = true; + mutex_unlock(&ifbdev->hpd_lock); + + if (send_hpd && (ifbdev->vma || ifbdev->helper.deferred_setup)) drm_fb_helper_hotplug_event(&ifbdev->helper); } diff --git a/drivers/gpu/drm/i915/intel_opregion.c b/drivers/gpu/drm/i915/intel_opregion.c index b8f106d9ecf8..3ac20153705a 100644 --- a/drivers/gpu/drm/i915/intel_opregion.c +++ b/drivers/gpu/drm/i915/intel_opregion.c @@ -55,7 +55,12 @@ struct opregion_header { u8 signature[16]; u32 size; - u32 opregion_ver; + struct { + u8 rsvd; + u8 revision; + u8 minor; + u8 major; + } __packed over; u8 bios_ver[32]; u8 vbios_ver[16]; u8 driver_ver[16]; @@ -119,7 +124,8 @@ struct opregion_asle { u64 fdss; u32 fdsp; u32 stat; - u64 rvda; /* Physical address of raw vbt data */ + u64 rvda; /* Physical (2.0) or relative from opregion (2.1+) + * address of raw VBT data. */ u32 rvds; /* Size of raw vbt data */ u8 rsvd[58]; } __packed; @@ -925,6 +931,11 @@ int intel_opregion_setup(struct drm_i915_private *dev_priv) opregion->header = base; opregion->lid_state = base + ACPI_CLID; + DRM_DEBUG_DRIVER("ACPI OpRegion version %u.%u.%u\n", + opregion->header->over.major, + opregion->header->over.minor, + opregion->header->over.revision); + mboxes = opregion->header->mboxes; if (mboxes & MBOX_ACPI) { DRM_DEBUG_DRIVER("Public ACPI methods supported\n"); @@ -953,11 +964,26 @@ int intel_opregion_setup(struct drm_i915_private *dev_priv) if (dmi_check_system(intel_no_opregion_vbt)) goto out; - if (opregion->header->opregion_ver >= 2 && opregion->asle && + if (opregion->header->over.major >= 2 && opregion->asle && opregion->asle->rvda && opregion->asle->rvds) { - opregion->rvda = memremap(opregion->asle->rvda, - opregion->asle->rvds, + resource_size_t rvda = opregion->asle->rvda; + + /* + * opregion 2.0: rvda is the physical VBT address. + * + * opregion 2.1+: rvda is unsigned, relative offset from + * opregion base, and should never point within opregion. + */ + if (opregion->header->over.major > 2 || + opregion->header->over.minor >= 1) { + WARN_ON(rvda < OPREGION_SIZE); + + rvda += asls; + } + + opregion->rvda = memremap(rvda, opregion->asle->rvds, MEMREMAP_WB); + vbt = opregion->rvda; vbt_size = opregion->asle->rvds; if (intel_bios_is_valid_vbt(vbt, vbt_size)) { @@ -967,6 +993,8 @@ int intel_opregion_setup(struct drm_i915_private *dev_priv) goto out; } else { DRM_DEBUG_KMS("Invalid VBT in ACPI OpRegion (RVDA)\n"); + memunmap(opregion->rvda); + opregion->rvda = NULL; } } diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index 72edaa7ff411..a1a7cc29fdd1 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -415,16 +415,17 @@ struct intel_engine_cs { /** * @enable_count: Reference count for the enabled samplers. * - * Index number corresponds to the bit number from @enable. + * Index number corresponds to @enum drm_i915_pmu_engine_sample. */ - unsigned int enable_count[I915_PMU_SAMPLE_BITS]; + unsigned int enable_count[I915_ENGINE_SAMPLE_COUNT]; /** * @sample: Counter values for sampling events. * * Our internal timer stores the current counters in this field. + * + * Index number corresponds to @enum drm_i915_pmu_engine_sample. */ -#define I915_ENGINE_SAMPLE_MAX (I915_SAMPLE_SEMA + 1) - struct i915_pmu_sample sample[I915_ENGINE_SAMPLE_MAX]; + struct i915_pmu_sample sample[I915_ENGINE_SAMPLE_COUNT]; } pmu; /* diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c index 2c5bbe317353..e31e263cf86b 100644 --- a/drivers/gpu/drm/imx/imx-ldb.c +++ b/drivers/gpu/drm/imx/imx-ldb.c @@ -643,8 +643,10 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data) int bus_format; ret = of_property_read_u32(child, "reg", &i); - if (ret || i < 0 || i > 1) - return -EINVAL; + if (ret || i < 0 || i > 1) { + ret = -EINVAL; + goto free_child; + } if (!of_device_is_available(child)) continue; @@ -657,7 +659,6 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data) channel = &imx_ldb->channel[i]; channel->ldb = imx_ldb; channel->chno = i; - channel->child = child; /* * The output port is port@4 with an external 4-port mux or @@ -667,13 +668,13 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data) imx_ldb->lvds_mux ? 4 : 2, 0, &channel->panel, &channel->bridge); if (ret && ret != -ENODEV) - return ret; + goto free_child; /* panel ddc only if there is no bridge */ if (!channel->bridge) { ret = imx_ldb_panel_ddc(dev, channel, child); if (ret) - return ret; + goto free_child; } bus_format = of_get_bus_format(dev, child); @@ -689,18 +690,26 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data) if (bus_format < 0) { dev_err(dev, "could not determine data mapping: %d\n", bus_format); - return bus_format; + ret = bus_format; + goto free_child; } channel->bus_format = bus_format; + channel->child = child; ret = imx_ldb_register(drm, channel); - if (ret) - return ret; + if (ret) { + channel->child = NULL; + goto free_child; + } } dev_set_drvdata(dev, imx_ldb); return 0; + +free_child: + of_node_put(child); + return ret; } static void imx_ldb_unbind(struct device *dev, struct device *master, diff --git a/drivers/gpu/drm/imx/ipuv3-plane.c b/drivers/gpu/drm/imx/ipuv3-plane.c index c390924de93d..21e964f6ab5c 100644 --- a/drivers/gpu/drm/imx/ipuv3-plane.c +++ b/drivers/gpu/drm/imx/ipuv3-plane.c @@ -370,9 +370,9 @@ static int ipu_plane_atomic_check(struct drm_plane *plane, if (ret) return ret; - /* CRTC should be enabled */ + /* nothing to check when disabling or disabled */ if (!crtc_state->enable) - return -EINVAL; + return 0; switch (plane->type) { case DRM_PLANE_TYPE_PRIMARY: diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index 4463d3826ecb..e2942c9a11a7 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -440,13 +440,10 @@ struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity) while ((entity->dependency = sched->ops->dependency(sched_job, entity))) { + trace_drm_sched_job_wait_dep(sched_job, entity->dependency); - if (drm_sched_entity_add_dependency_cb(entity)) { - - trace_drm_sched_job_wait_dep(sched_job, - entity->dependency); + if (drm_sched_entity_add_dependency_cb(entity)) return NULL; - } } /* skip jobs from entity that marked guilty */ diff --git a/drivers/gpu/drm/vkms/vkms_crc.c b/drivers/gpu/drm/vkms/vkms_crc.c index 9d9e8146db90..d7b409a3c0f8 100644 --- a/drivers/gpu/drm/vkms/vkms_crc.c +++ b/drivers/gpu/drm/vkms/vkms_crc.c @@ -1,4 +1,5 @@ -// SPDX-License-Identifier: GPL-2.0 +// SPDX-License-Identifier: GPL-2.0+ + #include "vkms_drv.h" #include <linux/crc32.h> #include <drm/drm_atomic.h> diff --git a/drivers/gpu/drm/vkms/vkms_crtc.c b/drivers/gpu/drm/vkms/vkms_crtc.c index 177bbcb38306..eb56ee893761 100644 --- a/drivers/gpu/drm/vkms/vkms_crtc.c +++ b/drivers/gpu/drm/vkms/vkms_crtc.c @@ -1,10 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ +// SPDX-License-Identifier: GPL-2.0+ #include "vkms_drv.h" #include <drm/drm_atomic_helper.h> diff --git a/drivers/gpu/drm/vkms/vkms_drv.c b/drivers/gpu/drm/vkms/vkms_drv.c index 83087877565c..7dcbecb5fac2 100644 --- a/drivers/gpu/drm/vkms/vkms_drv.c +++ b/drivers/gpu/drm/vkms/vkms_drv.c @@ -1,9 +1,4 @@ -/* - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ +// SPDX-License-Identifier: GPL-2.0+ /** * DOC: vkms (Virtual Kernel Modesetting) diff --git a/drivers/gpu/drm/vkms/vkms_drv.h b/drivers/gpu/drm/vkms/vkms_drv.h index e4469cd3d254..81f1cfbeb936 100644 --- a/drivers/gpu/drm/vkms/vkms_drv.h +++ b/drivers/gpu/drm/vkms/vkms_drv.h @@ -1,3 +1,5 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + #ifndef _VKMS_DRV_H_ #define _VKMS_DRV_H_ diff --git a/drivers/gpu/drm/vkms/vkms_gem.c b/drivers/gpu/drm/vkms/vkms_gem.c index 80311daed47a..138b0bb325cf 100644 --- a/drivers/gpu/drm/vkms/vkms_gem.c +++ b/drivers/gpu/drm/vkms/vkms_gem.c @@ -1,10 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ +// SPDX-License-Identifier: GPL-2.0+ #include <linux/shmem_fs.h> diff --git a/drivers/gpu/drm/vkms/vkms_output.c b/drivers/gpu/drm/vkms/vkms_output.c index 271a0eb9042c..4173e4f48334 100644 --- a/drivers/gpu/drm/vkms/vkms_output.c +++ b/drivers/gpu/drm/vkms/vkms_output.c @@ -1,10 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ +// SPDX-License-Identifier: GPL-2.0+ #include "vkms_drv.h" #include <drm/drm_crtc_helper.h> diff --git a/drivers/gpu/drm/vkms/vkms_plane.c b/drivers/gpu/drm/vkms/vkms_plane.c index 418817600ad1..0e67d2d42f0c 100644 --- a/drivers/gpu/drm/vkms/vkms_plane.c +++ b/drivers/gpu/drm/vkms/vkms_plane.c @@ -1,10 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ +// SPDX-License-Identifier: GPL-2.0+ #include "vkms_drv.h" #include <drm/drm_plane_helper.h> diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c index 474b00e19697..0a7d4395d427 100644 --- a/drivers/gpu/ipu-v3/ipu-common.c +++ b/drivers/gpu/ipu-v3/ipu-common.c @@ -898,8 +898,8 @@ static struct ipu_devtype ipu_type_imx51 = { .cpmem_ofs = 0x1f000000, .srm_ofs = 0x1f040000, .tpm_ofs = 0x1f060000, - .csi0_ofs = 0x1f030000, - .csi1_ofs = 0x1f038000, + .csi0_ofs = 0x1e030000, + .csi1_ofs = 0x1e038000, .ic_ofs = 0x1e020000, .disp0_ofs = 0x1e040000, .disp1_ofs = 0x1e048000, @@ -914,8 +914,8 @@ static struct ipu_devtype ipu_type_imx53 = { .cpmem_ofs = 0x07000000, .srm_ofs = 0x07040000, .tpm_ofs = 0x07060000, - .csi0_ofs = 0x07030000, - .csi1_ofs = 0x07038000, + .csi0_ofs = 0x06030000, + .csi1_ofs = 0x06038000, .ic_ofs = 0x06020000, .disp0_ofs = 0x06040000, .disp1_ofs = 0x06048000, diff --git a/drivers/gpu/ipu-v3/ipu-pre.c b/drivers/gpu/ipu-v3/ipu-pre.c index 2f8db9d62551..4a28f3fbb0a2 100644 --- a/drivers/gpu/ipu-v3/ipu-pre.c +++ b/drivers/gpu/ipu-v3/ipu-pre.c @@ -106,6 +106,7 @@ struct ipu_pre { void *buffer_virt; bool in_use; unsigned int safe_window_end; + unsigned int last_bufaddr; }; static DEFINE_MUTEX(ipu_pre_list_mutex); @@ -185,6 +186,7 @@ void ipu_pre_configure(struct ipu_pre *pre, unsigned int width, writel(bufaddr, pre->regs + IPU_PRE_CUR_BUF); writel(bufaddr, pre->regs + IPU_PRE_NEXT_BUF); + pre->last_bufaddr = bufaddr; val = IPU_PRE_PREF_ENG_CTRL_INPUT_PIXEL_FORMAT(0) | IPU_PRE_PREF_ENG_CTRL_INPUT_ACTIVE_BPP(active_bpp) | @@ -242,7 +244,11 @@ void ipu_pre_update(struct ipu_pre *pre, unsigned int bufaddr) unsigned short current_yblock; u32 val; + if (bufaddr == pre->last_bufaddr) + return; + writel(bufaddr, pre->regs + IPU_PRE_NEXT_BUF); + pre->last_bufaddr = bufaddr; do { if (time_after(jiffies, timeout)) { diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c index 4adec4ab7d06..59ee01f3d022 100644 --- a/drivers/hwmon/nct6775.c +++ b/drivers/hwmon/nct6775.c @@ -3594,7 +3594,8 @@ nct6775_check_fan_inputs(struct nct6775_data *data) fan5pin |= cr1b & BIT(5); fan5pin |= creb & BIT(5); - fan6pin = creb & BIT(3); + fan6pin = !dsw_en && (cr2d & BIT(1)); + fan6pin |= creb & BIT(3); pwm5pin |= cr2d & BIT(7); pwm5pin |= (creb & BIT(4)) && !(cr2a & BIT(0)); diff --git a/drivers/i2c/busses/i2c-bcm2835.c b/drivers/i2c/busses/i2c-bcm2835.c index ec6e69aa3a8e..d2fbb4bb4a43 100644 --- a/drivers/i2c/busses/i2c-bcm2835.c +++ b/drivers/i2c/busses/i2c-bcm2835.c @@ -183,6 +183,15 @@ static void bcm2835_i2c_start_transfer(struct bcm2835_i2c_dev *i2c_dev) bcm2835_i2c_writel(i2c_dev, BCM2835_I2C_C, c); } +static void bcm2835_i2c_finish_transfer(struct bcm2835_i2c_dev *i2c_dev) +{ + i2c_dev->curr_msg = NULL; + i2c_dev->num_msgs = 0; + + i2c_dev->msg_buf = NULL; + i2c_dev->msg_buf_remaining = 0; +} + /* * Note about I2C_C_CLEAR on error: * The I2C_C_CLEAR on errors will take some time to resolve -- if you were in @@ -283,6 +292,9 @@ static int bcm2835_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msgs[], time_left = wait_for_completion_timeout(&i2c_dev->completion, adap->timeout); + + bcm2835_i2c_finish_transfer(i2c_dev); + if (!time_left) { bcm2835_i2c_writel(i2c_dev, BCM2835_I2C_C, BCM2835_I2C_C_CLEAR); diff --git a/drivers/i2c/busses/i2c-cadence.c b/drivers/i2c/busses/i2c-cadence.c index b13605718291..d917cefc5a19 100644 --- a/drivers/i2c/busses/i2c-cadence.c +++ b/drivers/i2c/busses/i2c-cadence.c @@ -382,8 +382,10 @@ static void cdns_i2c_mrecv(struct cdns_i2c *id) * Check for the message size against FIFO depth and set the * 'hold bus' bit if it is greater than FIFO depth. */ - if (id->recv_count > CDNS_I2C_FIFO_DEPTH) + if ((id->recv_count > CDNS_I2C_FIFO_DEPTH) || id->bus_hold_flag) ctrl_reg |= CDNS_I2C_CR_HOLD; + else + ctrl_reg = ctrl_reg & ~CDNS_I2C_CR_HOLD; cdns_i2c_writereg(ctrl_reg, CDNS_I2C_CR_OFFSET); @@ -440,8 +442,11 @@ static void cdns_i2c_msend(struct cdns_i2c *id) * Check for the message size against FIFO depth and set the * 'hold bus' bit if it is greater than FIFO depth. */ - if (id->send_count > CDNS_I2C_FIFO_DEPTH) + if ((id->send_count > CDNS_I2C_FIFO_DEPTH) || id->bus_hold_flag) ctrl_reg |= CDNS_I2C_CR_HOLD; + else + ctrl_reg = ctrl_reg & ~CDNS_I2C_CR_HOLD; + cdns_i2c_writereg(ctrl_reg, CDNS_I2C_CR_OFFSET); /* Clear the interrupts in interrupt status register. */ diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 8b5d85c91e9d..b8647b5c3d4d 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -1103,6 +1103,7 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = { INTEL_CPU_FAM6(ATOM_GOLDMONT, idle_cpu_bxt), INTEL_CPU_FAM6(ATOM_GOLDMONT_PLUS, idle_cpu_bxt), INTEL_CPU_FAM6(ATOM_GOLDMONT_X, idle_cpu_dnv), + INTEL_CPU_FAM6(ATOM_TREMONT_X, idle_cpu_dnv), {} }; diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig index 4713957b0cbb..a878351f1643 100644 --- a/drivers/input/keyboard/Kconfig +++ b/drivers/input/keyboard/Kconfig @@ -420,7 +420,7 @@ config KEYBOARD_MPR121 config KEYBOARD_SNVS_PWRKEY tristate "IMX SNVS Power Key Driver" - depends on SOC_IMX6SX + depends on SOC_IMX6SX || SOC_IMX7D depends on OF help This is the snvs powerkey driver for the Freescale i.MX application diff --git a/drivers/input/keyboard/cap11xx.c b/drivers/input/keyboard/cap11xx.c index 312916f99597..73686c2460ce 100644 --- a/drivers/input/keyboard/cap11xx.c +++ b/drivers/input/keyboard/cap11xx.c @@ -75,9 +75,7 @@ struct cap11xx_led { struct cap11xx_priv *priv; struct led_classdev cdev; - struct work_struct work; u32 reg; - enum led_brightness new_brightness; }; #endif @@ -233,30 +231,21 @@ static void cap11xx_input_close(struct input_dev *idev) } #ifdef CONFIG_LEDS_CLASS -static void cap11xx_led_work(struct work_struct *work) +static int cap11xx_led_set(struct led_classdev *cdev, + enum led_brightness value) { - struct cap11xx_led *led = container_of(work, struct cap11xx_led, work); + struct cap11xx_led *led = container_of(cdev, struct cap11xx_led, cdev); struct cap11xx_priv *priv = led->priv; - int value = led->new_brightness; /* - * All LEDs share the same duty cycle as this is a HW limitation. - * Brightness levels per LED are either 0 (OFF) and 1 (ON). + * All LEDs share the same duty cycle as this is a HW + * limitation. Brightness levels per LED are either + * 0 (OFF) and 1 (ON). */ - regmap_update_bits(priv->regmap, CAP11XX_REG_LED_OUTPUT_CONTROL, - BIT(led->reg), value ? BIT(led->reg) : 0); -} - -static void cap11xx_led_set(struct led_classdev *cdev, - enum led_brightness value) -{ - struct cap11xx_led *led = container_of(cdev, struct cap11xx_led, cdev); - - if (led->new_brightness == value) - return; - - led->new_brightness = value; - schedule_work(&led->work); + return regmap_update_bits(priv->regmap, + CAP11XX_REG_LED_OUTPUT_CONTROL, + BIT(led->reg), + value ? BIT(led->reg) : 0); } static int cap11xx_init_leds(struct device *dev, @@ -299,7 +288,7 @@ static int cap11xx_init_leds(struct device *dev, led->cdev.default_trigger = of_get_property(child, "linux,default-trigger", NULL); led->cdev.flags = 0; - led->cdev.brightness_set = cap11xx_led_set; + led->cdev.brightness_set_blocking = cap11xx_led_set; led->cdev.max_brightness = 1; led->cdev.brightness = LED_OFF; @@ -312,8 +301,6 @@ static int cap11xx_init_leds(struct device *dev, led->reg = reg; led->priv = priv; - INIT_WORK(&led->work, cap11xx_led_work); - error = devm_led_classdev_register(dev, &led->cdev); if (error) { of_node_put(child); diff --git a/drivers/input/keyboard/matrix_keypad.c b/drivers/input/keyboard/matrix_keypad.c index 403452ef00e6..3d1cb7bf5e35 100644 --- a/drivers/input/keyboard/matrix_keypad.c +++ b/drivers/input/keyboard/matrix_keypad.c @@ -222,7 +222,7 @@ static void matrix_keypad_stop(struct input_dev *dev) keypad->stopped = true; spin_unlock_irq(&keypad->lock); - flush_work(&keypad->work.work); + flush_delayed_work(&keypad->work); /* * matrix_keypad_scan() will leave IRQs enabled; * we should disable them now. diff --git a/drivers/input/keyboard/qt2160.c b/drivers/input/keyboard/qt2160.c index 43b86482dda0..d466bc07aebb 100644 --- a/drivers/input/keyboard/qt2160.c +++ b/drivers/input/keyboard/qt2160.c @@ -58,10 +58,9 @@ static unsigned char qt2160_key2code[] = { struct qt2160_led { struct qt2160_data *qt2160; struct led_classdev cdev; - struct work_struct work; char name[32]; int id; - enum led_brightness new_brightness; + enum led_brightness brightness; }; #endif @@ -74,7 +73,6 @@ struct qt2160_data { u16 key_matrix; #ifdef CONFIG_LEDS_CLASS struct qt2160_led leds[QT2160_NUM_LEDS_X]; - struct mutex led_lock; #endif }; @@ -83,46 +81,39 @@ static int qt2160_write(struct i2c_client *client, u8 reg, u8 data); #ifdef CONFIG_LEDS_CLASS -static void qt2160_led_work(struct work_struct *work) +static int qt2160_led_set(struct led_classdev *cdev, + enum led_brightness value) { - struct qt2160_led *led = container_of(work, struct qt2160_led, work); + struct qt2160_led *led = container_of(cdev, struct qt2160_led, cdev); struct qt2160_data *qt2160 = led->qt2160; struct i2c_client *client = qt2160->client; - int value = led->new_brightness; u32 drive, pwmen; - mutex_lock(&qt2160->led_lock); - - drive = qt2160_read(client, QT2160_CMD_DRIVE_X); - pwmen = qt2160_read(client, QT2160_CMD_PWMEN_X); - if (value != LED_OFF) { - drive |= (1 << led->id); - pwmen |= (1 << led->id); - - } else { - drive &= ~(1 << led->id); - pwmen &= ~(1 << led->id); - } - qt2160_write(client, QT2160_CMD_DRIVE_X, drive); - qt2160_write(client, QT2160_CMD_PWMEN_X, pwmen); + if (value != led->brightness) { + drive = qt2160_read(client, QT2160_CMD_DRIVE_X); + pwmen = qt2160_read(client, QT2160_CMD_PWMEN_X); + if (value != LED_OFF) { + drive |= BIT(led->id); + pwmen |= BIT(led->id); - /* - * Changing this register will change the brightness - * of every LED in the qt2160. It's a HW limitation. - */ - if (value != LED_OFF) - qt2160_write(client, QT2160_CMD_PWM_DUTY, value); + } else { + drive &= ~BIT(led->id); + pwmen &= ~BIT(led->id); + } + qt2160_write(client, QT2160_CMD_DRIVE_X, drive); + qt2160_write(client, QT2160_CMD_PWMEN_X, pwmen); - mutex_unlock(&qt2160->led_lock); -} + /* + * Changing this register will change the brightness + * of every LED in the qt2160. It's a HW limitation. + */ + if (value != LED_OFF) + qt2160_write(client, QT2160_CMD_PWM_DUTY, value); -static void qt2160_led_set(struct led_classdev *cdev, - enum led_brightness value) -{ - struct qt2160_led *led = container_of(cdev, struct qt2160_led, cdev); + led->brightness = value; + } - led->new_brightness = value; - schedule_work(&led->work); + return 0; } #endif /* CONFIG_LEDS_CLASS */ @@ -293,20 +284,16 @@ static int qt2160_register_leds(struct qt2160_data *qt2160) int ret; int i; - mutex_init(&qt2160->led_lock); - for (i = 0; i < QT2160_NUM_LEDS_X; i++) { struct qt2160_led *led = &qt2160->leds[i]; snprintf(led->name, sizeof(led->name), "qt2160:x%d", i); led->cdev.name = led->name; - led->cdev.brightness_set = qt2160_led_set; + led->cdev.brightness_set_blocking = qt2160_led_set; led->cdev.brightness = LED_OFF; led->id = i; led->qt2160 = qt2160; - INIT_WORK(&led->work, qt2160_led_work); - ret = led_classdev_register(&client->dev, &led->cdev); if (ret < 0) return ret; @@ -324,10 +311,8 @@ static void qt2160_unregister_leds(struct qt2160_data *qt2160) { int i; - for (i = 0; i < QT2160_NUM_LEDS_X; i++) { + for (i = 0; i < QT2160_NUM_LEDS_X; i++) led_classdev_unregister(&qt2160->leds[i].cdev); - cancel_work_sync(&qt2160->leds[i].work); - } } #else diff --git a/drivers/input/keyboard/st-keyscan.c b/drivers/input/keyboard/st-keyscan.c index babcfb165e4f..3b85631fde91 100644 --- a/drivers/input/keyboard/st-keyscan.c +++ b/drivers/input/keyboard/st-keyscan.c @@ -153,6 +153,8 @@ static int keyscan_probe(struct platform_device *pdev) input_dev->id.bustype = BUS_HOST; + keypad_data->input_dev = input_dev; + error = keypad_matrix_key_parse_dt(keypad_data); if (error) return error; @@ -168,8 +170,6 @@ static int keyscan_probe(struct platform_device *pdev) input_set_drvdata(input_dev, keypad_data); - keypad_data->input_dev = input_dev; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); keypad_data->base = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(keypad_data->base)) diff --git a/drivers/input/misc/apanel.c b/drivers/input/misc/apanel.c index 094bddf56755..c1e66f45d552 100644 --- a/drivers/input/misc/apanel.c +++ b/drivers/input/misc/apanel.c @@ -22,7 +22,6 @@ #include <linux/io.h> #include <linux/input-polldev.h> #include <linux/i2c.h> -#include <linux/workqueue.h> #include <linux/leds.h> #define APANEL_NAME "Fujitsu Application Panel" @@ -59,8 +58,6 @@ struct apanel { struct i2c_client *client; unsigned short keymap[MAX_PANEL_KEYS]; u16 nkeys; - u16 led_bits; - struct work_struct led_work; struct led_classdev mail_led; }; @@ -109,25 +106,13 @@ static void apanel_poll(struct input_polled_dev *ipdev) report_key(idev, ap->keymap[i]); } -/* Track state changes of LED */ -static void led_update(struct work_struct *work) -{ - struct apanel *ap = container_of(work, struct apanel, led_work); - - i2c_smbus_write_word_data(ap->client, 0x10, ap->led_bits); -} - -static void mail_led_set(struct led_classdev *led, +static int mail_led_set(struct led_classdev *led, enum led_brightness value) { struct apanel *ap = container_of(led, struct apanel, mail_led); + u16 led_bits = value != LED_OFF ? 0x8000 : 0x0000; - if (value != LED_OFF) - ap->led_bits |= 0x8000; - else - ap->led_bits &= ~0x8000; - - schedule_work(&ap->led_work); + return i2c_smbus_write_word_data(ap->client, 0x10, led_bits); } static int apanel_remove(struct i2c_client *client) @@ -179,7 +164,7 @@ static struct apanel apanel = { }, .mail_led = { .name = "mail:blue", - .brightness_set = mail_led_set, + .brightness_set_blocking = mail_led_set, }, }; @@ -235,7 +220,6 @@ static int apanel_probe(struct i2c_client *client, if (err) goto out3; - INIT_WORK(&ap->led_work, led_update); if (device_chip[APANEL_DEV_LED] != CHIP_NONE) { err = led_classdev_register(&client->dev, &ap->mail_led); if (err) diff --git a/drivers/input/misc/bma150.c b/drivers/input/misc/bma150.c index 1efcfdf9f8a8..dd9dd4e40827 100644 --- a/drivers/input/misc/bma150.c +++ b/drivers/input/misc/bma150.c @@ -481,13 +481,14 @@ static int bma150_register_input_device(struct bma150_data *bma150) idev->close = bma150_irq_close; input_set_drvdata(idev, bma150); + bma150->input = idev; + error = input_register_device(idev); if (error) { input_free_device(idev); return error; } - bma150->input = idev; return 0; } @@ -510,15 +511,15 @@ static int bma150_register_polled_device(struct bma150_data *bma150) bma150_init_input_device(bma150, ipoll_dev->input); + bma150->input_polled = ipoll_dev; + bma150->input = ipoll_dev->input; + error = input_register_polled_device(ipoll_dev); if (error) { input_free_polled_device(ipoll_dev); return error; } - bma150->input_polled = ipoll_dev; - bma150->input = ipoll_dev->input; - return 0; } diff --git a/drivers/input/misc/pwm-vibra.c b/drivers/input/misc/pwm-vibra.c index 55da191ae550..dbb6d9e1b947 100644 --- a/drivers/input/misc/pwm-vibra.c +++ b/drivers/input/misc/pwm-vibra.c @@ -34,6 +34,7 @@ struct pwm_vibrator { struct work_struct play_work; u16 level; u32 direction_duty_cycle; + bool vcc_on; }; static int pwm_vibrator_start(struct pwm_vibrator *vibrator) @@ -42,10 +43,13 @@ static int pwm_vibrator_start(struct pwm_vibrator *vibrator) struct pwm_state state; int err; - err = regulator_enable(vibrator->vcc); - if (err) { - dev_err(pdev, "failed to enable regulator: %d", err); - return err; + if (!vibrator->vcc_on) { + err = regulator_enable(vibrator->vcc); + if (err) { + dev_err(pdev, "failed to enable regulator: %d", err); + return err; + } + vibrator->vcc_on = true; } pwm_get_state(vibrator->pwm, &state); @@ -76,11 +80,14 @@ static int pwm_vibrator_start(struct pwm_vibrator *vibrator) static void pwm_vibrator_stop(struct pwm_vibrator *vibrator) { - regulator_disable(vibrator->vcc); - if (vibrator->pwm_dir) pwm_disable(vibrator->pwm_dir); pwm_disable(vibrator->pwm); + + if (vibrator->vcc_on) { + regulator_disable(vibrator->vcc); + vibrator->vcc_on = false; + } } static void pwm_vibrator_play_work(struct work_struct *work) diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c index f322a1768fbb..225ae6980182 100644 --- a/drivers/input/mouse/elan_i2c_core.c +++ b/drivers/input/mouse/elan_i2c_core.c @@ -1336,7 +1336,6 @@ MODULE_DEVICE_TABLE(i2c, elan_id); static const struct acpi_device_id elan_acpi_id[] = { { "ELAN0000", 0 }, { "ELAN0100", 0 }, - { "ELAN0501", 0 }, { "ELAN0600", 0 }, { "ELAN0602", 0 }, { "ELAN0605", 0 }, @@ -1346,6 +1345,7 @@ static const struct acpi_device_id elan_acpi_id[] = { { "ELAN060C", 0 }, { "ELAN0611", 0 }, { "ELAN0612", 0 }, + { "ELAN0617", 0 }, { "ELAN0618", 0 }, { "ELAN061C", 0 }, { "ELAN061D", 0 }, diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c index 9fe075c137dc..a7f8b1614559 100644 --- a/drivers/input/mouse/elantech.c +++ b/drivers/input/mouse/elantech.c @@ -1119,6 +1119,8 @@ static int elantech_get_resolution_v4(struct psmouse *psmouse, * Asus UX31 0x361f00 20, 15, 0e clickpad * Asus UX32VD 0x361f02 00, 15, 0e clickpad * Avatar AVIU-145A2 0x361f00 ? clickpad + * Fujitsu CELSIUS H760 0x570f02 40, 14, 0c 3 hw buttons (**) + * Fujitsu CELSIUS H780 0x5d0f02 41, 16, 0d 3 hw buttons (**) * 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 @@ -1171,6 +1173,13 @@ static const struct dmi_system_id elantech_dmi_has_middle_button[] = { DMI_MATCH(DMI_PRODUCT_NAME, "CELSIUS H760"), }, }, + { + /* Fujitsu H780 also has a middle button */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "CELSIUS H780"), + }, + }, #endif { } }; diff --git a/drivers/input/serio/ps2-gpio.c b/drivers/input/serio/ps2-gpio.c index c62cceb97bb1..5e8d8384aa2a 100644 --- a/drivers/input/serio/ps2-gpio.c +++ b/drivers/input/serio/ps2-gpio.c @@ -76,6 +76,7 @@ static void ps2_gpio_close(struct serio *serio) { struct ps2_gpio_data *drvdata = serio->port_data; + flush_delayed_work(&drvdata->tx_work); disable_irq(drvdata->irq); } diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 47d4e0d30bf0..dd538e6b2748 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -932,7 +932,7 @@ static int dm_crypt_integrity_io_alloc(struct dm_crypt_io *io, struct bio *bio) if (IS_ERR(bip)) return PTR_ERR(bip); - tag_len = io->cc->on_disk_tag_size * bio_sectors(bio); + tag_len = io->cc->on_disk_tag_size * (bio_sectors(bio) >> io->cc->sector_shift); bip->bip_iter.bi_size = tag_len; bip->bip_iter.bi_sector = io->cc->start + io->sector; diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index ca8af21bf644..e83b63608262 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -257,6 +257,7 @@ struct pool { spinlock_t lock; struct bio_list deferred_flush_bios; + struct bio_list deferred_flush_completions; struct list_head prepared_mappings; struct list_head prepared_discards; struct list_head prepared_discards_pt2; @@ -956,6 +957,39 @@ static void process_prepared_mapping_fail(struct dm_thin_new_mapping *m) mempool_free(m, &m->tc->pool->mapping_pool); } +static void complete_overwrite_bio(struct thin_c *tc, struct bio *bio) +{ + struct pool *pool = tc->pool; + unsigned long flags; + + /* + * If the bio has the REQ_FUA flag set we must commit the metadata + * before signaling its completion. + */ + if (!bio_triggers_commit(tc, bio)) { + bio_endio(bio); + return; + } + + /* + * Complete bio with an error if earlier I/O caused changes to the + * metadata that can't be committed, e.g, due to I/O errors on the + * metadata device. + */ + if (dm_thin_aborted_changes(tc->td)) { + bio_io_error(bio); + return; + } + + /* + * Batch together any bios that trigger commits and then issue a + * single commit for them in process_deferred_bios(). + */ + spin_lock_irqsave(&pool->lock, flags); + bio_list_add(&pool->deferred_flush_completions, bio); + spin_unlock_irqrestore(&pool->lock, flags); +} + static void process_prepared_mapping(struct dm_thin_new_mapping *m) { struct thin_c *tc = m->tc; @@ -988,7 +1022,7 @@ static void process_prepared_mapping(struct dm_thin_new_mapping *m) */ if (bio) { inc_remap_and_issue_cell(tc, m->cell, m->data_block); - bio_endio(bio); + complete_overwrite_bio(tc, bio); } else { inc_all_io_entry(tc->pool, m->cell->holder); remap_and_issue(tc, m->cell->holder, m->data_block); @@ -2317,7 +2351,7 @@ static void process_deferred_bios(struct pool *pool) { unsigned long flags; struct bio *bio; - struct bio_list bios; + struct bio_list bios, bio_completions; struct thin_c *tc; tc = get_first_thin(pool); @@ -2328,26 +2362,36 @@ static void process_deferred_bios(struct pool *pool) } /* - * If there are any deferred flush bios, we must commit - * the metadata before issuing them. + * If there are any deferred flush bios, we must commit the metadata + * before issuing them or signaling their completion. */ bio_list_init(&bios); + bio_list_init(&bio_completions); + spin_lock_irqsave(&pool->lock, flags); bio_list_merge(&bios, &pool->deferred_flush_bios); bio_list_init(&pool->deferred_flush_bios); + + bio_list_merge(&bio_completions, &pool->deferred_flush_completions); + bio_list_init(&pool->deferred_flush_completions); spin_unlock_irqrestore(&pool->lock, flags); - if (bio_list_empty(&bios) && + if (bio_list_empty(&bios) && bio_list_empty(&bio_completions) && !(dm_pool_changed_this_transaction(pool->pmd) && need_commit_due_to_time(pool))) return; if (commit(pool)) { + bio_list_merge(&bios, &bio_completions); + while ((bio = bio_list_pop(&bios))) bio_io_error(bio); return; } pool->last_commit_jiffies = jiffies; + while ((bio = bio_list_pop(&bio_completions))) + bio_endio(bio); + while ((bio = bio_list_pop(&bios))) generic_make_request(bio); } @@ -2954,6 +2998,7 @@ static struct pool *pool_create(struct mapped_device *pool_md, INIT_DELAYED_WORK(&pool->no_space_timeout, do_no_space_timeout); spin_lock_init(&pool->lock); bio_list_init(&pool->deferred_flush_bios); + bio_list_init(&pool->deferred_flush_completions); INIT_LIST_HEAD(&pool->prepared_mappings); INIT_LIST_HEAD(&pool->prepared_discards); INIT_LIST_HEAD(&pool->prepared_discards_pt2); diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 1d54109071cc..fa47249fa3e4 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1863,6 +1863,20 @@ static void end_sync_read(struct bio *bio) reschedule_retry(r1_bio); } +static void abort_sync_write(struct mddev *mddev, struct r1bio *r1_bio) +{ + sector_t sync_blocks = 0; + sector_t s = r1_bio->sector; + long sectors_to_go = r1_bio->sectors; + + /* make sure these bits don't get cleared. */ + do { + md_bitmap_end_sync(mddev->bitmap, s, &sync_blocks, 1); + s += sync_blocks; + sectors_to_go -= sync_blocks; + } while (sectors_to_go > 0); +} + static void end_sync_write(struct bio *bio) { int uptodate = !bio->bi_status; @@ -1874,15 +1888,7 @@ static void end_sync_write(struct bio *bio) struct md_rdev *rdev = conf->mirrors[find_bio_disk(r1_bio, bio)].rdev; if (!uptodate) { - sector_t sync_blocks = 0; - sector_t s = r1_bio->sector; - long sectors_to_go = r1_bio->sectors; - /* make sure these bits doesn't get cleared. */ - do { - md_bitmap_end_sync(mddev->bitmap, s, &sync_blocks, 1); - s += sync_blocks; - sectors_to_go -= sync_blocks; - } while (sectors_to_go > 0); + abort_sync_write(mddev, r1_bio); set_bit(WriteErrorSeen, &rdev->flags); if (!test_and_set_bit(WantReplacement, &rdev->flags)) set_bit(MD_RECOVERY_NEEDED, & @@ -2172,8 +2178,10 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio) (i == r1_bio->read_disk || !test_bit(MD_RECOVERY_SYNC, &mddev->recovery)))) continue; - if (test_bit(Faulty, &conf->mirrors[i].rdev->flags)) + if (test_bit(Faulty, &conf->mirrors[i].rdev->flags)) { + abort_sync_write(mddev, r1_bio); continue; + } bio_set_op_attrs(wbio, REQ_OP_WRITE, 0); if (test_bit(FailFast, &conf->mirrors[i].rdev->flags)) diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index aef1185f383d..14f3fdb8c6bb 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -2112,7 +2112,7 @@ static void mmc_blk_mq_req_done(struct mmc_request *mrq) if (waiting) wake_up(&mq->wait); else - kblockd_schedule_work(&mq->complete_work); + queue_work(mq->card->complete_wq, &mq->complete_work); return; } @@ -2924,6 +2924,13 @@ static int mmc_blk_probe(struct mmc_card *card) mmc_fixup_device(card, mmc_blk_fixups); + card->complete_wq = alloc_workqueue("mmc_complete", + WQ_MEM_RECLAIM | WQ_HIGHPRI, 0); + if (unlikely(!card->complete_wq)) { + pr_err("Failed to create mmc completion workqueue"); + return -ENOMEM; + } + md = mmc_blk_alloc(card); if (IS_ERR(md)) return PTR_ERR(md); @@ -2987,6 +2994,7 @@ static void mmc_blk_remove(struct mmc_card *card) pm_runtime_put_noidle(&card->dev); mmc_blk_remove_req(md); dev_set_drvdata(&card->dev, NULL); + destroy_workqueue(card->complete_wq); } static int _mmc_blk_suspend(struct mmc_card *card) diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c index f19ec60bcbdc..2eba507790e4 100644 --- a/drivers/mmc/host/meson-gx-mmc.c +++ b/drivers/mmc/host/meson-gx-mmc.c @@ -1338,7 +1338,8 @@ static int meson_mmc_probe(struct platform_device *pdev) host->regs + SD_EMMC_IRQ_EN); ret = request_threaded_irq(host->irq, meson_mmc_irq, - meson_mmc_irq_thread, IRQF_SHARED, NULL, host); + meson_mmc_irq_thread, IRQF_SHARED, + dev_name(&pdev->dev), host); if (ret) goto err_init_clk; diff --git a/drivers/mmc/host/sunxi-mmc.c b/drivers/mmc/host/sunxi-mmc.c index 279e326e397e..70fadc976795 100644 --- a/drivers/mmc/host/sunxi-mmc.c +++ b/drivers/mmc/host/sunxi-mmc.c @@ -1399,13 +1399,37 @@ static int sunxi_mmc_probe(struct platform_device *pdev) mmc->caps |= MMC_CAP_MMC_HIGHSPEED | MMC_CAP_SD_HIGHSPEED | MMC_CAP_ERASE | MMC_CAP_SDIO_IRQ; - if (host->cfg->clk_delays || host->use_new_timings) + /* + * Some H5 devices do not have signal traces precise enough to + * use HS DDR mode for their eMMC chips. + * + * We still enable HS DDR modes for all the other controller + * variants that support them. + */ + if ((host->cfg->clk_delays || host->use_new_timings) && + !of_device_is_compatible(pdev->dev.of_node, + "allwinner,sun50i-h5-emmc")) mmc->caps |= MMC_CAP_1_8V_DDR | MMC_CAP_3_3V_DDR; ret = mmc_of_parse(mmc); if (ret) goto error_free_dma; + /* + * If we don't support delay chains in the SoC, we can't use any + * of the higher speed modes. Mask them out in case the device + * tree specifies the properties for them, which gets added to + * the caps by mmc_of_parse() above. + */ + if (!(host->cfg->clk_delays || host->use_new_timings)) { + mmc->caps &= ~(MMC_CAP_3_3V_DDR | MMC_CAP_1_8V_DDR | + MMC_CAP_1_2V_DDR | MMC_CAP_UHS); + mmc->caps2 &= ~MMC_CAP2_HS200; + } + + /* TODO: This driver doesn't support HS400 mode yet */ + mmc->caps2 &= ~MMC_CAP2_HS400; + ret = sunxi_mmc_init_host(host); if (ret) goto error_free_dma; diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index edb1c023a753..21bf8ac78380 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -197,9 +197,9 @@ config VXLAN config GENEVE tristate "Generic Network Virtualization Encapsulation" - depends on INET && NET_UDP_TUNNEL + depends on INET depends on IPV6 || !IPV6 - select NET_IP_TUNNEL + select NET_UDP_TUNNEL select GRO_CELLS ---help--- This allows one to create geneve virtual interfaces that provide diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 361fbde76654..17ec32b0a1cc 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -690,7 +690,7 @@ static int bcm_sf2_sw_suspend(struct dsa_switch *ds) * port, the other ones have already been disabled during * bcm_sf2_sw_setup */ - for (port = 0; port < DSA_MAX_PORTS; port++) { + for (port = 0; port < ds->num_ports; port++) { if (dsa_is_user_port(ds, port) || dsa_is_cpu_port(ds, port)) bcm_sf2_port_disable(ds, port, NULL); } diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 8dca2c949e73..12fd7ce3f1ff 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -261,6 +261,7 @@ static irqreturn_t mv88e6xxx_g1_irq_thread_work(struct mv88e6xxx_chip *chip) unsigned int sub_irq; unsigned int n; u16 reg; + u16 ctl1; int err; mutex_lock(&chip->reg_lock); @@ -270,13 +271,28 @@ static irqreturn_t mv88e6xxx_g1_irq_thread_work(struct mv88e6xxx_chip *chip) if (err) goto out; - for (n = 0; n < chip->g1_irq.nirqs; ++n) { - if (reg & (1 << n)) { - sub_irq = irq_find_mapping(chip->g1_irq.domain, n); - handle_nested_irq(sub_irq); - ++nhandled; + do { + for (n = 0; n < chip->g1_irq.nirqs; ++n) { + if (reg & (1 << n)) { + sub_irq = irq_find_mapping(chip->g1_irq.domain, + n); + handle_nested_irq(sub_irq); + ++nhandled; + } } - } + + mutex_lock(&chip->reg_lock); + err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_CTL1, &ctl1); + if (err) + goto unlock; + err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_STS, ®); +unlock: + mutex_unlock(&chip->reg_lock); + if (err) + goto out; + ctl1 &= GENMASK(chip->g1_irq.nirqs, 0); + } while (reg & ctl1); + out: return (nhandled > 0 ? IRQ_HANDLED : IRQ_NONE); } diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index a70bb1bb90e7..a6eacf2099c3 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -2663,11 +2663,6 @@ static int ena_restore_device(struct ena_adapter *adapter) goto err_device_destroy; } - clear_bit(ENA_FLAG_ONGOING_RESET, &adapter->flags); - /* Make sure we don't have a race with AENQ Links state handler */ - if (test_bit(ENA_FLAG_LINK_UP, &adapter->flags)) - netif_carrier_on(adapter->netdev); - rc = ena_enable_msix_and_set_admin_interrupts(adapter, adapter->num_queues); if (rc) { @@ -2684,6 +2679,11 @@ static int ena_restore_device(struct ena_adapter *adapter) } set_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags); + + clear_bit(ENA_FLAG_ONGOING_RESET, &adapter->flags); + if (test_bit(ENA_FLAG_LINK_UP, &adapter->flags)) + netif_carrier_on(adapter->netdev); + mod_timer(&adapter->timer_service, round_jiffies(jiffies + HZ)); dev_err(&pdev->dev, "Device reset completed successfully, Driver info: %s\n", diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h index dc8b6173d8d8..63870072cbbd 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.h +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h @@ -45,7 +45,7 @@ #define DRV_MODULE_VER_MAJOR 2 #define DRV_MODULE_VER_MINOR 0 -#define DRV_MODULE_VER_SUBMINOR 2 +#define DRV_MODULE_VER_SUBMINOR 3 #define DRV_MODULE_NAME "ena" #ifndef DRV_MODULE_VERSION diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 2370dc204202..697c2427f2b7 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -2098,6 +2098,7 @@ static int fec_enet_get_regs_len(struct net_device *ndev) #if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \ defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) || \ defined(CONFIG_ARM64) || defined(CONFIG_COMPILE_TEST) +static __u32 fec_enet_register_version = 2; static u32 fec_enet_register_offset[] = { FEC_IEVENT, FEC_IMASK, FEC_R_DES_ACTIVE_0, FEC_X_DES_ACTIVE_0, FEC_ECNTRL, FEC_MII_DATA, FEC_MII_SPEED, FEC_MIB_CTRLSTAT, FEC_R_CNTRL, @@ -2128,6 +2129,7 @@ static u32 fec_enet_register_offset[] = { IEEE_R_FDXFC, IEEE_R_OCTETS_OK }; #else +static __u32 fec_enet_register_version = 1; static u32 fec_enet_register_offset[] = { FEC_ECNTRL, FEC_IEVENT, FEC_IMASK, FEC_IVEC, FEC_R_DES_ACTIVE_0, FEC_R_DES_ACTIVE_1, FEC_R_DES_ACTIVE_2, FEC_X_DES_ACTIVE_0, @@ -2149,6 +2151,8 @@ static void fec_enet_get_regs(struct net_device *ndev, u32 *buf = (u32 *)regbuf; u32 i, off; + regs->version = fec_enet_register_version; + memset(buf, 0, regs->len); for (i = 0; i < ARRAY_SIZE(fec_enet_register_offset); i++) { diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c index 3b9e74be5fbd..b8155f5e71b4 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c @@ -3081,6 +3081,7 @@ int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset) dsaf_dev = dev_get_drvdata(&pdev->dev); if (!dsaf_dev) { dev_err(&pdev->dev, "dsaf_dev is NULL\n"); + put_device(&pdev->dev); return -ENODEV; } @@ -3088,6 +3089,7 @@ int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset) if (AE_IS_VER1(dsaf_dev->dsaf_ver)) { dev_err(dsaf_dev->dev, "%s v1 chip doesn't support RoCE!\n", dsaf_dev->ae_dev.name); + put_device(&pdev->dev); return -ENODEV; } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 9a0881cb7f51..6c01314e87b0 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -617,6 +617,8 @@ static int get_fixed_ipv6_csum(__wsum hw_checksum, struct sk_buff *skb, } #endif +#define short_frame(size) ((size) <= ETH_ZLEN + ETH_FCS_LEN) + /* We reach this function only after checking that any of * the (IPv4 | IPv6) bits are set in cqe->status. */ @@ -624,9 +626,20 @@ static int check_csum(struct mlx4_cqe *cqe, struct sk_buff *skb, void *va, netdev_features_t dev_features) { __wsum hw_checksum = 0; + void *hdr; + + /* CQE csum doesn't cover padding octets in short ethernet + * frames. And the pad field is appended prior to calculating + * and appending the FCS field. + * + * Detecting these padded frames requires to verify and parse + * IP headers, so we simply force all those small frames to skip + * checksum complete. + */ + if (short_frame(skb->len)) + return -EINVAL; - void *hdr = (u8 *)va + sizeof(struct ethhdr); - + hdr = (u8 *)va + sizeof(struct ethhdr); hw_checksum = csum_unfold((__force __sum16)cqe->checksum); if (cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_CVLAN_PRESENT_MASK) && @@ -819,6 +832,11 @@ xdp_drop_no_cnt: skb_record_rx_queue(skb, cq_ring); if (likely(dev->features & NETIF_F_RXCSUM)) { + /* TODO: For IP non TCP/UDP packets when csum complete is + * not an option (not supported or any other reason) we can + * actually check cqe IPOK status bit and report + * CHECKSUM_UNNECESSARY rather than CHECKSUM_NONE + */ if ((cqe->status & cpu_to_be16(MLX4_CQE_STATUS_TCP | MLX4_CQE_STATUS_UDP)) && (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPOK)) && diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 3e0fa8a8077b..e267ff93e8a8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -1583,6 +1583,24 @@ no_trig: spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags); } +void mlx5_cmd_flush(struct mlx5_core_dev *dev) +{ + struct mlx5_cmd *cmd = &dev->cmd; + int i; + + for (i = 0; i < cmd->max_reg_cmds; i++) + while (down_trylock(&cmd->sem)) + mlx5_cmd_trigger_completions(dev); + + while (down_trylock(&cmd->pages_sem)) + mlx5_cmd_trigger_completions(dev); + + /* Unlock cmdif */ + up(&cmd->pages_sem); + for (i = 0; i < cmd->max_reg_cmds; i++) + up(&cmd->sem); +} + static int status_to_err(u8 status) { return status ? -1 : 0; /* TBD more meaningful codes */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 8fa8fdd30b85..448a92561567 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -657,6 +657,7 @@ struct mlx5e_channel_stats { enum { MLX5E_STATE_OPENED, MLX5E_STATE_DESTROYING, + MLX5E_STATE_XDP_TX_ENABLED, }; struct mlx5e_rqt { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index 3740177eed09..03b2a9f9c589 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -365,7 +365,8 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, int sq_num; int i; - if (unlikely(!test_bit(MLX5E_STATE_OPENED, &priv->state))) + /* this flag is sufficient, no need to test internal sq state */ + if (unlikely(!mlx5e_xdp_tx_is_enabled(priv))) return -ENETDOWN; if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) @@ -378,9 +379,6 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, sq = &priv->channels.c[sq_num]->xdpsq; - if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))) - return -ENETDOWN; - for (i = 0; i < n; i++) { struct xdp_frame *xdpf = frames[i]; struct mlx5e_xdp_info xdpi; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h index 3a67cb3cd179..ee27a7c8cd87 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h @@ -50,6 +50,23 @@ void mlx5e_xdp_rx_poll_complete(struct mlx5e_rq *rq); int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags); +static inline void mlx5e_xdp_tx_enable(struct mlx5e_priv *priv) +{ + set_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state); +} + +static inline void mlx5e_xdp_tx_disable(struct mlx5e_priv *priv) +{ + clear_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state); + /* let other device's napi(s) see our new state */ + synchronize_rcu(); +} + +static inline bool mlx5e_xdp_tx_is_enabled(struct mlx5e_priv *priv) +{ + return test_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state); +} + static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq) { if (sq->doorbell_cseg) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 3bbccead2f63..47233b9a4f81 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -354,9 +354,6 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv, new_channels.params = priv->channels.params; new_channels.params.num_channels = count; - if (!netif_is_rxfh_configured(priv->netdev)) - mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt, - MLX5E_INDIR_RQT_SIZE, count); if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { priv->channels.params = new_channels.params; @@ -372,6 +369,10 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv, if (arfs_enabled) mlx5e_arfs_disable(priv); + if (!netif_is_rxfh_configured(priv->netdev)) + mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt, + MLX5E_INDIR_RQT_SIZE, count); + /* Switch to new channels, set new parameters and close old ones */ mlx5e_switch_priv_channels(priv, &new_channels, NULL); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 01819e5c9975..93e50ccd44c3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2938,6 +2938,7 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv) mlx5e_build_tx2sq_maps(priv); mlx5e_activate_channels(&priv->channels); + mlx5e_xdp_tx_enable(priv); netif_tx_start_all_queues(priv->netdev); if (mlx5e_is_vport_rep(priv)) @@ -2959,6 +2960,7 @@ void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv) */ netif_tx_stop_all_queues(priv->netdev); netif_tx_disable(priv->netdev); + mlx5e_xdp_tx_disable(priv); mlx5e_deactivate_channels(&priv->channels); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c index fbc42b7252a9..503035469d2d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/events.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c @@ -211,11 +211,10 @@ static int port_module(struct notifier_block *nb, unsigned long type, void *data enum port_module_event_status_type module_status; enum port_module_event_error_type error_type; struct mlx5_eqe_port_module *module_event_eqe; - const char *status_str, *error_str; + const char *status_str; u8 module_num; module_event_eqe = &eqe->data.port_module; - module_num = module_event_eqe->module; module_status = module_event_eqe->module_status & PORT_MODULE_EVENT_MODULE_STATUS_MASK; error_type = module_event_eqe->error_type & @@ -223,25 +222,27 @@ static int port_module(struct notifier_block *nb, unsigned long type, void *data if (module_status < MLX5_MODULE_STATUS_NUM) events->pme_stats.status_counters[module_status]++; - status_str = mlx5_pme_status_to_string(module_status); - if (module_status == MLX5_MODULE_STATUS_ERROR) { + if (module_status == MLX5_MODULE_STATUS_ERROR) if (error_type < MLX5_MODULE_EVENT_ERROR_NUM) events->pme_stats.error_counters[error_type]++; - error_str = mlx5_pme_error_to_string(error_type); - } if (!printk_ratelimit()) return NOTIFY_OK; - if (module_status == MLX5_MODULE_STATUS_ERROR) + module_num = module_event_eqe->module; + status_str = mlx5_pme_status_to_string(module_status); + if (module_status == MLX5_MODULE_STATUS_ERROR) { + const char *error_str = mlx5_pme_error_to_string(error_type); + mlx5_core_err(events->dev, "Port module event[error]: module %u, %s, %s\n", module_num, status_str, error_str); - else + } else { mlx5_core_info(events->dev, "Port module event: module %u, %s\n", module_num, status_str); + } return NOTIFY_OK; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 196c07383082..cb9fa3430c53 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -103,7 +103,7 @@ void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force) mlx5_core_err(dev, "start\n"); if (pci_channel_offline(dev->pdev) || in_fatal(dev) || force) { dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR; - mlx5_cmd_trigger_completions(dev); + mlx5_cmd_flush(dev); } mlx5_notifier_call_chain(dev->priv.events, MLX5_DEV_EVENT_SYS_ERROR, (void *)1); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 5300b0b6d836..4fdac020b795 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -126,6 +126,7 @@ u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev, struct ptp_system_timestamp *sts); void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev); +void mlx5_cmd_flush(struct mlx5_core_dev *dev); int mlx5_cq_debugfs_init(struct mlx5_core_dev *dev); void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index abb94c543aa2..6e36b88ca7c9 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -1286,11 +1286,13 @@ static u16 rtl_get_events(struct rtl8169_private *tp) static void rtl_ack_events(struct rtl8169_private *tp, u16 bits) { RTL_W16(tp, IntrStatus, bits); + mmiowb(); } static void rtl_irq_disable(struct rtl8169_private *tp) { RTL_W16(tp, IntrMask, 0); + mmiowb(); } #define RTL_EVENT_NAPI_RX (RxOK | RxErr) @@ -6072,7 +6074,6 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, struct device *d = tp_to_dev(tp); dma_addr_t mapping; u32 opts[2], len; - bool stop_queue; int frags; if (unlikely(!rtl_tx_slots_avail(tp, skb_shinfo(skb)->nr_frags))) { @@ -6114,6 +6115,8 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, txd->opts2 = cpu_to_le32(opts[1]); + netdev_sent_queue(dev, skb->len); + skb_tx_timestamp(skb); /* Force memory writes to complete before releasing descriptor */ @@ -6126,14 +6129,16 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, tp->cur_tx += frags + 1; - stop_queue = !rtl_tx_slots_avail(tp, MAX_SKB_FRAGS); - if (unlikely(stop_queue)) - netif_stop_queue(dev); + RTL_W8(tp, TxPoll, NPQ); - if (__netdev_sent_queue(dev, skb->len, skb->xmit_more)) - RTL_W8(tp, TxPoll, NPQ); + mmiowb(); - if (unlikely(stop_queue)) { + if (!rtl_tx_slots_avail(tp, MAX_SKB_FRAGS)) { + /* Avoid wrongly optimistic queue wake-up: rtl_tx thread must + * not miss a ring update when it notices a stopped queue. + */ + smp_wmb(); + netif_stop_queue(dev); /* Sync with rtl_tx: * - publish queue status and cur_tx ring index (write barrier) * - refresh dirty_tx ring index (read barrier). @@ -6483,7 +6488,9 @@ static int rtl8169_poll(struct napi_struct *napi, int budget) if (work_done < budget) { napi_complete_done(napi, work_done); + rtl_irq_enable(tp); + mmiowb(); } return work_done; diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 2f2bda68d861..c08034154a9a 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -6115,7 +6115,7 @@ static int efx_ef10_mtd_probe_partition(struct efx_nic *efx, static int efx_ef10_mtd_probe(struct efx_nic *efx) { MCDI_DECLARE_BUF(outbuf, MC_CMD_NVRAM_PARTITIONS_OUT_LENMAX); - DECLARE_BITMAP(found, EF10_NVRAM_PARTITION_COUNT); + DECLARE_BITMAP(found, EF10_NVRAM_PARTITION_COUNT) = { 0 }; struct efx_mcdi_mtd_partition *parts; size_t outlen, n_parts_total, i, n_parts; unsigned int type; diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 189cd2048c3a..c5675df5fc6f 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -553,7 +553,7 @@ int phy_start_aneg(struct phy_device *phydev) if (err < 0) goto out_unlock; - if (__phy_is_started(phydev)) { + if (phy_is_started(phydev)) { if (phydev->autoneg == AUTONEG_ENABLE) { err = phy_check_link_status(phydev); } else { @@ -709,7 +709,7 @@ void phy_stop_machine(struct phy_device *phydev) cancel_delayed_work_sync(&phydev->state_queue); mutex_lock(&phydev->lock); - if (__phy_is_started(phydev)) + if (phy_is_started(phydev)) phydev->state = PHY_UP; mutex_unlock(&phydev->lock); } @@ -762,9 +762,6 @@ static irqreturn_t phy_interrupt(int irq, void *phy_dat) { struct phy_device *phydev = phy_dat; - if (!phy_is_started(phydev)) - return IRQ_NONE; /* It can't be ours. */ - if (phydev->drv->did_interrupt && !phydev->drv->did_interrupt(phydev)) return IRQ_NONE; @@ -842,15 +839,14 @@ EXPORT_SYMBOL(phy_stop_interrupts); */ void phy_stop(struct phy_device *phydev) { - mutex_lock(&phydev->lock); - - if (!__phy_is_started(phydev)) { + if (!phy_is_started(phydev)) { WARN(1, "called from state %s\n", phy_state_to_str(phydev->state)); - mutex_unlock(&phydev->lock); return; } + mutex_lock(&phydev->lock); + if (phy_interrupt_is_valid(phydev)) phy_disable_interrupts(phydev); @@ -989,8 +985,10 @@ void phy_state_machine(struct work_struct *work) * state machine would be pointless and possibly error prone when * called from phy_disconnect() synchronously. */ + mutex_lock(&phydev->lock); if (phy_polling_mode(phydev) && phy_is_started(phydev)) phy_queue_state_machine(phydev, PHY_STATE_TIME); + mutex_unlock(&phydev->lock); } /** diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index e7becc7379d7..938803237d7f 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -474,6 +474,17 @@ static void phylink_run_resolve(struct phylink *pl) queue_work(system_power_efficient_wq, &pl->resolve); } +static void phylink_run_resolve_and_disable(struct phylink *pl, int bit) +{ + unsigned long state = pl->phylink_disable_state; + + set_bit(bit, &pl->phylink_disable_state); + if (state == 0) { + queue_work(system_power_efficient_wq, &pl->resolve); + flush_work(&pl->resolve); + } +} + static void phylink_fixed_poll(struct timer_list *t) { struct phylink *pl = container_of(t, struct phylink, link_poll); @@ -924,9 +935,7 @@ void phylink_stop(struct phylink *pl) if (pl->link_an_mode == MLO_AN_FIXED && !IS_ERR(pl->link_gpio)) del_timer_sync(&pl->link_poll); - set_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state); - queue_work(system_power_efficient_wq, &pl->resolve); - flush_work(&pl->resolve); + phylink_run_resolve_and_disable(pl, PHYLINK_DISABLE_STOPPED); } EXPORT_SYMBOL_GPL(phylink_stop); @@ -1632,9 +1641,7 @@ static void phylink_sfp_link_down(void *upstream) ASSERT_RTNL(); - set_bit(PHYLINK_DISABLE_LINK, &pl->phylink_disable_state); - queue_work(system_power_efficient_wq, &pl->resolve); - flush_work(&pl->resolve); + phylink_run_resolve_and_disable(pl, PHYLINK_DISABLE_LINK); } static void phylink_sfp_link_up(void *upstream) diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c index ad9db652874d..fef701bfad62 100644 --- a/drivers/net/phy/sfp-bus.c +++ b/drivers/net/phy/sfp-bus.c @@ -347,6 +347,7 @@ static int sfp_register_bus(struct sfp_bus *bus) return ret; } } + bus->socket_ops->attach(bus->sfp); if (bus->started) bus->socket_ops->start(bus->sfp); bus->netdev->sfp_bus = bus; @@ -362,6 +363,7 @@ static void sfp_unregister_bus(struct sfp_bus *bus) if (bus->registered) { if (bus->started) bus->socket_ops->stop(bus->sfp); + bus->socket_ops->detach(bus->sfp); if (bus->phydev && ops && ops->disconnect_phy) ops->disconnect_phy(bus->upstream); } diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index fd8bb998ae52..68c8fbf099f8 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -184,6 +184,7 @@ struct sfp { struct gpio_desc *gpio[GPIO_MAX]; + bool attached; unsigned int state; struct delayed_work poll; struct delayed_work timeout; @@ -1475,7 +1476,7 @@ static void sfp_sm_event(struct sfp *sfp, unsigned int event) */ switch (sfp->sm_mod_state) { default: - if (event == SFP_E_INSERT) { + if (event == SFP_E_INSERT && sfp->attached) { sfp_module_tx_disable(sfp); sfp_sm_ins_next(sfp, SFP_MOD_PROBE, T_PROBE_INIT); } @@ -1607,6 +1608,19 @@ static void sfp_sm_event(struct sfp *sfp, unsigned int event) mutex_unlock(&sfp->sm_mutex); } +static void sfp_attach(struct sfp *sfp) +{ + sfp->attached = true; + if (sfp->state & SFP_F_PRESENT) + sfp_sm_event(sfp, SFP_E_INSERT); +} + +static void sfp_detach(struct sfp *sfp) +{ + sfp->attached = false; + sfp_sm_event(sfp, SFP_E_REMOVE); +} + static void sfp_start(struct sfp *sfp) { sfp_sm_event(sfp, SFP_E_DEV_UP); @@ -1667,6 +1681,8 @@ static int sfp_module_eeprom(struct sfp *sfp, struct ethtool_eeprom *ee, } static const struct sfp_socket_ops sfp_module_ops = { + .attach = sfp_attach, + .detach = sfp_detach, .start = sfp_start, .stop = sfp_stop, .module_info = sfp_module_info, @@ -1834,10 +1850,6 @@ static int sfp_probe(struct platform_device *pdev) dev_info(sfp->dev, "Host maximum power %u.%uW\n", sfp->max_power_mW / 1000, (sfp->max_power_mW / 100) % 10); - sfp->sfp_bus = sfp_register_socket(sfp->dev, sfp, &sfp_module_ops); - if (!sfp->sfp_bus) - return -ENOMEM; - /* Get the initial state, and always signal TX disable, * since the network interface will not be up. */ @@ -1848,10 +1860,6 @@ static int sfp_probe(struct platform_device *pdev) sfp->state |= SFP_F_RATE_SELECT; sfp_set_state(sfp, sfp->state); sfp_module_tx_disable(sfp); - rtnl_lock(); - if (sfp->state & SFP_F_PRESENT) - sfp_sm_event(sfp, SFP_E_INSERT); - rtnl_unlock(); for (i = 0; i < GPIO_MAX; i++) { if (gpio_flags[i] != GPIOD_IN || !sfp->gpio[i]) @@ -1884,6 +1892,10 @@ static int sfp_probe(struct platform_device *pdev) dev_warn(sfp->dev, "No tx_disable pin: SFP modules will always be emitting.\n"); + sfp->sfp_bus = sfp_register_socket(sfp->dev, sfp, &sfp_module_ops); + if (!sfp->sfp_bus) + return -ENOMEM; + return 0; } diff --git a/drivers/net/phy/sfp.h b/drivers/net/phy/sfp.h index 31b0acf337e2..64f54b0bbd8c 100644 --- a/drivers/net/phy/sfp.h +++ b/drivers/net/phy/sfp.h @@ -7,6 +7,8 @@ struct sfp; struct sfp_socket_ops { + void (*attach)(struct sfp *sfp); + void (*detach)(struct sfp *sfp); void (*start)(struct sfp *sfp); void (*stop)(struct sfp *sfp); int (*module_info)(struct sfp *sfp, struct ethtool_modinfo *modinfo); diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index afd9d25d1992..958f1cf67282 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -256,17 +256,6 @@ static void __team_option_inst_mark_removed_port(struct team *team, } } -static bool __team_option_inst_tmp_find(const struct list_head *opts, - const struct team_option_inst *needle) -{ - struct team_option_inst *opt_inst; - - list_for_each_entry(opt_inst, opts, tmp_list) - if (opt_inst == needle) - return true; - return false; -} - static int __team_options_register(struct team *team, const struct team_option *option, size_t option_count) @@ -2460,7 +2449,6 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info) int err = 0; int i; struct nlattr *nl_option; - LIST_HEAD(opt_inst_list); rtnl_lock(); @@ -2480,6 +2468,7 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info) struct nlattr *opt_attrs[TEAM_ATTR_OPTION_MAX + 1]; struct nlattr *attr; struct nlattr *attr_data; + LIST_HEAD(opt_inst_list); enum team_option_type opt_type; int opt_port_ifindex = 0; /* != 0 for per-port options */ u32 opt_array_index = 0; @@ -2584,23 +2573,17 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info) if (err) goto team_put; opt_inst->changed = true; - - /* dumb/evil user-space can send us duplicate opt, - * keep only the last one - */ - if (__team_option_inst_tmp_find(&opt_inst_list, - opt_inst)) - continue; - list_add(&opt_inst->tmp_list, &opt_inst_list); } if (!opt_found) { err = -ENOENT; goto team_put; } - } - err = team_nl_send_event_options_get(team, &opt_inst_list); + err = team_nl_send_event_options_get(team, &opt_inst_list); + if (err) + break; + } team_put: team_nl_team_put(team); diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 5209ee9aac47..2aae11feff0c 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2219,7 +2219,7 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, struct pcpu_sw_netstats *tx_stats, *rx_stats; union vxlan_addr loopback; union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip; - struct net_device *dev = skb->dev; + struct net_device *dev; int len = skb->len; tx_stats = this_cpu_ptr(src_vxlan->dev->tstats); @@ -2239,9 +2239,15 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, #endif } + rcu_read_lock(); + dev = skb->dev; + if (unlikely(!(dev->flags & IFF_UP))) { + kfree_skb(skb); + goto drop; + } + if (dst_vxlan->cfg.flags & VXLAN_F_LEARN) - vxlan_snoop(skb->dev, &loopback, eth_hdr(skb)->h_source, 0, - vni); + vxlan_snoop(dev, &loopback, eth_hdr(skb)->h_source, 0, vni); u64_stats_update_begin(&tx_stats->syncp); tx_stats->tx_packets++; @@ -2254,8 +2260,10 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, rx_stats->rx_bytes += len; u64_stats_update_end(&rx_stats->syncp); } else { +drop: dev->stats.rx_dropped++; } + rcu_read_unlock(); } static int encap_bypass_if_local(struct sk_buff *skb, struct net_device *dev, diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 022ea1ee63f8..7fee665ec45e 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2560,15 +2560,15 @@ static void nvme_reset_work(struct work_struct *work) mutex_lock(&dev->shutdown_lock); result = nvme_pci_enable(dev); if (result) - goto out; + goto out_unlock; result = nvme_pci_configure_admin_queue(dev); if (result) - goto out; + goto out_unlock; result = nvme_alloc_admin_tags(dev); if (result) - goto out; + goto out_unlock; /* * Limit the max command size to prevent iod->sg allocations going @@ -2651,6 +2651,8 @@ static void nvme_reset_work(struct work_struct *work) nvme_start_ctrl(&dev->ctrl); return; + out_unlock: + mutex_unlock(&dev->shutdown_lock); out: nvme_remove_dead_ctrl(dev, result); } diff --git a/drivers/powercap/intel_rapl.c b/drivers/powercap/intel_rapl.c index 6cdb2c14eee4..4347f15165f8 100644 --- a/drivers/powercap/intel_rapl.c +++ b/drivers/powercap/intel_rapl.c @@ -1156,6 +1156,7 @@ static const struct x86_cpu_id rapl_ids[] __initconst = { INTEL_CPU_FAM6(KABYLAKE_MOBILE, rapl_defaults_core), INTEL_CPU_FAM6(KABYLAKE_DESKTOP, rapl_defaults_core), INTEL_CPU_FAM6(CANNONLAKE_MOBILE, rapl_defaults_core), + INTEL_CPU_FAM6(ICELAKE_MOBILE, rapl_defaults_core), INTEL_CPU_FAM6(ATOM_SILVERMONT, rapl_defaults_byt), INTEL_CPU_FAM6(ATOM_AIRMONT, rapl_defaults_cht), @@ -1164,6 +1165,7 @@ static const struct x86_cpu_id rapl_ids[] __initconst = { INTEL_CPU_FAM6(ATOM_GOLDMONT, rapl_defaults_core), INTEL_CPU_FAM6(ATOM_GOLDMONT_PLUS, rapl_defaults_core), INTEL_CPU_FAM6(ATOM_GOLDMONT_X, rapl_defaults_core), + INTEL_CPU_FAM6(ATOM_TREMONT_X, rapl_defaults_core), INTEL_CPU_FAM6(XEON_PHI_KNL, rapl_defaults_hsw_server), INTEL_CPU_FAM6(XEON_PHI_KNM, rapl_defaults_hsw_server), diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index 4e7b55a14b1a..6e294b4d3635 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -4469,6 +4469,14 @@ static int dasd_symm_io(struct dasd_device *device, void __user *argp) usrparm.psf_data &= 0x7fffffffULL; usrparm.rssd_result &= 0x7fffffffULL; } + /* at least 2 bytes are accessed and should be allocated */ + if (usrparm.psf_data_len < 2) { + DBF_DEV_EVENT(DBF_WARNING, device, + "Symmetrix ioctl invalid data length %d", + usrparm.psf_data_len); + rc = -EINVAL; + goto out; + } /* alloc I/O data area */ psf_data = kzalloc(usrparm.psf_data_len, GFP_KERNEL | GFP_DMA); rssd_result = kzalloc(usrparm.rssd_result_len, GFP_KERNEL | GFP_DMA); diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 48ea0004a56d..5a699746c357 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -248,7 +248,8 @@ static inline int ap_test_config(unsigned int *field, unsigned int nr) static inline int ap_test_config_card_id(unsigned int id) { if (!ap_configuration) /* QCI not supported */ - return 1; + /* only ids 0...3F may be probed */ + return id < 0x40 ? 1 : 0; return ap_test_config(ap_configuration->apm, id); } diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index aeeb0144bd55..8d1acc802a67 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -1785,13 +1785,13 @@ qla2x00_async_tm_cmd(fc_port_t *fcport, uint32_t flags, uint32_t lun, /* Issue Marker IOCB */ qla2x00_marker(vha, vha->hw->req_q_map[0], - vha->hw->rsp_q_map[0], sp->fcport->loop_id, lun, + vha->hw->rsp_q_map[0], fcport->loop_id, lun, flags == TCF_LUN_RESET ? MK_SYNC_ID_LUN : MK_SYNC_ID); } done_free_sp: sp->free(sp); - sp->fcport->flags &= ~FCF_ASYNC_SENT; + fcport->flags &= ~FCF_ASYNC_SENT; done: return rval; } diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index b2da8a00ec33..5464d467e23e 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -2951,9 +2951,6 @@ static void sd_read_block_characteristics(struct scsi_disk *sdkp) if (rot == 1) { blk_queue_flag_set(QUEUE_FLAG_NONROT, q); blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, q); - } else { - blk_queue_flag_clear(QUEUE_FLAG_NONROT, q); - blk_queue_flag_set(QUEUE_FLAG_ADD_RANDOM, q); } if (sdkp->device->type == TYPE_ZBC) { @@ -3090,6 +3087,15 @@ static int sd_revalidate_disk(struct gendisk *disk) if (sdkp->media_present) { sd_read_capacity(sdkp, buffer); + /* + * set the default to rotational. All non-rotational devices + * support the block characteristics VPD page, which will + * cause this to be updated correctly and any device which + * doesn't support it should be treated as rotational. + */ + blk_queue_flag_clear(QUEUE_FLAG_NONROT, q); + blk_queue_flag_set(QUEUE_FLAG_ADD_RANDOM, q); + if (scsi_device_supports_vpd(sdp)) { sd_read_block_provisioning(sdkp); sd_read_block_limits(sdkp); diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig index 30323426902e..58bb7d72dc2b 100644 --- a/drivers/thermal/Kconfig +++ b/drivers/thermal/Kconfig @@ -152,6 +152,7 @@ config CPU_THERMAL bool "generic cpu cooling support" depends on CPU_FREQ depends on THERMAL_OF + depends on THERMAL=y help This implements the generic cpu cooling mechanism through frequency reduction. An ACPI version of this already exists diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c index dfd23245f778..6fff16113628 100644 --- a/drivers/thermal/cpu_cooling.c +++ b/drivers/thermal/cpu_cooling.c @@ -774,7 +774,7 @@ of_cpufreq_cooling_register(struct cpufreq_policy *policy) cdev = __cpufreq_cooling_register(np, policy, capacitance); if (IS_ERR(cdev)) { - pr_err("cpu_cooling: cpu%d is not running as cooling device: %ld\n", + pr_err("cpu_cooling: cpu%d failed to register as cooling device: %ld\n", policy->cpu, PTR_ERR(cdev)); cdev = NULL; } diff --git a/drivers/thermal/of-thermal.c b/drivers/thermal/of-thermal.c index 4bfdb4a1e47d..2df059cc07e2 100644 --- a/drivers/thermal/of-thermal.c +++ b/drivers/thermal/of-thermal.c @@ -867,14 +867,14 @@ __init *thermal_of_build_thermal_zone(struct device_node *np) ret = of_property_read_u32(np, "polling-delay-passive", &prop); if (ret < 0) { - pr_err("missing polling-delay-passive property\n"); + pr_err("%pOFn: missing polling-delay-passive property\n", np); goto free_tz; } tz->passive_delay = prop; ret = of_property_read_u32(np, "polling-delay", &prop); if (ret < 0) { - pr_err("missing polling-delay property\n"); + pr_err("%pOFn: missing polling-delay property\n", np); goto free_tz; } tz->polling_delay = prop; diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c index d0078cbb718b..7cde3f46ad26 100644 --- a/fs/binfmt_script.c +++ b/fs/binfmt_script.c @@ -42,14 +42,10 @@ static int load_script(struct linux_binprm *bprm) fput(bprm->file); bprm->file = NULL; - for (cp = bprm->buf+2;; cp++) { - if (cp >= bprm->buf + BINPRM_BUF_SIZE) - return -ENOEXEC; - if (!*cp || (*cp == '\n')) - break; - } + bprm->buf[BINPRM_BUF_SIZE - 1] = '\0'; + if ((cp = strchr(bprm->buf, '\n')) == NULL) + cp = bprm->buf+BINPRM_BUF_SIZE-1; *cp = '\0'; - while (cp > bprm->buf) { cp--; if ((*cp == ' ') || (*cp == '\t')) diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 712f00995390..5508baa11bb6 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -116,16 +116,8 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) goto out; } - ret = file_write_and_wait_range(file, start, end); - if (ret) - return ret; - if (!journal) { - struct writeback_control wbc = { - .sync_mode = WB_SYNC_ALL - }; - - ret = ext4_write_inode(inode, &wbc); + ret = __generic_file_fsync(file, start, end, datasync); if (!ret) ret = ext4_sync_parent(inode); if (test_opt(inode->i_sb, BARRIER)) @@ -133,6 +125,9 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) goto out; } + ret = file_write_and_wait_range(file, start, end); + if (ret) + return ret; /* * data=writeback,ordered: * The caller's filemap_fdatawrite()/wait will sync the data. diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index f15b4c57c4bd..78510ab91835 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -28,7 +28,6 @@ #include "util.h" #include "trans.h" #include "dir.h" -#include "lops.h" struct workqueue_struct *gfs2_freeze_wq; diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 5bfaf381921a..b8830fda51e8 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -733,7 +733,7 @@ void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd, lh->lh_crc = cpu_to_be32(crc); gfs2_log_write(sdp, page, sb->s_blocksize, 0, addr); - gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE | op_flags); + gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE, op_flags); log_flush_wait(sdp); } @@ -810,7 +810,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags) gfs2_ordered_write(sdp); lops_before_commit(sdp, tr); - gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE); + gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE, 0); if (sdp->sd_log_head != sdp->sd_log_flush_head) { log_flush_wait(sdp); diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 94dcab655bc0..2295042bc625 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -17,9 +17,7 @@ #include <linux/bio.h> #include <linux/fs.h> #include <linux/list_sort.h> -#include <linux/blkdev.h> -#include "bmap.h" #include "dir.h" #include "gfs2.h" #include "incore.h" @@ -195,6 +193,7 @@ static void gfs2_end_log_write_bh(struct gfs2_sbd *sdp, struct bio_vec *bvec, /** * gfs2_end_log_write - end of i/o to the log * @bio: The bio + * @error: Status of i/o request * * Each bio_vec contains either data from the pagecache or data * relating to the log itself. Here we iterate over the bio_vec @@ -231,19 +230,20 @@ static void gfs2_end_log_write(struct bio *bio) /** * gfs2_log_submit_bio - Submit any pending log bio * @biop: Address of the bio pointer - * @opf: REQ_OP | op_flags + * @op: REQ_OP + * @op_flags: req_flag_bits * * Submit any pending part-built or full bio to the block device. If * there is no pending bio, then this is a no-op. */ -void gfs2_log_submit_bio(struct bio **biop, int opf) +void gfs2_log_submit_bio(struct bio **biop, int op, int op_flags) { struct bio *bio = *biop; if (bio) { struct gfs2_sbd *sdp = bio->bi_private; atomic_inc(&sdp->sd_log_in_flight); - bio->bi_opf = opf; + bio_set_op_attrs(bio, op, op_flags); submit_bio(bio); *biop = NULL; } @@ -304,7 +304,7 @@ static struct bio *gfs2_log_get_bio(struct gfs2_sbd *sdp, u64 blkno, nblk >>= sdp->sd_fsb2bb_shift; if (blkno == nblk && !flush) return bio; - gfs2_log_submit_bio(biop, op); + gfs2_log_submit_bio(biop, op, 0); } *biop = gfs2_log_alloc_bio(sdp, blkno, end_io); @@ -375,184 +375,6 @@ void gfs2_log_write_page(struct gfs2_sbd *sdp, struct page *page) gfs2_log_bmap(sdp)); } -/** - * gfs2_end_log_read - end I/O callback for reads from the log - * @bio: The bio - * - * Simply unlock the pages in the bio. The main thread will wait on them and - * process them in order as necessary. - */ - -static void gfs2_end_log_read(struct bio *bio) -{ - struct page *page; - struct bio_vec *bvec; - int i; - - bio_for_each_segment_all(bvec, bio, i) { - page = bvec->bv_page; - if (bio->bi_status) { - int err = blk_status_to_errno(bio->bi_status); - - SetPageError(page); - mapping_set_error(page->mapping, err); - } - unlock_page(page); - } - - bio_put(bio); -} - -/** - * gfs2_jhead_pg_srch - Look for the journal head in a given page. - * @jd: The journal descriptor - * @page: The page to look in - * - * Returns: 1 if found, 0 otherwise. - */ - -static bool gfs2_jhead_pg_srch(struct gfs2_jdesc *jd, - struct gfs2_log_header_host *head, - struct page *page) -{ - struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode); - struct gfs2_log_header_host uninitialized_var(lh); - void *kaddr = kmap_atomic(page); - unsigned int offset; - bool ret = false; - - for (offset = 0; offset < PAGE_SIZE; offset += sdp->sd_sb.sb_bsize) { - if (!__get_log_header(sdp, kaddr + offset, 0, &lh)) { - if (lh.lh_sequence > head->lh_sequence) - *head = lh; - else { - ret = true; - break; - } - } - } - kunmap_atomic(kaddr); - return ret; -} - -/** - * gfs2_jhead_process_page - Search/cleanup a page - * @jd: The journal descriptor - * @index: Index of the page to look into - * @done: If set, perform only cleanup, else search and set if found. - * - * Find the page with 'index' in the journal's mapping. Search the page for - * the journal head if requested (cleanup == false). Release refs on the - * page so the page cache can reclaim it (put_page() twice). We grabbed a - * reference on this page two times, first when we did a find_or_create_page() - * to obtain the page to add it to the bio and second when we do a - * find_get_page() here to get the page to wait on while I/O on it is being - * completed. - * This function is also used to free up a page we might've grabbed but not - * used. Maybe we added it to a bio, but not submitted it for I/O. Or we - * submitted the I/O, but we already found the jhead so we only need to drop - * our references to the page. - */ - -static void gfs2_jhead_process_page(struct gfs2_jdesc *jd, unsigned long index, - struct gfs2_log_header_host *head, - bool *done) -{ - struct page *page; - - page = find_get_page(jd->jd_inode->i_mapping, index); - wait_on_page_locked(page); - - if (PageError(page)) - *done = true; - - if (!*done) - *done = gfs2_jhead_pg_srch(jd, head, page); - - put_page(page); /* Once for find_get_page */ - put_page(page); /* Once more for find_or_create_page */ -} - -/** - * gfs2_find_jhead - find the head of a log - * @jd: The journal descriptor - * @head: The log descriptor for the head of the log is returned here - * - * Do a search of a journal by reading it in large chunks using bios and find - * the valid log entry with the highest sequence number. (i.e. the log head) - * - * Returns: 0 on success, errno otherwise - */ - -int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head) -{ - struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode); - struct address_space *mapping = jd->jd_inode->i_mapping; - struct gfs2_journal_extent *je; - u32 block, read_idx = 0, submit_idx = 0, index = 0; - int shift = PAGE_SHIFT - sdp->sd_sb.sb_bsize_shift; - int blocks_per_page = 1 << shift, sz, ret = 0; - struct bio *bio = NULL; - struct page *page; - bool done = false; - errseq_t since; - - memset(head, 0, sizeof(*head)); - if (list_empty(&jd->extent_list)) - gfs2_map_journal_extents(sdp, jd); - - since = filemap_sample_wb_err(mapping); - list_for_each_entry(je, &jd->extent_list, list) { - for (block = 0; block < je->blocks; block += blocks_per_page) { - index = (je->lblock + block) >> shift; - - page = find_or_create_page(mapping, index, GFP_NOFS); - if (!page) { - ret = -ENOMEM; - done = true; - goto out; - } - - if (bio) { - sz = bio_add_page(bio, page, PAGE_SIZE, 0); - if (sz == PAGE_SIZE) - goto page_added; - submit_idx = index; - submit_bio(bio); - bio = NULL; - } - - bio = gfs2_log_alloc_bio(sdp, - je->dblock + (index << shift), - gfs2_end_log_read); - bio->bi_opf = REQ_OP_READ; - sz = bio_add_page(bio, page, PAGE_SIZE, 0); - gfs2_assert_warn(sdp, sz == PAGE_SIZE); - -page_added: - if (submit_idx <= read_idx + BIO_MAX_PAGES) { - /* Keep at least one bio in flight */ - continue; - } - - gfs2_jhead_process_page(jd, read_idx++, head, &done); - if (done) - goto out; /* found */ - } - } - -out: - if (bio) - submit_bio(bio); - while (read_idx <= index) - gfs2_jhead_process_page(jd, read_idx++, head, &done); - - if (!ret) - ret = filemap_check_wb_err(mapping, since); - - return ret; -} - static struct page *gfs2_get_log_desc(struct gfs2_sbd *sdp, u32 ld_type, u32 ld_length, u32 ld_data1) { diff --git a/fs/gfs2/lops.h b/fs/gfs2/lops.h index 331160fc568b..711c4d89c063 100644 --- a/fs/gfs2/lops.h +++ b/fs/gfs2/lops.h @@ -30,10 +30,8 @@ extern u64 gfs2_log_bmap(struct gfs2_sbd *sdp); extern void gfs2_log_write(struct gfs2_sbd *sdp, struct page *page, unsigned size, unsigned offset, u64 blkno); extern void gfs2_log_write_page(struct gfs2_sbd *sdp, struct page *page); -extern void gfs2_log_submit_bio(struct bio **biop, int opf); +extern void gfs2_log_submit_bio(struct bio **biop, int op, int op_flags); extern void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh); -extern int gfs2_find_jhead(struct gfs2_jdesc *jd, - struct gfs2_log_header_host *head); static inline unsigned int buf_limit(struct gfs2_sbd *sdp) { diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 1179763f6370..b041cb8ae383 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -41,7 +41,6 @@ #include "dir.h" #include "meta_io.h" #include "trace_gfs2.h" -#include "lops.h" #define DO 0 #define UNDO 1 diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c index 7389e445a7a7..2dac43065382 100644 --- a/fs/gfs2/recovery.c +++ b/fs/gfs2/recovery.c @@ -182,6 +182,129 @@ static int get_log_header(struct gfs2_jdesc *jd, unsigned int blk, } /** + * find_good_lh - find a good log header + * @jd: the journal + * @blk: the segment to start searching from + * @lh: the log header to fill in + * @forward: if true search forward in the log, else search backward + * + * Call get_log_header() to get a log header for a segment, but if the + * segment is bad, either scan forward or backward until we find a good one. + * + * Returns: errno + */ + +static int find_good_lh(struct gfs2_jdesc *jd, unsigned int *blk, + struct gfs2_log_header_host *head) +{ + unsigned int orig_blk = *blk; + int error; + + for (;;) { + error = get_log_header(jd, *blk, head); + if (error <= 0) + return error; + + if (++*blk == jd->jd_blocks) + *blk = 0; + + if (*blk == orig_blk) { + gfs2_consist_inode(GFS2_I(jd->jd_inode)); + return -EIO; + } + } +} + +/** + * jhead_scan - make sure we've found the head of the log + * @jd: the journal + * @head: this is filled in with the log descriptor of the head + * + * At this point, seg and lh should be either the head of the log or just + * before. Scan forward until we find the head. + * + * Returns: errno + */ + +static int jhead_scan(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head) +{ + unsigned int blk = head->lh_blkno; + struct gfs2_log_header_host lh; + int error; + + for (;;) { + if (++blk == jd->jd_blocks) + blk = 0; + + error = get_log_header(jd, blk, &lh); + if (error < 0) + return error; + if (error == 1) + continue; + + if (lh.lh_sequence == head->lh_sequence) { + gfs2_consist_inode(GFS2_I(jd->jd_inode)); + return -EIO; + } + if (lh.lh_sequence < head->lh_sequence) + break; + + *head = lh; + } + + return 0; +} + +/** + * gfs2_find_jhead - find the head of a log + * @jd: the journal + * @head: the log descriptor for the head of the log is returned here + * + * Do a binary search of a journal and find the valid log entry with the + * highest sequence number. (i.e. the log head) + * + * Returns: errno + */ + +int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head) +{ + struct gfs2_log_header_host lh_1, lh_m; + u32 blk_1, blk_2, blk_m; + int error; + + blk_1 = 0; + blk_2 = jd->jd_blocks - 1; + + for (;;) { + blk_m = (blk_1 + blk_2) / 2; + + error = find_good_lh(jd, &blk_1, &lh_1); + if (error) + return error; + + error = find_good_lh(jd, &blk_m, &lh_m); + if (error) + return error; + + if (blk_1 == blk_m || blk_m == blk_2) + break; + + if (lh_1.lh_sequence <= lh_m.lh_sequence) + blk_1 = blk_m; + else + blk_2 = blk_m; + } + + error = jhead_scan(jd, &lh_1); + if (error) + return error; + + *head = lh_1; + + return error; +} + +/** * foreach_descriptor - go through the active part of the log * @jd: the journal * @start: the first log header in the active region diff --git a/fs/gfs2/recovery.h b/fs/gfs2/recovery.h index 99575ab81202..11d81248be85 100644 --- a/fs/gfs2/recovery.h +++ b/fs/gfs2/recovery.h @@ -27,6 +27,8 @@ extern int gfs2_revoke_add(struct gfs2_jdesc *jd, u64 blkno, unsigned int where) extern int gfs2_revoke_check(struct gfs2_jdesc *jd, u64 blkno, unsigned int where); extern void gfs2_revoke_clean(struct gfs2_jdesc *jd); +extern int gfs2_find_jhead(struct gfs2_jdesc *jd, + struct gfs2_log_header_host *head); extern int gfs2_recover_journal(struct gfs2_jdesc *gfs2_jd, bool wait); extern void gfs2_recover_func(struct work_struct *work); extern int __get_log_header(struct gfs2_sbd *sdp, diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index d4b11c903971..ca71163ff7cf 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -45,7 +45,6 @@ #include "util.h" #include "sys.h" #include "xattr.h" -#include "lops.h" #define args_neq(a1, a2, x) ((a1)->ar_##x != (a2)->ar_##x) diff --git a/fs/inode.c b/fs/inode.c index 0cd47fe0dbe5..73432e64f874 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -730,11 +730,8 @@ static enum lru_status inode_lru_isolate(struct list_head *item, return LRU_REMOVED; } - /* - * Recently referenced inodes and inodes with many attached pages - * get one more pass. - */ - if (inode->i_state & I_REFERENCED || inode->i_data.nrpages > 1) { + /* recently referenced inodes get one more pass */ + if (inode->i_state & I_REFERENCED) { inode->i_state &= ~I_REFERENCED; spin_unlock(&inode->i_lock); return LRU_ROTATE; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index f12cb31a41e5..d09c9f878141 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -238,9 +238,9 @@ out: } /* A writeback failed: mark the page as bad, and invalidate the page cache */ -static void nfs_set_pageerror(struct page *page) +static void nfs_set_pageerror(struct address_space *mapping) { - nfs_zap_mapping(page_file_mapping(page)->host, page_file_mapping(page)); + nfs_zap_mapping(mapping->host, mapping); } /* @@ -994,7 +994,7 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr) nfs_list_remove_request(req); if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) && (hdr->good_bytes < bytes)) { - nfs_set_pageerror(req->wb_page); + nfs_set_pageerror(page_file_mapping(req->wb_page)); nfs_context_set_write_error(req->wb_context, hdr->error); goto remove_req; } @@ -1348,7 +1348,8 @@ int nfs_updatepage(struct file *file, struct page *page, unsigned int offset, unsigned int count) { struct nfs_open_context *ctx = nfs_file_open_context(file); - struct inode *inode = page_file_mapping(page)->host; + struct address_space *mapping = page_file_mapping(page); + struct inode *inode = mapping->host; int status = 0; nfs_inc_stats(inode, NFSIOS_VFSUPDATEPAGE); @@ -1366,7 +1367,7 @@ int nfs_updatepage(struct file *file, struct page *page, status = nfs_writepage_setup(ctx, page, offset, count); if (status < 0) - nfs_set_pageerror(page); + nfs_set_pageerror(mapping); else __set_page_dirty_nobuffers(page); out: diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index b33f9785b756..72a7681f4046 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1239,8 +1239,8 @@ static __net_init int nfsd_init_net(struct net *net) retval = nfsd_idmap_init(net); if (retval) goto out_idmap_error; - nn->nfsd4_lease = 45; /* default lease time */ - nn->nfsd4_grace = 45; + nn->nfsd4_lease = 90; /* default lease time */ + nn->nfsd4_grace = 90; nn->somebody_reclaimed = false; nn->clverifier_counter = prandom_u32(); nn->clientid_counter = prandom_u32(); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index f0ec9edab2f3..85b0ef890b28 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -423,7 +423,7 @@ struct mem_size_stats { }; static void smaps_account(struct mem_size_stats *mss, struct page *page, - bool compound, bool young, bool dirty) + bool compound, bool young, bool dirty, bool locked) { int i, nr = compound ? 1 << compound_order(page) : 1; unsigned long size = nr * PAGE_SIZE; @@ -450,24 +450,31 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page, else mss->private_clean += size; mss->pss += (u64)size << PSS_SHIFT; + if (locked) + mss->pss_locked += (u64)size << PSS_SHIFT; return; } for (i = 0; i < nr; i++, page++) { int mapcount = page_mapcount(page); + unsigned long pss = (PAGE_SIZE << PSS_SHIFT); if (mapcount >= 2) { if (dirty || PageDirty(page)) mss->shared_dirty += PAGE_SIZE; else mss->shared_clean += PAGE_SIZE; - mss->pss += (PAGE_SIZE << PSS_SHIFT) / mapcount; + mss->pss += pss / mapcount; + if (locked) + mss->pss_locked += pss / mapcount; } else { if (dirty || PageDirty(page)) mss->private_dirty += PAGE_SIZE; else mss->private_clean += PAGE_SIZE; - mss->pss += PAGE_SIZE << PSS_SHIFT; + mss->pss += pss; + if (locked) + mss->pss_locked += pss; } } } @@ -490,6 +497,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, { struct mem_size_stats *mss = walk->private; struct vm_area_struct *vma = walk->vma; + bool locked = !!(vma->vm_flags & VM_LOCKED); struct page *page = NULL; if (pte_present(*pte)) { @@ -532,7 +540,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, if (!page) return; - smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte)); + smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte), locked); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -541,6 +549,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, { struct mem_size_stats *mss = walk->private; struct vm_area_struct *vma = walk->vma; + bool locked = !!(vma->vm_flags & VM_LOCKED); struct page *page; /* FOLL_DUMP will return -EFAULT on huge zero page */ @@ -555,7 +564,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, /* pass */; else VM_BUG_ON_PAGE(1, page); - smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd)); + smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd), locked); } #else static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, @@ -737,11 +746,8 @@ static void smap_gather_stats(struct vm_area_struct *vma, } } #endif - /* mmap_sem is held in m_start */ walk_page_vma(vma, &smaps_walk); - if (vma->vm_flags & VM_LOCKED) - mss->pss_locked += mss->pss; } #define SEQ_PUT_DEC(str, val) \ diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h index 4f34734e7f36..ba6fd7202775 100644 --- a/include/acpi/cppc_acpi.h +++ b/include/acpi/cppc_acpi.h @@ -137,6 +137,7 @@ struct cppc_cpudata { cpumask_var_t shared_cpu_map; }; +extern int cppc_get_desired_perf(int cpunum, u64 *desired_perf); extern int cppc_get_perf_ctrs(int cpu, struct cppc_perf_fb_ctrs *perf_fb_ctrs); extern int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls); extern int cppc_get_perf_caps(int cpu, struct cppc_perf_caps *caps); diff --git a/include/uapi/asm-generic/shmparam.h b/include/asm-generic/shmparam.h index 8b78c0ba08b1..8b78c0ba08b1 100644 --- a/include/uapi/asm-generic/shmparam.h +++ b/include/asm-generic/shmparam.h diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 4f31f96bbfab..c36c86f1ec9a 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -100,7 +100,7 @@ enum vgic_irq_config { }; struct vgic_irq { - spinlock_t irq_lock; /* Protects the content of the struct */ + raw_spinlock_t irq_lock; /* Protects the content of the struct */ struct list_head lpi_list; /* Used to link all LPIs together */ struct list_head ap_list; @@ -256,7 +256,7 @@ struct vgic_dist { u64 propbaser; /* Protects the lpi_list and the count value below. */ - spinlock_t lpi_list_lock; + raw_spinlock_t lpi_list_lock; struct list_head lpi_list_head; int lpi_list_count; @@ -307,7 +307,7 @@ struct vgic_cpu { unsigned int used_lrs; struct vgic_irq private_irqs[VGIC_NR_PRIVATE_IRQS]; - spinlock_t ap_list_lock; /* Protects the ap_list */ + raw_spinlock_t ap_list_lock; /* Protects the ap_list */ /* * List of IRQs that this VCPU should consider because they are either diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 19f32b0c29af..6b318efd8a74 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -34,6 +34,7 @@ #ifndef __has_attribute # define __has_attribute(x) __GCC4_has_attribute_##x # define __GCC4_has_attribute___assume_aligned__ (__GNUC_MINOR__ >= 9) +# define __GCC4_has_attribute___copy__ 0 # define __GCC4_has_attribute___designated_init__ 0 # define __GCC4_has_attribute___externally_visible__ 1 # define __GCC4_has_attribute___noclone__ 1 @@ -101,6 +102,19 @@ #define __attribute_const__ __attribute__((__const__)) /* + * Optional: only supported since gcc >= 9 + * Optional: not supported by clang + * Optional: not supported by icc + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-copy-function-attribute + */ +#if __has_attribute(__copy__) +# define __copy(symbol) __attribute__((__copy__(symbol))) +#else +# define __copy(symbol) +#endif + +/* * Don't. Just don't. See commit 771c035372a0 ("deprecate the '__deprecated' * attribute warnings entirely and for good") for more information. * diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index c86d6d8bdfed..b160e98076e3 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -151,6 +151,9 @@ struct cpufreq_policy { /* For cpufreq driver's internal use */ void *driver_data; + + /* Pointer to the cooling device if used for thermal mitigation */ + struct thermal_cooling_device *cdev; }; /* Only for ACPI */ @@ -254,20 +257,12 @@ __ATTR(_name, 0644, show_##_name, store_##_name) static struct freq_attr _name = \ __ATTR(_name, 0200, NULL, store_##_name) -struct global_attr { - struct attribute attr; - ssize_t (*show)(struct kobject *kobj, - struct attribute *attr, char *buf); - ssize_t (*store)(struct kobject *a, struct attribute *b, - const char *c, size_t count); -}; - #define define_one_global_ro(_name) \ -static struct global_attr _name = \ +static struct kobj_attribute _name = \ __ATTR(_name, 0444, show_##_name, NULL) #define define_one_global_rw(_name) \ -static struct global_attr _name = \ +static struct kobj_attribute _name = \ __ATTR(_name, 0644, show_##_name, store_##_name) @@ -330,6 +325,8 @@ struct cpufreq_driver { /* optional */ int (*bios_limit)(int cpu, unsigned int *limit); + int (*online)(struct cpufreq_policy *policy); + int (*offline)(struct cpufreq_policy *policy); int (*exit)(struct cpufreq_policy *policy); void (*stop_cpu)(struct cpufreq_policy *policy); int (*suspend)(struct cpufreq_policy *policy); @@ -346,14 +343,15 @@ struct cpufreq_driver { }; /* flags */ -#define CPUFREQ_STICKY (1 << 0) /* driver isn't removed even if - all ->init() calls failed */ -#define CPUFREQ_CONST_LOOPS (1 << 1) /* loops_per_jiffy or other - kernel "constants" aren't - affected by frequency - transitions */ -#define CPUFREQ_PM_NO_WARN (1 << 2) /* don't warn on suspend/resume - speed mismatches */ + +/* driver isn't removed even if all ->init() calls failed */ +#define CPUFREQ_STICKY BIT(0) + +/* loops_per_jiffy or other kernel "constants" aren't affected by frequency transitions */ +#define CPUFREQ_CONST_LOOPS BIT(1) + +/* don't warn on suspend/resume speed mismatches */ +#define CPUFREQ_PM_NO_WARN BIT(2) /* * This should be set by platforms having multiple clock-domains, i.e. @@ -361,14 +359,14 @@ struct cpufreq_driver { * be created in cpu/cpu<num>/cpufreq/ directory and so they can use the same * governor with different tunables for different clusters. */ -#define CPUFREQ_HAVE_GOVERNOR_PER_POLICY (1 << 3) +#define CPUFREQ_HAVE_GOVERNOR_PER_POLICY BIT(3) /* * Driver will do POSTCHANGE notifications from outside of their ->target() * routine and so must set cpufreq_driver->flags with this flag, so that core * can handle them specially. */ -#define CPUFREQ_ASYNC_NOTIFICATION (1 << 4) +#define CPUFREQ_ASYNC_NOTIFICATION BIT(4) /* * Set by drivers which want cpufreq core to check if CPU is running at a @@ -377,13 +375,19 @@ struct cpufreq_driver { * from the table. And if that fails, we will stop further boot process by * issuing a BUG_ON(). */ -#define CPUFREQ_NEED_INITIAL_FREQ_CHECK (1 << 5) +#define CPUFREQ_NEED_INITIAL_FREQ_CHECK BIT(5) /* * Set by drivers to disallow use of governors with "dynamic_switching" flag * set. */ -#define CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING (1 << 6) +#define CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING BIT(6) + +/* + * Set by drivers that want the core to automatically register the cpufreq + * driver as a thermal cooling device. + */ +#define CPUFREQ_IS_COOLING_DEV BIT(7) int cpufreq_register_driver(struct cpufreq_driver *driver_data); int cpufreq_unregister_driver(struct cpufreq_driver *driver_data); diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 4dff74f48d4b..3b39472324a3 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -69,11 +69,9 @@ struct cpuidle_state { /* Idle State Flags */ #define CPUIDLE_FLAG_NONE (0x00) -#define CPUIDLE_FLAG_POLLING (0x01) /* polling state */ -#define CPUIDLE_FLAG_COUPLED (0x02) /* state applies to multiple cpus */ -#define CPUIDLE_FLAG_TIMER_STOP (0x04) /* timer is stopped on this state */ - -#define CPUIDLE_DRIVER_FLAGS_MASK (0xFFFF0000) +#define CPUIDLE_FLAG_POLLING BIT(0) /* polling state */ +#define CPUIDLE_FLAG_COUPLED BIT(1) /* state applies to multiple cpus */ +#define CPUIDLE_FLAG_TIMER_STOP BIT(2) /* timer is stopped on this state */ struct cpuidle_device_kobj; struct cpuidle_state_kobj; diff --git a/include/linux/device.h b/include/linux/device.h index 6cb4640b6160..53028636fe39 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1165,6 +1165,16 @@ static inline bool device_async_suspend_enabled(struct device *dev) return !!dev->power.async_suspend; } +static inline bool device_pm_not_required(struct device *dev) +{ + return dev->power.no_pm; +} + +static inline void device_set_pm_not_required(struct device *dev) +{ + dev->power.no_pm = true; +} + static inline void dev_pm_syscore_device(struct device *dev, bool val) { #ifdef CONFIG_PM_SLEEP diff --git a/include/linux/efi.h b/include/linux/efi.h index 45ff763fba76..28604a8d0aa9 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1198,8 +1198,6 @@ static inline bool efi_enabled(int feature) extern void efi_reboot(enum reboot_mode reboot_mode, const char *__unused); extern bool efi_is_table_address(unsigned long phys_addr); - -extern int efi_apply_persistent_mem_reservations(void); #else static inline bool efi_enabled(int feature) { @@ -1218,11 +1216,6 @@ static inline bool efi_is_table_address(unsigned long phys_addr) { return false; } - -static inline int efi_apply_persistent_mem_reservations(void) -{ - return 0; -} #endif extern int efi_status_to_err(efi_status_t status); diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 64c41cf45590..859b55b66db2 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -29,9 +29,6 @@ extern unsigned long max_pfn; */ extern unsigned long long max_possible_pfn; -#define INIT_MEMBLOCK_REGIONS 128 -#define INIT_PHYSMEM_REGIONS 4 - /** * enum memblock_flags - definition of memory region attributes * @MEMBLOCK_NONE: no special request diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index de7377815b6b..8ef330027b13 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -308,6 +308,7 @@ struct mmc_card { unsigned int nr_parts; unsigned int bouncesz; /* Bounce buffer size */ + struct workqueue_struct *complete_wq; /* Private workqueue */ }; static inline bool mmc_large_sector(struct mmc_card *card) diff --git a/include/linux/module.h b/include/linux/module.h index 8fa38d3e7538..f5bc4c046461 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -129,13 +129,13 @@ extern void cleanup_module(void); #define module_init(initfn) \ static inline initcall_t __maybe_unused __inittest(void) \ { return initfn; } \ - int init_module(void) __attribute__((alias(#initfn))); + int init_module(void) __copy(initfn) __attribute__((alias(#initfn))); /* This is only required if you want to be unloadable. */ #define module_exit(exitfn) \ static inline exitcall_t __maybe_unused __exittest(void) \ { return exitfn; } \ - void cleanup_module(void) __attribute__((alias(#exitfn))); + void cleanup_module(void) __copy(exitfn) __attribute__((alias(#exitfn))); #endif diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 1d5c551a5add..e1a051724f7e 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -447,6 +447,11 @@ struct pmu { * Filter events for PMU-specific reasons. */ int (*filter_match) (struct perf_event *event); /* optional */ + + /* + * Check period value for PERF_EVENT_IOC_PERIOD ioctl. + */ + int (*check_period) (struct perf_event *event, u64 value); /* optional */ }; enum perf_addr_filter_action_t { diff --git a/include/linux/phy.h b/include/linux/phy.h index ef20aeea10cc..127fcc9c3778 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -674,26 +674,13 @@ phy_lookup_setting(int speed, int duplex, const unsigned long *mask, size_t phy_speeds(unsigned int *speeds, size_t size, unsigned long *mask); -static inline bool __phy_is_started(struct phy_device *phydev) -{ - WARN_ON(!mutex_is_locked(&phydev->lock)); - - return phydev->state >= PHY_UP; -} - /** * phy_is_started - Convenience function to check whether PHY is started * @phydev: The phy_device struct */ static inline bool phy_is_started(struct phy_device *phydev) { - bool started; - - mutex_lock(&phydev->lock); - started = __phy_is_started(phydev); - mutex_unlock(&phydev->lock); - - return started; + return phydev->state >= PHY_UP; } void phy_resolve_aneg_linkmode(struct phy_device *phydev); diff --git a/include/linux/platform_data/davinci-cpufreq.h b/include/linux/platform_data/davinci-cpufreq.h new file mode 100644 index 000000000000..3fbf9f2793b5 --- /dev/null +++ b/include/linux/platform_data/davinci-cpufreq.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * TI DaVinci CPUFreq platform support. + * + * Copyright (C) 2009 Texas Instruments, Inc. http://www.ti.com/ + */ + +#ifndef _MACH_DAVINCI_CPUFREQ_H +#define _MACH_DAVINCI_CPUFREQ_H + +#include <linux/cpufreq.h> + +struct davinci_cpufreq_config { + struct cpufreq_frequency_table *freq_table; + int (*set_voltage)(unsigned int index); + int (*init)(void); +}; + +#endif /* _MACH_DAVINCI_CPUFREQ_H */ diff --git a/include/linux/pm.h b/include/linux/pm.h index 0bd9de116826..06f7ed893928 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -592,6 +592,7 @@ struct dev_pm_info { bool is_suspended:1; /* Ditto */ bool is_noirq_suspended:1; bool is_late_suspended:1; + bool no_pm:1; bool early_init:1; /* Owned by the PM core */ bool direct_complete:1; /* Owned by the PM core */ u32 driver_flags; @@ -633,9 +634,9 @@ struct dev_pm_info { int runtime_error; int autosuspend_delay; u64 last_busy; - unsigned long active_jiffies; - unsigned long suspended_jiffies; - unsigned long accounting_timestamp; + u64 active_time; + u64 suspended_time; + u64 accounting_timestamp; #endif struct pm_subsys_data *subsys_data; /* Owned by the subsystem. */ void (*set_latency_tolerance)(struct device *, s32); diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index dd364abb649a..1ed5874bcee0 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -271,7 +271,7 @@ int genpd_dev_pm_attach(struct device *dev); struct device *genpd_dev_pm_attach_by_id(struct device *dev, unsigned int index); struct device *genpd_dev_pm_attach_by_name(struct device *dev, - char *name); + const char *name); #else /* !CONFIG_PM_GENERIC_DOMAINS_OF */ static inline int of_genpd_add_provider_simple(struct device_node *np, struct generic_pm_domain *genpd) @@ -324,7 +324,7 @@ static inline struct device *genpd_dev_pm_attach_by_id(struct device *dev, } static inline struct device *genpd_dev_pm_attach_by_name(struct device *dev, - char *name) + const char *name) { return NULL; } @@ -341,7 +341,7 @@ int dev_pm_domain_attach(struct device *dev, bool power_on); struct device *dev_pm_domain_attach_by_id(struct device *dev, unsigned int index); struct device *dev_pm_domain_attach_by_name(struct device *dev, - char *name); + const char *name); void dev_pm_domain_detach(struct device *dev, bool power_off); void dev_pm_domain_set(struct device *dev, struct dev_pm_domain *pd); #else @@ -355,7 +355,7 @@ static inline struct device *dev_pm_domain_attach_by_id(struct device *dev, return NULL; } static inline struct device *dev_pm_domain_attach_by_name(struct device *dev, - char *name) + const char *name) { return NULL; } diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index fed5be706bc9..9dc6eebf62d2 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -113,6 +113,8 @@ static inline bool pm_runtime_is_irq_safe(struct device *dev) return dev->power.irq_safe; } +extern u64 pm_runtime_suspended_time(struct device *dev); + #else /* !CONFIG_PM */ static inline bool queue_pm_work(struct work_struct *work) { return false; } diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h index 00b5e7825508..74ff688568a0 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -39,6 +39,7 @@ struct inet_peer { u32 metrics[RTAX_MAX]; u32 rate_tokens; /* rate limiting for ICMP */ + u32 n_redirects; unsigned long rate_last; /* * Once inet_peer is queued for deletion (refcnt == 0), following field diff --git a/include/net/sock.h b/include/net/sock.h index 2b229f7be8eb..f43f935cb113 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1277,7 +1277,7 @@ static inline void sk_sockets_allocated_inc(struct sock *sk) percpu_counter_inc(sk->sk_prot->sockets_allocated); } -static inline int +static inline u64 sk_sockets_allocated_read_positive(struct sock *sk) { return percpu_counter_read_positive(sk->sk_prot->sockets_allocated); diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h index 14565d703291..e8baca85bac6 100644 --- a/include/uapi/linux/inet_diag.h +++ b/include/uapi/linux/inet_diag.h @@ -137,15 +137,21 @@ enum { INET_DIAG_TCLASS, INET_DIAG_SKMEMINFO, INET_DIAG_SHUTDOWN, - INET_DIAG_DCTCPINFO, - INET_DIAG_PROTOCOL, /* response attribute only */ + + /* + * Next extenstions cannot be requested in struct inet_diag_req_v2: + * its field idiag_ext has only 8 bits. + */ + + INET_DIAG_DCTCPINFO, /* request as INET_DIAG_VEGASINFO */ + INET_DIAG_PROTOCOL, /* response attribute only */ INET_DIAG_SKV6ONLY, INET_DIAG_LOCALS, INET_DIAG_PEERS, INET_DIAG_PAD, - INET_DIAG_MARK, - INET_DIAG_BBRINFO, - INET_DIAG_CLASS_ID, + INET_DIAG_MARK, /* only with CAP_NET_ADMIN */ + INET_DIAG_BBRINFO, /* request as INET_DIAG_VEGASINFO */ + INET_DIAG_CLASS_ID, /* request as INET_DIAG_TCLASS */ INET_DIAG_MD5SIG, __INET_DIAG_MAX, }; diff --git a/init/main.c b/init/main.c index e2e80ca3165a..c86a1c8f19f4 100644 --- a/init/main.c +++ b/init/main.c @@ -695,7 +695,6 @@ asmlinkage __visible void __init start_kernel(void) initrd_start = 0; } #endif - page_ext_init(); kmemleak_init(); setup_per_cpu_pageset(); numa_policy_init(); @@ -1131,6 +1130,8 @@ static noinline void __init kernel_init_freeable(void) sched_init_smp(); page_alloc_init_late(); + /* Initialize page ext after all struct pages are initialized. */ + page_ext_init(); do_basic_setup(); diff --git a/kernel/events/core.c b/kernel/events/core.c index e5ede6918050..26d6edab051a 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4963,6 +4963,11 @@ static void __perf_event_period(struct perf_event *event, } } +static int perf_event_check_period(struct perf_event *event, u64 value) +{ + return event->pmu->check_period(event, value); +} + static int perf_event_period(struct perf_event *event, u64 __user *arg) { u64 value; @@ -4979,6 +4984,9 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg) if (event->attr.freq && value > sysctl_perf_event_sample_rate) return -EINVAL; + if (perf_event_check_period(event, value)) + return -EINVAL; + event_function_call(event, __perf_event_period, &value); return 0; @@ -9391,6 +9399,11 @@ static int perf_pmu_nop_int(struct pmu *pmu) return 0; } +static int perf_event_nop_int(struct perf_event *event, u64 value) +{ + return 0; +} + static DEFINE_PER_CPU(unsigned int, nop_txn_flags); static void perf_pmu_start_txn(struct pmu *pmu, unsigned int flags) @@ -9691,6 +9704,9 @@ got_cpu_context: pmu->pmu_disable = perf_pmu_nop_void; } + if (!pmu->check_period) + pmu->check_period = perf_event_nop_int; + if (!pmu->event_idx) pmu->event_idx = perf_event_idx_default; diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 309ef5a64af5..5ab4fe3b1dcc 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -734,7 +734,7 @@ struct ring_buffer *rb_alloc(int nr_pages, long watermark, int cpu, int flags) size = sizeof(struct ring_buffer); size += nr_pages * sizeof(void *); - if (order_base_2(size) >= MAX_ORDER) + if (order_base_2(size) >= PAGE_SHIFT+MAX_ORDER) goto fail; rb = kzalloc(size, GFP_KERNEL); diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index d9dc2c38764a..7d66ee68aaaf 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -10,6 +10,7 @@ #include <linux/cpu.h> #include <linux/cpumask.h> +#include <linux/debugfs.h> #include <linux/energy_model.h> #include <linux/sched/topology.h> #include <linux/slab.h> @@ -23,6 +24,60 @@ static DEFINE_PER_CPU(struct em_perf_domain *, em_data); */ static DEFINE_MUTEX(em_pd_mutex); +#ifdef CONFIG_DEBUG_FS +static struct dentry *rootdir; + +static void em_debug_create_cs(struct em_cap_state *cs, struct dentry *pd) +{ + struct dentry *d; + char name[24]; + + snprintf(name, sizeof(name), "cs:%lu", cs->frequency); + + /* Create per-cs directory */ + d = debugfs_create_dir(name, pd); + debugfs_create_ulong("frequency", 0444, d, &cs->frequency); + debugfs_create_ulong("power", 0444, d, &cs->power); + debugfs_create_ulong("cost", 0444, d, &cs->cost); +} + +static int em_debug_cpus_show(struct seq_file *s, void *unused) +{ + seq_printf(s, "%*pbl\n", cpumask_pr_args(to_cpumask(s->private))); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(em_debug_cpus); + +static void em_debug_create_pd(struct em_perf_domain *pd, int cpu) +{ + struct dentry *d; + char name[8]; + int i; + + snprintf(name, sizeof(name), "pd%d", cpu); + + /* Create the directory of the performance domain */ + d = debugfs_create_dir(name, rootdir); + + debugfs_create_file("cpus", 0444, d, pd->cpus, &em_debug_cpus_fops); + + /* Create a sub-directory for each capacity state */ + for (i = 0; i < pd->nr_cap_states; i++) + em_debug_create_cs(&pd->table[i], d); +} + +static int __init em_debug_init(void) +{ + /* Create /sys/kernel/debug/energy_model directory */ + rootdir = debugfs_create_dir("energy_model", NULL); + + return 0; +} +core_initcall(em_debug_init); +#else /* CONFIG_DEBUG_FS */ +static void em_debug_create_pd(struct em_perf_domain *pd, int cpu) {} +#endif static struct em_perf_domain *em_create_pd(cpumask_t *span, int nr_states, struct em_data_callback *cb) { @@ -102,6 +157,8 @@ static struct em_perf_domain *em_create_pd(cpumask_t *span, int nr_states, pd->nr_cap_states = nr_states; cpumask_copy(to_cpumask(pd->cpus), span); + em_debug_create_pd(pd, cpu); + return pd; free_cs_table: diff --git a/kernel/power/qos.c b/kernel/power/qos.c index b7a82502857a..9d22131afc1e 100644 --- a/kernel/power/qos.c +++ b/kernel/power/qos.c @@ -582,10 +582,8 @@ static int register_pm_qos_misc(struct pm_qos_object *qos, struct dentry *d) qos->pm_qos_power_miscdev.name = qos->name; qos->pm_qos_power_miscdev.fops = &pm_qos_power_fops; - if (d) { - (void)debugfs_create_file(qos->name, S_IRUGO, d, - (void *)qos, &pm_qos_debug_fops); - } + debugfs_create_file(qos->name, S_IRUGO, d, (void *)qos, + &pm_qos_debug_fops); return misc_register(&qos->pm_qos_power_miscdev); } @@ -685,8 +683,6 @@ static int __init pm_qos_power_init(void) BUILD_BUG_ON(ARRAY_SIZE(pm_qos_array) != PM_QOS_NUM_CLASSES); d = debugfs_create_dir("pm_qos", NULL); - if (IS_ERR_OR_NULL(d)) - d = NULL; for (i = PM_QOS_CPU_DMA_LATENCY; i < PM_QOS_NUM_CLASSES; i++) { ret = register_pm_qos_misc(pm_qos_array[i], d); diff --git a/kernel/signal.c b/kernel/signal.c index 99fa8ff06fd9..57b7771e20d7 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2436,9 +2436,12 @@ relock: } /* Has this task already been marked for death? */ - ksig->info.si_signo = signr = SIGKILL; - if (signal_group_exit(signal)) + if (signal_group_exit(signal)) { + ksig->info.si_signo = signr = SIGKILL; + sigdelset(¤t->pending.signal, SIGKILL); + recalc_sigpending(); goto fatal; + } for (;;) { struct k_sigaction *ka; diff --git a/kernel/trace/trace_probe_tmpl.h b/kernel/trace/trace_probe_tmpl.h index 5c56afc17cf8..4737bb8c07a3 100644 --- a/kernel/trace/trace_probe_tmpl.h +++ b/kernel/trace/trace_probe_tmpl.h @@ -180,10 +180,12 @@ store_trace_args(void *data, struct trace_probe *tp, struct pt_regs *regs, if (unlikely(arg->dynamic)) *dl = make_data_loc(maxlen, dyndata - base); ret = process_fetch_insn(arg->code, regs, dl, base); - if (unlikely(ret < 0 && arg->dynamic)) + if (unlikely(ret < 0 && arg->dynamic)) { *dl = make_data_loc(0, dyndata - base); - else + } else { dyndata += ret; + maxlen -= ret; + } } } diff --git a/lib/crc32.c b/lib/crc32.c index 45b1d67a1767..4a20455d1f61 100644 --- a/lib/crc32.c +++ b/lib/crc32.c @@ -206,8 +206,8 @@ u32 __pure __weak __crc32c_le(u32 crc, unsigned char const *p, size_t len) EXPORT_SYMBOL(crc32_le); EXPORT_SYMBOL(__crc32c_le); -u32 crc32_le_base(u32, unsigned char const *, size_t) __alias(crc32_le); -u32 __crc32c_le_base(u32, unsigned char const *, size_t) __alias(__crc32c_le); +u32 __pure crc32_le_base(u32, unsigned char const *, size_t) __alias(crc32_le); +u32 __pure __crc32c_le_base(u32, unsigned char const *, size_t) __alias(__crc32c_le); /* * This multiplies the polynomials x and y modulo the given modulus. @@ -1674,7 +1674,8 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, if (!pmd_present(pmd)) return 0; - if (unlikely(pmd_trans_huge(pmd) || pmd_huge(pmd))) { + if (unlikely(pmd_trans_huge(pmd) || pmd_huge(pmd) || + pmd_devmap(pmd))) { /* * NUMA hinting faults need to be handled in the GUP * slowpath for accounting purposes and so that they diff --git a/mm/memblock.c b/mm/memblock.c index 022d4cbb3618..ea31045ba704 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -26,6 +26,13 @@ #include "internal.h" +#define INIT_MEMBLOCK_REGIONS 128 +#define INIT_PHYSMEM_REGIONS 4 + +#ifndef INIT_MEMBLOCK_RESERVED_REGIONS +# define INIT_MEMBLOCK_RESERVED_REGIONS INIT_MEMBLOCK_REGIONS +#endif + /** * DOC: memblock overview * @@ -92,7 +99,7 @@ unsigned long max_pfn; unsigned long long max_possible_pfn; static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock; -static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock; +static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_RESERVED_REGIONS] __initdata_memblock; #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP static struct memblock_region memblock_physmem_init_regions[INIT_PHYSMEM_REGIONS] __initdata_memblock; #endif @@ -105,7 +112,7 @@ struct memblock memblock __initdata_memblock = { .reserved.regions = memblock_reserved_init_regions, .reserved.cnt = 1, /* empty dummy entry */ - .reserved.max = INIT_MEMBLOCK_REGIONS, + .reserved.max = INIT_MEMBLOCK_RESERVED_REGIONS, .reserved.name = "reserved", #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 35fdde041f5c..46285d28e43b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4675,11 +4675,11 @@ refill: /* Even if we own the page, we do not use atomic_set(). * This would break get_page_unless_zero() users. */ - page_ref_add(page, size - 1); + page_ref_add(page, size); /* reset page count bias and offset to start of new frag */ nc->pfmemalloc = page_is_pfmemalloc(page); - nc->pagecnt_bias = size; + nc->pagecnt_bias = size + 1; nc->offset = size; } @@ -4695,10 +4695,10 @@ refill: size = nc->size; #endif /* OK, page count is 0, we can safely set it */ - set_page_count(page, size); + set_page_count(page, size + 1); /* reset page count bias and offset to start of new frag */ - nc->pagecnt_bias = size; + nc->pagecnt_bias = size + 1; offset = size - fragsz; } diff --git a/mm/page_ext.c b/mm/page_ext.c index ae44f7adbe07..8c78b8d45117 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -398,10 +398,8 @@ void __init page_ext_init(void) * We know some arch can have a nodes layout such as * -------------pfn--------------> * N0 | N1 | N2 | N0 | N1 | N2|.... - * - * Take into account DEFERRED_STRUCT_PAGE_INIT. */ - if (early_pfn_to_nid(pfn) != nid) + if (pfn_to_nid(pfn) != nid) continue; if (init_section_page_ext(pfn, nid)) goto oom; diff --git a/mm/vmscan.c b/mm/vmscan.c index a714c4f800e9..e979705bbf32 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -491,16 +491,6 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, delta = freeable / 2; } - /* - * Make sure we apply some minimal pressure on default priority - * even on small cgroups. Stale objects are not only consuming memory - * by themselves, but can also hold a reference to a dying cgroup, - * preventing it from being reclaimed. A dying cgroup with all - * corresponding structures like per-cpu stats and kmem caches - * can be really big, so it may lead to a significant waste of memory. - */ - delta = max_t(unsigned long long, delta, min(freeable, batch_size)); - total_scan += delta; if (total_scan < 0) { pr_err("shrink_slab: %pF negative objects to delete nr=%ld\n", diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index b85ca809e509..ffc83bebfe40 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -227,6 +227,8 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb, switch (ntohs(ethhdr->h_proto)) { case ETH_P_8021Q: + if (!pskb_may_pull(skb, sizeof(*vhdr))) + goto dropped; vhdr = vlan_eth_hdr(skb); /* drop batman-in-batman packets to prevent loops */ diff --git a/net/core/sock.c b/net/core/sock.c index 6aa2e7e0b4fb..bc3512f230a3 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2380,7 +2380,7 @@ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind) } if (sk_has_memory_pressure(sk)) { - int alloc; + u64 alloc; if (!sk_under_memory_pressure(sk)) return 1; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 1a4e9ff02762..5731670c560b 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -108,6 +108,7 @@ static size_t inet_sk_attr_size(struct sock *sk, + nla_total_size(1) /* INET_DIAG_TOS */ + nla_total_size(1) /* INET_DIAG_TCLASS */ + nla_total_size(4) /* INET_DIAG_MARK */ + + nla_total_size(4) /* INET_DIAG_CLASS_ID */ + nla_total_size(sizeof(struct inet_diag_meminfo)) + nla_total_size(sizeof(struct inet_diag_msg)) + nla_total_size(SK_MEMINFO_VARS * sizeof(u32)) @@ -287,12 +288,19 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, goto errout; } - if (ext & (1 << (INET_DIAG_CLASS_ID - 1))) { + if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) || + ext & (1 << (INET_DIAG_TCLASS - 1))) { u32 classid = 0; #ifdef CONFIG_SOCK_CGROUP_DATA classid = sock_cgroup_classid(&sk->sk_cgrp_data); #endif + /* Fallback to socket priority if class id isn't set. + * Classful qdiscs use it as direct reference to class. + * For cgroup2 classid is always zero. + */ + if (!classid) + classid = sk->sk_priority; if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid)) goto errout; diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index d757b9642d0d..be778599bfed 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -216,6 +216,7 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base, atomic_set(&p->rid, 0); p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW; p->rate_tokens = 0; + p->n_redirects = 0; /* 60*HZ is arbitrary, but chosen enough high so that the first * calculation of tokens is at its maximum. */ diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c index 2687db015b6f..fa2ba7c500e4 100644 --- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c @@ -215,6 +215,7 @@ int nf_nat_icmp_reply_translation(struct sk_buff *skb, /* Change outer to look like the reply to an incoming packet */ nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple); + target.dst.protonum = IPPROTO_ICMP; if (!nf_nat_ipv4_manip_pkt(skb, 0, &target, manip)) return 0; diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic_main.c b/net/ipv4/netfilter/nf_nat_snmp_basic_main.c index a0aa13bcabda..0a8a60c1bf9a 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic_main.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic_main.c @@ -105,6 +105,8 @@ static void fast_csum(struct snmp_ctx *ctx, unsigned char offset) int snmp_version(void *context, size_t hdrlen, unsigned char tag, const void *data, size_t datalen) { + if (datalen != 1) + return -EINVAL; if (*(unsigned char *)data > 1) return -ENOTSUPP; return 1; @@ -114,8 +116,11 @@ int snmp_helper(void *context, size_t hdrlen, unsigned char tag, const void *data, size_t datalen) { struct snmp_ctx *ctx = (struct snmp_ctx *)context; - __be32 *pdata = (__be32 *)data; + __be32 *pdata; + if (datalen != 4) + return -EINVAL; + pdata = (__be32 *)data; if (*pdata == ctx->from) { pr_debug("%s: %pI4 to %pI4\n", __func__, (void *)&ctx->from, (void *)&ctx->to); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index ce92f73cf104..5163b64f8fb3 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -887,13 +887,15 @@ void ip_rt_send_redirect(struct sk_buff *skb) /* No redirected packets during ip_rt_redirect_silence; * reset the algorithm. */ - if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence)) + if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence)) { peer->rate_tokens = 0; + peer->n_redirects = 0; + } /* Too many ignored redirects; do not send anything * set dst.rate_last to the last seen redirected packet. */ - if (peer->rate_tokens >= ip_rt_redirect_number) { + if (peer->n_redirects >= ip_rt_redirect_number) { peer->rate_last = jiffies; goto out_put_peer; } @@ -910,6 +912,7 @@ void ip_rt_send_redirect(struct sk_buff *skb) icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw); peer->rate_last = jiffies; ++peer->rate_tokens; + ++peer->n_redirects; #ifdef CONFIG_IP_ROUTE_VERBOSE if (log_martians && peer->rate_tokens == ip_rt_redirect_number) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 84c358804355..72ffd3d760ff 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1165,7 +1165,8 @@ check_cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long *expires) list_for_each_entry(ifa, &idev->addr_list, if_list) { if (ifa == ifp) continue; - if (!ipv6_prefix_equal(&ifa->addr, &ifp->addr, + if (ifa->prefix_len != ifp->prefix_len || + !ipv6_prefix_equal(&ifa->addr, &ifp->addr, ifp->prefix_len)) continue; if (ifa->flags & (IFA_F_PERMANENT | IFA_F_NOPREFIXROUTE)) diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c index 23022447eb49..7a41ee3c11b4 100644 --- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -226,6 +226,7 @@ int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, } nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple); + target.dst.protonum = IPPROTO_ICMPV6; if (!nf_nat_ipv6_manip_pkt(skb, 0, &target, manip)) return 0; diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 8d0ba757a46c..9b2f272ca164 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -221,9 +221,7 @@ static int seg6_genl_get_tunsrc(struct sk_buff *skb, struct genl_info *info) rcu_read_unlock(); genlmsg_end(msg, hdr); - genlmsg_reply(msg, info); - - return 0; + return genlmsg_reply(msg, info); nla_put_failure: rcu_read_unlock(); diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 69e831bc317b..54821fb1a960 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -8,7 +8,7 @@ * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2007-2010, Intel Corporation * Copyright(c) 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018 Intel Corporation + * Copyright (C) 2018 - 2019 Intel Corporation * * 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 @@ -366,6 +366,8 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, set_bit(HT_AGG_STATE_STOPPING, &tid_tx->state); + ieee80211_agg_stop_txq(sta, tid); + spin_unlock_bh(&sta->lock); ht_dbg(sta->sdata, "Tx BA session stop requested for %pM tid %u\n", diff --git a/net/mac80211/util.c b/net/mac80211/util.c index d0eb38b890aa..ba950ae974fc 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -5,7 +5,7 @@ * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018 Intel Corporation + * Copyright (C) 2018-2019 Intel Corporation * * 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 @@ -2146,6 +2146,10 @@ int ieee80211_reconfig(struct ieee80211_local *local) case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_MONITOR: break; + case NL80211_IFTYPE_ADHOC: + if (sdata->vif.bss_conf.ibss_joined) + WARN_ON(drv_join_ibss(local, sdata)); + /* fall through */ default: ieee80211_reconfig_stations(sdata); /* fall through */ diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig index cad48d07c818..8401cefd9f65 100644 --- a/net/netfilter/ipvs/Kconfig +++ b/net/netfilter/ipvs/Kconfig @@ -29,6 +29,7 @@ config IP_VS_IPV6 bool "IPv6 support for IPVS" depends on IPV6 = y || IP_VS = IPV6 select IP6_NF_IPTABLES + select NF_DEFRAG_IPV6 ---help--- Add IPv6 support to IPVS. diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index fe9abf3cc10a..235205c93e14 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1536,14 +1536,12 @@ ip_vs_try_to_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, /* sorry, all this trouble for a no-hit :) */ IP_VS_DBG_PKT(12, af, pp, skb, iph->off, "ip_vs_in: packet continues traversal as normal"); - if (iph->fragoffs) { - /* Fragment that couldn't be mapped to a conn entry - * is missing module nf_defrag_ipv6 - */ - IP_VS_DBG_RL("Unhandled frag, load nf_defrag_ipv6\n"); + + /* Fragment couldn't be mapped to a conn entry */ + if (iph->fragoffs) IP_VS_DBG_PKT(7, af, pp, skb, iph->off, "unhandled fragment"); - } + *verdict = NF_ACCEPT; return 0; } diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 7d6318664eb2..86afacb07e5f 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -43,6 +43,7 @@ #ifdef CONFIG_IP_VS_IPV6 #include <net/ipv6.h> #include <net/ip6_route.h> +#include <net/netfilter/ipv6/nf_defrag_ipv6.h> #endif #include <net/route.h> #include <net/sock.h> @@ -895,6 +896,7 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest, { struct ip_vs_dest *dest; unsigned int atype, i; + int ret = 0; EnterFunction(2); @@ -905,6 +907,10 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest, atype & IPV6_ADDR_LINKLOCAL) && !__ip_vs_addr_is_local_v6(svc->ipvs->net, &udest->addr.in6)) return -EINVAL; + + ret = nf_defrag_ipv6_enable(svc->ipvs->net); + if (ret) + return ret; } else #endif { @@ -1228,6 +1234,10 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u, ret = -EINVAL; goto out_err; } + + ret = nf_defrag_ipv6_enable(ipvs->net); + if (ret) + goto out_err; } #endif diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index fe64df848365..0a4bad55a8aa 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -315,6 +315,7 @@ nft_target_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct xt_target *target = expr->ops->data; void *info = nft_expr_priv(expr); + struct module *me = target->me; struct xt_tgdtor_param par; par.net = ctx->net; @@ -325,7 +326,7 @@ nft_target_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) par.target->destroy(&par); if (nft_xt_put(container_of(expr->ops, struct nft_xt, ops))) - module_put(target->me); + module_put(me); } static int nft_extension_dump_info(struct sk_buff *skb, int attr, diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index aecadd471e1d..13e1ac333fa4 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1899,7 +1899,7 @@ static int __init xt_init(void) seqcount_init(&per_cpu(xt_recseq, i)); } - xt = kmalloc_array(NFPROTO_NUMPROTO, sizeof(struct xt_af), GFP_KERNEL); + xt = kcalloc(NFPROTO_NUMPROTO, sizeof(struct xt_af), GFP_KERNEL); if (!xt) return -ENOMEM; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 3b1a78906bc0..1cd1d83a4be0 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -4292,7 +4292,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, rb->frames_per_block = req->tp_block_size / req->tp_frame_size; if (unlikely(rb->frames_per_block == 0)) goto out; - if (unlikely(req->tp_block_size > UINT_MAX / req->tp_block_nr)) + if (unlikely(rb->frames_per_block > UINT_MAX / req->tp_block_nr)) goto out; if (unlikely((rb->frames_per_block * req->tp_block_nr) != req->tp_frame_nr)) diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index 9ccc93f257db..38bb882bb958 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -48,7 +48,7 @@ struct tcindex_data { u32 hash; /* hash table size; 0 if undefined */ u32 alloc_hash; /* allocated size */ u32 fall_through; /* 0: only classify if explicit match */ - struct rcu_head rcu; + struct rcu_work rwork; }; static inline int tcindex_filter_is_set(struct tcindex_filter_result *r) @@ -221,17 +221,11 @@ found: return 0; } -static int tcindex_destroy_element(struct tcf_proto *tp, - void *arg, struct tcf_walker *walker) -{ - bool last; - - return tcindex_delete(tp, arg, &last, NULL); -} - -static void __tcindex_destroy(struct rcu_head *head) +static void tcindex_destroy_work(struct work_struct *work) { - struct tcindex_data *p = container_of(head, struct tcindex_data, rcu); + struct tcindex_data *p = container_of(to_rcu_work(work), + struct tcindex_data, + rwork); kfree(p->perfect); kfree(p->h); @@ -258,9 +252,11 @@ static int tcindex_filter_result_init(struct tcindex_filter_result *r) return tcf_exts_init(&r->exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); } -static void __tcindex_partial_destroy(struct rcu_head *head) +static void tcindex_partial_destroy_work(struct work_struct *work) { - struct tcindex_data *p = container_of(head, struct tcindex_data, rcu); + struct tcindex_data *p = container_of(to_rcu_work(work), + struct tcindex_data, + rwork); kfree(p->perfect); kfree(p); @@ -275,7 +271,7 @@ static void tcindex_free_perfect_hash(struct tcindex_data *cp) kfree(cp->perfect); } -static int tcindex_alloc_perfect_hash(struct tcindex_data *cp) +static int tcindex_alloc_perfect_hash(struct net *net, struct tcindex_data *cp) { int i, err = 0; @@ -289,6 +285,9 @@ static int tcindex_alloc_perfect_hash(struct tcindex_data *cp) TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); if (err < 0) goto errout; +#ifdef CONFIG_NET_CLS_ACT + cp->perfect[i].exts.net = net; +#endif } return 0; @@ -305,9 +304,9 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, struct nlattr *est, bool ovr, struct netlink_ext_ack *extack) { struct tcindex_filter_result new_filter_result, *old_r = r; - struct tcindex_filter_result cr; struct tcindex_data *cp = NULL, *oldp; struct tcindex_filter *f = NULL; /* make gcc behave */ + struct tcf_result cr = {}; int err, balloc = 0; struct tcf_exts e; @@ -337,7 +336,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, if (p->perfect) { int i; - if (tcindex_alloc_perfect_hash(cp) < 0) + if (tcindex_alloc_perfect_hash(net, cp) < 0) goto errout; for (i = 0; i < cp->hash; i++) cp->perfect[i].res = p->perfect[i].res; @@ -348,11 +347,8 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, err = tcindex_filter_result_init(&new_filter_result); if (err < 0) goto errout1; - err = tcindex_filter_result_init(&cr); - if (err < 0) - goto errout1; if (old_r) - cr.res = r->res; + cr = r->res; if (tb[TCA_TCINDEX_HASH]) cp->hash = nla_get_u32(tb[TCA_TCINDEX_HASH]); @@ -406,7 +402,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, err = -ENOMEM; if (!cp->perfect && !cp->h) { if (valid_perfect_hash(cp)) { - if (tcindex_alloc_perfect_hash(cp) < 0) + if (tcindex_alloc_perfect_hash(net, cp) < 0) goto errout_alloc; balloc = 1; } else { @@ -443,8 +439,8 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, } if (tb[TCA_TCINDEX_CLASSID]) { - cr.res.classid = nla_get_u32(tb[TCA_TCINDEX_CLASSID]); - tcf_bind_filter(tp, &cr.res, base); + cr.classid = nla_get_u32(tb[TCA_TCINDEX_CLASSID]); + tcf_bind_filter(tp, &cr, base); } if (old_r && old_r != r) { @@ -456,7 +452,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, } oldp = p; - r->res = cr.res; + r->res = cr; tcf_exts_change(&r->exts, &e); rcu_assign_pointer(tp->root, cp); @@ -475,10 +471,12 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, ; /* nothing */ rcu_assign_pointer(*fp, f); + } else { + tcf_exts_destroy(&new_filter_result.exts); } if (oldp) - call_rcu(&oldp->rcu, __tcindex_partial_destroy); + tcf_queue_work(&oldp->rwork, tcindex_partial_destroy_work); return 0; errout_alloc: @@ -487,7 +485,6 @@ errout_alloc: else if (balloc == 2) kfree(cp->h); errout1: - tcf_exts_destroy(&cr.exts); tcf_exts_destroy(&new_filter_result.exts); errout: kfree(cp); @@ -562,15 +559,34 @@ static void tcindex_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct tcindex_data *p = rtnl_dereference(tp->root); - struct tcf_walker walker; + int i; pr_debug("tcindex_destroy(tp %p),p %p\n", tp, p); - walker.count = 0; - walker.skip = 0; - walker.fn = tcindex_destroy_element; - tcindex_walk(tp, &walker); - call_rcu(&p->rcu, __tcindex_destroy); + if (p->perfect) { + for (i = 0; i < p->hash; i++) { + struct tcindex_filter_result *r = p->perfect + i; + + tcf_unbind_filter(tp, &r->res); + if (tcf_exts_get_net(&r->exts)) + tcf_queue_work(&r->rwork, + tcindex_destroy_rexts_work); + else + __tcindex_destroy_rexts(r); + } + } + + for (i = 0; p->h && i < p->hash; i++) { + struct tcindex_filter *f, *next; + bool last; + + for (f = rtnl_dereference(p->h[i]); f; f = next) { + next = rtnl_dereference(f->next); + tcindex_delete(tp, &f->result, &last, NULL); + } + } + + tcf_queue_work(&p->rwork, tcindex_destroy_work); } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 66ba2ce2320f..968a85fe4d4a 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -500,7 +500,7 @@ static void dev_watchdog_down(struct net_device *dev) * netif_carrier_on - set carrier * @dev: network device * - * Device has detected that carrier. + * Device has detected acquisition of carrier. */ void netif_carrier_on(struct net_device *dev) { diff --git a/net/sctp/diag.c b/net/sctp/diag.c index 078f01a8d582..435847d98b51 100644 --- a/net/sctp/diag.c +++ b/net/sctp/diag.c @@ -256,6 +256,7 @@ static size_t inet_assoc_attr_size(struct sctp_association *asoc) + nla_total_size(1) /* INET_DIAG_TOS */ + nla_total_size(1) /* INET_DIAG_TCLASS */ + nla_total_size(4) /* INET_DIAG_MARK */ + + nla_total_size(4) /* INET_DIAG_CLASS_ID */ + nla_total_size(addrlen * asoc->peer.transport_count) + nla_total_size(addrlen * addrcnt) + nla_total_size(sizeof(struct inet_diag_meminfo)) diff --git a/net/sctp/offload.c b/net/sctp/offload.c index 123e9f2dc226..edfcf16e704c 100644 --- a/net/sctp/offload.c +++ b/net/sctp/offload.c @@ -36,6 +36,7 @@ static __le32 sctp_gso_make_checksum(struct sk_buff *skb) { skb->ip_summed = CHECKSUM_NONE; skb->csum_not_inet = 0; + gso_reset_checksum(skb, ~0); return sctp_compute_cksum(skb, skb_transport_offset(skb)); } diff --git a/net/sctp/stream.c b/net/sctp/stream.c index f24633114dfd..2936ed17bf9e 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -144,8 +144,10 @@ static void sctp_stream_outq_migrate(struct sctp_stream *stream, } } - for (i = outcnt; i < stream->outcnt; i++) + for (i = outcnt; i < stream->outcnt; i++) { kfree(SCTP_SO(stream, i)->ext); + SCTP_SO(stream, i)->ext = NULL; + } } static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt, diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index a712c9f8699b..fb07ad8d69a6 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -101,9 +101,7 @@ int smc_cdc_msg_send(struct smc_connection *conn, conn->tx_cdc_seq++; conn->local_tx_ctrl.seqno = conn->tx_cdc_seq; - smc_host_msg_to_cdc((struct smc_cdc_msg *)wr_buf, - &conn->local_tx_ctrl, conn); - smc_curs_copy(&cfed, &((struct smc_host_cdc_msg *)wr_buf)->cons, conn); + smc_host_msg_to_cdc((struct smc_cdc_msg *)wr_buf, conn, &cfed); rc = smc_wr_tx_send(link, (struct smc_wr_tx_pend_priv *)pend); if (!rc) smc_curs_copy(&conn->rx_curs_confirmed, &cfed, conn); diff --git a/net/smc/smc_cdc.h b/net/smc/smc_cdc.h index 271e2524dc8f..f1cdde9d4b89 100644 --- a/net/smc/smc_cdc.h +++ b/net/smc/smc_cdc.h @@ -211,26 +211,27 @@ static inline int smc_curs_diff_large(unsigned int size, static inline void smc_host_cursor_to_cdc(union smc_cdc_cursor *peer, union smc_host_cursor *local, + union smc_host_cursor *save, struct smc_connection *conn) { - union smc_host_cursor temp; - - smc_curs_copy(&temp, local, conn); - peer->count = htonl(temp.count); - peer->wrap = htons(temp.wrap); + smc_curs_copy(save, local, conn); + peer->count = htonl(save->count); + peer->wrap = htons(save->wrap); /* peer->reserved = htons(0); must be ensured by caller */ } static inline void smc_host_msg_to_cdc(struct smc_cdc_msg *peer, - struct smc_host_cdc_msg *local, - struct smc_connection *conn) + struct smc_connection *conn, + union smc_host_cursor *save) { + struct smc_host_cdc_msg *local = &conn->local_tx_ctrl; + peer->common.type = local->common.type; peer->len = local->len; peer->seqno = htons(local->seqno); peer->token = htonl(local->token); - smc_host_cursor_to_cdc(&peer->prod, &local->prod, conn); - smc_host_cursor_to_cdc(&peer->cons, &local->cons, conn); + smc_host_cursor_to_cdc(&peer->prod, &local->prod, save, conn); + smc_host_cursor_to_cdc(&peer->cons, &local->cons, save, conn); peer->prod_flags = local->prod_flags; peer->conn_state_flags = local->conn_state_flags; } diff --git a/net/sunrpc/auth_gss/gss_krb5_seqnum.c b/net/sunrpc/auth_gss/gss_krb5_seqnum.c index fb6656295204..507105127095 100644 --- a/net/sunrpc/auth_gss/gss_krb5_seqnum.c +++ b/net/sunrpc/auth_gss/gss_krb5_seqnum.c @@ -44,7 +44,7 @@ krb5_make_rc4_seq_num(struct krb5_ctx *kctx, int direction, s32 seqnum, unsigned char *cksum, unsigned char *buf) { struct crypto_sync_skcipher *cipher; - unsigned char plain[8]; + unsigned char *plain; s32 code; dprintk("RPC: %s:\n", __func__); @@ -52,6 +52,10 @@ krb5_make_rc4_seq_num(struct krb5_ctx *kctx, int direction, s32 seqnum, if (IS_ERR(cipher)) return PTR_ERR(cipher); + plain = kmalloc(8, GFP_NOFS); + if (!plain) + return -ENOMEM; + plain[0] = (unsigned char) ((seqnum >> 24) & 0xff); plain[1] = (unsigned char) ((seqnum >> 16) & 0xff); plain[2] = (unsigned char) ((seqnum >> 8) & 0xff); @@ -67,6 +71,7 @@ krb5_make_rc4_seq_num(struct krb5_ctx *kctx, int direction, s32 seqnum, code = krb5_encrypt(cipher, cksum, plain, buf, 8); out: + kfree(plain); crypto_free_sync_skcipher(cipher); return code; } @@ -77,12 +82,17 @@ krb5_make_seq_num(struct krb5_ctx *kctx, u32 seqnum, unsigned char *cksum, unsigned char *buf) { - unsigned char plain[8]; + unsigned char *plain; + s32 code; if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC) return krb5_make_rc4_seq_num(kctx, direction, seqnum, cksum, buf); + plain = kmalloc(8, GFP_NOFS); + if (!plain) + return -ENOMEM; + plain[0] = (unsigned char) (seqnum & 0xff); plain[1] = (unsigned char) ((seqnum >> 8) & 0xff); plain[2] = (unsigned char) ((seqnum >> 16) & 0xff); @@ -93,7 +103,9 @@ krb5_make_seq_num(struct krb5_ctx *kctx, plain[6] = direction; plain[7] = direction; - return krb5_encrypt(key, cksum, plain, buf, 8); + code = krb5_encrypt(key, cksum, plain, buf, 8); + kfree(plain); + return code; } static s32 @@ -101,7 +113,7 @@ krb5_get_rc4_seq_num(struct krb5_ctx *kctx, unsigned char *cksum, unsigned char *buf, int *direction, s32 *seqnum) { struct crypto_sync_skcipher *cipher; - unsigned char plain[8]; + unsigned char *plain; s32 code; dprintk("RPC: %s:\n", __func__); @@ -113,20 +125,28 @@ krb5_get_rc4_seq_num(struct krb5_ctx *kctx, unsigned char *cksum, if (code) goto out; + plain = kmalloc(8, GFP_NOFS); + if (!plain) { + code = -ENOMEM; + goto out; + } + code = krb5_decrypt(cipher, cksum, buf, plain, 8); if (code) - goto out; + goto out_plain; if ((plain[4] != plain[5]) || (plain[4] != plain[6]) || (plain[4] != plain[7])) { code = (s32)KG_BAD_SEQ; - goto out; + goto out_plain; } *direction = plain[4]; *seqnum = ((plain[0] << 24) | (plain[1] << 16) | (plain[2] << 8) | (plain[3])); +out_plain: + kfree(plain); out: crypto_free_sync_skcipher(cipher); return code; @@ -139,7 +159,7 @@ krb5_get_seq_num(struct krb5_ctx *kctx, int *direction, u32 *seqnum) { s32 code; - unsigned char plain[8]; + unsigned char *plain; struct crypto_sync_skcipher *key = kctx->seq; dprintk("RPC: krb5_get_seq_num:\n"); @@ -147,18 +167,25 @@ krb5_get_seq_num(struct krb5_ctx *kctx, if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC) return krb5_get_rc4_seq_num(kctx, cksum, buf, direction, seqnum); + plain = kmalloc(8, GFP_NOFS); + if (!plain) + return -ENOMEM; if ((code = krb5_decrypt(key, cksum, buf, plain, 8))) - return code; + goto out; if ((plain[4] != plain[5]) || (plain[4] != plain[6]) || - (plain[4] != plain[7])) - return (s32)KG_BAD_SEQ; + (plain[4] != plain[7])) { + code = (s32)KG_BAD_SEQ; + goto out; + } *direction = plain[4]; *seqnum = ((plain[0]) | (plain[1] << 8) | (plain[2] << 16) | (plain[3] << 24)); - return 0; +out: + kfree(plain); + return code; } diff --git a/net/sunrpc/debugfs.c b/net/sunrpc/debugfs.c index 45a033329cd4..19bb356230ed 100644 --- a/net/sunrpc/debugfs.c +++ b/net/sunrpc/debugfs.c @@ -146,7 +146,7 @@ rpc_clnt_debugfs_register(struct rpc_clnt *clnt) rcu_read_lock(); xprt = rcu_dereference(clnt->cl_xprt); /* no "debugfs" dentry? Don't bother with the symlink. */ - if (!xprt->debugfs) { + if (IS_ERR_OR_NULL(xprt->debugfs)) { rcu_read_unlock(); return; } diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 4994e75945b8..21113bfd4eca 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -527,7 +527,8 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, sendcq = ib_alloc_cq(ia->ri_device, NULL, ep->rep_attr.cap.max_send_wr + 1, - 1, IB_POLL_WORKQUEUE); + ia->ri_device->num_comp_vectors > 1 ? 1 : 0, + IB_POLL_WORKQUEUE); if (IS_ERR(sendcq)) { rc = PTR_ERR(sendcq); goto out1; diff --git a/net/tipc/link.c b/net/tipc/link.c index 2792a3cae682..85ad5c0678d0 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1145,7 +1145,7 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb, default: pr_warn("Dropping received illegal msg type\n"); kfree_skb(skb); - return false; + return true; }; } @@ -1425,6 +1425,10 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, l->rcv_unacked = 0; } else { /* RESET_MSG or ACTIVATE_MSG */ + if (mtyp == ACTIVATE_MSG) { + msg_set_dest_session_valid(hdr, 1); + msg_set_dest_session(hdr, l->peer_session); + } msg_set_max_pkt(hdr, l->advertised_mtu); strcpy(data, l->if_name); msg_set_size(hdr, INT_H_SIZE + TIPC_MAX_IF_NAME); @@ -1642,6 +1646,17 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, rc = tipc_link_fsm_evt(l, LINK_FAILURE_EVT); break; } + + /* If this endpoint was re-created while peer was ESTABLISHING + * it doesn't know current session number. Force re-synch. + */ + if (mtyp == ACTIVATE_MSG && msg_dest_session_valid(hdr) && + l->session != msg_dest_session(hdr)) { + if (less(l->session, msg_dest_session(hdr))) + l->session = msg_dest_session(hdr) + 1; + break; + } + /* ACTIVATE_MSG serves as PEER_RESET if link is already down */ if (mtyp == RESET_MSG || !link_is_up(l)) rc = tipc_link_fsm_evt(l, LINK_PEER_RESET_EVT); diff --git a/net/tipc/msg.h b/net/tipc/msg.h index a0924956bb61..d7e4b8b93f9d 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -360,6 +360,28 @@ static inline void msg_set_bcast_ack(struct tipc_msg *m, u16 n) msg_set_bits(m, 1, 0, 0xffff, n); } +/* Note: reusing bits in word 1 for ACTIVATE_MSG only, to re-synch + * link peer session number + */ +static inline bool msg_dest_session_valid(struct tipc_msg *m) +{ + return msg_bits(m, 1, 16, 0x1); +} + +static inline void msg_set_dest_session_valid(struct tipc_msg *m, bool valid) +{ + msg_set_bits(m, 1, 16, 0x1, valid); +} + +static inline u16 msg_dest_session(struct tipc_msg *m) +{ + return msg_bits(m, 1, 0, 0xffff); +} + +static inline void msg_set_dest_session(struct tipc_msg *m, u16 n) +{ + msg_set_bits(m, 1, 0, 0xffff, n); +} /* * Word 2 diff --git a/net/tipc/node.c b/net/tipc/node.c index db2a6c3e0be9..2dc4919ab23c 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -830,15 +830,16 @@ static void tipc_node_link_down(struct tipc_node *n, int bearer_id, bool delete) tipc_node_write_lock(n); if (!tipc_link_is_establishing(l)) { __tipc_node_link_down(n, &bearer_id, &xmitq, &maddr); - if (delete) { - kfree(l); - le->link = NULL; - n->link_cnt--; - } } else { /* Defuse pending tipc_node_link_up() */ + tipc_link_reset(l); tipc_link_fsm_evt(l, LINK_RESET_EVT); } + if (delete) { + kfree(l); + le->link = NULL; + n->link_cnt--; + } trace_tipc_node_link_down(n, true, "node link down or deleted!"); tipc_node_write_unlock(n); if (delete) diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index c361ce782412..c3d5ab01fba7 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -1651,6 +1651,10 @@ static void vmci_transport_cleanup(struct work_struct *work) static void vmci_transport_destruct(struct vsock_sock *vsk) { + /* transport can be NULL if we hit a failure at init() time */ + if (!vmci_trans(vsk)) + return; + /* Ensure that the detach callback doesn't use the sk/vsk * we are about to destruct. */ diff --git a/net/wireless/core.c b/net/wireless/core.c index 623dfe5e211c..b36ad8efb5e5 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1068,6 +1068,8 @@ static void __cfg80211_unregister_wdev(struct wireless_dev *wdev, bool sync) ASSERT_RTNL(); + flush_work(&wdev->pmsr_free_wk); + nl80211_notify_iface(rdev, wdev, NL80211_CMD_DEL_INTERFACE); list_del_rcu(&wdev->list); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 74150ad95823..d91a408db113 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -250,7 +250,7 @@ nl80211_pmsr_ftm_req_attr_policy[NL80211_PMSR_FTM_REQ_ATTR_MAX + 1] = { [NL80211_PMSR_FTM_REQ_ATTR_BURST_DURATION] = NLA_POLICY_MAX(NLA_U8, 15), [NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST] = - NLA_POLICY_MAX(NLA_U8, 15), + NLA_POLICY_MAX(NLA_U8, 31), [NL80211_PMSR_FTM_REQ_ATTR_NUM_FTMR_RETRIES] = { .type = NLA_U8 }, [NL80211_PMSR_FTM_REQ_ATTR_REQUEST_LCI] = { .type = NLA_FLAG }, [NL80211_PMSR_FTM_REQ_ATTR_REQUEST_CIVICLOC] = { .type = NLA_FLAG }, diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c index de9286703280..0216ab555249 100644 --- a/net/wireless/pmsr.c +++ b/net/wireless/pmsr.c @@ -256,8 +256,7 @@ int nl80211_pmsr_start(struct sk_buff *skb, struct genl_info *info) if (err) goto out_err; } else { - memcpy(req->mac_addr, nla_data(info->attrs[NL80211_ATTR_MAC]), - ETH_ALEN); + memcpy(req->mac_addr, wdev_address(wdev), ETH_ALEN); memset(req->mac_addr_mask, 0xff, ETH_ALEN); } @@ -272,6 +271,7 @@ int nl80211_pmsr_start(struct sk_buff *skb, struct genl_info *info) req->n_peers = count; req->cookie = cfg80211_assign_cookie(rdev); + req->nl_portid = info->snd_portid; err = rdev_start_pmsr(rdev, wdev, req); if (err) @@ -530,14 +530,14 @@ free: } EXPORT_SYMBOL_GPL(cfg80211_pmsr_report); -void cfg80211_pmsr_free_wk(struct work_struct *work) +static void cfg80211_pmsr_process_abort(struct wireless_dev *wdev) { - struct wireless_dev *wdev = container_of(work, struct wireless_dev, - pmsr_free_wk); struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_pmsr_request *req, *tmp; LIST_HEAD(free_list); + lockdep_assert_held(&wdev->mtx); + spin_lock_bh(&wdev->pmsr_lock); list_for_each_entry_safe(req, tmp, &wdev->pmsr_list, list) { if (req->nl_portid) @@ -547,14 +547,22 @@ void cfg80211_pmsr_free_wk(struct work_struct *work) spin_unlock_bh(&wdev->pmsr_lock); list_for_each_entry_safe(req, tmp, &free_list, list) { - wdev_lock(wdev); rdev_abort_pmsr(rdev, wdev, req); - wdev_unlock(wdev); kfree(req); } } +void cfg80211_pmsr_free_wk(struct work_struct *work) +{ + struct wireless_dev *wdev = container_of(work, struct wireless_dev, + pmsr_free_wk); + + wdev_lock(wdev); + cfg80211_pmsr_process_abort(wdev); + wdev_unlock(wdev); +} + void cfg80211_pmsr_wdev_down(struct wireless_dev *wdev) { struct cfg80211_pmsr_request *req; @@ -568,8 +576,8 @@ void cfg80211_pmsr_wdev_down(struct wireless_dev *wdev) spin_unlock_bh(&wdev->pmsr_lock); if (found) - schedule_work(&wdev->pmsr_free_wk); - flush_work(&wdev->pmsr_free_wk); + cfg80211_pmsr_process_abort(wdev); + WARN_ON(!list_empty(&wdev->pmsr_list)); } diff --git a/net/wireless/util.c b/net/wireless/util.c index cd48cdd582c0..ec30e3732c7b 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -5,7 +5,7 @@ * Copyright 2007-2009 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2017 Intel Deutschland GmbH - * Copyright (C) 2018 Intel Corporation + * Copyright (C) 2018-2019 Intel Corporation */ #include <linux/export.h> #include <linux/bitops.h> @@ -19,6 +19,7 @@ #include <linux/mpls.h> #include <linux/gcd.h> #include <linux/bitfield.h> +#include <linux/nospec.h> #include "core.h" #include "rdev-ops.h" @@ -715,20 +716,25 @@ unsigned int cfg80211_classify8021d(struct sk_buff *skb, { unsigned int dscp; unsigned char vlan_priority; + unsigned int ret; /* skb->priority values from 256->263 are magic values to * directly indicate a specific 802.1d priority. This is used * to allow 802.1d priority to be passed directly in from VLAN * tags, etc. */ - if (skb->priority >= 256 && skb->priority <= 263) - return skb->priority - 256; + if (skb->priority >= 256 && skb->priority <= 263) { + ret = skb->priority - 256; + goto out; + } if (skb_vlan_tag_present(skb)) { vlan_priority = (skb_vlan_tag_get(skb) & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; - if (vlan_priority > 0) - return vlan_priority; + if (vlan_priority > 0) { + ret = vlan_priority; + goto out; + } } switch (skb->protocol) { @@ -747,8 +753,9 @@ unsigned int cfg80211_classify8021d(struct sk_buff *skb, if (!mpls) return 0; - return (ntohl(mpls->entry) & MPLS_LS_TC_MASK) + ret = (ntohl(mpls->entry) & MPLS_LS_TC_MASK) >> MPLS_LS_TC_SHIFT; + goto out; } case htons(ETH_P_80221): /* 802.21 is always network control traffic */ @@ -761,18 +768,24 @@ unsigned int cfg80211_classify8021d(struct sk_buff *skb, unsigned int i, tmp_dscp = dscp >> 2; for (i = 0; i < qos_map->num_des; i++) { - if (tmp_dscp == qos_map->dscp_exception[i].dscp) - return qos_map->dscp_exception[i].up; + if (tmp_dscp == qos_map->dscp_exception[i].dscp) { + ret = qos_map->dscp_exception[i].up; + goto out; + } } for (i = 0; i < 8; i++) { if (tmp_dscp >= qos_map->up[i].low && - tmp_dscp <= qos_map->up[i].high) - return i; + tmp_dscp <= qos_map->up[i].high) { + ret = i; + goto out; + } } } - return dscp >> 5; + ret = dscp >> 5; +out: + return array_index_nospec(ret, IEEE80211_NUM_TIDS); } EXPORT_SYMBOL(cfg80211_classify8021d); diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 5121729b8b63..ec3a828672ef 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -352,17 +352,15 @@ static unsigned int x25_new_lci(struct x25_neigh *nb) unsigned int lci = 1; struct sock *sk; - read_lock_bh(&x25_list_lock); - - while ((sk = __x25_find_socket(lci, nb)) != NULL) { + while ((sk = x25_find_socket(lci, nb)) != NULL) { sock_put(sk); if (++lci == 4096) { lci = 0; break; } + cond_resched(); } - read_unlock_bh(&x25_list_lock); return lci; } diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index 6c99fa8ac5fa..6c0b30391ba9 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -2112,13 +2112,6 @@ int pcm_lib_apply_appl_ptr(struct snd_pcm_substream *substream, return 0; } -/* allow waiting for a capture stream that hasn't been started */ -#if IS_ENABLED(CONFIG_SND_PCM_OSS) -#define wait_capture_start(substream) ((substream)->oss.oss) -#else -#define wait_capture_start(substream) false -#endif - /* the common loop for read/write data */ snd_pcm_sframes_t __snd_pcm_lib_xfer(struct snd_pcm_substream *substream, void *data, bool interleaved, @@ -2184,16 +2177,11 @@ snd_pcm_sframes_t __snd_pcm_lib_xfer(struct snd_pcm_substream *substream, snd_pcm_update_hw_ptr(substream); if (!is_playback && - runtime->status->state == SNDRV_PCM_STATE_PREPARED) { - if (size >= runtime->start_threshold) { - err = snd_pcm_start(substream); - if (err < 0) - goto _end_unlock; - } else if (!wait_capture_start(substream)) { - /* nothing to do */ - err = 0; + runtime->status->state == SNDRV_PCM_STATE_PREPARED && + size >= runtime->start_threshold) { + err = snd_pcm_start(substream); + if (err < 0) goto _end_unlock; - } } avail = snd_pcm_avail(substream); diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index 152f54137082..a4ee7656d9ee 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -924,6 +924,7 @@ static const struct snd_pci_quirk cxt5066_fixups[] = { SND_PCI_QUIRK(0x103c, 0x807C, "HP EliteBook 820 G3", CXT_FIXUP_HP_DOCK), SND_PCI_QUIRK(0x103c, 0x80FD, "HP ProBook 640 G2", CXT_FIXUP_HP_DOCK), SND_PCI_QUIRK(0x103c, 0x828c, "HP EliteBook 840 G4", CXT_FIXUP_HP_DOCK), + SND_PCI_QUIRK(0x103c, 0x83b2, "HP EliteBook 840 G5", CXT_FIXUP_HP_DOCK), SND_PCI_QUIRK(0x103c, 0x83b3, "HP EliteBook 830 G5", CXT_FIXUP_HP_DOCK), SND_PCI_QUIRK(0x103c, 0x83d3, "HP ProBook 640 G4", CXT_FIXUP_HP_DOCK), SND_PCI_QUIRK(0x103c, 0x8174, "HP Spectre x360", CXT_FIXUP_HP_SPECTRE), diff --git a/sound/soc/codecs/hdmi-codec.c b/sound/soc/codecs/hdmi-codec.c index d00734d31e04..e5b6769b9797 100644 --- a/sound/soc/codecs/hdmi-codec.c +++ b/sound/soc/codecs/hdmi-codec.c @@ -795,6 +795,8 @@ static int hdmi_codec_probe(struct platform_device *pdev) if (hcd->spdif) hcp->daidrv[i] = hdmi_spdif_dai; + dev_set_drvdata(dev, hcp); + ret = devm_snd_soc_register_component(dev, &hdmi_driver, hcp->daidrv, dai_count); if (ret) { @@ -802,8 +804,6 @@ static int hdmi_codec_probe(struct platform_device *pdev) __func__, ret); return ret; } - - dev_set_drvdata(dev, hcp); return 0; } diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c index 89c43b26c379..a9b91bcfcc09 100644 --- a/sound/soc/codecs/rt5682.c +++ b/sound/soc/codecs/rt5682.c @@ -1778,7 +1778,9 @@ static const struct snd_soc_dapm_route rt5682_dapm_routes[] = { {"ADC Stereo1 Filter", NULL, "ADC STO1 ASRC", is_using_asrc}, {"DAC Stereo1 Filter", NULL, "DAC STO1 ASRC", is_using_asrc}, {"ADC STO1 ASRC", NULL, "AD ASRC"}, + {"ADC STO1 ASRC", NULL, "DA ASRC"}, {"ADC STO1 ASRC", NULL, "CLKDET"}, + {"DAC STO1 ASRC", NULL, "AD ASRC"}, {"DAC STO1 ASRC", NULL, "DA ASRC"}, {"DAC STO1 ASRC", NULL, "CLKDET"}, diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c index d6c62aa13041..ce00fe2f6aae 100644 --- a/sound/soc/samsung/i2s.c +++ b/sound/soc/samsung/i2s.c @@ -700,6 +700,7 @@ static int i2s_hw_params(struct snd_pcm_substream *substream, { struct i2s_dai *i2s = to_info(dai); u32 mod, mask = 0, val = 0; + struct clk *rclksrc; unsigned long flags; WARN_ON(!pm_runtime_active(dai->dev)); @@ -782,6 +783,10 @@ static int i2s_hw_params(struct snd_pcm_substream *substream, i2s->frmclk = params_rate(params); + rclksrc = i2s->clk_table[CLK_I2S_RCLK_SRC]; + if (rclksrc && !IS_ERR(rclksrc)) + i2s->rclk_srcrate = clk_get_rate(rclksrc); + return 0; } @@ -886,11 +891,6 @@ static int config_setup(struct i2s_dai *i2s) return 0; if (!(i2s->quirks & QUIRK_NO_MUXPSR)) { - struct clk *rclksrc = i2s->clk_table[CLK_I2S_RCLK_SRC]; - - if (rclksrc && !IS_ERR(rclksrc)) - i2s->rclk_srcrate = clk_get_rate(rclksrc); - psr = i2s->rclk_srcrate / i2s->frmclk / rfs; writel(((psr - 1) << 8) | PSR_PSREN, i2s->addr + I2SPSR); dev_dbg(&i2s->pdev->dev, diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c index 59e250cc2e9d..e819e965e1db 100644 --- a/sound/soc/sh/rcar/core.c +++ b/sound/soc/sh/rcar/core.c @@ -1526,14 +1526,14 @@ int rsnd_kctrl_new(struct rsnd_mod *mod, int ret; /* - * 1) Avoid duplicate register (ex. MIXer case) - * 2) re-register if card was rebinded + * 1) Avoid duplicate register for DVC with MIX case + * 2) Allow duplicate register for MIX + * 3) re-register if card was rebinded */ list_for_each_entry(kctrl, &card->controls, list) { struct rsnd_kctrl_cfg *c = kctrl->private_data; - if (strcmp(kctrl->id.name, name) == 0 && - c->mod == mod) + if (c == cfg) return 0; } diff --git a/sound/soc/sh/rcar/ssi.c b/sound/soc/sh/rcar/ssi.c index 45ef295743ec..f5afab631abb 100644 --- a/sound/soc/sh/rcar/ssi.c +++ b/sound/soc/sh/rcar/ssi.c @@ -286,7 +286,7 @@ static int rsnd_ssi_master_clk_start(struct rsnd_mod *mod, if (rsnd_ssi_is_multi_slave(mod, io)) return 0; - if (ssi->usrcnt > 1) { + if (ssi->usrcnt > 0) { if (ssi->rate != rate) { dev_err(dev, "SSI parent/child should use same rate\n"); return -EINVAL; diff --git a/sound/soc/sh/rcar/ssiu.c b/sound/soc/sh/rcar/ssiu.c index c5934adcfd01..c74991dd18ab 100644 --- a/sound/soc/sh/rcar/ssiu.c +++ b/sound/soc/sh/rcar/ssiu.c @@ -79,7 +79,7 @@ static int rsnd_ssiu_init(struct rsnd_mod *mod, break; case 9: for (i = 0; i < 4; i++) - rsnd_mod_write(mod, SSI_SYS_STATUS((i * 2) + 1), 0xf << (id * 4)); + rsnd_mod_write(mod, SSI_SYS_STATUS((i * 2) + 1), 0xf << 4); break; } diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index aae450ba4f08..50617db05c46 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -735,12 +735,17 @@ static struct snd_soc_component *soc_find_component( const struct device_node *of_node, const char *name) { struct snd_soc_component *component; + struct device_node *component_of_node; lockdep_assert_held(&client_mutex); for_each_component(component) { if (of_node) { - if (component->dev->of_node == of_node) + component_of_node = component->dev->of_node; + if (!component_of_node && component->dev->parent) + component_of_node = component->dev->parent->of_node; + + if (component_of_node == of_node) return component; } else if (name && strcmp(component->name, name) == 0) { return component; @@ -951,7 +956,7 @@ static void soc_remove_dai(struct snd_soc_dai *dai, int order) { int err; - if (!dai || !dai->probed || + if (!dai || !dai->probed || !dai->driver || dai->driver->remove_order != order) return; diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index 2c4c13419539..20bad755888b 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -70,12 +70,16 @@ static int dapm_up_seq[] = { [snd_soc_dapm_clock_supply] = 1, [snd_soc_dapm_supply] = 2, [snd_soc_dapm_micbias] = 3, + [snd_soc_dapm_vmid] = 3, [snd_soc_dapm_dai_link] = 2, [snd_soc_dapm_dai_in] = 4, [snd_soc_dapm_dai_out] = 4, [snd_soc_dapm_aif_in] = 4, [snd_soc_dapm_aif_out] = 4, [snd_soc_dapm_mic] = 5, + [snd_soc_dapm_siggen] = 5, + [snd_soc_dapm_input] = 5, + [snd_soc_dapm_output] = 5, [snd_soc_dapm_mux] = 6, [snd_soc_dapm_demux] = 6, [snd_soc_dapm_dac] = 7, @@ -83,11 +87,19 @@ static int dapm_up_seq[] = { [snd_soc_dapm_mixer] = 8, [snd_soc_dapm_mixer_named_ctl] = 8, [snd_soc_dapm_pga] = 9, + [snd_soc_dapm_buffer] = 9, + [snd_soc_dapm_scheduler] = 9, + [snd_soc_dapm_effect] = 9, + [snd_soc_dapm_src] = 9, + [snd_soc_dapm_asrc] = 9, + [snd_soc_dapm_encoder] = 9, + [snd_soc_dapm_decoder] = 9, [snd_soc_dapm_adc] = 10, [snd_soc_dapm_out_drv] = 11, [snd_soc_dapm_hp] = 11, [snd_soc_dapm_spk] = 11, [snd_soc_dapm_line] = 11, + [snd_soc_dapm_sink] = 11, [snd_soc_dapm_kcontrol] = 12, [snd_soc_dapm_post] = 13, }; @@ -100,13 +112,25 @@ static int dapm_down_seq[] = { [snd_soc_dapm_spk] = 3, [snd_soc_dapm_line] = 3, [snd_soc_dapm_out_drv] = 3, + [snd_soc_dapm_sink] = 3, [snd_soc_dapm_pga] = 4, + [snd_soc_dapm_buffer] = 4, + [snd_soc_dapm_scheduler] = 4, + [snd_soc_dapm_effect] = 4, + [snd_soc_dapm_src] = 4, + [snd_soc_dapm_asrc] = 4, + [snd_soc_dapm_encoder] = 4, + [snd_soc_dapm_decoder] = 4, [snd_soc_dapm_switch] = 5, [snd_soc_dapm_mixer_named_ctl] = 5, [snd_soc_dapm_mixer] = 5, [snd_soc_dapm_dac] = 6, [snd_soc_dapm_mic] = 7, + [snd_soc_dapm_siggen] = 7, + [snd_soc_dapm_input] = 7, + [snd_soc_dapm_output] = 7, [snd_soc_dapm_micbias] = 8, + [snd_soc_dapm_vmid] = 8, [snd_soc_dapm_mux] = 9, [snd_soc_dapm_demux] = 9, [snd_soc_dapm_aif_in] = 10, diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index 045ef136903d..fc79ec6927e3 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -502,6 +502,7 @@ static void remove_dai(struct snd_soc_component *comp, { struct snd_soc_dai_driver *dai_drv = container_of(dobj, struct snd_soc_dai_driver, dobj); + struct snd_soc_dai *dai; if (pass != SOC_TPLG_PASS_PCM_DAI) return; @@ -509,6 +510,10 @@ static void remove_dai(struct snd_soc_component *comp, if (dobj->ops && dobj->ops->dai_unload) dobj->ops->dai_unload(comp, dobj); + list_for_each_entry(dai, &comp->dai_list, list) + if (dai->driver == dai_drv) + dai->driver = NULL; + kfree(dai_drv->name); list_del(&dobj->list); kfree(dai_drv); diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index 382847154227..db114f3977e0 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -314,6 +314,9 @@ static int search_roland_implicit_fb(struct usb_device *dev, int ifnum, return 0; } +/* Setup an implicit feedback endpoint from a quirk. Returns 0 if no quirk + * applies. Returns 1 if a quirk was found. + */ static int set_sync_ep_implicit_fb_quirk(struct snd_usb_substream *subs, struct usb_device *dev, struct usb_interface_descriptor *altsd, @@ -384,7 +387,7 @@ add_sync_ep: subs->data_endpoint->sync_master = subs->sync_endpoint; - return 0; + return 1; } static int set_sync_endpoint(struct snd_usb_substream *subs, @@ -423,6 +426,10 @@ static int set_sync_endpoint(struct snd_usb_substream *subs, if (err < 0) return err; + /* endpoint set by quirk */ + if (err > 0) + return 0; + if (altsd->bNumEndpoints < 2) return 0; diff --git a/tools/include/uapi/asm/bitsperlong.h b/tools/include/uapi/asm/bitsperlong.h index fd92ce8388fc..57aaeaf8e192 100644 --- a/tools/include/uapi/asm/bitsperlong.h +++ b/tools/include/uapi/asm/bitsperlong.h @@ -15,6 +15,8 @@ #include "../../arch/ia64/include/uapi/asm/bitsperlong.h" #elif defined(__riscv) #include "../../arch/riscv/include/uapi/asm/bitsperlong.h" +#elif defined(__alpha__) +#include "../../arch/alpha/include/uapi/asm/bitsperlong.h" #else #include <asm-generic/bitsperlong.h> #endif diff --git a/tools/testing/selftests/networking/timestamping/Makefile b/tools/testing/selftests/networking/timestamping/Makefile index 9050eeea5f5f..1de8bd8ccf5d 100644 --- a/tools/testing/selftests/networking/timestamping/Makefile +++ b/tools/testing/selftests/networking/timestamping/Makefile @@ -9,6 +9,3 @@ all: $(TEST_PROGS) top_srcdir = ../../../../.. KSFT_KHDR_INSTALL := 1 include ../../lib.mk - -clean: - rm -fr $(TEST_GEN_FILES) diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index 9e350fd34504..9c486fad3f9f 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -626,6 +626,13 @@ static void vcpu_req_sleep(struct kvm_vcpu *vcpu) /* Awaken to handle a signal, request we sleep again later. */ kvm_make_request(KVM_REQ_SLEEP, vcpu); } + + /* + * Make sure we will observe a potential reset request if we've + * observed a change to the power state. Pairs with the smp_wmb() in + * kvm_psci_vcpu_on(). + */ + smp_rmb(); } static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu) @@ -639,6 +646,9 @@ static void check_vcpu_requests(struct kvm_vcpu *vcpu) if (kvm_check_request(KVM_REQ_SLEEP, vcpu)) vcpu_req_sleep(vcpu); + if (kvm_check_request(KVM_REQ_VCPU_RESET, vcpu)) + kvm_reset_vcpu(vcpu); + /* * Clear IRQ_PENDING requests that were made to guarantee * that a VCPU sees new virtual interrupts. diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c index fbdf3ac2f001..30251e288629 100644 --- a/virt/kvm/arm/mmu.c +++ b/virt/kvm/arm/mmu.c @@ -1695,11 +1695,14 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, vma_pagesize = vma_kernel_pagesize(vma); /* - * PUD level may not exist for a VM but PMD is guaranteed to - * exist. + * The stage2 has a minimum of 2 level table (For arm64 see + * kvm_arm_setup_stage2()). Hence, we are guaranteed that we can + * use PMD_SIZE huge mappings (even when the PMD is folded into PGD). + * As for PUD huge maps, we must make sure that we have at least + * 3 levels, i.e, PMD is not folded. */ if ((vma_pagesize == PMD_SIZE || - (vma_pagesize == PUD_SIZE && kvm_stage2_has_pud(kvm))) && + (vma_pagesize == PUD_SIZE && kvm_stage2_has_pmd(kvm))) && !force_pte) { gfn = (fault_ipa & huge_page_mask(hstate_vma(vma))) >> PAGE_SHIFT; } diff --git a/virt/kvm/arm/psci.c b/virt/kvm/arm/psci.c index 9b73d3ad918a..34d08ee63747 100644 --- a/virt/kvm/arm/psci.c +++ b/virt/kvm/arm/psci.c @@ -104,12 +104,10 @@ static void kvm_psci_vcpu_off(struct kvm_vcpu *vcpu) static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) { + struct vcpu_reset_state *reset_state; struct kvm *kvm = source_vcpu->kvm; struct kvm_vcpu *vcpu = NULL; - struct swait_queue_head *wq; unsigned long cpu_id; - unsigned long context_id; - phys_addr_t target_pc; cpu_id = smccc_get_arg1(source_vcpu) & MPIDR_HWID_BITMASK; if (vcpu_mode_is_32bit(source_vcpu)) @@ -130,32 +128,30 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) return PSCI_RET_INVALID_PARAMS; } - target_pc = smccc_get_arg2(source_vcpu); - context_id = smccc_get_arg3(source_vcpu); + reset_state = &vcpu->arch.reset_state; - kvm_reset_vcpu(vcpu); - - /* Gracefully handle Thumb2 entry point */ - if (vcpu_mode_is_32bit(vcpu) && (target_pc & 1)) { - target_pc &= ~((phys_addr_t) 1); - vcpu_set_thumb(vcpu); - } + reset_state->pc = smccc_get_arg2(source_vcpu); /* Propagate caller endianness */ - if (kvm_vcpu_is_be(source_vcpu)) - kvm_vcpu_set_be(vcpu); + reset_state->be = kvm_vcpu_is_be(source_vcpu); - *vcpu_pc(vcpu) = target_pc; /* * NOTE: We always update r0 (or x0) because for PSCI v0.1 * the general puspose registers are undefined upon CPU_ON. */ - smccc_set_retval(vcpu, context_id, 0, 0, 0); - vcpu->arch.power_off = false; - smp_mb(); /* Make sure the above is visible */ + reset_state->r0 = smccc_get_arg3(source_vcpu); + + WRITE_ONCE(reset_state->reset, true); + kvm_make_request(KVM_REQ_VCPU_RESET, vcpu); - wq = kvm_arch_vcpu_wq(vcpu); - swake_up_one(wq); + /* + * Make sure the reset request is observed if the change to + * power_state is observed. + */ + smp_wmb(); + + vcpu->arch.power_off = false; + kvm_vcpu_wake_up(vcpu); return PSCI_RET_SUCCESS; } diff --git a/virt/kvm/arm/vgic/vgic-debug.c b/virt/kvm/arm/vgic/vgic-debug.c index 07aa900bac56..1f62f2b8065d 100644 --- a/virt/kvm/arm/vgic/vgic-debug.c +++ b/virt/kvm/arm/vgic/vgic-debug.c @@ -251,9 +251,9 @@ static int vgic_debug_show(struct seq_file *s, void *v) return 0; } - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); print_irq_state(s, irq, vcpu); - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(kvm, irq); return 0; diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c index c0c0b88af1d5..3bdb31eaed64 100644 --- a/virt/kvm/arm/vgic/vgic-init.c +++ b/virt/kvm/arm/vgic/vgic-init.c @@ -64,7 +64,7 @@ void kvm_vgic_early_init(struct kvm *kvm) struct vgic_dist *dist = &kvm->arch.vgic; INIT_LIST_HEAD(&dist->lpi_list_head); - spin_lock_init(&dist->lpi_list_lock); + raw_spin_lock_init(&dist->lpi_list_lock); } /* CREATION */ @@ -171,7 +171,7 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis) irq->intid = i + VGIC_NR_PRIVATE_IRQS; INIT_LIST_HEAD(&irq->ap_list); - spin_lock_init(&irq->irq_lock); + raw_spin_lock_init(&irq->irq_lock); irq->vcpu = NULL; irq->target_vcpu = vcpu0; kref_init(&irq->refcount); @@ -206,7 +206,7 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu) vgic_cpu->sgi_iodev.base_addr = VGIC_ADDR_UNDEF; INIT_LIST_HEAD(&vgic_cpu->ap_list_head); - spin_lock_init(&vgic_cpu->ap_list_lock); + raw_spin_lock_init(&vgic_cpu->ap_list_lock); /* * Enable and configure all SGIs to be edge-triggered and @@ -216,7 +216,7 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu) struct vgic_irq *irq = &vgic_cpu->private_irqs[i]; INIT_LIST_HEAD(&irq->ap_list); - spin_lock_init(&irq->irq_lock); + raw_spin_lock_init(&irq->irq_lock); irq->intid = i; irq->vcpu = NULL; irq->target_vcpu = vcpu; @@ -231,13 +231,6 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu) irq->config = VGIC_CONFIG_LEVEL; } - /* - * GICv3 can only be created via the KVM_DEVICE_CREATE API and - * so we always know the emulation type at this point as it's - * either explicitly configured as GICv3, or explicitly - * configured as GICv2, or not configured yet which also - * implies GICv2. - */ if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) irq->group = 1; else @@ -281,7 +274,7 @@ int vgic_init(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; - int ret = 0, i; + int ret = 0, i, idx; if (vgic_initialized(kvm)) return 0; @@ -298,6 +291,19 @@ int vgic_init(struct kvm *kvm) if (ret) goto out; + /* Initialize groups on CPUs created before the VGIC type was known */ + kvm_for_each_vcpu(idx, vcpu, kvm) { + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + + for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) { + struct vgic_irq *irq = &vgic_cpu->private_irqs[i]; + if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) + irq->group = 1; + else + irq->group = 0; + } + } + if (vgic_has_its(kvm)) { ret = vgic_v4_init(kvm); if (ret) diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c index eb2a390a6c86..ab3f47745d9c 100644 --- a/virt/kvm/arm/vgic/vgic-its.c +++ b/virt/kvm/arm/vgic/vgic-its.c @@ -65,7 +65,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, INIT_LIST_HEAD(&irq->lpi_list); INIT_LIST_HEAD(&irq->ap_list); - spin_lock_init(&irq->irq_lock); + raw_spin_lock_init(&irq->irq_lock); irq->config = VGIC_CONFIG_EDGE; kref_init(&irq->refcount); @@ -73,7 +73,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, irq->target_vcpu = vcpu; irq->group = 1; - spin_lock_irqsave(&dist->lpi_list_lock, flags); + raw_spin_lock_irqsave(&dist->lpi_list_lock, flags); /* * There could be a race with another vgic_add_lpi(), so we need to @@ -101,7 +101,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, dist->lpi_list_count++; out_unlock: - spin_unlock_irqrestore(&dist->lpi_list_lock, flags); + raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags); /* * We "cache" the configuration table entries in our struct vgic_irq's. @@ -287,7 +287,7 @@ static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq, if (ret) return ret; - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); if (!filter_vcpu || filter_vcpu == irq->target_vcpu) { irq->priority = LPI_PROP_PRIORITY(prop); @@ -299,7 +299,7 @@ static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq, } } - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); if (irq->hw) return its_prop_update_vlpi(irq->host_irq, prop, needs_inv); @@ -332,7 +332,7 @@ int vgic_copy_lpi_list(struct kvm *kvm, struct kvm_vcpu *vcpu, u32 **intid_ptr) if (!intids) return -ENOMEM; - spin_lock_irqsave(&dist->lpi_list_lock, flags); + raw_spin_lock_irqsave(&dist->lpi_list_lock, flags); list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) { if (i == irq_count) break; @@ -341,7 +341,7 @@ int vgic_copy_lpi_list(struct kvm *kvm, struct kvm_vcpu *vcpu, u32 **intid_ptr) continue; intids[i++] = irq->intid; } - spin_unlock_irqrestore(&dist->lpi_list_lock, flags); + raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags); *intid_ptr = intids; return i; @@ -352,9 +352,9 @@ static int update_affinity(struct vgic_irq *irq, struct kvm_vcpu *vcpu) int ret = 0; unsigned long flags; - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->target_vcpu = vcpu; - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); if (irq->hw) { struct its_vlpi_map map; @@ -455,7 +455,7 @@ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu) } irq = vgic_get_irq(vcpu->kvm, NULL, intids[i]); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->pending_latch = pendmask & (1U << bit_nr); vgic_queue_irq_unlock(vcpu->kvm, irq, flags); vgic_put_irq(vcpu->kvm, irq); @@ -612,7 +612,7 @@ static int vgic_its_trigger_msi(struct kvm *kvm, struct vgic_its *its, return irq_set_irqchip_state(irq->host_irq, IRQCHIP_STATE_PENDING, true); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->pending_latch = true; vgic_queue_irq_unlock(kvm, irq, flags); diff --git a/virt/kvm/arm/vgic/vgic-mmio-v2.c b/virt/kvm/arm/vgic/vgic-mmio-v2.c index 738b65d2d0e7..b535fffc7400 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v2.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v2.c @@ -147,7 +147,7 @@ static void vgic_mmio_write_sgir(struct kvm_vcpu *source_vcpu, irq = vgic_get_irq(source_vcpu->kvm, vcpu, intid); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->pending_latch = true; irq->source |= 1U << source_vcpu->vcpu_id; @@ -191,13 +191,13 @@ static void vgic_mmio_write_target(struct kvm_vcpu *vcpu, struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, NULL, intid + i); int target; - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->targets = (val >> (i * 8)) & cpu_mask; target = irq->targets ? __ffs(irq->targets) : 0; irq->target_vcpu = kvm_get_vcpu(vcpu->kvm, target); - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } } @@ -230,13 +230,13 @@ static void vgic_mmio_write_sgipendc(struct kvm_vcpu *vcpu, for (i = 0; i < len; i++) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->source &= ~((val >> (i * 8)) & 0xff); if (!irq->source) irq->pending_latch = false; - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } } @@ -252,7 +252,7 @@ static void vgic_mmio_write_sgipends(struct kvm_vcpu *vcpu, for (i = 0; i < len; i++) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->source |= (val >> (i * 8)) & 0xff; @@ -260,7 +260,7 @@ static void vgic_mmio_write_sgipends(struct kvm_vcpu *vcpu, irq->pending_latch = true; vgic_queue_irq_unlock(vcpu->kvm, irq, flags); } else { - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); } vgic_put_irq(vcpu->kvm, irq); } diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c index b3d1f0985117..4a12322bf7df 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v3.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c @@ -169,13 +169,13 @@ static void vgic_mmio_write_irouter(struct kvm_vcpu *vcpu, if (!irq) return; - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); /* We only care about and preserve Aff0, Aff1 and Aff2. */ irq->mpidr = val & GENMASK(23, 0); irq->target_vcpu = kvm_mpidr_to_vcpu(vcpu->kvm, irq->mpidr); - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } @@ -281,7 +281,7 @@ static int vgic_v3_uaccess_write_pending(struct kvm_vcpu *vcpu, for (i = 0; i < len * 8; i++) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); if (test_bit(i, &val)) { /* * pending_latch is set irrespective of irq type @@ -292,7 +292,7 @@ static int vgic_v3_uaccess_write_pending(struct kvm_vcpu *vcpu, vgic_queue_irq_unlock(vcpu->kvm, irq, flags); } else { irq->pending_latch = false; - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); } vgic_put_irq(vcpu->kvm, irq); @@ -957,7 +957,7 @@ void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg, bool allow_group1) irq = vgic_get_irq(vcpu->kvm, c_vcpu, sgi); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); /* * An access targetting Group0 SGIs can only generate @@ -968,7 +968,7 @@ void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg, bool allow_group1) irq->pending_latch = true; vgic_queue_irq_unlock(vcpu->kvm, irq, flags); } else { - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); } vgic_put_irq(vcpu->kvm, irq); diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c index ceeda7e04a4d..7de42fba05b5 100644 --- a/virt/kvm/arm/vgic/vgic-mmio.c +++ b/virt/kvm/arm/vgic/vgic-mmio.c @@ -77,7 +77,7 @@ void vgic_mmio_write_group(struct kvm_vcpu *vcpu, gpa_t addr, for (i = 0; i < len * 8; i++) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->group = !!(val & BIT(i)); vgic_queue_irq_unlock(vcpu->kvm, irq, flags); @@ -120,7 +120,7 @@ void vgic_mmio_write_senable(struct kvm_vcpu *vcpu, for_each_set_bit(i, &val, len * 8) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->enabled = true; vgic_queue_irq_unlock(vcpu->kvm, irq, flags); @@ -139,11 +139,11 @@ void vgic_mmio_write_cenable(struct kvm_vcpu *vcpu, for_each_set_bit(i, &val, len * 8) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->enabled = false; - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } } @@ -160,10 +160,10 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); unsigned long flags; - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq_is_pending(irq)) value |= (1U << i); - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } @@ -215,7 +215,7 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu, for_each_set_bit(i, &val, len * 8) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->hw) vgic_hw_irq_spending(vcpu, irq, is_uaccess); else @@ -262,14 +262,14 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, for_each_set_bit(i, &val, len * 8) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->hw) vgic_hw_irq_cpending(vcpu, irq, is_uaccess); else irq->pending_latch = false; - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } } @@ -311,7 +311,7 @@ static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, unsigned long flags; struct kvm_vcpu *requester_vcpu = vgic_get_mmio_requester_vcpu(); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->hw) { vgic_hw_irq_change_active(vcpu, irq, active, !requester_vcpu); @@ -342,7 +342,7 @@ static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, if (irq->active) vgic_queue_irq_unlock(vcpu->kvm, irq, flags); else - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); } /* @@ -485,10 +485,10 @@ void vgic_mmio_write_priority(struct kvm_vcpu *vcpu, for (i = 0; i < len; i++) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); /* Narrow the priority range to what we actually support */ irq->priority = (val >> (i * 8)) & GENMASK(7, 8 - VGIC_PRI_BITS); - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } @@ -534,14 +534,14 @@ void vgic_mmio_write_config(struct kvm_vcpu *vcpu, continue; irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); if (test_bit(i * 2 + 1, &val)) irq->config = VGIC_CONFIG_EDGE; else irq->config = VGIC_CONFIG_LEVEL; - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } } @@ -590,12 +590,12 @@ void vgic_write_irq_line_level_info(struct kvm_vcpu *vcpu, u32 intid, * restore irq config before line level. */ new_level = !!(val & (1U << i)); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->line_level = new_level; if (new_level) vgic_queue_irq_unlock(vcpu->kvm, irq, flags); else - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } diff --git a/virt/kvm/arm/vgic/vgic-v2.c b/virt/kvm/arm/vgic/vgic-v2.c index 69b892abd7dc..d91a8938aa7c 100644 --- a/virt/kvm/arm/vgic/vgic-v2.c +++ b/virt/kvm/arm/vgic/vgic-v2.c @@ -84,7 +84,7 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu) irq = vgic_get_irq(vcpu->kvm, vcpu, intid); - spin_lock(&irq->irq_lock); + raw_spin_lock(&irq->irq_lock); /* Always preserve the active bit */ irq->active = !!(val & GICH_LR_ACTIVE_BIT); @@ -127,7 +127,7 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu) vgic_irq_set_phys_active(irq, false); } - spin_unlock(&irq->irq_lock); + raw_spin_unlock(&irq->irq_lock); vgic_put_irq(vcpu->kvm, irq); } diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index 9c0dd234ebe8..4ee0aeb9a905 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -76,7 +76,7 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu) if (!irq) /* An LPI could have been unmapped. */ continue; - spin_lock(&irq->irq_lock); + raw_spin_lock(&irq->irq_lock); /* Always preserve the active bit */ irq->active = !!(val & ICH_LR_ACTIVE_BIT); @@ -119,7 +119,7 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu) vgic_irq_set_phys_active(irq, false); } - spin_unlock(&irq->irq_lock); + raw_spin_unlock(&irq->irq_lock); vgic_put_irq(vcpu->kvm, irq); } @@ -347,9 +347,9 @@ retry: status = val & (1 << bit_nr); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->target_vcpu != vcpu) { - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); goto retry; } irq->pending_latch = status; diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c index 870b1185173b..abd9c7352677 100644 --- a/virt/kvm/arm/vgic/vgic.c +++ b/virt/kvm/arm/vgic/vgic.c @@ -54,11 +54,11 @@ struct vgic_global kvm_vgic_global_state __ro_after_init = { * When taking more than one ap_list_lock at the same time, always take the * lowest numbered VCPU's ap_list_lock first, so: * vcpuX->vcpu_id < vcpuY->vcpu_id: - * spin_lock(vcpuX->arch.vgic_cpu.ap_list_lock); - * spin_lock(vcpuY->arch.vgic_cpu.ap_list_lock); + * raw_spin_lock(vcpuX->arch.vgic_cpu.ap_list_lock); + * raw_spin_lock(vcpuY->arch.vgic_cpu.ap_list_lock); * * Since the VGIC must support injecting virtual interrupts from ISRs, we have - * to use the spin_lock_irqsave/spin_unlock_irqrestore versions of outer + * to use the raw_spin_lock_irqsave/raw_spin_unlock_irqrestore versions of outer * spinlocks for any lock that may be taken while injecting an interrupt. */ @@ -72,7 +72,7 @@ static struct vgic_irq *vgic_get_lpi(struct kvm *kvm, u32 intid) struct vgic_irq *irq = NULL; unsigned long flags; - spin_lock_irqsave(&dist->lpi_list_lock, flags); + raw_spin_lock_irqsave(&dist->lpi_list_lock, flags); list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) { if (irq->intid != intid) @@ -88,7 +88,7 @@ static struct vgic_irq *vgic_get_lpi(struct kvm *kvm, u32 intid) irq = NULL; out_unlock: - spin_unlock_irqrestore(&dist->lpi_list_lock, flags); + raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags); return irq; } @@ -138,15 +138,15 @@ void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq) if (irq->intid < VGIC_MIN_LPI) return; - spin_lock_irqsave(&dist->lpi_list_lock, flags); + raw_spin_lock_irqsave(&dist->lpi_list_lock, flags); if (!kref_put(&irq->refcount, vgic_irq_release)) { - spin_unlock_irqrestore(&dist->lpi_list_lock, flags); + raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags); return; }; list_del(&irq->lpi_list); dist->lpi_list_count--; - spin_unlock_irqrestore(&dist->lpi_list_lock, flags); + raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags); kfree(irq); } @@ -244,8 +244,8 @@ static int vgic_irq_cmp(void *priv, struct list_head *a, struct list_head *b) bool penda, pendb; int ret; - spin_lock(&irqa->irq_lock); - spin_lock_nested(&irqb->irq_lock, SINGLE_DEPTH_NESTING); + raw_spin_lock(&irqa->irq_lock); + raw_spin_lock_nested(&irqb->irq_lock, SINGLE_DEPTH_NESTING); if (irqa->active || irqb->active) { ret = (int)irqb->active - (int)irqa->active; @@ -263,8 +263,8 @@ static int vgic_irq_cmp(void *priv, struct list_head *a, struct list_head *b) /* Both pending and enabled, sort by priority */ ret = irqa->priority - irqb->priority; out: - spin_unlock(&irqb->irq_lock); - spin_unlock(&irqa->irq_lock); + raw_spin_unlock(&irqb->irq_lock); + raw_spin_unlock(&irqa->irq_lock); return ret; } @@ -325,7 +325,7 @@ retry: * not need to be inserted into an ap_list and there is also * no more work for us to do. */ - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); /* * We have to kick the VCPU here, because we could be @@ -347,12 +347,12 @@ retry: * We must unlock the irq lock to take the ap_list_lock where * we are going to insert this new pending interrupt. */ - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); /* someone can do stuff here, which we re-check below */ - spin_lock_irqsave(&vcpu->arch.vgic_cpu.ap_list_lock, flags); - spin_lock(&irq->irq_lock); + raw_spin_lock_irqsave(&vcpu->arch.vgic_cpu.ap_list_lock, flags); + raw_spin_lock(&irq->irq_lock); /* * Did something change behind our backs? @@ -367,10 +367,11 @@ retry: */ if (unlikely(irq->vcpu || vcpu != vgic_target_oracle(irq))) { - spin_unlock(&irq->irq_lock); - spin_unlock_irqrestore(&vcpu->arch.vgic_cpu.ap_list_lock, flags); + raw_spin_unlock(&irq->irq_lock); + raw_spin_unlock_irqrestore(&vcpu->arch.vgic_cpu.ap_list_lock, + flags); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); goto retry; } @@ -382,8 +383,8 @@ retry: list_add_tail(&irq->ap_list, &vcpu->arch.vgic_cpu.ap_list_head); irq->vcpu = vcpu; - spin_unlock(&irq->irq_lock); - spin_unlock_irqrestore(&vcpu->arch.vgic_cpu.ap_list_lock, flags); + raw_spin_unlock(&irq->irq_lock); + raw_spin_unlock_irqrestore(&vcpu->arch.vgic_cpu.ap_list_lock, flags); kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu); kvm_vcpu_kick(vcpu); @@ -430,11 +431,11 @@ int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid, if (!irq) return -EINVAL; - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); if (!vgic_validate_injection(irq, level, owner)) { /* Nothing to see here, move along... */ - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(kvm, irq); return 0; } @@ -494,9 +495,9 @@ int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, unsigned int host_irq, BUG_ON(!irq); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); ret = kvm_vgic_map_irq(vcpu, irq, host_irq, get_input_level); - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); return ret; @@ -519,11 +520,11 @@ void kvm_vgic_reset_mapped_irq(struct kvm_vcpu *vcpu, u32 vintid) if (!irq->hw) goto out; - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->active = false; irq->pending_latch = false; irq->line_level = false; - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); out: vgic_put_irq(vcpu->kvm, irq); } @@ -539,9 +540,9 @@ int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int vintid) irq = vgic_get_irq(vcpu->kvm, vcpu, vintid); BUG_ON(!irq); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); kvm_vgic_unmap_irq(irq); - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); return 0; @@ -571,12 +572,12 @@ int kvm_vgic_set_owner(struct kvm_vcpu *vcpu, unsigned int intid, void *owner) return -EINVAL; irq = vgic_get_irq(vcpu->kvm, vcpu, intid); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->owner && irq->owner != owner) ret = -EEXIST; else irq->owner = owner; - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); return ret; } @@ -597,13 +598,13 @@ static void vgic_prune_ap_list(struct kvm_vcpu *vcpu) DEBUG_SPINLOCK_BUG_ON(!irqs_disabled()); retry: - spin_lock(&vgic_cpu->ap_list_lock); + raw_spin_lock(&vgic_cpu->ap_list_lock); list_for_each_entry_safe(irq, tmp, &vgic_cpu->ap_list_head, ap_list) { struct kvm_vcpu *target_vcpu, *vcpuA, *vcpuB; bool target_vcpu_needs_kick = false; - spin_lock(&irq->irq_lock); + raw_spin_lock(&irq->irq_lock); BUG_ON(vcpu != irq->vcpu); @@ -616,7 +617,7 @@ retry: */ list_del(&irq->ap_list); irq->vcpu = NULL; - spin_unlock(&irq->irq_lock); + raw_spin_unlock(&irq->irq_lock); /* * This vgic_put_irq call matches the @@ -631,14 +632,14 @@ retry: if (target_vcpu == vcpu) { /* We're on the right CPU */ - spin_unlock(&irq->irq_lock); + raw_spin_unlock(&irq->irq_lock); continue; } /* This interrupt looks like it has to be migrated. */ - spin_unlock(&irq->irq_lock); - spin_unlock(&vgic_cpu->ap_list_lock); + raw_spin_unlock(&irq->irq_lock); + raw_spin_unlock(&vgic_cpu->ap_list_lock); /* * Ensure locking order by always locking the smallest @@ -652,10 +653,10 @@ retry: vcpuB = vcpu; } - spin_lock(&vcpuA->arch.vgic_cpu.ap_list_lock); - spin_lock_nested(&vcpuB->arch.vgic_cpu.ap_list_lock, - SINGLE_DEPTH_NESTING); - spin_lock(&irq->irq_lock); + raw_spin_lock(&vcpuA->arch.vgic_cpu.ap_list_lock); + raw_spin_lock_nested(&vcpuB->arch.vgic_cpu.ap_list_lock, + SINGLE_DEPTH_NESTING); + raw_spin_lock(&irq->irq_lock); /* * If the affinity has been preserved, move the @@ -675,9 +676,9 @@ retry: target_vcpu_needs_kick = true; } - spin_unlock(&irq->irq_lock); - spin_unlock(&vcpuB->arch.vgic_cpu.ap_list_lock); - spin_unlock(&vcpuA->arch.vgic_cpu.ap_list_lock); + raw_spin_unlock(&irq->irq_lock); + raw_spin_unlock(&vcpuB->arch.vgic_cpu.ap_list_lock); + raw_spin_unlock(&vcpuA->arch.vgic_cpu.ap_list_lock); if (target_vcpu_needs_kick) { kvm_make_request(KVM_REQ_IRQ_PENDING, target_vcpu); @@ -687,7 +688,7 @@ retry: goto retry; } - spin_unlock(&vgic_cpu->ap_list_lock); + raw_spin_unlock(&vgic_cpu->ap_list_lock); } static inline void vgic_fold_lr_state(struct kvm_vcpu *vcpu) @@ -741,10 +742,10 @@ static int compute_ap_list_depth(struct kvm_vcpu *vcpu, list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) { int w; - spin_lock(&irq->irq_lock); + raw_spin_lock(&irq->irq_lock); /* GICv2 SGIs can count for more than one... */ w = vgic_irq_get_lr_count(irq); - spin_unlock(&irq->irq_lock); + raw_spin_unlock(&irq->irq_lock); count += w; *multi_sgi |= (w > 1); @@ -770,7 +771,7 @@ static void vgic_flush_lr_state(struct kvm_vcpu *vcpu) count = 0; list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) { - spin_lock(&irq->irq_lock); + raw_spin_lock(&irq->irq_lock); /* * If we have multi-SGIs in the pipeline, we need to @@ -780,7 +781,7 @@ static void vgic_flush_lr_state(struct kvm_vcpu *vcpu) * the AP list has been sorted already. */ if (multi_sgi && irq->priority > prio) { - spin_unlock(&irq->irq_lock); + _raw_spin_unlock(&irq->irq_lock); break; } @@ -791,7 +792,7 @@ static void vgic_flush_lr_state(struct kvm_vcpu *vcpu) prio = irq->priority; } - spin_unlock(&irq->irq_lock); + raw_spin_unlock(&irq->irq_lock); if (count == kvm_vgic_global_state.nr_lr) { if (!list_is_last(&irq->ap_list, @@ -872,9 +873,9 @@ void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu) DEBUG_SPINLOCK_BUG_ON(!irqs_disabled()); - spin_lock(&vcpu->arch.vgic_cpu.ap_list_lock); + raw_spin_lock(&vcpu->arch.vgic_cpu.ap_list_lock); vgic_flush_lr_state(vcpu); - spin_unlock(&vcpu->arch.vgic_cpu.ap_list_lock); + raw_spin_unlock(&vcpu->arch.vgic_cpu.ap_list_lock); if (can_access_vgic_from_kernel()) vgic_restore_state(vcpu); @@ -918,20 +919,20 @@ int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu) vgic_get_vmcr(vcpu, &vmcr); - spin_lock_irqsave(&vgic_cpu->ap_list_lock, flags); + raw_spin_lock_irqsave(&vgic_cpu->ap_list_lock, flags); list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) { - spin_lock(&irq->irq_lock); + raw_spin_lock(&irq->irq_lock); pending = irq_is_pending(irq) && irq->enabled && !irq->active && irq->priority < vmcr.pmr; - spin_unlock(&irq->irq_lock); + raw_spin_unlock(&irq->irq_lock); if (pending) break; } - spin_unlock_irqrestore(&vgic_cpu->ap_list_lock, flags); + raw_spin_unlock_irqrestore(&vgic_cpu->ap_list_lock, flags); return pending; } @@ -963,11 +964,10 @@ bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int vintid) return false; irq = vgic_get_irq(vcpu->kvm, vcpu, vintid); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); map_is_active = irq->hw && irq->active; - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); return map_is_active; } - |