diff options
610 files changed, 10116 insertions, 3823 deletions
@@ -9,7 +9,7 @@ Linus ---------- -M: Matt Mackal +N: Matt Mackal E: mpm@selenic.com D: SLOB slab allocator @@ -1910,7 +1910,7 @@ S: Ra'annana, Israel N: Andi Kleen E: andi@firstfloor.org -U: http://www.halobates.de +W: http://www.halobates.de D: network, x86, NUMA, various hacks S: Schwalbenstr. 96 S: 85551 Ottobrunn @@ -2089,8 +2089,8 @@ D: ST Microelectronics SPEAr13xx PCI host bridge driver D: Synopsys Designware PCI host bridge driver N: Gabor Kuti -M: seasons@falcon.sch.bme.hu -M: seasons@makosteszta.sote.hu +E: seasons@falcon.sch.bme.hu +E: seasons@makosteszta.sote.hu D: Original author of software suspend N: Jaroslav Kysela diff --git a/Documentation/ABI/testing/sysfs-power b/Documentation/ABI/testing/sysfs-power index 50b368d490b5..f523e5a3ac33 100644 --- a/Documentation/ABI/testing/sysfs-power +++ b/Documentation/ABI/testing/sysfs-power @@ -7,30 +7,35 @@ Description: subsystem. What: /sys/power/state -Date: May 2014 +Date: November 2016 Contact: Rafael J. Wysocki <rjw@rjwysocki.net> Description: The /sys/power/state file controls system sleep states. Reading from this file returns the available sleep state - labels, which may be "mem", "standby", "freeze" and "disk" - (hibernation). The meanings of the first three labels depend on - the relative_sleep_states command line argument as follows: - 1) relative_sleep_states = 1 - "mem", "standby", "freeze" represent non-hibernation sleep - states from the deepest ("mem", always present) to the - shallowest ("freeze"). "standby" and "freeze" may or may - not be present depending on the capabilities of the - platform. "freeze" can only be present if "standby" is - present. - 2) relative_sleep_states = 0 (default) - "mem" - "suspend-to-RAM", present if supported. - "standby" - "power-on suspend", present if supported. - "freeze" - "suspend-to-idle", always present. - - Writing to this file one of these strings causes the system to - transition into the corresponding state, if available. See - Documentation/power/states.txt for a description of what - "suspend-to-RAM", "power-on suspend" and "suspend-to-idle" mean. + labels, which may be "mem" (suspend), "standby" (power-on + suspend), "freeze" (suspend-to-idle) and "disk" (hibernation). + + Writing one of the above strings to this file causes the system + to transition into the corresponding state, if available. + + See Documentation/power/states.txt for more information. + +What: /sys/power/mem_sleep +Date: November 2016 +Contact: Rafael J. Wysocki <rjw@rjwysocki.net> +Description: + The /sys/power/mem_sleep file controls the operating mode of + system suspend. Reading from it returns the available modes + as "s2idle" (always present), "shallow" and "deep" (present if + supported). The mode that will be used on subsequent attempts + to suspend the system (by writing "mem" to the /sys/power/state + file described above) is enclosed in square brackets. + + Writing one of the above strings to this file causes the mode + represented by it to be used on subsequent attempts to suspend + the system. + + See Documentation/power/states.txt for more information. What: /sys/power/disk Date: September 2006 diff --git a/Documentation/cpu-freq/cpufreq-stats.txt b/Documentation/cpu-freq/cpufreq-stats.txt index 8d9773f23550..3c355f6ad834 100644 --- a/Documentation/cpu-freq/cpufreq-stats.txt +++ b/Documentation/cpu-freq/cpufreq-stats.txt @@ -44,11 +44,17 @@ the stats driver insertion. total 0 drwxr-xr-x 2 root root 0 May 14 16:06 . drwxr-xr-x 3 root root 0 May 14 15:58 .. +--w------- 1 root root 4096 May 14 16:06 reset -r--r--r-- 1 root root 4096 May 14 16:06 time_in_state -r--r--r-- 1 root root 4096 May 14 16:06 total_trans -r--r--r-- 1 root root 4096 May 14 16:06 trans_table -------------------------------------------------------------------------------- +- reset +Write-only attribute that can be used to reset the stat counters. This can be +useful for evaluating system behaviour under different governors without the +need for a reboot. + - time_in_state This gives the amount of time spent in each of the frequencies supported by this CPU. The cat output will have "<frequency> <time>" pair in each line, which diff --git a/Documentation/cpu-freq/intel-pstate.txt b/Documentation/cpu-freq/intel-pstate.txt index e6bd1e6512a5..1953994ef5e6 100644 --- a/Documentation/cpu-freq/intel-pstate.txt +++ b/Documentation/cpu-freq/intel-pstate.txt @@ -48,7 +48,7 @@ In addition to the frequency-controlling interfaces provided by the cpufreq core, the driver provides its own sysfs files to control the P-State selection. These files have been added to /sys/devices/system/cpu/intel_pstate/. Any changes made to these files are applicable to all CPUs (even in a -multi-package system). +multi-package system, Refer to later section on placing "Per-CPU limits"). max_perf_pct: Limits the maximum P-State that will be requested by the driver. It states it as a percentage of the available performance. The @@ -120,13 +120,57 @@ frequency is fictional for Intel Core processors. Even if the scaling driver selects a single P-State, the actual frequency the processor will run at is selected by the processor itself. +Per-CPU limits + +The kernel command line option "intel_pstate=per_cpu_perf_limits" forces +the intel_pstate driver to use per-CPU performance limits. When it is set, +the sysfs control interface described above is subject to limitations. +- The following controls are not available for both read and write + /sys/devices/system/cpu/intel_pstate/max_perf_pct + /sys/devices/system/cpu/intel_pstate/min_perf_pct +- The following controls can be used to set performance limits, as far as the +architecture of the processor permits: + /sys/devices/system/cpu/cpu*/cpufreq/scaling_max_freq + /sys/devices/system/cpu/cpu*/cpufreq/scaling_min_freq + /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor +- User can still observe turbo percent and number of P-States from + /sys/devices/system/cpu/intel_pstate/turbo_pct + /sys/devices/system/cpu/intel_pstate/num_pstates +- User can read write system wide turbo status + /sys/devices/system/cpu/no_turbo + +Support of energy performance hints +It is possible to provide hints to the HWP algorithms in the processor +to be more performance centric to more energy centric. When the driver +is using HWP, two additional cpufreq sysfs attributes are presented for +each logical CPU. +These attributes are: + - energy_performance_available_preferences + - energy_performance_preference + +To get list of supported hints: +$ cat energy_performance_available_preferences + default performance balance_performance balance_power power + +The current preference can be read or changed via cpufreq sysfs +attribute "energy_performance_preference". Reading from this attribute +will display current effective setting. User can write any of the valid +preference string to this attribute. User can always restore to power-on +default by writing "default". + +Since threads can migrate to different CPUs, this is possible that the +new CPU may have different energy performance preference than the previous +one. To avoid such issues, either threads can be pinned to specific CPUs +or set the same energy performance preference value to all CPUs. + Tuning Intel P-State driver -When HWP mode is not used, debugfs files have also been added to allow the -tuning of the internal governor algorithm. These files are located at -/sys/kernel/debug/pstate_snb/. The algorithm uses a PID (Proportional -Integral Derivative) controller. The PID tunable parameters are: +When the performance can be tuned using PID (Proportional Integral +Derivative) controller, debugfs files are provided for adjusting performance. +They are presented under: +/sys/kernel/debug/pstate_snb/ +The PID tunable parameters are: deadband d_gain_pct i_gain_pct diff --git a/Documentation/devicetree/bindings/cpufreq/brcm,stb-avs-cpu-freq.txt b/Documentation/devicetree/bindings/cpufreq/brcm,stb-avs-cpu-freq.txt new file mode 100644 index 000000000000..af2385795d78 --- /dev/null +++ b/Documentation/devicetree/bindings/cpufreq/brcm,stb-avs-cpu-freq.txt @@ -0,0 +1,78 @@ +Broadcom AVS mail box and interrupt register bindings +===================================================== + +A total of three DT nodes are required. One node (brcm,avs-cpu-data-mem) +references the mailbox register used to communicate with the AVS CPU[1]. The +second node (brcm,avs-cpu-l2-intr) is required to trigger an interrupt on +the AVS CPU. The interrupt tells the AVS CPU that it needs to process a +command sent to it by a driver. Interrupting the AVS CPU is mandatory for +commands to be processed. + +The interface also requires a reference to the AVS host interrupt controller, +so a driver can react to interrupts generated by the AVS CPU whenever a command +has been processed. See [2] for more information on the brcm,l2-intc node. + +[1] The AVS CPU is an independent co-processor that runs proprietary +firmware. On some SoCs, this firmware supports DFS and DVFS in addition to +Adaptive Voltage Scaling. + +[2] Documentation/devicetree/bindings/interrupt-controller/brcm,l2-intc.txt + + +Node brcm,avs-cpu-data-mem +-------------------------- + +Required properties: +- compatible: must include: brcm,avs-cpu-data-mem and + should include: one of brcm,bcm7271-avs-cpu-data-mem or + brcm,bcm7268-avs-cpu-data-mem +- reg: Specifies base physical address and size of the registers. +- interrupts: The interrupt that the AVS CPU will use to interrupt the host + when a command completed. +- interrupt-parent: The interrupt controller the above interrupt is routed + through. +- interrupt-names: The name of the interrupt used to interrupt the host. + +Optional properties: +- None + +Node brcm,avs-cpu-l2-intr +------------------------- + +Required properties: +- compatible: must include: brcm,avs-cpu-l2-intr and + should include: one of brcm,bcm7271-avs-cpu-l2-intr or + brcm,bcm7268-avs-cpu-l2-intr +- reg: Specifies base physical address and size of the registers. + +Optional properties: +- None + + +Example +======= + + avs_host_l2_intc: interrupt-controller@f04d1200 { + #interrupt-cells = <1>; + compatible = "brcm,l2-intc"; + interrupt-parent = <&intc>; + reg = <0xf04d1200 0x48>; + interrupt-controller; + interrupts = <0x0 0x19 0x0>; + interrupt-names = "avs"; + }; + + avs-cpu-data-mem@f04c4000 { + compatible = "brcm,bcm7271-avs-cpu-data-mem", + "brcm,avs-cpu-data-mem"; + reg = <0xf04c4000 0x60>; + interrupts = <0x1a>; + interrupt-parent = <&avs_host_l2_intc>; + interrupt-names = "sw_intr"; + }; + + avs-cpu-l2-intr@f04d1100 { + compatible = "brcm,bcm7271-avs-cpu-l2-intr", + "brcm,avs-cpu-l2-intr"; + reg = <0xf04d1100 0x10>; + }; diff --git a/Documentation/devicetree/bindings/net/ethernet.txt b/Documentation/devicetree/bindings/net/ethernet.txt index e1d76812419c..05150957ecfd 100644 --- a/Documentation/devicetree/bindings/net/ethernet.txt +++ b/Documentation/devicetree/bindings/net/ethernet.txt @@ -9,10 +9,26 @@ The following properties are common to the Ethernet controllers: - max-speed: number, specifies maximum speed in Mbit/s supported by the device; - max-frame-size: number, maximum transfer unit (IEEE defined MTU), rather than the maximum frame size (there's contradiction in ePAPR). -- phy-mode: string, operation mode of the PHY interface; supported values are - "mii", "gmii", "sgmii", "qsgmii", "tbi", "rev-mii", "rmii", "rgmii", "rgmii-id", - "rgmii-rxid", "rgmii-txid", "rtbi", "smii", "xgmii", "trgmii"; this is now a - de-facto standard property; +- phy-mode: string, operation mode of the PHY interface. This is now a de-facto + standard property; supported values are: + * "mii" + * "gmii" + * "sgmii" + * "qsgmii" + * "tbi" + * "rev-mii" + * "rmii" + * "rgmii" (RX and TX delays are added by the MAC when required) + * "rgmii-id" (RGMII with internal RX and TX delays provided by the PHY, the + MAC should not add the RX or TX delays in this case) + * "rgmii-rxid" (RGMII with internal RX delay provided by the PHY, the MAC + should not add an RX delay in this case) + * "rgmii-txid" (RGMII with internal TX delay provided by the PHY, the MAC + should not add an TX delay in this case) + * "rtbi" + * "smii" + * "xgmii" + * "trgmii" - phy-connection-type: the same as "phy-mode" property but described in ePAPR; - phy-handle: phandle, specifies a reference to a node representing a PHY device; this property is described in ePAPR and so preferred; diff --git a/Documentation/devicetree/bindings/opp/opp.txt b/Documentation/devicetree/bindings/opp/opp.txt index ee91cbdd95ee..9f5ca4457b5f 100644 --- a/Documentation/devicetree/bindings/opp/opp.txt +++ b/Documentation/devicetree/bindings/opp/opp.txt @@ -86,8 +86,14 @@ Optional properties: Single entry is for target voltage and three entries are for <target min max> voltages. - Entries for multiple regulators must be present in the same order as - regulators are specified in device's DT node. + Entries for multiple regulators shall be provided in the same field separated + by angular brackets <>. The OPP binding doesn't provide any provisions to + relate the values to their power supplies or the order in which the supplies + need to be configured and that is left for the implementation specific + binding. + + Entries for all regulators shall be of the same size, i.e. either all use a + single value or triplets. - opp-microvolt-<name>: Named opp-microvolt property. This is exactly similar to the above opp-microvolt property, but allows multiple voltage ranges to be @@ -104,10 +110,13 @@ Optional properties: Should only be set if opp-microvolt is set for the OPP. - Entries for multiple regulators must be present in the same order as - regulators are specified in device's DT node. If this property isn't required - for few regulators, then this should be marked as zero for them. If it isn't - required for any regulator, then this property need not be present. + Entries for multiple regulators shall be provided in the same field separated + by angular brackets <>. If current values aren't required for a regulator, + then it shall be filled with 0. If current values aren't required for any of + the regulators, then this field is not required. The OPP binding doesn't + provide any provisions to relate the values to their power supplies or the + order in which the supplies need to be configured and that is left for the + implementation specific binding. - opp-microamp-<name>: Named opp-microamp property. Similar to opp-microvolt-<name> property, but for microamp instead. @@ -386,10 +395,12 @@ Example 4: Handling multiple regulators / { cpus { cpu@0 { - compatible = "arm,cortex-a7"; + compatible = "vendor,cpu-type"; ... - cpu-supply = <&cpu_supply0>, <&cpu_supply1>, <&cpu_supply2>; + vcc0-supply = <&cpu_supply0>; + vcc1-supply = <&cpu_supply1>; + vcc2-supply = <&cpu_supply2>; operating-points-v2 = <&cpu0_opp_table>; }; }; diff --git a/Documentation/devicetree/bindings/power/domain-idle-state.txt b/Documentation/devicetree/bindings/power/domain-idle-state.txt new file mode 100644 index 000000000000..eefc7ed22ca2 --- /dev/null +++ b/Documentation/devicetree/bindings/power/domain-idle-state.txt @@ -0,0 +1,33 @@ +PM Domain Idle State Node: + +A domain idle state node represents the state parameters that will be used to +select the state when there are no active components in the domain. + +The state node has the following parameters - + +- compatible: + Usage: Required + Value type: <string> + Definition: Must be "domain-idle-state". + +- entry-latency-us + Usage: Required + Value type: <prop-encoded-array> + Definition: u32 value representing worst case latency in + microseconds required to enter the idle state. + The exit-latency-us duration may be guaranteed + only after entry-latency-us has passed. + +- exit-latency-us + Usage: Required + Value type: <prop-encoded-array> + Definition: u32 value representing worst case latency + in microseconds required to exit the idle state. + +- min-residency-us + Usage: Required + Value type: <prop-encoded-array> + Definition: u32 value representing minimum residency duration + in microseconds after which the idle state will yield + power benefits after overcoming the overhead in entering +i the idle state. diff --git a/Documentation/devicetree/bindings/power/power_domain.txt b/Documentation/devicetree/bindings/power/power_domain.txt index 025b5e7df61c..723e1ad937da 100644 --- a/Documentation/devicetree/bindings/power/power_domain.txt +++ b/Documentation/devicetree/bindings/power/power_domain.txt @@ -29,6 +29,15 @@ Optional properties: specified by this binding. More details about power domain specifier are available in the next section. +- domain-idle-states : A phandle of an idle-state that shall be soaked into a + generic domain power state. The idle state definitions are + compatible with domain-idle-state specified in [1]. + The domain-idle-state property reflects the idle state of this PM domain and + not the idle states of the devices or sub-domains in the PM domain. Devices + and sub-domains have their own idle-states independent of the parent + domain's idle states. In the absence of this property, the domain would be + considered as capable of being powered-on or powered-off. + Example: power: power-controller@12340000 { @@ -59,6 +68,38 @@ The nodes above define two power controllers: 'parent' and 'child'. Domains created by the 'child' power controller are subdomains of '0' power domain provided by the 'parent' power controller. +Example 3: + parent: power-controller@12340000 { + compatible = "foo,power-controller"; + reg = <0x12340000 0x1000>; + #power-domain-cells = <0>; + domain-idle-states = <&DOMAIN_RET>, <&DOMAIN_PWR_DN>; + }; + + child: power-controller@12341000 { + compatible = "foo,power-controller"; + reg = <0x12341000 0x1000>; + power-domains = <&parent 0>; + #power-domain-cells = <0>; + domain-idle-states = <&DOMAIN_PWR_DN>; + }; + + DOMAIN_RET: state@0 { + compatible = "domain-idle-state"; + reg = <0x0>; + entry-latency-us = <1000>; + exit-latency-us = <2000>; + min-residency-us = <10000>; + }; + + DOMAIN_PWR_DN: state@1 { + compatible = "domain-idle-state"; + reg = <0x1>; + entry-latency-us = <5000>; + exit-latency-us = <8000>; + min-residency-us = <7000>; + }; + ==PM domain consumers== Required properties: @@ -76,3 +117,5 @@ Example: The node above defines a typical PM domain consumer device, which is located inside a PM domain with index 0 of a power controller represented by a node with the label "power". + +[1]. Documentation/devicetree/bindings/power/domain-idle-state.txt diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 37babf91f2cb..1f6cecc85750 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1760,6 +1760,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted. disable Do not enable intel_pstate as the default scaling driver for the supported processors + passive + Use intel_pstate as a scaling driver, but configure it + to work with generic cpufreq governors (instead of + enabling its internal governor). This mode cannot be + used along with the hardware-managed P-states (HWP) + feature. force Enable intel_pstate on systems that prohibit it by default in favor of acpi-cpufreq. Forcing the intel_pstate driver @@ -1780,6 +1786,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted. Description Table, specifies preferred power management profile as "Enterprise Server" or "Performance Server", then this feature is turned on by default. + per_cpu_perf_limits + Allow per-logical-CPU P-State performance control limits using + cpufreq sysfs interface intremap= [X86-64, Intel-IOMMU] on enable Interrupt Remapping (default) @@ -2325,6 +2334,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted. memory contents and reserves bad memory regions that are detected. + mem_sleep_default= [SUSPEND] Default system suspend mode: + s2idle - Suspend-To-Idle + shallow - Power-On Suspend or equivalent (if supported) + deep - Suspend-To-RAM or equivalent (if supported) + See Documentation/power/states.txt. + meye.*= [HW] Set MotionEye Camera parameters See Documentation/video4linux/meye.txt. @@ -3668,13 +3683,6 @@ bytes respectively. Such letter suffixes can also be entirely omitted. [KNL, SMP] Set scheduler's default relax_domain_level. See Documentation/cgroup-v1/cpusets.txt. - relative_sleep_states= - [SUSPEND] Use sleep state labeling where the deepest - state available other than hibernation is always "mem". - Format: { "0" | "1" } - 0 -- Traditional sleep state labels. - 1 -- Relative sleep state labels. - reserve= [KNL,BUGS] Force the kernel to ignore some iomem area reservetop= [X86-32] diff --git a/Documentation/networking/nf_conntrack-sysctl.txt b/Documentation/networking/nf_conntrack-sysctl.txt index 399e4e866a9c..433b6724797a 100644 --- a/Documentation/networking/nf_conntrack-sysctl.txt +++ b/Documentation/networking/nf_conntrack-sysctl.txt @@ -62,10 +62,13 @@ nf_conntrack_generic_timeout - INTEGER (seconds) protocols. nf_conntrack_helper - BOOLEAN - 0 - disabled - not 0 - enabled (default) + 0 - disabled (default) + not 0 - enabled Enable automatic conntrack helper assignment. + If disabled it is required to set up iptables rules to assign + helpers to connections. See the CT target description in the + iptables-extensions(8) man page for further information. nf_conntrack_icmp_timeout - INTEGER (seconds) default 30 diff --git a/Documentation/power/devices.txt b/Documentation/power/devices.txt index 8ba6625fdd63..73ddea39a9ce 100644 --- a/Documentation/power/devices.txt +++ b/Documentation/power/devices.txt @@ -607,7 +607,9 @@ individually. Instead, a set of devices sharing a power resource can be put into a low-power state together at the same time by turning off the shared power resource. Of course, they also need to be put into the full-power state together, by turning the shared power resource on. A set of devices with this -property is often referred to as a power domain. +property is often referred to as a power domain. A power domain may also be +nested inside another power domain. The nested domain is referred to as the +sub-domain of the parent domain. Support for power domains is provided through the pm_domain field of struct device. This field is a pointer to an object of type struct dev_pm_domain, @@ -629,6 +631,16 @@ support for power domains into subsystem-level callbacks, for example by modifying the platform bus type. Other platforms need not implement it or take it into account in any way. +Devices may be defined as IRQ-safe which indicates to the PM core that their +runtime PM callbacks may be invoked with disabled interrupts (see +Documentation/power/runtime_pm.txt for more information). If an IRQ-safe +device belongs to a PM domain, the runtime PM of the domain will be +disallowed, unless the domain itself is defined as IRQ-safe. However, it +makes sense to define a PM domain as IRQ-safe only if all the devices in it +are IRQ-safe. Moreover, if an IRQ-safe domain has a parent domain, the runtime +PM of the parent is only allowed if the parent itself is IRQ-safe too with the +additional restriction that all child domains of an IRQ-safe parent must also +be IRQ-safe. Device Low Power (suspend) States --------------------------------- diff --git a/Documentation/power/states.txt b/Documentation/power/states.txt index 50f3ef9177c1..8a39ce45d8a0 100644 --- a/Documentation/power/states.txt +++ b/Documentation/power/states.txt @@ -8,25 +8,43 @@ for each state. The states are represented by strings that can be read or written to the /sys/power/state file. Those strings may be "mem", "standby", "freeze" and -"disk", where the last one always represents hibernation (Suspend-To-Disk) and -the meaning of the remaining ones depends on the relative_sleep_states command -line argument. - -For relative_sleep_states=1, the strings "mem", "standby" and "freeze" label the -available non-hibernation sleep states from the deepest to the shallowest, -respectively. In that case, "mem" is always present in /sys/power/state, -because there is at least one non-hibernation sleep state in every system. If -the given system supports two non-hibernation sleep states, "standby" is present -in /sys/power/state in addition to "mem". If the system supports three -non-hibernation sleep states, "freeze" will be present in /sys/power/state in -addition to "mem" and "standby". - -For relative_sleep_states=0, which is the default, the following descriptions -apply. - -state: Suspend-To-Idle +"disk", where the last three always represent Power-On Suspend (if supported), +Suspend-To-Idle and hibernation (Suspend-To-Disk), respectively. + +The meaning of the "mem" string is controlled by the /sys/power/mem_sleep file. +It contains strings representing the available modes of system suspend that may +be triggered by writing "mem" to /sys/power/state. These modes are "s2idle" +(Suspend-To-Idle), "shallow" (Power-On Suspend) and "deep" (Suspend-To-RAM). +The "s2idle" mode is always available, while the other ones are only available +if supported by the platform (if not supported, the strings representing them +are not present in /sys/power/mem_sleep). The string representing the suspend +mode to be used subsequently is enclosed in square brackets. Writing one of +the other strings present in /sys/power/mem_sleep to it causes the suspend mode +to be used subsequently to change to the one represented by that string. + +Consequently, there are two ways to cause the system to go into the +Suspend-To-Idle sleep state. The first one is to write "freeze" directly to +/sys/power/state. The second one is to write "s2idle" to /sys/power/mem_sleep +and then to wrtie "mem" to /sys/power/state. Similarly, there are two ways +to cause the system to go into the Power-On Suspend sleep state (the strings to +write to the control files in that case are "standby" or "shallow" and "mem", +respectively) if that state is supported by the platform. In turn, there is +only one way to cause the system to go into the Suspend-To-RAM state (write +"deep" into /sys/power/mem_sleep and "mem" into /sys/power/state). + +The default suspend mode (ie. the one to be used without writing anything into +/sys/power/mem_sleep) is either "deep" (if Suspend-To-RAM is supported) or +"s2idle", but it can be overridden by the value of the "mem_sleep_default" +parameter in the kernel command line. On some ACPI-based systems, depending on +the information in the FADT, the default may be "s2idle" even if Suspend-To-RAM +is supported. + +The properties of all of the sleep states are described below. + + +State: Suspend-To-Idle ACPI state: S0 -Label: "freeze" +Label: "s2idle" ("freeze") This state is a generic, pure software, light-weight, system sleep state. It allows more energy to be saved relative to runtime idle by freezing user @@ -35,13 +53,13 @@ lower-power than available at run time), such that the processors can spend more time in their idle states. This state can be used for platforms without Power-On Suspend/Suspend-to-RAM -support, or it can be used in addition to Suspend-to-RAM (memory sleep) -to provide reduced resume latency. It is always supported. +support, or it can be used in addition to Suspend-to-RAM to provide reduced +resume latency. It is always supported. State: Standby / Power-On Suspend ACPI State: S1 -Label: "standby" +Label: "shallow" ("standby") This state, if supported, offers moderate, though real, power savings, while providing a relatively low-latency transition back to a working system. No @@ -58,7 +76,7 @@ state. State: Suspend-to-RAM ACPI State: S3 -Label: "mem" +Label: "deep" This state, if supported, offers significant power savings as everything in the system is put into a low-power state, except for memory, which should be placed diff --git a/MAINTAINERS b/MAINTAINERS index ad9b965e5e44..e89a18805bae 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -77,6 +77,7 @@ Descriptions of section entries: Q: Patchwork web based patch tracking system site T: SCM tree type and location. Type is one of: git, hg, quilt, stgit, topgit + B: Bug tracking system location. S: Status, one of the following: Supported: Someone is actually paid to look after this. Maintained: Someone actually looks after it. @@ -281,6 +282,7 @@ L: linux-acpi@vger.kernel.org W: https://01.org/linux-acpi Q: https://patchwork.kernel.org/project/linux-acpi/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm +B: https://bugzilla.kernel.org S: Supported F: drivers/acpi/ F: drivers/pnp/pnpacpi/ @@ -304,6 +306,8 @@ W: https://acpica.org/ W: https://github.com/acpica/acpica/ Q: https://patchwork.kernel.org/project/linux-acpi/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm +B: https://bugzilla.kernel.org +B: https://bugs.acpica.org S: Supported F: drivers/acpi/acpica/ F: include/acpi/ @@ -313,6 +317,7 @@ ACPI FAN DRIVER M: Zhang Rui <rui.zhang@intel.com> L: linux-acpi@vger.kernel.org W: https://01.org/linux-acpi +B: https://bugzilla.kernel.org S: Supported F: drivers/acpi/fan.c @@ -328,6 +333,7 @@ ACPI THERMAL DRIVER M: Zhang Rui <rui.zhang@intel.com> L: linux-acpi@vger.kernel.org W: https://01.org/linux-acpi +B: https://bugzilla.kernel.org S: Supported F: drivers/acpi/*thermal* @@ -335,6 +341,7 @@ ACPI VIDEO DRIVER M: Zhang Rui <rui.zhang@intel.com> L: linux-acpi@vger.kernel.org W: https://01.org/linux-acpi +B: https://bugzilla.kernel.org S: Supported F: drivers/acpi/acpi_video.c @@ -2742,6 +2749,14 @@ L: bcm-kernel-feedback-list@broadcom.com S: Maintained F: drivers/mtd/nand/brcmnand/ +BROADCOM STB AVS CPUFREQ DRIVER +M: Markus Mayer <mmayer@broadcom.com> +M: bcm-kernel-feedback-list@broadcom.com +L: linux-pm@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/cpufreq/brcm,stb-avs-cpu-freq.txt +F: drivers/cpufreq/brcmstb* + BROADCOM SPECIFIC AMBA DRIVER (BCMA) M: RafaÅ‚ MiÅ‚ecki <zajec5@gmail.com> L: linux-wireless@vger.kernel.org @@ -3334,6 +3349,7 @@ 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) +B: https://bugzilla.kernel.org F: Documentation/cpu-freq/ F: drivers/cpufreq/ F: include/linux/cpufreq.h @@ -3373,6 +3389,7 @@ M: Daniel Lezcano <daniel.lezcano@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 +B: https://bugzilla.kernel.org F: drivers/cpuidle/* F: include/linux/cpuidle.h @@ -5663,6 +5680,7 @@ HIBERNATION (aka Software Suspend, aka swsusp) M: "Rafael J. Wysocki" <rjw@rjwysocki.net> M: Pavel Machek <pavel@ucw.cz> L: linux-pm@vger.kernel.org +B: https://bugzilla.kernel.org S: Supported F: arch/x86/power/ F: drivers/base/power/ @@ -6281,9 +6299,11 @@ S: Maintained F: drivers/platform/x86/intel-vbtn.c INTEL IDLE DRIVER +M: Jacob Pan <jacob.jun.pan@linux.intel.com> M: Len Brown <lenb@kernel.org> L: linux-pm@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux.git +B: https://bugzilla.kernel.org S: Supported F: drivers/idle/intel_idle.c @@ -9249,11 +9269,12 @@ S: Maintained F: drivers/pci/host/*layerscape* PCI DRIVER FOR IMX6 -M: Richard Zhu <Richard.Zhu@freescale.com> +M: Richard Zhu <hongxing.zhu@nxp.com> M: Lucas Stach <l.stach@pengutronix.de> L: linux-pci@vger.kernel.org L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained +F: Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.txt F: drivers/pci/host/*imx6* PCI DRIVER FOR TI KEYSTONE @@ -9312,17 +9333,11 @@ F: drivers/pci/host/pci-exynos.c PCI DRIVER FOR SYNOPSIS DESIGNWARE M: Jingoo Han <jingoohan1@gmail.com> -M: Pratyush Anand <pratyush.anand@gmail.com> -L: linux-pci@vger.kernel.org -S: Maintained -F: drivers/pci/host/*designware* - -PCI DRIVER FOR SYNOPSYS PROTOTYPING DEVICE -M: Jose Abreu <Jose.Abreu@synopsys.com> +M: Joao Pinto <Joao.Pinto@synopsys.com> L: linux-pci@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/pci/designware-pcie.txt -F: drivers/pci/host/pcie-designware-plat.c +F: drivers/pci/host/*designware* PCI DRIVER FOR GENERIC OF HOSTS M: Will Deacon <will.deacon@arm.com> @@ -9624,6 +9639,7 @@ POWER MANAGEMENT CORE M: "Rafael J. Wysocki" <rjw@rjwysocki.net> L: linux-pm@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm +B: https://bugzilla.kernel.org S: Supported F: drivers/base/power/ F: include/linux/pm.h @@ -11613,6 +11629,7 @@ M: "Rafael J. Wysocki" <rjw@rjwysocki.net> M: Len Brown <len.brown@intel.com> M: Pavel Machek <pavel@ucw.cz> L: linux-pm@vger.kernel.org +B: https://bugzilla.kernel.org S: Supported F: Documentation/power/ F: arch/x86/kernel/acpi/ @@ -1,8 +1,8 @@ VERSION = 4 PATCHLEVEL = 9 SUBLEVEL = 0 -EXTRAVERSION = -rc6 -NAME = Psychotic Stoned Sheep +EXTRAVERSION = +NAME = Roaring Lionus # *DOCUMENTATION* # To see a list of typical targets execute "make help" @@ -607,6 +607,13 @@ else include/config/auto.conf: ; endif # $(dot-config) +# For the kernel to actually contain only the needed exported symbols, +# we have to build modules as well to determine what those symbols are. +# (this can be evaluated only once include/config/auto.conf has been included) +ifdef CONFIG_TRIM_UNUSED_KSYMS + KBUILD_MODULES := 1 +endif + # The all: target is the default when no target is given on the # command line. # This allow a user to issue only 'make' to build a kernel including modules @@ -944,7 +951,7 @@ ifdef CONFIG_GDB_SCRIPTS endif ifdef CONFIG_TRIM_UNUSED_KSYMS $(Q)$(CONFIG_SHELL) $(srctree)/scripts/adjust_autoksyms.sh \ - "$(MAKE) KBUILD_MODULES=1 -f $(srctree)/Makefile vmlinux_prereq" + "$(MAKE) -f $(srctree)/Makefile vmlinux" endif # standalone target for easier testing @@ -1019,8 +1026,6 @@ prepare2: prepare3 prepare-compiler-check outputmakefile asm-generic prepare1: prepare2 $(version_h) include/generated/utsrelease.h \ include/config/auto.conf $(cmd_crmodverdir) - $(Q)test -e include/generated/autoksyms.h || \ - touch include/generated/autoksyms.h archprepare: archheaders archscripts prepare1 scripts_basic diff --git a/arch/arc/include/asm/delay.h b/arch/arc/include/asm/delay.h index 08e7e2a16ac1..a36e8601114d 100644 --- a/arch/arc/include/asm/delay.h +++ b/arch/arc/include/asm/delay.h @@ -22,10 +22,11 @@ static inline void __delay(unsigned long loops) { __asm__ __volatile__( - " lp 1f \n" - " nop \n" - "1: \n" - : "+l"(loops)); + " mov lp_count, %0 \n" + " lp 1f \n" + " nop \n" + "1: \n" + : : "r"(loops)); } extern void __bad_udelay(void); diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h index 89eeb3720051..e94ca72b974e 100644 --- a/arch/arc/include/asm/pgtable.h +++ b/arch/arc/include/asm/pgtable.h @@ -280,7 +280,7 @@ static inline void pmd_set(pmd_t *pmdp, pte_t *ptep) #define pte_page(pte) pfn_to_page(pte_pfn(pte)) #define mk_pte(page, prot) pfn_pte(page_to_pfn(page), prot) -#define pfn_pte(pfn, prot) __pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot)) +#define pfn_pte(pfn, prot) __pte(__pfn_to_phys(pfn) | pgprot_val(prot)) /* Don't use virt_to_pfn for macros below: could cause truncations for PAE40*/ #define pte_pfn(pte) (pte_val(pte) >> PAGE_SHIFT) diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index 2b96cfc3be75..50d71695cd4e 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -23,7 +23,7 @@ static int l2_line_sz; static int ioc_exists; -int slc_enable = 1, ioc_enable = 1; +int slc_enable = 1, ioc_enable = 0; unsigned long perip_base = ARC_UNCACHED_ADDR_SPACE; /* legacy value for boot */ unsigned long perip_end = 0xFFFFFFFF; /* legacy value */ diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile index befcd2619902..c558ba75cbcc 100644 --- a/arch/arm/boot/dts/Makefile +++ b/arch/arm/boot/dts/Makefile @@ -745,7 +745,6 @@ dtb-$(CONFIG_MACH_SUN4I) += \ sun4i-a10-pcduino2.dtb \ sun4i-a10-pov-protab2-ips9.dtb dtb-$(CONFIG_MACH_SUN5I) += \ - ntc-gr8-evb.dtb \ sun5i-a10s-auxtek-t003.dtb \ sun5i-a10s-auxtek-t004.dtb \ sun5i-a10s-mk802.dtb \ @@ -761,6 +760,7 @@ dtb-$(CONFIG_MACH_SUN5I) += \ sun5i-a13-olinuxino-micro.dtb \ sun5i-a13-q8-tablet.dtb \ sun5i-a13-utoo-p66.dtb \ + sun5i-gr8-evb.dtb \ sun5i-r8-chip.dtb dtb-$(CONFIG_MACH_SUN6I) += \ sun6i-a31-app4-evb1.dtb \ diff --git a/arch/arm/boot/dts/imx7s.dtsi b/arch/arm/boot/dts/imx7s.dtsi index 0d7d5ac6257b..2b6cb05bc01a 100644 --- a/arch/arm/boot/dts/imx7s.dtsi +++ b/arch/arm/boot/dts/imx7s.dtsi @@ -643,9 +643,8 @@ reg = <0x30730000 0x10000>; interrupts = <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX7D_LCDIF_PIXEL_ROOT_CLK>, - <&clks IMX7D_CLK_DUMMY>, - <&clks IMX7D_CLK_DUMMY>; - clock-names = "pix", "axi", "disp_axi"; + <&clks IMX7D_LCDIF_PIXEL_ROOT_CLK>; + clock-names = "pix", "axi"; status = "disabled"; }; }; diff --git a/arch/arm/boot/dts/orion5x-linkstation-lsgl.dts b/arch/arm/boot/dts/orion5x-linkstation-lsgl.dts index 1cf644bfd7ea..51dc734cd5b9 100644 --- a/arch/arm/boot/dts/orion5x-linkstation-lsgl.dts +++ b/arch/arm/boot/dts/orion5x-linkstation-lsgl.dts @@ -82,6 +82,10 @@ gpios = <&gpio0 9 GPIO_ACTIVE_HIGH>; }; +&sata { + nr-ports = <2>; +}; + &ehci1 { status = "okay"; }; diff --git a/arch/arm/boot/dts/stih407-family.dtsi b/arch/arm/boot/dts/stih407-family.dtsi index 91096a49efa9..8f79b4147bba 100644 --- a/arch/arm/boot/dts/stih407-family.dtsi +++ b/arch/arm/boot/dts/stih407-family.dtsi @@ -283,6 +283,8 @@ clock-frequency = <400000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c0_default>; + #address-cells = <1>; + #size-cells = <0>; status = "disabled"; }; @@ -296,6 +298,8 @@ clock-frequency = <400000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c1_default>; + #address-cells = <1>; + #size-cells = <0>; status = "disabled"; }; @@ -309,6 +313,8 @@ clock-frequency = <400000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c2_default>; + #address-cells = <1>; + #size-cells = <0>; status = "disabled"; }; @@ -322,6 +328,8 @@ clock-frequency = <400000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c3_default>; + #address-cells = <1>; + #size-cells = <0>; status = "disabled"; }; @@ -335,6 +343,8 @@ clock-frequency = <400000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c4_default>; + #address-cells = <1>; + #size-cells = <0>; status = "disabled"; }; @@ -348,6 +358,8 @@ clock-frequency = <400000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c5_default>; + #address-cells = <1>; + #size-cells = <0>; status = "disabled"; }; @@ -363,6 +375,8 @@ clock-frequency = <400000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c10_default>; + #address-cells = <1>; + #size-cells = <0>; status = "disabled"; }; @@ -376,6 +390,8 @@ clock-frequency = <400000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c11_default>; + #address-cells = <1>; + #size-cells = <0>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/ntc-gr8-evb.dts b/arch/arm/boot/dts/sun5i-gr8-evb.dts index 4b622f3b5220..714381fd64d7 100644 --- a/arch/arm/boot/dts/ntc-gr8-evb.dts +++ b/arch/arm/boot/dts/sun5i-gr8-evb.dts @@ -44,7 +44,7 @@ */ /dts-v1/; -#include "ntc-gr8.dtsi" +#include "sun5i-gr8.dtsi" #include "sunxi-common-regulators.dtsi" #include <dt-bindings/gpio/gpio.h> diff --git a/arch/arm/boot/dts/ntc-gr8.dtsi b/arch/arm/boot/dts/sun5i-gr8.dtsi index ca54e03ef366..ca54e03ef366 100644 --- a/arch/arm/boot/dts/ntc-gr8.dtsi +++ b/arch/arm/boot/dts/sun5i-gr8.dtsi diff --git a/arch/arm/boot/dts/sun8i-h3.dtsi b/arch/arm/boot/dts/sun8i-h3.dtsi index 75a865406d3e..f4ba088b225e 100644 --- a/arch/arm/boot/dts/sun8i-h3.dtsi +++ b/arch/arm/boot/dts/sun8i-h3.dtsi @@ -410,7 +410,7 @@ }; uart3_pins: uart3 { - allwinner,pins = "PG13", "PG14"; + allwinner,pins = "PA13", "PA14"; allwinner,function = "uart3"; allwinner,drive = <SUN4I_PINCTRL_10_MA>; allwinner,pull = <SUN4I_PINCTRL_NO_PULL>; diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild index 0745538b26d3..55e0e3ea9cb6 100644 --- a/arch/arm/include/asm/Kbuild +++ b/arch/arm/include/asm/Kbuild @@ -8,7 +8,6 @@ generic-y += early_ioremap.h generic-y += emergency-restart.h generic-y += errno.h generic-y += exec.h -generic-y += export.h generic-y += ioctl.h generic-y += ipcbuf.h generic-y += irq_regs.h diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index 68c2c097cffe..ad325a8c7e1e 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -33,7 +33,7 @@ endif obj-$(CONFIG_CPU_IDLE) += cpuidle.o obj-$(CONFIG_ISA_DMA_API) += dma.o obj-$(CONFIG_FIQ) += fiq.o fiqasm.o -obj-$(CONFIG_MODULES) += module.o +obj-$(CONFIG_MODULES) += armksyms.o module.o obj-$(CONFIG_ARM_MODULE_PLTS) += module-plts.o obj-$(CONFIG_ISA_DMA) += dma-isa.o obj-$(CONFIG_PCI) += bios32.o isa.o diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c new file mode 100644 index 000000000000..7e45f69a0ddc --- /dev/null +++ b/arch/arm/kernel/armksyms.c @@ -0,0 +1,183 @@ +/* + * linux/arch/arm/kernel/armksyms.c + * + * Copyright (C) 2000 Russell King + * + * 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 + * published by the Free Software Foundation. + */ +#include <linux/export.h> +#include <linux/sched.h> +#include <linux/string.h> +#include <linux/cryptohash.h> +#include <linux/delay.h> +#include <linux/in6.h> +#include <linux/syscalls.h> +#include <linux/uaccess.h> +#include <linux/io.h> +#include <linux/arm-smccc.h> + +#include <asm/checksum.h> +#include <asm/ftrace.h> + +/* + * libgcc functions - functions that are used internally by the + * compiler... (prototypes are not correct though, but that + * doesn't really matter since they're not versioned). + */ +extern void __ashldi3(void); +extern void __ashrdi3(void); +extern void __divsi3(void); +extern void __lshrdi3(void); +extern void __modsi3(void); +extern void __muldi3(void); +extern void __ucmpdi2(void); +extern void __udivsi3(void); +extern void __umodsi3(void); +extern void __do_div64(void); +extern void __bswapsi2(void); +extern void __bswapdi2(void); + +extern void __aeabi_idiv(void); +extern void __aeabi_idivmod(void); +extern void __aeabi_lasr(void); +extern void __aeabi_llsl(void); +extern void __aeabi_llsr(void); +extern void __aeabi_lmul(void); +extern void __aeabi_uidiv(void); +extern void __aeabi_uidivmod(void); +extern void __aeabi_ulcmp(void); + +extern void fpundefinstr(void); + +void mmioset(void *, unsigned int, size_t); +void mmiocpy(void *, const void *, size_t); + + /* platform dependent support */ +EXPORT_SYMBOL(arm_delay_ops); + + /* networking */ +EXPORT_SYMBOL(csum_partial); +EXPORT_SYMBOL(csum_partial_copy_from_user); +EXPORT_SYMBOL(csum_partial_copy_nocheck); +EXPORT_SYMBOL(__csum_ipv6_magic); + + /* io */ +#ifndef __raw_readsb +EXPORT_SYMBOL(__raw_readsb); +#endif +#ifndef __raw_readsw +EXPORT_SYMBOL(__raw_readsw); +#endif +#ifndef __raw_readsl +EXPORT_SYMBOL(__raw_readsl); +#endif +#ifndef __raw_writesb +EXPORT_SYMBOL(__raw_writesb); +#endif +#ifndef __raw_writesw +EXPORT_SYMBOL(__raw_writesw); +#endif +#ifndef __raw_writesl +EXPORT_SYMBOL(__raw_writesl); +#endif + + /* string / mem functions */ +EXPORT_SYMBOL(strchr); +EXPORT_SYMBOL(strrchr); +EXPORT_SYMBOL(memset); +EXPORT_SYMBOL(memcpy); +EXPORT_SYMBOL(memmove); +EXPORT_SYMBOL(memchr); +EXPORT_SYMBOL(__memzero); + +EXPORT_SYMBOL(mmioset); +EXPORT_SYMBOL(mmiocpy); + +#ifdef CONFIG_MMU +EXPORT_SYMBOL(copy_page); + +EXPORT_SYMBOL(arm_copy_from_user); +EXPORT_SYMBOL(arm_copy_to_user); +EXPORT_SYMBOL(arm_clear_user); + +EXPORT_SYMBOL(__get_user_1); +EXPORT_SYMBOL(__get_user_2); +EXPORT_SYMBOL(__get_user_4); +EXPORT_SYMBOL(__get_user_8); + +#ifdef __ARMEB__ +EXPORT_SYMBOL(__get_user_64t_1); +EXPORT_SYMBOL(__get_user_64t_2); +EXPORT_SYMBOL(__get_user_64t_4); +EXPORT_SYMBOL(__get_user_32t_8); +#endif + +EXPORT_SYMBOL(__put_user_1); +EXPORT_SYMBOL(__put_user_2); +EXPORT_SYMBOL(__put_user_4); +EXPORT_SYMBOL(__put_user_8); +#endif + + /* gcc lib functions */ +EXPORT_SYMBOL(__ashldi3); +EXPORT_SYMBOL(__ashrdi3); +EXPORT_SYMBOL(__divsi3); +EXPORT_SYMBOL(__lshrdi3); +EXPORT_SYMBOL(__modsi3); +EXPORT_SYMBOL(__muldi3); +EXPORT_SYMBOL(__ucmpdi2); +EXPORT_SYMBOL(__udivsi3); +EXPORT_SYMBOL(__umodsi3); +EXPORT_SYMBOL(__do_div64); +EXPORT_SYMBOL(__bswapsi2); +EXPORT_SYMBOL(__bswapdi2); + +#ifdef CONFIG_AEABI +EXPORT_SYMBOL(__aeabi_idiv); +EXPORT_SYMBOL(__aeabi_idivmod); +EXPORT_SYMBOL(__aeabi_lasr); +EXPORT_SYMBOL(__aeabi_llsl); +EXPORT_SYMBOL(__aeabi_llsr); +EXPORT_SYMBOL(__aeabi_lmul); +EXPORT_SYMBOL(__aeabi_uidiv); +EXPORT_SYMBOL(__aeabi_uidivmod); +EXPORT_SYMBOL(__aeabi_ulcmp); +#endif + + /* bitops */ +EXPORT_SYMBOL(_set_bit); +EXPORT_SYMBOL(_test_and_set_bit); +EXPORT_SYMBOL(_clear_bit); +EXPORT_SYMBOL(_test_and_clear_bit); +EXPORT_SYMBOL(_change_bit); +EXPORT_SYMBOL(_test_and_change_bit); +EXPORT_SYMBOL(_find_first_zero_bit_le); +EXPORT_SYMBOL(_find_next_zero_bit_le); +EXPORT_SYMBOL(_find_first_bit_le); +EXPORT_SYMBOL(_find_next_bit_le); + +#ifdef __ARMEB__ +EXPORT_SYMBOL(_find_first_zero_bit_be); +EXPORT_SYMBOL(_find_next_zero_bit_be); +EXPORT_SYMBOL(_find_first_bit_be); +EXPORT_SYMBOL(_find_next_bit_be); +#endif + +#ifdef CONFIG_FUNCTION_TRACER +#ifdef CONFIG_OLD_MCOUNT +EXPORT_SYMBOL(mcount); +#endif +EXPORT_SYMBOL(__gnu_mcount_nc); +#endif + +#ifdef CONFIG_ARM_PATCH_PHYS_VIRT +EXPORT_SYMBOL(__pv_phys_pfn_offset); +EXPORT_SYMBOL(__pv_offset); +#endif + +#ifdef CONFIG_HAVE_ARM_SMCCC +EXPORT_SYMBOL(arm_smccc_smc); +EXPORT_SYMBOL(arm_smccc_hvc); +#endif diff --git a/arch/arm/kernel/entry-ftrace.S b/arch/arm/kernel/entry-ftrace.S index b629d3f11c3d..c73c4030ca5d 100644 --- a/arch/arm/kernel/entry-ftrace.S +++ b/arch/arm/kernel/entry-ftrace.S @@ -7,7 +7,6 @@ #include <asm/assembler.h> #include <asm/ftrace.h> #include <asm/unwind.h> -#include <asm/export.h> #include "entry-header.S" @@ -154,7 +153,6 @@ ENTRY(mcount) __mcount _old #endif ENDPROC(mcount) -EXPORT_SYMBOL(mcount) #ifdef CONFIG_DYNAMIC_FTRACE ENTRY(ftrace_caller_old) @@ -207,7 +205,6 @@ UNWIND(.fnstart) #endif UNWIND(.fnend) ENDPROC(__gnu_mcount_nc) -EXPORT_SYMBOL(__gnu_mcount_nc) #ifdef CONFIG_DYNAMIC_FTRACE ENTRY(ftrace_caller) diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index f41cee4c5746..04286fd9e09c 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -22,7 +22,6 @@ #include <asm/memory.h> #include <asm/thread_info.h> #include <asm/pgtable.h> -#include <asm/export.h> #if defined(CONFIG_DEBUG_LL) && !defined(CONFIG_DEBUG_SEMIHOSTING) #include CONFIG_DEBUG_LL_INCLUDE @@ -728,8 +727,6 @@ __pv_phys_pfn_offset: __pv_offset: .quad 0 .size __pv_offset, . -__pv_offset -EXPORT_SYMBOL(__pv_phys_pfn_offset) -EXPORT_SYMBOL(__pv_offset) #endif #include "head-common.S" diff --git a/arch/arm/kernel/smccc-call.S b/arch/arm/kernel/smccc-call.S index 37669e7e13af..2e48b674aab1 100644 --- a/arch/arm/kernel/smccc-call.S +++ b/arch/arm/kernel/smccc-call.S @@ -16,7 +16,6 @@ #include <asm/opcodes-sec.h> #include <asm/opcodes-virt.h> #include <asm/unwind.h> -#include <asm/export.h> /* * Wrap c macros in asm macros to delay expansion until after the @@ -52,7 +51,6 @@ UNWIND( .fnend) ENTRY(arm_smccc_smc) SMCCC SMCCC_SMC ENDPROC(arm_smccc_smc) -EXPORT_SYMBOL(arm_smccc_smc) /* * void smccc_hvc(unsigned long a0, unsigned long a1, unsigned long a2, @@ -62,4 +60,3 @@ EXPORT_SYMBOL(arm_smccc_smc) ENTRY(arm_smccc_hvc) SMCCC SMCCC_HVC ENDPROC(arm_smccc_hvc) -EXPORT_SYMBOL(arm_smccc_hvc) diff --git a/arch/arm/lib/ashldi3.S b/arch/arm/lib/ashldi3.S index a7e7de89bd75..b05e95840651 100644 --- a/arch/arm/lib/ashldi3.S +++ b/arch/arm/lib/ashldi3.S @@ -28,7 +28,6 @@ Boston, MA 02110-1301, USA. */ #include <linux/linkage.h> #include <asm/assembler.h> -#include <asm/export.h> #ifdef __ARMEB__ #define al r1 @@ -53,5 +52,3 @@ ENTRY(__aeabi_llsl) ENDPROC(__ashldi3) ENDPROC(__aeabi_llsl) -EXPORT_SYMBOL(__ashldi3) -EXPORT_SYMBOL(__aeabi_llsl) diff --git a/arch/arm/lib/ashrdi3.S b/arch/arm/lib/ashrdi3.S index 490336e42518..275d7d2341a4 100644 --- a/arch/arm/lib/ashrdi3.S +++ b/arch/arm/lib/ashrdi3.S @@ -28,7 +28,6 @@ Boston, MA 02110-1301, USA. */ #include <linux/linkage.h> #include <asm/assembler.h> -#include <asm/export.h> #ifdef __ARMEB__ #define al r1 @@ -53,5 +52,3 @@ ENTRY(__aeabi_lasr) ENDPROC(__ashrdi3) ENDPROC(__aeabi_lasr) -EXPORT_SYMBOL(__ashrdi3) -EXPORT_SYMBOL(__aeabi_lasr) diff --git a/arch/arm/lib/bitops.h b/arch/arm/lib/bitops.h index df06638b327c..7d807cfd8ef5 100644 --- a/arch/arm/lib/bitops.h +++ b/arch/arm/lib/bitops.h @@ -1,6 +1,5 @@ #include <asm/assembler.h> #include <asm/unwind.h> -#include <asm/export.h> #if __LINUX_ARM_ARCH__ >= 6 .macro bitop, name, instr @@ -26,7 +25,6 @@ UNWIND( .fnstart ) bx lr UNWIND( .fnend ) ENDPROC(\name ) -EXPORT_SYMBOL(\name ) .endm .macro testop, name, instr, store @@ -57,7 +55,6 @@ UNWIND( .fnstart ) 2: bx lr UNWIND( .fnend ) ENDPROC(\name ) -EXPORT_SYMBOL(\name ) .endm #else .macro bitop, name, instr @@ -77,7 +74,6 @@ UNWIND( .fnstart ) ret lr UNWIND( .fnend ) ENDPROC(\name ) -EXPORT_SYMBOL(\name ) .endm /** @@ -106,6 +102,5 @@ UNWIND( .fnstart ) ret lr UNWIND( .fnend ) ENDPROC(\name ) -EXPORT_SYMBOL(\name ) .endm #endif diff --git a/arch/arm/lib/bswapsdi2.S b/arch/arm/lib/bswapsdi2.S index f05f78247304..07cda737bb11 100644 --- a/arch/arm/lib/bswapsdi2.S +++ b/arch/arm/lib/bswapsdi2.S @@ -1,6 +1,5 @@ #include <linux/linkage.h> #include <asm/assembler.h> -#include <asm/export.h> #if __LINUX_ARM_ARCH__ >= 6 ENTRY(__bswapsi2) @@ -36,5 +35,3 @@ ENTRY(__bswapdi2) ret lr ENDPROC(__bswapdi2) #endif -EXPORT_SYMBOL(__bswapsi2) -EXPORT_SYMBOL(__bswapdi2) diff --git a/arch/arm/lib/clear_user.S b/arch/arm/lib/clear_user.S index b566154f5cf4..e936352ccb00 100644 --- a/arch/arm/lib/clear_user.S +++ b/arch/arm/lib/clear_user.S @@ -10,7 +10,6 @@ #include <linux/linkage.h> #include <asm/assembler.h> #include <asm/unwind.h> -#include <asm/export.h> .text @@ -51,9 +50,6 @@ USER( strnebt r2, [r0]) UNWIND(.fnend) ENDPROC(arm_clear_user) ENDPROC(__clear_user_std) -#ifndef CONFIG_UACCESS_WITH_MEMCPY -EXPORT_SYMBOL(arm_clear_user) -#endif .pushsection .text.fixup,"ax" .align 0 diff --git a/arch/arm/lib/copy_from_user.S b/arch/arm/lib/copy_from_user.S index 63e4c1ed0225..7a4b06049001 100644 --- a/arch/arm/lib/copy_from_user.S +++ b/arch/arm/lib/copy_from_user.S @@ -13,7 +13,6 @@ #include <linux/linkage.h> #include <asm/assembler.h> #include <asm/unwind.h> -#include <asm/export.h> /* * Prototype: @@ -95,7 +94,6 @@ ENTRY(arm_copy_from_user) #include "copy_template.S" ENDPROC(arm_copy_from_user) -EXPORT_SYMBOL(arm_copy_from_user) .pushsection .fixup,"ax" .align 0 diff --git a/arch/arm/lib/copy_page.S b/arch/arm/lib/copy_page.S index d97851d4af7a..6ee2f6706f86 100644 --- a/arch/arm/lib/copy_page.S +++ b/arch/arm/lib/copy_page.S @@ -13,7 +13,6 @@ #include <asm/assembler.h> #include <asm/asm-offsets.h> #include <asm/cache.h> -#include <asm/export.h> #define COPY_COUNT (PAGE_SZ / (2 * L1_CACHE_BYTES) PLD( -1 )) @@ -46,4 +45,3 @@ ENTRY(copy_page) PLD( beq 2b ) ldmfd sp!, {r4, pc} @ 3 ENDPROC(copy_page) -EXPORT_SYMBOL(copy_page) diff --git a/arch/arm/lib/copy_to_user.S b/arch/arm/lib/copy_to_user.S index 592c179112d1..caf5019d8161 100644 --- a/arch/arm/lib/copy_to_user.S +++ b/arch/arm/lib/copy_to_user.S @@ -13,7 +13,6 @@ #include <linux/linkage.h> #include <asm/assembler.h> #include <asm/unwind.h> -#include <asm/export.h> /* * Prototype: @@ -100,9 +99,6 @@ WEAK(arm_copy_to_user) ENDPROC(arm_copy_to_user) ENDPROC(__copy_to_user_std) -#ifndef CONFIG_UACCESS_WITH_MEMCPY -EXPORT_SYMBOL(arm_copy_to_user) -#endif .pushsection .text.fixup,"ax" .align 0 diff --git a/arch/arm/lib/csumipv6.S b/arch/arm/lib/csumipv6.S index 68603b5ee537..3ac6ef01bc43 100644 --- a/arch/arm/lib/csumipv6.S +++ b/arch/arm/lib/csumipv6.S @@ -9,7 +9,6 @@ */ #include <linux/linkage.h> #include <asm/assembler.h> -#include <asm/export.h> .text @@ -31,4 +30,4 @@ ENTRY(__csum_ipv6_magic) adcs r0, r0, #0 ldmfd sp!, {pc} ENDPROC(__csum_ipv6_magic) -EXPORT_SYMBOL(__csum_ipv6_magic) + diff --git a/arch/arm/lib/csumpartial.S b/arch/arm/lib/csumpartial.S index 830b20e81c37..984e0f29d548 100644 --- a/arch/arm/lib/csumpartial.S +++ b/arch/arm/lib/csumpartial.S @@ -9,7 +9,6 @@ */ #include <linux/linkage.h> #include <asm/assembler.h> -#include <asm/export.h> .text @@ -141,4 +140,3 @@ ENTRY(csum_partial) bne 4b b .Lless4 ENDPROC(csum_partial) -EXPORT_SYMBOL(csum_partial) diff --git a/arch/arm/lib/csumpartialcopy.S b/arch/arm/lib/csumpartialcopy.S index 9c3383fed129..d03fc71fc88c 100644 --- a/arch/arm/lib/csumpartialcopy.S +++ b/arch/arm/lib/csumpartialcopy.S @@ -49,6 +49,5 @@ #define FN_ENTRY ENTRY(csum_partial_copy_nocheck) #define FN_EXIT ENDPROC(csum_partial_copy_nocheck) -#define FN_EXPORT EXPORT_SYMBOL(csum_partial_copy_nocheck) #include "csumpartialcopygeneric.S" diff --git a/arch/arm/lib/csumpartialcopygeneric.S b/arch/arm/lib/csumpartialcopygeneric.S index 8b94d20e51d1..10b45909610c 100644 --- a/arch/arm/lib/csumpartialcopygeneric.S +++ b/arch/arm/lib/csumpartialcopygeneric.S @@ -8,7 +8,6 @@ * published by the Free Software Foundation. */ #include <asm/assembler.h> -#include <asm/export.h> /* * unsigned int @@ -332,4 +331,3 @@ FN_ENTRY mov r5, r4, get_byte_1 b .Lexit FN_EXIT -FN_EXPORT diff --git a/arch/arm/lib/csumpartialcopyuser.S b/arch/arm/lib/csumpartialcopyuser.S index 5d495edf3d83..1712f132b80d 100644 --- a/arch/arm/lib/csumpartialcopyuser.S +++ b/arch/arm/lib/csumpartialcopyuser.S @@ -73,7 +73,6 @@ #define FN_ENTRY ENTRY(csum_partial_copy_from_user) #define FN_EXIT ENDPROC(csum_partial_copy_from_user) -#define FN_EXPORT EXPORT_SYMBOL(csum_partial_copy_from_user) #include "csumpartialcopygeneric.S" diff --git a/arch/arm/lib/delay.c b/arch/arm/lib/delay.c index 69aad80a3af4..2cef11884857 100644 --- a/arch/arm/lib/delay.c +++ b/arch/arm/lib/delay.c @@ -24,7 +24,6 @@ #include <linux/init.h> #include <linux/kernel.h> #include <linux/module.h> -#include <linux/export.h> #include <linux/timex.h> /* @@ -35,7 +34,6 @@ struct arm_delay_ops arm_delay_ops __ro_after_init = { .const_udelay = __loop_const_udelay, .udelay = __loop_udelay, }; -EXPORT_SYMBOL(arm_delay_ops); static const struct delay_timer *delay_timer; static bool delay_calibrated; diff --git a/arch/arm/lib/div64.S b/arch/arm/lib/div64.S index 0c9e1c18fc9e..a9eafe4981eb 100644 --- a/arch/arm/lib/div64.S +++ b/arch/arm/lib/div64.S @@ -15,7 +15,6 @@ #include <linux/linkage.h> #include <asm/assembler.h> #include <asm/unwind.h> -#include <asm/export.h> #ifdef __ARMEB__ #define xh r0 @@ -211,4 +210,3 @@ Ldiv0_64: UNWIND(.fnend) ENDPROC(__do_div64) -EXPORT_SYMBOL(__do_div64) diff --git a/arch/arm/lib/findbit.S b/arch/arm/lib/findbit.S index 26302b8cd38f..7848780e8834 100644 --- a/arch/arm/lib/findbit.S +++ b/arch/arm/lib/findbit.S @@ -15,7 +15,6 @@ */ #include <linux/linkage.h> #include <asm/assembler.h> -#include <asm/export.h> .text /* @@ -38,7 +37,6 @@ ENTRY(_find_first_zero_bit_le) 3: mov r0, r1 @ no free bits ret lr ENDPROC(_find_first_zero_bit_le) -EXPORT_SYMBOL(_find_first_zero_bit_le) /* * Purpose : Find next 'zero' bit @@ -59,7 +57,6 @@ ENTRY(_find_next_zero_bit_le) add r2, r2, #1 @ align bit pointer b 2b @ loop for next bit ENDPROC(_find_next_zero_bit_le) -EXPORT_SYMBOL(_find_next_zero_bit_le) /* * Purpose : Find a 'one' bit @@ -81,7 +78,6 @@ ENTRY(_find_first_bit_le) 3: mov r0, r1 @ no free bits ret lr ENDPROC(_find_first_bit_le) -EXPORT_SYMBOL(_find_first_bit_le) /* * Purpose : Find next 'one' bit @@ -101,7 +97,6 @@ ENTRY(_find_next_bit_le) add r2, r2, #1 @ align bit pointer b 2b @ loop for next bit ENDPROC(_find_next_bit_le) -EXPORT_SYMBOL(_find_next_bit_le) #ifdef __ARMEB__ @@ -121,7 +116,6 @@ ENTRY(_find_first_zero_bit_be) 3: mov r0, r1 @ no free bits ret lr ENDPROC(_find_first_zero_bit_be) -EXPORT_SYMBOL(_find_first_zero_bit_be) ENTRY(_find_next_zero_bit_be) teq r1, #0 @@ -139,7 +133,6 @@ ENTRY(_find_next_zero_bit_be) add r2, r2, #1 @ align bit pointer b 2b @ loop for next bit ENDPROC(_find_next_zero_bit_be) -EXPORT_SYMBOL(_find_next_zero_bit_be) ENTRY(_find_first_bit_be) teq r1, #0 @@ -157,7 +150,6 @@ ENTRY(_find_first_bit_be) 3: mov r0, r1 @ no free bits ret lr ENDPROC(_find_first_bit_be) -EXPORT_SYMBOL(_find_first_bit_be) ENTRY(_find_next_bit_be) teq r1, #0 @@ -174,7 +166,6 @@ ENTRY(_find_next_bit_be) add r2, r2, #1 @ align bit pointer b 2b @ loop for next bit ENDPROC(_find_next_bit_be) -EXPORT_SYMBOL(_find_next_bit_be) #endif diff --git a/arch/arm/lib/getuser.S b/arch/arm/lib/getuser.S index 9d09a38e73af..8ecfd15c3a02 100644 --- a/arch/arm/lib/getuser.S +++ b/arch/arm/lib/getuser.S @@ -31,7 +31,6 @@ #include <asm/assembler.h> #include <asm/errno.h> #include <asm/domain.h> -#include <asm/export.h> ENTRY(__get_user_1) check_uaccess r0, 1, r1, r2, __get_user_bad @@ -39,7 +38,6 @@ ENTRY(__get_user_1) mov r0, #0 ret lr ENDPROC(__get_user_1) -EXPORT_SYMBOL(__get_user_1) ENTRY(__get_user_2) check_uaccess r0, 2, r1, r2, __get_user_bad @@ -60,7 +58,6 @@ rb .req r0 mov r0, #0 ret lr ENDPROC(__get_user_2) -EXPORT_SYMBOL(__get_user_2) ENTRY(__get_user_4) check_uaccess r0, 4, r1, r2, __get_user_bad @@ -68,7 +65,6 @@ ENTRY(__get_user_4) mov r0, #0 ret lr ENDPROC(__get_user_4) -EXPORT_SYMBOL(__get_user_4) ENTRY(__get_user_8) check_uaccess r0, 8, r1, r2, __get_user_bad @@ -82,7 +78,6 @@ ENTRY(__get_user_8) mov r0, #0 ret lr ENDPROC(__get_user_8) -EXPORT_SYMBOL(__get_user_8) #ifdef __ARMEB__ ENTRY(__get_user_32t_8) @@ -96,7 +91,6 @@ ENTRY(__get_user_32t_8) mov r0, #0 ret lr ENDPROC(__get_user_32t_8) -EXPORT_SYMBOL(__get_user_32t_8) ENTRY(__get_user_64t_1) check_uaccess r0, 1, r1, r2, __get_user_bad8 @@ -104,7 +98,6 @@ ENTRY(__get_user_64t_1) mov r0, #0 ret lr ENDPROC(__get_user_64t_1) -EXPORT_SYMBOL(__get_user_64t_1) ENTRY(__get_user_64t_2) check_uaccess r0, 2, r1, r2, __get_user_bad8 @@ -121,7 +114,6 @@ rb .req r0 mov r0, #0 ret lr ENDPROC(__get_user_64t_2) -EXPORT_SYMBOL(__get_user_64t_2) ENTRY(__get_user_64t_4) check_uaccess r0, 4, r1, r2, __get_user_bad8 @@ -129,7 +121,6 @@ ENTRY(__get_user_64t_4) mov r0, #0 ret lr ENDPROC(__get_user_64t_4) -EXPORT_SYMBOL(__get_user_64t_4) #endif __get_user_bad8: diff --git a/arch/arm/lib/io-readsb.S b/arch/arm/lib/io-readsb.S index 3dff7a3a2aef..c31b2f3153f1 100644 --- a/arch/arm/lib/io-readsb.S +++ b/arch/arm/lib/io-readsb.S @@ -9,7 +9,6 @@ */ #include <linux/linkage.h> #include <asm/assembler.h> -#include <asm/export.h> .Linsb_align: rsb ip, ip, #4 cmp ip, r2 @@ -122,4 +121,3 @@ ENTRY(__raw_readsb) ldmfd sp!, {r4 - r6, pc} ENDPROC(__raw_readsb) -EXPORT_SYMBOL(__raw_readsb) diff --git a/arch/arm/lib/io-readsl.S b/arch/arm/lib/io-readsl.S index bfd39682325b..2ed86fa5465f 100644 --- a/arch/arm/lib/io-readsl.S +++ b/arch/arm/lib/io-readsl.S @@ -9,7 +9,6 @@ */ #include <linux/linkage.h> #include <asm/assembler.h> -#include <asm/export.h> ENTRY(__raw_readsl) teq r2, #0 @ do we have to check for the zero len? @@ -78,4 +77,3 @@ ENTRY(__raw_readsl) strb r3, [r1, #0] ret lr ENDPROC(__raw_readsl) -EXPORT_SYMBOL(__raw_readsl) diff --git a/arch/arm/lib/io-readsw-armv3.S b/arch/arm/lib/io-readsw-armv3.S index b3af3db6caac..413da9914529 100644 --- a/arch/arm/lib/io-readsw-armv3.S +++ b/arch/arm/lib/io-readsw-armv3.S @@ -9,7 +9,6 @@ */ #include <linux/linkage.h> #include <asm/assembler.h> -#include <asm/export.h> .Linsw_bad_alignment: adr r0, .Linsw_bad_align_msg @@ -104,4 +103,4 @@ ENTRY(__raw_readsw) ldmfd sp!, {r4, r5, r6, pc} -EXPORT_SYMBOL(__raw_readsw) + diff --git a/arch/arm/lib/io-readsw-armv4.S b/arch/arm/lib/io-readsw-armv4.S index 3c7a7a40b33e..d9a45e9692ae 100644 --- a/arch/arm/lib/io-readsw-armv4.S +++ b/arch/arm/lib/io-readsw-armv4.S @@ -9,7 +9,6 @@ */ #include <linux/linkage.h> #include <asm/assembler.h> -#include <asm/export.h> .macro pack, rd, hw1, hw2 #ifndef __ARMEB__ @@ -130,4 +129,3 @@ ENTRY(__raw_readsw) strneb ip, [r1] ldmfd sp!, {r4, pc} ENDPROC(__raw_readsw) -EXPORT_SYMBOL(__raw_readsw) diff --git a/arch/arm/lib/io-writesb.S b/arch/arm/lib/io-writesb.S index fa3633594415..a46bbc9b168b 100644 --- a/arch/arm/lib/io-writesb.S +++ b/arch/arm/lib/io-writesb.S @@ -9,7 +9,6 @@ */ #include <linux/linkage.h> #include <asm/assembler.h> -#include <asm/export.h> .macro outword, rd #ifndef __ARMEB__ @@ -93,4 +92,3 @@ ENTRY(__raw_writesb) ldmfd sp!, {r4, r5, pc} ENDPROC(__raw_writesb) -EXPORT_SYMBOL(__raw_writesb) diff --git a/arch/arm/lib/io-writesl.S b/arch/arm/lib/io-writesl.S index 98ed6aec0b47..4ea2435988c1 100644 --- a/arch/arm/lib/io-writesl.S +++ b/arch/arm/lib/io-writesl.S @@ -9,7 +9,6 @@ */ #include <linux/linkage.h> #include <asm/assembler.h> -#include <asm/export.h> ENTRY(__raw_writesl) teq r2, #0 @ do we have to check for the zero len? @@ -66,4 +65,3 @@ ENTRY(__raw_writesl) bne 6b ret lr ENDPROC(__raw_writesl) -EXPORT_SYMBOL(__raw_writesl) diff --git a/arch/arm/lib/io-writesw-armv3.S b/arch/arm/lib/io-writesw-armv3.S index 577184c082bb..121789eb6802 100644 --- a/arch/arm/lib/io-writesw-armv3.S +++ b/arch/arm/lib/io-writesw-armv3.S @@ -9,7 +9,6 @@ */ #include <linux/linkage.h> #include <asm/assembler.h> -#include <asm/export.h> .Loutsw_bad_alignment: adr r0, .Loutsw_bad_align_msg @@ -125,4 +124,3 @@ ENTRY(__raw_writesw) strne ip, [r0] ldmfd sp!, {r4, r5, r6, pc} -EXPORT_SYMBOL(__raw_writesw) diff --git a/arch/arm/lib/io-writesw-armv4.S b/arch/arm/lib/io-writesw-armv4.S index e335f489d1fc..269f90c51ad2 100644 --- a/arch/arm/lib/io-writesw-armv4.S +++ b/arch/arm/lib/io-writesw-armv4.S @@ -9,7 +9,6 @@ */ #include <linux/linkage.h> #include <asm/assembler.h> -#include <asm/export.h> .macro outword, rd #ifndef __ARMEB__ @@ -99,4 +98,3 @@ ENTRY(__raw_writesw) strneh ip, [r0] ret lr ENDPROC(__raw_writesw) -EXPORT_SYMBOL(__raw_writesw) diff --git a/arch/arm/lib/lib1funcs.S b/arch/arm/lib/lib1funcs.S index f541bc013bff..9397b2e532af 100644 --- a/arch/arm/lib/lib1funcs.S +++ b/arch/arm/lib/lib1funcs.S @@ -36,7 +36,6 @@ Boston, MA 02111-1307, USA. */ #include <linux/linkage.h> #include <asm/assembler.h> #include <asm/unwind.h> -#include <asm/export.h> .macro ARM_DIV_BODY dividend, divisor, result, curbit @@ -239,8 +238,6 @@ UNWIND(.fnstart) UNWIND(.fnend) ENDPROC(__udivsi3) ENDPROC(__aeabi_uidiv) -EXPORT_SYMBOL(__udivsi3) -EXPORT_SYMBOL(__aeabi_uidiv) ENTRY(__umodsi3) UNWIND(.fnstart) @@ -259,7 +256,6 @@ UNWIND(.fnstart) UNWIND(.fnend) ENDPROC(__umodsi3) -EXPORT_SYMBOL(__umodsi3) #ifdef CONFIG_ARM_PATCH_IDIV .align 3 @@ -307,8 +303,6 @@ UNWIND(.fnstart) UNWIND(.fnend) ENDPROC(__divsi3) ENDPROC(__aeabi_idiv) -EXPORT_SYMBOL(__divsi3) -EXPORT_SYMBOL(__aeabi_idiv) ENTRY(__modsi3) UNWIND(.fnstart) @@ -333,7 +327,6 @@ UNWIND(.fnstart) UNWIND(.fnend) ENDPROC(__modsi3) -EXPORT_SYMBOL(__modsi3) #ifdef CONFIG_AEABI @@ -350,7 +343,6 @@ UNWIND(.save {r0, r1, ip, lr} ) UNWIND(.fnend) ENDPROC(__aeabi_uidivmod) -EXPORT_SYMBOL(__aeabi_uidivmod) ENTRY(__aeabi_idivmod) UNWIND(.fnstart) @@ -364,7 +356,6 @@ UNWIND(.save {r0, r1, ip, lr} ) UNWIND(.fnend) ENDPROC(__aeabi_idivmod) -EXPORT_SYMBOL(__aeabi_idivmod) #endif diff --git a/arch/arm/lib/lshrdi3.S b/arch/arm/lib/lshrdi3.S index e40833981417..922dcd88b02b 100644 --- a/arch/arm/lib/lshrdi3.S +++ b/arch/arm/lib/lshrdi3.S @@ -28,7 +28,6 @@ Boston, MA 02110-1301, USA. */ #include <linux/linkage.h> #include <asm/assembler.h> -#include <asm/export.h> #ifdef __ARMEB__ #define al r1 @@ -53,5 +52,3 @@ ENTRY(__aeabi_llsr) ENDPROC(__lshrdi3) ENDPROC(__aeabi_llsr) -EXPORT_SYMBOL(__lshrdi3) -EXPORT_SYMBOL(__aeabi_llsr) diff --git a/arch/arm/lib/memchr.S b/arch/arm/lib/memchr.S index 44182bf686a5..74a5bed6d999 100644 --- a/arch/arm/lib/memchr.S +++ b/arch/arm/lib/memchr.S @@ -11,7 +11,6 @@ */ #include <linux/linkage.h> #include <asm/assembler.h> -#include <asm/export.h> .text .align 5 @@ -25,4 +24,3 @@ ENTRY(memchr) 2: movne r0, #0 ret lr ENDPROC(memchr) -EXPORT_SYMBOL(memchr) diff --git a/arch/arm/lib/memcpy.S b/arch/arm/lib/memcpy.S index 1be5b6ddf37c..64111bd4440b 100644 --- a/arch/arm/lib/memcpy.S +++ b/arch/arm/lib/memcpy.S @@ -13,7 +13,6 @@ #include <linux/linkage.h> #include <asm/assembler.h> #include <asm/unwind.h> -#include <asm/export.h> #define LDR1W_SHIFT 0 #define STR1W_SHIFT 0 @@ -69,5 +68,3 @@ ENTRY(memcpy) ENDPROC(memcpy) ENDPROC(mmiocpy) -EXPORT_SYMBOL(memcpy) -EXPORT_SYMBOL(mmiocpy) diff --git a/arch/arm/lib/memmove.S b/arch/arm/lib/memmove.S index 71dcc5400d02..69a9d47fc5ab 100644 --- a/arch/arm/lib/memmove.S +++ b/arch/arm/lib/memmove.S @@ -13,7 +13,6 @@ #include <linux/linkage.h> #include <asm/assembler.h> #include <asm/unwind.h> -#include <asm/export.h> .text @@ -226,4 +225,3 @@ ENTRY(memmove) 18: backward_copy_shift push=24 pull=8 ENDPROC(memmove) -EXPORT_SYMBOL(memmove) diff --git a/arch/arm/lib/memset.S b/arch/arm/lib/memset.S index 7b72044cba62..3c65e3bd790f 100644 --- a/arch/arm/lib/memset.S +++ b/arch/arm/lib/memset.S @@ -12,7 +12,6 @@ #include <linux/linkage.h> #include <asm/assembler.h> #include <asm/unwind.h> -#include <asm/export.h> .text .align 5 @@ -136,5 +135,3 @@ UNWIND( .fnstart ) UNWIND( .fnend ) ENDPROC(memset) ENDPROC(mmioset) -EXPORT_SYMBOL(memset) -EXPORT_SYMBOL(mmioset) diff --git a/arch/arm/lib/memzero.S b/arch/arm/lib/memzero.S index 6dec26ed5bcc..0eded952e089 100644 --- a/arch/arm/lib/memzero.S +++ b/arch/arm/lib/memzero.S @@ -10,7 +10,6 @@ #include <linux/linkage.h> #include <asm/assembler.h> #include <asm/unwind.h> -#include <asm/export.h> .text .align 5 @@ -136,4 +135,3 @@ UNWIND( .fnstart ) ret lr @ 1 UNWIND( .fnend ) ENDPROC(__memzero) -EXPORT_SYMBOL(__memzero) diff --git a/arch/arm/lib/muldi3.S b/arch/arm/lib/muldi3.S index b8f12388ccac..204305956925 100644 --- a/arch/arm/lib/muldi3.S +++ b/arch/arm/lib/muldi3.S @@ -12,7 +12,6 @@ #include <linux/linkage.h> #include <asm/assembler.h> -#include <asm/export.h> #ifdef __ARMEB__ #define xh r0 @@ -47,5 +46,3 @@ ENTRY(__aeabi_lmul) ENDPROC(__muldi3) ENDPROC(__aeabi_lmul) -EXPORT_SYMBOL(__muldi3) -EXPORT_SYMBOL(__aeabi_lmul) diff --git a/arch/arm/lib/putuser.S b/arch/arm/lib/putuser.S index 11de126e2ed6..38d660d3705f 100644 --- a/arch/arm/lib/putuser.S +++ b/arch/arm/lib/putuser.S @@ -31,7 +31,6 @@ #include <asm/assembler.h> #include <asm/errno.h> #include <asm/domain.h> -#include <asm/export.h> ENTRY(__put_user_1) check_uaccess r0, 1, r1, ip, __put_user_bad @@ -39,7 +38,6 @@ ENTRY(__put_user_1) mov r0, #0 ret lr ENDPROC(__put_user_1) -EXPORT_SYMBOL(__put_user_1) ENTRY(__put_user_2) check_uaccess r0, 2, r1, ip, __put_user_bad @@ -64,7 +62,6 @@ ENTRY(__put_user_2) mov r0, #0 ret lr ENDPROC(__put_user_2) -EXPORT_SYMBOL(__put_user_2) ENTRY(__put_user_4) check_uaccess r0, 4, r1, ip, __put_user_bad @@ -72,7 +69,6 @@ ENTRY(__put_user_4) mov r0, #0 ret lr ENDPROC(__put_user_4) -EXPORT_SYMBOL(__put_user_4) ENTRY(__put_user_8) check_uaccess r0, 8, r1, ip, __put_user_bad @@ -86,7 +82,6 @@ ENTRY(__put_user_8) mov r0, #0 ret lr ENDPROC(__put_user_8) -EXPORT_SYMBOL(__put_user_8) __put_user_bad: mov r0, #-EFAULT diff --git a/arch/arm/lib/strchr.S b/arch/arm/lib/strchr.S index 7301f6e6046c..013d64c71e8d 100644 --- a/arch/arm/lib/strchr.S +++ b/arch/arm/lib/strchr.S @@ -11,7 +11,6 @@ */ #include <linux/linkage.h> #include <asm/assembler.h> -#include <asm/export.h> .text .align 5 @@ -26,4 +25,3 @@ ENTRY(strchr) subeq r0, r0, #1 ret lr ENDPROC(strchr) -EXPORT_SYMBOL(strchr) diff --git a/arch/arm/lib/strrchr.S b/arch/arm/lib/strrchr.S index aaf9fd98b754..3cec1c7482c4 100644 --- a/arch/arm/lib/strrchr.S +++ b/arch/arm/lib/strrchr.S @@ -11,7 +11,6 @@ */ #include <linux/linkage.h> #include <asm/assembler.h> -#include <asm/export.h> .text .align 5 @@ -25,4 +24,3 @@ ENTRY(strrchr) mov r0, r3 ret lr ENDPROC(strrchr) -EXPORT_SYMBOL(strrchr) diff --git a/arch/arm/lib/uaccess_with_memcpy.c b/arch/arm/lib/uaccess_with_memcpy.c index 1626e3a551a1..6bd1089b07e0 100644 --- a/arch/arm/lib/uaccess_with_memcpy.c +++ b/arch/arm/lib/uaccess_with_memcpy.c @@ -19,7 +19,6 @@ #include <linux/gfp.h> #include <linux/highmem.h> #include <linux/hugetlb.h> -#include <linux/export.h> #include <asm/current.h> #include <asm/page.h> @@ -157,7 +156,6 @@ arm_copy_to_user(void __user *to, const void *from, unsigned long n) } return n; } -EXPORT_SYMBOL(arm_copy_to_user); static unsigned long noinline __clear_user_memset(void __user *addr, unsigned long n) @@ -215,7 +213,6 @@ unsigned long arm_clear_user(void __user *addr, unsigned long n) } return n; } -EXPORT_SYMBOL(arm_clear_user); #if 0 diff --git a/arch/arm/lib/ucmpdi2.S b/arch/arm/lib/ucmpdi2.S index 127a91af46f3..ad4a6309141a 100644 --- a/arch/arm/lib/ucmpdi2.S +++ b/arch/arm/lib/ucmpdi2.S @@ -12,7 +12,6 @@ #include <linux/linkage.h> #include <asm/assembler.h> -#include <asm/export.h> #ifdef __ARMEB__ #define xh r0 @@ -36,7 +35,6 @@ ENTRY(__ucmpdi2) ret lr ENDPROC(__ucmpdi2) -EXPORT_SYMBOL(__ucmpdi2) #ifdef CONFIG_AEABI @@ -50,7 +48,6 @@ ENTRY(__aeabi_ulcmp) ret lr ENDPROC(__aeabi_ulcmp) -EXPORT_SYMBOL(__aeabi_ulcmp) #endif diff --git a/arch/arm/mach-imx/Makefile b/arch/arm/mach-imx/Makefile index 737450fe790c..cab128913e72 100644 --- a/arch/arm/mach-imx/Makefile +++ b/arch/arm/mach-imx/Makefile @@ -32,6 +32,7 @@ endif ifdef CONFIG_SND_IMX_SOC obj-y += ssi-fiq.o +obj-y += ssi-fiq-ksym.o endif # i.MX21 based machines diff --git a/arch/arm/mach-imx/gpc.c b/arch/arm/mach-imx/gpc.c index b54db47f6f32..1dc2a34b9dbd 100644 --- a/arch/arm/mach-imx/gpc.c +++ b/arch/arm/mach-imx/gpc.c @@ -380,13 +380,6 @@ static struct pu_domain imx6q_pu_domain = { .name = "PU", .power_off = imx6q_pm_pu_power_off, .power_on = imx6q_pm_pu_power_on, - .states = { - [0] = { - .power_off_latency_ns = 25000, - .power_on_latency_ns = 2000000, - }, - }, - .state_count = 1, }, }; @@ -430,6 +423,16 @@ static int imx_gpc_genpd_init(struct device *dev, struct regulator *pu_reg) if (!IS_ENABLED(CONFIG_PM_GENERIC_DOMAINS)) return 0; + imx6q_pu_domain.base.states = devm_kzalloc(dev, + sizeof(*imx6q_pu_domain.base.states), + GFP_KERNEL); + if (!imx6q_pu_domain.base.states) + return -ENOMEM; + + imx6q_pu_domain.base.states[0].power_off_latency_ns = 25000; + imx6q_pu_domain.base.states[0].power_on_latency_ns = 2000000; + imx6q_pu_domain.base.state_count = 1; + for (i = 0; i < ARRAY_SIZE(imx_gpc_domains); i++) pm_genpd_init(imx_gpc_domains[i], NULL, false); diff --git a/arch/arm/mach-imx/ssi-fiq-ksym.c b/arch/arm/mach-imx/ssi-fiq-ksym.c new file mode 100644 index 000000000000..792090f9a032 --- /dev/null +++ b/arch/arm/mach-imx/ssi-fiq-ksym.c @@ -0,0 +1,20 @@ +/* + * Exported ksyms for the SSI FIQ handler + * + * Copyright (C) 2009, Sascha Hauer <s.hauer@pengutronix.de> + * + * 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 + * published by the Free Software Foundation. + */ + +#include <linux/module.h> + +#include <linux/platform_data/asoc-imx-ssi.h> + +EXPORT_SYMBOL(imx_ssi_fiq_tx_buffer); +EXPORT_SYMBOL(imx_ssi_fiq_rx_buffer); +EXPORT_SYMBOL(imx_ssi_fiq_start); +EXPORT_SYMBOL(imx_ssi_fiq_end); +EXPORT_SYMBOL(imx_ssi_fiq_base); + diff --git a/arch/arm/mach-imx/ssi-fiq.S b/arch/arm/mach-imx/ssi-fiq.S index fd7917f1c204..a8b93c5f29b5 100644 --- a/arch/arm/mach-imx/ssi-fiq.S +++ b/arch/arm/mach-imx/ssi-fiq.S @@ -8,7 +8,6 @@ #include <linux/linkage.h> #include <asm/assembler.h> -#include <asm/export.h> /* * r8 = bit 0-15: tx offset, bit 16-31: tx buffer size @@ -145,8 +144,4 @@ imx_ssi_fiq_tx_buffer: .word 0x0 .L_imx_ssi_fiq_end: imx_ssi_fiq_end: -EXPORT_SYMBOL(imx_ssi_fiq_tx_buffer) -EXPORT_SYMBOL(imx_ssi_fiq_rx_buffer) -EXPORT_SYMBOL(imx_ssi_fiq_start) -EXPORT_SYMBOL(imx_ssi_fiq_end) -EXPORT_SYMBOL(imx_ssi_fiq_base) + diff --git a/arch/arm64/boot/dts/arm/juno-base.dtsi b/arch/arm64/boot/dts/arm/juno-base.dtsi index 334271a25f70..7d3a2acc6a55 100644 --- a/arch/arm64/boot/dts/arm/juno-base.dtsi +++ b/arch/arm64/boot/dts/arm/juno-base.dtsi @@ -393,7 +393,7 @@ #address-cells = <3>; #size-cells = <2>; dma-coherent; - ranges = <0x01000000 0x00 0x5f800000 0x00 0x5f800000 0x0 0x00800000>, + ranges = <0x01000000 0x00 0x00000000 0x00 0x5f800000 0x0 0x00800000>, <0x02000000 0x00 0x50000000 0x00 0x50000000 0x0 0x08000000>, <0x42000000 0x40 0x00000000 0x40 0x00000000 0x1 0x00000000>; #interrupt-cells = <1>; diff --git a/arch/arm64/boot/dts/arm/juno-r1.dts b/arch/arm64/boot/dts/arm/juno-r1.dts index 123a58b29cbd..f0b857d6d73c 100644 --- a/arch/arm64/boot/dts/arm/juno-r1.dts +++ b/arch/arm64/boot/dts/arm/juno-r1.dts @@ -76,7 +76,7 @@ compatible = "arm,idle-state"; arm,psci-suspend-param = <0x1010000>; local-timer-stop; - entry-latency-us = <300>; + entry-latency-us = <400>; exit-latency-us = <1200>; min-residency-us = <2500>; }; diff --git a/arch/arm64/boot/dts/arm/juno-r2.dts b/arch/arm64/boot/dts/arm/juno-r2.dts index 007be826efce..26aaa6a7670f 100644 --- a/arch/arm64/boot/dts/arm/juno-r2.dts +++ b/arch/arm64/boot/dts/arm/juno-r2.dts @@ -76,7 +76,7 @@ compatible = "arm,idle-state"; arm,psci-suspend-param = <0x1010000>; local-timer-stop; - entry-latency-us = <300>; + entry-latency-us = <400>; exit-latency-us = <1200>; min-residency-us = <2500>; }; diff --git a/arch/arm64/boot/dts/arm/juno.dts b/arch/arm64/boot/dts/arm/juno.dts index a7270eff6939..6e154d948a80 100644 --- a/arch/arm64/boot/dts/arm/juno.dts +++ b/arch/arm64/boot/dts/arm/juno.dts @@ -76,7 +76,7 @@ compatible = "arm,idle-state"; arm,psci-suspend-param = <0x1010000>; local-timer-stop; - entry-latency-us = <300>; + entry-latency-us = <400>; exit-latency-us = <1200>; min-residency-us = <2500>; }; diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig index 55be7e3ff109..b98acd15ca22 100644 --- a/arch/m68k/configs/amiga_defconfig +++ b/arch/m68k/configs/amiga_defconfig @@ -95,9 +95,10 @@ CONFIG_NF_TABLES_INET=m CONFIG_NF_TABLES_NETDEV=m CONFIG_NFT_EXTHDR=m CONFIG_NFT_META=m +CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m -CONFIG_NFT_RBTREE=m -CONFIG_NFT_HASH=m +CONFIG_NFT_SET_RBTREE=m +CONFIG_NFT_SET_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m @@ -105,8 +106,10 @@ CONFIG_NFT_MASQ=m CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m +CONFIG_NFT_QUOTA=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m +CONFIG_NFT_HASH=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NETFILTER_XT_SET=m @@ -366,6 +369,7 @@ CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y CONFIG_VETH=m # CONFIG_NET_VENDOR_3COM is not set +# CONFIG_NET_VENDOR_AMAZON is not set CONFIG_A2065=y CONFIG_ARIADNE=y # CONFIG_NET_VENDOR_ARC is not set diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig index 365dda66b0e6..f80dc57e6374 100644 --- a/arch/m68k/configs/apollo_defconfig +++ b/arch/m68k/configs/apollo_defconfig @@ -93,9 +93,10 @@ CONFIG_NF_TABLES_INET=m CONFIG_NF_TABLES_NETDEV=m CONFIG_NFT_EXTHDR=m CONFIG_NFT_META=m +CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m -CONFIG_NFT_RBTREE=m -CONFIG_NFT_HASH=m +CONFIG_NFT_SET_RBTREE=m +CONFIG_NFT_SET_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m @@ -103,8 +104,10 @@ CONFIG_NFT_MASQ=m CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m +CONFIG_NFT_QUOTA=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m +CONFIG_NFT_HASH=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NETFILTER_XT_SET=m @@ -347,6 +350,7 @@ CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y CONFIG_VETH=m +# CONFIG_NET_VENDOR_AMAZON is not set # CONFIG_NET_VENDOR_ARC is not set # CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig index ce3cbfd16fcd..4e16b1821fbb 100644 --- a/arch/m68k/configs/atari_defconfig +++ b/arch/m68k/configs/atari_defconfig @@ -93,9 +93,10 @@ CONFIG_NF_TABLES_INET=m CONFIG_NF_TABLES_NETDEV=m CONFIG_NFT_EXTHDR=m CONFIG_NFT_META=m +CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m -CONFIG_NFT_RBTREE=m -CONFIG_NFT_HASH=m +CONFIG_NFT_SET_RBTREE=m +CONFIG_NFT_SET_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m @@ -103,8 +104,10 @@ CONFIG_NFT_MASQ=m CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m +CONFIG_NFT_QUOTA=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m +CONFIG_NFT_HASH=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NETFILTER_XT_SET=m @@ -356,6 +359,7 @@ CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y CONFIG_VETH=m +# CONFIG_NET_VENDOR_AMAZON is not set CONFIG_ATARILANCE=y # CONFIG_NET_VENDOR_ARC is not set # CONFIG_NET_CADENCE is not set diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig index 8db496a9797d..2767bbf5ad61 100644 --- a/arch/m68k/configs/bvme6000_defconfig +++ b/arch/m68k/configs/bvme6000_defconfig @@ -91,9 +91,10 @@ CONFIG_NF_TABLES_INET=m CONFIG_NF_TABLES_NETDEV=m CONFIG_NFT_EXTHDR=m CONFIG_NFT_META=m +CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m -CONFIG_NFT_RBTREE=m -CONFIG_NFT_HASH=m +CONFIG_NFT_SET_RBTREE=m +CONFIG_NFT_SET_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m @@ -101,8 +102,10 @@ CONFIG_NFT_MASQ=m CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m +CONFIG_NFT_QUOTA=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m +CONFIG_NFT_HASH=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NETFILTER_XT_SET=m @@ -346,6 +349,7 @@ CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y CONFIG_VETH=m +# CONFIG_NET_VENDOR_AMAZON is not set # CONFIG_NET_VENDOR_ARC is not set # CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig index 8314156f7149..d13ba309265e 100644 --- a/arch/m68k/configs/hp300_defconfig +++ b/arch/m68k/configs/hp300_defconfig @@ -93,9 +93,10 @@ CONFIG_NF_TABLES_INET=m CONFIG_NF_TABLES_NETDEV=m CONFIG_NFT_EXTHDR=m CONFIG_NFT_META=m +CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m -CONFIG_NFT_RBTREE=m -CONFIG_NFT_HASH=m +CONFIG_NFT_SET_RBTREE=m +CONFIG_NFT_SET_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m @@ -103,8 +104,10 @@ CONFIG_NFT_MASQ=m CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m +CONFIG_NFT_QUOTA=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m +CONFIG_NFT_HASH=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NETFILTER_XT_SET=m @@ -347,6 +350,7 @@ CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y CONFIG_VETH=m +# CONFIG_NET_VENDOR_AMAZON is not set CONFIG_HPLANCE=y # CONFIG_NET_VENDOR_ARC is not set # CONFIG_NET_CADENCE is not set diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig index 6600270b9622..78b5101c1aa6 100644 --- a/arch/m68k/configs/mac_defconfig +++ b/arch/m68k/configs/mac_defconfig @@ -92,9 +92,10 @@ CONFIG_NF_TABLES_INET=m CONFIG_NF_TABLES_NETDEV=m CONFIG_NFT_EXTHDR=m CONFIG_NFT_META=m +CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m -CONFIG_NFT_RBTREE=m -CONFIG_NFT_HASH=m +CONFIG_NFT_SET_RBTREE=m +CONFIG_NFT_SET_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m @@ -102,8 +103,10 @@ CONFIG_NFT_MASQ=m CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m +CONFIG_NFT_QUOTA=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m +CONFIG_NFT_HASH=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NETFILTER_XT_SET=m @@ -363,6 +366,7 @@ CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y CONFIG_VETH=m +# CONFIG_NET_VENDOR_AMAZON is not set CONFIG_MACMACE=y # CONFIG_NET_VENDOR_ARC is not set # CONFIG_NET_CADENCE is not set diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig index 90abfe9eabba..38e5bcbd0d62 100644 --- a/arch/m68k/configs/multi_defconfig +++ b/arch/m68k/configs/multi_defconfig @@ -102,9 +102,10 @@ CONFIG_NF_TABLES_INET=m CONFIG_NF_TABLES_NETDEV=m CONFIG_NFT_EXTHDR=m CONFIG_NFT_META=m +CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m -CONFIG_NFT_RBTREE=m -CONFIG_NFT_HASH=m +CONFIG_NFT_SET_RBTREE=m +CONFIG_NFT_SET_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m @@ -112,8 +113,10 @@ CONFIG_NFT_MASQ=m CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m +CONFIG_NFT_QUOTA=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m +CONFIG_NFT_HASH=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NETFILTER_XT_SET=m @@ -397,6 +400,7 @@ CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y CONFIG_VETH=m # CONFIG_NET_VENDOR_3COM is not set +# CONFIG_NET_VENDOR_AMAZON is not set CONFIG_A2065=y CONFIG_ARIADNE=y CONFIG_ATARILANCE=y diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig index 0d502c2f73d5..28687192b68e 100644 --- a/arch/m68k/configs/mvme147_defconfig +++ b/arch/m68k/configs/mvme147_defconfig @@ -90,9 +90,10 @@ CONFIG_NF_TABLES_INET=m CONFIG_NF_TABLES_NETDEV=m CONFIG_NFT_EXTHDR=m CONFIG_NFT_META=m +CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m -CONFIG_NFT_RBTREE=m -CONFIG_NFT_HASH=m +CONFIG_NFT_SET_RBTREE=m +CONFIG_NFT_SET_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m @@ -100,8 +101,10 @@ CONFIG_NFT_MASQ=m CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m +CONFIG_NFT_QUOTA=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m +CONFIG_NFT_HASH=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NETFILTER_XT_SET=m @@ -345,6 +348,7 @@ CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y CONFIG_VETH=m +# CONFIG_NET_VENDOR_AMAZON is not set CONFIG_MVME147_NET=y # CONFIG_NET_VENDOR_ARC is not set # CONFIG_NET_CADENCE is not set diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig index 5930e91fc710..5a5f109ab3cd 100644 --- a/arch/m68k/configs/mvme16x_defconfig +++ b/arch/m68k/configs/mvme16x_defconfig @@ -91,9 +91,10 @@ CONFIG_NF_TABLES_INET=m CONFIG_NF_TABLES_NETDEV=m CONFIG_NFT_EXTHDR=m CONFIG_NFT_META=m +CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m -CONFIG_NFT_RBTREE=m -CONFIG_NFT_HASH=m +CONFIG_NFT_SET_RBTREE=m +CONFIG_NFT_SET_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m @@ -101,8 +102,10 @@ CONFIG_NFT_MASQ=m CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m +CONFIG_NFT_QUOTA=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m +CONFIG_NFT_HASH=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NETFILTER_XT_SET=m @@ -346,6 +349,7 @@ CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y CONFIG_VETH=m +# CONFIG_NET_VENDOR_AMAZON is not set # CONFIG_NET_VENDOR_ARC is not set # CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig index 74e3ad82eca9..e557c9de3fbc 100644 --- a/arch/m68k/configs/q40_defconfig +++ b/arch/m68k/configs/q40_defconfig @@ -91,9 +91,10 @@ CONFIG_NF_TABLES_INET=m CONFIG_NF_TABLES_NETDEV=m CONFIG_NFT_EXTHDR=m CONFIG_NFT_META=m +CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m -CONFIG_NFT_RBTREE=m -CONFIG_NFT_HASH=m +CONFIG_NFT_SET_RBTREE=m +CONFIG_NFT_SET_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m @@ -101,8 +102,10 @@ CONFIG_NFT_MASQ=m CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m +CONFIG_NFT_QUOTA=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m +CONFIG_NFT_HASH=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NETFILTER_XT_SET=m @@ -353,6 +356,7 @@ CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y CONFIG_VETH=m # CONFIG_NET_VENDOR_3COM is not set +# CONFIG_NET_VENDOR_AMAZON is not set # CONFIG_NET_VENDOR_AMD is not set # CONFIG_NET_VENDOR_ARC is not set # CONFIG_NET_CADENCE is not set diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig index 4ba8606a4e69..c6a748a36daf 100644 --- a/arch/m68k/configs/sun3_defconfig +++ b/arch/m68k/configs/sun3_defconfig @@ -88,9 +88,10 @@ CONFIG_NF_TABLES_INET=m CONFIG_NF_TABLES_NETDEV=m CONFIG_NFT_EXTHDR=m CONFIG_NFT_META=m +CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m -CONFIG_NFT_RBTREE=m -CONFIG_NFT_HASH=m +CONFIG_NFT_SET_RBTREE=m +CONFIG_NFT_SET_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m @@ -98,8 +99,10 @@ CONFIG_NFT_MASQ=m CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m +CONFIG_NFT_QUOTA=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m +CONFIG_NFT_HASH=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NETFILTER_XT_SET=m @@ -343,6 +346,7 @@ CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y CONFIG_VETH=m +# CONFIG_NET_VENDOR_AMAZON is not set CONFIG_SUN3LANCE=y # CONFIG_NET_VENDOR_ARC is not set # CONFIG_NET_CADENCE is not set diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig index c6f49726a6c9..10d60857b9a6 100644 --- a/arch/m68k/configs/sun3x_defconfig +++ b/arch/m68k/configs/sun3x_defconfig @@ -88,9 +88,10 @@ CONFIG_NF_TABLES_INET=m CONFIG_NF_TABLES_NETDEV=m CONFIG_NFT_EXTHDR=m CONFIG_NFT_META=m +CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m -CONFIG_NFT_RBTREE=m -CONFIG_NFT_HASH=m +CONFIG_NFT_SET_RBTREE=m +CONFIG_NFT_SET_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m @@ -98,8 +99,10 @@ CONFIG_NFT_MASQ=m CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m +CONFIG_NFT_QUOTA=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m +CONFIG_NFT_HASH=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NETFILTER_XT_SET=m @@ -343,6 +346,7 @@ CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y CONFIG_VETH=m +# CONFIG_NET_VENDOR_AMAZON is not set CONFIG_SUN3LANCE=y # CONFIG_NET_VENDOR_ARC is not set # CONFIG_NET_CADENCE is not set diff --git a/arch/m68k/include/asm/delay.h b/arch/m68k/include/asm/delay.h index d28fa8fe26fe..c598d847d56b 100644 --- a/arch/m68k/include/asm/delay.h +++ b/arch/m68k/include/asm/delay.h @@ -114,6 +114,6 @@ static inline void __udelay(unsigned long usecs) */ #define HZSCALE (268435456 / (1000000 / HZ)) -#define ndelay(n) __delay(DIV_ROUND_UP((n) * ((((HZSCALE) >> 11) * (loops_per_jiffy >> 11)) >> 6), 1000)); +#define ndelay(n) __delay(DIV_ROUND_UP((n) * ((((HZSCALE) >> 11) * (loops_per_jiffy >> 11)) >> 6), 1000)) #endif /* defined(_M68K_DELAY_H) */ diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h index 7dd2dd47909a..df78b2ca70eb 100644 --- a/arch/mips/include/asm/mipsregs.h +++ b/arch/mips/include/asm/mipsregs.h @@ -215,6 +215,12 @@ #endif /* + * Wired register bits + */ +#define MIPSR6_WIRED_LIMIT (_ULCAST_(0xffff) << 16) +#define MIPSR6_WIRED_WIRED (_ULCAST_(0xffff) << 0) + +/* * Values used for computation of new tlb entries */ #define PL_4K 12 diff --git a/arch/mips/include/asm/tlb.h b/arch/mips/include/asm/tlb.h index 4a2349302b55..dd179fd8acda 100644 --- a/arch/mips/include/asm/tlb.h +++ b/arch/mips/include/asm/tlb.h @@ -1,6 +1,9 @@ #ifndef __ASM_TLB_H #define __ASM_TLB_H +#include <asm/cpu-features.h> +#include <asm/mipsregs.h> + /* * MIPS doesn't need any special per-pte or per-vma handling, except * we need to flush cache for area to be unmapped. @@ -22,6 +25,16 @@ ((CKSEG0 + ((idx) << (PAGE_SHIFT + 1))) | \ (cpu_has_tlbinv ? MIPS_ENTRYHI_EHINV : 0)) +static inline unsigned int num_wired_entries(void) +{ + unsigned int wired = read_c0_wired(); + + if (cpu_has_mips_r6) + wired &= MIPSR6_WIRED_WIRED; + + return wired; +} + #include <asm-generic/tlb.h> #endif /* __ASM_TLB_H */ diff --git a/arch/mips/kernel/time.c b/arch/mips/kernel/time.c index 8d0170969e22..a7f81261c781 100644 --- a/arch/mips/kernel/time.c +++ b/arch/mips/kernel/time.c @@ -36,7 +36,7 @@ EXPORT_SYMBOL(rtc_lock); int __weak rtc_mips_set_time(unsigned long sec) { - return 0; + return -ENODEV; } int __weak rtc_mips_set_mmss(unsigned long nowtime) diff --git a/arch/mips/lantiq/falcon/sysctrl.c b/arch/mips/lantiq/falcon/sysctrl.c index 2a1b3021589c..82bbd0e2e298 100644 --- a/arch/mips/lantiq/falcon/sysctrl.c +++ b/arch/mips/lantiq/falcon/sysctrl.c @@ -24,7 +24,7 @@ /* GPE frequency selection */ #define GPPC_OFFSET 24 -#define GPEFREQ_MASK 0x00000C0 +#define GPEFREQ_MASK 0x0000C00 #define GPEFREQ_OFFSET 10 /* Clock status register */ #define SYSCTL_CLKS 0x0000 diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c index d56a855828c2..3bef306cdfdb 100644 --- a/arch/mips/mm/fault.c +++ b/arch/mips/mm/fault.c @@ -209,17 +209,18 @@ bad_area_nosemaphore: if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) && __ratelimit(&ratelimit_state)) { - pr_info("\ndo_page_fault(): sending SIGSEGV to %s for invalid %s %0*lx", + pr_info("do_page_fault(): sending SIGSEGV to %s for invalid %s %0*lx\n", tsk->comm, write ? "write access to" : "read access from", field, address); pr_info("epc = %0*lx in", field, (unsigned long) regs->cp0_epc); - print_vma_addr(" ", regs->cp0_epc); + print_vma_addr(KERN_CONT " ", regs->cp0_epc); + pr_cont("\n"); pr_info("ra = %0*lx in", field, (unsigned long) regs->regs[31]); - print_vma_addr(" ", regs->regs[31]); - pr_info("\n"); + print_vma_addr(KERN_CONT " ", regs->regs[31]); + pr_cont("\n"); } current->thread.trap_nr = (regs->cp0_cause >> 2) & 0x1f; info.si_signo = SIGSEGV; diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 3a6edecc3f38..e86ebcf5c071 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -118,7 +118,7 @@ static void *__kmap_pgprot(struct page *page, unsigned long addr, pgprot_t prot) writex_c0_entrylo1(entrylo); } #endif - tlbidx = read_c0_wired(); + tlbidx = num_wired_entries(); write_c0_wired(tlbidx + 1); write_c0_index(tlbidx); mtc0_tlbw_hazard(); @@ -147,7 +147,7 @@ void kunmap_coherent(void) local_irq_save(flags); old_ctx = read_c0_entryhi(); - wired = read_c0_wired() - 1; + wired = num_wired_entries() - 1; write_c0_wired(wired); write_c0_index(wired); write_c0_entryhi(UNIQUE_ENTRYHI(wired)); diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c index bba9c1484b41..0596505770db 100644 --- a/arch/mips/mm/tlb-r4k.c +++ b/arch/mips/mm/tlb-r4k.c @@ -65,7 +65,7 @@ void local_flush_tlb_all(void) write_c0_entrylo0(0); write_c0_entrylo1(0); - entry = read_c0_wired(); + entry = num_wired_entries(); /* * Blast 'em all away. @@ -385,7 +385,7 @@ void add_wired_entry(unsigned long entrylo0, unsigned long entrylo1, old_ctx = read_c0_entryhi(); htw_stop(); old_pagemask = read_c0_pagemask(); - wired = read_c0_wired(); + wired = num_wired_entries(); write_c0_wired(wired + 1); write_c0_index(wired); tlbw_use_hazard(); /* What is the hazard here? */ @@ -449,7 +449,7 @@ __init int add_temporary_entry(unsigned long entrylo0, unsigned long entrylo1, htw_stop(); old_ctx = read_c0_entryhi(); old_pagemask = read_c0_pagemask(); - wired = read_c0_wired(); + wired = num_wired_entries(); if (--temp_tlb_entry < wired) { printk(KERN_WARNING "No TLB space left for add_temporary_entry\n"); diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 71c4a3aa3752..a14b86587013 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -34,7 +34,9 @@ config PARISC select HAVE_ARCH_HASH select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK - select HAVE_UNSTABLE_SCHED_CLOCK if (SMP || !64BIT) + select GENERIC_SCHED_CLOCK + select HAVE_UNSTABLE_SCHED_CLOCK if SMP + select GENERIC_CLOCKEVENTS select ARCH_NO_COHERENT_DMA_MMAP select CPU_NO_EFFICIENT_FFS diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index c2c43f714684..3a4ed9f91d57 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -65,9 +65,9 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) unsigned long flags; \ spin_lock_irqsave(&pa_tlb_lock, flags); \ old_pte = *ptep; \ - set_pte(ptep, pteval); \ if (pte_inserted(old_pte)) \ purge_tlb_entries(mm, addr); \ + set_pte(ptep, pteval); \ spin_unlock_irqrestore(&pa_tlb_lock, flags); \ } while (0) @@ -478,8 +478,8 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned spin_unlock_irqrestore(&pa_tlb_lock, flags); return 0; } - set_pte(ptep, pte_mkold(pte)); purge_tlb_entries(vma->vm_mm, addr); + set_pte(ptep, pte_mkold(pte)); spin_unlock_irqrestore(&pa_tlb_lock, flags); return 1; } @@ -492,9 +492,9 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, spin_lock_irqsave(&pa_tlb_lock, flags); old_pte = *ptep; - set_pte(ptep, __pte(0)); if (pte_inserted(old_pte)) purge_tlb_entries(mm, addr); + set_pte(ptep, __pte(0)); spin_unlock_irqrestore(&pa_tlb_lock, flags); return old_pte; @@ -504,8 +504,8 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, { unsigned long flags; spin_lock_irqsave(&pa_tlb_lock, flags); - set_pte(ptep, pte_wrprotect(*ptep)); purge_tlb_entries(mm, addr); + set_pte(ptep, pte_wrprotect(*ptep)); spin_unlock_irqrestore(&pa_tlb_lock, flags); } diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index 629eb464d5ba..977f0a4f5ecf 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -369,6 +369,7 @@ void __init parisc_setup_cache_timing(void) { unsigned long rangetime, alltime; unsigned long size, start; + unsigned long threshold; alltime = mfctl(16); flush_data_cache(); @@ -382,26 +383,30 @@ void __init parisc_setup_cache_timing(void) printk(KERN_DEBUG "Whole cache flush %lu cycles, flushing %lu bytes %lu cycles\n", alltime, size, rangetime); - /* Racy, but if we see an intermediate value, it's ok too... */ - parisc_cache_flush_threshold = size * alltime / rangetime; - - parisc_cache_flush_threshold = L1_CACHE_ALIGN(parisc_cache_flush_threshold); - if (!parisc_cache_flush_threshold) - parisc_cache_flush_threshold = FLUSH_THRESHOLD; - - if (parisc_cache_flush_threshold > cache_info.dc_size) - parisc_cache_flush_threshold = cache_info.dc_size; - - printk(KERN_INFO "Setting cache flush threshold to %lu kB\n", + threshold = L1_CACHE_ALIGN(size * alltime / rangetime); + if (threshold > cache_info.dc_size) + threshold = cache_info.dc_size; + if (threshold) + parisc_cache_flush_threshold = threshold; + printk(KERN_INFO "Cache flush threshold set to %lu KiB\n", parisc_cache_flush_threshold/1024); /* calculate TLB flush threshold */ + /* On SMP machines, skip the TLB measure of kernel text which + * has been mapped as huge pages. */ + if (num_online_cpus() > 1 && !parisc_requires_coherency()) { + threshold = max(cache_info.it_size, cache_info.dt_size); + threshold *= PAGE_SIZE; + threshold /= num_online_cpus(); + goto set_tlb_threshold; + } + alltime = mfctl(16); flush_tlb_all(); alltime = mfctl(16) - alltime; - size = PAGE_SIZE; + size = 0; start = (unsigned long) _text; rangetime = mfctl(16); while (start < (unsigned long) _end) { @@ -414,13 +419,12 @@ void __init parisc_setup_cache_timing(void) printk(KERN_DEBUG "Whole TLB flush %lu cycles, flushing %lu bytes %lu cycles\n", alltime, size, rangetime); - parisc_tlb_flush_threshold = size * alltime / rangetime; - parisc_tlb_flush_threshold *= num_online_cpus(); - parisc_tlb_flush_threshold = PAGE_ALIGN(parisc_tlb_flush_threshold); - if (!parisc_tlb_flush_threshold) - parisc_tlb_flush_threshold = FLUSH_TLB_THRESHOLD; + threshold = PAGE_ALIGN(num_online_cpus() * size * alltime / rangetime); - printk(KERN_INFO "Setting TLB flush threshold to %lu kB\n", +set_tlb_threshold: + if (threshold) + parisc_tlb_flush_threshold = threshold; + printk(KERN_INFO "TLB flush threshold set to %lu KiB\n", parisc_tlb_flush_threshold/1024); } diff --git a/arch/parisc/kernel/inventory.c b/arch/parisc/kernel/inventory.c index 545f9d2fe711..c05d1876d27c 100644 --- a/arch/parisc/kernel/inventory.c +++ b/arch/parisc/kernel/inventory.c @@ -58,7 +58,7 @@ void __init setup_pdc(void) status = pdc_system_map_find_mods(&module_result, &module_path, 0); if (status == PDC_OK) { pdc_type = PDC_TYPE_SYSTEM_MAP; - printk("System Map.\n"); + pr_cont("System Map.\n"); return; } @@ -77,7 +77,7 @@ void __init setup_pdc(void) status = pdc_pat_cell_get_number(&cell_info); if (status == PDC_OK) { pdc_type = PDC_TYPE_PAT; - printk("64 bit PAT.\n"); + pr_cont("64 bit PAT.\n"); return; } #endif @@ -97,12 +97,12 @@ void __init setup_pdc(void) case 0xC: /* 715/64, at least */ pdc_type = PDC_TYPE_SNAKE; - printk("Snake.\n"); + pr_cont("Snake.\n"); return; default: /* Everything else */ - printk("Unsupported.\n"); + pr_cont("Unsupported.\n"); panic("If this is a 64-bit machine, please try a 64-bit kernel.\n"); } } diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S index 985e06da37f5..adf7187f8951 100644 --- a/arch/parisc/kernel/pacache.S +++ b/arch/parisc/kernel/pacache.S @@ -96,7 +96,7 @@ fitmanyloop: /* Loop if LOOP >= 2 */ fitmanymiddle: /* Loop if LOOP >= 2 */ addib,COND(>) -1, %r31, fitmanymiddle /* Adjusted inner loop decr */ - pitlbe 0(%sr1, %r28) + pitlbe %r0(%sr1, %r28) pitlbe,m %arg1(%sr1, %r28) /* Last pitlbe and addr adjust */ addib,COND(>) -1, %r29, fitmanymiddle /* Middle loop decr */ copy %arg3, %r31 /* Re-init inner loop count */ @@ -139,7 +139,7 @@ fdtmanyloop: /* Loop if LOOP >= 2 */ fdtmanymiddle: /* Loop if LOOP >= 2 */ addib,COND(>) -1, %r31, fdtmanymiddle /* Adjusted inner loop decr */ - pdtlbe 0(%sr1, %r28) + pdtlbe %r0(%sr1, %r28) pdtlbe,m %arg1(%sr1, %r28) /* Last pdtlbe and addr adjust */ addib,COND(>) -1, %r29, fdtmanymiddle /* Middle loop decr */ copy %arg3, %r31 /* Re-init inner loop count */ @@ -626,12 +626,12 @@ ENTRY_CFI(copy_user_page_asm) /* Purge any old translations */ #ifdef CONFIG_PA20 - pdtlb,l 0(%r28) - pdtlb,l 0(%r29) + pdtlb,l %r0(%r28) + pdtlb,l %r0(%r29) #else tlb_lock %r20,%r21,%r22 - pdtlb 0(%r28) - pdtlb 0(%r29) + pdtlb %r0(%r28) + pdtlb %r0(%r29) tlb_unlock %r20,%r21,%r22 #endif @@ -774,10 +774,10 @@ ENTRY_CFI(clear_user_page_asm) /* Purge any old translation */ #ifdef CONFIG_PA20 - pdtlb,l 0(%r28) + pdtlb,l %r0(%r28) #else tlb_lock %r20,%r21,%r22 - pdtlb 0(%r28) + pdtlb %r0(%r28) tlb_unlock %r20,%r21,%r22 #endif @@ -858,10 +858,10 @@ ENTRY_CFI(flush_dcache_page_asm) /* Purge any old translation */ #ifdef CONFIG_PA20 - pdtlb,l 0(%r28) + pdtlb,l %r0(%r28) #else tlb_lock %r20,%r21,%r22 - pdtlb 0(%r28) + pdtlb %r0(%r28) tlb_unlock %r20,%r21,%r22 #endif @@ -892,19 +892,10 @@ ENTRY_CFI(flush_dcache_page_asm) fdc,m r31(%r28) fdc,m r31(%r28) fdc,m r31(%r28) - cmpb,COND(<<) %r28, %r25,1b + cmpb,COND(<<) %r28, %r25,1b fdc,m r31(%r28) sync - -#ifdef CONFIG_PA20 - pdtlb,l 0(%r25) -#else - tlb_lock %r20,%r21,%r22 - pdtlb 0(%r25) - tlb_unlock %r20,%r21,%r22 -#endif - bv %r0(%r2) nop .exit @@ -931,13 +922,18 @@ ENTRY_CFI(flush_icache_page_asm) depwi 0, 31,PAGE_SHIFT, %r28 /* Clear any offset bits */ #endif - /* Purge any old translation */ + /* Purge any old translation. Note that the FIC instruction + * may use either the instruction or data TLB. Given that we + * have a flat address space, it's not clear which TLB will be + * used. So, we purge both entries. */ #ifdef CONFIG_PA20 + pdtlb,l %r0(%r28) pitlb,l %r0(%sr4,%r28) #else tlb_lock %r20,%r21,%r22 - pitlb (%sr4,%r28) + pdtlb %r0(%r28) + pitlb %r0(%sr4,%r28) tlb_unlock %r20,%r21,%r22 #endif @@ -974,15 +970,6 @@ ENTRY_CFI(flush_icache_page_asm) fic,m %r31(%sr4,%r28) sync - -#ifdef CONFIG_PA20 - pitlb,l %r0(%sr4,%r25) -#else - tlb_lock %r20,%r21,%r22 - pitlb (%sr4,%r25) - tlb_unlock %r20,%r21,%r22 -#endif - bv %r0(%r2) nop .exit diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c index 02d9ed0f3949..494ff6e8c88a 100644 --- a/arch/parisc/kernel/pci-dma.c +++ b/arch/parisc/kernel/pci-dma.c @@ -95,8 +95,8 @@ static inline int map_pte_uncached(pte_t * pte, if (!pte_none(*pte)) printk(KERN_ERR "map_pte_uncached: page already exists\n"); - set_pte(pte, __mk_pte(*paddr_ptr, PAGE_KERNEL_UNC)); purge_tlb_start(flags); + set_pte(pte, __mk_pte(*paddr_ptr, PAGE_KERNEL_UNC)); pdtlb_kernel(orig_vaddr); purge_tlb_end(flags); vaddr += PAGE_SIZE; diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c index 81d6f6391944..2e66a887788e 100644 --- a/arch/parisc/kernel/setup.c +++ b/arch/parisc/kernel/setup.c @@ -334,6 +334,10 @@ static int __init parisc_init(void) /* tell PDC we're Linux. Nevermind failure. */ pdc_stable_write(0x40, &osid, sizeof(osid)); + /* start with known state */ + flush_cache_all_local(); + flush_tlb_all_local(NULL); + processor_init(); #ifdef CONFIG_SMP pr_info("CPU(s): %d out of %d %s at %d.%06d MHz online\n", diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c index 9b63b876a13a..325f30d82b64 100644 --- a/arch/parisc/kernel/time.c +++ b/arch/parisc/kernel/time.c @@ -14,6 +14,7 @@ #include <linux/module.h> #include <linux/rtc.h> #include <linux/sched.h> +#include <linux/sched_clock.h> #include <linux/kernel.h> #include <linux/param.h> #include <linux/string.h> @@ -39,18 +40,6 @@ static unsigned long clocktick __read_mostly; /* timer cycles per tick */ -#ifndef CONFIG_64BIT -/* - * The processor-internal cycle counter (Control Register 16) is used as time - * source for the sched_clock() function. This register is 64bit wide on a - * 64-bit kernel and 32bit on a 32-bit kernel. Since sched_clock() always - * requires a 64bit counter we emulate on the 32-bit kernel the higher 32bits - * with a per-cpu variable which we increase every time the counter - * wraps-around (which happens every ~4 secounds). - */ -static DEFINE_PER_CPU(unsigned long, cr16_high_32_bits); -#endif - /* * We keep time on PA-RISC Linux by using the Interval Timer which is * a pair of registers; one is read-only and one is write-only; both @@ -121,12 +110,6 @@ irqreturn_t __irq_entry timer_interrupt(int irq, void *dev_id) */ mtctl(next_tick, 16); -#if !defined(CONFIG_64BIT) - /* check for overflow on a 32bit kernel (every ~4 seconds). */ - if (unlikely(next_tick < now)) - this_cpu_inc(cr16_high_32_bits); -#endif - /* Skip one clocktick on purpose if we missed next_tick. * The new CR16 must be "later" than current CR16 otherwise * itimer would not fire until CR16 wrapped - e.g 4 seconds @@ -208,7 +191,7 @@ EXPORT_SYMBOL(profile_pc); /* clock source code */ -static cycle_t read_cr16(struct clocksource *cs) +static cycle_t notrace read_cr16(struct clocksource *cs) { return get_cycles(); } @@ -287,26 +270,9 @@ void read_persistent_clock(struct timespec *ts) } -/* - * sched_clock() framework - */ - -static u32 cyc2ns_mul __read_mostly; -static u32 cyc2ns_shift __read_mostly; - -u64 sched_clock(void) +static u64 notrace read_cr16_sched_clock(void) { - u64 now; - - /* Get current cycle counter (Control Register 16). */ -#ifdef CONFIG_64BIT - now = mfctl(16); -#else - now = mfctl(16) + (((u64) this_cpu_read(cr16_high_32_bits)) << 32); -#endif - - /* return the value in ns (cycles_2_ns) */ - return mul_u64_u32_shr(now, cyc2ns_mul, cyc2ns_shift); + return get_cycles(); } @@ -316,17 +282,16 @@ u64 sched_clock(void) void __init time_init(void) { - unsigned long current_cr16_khz; + unsigned long cr16_hz; - current_cr16_khz = PAGE0->mem_10msec/10; /* kHz */ clocktick = (100 * PAGE0->mem_10msec) / HZ; - - /* calculate mult/shift values for cr16 */ - clocks_calc_mult_shift(&cyc2ns_mul, &cyc2ns_shift, current_cr16_khz, - NSEC_PER_MSEC, 0); - start_cpu_itimer(); /* get CPU 0 started */ + cr16_hz = 100 * PAGE0->mem_10msec; /* Hz */ + /* register at clocksource framework */ - clocksource_register_khz(&clocksource_cr16, current_cr16_khz); + clocksource_register_hz(&clocksource_cr16, cr16_hz); + + /* register as sched_clock source */ + sched_clock_register(read_cr16_sched_clock, BITS_PER_LONG, cr16_hz); } diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index eae2dc8bc218..9d47f2efa830 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -100,7 +100,8 @@ src-wlib-y := string.S crt0.S crtsavres.S stdio.c decompress.c main.c \ ns16550.c serial.c simple_alloc.c div64.S util.S \ elf_util.c $(zlib-y) devtree.c stdlib.c \ oflib.c ofconsole.c cuboot.c mpsc.c cpm-serial.c \ - uartlite.c mpc52xx-psc.c opal.c opal-calls.S + uartlite.c mpc52xx-psc.c opal.c +src-wlib-$(CONFIG_PPC64_BOOT_WRAPPER) += opal-calls.S src-wlib-$(CONFIG_40x) += 4xx.c planetcore.c src-wlib-$(CONFIG_44x) += 4xx.c ebony.c bamboo.c src-wlib-$(CONFIG_8xx) += mpc8xx.c planetcore.c fsl-soc.c diff --git a/arch/powerpc/boot/main.c b/arch/powerpc/boot/main.c index 57d42d129033..78aaf4ffd7ab 100644 --- a/arch/powerpc/boot/main.c +++ b/arch/powerpc/boot/main.c @@ -232,8 +232,12 @@ void start(void) console_ops.close(); kentry = (kernel_entry_t) vmlinux.addr; - if (ft_addr) - kentry(ft_addr, 0, NULL); + if (ft_addr) { + if(platform_ops.kentry) + platform_ops.kentry(ft_addr, vmlinux.addr); + else + kentry(ft_addr, 0, NULL); + } else kentry((unsigned long)initrd.addr, initrd.size, loader_info.promptr); diff --git a/arch/powerpc/boot/opal-calls.S b/arch/powerpc/boot/opal-calls.S index ff2f1b97bc53..2a99fc9a3ccf 100644 --- a/arch/powerpc/boot/opal-calls.S +++ b/arch/powerpc/boot/opal-calls.S @@ -12,6 +12,19 @@ .text + .globl opal_kentry +opal_kentry: + /* r3 is the fdt ptr */ + mtctr r4 + li r4, 0 + li r5, 0 + li r6, 0 + li r7, 0 + ld r11,opal@got(r2) + ld r8,0(r11) + ld r9,8(r11) + bctr + #define OPAL_CALL(name, token) \ .globl name; \ name: \ diff --git a/arch/powerpc/boot/opal.c b/arch/powerpc/boot/opal.c index 1f37e1c1d6d8..0272570d02de 100644 --- a/arch/powerpc/boot/opal.c +++ b/arch/powerpc/boot/opal.c @@ -13,7 +13,7 @@ #include <libfdt.h> #include "../include/asm/opal-api.h" -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64_BOOT_WRAPPER /* Global OPAL struct used by opal-call.S */ struct opal { @@ -23,14 +23,25 @@ struct opal { static u32 opal_con_id; +/* see opal-wrappers.S */ int64_t opal_console_write(int64_t term_number, u64 *length, const u8 *buffer); int64_t opal_console_read(int64_t term_number, uint64_t *length, u8 *buffer); int64_t opal_console_write_buffer_space(uint64_t term_number, uint64_t *length); int64_t opal_console_flush(uint64_t term_number); int64_t opal_poll_events(uint64_t *outstanding_event_mask); +void opal_kentry(unsigned long fdt_addr, void *vmlinux_addr); + static int opal_con_open(void) { + /* + * When OPAL loads the boot kernel it stashes the OPAL base and entry + * address in r8 and r9 so the kernel can use the OPAL console + * before unflattening the devicetree. While executing the wrapper will + * probably trash r8 and r9 so this kentry hook restores them before + * entering the decompressed kernel. + */ + platform_ops.kentry = opal_kentry; return 0; } diff --git a/arch/powerpc/boot/ops.h b/arch/powerpc/boot/ops.h index 309d1b127e96..fad1862f4b2d 100644 --- a/arch/powerpc/boot/ops.h +++ b/arch/powerpc/boot/ops.h @@ -30,6 +30,7 @@ struct platform_ops { void * (*realloc)(void *ptr, unsigned long size); void (*exit)(void); void * (*vmlinux_alloc)(unsigned long size); + void (*kentry)(unsigned long fdt_addr, void *vmlinux_addr); }; extern struct platform_ops platform_ops; diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h index d1492736d852..e0baba1535e6 100644 --- a/arch/powerpc/include/asm/asm-prototypes.h +++ b/arch/powerpc/include/asm/asm-prototypes.h @@ -14,6 +14,10 @@ #include <linux/threads.h> #include <linux/kprobes.h> +#include <asm/cacheflush.h> +#include <asm/checksum.h> +#include <asm/uaccess.h> +#include <asm/epapr_hcalls.h> #include <uapi/asm/ucontext.h> @@ -109,4 +113,12 @@ void early_setup_secondary(void); /* time */ void accumulate_stolen_time(void); +/* misc runtime */ +extern u64 __bswapdi2(u64); +extern s64 __lshrdi3(s64, int); +extern s64 __ashldi3(s64, int); +extern s64 __ashrdi3(s64, int); +extern int __cmpdi2(s64, s64); +extern int __ucmpdi2(u64, u64); + #endif /* _ASM_POWERPC_ASM_PROTOTYPES_H */ diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index e88368354e49..e311c25751a4 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -29,6 +29,12 @@ */ /* + * Kernel read only support. + * We added the ppp value 0b110 in ISA 2.04. + */ +#define MMU_FTR_KERNEL_RO ASM_CONST(0x00004000) + +/* * We need to clear top 16bits of va (from the remaining 64 bits )in * tlbie* instructions */ @@ -103,10 +109,10 @@ #define MMU_FTRS_POWER4 MMU_FTRS_DEFAULT_HPTE_ARCH_V2 #define MMU_FTRS_PPC970 MMU_FTRS_POWER4 | MMU_FTR_TLBIE_CROP_VA #define MMU_FTRS_POWER5 MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE -#define MMU_FTRS_POWER6 MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE -#define MMU_FTRS_POWER7 MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE -#define MMU_FTRS_POWER8 MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE -#define MMU_FTRS_POWER9 MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE +#define MMU_FTRS_POWER6 MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE | MMU_FTR_KERNEL_RO +#define MMU_FTRS_POWER7 MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE | MMU_FTR_KERNEL_RO +#define MMU_FTRS_POWER8 MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE | MMU_FTR_KERNEL_RO +#define MMU_FTRS_POWER9 MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE | MMU_FTR_KERNEL_RO #define MMU_FTRS_CELL MMU_FTRS_DEFAULT_HPTE_ARCH_V2 | \ MMU_FTR_CI_LARGE_PAGE #define MMU_FTRS_PA6T MMU_FTRS_DEFAULT_HPTE_ARCH_V2 | \ diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 9cd4e8cbc78c..9e1499f98def 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -355,6 +355,7 @@ #define LPCR_PECE0 ASM_CONST(0x0000000000004000) /* ext. exceptions can cause exit */ #define LPCR_PECE1 ASM_CONST(0x0000000000002000) /* decrementer can cause exit */ #define LPCR_PECE2 ASM_CONST(0x0000000000001000) /* machine check etc can cause exit */ +#define LPCR_PECE_HVEE ASM_CONST(0x0000400000000000) /* P9 Wakeup on HV interrupts */ #define LPCR_MER ASM_CONST(0x0000000000000800) /* Mediated External Exception */ #define LPCR_MER_SH 11 #define LPCR_TC ASM_CONST(0x0000000000000200) /* Translation control */ diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S index 52ff3f025437..37c027ca83b2 100644 --- a/arch/powerpc/kernel/cpu_setup_power.S +++ b/arch/powerpc/kernel/cpu_setup_power.S @@ -98,8 +98,8 @@ _GLOBAL(__setup_cpu_power9) li r0,0 mtspr SPRN_LPID,r0 mfspr r3,SPRN_LPCR - ori r3, r3, LPCR_PECEDH - ori r3, r3, LPCR_HVICE + LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE) + or r3, r3, r4 bl __init_LPCR bl __init_HFSCR bl __init_tlb_power9 @@ -118,8 +118,8 @@ _GLOBAL(__restore_cpu_power9) li r0,0 mtspr SPRN_LPID,r0 mfspr r3,SPRN_LPCR - ori r3, r3, LPCR_PECEDH - ori r3, r3, LPCR_HVICE + LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE) + or r3, r3, r4 bl __init_LPCR bl __init_HFSCR bl __init_tlb_power9 diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index a62be72da274..5c31369435f2 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -671,8 +671,10 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, /* Clear frozen state */ rc = eeh_clear_pe_frozen_state(pe, false); - if (rc) + if (rc) { + pci_unlock_rescan_remove(); return rc; + } /* Give the system 5 seconds to finish running the user-space * hotplug shutdown scripts, e.g. ifdown for ethernet. Yes, diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 8295f51c1a5f..7394b770ae1f 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -94,8 +94,17 @@ SECTIONS * detected, and will result in a crash at boot due to offsets being * wrong. */ +#ifdef CONFIG_PPC64 + /* + * BLOCK(0) overrides the default output section alignment because + * this needs to start right after .head.text in order for fixed + * section placement to work. + */ + .text BLOCK(0) : AT(ADDR(.text) - LOAD_OFFSET) { +#else .text : AT(ADDR(.text) - LOAD_OFFSET) { ALIGN_FUNCTION(); +#endif /* careful! __ftr_alt_* sections need to be close to .text */ *(.text .fixup __ftr_alt_* .ref.text) SCHED_TEXT diff --git a/arch/powerpc/mm/hash64_4k.c b/arch/powerpc/mm/hash64_4k.c index 42c702b3be1f..6fa450c12d6d 100644 --- a/arch/powerpc/mm/hash64_4k.c +++ b/arch/powerpc/mm/hash64_4k.c @@ -55,7 +55,7 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid, */ rflags = htab_convert_pte_flags(new_pte); - if (!cpu_has_feature(CPU_FTR_NOEXECUTE) && + if (cpu_has_feature(CPU_FTR_NOEXECUTE) && !cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) rflags = hash_page_do_lazy_icache(rflags, __pte(old_pte), trap); diff --git a/arch/powerpc/mm/hash64_64k.c b/arch/powerpc/mm/hash64_64k.c index 3bbbea07378c..1a68cb19b0e3 100644 --- a/arch/powerpc/mm/hash64_64k.c +++ b/arch/powerpc/mm/hash64_64k.c @@ -87,7 +87,7 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid, subpg_pte = new_pte & ~subpg_prot; rflags = htab_convert_pte_flags(subpg_pte); - if (!cpu_has_feature(CPU_FTR_NOEXECUTE) && + if (cpu_has_feature(CPU_FTR_NOEXECUTE) && !cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) { /* @@ -258,7 +258,7 @@ int __hash_page_64K(unsigned long ea, unsigned long access, rflags = htab_convert_pte_flags(new_pte); - if (!cpu_has_feature(CPU_FTR_NOEXECUTE) && + if (cpu_has_feature(CPU_FTR_NOEXECUTE) && !cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) rflags = hash_page_do_lazy_icache(rflags, __pte(old_pte), trap); diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 5503078090cd..78dabf065ba9 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -193,8 +193,12 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags) /* * Kernel read only mapped with ppp bits 0b110 */ - if (!(pteflags & _PAGE_WRITE)) - rflags |= (HPTE_R_PP0 | 0x2); + if (!(pteflags & _PAGE_WRITE)) { + if (mmu_has_feature(MMU_FTR_KERNEL_RO)) + rflags |= (HPTE_R_PP0 | 0x2); + else + rflags |= 0x3; + } } else { if (pteflags & _PAGE_RWX) rflags |= 0x2; diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index b23c76b42d6e..165ecdd24d22 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -43,6 +43,7 @@ config SPARC select ARCH_HAS_SG_CHAIN select CPU_NO_EFFICIENT_FFS select HAVE_ARCH_HARDENED_USERCOPY + select PROVE_LOCKING_SMALL if PROVE_LOCKING config SPARC32 def_bool !64BIT @@ -89,6 +90,14 @@ config ARCH_DEFCONFIG config ARCH_PROC_KCORE_TEXT def_bool y +config ARCH_ATU + bool + default y if SPARC64 + +config ARCH_DMA_ADDR_T_64BIT + bool + default y if ARCH_ATU + config IOMMU_HELPER bool default y if SPARC64 @@ -304,6 +313,20 @@ config ARCH_SPARSEMEM_ENABLE config ARCH_SPARSEMEM_DEFAULT def_bool y if SPARC64 +config FORCE_MAX_ZONEORDER + int "Maximum zone order" + default "13" + help + The kernel memory allocator divides physically contiguous memory + blocks into "zones", where each zone is a power of two number of + pages. This option selects the largest power of two that the kernel + keeps in the memory allocator. If you need to allocate very large + blocks of physically contiguous memory, then you may need to + increase this value. + + This config option is actually maximum order plus one. For example, + a value of 13 means that the largest free memory block is 2^12 pages. + source "mm/Kconfig" if SPARC64 diff --git a/arch/sparc/include/asm/hypervisor.h b/arch/sparc/include/asm/hypervisor.h index 666d5ba230d2..73cb8978df58 100644 --- a/arch/sparc/include/asm/hypervisor.h +++ b/arch/sparc/include/asm/hypervisor.h @@ -2335,6 +2335,348 @@ unsigned long sun4v_vintr_set_target(unsigned long dev_handle, */ #define HV_FAST_PCI_MSG_SETVALID 0xd3 +/* PCI IOMMU v2 definitions and services + * + * While the PCI IO definitions above is valid IOMMU v2 adds new PCI IO + * definitions and services. + * + * CTE Clump Table Entry. First level table entry in the ATU. + * + * pci_device_list + * A 32-bit aligned list of pci_devices. + * + * pci_device_listp + * real address of a pci_device_list. 32-bit aligned. + * + * iotte IOMMU translation table entry. + * + * iotte_attributes + * IO Attributes for IOMMU v2 mappings. In addition to + * read, write IOMMU v2 supports relax ordering + * + * io_page_list A 64-bit aligned list of real addresses. Each real + * address in an io_page_list must be properly aligned + * to the pagesize of the given IOTSB. + * + * io_page_list_p Real address of an io_page_list, 64-bit aligned. + * + * IOTSB IO Translation Storage Buffer. An aligned table of + * IOTTEs. Each IOTSB has a pagesize, table size, and + * virtual address associated with it that must match + * a pagesize and table size supported by the un-derlying + * hardware implementation. The alignment requirements + * for an IOTSB depend on the pagesize used for that IOTSB. + * Each IOTTE in an IOTSB maps one pagesize-sized page. + * The size of the IOTSB dictates how large of a virtual + * address space the IOTSB is capable of mapping. + * + * iotsb_handle An opaque identifier for an IOTSB. A devhandle plus + * iotsb_handle represents a binding of an IOTSB to a + * PCI root complex. + * + * iotsb_index Zero-based IOTTE number within an IOTSB. + */ + +/* The index_count argument consists of two fields: + * bits 63:48 #iottes and bits 47:0 iotsb_index + */ +#define HV_PCI_IOTSB_INDEX_COUNT(__iottes, __iotsb_index) \ + (((u64)(__iottes) << 48UL) | ((u64)(__iotsb_index))) + +/* pci_iotsb_conf() + * TRAP: HV_FAST_TRAP + * FUNCTION: HV_FAST_PCI_IOTSB_CONF + * ARG0: devhandle + * ARG1: r_addr + * ARG2: size + * ARG3: pagesize + * ARG4: iova + * RET0: status + * RET1: iotsb_handle + * ERRORS: EINVAL Invalid devhandle, size, iova, or pagesize + * EBADALIGN r_addr is not properly aligned + * ENORADDR r_addr is not a valid real address + * ETOOMANY No further IOTSBs may be configured + * EBUSY Duplicate devhandle, raddir, iova combination + * + * Create an IOTSB suitable for the PCI root complex identified by devhandle, + * for the DMA virtual address defined by the argument iova. + * + * r_addr is the properly aligned base address of the IOTSB and size is the + * IOTSB (table) size in bytes.The IOTSB is required to be zeroed prior to + * being configured. If it contains any values other than zeros then the + * behavior is undefined. + * + * pagesize is the size of each page in the IOTSB. Note that the combination of + * size (table size) and pagesize must be valid. + * + * virt is the DMA virtual address this IOTSB will map. + * + * If successful, the opaque 64-bit handle iotsb_handle is returned in ret1. + * Once configured, privileged access to the IOTSB memory is prohibited and + * creates undefined behavior. The only permitted access is indirect via these + * services. + */ +#define HV_FAST_PCI_IOTSB_CONF 0x190 + +/* pci_iotsb_info() + * TRAP: HV_FAST_TRAP + * FUNCTION: HV_FAST_PCI_IOTSB_INFO + * ARG0: devhandle + * ARG1: iotsb_handle + * RET0: status + * RET1: r_addr + * RET2: size + * RET3: pagesize + * RET4: iova + * RET5: #bound + * ERRORS: EINVAL Invalid devhandle or iotsb_handle + * + * This service returns configuration information about an IOTSB previously + * created with pci_iotsb_conf. + * + * iotsb_handle value 0 may be used with this service to inquire about the + * legacy IOTSB that may or may not exist. If the service succeeds, the return + * values describe the legacy IOTSB and I/O virtual addresses mapped by that + * table. However, the table base address r_addr may contain the value -1 which + * indicates a memory range that cannot be accessed or be reclaimed. + * + * The return value #bound contains the number of PCI devices that iotsb_handle + * is currently bound to. + */ +#define HV_FAST_PCI_IOTSB_INFO 0x191 + +/* pci_iotsb_unconf() + * TRAP: HV_FAST_TRAP + * FUNCTION: HV_FAST_PCI_IOTSB_UNCONF + * ARG0: devhandle + * ARG1: iotsb_handle + * RET0: status + * ERRORS: EINVAL Invalid devhandle or iotsb_handle + * EBUSY The IOTSB is bound and may not be unconfigured + * + * This service unconfigures the IOTSB identified by the devhandle and + * iotsb_handle arguments, previously created with pci_iotsb_conf. + * The IOTSB must not be currently bound to any device or the service will fail + * + * If the call succeeds, iotsb_handle is no longer valid. + */ +#define HV_FAST_PCI_IOTSB_UNCONF 0x192 + +/* pci_iotsb_bind() + * TRAP: HV_FAST_TRAP + * FUNCTION: HV_FAST_PCI_IOTSB_BIND + * ARG0: devhandle + * ARG1: iotsb_handle + * ARG2: pci_device + * RET0: status + * ERRORS: EINVAL Invalid devhandle, iotsb_handle, or pci_device + * EBUSY A PCI function is already bound to an IOTSB at the same + * address range as specified by devhandle, iotsb_handle. + * + * This service binds the PCI function specified by the argument pci_device to + * the IOTSB specified by the arguments devhandle and iotsb_handle. + * + * The PCI device function is bound to the specified IOTSB with the IOVA range + * specified when the IOTSB was configured via pci_iotsb_conf. If the function + * is already bound then it is unbound first. + */ +#define HV_FAST_PCI_IOTSB_BIND 0x193 + +/* pci_iotsb_unbind() + * TRAP: HV_FAST_TRAP + * FUNCTION: HV_FAST_PCI_IOTSB_UNBIND + * ARG0: devhandle + * ARG1: iotsb_handle + * ARG2: pci_device + * RET0: status + * ERRORS: EINVAL Invalid devhandle, iotsb_handle, or pci_device + * ENOMAP The PCI function was not bound to the specified IOTSB + * + * This service unbinds the PCI device specified by the argument pci_device + * from the IOTSB identified * by the arguments devhandle and iotsb_handle. + * + * If the PCI device is not bound to the specified IOTSB then this service will + * fail with status ENOMAP + */ +#define HV_FAST_PCI_IOTSB_UNBIND 0x194 + +/* pci_iotsb_get_binding() + * TRAP: HV_FAST_TRAP + * FUNCTION: HV_FAST_PCI_IOTSB_GET_BINDING + * ARG0: devhandle + * ARG1: iotsb_handle + * ARG2: iova + * RET0: status + * RET1: iotsb_handle + * ERRORS: EINVAL Invalid devhandle, pci_device, or iova + * ENOMAP The PCI function is not bound to an IOTSB at iova + * + * This service returns the IOTSB binding, iotsb_handle, for a given pci_device + * and DMA virtual address, iova. + * + * iova must be the base address of a DMA virtual address range as defined by + * the iommu-address-ranges property in the root complex device node defined + * by the argument devhandle. + */ +#define HV_FAST_PCI_IOTSB_GET_BINDING 0x195 + +/* pci_iotsb_map() + * TRAP: HV_FAST_TRAP + * FUNCTION: HV_FAST_PCI_IOTSB_MAP + * ARG0: devhandle + * ARG1: iotsb_handle + * ARG2: index_count + * ARG3: iotte_attributes + * ARG4: io_page_list_p + * RET0: status + * RET1: #mapped + * ERRORS: EINVAL Invalid devhandle, iotsb_handle, #iottes, + * iotsb_index or iotte_attributes + * EBADALIGN Improperly aligned io_page_list_p or I/O page + * address in the I/O page list. + * ENORADDR Invalid io_page_list_p or I/O page address in + * the I/O page list. + * + * This service creates and flushes mappings in the IOTSB defined by the + * arguments devhandle, iotsb. + * + * The index_count argument consists of two fields. Bits 63:48 contain #iotte + * and bits 47:0 contain iotsb_index + * + * The first mapping is created in the IOTSB index specified by iotsb_index. + * Subsequent mappings are created at iotsb_index+1 and so on. + * + * The attributes of each mapping are defined by the argument iotte_attributes. + * + * The io_page_list_p specifies the real address of the 64-bit-aligned list of + * #iottes I/O page addresses. Each page address must be a properly aligned + * real address of a page to be mapped in the IOTSB. The first entry in the I/O + * page list contains the real address of the first page, the 2nd entry for the + * 2nd page, and so on. + * + * #iottes must be greater than zero. + * + * The return value #mapped is the actual number of mappings created, which may + * be less than or equal to the argument #iottes. If the function returns + * successfully with a #mapped value less than the requested #iottes then the + * caller should continue to invoke the service with updated iotsb_index, + * #iottes, and io_page_list_p arguments until all pages are mapped. + * + * This service must not be used to demap a mapping. In other words, all + * mappings must be valid and have one or both of the RW attribute bits set. + * + * Note: + * It is implementation-defined whether I/O page real address validity checking + * is done at time mappings are established or deferred until they are + * accessed. + */ +#define HV_FAST_PCI_IOTSB_MAP 0x196 + +/* pci_iotsb_map_one() + * TRAP: HV_FAST_TRAP + * FUNCTION: HV_FAST_PCI_IOTSB_MAP_ONE + * ARG0: devhandle + * ARG1: iotsb_handle + * ARG2: iotsb_index + * ARG3: iotte_attributes + * ARG4: r_addr + * RET0: status + * ERRORS: EINVAL Invalid devhandle,iotsb_handle, iotsb_index + * or iotte_attributes + * EBADALIGN Improperly aligned r_addr + * ENORADDR Invalid r_addr + * + * This service creates and flushes a single mapping in the IOTSB defined by the + * arguments devhandle, iotsb. + * + * The mapping for the page at r_addr is created at the IOTSB index specified by + * iotsb_index with the attributes iotte_attributes. + * + * This service must not be used to demap a mapping. In other words, the mapping + * must be valid and have one or both of the RW attribute bits set. + * + * Note: + * It is implementation-defined whether I/O page real address validity checking + * is done at time mappings are established or deferred until they are + * accessed. + */ +#define HV_FAST_PCI_IOTSB_MAP_ONE 0x197 + +/* pci_iotsb_demap() + * TRAP: HV_FAST_TRAP + * FUNCTION: HV_FAST_PCI_IOTSB_DEMAP + * ARG0: devhandle + * ARG1: iotsb_handle + * ARG2: iotsb_index + * ARG3: #iottes + * RET0: status + * RET1: #unmapped + * ERRORS: EINVAL Invalid devhandle, iotsb_handle, iotsb_index or #iottes + * + * This service unmaps and flushes up to #iottes mappings starting at index + * iotsb_index from the IOTSB defined by the arguments devhandle, iotsb. + * + * #iottes must be greater than zero. + * + * The actual number of IOTTEs unmapped is returned in #unmapped and may be less + * than or equal to the requested number of IOTTEs, #iottes. + * + * If #unmapped is less than #iottes, the caller should continue to invoke this + * service with updated iotsb_index and #iottes arguments until all pages are + * demapped. + */ +#define HV_FAST_PCI_IOTSB_DEMAP 0x198 + +/* pci_iotsb_getmap() + * TRAP: HV_FAST_TRAP + * FUNCTION: HV_FAST_PCI_IOTSB_GETMAP + * ARG0: devhandle + * ARG1: iotsb_handle + * ARG2: iotsb_index + * RET0: status + * RET1: r_addr + * RET2: iotte_attributes + * ERRORS: EINVAL Invalid devhandle, iotsb_handle, or iotsb_index + * ENOMAP No mapping was found + * + * This service returns the mapping specified by index iotsb_index from the + * IOTSB defined by the arguments devhandle, iotsb. + * + * Upon success, the real address of the mapping shall be returned in + * r_addr and thethe IOTTE mapping attributes shall be returned in + * iotte_attributes. + * + * The return value iotte_attributes may not include optional features used in + * the call to create the mapping. + */ +#define HV_FAST_PCI_IOTSB_GETMAP 0x199 + +/* pci_iotsb_sync_mappings() + * TRAP: HV_FAST_TRAP + * FUNCTION: HV_FAST_PCI_IOTSB_SYNC_MAPPINGS + * ARG0: devhandle + * ARG1: iotsb_handle + * ARG2: iotsb_index + * ARG3: #iottes + * RET0: status + * RET1: #synced + * ERROS: EINVAL Invalid devhandle, iotsb_handle, iotsb_index, or #iottes + * + * This service synchronizes #iottes mappings starting at index iotsb_index in + * the IOTSB defined by the arguments devhandle, iotsb. + * + * #iottes must be greater than zero. + * + * The actual number of IOTTEs synchronized is returned in #synced, which may + * be less than or equal to the requested number, #iottes. + * + * Upon a successful return, #synced is less than #iottes, the caller should + * continue to invoke this service with updated iotsb_index and #iottes + * arguments until all pages are synchronized. + */ +#define HV_FAST_PCI_IOTSB_SYNC_MAPPINGS 0x19a + /* Logical Domain Channel services. */ #define LDC_CHANNEL_DOWN 0 @@ -2993,6 +3335,7 @@ unsigned long sun4v_m7_set_perfreg(unsigned long reg_num, #define HV_GRP_SDIO 0x0108 #define HV_GRP_SDIO_ERR 0x0109 #define HV_GRP_REBOOT_DATA 0x0110 +#define HV_GRP_ATU 0x0111 #define HV_GRP_M7_PERF 0x0114 #define HV_GRP_NIAG_PERF 0x0200 #define HV_GRP_FIRE_PERF 0x0201 diff --git a/arch/sparc/include/asm/iommu_64.h b/arch/sparc/include/asm/iommu_64.h index cd0d69fa7592..f24f356f2503 100644 --- a/arch/sparc/include/asm/iommu_64.h +++ b/arch/sparc/include/asm/iommu_64.h @@ -24,8 +24,36 @@ struct iommu_arena { unsigned int limit; }; +#define ATU_64_SPACE_SIZE 0x800000000 /* 32G */ + +/* Data structures for SPARC ATU architecture */ +struct atu_iotsb { + void *table; /* IOTSB table base virtual addr*/ + u64 ra; /* IOTSB table real addr */ + u64 dvma_size; /* ranges[3].size or OS slected 32G size */ + u64 dvma_base; /* ranges[3].base */ + u64 table_size; /* IOTSB table size */ + u64 page_size; /* IO PAGE size for IOTSB */ + u32 iotsb_num; /* tsbnum is same as iotsb_handle */ +}; + +struct atu_ranges { + u64 base; + u64 size; +}; + +struct atu { + struct atu_ranges *ranges; + struct atu_iotsb *iotsb; + struct iommu_map_table tbl; + u64 base; + u64 size; + u64 dma_addr_mask; +}; + struct iommu { struct iommu_map_table tbl; + struct atu *atu; spinlock_t lock; u32 dma_addr_mask; iopte_t *page_table; diff --git a/arch/sparc/kernel/hvapi.c b/arch/sparc/kernel/hvapi.c index 662500fa555f..267731234ce8 100644 --- a/arch/sparc/kernel/hvapi.c +++ b/arch/sparc/kernel/hvapi.c @@ -39,6 +39,7 @@ static struct api_info api_table[] = { { .group = HV_GRP_SDIO, }, { .group = HV_GRP_SDIO_ERR, }, { .group = HV_GRP_REBOOT_DATA, }, + { .group = HV_GRP_ATU, .flags = FLAG_PRE_API }, { .group = HV_GRP_NIAG_PERF, .flags = FLAG_PRE_API }, { .group = HV_GRP_FIRE_PERF, }, { .group = HV_GRP_N2_CPU, }, diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c index 5c615abff030..852a3291db96 100644 --- a/arch/sparc/kernel/iommu.c +++ b/arch/sparc/kernel/iommu.c @@ -760,8 +760,12 @@ int dma_supported(struct device *dev, u64 device_mask) struct iommu *iommu = dev->archdata.iommu; u64 dma_addr_mask = iommu->dma_addr_mask; - if (device_mask >= (1UL << 32UL)) - return 0; + if (device_mask > DMA_BIT_MASK(32)) { + if (iommu->atu) + dma_addr_mask = iommu->atu->dma_addr_mask; + else + return 0; + } if ((device_mask & dma_addr_mask) == dma_addr_mask) return 1; diff --git a/arch/sparc/kernel/iommu_common.h b/arch/sparc/kernel/iommu_common.h index b40cec252905..828493329f68 100644 --- a/arch/sparc/kernel/iommu_common.h +++ b/arch/sparc/kernel/iommu_common.h @@ -13,7 +13,6 @@ #include <linux/scatterlist.h> #include <linux/device.h> #include <linux/iommu-helper.h> -#include <linux/scatterlist.h> #include <asm/iommu.h> diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c index db57d8acdc01..06981cc716b6 100644 --- a/arch/sparc/kernel/pci_sun4v.c +++ b/arch/sparc/kernel/pci_sun4v.c @@ -44,6 +44,9 @@ static struct vpci_version vpci_versions[] = { { .major = 1, .minor = 1 }, }; +static unsigned long vatu_major = 1; +static unsigned long vatu_minor = 1; + #define PGLIST_NENTS (PAGE_SIZE / sizeof(u64)) struct iommu_batch { @@ -69,34 +72,57 @@ static inline void iommu_batch_start(struct device *dev, unsigned long prot, uns } /* Interrupts must be disabled. */ -static long iommu_batch_flush(struct iommu_batch *p) +static long iommu_batch_flush(struct iommu_batch *p, u64 mask) { struct pci_pbm_info *pbm = p->dev->archdata.host_controller; + u64 *pglist = p->pglist; + u64 index_count; unsigned long devhandle = pbm->devhandle; unsigned long prot = p->prot; unsigned long entry = p->entry; - u64 *pglist = p->pglist; unsigned long npages = p->npages; + unsigned long iotsb_num; + unsigned long ret; + long num; /* VPCI maj=1, min=[0,1] only supports read and write */ if (vpci_major < 2) prot &= (HV_PCI_MAP_ATTR_READ | HV_PCI_MAP_ATTR_WRITE); while (npages != 0) { - long num; - - num = pci_sun4v_iommu_map(devhandle, HV_PCI_TSBID(0, entry), - npages, prot, __pa(pglist)); - if (unlikely(num < 0)) { - if (printk_ratelimit()) - printk("iommu_batch_flush: IOMMU map of " - "[%08lx:%08llx:%lx:%lx:%lx] failed with " - "status %ld\n", - devhandle, HV_PCI_TSBID(0, entry), - npages, prot, __pa(pglist), num); - return -1; + if (mask <= DMA_BIT_MASK(32)) { + num = pci_sun4v_iommu_map(devhandle, + HV_PCI_TSBID(0, entry), + npages, + prot, + __pa(pglist)); + if (unlikely(num < 0)) { + pr_err_ratelimited("%s: IOMMU map of [%08lx:%08llx:%lx:%lx:%lx] failed with status %ld\n", + __func__, + devhandle, + HV_PCI_TSBID(0, entry), + npages, prot, __pa(pglist), + num); + return -1; + } + } else { + index_count = HV_PCI_IOTSB_INDEX_COUNT(npages, entry), + iotsb_num = pbm->iommu->atu->iotsb->iotsb_num; + ret = pci_sun4v_iotsb_map(devhandle, + iotsb_num, + index_count, + prot, + __pa(pglist), + &num); + if (unlikely(ret != HV_EOK)) { + pr_err_ratelimited("%s: ATU map of [%08lx:%lx:%llx:%lx:%lx] failed with status %ld\n", + __func__, + devhandle, iotsb_num, + index_count, prot, + __pa(pglist), ret); + return -1; + } } - entry += num; npages -= num; pglist += num; @@ -108,19 +134,19 @@ static long iommu_batch_flush(struct iommu_batch *p) return 0; } -static inline void iommu_batch_new_entry(unsigned long entry) +static inline void iommu_batch_new_entry(unsigned long entry, u64 mask) { struct iommu_batch *p = this_cpu_ptr(&iommu_batch); if (p->entry + p->npages == entry) return; if (p->entry != ~0UL) - iommu_batch_flush(p); + iommu_batch_flush(p, mask); p->entry = entry; } /* Interrupts must be disabled. */ -static inline long iommu_batch_add(u64 phys_page) +static inline long iommu_batch_add(u64 phys_page, u64 mask) { struct iommu_batch *p = this_cpu_ptr(&iommu_batch); @@ -128,28 +154,31 @@ static inline long iommu_batch_add(u64 phys_page) p->pglist[p->npages++] = phys_page; if (p->npages == PGLIST_NENTS) - return iommu_batch_flush(p); + return iommu_batch_flush(p, mask); return 0; } /* Interrupts must be disabled. */ -static inline long iommu_batch_end(void) +static inline long iommu_batch_end(u64 mask) { struct iommu_batch *p = this_cpu_ptr(&iommu_batch); BUG_ON(p->npages >= PGLIST_NENTS); - return iommu_batch_flush(p); + return iommu_batch_flush(p, mask); } static void *dma_4v_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addrp, gfp_t gfp, unsigned long attrs) { + u64 mask; unsigned long flags, order, first_page, npages, n; unsigned long prot = 0; struct iommu *iommu; + struct atu *atu; + struct iommu_map_table *tbl; struct page *page; void *ret; long entry; @@ -174,14 +203,21 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size, memset((char *)first_page, 0, PAGE_SIZE << order); iommu = dev->archdata.iommu; + atu = iommu->atu; + + mask = dev->coherent_dma_mask; + if (mask <= DMA_BIT_MASK(32)) + tbl = &iommu->tbl; + else + tbl = &atu->tbl; - entry = iommu_tbl_range_alloc(dev, &iommu->tbl, npages, NULL, + entry = iommu_tbl_range_alloc(dev, tbl, npages, NULL, (unsigned long)(-1), 0); if (unlikely(entry == IOMMU_ERROR_CODE)) goto range_alloc_fail; - *dma_addrp = (iommu->tbl.table_map_base + (entry << IO_PAGE_SHIFT)); + *dma_addrp = (tbl->table_map_base + (entry << IO_PAGE_SHIFT)); ret = (void *) first_page; first_page = __pa(first_page); @@ -193,12 +229,12 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size, entry); for (n = 0; n < npages; n++) { - long err = iommu_batch_add(first_page + (n * PAGE_SIZE)); + long err = iommu_batch_add(first_page + (n * PAGE_SIZE), mask); if (unlikely(err < 0L)) goto iommu_map_fail; } - if (unlikely(iommu_batch_end() < 0L)) + if (unlikely(iommu_batch_end(mask) < 0L)) goto iommu_map_fail; local_irq_restore(flags); @@ -206,25 +242,71 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size, return ret; iommu_map_fail: - iommu_tbl_range_free(&iommu->tbl, *dma_addrp, npages, IOMMU_ERROR_CODE); + iommu_tbl_range_free(tbl, *dma_addrp, npages, IOMMU_ERROR_CODE); range_alloc_fail: free_pages(first_page, order); return NULL; } -static void dma_4v_iommu_demap(void *demap_arg, unsigned long entry, - unsigned long npages) +unsigned long dma_4v_iotsb_bind(unsigned long devhandle, + unsigned long iotsb_num, + struct pci_bus *bus_dev) +{ + struct pci_dev *pdev; + unsigned long err; + unsigned int bus; + unsigned int device; + unsigned int fun; + + list_for_each_entry(pdev, &bus_dev->devices, bus_list) { + if (pdev->subordinate) { + /* No need to bind pci bridge */ + dma_4v_iotsb_bind(devhandle, iotsb_num, + pdev->subordinate); + } else { + bus = bus_dev->number; + device = PCI_SLOT(pdev->devfn); + fun = PCI_FUNC(pdev->devfn); + err = pci_sun4v_iotsb_bind(devhandle, iotsb_num, + HV_PCI_DEVICE_BUILD(bus, + device, + fun)); + + /* If bind fails for one device it is going to fail + * for rest of the devices because we are sharing + * IOTSB. So in case of failure simply return with + * error. + */ + if (err) + return err; + } + } + + return 0; +} + +static void dma_4v_iommu_demap(struct device *dev, unsigned long devhandle, + dma_addr_t dvma, unsigned long iotsb_num, + unsigned long entry, unsigned long npages) { - u32 devhandle = *(u32 *)demap_arg; unsigned long num, flags; + unsigned long ret; local_irq_save(flags); do { - num = pci_sun4v_iommu_demap(devhandle, - HV_PCI_TSBID(0, entry), - npages); - + if (dvma <= DMA_BIT_MASK(32)) { + num = pci_sun4v_iommu_demap(devhandle, + HV_PCI_TSBID(0, entry), + npages); + } else { + ret = pci_sun4v_iotsb_demap(devhandle, iotsb_num, + entry, npages, &num); + if (unlikely(ret != HV_EOK)) { + pr_err_ratelimited("pci_iotsb_demap() failed with error: %ld\n", + ret); + } + } entry += num; npages -= num; } while (npages != 0); @@ -236,16 +318,28 @@ static void dma_4v_free_coherent(struct device *dev, size_t size, void *cpu, { struct pci_pbm_info *pbm; struct iommu *iommu; + struct atu *atu; + struct iommu_map_table *tbl; unsigned long order, npages, entry; + unsigned long iotsb_num; u32 devhandle; npages = IO_PAGE_ALIGN(size) >> IO_PAGE_SHIFT; iommu = dev->archdata.iommu; pbm = dev->archdata.host_controller; + atu = iommu->atu; devhandle = pbm->devhandle; - entry = ((dvma - iommu->tbl.table_map_base) >> IO_PAGE_SHIFT); - dma_4v_iommu_demap(&devhandle, entry, npages); - iommu_tbl_range_free(&iommu->tbl, dvma, npages, IOMMU_ERROR_CODE); + + if (dvma <= DMA_BIT_MASK(32)) { + tbl = &iommu->tbl; + iotsb_num = 0; /* we don't care for legacy iommu */ + } else { + tbl = &atu->tbl; + iotsb_num = atu->iotsb->iotsb_num; + } + entry = ((dvma - tbl->table_map_base) >> IO_PAGE_SHIFT); + dma_4v_iommu_demap(dev, devhandle, dvma, iotsb_num, entry, npages); + iommu_tbl_range_free(tbl, dvma, npages, IOMMU_ERROR_CODE); order = get_order(size); if (order < 10) free_pages((unsigned long)cpu, order); @@ -257,13 +351,17 @@ static dma_addr_t dma_4v_map_page(struct device *dev, struct page *page, unsigned long attrs) { struct iommu *iommu; + struct atu *atu; + struct iommu_map_table *tbl; + u64 mask; unsigned long flags, npages, oaddr; unsigned long i, base_paddr; - u32 bus_addr, ret; unsigned long prot; + dma_addr_t bus_addr, ret; long entry; iommu = dev->archdata.iommu; + atu = iommu->atu; if (unlikely(direction == DMA_NONE)) goto bad; @@ -272,13 +370,19 @@ static dma_addr_t dma_4v_map_page(struct device *dev, struct page *page, npages = IO_PAGE_ALIGN(oaddr + sz) - (oaddr & IO_PAGE_MASK); npages >>= IO_PAGE_SHIFT; - entry = iommu_tbl_range_alloc(dev, &iommu->tbl, npages, NULL, + mask = *dev->dma_mask; + if (mask <= DMA_BIT_MASK(32)) + tbl = &iommu->tbl; + else + tbl = &atu->tbl; + + entry = iommu_tbl_range_alloc(dev, tbl, npages, NULL, (unsigned long)(-1), 0); if (unlikely(entry == IOMMU_ERROR_CODE)) goto bad; - bus_addr = (iommu->tbl.table_map_base + (entry << IO_PAGE_SHIFT)); + bus_addr = (tbl->table_map_base + (entry << IO_PAGE_SHIFT)); ret = bus_addr | (oaddr & ~IO_PAGE_MASK); base_paddr = __pa(oaddr & IO_PAGE_MASK); prot = HV_PCI_MAP_ATTR_READ; @@ -293,11 +397,11 @@ static dma_addr_t dma_4v_map_page(struct device *dev, struct page *page, iommu_batch_start(dev, prot, entry); for (i = 0; i < npages; i++, base_paddr += IO_PAGE_SIZE) { - long err = iommu_batch_add(base_paddr); + long err = iommu_batch_add(base_paddr, mask); if (unlikely(err < 0L)) goto iommu_map_fail; } - if (unlikely(iommu_batch_end() < 0L)) + if (unlikely(iommu_batch_end(mask) < 0L)) goto iommu_map_fail; local_irq_restore(flags); @@ -310,7 +414,7 @@ bad: return DMA_ERROR_CODE; iommu_map_fail: - iommu_tbl_range_free(&iommu->tbl, bus_addr, npages, IOMMU_ERROR_CODE); + iommu_tbl_range_free(tbl, bus_addr, npages, IOMMU_ERROR_CODE); return DMA_ERROR_CODE; } @@ -320,7 +424,10 @@ static void dma_4v_unmap_page(struct device *dev, dma_addr_t bus_addr, { struct pci_pbm_info *pbm; struct iommu *iommu; + struct atu *atu; + struct iommu_map_table *tbl; unsigned long npages; + unsigned long iotsb_num; long entry; u32 devhandle; @@ -332,14 +439,23 @@ static void dma_4v_unmap_page(struct device *dev, dma_addr_t bus_addr, iommu = dev->archdata.iommu; pbm = dev->archdata.host_controller; + atu = iommu->atu; devhandle = pbm->devhandle; npages = IO_PAGE_ALIGN(bus_addr + sz) - (bus_addr & IO_PAGE_MASK); npages >>= IO_PAGE_SHIFT; bus_addr &= IO_PAGE_MASK; - entry = (bus_addr - iommu->tbl.table_map_base) >> IO_PAGE_SHIFT; - dma_4v_iommu_demap(&devhandle, entry, npages); - iommu_tbl_range_free(&iommu->tbl, bus_addr, npages, IOMMU_ERROR_CODE); + + if (bus_addr <= DMA_BIT_MASK(32)) { + iotsb_num = 0; /* we don't care for legacy iommu */ + tbl = &iommu->tbl; + } else { + iotsb_num = atu->iotsb->iotsb_num; + tbl = &atu->tbl; + } + entry = (bus_addr - tbl->table_map_base) >> IO_PAGE_SHIFT; + dma_4v_iommu_demap(dev, devhandle, bus_addr, iotsb_num, entry, npages); + iommu_tbl_range_free(tbl, bus_addr, npages, IOMMU_ERROR_CODE); } static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist, @@ -353,12 +469,17 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist, unsigned long seg_boundary_size; int outcount, incount, i; struct iommu *iommu; + struct atu *atu; + struct iommu_map_table *tbl; + u64 mask; unsigned long base_shift; long err; BUG_ON(direction == DMA_NONE); iommu = dev->archdata.iommu; + atu = iommu->atu; + if (nelems == 0 || !iommu) return 0; @@ -384,7 +505,15 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist, max_seg_size = dma_get_max_seg_size(dev); seg_boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1, IO_PAGE_SIZE) >> IO_PAGE_SHIFT; - base_shift = iommu->tbl.table_map_base >> IO_PAGE_SHIFT; + + mask = *dev->dma_mask; + if (mask <= DMA_BIT_MASK(32)) + tbl = &iommu->tbl; + else + tbl = &atu->tbl; + + base_shift = tbl->table_map_base >> IO_PAGE_SHIFT; + for_each_sg(sglist, s, nelems, i) { unsigned long paddr, npages, entry, out_entry = 0, slen; @@ -397,27 +526,26 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist, /* Allocate iommu entries for that segment */ paddr = (unsigned long) SG_ENT_PHYS_ADDRESS(s); npages = iommu_num_pages(paddr, slen, IO_PAGE_SIZE); - entry = iommu_tbl_range_alloc(dev, &iommu->tbl, npages, + entry = iommu_tbl_range_alloc(dev, tbl, npages, &handle, (unsigned long)(-1), 0); /* Handle failure */ if (unlikely(entry == IOMMU_ERROR_CODE)) { - if (printk_ratelimit()) - printk(KERN_INFO "iommu_alloc failed, iommu %p paddr %lx" - " npages %lx\n", iommu, paddr, npages); + pr_err_ratelimited("iommu_alloc failed, iommu %p paddr %lx npages %lx\n", + tbl, paddr, npages); goto iommu_map_failed; } - iommu_batch_new_entry(entry); + iommu_batch_new_entry(entry, mask); /* Convert entry to a dma_addr_t */ - dma_addr = iommu->tbl.table_map_base + (entry << IO_PAGE_SHIFT); + dma_addr = tbl->table_map_base + (entry << IO_PAGE_SHIFT); dma_addr |= (s->offset & ~IO_PAGE_MASK); /* Insert into HW table */ paddr &= IO_PAGE_MASK; while (npages--) { - err = iommu_batch_add(paddr); + err = iommu_batch_add(paddr, mask); if (unlikely(err < 0L)) goto iommu_map_failed; paddr += IO_PAGE_SIZE; @@ -452,7 +580,7 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist, dma_next = dma_addr + slen; } - err = iommu_batch_end(); + err = iommu_batch_end(mask); if (unlikely(err < 0L)) goto iommu_map_failed; @@ -475,7 +603,7 @@ iommu_map_failed: vaddr = s->dma_address & IO_PAGE_MASK; npages = iommu_num_pages(s->dma_address, s->dma_length, IO_PAGE_SIZE); - iommu_tbl_range_free(&iommu->tbl, vaddr, npages, + iommu_tbl_range_free(tbl, vaddr, npages, IOMMU_ERROR_CODE); /* XXX demap? XXX */ s->dma_address = DMA_ERROR_CODE; @@ -496,13 +624,16 @@ static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist, struct pci_pbm_info *pbm; struct scatterlist *sg; struct iommu *iommu; + struct atu *atu; unsigned long flags, entry; + unsigned long iotsb_num; u32 devhandle; BUG_ON(direction == DMA_NONE); iommu = dev->archdata.iommu; pbm = dev->archdata.host_controller; + atu = iommu->atu; devhandle = pbm->devhandle; local_irq_save(flags); @@ -512,15 +643,24 @@ static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist, dma_addr_t dma_handle = sg->dma_address; unsigned int len = sg->dma_length; unsigned long npages; - struct iommu_map_table *tbl = &iommu->tbl; + struct iommu_map_table *tbl; unsigned long shift = IO_PAGE_SHIFT; if (!len) break; npages = iommu_num_pages(dma_handle, len, IO_PAGE_SIZE); + + if (dma_handle <= DMA_BIT_MASK(32)) { + iotsb_num = 0; /* we don't care for legacy iommu */ + tbl = &iommu->tbl; + } else { + iotsb_num = atu->iotsb->iotsb_num; + tbl = &atu->tbl; + } entry = ((dma_handle - tbl->table_map_base) >> shift); - dma_4v_iommu_demap(&devhandle, entry, npages); - iommu_tbl_range_free(&iommu->tbl, dma_handle, npages, + dma_4v_iommu_demap(dev, devhandle, dma_handle, iotsb_num, + entry, npages); + iommu_tbl_range_free(tbl, dma_handle, npages, IOMMU_ERROR_CODE); sg = sg_next(sg); } @@ -581,6 +721,132 @@ static unsigned long probe_existing_entries(struct pci_pbm_info *pbm, return cnt; } +static int pci_sun4v_atu_alloc_iotsb(struct pci_pbm_info *pbm) +{ + struct atu *atu = pbm->iommu->atu; + struct atu_iotsb *iotsb; + void *table; + u64 table_size; + u64 iotsb_num; + unsigned long order; + unsigned long err; + + iotsb = kzalloc(sizeof(*iotsb), GFP_KERNEL); + if (!iotsb) { + err = -ENOMEM; + goto out_err; + } + atu->iotsb = iotsb; + + /* calculate size of IOTSB */ + table_size = (atu->size / IO_PAGE_SIZE) * 8; + order = get_order(table_size); + table = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, order); + if (!table) { + err = -ENOMEM; + goto table_failed; + } + iotsb->table = table; + iotsb->ra = __pa(table); + iotsb->dvma_size = atu->size; + iotsb->dvma_base = atu->base; + iotsb->table_size = table_size; + iotsb->page_size = IO_PAGE_SIZE; + + /* configure and register IOTSB with HV */ + err = pci_sun4v_iotsb_conf(pbm->devhandle, + iotsb->ra, + iotsb->table_size, + iotsb->page_size, + iotsb->dvma_base, + &iotsb_num); + if (err) { + pr_err(PFX "pci_iotsb_conf failed error: %ld\n", err); + goto iotsb_conf_failed; + } + iotsb->iotsb_num = iotsb_num; + + err = dma_4v_iotsb_bind(pbm->devhandle, iotsb_num, pbm->pci_bus); + if (err) { + pr_err(PFX "pci_iotsb_bind failed error: %ld\n", err); + goto iotsb_conf_failed; + } + + return 0; + +iotsb_conf_failed: + free_pages((unsigned long)table, order); +table_failed: + kfree(iotsb); +out_err: + return err; +} + +static int pci_sun4v_atu_init(struct pci_pbm_info *pbm) +{ + struct atu *atu = pbm->iommu->atu; + unsigned long err; + const u64 *ranges; + u64 map_size, num_iotte; + u64 dma_mask; + const u32 *page_size; + int len; + + ranges = of_get_property(pbm->op->dev.of_node, "iommu-address-ranges", + &len); + if (!ranges) { + pr_err(PFX "No iommu-address-ranges\n"); + return -EINVAL; + } + + page_size = of_get_property(pbm->op->dev.of_node, "iommu-pagesizes", + NULL); + if (!page_size) { + pr_err(PFX "No iommu-pagesizes\n"); + return -EINVAL; + } + + /* There are 4 iommu-address-ranges supported. Each range is pair of + * {base, size}. The ranges[0] and ranges[1] are 32bit address space + * while ranges[2] and ranges[3] are 64bit space. We want to use 64bit + * address ranges to support 64bit addressing. Because 'size' for + * address ranges[2] and ranges[3] are same we can select either of + * ranges[2] or ranges[3] for mapping. However due to 'size' is too + * large for OS to allocate IOTSB we are using fix size 32G + * (ATU_64_SPACE_SIZE) which is more than enough for all PCIe devices + * to share. + */ + atu->ranges = (struct atu_ranges *)ranges; + atu->base = atu->ranges[3].base; + atu->size = ATU_64_SPACE_SIZE; + + /* Create IOTSB */ + err = pci_sun4v_atu_alloc_iotsb(pbm); + if (err) { + pr_err(PFX "Error creating ATU IOTSB\n"); + return err; + } + + /* Create ATU iommu map. + * One bit represents one iotte in IOTSB table. + */ + dma_mask = (roundup_pow_of_two(atu->size) - 1UL); + num_iotte = atu->size / IO_PAGE_SIZE; + map_size = num_iotte / 8; + atu->tbl.table_map_base = atu->base; + atu->dma_addr_mask = dma_mask; + atu->tbl.map = kzalloc(map_size, GFP_KERNEL); + if (!atu->tbl.map) + return -ENOMEM; + + iommu_tbl_pool_init(&atu->tbl, num_iotte, IO_PAGE_SHIFT, + NULL, false /* no large_pool */, + 0 /* default npools */, + false /* want span boundary checking */); + + return 0; +} + static int pci_sun4v_iommu_init(struct pci_pbm_info *pbm) { static const u32 vdma_default[] = { 0x80000000, 0x80000000 }; @@ -918,6 +1184,18 @@ static int pci_sun4v_pbm_init(struct pci_pbm_info *pbm, pci_sun4v_scan_bus(pbm, &op->dev); + /* if atu_init fails its not complete failure. + * we can still continue using legacy iommu. + */ + if (pbm->iommu->atu) { + err = pci_sun4v_atu_init(pbm); + if (err) { + kfree(pbm->iommu->atu); + pbm->iommu->atu = NULL; + pr_err(PFX "ATU init failed, err=%d\n", err); + } + } + pbm->next = pci_pbm_root; pci_pbm_root = pbm; @@ -931,8 +1209,10 @@ static int pci_sun4v_probe(struct platform_device *op) struct pci_pbm_info *pbm; struct device_node *dp; struct iommu *iommu; + struct atu *atu; u32 devhandle; int i, err = -ENODEV; + static bool hv_atu = true; dp = op->dev.of_node; @@ -954,6 +1234,19 @@ static int pci_sun4v_probe(struct platform_device *op) pr_info(PFX "Registered hvapi major[%lu] minor[%lu]\n", vpci_major, vpci_minor); + err = sun4v_hvapi_register(HV_GRP_ATU, vatu_major, &vatu_minor); + if (err) { + /* don't return an error if we fail to register the + * ATU group, but ATU hcalls won't be available. + */ + hv_atu = false; + pr_err(PFX "Could not register hvapi ATU err=%d\n", + err); + } else { + pr_info(PFX "Registered hvapi ATU major[%lu] minor[%lu]\n", + vatu_major, vatu_minor); + } + dma_ops = &sun4v_dma_ops; } @@ -991,6 +1284,14 @@ static int pci_sun4v_probe(struct platform_device *op) } pbm->iommu = iommu; + iommu->atu = NULL; + if (hv_atu) { + atu = kzalloc(sizeof(*atu), GFP_KERNEL); + if (!atu) + pr_err(PFX "Could not allocate atu\n"); + else + iommu->atu = atu; + } err = pci_sun4v_pbm_init(pbm, op, devhandle); if (err) @@ -1001,6 +1302,7 @@ static int pci_sun4v_probe(struct platform_device *op) return 0; out_free_iommu: + kfree(iommu->atu); kfree(pbm->iommu); out_free_controller: diff --git a/arch/sparc/kernel/pci_sun4v.h b/arch/sparc/kernel/pci_sun4v.h index 5642212390b2..22603a4e48bf 100644 --- a/arch/sparc/kernel/pci_sun4v.h +++ b/arch/sparc/kernel/pci_sun4v.h @@ -89,4 +89,25 @@ unsigned long pci_sun4v_msg_setvalid(unsigned long devhandle, unsigned long msinum, unsigned long valid); +/* Sun4v HV IOMMU v2 APIs */ +unsigned long pci_sun4v_iotsb_conf(unsigned long devhandle, + unsigned long ra, + unsigned long table_size, + unsigned long page_size, + unsigned long dvma_base, + u64 *iotsb_num); +unsigned long pci_sun4v_iotsb_bind(unsigned long devhandle, + unsigned long iotsb_num, + unsigned int pci_device); +unsigned long pci_sun4v_iotsb_map(unsigned long devhandle, + unsigned long iotsb_num, + unsigned long iotsb_index_iottes, + unsigned long io_attributes, + unsigned long io_page_list_pa, + long *mapped); +unsigned long pci_sun4v_iotsb_demap(unsigned long devhandle, + unsigned long iotsb_num, + unsigned long iotsb_index, + unsigned long iottes, + unsigned long *demapped); #endif /* !(_PCI_SUN4V_H) */ diff --git a/arch/sparc/kernel/pci_sun4v_asm.S b/arch/sparc/kernel/pci_sun4v_asm.S index e606d46c6815..578f09657916 100644 --- a/arch/sparc/kernel/pci_sun4v_asm.S +++ b/arch/sparc/kernel/pci_sun4v_asm.S @@ -360,3 +360,71 @@ ENTRY(pci_sun4v_msg_setvalid) mov %o0, %o0 ENDPROC(pci_sun4v_msg_setvalid) + /* + * %o0: devhandle + * %o1: r_addr + * %o2: size + * %o3: pagesize + * %o4: virt + * %o5: &iotsb_num/&iotsb_handle + * + * returns %o0: status + * %o1: iotsb_num/iotsb_handle + */ +ENTRY(pci_sun4v_iotsb_conf) + mov %o5, %g1 + mov HV_FAST_PCI_IOTSB_CONF, %o5 + ta HV_FAST_TRAP + retl + stx %o1, [%g1] +ENDPROC(pci_sun4v_iotsb_conf) + + /* + * %o0: devhandle + * %o1: iotsb_num/iotsb_handle + * %o2: pci_device + * + * returns %o0: status + */ +ENTRY(pci_sun4v_iotsb_bind) + mov HV_FAST_PCI_IOTSB_BIND, %o5 + ta HV_FAST_TRAP + retl + nop +ENDPROC(pci_sun4v_iotsb_bind) + + /* + * %o0: devhandle + * %o1: iotsb_num/iotsb_handle + * %o2: index_count + * %o3: iotte_attributes + * %o4: io_page_list_p + * %o5: &mapped + * + * returns %o0: status + * %o1: #mapped + */ +ENTRY(pci_sun4v_iotsb_map) + mov %o5, %g1 + mov HV_FAST_PCI_IOTSB_MAP, %o5 + ta HV_FAST_TRAP + retl + stx %o1, [%g1] +ENDPROC(pci_sun4v_iotsb_map) + + /* + * %o0: devhandle + * %o1: iotsb_num/iotsb_handle + * %o2: iotsb_index + * %o3: #iottes + * %o4: &demapped + * + * returns %o0: status + * %o1: #demapped + */ +ENTRY(pci_sun4v_iotsb_demap) + mov HV_FAST_PCI_IOTSB_DEMAP, %o5 + ta HV_FAST_TRAP + retl + stx %o1, [%o4] +ENDPROC(pci_sun4v_iotsb_demap) diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c index c3c12efe0bc0..9c0c8fd0b292 100644 --- a/arch/sparc/kernel/signal_32.c +++ b/arch/sparc/kernel/signal_32.c @@ -89,7 +89,7 @@ asmlinkage void do_sigreturn(struct pt_regs *regs) sf = (struct signal_frame __user *) regs->u_regs[UREG_FP]; /* 1. Make sure we are not getting garbage from the user */ - if (!invalid_frame_pointer(sf, sizeof(*sf))) + if (invalid_frame_pointer(sf, sizeof(*sf))) goto segv_and_exit; if (get_user(ufp, &sf->info.si_regs.u_regs[UREG_FP])) @@ -150,7 +150,7 @@ asmlinkage void do_rt_sigreturn(struct pt_regs *regs) synchronize_user_stack(); sf = (struct rt_signal_frame __user *) regs->u_regs[UREG_FP]; - if (!invalid_frame_pointer(sf, sizeof(*sf))) + if (invalid_frame_pointer(sf, sizeof(*sf))) goto segv; if (get_user(ufp, &sf->regs.u_regs[UREG_FP])) diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 439784b7b7ac..37aa537b3ad8 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -802,8 +802,10 @@ struct mdesc_mblock { }; static struct mdesc_mblock *mblocks; static int num_mblocks; +static int find_numa_node_for_addr(unsigned long pa, + struct node_mem_mask *pnode_mask); -static unsigned long ra_to_pa(unsigned long addr) +static unsigned long __init ra_to_pa(unsigned long addr) { int i; @@ -819,8 +821,11 @@ static unsigned long ra_to_pa(unsigned long addr) return addr; } -static int find_node(unsigned long addr) +static int __init find_node(unsigned long addr) { + static bool search_mdesc = true; + static struct node_mem_mask last_mem_mask = { ~0UL, ~0UL }; + static int last_index; int i; addr = ra_to_pa(addr); @@ -830,13 +835,30 @@ static int find_node(unsigned long addr) if ((addr & p->mask) == p->val) return i; } - /* The following condition has been observed on LDOM guests.*/ - WARN_ONCE(1, "find_node: A physical address doesn't match a NUMA node" - " rule. Some physical memory will be owned by node 0."); - return 0; + /* The following condition has been observed on LDOM guests because + * node_masks only contains the best latency mask and value. + * LDOM guest's mdesc can contain a single latency group to + * cover multiple address range. Print warning message only if the + * address cannot be found in node_masks nor mdesc. + */ + if ((search_mdesc) && + ((addr & last_mem_mask.mask) != last_mem_mask.val)) { + /* find the available node in the mdesc */ + last_index = find_numa_node_for_addr(addr, &last_mem_mask); + numadbg("find_node: latency group for address 0x%lx is %d\n", + addr, last_index); + if ((last_index < 0) || (last_index >= num_node_masks)) { + /* WARN_ONCE() and use default group 0 */ + WARN_ONCE(1, "find_node: A physical address doesn't match a NUMA node rule. Some physical memory will be owned by node 0."); + search_mdesc = false; + last_index = 0; + } + } + + return last_index; } -static u64 memblock_nid_range(u64 start, u64 end, int *nid) +static u64 __init memblock_nid_range(u64 start, u64 end, int *nid) { *nid = find_node(start); start += PAGE_SIZE; @@ -1160,6 +1182,41 @@ int __node_distance(int from, int to) return numa_latency[from][to]; } +static int find_numa_node_for_addr(unsigned long pa, + struct node_mem_mask *pnode_mask) +{ + struct mdesc_handle *md = mdesc_grab(); + u64 node, arc; + int i = 0; + + node = mdesc_node_by_name(md, MDESC_NODE_NULL, "latency-groups"); + if (node == MDESC_NODE_NULL) + goto out; + + mdesc_for_each_node_by_name(md, node, "group") { + mdesc_for_each_arc(arc, md, node, MDESC_ARC_TYPE_FWD) { + u64 target = mdesc_arc_target(md, arc); + struct mdesc_mlgroup *m = find_mlgroup(target); + + if (!m) + continue; + if ((pa & m->mask) == m->match) { + if (pnode_mask) { + pnode_mask->mask = m->mask; + pnode_mask->val = m->match; + } + mdesc_release(md); + return i; + } + } + i++; + } + +out: + mdesc_release(md); + return -1; +} + static int __init find_best_numa_node_for_mlgroup(struct mdesc_mlgroup *grp) { int i; diff --git a/arch/tile/kernel/time.c b/arch/tile/kernel/time.c index 178989e6d3e3..ea960d660917 100644 --- a/arch/tile/kernel/time.c +++ b/arch/tile/kernel/time.c @@ -218,8 +218,8 @@ void do_timer_interrupt(struct pt_regs *regs, int fault_num) */ unsigned long long sched_clock(void) { - return clocksource_cyc2ns(get_cycles(), - sched_clock_mult, SCHED_CLOCK_SHIFT); + return mult_frac(get_cycles(), + sched_clock_mult, 1ULL << SCHED_CLOCK_SHIFT); } int setup_profiling_timer(unsigned int multiplier) diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 536ccfcc01c6..34d9e15857c3 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -40,8 +40,8 @@ GCOV_PROFILE := n UBSAN_SANITIZE :=n LDFLAGS := -m elf_$(UTS_MACHINE) -ifeq ($(CONFIG_RELOCATABLE),y) -# If kernel is relocatable, build compressed kernel as PIE. +# Compressed kernel should be built as PIE since it may be loaded at any +# address by the bootloader. ifeq ($(CONFIG_X86_32),y) LDFLAGS += $(call ld-option, -pie) $(call ld-option, --no-dynamic-linker) else @@ -51,7 +51,6 @@ else LDFLAGS += $(shell $(LD) --help 2>&1 | grep -q "\-z noreloc-overflow" \ && echo "-z noreloc-overflow -pie --no-dynamic-linker") endif -endif LDFLAGS_vmlinux := -T hostprogs-y := mkpiggy diff --git a/arch/x86/boot/cpu.c b/arch/x86/boot/cpu.c index 26240dde081e..4224ede43b4e 100644 --- a/arch/x86/boot/cpu.c +++ b/arch/x86/boot/cpu.c @@ -87,6 +87,12 @@ int validate_cpu(void) return -1; } + if (CONFIG_X86_MINIMUM_CPU_FAMILY <= 4 && !IS_ENABLED(CONFIG_M486) && + !has_eflag(X86_EFLAGS_ID)) { + printf("This kernel requires a CPU with the CPUID instruction. Build with CONFIG_M486=y to run on this CPU.\n"); + return -1; + } + if (err_flags) { puts("This kernel requires the following features " "not present on the CPU:\n"); diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index f5f4b3fbbbc2..afb222b63cae 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -662,7 +662,13 @@ static int __init amd_core_pmu_init(void) pr_cont("Fam15h "); x86_pmu.get_event_constraints = amd_get_event_constraints_f15h; break; - + case 0x17: + pr_cont("Fam17h "); + /* + * In family 17h, there are no event constraints in the PMC hardware. + * We fallback to using default amd_get_event_constraints. + */ + break; default: pr_err("core perfctr but no constraints; unknown hardware!\n"); return -ENODEV; diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index d31735f37ed7..6e395c996900 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -69,7 +69,7 @@ u64 x86_perf_event_update(struct perf_event *event) int shift = 64 - x86_pmu.cntval_bits; u64 prev_raw_count, new_raw_count; int idx = hwc->idx; - s64 delta; + u64 delta; if (idx == INTEL_PMC_IDX_FIXED_BTS) return 0; @@ -2352,7 +2352,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent frame.next_frame = 0; frame.return_address = 0; - if (!access_ok(VERIFY_READ, fp, 8)) + if (!valid_user_frame(fp, sizeof(frame))) break; bytes = __copy_from_user_nmi(&frame.next_frame, fp, 4); @@ -2362,9 +2362,6 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent if (bytes != 0) break; - if (!valid_user_frame(fp, sizeof(frame))) - break; - perf_callchain_store(entry, cs_base + frame.return_address); fp = compat_ptr(ss_base + frame.next_frame); } @@ -2413,7 +2410,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs frame.next_frame = NULL; frame.return_address = 0; - if (!access_ok(VERIFY_READ, fp, sizeof(*fp) * 2)) + if (!valid_user_frame(fp, sizeof(frame))) break; bytes = __copy_from_user_nmi(&frame.next_frame, fp, sizeof(*fp)); @@ -2423,9 +2420,6 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs if (bytes != 0) break; - if (!valid_user_frame(fp, sizeof(frame))) - break; - perf_callchain_store(entry, frame.return_address); fp = (void __user *)frame.next_frame; } diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index a74a2dbc0180..cb8522290e6a 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4034,7 +4034,7 @@ __init int intel_pmu_init(void) /* Support full width counters using alternative MSR range */ if (x86_pmu.intel_cap.full_width_write) { - x86_pmu.max_period = x86_pmu.cntval_mask; + x86_pmu.max_period = x86_pmu.cntval_mask >> 1; x86_pmu.perfctr = MSR_IA32_PMC0; pr_cont("full-width counters, "); } diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 4f5ac726335f..da51e5a3e2ff 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -540,6 +540,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates), X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNL, knl_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates), { }, }; MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match); diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 0319311dbdbb..be202390bbd3 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1108,20 +1108,20 @@ static void setup_pebs_sample_data(struct perf_event *event, } /* - * We use the interrupt regs as a base because the PEBS record - * does not contain a full regs set, specifically it seems to - * lack segment descriptors, which get used by things like - * user_mode(). + * We use the interrupt regs as a base because the PEBS record does not + * contain a full regs set, specifically it seems to lack segment + * descriptors, which get used by things like user_mode(). * - * In the simple case fix up only the IP and BP,SP regs, for - * PERF_SAMPLE_IP and PERF_SAMPLE_CALLCHAIN to function properly. - * A possible PERF_SAMPLE_REGS will have to transfer all regs. + * In the simple case fix up only the IP for PERF_SAMPLE_IP. + * + * We must however always use BP,SP from iregs for the unwinder to stay + * sane; the record BP,SP can point into thin air when the record is + * from a previous PMI context or an (I)RET happend between the record + * and PMI. */ *regs = *iregs; regs->flags = pebs->flags; set_linear_ip(regs, pebs->ip); - regs->bp = pebs->bp; - regs->sp = pebs->sp; if (sample_type & PERF_SAMPLE_REGS_INTR) { regs->ax = pebs->ax; @@ -1130,10 +1130,21 @@ static void setup_pebs_sample_data(struct perf_event *event, regs->dx = pebs->dx; regs->si = pebs->si; regs->di = pebs->di; - regs->bp = pebs->bp; - regs->sp = pebs->sp; - regs->flags = pebs->flags; + /* + * Per the above; only set BP,SP if we don't need callchains. + * + * XXX: does this make sense? + */ + if (!(sample_type & PERF_SAMPLE_CALLCHAIN)) { + regs->bp = pebs->bp; + regs->sp = pebs->sp; + } + + /* + * Preserve PERF_EFLAGS_VM from set_linear_ip(). + */ + regs->flags = pebs->flags | (regs->flags & PERF_EFLAGS_VM); #ifndef CONFIG_X86_32 regs->r8 = pebs->r8; regs->r9 = pebs->r9; diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index efca2685d876..dbaaf7dc8373 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -319,9 +319,9 @@ static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, */ static int uncore_pmu_event_init(struct perf_event *event); -static bool is_uncore_event(struct perf_event *event) +static bool is_box_event(struct intel_uncore_box *box, struct perf_event *event) { - return event->pmu->event_init == uncore_pmu_event_init; + return &box->pmu->pmu == event->pmu; } static int @@ -340,7 +340,7 @@ uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, n = box->n_events; - if (is_uncore_event(leader)) { + if (is_box_event(box, leader)) { box->event_list[n] = leader; n++; } @@ -349,7 +349,7 @@ uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, return n; list_for_each_entry(event, &leader->sibling_list, group_entry) { - if (!is_uncore_event(event) || + if (!is_box_event(box, event) || event->state <= PERF_EVENT_STATE_OFF) continue; diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index 81195cca7eae..a3dcc12bef4a 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -490,24 +490,12 @@ static int snb_uncore_imc_event_add(struct perf_event *event, int flags) snb_uncore_imc_event_start(event, 0); - box->n_events++; - return 0; } static void snb_uncore_imc_event_del(struct perf_event *event, int flags) { - struct intel_uncore_box *box = uncore_event_to_box(event); - int i; - snb_uncore_imc_event_stop(event, PERF_EF_UPDATE); - - for (i = 0; i < box->n_events; i++) { - if (event == box->event_list[i]) { - --box->n_events; - break; - } - } } int snb_pci2phy_map_init(int devid) diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 5874d8de1f8d..a77ee026643d 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -113,7 +113,7 @@ struct debug_store { * Per register state. */ struct er_account { - raw_spinlock_t lock; /* per-core: protect structure */ + raw_spinlock_t lock; /* per-core: protect structure */ u64 config; /* extra MSR config */ u64 reg; /* extra MSR number */ atomic_t ref; /* reference count */ diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index 03d269bed941..24118c0b4640 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -272,7 +272,6 @@ struct compat_shmid64_ds { /* * The type of struct elf_prstatus.pr_reg in compatible core dumps. */ -#ifdef CONFIG_X86_X32_ABI typedef struct user_regs_struct compat_elf_gregset_t; /* Full regset -- prstatus on x32, otherwise on ia32 */ @@ -281,10 +280,9 @@ typedef struct user_regs_struct compat_elf_gregset_t; do { *(int *) (((void *) &((S)->pr_reg)) + R) = (V); } \ while (0) +#ifdef CONFIG_X86_X32_ABI #define COMPAT_USE_64BIT_TIME \ (!!(task_pt_regs(current)->orig_ax & __X32_SYSCALL_BIT)) -#else -typedef struct user_regs_struct32 compat_elf_gregset_t; #endif /* diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S index 169963f471bb..50b8ed0317a3 100644 --- a/arch/x86/kernel/acpi/wakeup_64.S +++ b/arch/x86/kernel/acpi/wakeup_64.S @@ -109,6 +109,15 @@ ENTRY(do_suspend_lowlevel) movq pt_regs_r14(%rax), %r14 movq pt_regs_r15(%rax), %r15 +#ifdef CONFIG_KASAN + /* + * The suspend path may have poisoned some areas deeper in the stack, + * which we now need to unpoison. + */ + movq %rsp, %rdi + call kasan_unpoison_task_stack_below +#endif + xorl %eax, %eax addq $8, %rsp FRAME_END diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index aeef53ce93e1..35690a168cf7 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -815,9 +815,9 @@ static __init void map_mmioh_high_uv3(int index, int min_pnode, int max_pnode) l = li; } addr1 = (base << shift) + - f * (unsigned long)(1 << m_io); + f * (1ULL << m_io); addr2 = (base << shift) + - (l + 1) * (unsigned long)(1 << m_io); + (l + 1) * (1ULL << m_io); pr_info("UV: %s[%03d..%03d] NASID 0x%04x ADDR 0x%016lx - 0x%016lx\n", id, fi, li, lnasid, addr1, addr2); if (max_io < l) diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 9b7cf5c28f5f..85f854b98a9d 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -112,7 +112,7 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, for (; stack < stack_info.end; stack++) { unsigned long real_addr; int reliable = 0; - unsigned long addr = *stack; + unsigned long addr = READ_ONCE_NOCHECK(*stack); unsigned long *ret_addr_p = unwind_get_return_address_ptr(&state); diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 47004010ad5d..ebb4e95fbd74 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -521,14 +521,14 @@ void fpu__clear(struct fpu *fpu) { WARN_ON_FPU(fpu != ¤t->thread.fpu); /* Almost certainly an anomaly */ - if (!use_eager_fpu() || !static_cpu_has(X86_FEATURE_FPU)) { - /* FPU state will be reallocated lazily at the first use. */ - fpu__drop(fpu); - } else { - if (!fpu->fpstate_active) { - fpu__activate_curr(fpu); - user_fpu_begin(); - } + fpu__drop(fpu); + + /* + * Make sure fpstate is cleared and initialized. + */ + if (static_cpu_has(X86_FEATURE_FPU)) { + fpu__activate_curr(fpu); + user_fpu_begin(); copy_init_fpstate_to_fpregs(); } } diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index b6b2f0264af3..2dabea46f039 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -665,14 +665,17 @@ __PAGE_ALIGNED_BSS initial_pg_pmd: .fill 1024*KPMDS,4,0 #else -ENTRY(initial_page_table) +.globl initial_page_table +initial_page_table: .fill 1024,4,0 #endif initial_pg_fixmap: .fill 1024,4,0 -ENTRY(empty_zero_page) +.globl empty_zero_page +empty_zero_page: .fill 4096,1,0 -ENTRY(swapper_pg_dir) +.globl swapper_pg_dir +swapper_pg_dir: .fill 1024,4,0 EXPORT_SYMBOL(empty_zero_page) diff --git a/arch/x86/kernel/sysfb_simplefb.c b/arch/x86/kernel/sysfb_simplefb.c index 764a29f84de7..85195d447a92 100644 --- a/arch/x86/kernel/sysfb_simplefb.c +++ b/arch/x86/kernel/sysfb_simplefb.c @@ -66,13 +66,36 @@ __init int create_simplefb(const struct screen_info *si, { struct platform_device *pd; struct resource res; - unsigned long len; + u64 base, size; + u32 length; - /* don't use lfb_size as it may contain the whole VMEM instead of only - * the part that is occupied by the framebuffer */ - len = mode->height * mode->stride; - len = PAGE_ALIGN(len); - if (len > (u64)si->lfb_size << 16) { + /* + * If the 64BIT_BASE capability is set, ext_lfb_base will contain the + * upper half of the base address. Assemble the address, then make sure + * it is valid and we can actually access it. + */ + base = si->lfb_base; + if (si->capabilities & VIDEO_CAPABILITY_64BIT_BASE) + base |= (u64)si->ext_lfb_base << 32; + if (!base || (u64)(resource_size_t)base != base) { + printk(KERN_DEBUG "sysfb: inaccessible VRAM base\n"); + return -EINVAL; + } + + /* + * Don't use lfb_size as IORESOURCE size, since it may contain the + * entire VMEM, and thus require huge mappings. Use just the part we + * need, that is, the part where the framebuffer is located. But verify + * that it does not exceed the advertised VMEM. + * Note that in case of VBE, the lfb_size is shifted by 16 bits for + * historical reasons. + */ + size = si->lfb_size; + if (si->orig_video_isVGA == VIDEO_TYPE_VLFB) + size <<= 16; + length = mode->height * mode->stride; + length = PAGE_ALIGN(length); + if (length > size) { printk(KERN_WARNING "sysfb: VRAM smaller than advertised\n"); return -EINVAL; } @@ -81,8 +104,8 @@ __init int create_simplefb(const struct screen_info *si, memset(&res, 0, sizeof(res)); res.flags = IORESOURCE_MEM | IORESOURCE_BUSY; res.name = simplefb_resname; - res.start = si->lfb_base; - res.end = si->lfb_base + len - 1; + res.start = base; + res.end = res.start + length - 1; if (res.end <= res.start) return -EINVAL; diff --git a/arch/x86/kernel/unwind_guess.c b/arch/x86/kernel/unwind_guess.c index 2d721e533cf4..22881ddcbb9f 100644 --- a/arch/x86/kernel/unwind_guess.c +++ b/arch/x86/kernel/unwind_guess.c @@ -7,11 +7,15 @@ unsigned long unwind_get_return_address(struct unwind_state *state) { + unsigned long addr; + if (unwind_done(state)) return 0; + addr = READ_ONCE_NOCHECK(*state->sp); + return ftrace_graph_ret_addr(state->task, &state->graph_idx, - *state->sp, state->sp); + addr, state->sp); } EXPORT_SYMBOL_GPL(unwind_get_return_address); @@ -23,9 +27,12 @@ bool unwind_next_frame(struct unwind_state *state) return false; do { - for (state->sp++; state->sp < info->end; state->sp++) - if (__kernel_text_address(*state->sp)) + for (state->sp++; state->sp < info->end; state->sp++) { + unsigned long addr = READ_ONCE_NOCHECK(*state->sp); + + if (__kernel_text_address(addr)) return true; + } state->sp = info->next_sp; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index cbd7b92585bb..a3ce9d260d68 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -2105,16 +2105,10 @@ static int em_iret(struct x86_emulate_ctxt *ctxt) static int em_jmp_far(struct x86_emulate_ctxt *ctxt) { int rc; - unsigned short sel, old_sel; - struct desc_struct old_desc, new_desc; - const struct x86_emulate_ops *ops = ctxt->ops; + unsigned short sel; + struct desc_struct new_desc; u8 cpl = ctxt->ops->cpl(ctxt); - /* Assignment of RIP may only fail in 64-bit mode */ - if (ctxt->mode == X86EMUL_MODE_PROT64) - ops->get_segment(ctxt, &old_sel, &old_desc, NULL, - VCPU_SREG_CS); - memcpy(&sel, ctxt->src.valptr + ctxt->op_bytes, 2); rc = __load_segment_descriptor(ctxt, sel, VCPU_SREG_CS, cpl, @@ -2124,12 +2118,10 @@ static int em_jmp_far(struct x86_emulate_ctxt *ctxt) return rc; rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc); - if (rc != X86EMUL_CONTINUE) { - WARN_ON(ctxt->mode != X86EMUL_MODE_PROT64); - /* assigning eip failed; restore the old cs */ - ops->set_segment(ctxt, old_sel, &old_desc, 0, VCPU_SREG_CS); - return rc; - } + /* Error handling is not implemented. */ + if (rc != X86EMUL_CONTINUE) + return X86EMUL_UNHANDLEABLE; + return rc; } @@ -2189,14 +2181,8 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt) { int rc; unsigned long eip, cs; - u16 old_cs; int cpl = ctxt->ops->cpl(ctxt); - struct desc_struct old_desc, new_desc; - const struct x86_emulate_ops *ops = ctxt->ops; - - if (ctxt->mode == X86EMUL_MODE_PROT64) - ops->get_segment(ctxt, &old_cs, &old_desc, NULL, - VCPU_SREG_CS); + struct desc_struct new_desc; rc = emulate_pop(ctxt, &eip, ctxt->op_bytes); if (rc != X86EMUL_CONTINUE) @@ -2213,10 +2199,10 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; rc = assign_eip_far(ctxt, eip, &new_desc); - if (rc != X86EMUL_CONTINUE) { - WARN_ON(ctxt->mode != X86EMUL_MODE_PROT64); - ops->set_segment(ctxt, old_cs, &old_desc, 0, VCPU_SREG_CS); - } + /* Error handling is not implemented. */ + if (rc != X86EMUL_CONTINUE) + return X86EMUL_UNHANDLEABLE; + return rc; } diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 1a22de70f7f7..6e219e5c07d2 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -94,7 +94,7 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic, static void rtc_irq_eoi_tracking_reset(struct kvm_ioapic *ioapic) { ioapic->rtc_status.pending_eoi = 0; - bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPUS); + bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_ID); } static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic); diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h index 7d2692a49657..1cc6e54436db 100644 --- a/arch/x86/kvm/ioapic.h +++ b/arch/x86/kvm/ioapic.h @@ -42,13 +42,13 @@ struct kvm_vcpu; struct dest_map { /* vcpu bitmap where IRQ has been sent */ - DECLARE_BITMAP(map, KVM_MAX_VCPUS); + DECLARE_BITMAP(map, KVM_MAX_VCPU_ID); /* * Vector sent to a given vcpu, only valid when * the vcpu's bit in map is set */ - u8 vectors[KVM_MAX_VCPUS]; + u8 vectors[KVM_MAX_VCPU_ID]; }; diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 4da03030d5a7..6c0191615f23 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -41,6 +41,15 @@ static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e, bool line_status) { struct kvm_pic *pic = pic_irqchip(kvm); + + /* + * XXX: rejecting pic routes when pic isn't in use would be better, + * but the default routing table is installed while kvm->arch.vpic is + * NULL and KVM_CREATE_IRQCHIP can race with KVM_IRQ_LINE. + */ + if (!pic) + return -1; + return kvm_pic_set_irq(pic, e->irqchip.pin, irq_source_id, level); } @@ -49,6 +58,10 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e, bool line_status) { struct kvm_ioapic *ioapic = kvm->arch.vioapic; + + if (!ioapic) + return -1; + return kvm_ioapic_set_irq(ioapic, e->irqchip.pin, irq_source_id, level, line_status); } diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 23b99f305382..6f69340f9fa3 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -138,7 +138,7 @@ static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map, *mask = dest_id & 0xff; return true; case KVM_APIC_MODE_XAPIC_CLUSTER: - *cluster = map->xapic_cluster_map[dest_id >> 4]; + *cluster = map->xapic_cluster_map[(dest_id >> 4) & 0xf]; *mask = dest_id & 0xf; return true; default: diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index 79ae939970d3..fcd06f7526de 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -135,7 +135,12 @@ void __init early_fixup_exception(struct pt_regs *regs, int trapnr) if (early_recursion_flag > 2) goto halt_loop; - if (regs->cs != __KERNEL_CS) + /* + * Old CPUs leave the high bits of CS on the stack + * undefined. I'm not sure which CPUs do this, but at least + * the 486 DX works this way. + */ + if ((regs->cs & 0xFFFF) != __KERNEL_CS) goto fail; /* diff --git a/arch/x86/platform/intel-mid/device_libs/Makefile b/arch/x86/platform/intel-mid/device_libs/Makefile index 429d08be7848..dd6cfa4ad3ac 100644 --- a/arch/x86/platform/intel-mid/device_libs/Makefile +++ b/arch/x86/platform/intel-mid/device_libs/Makefile @@ -28,4 +28,4 @@ obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_pcal9555a.o obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_tca6416.o # MISC Devices obj-$(subst m,y,$(CONFIG_KEYBOARD_GPIO)) += platform_gpio_keys.o -obj-$(subst m,y,$(CONFIG_INTEL_MID_WATCHDOG)) += platform_wdt.o +obj-$(subst m,y,$(CONFIG_INTEL_MID_WATCHDOG)) += platform_mrfld_wdt.o diff --git a/arch/x86/platform/intel-mid/device_libs/platform_wdt.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c index de734134bc8d..3f1f1c77d090 100644 --- a/arch/x86/platform/intel-mid/device_libs/platform_wdt.c +++ b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c @@ -1,5 +1,5 @@ /* - * platform_wdt.c: Watchdog platform library file + * Intel Merrifield watchdog platform device library file * * (C) Copyright 2014 Intel Corporation * Author: David Cohen <david.a.cohen@linux.intel.com> @@ -14,7 +14,9 @@ #include <linux/interrupt.h> #include <linux/platform_device.h> #include <linux/platform_data/intel-mid_wdt.h> + #include <asm/intel-mid.h> +#include <asm/intel_scu_ipc.h> #include <asm/io_apic.h> #define TANGIER_EXT_TIMER0_MSI 15 @@ -50,14 +52,34 @@ static struct intel_mid_wdt_pdata tangier_pdata = { .probe = tangier_probe, }; -static int __init register_mid_wdt(void) +static int wdt_scu_status_change(struct notifier_block *nb, + unsigned long code, void *data) { - if (intel_mid_identify_cpu() == INTEL_MID_CPU_CHIP_TANGIER) { - wdt_dev.dev.platform_data = &tangier_pdata; - return platform_device_register(&wdt_dev); + if (code == SCU_DOWN) { + platform_device_unregister(&wdt_dev); + return 0; } - return -ENODEV; + return platform_device_register(&wdt_dev); } +static struct notifier_block wdt_scu_notifier = { + .notifier_call = wdt_scu_status_change, +}; + +static int __init register_mid_wdt(void) +{ + if (intel_mid_identify_cpu() != INTEL_MID_CPU_CHIP_TANGIER) + return -ENODEV; + + wdt_dev.dev.platform_data = &tangier_pdata; + + /* + * We need to be sure that the SCU IPC is ready before watchdog device + * can be registered: + */ + intel_scu_notifier_add(&wdt_scu_notifier); + + return 0; +} rootfs_initcall(register_mid_wdt); diff --git a/arch/x86/platform/olpc/olpc-xo15-sci.c b/arch/x86/platform/olpc/olpc-xo15-sci.c index 55130846ac87..c0533fbc39e3 100644 --- a/arch/x86/platform/olpc/olpc-xo15-sci.c +++ b/arch/x86/platform/olpc/olpc-xo15-sci.c @@ -196,6 +196,7 @@ static int xo15_sci_remove(struct acpi_device *device) return 0; } +#ifdef CONFIG_PM_SLEEP static int xo15_sci_resume(struct device *dev) { /* Enable all EC events */ @@ -207,6 +208,7 @@ static int xo15_sci_resume(struct device *dev) return 0; } +#endif static SIMPLE_DEV_PM_OPS(xo15_sci_pm, NULL, xo15_sci_resume); diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index 9634557a5444..ded2e8272382 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -11,6 +11,10 @@ #include <linux/gfp.h> #include <linux/smp.h> #include <linux/suspend.h> +#include <linux/scatterlist.h> +#include <linux/kdebug.h> + +#include <crypto/hash.h> #include <asm/init.h> #include <asm/proto.h> @@ -177,14 +181,86 @@ int pfn_is_nosave(unsigned long pfn) return (pfn >= nosave_begin_pfn) && (pfn < nosave_end_pfn); } +#define MD5_DIGEST_SIZE 16 + struct restore_data_record { unsigned long jump_address; unsigned long jump_address_phys; unsigned long cr3; unsigned long magic; + u8 e820_digest[MD5_DIGEST_SIZE]; }; -#define RESTORE_MAGIC 0x123456789ABCDEF0UL +#define RESTORE_MAGIC 0x23456789ABCDEF01UL + +#if IS_BUILTIN(CONFIG_CRYPTO_MD5) +/** + * get_e820_md5 - calculate md5 according to given e820 map + * + * @map: the e820 map to be calculated + * @buf: the md5 result to be stored to + */ +static int get_e820_md5(struct e820map *map, void *buf) +{ + struct scatterlist sg; + struct crypto_ahash *tfm; + int size; + int ret = 0; + + tfm = crypto_alloc_ahash("md5", 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(tfm)) + return -ENOMEM; + + { + AHASH_REQUEST_ON_STACK(req, tfm); + size = offsetof(struct e820map, map) + + sizeof(struct e820entry) * map->nr_map; + ahash_request_set_tfm(req, tfm); + sg_init_one(&sg, (u8 *)map, size); + ahash_request_set_callback(req, 0, NULL, NULL); + ahash_request_set_crypt(req, &sg, buf, size); + + if (crypto_ahash_digest(req)) + ret = -EINVAL; + ahash_request_zero(req); + } + crypto_free_ahash(tfm); + + return ret; +} + +static void hibernation_e820_save(void *buf) +{ + get_e820_md5(e820_saved, buf); +} + +static bool hibernation_e820_mismatch(void *buf) +{ + int ret; + u8 result[MD5_DIGEST_SIZE]; + + memset(result, 0, MD5_DIGEST_SIZE); + /* If there is no digest in suspend kernel, let it go. */ + if (!memcmp(result, buf, MD5_DIGEST_SIZE)) + return false; + + ret = get_e820_md5(e820_saved, result); + if (ret) + return true; + + return memcmp(result, buf, MD5_DIGEST_SIZE) ? true : false; +} +#else +static void hibernation_e820_save(void *buf) +{ +} + +static bool hibernation_e820_mismatch(void *buf) +{ + /* If md5 is not builtin for restore kernel, let it go. */ + return false; +} +#endif /** * arch_hibernation_header_save - populate the architecture specific part @@ -201,6 +277,9 @@ int arch_hibernation_header_save(void *addr, unsigned int max_size) rdr->jump_address_phys = __pa_symbol(&restore_registers); rdr->cr3 = restore_cr3; rdr->magic = RESTORE_MAGIC; + + hibernation_e820_save(rdr->e820_digest); + return 0; } @@ -216,5 +295,16 @@ int arch_hibernation_header_restore(void *addr) restore_jump_address = rdr->jump_address; jump_address_phys = rdr->jump_address_phys; restore_cr3 = rdr->cr3; - return (rdr->magic == RESTORE_MAGIC) ? 0 : -EINVAL; + + if (rdr->magic != RESTORE_MAGIC) { + pr_crit("Unrecognized hibernate image header format!\n"); + return -EINVAL; + } + + if (hibernation_e820_mismatch(rdr->e820_digest)) { + pr_crit("Hibernate inconsistent memory map detected!\n"); + return -ENODEV; + } + + return 0; } diff --git a/arch/x86/tools/relocs.h b/arch/x86/tools/relocs.h index f59590645b68..1d23bf953a4a 100644 --- a/arch/x86/tools/relocs.h +++ b/arch/x86/tools/relocs.h @@ -16,7 +16,7 @@ #include <regex.h> #include <tools/le_byteshift.h> -void die(char *fmt, ...); +void die(char *fmt, ...) __attribute__((noreturn)); #define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) diff --git a/block/blk-map.c b/block/blk-map.c index b8657fa8dc9a..27fd8d92892d 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -118,6 +118,9 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq, struct iov_iter i; int ret; + if (!iter_is_iovec(iter)) + goto fail; + if (map_data) copy = true; else if (iov_iter_alignment(iter) & align) @@ -140,6 +143,7 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq, unmap_rq: __blk_rq_unmap_user(bio); +fail: rq->bio = NULL; return -EINVAL; } diff --git a/crypto/Makefile b/crypto/Makefile index 99cc64ac70ef..bd6a029094e6 100644 --- a/crypto/Makefile +++ b/crypto/Makefile @@ -40,6 +40,7 @@ obj-$(CONFIG_CRYPTO_ECDH) += ecdh_generic.o $(obj)/rsapubkey-asn1.o: $(obj)/rsapubkey-asn1.c $(obj)/rsapubkey-asn1.h $(obj)/rsaprivkey-asn1.o: $(obj)/rsaprivkey-asn1.c $(obj)/rsaprivkey-asn1.h +$(obj)/rsa_helper.o: $(obj)/rsapubkey-asn1.h $(obj)/rsaprivkey-asn1.h clean-files += rsapubkey-asn1.c rsapubkey-asn1.h clean-files += rsaprivkey-asn1.c rsaprivkey-asn1.h diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c index 80a0f1a78551..e9c0993b131d 100644 --- a/crypto/algif_aead.c +++ b/crypto/algif_aead.c @@ -81,7 +81,11 @@ static inline bool aead_sufficient_data(struct aead_ctx *ctx) { unsigned as = crypto_aead_authsize(crypto_aead_reqtfm(&ctx->aead_req)); - return ctx->used >= ctx->aead_assoclen + as; + /* + * The minimum amount of memory needed for an AEAD cipher is + * the AAD and in case of decryption the tag. + */ + return ctx->used >= ctx->aead_assoclen + (ctx->enc ? 0 : as); } static void aead_reset_ctx(struct aead_ctx *ctx) @@ -416,7 +420,7 @@ static int aead_recvmsg_async(struct socket *sock, struct msghdr *msg, unsigned int i, reqlen = GET_REQ_SIZE(tfm); int err = -ENOMEM; unsigned long used; - size_t outlen; + size_t outlen = 0; size_t usedpages = 0; lock_sock(sk); @@ -426,12 +430,15 @@ static int aead_recvmsg_async(struct socket *sock, struct msghdr *msg, goto unlock; } - used = ctx->used; - outlen = used; - if (!aead_sufficient_data(ctx)) goto unlock; + used = ctx->used; + if (ctx->enc) + outlen = used + as; + else + outlen = used - as; + req = sock_kmalloc(sk, reqlen, GFP_KERNEL); if (unlikely(!req)) goto unlock; @@ -445,7 +452,7 @@ static int aead_recvmsg_async(struct socket *sock, struct msghdr *msg, aead_request_set_ad(req, ctx->aead_assoclen); aead_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, aead_async_cb, sk); - used -= ctx->aead_assoclen + (ctx->enc ? as : 0); + used -= ctx->aead_assoclen; /* take over all tx sgls from ctx */ areq->tsgl = sock_kmalloc(sk, sizeof(*areq->tsgl) * sgl->cur, @@ -461,7 +468,7 @@ static int aead_recvmsg_async(struct socket *sock, struct msghdr *msg, areq->tsgls = sgl->cur; /* create rx sgls */ - while (iov_iter_count(&msg->msg_iter)) { + while (outlen > usedpages && iov_iter_count(&msg->msg_iter)) { size_t seglen = min_t(size_t, iov_iter_count(&msg->msg_iter), (outlen - usedpages)); @@ -491,16 +498,14 @@ static int aead_recvmsg_async(struct socket *sock, struct msghdr *msg, last_rsgl = rsgl; - /* we do not need more iovecs as we have sufficient memory */ - if (outlen <= usedpages) - break; - iov_iter_advance(&msg->msg_iter, err); } - err = -EINVAL; + /* ensure output buffer is sufficiently large */ - if (usedpages < outlen) - goto free; + if (usedpages < outlen) { + err = -EINVAL; + goto unlock; + } aead_request_set_crypt(req, areq->tsgl, areq->first_rsgl.sgl.sg, used, areq->iv); @@ -571,6 +576,7 @@ static int aead_recvmsg_sync(struct socket *sock, struct msghdr *msg, int flags) goto unlock; } + /* data length provided by caller via sendmsg/sendpage */ used = ctx->used; /* @@ -585,16 +591,27 @@ static int aead_recvmsg_sync(struct socket *sock, struct msghdr *msg, int flags) if (!aead_sufficient_data(ctx)) goto unlock; - outlen = used; + /* + * Calculate the minimum output buffer size holding the result of the + * cipher operation. When encrypting data, the receiving buffer is + * larger by the tag length compared to the input buffer as the + * encryption operation generates the tag. For decryption, the input + * buffer provides the tag which is consumed resulting in only the + * plaintext without a buffer for the tag returned to the caller. + */ + if (ctx->enc) + outlen = used + as; + else + outlen = used - as; /* * The cipher operation input data is reduced by the associated data * length as this data is processed separately later on. */ - used -= ctx->aead_assoclen + (ctx->enc ? as : 0); + used -= ctx->aead_assoclen; /* convert iovecs of output buffers into scatterlists */ - while (iov_iter_count(&msg->msg_iter)) { + while (outlen > usedpages && iov_iter_count(&msg->msg_iter)) { size_t seglen = min_t(size_t, iov_iter_count(&msg->msg_iter), (outlen - usedpages)); @@ -621,16 +638,14 @@ static int aead_recvmsg_sync(struct socket *sock, struct msghdr *msg, int flags) last_rsgl = rsgl; - /* we do not need more iovecs as we have sufficient memory */ - if (outlen <= usedpages) - break; iov_iter_advance(&msg->msg_iter, err); } - err = -EINVAL; /* ensure output buffer is sufficiently large */ - if (usedpages < outlen) + if (usedpages < outlen) { + err = -EINVAL; goto unlock; + } sg_mark_end(sgl->sg + sgl->cur - 1); aead_request_set_crypt(&ctx->aead_req, sgl->sg, ctx->first_rsgl.sgl.sg, diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c index 05e21b464433..d19b09cdf284 100644 --- a/crypto/algif_hash.c +++ b/crypto/algif_hash.c @@ -214,7 +214,7 @@ static int hash_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, ahash_request_set_crypt(&ctx->req, NULL, ctx->result, 0); - if (!result) { + if (!result && !ctx->more) { err = af_alg_wait_for_completion( crypto_ahash_init(&ctx->req), &ctx->completion); diff --git a/crypto/asymmetric_keys/x509_cert_parser.c b/crypto/asymmetric_keys/x509_cert_parser.c index 865f46ea724f..c80765b211cf 100644 --- a/crypto/asymmetric_keys/x509_cert_parser.c +++ b/crypto/asymmetric_keys/x509_cert_parser.c @@ -133,7 +133,6 @@ struct x509_certificate *x509_cert_parse(const void *data, size_t datalen) return cert; error_decode: - kfree(cert->pub->key); kfree(ctx); error_no_ctx: x509_free_certificate(cert); diff --git a/crypto/drbg.c b/crypto/drbg.c index fb33f7d3b052..053035b5c8f8 100644 --- a/crypto/drbg.c +++ b/crypto/drbg.c @@ -262,6 +262,7 @@ static int drbg_kcapi_sym_ctr(struct drbg_state *drbg, u8 *inbuf, u32 inbuflen, u8 *outbuf, u32 outlen); #define DRBG_CTR_NULL_LEN 128 +#define DRBG_OUTSCRATCHLEN DRBG_CTR_NULL_LEN /* BCC function for CTR DRBG as defined in 10.4.3 */ static int drbg_ctr_bcc(struct drbg_state *drbg, @@ -1644,6 +1645,9 @@ static int drbg_fini_sym_kernel(struct drbg_state *drbg) kfree(drbg->ctr_null_value_buf); drbg->ctr_null_value = NULL; + kfree(drbg->outscratchpadbuf); + drbg->outscratchpadbuf = NULL; + return 0; } @@ -1708,6 +1712,15 @@ static int drbg_init_sym_kernel(struct drbg_state *drbg) drbg->ctr_null_value = (u8 *)PTR_ALIGN(drbg->ctr_null_value_buf, alignmask + 1); + drbg->outscratchpadbuf = kmalloc(DRBG_OUTSCRATCHLEN + alignmask, + GFP_KERNEL); + if (!drbg->outscratchpadbuf) { + drbg_fini_sym_kernel(drbg); + return -ENOMEM; + } + drbg->outscratchpad = (u8 *)PTR_ALIGN(drbg->outscratchpadbuf, + alignmask + 1); + return alignmask; } @@ -1737,15 +1750,16 @@ static int drbg_kcapi_sym_ctr(struct drbg_state *drbg, u8 *outbuf, u32 outlen) { struct scatterlist sg_in; + int ret; sg_init_one(&sg_in, inbuf, inlen); while (outlen) { - u32 cryptlen = min_t(u32, inlen, outlen); + u32 cryptlen = min3(inlen, outlen, (u32)DRBG_OUTSCRATCHLEN); struct scatterlist sg_out; - int ret; - sg_init_one(&sg_out, outbuf, cryptlen); + /* Output buffer may not be valid for SGL, use scratchpad */ + sg_init_one(&sg_out, drbg->outscratchpad, cryptlen); skcipher_request_set_crypt(drbg->ctr_req, &sg_in, &sg_out, cryptlen, drbg->V); ret = crypto_skcipher_encrypt(drbg->ctr_req); @@ -1761,14 +1775,19 @@ static int drbg_kcapi_sym_ctr(struct drbg_state *drbg, break; } default: - return ret; + goto out; } init_completion(&drbg->ctr_completion); + memcpy(outbuf, drbg->outscratchpad, cryptlen); + outlen -= cryptlen; } + ret = 0; - return 0; +out: + memzero_explicit(drbg->outscratchpad, DRBG_OUTSCRATCHLEN); + return ret; } #endif /* CONFIG_CRYPTO_DRBG_CTR */ diff --git a/crypto/mcryptd.c b/crypto/mcryptd.c index 94ee44acd465..c207458d6299 100644 --- a/crypto/mcryptd.c +++ b/crypto/mcryptd.c @@ -254,18 +254,22 @@ out_free_inst: goto out; } -static inline void mcryptd_check_internal(struct rtattr **tb, u32 *type, +static inline bool mcryptd_check_internal(struct rtattr **tb, u32 *type, u32 *mask) { struct crypto_attr_type *algt; algt = crypto_get_attr_type(tb); if (IS_ERR(algt)) - return; - if ((algt->type & CRYPTO_ALG_INTERNAL)) - *type |= CRYPTO_ALG_INTERNAL; - if ((algt->mask & CRYPTO_ALG_INTERNAL)) - *mask |= CRYPTO_ALG_INTERNAL; + return false; + + *type |= algt->type & CRYPTO_ALG_INTERNAL; + *mask |= algt->mask & CRYPTO_ALG_INTERNAL; + + if (*type & *mask & CRYPTO_ALG_INTERNAL) + return true; + else + return false; } static int mcryptd_hash_init_tfm(struct crypto_tfm *tfm) @@ -492,7 +496,8 @@ static int mcryptd_create_hash(struct crypto_template *tmpl, struct rtattr **tb, u32 mask = 0; int err; - mcryptd_check_internal(tb, &type, &mask); + if (!mcryptd_check_internal(tb, &type, &mask)) + return -EINVAL; halg = ahash_attr_alg(tb[1], type, mask); if (IS_ERR(halg)) diff --git a/crypto/scatterwalk.c b/crypto/scatterwalk.c index 52ce17a3dd63..c16c94f88733 100644 --- a/crypto/scatterwalk.c +++ b/crypto/scatterwalk.c @@ -68,10 +68,6 @@ void scatterwalk_map_and_copy(void *buf, struct scatterlist *sg, sg = scatterwalk_ffwd(tmp, sg, start); - if (sg_page(sg) == virt_to_page(buf) && - sg->offset == offset_in_page(buf)) - return; - scatterwalk_start(&walk, sg); scatterwalk_copychunks(buf, &walk, nbytes, out); scatterwalk_done(&walk, out, 0); diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 71a7d07c28c9..312c4b4dc363 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -94,7 +94,7 @@ static struct acpi_device *to_acpi_dev(struct acpi_nfit_desc *acpi_desc) return to_acpi_device(acpi_desc->dev); } -static int xlat_status(void *buf, unsigned int cmd, u32 status) +static int xlat_bus_status(void *buf, unsigned int cmd, u32 status) { struct nd_cmd_clear_error *clear_err; struct nd_cmd_ars_status *ars_status; @@ -113,7 +113,7 @@ static int xlat_status(void *buf, unsigned int cmd, u32 status) flags = ND_ARS_PERSISTENT | ND_ARS_VOLATILE; if ((status >> 16 & flags) == 0) return -ENOTTY; - break; + return 0; case ND_CMD_ARS_START: /* ARS is in progress */ if ((status & 0xffff) == NFIT_ARS_START_BUSY) @@ -122,7 +122,7 @@ static int xlat_status(void *buf, unsigned int cmd, u32 status) /* Command failed */ if (status & 0xffff) return -EIO; - break; + return 0; case ND_CMD_ARS_STATUS: ars_status = buf; /* Command failed */ @@ -146,7 +146,8 @@ static int xlat_status(void *buf, unsigned int cmd, u32 status) * then just continue with the returned results. */ if (status == NFIT_ARS_STATUS_INTR) { - if (ars_status->flags & NFIT_ARS_F_OVERFLOW) + if (ars_status->out_length >= 40 && (ars_status->flags + & NFIT_ARS_F_OVERFLOW)) return -ENOSPC; return 0; } @@ -154,7 +155,7 @@ static int xlat_status(void *buf, unsigned int cmd, u32 status) /* Unknown status */ if (status >> 16) return -EIO; - break; + return 0; case ND_CMD_CLEAR_ERROR: clear_err = buf; if (status & 0xffff) @@ -163,7 +164,7 @@ static int xlat_status(void *buf, unsigned int cmd, u32 status) return -EIO; if (clear_err->length > clear_err->cleared) return clear_err->cleared; - break; + return 0; default: break; } @@ -174,9 +175,18 @@ static int xlat_status(void *buf, unsigned int cmd, u32 status) return 0; } -static int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, - struct nvdimm *nvdimm, unsigned int cmd, void *buf, - unsigned int buf_len, int *cmd_rc) +static int xlat_status(struct nvdimm *nvdimm, void *buf, unsigned int cmd, + u32 status) +{ + if (!nvdimm) + return xlat_bus_status(buf, cmd, status); + if (status) + return -EIO; + return 0; +} + +int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, + unsigned int cmd, void *buf, unsigned int buf_len, int *cmd_rc) { struct acpi_nfit_desc *acpi_desc = to_acpi_nfit_desc(nd_desc); union acpi_object in_obj, in_buf, *out_obj; @@ -298,7 +308,8 @@ static int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, for (i = 0, offset = 0; i < desc->out_num; i++) { u32 out_size = nd_cmd_out_size(nvdimm, cmd, desc, i, buf, - (u32 *) out_obj->buffer.pointer); + (u32 *) out_obj->buffer.pointer, + out_obj->buffer.length - offset); if (offset + out_size > out_obj->buffer.length) { dev_dbg(dev, "%s:%s output object underflow cmd: %s field: %d\n", @@ -333,7 +344,8 @@ static int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, */ rc = buf_len - offset - in_buf.buffer.length; if (cmd_rc) - *cmd_rc = xlat_status(buf, cmd, fw_status); + *cmd_rc = xlat_status(nvdimm, buf, cmd, + fw_status); } else { dev_err(dev, "%s:%s underrun cmd: %s buf_len: %d out_len: %d\n", __func__, dimm_name, cmd_name, buf_len, @@ -343,7 +355,7 @@ static int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, } else { rc = 0; if (cmd_rc) - *cmd_rc = xlat_status(buf, cmd, fw_status); + *cmd_rc = xlat_status(nvdimm, buf, cmd, fw_status); } out: @@ -351,6 +363,7 @@ static int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, return rc; } +EXPORT_SYMBOL_GPL(acpi_nfit_ctl); static const char *spa_type_name(u16 type) { @@ -2001,19 +2014,32 @@ static int ars_get_status(struct acpi_nfit_desc *acpi_desc) return cmd_rc; } -static int ars_status_process_records(struct nvdimm_bus *nvdimm_bus, +static int ars_status_process_records(struct acpi_nfit_desc *acpi_desc, struct nd_cmd_ars_status *ars_status) { + struct nvdimm_bus *nvdimm_bus = acpi_desc->nvdimm_bus; int rc; u32 i; + /* + * First record starts at 44 byte offset from the start of the + * payload. + */ + if (ars_status->out_length < 44) + return 0; for (i = 0; i < ars_status->num_records; i++) { + /* only process full records */ + if (ars_status->out_length + < 44 + sizeof(struct nd_ars_record) * (i + 1)) + break; rc = nvdimm_bus_add_poison(nvdimm_bus, ars_status->records[i].err_address, ars_status->records[i].length); if (rc) return rc; } + if (i < ars_status->num_records) + dev_warn(acpi_desc->dev, "detected truncated ars results\n"); return 0; } @@ -2266,8 +2292,7 @@ static int acpi_nfit_query_poison(struct acpi_nfit_desc *acpi_desc, if (rc < 0 && rc != -ENOSPC) return rc; - if (ars_status_process_records(acpi_desc->nvdimm_bus, - acpi_desc->ars_status)) + if (ars_status_process_records(acpi_desc, acpi_desc->ars_status)) return -ENOMEM; return 0; diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h index 14296f5267c8..fc29c2e9832e 100644 --- a/drivers/acpi/nfit/nfit.h +++ b/drivers/acpi/nfit/nfit.h @@ -240,5 +240,7 @@ const u8 *to_nfit_uuid(enum nfit_uuids id); int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, void *nfit, acpi_size sz); void __acpi_nfit_notify(struct device *dev, acpi_handle handle, u32 event); void __acpi_nvdimm_notify(struct device *dev, u32 event); +int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, + unsigned int cmd, void *buf, unsigned int buf_len, int *cmd_rc); void acpi_nfit_desc_init(struct acpi_nfit_desc *acpi_desc, struct device *dev); #endif /* __NFIT_H__ */ diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c index bb01dea39fdc..f0b4a981b8d3 100644 --- a/drivers/acpi/processor_perflib.c +++ b/drivers/acpi/processor_perflib.c @@ -157,7 +157,7 @@ static void acpi_processor_ppc_ost(acpi_handle handle, int status) status, NULL); } -int acpi_processor_ppc_has_changed(struct acpi_processor *pr, int event_flag) +void acpi_processor_ppc_has_changed(struct acpi_processor *pr, int event_flag) { int ret; @@ -168,7 +168,7 @@ int acpi_processor_ppc_has_changed(struct acpi_processor *pr, int event_flag) */ if (event_flag) acpi_processor_ppc_ost(pr->handle, 1); - return 0; + return; } ret = acpi_processor_get_platform_limit(pr); @@ -182,10 +182,8 @@ int acpi_processor_ppc_has_changed(struct acpi_processor *pr, int event_flag) else acpi_processor_ppc_ost(pr->handle, 0); } - if (ret < 0) - return (ret); - else - return cpufreq_update_policy(pr->id); + if (ret >= 0) + cpufreq_update_policy(pr->id); } int acpi_processor_get_bios_limit(int cpu, unsigned int *limit) @@ -465,11 +463,33 @@ int acpi_processor_get_performance_info(struct acpi_processor *pr) return result; } EXPORT_SYMBOL_GPL(acpi_processor_get_performance_info); -int acpi_processor_notify_smm(struct module *calling_module) + +int acpi_processor_pstate_control(void) { acpi_status status; - static int is_done = 0; + if (!acpi_gbl_FADT.smi_command || !acpi_gbl_FADT.pstate_control) + return 0; + + ACPI_DEBUG_PRINT((ACPI_DB_INFO, + "Writing pstate_control [0x%x] to smi_command [0x%x]\n", + acpi_gbl_FADT.pstate_control, acpi_gbl_FADT.smi_command)); + + status = acpi_os_write_port(acpi_gbl_FADT.smi_command, + (u32)acpi_gbl_FADT.pstate_control, 8); + if (ACPI_SUCCESS(status)) + return 1; + + ACPI_EXCEPTION((AE_INFO, status, + "Failed to write pstate_control [0x%x] to smi_command [0x%x]", + acpi_gbl_FADT.pstate_control, acpi_gbl_FADT.smi_command)); + return -EIO; +} + +int acpi_processor_notify_smm(struct module *calling_module) +{ + static int is_done = 0; + int result; if (!(acpi_processor_ppc_status & PPC_REGISTERED)) return -EBUSY; @@ -492,26 +512,15 @@ int acpi_processor_notify_smm(struct module *calling_module) is_done = -EIO; - /* Can't write pstate_control to smi_command if either value is zero */ - if ((!acpi_gbl_FADT.smi_command) || (!acpi_gbl_FADT.pstate_control)) { + result = acpi_processor_pstate_control(); + if (!result) { ACPI_DEBUG_PRINT((ACPI_DB_INFO, "No SMI port or pstate_control\n")); module_put(calling_module); return 0; } - - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "Writing pstate_control [0x%x] to smi_command [0x%x]\n", - acpi_gbl_FADT.pstate_control, acpi_gbl_FADT.smi_command)); - - status = acpi_os_write_port(acpi_gbl_FADT.smi_command, - (u32) acpi_gbl_FADT.pstate_control, 8); - if (ACPI_FAILURE(status)) { - ACPI_EXCEPTION((AE_INFO, status, - "Failed to write pstate_control [0x%x] to " - "smi_command [0x%x]", acpi_gbl_FADT.pstate_control, - acpi_gbl_FADT.smi_command)); + if (result < 0) { module_put(calling_module); - return status; + return result; } /* Success. If there's no _PPC, we need to fear nothing, so diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index deb0ff78eba8..9b6cebe227a0 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -47,32 +47,15 @@ static void acpi_sleep_tts_switch(u32 acpi_state) } } -static void acpi_sleep_pts_switch(u32 acpi_state) -{ - acpi_status status; - - status = acpi_execute_simple_method(NULL, "\\_PTS", acpi_state); - if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) { - /* - * OS can't evaluate the _PTS object correctly. Some warning - * message will be printed. But it won't break anything. - */ - printk(KERN_NOTICE "Failure in evaluating _PTS object\n"); - } -} - -static int sleep_notify_reboot(struct notifier_block *this, +static int tts_notify_reboot(struct notifier_block *this, unsigned long code, void *x) { acpi_sleep_tts_switch(ACPI_STATE_S5); - - acpi_sleep_pts_switch(ACPI_STATE_S5); - return NOTIFY_DONE; } -static struct notifier_block sleep_notifier = { - .notifier_call = sleep_notify_reboot, +static struct notifier_block tts_notifier = { + .notifier_call = tts_notify_reboot, .next = NULL, .priority = 0, }; @@ -691,6 +674,14 @@ static void acpi_sleep_suspend_setup(void) if (acpi_sleep_state_supported(i)) sleep_states[i] = 1; + /* + * Use suspend-to-idle by default if ACPI_FADT_LOW_POWER_S0 is set and + * the default suspend mode was not selected from the command line. + */ + if (acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0 && + mem_sleep_default > PM_SUSPEND_MEM) + mem_sleep_default = PM_SUSPEND_FREEZE; + suspend_set_ops(old_suspend_ordering ? &acpi_suspend_ops_old : &acpi_suspend_ops); freeze_set_ops(&acpi_freeze_ops); @@ -916,9 +907,9 @@ int __init acpi_sleep_init(void) pr_info(PREFIX "(supports%s)\n", supported); /* - * Register the sleep_notifier to reboot notifier list so that the _TTS - * and _PTS object can also be evaluated when the system enters S5. + * Register the tts_notifier to reboot notifier list so that the _TTS + * object can also be evaluated when the system enters S5. */ - register_reboot_notifier(&sleep_notifier); + register_reboot_notifier(&tts_notifier); return 0; } diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 9669fc7c19df..74f4c662f776 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -1436,13 +1436,6 @@ static int ahci_init_msi(struct pci_dev *pdev, unsigned int n_ports, "ahci: MRSM is on, fallback to single MSI\n"); pci_free_irq_vectors(pdev); } - - /* - * -ENOSPC indicated we don't have enough vectors. Don't bother - * trying a single vectors for any other error: - */ - if (nvec < 0 && nvec != -ENOSPC) - return nvec; } /* diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 9cceb4a875a5..8e575fbdf31d 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1088,7 +1088,7 @@ static void ata_gen_passthru_sense(struct ata_queued_cmd *qc) desc[1] = tf->command; /* status */ desc[2] = tf->device; desc[3] = tf->nsect; - desc[0] = 0; + desc[7] = 0; if (tf->flags & ATA_TFLAG_LBA48) { desc[8] |= 0x80; if (tf->hob_nsect) @@ -1159,6 +1159,7 @@ static void ata_scsi_sdev_config(struct scsi_device *sdev) { sdev->use_10_for_rw = 1; sdev->use_10_for_ms = 1; + sdev->no_write_same = 1; /* Schedule policy is determined by ->qc_defer() callback and * it needs to see every deferred qc. Set dev_blocked to 1 to diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c index efc48bf89d51..823e938c9a78 100644 --- a/drivers/ata/sata_mv.c +++ b/drivers/ata/sata_mv.c @@ -4090,7 +4090,20 @@ static int mv_platform_probe(struct platform_device *pdev) /* allocate host */ if (pdev->dev.of_node) { - of_property_read_u32(pdev->dev.of_node, "nr-ports", &n_ports); + rc = of_property_read_u32(pdev->dev.of_node, "nr-ports", + &n_ports); + if (rc) { + dev_err(&pdev->dev, + "error parsing nr-ports property: %d\n", rc); + return rc; + } + + if (n_ports <= 0) { + dev_err(&pdev->dev, "nr-ports must be positive: %d\n", + n_ports); + return -EINVAL; + } + irq = irq_of_parse_and_map(pdev->dev.of_node, 0); } else { mv_platform_data = dev_get_platdata(&pdev->dev); diff --git a/drivers/atm/eni.c b/drivers/atm/eni.c index f2aaf9e32a36..40c2d561417b 100644 --- a/drivers/atm/eni.c +++ b/drivers/atm/eni.c @@ -1727,7 +1727,7 @@ static int eni_do_init(struct atm_dev *dev) printk("\n"); printk(KERN_ERR DEV_LABEL "(itf %d): can't set up page " "mapping\n",dev->number); - return error; + return -ENOMEM; } eni_dev->ioaddr = base; eni_dev->base_diff = real_base - (unsigned long) base; diff --git a/drivers/atm/lanai.c b/drivers/atm/lanai.c index ce43ae3e87b3..445505d9ea07 100644 --- a/drivers/atm/lanai.c +++ b/drivers/atm/lanai.c @@ -2143,6 +2143,7 @@ static int lanai_dev_open(struct atm_dev *atmdev) lanai->base = (bus_addr_t) ioremap(raw_base, LANAI_MAPPING_SIZE); if (lanai->base == NULL) { printk(KERN_ERR DEV_LABEL ": couldn't remap I/O space\n"); + result = -ENOMEM; goto error_pci; } /* 3.3: Reset lanai and PHY */ diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index e023066e4215..5711708532db 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -39,6 +39,105 @@ static LIST_HEAD(gpd_list); static DEFINE_MUTEX(gpd_list_lock); +struct genpd_lock_ops { + void (*lock)(struct generic_pm_domain *genpd); + void (*lock_nested)(struct generic_pm_domain *genpd, int depth); + int (*lock_interruptible)(struct generic_pm_domain *genpd); + void (*unlock)(struct generic_pm_domain *genpd); +}; + +static void genpd_lock_mtx(struct generic_pm_domain *genpd) +{ + mutex_lock(&genpd->mlock); +} + +static void genpd_lock_nested_mtx(struct generic_pm_domain *genpd, + int depth) +{ + mutex_lock_nested(&genpd->mlock, depth); +} + +static int genpd_lock_interruptible_mtx(struct generic_pm_domain *genpd) +{ + return mutex_lock_interruptible(&genpd->mlock); +} + +static void genpd_unlock_mtx(struct generic_pm_domain *genpd) +{ + return mutex_unlock(&genpd->mlock); +} + +static const struct genpd_lock_ops genpd_mtx_ops = { + .lock = genpd_lock_mtx, + .lock_nested = genpd_lock_nested_mtx, + .lock_interruptible = genpd_lock_interruptible_mtx, + .unlock = genpd_unlock_mtx, +}; + +static void genpd_lock_spin(struct generic_pm_domain *genpd) + __acquires(&genpd->slock) +{ + unsigned long flags; + + spin_lock_irqsave(&genpd->slock, flags); + genpd->lock_flags = flags; +} + +static void genpd_lock_nested_spin(struct generic_pm_domain *genpd, + int depth) + __acquires(&genpd->slock) +{ + unsigned long flags; + + spin_lock_irqsave_nested(&genpd->slock, flags, depth); + genpd->lock_flags = flags; +} + +static int genpd_lock_interruptible_spin(struct generic_pm_domain *genpd) + __acquires(&genpd->slock) +{ + unsigned long flags; + + spin_lock_irqsave(&genpd->slock, flags); + genpd->lock_flags = flags; + return 0; +} + +static void genpd_unlock_spin(struct generic_pm_domain *genpd) + __releases(&genpd->slock) +{ + spin_unlock_irqrestore(&genpd->slock, genpd->lock_flags); +} + +static const struct genpd_lock_ops genpd_spin_ops = { + .lock = genpd_lock_spin, + .lock_nested = genpd_lock_nested_spin, + .lock_interruptible = genpd_lock_interruptible_spin, + .unlock = genpd_unlock_spin, +}; + +#define genpd_lock(p) p->lock_ops->lock(p) +#define genpd_lock_nested(p, d) p->lock_ops->lock_nested(p, d) +#define genpd_lock_interruptible(p) p->lock_ops->lock_interruptible(p) +#define genpd_unlock(p) p->lock_ops->unlock(p) + +#define genpd_is_irq_safe(genpd) (genpd->flags & GENPD_FLAG_IRQ_SAFE) + +static inline bool irq_safe_dev_in_no_sleep_domain(struct device *dev, + struct generic_pm_domain *genpd) +{ + bool ret; + + ret = pm_runtime_is_irq_safe(dev) && !genpd_is_irq_safe(genpd); + + /* Warn once for each IRQ safe dev in no sleep domain */ + if (ret) + dev_warn_once(dev, "PM domain %s will not be powered off\n", + genpd->name); + + return ret; +} + /* * Get the generic PM domain for a particular struct device. * This validates the struct device pointer, the PM domain pointer, @@ -200,9 +299,9 @@ static int genpd_poweron(struct generic_pm_domain *genpd, unsigned int depth) genpd_sd_counter_inc(master); - mutex_lock_nested(&master->lock, depth + 1); + genpd_lock_nested(master, depth + 1); ret = genpd_poweron(master, depth + 1); - mutex_unlock(&master->lock); + genpd_unlock(master); if (ret) { genpd_sd_counter_dec(master); @@ -255,9 +354,9 @@ static int genpd_dev_pm_qos_notifier(struct notifier_block *nb, spin_unlock_irq(&dev->power.lock); if (!IS_ERR(genpd)) { - mutex_lock(&genpd->lock); + genpd_lock(genpd); genpd->max_off_time_changed = true; - mutex_unlock(&genpd->lock); + genpd_unlock(genpd); } dev = dev->parent; @@ -303,7 +402,12 @@ static int genpd_poweroff(struct generic_pm_domain *genpd, bool is_async) if (stat > PM_QOS_FLAGS_NONE) return -EBUSY; - if (!pm_runtime_suspended(pdd->dev) || pdd->dev->power.irq_safe) + /* + * Do not allow PM domain to be powered off, when an IRQ safe + * device is part of a non-IRQ safe domain. + */ + if (!pm_runtime_suspended(pdd->dev) || + irq_safe_dev_in_no_sleep_domain(pdd->dev, genpd)) not_suspended++; } @@ -354,9 +458,9 @@ static void genpd_power_off_work_fn(struct work_struct *work) genpd = container_of(work, struct generic_pm_domain, power_off_work); - mutex_lock(&genpd->lock); + genpd_lock(genpd); genpd_poweroff(genpd, true); - mutex_unlock(&genpd->lock); + genpd_unlock(genpd); } /** @@ -466,15 +570,15 @@ static int genpd_runtime_suspend(struct device *dev) } /* - * If power.irq_safe is set, this routine will be run with interrupts - * off, so it can't use mutexes. + * If power.irq_safe is set, this routine may be run with + * IRQs disabled, so suspend only if the PM domain also is irq_safe. */ - if (dev->power.irq_safe) + if (irq_safe_dev_in_no_sleep_domain(dev, genpd)) return 0; - mutex_lock(&genpd->lock); + genpd_lock(genpd); genpd_poweroff(genpd, false); - mutex_unlock(&genpd->lock); + genpd_unlock(genpd); return 0; } @@ -503,15 +607,18 @@ static int genpd_runtime_resume(struct device *dev) if (IS_ERR(genpd)) return -EINVAL; - /* If power.irq_safe, the PM domain is never powered off. */ - if (dev->power.irq_safe) { + /* + * As we don't power off a non IRQ safe domain, which holds + * an IRQ safe device, we don't need to restore power to it. + */ + if (irq_safe_dev_in_no_sleep_domain(dev, genpd)) { timed = false; goto out; } - mutex_lock(&genpd->lock); + genpd_lock(genpd); ret = genpd_poweron(genpd, 0); - mutex_unlock(&genpd->lock); + genpd_unlock(genpd); if (ret) return ret; @@ -546,10 +653,11 @@ static int genpd_runtime_resume(struct device *dev) err_stop: genpd_stop_dev(genpd, dev); err_poweroff: - if (!dev->power.irq_safe) { - mutex_lock(&genpd->lock); + if (!pm_runtime_is_irq_safe(dev) || + (pm_runtime_is_irq_safe(dev) && genpd_is_irq_safe(genpd))) { + genpd_lock(genpd); genpd_poweroff(genpd, 0); - mutex_unlock(&genpd->lock); + genpd_unlock(genpd); } return ret; @@ -732,20 +840,20 @@ static int pm_genpd_prepare(struct device *dev) if (resume_needed(dev, genpd)) pm_runtime_resume(dev); - mutex_lock(&genpd->lock); + genpd_lock(genpd); if (genpd->prepared_count++ == 0) genpd->suspended_count = 0; - mutex_unlock(&genpd->lock); + genpd_unlock(genpd); ret = pm_generic_prepare(dev); if (ret) { - mutex_lock(&genpd->lock); + genpd_lock(genpd); genpd->prepared_count--; - mutex_unlock(&genpd->lock); + genpd_unlock(genpd); } return ret; @@ -936,13 +1044,13 @@ static void pm_genpd_complete(struct device *dev) pm_generic_complete(dev); - mutex_lock(&genpd->lock); + genpd_lock(genpd); genpd->prepared_count--; if (!genpd->prepared_count) genpd_queue_power_off_work(genpd); - mutex_unlock(&genpd->lock); + genpd_unlock(genpd); } /** @@ -1071,7 +1179,7 @@ static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev, if (IS_ERR(gpd_data)) return PTR_ERR(gpd_data); - mutex_lock(&genpd->lock); + genpd_lock(genpd); if (genpd->prepared_count > 0) { ret = -EAGAIN; @@ -1088,7 +1196,7 @@ static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev, list_add_tail(&gpd_data->base.list_node, &genpd->dev_list); out: - mutex_unlock(&genpd->lock); + genpd_unlock(genpd); if (ret) genpd_free_dev_data(dev, gpd_data); @@ -1130,7 +1238,7 @@ static int genpd_remove_device(struct generic_pm_domain *genpd, gpd_data = to_gpd_data(pdd); dev_pm_qos_remove_notifier(dev, &gpd_data->nb); - mutex_lock(&genpd->lock); + genpd_lock(genpd); if (genpd->prepared_count > 0) { ret = -EAGAIN; @@ -1145,14 +1253,14 @@ static int genpd_remove_device(struct generic_pm_domain *genpd, list_del_init(&pdd->list_node); - mutex_unlock(&genpd->lock); + genpd_unlock(genpd); genpd_free_dev_data(dev, gpd_data); return 0; out: - mutex_unlock(&genpd->lock); + genpd_unlock(genpd); dev_pm_qos_add_notifier(dev, &gpd_data->nb); return ret; @@ -1183,12 +1291,23 @@ static int genpd_add_subdomain(struct generic_pm_domain *genpd, || genpd == subdomain) return -EINVAL; + /* + * If the domain can be powered on/off in an IRQ safe + * context, ensure that the subdomain can also be + * powered on/off in that context. + */ + if (!genpd_is_irq_safe(genpd) && genpd_is_irq_safe(subdomain)) { + WARN(1, "Parent %s of subdomain %s must be IRQ safe\n", + genpd->name, subdomain->name); + return -EINVAL; + } + link = kzalloc(sizeof(*link), GFP_KERNEL); if (!link) return -ENOMEM; - mutex_lock(&subdomain->lock); - mutex_lock_nested(&genpd->lock, SINGLE_DEPTH_NESTING); + genpd_lock(subdomain); + genpd_lock_nested(genpd, SINGLE_DEPTH_NESTING); if (genpd->status == GPD_STATE_POWER_OFF && subdomain->status != GPD_STATE_POWER_OFF) { @@ -1211,8 +1330,8 @@ static int genpd_add_subdomain(struct generic_pm_domain *genpd, genpd_sd_counter_inc(genpd); out: - mutex_unlock(&genpd->lock); - mutex_unlock(&subdomain->lock); + genpd_unlock(genpd); + genpd_unlock(subdomain); if (ret) kfree(link); return ret; @@ -1250,8 +1369,8 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(subdomain)) return -EINVAL; - mutex_lock(&subdomain->lock); - mutex_lock_nested(&genpd->lock, SINGLE_DEPTH_NESTING); + genpd_lock(subdomain); + genpd_lock_nested(genpd, SINGLE_DEPTH_NESTING); if (!list_empty(&subdomain->master_links) || subdomain->device_count) { pr_warn("%s: unable to remove subdomain %s\n", genpd->name, @@ -1275,13 +1394,39 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, } out: - mutex_unlock(&genpd->lock); - mutex_unlock(&subdomain->lock); + genpd_unlock(genpd); + genpd_unlock(subdomain); return ret; } EXPORT_SYMBOL_GPL(pm_genpd_remove_subdomain); +static int genpd_set_default_power_state(struct generic_pm_domain *genpd) +{ + struct genpd_power_state *state; + + state = kzalloc(sizeof(*state), GFP_KERNEL); + if (!state) + return -ENOMEM; + + genpd->states = state; + genpd->state_count = 1; + genpd->free = state; + + return 0; +} + +static void genpd_lock_init(struct generic_pm_domain *genpd) +{ + if (genpd->flags & GENPD_FLAG_IRQ_SAFE) { + spin_lock_init(&genpd->slock); + genpd->lock_ops = &genpd_spin_ops; + } else { + mutex_init(&genpd->mlock); + genpd->lock_ops = &genpd_mtx_ops; + } +} + /** * pm_genpd_init - Initialize a generic I/O PM domain object. * @genpd: PM domain object to initialize. @@ -1293,13 +1438,15 @@ EXPORT_SYMBOL_GPL(pm_genpd_remove_subdomain); int pm_genpd_init(struct generic_pm_domain *genpd, struct dev_power_governor *gov, bool is_off) { + int ret; + if (IS_ERR_OR_NULL(genpd)) return -EINVAL; INIT_LIST_HEAD(&genpd->master_links); INIT_LIST_HEAD(&genpd->slave_links); INIT_LIST_HEAD(&genpd->dev_list); - mutex_init(&genpd->lock); + genpd_lock_init(genpd); genpd->gov = gov; INIT_WORK(&genpd->power_off_work, genpd_power_off_work_fn); atomic_set(&genpd->sd_count, 0); @@ -1325,19 +1472,12 @@ int pm_genpd_init(struct generic_pm_domain *genpd, genpd->dev_ops.start = pm_clk_resume; } - if (genpd->state_idx >= GENPD_MAX_NUM_STATES) { - pr_warn("Initial state index out of bounds.\n"); - genpd->state_idx = GENPD_MAX_NUM_STATES - 1; - } - - if (genpd->state_count > GENPD_MAX_NUM_STATES) { - pr_warn("Limiting states to %d\n", GENPD_MAX_NUM_STATES); - genpd->state_count = GENPD_MAX_NUM_STATES; - } - /* Use only one "off" state if there were no states declared */ - if (genpd->state_count == 0) - genpd->state_count = 1; + if (genpd->state_count == 0) { + ret = genpd_set_default_power_state(genpd); + if (ret) + return ret; + } mutex_lock(&gpd_list_lock); list_add(&genpd->gpd_list_node, &gpd_list); @@ -1354,16 +1494,16 @@ static int genpd_remove(struct generic_pm_domain *genpd) if (IS_ERR_OR_NULL(genpd)) return -EINVAL; - mutex_lock(&genpd->lock); + genpd_lock(genpd); if (genpd->has_provider) { - mutex_unlock(&genpd->lock); + genpd_unlock(genpd); pr_err("Provider present, unable to remove %s\n", genpd->name); return -EBUSY; } if (!list_empty(&genpd->master_links) || genpd->device_count) { - mutex_unlock(&genpd->lock); + genpd_unlock(genpd); pr_err("%s: unable to remove %s\n", __func__, genpd->name); return -EBUSY; } @@ -1375,8 +1515,9 @@ static int genpd_remove(struct generic_pm_domain *genpd) } list_del(&genpd->gpd_list_node); - mutex_unlock(&genpd->lock); + genpd_unlock(genpd); cancel_work_sync(&genpd->power_off_work); + kfree(genpd->free); pr_debug("%s: removed %s\n", __func__, genpd->name); return 0; @@ -1890,21 +2031,117 @@ int genpd_dev_pm_attach(struct device *dev) mutex_unlock(&gpd_list_lock); if (ret < 0) { - dev_err(dev, "failed to add to PM domain %s: %d", - pd->name, ret); + if (ret != -EPROBE_DEFER) + dev_err(dev, "failed to add to PM domain %s: %d", + pd->name, ret); goto out; } dev->pm_domain->detach = genpd_dev_pm_detach; dev->pm_domain->sync = genpd_dev_pm_sync; - mutex_lock(&pd->lock); + genpd_lock(pd); ret = genpd_poweron(pd, 0); - mutex_unlock(&pd->lock); + genpd_unlock(pd); out: return ret ? -EPROBE_DEFER : 0; } EXPORT_SYMBOL_GPL(genpd_dev_pm_attach); + +static const struct of_device_id idle_state_match[] = { + { .compatible = "domain-idle-state", }, + { } +}; + +static int genpd_parse_state(struct genpd_power_state *genpd_state, + struct device_node *state_node) +{ + int err; + u32 residency; + u32 entry_latency, exit_latency; + const struct of_device_id *match_id; + + match_id = of_match_node(idle_state_match, state_node); + if (!match_id) + return -EINVAL; + + err = of_property_read_u32(state_node, "entry-latency-us", + &entry_latency); + if (err) { + pr_debug(" * %s missing entry-latency-us property\n", + state_node->full_name); + return -EINVAL; + } + + err = of_property_read_u32(state_node, "exit-latency-us", + &exit_latency); + if (err) { + pr_debug(" * %s missing exit-latency-us property\n", + state_node->full_name); + return -EINVAL; + } + + err = of_property_read_u32(state_node, "min-residency-us", &residency); + if (!err) + genpd_state->residency_ns = 1000 * residency; + + genpd_state->power_on_latency_ns = 1000 * exit_latency; + genpd_state->power_off_latency_ns = 1000 * entry_latency; + genpd_state->fwnode = &state_node->fwnode; + + return 0; +} + +/** + * of_genpd_parse_idle_states: Return array of idle states for the genpd. + * + * @dn: The genpd device node + * @states: The pointer to which the state array will be saved. + * @n: The count of elements in the array returned from this function. + * + * Returns the device states parsed from the OF node. The memory for the states + * is allocated by this function and is the responsibility of the caller to + * free the memory after use. + */ +int of_genpd_parse_idle_states(struct device_node *dn, + struct genpd_power_state **states, int *n) +{ + struct genpd_power_state *st; + struct device_node *np; + int i = 0; + int err, ret; + int count; + struct of_phandle_iterator it; + + count = of_count_phandle_with_args(dn, "domain-idle-states", NULL); + if (count <= 0) + return -EINVAL; + + st = kcalloc(count, sizeof(*st), GFP_KERNEL); + if (!st) + return -ENOMEM; + + /* Loop over the phandles until all the requested entry is found */ + of_for_each_phandle(&it, err, dn, "domain-idle-states", NULL, 0) { + np = it.node; + ret = genpd_parse_state(&st[i++], np); + if (ret) { + pr_err + ("Parsing idle state node %s failed with err %d\n", + np->full_name, ret); + of_node_put(np); + kfree(st); + return ret; + } + } + + *n = count; + *states = st; + + return 0; +} +EXPORT_SYMBOL_GPL(of_genpd_parse_idle_states); + #endif /* CONFIG_PM_GENERIC_DOMAINS_OF */ @@ -1958,7 +2195,7 @@ static int pm_genpd_summary_one(struct seq_file *s, char state[16]; int ret; - ret = mutex_lock_interruptible(&genpd->lock); + ret = genpd_lock_interruptible(genpd); if (ret) return -ERESTARTSYS; @@ -1984,7 +2221,9 @@ static int pm_genpd_summary_one(struct seq_file *s, } list_for_each_entry(pm_data, &genpd->dev_list, list_node) { - kobj_path = kobject_get_path(&pm_data->dev->kobj, GFP_KERNEL); + kobj_path = kobject_get_path(&pm_data->dev->kobj, + genpd_is_irq_safe(genpd) ? + GFP_ATOMIC : GFP_KERNEL); if (kobj_path == NULL) continue; @@ -1995,7 +2234,7 @@ static int pm_genpd_summary_one(struct seq_file *s, seq_puts(s, "\n"); exit: - mutex_unlock(&genpd->lock); + genpd_unlock(genpd); return 0; } diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index 2932a5bd892f..eb474c882ebe 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -1460,10 +1460,10 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) dpm_watchdog_clear(&wd); Complete: - complete_all(&dev->power.completion); if (error) async_error = error; + complete_all(&dev->power.completion); TRACE_SUSPEND(error); return error; } diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c index 4c7c6da7a989..35ff06283738 100644 --- a/drivers/base/power/opp/core.c +++ b/drivers/base/power/opp/core.c @@ -93,6 +93,8 @@ struct opp_table *_find_opp_table(struct device *dev) * Return: voltage in micro volt corresponding to the opp, else * return 0 * + * This is useful only for devices with single power supply. + * * Locking: This function must be called under rcu_read_lock(). opp is a rcu * protected pointer. This means that opp which could have been fetched by * opp_find_freq_{exact,ceil,floor} functions is valid as long as we are @@ -112,7 +114,7 @@ unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp) if (IS_ERR_OR_NULL(tmp_opp)) pr_err("%s: Invalid parameters\n", __func__); else - v = tmp_opp->u_volt; + v = tmp_opp->supplies[0].u_volt; return v; } @@ -210,6 +212,24 @@ unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev) } EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_clock_latency); +static int _get_regulator_count(struct device *dev) +{ + struct opp_table *opp_table; + int count; + + rcu_read_lock(); + + opp_table = _find_opp_table(dev); + if (!IS_ERR(opp_table)) + count = opp_table->regulator_count; + else + count = 0; + + rcu_read_unlock(); + + return count; +} + /** * dev_pm_opp_get_max_volt_latency() - Get max voltage latency in nanoseconds * @dev: device for which we do this operation @@ -222,34 +242,51 @@ unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev) { struct opp_table *opp_table; struct dev_pm_opp *opp; - struct regulator *reg; + struct regulator *reg, **regulators; unsigned long latency_ns = 0; - unsigned long min_uV = ~0, max_uV = 0; - int ret; + int ret, i, count; + struct { + unsigned long min; + unsigned long max; + } *uV; + + count = _get_regulator_count(dev); + + /* Regulator may not be required for the device */ + if (!count) + return 0; + + regulators = kmalloc_array(count, sizeof(*regulators), GFP_KERNEL); + if (!regulators) + return 0; + + uV = kmalloc_array(count, sizeof(*uV), GFP_KERNEL); + if (!uV) + goto free_regulators; rcu_read_lock(); opp_table = _find_opp_table(dev); if (IS_ERR(opp_table)) { rcu_read_unlock(); - return 0; + goto free_uV; } - reg = opp_table->regulator; - if (IS_ERR(reg)) { - /* Regulator may not be required for device */ - rcu_read_unlock(); - return 0; - } + memcpy(regulators, opp_table->regulators, count * sizeof(*regulators)); - list_for_each_entry_rcu(opp, &opp_table->opp_list, node) { - if (!opp->available) - continue; + for (i = 0; i < count; i++) { + uV[i].min = ~0; + uV[i].max = 0; + + list_for_each_entry_rcu(opp, &opp_table->opp_list, node) { + if (!opp->available) + continue; - if (opp->u_volt_min < min_uV) - min_uV = opp->u_volt_min; - if (opp->u_volt_max > max_uV) - max_uV = opp->u_volt_max; + if (opp->supplies[i].u_volt_min < uV[i].min) + uV[i].min = opp->supplies[i].u_volt_min; + if (opp->supplies[i].u_volt_max > uV[i].max) + uV[i].max = opp->supplies[i].u_volt_max; + } } rcu_read_unlock(); @@ -258,9 +295,16 @@ unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev) * The caller needs to ensure that opp_table (and hence the regulator) * isn't freed, while we are executing this routine. */ - ret = regulator_set_voltage_time(reg, min_uV, max_uV); - if (ret > 0) - latency_ns = ret * 1000; + for (i = 0; reg = regulators[i], i < count; i++) { + ret = regulator_set_voltage_time(reg, uV[i].min, uV[i].max); + if (ret > 0) + latency_ns += ret * 1000; + } + +free_uV: + kfree(uV); +free_regulators: + kfree(regulators); return latency_ns; } @@ -542,8 +586,7 @@ unlock: } static int _set_opp_voltage(struct device *dev, struct regulator *reg, - unsigned long u_volt, unsigned long u_volt_min, - unsigned long u_volt_max) + struct dev_pm_opp_supply *supply) { int ret; @@ -554,14 +597,78 @@ static int _set_opp_voltage(struct device *dev, struct regulator *reg, return 0; } - dev_dbg(dev, "%s: voltages (mV): %lu %lu %lu\n", __func__, u_volt_min, - u_volt, u_volt_max); + dev_dbg(dev, "%s: voltages (mV): %lu %lu %lu\n", __func__, + supply->u_volt_min, supply->u_volt, supply->u_volt_max); - ret = regulator_set_voltage_triplet(reg, u_volt_min, u_volt, - u_volt_max); + ret = regulator_set_voltage_triplet(reg, supply->u_volt_min, + supply->u_volt, supply->u_volt_max); if (ret) dev_err(dev, "%s: failed to set voltage (%lu %lu %lu mV): %d\n", - __func__, u_volt_min, u_volt, u_volt_max, ret); + __func__, supply->u_volt_min, supply->u_volt, + supply->u_volt_max, ret); + + return ret; +} + +static inline int +_generic_set_opp_clk_only(struct device *dev, struct clk *clk, + unsigned long old_freq, unsigned long freq) +{ + int ret; + + ret = clk_set_rate(clk, freq); + if (ret) { + dev_err(dev, "%s: failed to set clock rate: %d\n", __func__, + ret); + } + + return ret; +} + +static int _generic_set_opp(struct dev_pm_set_opp_data *data) +{ + struct dev_pm_opp_supply *old_supply = data->old_opp.supplies; + struct dev_pm_opp_supply *new_supply = data->new_opp.supplies; + unsigned long old_freq = data->old_opp.rate, freq = data->new_opp.rate; + struct regulator *reg = data->regulators[0]; + struct device *dev= data->dev; + int ret; + + /* This function only supports single regulator per device */ + if (WARN_ON(data->regulator_count > 1)) { + dev_err(dev, "multiple regulators are not supported\n"); + return -EINVAL; + } + + /* Scaling up? Scale voltage before frequency */ + if (freq > old_freq) { + ret = _set_opp_voltage(dev, reg, new_supply); + if (ret) + goto restore_voltage; + } + + /* Change frequency */ + ret = _generic_set_opp_clk_only(dev, data->clk, old_freq, freq); + if (ret) + goto restore_voltage; + + /* Scaling down? Scale voltage after frequency */ + if (freq < old_freq) { + ret = _set_opp_voltage(dev, reg, new_supply); + if (ret) + goto restore_freq; + } + + return 0; + +restore_freq: + if (_generic_set_opp_clk_only(dev, data->clk, freq, old_freq)) + dev_err(dev, "%s: failed to restore old-freq (%lu Hz)\n", + __func__, old_freq); +restore_voltage: + /* This shouldn't harm even if the voltages weren't updated earlier */ + if (old_supply->u_volt) + _set_opp_voltage(dev, reg, old_supply); return ret; } @@ -579,12 +686,13 @@ static int _set_opp_voltage(struct device *dev, struct regulator *reg, int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) { struct opp_table *opp_table; + unsigned long freq, old_freq; + int (*set_opp)(struct dev_pm_set_opp_data *data); struct dev_pm_opp *old_opp, *opp; - struct regulator *reg; + struct regulator **regulators; + struct dev_pm_set_opp_data *data; struct clk *clk; - unsigned long freq, old_freq; - unsigned long u_volt, u_volt_min, u_volt_max; - int ret; + int ret, size; if (unlikely(!target_freq)) { dev_err(dev, "%s: Invalid target frequency %lu\n", __func__, @@ -633,55 +741,41 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) return ret; } - u_volt = opp->u_volt; - u_volt_min = opp->u_volt_min; - u_volt_max = opp->u_volt_max; + dev_dbg(dev, "%s: switching OPP: %lu Hz --> %lu Hz\n", __func__, + old_freq, freq); - reg = opp_table->regulator; + regulators = opp_table->regulators; - rcu_read_unlock(); - - /* Scaling up? Scale voltage before frequency */ - if (freq > old_freq) { - ret = _set_opp_voltage(dev, reg, u_volt, u_volt_min, - u_volt_max); - if (ret) - goto restore_voltage; - } - - /* Change frequency */ - - dev_dbg(dev, "%s: switching OPP: %lu Hz --> %lu Hz\n", - __func__, old_freq, freq); - - ret = clk_set_rate(clk, freq); - if (ret) { - dev_err(dev, "%s: failed to set clock rate: %d\n", __func__, - ret); - goto restore_voltage; + /* Only frequency scaling */ + if (!regulators) { + rcu_read_unlock(); + return _generic_set_opp_clk_only(dev, clk, old_freq, freq); } - /* Scaling down? Scale voltage after frequency */ - if (freq < old_freq) { - ret = _set_opp_voltage(dev, reg, u_volt, u_volt_min, - u_volt_max); - if (ret) - goto restore_freq; - } + if (opp_table->set_opp) + set_opp = opp_table->set_opp; + else + set_opp = _generic_set_opp; + + data = opp_table->set_opp_data; + data->regulators = regulators; + data->regulator_count = opp_table->regulator_count; + data->clk = clk; + data->dev = dev; + + data->old_opp.rate = old_freq; + size = sizeof(*opp->supplies) * opp_table->regulator_count; + if (IS_ERR(old_opp)) + memset(data->old_opp.supplies, 0, size); + else + memcpy(data->old_opp.supplies, old_opp->supplies, size); - return 0; + data->new_opp.rate = freq; + memcpy(data->new_opp.supplies, opp->supplies, size); -restore_freq: - if (clk_set_rate(clk, old_freq)) - dev_err(dev, "%s: failed to restore old-freq (%lu Hz)\n", - __func__, old_freq); -restore_voltage: - /* This shouldn't harm even if the voltages weren't updated earlier */ - if (!IS_ERR(old_opp)) - _set_opp_voltage(dev, reg, old_opp->u_volt, - old_opp->u_volt_min, old_opp->u_volt_max); + rcu_read_unlock(); - return ret; + return set_opp(data); } EXPORT_SYMBOL_GPL(dev_pm_opp_set_rate); @@ -764,9 +858,6 @@ static struct opp_table *_add_opp_table(struct device *dev) _of_init_opp_table(opp_table, dev); - /* Set regulator to a non-NULL error value */ - opp_table->regulator = ERR_PTR(-ENXIO); - /* Find clk for the device */ opp_table->clk = clk_get(dev, NULL); if (IS_ERR(opp_table->clk)) { @@ -815,7 +906,10 @@ static void _remove_opp_table(struct opp_table *opp_table) if (opp_table->prop_name) return; - if (!IS_ERR(opp_table->regulator)) + if (opp_table->regulators) + return; + + if (opp_table->set_opp) return; /* Release clk */ @@ -924,34 +1018,50 @@ struct dev_pm_opp *_allocate_opp(struct device *dev, struct opp_table **opp_table) { struct dev_pm_opp *opp; + int count, supply_size; + struct opp_table *table; - /* allocate new OPP node */ - opp = kzalloc(sizeof(*opp), GFP_KERNEL); - if (!opp) + table = _add_opp_table(dev); + if (!table) return NULL; - INIT_LIST_HEAD(&opp->node); + /* Allocate space for at least one supply */ + count = table->regulator_count ? table->regulator_count : 1; + supply_size = sizeof(*opp->supplies) * count; - *opp_table = _add_opp_table(dev); - if (!*opp_table) { - kfree(opp); + /* allocate new OPP node and supplies structures */ + opp = kzalloc(sizeof(*opp) + supply_size, GFP_KERNEL); + if (!opp) { + kfree(table); return NULL; } + /* Put the supplies at the end of the OPP structure as an empty array */ + opp->supplies = (struct dev_pm_opp_supply *)(opp + 1); + INIT_LIST_HEAD(&opp->node); + + *opp_table = table; + return opp; } static bool _opp_supported_by_regulators(struct dev_pm_opp *opp, struct opp_table *opp_table) { - struct regulator *reg = opp_table->regulator; - - if (!IS_ERR(reg) && - !regulator_is_supported_voltage(reg, opp->u_volt_min, - opp->u_volt_max)) { - pr_warn("%s: OPP minuV: %lu maxuV: %lu, not supported by regulator\n", - __func__, opp->u_volt_min, opp->u_volt_max); - return false; + struct regulator *reg; + int i; + + for (i = 0; i < opp_table->regulator_count; i++) { + reg = opp_table->regulators[i]; + + if (!regulator_is_supported_voltage(reg, + opp->supplies[i].u_volt_min, + opp->supplies[i].u_volt_max)) { + pr_warn("%s: OPP minuV: %lu maxuV: %lu, not supported by regulator\n", + __func__, opp->supplies[i].u_volt_min, + opp->supplies[i].u_volt_max); + return false; + } } return true; @@ -983,11 +1093,13 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, /* Duplicate OPPs */ dev_warn(dev, "%s: duplicate OPPs detected. Existing: freq: %lu, volt: %lu, enabled: %d. New: freq: %lu, volt: %lu, enabled: %d\n", - __func__, opp->rate, opp->u_volt, opp->available, - new_opp->rate, new_opp->u_volt, new_opp->available); + __func__, opp->rate, opp->supplies[0].u_volt, + opp->available, new_opp->rate, + new_opp->supplies[0].u_volt, new_opp->available); - return opp->available && new_opp->u_volt == opp->u_volt ? - 0 : -EEXIST; + /* Should we compare voltages for all regulators here ? */ + return opp->available && + new_opp->supplies[0].u_volt == opp->supplies[0].u_volt ? 0 : -EEXIST; } new_opp->opp_table = opp_table; @@ -1054,9 +1166,9 @@ int _opp_add_v1(struct device *dev, unsigned long freq, long u_volt, /* populate the opp table */ new_opp->rate = freq; tol = u_volt * opp_table->voltage_tolerance_v1 / 100; - new_opp->u_volt = u_volt; - new_opp->u_volt_min = u_volt - tol; - new_opp->u_volt_max = u_volt + tol; + new_opp->supplies[0].u_volt = u_volt; + new_opp->supplies[0].u_volt_min = u_volt - tol; + new_opp->supplies[0].u_volt_max = u_volt + tol; new_opp->available = true; new_opp->dynamic = dynamic; @@ -1300,13 +1412,47 @@ unlock: } EXPORT_SYMBOL_GPL(dev_pm_opp_put_prop_name); +static int _allocate_set_opp_data(struct opp_table *opp_table) +{ + struct dev_pm_set_opp_data *data; + int len, count = opp_table->regulator_count; + + if (WARN_ON(!count)) + return -EINVAL; + + /* space for set_opp_data */ + len = sizeof(*data); + + /* space for old_opp.supplies and new_opp.supplies */ + len += 2 * sizeof(struct dev_pm_opp_supply) * count; + + data = kzalloc(len, GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->old_opp.supplies = (void *)(data + 1); + data->new_opp.supplies = data->old_opp.supplies + count; + + opp_table->set_opp_data = data; + + return 0; +} + +static void _free_set_opp_data(struct opp_table *opp_table) +{ + kfree(opp_table->set_opp_data); + opp_table->set_opp_data = NULL; +} + /** - * dev_pm_opp_set_regulator() - Set regulator name for the device + * dev_pm_opp_set_regulators() - Set regulator names for the device * @dev: Device for which regulator name is being set. - * @name: Name of the regulator. + * @names: Array of pointers to the names of the regulator. + * @count: Number of regulators. * * In order to support OPP switching, OPP layer needs to know the name of the - * device's regulator, as the core would be required to switch voltages as well. + * device's regulators, as the core would be required to switch voltages as + * well. * * This must be called before any OPPs are initialized for the device. * @@ -1316,11 +1462,13 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_put_prop_name); * that this function is *NOT* called under RCU protection or in contexts where * mutex cannot be locked. */ -int dev_pm_opp_set_regulator(struct device *dev, const char *name) +struct opp_table *dev_pm_opp_set_regulators(struct device *dev, + const char * const names[], + unsigned int count) { struct opp_table *opp_table; struct regulator *reg; - int ret; + int ret, i; mutex_lock(&opp_table_lock); @@ -1336,22 +1484,146 @@ int dev_pm_opp_set_regulator(struct device *dev, const char *name) goto err; } - /* Already have a regulator set */ - if (WARN_ON(!IS_ERR(opp_table->regulator))) { + /* Already have regulators set */ + if (opp_table->regulators) { ret = -EBUSY; goto err; } - /* Allocate the regulator */ - reg = regulator_get_optional(dev, name); - if (IS_ERR(reg)) { - ret = PTR_ERR(reg); - if (ret != -EPROBE_DEFER) - dev_err(dev, "%s: no regulator (%s) found: %d\n", - __func__, name, ret); + + opp_table->regulators = kmalloc_array(count, + sizeof(*opp_table->regulators), + GFP_KERNEL); + if (!opp_table->regulators) { + ret = -ENOMEM; + goto err; + } + + for (i = 0; i < count; i++) { + reg = regulator_get_optional(dev, names[i]); + if (IS_ERR(reg)) { + ret = PTR_ERR(reg); + if (ret != -EPROBE_DEFER) + dev_err(dev, "%s: no regulator (%s) found: %d\n", + __func__, names[i], ret); + goto free_regulators; + } + + opp_table->regulators[i] = reg; + } + + opp_table->regulator_count = count; + + /* Allocate block only once to pass to set_opp() routines */ + ret = _allocate_set_opp_data(opp_table); + if (ret) + goto free_regulators; + + mutex_unlock(&opp_table_lock); + return opp_table; + +free_regulators: + while (i != 0) + regulator_put(opp_table->regulators[--i]); + + kfree(opp_table->regulators); + opp_table->regulators = NULL; + opp_table->regulator_count = 0; +err: + _remove_opp_table(opp_table); +unlock: + mutex_unlock(&opp_table_lock); + + return ERR_PTR(ret); +} +EXPORT_SYMBOL_GPL(dev_pm_opp_set_regulators); + +/** + * dev_pm_opp_put_regulators() - Releases resources blocked for regulator + * @opp_table: OPP table returned from dev_pm_opp_set_regulators(). + * + * Locking: The internal opp_table and opp structures are RCU protected. + * Hence this function internally uses RCU updater strategy with mutex locks + * to keep the integrity of the internal data structures. Callers should ensure + * that this function is *NOT* called under RCU protection or in contexts where + * mutex cannot be locked. + */ +void dev_pm_opp_put_regulators(struct opp_table *opp_table) +{ + int i; + + mutex_lock(&opp_table_lock); + + if (!opp_table->regulators) { + pr_err("%s: Doesn't have regulators set\n", __func__); + goto unlock; + } + + /* Make sure there are no concurrent readers while updating opp_table */ + WARN_ON(!list_empty(&opp_table->opp_list)); + + for (i = opp_table->regulator_count - 1; i >= 0; i--) + regulator_put(opp_table->regulators[i]); + + _free_set_opp_data(opp_table); + + kfree(opp_table->regulators); + opp_table->regulators = NULL; + opp_table->regulator_count = 0; + + /* Try freeing opp_table if this was the last blocking resource */ + _remove_opp_table(opp_table); + +unlock: + mutex_unlock(&opp_table_lock); +} +EXPORT_SYMBOL_GPL(dev_pm_opp_put_regulators); + +/** + * dev_pm_opp_register_set_opp_helper() - Register custom set OPP helper + * @dev: Device for which the helper is getting registered. + * @set_opp: Custom set OPP helper. + * + * This is useful to support complex platforms (like platforms with multiple + * regulators per device), instead of the generic OPP set rate helper. + * + * This must be called before any OPPs are initialized for the device. + * + * Locking: The internal opp_table and opp structures are RCU protected. + * Hence this function internally uses RCU updater strategy with mutex locks + * to keep the integrity of the internal data structures. Callers should ensure + * that this function is *NOT* called under RCU protection or in contexts where + * mutex cannot be locked. + */ +int dev_pm_opp_register_set_opp_helper(struct device *dev, + int (*set_opp)(struct dev_pm_set_opp_data *data)) +{ + struct opp_table *opp_table; + int ret; + + if (!set_opp) + return -EINVAL; + + mutex_lock(&opp_table_lock); + + opp_table = _add_opp_table(dev); + if (!opp_table) { + ret = -ENOMEM; + goto unlock; + } + + /* This should be called before OPPs are initialized */ + if (WARN_ON(!list_empty(&opp_table->opp_list))) { + ret = -EBUSY; goto err; } - opp_table->regulator = reg; + /* Already have custom set_opp helper */ + if (WARN_ON(opp_table->set_opp)) { + ret = -EBUSY; + goto err; + } + + opp_table->set_opp = set_opp; mutex_unlock(&opp_table_lock); return 0; @@ -1363,11 +1635,12 @@ unlock: return ret; } -EXPORT_SYMBOL_GPL(dev_pm_opp_set_regulator); +EXPORT_SYMBOL_GPL(dev_pm_opp_register_set_opp_helper); /** - * dev_pm_opp_put_regulator() - Releases resources blocked for regulator - * @dev: Device for which regulator was set. + * dev_pm_opp_register_put_opp_helper() - Releases resources blocked for + * set_opp helper + * @dev: Device for which custom set_opp helper has to be cleared. * * Locking: The internal opp_table and opp structures are RCU protected. * Hence this function internally uses RCU updater strategy with mutex locks @@ -1375,7 +1648,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_set_regulator); * that this function is *NOT* called under RCU protection or in contexts where * mutex cannot be locked. */ -void dev_pm_opp_put_regulator(struct device *dev) +void dev_pm_opp_register_put_opp_helper(struct device *dev) { struct opp_table *opp_table; @@ -1389,16 +1662,16 @@ void dev_pm_opp_put_regulator(struct device *dev) goto unlock; } - if (IS_ERR(opp_table->regulator)) { - dev_err(dev, "%s: Doesn't have regulator set\n", __func__); + if (!opp_table->set_opp) { + dev_err(dev, "%s: Doesn't have custom set_opp helper set\n", + __func__); goto unlock; } /* Make sure there are no concurrent readers while updating opp_table */ WARN_ON(!list_empty(&opp_table->opp_list)); - regulator_put(opp_table->regulator); - opp_table->regulator = ERR_PTR(-ENXIO); + opp_table->set_opp = NULL; /* Try freeing opp_table if this was the last blocking resource */ _remove_opp_table(opp_table); @@ -1406,7 +1679,7 @@ void dev_pm_opp_put_regulator(struct device *dev) unlock: mutex_unlock(&opp_table_lock); } -EXPORT_SYMBOL_GPL(dev_pm_opp_put_regulator); +EXPORT_SYMBOL_GPL(dev_pm_opp_register_put_opp_helper); /** * dev_pm_opp_add() - Add an OPP table from a table definitions diff --git a/drivers/base/power/opp/debugfs.c b/drivers/base/power/opp/debugfs.c index ef1ae6b52042..95f433db4ac7 100644 --- a/drivers/base/power/opp/debugfs.c +++ b/drivers/base/power/opp/debugfs.c @@ -15,6 +15,7 @@ #include <linux/err.h> #include <linux/init.h> #include <linux/limits.h> +#include <linux/slab.h> #include "opp.h" @@ -34,6 +35,46 @@ void opp_debug_remove_one(struct dev_pm_opp *opp) debugfs_remove_recursive(opp->dentry); } +static bool opp_debug_create_supplies(struct dev_pm_opp *opp, + struct opp_table *opp_table, + struct dentry *pdentry) +{ + struct dentry *d; + int i = 0; + char *name; + + /* Always create at least supply-0 directory */ + do { + name = kasprintf(GFP_KERNEL, "supply-%d", i); + + /* Create per-opp directory */ + d = debugfs_create_dir(name, pdentry); + + kfree(name); + + if (!d) + return false; + + if (!debugfs_create_ulong("u_volt_target", S_IRUGO, d, + &opp->supplies[i].u_volt)) + return false; + + if (!debugfs_create_ulong("u_volt_min", S_IRUGO, d, + &opp->supplies[i].u_volt_min)) + return false; + + if (!debugfs_create_ulong("u_volt_max", S_IRUGO, d, + &opp->supplies[i].u_volt_max)) + return false; + + if (!debugfs_create_ulong("u_amp", S_IRUGO, d, + &opp->supplies[i].u_amp)) + return false; + } while (++i < opp_table->regulator_count); + + return true; +} + int opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table) { struct dentry *pdentry = opp_table->dentry; @@ -63,16 +104,7 @@ int opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table) if (!debugfs_create_ulong("rate_hz", S_IRUGO, d, &opp->rate)) return -ENOMEM; - if (!debugfs_create_ulong("u_volt_target", S_IRUGO, d, &opp->u_volt)) - return -ENOMEM; - - if (!debugfs_create_ulong("u_volt_min", S_IRUGO, d, &opp->u_volt_min)) - return -ENOMEM; - - if (!debugfs_create_ulong("u_volt_max", S_IRUGO, d, &opp->u_volt_max)) - return -ENOMEM; - - if (!debugfs_create_ulong("u_amp", S_IRUGO, d, &opp->u_amp)) + if (!opp_debug_create_supplies(opp, opp_table, d)) return -ENOMEM; if (!debugfs_create_ulong("clock_latency_ns", S_IRUGO, d, diff --git a/drivers/base/power/opp/of.c b/drivers/base/power/opp/of.c index 5552211e6fcd..3f7d2591b173 100644 --- a/drivers/base/power/opp/of.c +++ b/drivers/base/power/opp/of.c @@ -17,6 +17,7 @@ #include <linux/errno.h> #include <linux/device.h> #include <linux/of.h> +#include <linux/slab.h> #include <linux/export.h> #include "opp.h" @@ -101,16 +102,16 @@ static bool _opp_is_supported(struct device *dev, struct opp_table *opp_table, return true; } -/* TODO: Support multiple regulators */ static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev, struct opp_table *opp_table) { - u32 microvolt[3] = {0}; - u32 val; - int count, ret; + u32 *microvolt, *microamp = NULL; + int supplies, vcount, icount, ret, i, j; struct property *prop = NULL; char name[NAME_MAX]; + supplies = opp_table->regulator_count ? opp_table->regulator_count : 1; + /* Search for "opp-microvolt-<name>" */ if (opp_table->prop_name) { snprintf(name, sizeof(name), "opp-microvolt-%s", @@ -128,34 +129,29 @@ static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev, return 0; } - count = of_property_count_u32_elems(opp->np, name); - if (count < 0) { + vcount = of_property_count_u32_elems(opp->np, name); + if (vcount < 0) { dev_err(dev, "%s: Invalid %s property (%d)\n", - __func__, name, count); - return count; + __func__, name, vcount); + return vcount; } - /* There can be one or three elements here */ - if (count != 1 && count != 3) { - dev_err(dev, "%s: Invalid number of elements in %s property (%d)\n", - __func__, name, count); + /* There can be one or three elements per supply */ + if (vcount != supplies && vcount != supplies * 3) { + dev_err(dev, "%s: Invalid number of elements in %s property (%d) with supplies (%d)\n", + __func__, name, vcount, supplies); return -EINVAL; } - ret = of_property_read_u32_array(opp->np, name, microvolt, count); + microvolt = kmalloc_array(vcount, sizeof(*microvolt), GFP_KERNEL); + if (!microvolt) + return -ENOMEM; + + ret = of_property_read_u32_array(opp->np, name, microvolt, vcount); if (ret) { dev_err(dev, "%s: error parsing %s: %d\n", __func__, name, ret); - return -EINVAL; - } - - opp->u_volt = microvolt[0]; - - if (count == 1) { - opp->u_volt_min = opp->u_volt; - opp->u_volt_max = opp->u_volt; - } else { - opp->u_volt_min = microvolt[1]; - opp->u_volt_max = microvolt[2]; + ret = -EINVAL; + goto free_microvolt; } /* Search for "opp-microamp-<name>" */ @@ -172,10 +168,59 @@ static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev, prop = of_find_property(opp->np, name, NULL); } - if (prop && !of_property_read_u32(opp->np, name, &val)) - opp->u_amp = val; + if (prop) { + icount = of_property_count_u32_elems(opp->np, name); + if (icount < 0) { + dev_err(dev, "%s: Invalid %s property (%d)\n", __func__, + name, icount); + ret = icount; + goto free_microvolt; + } - return 0; + if (icount != supplies) { + dev_err(dev, "%s: Invalid number of elements in %s property (%d) with supplies (%d)\n", + __func__, name, icount, supplies); + ret = -EINVAL; + goto free_microvolt; + } + + microamp = kmalloc_array(icount, sizeof(*microamp), GFP_KERNEL); + if (!microamp) { + ret = -EINVAL; + goto free_microvolt; + } + + ret = of_property_read_u32_array(opp->np, name, microamp, + icount); + if (ret) { + dev_err(dev, "%s: error parsing %s: %d\n", __func__, + name, ret); + ret = -EINVAL; + goto free_microamp; + } + } + + for (i = 0, j = 0; i < supplies; i++) { + opp->supplies[i].u_volt = microvolt[j++]; + + if (vcount == supplies) { + opp->supplies[i].u_volt_min = opp->supplies[i].u_volt; + opp->supplies[i].u_volt_max = opp->supplies[i].u_volt; + } else { + opp->supplies[i].u_volt_min = microvolt[j++]; + opp->supplies[i].u_volt_max = microvolt[j++]; + } + + if (microamp) + opp->supplies[i].u_amp = microamp[i]; + } + +free_microamp: + kfree(microamp); +free_microvolt: + kfree(microvolt); + + return ret; } /** @@ -198,7 +243,7 @@ void dev_pm_opp_of_remove_table(struct device *dev) EXPORT_SYMBOL_GPL(dev_pm_opp_of_remove_table); /* Returns opp descriptor node for a device, caller must do of_node_put() */ -struct device_node *_of_get_opp_desc_node(struct device *dev) +static struct device_node *_of_get_opp_desc_node(struct device *dev) { /* * TODO: Support for multiple OPP tables. @@ -303,9 +348,9 @@ static int _opp_add_static_v2(struct device *dev, struct device_node *np) mutex_unlock(&opp_table_lock); pr_debug("%s: turbo:%d rate:%lu uv:%lu uvmin:%lu uvmax:%lu latency:%lu\n", - __func__, new_opp->turbo, new_opp->rate, new_opp->u_volt, - new_opp->u_volt_min, new_opp->u_volt_max, - new_opp->clock_latency_ns); + __func__, new_opp->turbo, new_opp->rate, + new_opp->supplies[0].u_volt, new_opp->supplies[0].u_volt_min, + new_opp->supplies[0].u_volt_max, new_opp->clock_latency_ns); /* * Notify the changes in the availability of the operable @@ -562,7 +607,7 @@ int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, /* Get OPP descriptor node */ np = _of_get_opp_desc_node(cpu_dev); if (!np) { - dev_dbg(cpu_dev, "%s: Couldn't find cpu_dev node.\n", __func__); + dev_dbg(cpu_dev, "%s: Couldn't find opp node.\n", __func__); return -ENOENT; } @@ -587,7 +632,7 @@ int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, /* Get OPP descriptor node */ tmp_np = _of_get_opp_desc_node(tcpu_dev); if (!tmp_np) { - dev_err(tcpu_dev, "%s: Couldn't find tcpu_dev node.\n", + dev_err(tcpu_dev, "%s: Couldn't find opp node.\n", __func__); ret = -ENOENT; goto put_cpu_node; diff --git a/drivers/base/power/opp/opp.h b/drivers/base/power/opp/opp.h index fabd5ca1a083..af9f2b849a66 100644 --- a/drivers/base/power/opp/opp.h +++ b/drivers/base/power/opp/opp.h @@ -61,10 +61,7 @@ extern struct list_head opp_tables; * @turbo: true if turbo (boost) OPP * @suspend: true if suspend OPP * @rate: Frequency in hertz - * @u_volt: Target voltage in microvolts corresponding to this OPP - * @u_volt_min: Minimum voltage in microvolts corresponding to this OPP - * @u_volt_max: Maximum voltage in microvolts corresponding to this OPP - * @u_amp: Maximum current drawn by the device in microamperes + * @supplies: Power supplies voltage/current values * @clock_latency_ns: Latency (in nanoseconds) of switching to this OPP's * frequency from any other OPP's frequency. * @opp_table: points back to the opp_table struct this opp belongs to @@ -83,10 +80,8 @@ struct dev_pm_opp { bool suspend; unsigned long rate; - unsigned long u_volt; - unsigned long u_volt_min; - unsigned long u_volt_max; - unsigned long u_amp; + struct dev_pm_opp_supply *supplies; + unsigned long clock_latency_ns; struct opp_table *opp_table; @@ -144,7 +139,10 @@ enum opp_table_access { * @supported_hw_count: Number of elements in supported_hw array. * @prop_name: A name to postfix to many DT properties, while parsing them. * @clk: Device's clock handle - * @regulator: Supply regulator + * @regulators: Supply regulators + * @regulator_count: Number of power supply regulators + * @set_opp: Platform specific set_opp callback + * @set_opp_data: Data to be passed to set_opp callback * @dentry: debugfs dentry pointer of the real device directory (not links). * @dentry_name: Name of the real dentry. * @@ -179,7 +177,11 @@ struct opp_table { unsigned int supported_hw_count; const char *prop_name; struct clk *clk; - struct regulator *regulator; + struct regulator **regulators; + unsigned int regulator_count; + + int (*set_opp)(struct dev_pm_set_opp_data *data); + struct dev_pm_set_opp_data *set_opp_data; #ifdef CONFIG_DEBUG_FS struct dentry *dentry; @@ -190,7 +192,6 @@ struct opp_table { /* Routines internal to opp core */ struct opp_table *_find_opp_table(struct device *dev); struct opp_device *_add_opp_dev(const struct device *dev, struct opp_table *opp_table); -struct device_node *_of_get_opp_desc_node(struct device *dev); void _dev_pm_opp_remove_table(struct device *dev, bool remove_all); struct dev_pm_opp *_allocate_opp(struct device *dev, struct opp_table **opp_table); int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, struct opp_table *opp_table); diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h index 50e30e7b059d..a84332aefc2d 100644 --- a/drivers/base/power/power.h +++ b/drivers/base/power/power.h @@ -21,14 +21,22 @@ extern void pm_runtime_init(struct device *dev); extern void pm_runtime_reinit(struct device *dev); extern void pm_runtime_remove(struct device *dev); +#define WAKE_IRQ_DEDICATED_ALLOCATED BIT(0) +#define WAKE_IRQ_DEDICATED_MANAGED BIT(1) +#define WAKE_IRQ_DEDICATED_MASK (WAKE_IRQ_DEDICATED_ALLOCATED | \ + WAKE_IRQ_DEDICATED_MANAGED) + struct wake_irq { struct device *dev; + unsigned int status; int irq; - bool dedicated_irq:1; }; extern void dev_pm_arm_wake_irq(struct wake_irq *wirq); extern void dev_pm_disarm_wake_irq(struct wake_irq *wirq); +extern void dev_pm_enable_wake_irq_check(struct device *dev, + bool can_change_status); +extern void dev_pm_disable_wake_irq_check(struct device *dev); #ifdef CONFIG_PM_SLEEP @@ -104,6 +112,15 @@ static inline void dev_pm_disarm_wake_irq(struct wake_irq *wirq) { } +static inline void dev_pm_enable_wake_irq_check(struct device *dev, + bool can_change_status) +{ +} + +static inline void dev_pm_disable_wake_irq_check(struct device *dev) +{ +} + #endif #ifdef CONFIG_PM_SLEEP diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c index 7f3646e459cb..58fcc758334e 100644 --- a/drivers/base/power/qos.c +++ b/drivers/base/power/qos.c @@ -856,7 +856,10 @@ int dev_pm_qos_update_user_latency_tolerance(struct device *dev, s32 val) struct dev_pm_qos_request *req; if (val < 0) { - ret = -EINVAL; + if (val == PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT) + ret = 0; + else + ret = -EINVAL; goto out; } req = kzalloc(sizeof(*req), GFP_KERNEL); @@ -883,6 +886,7 @@ int dev_pm_qos_update_user_latency_tolerance(struct device *dev, s32 val) mutex_unlock(&dev_pm_qos_mtx); return ret; } +EXPORT_SYMBOL_GPL(dev_pm_qos_update_user_latency_tolerance); /** * dev_pm_qos_expose_latency_tolerance - Expose latency tolerance to userspace diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 82a081ea4317..26856d050037 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -241,7 +241,8 @@ static int rpm_check_suspend_allowed(struct device *dev) retval = -EACCES; else if (atomic_read(&dev->power.usage_count) > 0) retval = -EAGAIN; - else if (!pm_children_suspended(dev)) + else if (!dev->power.ignore_children && + atomic_read(&dev->power.child_count)) retval = -EBUSY; /* Pending resume requests take precedence over suspends. */ @@ -515,7 +516,7 @@ static int rpm_suspend(struct device *dev, int rpmflags) callback = RPM_GET_CALLBACK(dev, runtime_suspend); - dev_pm_enable_wake_irq(dev); + dev_pm_enable_wake_irq_check(dev, true); retval = rpm_callback(callback, dev); if (retval) goto fail; @@ -554,7 +555,7 @@ static int rpm_suspend(struct device *dev, int rpmflags) return retval; fail: - dev_pm_disable_wake_irq(dev); + dev_pm_disable_wake_irq_check(dev); __update_runtime_status(dev, RPM_ACTIVE); dev->power.deferred_resume = false; wake_up_all(&dev->power.wait_queue); @@ -712,8 +713,8 @@ static int rpm_resume(struct device *dev, int rpmflags) spin_lock(&parent->power.lock); /* - * We can resume if the parent's runtime PM is disabled or it - * is set to ignore children. + * Resume the parent if it has runtime PM enabled and not been + * set to ignore its children. */ if (!parent->power.disable_depth && !parent->power.ignore_children) { @@ -737,12 +738,12 @@ static int rpm_resume(struct device *dev, int rpmflags) callback = RPM_GET_CALLBACK(dev, runtime_resume); - dev_pm_disable_wake_irq(dev); + dev_pm_disable_wake_irq_check(dev); retval = rpm_callback(callback, dev); if (retval) { __update_runtime_status(dev, RPM_SUSPENDED); pm_runtime_cancel_pending(dev); - dev_pm_enable_wake_irq(dev); + dev_pm_enable_wake_irq_check(dev, false); } else { no_callback: __update_runtime_status(dev, RPM_ACTIVE); @@ -1027,7 +1028,17 @@ int __pm_runtime_set_status(struct device *dev, unsigned int status) goto out_set; if (status == RPM_SUSPENDED) { - /* It always is possible to set the status to 'suspended'. */ + /* + * It is invalid to suspend a device with an active child, + * unless it has been set to ignore its children. + */ + if (!dev->power.ignore_children && + atomic_read(&dev->power.child_count)) { + dev_err(dev, "runtime PM trying to suspend device but active child\n"); + error = -EBUSY; + goto out; + } + if (parent) { atomic_add_unless(&parent->power.child_count, -1, 0); notify_parent = !parent->power.ignore_children; @@ -1478,6 +1489,16 @@ int pm_runtime_force_suspend(struct device *dev) if (ret) goto err; + /* + * Increase the runtime PM usage count for the device's parent, in case + * when we find the device being used when system suspend was invoked. + * This informs pm_runtime_force_resume() to resume the parent + * immediately, which is needed to be able to resume its children, + * when not deferring the resume to be managed via runtime PM. + */ + if (dev->parent && atomic_read(&dev->power.usage_count) > 1) + pm_runtime_get_noresume(dev->parent); + pm_runtime_set_suspended(dev); return 0; err: @@ -1487,16 +1508,20 @@ err: EXPORT_SYMBOL_GPL(pm_runtime_force_suspend); /** - * pm_runtime_force_resume - Force a device into resume state. + * pm_runtime_force_resume - Force a device into resume state if needed. * @dev: Device to resume. * * Prior invoking this function we expect the user to have brought the device * into low power state by a call to pm_runtime_force_suspend(). Here we reverse - * those actions and brings the device into full power. We update the runtime PM - * status and re-enables runtime PM. + * those actions and brings the device into full power, if it is expected to be + * used on system resume. To distinguish that, we check whether the runtime PM + * usage count is greater than 1 (the PM core increases the usage count in the + * system PM prepare phase), as that indicates a real user (such as a subsystem, + * driver, userspace, etc.) is using it. If that is the case, the device is + * expected to be used on system resume as well, so then we resume it. In the + * other case, we defer the resume to be managed via runtime PM. * - * Typically this function may be invoked from a system resume callback to make - * sure the device is put into full power state. + * Typically this function may be invoked from a system resume callback. */ int pm_runtime_force_resume(struct device *dev) { @@ -1513,6 +1538,17 @@ int pm_runtime_force_resume(struct device *dev) if (!pm_runtime_status_suspended(dev)) goto out; + /* + * Decrease the parent's runtime PM usage count, if we increased it + * during system suspend in pm_runtime_force_suspend(). + */ + if (atomic_read(&dev->power.usage_count) > 1) { + if (dev->parent) + pm_runtime_put_noidle(dev->parent); + } else { + goto out; + } + ret = pm_runtime_set_active(dev); if (ret) goto out; diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c index a7b46798c81d..33b4b902741a 100644 --- a/drivers/base/power/sysfs.c +++ b/drivers/base/power/sysfs.c @@ -263,7 +263,11 @@ static ssize_t pm_qos_latency_tolerance_store(struct device *dev, s32 value; int ret; - if (kstrtos32(buf, 0, &value)) { + if (kstrtos32(buf, 0, &value) == 0) { + /* Users can't write negative values directly */ + if (value < 0) + return -EINVAL; + } else { if (!strcmp(buf, "auto") || !strcmp(buf, "auto\n")) value = PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT; else if (!strcmp(buf, "any") || !strcmp(buf, "any\n")) diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c index 0d77cd6fd8d1..404d94c6c8bc 100644 --- a/drivers/base/power/wakeirq.c +++ b/drivers/base/power/wakeirq.c @@ -110,8 +110,10 @@ void dev_pm_clear_wake_irq(struct device *dev) dev->power.wakeirq = NULL; spin_unlock_irqrestore(&dev->power.lock, flags); - if (wirq->dedicated_irq) + if (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED) { free_irq(wirq->irq, wirq); + wirq->status &= ~WAKE_IRQ_DEDICATED_MASK; + } kfree(wirq); } EXPORT_SYMBOL_GPL(dev_pm_clear_wake_irq); @@ -179,7 +181,6 @@ int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq) wirq->dev = dev; wirq->irq = irq; - wirq->dedicated_irq = true; irq_set_status_flags(irq, IRQ_NOAUTOEN); /* @@ -195,6 +196,8 @@ int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq) if (err) goto err_free_irq; + wirq->status = WAKE_IRQ_DEDICATED_ALLOCATED; + return err; err_free_irq: @@ -210,9 +213,9 @@ EXPORT_SYMBOL_GPL(dev_pm_set_dedicated_wake_irq); * dev_pm_enable_wake_irq - Enable device wake-up interrupt * @dev: Device * - * Called from the bus code or the device driver for - * runtime_suspend() to enable the wake-up interrupt while - * the device is running. + * Optionally called from the bus code or the device driver for + * runtime_resume() to override the PM runtime core managed wake-up + * interrupt handling to enable the wake-up interrupt. * * Note that for runtime_suspend()) the wake-up interrupts * should be unconditionally enabled unlike for suspend() @@ -222,7 +225,7 @@ void dev_pm_enable_wake_irq(struct device *dev) { struct wake_irq *wirq = dev->power.wakeirq; - if (wirq && wirq->dedicated_irq) + if (wirq && (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED)) enable_irq(wirq->irq); } EXPORT_SYMBOL_GPL(dev_pm_enable_wake_irq); @@ -231,20 +234,73 @@ EXPORT_SYMBOL_GPL(dev_pm_enable_wake_irq); * dev_pm_disable_wake_irq - Disable device wake-up interrupt * @dev: Device * - * Called from the bus code or the device driver for - * runtime_resume() to disable the wake-up interrupt while - * the device is running. + * Optionally called from the bus code or the device driver for + * runtime_suspend() to override the PM runtime core managed wake-up + * interrupt handling to disable the wake-up interrupt. */ void dev_pm_disable_wake_irq(struct device *dev) { struct wake_irq *wirq = dev->power.wakeirq; - if (wirq && wirq->dedicated_irq) + if (wirq && (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED)) disable_irq_nosync(wirq->irq); } EXPORT_SYMBOL_GPL(dev_pm_disable_wake_irq); /** + * dev_pm_enable_wake_irq_check - Checks and enables wake-up interrupt + * @dev: Device + * @can_change_status: Can change wake-up interrupt status + * + * Enables wakeirq conditionally. We need to enable wake-up interrupt + * lazily on the first rpm_suspend(). This is needed as the consumer device + * starts in RPM_SUSPENDED state, and the the first pm_runtime_get() would + * otherwise try to disable already disabled wakeirq. The wake-up interrupt + * starts disabled with IRQ_NOAUTOEN set. + * + * Should be only called from rpm_suspend() and rpm_resume() path. + * Caller must hold &dev->power.lock to change wirq->status + */ +void dev_pm_enable_wake_irq_check(struct device *dev, + bool can_change_status) +{ + struct wake_irq *wirq = dev->power.wakeirq; + + if (!wirq || !((wirq->status & WAKE_IRQ_DEDICATED_MASK))) + return; + + if (likely(wirq->status & WAKE_IRQ_DEDICATED_MANAGED)) { + goto enable; + } else if (can_change_status) { + wirq->status |= WAKE_IRQ_DEDICATED_MANAGED; + goto enable; + } + + return; + +enable: + enable_irq(wirq->irq); +} + +/** + * dev_pm_disable_wake_irq_check - Checks and disables wake-up interrupt + * @dev: Device + * + * Disables wake-up interrupt conditionally based on status. + * Should be only called from rpm_suspend() and rpm_resume() path. + */ +void dev_pm_disable_wake_irq_check(struct device *dev) +{ + struct wake_irq *wirq = dev->power.wakeirq; + + if (!wirq || !((wirq->status & WAKE_IRQ_DEDICATED_MASK))) + return; + + if (wirq->status & WAKE_IRQ_DEDICATED_MANAGED) + disable_irq_nosync(wirq->irq); +} + +/** * dev_pm_arm_wake_irq - Arm device wake-up * @wirq: Device wake-up interrupt * diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c index 62e4de2aa8d1..bf9ba26981a5 100644 --- a/drivers/base/power/wakeup.c +++ b/drivers/base/power/wakeup.c @@ -811,7 +811,7 @@ void pm_print_active_wakeup_sources(void) rcu_read_lock(); list_for_each_entry_rcu(ws, &wakeup_sources, entry) { if (ws->active) { - pr_info("active wakeup source: %s\n", ws->name); + pr_debug("active wakeup source: %s\n", ws->name); active = 1; } else if (!active && (!last_activity_ws || @@ -822,7 +822,7 @@ void pm_print_active_wakeup_sources(void) } if (!active && last_activity_ws) - pr_info("last active wakeup source: %s\n", + pr_debug("last active wakeup source: %s\n", last_activity_ws->name); rcu_read_unlock(); } @@ -905,7 +905,7 @@ bool pm_get_wakeup_count(unsigned int *count, bool block) split_counters(&cnt, &inpr); if (inpr == 0 || signal_pending(current)) break; - + pm_print_active_wakeup_sources(); schedule(); } finish_wait(&wakeup_count_wait_queue, &wait); diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 04365b17ee67..5497f7fc44d0 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1403,7 +1403,8 @@ static ssize_t hot_remove_store(struct class *class, zram = idr_find(&zram_index_idr, dev_id); if (zram) { ret = zram_remove(zram); - idr_remove(&zram_index_idr, dev_id); + if (!ret) + idr_remove(&zram_index_idr, dev_id); } else { ret = -ENODEV; } @@ -1412,8 +1413,14 @@ static ssize_t hot_remove_store(struct class *class, return ret ? ret : count; } +/* + * NOTE: hot_add attribute is not the usual read-only sysfs attribute. In a + * sense that reading from this file does alter the state of your system -- it + * creates a new un-initialized zram device and returns back this device's + * device_id (or an error code if it fails to create a new device). + */ static struct class_attribute zram_control_class_attrs[] = { - __ATTR_RO(hot_add), + __ATTR(hot_add, 0400, hot_add_show, NULL), __ATTR_WO(hot_remove), __ATTR_NULL, }; diff --git a/drivers/clk/bcm/Kconfig b/drivers/clk/bcm/Kconfig index f21e9b7afd1a..e3eed5a78404 100644 --- a/drivers/clk/bcm/Kconfig +++ b/drivers/clk/bcm/Kconfig @@ -20,7 +20,7 @@ config CLK_BCM_KONA config COMMON_CLK_IPROC bool "Broadcom iProc clock support" - depends on ARCH_BCM_IPROC || COMPILE_TEST + depends on ARCH_BCM_IPROC || ARCH_BCM_63XX || COMPILE_TEST depends on COMMON_CLK default ARCH_BCM_IPROC help diff --git a/drivers/clk/berlin/bg2.c b/drivers/clk/berlin/bg2.c index edf3b96b3b73..1d99292e2039 100644 --- a/drivers/clk/berlin/bg2.c +++ b/drivers/clk/berlin/bg2.c @@ -685,7 +685,7 @@ static void __init berlin2_clock_setup(struct device_node *np) } /* register clk-provider */ - of_clk_add_hw_provider(np, of_clk_hw_onecell_get, &clk_data); + of_clk_add_hw_provider(np, of_clk_hw_onecell_get, clk_data); return; diff --git a/drivers/clk/berlin/bg2q.c b/drivers/clk/berlin/bg2q.c index 0718e831475f..3b784b593afd 100644 --- a/drivers/clk/berlin/bg2q.c +++ b/drivers/clk/berlin/bg2q.c @@ -382,7 +382,7 @@ static void __init berlin2q_clock_setup(struct device_node *np) } /* register clk-provider */ - of_clk_add_hw_provider(np, of_clk_hw_onecell_get, &clk_data); + of_clk_add_hw_provider(np, of_clk_hw_onecell_get, clk_data); return; diff --git a/drivers/clk/clk-efm32gg.c b/drivers/clk/clk-efm32gg.c index 8802a2dd56ac..f674778fb3ac 100644 --- a/drivers/clk/clk-efm32gg.c +++ b/drivers/clk/clk-efm32gg.c @@ -82,6 +82,6 @@ static void __init efm32gg_cmu_init(struct device_node *np) hws[clk_HFPERCLKDAC0] = clk_hw_register_gate(NULL, "HFPERCLK.DAC0", "HFXO", 0, base + CMU_HFPERCLKEN0, 17, 0, NULL); - of_clk_add_hw_provider(np, of_clk_hw_onecell_get, &clk_data); + of_clk_add_hw_provider(np, of_clk_hw_onecell_get, clk_data); } CLK_OF_DECLARE(efm32ggcmu, "efm32gg,cmu", efm32gg_cmu_init); diff --git a/drivers/clk/sunxi-ng/ccu-sun6i-a31.c b/drivers/clk/sunxi-ng/ccu-sun6i-a31.c index 79596463e0d9..fc75a335a7ce 100644 --- a/drivers/clk/sunxi-ng/ccu-sun6i-a31.c +++ b/drivers/clk/sunxi-ng/ccu-sun6i-a31.c @@ -143,7 +143,7 @@ static SUNXI_CCU_NKM_WITH_MUX_GATE_LOCK(pll_mipi_clk, "pll-mipi", 4, 2, /* K */ 0, 4, /* M */ 21, 0, /* mux */ - BIT(31), /* gate */ + BIT(31) | BIT(23) | BIT(22), /* gate */ BIT(28), /* lock */ CLK_SET_RATE_UNGATE); @@ -191,6 +191,8 @@ static struct clk_div_table axi_div_table[] = { static SUNXI_CCU_DIV_TABLE(axi_clk, "axi", "cpu", 0x050, 0, 3, axi_div_table, 0); +#define SUN6I_A31_AHB1_REG 0x054 + static const char * const ahb1_parents[] = { "osc32k", "osc24M", "axi", "pll-periph" }; @@ -1230,6 +1232,16 @@ static void __init sun6i_a31_ccu_setup(struct device_node *node) val &= BIT(16); writel(val, reg + SUN6I_A31_PLL_MIPI_REG); + /* Force AHB1 to PLL6 / 3 */ + val = readl(reg + SUN6I_A31_AHB1_REG); + /* set PLL6 pre-div = 3 */ + val &= ~GENMASK(7, 6); + val |= 0x2 << 6; + /* select PLL6 / pre-div */ + val &= ~GENMASK(13, 12); + val |= 0x3 << 12; + writel(val, reg + SUN6I_A31_AHB1_REG); + sunxi_ccu_probe(node, reg, &sun6i_a31_ccu_desc); ccu_mux_notifier_register(pll_cpu_clk.common.hw.clk, diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-a33.c b/drivers/clk/sunxi-ng/ccu-sun8i-a33.c index 96b40ca57697..9bd1f78a0547 100644 --- a/drivers/clk/sunxi-ng/ccu-sun8i-a33.c +++ b/drivers/clk/sunxi-ng/ccu-sun8i-a33.c @@ -131,7 +131,7 @@ static SUNXI_CCU_NKM_WITH_GATE_LOCK(pll_mipi_clk, "pll-mipi", 8, 4, /* N */ 4, 2, /* K */ 0, 4, /* M */ - BIT(31), /* gate */ + BIT(31) | BIT(23) | BIT(22), /* gate */ BIT(28), /* lock */ CLK_SET_RATE_UNGATE); diff --git a/drivers/clk/sunxi/clk-sunxi.c b/drivers/clk/sunxi/clk-sunxi.c index 838b22aa8b67..f2c9274b8bd5 100644 --- a/drivers/clk/sunxi/clk-sunxi.c +++ b/drivers/clk/sunxi/clk-sunxi.c @@ -373,7 +373,7 @@ static void sun4i_get_apb1_factors(struct factors_request *req) else calcp = 3; - calcm = (req->parent_rate >> calcp) - 1; + calcm = (div >> calcp) - 1; req->rate = (req->parent_rate >> calcp) / (calcm + 1); req->m = calcm; diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index d89b8afe23b6..920c469f3953 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -12,6 +12,27 @@ config ARM_BIG_LITTLE_CPUFREQ help This enables the Generic CPUfreq driver for ARM big.LITTLE platforms. +config ARM_BRCMSTB_AVS_CPUFREQ + tristate "Broadcom STB AVS CPUfreq driver" + depends on ARCH_BRCMSTB || COMPILE_TEST + default y + help + Some Broadcom STB SoCs use a co-processor running proprietary firmware + ("AVS") to handle voltage and frequency scaling. This driver provides + a standard CPUfreq interface to to the firmware. + + Say Y, if you have a Broadcom SoC with AVS support for DFS or DVFS. + +config ARM_BRCMSTB_AVS_CPUFREQ_DEBUG + bool "Broadcom STB AVS CPUfreq driver sysfs debug capability" + depends on ARM_BRCMSTB_AVS_CPUFREQ + help + Enabling this option turns on debug support via sysfs under + /sys/kernel/debug/brcmstb-avs-cpufreq. It is possible to read all and + write some AVS mailbox registers through sysfs entries. + + If in doubt, say N. + config ARM_DT_BL_CPUFREQ tristate "Generic probing via DT for ARM big LITTLE CPUfreq driver" depends on ARM_BIG_LITTLE_CPUFREQ && OF @@ -60,14 +81,6 @@ config ARM_IMX6Q_CPUFREQ If in doubt, say N. -config ARM_INTEGRATOR - tristate "CPUfreq driver for ARM Integrator CPUs" - depends on ARCH_INTEGRATOR - default y - help - This enables the CPUfreq driver for ARM Integrator CPUs. - If in doubt, say Y. - config ARM_KIRKWOOD_CPUFREQ def_bool MACH_KIRKWOOD help diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile index 0a9b6a093646..1e46c3918e7a 100644 --- a/drivers/cpufreq/Makefile +++ b/drivers/cpufreq/Makefile @@ -51,12 +51,12 @@ obj-$(CONFIG_ARM_BIG_LITTLE_CPUFREQ) += arm_big_little.o # LITTLE drivers, so that it is probed last. obj-$(CONFIG_ARM_DT_BL_CPUFREQ) += arm_big_little_dt.o +obj-$(CONFIG_ARM_BRCMSTB_AVS_CPUFREQ) += brcmstb-avs-cpufreq.o obj-$(CONFIG_ARCH_DAVINCI) += davinci-cpufreq.o obj-$(CONFIG_UX500_SOC_DB8500) += dbx500-cpufreq.o obj-$(CONFIG_ARM_EXYNOS5440_CPUFREQ) += exynos5440-cpufreq.o obj-$(CONFIG_ARM_HIGHBANK_CPUFREQ) += highbank-cpufreq.o obj-$(CONFIG_ARM_IMX6Q_CPUFREQ) += imx6q-cpufreq.o -obj-$(CONFIG_ARM_INTEGRATOR) += integrator-cpufreq.o obj-$(CONFIG_ARM_KIRKWOOD_CPUFREQ) += kirkwood-cpufreq.o obj-$(CONFIG_ARM_MT8173_CPUFREQ) += mt8173-cpufreq.o obj-$(CONFIG_ARM_OMAP2PLUS_CPUFREQ) += omap-cpufreq.o diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index 297e9128fe9f..3a98702b7445 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -84,7 +84,6 @@ static inline struct acpi_processor_performance *to_perf_data(struct acpi_cpufre static struct cpufreq_driver acpi_cpufreq_driver; static unsigned int acpi_pstate_strict; -static struct msr __percpu *msrs; static bool boost_state(unsigned int cpu) { @@ -104,11 +103,10 @@ static bool boost_state(unsigned int cpu) return false; } -static void boost_set_msrs(bool enable, const struct cpumask *cpumask) +static int boost_set_msr(bool enable) { - u32 cpu; u32 msr_addr; - u64 msr_mask; + u64 msr_mask, val; switch (boot_cpu_data.x86_vendor) { case X86_VENDOR_INTEL: @@ -120,26 +118,31 @@ static void boost_set_msrs(bool enable, const struct cpumask *cpumask) msr_mask = MSR_K7_HWCR_CPB_DIS; break; default: - return; + return -EINVAL; } - rdmsr_on_cpus(cpumask, msr_addr, msrs); + rdmsrl(msr_addr, val); - for_each_cpu(cpu, cpumask) { - struct msr *reg = per_cpu_ptr(msrs, cpu); - if (enable) - reg->q &= ~msr_mask; - else - reg->q |= msr_mask; - } + if (enable) + val &= ~msr_mask; + else + val |= msr_mask; + + wrmsrl(msr_addr, val); + return 0; +} + +static void boost_set_msr_each(void *p_en) +{ + bool enable = (bool) p_en; - wrmsr_on_cpus(cpumask, msr_addr, msrs); + boost_set_msr(enable); } static int set_boost(int val) { get_online_cpus(); - boost_set_msrs(val, cpu_online_mask); + on_each_cpu(boost_set_msr_each, (void *)(long)val, 1); put_online_cpus(); pr_debug("Core Boosting %sabled.\n", val ? "en" : "dis"); @@ -536,46 +539,24 @@ static void free_acpi_perf_data(void) free_percpu(acpi_perf_data); } -static int boost_notify(struct notifier_block *nb, unsigned long action, - void *hcpu) +static int cpufreq_boost_online(unsigned int cpu) { - unsigned cpu = (long)hcpu; - const struct cpumask *cpumask; - - cpumask = get_cpu_mask(cpu); + /* + * On the CPU_UP path we simply keep the boost-disable flag + * in sync with the current global state. + */ + return boost_set_msr(acpi_cpufreq_driver.boost_enabled); +} +static int cpufreq_boost_down_prep(unsigned int cpu) +{ /* * Clear the boost-disable bit on the CPU_DOWN path so that - * this cpu cannot block the remaining ones from boosting. On - * the CPU_UP path we simply keep the boost-disable flag in - * sync with the current global state. + * this cpu cannot block the remaining ones from boosting. */ - - switch (action) { - case CPU_DOWN_FAILED: - case CPU_DOWN_FAILED_FROZEN: - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - boost_set_msrs(acpi_cpufreq_driver.boost_enabled, cpumask); - break; - - case CPU_DOWN_PREPARE: - case CPU_DOWN_PREPARE_FROZEN: - boost_set_msrs(1, cpumask); - break; - - default: - break; - } - - return NOTIFY_OK; + return boost_set_msr(1); } - -static struct notifier_block boost_nb = { - .notifier_call = boost_notify, -}; - /* * acpi_cpufreq_early_init - initialize ACPI P-States library * @@ -922,37 +903,35 @@ static struct cpufreq_driver acpi_cpufreq_driver = { .attr = acpi_cpufreq_attr, }; +static enum cpuhp_state acpi_cpufreq_online; + static void __init acpi_cpufreq_boost_init(void) { - if (boot_cpu_has(X86_FEATURE_CPB) || boot_cpu_has(X86_FEATURE_IDA)) { - msrs = msrs_alloc(); - - if (!msrs) - return; - - acpi_cpufreq_driver.set_boost = set_boost; - acpi_cpufreq_driver.boost_enabled = boost_state(0); - - cpu_notifier_register_begin(); + int ret; - /* Force all MSRs to the same value */ - boost_set_msrs(acpi_cpufreq_driver.boost_enabled, - cpu_online_mask); + if (!(boot_cpu_has(X86_FEATURE_CPB) || boot_cpu_has(X86_FEATURE_IDA))) + return; - __register_cpu_notifier(&boost_nb); + acpi_cpufreq_driver.set_boost = set_boost; + acpi_cpufreq_driver.boost_enabled = boost_state(0); - cpu_notifier_register_done(); + /* + * This calls the online callback on all online cpu and forces all + * MSRs to the same value. + */ + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "cpufreq/acpi:online", + cpufreq_boost_online, cpufreq_boost_down_prep); + if (ret < 0) { + pr_err("acpi_cpufreq: failed to register hotplug callbacks\n"); + return; } + acpi_cpufreq_online = ret; } static void acpi_cpufreq_boost_exit(void) { - if (msrs) { - unregister_cpu_notifier(&boost_nb); - - msrs_free(msrs); - msrs = NULL; - } + if (acpi_cpufreq_online >= 0) + cpuhp_remove_state_nocalls(acpi_cpufreq_online); } static int __init acpi_cpufreq_init(void) diff --git a/drivers/cpufreq/brcmstb-avs-cpufreq.c b/drivers/cpufreq/brcmstb-avs-cpufreq.c new file mode 100644 index 000000000000..4fda623e55bb --- /dev/null +++ b/drivers/cpufreq/brcmstb-avs-cpufreq.c @@ -0,0 +1,1057 @@ +/* + * CPU frequency scaling for Broadcom SoCs with AVS firmware that + * supports DVS or DVFS + * + * Copyright (c) 2016 Broadcom + * + * 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. + */ + +/* + * "AVS" is the name of a firmware developed at Broadcom. It derives + * its name from the technique called "Adaptive Voltage Scaling". + * Adaptive voltage scaling was the original purpose of this firmware. + * The AVS firmware still supports "AVS mode", where all it does is + * adaptive voltage scaling. However, on some newer Broadcom SoCs, the + * AVS Firmware, despite its unchanged name, also supports DFS mode and + * DVFS mode. + * + * In the context of this document and the related driver, "AVS" by + * itself always means the Broadcom firmware and never refers to the + * technique called "Adaptive Voltage Scaling". + * + * The Broadcom STB AVS CPUfreq driver provides voltage and frequency + * scaling on Broadcom SoCs using AVS firmware with support for DFS and + * DVFS. The AVS firmware is running on its own co-processor. The + * driver supports both uniprocessor (UP) and symmetric multiprocessor + * (SMP) systems which share clock and voltage across all CPUs. + * + * Actual voltage and frequency scaling is done solely by the AVS + * firmware. This driver does not change frequency or voltage itself. + * It provides a standard CPUfreq interface to the rest of the kernel + * and to userland. It interfaces with the AVS firmware to effect the + * requested changes and to report back the current system status in a + * way that is expected by existing tools. + */ + +#include <linux/cpufreq.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/module.h> +#include <linux/of_address.h> +#include <linux/platform_device.h> +#include <linux/semaphore.h> + +#ifdef CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG +#include <linux/ctype.h> +#include <linux/debugfs.h> +#include <linux/slab.h> +#include <linux/uaccess.h> +#endif + +/* Max number of arguments AVS calls take */ +#define AVS_MAX_CMD_ARGS 4 +/* + * This macro is used to generate AVS parameter register offsets. For + * x >= AVS_MAX_CMD_ARGS, it returns 0 to protect against accidental memory + * access outside of the parameter range. (Offset 0 is the first parameter.) + */ +#define AVS_PARAM_MULT(x) ((x) < AVS_MAX_CMD_ARGS ? (x) : 0) + +/* AVS Mailbox Register offsets */ +#define AVS_MBOX_COMMAND 0x00 +#define AVS_MBOX_STATUS 0x04 +#define AVS_MBOX_VOLTAGE0 0x08 +#define AVS_MBOX_TEMP0 0x0c +#define AVS_MBOX_PV0 0x10 +#define AVS_MBOX_MV0 0x14 +#define AVS_MBOX_PARAM(x) (0x18 + AVS_PARAM_MULT(x) * sizeof(u32)) +#define AVS_MBOX_REVISION 0x28 +#define AVS_MBOX_PSTATE 0x2c +#define AVS_MBOX_HEARTBEAT 0x30 +#define AVS_MBOX_MAGIC 0x34 +#define AVS_MBOX_SIGMA_HVT 0x38 +#define AVS_MBOX_SIGMA_SVT 0x3c +#define AVS_MBOX_VOLTAGE1 0x40 +#define AVS_MBOX_TEMP1 0x44 +#define AVS_MBOX_PV1 0x48 +#define AVS_MBOX_MV1 0x4c +#define AVS_MBOX_FREQUENCY 0x50 + +/* AVS Commands */ +#define AVS_CMD_AVAILABLE 0x00 +#define AVS_CMD_DISABLE 0x10 +#define AVS_CMD_ENABLE 0x11 +#define AVS_CMD_S2_ENTER 0x12 +#define AVS_CMD_S2_EXIT 0x13 +#define AVS_CMD_BBM_ENTER 0x14 +#define AVS_CMD_BBM_EXIT 0x15 +#define AVS_CMD_S3_ENTER 0x16 +#define AVS_CMD_S3_EXIT 0x17 +#define AVS_CMD_BALANCE 0x18 +/* PMAP and P-STATE commands */ +#define AVS_CMD_GET_PMAP 0x30 +#define AVS_CMD_SET_PMAP 0x31 +#define AVS_CMD_GET_PSTATE 0x40 +#define AVS_CMD_SET_PSTATE 0x41 + +/* Different modes AVS supports (for GET_PMAP/SET_PMAP) */ +#define AVS_MODE_AVS 0x0 +#define AVS_MODE_DFS 0x1 +#define AVS_MODE_DVS 0x2 +#define AVS_MODE_DVFS 0x3 + +/* + * PMAP parameter p1 + * unused:31-24, mdiv_p0:23-16, unused:15-14, pdiv:13-10 , ndiv_int:9-0 + */ +#define NDIV_INT_SHIFT 0 +#define NDIV_INT_MASK 0x3ff +#define PDIV_SHIFT 10 +#define PDIV_MASK 0xf +#define MDIV_P0_SHIFT 16 +#define MDIV_P0_MASK 0xff +/* + * PMAP parameter p2 + * mdiv_p4:31-24, mdiv_p3:23-16, mdiv_p2:15:8, mdiv_p1:7:0 + */ +#define MDIV_P1_SHIFT 0 +#define MDIV_P1_MASK 0xff +#define MDIV_P2_SHIFT 8 +#define MDIV_P2_MASK 0xff +#define MDIV_P3_SHIFT 16 +#define MDIV_P3_MASK 0xff +#define MDIV_P4_SHIFT 24 +#define MDIV_P4_MASK 0xff + +/* Different P-STATES AVS supports (for GET_PSTATE/SET_PSTATE) */ +#define AVS_PSTATE_P0 0x0 +#define AVS_PSTATE_P1 0x1 +#define AVS_PSTATE_P2 0x2 +#define AVS_PSTATE_P3 0x3 +#define AVS_PSTATE_P4 0x4 +#define AVS_PSTATE_MAX AVS_PSTATE_P4 + +/* CPU L2 Interrupt Controller Registers */ +#define AVS_CPU_L2_SET0 0x04 +#define AVS_CPU_L2_INT_MASK BIT(31) + +/* AVS Command Status Values */ +#define AVS_STATUS_CLEAR 0x00 +/* Command/notification accepted */ +#define AVS_STATUS_SUCCESS 0xf0 +/* Command/notification rejected */ +#define AVS_STATUS_FAILURE 0xff +/* Invalid command/notification (unknown) */ +#define AVS_STATUS_INVALID 0xf1 +/* Non-AVS modes are not supported */ +#define AVS_STATUS_NO_SUPP 0xf2 +/* Cannot set P-State until P-Map supplied */ +#define AVS_STATUS_NO_MAP 0xf3 +/* Cannot change P-Map after initial P-Map set */ +#define AVS_STATUS_MAP_SET 0xf4 +/* Max AVS status; higher numbers are used for debugging */ +#define AVS_STATUS_MAX 0xff + +/* Other AVS related constants */ +#define AVS_LOOP_LIMIT 10000 +#define AVS_TIMEOUT 300 /* in ms; expected completion is < 10ms */ +#define AVS_FIRMWARE_MAGIC 0xa11600d1 + +#define BRCM_AVS_CPUFREQ_PREFIX "brcmstb-avs" +#define BRCM_AVS_CPUFREQ_NAME BRCM_AVS_CPUFREQ_PREFIX "-cpufreq" +#define BRCM_AVS_CPU_DATA "brcm,avs-cpu-data-mem" +#define BRCM_AVS_CPU_INTR "brcm,avs-cpu-l2-intr" +#define BRCM_AVS_HOST_INTR "sw_intr" + +struct pmap { + unsigned int mode; + unsigned int p1; + unsigned int p2; + unsigned int state; +}; + +struct private_data { + void __iomem *base; + void __iomem *avs_intr_base; + struct device *dev; +#ifdef CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG + struct dentry *debugfs; +#endif + struct completion done; + struct semaphore sem; + struct pmap pmap; +}; + +#ifdef CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG + +enum debugfs_format { + DEBUGFS_NORMAL, + DEBUGFS_FLOAT, + DEBUGFS_REV, +}; + +struct debugfs_data { + struct debugfs_entry *entry; + struct private_data *priv; +}; + +struct debugfs_entry { + char *name; + u32 offset; + fmode_t mode; + enum debugfs_format format; +}; + +#define DEBUGFS_ENTRY(name, mode, format) { \ + #name, AVS_MBOX_##name, mode, format \ +} + +/* + * These are used for debugfs only. Otherwise we use AVS_MBOX_PARAM() directly. + */ +#define AVS_MBOX_PARAM1 AVS_MBOX_PARAM(0) +#define AVS_MBOX_PARAM2 AVS_MBOX_PARAM(1) +#define AVS_MBOX_PARAM3 AVS_MBOX_PARAM(2) +#define AVS_MBOX_PARAM4 AVS_MBOX_PARAM(3) + +/* + * This table stores the name, access permissions and offset for each hardware + * register and is used to generate debugfs entries. + */ +static struct debugfs_entry debugfs_entries[] = { + DEBUGFS_ENTRY(COMMAND, S_IWUSR, DEBUGFS_NORMAL), + DEBUGFS_ENTRY(STATUS, S_IWUSR, DEBUGFS_NORMAL), + DEBUGFS_ENTRY(VOLTAGE0, 0, DEBUGFS_FLOAT), + DEBUGFS_ENTRY(TEMP0, 0, DEBUGFS_FLOAT), + DEBUGFS_ENTRY(PV0, 0, DEBUGFS_FLOAT), + DEBUGFS_ENTRY(MV0, 0, DEBUGFS_FLOAT), + DEBUGFS_ENTRY(PARAM1, S_IWUSR, DEBUGFS_NORMAL), + DEBUGFS_ENTRY(PARAM2, S_IWUSR, DEBUGFS_NORMAL), + DEBUGFS_ENTRY(PARAM3, S_IWUSR, DEBUGFS_NORMAL), + DEBUGFS_ENTRY(PARAM4, S_IWUSR, DEBUGFS_NORMAL), + DEBUGFS_ENTRY(REVISION, 0, DEBUGFS_REV), + DEBUGFS_ENTRY(PSTATE, 0, DEBUGFS_NORMAL), + DEBUGFS_ENTRY(HEARTBEAT, 0, DEBUGFS_NORMAL), + DEBUGFS_ENTRY(MAGIC, S_IWUSR, DEBUGFS_NORMAL), + DEBUGFS_ENTRY(SIGMA_HVT, 0, DEBUGFS_NORMAL), + DEBUGFS_ENTRY(SIGMA_SVT, 0, DEBUGFS_NORMAL), + DEBUGFS_ENTRY(VOLTAGE1, 0, DEBUGFS_FLOAT), + DEBUGFS_ENTRY(TEMP1, 0, DEBUGFS_FLOAT), + DEBUGFS_ENTRY(PV1, 0, DEBUGFS_FLOAT), + DEBUGFS_ENTRY(MV1, 0, DEBUGFS_FLOAT), + DEBUGFS_ENTRY(FREQUENCY, 0, DEBUGFS_NORMAL), +}; + +static int brcm_avs_target_index(struct cpufreq_policy *, unsigned int); + +static char *__strtolower(char *s) +{ + char *p; + + for (p = s; *p; p++) + *p = tolower(*p); + + return s; +} + +#endif /* CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG */ + +static void __iomem *__map_region(const char *name) +{ + struct device_node *np; + void __iomem *ptr; + + np = of_find_compatible_node(NULL, NULL, name); + if (!np) + return NULL; + + ptr = of_iomap(np, 0); + of_node_put(np); + + return ptr; +} + +static int __issue_avs_command(struct private_data *priv, int cmd, bool is_send, + u32 args[]) +{ + unsigned long time_left = msecs_to_jiffies(AVS_TIMEOUT); + void __iomem *base = priv->base; + unsigned int i; + int ret; + u32 val; + + ret = down_interruptible(&priv->sem); + if (ret) + return ret; + + /* + * Make sure no other command is currently running: cmd is 0 if AVS + * co-processor is idle. Due to the guard above, we should almost never + * have to wait here. + */ + for (i = 0, val = 1; val != 0 && i < AVS_LOOP_LIMIT; i++) + val = readl(base + AVS_MBOX_COMMAND); + + /* Give the caller a chance to retry if AVS is busy. */ + if (i == AVS_LOOP_LIMIT) { + ret = -EAGAIN; + goto out; + } + + /* Clear status before we begin. */ + writel(AVS_STATUS_CLEAR, base + AVS_MBOX_STATUS); + + /* We need to send arguments for this command. */ + if (args && is_send) { + for (i = 0; i < AVS_MAX_CMD_ARGS; i++) + writel(args[i], base + AVS_MBOX_PARAM(i)); + } + + /* Protect from spurious interrupts. */ + reinit_completion(&priv->done); + + /* Now issue the command & tell firmware to wake up to process it. */ + writel(cmd, base + AVS_MBOX_COMMAND); + writel(AVS_CPU_L2_INT_MASK, priv->avs_intr_base + AVS_CPU_L2_SET0); + + /* Wait for AVS co-processor to finish processing the command. */ + time_left = wait_for_completion_timeout(&priv->done, time_left); + + /* + * If the AVS status is not in the expected range, it means AVS didn't + * complete our command in time, and we return an error. Also, if there + * is no "time left", we timed out waiting for the interrupt. + */ + val = readl(base + AVS_MBOX_STATUS); + if (time_left == 0 || val == 0 || val > AVS_STATUS_MAX) { + dev_err(priv->dev, "AVS command %#x didn't complete in time\n", + cmd); + dev_err(priv->dev, " Time left: %u ms, AVS status: %#x\n", + jiffies_to_msecs(time_left), val); + ret = -ETIMEDOUT; + goto out; + } + + /* This command returned arguments, so we read them back. */ + if (args && !is_send) { + for (i = 0; i < AVS_MAX_CMD_ARGS; i++) + args[i] = readl(base + AVS_MBOX_PARAM(i)); + } + + /* Clear status to tell AVS co-processor we are done. */ + writel(AVS_STATUS_CLEAR, base + AVS_MBOX_STATUS); + + /* Convert firmware errors to errno's as much as possible. */ + switch (val) { + case AVS_STATUS_INVALID: + ret = -EINVAL; + break; + case AVS_STATUS_NO_SUPP: + ret = -ENOTSUPP; + break; + case AVS_STATUS_NO_MAP: + ret = -ENOENT; + break; + case AVS_STATUS_MAP_SET: + ret = -EEXIST; + break; + case AVS_STATUS_FAILURE: + ret = -EIO; + break; + } + +out: + up(&priv->sem); + + return ret; +} + +static irqreturn_t irq_handler(int irq, void *data) +{ + struct private_data *priv = data; + + /* AVS command completed execution. Wake up __issue_avs_command(). */ + complete(&priv->done); + + return IRQ_HANDLED; +} + +static char *brcm_avs_mode_to_string(unsigned int mode) +{ + switch (mode) { + case AVS_MODE_AVS: + return "AVS"; + case AVS_MODE_DFS: + return "DFS"; + case AVS_MODE_DVS: + return "DVS"; + case AVS_MODE_DVFS: + return "DVFS"; + } + return NULL; +} + +static void brcm_avs_parse_p1(u32 p1, unsigned int *mdiv_p0, unsigned int *pdiv, + unsigned int *ndiv) +{ + *mdiv_p0 = (p1 >> MDIV_P0_SHIFT) & MDIV_P0_MASK; + *pdiv = (p1 >> PDIV_SHIFT) & PDIV_MASK; + *ndiv = (p1 >> NDIV_INT_SHIFT) & NDIV_INT_MASK; +} + +static void brcm_avs_parse_p2(u32 p2, unsigned int *mdiv_p1, + unsigned int *mdiv_p2, unsigned int *mdiv_p3, + unsigned int *mdiv_p4) +{ + *mdiv_p4 = (p2 >> MDIV_P4_SHIFT) & MDIV_P4_MASK; + *mdiv_p3 = (p2 >> MDIV_P3_SHIFT) & MDIV_P3_MASK; + *mdiv_p2 = (p2 >> MDIV_P2_SHIFT) & MDIV_P2_MASK; + *mdiv_p1 = (p2 >> MDIV_P1_SHIFT) & MDIV_P1_MASK; +} + +static int brcm_avs_get_pmap(struct private_data *priv, struct pmap *pmap) +{ + u32 args[AVS_MAX_CMD_ARGS]; + int ret; + + ret = __issue_avs_command(priv, AVS_CMD_GET_PMAP, false, args); + if (ret || !pmap) + return ret; + + pmap->mode = args[0]; + pmap->p1 = args[1]; + pmap->p2 = args[2]; + pmap->state = args[3]; + + return 0; +} + +static int brcm_avs_set_pmap(struct private_data *priv, struct pmap *pmap) +{ + u32 args[AVS_MAX_CMD_ARGS]; + + args[0] = pmap->mode; + args[1] = pmap->p1; + args[2] = pmap->p2; + args[3] = pmap->state; + + return __issue_avs_command(priv, AVS_CMD_SET_PMAP, true, args); +} + +static int brcm_avs_get_pstate(struct private_data *priv, unsigned int *pstate) +{ + u32 args[AVS_MAX_CMD_ARGS]; + int ret; + + ret = __issue_avs_command(priv, AVS_CMD_GET_PSTATE, false, args); + if (ret) + return ret; + *pstate = args[0]; + + return 0; +} + +static int brcm_avs_set_pstate(struct private_data *priv, unsigned int pstate) +{ + u32 args[AVS_MAX_CMD_ARGS]; + + args[0] = pstate; + + return __issue_avs_command(priv, AVS_CMD_SET_PSTATE, true, args); +} + +static unsigned long brcm_avs_get_voltage(void __iomem *base) +{ + return readl(base + AVS_MBOX_VOLTAGE1); +} + +static unsigned long brcm_avs_get_frequency(void __iomem *base) +{ + return readl(base + AVS_MBOX_FREQUENCY) * 1000; /* in kHz */ +} + +/* + * We determine which frequencies are supported by cycling through all P-states + * and reading back what frequency we are running at for each P-state. + */ +static struct cpufreq_frequency_table * +brcm_avs_get_freq_table(struct device *dev, struct private_data *priv) +{ + struct cpufreq_frequency_table *table; + unsigned int pstate; + int i, ret; + + /* Remember P-state for later */ + ret = brcm_avs_get_pstate(priv, &pstate); + if (ret) + return ERR_PTR(ret); + + table = devm_kzalloc(dev, (AVS_PSTATE_MAX + 1) * sizeof(*table), + GFP_KERNEL); + if (!table) + return ERR_PTR(-ENOMEM); + + for (i = AVS_PSTATE_P0; i <= AVS_PSTATE_MAX; i++) { + ret = brcm_avs_set_pstate(priv, i); + if (ret) + return ERR_PTR(ret); + table[i].frequency = brcm_avs_get_frequency(priv->base); + table[i].driver_data = i; + } + table[i].frequency = CPUFREQ_TABLE_END; + + /* Restore P-state */ + ret = brcm_avs_set_pstate(priv, pstate); + if (ret) + return ERR_PTR(ret); + + return table; +} + +#ifdef CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG + +#define MANT(x) (unsigned int)(abs((x)) / 1000) +#define FRAC(x) (unsigned int)(abs((x)) - abs((x)) / 1000 * 1000) + +static int brcm_avs_debug_show(struct seq_file *s, void *data) +{ + struct debugfs_data *dbgfs = s->private; + void __iomem *base; + u32 val, offset; + + if (!dbgfs) { + seq_puts(s, "No device pointer\n"); + return 0; + } + + base = dbgfs->priv->base; + offset = dbgfs->entry->offset; + val = readl(base + offset); + switch (dbgfs->entry->format) { + case DEBUGFS_NORMAL: + seq_printf(s, "%u\n", val); + break; + case DEBUGFS_FLOAT: + seq_printf(s, "%d.%03d\n", MANT(val), FRAC(val)); + break; + case DEBUGFS_REV: + seq_printf(s, "%c.%c.%c.%c\n", (val >> 24 & 0xff), + (val >> 16 & 0xff), (val >> 8 & 0xff), + val & 0xff); + break; + } + seq_printf(s, "0x%08x\n", val); + + return 0; +} + +#undef MANT +#undef FRAC + +static ssize_t brcm_avs_seq_write(struct file *file, const char __user *buf, + size_t size, loff_t *ppos) +{ + struct seq_file *s = file->private_data; + struct debugfs_data *dbgfs = s->private; + struct private_data *priv = dbgfs->priv; + void __iomem *base, *avs_intr_base; + bool use_issue_command = false; + unsigned long val, offset; + char str[128]; + int ret; + char *str_ptr = str; + + if (size >= sizeof(str)) + return -E2BIG; + + memset(str, 0, sizeof(str)); + ret = copy_from_user(str, buf, size); + if (ret) + return ret; + + base = priv->base; + avs_intr_base = priv->avs_intr_base; + offset = dbgfs->entry->offset; + /* + * Special case writing to "command" entry only: if the string starts + * with a 'c', we use the driver's __issue_avs_command() function. + * Otherwise, we perform a raw write. This should allow testing of raw + * access as well as using the higher level function. (Raw access + * doesn't clear the firmware return status after issuing the command.) + */ + if (str_ptr[0] == 'c' && offset == AVS_MBOX_COMMAND) { + use_issue_command = true; + str_ptr++; + } + if (kstrtoul(str_ptr, 0, &val) != 0) + return -EINVAL; + + /* + * Setting the P-state is a special case. We need to update the CPU + * frequency we report. + */ + if (val == AVS_CMD_SET_PSTATE) { + struct cpufreq_policy *policy; + unsigned int pstate; + + policy = cpufreq_cpu_get(smp_processor_id()); + /* Read back the P-state we are about to set */ + pstate = readl(base + AVS_MBOX_PARAM(0)); + if (use_issue_command) { + ret = brcm_avs_target_index(policy, pstate); + return ret ? ret : size; + } + policy->cur = policy->freq_table[pstate].frequency; + } + + if (use_issue_command) { + ret = __issue_avs_command(priv, val, false, NULL); + } else { + /* Locking here is not perfect, but is only for debug. */ + ret = down_interruptible(&priv->sem); + if (ret) + return ret; + + writel(val, base + offset); + /* We have to wake up the firmware to process a command. */ + if (offset == AVS_MBOX_COMMAND) + writel(AVS_CPU_L2_INT_MASK, + avs_intr_base + AVS_CPU_L2_SET0); + up(&priv->sem); + } + + return ret ? ret : size; +} + +static struct debugfs_entry *__find_debugfs_entry(const char *name) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(debugfs_entries); i++) + if (strcasecmp(debugfs_entries[i].name, name) == 0) + return &debugfs_entries[i]; + + return NULL; +} + +static int brcm_avs_debug_open(struct inode *inode, struct file *file) +{ + struct debugfs_data *data; + fmode_t fmode; + int ret; + + /* + * seq_open(), which is called by single_open(), clears "write" access. + * We need write access to some files, so we preserve our access mode + * and restore it. + */ + fmode = file->f_mode; + /* + * Check access permissions even for root. We don't want to be writing + * to read-only registers. Access for regular users has already been + * checked by the VFS layer. + */ + if ((fmode & FMODE_WRITER) && !(inode->i_mode & S_IWUSR)) + return -EACCES; + + data = kmalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + /* + * We use the same file system operations for all our debug files. To + * produce specific output, we look up the file name upon opening a + * debugfs entry and map it to a memory offset. This offset is then used + * in the generic "show" function to read a specific register. + */ + data->entry = __find_debugfs_entry(file->f_path.dentry->d_iname); + data->priv = inode->i_private; + + ret = single_open(file, brcm_avs_debug_show, data); + if (ret) + kfree(data); + file->f_mode = fmode; + + return ret; +} + +static int brcm_avs_debug_release(struct inode *inode, struct file *file) +{ + struct seq_file *seq_priv = file->private_data; + struct debugfs_data *data = seq_priv->private; + + kfree(data); + return single_release(inode, file); +} + +static const struct file_operations brcm_avs_debug_ops = { + .open = brcm_avs_debug_open, + .read = seq_read, + .write = brcm_avs_seq_write, + .llseek = seq_lseek, + .release = brcm_avs_debug_release, +}; + +static void brcm_avs_cpufreq_debug_init(struct platform_device *pdev) +{ + struct private_data *priv = platform_get_drvdata(pdev); + struct dentry *dir; + int i; + + if (!priv) + return; + + dir = debugfs_create_dir(BRCM_AVS_CPUFREQ_NAME, NULL); + if (IS_ERR_OR_NULL(dir)) + return; + priv->debugfs = dir; + + for (i = 0; i < ARRAY_SIZE(debugfs_entries); i++) { + /* + * The DEBUGFS_ENTRY macro generates uppercase strings. We + * convert them to lowercase before creating the debugfs + * entries. + */ + char *entry = __strtolower(debugfs_entries[i].name); + fmode_t mode = debugfs_entries[i].mode; + + if (!debugfs_create_file(entry, S_IFREG | S_IRUGO | mode, + dir, priv, &brcm_avs_debug_ops)) { + priv->debugfs = NULL; + debugfs_remove_recursive(dir); + break; + } + } +} + +static void brcm_avs_cpufreq_debug_exit(struct platform_device *pdev) +{ + struct private_data *priv = platform_get_drvdata(pdev); + + if (priv && priv->debugfs) { + debugfs_remove_recursive(priv->debugfs); + priv->debugfs = NULL; + } +} + +#else + +static void brcm_avs_cpufreq_debug_init(struct platform_device *pdev) {} +static void brcm_avs_cpufreq_debug_exit(struct platform_device *pdev) {} + +#endif /* CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG */ + +/* + * To ensure the right firmware is running we need to + * - check the MAGIC matches what we expect + * - brcm_avs_get_pmap() doesn't return -ENOTSUPP or -EINVAL + * We need to set up our interrupt handling before calling brcm_avs_get_pmap()! + */ +static bool brcm_avs_is_firmware_loaded(struct private_data *priv) +{ + u32 magic; + int rc; + + rc = brcm_avs_get_pmap(priv, NULL); + magic = readl(priv->base + AVS_MBOX_MAGIC); + + return (magic == AVS_FIRMWARE_MAGIC) && (rc != -ENOTSUPP) && + (rc != -EINVAL); +} + +static unsigned int brcm_avs_cpufreq_get(unsigned int cpu) +{ + struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); + struct private_data *priv = policy->driver_data; + + return brcm_avs_get_frequency(priv->base); +} + +static int brcm_avs_target_index(struct cpufreq_policy *policy, + unsigned int index) +{ + return brcm_avs_set_pstate(policy->driver_data, + policy->freq_table[index].driver_data); +} + +static int brcm_avs_suspend(struct cpufreq_policy *policy) +{ + struct private_data *priv = policy->driver_data; + + return brcm_avs_get_pmap(priv, &priv->pmap); +} + +static int brcm_avs_resume(struct cpufreq_policy *policy) +{ + struct private_data *priv = policy->driver_data; + int ret; + + ret = brcm_avs_set_pmap(priv, &priv->pmap); + if (ret == -EEXIST) { + struct platform_device *pdev = cpufreq_get_driver_data(); + struct device *dev = &pdev->dev; + + dev_warn(dev, "PMAP was already set\n"); + ret = 0; + } + + return ret; +} + +/* + * All initialization code that we only want to execute once goes here. Setup + * code that can be re-tried on every core (if it failed before) can go into + * brcm_avs_cpufreq_init(). + */ +static int brcm_avs_prepare_init(struct platform_device *pdev) +{ + struct private_data *priv; + struct device *dev; + int host_irq, ret; + + dev = &pdev->dev; + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->dev = dev; + sema_init(&priv->sem, 1); + init_completion(&priv->done); + platform_set_drvdata(pdev, priv); + + priv->base = __map_region(BRCM_AVS_CPU_DATA); + if (!priv->base) { + dev_err(dev, "Couldn't find property %s in device tree.\n", + BRCM_AVS_CPU_DATA); + return -ENOENT; + } + + priv->avs_intr_base = __map_region(BRCM_AVS_CPU_INTR); + if (!priv->avs_intr_base) { + dev_err(dev, "Couldn't find property %s in device tree.\n", + BRCM_AVS_CPU_INTR); + ret = -ENOENT; + goto unmap_base; + } + + host_irq = platform_get_irq_byname(pdev, BRCM_AVS_HOST_INTR); + if (host_irq < 0) { + dev_err(dev, "Couldn't find interrupt %s -- %d\n", + BRCM_AVS_HOST_INTR, host_irq); + ret = host_irq; + goto unmap_intr_base; + } + + ret = devm_request_irq(dev, host_irq, irq_handler, IRQF_TRIGGER_RISING, + BRCM_AVS_HOST_INTR, priv); + if (ret) { + dev_err(dev, "IRQ request failed: %s (%d) -- %d\n", + BRCM_AVS_HOST_INTR, host_irq, ret); + goto unmap_intr_base; + } + + if (brcm_avs_is_firmware_loaded(priv)) + return 0; + + dev_err(dev, "AVS firmware is not loaded or doesn't support DVFS\n"); + ret = -ENODEV; + +unmap_intr_base: + iounmap(priv->avs_intr_base); +unmap_base: + iounmap(priv->base); + platform_set_drvdata(pdev, NULL); + + return ret; +} + +static int brcm_avs_cpufreq_init(struct cpufreq_policy *policy) +{ + struct cpufreq_frequency_table *freq_table; + struct platform_device *pdev; + struct private_data *priv; + struct device *dev; + int ret; + + pdev = cpufreq_get_driver_data(); + priv = platform_get_drvdata(pdev); + policy->driver_data = priv; + dev = &pdev->dev; + + freq_table = brcm_avs_get_freq_table(dev, priv); + if (IS_ERR(freq_table)) { + ret = PTR_ERR(freq_table); + dev_err(dev, "Couldn't determine frequency table (%d).\n", ret); + return ret; + } + + ret = cpufreq_table_validate_and_show(policy, freq_table); + if (ret) { + dev_err(dev, "invalid frequency table: %d\n", ret); + return ret; + } + + /* All cores share the same clock and thus the same policy. */ + cpumask_setall(policy->cpus); + + ret = __issue_avs_command(priv, AVS_CMD_ENABLE, false, NULL); + if (!ret) { + unsigned int pstate; + + ret = brcm_avs_get_pstate(priv, &pstate); + if (!ret) { + policy->cur = freq_table[pstate].frequency; + dev_info(dev, "registered\n"); + return 0; + } + } + + dev_err(dev, "couldn't initialize driver (%d)\n", ret); + + return ret; +} + +static ssize_t show_brcm_avs_pstate(struct cpufreq_policy *policy, char *buf) +{ + struct private_data *priv = policy->driver_data; + unsigned int pstate; + + if (brcm_avs_get_pstate(priv, &pstate)) + return sprintf(buf, "<unknown>\n"); + + return sprintf(buf, "%u\n", pstate); +} + +static ssize_t show_brcm_avs_mode(struct cpufreq_policy *policy, char *buf) +{ + struct private_data *priv = policy->driver_data; + struct pmap pmap; + + if (brcm_avs_get_pmap(priv, &pmap)) + return sprintf(buf, "<unknown>\n"); + + return sprintf(buf, "%s %u\n", brcm_avs_mode_to_string(pmap.mode), + pmap.mode); +} + +static ssize_t show_brcm_avs_pmap(struct cpufreq_policy *policy, char *buf) +{ + unsigned int mdiv_p0, mdiv_p1, mdiv_p2, mdiv_p3, mdiv_p4; + struct private_data *priv = policy->driver_data; + unsigned int ndiv, pdiv; + struct pmap pmap; + + if (brcm_avs_get_pmap(priv, &pmap)) + return sprintf(buf, "<unknown>\n"); + + brcm_avs_parse_p1(pmap.p1, &mdiv_p0, &pdiv, &ndiv); + brcm_avs_parse_p2(pmap.p2, &mdiv_p1, &mdiv_p2, &mdiv_p3, &mdiv_p4); + + return sprintf(buf, "0x%08x 0x%08x %u %u %u %u %u %u %u\n", + pmap.p1, pmap.p2, ndiv, pdiv, mdiv_p0, mdiv_p1, mdiv_p2, + mdiv_p3, mdiv_p4); +} + +static ssize_t show_brcm_avs_voltage(struct cpufreq_policy *policy, char *buf) +{ + struct private_data *priv = policy->driver_data; + + return sprintf(buf, "0x%08lx\n", brcm_avs_get_voltage(priv->base)); +} + +static ssize_t show_brcm_avs_frequency(struct cpufreq_policy *policy, char *buf) +{ + struct private_data *priv = policy->driver_data; + + return sprintf(buf, "0x%08lx\n", brcm_avs_get_frequency(priv->base)); +} + +cpufreq_freq_attr_ro(brcm_avs_pstate); +cpufreq_freq_attr_ro(brcm_avs_mode); +cpufreq_freq_attr_ro(brcm_avs_pmap); +cpufreq_freq_attr_ro(brcm_avs_voltage); +cpufreq_freq_attr_ro(brcm_avs_frequency); + +static struct freq_attr *brcm_avs_cpufreq_attr[] = { + &cpufreq_freq_attr_scaling_available_freqs, + &brcm_avs_pstate, + &brcm_avs_mode, + &brcm_avs_pmap, + &brcm_avs_voltage, + &brcm_avs_frequency, + NULL +}; + +static struct cpufreq_driver brcm_avs_driver = { + .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK, + .verify = cpufreq_generic_frequency_table_verify, + .target_index = brcm_avs_target_index, + .get = brcm_avs_cpufreq_get, + .suspend = brcm_avs_suspend, + .resume = brcm_avs_resume, + .init = brcm_avs_cpufreq_init, + .attr = brcm_avs_cpufreq_attr, + .name = BRCM_AVS_CPUFREQ_PREFIX, +}; + +static int brcm_avs_cpufreq_probe(struct platform_device *pdev) +{ + int ret; + + ret = brcm_avs_prepare_init(pdev); + if (ret) + return ret; + + brcm_avs_driver.driver_data = pdev; + ret = cpufreq_register_driver(&brcm_avs_driver); + if (!ret) + brcm_avs_cpufreq_debug_init(pdev); + + return ret; +} + +static int brcm_avs_cpufreq_remove(struct platform_device *pdev) +{ + struct private_data *priv; + int ret; + + ret = cpufreq_unregister_driver(&brcm_avs_driver); + if (ret) + return ret; + + brcm_avs_cpufreq_debug_exit(pdev); + + priv = platform_get_drvdata(pdev); + iounmap(priv->base); + iounmap(priv->avs_intr_base); + platform_set_drvdata(pdev, NULL); + + return 0; +} + +static const struct of_device_id brcm_avs_cpufreq_match[] = { + { .compatible = BRCM_AVS_CPU_DATA }, + { } +}; +MODULE_DEVICE_TABLE(of, brcm_avs_cpufreq_match); + +static struct platform_driver brcm_avs_cpufreq_platdrv = { + .driver = { + .name = BRCM_AVS_CPUFREQ_NAME, + .of_match_table = brcm_avs_cpufreq_match, + }, + .probe = brcm_avs_cpufreq_probe, + .remove = brcm_avs_cpufreq_remove, +}; +module_platform_driver(brcm_avs_cpufreq_platdrv); + +MODULE_AUTHOR("Markus Mayer <mmayer@broadcom.com>"); +MODULE_DESCRIPTION("CPUfreq driver for Broadcom STB AVS"); +MODULE_LICENSE("GPL"); diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c index 4852d9efe74e..e82bb3c30b92 100644 --- a/drivers/cpufreq/cppc_cpufreq.c +++ b/drivers/cpufreq/cppc_cpufreq.c @@ -247,3 +247,10 @@ MODULE_DESCRIPTION("CPUFreq driver based on the ACPI CPPC v5.0+ spec"); MODULE_LICENSE("GPL"); late_initcall(cppc_cpufreq_init); + +static const struct acpi_device_id cppc_acpi_ids[] = { + {ACPI_PROCESSOR_DEVICE_HID, }, + {} +}; + +MODULE_DEVICE_TABLE(acpi, cppc_acpi_ids); diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c index 71267626456b..bc97b6a4b1cf 100644 --- a/drivers/cpufreq/cpufreq-dt-platdev.c +++ b/drivers/cpufreq/cpufreq-dt-platdev.c @@ -26,6 +26,9 @@ static const struct of_device_id machines[] __initconst = { { .compatible = "allwinner,sun8i-a83t", }, { .compatible = "allwinner,sun8i-h3", }, + { .compatible = "arm,integrator-ap", }, + { .compatible = "arm,integrator-cp", }, + { .compatible = "hisilicon,hi6220", }, { .compatible = "fsl,imx27", }, @@ -34,6 +37,8 @@ static const struct of_device_id machines[] __initconst = { { .compatible = "fsl,imx7d", }, { .compatible = "marvell,berlin", }, + { .compatible = "marvell,pxa250", }, + { .compatible = "marvell,pxa270", }, { .compatible = "samsung,exynos3250", }, { .compatible = "samsung,exynos4210", }, @@ -50,6 +55,8 @@ static const struct of_device_id machines[] __initconst = { { .compatible = "renesas,r7s72100", }, { .compatible = "renesas,r8a73a4", }, { .compatible = "renesas,r8a7740", }, + { .compatible = "renesas,r8a7743", }, + { .compatible = "renesas,r8a7745", }, { .compatible = "renesas,r8a7778", }, { .compatible = "renesas,r8a7779", }, { .compatible = "renesas,r8a7790", }, @@ -72,6 +79,12 @@ static const struct of_device_id machines[] __initconst = { { .compatible = "sigma,tango4" }, + { .compatible = "socionext,uniphier-pro5", }, + { .compatible = "socionext,uniphier-pxs2", }, + { .compatible = "socionext,uniphier-ld6b", }, + { .compatible = "socionext,uniphier-ld11", }, + { .compatible = "socionext,uniphier-ld20", }, + { .compatible = "ti,am33xx", }, { .compatible = "ti,dra7", }, { .compatible = "ti,omap2", }, @@ -81,6 +94,8 @@ static const struct of_device_id machines[] __initconst = { { .compatible = "xlnx,zynq-7000", }, + { .compatible = "zte,zx296718", }, + { } }; diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c index 5c07ae05d69a..269013311e79 100644 --- a/drivers/cpufreq/cpufreq-dt.c +++ b/drivers/cpufreq/cpufreq-dt.c @@ -28,6 +28,7 @@ #include "cpufreq-dt.h" struct private_data { + struct opp_table *opp_table; struct device *cpu_dev; struct thermal_cooling_device *cdev; const char *reg_name; @@ -143,6 +144,7 @@ static int resources_available(void) static int cpufreq_init(struct cpufreq_policy *policy) { struct cpufreq_frequency_table *freq_table; + struct opp_table *opp_table = NULL; struct private_data *priv; struct device *cpu_dev; struct clk *cpu_clk; @@ -186,8 +188,9 @@ static int cpufreq_init(struct cpufreq_policy *policy) */ name = find_supply_name(cpu_dev); if (name) { - ret = dev_pm_opp_set_regulator(cpu_dev, name); - if (ret) { + opp_table = dev_pm_opp_set_regulators(cpu_dev, &name, 1); + if (IS_ERR(opp_table)) { + ret = PTR_ERR(opp_table); dev_err(cpu_dev, "Failed to set regulator for cpu%d: %d\n", policy->cpu, ret); goto out_put_clk; @@ -237,6 +240,7 @@ static int cpufreq_init(struct cpufreq_policy *policy) } priv->reg_name = name; + priv->opp_table = opp_table; ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table); if (ret) { @@ -285,7 +289,7 @@ out_free_priv: out_free_opp: dev_pm_opp_of_cpumask_remove_table(policy->cpus); if (name) - dev_pm_opp_put_regulator(cpu_dev); + dev_pm_opp_put_regulators(opp_table); out_put_clk: clk_put(cpu_clk); @@ -300,7 +304,7 @@ static int cpufreq_exit(struct cpufreq_policy *policy) dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table); dev_pm_opp_of_cpumask_remove_table(policy->related_cpus); if (priv->reg_name) - dev_pm_opp_put_regulator(priv->cpu_dev); + dev_pm_opp_put_regulators(priv->opp_table); clk_put(policy->clk); kfree(priv); diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 6e6c1fb60fbc..cc475eff90b3 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1526,7 +1526,10 @@ unsigned int cpufreq_get(unsigned int cpu) if (policy) { down_read(&policy->rwsem); - ret_freq = __cpufreq_get(policy); + + if (!policy_is_inactive(policy)) + ret_freq = __cpufreq_get(policy); + up_read(&policy->rwsem); cpufreq_cpu_put(policy); @@ -2254,17 +2257,19 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy, * Useful for policy notifiers which have different necessities * at different times. */ -int cpufreq_update_policy(unsigned int cpu) +void cpufreq_update_policy(unsigned int cpu) { struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); struct cpufreq_policy new_policy; - int ret; if (!policy) - return -ENODEV; + return; down_write(&policy->rwsem); + 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; @@ -2275,24 +2280,20 @@ int cpufreq_update_policy(unsigned int cpu) * -> ask driver for current freq and notify governors about a change */ if (cpufreq_driver->get && !cpufreq_driver->setpolicy) { - if (cpufreq_suspended) { - ret = -EAGAIN; + if (cpufreq_suspended) goto unlock; - } + new_policy.cur = cpufreq_update_current_freq(policy); - if (WARN_ON(!new_policy.cur)) { - ret = -EIO; + if (WARN_ON(!new_policy.cur)) goto unlock; - } } - ret = cpufreq_set_policy(policy, &new_policy); + cpufreq_set_policy(policy, &new_policy); unlock: up_write(&policy->rwsem); cpufreq_cpu_put(policy); - return ret; } EXPORT_SYMBOL(cpufreq_update_policy); diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c index 13475890d792..992f7c20760f 100644 --- a/drivers/cpufreq/cpufreq_conservative.c +++ b/drivers/cpufreq/cpufreq_conservative.c @@ -37,16 +37,16 @@ struct cs_dbs_tuners { #define DEF_SAMPLING_DOWN_FACTOR (1) #define MAX_SAMPLING_DOWN_FACTOR (10) -static inline unsigned int get_freq_target(struct cs_dbs_tuners *cs_tuners, - struct cpufreq_policy *policy) +static inline unsigned int get_freq_step(struct cs_dbs_tuners *cs_tuners, + struct cpufreq_policy *policy) { - unsigned int freq_target = (cs_tuners->freq_step * policy->max) / 100; + unsigned int freq_step = (cs_tuners->freq_step * policy->max) / 100; /* max freq cannot be less than 100. But who knows... */ - if (unlikely(freq_target == 0)) - freq_target = DEF_FREQUENCY_STEP; + if (unlikely(freq_step == 0)) + freq_step = DEF_FREQUENCY_STEP; - return freq_target; + return freq_step; } /* @@ -55,10 +55,10 @@ static inline unsigned int get_freq_target(struct cs_dbs_tuners *cs_tuners, * sampling_down_factor, we check, if current idle time is more than 80% * (default), then we try to decrease frequency * - * Any frequency increase takes it to the maximum frequency. Frequency reduction - * happens at minimum steps of 5% (default) of maximum frequency + * Frequency updates happen at minimum steps of 5% (default) of maximum + * frequency */ -static unsigned int cs_dbs_timer(struct cpufreq_policy *policy) +static unsigned int cs_dbs_update(struct cpufreq_policy *policy) { struct policy_dbs_info *policy_dbs = policy->governor_data; struct cs_policy_dbs_info *dbs_info = to_dbs_info(policy_dbs); @@ -66,6 +66,7 @@ static unsigned int cs_dbs_timer(struct cpufreq_policy *policy) struct dbs_data *dbs_data = policy_dbs->dbs_data; struct cs_dbs_tuners *cs_tuners = dbs_data->tuners; unsigned int load = dbs_update(policy); + unsigned int freq_step; /* * break out if we 'cannot' reduce the speed as the user might @@ -82,6 +83,23 @@ static unsigned int cs_dbs_timer(struct cpufreq_policy *policy) if (requested_freq > policy->max || requested_freq < policy->min) requested_freq = policy->cur; + freq_step = get_freq_step(cs_tuners, policy); + + /* + * Decrease requested_freq one freq_step for each idle period that + * we didn't update the frequency. + */ + if (policy_dbs->idle_periods < UINT_MAX) { + unsigned int freq_steps = policy_dbs->idle_periods * freq_step; + + if (requested_freq > freq_steps) + requested_freq -= freq_steps; + else + requested_freq = policy->min; + + policy_dbs->idle_periods = UINT_MAX; + } + /* Check for frequency increase */ if (load > dbs_data->up_threshold) { dbs_info->down_skip = 0; @@ -90,7 +108,7 @@ static unsigned int cs_dbs_timer(struct cpufreq_policy *policy) if (requested_freq == policy->max) goto out; - requested_freq += get_freq_target(cs_tuners, policy); + requested_freq += freq_step; if (requested_freq > policy->max) requested_freq = policy->max; @@ -106,16 +124,14 @@ static unsigned int cs_dbs_timer(struct cpufreq_policy *policy) /* Check for frequency decrease */ if (load < cs_tuners->down_threshold) { - unsigned int freq_target; /* * if we cannot reduce the frequency anymore, break out early */ if (requested_freq == policy->min) goto out; - freq_target = get_freq_target(cs_tuners, policy); - if (requested_freq > freq_target) - requested_freq -= freq_target; + if (requested_freq > freq_step) + requested_freq -= freq_step; else requested_freq = policy->min; @@ -305,7 +321,7 @@ static void cs_start(struct cpufreq_policy *policy) static struct dbs_governor cs_governor = { .gov = CPUFREQ_DBS_GOVERNOR_INITIALIZER("conservative"), .kobj_type = { .default_attrs = cs_attributes }, - .gov_dbs_timer = cs_dbs_timer, + .gov_dbs_update = cs_dbs_update, .alloc = cs_alloc, .free = cs_free, .init = cs_init, diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c index 642dd0f183a8..0196467280bd 100644 --- a/drivers/cpufreq/cpufreq_governor.c +++ b/drivers/cpufreq/cpufreq_governor.c @@ -61,7 +61,7 @@ ssize_t store_sampling_rate(struct gov_attr_set *attr_set, const char *buf, * entries can't be freed concurrently. */ list_for_each_entry(policy_dbs, &attr_set->policy_list, list) { - mutex_lock(&policy_dbs->timer_mutex); + mutex_lock(&policy_dbs->update_mutex); /* * On 32-bit architectures this may race with the * sample_delay_ns read in dbs_update_util_handler(), but that @@ -76,7 +76,7 @@ ssize_t store_sampling_rate(struct gov_attr_set *attr_set, const char *buf, * taken, so it shouldn't be significant. */ gov_update_sample_delay(policy_dbs, 0); - mutex_unlock(&policy_dbs->timer_mutex); + mutex_unlock(&policy_dbs->update_mutex); } return count; @@ -117,7 +117,7 @@ unsigned int dbs_update(struct cpufreq_policy *policy) struct policy_dbs_info *policy_dbs = policy->governor_data; struct dbs_data *dbs_data = policy_dbs->dbs_data; unsigned int ignore_nice = dbs_data->ignore_nice_load; - unsigned int max_load = 0; + unsigned int max_load = 0, idle_periods = UINT_MAX; unsigned int sampling_rate, io_busy, j; /* @@ -215,9 +215,19 @@ unsigned int dbs_update(struct cpufreq_policy *policy) j_cdbs->prev_load = load; } + if (time_elapsed > 2 * sampling_rate) { + unsigned int periods = time_elapsed / sampling_rate; + + if (periods < idle_periods) + idle_periods = periods; + } + if (load > max_load) max_load = load; } + + policy_dbs->idle_periods = idle_periods; + return max_load; } EXPORT_SYMBOL_GPL(dbs_update); @@ -236,9 +246,9 @@ static void dbs_work_handler(struct work_struct *work) * Make sure cpufreq_governor_limits() isn't evaluating load or the * ondemand governor isn't updating the sampling rate in parallel. */ - mutex_lock(&policy_dbs->timer_mutex); - gov_update_sample_delay(policy_dbs, gov->gov_dbs_timer(policy)); - mutex_unlock(&policy_dbs->timer_mutex); + mutex_lock(&policy_dbs->update_mutex); + gov_update_sample_delay(policy_dbs, gov->gov_dbs_update(policy)); + mutex_unlock(&policy_dbs->update_mutex); /* Allow the utilization update handler to queue up more work. */ atomic_set(&policy_dbs->work_count, 0); @@ -348,7 +358,7 @@ static struct policy_dbs_info *alloc_policy_dbs_info(struct cpufreq_policy *poli return NULL; policy_dbs->policy = policy; - mutex_init(&policy_dbs->timer_mutex); + mutex_init(&policy_dbs->update_mutex); atomic_set(&policy_dbs->work_count, 0); init_irq_work(&policy_dbs->irq_work, dbs_irq_work); INIT_WORK(&policy_dbs->work, dbs_work_handler); @@ -367,7 +377,7 @@ static void free_policy_dbs_info(struct policy_dbs_info *policy_dbs, { int j; - mutex_destroy(&policy_dbs->timer_mutex); + mutex_destroy(&policy_dbs->update_mutex); for_each_cpu(j, policy_dbs->policy->related_cpus) { struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j); @@ -547,10 +557,10 @@ void cpufreq_dbs_governor_limits(struct cpufreq_policy *policy) { struct policy_dbs_info *policy_dbs = policy->governor_data; - mutex_lock(&policy_dbs->timer_mutex); + mutex_lock(&policy_dbs->update_mutex); cpufreq_policy_apply_limits(policy); gov_update_sample_delay(policy_dbs, 0); - mutex_unlock(&policy_dbs->timer_mutex); + mutex_unlock(&policy_dbs->update_mutex); } EXPORT_SYMBOL_GPL(cpufreq_dbs_governor_limits); diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h index ef1037e9c92b..f5717ca070cc 100644 --- a/drivers/cpufreq/cpufreq_governor.h +++ b/drivers/cpufreq/cpufreq_governor.h @@ -85,7 +85,7 @@ struct policy_dbs_info { * Per policy mutex that serializes load evaluation from limit-change * and work-handler. */ - struct mutex timer_mutex; + struct mutex update_mutex; u64 last_sample_time; s64 sample_delay_ns; @@ -97,6 +97,7 @@ struct policy_dbs_info { struct list_head list; /* Multiplier for increasing sample delay temporarily. */ unsigned int rate_mult; + unsigned int idle_periods; /* For conservative */ /* Status indicators */ bool is_shared; /* This object is used by multiple CPUs */ bool work_in_progress; /* Work is being queued up or in progress */ @@ -135,7 +136,7 @@ struct dbs_governor { */ struct dbs_data *gdbs_data; - unsigned int (*gov_dbs_timer)(struct cpufreq_policy *policy); + unsigned int (*gov_dbs_update)(struct cpufreq_policy *policy); struct policy_dbs_info *(*alloc)(void); void (*free)(struct policy_dbs_info *policy_dbs); int (*init)(struct dbs_data *dbs_data); diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c index 3a1f49f5f4c6..4a017e895296 100644 --- a/drivers/cpufreq/cpufreq_ondemand.c +++ b/drivers/cpufreq/cpufreq_ondemand.c @@ -25,7 +25,7 @@ #define MAX_SAMPLING_DOWN_FACTOR (100000) #define MICRO_FREQUENCY_UP_THRESHOLD (95) #define MICRO_FREQUENCY_MIN_SAMPLE_RATE (10000) -#define MIN_FREQUENCY_UP_THRESHOLD (11) +#define MIN_FREQUENCY_UP_THRESHOLD (1) #define MAX_FREQUENCY_UP_THRESHOLD (100) static struct od_ops od_ops; @@ -169,7 +169,7 @@ static void od_update(struct cpufreq_policy *policy) } } -static unsigned int od_dbs_timer(struct cpufreq_policy *policy) +static unsigned int od_dbs_update(struct cpufreq_policy *policy) { struct policy_dbs_info *policy_dbs = policy->governor_data; struct dbs_data *dbs_data = policy_dbs->dbs_data; @@ -191,7 +191,7 @@ static unsigned int od_dbs_timer(struct cpufreq_policy *policy) od_update(policy); if (dbs_info->freq_lo) { - /* Setup timer for SUB_SAMPLE */ + /* Setup SUB_SAMPLE */ dbs_info->sample_type = OD_SUB_SAMPLE; return dbs_info->freq_hi_delay_us; } @@ -255,11 +255,11 @@ static ssize_t store_sampling_down_factor(struct gov_attr_set *attr_set, list_for_each_entry(policy_dbs, &attr_set->policy_list, list) { /* * Doing this without locking might lead to using different - * rate_mult values in od_update() and od_dbs_timer(). + * rate_mult values in od_update() and od_dbs_update(). */ - mutex_lock(&policy_dbs->timer_mutex); + mutex_lock(&policy_dbs->update_mutex); policy_dbs->rate_mult = 1; - mutex_unlock(&policy_dbs->timer_mutex); + mutex_unlock(&policy_dbs->update_mutex); } return count; @@ -374,8 +374,7 @@ static int od_init(struct dbs_data *dbs_data) dbs_data->up_threshold = MICRO_FREQUENCY_UP_THRESHOLD; /* * In nohz/micro accounting case we set the minimum frequency - * not depending on HZ, but fixed (very low). The deferred - * timer might skip some samples if idle/sleeping as needed. + * not depending on HZ, but fixed (very low). */ dbs_data->min_sampling_rate = MICRO_FREQUENCY_MIN_SAMPLE_RATE; } else { @@ -415,7 +414,7 @@ static struct od_ops od_ops = { static struct dbs_governor od_dbs_gov = { .gov = CPUFREQ_DBS_GOVERNOR_INITIALIZER("ondemand"), .kobj_type = { .default_attrs = od_attributes }, - .gov_dbs_timer = od_dbs_timer, + .gov_dbs_update = od_dbs_update, .alloc = od_alloc, .free = od_free, .init = od_init, diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c index 06d3abdffd3a..ac284e66839c 100644 --- a/drivers/cpufreq/cpufreq_stats.c +++ b/drivers/cpufreq/cpufreq_stats.c @@ -41,6 +41,18 @@ static int cpufreq_stats_update(struct cpufreq_stats *stats) return 0; } +static void cpufreq_stats_clear_table(struct cpufreq_stats *stats) +{ + unsigned int count = stats->max_state; + + memset(stats->time_in_state, 0, count * sizeof(u64)); +#ifdef CONFIG_CPU_FREQ_STAT_DETAILS + memset(stats->trans_table, 0, count * count * sizeof(int)); +#endif + stats->last_time = get_jiffies_64(); + stats->total_trans = 0; +} + static ssize_t show_total_trans(struct cpufreq_policy *policy, char *buf) { return sprintf(buf, "%d\n", policy->stats->total_trans); @@ -64,6 +76,14 @@ static ssize_t show_time_in_state(struct cpufreq_policy *policy, char *buf) return len; } +static ssize_t store_reset(struct cpufreq_policy *policy, const char *buf, + size_t count) +{ + /* We don't care what is written to the attribute. */ + cpufreq_stats_clear_table(policy->stats); + return count; +} + #ifdef CONFIG_CPU_FREQ_STAT_DETAILS static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf) { @@ -113,10 +133,12 @@ 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, + &reset.attr, #ifdef CONFIG_CPU_FREQ_STAT_DETAILS &trans_table.attr, #endif diff --git a/drivers/cpufreq/integrator-cpufreq.c b/drivers/cpufreq/integrator-cpufreq.c deleted file mode 100644 index 79e3ff2771a6..000000000000 --- a/drivers/cpufreq/integrator-cpufreq.c +++ /dev/null @@ -1,239 +0,0 @@ -/* - * Copyright (C) 2001-2002 Deep Blue Solutions Ltd. - * - * 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 - * published by the Free Software Foundation. - * - * CPU support functions - */ -#include <linux/module.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/cpufreq.h> -#include <linux/sched.h> -#include <linux/smp.h> -#include <linux/init.h> -#include <linux/io.h> -#include <linux/platform_device.h> -#include <linux/of.h> -#include <linux/of_address.h> - -#include <asm/mach-types.h> -#include <asm/hardware/icst.h> - -static void __iomem *cm_base; -/* The cpufreq driver only use the OSC register */ -#define INTEGRATOR_HDR_OSC_OFFSET 0x08 -#define INTEGRATOR_HDR_LOCK_OFFSET 0x14 - -static struct cpufreq_driver integrator_driver; - -static const struct icst_params lclk_params = { - .ref = 24000000, - .vco_max = ICST525_VCO_MAX_5V, - .vco_min = ICST525_VCO_MIN, - .vd_min = 8, - .vd_max = 132, - .rd_min = 24, - .rd_max = 24, - .s2div = icst525_s2div, - .idx2s = icst525_idx2s, -}; - -static const struct icst_params cclk_params = { - .ref = 24000000, - .vco_max = ICST525_VCO_MAX_5V, - .vco_min = ICST525_VCO_MIN, - .vd_min = 12, - .vd_max = 160, - .rd_min = 24, - .rd_max = 24, - .s2div = icst525_s2div, - .idx2s = icst525_idx2s, -}; - -/* - * Validate the speed policy. - */ -static int integrator_verify_policy(struct cpufreq_policy *policy) -{ - struct icst_vco vco; - - cpufreq_verify_within_cpu_limits(policy); - - vco = icst_hz_to_vco(&cclk_params, policy->max * 1000); - policy->max = icst_hz(&cclk_params, vco) / 1000; - - vco = icst_hz_to_vco(&cclk_params, policy->min * 1000); - policy->min = icst_hz(&cclk_params, vco) / 1000; - - cpufreq_verify_within_cpu_limits(policy); - return 0; -} - - -static int integrator_set_target(struct cpufreq_policy *policy, - unsigned int target_freq, - unsigned int relation) -{ - cpumask_t cpus_allowed; - int cpu = policy->cpu; - struct icst_vco vco; - struct cpufreq_freqs freqs; - u_int cm_osc; - - /* - * Save this threads cpus_allowed mask. - */ - cpus_allowed = current->cpus_allowed; - - /* - * Bind to the specified CPU. When this call returns, - * we should be running on the right CPU. - */ - set_cpus_allowed_ptr(current, cpumask_of(cpu)); - BUG_ON(cpu != smp_processor_id()); - - /* get current setting */ - cm_osc = __raw_readl(cm_base + INTEGRATOR_HDR_OSC_OFFSET); - - if (machine_is_integrator()) - vco.s = (cm_osc >> 8) & 7; - else if (machine_is_cintegrator()) - vco.s = 1; - vco.v = cm_osc & 255; - vco.r = 22; - freqs.old = icst_hz(&cclk_params, vco) / 1000; - - /* icst_hz_to_vco rounds down -- so we need the next - * larger freq in case of CPUFREQ_RELATION_L. - */ - if (relation == CPUFREQ_RELATION_L) - target_freq += 999; - if (target_freq > policy->max) - target_freq = policy->max; - vco = icst_hz_to_vco(&cclk_params, target_freq * 1000); - freqs.new = icst_hz(&cclk_params, vco) / 1000; - - if (freqs.old == freqs.new) { - set_cpus_allowed_ptr(current, &cpus_allowed); - return 0; - } - - cpufreq_freq_transition_begin(policy, &freqs); - - cm_osc = __raw_readl(cm_base + INTEGRATOR_HDR_OSC_OFFSET); - - if (machine_is_integrator()) { - cm_osc &= 0xfffff800; - cm_osc |= vco.s << 8; - } else if (machine_is_cintegrator()) { - cm_osc &= 0xffffff00; - } - cm_osc |= vco.v; - - __raw_writel(0xa05f, cm_base + INTEGRATOR_HDR_LOCK_OFFSET); - __raw_writel(cm_osc, cm_base + INTEGRATOR_HDR_OSC_OFFSET); - __raw_writel(0, cm_base + INTEGRATOR_HDR_LOCK_OFFSET); - - /* - * Restore the CPUs allowed mask. - */ - set_cpus_allowed_ptr(current, &cpus_allowed); - - cpufreq_freq_transition_end(policy, &freqs, 0); - - return 0; -} - -static unsigned int integrator_get(unsigned int cpu) -{ - cpumask_t cpus_allowed; - unsigned int current_freq; - u_int cm_osc; - struct icst_vco vco; - - cpus_allowed = current->cpus_allowed; - - set_cpus_allowed_ptr(current, cpumask_of(cpu)); - BUG_ON(cpu != smp_processor_id()); - - /* detect memory etc. */ - cm_osc = __raw_readl(cm_base + INTEGRATOR_HDR_OSC_OFFSET); - - if (machine_is_integrator()) - vco.s = (cm_osc >> 8) & 7; - else - vco.s = 1; - vco.v = cm_osc & 255; - vco.r = 22; - - current_freq = icst_hz(&cclk_params, vco) / 1000; /* current freq */ - - set_cpus_allowed_ptr(current, &cpus_allowed); - - return current_freq; -} - -static int integrator_cpufreq_init(struct cpufreq_policy *policy) -{ - - /* set default policy and cpuinfo */ - policy->max = policy->cpuinfo.max_freq = 160000; - policy->min = policy->cpuinfo.min_freq = 12000; - policy->cpuinfo.transition_latency = 1000000; /* 1 ms, assumed */ - - return 0; -} - -static struct cpufreq_driver integrator_driver = { - .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK, - .verify = integrator_verify_policy, - .target = integrator_set_target, - .get = integrator_get, - .init = integrator_cpufreq_init, - .name = "integrator", -}; - -static int __init integrator_cpufreq_probe(struct platform_device *pdev) -{ - struct resource *res; - - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!res) - return -ENODEV; - - cm_base = devm_ioremap(&pdev->dev, res->start, resource_size(res)); - if (!cm_base) - return -ENODEV; - - return cpufreq_register_driver(&integrator_driver); -} - -static int __exit integrator_cpufreq_remove(struct platform_device *pdev) -{ - return cpufreq_unregister_driver(&integrator_driver); -} - -static const struct of_device_id integrator_cpufreq_match[] = { - { .compatible = "arm,core-module-integrator"}, - { }, -}; - -MODULE_DEVICE_TABLE(of, integrator_cpufreq_match); - -static struct platform_driver integrator_cpufreq_driver = { - .driver = { - .name = "integrator-cpufreq", - .of_match_table = integrator_cpufreq_match, - }, - .remove = __exit_p(integrator_cpufreq_remove), -}; - -module_platform_driver_probe(integrator_cpufreq_driver, - integrator_cpufreq_probe); - -MODULE_AUTHOR("Russell M. King"); -MODULE_DESCRIPTION("cpufreq driver for ARM Integrator CPUs"); -MODULE_LICENSE("GPL"); diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 4737520ec823..7cd0177ddeaf 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -37,6 +37,8 @@ #include <asm/cpufeature.h> #include <asm/intel-family.h> +#define INTEL_CPUFREQ_TRANSITION_LATENCY 20000 + #define ATOM_RATIOS 0x66a #define ATOM_VIDS 0x66b #define ATOM_TURBO_RATIOS 0x66c @@ -52,6 +54,8 @@ #define EXT_BITS 6 #define EXT_FRAC_BITS (EXT_BITS + FRAC_BITS) +#define fp_ext_toint(X) ((X) >> EXT_FRAC_BITS) +#define int_ext_tofp(X) ((int64_t)(X) << EXT_FRAC_BITS) static inline int32_t mul_fp(int32_t x, int32_t y) { @@ -122,6 +126,8 @@ struct sample { * @scaling: Scaling factor to convert frequency to cpufreq * frequency units * @turbo_pstate: Max Turbo P state possible for this platform + * @max_freq: @max_pstate frequency in cpufreq units + * @turbo_freq: @turbo_pstate frequency in cpufreq units * * Stores the per cpu model P state limits and current P state. */ @@ -132,6 +138,8 @@ struct pstate_data { int max_pstate_physical; int scaling; int turbo_pstate; + unsigned int max_freq; + unsigned int turbo_freq; }; /** @@ -177,6 +185,48 @@ struct _pid { }; /** + * struct perf_limits - Store user and policy limits + * @no_turbo: User requested turbo state from intel_pstate sysfs + * @turbo_disabled: Platform turbo status either from msr + * MSR_IA32_MISC_ENABLE or when maximum available pstate + * matches the maximum turbo pstate + * @max_perf_pct: Effective maximum performance limit in percentage, this + * is minimum of either limits enforced by cpufreq policy + * or limits from user set limits via intel_pstate sysfs + * @min_perf_pct: Effective minimum performance limit in percentage, this + * is maximum of either limits enforced by cpufreq policy + * or limits from user set limits via intel_pstate sysfs + * @max_perf: This is a scaled value between 0 to 255 for max_perf_pct + * This value is used to limit max pstate + * @min_perf: This is a scaled value between 0 to 255 for min_perf_pct + * This value is used to limit min pstate + * @max_policy_pct: The maximum performance in percentage enforced by + * cpufreq setpolicy interface + * @max_sysfs_pct: The maximum performance in percentage enforced by + * intel pstate sysfs interface, unused when per cpu + * controls are enforced + * @min_policy_pct: The minimum performance in percentage enforced by + * cpufreq setpolicy interface + * @min_sysfs_pct: The minimum performance in percentage enforced by + * intel pstate sysfs interface, unused when per cpu + * controls are enforced + * + * Storage for user and policy defined limits. + */ +struct perf_limits { + int no_turbo; + int turbo_disabled; + int max_perf_pct; + int min_perf_pct; + int32_t max_perf; + int32_t min_perf; + int max_policy_pct; + int max_sysfs_pct; + int min_policy_pct; + int min_sysfs_pct; +}; + +/** * struct cpudata - Per CPU instance data storage * @cpu: CPU number for this instance data * @policy: CPUFreq policy value @@ -194,8 +244,19 @@ struct _pid { * @prev_cummulative_iowait: IO Wait time difference from last and * current sample * @sample: Storage for storing last Sample data + * @perf_limits: Pointer to perf_limit unique to this CPU + * Not all field in the structure are applicable + * when per cpu controls are enforced * @acpi_perf_data: Stores ACPI perf information read from _PSS * @valid_pss_table: Set to true for valid ACPI _PSS entries found + * @epp_powersave: Last saved HWP energy performance preference + * (EPP) or energy performance bias (EPB), + * when policy switched to performance + * @epp_policy: Last saved policy used to set EPP/EPB + * @epp_default: Power on default HWP energy performance + * preference/bias + * @epp_saved: Saved EPP/EPB during system suspend or CPU offline + * operation * * This structure stores per CPU instance data for all CPUs. */ @@ -217,11 +278,16 @@ struct cpudata { u64 prev_tsc; u64 prev_cummulative_iowait; struct sample sample; + struct perf_limits *perf_limits; #ifdef CONFIG_ACPI struct acpi_processor_performance acpi_perf_data; bool valid_pss_table; #endif unsigned int iowait_boost; + s16 epp_powersave; + s16 epp_policy; + s16 epp_default; + s16 epp_saved; }; static struct cpudata **all_cpu_data; @@ -235,7 +301,6 @@ static struct cpudata **all_cpu_data; * @p_gain_pct: PID proportional gain * @i_gain_pct: PID integral gain * @d_gain_pct: PID derivative gain - * @boost_iowait: Whether or not to use iowait boosting. * * Stores per CPU model static PID configuration data. */ @@ -247,7 +312,6 @@ struct pstate_adjust_policy { int p_gain_pct; int d_gain_pct; int i_gain_pct; - bool boost_iowait; }; /** @@ -291,58 +355,19 @@ static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu); static struct pstate_adjust_policy pid_params __read_mostly; static struct pstate_funcs pstate_funcs __read_mostly; static int hwp_active __read_mostly; +static bool per_cpu_limits __read_mostly; #ifdef CONFIG_ACPI static bool acpi_ppc; #endif -/** - * struct perf_limits - Store user and policy limits - * @no_turbo: User requested turbo state from intel_pstate sysfs - * @turbo_disabled: Platform turbo status either from msr - * MSR_IA32_MISC_ENABLE or when maximum available pstate - * matches the maximum turbo pstate - * @max_perf_pct: Effective maximum performance limit in percentage, this - * is minimum of either limits enforced by cpufreq policy - * or limits from user set limits via intel_pstate sysfs - * @min_perf_pct: Effective minimum performance limit in percentage, this - * is maximum of either limits enforced by cpufreq policy - * or limits from user set limits via intel_pstate sysfs - * @max_perf: This is a scaled value between 0 to 255 for max_perf_pct - * This value is used to limit max pstate - * @min_perf: This is a scaled value between 0 to 255 for min_perf_pct - * This value is used to limit min pstate - * @max_policy_pct: The maximum performance in percentage enforced by - * cpufreq setpolicy interface - * @max_sysfs_pct: The maximum performance in percentage enforced by - * intel pstate sysfs interface - * @min_policy_pct: The minimum performance in percentage enforced by - * cpufreq setpolicy interface - * @min_sysfs_pct: The minimum performance in percentage enforced by - * intel pstate sysfs interface - * - * Storage for user and policy defined limits. - */ -struct perf_limits { - int no_turbo; - int turbo_disabled; - int max_perf_pct; - int min_perf_pct; - int32_t max_perf; - int32_t min_perf; - int max_policy_pct; - int max_sysfs_pct; - int min_policy_pct; - int min_sysfs_pct; -}; - static struct perf_limits performance_limits = { .no_turbo = 0, .turbo_disabled = 0, .max_perf_pct = 100, - .max_perf = int_tofp(1), + .max_perf = int_ext_tofp(1), .min_perf_pct = 100, - .min_perf = int_tofp(1), + .min_perf = int_ext_tofp(1), .max_policy_pct = 100, .max_sysfs_pct = 100, .min_policy_pct = 0, @@ -353,7 +378,7 @@ static struct perf_limits powersave_limits = { .no_turbo = 0, .turbo_disabled = 0, .max_perf_pct = 100, - .max_perf = int_tofp(1), + .max_perf = int_ext_tofp(1), .min_perf_pct = 0, .min_perf = 0, .max_policy_pct = 100, @@ -368,6 +393,8 @@ static struct perf_limits *limits = &performance_limits; static struct perf_limits *limits = &powersave_limits; #endif +static DEFINE_MUTEX(intel_pstate_limits_lock); + #ifdef CONFIG_ACPI static bool intel_pstate_get_ppc_enable_status(void) @@ -459,11 +486,11 @@ static void intel_pstate_exit_perf_limits(struct cpufreq_policy *policy) } #else -static void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy) +static inline void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy) { } -static void intel_pstate_exit_perf_limits(struct cpufreq_policy *policy) +static inline void intel_pstate_exit_perf_limits(struct cpufreq_policy *policy) { } #endif @@ -559,24 +586,252 @@ static inline void update_turbo_state(void) cpu->pstate.max_pstate == cpu->pstate.turbo_pstate); } +static s16 intel_pstate_get_epb(struct cpudata *cpu_data) +{ + u64 epb; + int ret; + + if (!static_cpu_has(X86_FEATURE_EPB)) + return -ENXIO; + + ret = rdmsrl_on_cpu(cpu_data->cpu, MSR_IA32_ENERGY_PERF_BIAS, &epb); + if (ret) + return (s16)ret; + + return (s16)(epb & 0x0f); +} + +static s16 intel_pstate_get_epp(struct cpudata *cpu_data, u64 hwp_req_data) +{ + s16 epp; + + if (static_cpu_has(X86_FEATURE_HWP_EPP)) { + /* + * When hwp_req_data is 0, means that caller didn't read + * MSR_HWP_REQUEST, so need to read and get EPP. + */ + if (!hwp_req_data) { + epp = rdmsrl_on_cpu(cpu_data->cpu, MSR_HWP_REQUEST, + &hwp_req_data); + if (epp) + return epp; + } + epp = (hwp_req_data >> 24) & 0xff; + } else { + /* When there is no EPP present, HWP uses EPB settings */ + epp = intel_pstate_get_epb(cpu_data); + } + + return epp; +} + +static int intel_pstate_set_epb(int cpu, s16 pref) +{ + u64 epb; + int ret; + + if (!static_cpu_has(X86_FEATURE_EPB)) + return -ENXIO; + + ret = rdmsrl_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS, &epb); + if (ret) + return ret; + + epb = (epb & ~0x0f) | pref; + wrmsrl_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS, epb); + + return 0; +} + +/* + * EPP/EPB display strings corresponding to EPP index in the + * energy_perf_strings[] + * index String + *------------------------------------- + * 0 default + * 1 performance + * 2 balance_performance + * 3 balance_power + * 4 power + */ +static const char * const energy_perf_strings[] = { + "default", + "performance", + "balance_performance", + "balance_power", + "power", + NULL +}; + +static int intel_pstate_get_energy_pref_index(struct cpudata *cpu_data) +{ + s16 epp; + int index = -EINVAL; + + epp = intel_pstate_get_epp(cpu_data, 0); + if (epp < 0) + return epp; + + if (static_cpu_has(X86_FEATURE_HWP_EPP)) { + /* + * Range: + * 0x00-0x3F : Performance + * 0x40-0x7F : Balance performance + * 0x80-0xBF : Balance power + * 0xC0-0xFF : Power + * The EPP is a 8 bit value, but our ranges restrict the + * value which can be set. Here only using top two bits + * effectively. + */ + index = (epp >> 6) + 1; + } else if (static_cpu_has(X86_FEATURE_EPB)) { + /* + * Range: + * 0x00-0x03 : Performance + * 0x04-0x07 : Balance performance + * 0x08-0x0B : Balance power + * 0x0C-0x0F : Power + * The EPB is a 4 bit value, but our ranges restrict the + * value which can be set. Here only using top two bits + * effectively. + */ + index = (epp >> 2) + 1; + } + + return index; +} + +static int intel_pstate_set_energy_pref_index(struct cpudata *cpu_data, + int pref_index) +{ + int epp = -EINVAL; + int ret; + + if (!pref_index) + epp = cpu_data->epp_default; + + mutex_lock(&intel_pstate_limits_lock); + + if (static_cpu_has(X86_FEATURE_HWP_EPP)) { + u64 value; + + ret = rdmsrl_on_cpu(cpu_data->cpu, MSR_HWP_REQUEST, &value); + if (ret) + goto return_pref; + + value &= ~GENMASK_ULL(31, 24); + + /* + * If epp is not default, convert from index into + * energy_perf_strings to epp value, by shifting 6 + * bits left to use only top two bits in epp. + * The resultant epp need to shifted by 24 bits to + * epp position in MSR_HWP_REQUEST. + */ + if (epp == -EINVAL) + epp = (pref_index - 1) << 6; + + value |= (u64)epp << 24; + ret = wrmsrl_on_cpu(cpu_data->cpu, MSR_HWP_REQUEST, value); + } else { + if (epp == -EINVAL) + epp = (pref_index - 1) << 2; + ret = intel_pstate_set_epb(cpu_data->cpu, epp); + } +return_pref: + mutex_unlock(&intel_pstate_limits_lock); + + return ret; +} + +static ssize_t show_energy_performance_available_preferences( + struct cpufreq_policy *policy, char *buf) +{ + int i = 0; + int ret = 0; + + while (energy_perf_strings[i] != NULL) + ret += sprintf(&buf[ret], "%s ", energy_perf_strings[i++]); + + ret += sprintf(&buf[ret], "\n"); + + return ret; +} + +cpufreq_freq_attr_ro(energy_performance_available_preferences); + +static ssize_t store_energy_performance_preference( + struct cpufreq_policy *policy, const char *buf, size_t count) +{ + struct cpudata *cpu_data = all_cpu_data[policy->cpu]; + char str_preference[21]; + int ret, i = 0; + + ret = sscanf(buf, "%20s", str_preference); + if (ret != 1) + return -EINVAL; + + while (energy_perf_strings[i] != NULL) { + if (!strcmp(str_preference, energy_perf_strings[i])) { + intel_pstate_set_energy_pref_index(cpu_data, i); + return count; + } + ++i; + } + + return -EINVAL; +} + +static ssize_t show_energy_performance_preference( + struct cpufreq_policy *policy, char *buf) +{ + struct cpudata *cpu_data = all_cpu_data[policy->cpu]; + int preference; + + preference = intel_pstate_get_energy_pref_index(cpu_data); + if (preference < 0) + return preference; + + return sprintf(buf, "%s\n", energy_perf_strings[preference]); +} + +cpufreq_freq_attr_rw(energy_performance_preference); + +static struct freq_attr *hwp_cpufreq_attrs[] = { + &energy_performance_preference, + &energy_performance_available_preferences, + NULL, +}; + static void intel_pstate_hwp_set(const struct cpumask *cpumask) { int min, hw_min, max, hw_max, cpu, range, adj_range; + struct perf_limits *perf_limits = limits; u64 value, cap; for_each_cpu(cpu, cpumask) { + int max_perf_pct, min_perf_pct; + struct cpudata *cpu_data = all_cpu_data[cpu]; + s16 epp; + + if (per_cpu_limits) + perf_limits = all_cpu_data[cpu]->perf_limits; + rdmsrl_on_cpu(cpu, MSR_HWP_CAPABILITIES, &cap); hw_min = HWP_LOWEST_PERF(cap); hw_max = HWP_HIGHEST_PERF(cap); range = hw_max - hw_min; + max_perf_pct = perf_limits->max_perf_pct; + min_perf_pct = perf_limits->min_perf_pct; + rdmsrl_on_cpu(cpu, MSR_HWP_REQUEST, &value); - adj_range = limits->min_perf_pct * range / 100; + adj_range = min_perf_pct * range / 100; min = hw_min + adj_range; value &= ~HWP_MIN_PERF(~0L); value |= HWP_MIN_PERF(min); - adj_range = limits->max_perf_pct * range / 100; + adj_range = max_perf_pct * range / 100; max = hw_min + adj_range; if (limits->no_turbo) { hw_max = HWP_GUARANTEED_PERF(cap); @@ -586,6 +841,53 @@ static void intel_pstate_hwp_set(const struct cpumask *cpumask) value &= ~HWP_MAX_PERF(~0L); value |= HWP_MAX_PERF(max); + + if (cpu_data->epp_policy == cpu_data->policy) + goto skip_epp; + + cpu_data->epp_policy = cpu_data->policy; + + if (cpu_data->epp_saved >= 0) { + epp = cpu_data->epp_saved; + cpu_data->epp_saved = -EINVAL; + goto update_epp; + } + + if (cpu_data->policy == CPUFREQ_POLICY_PERFORMANCE) { + epp = intel_pstate_get_epp(cpu_data, value); + cpu_data->epp_powersave = epp; + /* If EPP read was failed, then don't try to write */ + if (epp < 0) + goto skip_epp; + + + epp = 0; + } else { + /* skip setting EPP, when saved value is invalid */ + if (cpu_data->epp_powersave < 0) + goto skip_epp; + + /* + * No need to restore EPP when it is not zero. This + * means: + * - Policy is not changed + * - user has manually changed + * - Error reading EPB + */ + epp = intel_pstate_get_epp(cpu_data, value); + if (epp) + goto skip_epp; + + epp = cpu_data->epp_powersave; + } +update_epp: + if (static_cpu_has(X86_FEATURE_HWP_EPP)) { + value &= ~GENMASK_ULL(31, 24); + value |= (u64)epp << 24; + } else { + intel_pstate_set_epb(cpu, epp); + } +skip_epp: wrmsrl_on_cpu(cpu, MSR_HWP_REQUEST, value); } } @@ -598,6 +900,28 @@ static int intel_pstate_hwp_set_policy(struct cpufreq_policy *policy) return 0; } +static int intel_pstate_hwp_save_state(struct cpufreq_policy *policy) +{ + struct cpudata *cpu_data = all_cpu_data[policy->cpu]; + + if (!hwp_active) + return 0; + + cpu_data->epp_saved = intel_pstate_get_epp(cpu_data, 0); + + return 0; +} + +static int intel_pstate_resume(struct cpufreq_policy *policy) +{ + if (!hwp_active) + return 0; + + all_cpu_data[policy->cpu]->epp_policy = 0; + + return intel_pstate_hwp_set_policy(policy); +} + static void intel_pstate_hwp_set_online_cpus(void) { get_online_cpus(); @@ -640,8 +964,10 @@ static void __init intel_pstate_debug_expose_params(void) struct dentry *debugfs_parent; int i = 0; - if (hwp_active) + if (hwp_active || + pstate_funcs.get_target_pstate == get_target_pstate_use_cpu_load) return; + debugfs_parent = debugfs_create_dir("pstate_snb", NULL); if (IS_ERR_OR_NULL(debugfs_parent)) return; @@ -714,9 +1040,12 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b, if (ret != 1) return -EINVAL; + mutex_lock(&intel_pstate_limits_lock); + update_turbo_state(); if (limits->turbo_disabled) { pr_warn("Turbo disabled by BIOS or unavailable on processor\n"); + mutex_unlock(&intel_pstate_limits_lock); return -EPERM; } @@ -725,6 +1054,8 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b, if (hwp_active) intel_pstate_hwp_set_online_cpus(); + mutex_unlock(&intel_pstate_limits_lock); + return count; } @@ -738,6 +1069,8 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b, if (ret != 1) return -EINVAL; + mutex_lock(&intel_pstate_limits_lock); + limits->max_sysfs_pct = clamp_t(int, input, 0 , 100); limits->max_perf_pct = min(limits->max_policy_pct, limits->max_sysfs_pct); @@ -745,10 +1078,13 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b, limits->max_perf_pct); limits->max_perf_pct = max(limits->min_perf_pct, limits->max_perf_pct); - limits->max_perf = div_fp(limits->max_perf_pct, 100); + limits->max_perf = div_ext_fp(limits->max_perf_pct, 100); if (hwp_active) intel_pstate_hwp_set_online_cpus(); + + mutex_unlock(&intel_pstate_limits_lock); + return count; } @@ -762,6 +1098,8 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b, if (ret != 1) return -EINVAL; + mutex_lock(&intel_pstate_limits_lock); + limits->min_sysfs_pct = clamp_t(int, input, 0 , 100); limits->min_perf_pct = max(limits->min_policy_pct, limits->min_sysfs_pct); @@ -769,10 +1107,13 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b, limits->min_perf_pct); limits->min_perf_pct = min(limits->max_perf_pct, limits->min_perf_pct); - limits->min_perf = div_fp(limits->min_perf_pct, 100); + limits->min_perf = div_ext_fp(limits->min_perf_pct, 100); if (hwp_active) intel_pstate_hwp_set_online_cpus(); + + mutex_unlock(&intel_pstate_limits_lock); + return count; } @@ -787,8 +1128,6 @@ define_one_global_ro(num_pstates); static struct attribute *intel_pstate_attributes[] = { &no_turbo.attr, - &max_perf_pct.attr, - &min_perf_pct.attr, &turbo_pct.attr, &num_pstates.attr, NULL @@ -805,9 +1144,26 @@ static void __init intel_pstate_sysfs_expose_params(void) intel_pstate_kobject = kobject_create_and_add("intel_pstate", &cpu_subsys.dev_root->kobj); - BUG_ON(!intel_pstate_kobject); + if (WARN_ON(!intel_pstate_kobject)) + return; + rc = sysfs_create_group(intel_pstate_kobject, &intel_pstate_attr_group); - BUG_ON(rc); + if (WARN_ON(rc)) + return; + + /* + * If per cpu limits are enforced there are no global limits, so + * return without creating max/min_perf_pct attributes + */ + if (per_cpu_limits) + return; + + rc = sysfs_create_file(intel_pstate_kobject, &max_perf_pct.attr); + WARN_ON(rc); + + rc = sysfs_create_file(intel_pstate_kobject, &min_perf_pct.attr); + WARN_ON(rc); + } /************************** sysfs end ************************/ @@ -818,6 +1174,9 @@ static void intel_pstate_hwp_enable(struct cpudata *cpudata) wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x00); wrmsrl_on_cpu(cpudata->cpu, MSR_PM_ENABLE, 0x1); + cpudata->epp_policy = 0; + if (cpudata->epp_default == -EINVAL) + cpudata->epp_default = intel_pstate_get_epp(cpudata, 0); } static int atom_get_min_pstate(void) @@ -1045,7 +1404,6 @@ static const struct cpu_defaults silvermont_params = { .p_gain_pct = 14, .d_gain_pct = 0, .i_gain_pct = 4, - .boost_iowait = true, }, .funcs = { .get_max = atom_get_max_pstate, @@ -1067,7 +1425,6 @@ static const struct cpu_defaults airmont_params = { .p_gain_pct = 14, .d_gain_pct = 0, .i_gain_pct = 4, - .boost_iowait = true, }, .funcs = { .get_max = atom_get_max_pstate, @@ -1109,7 +1466,6 @@ static const struct cpu_defaults bxt_params = { .p_gain_pct = 14, .d_gain_pct = 0, .i_gain_pct = 4, - .boost_iowait = true, }, .funcs = { .get_max = core_get_max_pstate, @@ -1127,20 +1483,24 @@ static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max) int max_perf = cpu->pstate.turbo_pstate; int max_perf_adj; int min_perf; + struct perf_limits *perf_limits = limits; if (limits->no_turbo || limits->turbo_disabled) max_perf = cpu->pstate.max_pstate; + if (per_cpu_limits) + perf_limits = cpu->perf_limits; + /* * performance can be limited by user through sysfs, by cpufreq * policy, or by cpu specific default values determined through * experimentation. */ - max_perf_adj = fp_toint(max_perf * limits->max_perf); + max_perf_adj = fp_ext_toint(max_perf * perf_limits->max_perf); *max = clamp_t(int, max_perf_adj, cpu->pstate.min_pstate, cpu->pstate.turbo_pstate); - min_perf = fp_toint(max_perf * limits->min_perf); + min_perf = fp_ext_toint(max_perf * perf_limits->min_perf); *min = clamp_t(int, min_perf, cpu->pstate.min_pstate, max_perf); } @@ -1178,6 +1538,8 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu) cpu->pstate.max_pstate_physical = pstate_funcs.get_max_physical(); cpu->pstate.turbo_pstate = pstate_funcs.get_turbo(); cpu->pstate.scaling = pstate_funcs.get_scaling(); + cpu->pstate.max_freq = cpu->pstate.max_pstate * cpu->pstate.scaling; + cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * cpu->pstate.scaling; if (pstate_funcs.get_vid) pstate_funcs.get_vid(cpu); @@ -1316,15 +1678,19 @@ static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu) return cpu->pstate.current_pstate - pid_calc(&cpu->pid, perf_scaled); } -static inline void intel_pstate_update_pstate(struct cpudata *cpu, int pstate) +static int intel_pstate_prepare_request(struct cpudata *cpu, int pstate) { int max_perf, min_perf; - update_turbo_state(); - intel_pstate_get_min_max(cpu, &min_perf, &max_perf); pstate = clamp_t(int, pstate, min_perf, max_perf); trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu); + return pstate; +} + +static void intel_pstate_update_pstate(struct cpudata *cpu, int pstate) +{ + pstate = intel_pstate_prepare_request(cpu, pstate); if (pstate == cpu->pstate.current_pstate) return; @@ -1342,6 +1708,8 @@ static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu) target_pstate = cpu->policy == CPUFREQ_POLICY_PERFORMANCE ? cpu->pstate.turbo_pstate : pstate_funcs.get_target_pstate(cpu); + update_turbo_state(); + intel_pstate_update_pstate(cpu, target_pstate); sample = &cpu->sample; @@ -1362,7 +1730,7 @@ static void intel_pstate_update_util(struct update_util_data *data, u64 time, struct cpudata *cpu = container_of(data, struct cpudata, update_util); u64 delta_ns; - if (pid_params.boost_iowait) { + if (pstate_funcs.get_target_pstate == get_target_pstate_use_cpu_load) { if (flags & SCHED_CPUFREQ_IOWAIT) { cpu->iowait_boost = int_tofp(1); } else if (cpu->iowait_boost) { @@ -1408,6 +1776,7 @@ static const struct x86_cpu_id intel_pstate_cpu_ids[] = { ICPU(INTEL_FAM6_SKYLAKE_DESKTOP, core_params), ICPU(INTEL_FAM6_BROADWELL_XEON_D, core_params), ICPU(INTEL_FAM6_XEON_PHI_KNL, knl_params), + ICPU(INTEL_FAM6_XEON_PHI_KNM, knl_params), ICPU(INTEL_FAM6_ATOM_GOLDMONT, bxt_params), {} }; @@ -1424,11 +1793,26 @@ static int intel_pstate_init_cpu(unsigned int cpunum) { struct cpudata *cpu; - if (!all_cpu_data[cpunum]) - all_cpu_data[cpunum] = kzalloc(sizeof(struct cpudata), - GFP_KERNEL); - if (!all_cpu_data[cpunum]) - return -ENOMEM; + cpu = all_cpu_data[cpunum]; + + if (!cpu) { + unsigned int size = sizeof(struct cpudata); + + if (per_cpu_limits) + size += sizeof(struct perf_limits); + + cpu = kzalloc(size, GFP_KERNEL); + if (!cpu) + return -ENOMEM; + + all_cpu_data[cpunum] = cpu; + if (per_cpu_limits) + cpu->perf_limits = (struct perf_limits *)(cpu + 1); + + cpu->epp_default = -EINVAL; + cpu->epp_powersave = -EINVAL; + cpu->epp_saved = -EINVAL; + } cpu = all_cpu_data[cpunum]; @@ -1487,18 +1871,57 @@ static void intel_pstate_set_performance_limits(struct perf_limits *limits) limits->no_turbo = 0; limits->turbo_disabled = 0; limits->max_perf_pct = 100; - limits->max_perf = int_tofp(1); + limits->max_perf = int_ext_tofp(1); limits->min_perf_pct = 100; - limits->min_perf = int_tofp(1); + limits->min_perf = int_ext_tofp(1); limits->max_policy_pct = 100; limits->max_sysfs_pct = 100; limits->min_policy_pct = 0; limits->min_sysfs_pct = 0; } +static void intel_pstate_update_perf_limits(struct cpufreq_policy *policy, + struct perf_limits *limits) +{ + + limits->max_policy_pct = DIV_ROUND_UP(policy->max * 100, + policy->cpuinfo.max_freq); + limits->max_policy_pct = clamp_t(int, limits->max_policy_pct, 0, 100); + if (policy->max == policy->min) { + limits->min_policy_pct = limits->max_policy_pct; + } else { + limits->min_policy_pct = DIV_ROUND_UP(policy->min * 100, + policy->cpuinfo.max_freq); + limits->min_policy_pct = clamp_t(int, limits->min_policy_pct, + 0, 100); + } + + /* Normalize user input to [min_policy_pct, max_policy_pct] */ + limits->min_perf_pct = max(limits->min_policy_pct, + limits->min_sysfs_pct); + limits->min_perf_pct = min(limits->max_policy_pct, + limits->min_perf_pct); + limits->max_perf_pct = min(limits->max_policy_pct, + limits->max_sysfs_pct); + limits->max_perf_pct = max(limits->min_policy_pct, + limits->max_perf_pct); + + /* Make sure min_perf_pct <= max_perf_pct */ + limits->min_perf_pct = min(limits->max_perf_pct, limits->min_perf_pct); + + limits->min_perf = div_ext_fp(limits->min_perf_pct, 100); + limits->max_perf = div_ext_fp(limits->max_perf_pct, 100); + limits->max_perf = round_up(limits->max_perf, EXT_FRAC_BITS); + limits->min_perf = round_up(limits->min_perf, EXT_FRAC_BITS); + + pr_debug("cpu:%d max_perf_pct:%d min_perf_pct:%d\n", policy->cpu, + limits->max_perf_pct, limits->min_perf_pct); +} + static int intel_pstate_set_policy(struct cpufreq_policy *policy) { struct cpudata *cpu; + struct perf_limits *perf_limits = NULL; if (!policy->cpuinfo.max_freq) return -ENODEV; @@ -1516,41 +1939,31 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) policy->max = policy->cpuinfo.max_freq; } - if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE) { - limits = &performance_limits; + if (per_cpu_limits) + perf_limits = cpu->perf_limits; + + mutex_lock(&intel_pstate_limits_lock); + + if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) { + if (!perf_limits) { + limits = &performance_limits; + perf_limits = limits; + } if (policy->max >= policy->cpuinfo.max_freq) { pr_debug("set performance\n"); - intel_pstate_set_performance_limits(limits); + intel_pstate_set_performance_limits(perf_limits); goto out; } } else { pr_debug("set powersave\n"); - limits = &powersave_limits; - } - - limits->min_policy_pct = (policy->min * 100) / policy->cpuinfo.max_freq; - limits->min_policy_pct = clamp_t(int, limits->min_policy_pct, 0 , 100); - limits->max_policy_pct = DIV_ROUND_UP(policy->max * 100, - policy->cpuinfo.max_freq); - limits->max_policy_pct = clamp_t(int, limits->max_policy_pct, 0 , 100); - - /* Normalize user input to [min_policy_pct, max_policy_pct] */ - limits->min_perf_pct = max(limits->min_policy_pct, - limits->min_sysfs_pct); - limits->min_perf_pct = min(limits->max_policy_pct, - limits->min_perf_pct); - limits->max_perf_pct = min(limits->max_policy_pct, - limits->max_sysfs_pct); - limits->max_perf_pct = max(limits->min_policy_pct, - limits->max_perf_pct); - - /* Make sure min_perf_pct <= max_perf_pct */ - limits->min_perf_pct = min(limits->max_perf_pct, limits->min_perf_pct); + if (!perf_limits) { + limits = &powersave_limits; + perf_limits = limits; + } - limits->min_perf = div_fp(limits->min_perf_pct, 100); - limits->max_perf = div_fp(limits->max_perf_pct, 100); - limits->max_perf = round_up(limits->max_perf, FRAC_BITS); + } + intel_pstate_update_perf_limits(policy, perf_limits); out: if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE) { /* @@ -1565,6 +1978,8 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) intel_pstate_hwp_set_policy(policy); + mutex_unlock(&intel_pstate_limits_lock); + return 0; } @@ -1579,22 +1994,32 @@ static int intel_pstate_verify_policy(struct cpufreq_policy *policy) return 0; } +static void intel_cpufreq_stop_cpu(struct cpufreq_policy *policy) +{ + intel_pstate_set_min_pstate(all_cpu_data[policy->cpu]); +} + static void intel_pstate_stop_cpu(struct cpufreq_policy *policy) { - int cpu_num = policy->cpu; - struct cpudata *cpu = all_cpu_data[cpu_num]; + pr_debug("CPU %d exiting\n", policy->cpu); - pr_debug("CPU %d exiting\n", cpu_num); + intel_pstate_clear_update_util_hook(policy->cpu); + if (hwp_active) + intel_pstate_hwp_save_state(policy); + else + intel_cpufreq_stop_cpu(policy); +} - intel_pstate_clear_update_util_hook(cpu_num); +static int intel_pstate_cpu_exit(struct cpufreq_policy *policy) +{ + intel_pstate_exit_perf_limits(policy); - if (hwp_active) - return; + policy->fast_switch_possible = false; - intel_pstate_set_min_pstate(cpu); + return 0; } -static int intel_pstate_cpu_init(struct cpufreq_policy *policy) +static int __intel_pstate_cpu_init(struct cpufreq_policy *policy) { struct cpudata *cpu; int rc; @@ -1605,10 +2030,13 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy) cpu = all_cpu_data[policy->cpu]; - if (limits->min_perf_pct == 100 && limits->max_perf_pct == 100) - policy->policy = CPUFREQ_POLICY_PERFORMANCE; - else - policy->policy = CPUFREQ_POLICY_POWERSAVE; + /* + * We need sane value in the cpu->perf_limits, so inherit from global + * perf_limits limits, which are seeded with values based on the + * CONFIG_CPU_FREQ_DEFAULT_GOV_*, during boot up. + */ + if (per_cpu_limits) + memcpy(cpu->perf_limits, limits, sizeof(struct perf_limits)); policy->min = cpu->pstate.min_pstate * cpu->pstate.scaling; policy->max = cpu->pstate.turbo_pstate * cpu->pstate.scaling; @@ -1621,24 +2049,35 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy) policy->cpuinfo.max_freq *= cpu->pstate.scaling; intel_pstate_init_acpi_perf_limits(policy); - policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL; cpumask_set_cpu(policy->cpu, policy->cpus); + policy->fast_switch_possible = true; + return 0; } -static int intel_pstate_cpu_exit(struct cpufreq_policy *policy) +static int intel_pstate_cpu_init(struct cpufreq_policy *policy) { - intel_pstate_exit_perf_limits(policy); + int ret = __intel_pstate_cpu_init(policy); + + if (ret) + return ret; + + policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL; + if (limits->min_perf_pct == 100 && limits->max_perf_pct == 100) + policy->policy = CPUFREQ_POLICY_PERFORMANCE; + else + policy->policy = CPUFREQ_POLICY_POWERSAVE; return 0; } -static struct cpufreq_driver intel_pstate_driver = { +static struct cpufreq_driver intel_pstate = { .flags = CPUFREQ_CONST_LOOPS, .verify = intel_pstate_verify_policy, .setpolicy = intel_pstate_set_policy, - .resume = intel_pstate_hwp_set_policy, + .suspend = intel_pstate_hwp_save_state, + .resume = intel_pstate_resume, .get = intel_pstate_get, .init = intel_pstate_cpu_init, .exit = intel_pstate_cpu_exit, @@ -1646,6 +2085,118 @@ static struct cpufreq_driver intel_pstate_driver = { .name = "intel_pstate", }; +static int intel_cpufreq_verify_policy(struct cpufreq_policy *policy) +{ + struct cpudata *cpu = all_cpu_data[policy->cpu]; + struct perf_limits *perf_limits = limits; + + update_turbo_state(); + policy->cpuinfo.max_freq = limits->turbo_disabled ? + cpu->pstate.max_freq : cpu->pstate.turbo_freq; + + cpufreq_verify_within_cpu_limits(policy); + + if (per_cpu_limits) + perf_limits = cpu->perf_limits; + + intel_pstate_update_perf_limits(policy, perf_limits); + + return 0; +} + +static unsigned int intel_cpufreq_turbo_update(struct cpudata *cpu, + struct cpufreq_policy *policy, + unsigned int target_freq) +{ + unsigned int max_freq; + + update_turbo_state(); + + max_freq = limits->no_turbo || limits->turbo_disabled ? + cpu->pstate.max_freq : cpu->pstate.turbo_freq; + policy->cpuinfo.max_freq = max_freq; + if (policy->max > max_freq) + policy->max = max_freq; + + if (target_freq > max_freq) + target_freq = max_freq; + + return target_freq; +} + +static int intel_cpufreq_target(struct cpufreq_policy *policy, + unsigned int target_freq, + unsigned int relation) +{ + struct cpudata *cpu = all_cpu_data[policy->cpu]; + struct cpufreq_freqs freqs; + int target_pstate; + + freqs.old = policy->cur; + freqs.new = intel_cpufreq_turbo_update(cpu, policy, target_freq); + + cpufreq_freq_transition_begin(policy, &freqs); + switch (relation) { + case CPUFREQ_RELATION_L: + target_pstate = DIV_ROUND_UP(freqs.new, cpu->pstate.scaling); + break; + case CPUFREQ_RELATION_H: + target_pstate = freqs.new / cpu->pstate.scaling; + break; + default: + target_pstate = DIV_ROUND_CLOSEST(freqs.new, cpu->pstate.scaling); + break; + } + target_pstate = intel_pstate_prepare_request(cpu, target_pstate); + if (target_pstate != cpu->pstate.current_pstate) { + cpu->pstate.current_pstate = target_pstate; + wrmsrl_on_cpu(policy->cpu, MSR_IA32_PERF_CTL, + pstate_funcs.get_val(cpu, target_pstate)); + } + cpufreq_freq_transition_end(policy, &freqs, false); + + return 0; +} + +static unsigned int intel_cpufreq_fast_switch(struct cpufreq_policy *policy, + unsigned int target_freq) +{ + struct cpudata *cpu = all_cpu_data[policy->cpu]; + int target_pstate; + + target_freq = intel_cpufreq_turbo_update(cpu, policy, target_freq); + target_pstate = DIV_ROUND_UP(target_freq, cpu->pstate.scaling); + intel_pstate_update_pstate(cpu, target_pstate); + return target_freq; +} + +static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy) +{ + int ret = __intel_pstate_cpu_init(policy); + + if (ret) + return ret; + + policy->cpuinfo.transition_latency = INTEL_CPUFREQ_TRANSITION_LATENCY; + /* This reflects the intel_pstate_get_cpu_pstates() setting. */ + policy->cur = policy->cpuinfo.min_freq; + + return 0; +} + +static struct cpufreq_driver intel_cpufreq = { + .flags = CPUFREQ_CONST_LOOPS, + .verify = intel_cpufreq_verify_policy, + .target = intel_cpufreq_target, + .fast_switch = intel_cpufreq_fast_switch, + .init = intel_cpufreq_cpu_init, + .exit = intel_pstate_cpu_exit, + .stop_cpu = intel_cpufreq_stop_cpu, + .name = "intel_cpufreq", +}; + +static struct cpufreq_driver *intel_pstate_driver = &intel_pstate; + static int no_load __initdata; static int no_hwp __initdata; static int hwp_only __initdata; @@ -1672,6 +2223,19 @@ static void __init copy_pid_params(struct pstate_adjust_policy *policy) pid_params.setpoint = policy->setpoint; } +#ifdef CONFIG_ACPI +static void intel_pstate_use_acpi_profile(void) +{ + if (acpi_gbl_FADT.preferred_profile == PM_MOBILE) + pstate_funcs.get_target_pstate = + get_target_pstate_use_cpu_load; +} +#else +static void intel_pstate_use_acpi_profile(void) +{ +} +#endif + static void __init copy_cpu_funcs(struct pstate_funcs *funcs) { pstate_funcs.get_max = funcs->get_max; @@ -1683,6 +2247,7 @@ static void __init copy_cpu_funcs(struct pstate_funcs *funcs) pstate_funcs.get_vid = funcs->get_vid; pstate_funcs.get_target_pstate = funcs->get_target_pstate; + intel_pstate_use_acpi_profile(); } #ifdef CONFIG_ACPI @@ -1796,9 +2361,20 @@ static bool __init intel_pstate_platform_pwr_mgmt_exists(void) return false; } + +static void intel_pstate_request_control_from_smm(void) +{ + /* + * It may be unsafe to request P-states control from SMM if _PPC support + * has not been enabled. + */ + if (acpi_ppc) + acpi_processor_pstate_control(); +} #else /* CONFIG_ACPI not enabled */ static inline bool intel_pstate_platform_pwr_mgmt_exists(void) { return false; } static inline bool intel_pstate_has_acpi_ppc(void) { return false; } +static inline void intel_pstate_request_control_from_smm(void) {} #endif /* CONFIG_ACPI */ static const struct x86_cpu_id hwp_support_ids[] __initconst = { @@ -1818,6 +2394,7 @@ static int __init intel_pstate_init(void) if (x86_match_cpu(hwp_support_ids) && !no_hwp) { copy_cpu_funcs(&core_params.funcs); hwp_active++; + intel_pstate.attr = hwp_cpufreq_attrs; goto hwp_cpu_matched; } @@ -1850,7 +2427,9 @@ hwp_cpu_matched: if (!hwp_active && hwp_only) goto out; - rc = cpufreq_register_driver(&intel_pstate_driver); + intel_pstate_request_control_from_smm(); + + rc = cpufreq_register_driver(intel_pstate_driver); if (rc) goto out; @@ -1865,7 +2444,9 @@ out: get_online_cpus(); for_each_online_cpu(cpu) { if (all_cpu_data[cpu]) { - intel_pstate_clear_update_util_hook(cpu); + if (intel_pstate_driver == &intel_pstate) + intel_pstate_clear_update_util_hook(cpu); + kfree(all_cpu_data[cpu]); } } @@ -1881,8 +2462,13 @@ static int __init intel_pstate_setup(char *str) if (!str) return -EINVAL; - if (!strcmp(str, "disable")) + if (!strcmp(str, "disable")) { no_load = 1; + } else if (!strcmp(str, "passive")) { + pr_info("Passive mode enabled\n"); + intel_pstate_driver = &intel_cpufreq; + no_hwp = 1; + } if (!strcmp(str, "no_hwp")) { pr_info("HWP disabled\n"); no_hwp = 1; @@ -1891,6 +2477,8 @@ static int __init intel_pstate_setup(char *str) force_load = 1; if (!strcmp(str, "hwp_only")) hwp_only = 1; + if (!strcmp(str, "per_cpu_perf_limits")) + per_cpu_limits = true; #ifdef CONFIG_ACPI if (!strcmp(str, "support_acpi_ppc")) diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c index d3ffde806629..37671b545880 100644 --- a/drivers/cpufreq/powernv-cpufreq.c +++ b/drivers/cpufreq/powernv-cpufreq.c @@ -42,6 +42,10 @@ #define PMSR_PSAFE_ENABLE (1UL << 30) #define PMSR_SPR_EM_DISABLE (1UL << 31) #define PMSR_MAX(x) ((x >> 32) & 0xFF) +#define LPSTATE_SHIFT 48 +#define GPSTATE_SHIFT 56 +#define GET_LPSTATE(x) (((x) >> LPSTATE_SHIFT) & 0xFF) +#define GET_GPSTATE(x) (((x) >> GPSTATE_SHIFT) & 0xFF) #define MAX_RAMP_DOWN_TIME 5120 /* @@ -592,7 +596,8 @@ void gpstate_timer_handler(unsigned long data) { struct cpufreq_policy *policy = (struct cpufreq_policy *)data; struct global_pstate_info *gpstates = policy->driver_data; - int gpstate_idx; + int gpstate_idx, lpstate_idx; + unsigned long val; unsigned int time_diff = jiffies_to_msecs(jiffies) - gpstates->last_sampled_time; struct powernv_smp_call_data freq_data; @@ -600,21 +605,37 @@ void gpstate_timer_handler(unsigned long data) if (!spin_trylock(&gpstates->gpstate_lock)) return; + /* + * If PMCR was last updated was using fast_swtich then + * We may have wrong in gpstate->last_lpstate_idx + * value. Hence, read from PMCR to get correct data. + */ + val = get_pmspr(SPRN_PMCR); + freq_data.gpstate_id = (s8)GET_GPSTATE(val); + freq_data.pstate_id = (s8)GET_LPSTATE(val); + if (freq_data.gpstate_id == freq_data.pstate_id) { + reset_gpstates(policy); + spin_unlock(&gpstates->gpstate_lock); + return; + } + gpstates->last_sampled_time += time_diff; gpstates->elapsed_time += time_diff; - freq_data.pstate_id = idx_to_pstate(gpstates->last_lpstate_idx); - if ((gpstates->last_gpstate_idx == gpstates->last_lpstate_idx) || - (gpstates->elapsed_time > MAX_RAMP_DOWN_TIME)) { + if (gpstates->elapsed_time > MAX_RAMP_DOWN_TIME) { gpstate_idx = pstate_to_idx(freq_data.pstate_id); + lpstate_idx = gpstate_idx; reset_gpstates(policy); gpstates->highest_lpstate_idx = gpstate_idx; } else { + lpstate_idx = pstate_to_idx(freq_data.pstate_id); gpstate_idx = calc_global_pstate(gpstates->elapsed_time, gpstates->highest_lpstate_idx, - gpstates->last_lpstate_idx); + lpstate_idx); } - + freq_data.gpstate_id = idx_to_pstate(gpstate_idx); + gpstates->last_gpstate_idx = gpstate_idx; + gpstates->last_lpstate_idx = lpstate_idx; /* * If local pstate is equal to global pstate, rampdown is over * So timer is not required to be queued. @@ -622,10 +643,6 @@ void gpstate_timer_handler(unsigned long data) if (gpstate_idx != gpstates->last_lpstate_idx) queue_gpstate_timer(gpstates); - freq_data.gpstate_id = idx_to_pstate(gpstate_idx); - gpstates->last_gpstate_idx = pstate_to_idx(freq_data.gpstate_id); - gpstates->last_lpstate_idx = pstate_to_idx(freq_data.pstate_id); - spin_unlock(&gpstates->gpstate_lock); /* Timer may get migrated to a different cpu on cpu hot unplug */ @@ -647,8 +664,14 @@ static int powernv_cpufreq_target_index(struct cpufreq_policy *policy, if (unlikely(rebooting) && new_index != get_nominal_index()) return 0; - if (!throttled) + if (!throttled) { + /* we don't want to be preempted while + * checking if the CPU frequency has been throttled + */ + preempt_disable(); powernv_cpufreq_throttle_check(NULL); + preempt_enable(); + } cur_msec = jiffies_to_msecs(get_jiffies_64()); @@ -752,9 +775,12 @@ static int powernv_cpufreq_cpu_init(struct cpufreq_policy *policy) spin_lock_init(&gpstates->gpstate_lock); ret = cpufreq_table_validate_and_show(policy, powernv_freqs); - if (ret < 0) + if (ret < 0) { kfree(policy->driver_data); + return ret; + } + policy->fast_switch_possible = true; return ret; } @@ -897,6 +923,20 @@ static void powernv_cpufreq_stop_cpu(struct cpufreq_policy *policy) del_timer_sync(&gpstates->timer); } +static unsigned int powernv_fast_switch(struct cpufreq_policy *policy, + unsigned int target_freq) +{ + int index; + struct powernv_smp_call_data freq_data; + + index = cpufreq_table_find_index_dl(policy, target_freq); + freq_data.pstate_id = powernv_freqs[index].driver_data; + freq_data.gpstate_id = powernv_freqs[index].driver_data; + set_pstate(&freq_data); + + return powernv_freqs[index].frequency; +} + static struct cpufreq_driver powernv_cpufreq_driver = { .name = "powernv-cpufreq", .flags = CPUFREQ_CONST_LOOPS, @@ -904,6 +944,7 @@ static struct cpufreq_driver powernv_cpufreq_driver = { .exit = powernv_cpufreq_cpu_exit, .verify = cpufreq_generic_frequency_table_verify, .target_index = powernv_cpufreq_target_index, + .fast_switch = powernv_fast_switch, .get = powernv_cpufreq_get, .stop_cpu = powernv_cpufreq_stop_cpu, .attr = powernv_cpu_freq_attr, diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c index 7fe442ca38f4..0835a37a5f3a 100644 --- a/drivers/cpuidle/cpuidle-powernv.c +++ b/drivers/cpuidle/cpuidle-powernv.c @@ -22,7 +22,7 @@ #define POWERNV_THRESHOLD_LATENCY_NS 200000 -struct cpuidle_driver powernv_idle_driver = { +static struct cpuidle_driver powernv_idle_driver = { .name = "powernv_idle", .owner = THIS_MODULE, }; diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index c73207abb5a4..62810ff3b00f 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -97,7 +97,23 @@ static int find_deepest_state(struct cpuidle_driver *drv, return ret; } -#ifdef CONFIG_SUSPEND +/** + * cpuidle_use_deepest_state - Set/clear governor override flag. + * @enable: New value of the flag. + * + * Set/unset the current CPU to use the deepest idle state (override governors + * going forward if set). + */ +void cpuidle_use_deepest_state(bool enable) +{ + struct cpuidle_device *dev; + + preempt_disable(); + dev = cpuidle_get_device(); + dev->use_deepest_state = enable; + preempt_enable(); +} + /** * cpuidle_find_deepest_state - Find the deepest available idle state. * @drv: cpuidle driver for the given CPU. @@ -109,6 +125,7 @@ int cpuidle_find_deepest_state(struct cpuidle_driver *drv, return find_deepest_state(drv, dev, UINT_MAX, 0, false); } +#ifdef CONFIG_SUSPEND static void enter_freeze_proper(struct cpuidle_driver *drv, struct cpuidle_device *dev, int index) { diff --git a/drivers/cpuidle/dt_idle_states.c b/drivers/cpuidle/dt_idle_states.c index a5c111b67f37..ffca4fc0061d 100644 --- a/drivers/cpuidle/dt_idle_states.c +++ b/drivers/cpuidle/dt_idle_states.c @@ -38,6 +38,12 @@ static int init_state_node(struct cpuidle_state *idle_state, * state enter function. */ idle_state->enter = match_id->data; + /* + * Since this is not a "coupled" state, it's safe to assume interrupts + * won't be enabled when it exits allowing the tick to be frozen + * safely. So enter() can be also enter_freeze() callback. + */ + idle_state->enter_freeze = match_id->data; err = of_property_read_u32(state_node, "wakeup-latency-us", &idle_state->exit_latency); diff --git a/drivers/cpuidle/governor.c b/drivers/cpuidle/governor.c index fb9f511cca23..4e78263e34a4 100644 --- a/drivers/cpuidle/governor.c +++ b/drivers/cpuidle/governor.c @@ -9,7 +9,6 @@ */ #include <linux/mutex.h> -#include <linux/module.h> #include <linux/cpuidle.h> #include "cpuidle.h" @@ -53,14 +52,11 @@ int cpuidle_switch_governor(struct cpuidle_governor *gov) if (cpuidle_curr_governor) { list_for_each_entry(dev, &cpuidle_detected_devices, device_list) cpuidle_disable_device(dev); - module_put(cpuidle_curr_governor->owner); } cpuidle_curr_governor = gov; if (gov) { - if (!try_module_get(cpuidle_curr_governor->owner)) - return -EINVAL; list_for_each_entry(dev, &cpuidle_detected_devices, device_list) cpuidle_enable_device(dev); cpuidle_install_idle_handler(); diff --git a/drivers/cpuidle/governors/ladder.c b/drivers/cpuidle/governors/ladder.c index 63bd5a403e22..fe8f08948fcb 100644 --- a/drivers/cpuidle/governors/ladder.c +++ b/drivers/cpuidle/governors/ladder.c @@ -15,7 +15,6 @@ #include <linux/kernel.h> #include <linux/cpuidle.h> #include <linux/pm_qos.h> -#include <linux/module.h> #include <linux/jiffies.h> #include <linux/tick.h> @@ -177,7 +176,6 @@ static struct cpuidle_governor ladder_governor = { .enable = ladder_enable_device, .select = ladder_select_state, .reflect = ladder_reflect, - .owner = THIS_MODULE, }; /** diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c index 03d38c291de6..d9b5b9398a0f 100644 --- a/drivers/cpuidle/governors/menu.c +++ b/drivers/cpuidle/governors/menu.c @@ -19,7 +19,6 @@ #include <linux/tick.h> #include <linux/sched.h> #include <linux/math64.h> -#include <linux/module.h> /* * Please note when changing the tuning values: @@ -484,7 +483,6 @@ static struct cpuidle_governor menu_governor = { .enable = menu_enable_device, .select = menu_select, .reflect = menu_reflect, - .owner = THIS_MODULE, }; /** diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c index 832a2c3f01ff..c5adc8c9ac43 100644 --- a/drivers/cpuidle/sysfs.c +++ b/drivers/cpuidle/sysfs.c @@ -403,8 +403,10 @@ static int cpuidle_add_state_sysfs(struct cpuidle_device *device) /* state statistics */ for (i = 0; i < drv->state_count; i++) { kobj = kzalloc(sizeof(struct cpuidle_state_kobj), GFP_KERNEL); - if (!kobj) + if (!kobj) { + ret = -ENOMEM; goto error_state; + } kobj->state = &drv->states[i]; kobj->state_usage = &device->states_usage[i]; init_completion(&kobj->kobj_unregister); diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c index 72ff19658985..e483b78c6343 100644 --- a/drivers/crypto/caam/ctrl.c +++ b/drivers/crypto/caam/ctrl.c @@ -558,8 +558,9 @@ static int caam_probe(struct platform_device *pdev) * Enable DECO watchdogs and, if this is a PHYS_ADDR_T_64BIT kernel, * long pointers in master configuration register */ - clrsetbits_32(&ctrl->mcr, MCFGR_AWCACHE_MASK, MCFGR_AWCACHE_CACH | - MCFGR_AWCACHE_BUFF | MCFGR_WDENABLE | MCFGR_LARGE_BURST | + clrsetbits_32(&ctrl->mcr, MCFGR_AWCACHE_MASK | MCFGR_LONG_PTR, + MCFGR_AWCACHE_CACH | MCFGR_AWCACHE_BUFF | + MCFGR_WDENABLE | MCFGR_LARGE_BURST | (sizeof(dma_addr_t) == sizeof(u64) ? MCFGR_LONG_PTR : 0)); /* diff --git a/drivers/crypto/chelsio/chcr_algo.h b/drivers/crypto/chelsio/chcr_algo.h index ec64fbcdeb49..199b0bb69b89 100644 --- a/drivers/crypto/chelsio/chcr_algo.h +++ b/drivers/crypto/chelsio/chcr_algo.h @@ -422,7 +422,7 @@ static inline void get_aes_decrypt_key(unsigned char *dec_key, { u32 temp; u32 w_ring[MAX_NK]; - int i, j, k = 0; + int i, j, k; u8 nr, nk; switch (keylength) { @@ -460,6 +460,7 @@ static inline void get_aes_decrypt_key(unsigned char *dec_key, temp = w_ring[i % nk]; i++; } + i--; for (k = 0, j = i % nk; k < nk; k++) { *((u32 *)dec_key + k) = htonl(w_ring[j]); j--; diff --git a/drivers/crypto/marvell/hash.c b/drivers/crypto/marvell/hash.c index 9f284682c091..77712b375b84 100644 --- a/drivers/crypto/marvell/hash.c +++ b/drivers/crypto/marvell/hash.c @@ -168,12 +168,11 @@ static void mv_cesa_ahash_std_step(struct ahash_request *req) mv_cesa_adjust_op(engine, &creq->op_tmpl); memcpy_toio(engine->sram, &creq->op_tmpl, sizeof(creq->op_tmpl)); - digsize = crypto_ahash_digestsize(crypto_ahash_reqtfm(req)); - for (i = 0; i < digsize / 4; i++) - writel_relaxed(creq->state[i], engine->regs + CESA_IVDIG(i)); - - mv_cesa_adjust_op(engine, &creq->op_tmpl); - memcpy_toio(engine->sram, &creq->op_tmpl, sizeof(creq->op_tmpl)); + if (!sreq->offset) { + digsize = crypto_ahash_digestsize(crypto_ahash_reqtfm(req)); + for (i = 0; i < digsize / 4; i++) + writel_relaxed(creq->state[i], engine->regs + CESA_IVDIG(i)); + } if (creq->cache_ptr) memcpy_toio(engine->sram + CESA_SA_DATA_SRAM_OFFSET, diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c index 0e499bfca41c..286447a83dab 100644 --- a/drivers/dax/dax.c +++ b/drivers/dax/dax.c @@ -270,8 +270,8 @@ static int check_vma(struct dax_dev *dax_dev, struct vm_area_struct *vma, if (!dax_dev->alive) return -ENXIO; - /* prevent private / writable mappings from being established */ - if ((vma->vm_flags & (VM_NORESERVE|VM_SHARED|VM_WRITE)) == VM_WRITE) { + /* prevent private mappings from being established */ + if ((vma->vm_flags & VM_MAYSHARE) != VM_MAYSHARE) { dev_info(dev, "%s: %s: fail, attempted private mapping\n", current->comm, func); return -EINVAL; diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c index 4a15fa5df98b..73c6ce93a0d9 100644 --- a/drivers/dax/pmem.c +++ b/drivers/dax/pmem.c @@ -78,7 +78,9 @@ static int dax_pmem_probe(struct device *dev) nsio = to_nd_namespace_io(&ndns->dev); /* parse the 'pfn' info block via ->rw_bytes */ - devm_nsio_enable(dev, nsio); + rc = devm_nsio_enable(dev, nsio); + if (rc) + return rc; altmap = nvdimm_setup_pfn(nd_pfn, &res, &__altmap); if (IS_ERR(altmap)) return PTR_ERR(altmap); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 496f72b134eb..05c2850c04b0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -2472,6 +2472,7 @@ void amdgpu_driver_postclose_kms(struct drm_device *dev, struct drm_file *file_priv); void amdgpu_driver_preclose_kms(struct drm_device *dev, struct drm_file *file_priv); +int amdgpu_suspend(struct amdgpu_device *adev); int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon); int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon); u32 amdgpu_get_vblank_counter_kms(struct drm_device *dev, unsigned int pipe); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c index dae35a96a694..6c343a933182 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c @@ -34,6 +34,7 @@ struct amdgpu_atpx { static struct amdgpu_atpx_priv { bool atpx_detected; + bool bridge_pm_usable; /* handle for device - and atpx */ acpi_handle dhandle; acpi_handle other_handle; @@ -205,7 +206,11 @@ static int amdgpu_atpx_validate(struct amdgpu_atpx *atpx) atpx->is_hybrid = false; if (valid_bits & ATPX_MS_HYBRID_GFX_SUPPORTED) { printk("ATPX Hybrid Graphics\n"); - atpx->functions.power_cntl = false; + /* + * Disable legacy PM methods only when pcie port PM is usable, + * otherwise the device might fail to power off or power on. + */ + atpx->functions.power_cntl = !amdgpu_atpx_priv.bridge_pm_usable; atpx->is_hybrid = true; } @@ -555,17 +560,25 @@ static bool amdgpu_atpx_detect(void) struct pci_dev *pdev = NULL; bool has_atpx = false; int vga_count = 0; + bool d3_supported = false; + struct pci_dev *parent_pdev; while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_VGA << 8, pdev)) != NULL) { vga_count++; has_atpx |= (amdgpu_atpx_pci_probe_handle(pdev) == true); + + parent_pdev = pci_upstream_bridge(pdev); + d3_supported |= parent_pdev && parent_pdev->bridge_d3; } while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_OTHER << 8, pdev)) != NULL) { vga_count++; has_atpx |= (amdgpu_atpx_pci_probe_handle(pdev) == true); + + parent_pdev = pci_upstream_bridge(pdev); + d3_supported |= parent_pdev && parent_pdev->bridge_d3; } if (has_atpx && vga_count == 2) { @@ -573,6 +586,7 @@ static bool amdgpu_atpx_detect(void) printk(KERN_INFO "vga_switcheroo: detected switching method %s handle\n", acpi_method_name); amdgpu_atpx_priv.atpx_detected = true; + amdgpu_atpx_priv.bridge_pm_usable = d3_supported; amdgpu_atpx_init(); return true; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 3161d77bf299..e41d4baebf86 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -1493,7 +1493,7 @@ static int amdgpu_fini(struct amdgpu_device *adev) return 0; } -static int amdgpu_suspend(struct amdgpu_device *adev) +int amdgpu_suspend(struct amdgpu_device *adev) { int i, r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 02ff0747197c..e0890deccb2f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -479,12 +479,15 @@ amdgpu_pci_remove(struct pci_dev *pdev) static void amdgpu_pci_shutdown(struct pci_dev *pdev) { + struct drm_device *dev = pci_get_drvdata(pdev); + struct amdgpu_device *adev = dev->dev_private; + /* if we are running in a VM, make sure the device * torn down properly on reboot/shutdown. * unfortunately we can't detect certain * hypervisors so just do this all the time. */ - amdgpu_pci_remove(pdev); + amdgpu_suspend(adev); } static int amdgpu_pmops_suspend(struct device *dev) diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c index 13f2b705ea49..08cd0bd3ebe5 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c @@ -2984,19 +2984,19 @@ static int smu7_get_pp_table_entry_callback_func_v0(struct pp_hwmgr *hwmgr, if (!(data->mc_micro_code_feature & DISABLE_MC_LOADMICROCODE) && memory_clock > data->highest_mclk) data->highest_mclk = memory_clock; - performance_level = &(ps->performance_levels - [ps->performance_level_count++]); - PP_ASSERT_WITH_CODE( (ps->performance_level_count < smum_get_mac_definition(hwmgr->smumgr, SMU_MAX_LEVELS_GRAPHICS)), "Performance levels exceeds SMC limit!", return -EINVAL); PP_ASSERT_WITH_CODE( - (ps->performance_level_count <= + (ps->performance_level_count < hwmgr->platform_descriptor.hardwareActivityPerformanceLevels), - "Performance levels exceeds Driver limit!", - return -EINVAL); + "Performance levels exceeds Driver limit, Skip!", + return 0); + + performance_level = &(ps->performance_levels + [ps->performance_level_count++]); /* Performance levels are arranged from low to high. */ performance_level->memory_clock = memory_clock; diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smc.c b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smc.c index 4ccc0b72324d..71bb2f8dc157 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smc.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smc.c @@ -2214,6 +2214,7 @@ uint32_t polaris10_get_mac_definition(uint32_t value) int polaris10_process_firmware_header(struct pp_hwmgr *hwmgr) { struct polaris10_smumgr *smu_data = (struct polaris10_smumgr *)(hwmgr->smumgr->backend); + struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend); uint32_t tmp; int result; bool error = false; @@ -2233,8 +2234,10 @@ int polaris10_process_firmware_header(struct pp_hwmgr *hwmgr) offsetof(SMU74_Firmware_Header, SoftRegisters), &tmp, SMC_RAM_END); - if (!result) + if (!result) { + data->soft_regs_start = tmp; smu_data->smu7_data.soft_regs_start = tmp; + } error |= (0 != result); diff --git a/drivers/gpu/drm/arm/hdlcd_crtc.c b/drivers/gpu/drm/arm/hdlcd_crtc.c index 48019ae22ddb..28341b32067f 100644 --- a/drivers/gpu/drm/arm/hdlcd_crtc.c +++ b/drivers/gpu/drm/arm/hdlcd_crtc.c @@ -150,15 +150,14 @@ static void hdlcd_crtc_enable(struct drm_crtc *crtc) clk_prepare_enable(hdlcd->clk); hdlcd_crtc_mode_set_nofb(crtc); hdlcd_write(hdlcd, HDLCD_REG_COMMAND, 1); + drm_crtc_vblank_on(crtc); } static void hdlcd_crtc_disable(struct drm_crtc *crtc) { struct hdlcd_drm_private *hdlcd = crtc_to_hdlcd_priv(crtc); - if (!crtc->state->active) - return; - + drm_crtc_vblank_off(crtc); hdlcd_write(hdlcd, HDLCD_REG_COMMAND, 0); clk_disable_unprepare(hdlcd->clk); } diff --git a/drivers/gpu/drm/arm/hdlcd_drv.c b/drivers/gpu/drm/arm/hdlcd_drv.c index fb6a418ce6be..e138fb51e8ce 100644 --- a/drivers/gpu/drm/arm/hdlcd_drv.c +++ b/drivers/gpu/drm/arm/hdlcd_drv.c @@ -375,7 +375,6 @@ static int hdlcd_drm_bind(struct device *dev) err_fbdev: drm_kms_helper_poll_fini(drm); - drm_mode_config_cleanup(drm); drm_vblank_cleanup(drm); err_vblank: pm_runtime_disable(drm->dev); @@ -387,6 +386,7 @@ err_unload: drm_irq_uninstall(drm); of_reserved_mem_device_release(drm->dev); err_free: + drm_mode_config_cleanup(drm); dev_set_drvdata(dev, NULL); drm_dev_unref(drm); diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c index 0ad2c47f808f..71c3473476c7 100644 --- a/drivers/gpu/drm/drm_ioctl.c +++ b/drivers/gpu/drm/drm_ioctl.c @@ -254,10 +254,12 @@ static int drm_getcap(struct drm_device *dev, void *data, struct drm_file *file_ req->value = dev->mode_config.async_page_flip; break; case DRM_CAP_PAGE_FLIP_TARGET: - req->value = 1; - drm_for_each_crtc(crtc, dev) { - if (!crtc->funcs->page_flip_target) - req->value = 0; + if (drm_core_check_feature(dev, DRIVER_MODESET)) { + req->value = 1; + drm_for_each_crtc(crtc, dev) { + if (!crtc->funcs->page_flip_target) + req->value = 0; + } } break; case DRM_CAP_CURSOR_WIDTH: diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c index e8fb6ef947ee..38eaa63afb31 100644 --- a/drivers/gpu/drm/exynos/exynos_hdmi.c +++ b/drivers/gpu/drm/exynos/exynos_hdmi.c @@ -1907,6 +1907,8 @@ err_disable_pm_runtime: err_hdmiphy: if (hdata->hdmiphy_port) put_device(&hdata->hdmiphy_port->dev); + if (hdata->regs_hdmiphy) + iounmap(hdata->regs_hdmiphy); err_ddc: put_device(&hdata->ddc_adpt->dev); @@ -1929,6 +1931,9 @@ static int hdmi_remove(struct platform_device *pdev) if (hdata->hdmiphy_port) put_device(&hdata->hdmiphy_port->dev); + if (hdata->regs_hdmiphy) + iounmap(hdata->regs_hdmiphy); + put_device(&hdata->ddc_adpt->dev); return 0; diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 91ab7e9d6d2e..00eb4814b913 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -2268,7 +2268,7 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj) page = shmem_read_mapping_page(mapping, i); if (IS_ERR(page)) { ret = PTR_ERR(page); - goto err_pages; + goto err_sg; } } #ifdef CONFIG_SWIOTLB @@ -2311,8 +2311,9 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj) return 0; -err_pages: +err_sg: sg_mark_end(sg); +err_pages: for_each_sgt_page(page, sgt_iter, st) put_page(page); sg_free_table(st); diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 81c11499bcf0..3cb70d73239b 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -12260,7 +12260,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc, intel_crtc->reset_count = i915_reset_count(&dev_priv->gpu_error); if (i915_reset_in_progress_or_wedged(&dev_priv->gpu_error)) { ret = -EIO; - goto cleanup; + goto unlock; } atomic_inc(&intel_crtc->unpin_work_count); @@ -12352,6 +12352,7 @@ cleanup_unpin: intel_unpin_fb_obj(fb, crtc->primary->state->rotation); cleanup_pending: atomic_dec(&intel_crtc->unpin_work_count); +unlock: mutex_unlock(&dev->struct_mutex); cleanup: crtc->primary->fb = old_fb; diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c index f75c5b5a536c..c70310206ac5 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c @@ -251,13 +251,6 @@ static int mtk_disp_ovl_probe(struct platform_device *pdev) if (irq < 0) return irq; - ret = devm_request_irq(dev, irq, mtk_disp_ovl_irq_handler, - IRQF_TRIGGER_NONE, dev_name(dev), priv); - if (ret < 0) { - dev_err(dev, "Failed to request irq %d: %d\n", irq, ret); - return ret; - } - comp_id = mtk_ddp_comp_get_id(dev->of_node, MTK_DISP_OVL); if (comp_id < 0) { dev_err(dev, "Failed to identify by alias: %d\n", comp_id); @@ -273,6 +266,13 @@ static int mtk_disp_ovl_probe(struct platform_device *pdev) platform_set_drvdata(pdev, priv); + ret = devm_request_irq(dev, irq, mtk_disp_ovl_irq_handler, + IRQF_TRIGGER_NONE, dev_name(dev), priv); + if (ret < 0) { + dev_err(dev, "Failed to request irq %d: %d\n", irq, ret); + return ret; + } + ret = component_add(dev, &mtk_disp_ovl_component_ops); if (ret) dev_err(dev, "Failed to add component: %d\n", ret); diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c index df33b3ca6ffd..48cc01fd20c7 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c @@ -123,7 +123,7 @@ static void mtk_od_config(struct mtk_ddp_comp *comp, unsigned int w, unsigned int bpc) { writel(w << 16 | h, comp->regs + DISP_OD_SIZE); - writel(OD_RELAYMODE, comp->regs + OD_RELAYMODE); + writel(OD_RELAYMODE, comp->regs + DISP_OD_CFG); mtk_dither_set(comp, bpc, DISP_OD_CFG); } diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index 28b2044ed9f2..eaa5a2240c0c 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -86,7 +86,7 @@ #define DSI_PHY_TIMECON0 0x110 #define LPX (0xff << 0) -#define HS_PRPR (0xff << 8) +#define HS_PREP (0xff << 8) #define HS_ZERO (0xff << 16) #define HS_TRAIL (0xff << 24) @@ -102,10 +102,16 @@ #define CLK_TRAIL (0xff << 24) #define DSI_PHY_TIMECON3 0x11c -#define CLK_HS_PRPR (0xff << 0) +#define CLK_HS_PREP (0xff << 0) #define CLK_HS_POST (0xff << 8) #define CLK_HS_EXIT (0xff << 16) +#define T_LPX 5 +#define T_HS_PREP 6 +#define T_HS_TRAIL 8 +#define T_HS_EXIT 7 +#define T_HS_ZERO 10 + #define NS_TO_CYCLE(n, c) ((n) / (c) + (((n) % (c)) ? 1 : 0)) struct phy; @@ -161,20 +167,18 @@ static void mtk_dsi_mask(struct mtk_dsi *dsi, u32 offset, u32 mask, u32 data) static void dsi_phy_timconfig(struct mtk_dsi *dsi) { u32 timcon0, timcon1, timcon2, timcon3; - unsigned int ui, cycle_time; - unsigned int lpx; + u32 ui, cycle_time; ui = 1000 / dsi->data_rate + 0x01; cycle_time = 8000 / dsi->data_rate + 0x01; - lpx = 5; - timcon0 = (8 << 24) | (0xa << 16) | (0x6 << 8) | lpx; - timcon1 = (7 << 24) | (5 * lpx << 16) | ((3 * lpx) / 2) << 8 | - (4 * lpx); + timcon0 = T_LPX | T_HS_PREP << 8 | T_HS_ZERO << 16 | T_HS_TRAIL << 24; + timcon1 = 4 * T_LPX | (3 * T_LPX / 2) << 8 | 5 * T_LPX << 16 | + T_HS_EXIT << 24; timcon2 = ((NS_TO_CYCLE(0x64, cycle_time) + 0xa) << 24) | (NS_TO_CYCLE(0x150, cycle_time) << 16); - timcon3 = (2 * lpx) << 16 | NS_TO_CYCLE(80 + 52 * ui, cycle_time) << 8 | - NS_TO_CYCLE(0x40, cycle_time); + timcon3 = NS_TO_CYCLE(0x40, cycle_time) | (2 * T_LPX) << 16 | + NS_TO_CYCLE(80 + 52 * ui, cycle_time) << 8; writel(timcon0, dsi->regs + DSI_PHY_TIMECON0); writel(timcon1, dsi->regs + DSI_PHY_TIMECON1); @@ -202,19 +206,47 @@ static int mtk_dsi_poweron(struct mtk_dsi *dsi) { struct device *dev = dsi->dev; int ret; + u64 pixel_clock, total_bits; + u32 htotal, htotal_bits, bit_per_pixel, overhead_cycles, overhead_bits; if (++dsi->refcount != 1) return 0; + switch (dsi->format) { + case MIPI_DSI_FMT_RGB565: + bit_per_pixel = 16; + break; + case MIPI_DSI_FMT_RGB666_PACKED: + bit_per_pixel = 18; + break; + case MIPI_DSI_FMT_RGB666: + case MIPI_DSI_FMT_RGB888: + default: + bit_per_pixel = 24; + break; + } + /** - * data_rate = (pixel_clock / 1000) * pixel_dipth * mipi_ratio; - * pixel_clock unit is Khz, data_rata unit is MHz, so need divide 1000. - * mipi_ratio is mipi clk coefficient for balance the pixel clk in mipi. - * we set mipi_ratio is 1.05. + * vm.pixelclock is in kHz, pixel_clock unit is Hz, so multiply by 1000 + * htotal_time = htotal * byte_per_pixel / num_lanes + * overhead_time = lpx + hs_prepare + hs_zero + hs_trail + hs_exit + * mipi_ratio = (htotal_time + overhead_time) / htotal_time + * data_rate = pixel_clock * bit_per_pixel * mipi_ratio / num_lanes; */ - dsi->data_rate = dsi->vm.pixelclock * 3 * 21 / (1 * 1000 * 10); + pixel_clock = dsi->vm.pixelclock * 1000; + htotal = dsi->vm.hactive + dsi->vm.hback_porch + dsi->vm.hfront_porch + + dsi->vm.hsync_len; + htotal_bits = htotal * bit_per_pixel; + + overhead_cycles = T_LPX + T_HS_PREP + T_HS_ZERO + T_HS_TRAIL + + T_HS_EXIT; + overhead_bits = overhead_cycles * dsi->lanes * 8; + total_bits = htotal_bits + overhead_bits; + + dsi->data_rate = DIV_ROUND_UP_ULL(pixel_clock * total_bits, + htotal * dsi->lanes); - ret = clk_set_rate(dsi->hs_clk, dsi->data_rate * 1000000); + ret = clk_set_rate(dsi->hs_clk, dsi->data_rate); if (ret < 0) { dev_err(dev, "Failed to set data rate: %d\n", ret); goto err_refcount; diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c index 2fdcd04bc93f..0ae13cd2adda 100644 --- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c +++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c @@ -34,6 +34,7 @@ struct radeon_atpx { static struct radeon_atpx_priv { bool atpx_detected; + bool bridge_pm_usable; /* handle for device - and atpx */ acpi_handle dhandle; struct radeon_atpx atpx; @@ -203,7 +204,11 @@ static int radeon_atpx_validate(struct radeon_atpx *atpx) atpx->is_hybrid = false; if (valid_bits & ATPX_MS_HYBRID_GFX_SUPPORTED) { printk("ATPX Hybrid Graphics\n"); - atpx->functions.power_cntl = false; + /* + * Disable legacy PM methods only when pcie port PM is usable, + * otherwise the device might fail to power off or power on. + */ + atpx->functions.power_cntl = !radeon_atpx_priv.bridge_pm_usable; atpx->is_hybrid = true; } @@ -548,11 +553,16 @@ static bool radeon_atpx_detect(void) struct pci_dev *pdev = NULL; bool has_atpx = false; int vga_count = 0; + bool d3_supported = false; + struct pci_dev *parent_pdev; while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_VGA << 8, pdev)) != NULL) { vga_count++; has_atpx |= (radeon_atpx_pci_probe_handle(pdev) == true); + + parent_pdev = pci_upstream_bridge(pdev); + d3_supported |= parent_pdev && parent_pdev->bridge_d3; } /* some newer PX laptops mark the dGPU as a non-VGA display device */ @@ -560,6 +570,9 @@ static bool radeon_atpx_detect(void) vga_count++; has_atpx |= (radeon_atpx_pci_probe_handle(pdev) == true); + + parent_pdev = pci_upstream_bridge(pdev); + d3_supported |= parent_pdev && parent_pdev->bridge_d3; } if (has_atpx && vga_count == 2) { @@ -567,6 +580,7 @@ static bool radeon_atpx_detect(void) printk(KERN_INFO "vga_switcheroo: detected switching method %s handle\n", acpi_method_name); radeon_atpx_priv.atpx_detected = true; + radeon_atpx_priv.bridge_pm_usable = d3_supported; radeon_atpx_init(); return true; } diff --git a/drivers/hid/hid-cp2112.c b/drivers/hid/hid-cp2112.c index 086d8a507157..60d30203a5fa 100644 --- a/drivers/hid/hid-cp2112.c +++ b/drivers/hid/hid-cp2112.c @@ -32,6 +32,11 @@ #include <linux/usb/ch9.h> #include "hid-ids.h" +#define CP2112_REPORT_MAX_LENGTH 64 +#define CP2112_GPIO_CONFIG_LENGTH 5 +#define CP2112_GPIO_GET_LENGTH 2 +#define CP2112_GPIO_SET_LENGTH 3 + enum { CP2112_GPIO_CONFIG = 0x02, CP2112_GPIO_GET = 0x03, @@ -161,6 +166,8 @@ struct cp2112_device { atomic_t read_avail; atomic_t xfer_avail; struct gpio_chip gc; + u8 *in_out_buffer; + spinlock_t lock; }; static int gpio_push_pull = 0xFF; @@ -171,62 +178,86 @@ static int cp2112_gpio_direction_input(struct gpio_chip *chip, unsigned offset) { struct cp2112_device *dev = gpiochip_get_data(chip); struct hid_device *hdev = dev->hdev; - u8 buf[5]; + u8 *buf = dev->in_out_buffer; + unsigned long flags; int ret; + spin_lock_irqsave(&dev->lock, flags); + ret = hid_hw_raw_request(hdev, CP2112_GPIO_CONFIG, buf, - sizeof(buf), HID_FEATURE_REPORT, - HID_REQ_GET_REPORT); - if (ret != sizeof(buf)) { + CP2112_GPIO_CONFIG_LENGTH, HID_FEATURE_REPORT, + HID_REQ_GET_REPORT); + if (ret != CP2112_GPIO_CONFIG_LENGTH) { hid_err(hdev, "error requesting GPIO config: %d\n", ret); - return ret; + goto exit; } buf[1] &= ~(1 << offset); buf[2] = gpio_push_pull; - ret = hid_hw_raw_request(hdev, CP2112_GPIO_CONFIG, buf, sizeof(buf), - HID_FEATURE_REPORT, HID_REQ_SET_REPORT); + ret = hid_hw_raw_request(hdev, CP2112_GPIO_CONFIG, buf, + CP2112_GPIO_CONFIG_LENGTH, HID_FEATURE_REPORT, + HID_REQ_SET_REPORT); if (ret < 0) { hid_err(hdev, "error setting GPIO config: %d\n", ret); - return ret; + goto exit; } - return 0; + ret = 0; + +exit: + spin_unlock_irqrestore(&dev->lock, flags); + return ret <= 0 ? ret : -EIO; } static void cp2112_gpio_set(struct gpio_chip *chip, unsigned offset, int value) { struct cp2112_device *dev = gpiochip_get_data(chip); struct hid_device *hdev = dev->hdev; - u8 buf[3]; + u8 *buf = dev->in_out_buffer; + unsigned long flags; int ret; + spin_lock_irqsave(&dev->lock, flags); + buf[0] = CP2112_GPIO_SET; buf[1] = value ? 0xff : 0; buf[2] = 1 << offset; - ret = hid_hw_raw_request(hdev, CP2112_GPIO_SET, buf, sizeof(buf), - HID_FEATURE_REPORT, HID_REQ_SET_REPORT); + ret = hid_hw_raw_request(hdev, CP2112_GPIO_SET, buf, + CP2112_GPIO_SET_LENGTH, HID_FEATURE_REPORT, + HID_REQ_SET_REPORT); if (ret < 0) hid_err(hdev, "error setting GPIO values: %d\n", ret); + + spin_unlock_irqrestore(&dev->lock, flags); } static int cp2112_gpio_get(struct gpio_chip *chip, unsigned offset) { struct cp2112_device *dev = gpiochip_get_data(chip); struct hid_device *hdev = dev->hdev; - u8 buf[2]; + u8 *buf = dev->in_out_buffer; + unsigned long flags; int ret; - ret = hid_hw_raw_request(hdev, CP2112_GPIO_GET, buf, sizeof(buf), - HID_FEATURE_REPORT, HID_REQ_GET_REPORT); - if (ret != sizeof(buf)) { + spin_lock_irqsave(&dev->lock, flags); + + ret = hid_hw_raw_request(hdev, CP2112_GPIO_GET, buf, + CP2112_GPIO_GET_LENGTH, HID_FEATURE_REPORT, + HID_REQ_GET_REPORT); + if (ret != CP2112_GPIO_GET_LENGTH) { hid_err(hdev, "error requesting GPIO values: %d\n", ret); - return ret; + ret = ret < 0 ? ret : -EIO; + goto exit; } - return (buf[1] >> offset) & 1; + ret = (buf[1] >> offset) & 1; + +exit: + spin_unlock_irqrestore(&dev->lock, flags); + + return ret; } static int cp2112_gpio_direction_output(struct gpio_chip *chip, @@ -234,27 +265,33 @@ static int cp2112_gpio_direction_output(struct gpio_chip *chip, { struct cp2112_device *dev = gpiochip_get_data(chip); struct hid_device *hdev = dev->hdev; - u8 buf[5]; + u8 *buf = dev->in_out_buffer; + unsigned long flags; int ret; + spin_lock_irqsave(&dev->lock, flags); + ret = hid_hw_raw_request(hdev, CP2112_GPIO_CONFIG, buf, - sizeof(buf), HID_FEATURE_REPORT, - HID_REQ_GET_REPORT); - if (ret != sizeof(buf)) { + CP2112_GPIO_CONFIG_LENGTH, HID_FEATURE_REPORT, + HID_REQ_GET_REPORT); + if (ret != CP2112_GPIO_CONFIG_LENGTH) { hid_err(hdev, "error requesting GPIO config: %d\n", ret); - return ret; + goto fail; } buf[1] |= 1 << offset; buf[2] = gpio_push_pull; - ret = hid_hw_raw_request(hdev, CP2112_GPIO_CONFIG, buf, sizeof(buf), - HID_FEATURE_REPORT, HID_REQ_SET_REPORT); + ret = hid_hw_raw_request(hdev, CP2112_GPIO_CONFIG, buf, + CP2112_GPIO_CONFIG_LENGTH, HID_FEATURE_REPORT, + HID_REQ_SET_REPORT); if (ret < 0) { hid_err(hdev, "error setting GPIO config: %d\n", ret); - return ret; + goto fail; } + spin_unlock_irqrestore(&dev->lock, flags); + /* * Set gpio value when output direction is already set, * as specified in AN495, Rev. 0.2, cpt. 4.4 @@ -262,6 +299,10 @@ static int cp2112_gpio_direction_output(struct gpio_chip *chip, cp2112_gpio_set(chip, offset, value); return 0; + +fail: + spin_unlock_irqrestore(&dev->lock, flags); + return ret < 0 ? ret : -EIO; } static int cp2112_hid_get(struct hid_device *hdev, unsigned char report_number, @@ -1007,6 +1048,17 @@ static int cp2112_probe(struct hid_device *hdev, const struct hid_device_id *id) struct cp2112_smbus_config_report config; int ret; + dev = devm_kzalloc(&hdev->dev, sizeof(*dev), GFP_KERNEL); + if (!dev) + return -ENOMEM; + + dev->in_out_buffer = devm_kzalloc(&hdev->dev, CP2112_REPORT_MAX_LENGTH, + GFP_KERNEL); + if (!dev->in_out_buffer) + return -ENOMEM; + + spin_lock_init(&dev->lock); + ret = hid_parse(hdev); if (ret) { hid_err(hdev, "parse failed\n"); @@ -1063,12 +1115,6 @@ static int cp2112_probe(struct hid_device *hdev, const struct hid_device_id *id) goto err_power_normal; } - dev = kzalloc(sizeof(*dev), GFP_KERNEL); - if (!dev) { - ret = -ENOMEM; - goto err_power_normal; - } - hid_set_drvdata(hdev, (void *)dev); dev->hdev = hdev; dev->adap.owner = THIS_MODULE; @@ -1087,7 +1133,7 @@ static int cp2112_probe(struct hid_device *hdev, const struct hid_device_id *id) if (ret) { hid_err(hdev, "error registering i2c adapter\n"); - goto err_free_dev; + goto err_power_normal; } hid_dbg(hdev, "adapter registered\n"); @@ -1123,8 +1169,6 @@ err_gpiochip_remove: gpiochip_remove(&dev->gc); err_free_i2c: i2c_del_adapter(&dev->adap); -err_free_dev: - kfree(dev); err_power_normal: hid_hw_power(hdev, PM_HINT_NORMAL); err_hid_close: @@ -1149,7 +1193,6 @@ static void cp2112_remove(struct hid_device *hdev) */ hid_hw_close(hdev); hid_hw_stop(hdev); - kfree(dev); } static int cp2112_raw_event(struct hid_device *hdev, struct hid_report *report, diff --git a/drivers/hid/hid-lg.c b/drivers/hid/hid-lg.c index 76f644deb0a7..c5c5fbe9d605 100644 --- a/drivers/hid/hid-lg.c +++ b/drivers/hid/hid-lg.c @@ -756,11 +756,16 @@ static int lg_probe(struct hid_device *hdev, const struct hid_device_id *id) /* Setup wireless link with Logitech Wii wheel */ if (hdev->product == USB_DEVICE_ID_LOGITECH_WII_WHEEL) { - unsigned char buf[] = { 0x00, 0xAF, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }; + const unsigned char cbuf[] = { 0x00, 0xAF, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }; + u8 *buf = kmemdup(cbuf, sizeof(cbuf), GFP_KERNEL); - ret = hid_hw_raw_request(hdev, buf[0], buf, sizeof(buf), - HID_FEATURE_REPORT, HID_REQ_SET_REPORT); + if (!buf) { + ret = -ENOMEM; + goto err_free; + } + ret = hid_hw_raw_request(hdev, buf[0], buf, sizeof(cbuf), + HID_FEATURE_REPORT, HID_REQ_SET_REPORT); if (ret >= 0) { /* insert a little delay of 10 jiffies ~ 40ms */ wait_queue_head_t wait; @@ -772,9 +777,10 @@ static int lg_probe(struct hid_device *hdev, const struct hid_device_id *id) buf[1] = 0xB2; get_random_bytes(&buf[2], 2); - ret = hid_hw_raw_request(hdev, buf[0], buf, sizeof(buf), + ret = hid_hw_raw_request(hdev, buf[0], buf, sizeof(cbuf), HID_FEATURE_REPORT, HID_REQ_SET_REPORT); } + kfree(buf); } if (drv_data->quirks & LG_FF) diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c index d6fa496d0ca2..20b40ad26325 100644 --- a/drivers/hid/hid-magicmouse.c +++ b/drivers/hid/hid-magicmouse.c @@ -493,7 +493,8 @@ static int magicmouse_input_configured(struct hid_device *hdev, static int magicmouse_probe(struct hid_device *hdev, const struct hid_device_id *id) { - __u8 feature[] = { 0xd7, 0x01 }; + const u8 feature[] = { 0xd7, 0x01 }; + u8 *buf; struct magicmouse_sc *msc; struct hid_report *report; int ret; @@ -544,6 +545,12 @@ static int magicmouse_probe(struct hid_device *hdev, } report->size = 6; + buf = kmemdup(feature, sizeof(feature), GFP_KERNEL); + if (!buf) { + ret = -ENOMEM; + goto err_stop_hw; + } + /* * Some devices repond with 'invalid report id' when feature * report switching it into multitouch mode is sent to it. @@ -552,8 +559,9 @@ static int magicmouse_probe(struct hid_device *hdev, * but there seems to be no other way of switching the mode. * Thus the super-ugly hacky success check below. */ - ret = hid_hw_raw_request(hdev, feature[0], feature, sizeof(feature), + ret = hid_hw_raw_request(hdev, buf[0], buf, sizeof(feature), HID_FEATURE_REPORT, HID_REQ_SET_REPORT); + kfree(buf); if (ret != -EIO && ret != sizeof(feature)) { hid_err(hdev, "unable to request touch data (%d)\n", ret); goto err_stop_hw; diff --git a/drivers/hid/hid-rmi.c b/drivers/hid/hid-rmi.c index 9cd2ca34a6be..be89bcbf6a71 100644 --- a/drivers/hid/hid-rmi.c +++ b/drivers/hid/hid-rmi.c @@ -188,10 +188,16 @@ static int rmi_set_page(struct hid_device *hdev, u8 page) static int rmi_set_mode(struct hid_device *hdev, u8 mode) { int ret; - u8 txbuf[2] = {RMI_SET_RMI_MODE_REPORT_ID, mode}; + const u8 txbuf[2] = {RMI_SET_RMI_MODE_REPORT_ID, mode}; + u8 *buf; - ret = hid_hw_raw_request(hdev, RMI_SET_RMI_MODE_REPORT_ID, txbuf, + buf = kmemdup(txbuf, sizeof(txbuf), GFP_KERNEL); + if (!buf) + return -ENOMEM; + + ret = hid_hw_raw_request(hdev, RMI_SET_RMI_MODE_REPORT_ID, buf, sizeof(txbuf), HID_FEATURE_REPORT, HID_REQ_SET_REPORT); + kfree(buf); if (ret < 0) { dev_err(&hdev->dev, "unable to set rmi mode to %d (%d)\n", mode, ret); diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c index c5c3d6111729..60875625cbdf 100644 --- a/drivers/hid/hid-sensor-hub.c +++ b/drivers/hid/hid-sensor-hub.c @@ -212,6 +212,7 @@ int sensor_hub_set_feature(struct hid_sensor_hub_device *hsdev, u32 report_id, __s32 value; int ret = 0; + memset(buffer, 0, buffer_size); mutex_lock(&data->mutex); report = sensor_hub_report(report_id, hsdev->hdev, HID_FEATURE_REPORT); if (!report || (field_index >= report->maxfield)) { diff --git a/drivers/i2c/busses/i2c-designware-core.c b/drivers/i2c/busses/i2c-designware-core.c index 11e866d05368..b403fa5ecf49 100644 --- a/drivers/i2c/busses/i2c-designware-core.c +++ b/drivers/i2c/busses/i2c-designware-core.c @@ -91,9 +91,7 @@ DW_IC_INTR_TX_ABRT | \ DW_IC_INTR_STOP_DET) -#define DW_IC_STATUS_ACTIVITY 0x1 -#define DW_IC_STATUS_TFE BIT(2) -#define DW_IC_STATUS_MST_ACTIVITY BIT(5) +#define DW_IC_STATUS_ACTIVITY 0x1 #define DW_IC_SDA_HOLD_RX_SHIFT 16 #define DW_IC_SDA_HOLD_RX_MASK GENMASK(23, DW_IC_SDA_HOLD_RX_SHIFT) @@ -478,25 +476,9 @@ static void i2c_dw_xfer_init(struct dw_i2c_dev *dev) { struct i2c_msg *msgs = dev->msgs; u32 ic_tar = 0; - bool enabled; - enabled = dw_readl(dev, DW_IC_ENABLE_STATUS) & 1; - - if (enabled) { - u32 ic_status; - - /* - * Only disable adapter if ic_tar and ic_con can't be - * dynamically updated - */ - ic_status = dw_readl(dev, DW_IC_STATUS); - if (!dev->dynamic_tar_update_enabled || - (ic_status & DW_IC_STATUS_MST_ACTIVITY) || - !(ic_status & DW_IC_STATUS_TFE)) { - __i2c_dw_enable_and_wait(dev, false); - enabled = false; - } - } + /* Disable the adapter */ + __i2c_dw_enable_and_wait(dev, false); /* if the slave address is ten bit address, enable 10BITADDR */ if (dev->dynamic_tar_update_enabled) { @@ -526,8 +508,8 @@ static void i2c_dw_xfer_init(struct dw_i2c_dev *dev) /* enforce disabled interrupts (due to HW issues) */ i2c_dw_disable_int(dev); - if (!enabled) - __i2c_dw_enable(dev, true); + /* Enable the adapter */ + __i2c_dw_enable(dev, true); /* Clear and enable interrupts */ dw_readl(dev, DW_IC_CLR_INTR); @@ -611,7 +593,7 @@ i2c_dw_xfer_msg(struct dw_i2c_dev *dev) if (msgs[dev->msg_write_idx].flags & I2C_M_RD) { /* avoid rx buffer overrun */ - if (rx_limit - dev->rx_outstanding <= 0) + if (dev->rx_outstanding >= dev->rx_fifo_depth) break; dw_writel(dev, cmd | 0x100, DW_IC_DATA_CMD); @@ -708,8 +690,7 @@ static int i2c_dw_handle_tx_abort(struct dw_i2c_dev *dev) } /* - * Prepare controller for a transaction and start transfer by calling - * i2c_dw_xfer_init() + * Prepare controller for a transaction and call i2c_dw_xfer_msg */ static int i2c_dw_xfer(struct i2c_adapter *adap, struct i2c_msg msgs[], int num) @@ -752,13 +733,23 @@ i2c_dw_xfer(struct i2c_adapter *adap, struct i2c_msg msgs[], int num) goto done; } + /* + * We must disable the adapter before returning and signaling the end + * of the current transfer. Otherwise the hardware might continue + * generating interrupts which in turn causes a race condition with + * the following transfer. Needs some more investigation if the + * additional interrupts are a hardware bug or this driver doesn't + * handle them correctly yet. + */ + __i2c_dw_enable(dev, false); + if (dev->msg_err) { ret = dev->msg_err; goto done; } /* no error */ - if (likely(!dev->cmd_err)) { + if (likely(!dev->cmd_err && !dev->status)) { ret = num; goto done; } @@ -768,6 +759,11 @@ i2c_dw_xfer(struct i2c_adapter *adap, struct i2c_msg msgs[], int num) ret = i2c_dw_handle_tx_abort(dev); goto done; } + + if (dev->status) + dev_err(dev->dev, + "transfer terminated early - interrupt latency too high?\n"); + ret = -EIO; done: @@ -888,19 +884,9 @@ static irqreturn_t i2c_dw_isr(int this_irq, void *dev_id) */ tx_aborted: - if ((stat & (DW_IC_INTR_TX_ABRT | DW_IC_INTR_STOP_DET)) - || dev->msg_err) { - /* - * We must disable interruts before returning and signaling - * the end of the current transfer. Otherwise the hardware - * might continue generating interrupts for non-existent - * transfers. - */ - i2c_dw_disable_int(dev); - dw_readl(dev, DW_IC_CLR_INTR); - + if ((stat & (DW_IC_INTR_TX_ABRT | DW_IC_INTR_STOP_DET)) || dev->msg_err) complete(&dev->cmd_complete); - } else if (unlikely(dev->accessor_flags & ACCESS_INTR_MASK)) { + else if (unlikely(dev->accessor_flags & ACCESS_INTR_MASK)) { /* workaround to trigger pending interrupt */ stat = dw_readl(dev, DW_IC_INTR_MASK); i2c_dw_disable_int(dev); diff --git a/drivers/i2c/busses/i2c-octeon-core.c b/drivers/i2c/busses/i2c-octeon-core.c index 419b54bfc7c7..5e63b17f935d 100644 --- a/drivers/i2c/busses/i2c-octeon-core.c +++ b/drivers/i2c/busses/i2c-octeon-core.c @@ -381,9 +381,7 @@ static int octeon_i2c_read(struct octeon_i2c *i2c, int target, if (result) return result; - data[i] = octeon_i2c_data_read(i2c, &result); - if (result) - return result; + data[i] = octeon_i2c_data_read(i2c); if (recv_len && i == 0) { if (data[i] > I2C_SMBUS_BLOCK_MAX + 1) return -EPROTO; diff --git a/drivers/i2c/busses/i2c-octeon-core.h b/drivers/i2c/busses/i2c-octeon-core.h index 1db7c835a454..87151ea74acd 100644 --- a/drivers/i2c/busses/i2c-octeon-core.h +++ b/drivers/i2c/busses/i2c-octeon-core.h @@ -5,7 +5,6 @@ #include <linux/i2c.h> #include <linux/i2c-smbus.h> #include <linux/io.h> -#include <linux/iopoll.h> #include <linux/kernel.h> #include <linux/pci.h> @@ -145,9 +144,9 @@ static inline void octeon_i2c_reg_write(struct octeon_i2c *i2c, u64 eop_reg, u8 u64 tmp; __raw_writeq(SW_TWSI_V | eop_reg | data, i2c->twsi_base + SW_TWSI(i2c)); - - readq_poll_timeout(i2c->twsi_base + SW_TWSI(i2c), tmp, tmp & SW_TWSI_V, - I2C_OCTEON_EVENT_WAIT, i2c->adap.timeout); + do { + tmp = __raw_readq(i2c->twsi_base + SW_TWSI(i2c)); + } while ((tmp & SW_TWSI_V) != 0); } #define octeon_i2c_ctl_write(i2c, val) \ @@ -164,28 +163,24 @@ static inline void octeon_i2c_reg_write(struct octeon_i2c *i2c, u64 eop_reg, u8 * * The I2C core registers are accessed indirectly via the SW_TWSI CSR. */ -static inline int octeon_i2c_reg_read(struct octeon_i2c *i2c, u64 eop_reg, - int *error) +static inline u8 octeon_i2c_reg_read(struct octeon_i2c *i2c, u64 eop_reg) { u64 tmp; - int ret; __raw_writeq(SW_TWSI_V | eop_reg | SW_TWSI_R, i2c->twsi_base + SW_TWSI(i2c)); + do { + tmp = __raw_readq(i2c->twsi_base + SW_TWSI(i2c)); + } while ((tmp & SW_TWSI_V) != 0); - ret = readq_poll_timeout(i2c->twsi_base + SW_TWSI(i2c), tmp, - tmp & SW_TWSI_V, I2C_OCTEON_EVENT_WAIT, - i2c->adap.timeout); - if (error) - *error = ret; return tmp & 0xFF; } #define octeon_i2c_ctl_read(i2c) \ - octeon_i2c_reg_read(i2c, SW_TWSI_EOP_TWSI_CTL, NULL) -#define octeon_i2c_data_read(i2c, error) \ - octeon_i2c_reg_read(i2c, SW_TWSI_EOP_TWSI_DATA, error) + octeon_i2c_reg_read(i2c, SW_TWSI_EOP_TWSI_CTL) +#define octeon_i2c_data_read(i2c) \ + octeon_i2c_reg_read(i2c, SW_TWSI_EOP_TWSI_DATA) #define octeon_i2c_stat_read(i2c) \ - octeon_i2c_reg_read(i2c, SW_TWSI_EOP_TWSI_STAT, NULL) + octeon_i2c_reg_read(i2c, SW_TWSI_EOP_TWSI_STAT) /** * octeon_i2c_read_int - read the TWSI_INT register diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 4466a2f969d7..7d8ea3d5fda6 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -98,8 +98,6 @@ static int intel_idle(struct cpuidle_device *dev, struct cpuidle_driver *drv, int index); static void intel_idle_freeze(struct cpuidle_device *dev, struct cpuidle_driver *drv, int index); -static int intel_idle_cpu_init(int cpu); - static struct cpuidle_state *cpuidle_state_table; /* @@ -724,6 +722,50 @@ static struct cpuidle_state atom_cstates[] = { { .enter = NULL } }; +static struct cpuidle_state tangier_cstates[] = { + { + .name = "C1-TNG", + .desc = "MWAIT 0x00", + .flags = MWAIT2flg(0x00), + .exit_latency = 1, + .target_residency = 4, + .enter = &intel_idle, + .enter_freeze = intel_idle_freeze, }, + { + .name = "C4-TNG", + .desc = "MWAIT 0x30", + .flags = MWAIT2flg(0x30) | CPUIDLE_FLAG_TLB_FLUSHED, + .exit_latency = 100, + .target_residency = 400, + .enter = &intel_idle, + .enter_freeze = intel_idle_freeze, }, + { + .name = "C6-TNG", + .desc = "MWAIT 0x52", + .flags = MWAIT2flg(0x52) | CPUIDLE_FLAG_TLB_FLUSHED, + .exit_latency = 140, + .target_residency = 560, + .enter = &intel_idle, + .enter_freeze = intel_idle_freeze, }, + { + .name = "C7-TNG", + .desc = "MWAIT 0x60", + .flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED, + .exit_latency = 1200, + .target_residency = 4000, + .enter = &intel_idle, + .enter_freeze = intel_idle_freeze, }, + { + .name = "C9-TNG", + .desc = "MWAIT 0x64", + .flags = MWAIT2flg(0x64) | CPUIDLE_FLAG_TLB_FLUSHED, + .exit_latency = 10000, + .target_residency = 20000, + .enter = &intel_idle, + .enter_freeze = intel_idle_freeze, }, + { + .enter = NULL } +}; static struct cpuidle_state avn_cstates[] = { { .name = "C1-AVN", @@ -907,51 +949,15 @@ static void intel_idle_freeze(struct cpuidle_device *dev, mwait_idle_with_hints(eax, ecx); } -static void __setup_broadcast_timer(void *arg) +static void __setup_broadcast_timer(bool on) { - unsigned long on = (unsigned long)arg; - if (on) tick_broadcast_enable(); else tick_broadcast_disable(); } -static int cpu_hotplug_notify(struct notifier_block *n, - unsigned long action, void *hcpu) -{ - int hotcpu = (unsigned long)hcpu; - struct cpuidle_device *dev; - - switch (action & ~CPU_TASKS_FROZEN) { - case CPU_ONLINE: - - if (lapic_timer_reliable_states != LAPIC_TIMER_ALWAYS_RELIABLE) - smp_call_function_single(hotcpu, __setup_broadcast_timer, - (void *)true, 1); - - /* - * Some systems can hotplug a cpu at runtime after - * the kernel has booted, we have to initialize the - * driver in this case - */ - dev = per_cpu_ptr(intel_idle_cpuidle_devices, hotcpu); - if (dev->registered) - break; - - if (intel_idle_cpu_init(hotcpu)) - return NOTIFY_BAD; - - break; - } - return NOTIFY_OK; -} - -static struct notifier_block cpu_hotplug_notifier = { - .notifier_call = cpu_hotplug_notify, -}; - -static void auto_demotion_disable(void *dummy) +static void auto_demotion_disable(void) { unsigned long long msr_bits; @@ -959,7 +965,7 @@ static void auto_demotion_disable(void *dummy) msr_bits &= ~(icpu->auto_demotion_disable_flags); wrmsrl(MSR_NHM_SNB_PKG_CST_CFG_CTL, msr_bits); } -static void c1e_promotion_disable(void *dummy) +static void c1e_promotion_disable(void) { unsigned long long msr_bits; @@ -978,6 +984,10 @@ static const struct idle_cpu idle_cpu_atom = { .state_table = atom_cstates, }; +static const struct idle_cpu idle_cpu_tangier = { + .state_table = tangier_cstates, +}; + static const struct idle_cpu idle_cpu_lincroft = { .state_table = atom_cstates, .auto_demotion_disable_flags = ATM_LNC_C6_AUTO_DEMOTE, @@ -1066,6 +1076,7 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = { ICPU(INTEL_FAM6_SANDYBRIDGE_X, idle_cpu_snb), ICPU(INTEL_FAM6_ATOM_CEDARVIEW, idle_cpu_atom), ICPU(INTEL_FAM6_ATOM_SILVERMONT1, idle_cpu_byt), + ICPU(INTEL_FAM6_ATOM_MERRIFIELD, idle_cpu_tangier), ICPU(INTEL_FAM6_ATOM_AIRMONT, idle_cpu_cht), ICPU(INTEL_FAM6_IVYBRIDGE, idle_cpu_ivb), ICPU(INTEL_FAM6_IVYBRIDGE_X, idle_cpu_ivt), @@ -1084,6 +1095,7 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = { ICPU(INTEL_FAM6_KABYLAKE_DESKTOP, idle_cpu_skl), ICPU(INTEL_FAM6_SKYLAKE_X, idle_cpu_skx), ICPU(INTEL_FAM6_XEON_PHI_KNL, idle_cpu_knl), + ICPU(INTEL_FAM6_XEON_PHI_KNM, idle_cpu_knl), ICPU(INTEL_FAM6_ATOM_GOLDMONT, idle_cpu_bxt), ICPU(INTEL_FAM6_ATOM_DENVERTON, idle_cpu_dnv), {} @@ -1373,12 +1385,11 @@ static void __init intel_idle_cpuidle_driver_init(void) * allocate, initialize, register cpuidle_devices * @cpu: cpu/core to initialize */ -static int intel_idle_cpu_init(int cpu) +static int intel_idle_cpu_init(unsigned int cpu) { struct cpuidle_device *dev; dev = per_cpu_ptr(intel_idle_cpuidle_devices, cpu); - dev->cpu = cpu; if (cpuidle_register_device(dev)) { @@ -1387,17 +1398,36 @@ static int intel_idle_cpu_init(int cpu) } if (icpu->auto_demotion_disable_flags) - smp_call_function_single(cpu, auto_demotion_disable, NULL, 1); + auto_demotion_disable(); if (icpu->disable_promotion_to_c1e) - smp_call_function_single(cpu, c1e_promotion_disable, NULL, 1); + c1e_promotion_disable(); + + return 0; +} + +static int intel_idle_cpu_online(unsigned int cpu) +{ + struct cpuidle_device *dev; + + if (lapic_timer_reliable_states != LAPIC_TIMER_ALWAYS_RELIABLE) + __setup_broadcast_timer(true); + + /* + * Some systems can hotplug a cpu at runtime after + * the kernel has booted, we have to initialize the + * driver in this case + */ + dev = per_cpu_ptr(intel_idle_cpuidle_devices, cpu); + if (!dev->registered) + return intel_idle_cpu_init(cpu); return 0; } static int __init intel_idle_init(void) { - int retval, i; + int retval; /* Do not load intel_idle at all for now if idle= is passed */ if (boot_option_idle_override != IDLE_NO_OVERRIDE) @@ -1417,35 +1447,29 @@ static int __init intel_idle_init(void) struct cpuidle_driver *drv = cpuidle_get_driver(); printk(KERN_DEBUG PREFIX "intel_idle yielding to %s", drv ? drv->name : "none"); - free_percpu(intel_idle_cpuidle_devices); - return retval; + goto init_driver_fail; } - cpu_notifier_register_begin(); - - for_each_online_cpu(i) { - retval = intel_idle_cpu_init(i); - if (retval) { - intel_idle_cpuidle_devices_uninit(); - cpu_notifier_register_done(); - cpuidle_unregister_driver(&intel_idle_driver); - free_percpu(intel_idle_cpuidle_devices); - return retval; - } - } - __register_cpu_notifier(&cpu_hotplug_notifier); - if (boot_cpu_has(X86_FEATURE_ARAT)) /* Always Reliable APIC Timer */ lapic_timer_reliable_states = LAPIC_TIMER_ALWAYS_RELIABLE; - else - on_each_cpu(__setup_broadcast_timer, (void *)true, 1); - cpu_notifier_register_done(); + retval = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "idle/intel:online", + intel_idle_cpu_online, NULL); + if (retval < 0) + goto hp_setup_fail; pr_debug(PREFIX "lapic_timer_reliable_states 0x%x\n", lapic_timer_reliable_states); return 0; + +hp_setup_fail: + intel_idle_cpuidle_devices_uninit(); + cpuidle_unregister_driver(&intel_idle_driver); +init_driver_fail: + free_percpu(intel_idle_cpuidle_devices); + return retval; + } device_initcall(intel_idle_init); diff --git a/drivers/input/mouse/psmouse-base.c b/drivers/input/mouse/psmouse-base.c index fb4b185dea96..bee267424972 100644 --- a/drivers/input/mouse/psmouse-base.c +++ b/drivers/input/mouse/psmouse-base.c @@ -1115,10 +1115,6 @@ static int psmouse_extensions(struct psmouse *psmouse, if (psmouse_try_protocol(psmouse, PSMOUSE_TOUCHKIT_PS2, &max_proto, set_properties, true)) return PSMOUSE_TOUCHKIT_PS2; - - if (psmouse_try_protocol(psmouse, PSMOUSE_BYD, - &max_proto, set_properties, true)) - return PSMOUSE_BYD; } /* diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index 58470f5ced04..8c53748a769d 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -338,7 +338,9 @@ static int dmar_pci_bus_notifier(struct notifier_block *nb, struct pci_dev *pdev = to_pci_dev(data); struct dmar_pci_notify_info *info; - /* Only care about add/remove events for physical functions */ + /* Only care about add/remove events for physical functions. + * For VFs we actually do the lookup based on the corresponding + * PF in device_to_iommu() anyway. */ if (pdev->is_virtfn) return NOTIFY_DONE; if (action != BUS_NOTIFY_ADD_DEVICE && diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 3965e73db51c..d8376c2d18b3 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -892,7 +892,13 @@ static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devf return NULL; if (dev_is_pci(dev)) { + struct pci_dev *pf_pdev; + pdev = to_pci_dev(dev); + /* VFs aren't listed in scope tables; we need to look up + * the PF instead to find the IOMMU. */ + pf_pdev = pci_physfn(pdev); + dev = &pf_pdev->dev; segment = pci_domain_nr(pdev->bus); } else if (has_acpi_companion(dev)) dev = &ACPI_COMPANION(dev)->dev; @@ -905,6 +911,13 @@ static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devf for_each_active_dev_scope(drhd->devices, drhd->devices_cnt, i, tmp) { if (tmp == dev) { + /* For a VF use its original BDF# not that of the PF + * which we used for the IOMMU lookup. Strictly speaking + * we could do this for all PCI devices; we only need to + * get the BDF# from the scope table for ACPI matches. */ + if (pdev->is_virtfn) + goto got_pdev; + *bus = drhd->devices[i].bus; *devfn = drhd->devices[i].devfn; goto out; diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c index 8ebb3530afa7..cb72e0011310 100644 --- a/drivers/iommu/intel-svm.c +++ b/drivers/iommu/intel-svm.c @@ -39,10 +39,18 @@ int intel_svm_alloc_pasid_tables(struct intel_iommu *iommu) struct page *pages; int order; - order = ecap_pss(iommu->ecap) + 7 - PAGE_SHIFT; - if (order < 0) - order = 0; - + /* Start at 2 because it's defined as 2^(1+PSS) */ + iommu->pasid_max = 2 << ecap_pss(iommu->ecap); + + /* Eventually I'm promised we will get a multi-level PASID table + * and it won't have to be physically contiguous. Until then, + * limit the size because 8MiB contiguous allocations can be hard + * to come by. The limit of 0x20000, which is 1MiB for each of + * the PASID and PASID-state tables, is somewhat arbitrary. */ + if (iommu->pasid_max > 0x20000) + iommu->pasid_max = 0x20000; + + order = get_order(sizeof(struct pasid_entry) * iommu->pasid_max); pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, order); if (!pages) { pr_warn("IOMMU: %s: Failed to allocate PASID table\n", @@ -53,6 +61,8 @@ int intel_svm_alloc_pasid_tables(struct intel_iommu *iommu) pr_info("%s: Allocated order %d PASID table.\n", iommu->name, order); if (ecap_dis(iommu->ecap)) { + /* Just making it explicit... */ + BUILD_BUG_ON(sizeof(struct pasid_entry) != sizeof(struct pasid_state_entry)); pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, order); if (pages) iommu->pasid_state_table = page_address(pages); @@ -68,11 +78,7 @@ int intel_svm_alloc_pasid_tables(struct intel_iommu *iommu) int intel_svm_free_pasid_tables(struct intel_iommu *iommu) { - int order; - - order = ecap_pss(iommu->ecap) + 7 - PAGE_SHIFT; - if (order < 0) - order = 0; + int order = get_order(sizeof(struct pasid_entry) * iommu->pasid_max); if (iommu->pasid_table) { free_pages((unsigned long)iommu->pasid_table, order); @@ -371,8 +377,8 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_ } svm->iommu = iommu; - if (pasid_max > 2 << ecap_pss(iommu->ecap)) - pasid_max = 2 << ecap_pss(iommu->ecap); + if (pasid_max > iommu->pasid_max) + pasid_max = iommu->pasid_max; /* Do not use PASID 0 in caching mode (virtualised IOMMU) */ ret = idr_alloc(&iommu->pasid_idr, svm, diff --git a/drivers/isdn/gigaset/ser-gigaset.c b/drivers/isdn/gigaset/ser-gigaset.c index d1f8ab915b15..b90776ef56ec 100644 --- a/drivers/isdn/gigaset/ser-gigaset.c +++ b/drivers/isdn/gigaset/ser-gigaset.c @@ -755,8 +755,10 @@ static int __init ser_gigaset_init(void) driver = gigaset_initdriver(GIGASET_MINOR, GIGASET_MINORS, GIGASET_MODULENAME, GIGASET_DEVNAME, &ops, THIS_MODULE); - if (!driver) + if (!driver) { + rc = -ENOMEM; goto error; + } rc = tty_register_ldisc(N_GIGASET_M101, &gigaset_ldisc); if (rc != 0) { diff --git a/drivers/isdn/hisax/hfc4s8s_l1.c b/drivers/isdn/hisax/hfc4s8s_l1.c index 9600cd771f1a..e034ed847ff3 100644 --- a/drivers/isdn/hisax/hfc4s8s_l1.c +++ b/drivers/isdn/hisax/hfc4s8s_l1.c @@ -1499,6 +1499,7 @@ hfc4s8s_probe(struct pci_dev *pdev, const struct pci_device_id *ent) printk(KERN_INFO "HFC-4S/8S: failed to request address space at 0x%04x\n", hw->iobase); + err = -EBUSY; goto out; } diff --git a/drivers/media/tuners/tuner-xc2028.c b/drivers/media/tuners/tuner-xc2028.c index 317ef63ee789..8d96a22647b3 100644 --- a/drivers/media/tuners/tuner-xc2028.c +++ b/drivers/media/tuners/tuner-xc2028.c @@ -281,6 +281,14 @@ static void free_firmware(struct xc2028_data *priv) int i; tuner_dbg("%s called\n", __func__); + /* free allocated f/w string */ + if (priv->fname != firmware_name) + kfree(priv->fname); + priv->fname = NULL; + + priv->state = XC2028_NO_FIRMWARE; + memset(&priv->cur_fw, 0, sizeof(priv->cur_fw)); + if (!priv->firm) return; @@ -291,9 +299,6 @@ static void free_firmware(struct xc2028_data *priv) priv->firm = NULL; priv->firm_size = 0; - priv->state = XC2028_NO_FIRMWARE; - - memset(&priv->cur_fw, 0, sizeof(priv->cur_fw)); } static int load_all_firmwares(struct dvb_frontend *fe, @@ -884,9 +889,8 @@ read_not_reliable: return 0; fail: - priv->state = XC2028_NO_FIRMWARE; + free_firmware(priv); - memset(&priv->cur_fw, 0, sizeof(priv->cur_fw)); if (retry_count < 8) { msleep(50); retry_count++; @@ -1332,11 +1336,8 @@ static int xc2028_dvb_release(struct dvb_frontend *fe) mutex_lock(&xc2028_list_mutex); /* only perform final cleanup if this is the last instance */ - if (hybrid_tuner_report_instance_count(priv) == 1) { + if (hybrid_tuner_report_instance_count(priv) == 1) free_firmware(priv); - kfree(priv->ctrl.fname); - priv->ctrl.fname = NULL; - } if (priv) hybrid_tuner_release_state(priv); @@ -1399,19 +1400,8 @@ static int xc2028_set_config(struct dvb_frontend *fe, void *priv_cfg) /* * Copy the config data. - * For the firmware name, keep a local copy of the string, - * in order to avoid troubles during device release. */ - kfree(priv->ctrl.fname); - priv->ctrl.fname = NULL; memcpy(&priv->ctrl, p, sizeof(priv->ctrl)); - if (p->fname) { - priv->ctrl.fname = kstrdup(p->fname, GFP_KERNEL); - if (priv->ctrl.fname == NULL) { - rc = -ENOMEM; - goto unlock; - } - } /* * If firmware name changed, frees firmware. As free_firmware will @@ -1426,10 +1416,15 @@ static int xc2028_set_config(struct dvb_frontend *fe, void *priv_cfg) if (priv->state == XC2028_NO_FIRMWARE) { if (!firmware_name[0]) - priv->fname = priv->ctrl.fname; + priv->fname = kstrdup(p->fname, GFP_KERNEL); else priv->fname = firmware_name; + if (!priv->fname) { + rc = -ENOMEM; + goto unlock; + } + rc = request_firmware_nowait(THIS_MODULE, 1, priv->fname, priv->i2c_props.adap->dev.parent, diff --git a/drivers/mfd/syscon.c b/drivers/mfd/syscon.c index 2f2225e845ef..b93fe4c4957a 100644 --- a/drivers/mfd/syscon.c +++ b/drivers/mfd/syscon.c @@ -73,8 +73,10 @@ static struct syscon *of_syscon_register(struct device_node *np) /* Parse the device's DT node for an endianness specification */ if (of_property_read_bool(np, "big-endian")) syscon_config.val_format_endian = REGMAP_ENDIAN_BIG; - else if (of_property_read_bool(np, "little-endian")) + else if (of_property_read_bool(np, "little-endian")) syscon_config.val_format_endian = REGMAP_ENDIAN_LITTLE; + else if (of_property_read_bool(np, "native-endian")) + syscon_config.val_format_endian = REGMAP_ENDIAN_NATIVE; /* * search for reg-io-width property in DT. If it is not provided, diff --git a/drivers/mfd/wm8994-core.c b/drivers/mfd/wm8994-core.c index 7eec619a6023..8588dbad3301 100644 --- a/drivers/mfd/wm8994-core.c +++ b/drivers/mfd/wm8994-core.c @@ -393,8 +393,13 @@ static int wm8994_device_init(struct wm8994 *wm8994, int irq) BUG(); goto err; } - - ret = devm_regulator_bulk_get(wm8994->dev, wm8994->num_supplies, + + /* + * Can't use devres helper here as some of the supplies are provided by + * wm8994->dev's children (regulators) and those regulators are + * unregistered by the devres core before the supplies are freed. + */ + ret = regulator_bulk_get(wm8994->dev, wm8994->num_supplies, wm8994->supplies); if (ret != 0) { dev_err(wm8994->dev, "Failed to get supplies: %d\n", ret); @@ -405,7 +410,7 @@ static int wm8994_device_init(struct wm8994 *wm8994, int irq) wm8994->supplies); if (ret != 0) { dev_err(wm8994->dev, "Failed to enable supplies: %d\n", ret); - goto err; + goto err_regulator_free; } ret = wm8994_reg_read(wm8994, WM8994_SOFTWARE_RESET); @@ -596,6 +601,8 @@ err_irq: err_enable: regulator_bulk_disable(wm8994->num_supplies, wm8994->supplies); +err_regulator_free: + regulator_bulk_free(wm8994->num_supplies, wm8994->supplies); err: mfd_remove_devices(wm8994->dev); return ret; @@ -604,10 +611,11 @@ err: static void wm8994_device_exit(struct wm8994 *wm8994) { pm_runtime_disable(wm8994->dev); - mfd_remove_devices(wm8994->dev); wm8994_irq_exit(wm8994); regulator_bulk_disable(wm8994->num_supplies, wm8994->supplies); + regulator_bulk_free(wm8994->num_supplies, wm8994->supplies); + mfd_remove_devices(wm8994->dev); } static const struct of_device_id wm8994_of_match[] = { diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c index 50a674be6655..df478ae72e23 100644 --- a/drivers/mmc/host/dw_mmc.c +++ b/drivers/mmc/host/dw_mmc.c @@ -1058,6 +1058,7 @@ static int dw_mci_submit_data_dma(struct dw_mci *host, struct mmc_data *data) spin_unlock_irqrestore(&host->irq_lock, irqflags); if (host->dma_ops->start(host, sg_len)) { + host->dma_ops->stop(host); /* We can't do DMA, try PIO for this one */ dev_dbg(host->dev, "%s: fall back to PIO mode for current transfer\n", diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c index fb71c866eacc..1bb11e4a9fe5 100644 --- a/drivers/mmc/host/sdhci-of-esdhc.c +++ b/drivers/mmc/host/sdhci-of-esdhc.c @@ -66,6 +66,20 @@ static u32 esdhc_readl_fixup(struct sdhci_host *host, return ret; } } + /* + * The DAT[3:0] line signal levels and the CMD line signal level are + * not compatible with standard SDHC register. The line signal levels + * DAT[7:0] are at bits 31:24 and the command line signal level is at + * bit 23. All other bits are the same as in the standard SDHC + * register. + */ + if (spec_reg == SDHCI_PRESENT_STATE) { + ret = value & 0x000fffff; + ret |= (value >> 4) & SDHCI_DATA_LVL_MASK; + ret |= (value << 1) & SDHCI_CMD_LVL; + return ret; + } + ret = value; return ret; } diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h index 766df17fb7eb..2570455b219a 100644 --- a/drivers/mmc/host/sdhci.h +++ b/drivers/mmc/host/sdhci.h @@ -73,6 +73,7 @@ #define SDHCI_DATA_LVL_MASK 0x00F00000 #define SDHCI_DATA_LVL_SHIFT 20 #define SDHCI_DATA_0_LVL_MASK 0x00100000 +#define SDHCI_CMD_LVL 0x01000000 #define SDHCI_HOST_CONTROL 0x28 #define SDHCI_CTRL_LED 0x01 diff --git a/drivers/net/can/usb/peak_usb/pcan_ucan.h b/drivers/net/can/usb/peak_usb/pcan_ucan.h index e8fc4952c6b0..2147678f0225 100644 --- a/drivers/net/can/usb/peak_usb/pcan_ucan.h +++ b/drivers/net/can/usb/peak_usb/pcan_ucan.h @@ -43,11 +43,22 @@ struct __packed pucan_command { u16 args[3]; }; +#define PUCAN_TSLOW_BRP_BITS 10 +#define PUCAN_TSLOW_TSGEG1_BITS 8 +#define PUCAN_TSLOW_TSGEG2_BITS 7 +#define PUCAN_TSLOW_SJW_BITS 7 + +#define PUCAN_TSLOW_BRP_MASK ((1 << PUCAN_TSLOW_BRP_BITS) - 1) +#define PUCAN_TSLOW_TSEG1_MASK ((1 << PUCAN_TSLOW_TSGEG1_BITS) - 1) +#define PUCAN_TSLOW_TSEG2_MASK ((1 << PUCAN_TSLOW_TSGEG2_BITS) - 1) +#define PUCAN_TSLOW_SJW_MASK ((1 << PUCAN_TSLOW_SJW_BITS) - 1) + /* uCAN TIMING_SLOW command fields */ -#define PUCAN_TSLOW_SJW_T(s, t) (((s) & 0xf) | ((!!(t)) << 7)) -#define PUCAN_TSLOW_TSEG2(t) ((t) & 0xf) -#define PUCAN_TSLOW_TSEG1(t) ((t) & 0x3f) -#define PUCAN_TSLOW_BRP(b) ((b) & 0x3ff) +#define PUCAN_TSLOW_SJW_T(s, t) (((s) & PUCAN_TSLOW_SJW_MASK) | \ + ((!!(t)) << 7)) +#define PUCAN_TSLOW_TSEG2(t) ((t) & PUCAN_TSLOW_TSEG2_MASK) +#define PUCAN_TSLOW_TSEG1(t) ((t) & PUCAN_TSLOW_TSEG1_MASK) +#define PUCAN_TSLOW_BRP(b) ((b) & PUCAN_TSLOW_BRP_MASK) struct __packed pucan_timing_slow { __le16 opcode_channel; @@ -60,11 +71,21 @@ struct __packed pucan_timing_slow { __le16 brp; /* BaudRate Prescaler */ }; +#define PUCAN_TFAST_BRP_BITS 10 +#define PUCAN_TFAST_TSGEG1_BITS 5 +#define PUCAN_TFAST_TSGEG2_BITS 4 +#define PUCAN_TFAST_SJW_BITS 4 + +#define PUCAN_TFAST_BRP_MASK ((1 << PUCAN_TFAST_BRP_BITS) - 1) +#define PUCAN_TFAST_TSEG1_MASK ((1 << PUCAN_TFAST_TSGEG1_BITS) - 1) +#define PUCAN_TFAST_TSEG2_MASK ((1 << PUCAN_TFAST_TSGEG2_BITS) - 1) +#define PUCAN_TFAST_SJW_MASK ((1 << PUCAN_TFAST_SJW_BITS) - 1) + /* uCAN TIMING_FAST command fields */ -#define PUCAN_TFAST_SJW(s) ((s) & 0x3) -#define PUCAN_TFAST_TSEG2(t) ((t) & 0x7) -#define PUCAN_TFAST_TSEG1(t) ((t) & 0xf) -#define PUCAN_TFAST_BRP(b) ((b) & 0x3ff) +#define PUCAN_TFAST_SJW(s) ((s) & PUCAN_TFAST_SJW_MASK) +#define PUCAN_TFAST_TSEG2(t) ((t) & PUCAN_TFAST_TSEG2_MASK) +#define PUCAN_TFAST_TSEG1(t) ((t) & PUCAN_TFAST_TSEG1_MASK) +#define PUCAN_TFAST_BRP(b) ((b) & PUCAN_TFAST_BRP_MASK) struct __packed pucan_timing_fast { __le16 opcode_channel; diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c index c06382cdfdfe..0b0302af3bd2 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c @@ -39,6 +39,7 @@ static struct usb_device_id peak_usb_table[] = { {USB_DEVICE(PCAN_USB_VENDOR_ID, PCAN_USBPRO_PRODUCT_ID)}, {USB_DEVICE(PCAN_USB_VENDOR_ID, PCAN_USBFD_PRODUCT_ID)}, {USB_DEVICE(PCAN_USB_VENDOR_ID, PCAN_USBPROFD_PRODUCT_ID)}, + {USB_DEVICE(PCAN_USB_VENDOR_ID, PCAN_USBX6_PRODUCT_ID)}, {} /* Terminating entry */ }; @@ -50,6 +51,7 @@ static const struct peak_usb_adapter *const peak_usb_adapters_list[] = { &pcan_usb_pro, &pcan_usb_fd, &pcan_usb_pro_fd, + &pcan_usb_x6, }; /* @@ -868,23 +870,25 @@ lbl_free_candev: static void peak_usb_disconnect(struct usb_interface *intf) { struct peak_usb_device *dev; + struct peak_usb_device *dev_prev_siblings; /* unregister as many netdev devices as siblings */ - for (dev = usb_get_intfdata(intf); dev; dev = dev->prev_siblings) { + for (dev = usb_get_intfdata(intf); dev; dev = dev_prev_siblings) { struct net_device *netdev = dev->netdev; char name[IFNAMSIZ]; + dev_prev_siblings = dev->prev_siblings; dev->state &= ~PCAN_USB_STATE_CONNECTED; strncpy(name, netdev->name, IFNAMSIZ); unregister_netdev(netdev); - free_candev(netdev); kfree(dev->cmd_buf); dev->next_siblings = NULL; if (dev->adapter->dev_free) dev->adapter->dev_free(dev); + free_candev(netdev); dev_info(&intf->dev, "%s removed\n", name); } diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.h b/drivers/net/can/usb/peak_usb/pcan_usb_core.h index 506fe506c9d3..3cbfb069893d 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.h +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.h @@ -27,6 +27,7 @@ #define PCAN_USBPRO_PRODUCT_ID 0x000d #define PCAN_USBPROFD_PRODUCT_ID 0x0011 #define PCAN_USBFD_PRODUCT_ID 0x0012 +#define PCAN_USBX6_PRODUCT_ID 0x0014 #define PCAN_USB_DRIVER_NAME "peak_usb" @@ -90,6 +91,7 @@ extern const struct peak_usb_adapter pcan_usb; extern const struct peak_usb_adapter pcan_usb_pro; extern const struct peak_usb_adapter pcan_usb_fd; extern const struct peak_usb_adapter pcan_usb_pro_fd; +extern const struct peak_usb_adapter pcan_usb_x6; struct peak_time_ref { struct timeval tv_host_0, tv_host; diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c index ce44a033f63b..304732550f0a 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c @@ -993,24 +993,24 @@ static void pcan_usb_fd_free(struct peak_usb_device *dev) static const struct can_bittiming_const pcan_usb_fd_const = { .name = "pcan_usb_fd", .tseg1_min = 1, - .tseg1_max = 64, + .tseg1_max = (1 << PUCAN_TSLOW_TSGEG1_BITS), .tseg2_min = 1, - .tseg2_max = 16, - .sjw_max = 16, + .tseg2_max = (1 << PUCAN_TSLOW_TSGEG2_BITS), + .sjw_max = (1 << PUCAN_TSLOW_SJW_BITS), .brp_min = 1, - .brp_max = 1024, + .brp_max = (1 << PUCAN_TSLOW_BRP_BITS), .brp_inc = 1, }; static const struct can_bittiming_const pcan_usb_fd_data_const = { .name = "pcan_usb_fd", .tseg1_min = 1, - .tseg1_max = 16, + .tseg1_max = (1 << PUCAN_TFAST_TSGEG1_BITS), .tseg2_min = 1, - .tseg2_max = 8, - .sjw_max = 4, + .tseg2_max = (1 << PUCAN_TFAST_TSGEG2_BITS), + .sjw_max = (1 << PUCAN_TFAST_SJW_BITS), .brp_min = 1, - .brp_max = 1024, + .brp_max = (1 << PUCAN_TFAST_BRP_BITS), .brp_inc = 1, }; @@ -1065,24 +1065,24 @@ const struct peak_usb_adapter pcan_usb_fd = { static const struct can_bittiming_const pcan_usb_pro_fd_const = { .name = "pcan_usb_pro_fd", .tseg1_min = 1, - .tseg1_max = 64, + .tseg1_max = (1 << PUCAN_TSLOW_TSGEG1_BITS), .tseg2_min = 1, - .tseg2_max = 16, - .sjw_max = 16, + .tseg2_max = (1 << PUCAN_TSLOW_TSGEG2_BITS), + .sjw_max = (1 << PUCAN_TSLOW_SJW_BITS), .brp_min = 1, - .brp_max = 1024, + .brp_max = (1 << PUCAN_TSLOW_BRP_BITS), .brp_inc = 1, }; static const struct can_bittiming_const pcan_usb_pro_fd_data_const = { .name = "pcan_usb_pro_fd", .tseg1_min = 1, - .tseg1_max = 16, + .tseg1_max = (1 << PUCAN_TFAST_TSGEG1_BITS), .tseg2_min = 1, - .tseg2_max = 8, - .sjw_max = 4, + .tseg2_max = (1 << PUCAN_TFAST_TSGEG2_BITS), + .sjw_max = (1 << PUCAN_TFAST_SJW_BITS), .brp_min = 1, - .brp_max = 1024, + .brp_max = (1 << PUCAN_TFAST_BRP_BITS), .brp_inc = 1, }; @@ -1132,3 +1132,75 @@ const struct peak_usb_adapter pcan_usb_pro_fd = { .do_get_berr_counter = pcan_usb_fd_get_berr_counter, }; + +/* describes the PCAN-USB X6 adapter */ +static const struct can_bittiming_const pcan_usb_x6_const = { + .name = "pcan_usb_x6", + .tseg1_min = 1, + .tseg1_max = (1 << PUCAN_TSLOW_TSGEG1_BITS), + .tseg2_min = 1, + .tseg2_max = (1 << PUCAN_TSLOW_TSGEG2_BITS), + .sjw_max = (1 << PUCAN_TSLOW_SJW_BITS), + .brp_min = 1, + .brp_max = (1 << PUCAN_TSLOW_BRP_BITS), + .brp_inc = 1, +}; + +static const struct can_bittiming_const pcan_usb_x6_data_const = { + .name = "pcan_usb_x6", + .tseg1_min = 1, + .tseg1_max = (1 << PUCAN_TFAST_TSGEG1_BITS), + .tseg2_min = 1, + .tseg2_max = (1 << PUCAN_TFAST_TSGEG2_BITS), + .sjw_max = (1 << PUCAN_TFAST_SJW_BITS), + .brp_min = 1, + .brp_max = (1 << PUCAN_TFAST_BRP_BITS), + .brp_inc = 1, +}; + +const struct peak_usb_adapter pcan_usb_x6 = { + .name = "PCAN-USB X6", + .device_id = PCAN_USBX6_PRODUCT_ID, + .ctrl_count = PCAN_USBPROFD_CHANNEL_COUNT, + .ctrlmode_supported = CAN_CTRLMODE_FD | + CAN_CTRLMODE_3_SAMPLES | CAN_CTRLMODE_LISTENONLY, + .clock = { + .freq = PCAN_UFD_CRYSTAL_HZ, + }, + .bittiming_const = &pcan_usb_x6_const, + .data_bittiming_const = &pcan_usb_x6_data_const, + + /* size of device private data */ + .sizeof_dev_private = sizeof(struct pcan_usb_fd_device), + + /* timestamps usage */ + .ts_used_bits = 32, + .ts_period = 1000000, /* calibration period in ts. */ + .us_per_ts_scale = 1, /* us = (ts * scale) >> shift */ + .us_per_ts_shift = 0, + + /* give here messages in/out endpoints */ + .ep_msg_in = PCAN_USBPRO_EP_MSGIN, + .ep_msg_out = {PCAN_USBPRO_EP_MSGOUT_0, PCAN_USBPRO_EP_MSGOUT_1}, + + /* size of rx/tx usb buffers */ + .rx_buffer_size = PCAN_UFD_RX_BUFFER_SIZE, + .tx_buffer_size = PCAN_UFD_TX_BUFFER_SIZE, + + /* device callbacks */ + .intf_probe = pcan_usb_pro_probe, /* same as PCAN-USB Pro */ + .dev_init = pcan_usb_fd_init, + + .dev_exit = pcan_usb_fd_exit, + .dev_free = pcan_usb_fd_free, + .dev_set_bus = pcan_usb_fd_set_bus, + .dev_set_bittiming = pcan_usb_fd_set_bittiming_slow, + .dev_set_data_bittiming = pcan_usb_fd_set_bittiming_fast, + .dev_decode_buf = pcan_usb_fd_decode_buf, + .dev_start = pcan_usb_fd_start, + .dev_stop = pcan_usb_fd_stop, + .dev_restart_async = pcan_usb_fd_restart_async, + .dev_encode_msg = pcan_usb_fd_encode_msg, + + .do_get_berr_counter = pcan_usb_fd_get_berr_counter, +}; diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 7717b19dc806..947adda3397d 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -962,9 +962,10 @@ static void b53_vlan_add(struct dsa_switch *ds, int port, vl->members |= BIT(port) | BIT(cpu_port); if (untagged) - vl->untag |= BIT(port) | BIT(cpu_port); + vl->untag |= BIT(port); else - vl->untag &= ~(BIT(port) | BIT(cpu_port)); + vl->untag &= ~BIT(port); + vl->untag &= ~BIT(cpu_port); b53_set_vlan_entry(dev, vid, vl); b53_fast_age_vlan(dev, vid); @@ -973,8 +974,6 @@ static void b53_vlan_add(struct dsa_switch *ds, int port, if (pvid) { b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port), vlan->vid_end); - b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(cpu_port), - vlan->vid_end); b53_fast_age_vlan(dev, vid); } } @@ -984,7 +983,6 @@ static int b53_vlan_del(struct dsa_switch *ds, int port, { struct b53_device *dev = ds->priv; bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED; - unsigned int cpu_port = dev->cpu_port; struct b53_vlan *vl; u16 vid; u16 pvid; @@ -997,8 +995,6 @@ static int b53_vlan_del(struct dsa_switch *ds, int port, b53_get_vlan_entry(dev, vid, vl); vl->members &= ~BIT(port); - if ((vl->members & BIT(cpu_port)) == BIT(cpu_port)) - vl->members = 0; if (pvid == vid) { if (is5325(dev) || is5365(dev)) @@ -1007,18 +1003,14 @@ static int b53_vlan_del(struct dsa_switch *ds, int port, pvid = 0; } - if (untagged) { + if (untagged) vl->untag &= ~(BIT(port)); - if ((vl->untag & BIT(cpu_port)) == BIT(cpu_port)) - vl->untag = 0; - } b53_set_vlan_entry(dev, vid, vl); b53_fast_age_vlan(dev, vid); } b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port), pvid); - b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(cpu_port), pvid); b53_fast_age_vlan(dev, pvid); return 0; diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index e3ee27ce13dd..9ec33b51a0ed 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -588,6 +588,7 @@ static void bcm_sf2_sw_adjust_link(struct dsa_switch *ds, int port, struct phy_device *phydev) { struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); + struct ethtool_eee *p = &priv->port_sts[port].eee; u32 id_mode_dis = 0, port_mode; const char *str = NULL; u32 reg; @@ -662,6 +663,9 @@ force_link: reg |= DUPLX_MODE; core_writel(priv, reg, CORE_STS_OVERRIDE_GMIIP_PORT(port)); + + if (!phydev->is_pseudo_fixed_link) + p->eee_enabled = bcm_sf2_eee_init(ds, port, phydev); } static void bcm_sf2_sw_fixed_link_update(struct dsa_switch *ds, int port, diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c index bda31f308cc2..a0eee7218695 100644 --- a/drivers/net/ethernet/altera/altera_tse_main.c +++ b/drivers/net/ethernet/altera/altera_tse_main.c @@ -400,12 +400,6 @@ static int tse_rx(struct altera_tse_private *priv, int limit) skb_put(skb, pktlength); - /* make cache consistent with receive packet buffer */ - dma_sync_single_for_cpu(priv->device, - priv->rx_ring[entry].dma_addr, - priv->rx_ring[entry].len, - DMA_FROM_DEVICE); - dma_unmap_single(priv->device, priv->rx_ring[entry].dma_addr, priv->rx_ring[entry].len, DMA_FROM_DEVICE); @@ -469,7 +463,6 @@ static int tse_tx_complete(struct altera_tse_private *priv) if (unlikely(netif_queue_stopped(priv->dev) && tse_tx_avail(priv) > TSE_TX_THRESH(priv))) { - netif_tx_lock(priv->dev); if (netif_queue_stopped(priv->dev) && tse_tx_avail(priv) > TSE_TX_THRESH(priv)) { if (netif_msg_tx_done(priv)) @@ -477,7 +470,6 @@ static int tse_tx_complete(struct altera_tse_private *priv) __func__); netif_wake_queue(priv->dev); } - netif_tx_unlock(priv->dev); } spin_unlock(&priv->tx_lock); @@ -592,10 +584,6 @@ static int tse_start_xmit(struct sk_buff *skb, struct net_device *dev) buffer->dma_addr = dma_addr; buffer->len = nopaged_len; - /* Push data out of the cache hierarchy into main memory */ - dma_sync_single_for_device(priv->device, buffer->dma_addr, - buffer->len, DMA_TO_DEVICE); - priv->dmaops->tx_buffer(priv, buffer); skb_tx_timestamp(skb); @@ -819,6 +807,8 @@ static int init_phy(struct net_device *dev) if (!phydev) { netdev_err(dev, "Could not find the PHY\n"); + if (fixed_link) + of_phy_deregister_fixed_link(priv->device->of_node); return -ENODEV; } @@ -1545,10 +1535,15 @@ err_free_netdev: static int altera_tse_remove(struct platform_device *pdev) { struct net_device *ndev = platform_get_drvdata(pdev); + struct altera_tse_private *priv = netdev_priv(ndev); - if (ndev->phydev) + if (ndev->phydev) { phy_disconnect(ndev->phydev); + if (of_phy_is_fixed_link(priv->device->of_node)) + of_phy_deregister_fixed_link(priv->device->of_node); + } + platform_set_drvdata(pdev, NULL); altera_tse_mdio_destroy(ndev); unregister_netdev(ndev); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-main.c b/drivers/net/ethernet/amd/xgbe/xgbe-main.c index 9de078819aa6..4f7635178200 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-main.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-main.c @@ -829,7 +829,7 @@ static int xgbe_remove(struct platform_device *pdev) return 0; } -#ifdef CONFIG_PM +#ifdef CONFIG_PM_SLEEP static int xgbe_suspend(struct device *dev) { struct net_device *netdev = dev_get_drvdata(dev); @@ -874,7 +874,7 @@ static int xgbe_resume(struct device *dev) return ret; } -#endif /* CONFIG_PM */ +#endif /* CONFIG_PM_SLEEP */ #ifdef CONFIG_ACPI static const struct acpi_device_id xgbe_acpi_match[] = { diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c index b0da9693f28a..be865b4dada2 100644 --- a/drivers/net/ethernet/arc/emac_main.c +++ b/drivers/net/ethernet/arc/emac_main.c @@ -460,7 +460,7 @@ static void arc_emac_set_rx_mode(struct net_device *ndev) if (ndev->flags & IFF_ALLMULTI) { arc_reg_set(priv, R_LAFL, ~0); arc_reg_set(priv, R_LAFH, ~0); - } else { + } else if (ndev->flags & IFF_MULTICAST) { struct netdev_hw_addr *ha; unsigned int filter[2] = { 0, 0 }; int bit; @@ -472,6 +472,9 @@ static void arc_emac_set_rx_mode(struct net_device *ndev) arc_reg_set(priv, R_LAFL, filter[0]); arc_reg_set(priv, R_LAFH, filter[1]); + } else { + arc_reg_set(priv, R_LAFL, 0); + arc_reg_set(priv, R_LAFH, 0); } } } @@ -764,8 +767,6 @@ int arc_emac_probe(struct net_device *ndev, int interface) ndev->netdev_ops = &arc_emac_netdev_ops; ndev->ethtool_ops = &arc_emac_ethtool_ops; ndev->watchdog_timeo = TX_TIMEOUT; - /* FIXME :: no multicast support yet */ - ndev->flags &= ~IFF_MULTICAST; priv = netdev_priv(ndev); priv->dev = dev; diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c index 00c38bf151e6..e078d8da978c 100644 --- a/drivers/net/ethernet/aurora/nb8800.c +++ b/drivers/net/ethernet/aurora/nb8800.c @@ -1466,12 +1466,12 @@ static int nb8800_probe(struct platform_device *pdev) ret = nb8800_hw_init(dev); if (ret) - goto err_free_bus; + goto err_deregister_fixed_link; if (ops && ops->init) { ret = ops->init(dev); if (ret) - goto err_free_bus; + goto err_deregister_fixed_link; } dev->netdev_ops = &nb8800_netdev_ops; @@ -1504,6 +1504,9 @@ static int nb8800_probe(struct platform_device *pdev) err_free_dma: nb8800_dma_free(dev); +err_deregister_fixed_link: + if (of_phy_is_fixed_link(pdev->dev.of_node)) + of_phy_deregister_fixed_link(pdev->dev.of_node); err_free_bus: of_node_put(priv->phy_node); mdiobus_unregister(bus); @@ -1521,6 +1524,8 @@ static int nb8800_remove(struct platform_device *pdev) struct nb8800_priv *priv = netdev_priv(ndev); unregister_netdev(ndev); + if (of_phy_is_fixed_link(pdev->dev.of_node)) + of_phy_deregister_fixed_link(pdev->dev.of_node); of_node_put(priv->phy_node); mdiobus_unregister(priv->mii_bus); diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index c3354b9941d1..25d1eb4933d0 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -1755,13 +1755,13 @@ static int bcm_sysport_probe(struct platform_device *pdev) if (priv->irq0 <= 0 || priv->irq1 <= 0) { dev_err(&pdev->dev, "invalid interrupts\n"); ret = -EINVAL; - goto err; + goto err_free_netdev; } priv->base = devm_ioremap_resource(&pdev->dev, r); if (IS_ERR(priv->base)) { ret = PTR_ERR(priv->base); - goto err; + goto err_free_netdev; } priv->netdev = dev; @@ -1779,7 +1779,7 @@ static int bcm_sysport_probe(struct platform_device *pdev) ret = of_phy_register_fixed_link(dn); if (ret) { dev_err(&pdev->dev, "failed to register fixed PHY\n"); - goto err; + goto err_free_netdev; } priv->phy_dn = dn; @@ -1821,7 +1821,7 @@ static int bcm_sysport_probe(struct platform_device *pdev) ret = register_netdev(dev); if (ret) { dev_err(&pdev->dev, "failed to register net_device\n"); - goto err; + goto err_deregister_fixed_link; } priv->rev = topctrl_readl(priv, REV_CNTL) & REV_MASK; @@ -1832,7 +1832,11 @@ static int bcm_sysport_probe(struct platform_device *pdev) priv->base, priv->irq0, priv->irq1, txq, rxq); return 0; -err: + +err_deregister_fixed_link: + if (of_phy_is_fixed_link(dn)) + of_phy_deregister_fixed_link(dn); +err_free_netdev: free_netdev(dev); return ret; } @@ -1840,11 +1844,14 @@ err: static int bcm_sysport_remove(struct platform_device *pdev) { struct net_device *dev = dev_get_drvdata(&pdev->dev); + struct device_node *dn = pdev->dev.of_node; /* Not much to do, ndo_close has been called * and we use managed allocations */ unregister_netdev(dev); + if (of_phy_is_fixed_link(dn)) + of_phy_deregister_fixed_link(dn); free_netdev(dev); dev_set_drvdata(&pdev->dev, NULL); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index 85a7800bfc12..5f19427c7b27 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -1872,8 +1872,16 @@ static void bnx2x_get_ringparam(struct net_device *dev, ering->rx_max_pending = MAX_RX_AVAIL; + /* If size isn't already set, we give an estimation of the number + * of buffers we'll have. We're neglecting some possible conditions + * [we couldn't know for certain at this point if number of queues + * might shrink] but the number would be correct for the likely + * scenario. + */ if (bp->rx_ring_size) ering->rx_pending = bp->rx_ring_size; + else if (BNX2X_NUM_RX_QUEUES(bp)) + ering->rx_pending = MAX_RX_AVAIL / BNX2X_NUM_RX_QUEUES(bp); else ering->rx_pending = MAX_RX_AVAIL; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 0cee4c0283f9..4febe60eadc2 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -10138,7 +10138,7 @@ static void __bnx2x_add_udp_port(struct bnx2x *bp, u16 port, { struct bnx2x_udp_tunnel *udp_port = &bp->udp_tunnel_ports[type]; - if (!netif_running(bp->dev) || !IS_PF(bp)) + if (!netif_running(bp->dev) || !IS_PF(bp) || CHIP_IS_E1x(bp)) return; if (udp_port->count && udp_port->dst_port == port) { @@ -10163,7 +10163,7 @@ static void __bnx2x_del_udp_port(struct bnx2x *bp, u16 port, { struct bnx2x_udp_tunnel *udp_port = &bp->udp_tunnel_ports[type]; - if (!IS_PF(bp)) + if (!IS_PF(bp) || CHIP_IS_E1x(bp)) return; if (!udp_port->count || udp_port->dst_port != port) { @@ -13505,6 +13505,7 @@ static int bnx2x_init_firmware(struct bnx2x *bp) /* Initialize the pointers to the init arrays */ /* Blob */ + rc = -ENOMEM; BNX2X_ALLOC_AND_SET(init_data, request_firmware_exit, be32_to_cpu_n); /* Opcodes */ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index c6909660e097..f08a20b921e7 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1811,6 +1811,9 @@ static int bnxt_busy_poll(struct napi_struct *napi) if (atomic_read(&bp->intr_sem) != 0) return LL_FLUSH_FAILED; + if (!bp->link_info.link_up) + return LL_FLUSH_FAILED; + if (!bnxt_lock_poll(bnapi)) return LL_FLUSH_BUSY; @@ -3210,11 +3213,17 @@ static int bnxt_hwrm_tunnel_dst_port_alloc(struct bnxt *bp, __be16 port, goto err_out; } - if (tunnel_type & TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN) + switch (tunnel_type) { + case TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN: bp->vxlan_fw_dst_port_id = resp->tunnel_dst_port_id; - - else if (tunnel_type & TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GENEVE) + break; + case TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GENEVE: bp->nge_fw_dst_port_id = resp->tunnel_dst_port_id; + break; + default: + break; + } + err_out: mutex_unlock(&bp->hwrm_cmd_lock); return rc; @@ -4111,7 +4120,7 @@ static int bnxt_hwrm_stat_ctx_alloc(struct bnxt *bp) bp->grp_info[i].fw_stats_ctx = cpr->hw_stats_ctx_id; } mutex_unlock(&bp->hwrm_cmd_lock); - return 0; + return rc; } static int bnxt_hwrm_func_qcfg(struct bnxt *bp) @@ -4934,6 +4943,10 @@ static void bnxt_del_napi(struct bnxt *bp) napi_hash_del(&bnapi->napi); netif_napi_del(&bnapi->napi); } + /* We called napi_hash_del() before netif_napi_del(), we need + * to respect an RCU grace period before freeing napi structures. + */ + synchronize_net(); } static void bnxt_init_napi(struct bnxt *bp) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 4464bc5db934..a4e60e56c14f 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1172,6 +1172,7 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev, struct bcmgenet_tx_ring *ring) { struct bcmgenet_priv *priv = netdev_priv(dev); + struct device *kdev = &priv->pdev->dev; struct enet_cb *tx_cb_ptr; struct netdev_queue *txq; unsigned int pkts_compl = 0; @@ -1199,13 +1200,13 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev, if (tx_cb_ptr->skb) { pkts_compl++; bytes_compl += GENET_CB(tx_cb_ptr->skb)->bytes_sent; - dma_unmap_single(&dev->dev, + dma_unmap_single(kdev, dma_unmap_addr(tx_cb_ptr, dma_addr), dma_unmap_len(tx_cb_ptr, dma_len), DMA_TO_DEVICE); bcmgenet_free_cb(tx_cb_ptr); } else if (dma_unmap_addr(tx_cb_ptr, dma_addr)) { - dma_unmap_page(&dev->dev, + dma_unmap_page(kdev, dma_unmap_addr(tx_cb_ptr, dma_addr), dma_unmap_len(tx_cb_ptr, dma_len), DMA_TO_DEVICE); @@ -1775,6 +1776,7 @@ static int bcmgenet_alloc_rx_buffers(struct bcmgenet_priv *priv, static void bcmgenet_free_rx_buffers(struct bcmgenet_priv *priv) { + struct device *kdev = &priv->pdev->dev; struct enet_cb *cb; int i; @@ -1782,7 +1784,7 @@ static void bcmgenet_free_rx_buffers(struct bcmgenet_priv *priv) cb = &priv->rx_cbs[i]; if (dma_unmap_addr(cb, dma_addr)) { - dma_unmap_single(&priv->dev->dev, + dma_unmap_single(kdev, dma_unmap_addr(cb, dma_addr), priv->rx_buf_len, DMA_FROM_DEVICE); dma_unmap_addr_set(cb, dma_addr, 0); diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 457c3bc8cfff..e87607621e62 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -542,8 +542,10 @@ static int bcmgenet_mii_of_init(struct bcmgenet_priv *priv) /* Make sure we initialize MoCA PHYs with a link down */ if (phy_mode == PHY_INTERFACE_MODE_MOCA) { phydev = of_phy_find_device(dn); - if (phydev) + if (phydev) { phydev->link = 0; + put_device(&phydev->mdio.dev); + } } return 0; @@ -625,6 +627,7 @@ static int bcmgenet_mii_bus_init(struct bcmgenet_priv *priv) int bcmgenet_mii_init(struct net_device *dev) { struct bcmgenet_priv *priv = netdev_priv(dev); + struct device_node *dn = priv->pdev->dev.of_node; int ret; ret = bcmgenet_mii_alloc(priv); @@ -638,6 +641,8 @@ int bcmgenet_mii_init(struct net_device *dev) return 0; out: + if (of_phy_is_fixed_link(dn)) + of_phy_deregister_fixed_link(dn); of_node_put(priv->phy_dn); mdiobus_unregister(priv->mii_bus); mdiobus_free(priv->mii_bus); @@ -647,7 +652,10 @@ out: void bcmgenet_mii_exit(struct net_device *dev) { struct bcmgenet_priv *priv = netdev_priv(dev); + struct device_node *dn = priv->pdev->dev.of_node; + if (of_phy_is_fixed_link(dn)) + of_phy_deregister_fixed_link(dn); of_node_put(priv->phy_dn); mdiobus_unregister(priv->mii_bus); mdiobus_free(priv->mii_bus); diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index b32444a3ed79..ec09fcece711 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -975,6 +975,7 @@ static inline void macb_init_rx_ring(struct macb *bp) addr += bp->rx_buffer_size; } bp->rx_ring[RX_RING_SIZE - 1].addr |= MACB_BIT(RX_WRAP); + bp->rx_tail = 0; } static int macb_rx(struct macb *bp, int budget) @@ -1156,6 +1157,7 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id) if (status & MACB_BIT(RXUBR)) { ctrl = macb_readl(bp, NCR); macb_writel(bp, NCR, ctrl & ~MACB_BIT(RE)); + wmb(); macb_writel(bp, NCR, ctrl | MACB_BIT(RE)); if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE) @@ -1616,8 +1618,6 @@ static void macb_init_rings(struct macb *bp) bp->queues[0].tx_head = 0; bp->queues[0].tx_tail = 0; bp->queues[0].tx_ring[TX_RING_SIZE - 1].ctrl |= MACB_BIT(TX_WRAP); - - bp->rx_tail = 0; } static void macb_reset_hw(struct macb *bp) @@ -2673,6 +2673,12 @@ static int at91ether_start_xmit(struct sk_buff *skb, struct net_device *dev) lp->skb_length = skb->len; lp->skb_physaddr = dma_map_single(NULL, skb->data, skb->len, DMA_TO_DEVICE); + if (dma_mapping_error(NULL, lp->skb_physaddr)) { + dev_kfree_skb_any(skb); + dev->stats.tx_dropped++; + netdev_err(dev, "%s: DMA mapping error\n", __func__); + return NETDEV_TX_OK; + } /* Set address of the data in the Transmit Address register */ macb_writel(lp, TAR, lp->skb_physaddr); @@ -2764,6 +2770,7 @@ static irqreturn_t at91ether_interrupt(int irq, void *dev_id) if (intstatus & MACB_BIT(RXUBR)) { ctl = macb_readl(lp, NCR); macb_writel(lp, NCR, ctl & ~MACB_BIT(RE)); + wmb(); macb_writel(lp, NCR, ctl | MACB_BIT(RE)); } diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h index 30426109711c..86bd93ce2ea3 100644 --- a/drivers/net/ethernet/cavium/thunder/nic.h +++ b/drivers/net/ethernet/cavium/thunder/nic.h @@ -47,7 +47,7 @@ /* Min/Max packet size */ #define NIC_HW_MIN_FRS 64 -#define NIC_HW_MAX_FRS 9200 /* 9216 max packet including FCS */ +#define NIC_HW_MAX_FRS 9190 /* Excluding L2 header and FCS */ /* Max pkinds */ #define NIC_MAX_PKIND 16 @@ -178,11 +178,11 @@ enum tx_stats_reg_offset { struct nicvf_hw_stats { u64 rx_bytes; + u64 rx_frames; u64 rx_ucast_frames; u64 rx_bcast_frames; u64 rx_mcast_frames; - u64 rx_fcs_errors; - u64 rx_l2_errors; + u64 rx_drops; u64 rx_drop_red; u64 rx_drop_red_bytes; u64 rx_drop_overrun; @@ -191,6 +191,19 @@ struct nicvf_hw_stats { u64 rx_drop_mcast; u64 rx_drop_l3_bcast; u64 rx_drop_l3_mcast; + u64 rx_fcs_errors; + u64 rx_l2_errors; + + u64 tx_bytes; + u64 tx_frames; + u64 tx_ucast_frames; + u64 tx_bcast_frames; + u64 tx_mcast_frames; + u64 tx_drops; +}; + +struct nicvf_drv_stats { + /* CQE Rx errs */ u64 rx_bgx_truncated_pkts; u64 rx_jabber_errs; u64 rx_fcs_errs; @@ -216,34 +229,30 @@ struct nicvf_hw_stats { u64 rx_l4_pclp; u64 rx_truncated_pkts; - u64 tx_bytes_ok; - u64 tx_ucast_frames_ok; - u64 tx_bcast_frames_ok; - u64 tx_mcast_frames_ok; - u64 tx_drops; -}; - -struct nicvf_drv_stats { - /* Rx */ - u64 rx_frames_ok; - u64 rx_frames_64; - u64 rx_frames_127; - u64 rx_frames_255; - u64 rx_frames_511; - u64 rx_frames_1023; - u64 rx_frames_1518; - u64 rx_frames_jumbo; - u64 rx_drops; - + /* CQE Tx errs */ + u64 tx_desc_fault; + u64 tx_hdr_cons_err; + u64 tx_subdesc_err; + u64 tx_max_size_exceeded; + u64 tx_imm_size_oflow; + u64 tx_data_seq_err; + u64 tx_mem_seq_err; + u64 tx_lock_viol; + u64 tx_data_fault; + u64 tx_tstmp_conflict; + u64 tx_tstmp_timeout; + u64 tx_mem_fault; + u64 tx_csum_overlap; + u64 tx_csum_overflow; + + /* driver debug stats */ u64 rcv_buffer_alloc_failures; - - /* Tx */ - u64 tx_frames_ok; - u64 tx_drops; u64 tx_tso; u64 tx_timeout; u64 txq_stop; u64 txq_wake; + + struct u64_stats_sync syncp; }; struct nicvf { @@ -282,7 +291,6 @@ struct nicvf { u8 node; u8 cpi_alg; - u16 mtu; bool link_up; u8 duplex; u32 speed; @@ -298,7 +306,7 @@ struct nicvf { /* Stats */ struct nicvf_hw_stats hw_stats; - struct nicvf_drv_stats drv_stats; + struct nicvf_drv_stats __percpu *drv_stats; struct bgx_stats bgx_stats; /* MSI-X */ diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c index 2bbf4cbf08b2..6677b96e1f3f 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_main.c +++ b/drivers/net/ethernet/cavium/thunder/nic_main.c @@ -11,6 +11,7 @@ #include <linux/pci.h> #include <linux/etherdevice.h> #include <linux/of.h> +#include <linux/if_vlan.h> #include "nic_reg.h" #include "nic.h" @@ -260,18 +261,31 @@ static void nic_get_bgx_stats(struct nicpf *nic, struct bgx_stats_msg *bgx) /* Update hardware min/max frame size */ static int nic_update_hw_frs(struct nicpf *nic, int new_frs, int vf) { - if ((new_frs > NIC_HW_MAX_FRS) || (new_frs < NIC_HW_MIN_FRS)) { - dev_err(&nic->pdev->dev, - "Invalid MTU setting from VF%d rejected, should be between %d and %d\n", - vf, NIC_HW_MIN_FRS, NIC_HW_MAX_FRS); + int bgx, lmac, lmac_cnt; + u64 lmac_credits; + + if ((new_frs > NIC_HW_MAX_FRS) || (new_frs < NIC_HW_MIN_FRS)) return 1; - } - new_frs += ETH_HLEN; - if (new_frs <= nic->pkind.maxlen) - return 0; - nic->pkind.maxlen = new_frs; - nic_reg_write(nic, NIC_PF_PKIND_0_15_CFG, *(u64 *)&nic->pkind); + bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); + lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); + lmac += bgx * MAX_LMAC_PER_BGX; + + new_frs += VLAN_ETH_HLEN + ETH_FCS_LEN + 4; + + /* Update corresponding LMAC credits */ + lmac_cnt = bgx_get_lmac_count(nic->node, bgx); + lmac_credits = nic_reg_read(nic, NIC_PF_LMAC_0_7_CREDIT + (lmac * 8)); + lmac_credits &= ~(0xFFFFFULL << 12); + lmac_credits |= (((((48 * 1024) / lmac_cnt) - new_frs) / 16) << 12); + nic_reg_write(nic, NIC_PF_LMAC_0_7_CREDIT + (lmac * 8), lmac_credits); + + /* Enforce MTU in HW + * This config is supported only from 88xx pass 2.0 onwards. + */ + if (!pass1_silicon(nic->pdev)) + nic_reg_write(nic, + NIC_PF_LMAC_0_7_CFG2 + (lmac * 8), new_frs); return 0; } @@ -464,7 +478,7 @@ static int nic_init_hw(struct nicpf *nic) /* PKIND configuration */ nic->pkind.minlen = 0; - nic->pkind.maxlen = NIC_HW_MAX_FRS + ETH_HLEN; + nic->pkind.maxlen = NIC_HW_MAX_FRS + VLAN_ETH_HLEN + ETH_FCS_LEN + 4; nic->pkind.lenerr_en = 1; nic->pkind.rx_hdr = 0; nic->pkind.hdr_sl = 0; @@ -837,6 +851,7 @@ static int nic_reset_stat_counters(struct nicpf *nic, nic_reg_write(nic, reg_addr, 0); } } + return 0; } diff --git a/drivers/net/ethernet/cavium/thunder/nic_reg.h b/drivers/net/ethernet/cavium/thunder/nic_reg.h index edf779f5a227..80d46337cf29 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_reg.h +++ b/drivers/net/ethernet/cavium/thunder/nic_reg.h @@ -106,6 +106,7 @@ #define NIC_PF_MPI_0_2047_CFG (0x210000) #define NIC_PF_RSSI_0_4097_RQ (0x220000) #define NIC_PF_LMAC_0_7_CFG (0x240000) +#define NIC_PF_LMAC_0_7_CFG2 (0x240100) #define NIC_PF_LMAC_0_7_SW_XOFF (0x242000) #define NIC_PF_LMAC_0_7_CREDIT (0x244000) #define NIC_PF_CHAN_0_255_TX_CFG (0x400000) diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c index ad4fddb55421..432bf6be57cb 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c @@ -36,11 +36,11 @@ struct nicvf_stat { static const struct nicvf_stat nicvf_hw_stats[] = { NICVF_HW_STAT(rx_bytes), + NICVF_HW_STAT(rx_frames), NICVF_HW_STAT(rx_ucast_frames), NICVF_HW_STAT(rx_bcast_frames), NICVF_HW_STAT(rx_mcast_frames), - NICVF_HW_STAT(rx_fcs_errors), - NICVF_HW_STAT(rx_l2_errors), + NICVF_HW_STAT(rx_drops), NICVF_HW_STAT(rx_drop_red), NICVF_HW_STAT(rx_drop_red_bytes), NICVF_HW_STAT(rx_drop_overrun), @@ -49,50 +49,59 @@ static const struct nicvf_stat nicvf_hw_stats[] = { NICVF_HW_STAT(rx_drop_mcast), NICVF_HW_STAT(rx_drop_l3_bcast), NICVF_HW_STAT(rx_drop_l3_mcast), - NICVF_HW_STAT(rx_bgx_truncated_pkts), - NICVF_HW_STAT(rx_jabber_errs), - NICVF_HW_STAT(rx_fcs_errs), - NICVF_HW_STAT(rx_bgx_errs), - NICVF_HW_STAT(rx_prel2_errs), - NICVF_HW_STAT(rx_l2_hdr_malformed), - NICVF_HW_STAT(rx_oversize), - NICVF_HW_STAT(rx_undersize), - NICVF_HW_STAT(rx_l2_len_mismatch), - NICVF_HW_STAT(rx_l2_pclp), - NICVF_HW_STAT(rx_ip_ver_errs), - NICVF_HW_STAT(rx_ip_csum_errs), - NICVF_HW_STAT(rx_ip_hdr_malformed), - NICVF_HW_STAT(rx_ip_payload_malformed), - NICVF_HW_STAT(rx_ip_ttl_errs), - NICVF_HW_STAT(rx_l3_pclp), - NICVF_HW_STAT(rx_l4_malformed), - NICVF_HW_STAT(rx_l4_csum_errs), - NICVF_HW_STAT(rx_udp_len_errs), - NICVF_HW_STAT(rx_l4_port_errs), - NICVF_HW_STAT(rx_tcp_flag_errs), - NICVF_HW_STAT(rx_tcp_offset_errs), - NICVF_HW_STAT(rx_l4_pclp), - NICVF_HW_STAT(rx_truncated_pkts), - NICVF_HW_STAT(tx_bytes_ok), - NICVF_HW_STAT(tx_ucast_frames_ok), - NICVF_HW_STAT(tx_bcast_frames_ok), - NICVF_HW_STAT(tx_mcast_frames_ok), + NICVF_HW_STAT(rx_fcs_errors), + NICVF_HW_STAT(rx_l2_errors), + NICVF_HW_STAT(tx_bytes), + NICVF_HW_STAT(tx_frames), + NICVF_HW_STAT(tx_ucast_frames), + NICVF_HW_STAT(tx_bcast_frames), + NICVF_HW_STAT(tx_mcast_frames), + NICVF_HW_STAT(tx_drops), }; static const struct nicvf_stat nicvf_drv_stats[] = { - NICVF_DRV_STAT(rx_frames_ok), - NICVF_DRV_STAT(rx_frames_64), - NICVF_DRV_STAT(rx_frames_127), - NICVF_DRV_STAT(rx_frames_255), - NICVF_DRV_STAT(rx_frames_511), - NICVF_DRV_STAT(rx_frames_1023), - NICVF_DRV_STAT(rx_frames_1518), - NICVF_DRV_STAT(rx_frames_jumbo), - NICVF_DRV_STAT(rx_drops), + NICVF_DRV_STAT(rx_bgx_truncated_pkts), + NICVF_DRV_STAT(rx_jabber_errs), + NICVF_DRV_STAT(rx_fcs_errs), + NICVF_DRV_STAT(rx_bgx_errs), + NICVF_DRV_STAT(rx_prel2_errs), + NICVF_DRV_STAT(rx_l2_hdr_malformed), + NICVF_DRV_STAT(rx_oversize), + NICVF_DRV_STAT(rx_undersize), + NICVF_DRV_STAT(rx_l2_len_mismatch), + NICVF_DRV_STAT(rx_l2_pclp), + NICVF_DRV_STAT(rx_ip_ver_errs), + NICVF_DRV_STAT(rx_ip_csum_errs), + NICVF_DRV_STAT(rx_ip_hdr_malformed), + NICVF_DRV_STAT(rx_ip_payload_malformed), + NICVF_DRV_STAT(rx_ip_ttl_errs), + NICVF_DRV_STAT(rx_l3_pclp), + NICVF_DRV_STAT(rx_l4_malformed), + NICVF_DRV_STAT(rx_l4_csum_errs), + NICVF_DRV_STAT(rx_udp_len_errs), + NICVF_DRV_STAT(rx_l4_port_errs), + NICVF_DRV_STAT(rx_tcp_flag_errs), + NICVF_DRV_STAT(rx_tcp_offset_errs), + NICVF_DRV_STAT(rx_l4_pclp), + NICVF_DRV_STAT(rx_truncated_pkts), + + NICVF_DRV_STAT(tx_desc_fault), + NICVF_DRV_STAT(tx_hdr_cons_err), + NICVF_DRV_STAT(tx_subdesc_err), + NICVF_DRV_STAT(tx_max_size_exceeded), + NICVF_DRV_STAT(tx_imm_size_oflow), + NICVF_DRV_STAT(tx_data_seq_err), + NICVF_DRV_STAT(tx_mem_seq_err), + NICVF_DRV_STAT(tx_lock_viol), + NICVF_DRV_STAT(tx_data_fault), + NICVF_DRV_STAT(tx_tstmp_conflict), + NICVF_DRV_STAT(tx_tstmp_timeout), + NICVF_DRV_STAT(tx_mem_fault), + NICVF_DRV_STAT(tx_csum_overlap), + NICVF_DRV_STAT(tx_csum_overflow), + NICVF_DRV_STAT(rcv_buffer_alloc_failures), - NICVF_DRV_STAT(tx_frames_ok), NICVF_DRV_STAT(tx_tso), - NICVF_DRV_STAT(tx_drops), NICVF_DRV_STAT(tx_timeout), NICVF_DRV_STAT(txq_stop), NICVF_DRV_STAT(txq_wake), @@ -278,8 +287,8 @@ static void nicvf_get_ethtool_stats(struct net_device *netdev, struct ethtool_stats *stats, u64 *data) { struct nicvf *nic = netdev_priv(netdev); - int stat; - int sqs; + int stat, tmp_stats; + int sqs, cpu; nicvf_update_stats(nic); @@ -289,9 +298,13 @@ static void nicvf_get_ethtool_stats(struct net_device *netdev, for (stat = 0; stat < nicvf_n_hw_stats; stat++) *(data++) = ((u64 *)&nic->hw_stats) [nicvf_hw_stats[stat].index]; - for (stat = 0; stat < nicvf_n_drv_stats; stat++) - *(data++) = ((u64 *)&nic->drv_stats) - [nicvf_drv_stats[stat].index]; + for (stat = 0; stat < nicvf_n_drv_stats; stat++) { + tmp_stats = 0; + for_each_possible_cpu(cpu) + tmp_stats += ((u64 *)per_cpu_ptr(nic->drv_stats, cpu)) + [nicvf_drv_stats[stat].index]; + *(data++) = tmp_stats; + } nicvf_get_qset_stats(nic, stats, &data); diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index 45a13f718863..8a37012c9c89 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -69,25 +69,6 @@ static inline u8 nicvf_netdev_qidx(struct nicvf *nic, u8 qidx) return qidx; } -static inline void nicvf_set_rx_frame_cnt(struct nicvf *nic, - struct sk_buff *skb) -{ - if (skb->len <= 64) - nic->drv_stats.rx_frames_64++; - else if (skb->len <= 127) - nic->drv_stats.rx_frames_127++; - else if (skb->len <= 255) - nic->drv_stats.rx_frames_255++; - else if (skb->len <= 511) - nic->drv_stats.rx_frames_511++; - else if (skb->len <= 1023) - nic->drv_stats.rx_frames_1023++; - else if (skb->len <= 1518) - nic->drv_stats.rx_frames_1518++; - else - nic->drv_stats.rx_frames_jumbo++; -} - /* The Cavium ThunderX network controller can *only* be found in SoCs * containing the ThunderX ARM64 CPU implementation. All accesses to the device * registers on this platform are implicitly strongly ordered with respect @@ -492,9 +473,6 @@ int nicvf_set_real_num_queues(struct net_device *netdev, static int nicvf_init_resources(struct nicvf *nic) { int err; - union nic_mbx mbx = {}; - - mbx.msg.msg = NIC_MBOX_MSG_CFG_DONE; /* Enable Qset */ nicvf_qset_config(nic, true); @@ -507,14 +485,10 @@ static int nicvf_init_resources(struct nicvf *nic) return err; } - /* Send VF config done msg to PF */ - nicvf_write_to_mbx(nic, &mbx); - return 0; } static void nicvf_snd_pkt_handler(struct net_device *netdev, - struct cmp_queue *cq, struct cqe_send_t *cqe_tx, int cqe_type, int budget, unsigned int *tx_pkts, unsigned int *tx_bytes) @@ -536,7 +510,7 @@ static void nicvf_snd_pkt_handler(struct net_device *netdev, __func__, cqe_tx->sq_qs, cqe_tx->sq_idx, cqe_tx->sqe_ptr, hdr->subdesc_cnt); - nicvf_check_cqe_tx_errs(nic, cq, cqe_tx); + nicvf_check_cqe_tx_errs(nic, cqe_tx); skb = (struct sk_buff *)sq->skbuff[cqe_tx->sqe_ptr]; if (skb) { /* Check for dummy descriptor used for HW TSO offload on 88xx */ @@ -630,8 +604,6 @@ static void nicvf_rcv_pkt_handler(struct net_device *netdev, return; } - nicvf_set_rx_frame_cnt(nic, skb); - nicvf_set_rxhash(netdev, cqe_rx, skb); skb_record_rx_queue(skb, rq_idx); @@ -703,7 +675,7 @@ loop: work_done++; break; case CQE_TYPE_SEND: - nicvf_snd_pkt_handler(netdev, cq, + nicvf_snd_pkt_handler(netdev, (void *)cq_desc, CQE_TYPE_SEND, budget, &tx_pkts, &tx_bytes); tx_done++; @@ -740,7 +712,7 @@ done: nic = nic->pnicvf; if (netif_tx_queue_stopped(txq) && netif_carrier_ok(netdev)) { netif_tx_start_queue(txq); - nic->drv_stats.txq_wake++; + this_cpu_inc(nic->drv_stats->txq_wake); if (netif_msg_tx_err(nic)) netdev_warn(netdev, "%s: Transmit queue wakeup SQ%d\n", @@ -1084,7 +1056,7 @@ static netdev_tx_t nicvf_xmit(struct sk_buff *skb, struct net_device *netdev) if (!netif_tx_queue_stopped(txq) && !nicvf_sq_append_skb(nic, skb)) { netif_tx_stop_queue(txq); - nic->drv_stats.txq_stop++; + this_cpu_inc(nic->drv_stats->txq_stop); if (netif_msg_tx_err(nic)) netdev_warn(netdev, "%s: Transmit ring full, stopping SQ%d\n", @@ -1189,14 +1161,24 @@ int nicvf_stop(struct net_device *netdev) return 0; } +static int nicvf_update_hw_max_frs(struct nicvf *nic, int mtu) +{ + union nic_mbx mbx = {}; + + mbx.frs.msg = NIC_MBOX_MSG_SET_MAX_FRS; + mbx.frs.max_frs = mtu; + mbx.frs.vf_id = nic->vf_id; + + return nicvf_send_msg_to_pf(nic, &mbx); +} + int nicvf_open(struct net_device *netdev) { - int err, qidx; + int cpu, err, qidx; struct nicvf *nic = netdev_priv(netdev); struct queue_set *qs = nic->qs; struct nicvf_cq_poll *cq_poll = NULL; - - nic->mtu = netdev->mtu; + union nic_mbx mbx = {}; netif_carrier_off(netdev); @@ -1248,9 +1230,17 @@ int nicvf_open(struct net_device *netdev) if (nic->sqs_mode) nicvf_get_primary_vf_struct(nic); - /* Configure receive side scaling */ - if (!nic->sqs_mode) + /* Configure receive side scaling and MTU */ + if (!nic->sqs_mode) { nicvf_rss_init(nic); + if (nicvf_update_hw_max_frs(nic, netdev->mtu)) + goto cleanup; + + /* Clear percpu stats */ + for_each_possible_cpu(cpu) + memset(per_cpu_ptr(nic->drv_stats, cpu), 0, + sizeof(struct nicvf_drv_stats)); + } err = nicvf_register_interrupts(nic); if (err) @@ -1276,8 +1266,9 @@ int nicvf_open(struct net_device *netdev) for (qidx = 0; qidx < qs->rbdr_cnt; qidx++) nicvf_enable_intr(nic, NICVF_INTR_RBDR, qidx); - nic->drv_stats.txq_stop = 0; - nic->drv_stats.txq_wake = 0; + /* Send VF config done msg to PF */ + mbx.msg.msg = NIC_MBOX_MSG_CFG_DONE; + nicvf_write_to_mbx(nic, &mbx); return 0; cleanup: @@ -1297,17 +1288,6 @@ napi_del: return err; } -static int nicvf_update_hw_max_frs(struct nicvf *nic, int mtu) -{ - union nic_mbx mbx = {}; - - mbx.frs.msg = NIC_MBOX_MSG_SET_MAX_FRS; - mbx.frs.max_frs = mtu; - mbx.frs.vf_id = nic->vf_id; - - return nicvf_send_msg_to_pf(nic, &mbx); -} - static int nicvf_change_mtu(struct net_device *netdev, int new_mtu) { struct nicvf *nic = netdev_priv(netdev); @@ -1318,10 +1298,13 @@ static int nicvf_change_mtu(struct net_device *netdev, int new_mtu) if (new_mtu < NIC_HW_MIN_FRS) return -EINVAL; + netdev->mtu = new_mtu; + + if (!netif_running(netdev)) + return 0; + if (nicvf_update_hw_max_frs(nic, new_mtu)) return -EINVAL; - netdev->mtu = new_mtu; - nic->mtu = new_mtu; return 0; } @@ -1379,9 +1362,10 @@ void nicvf_update_lmac_stats(struct nicvf *nic) void nicvf_update_stats(struct nicvf *nic) { - int qidx; + int qidx, cpu; + u64 tmp_stats = 0; struct nicvf_hw_stats *stats = &nic->hw_stats; - struct nicvf_drv_stats *drv_stats = &nic->drv_stats; + struct nicvf_drv_stats *drv_stats; struct queue_set *qs = nic->qs; #define GET_RX_STATS(reg) \ @@ -1404,21 +1388,33 @@ void nicvf_update_stats(struct nicvf *nic) stats->rx_drop_l3_bcast = GET_RX_STATS(RX_DRP_L3BCAST); stats->rx_drop_l3_mcast = GET_RX_STATS(RX_DRP_L3MCAST); - stats->tx_bytes_ok = GET_TX_STATS(TX_OCTS); - stats->tx_ucast_frames_ok = GET_TX_STATS(TX_UCAST); - stats->tx_bcast_frames_ok = GET_TX_STATS(TX_BCAST); - stats->tx_mcast_frames_ok = GET_TX_STATS(TX_MCAST); + stats->tx_bytes = GET_TX_STATS(TX_OCTS); + stats->tx_ucast_frames = GET_TX_STATS(TX_UCAST); + stats->tx_bcast_frames = GET_TX_STATS(TX_BCAST); + stats->tx_mcast_frames = GET_TX_STATS(TX_MCAST); stats->tx_drops = GET_TX_STATS(TX_DROP); - drv_stats->tx_frames_ok = stats->tx_ucast_frames_ok + - stats->tx_bcast_frames_ok + - stats->tx_mcast_frames_ok; - drv_stats->rx_frames_ok = stats->rx_ucast_frames + - stats->rx_bcast_frames + - stats->rx_mcast_frames; - drv_stats->rx_drops = stats->rx_drop_red + - stats->rx_drop_overrun; - drv_stats->tx_drops = stats->tx_drops; + /* On T88 pass 2.0, the dummy SQE added for TSO notification + * via CQE has 'dont_send' set. Hence HW drops the pkt pointed + * pointed by dummy SQE and results in tx_drops counter being + * incremented. Subtracting it from tx_tso counter will give + * exact tx_drops counter. + */ + if (nic->t88 && nic->hw_tso) { + for_each_possible_cpu(cpu) { + drv_stats = per_cpu_ptr(nic->drv_stats, cpu); + tmp_stats += drv_stats->tx_tso; + } + stats->tx_drops = tmp_stats - stats->tx_drops; + } + stats->tx_frames = stats->tx_ucast_frames + + stats->tx_bcast_frames + + stats->tx_mcast_frames; + stats->rx_frames = stats->rx_ucast_frames + + stats->rx_bcast_frames + + stats->rx_mcast_frames; + stats->rx_drops = stats->rx_drop_red + + stats->rx_drop_overrun; /* Update RQ and SQ stats */ for (qidx = 0; qidx < qs->rq_cnt; qidx++) @@ -1432,18 +1428,17 @@ static struct rtnl_link_stats64 *nicvf_get_stats64(struct net_device *netdev, { struct nicvf *nic = netdev_priv(netdev); struct nicvf_hw_stats *hw_stats = &nic->hw_stats; - struct nicvf_drv_stats *drv_stats = &nic->drv_stats; nicvf_update_stats(nic); stats->rx_bytes = hw_stats->rx_bytes; - stats->rx_packets = drv_stats->rx_frames_ok; - stats->rx_dropped = drv_stats->rx_drops; + stats->rx_packets = hw_stats->rx_frames; + stats->rx_dropped = hw_stats->rx_drops; stats->multicast = hw_stats->rx_mcast_frames; - stats->tx_bytes = hw_stats->tx_bytes_ok; - stats->tx_packets = drv_stats->tx_frames_ok; - stats->tx_dropped = drv_stats->tx_drops; + stats->tx_bytes = hw_stats->tx_bytes; + stats->tx_packets = hw_stats->tx_frames; + stats->tx_dropped = hw_stats->tx_drops; return stats; } @@ -1456,7 +1451,7 @@ static void nicvf_tx_timeout(struct net_device *dev) netdev_warn(dev, "%s: Transmit timed out, resetting\n", dev->name); - nic->drv_stats.tx_timeout++; + this_cpu_inc(nic->drv_stats->tx_timeout); schedule_work(&nic->reset_task); } @@ -1590,6 +1585,12 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_free_netdev; } + nic->drv_stats = netdev_alloc_pcpu_stats(struct nicvf_drv_stats); + if (!nic->drv_stats) { + err = -ENOMEM; + goto err_free_netdev; + } + err = nicvf_set_qset_resources(nic); if (err) goto err_free_netdev; @@ -1648,6 +1649,8 @@ err_unregister_interrupts: nicvf_unregister_interrupts(nic); err_free_netdev: pci_set_drvdata(pdev, NULL); + if (nic->drv_stats) + free_percpu(nic->drv_stats); free_netdev(netdev); err_release_regions: pci_release_regions(pdev); @@ -1675,6 +1678,8 @@ static void nicvf_remove(struct pci_dev *pdev) unregister_netdev(pnetdev); nicvf_unregister_interrupts(nic); pci_set_drvdata(pdev, NULL); + if (nic->drv_stats) + free_percpu(nic->drv_stats); free_netdev(netdev); pci_release_regions(pdev); pci_disable_device(pdev); diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c index a4fc50155881..747ef0882976 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c @@ -104,7 +104,8 @@ static inline int nicvf_alloc_rcv_buffer(struct nicvf *nic, gfp_t gfp, nic->rb_page = alloc_pages(gfp | __GFP_COMP | __GFP_NOWARN, order); if (!nic->rb_page) { - nic->drv_stats.rcv_buffer_alloc_failures++; + this_cpu_inc(nic->pnicvf->drv_stats-> + rcv_buffer_alloc_failures); return -ENOMEM; } nic->rb_page_offset = 0; @@ -270,7 +271,8 @@ refill: rbdr_idx, new_rb); next_rbdr: /* Re-enable RBDR interrupts only if buffer allocation is success */ - if (!nic->rb_alloc_fail && rbdr->enable) + if (!nic->rb_alloc_fail && rbdr->enable && + netif_running(nic->pnicvf->netdev)) nicvf_enable_intr(nic, NICVF_INTR_RBDR, rbdr_idx); if (rbdr_idx) @@ -361,6 +363,8 @@ static int nicvf_init_snd_queue(struct nicvf *nic, static void nicvf_free_snd_queue(struct nicvf *nic, struct snd_queue *sq) { + struct sk_buff *skb; + if (!sq) return; if (!sq->dmem.base) @@ -371,6 +375,15 @@ static void nicvf_free_snd_queue(struct nicvf *nic, struct snd_queue *sq) sq->dmem.q_len * TSO_HEADER_SIZE, sq->tso_hdrs, sq->tso_hdrs_phys); + /* Free pending skbs in the queue */ + smp_rmb(); + while (sq->head != sq->tail) { + skb = (struct sk_buff *)sq->skbuff[sq->head]; + if (skb) + dev_kfree_skb_any(skb); + sq->head++; + sq->head &= (sq->dmem.q_len - 1); + } kfree(sq->skbuff); nicvf_free_q_desc_mem(nic, &sq->dmem); } @@ -483,9 +496,12 @@ static void nicvf_reset_rcv_queue_stats(struct nicvf *nic) { union nic_mbx mbx = {}; - /* Reset all RXQ's stats */ + /* Reset all RQ/SQ and VF stats */ mbx.reset_stat.msg = NIC_MBOX_MSG_RESET_STAT_COUNTER; + mbx.reset_stat.rx_stat_mask = 0x3FFF; + mbx.reset_stat.tx_stat_mask = 0x1F; mbx.reset_stat.rq_stat_mask = 0xFFFF; + mbx.reset_stat.sq_stat_mask = 0xFFFF; nicvf_send_msg_to_pf(nic, &mbx); } @@ -538,9 +554,12 @@ static void nicvf_rcv_queue_config(struct nicvf *nic, struct queue_set *qs, mbx.rq.cfg = (1ULL << 62) | (RQ_CQ_DROP << 8); nicvf_send_msg_to_pf(nic, &mbx); - nicvf_queue_reg_write(nic, NIC_QSET_RQ_GEN_CFG, 0, 0x00); - if (!nic->sqs_mode) + if (!nic->sqs_mode && (qidx == 0)) { + /* Enable checking L3/L4 length and TCP/UDP checksums */ + nicvf_queue_reg_write(nic, NIC_QSET_RQ_GEN_CFG, 0, + (BIT(24) | BIT(23) | BIT(21))); nicvf_config_vlan_stripping(nic, nic->netdev->features); + } /* Enable Receive queue */ memset(&rq_cfg, 0, sizeof(struct rq_cfg)); @@ -1029,7 +1048,7 @@ nicvf_sq_add_hdr_subdesc(struct nicvf *nic, struct snd_queue *sq, int qentry, hdr->tso_max_paysize = skb_shinfo(skb)->gso_size; /* For non-tunneled pkts, point this to L2 ethertype */ hdr->inner_l3_offset = skb_network_offset(skb) - 2; - nic->drv_stats.tx_tso++; + this_cpu_inc(nic->pnicvf->drv_stats->tx_tso); } } @@ -1161,7 +1180,7 @@ static int nicvf_sq_append_tso(struct nicvf *nic, struct snd_queue *sq, nicvf_sq_doorbell(nic, skb, sq_num, desc_cnt); - nic->drv_stats.tx_tso++; + this_cpu_inc(nic->pnicvf->drv_stats->tx_tso); return 1; } @@ -1422,8 +1441,6 @@ void nicvf_update_sq_stats(struct nicvf *nic, int sq_idx) /* Check for errors in the receive cmp.queue entry */ int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx) { - struct nicvf_hw_stats *stats = &nic->hw_stats; - if (!cqe_rx->err_level && !cqe_rx->err_opcode) return 0; @@ -1435,76 +1452,76 @@ int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx) switch (cqe_rx->err_opcode) { case CQ_RX_ERROP_RE_PARTIAL: - stats->rx_bgx_truncated_pkts++; + this_cpu_inc(nic->drv_stats->rx_bgx_truncated_pkts); break; case CQ_RX_ERROP_RE_JABBER: - stats->rx_jabber_errs++; + this_cpu_inc(nic->drv_stats->rx_jabber_errs); break; case CQ_RX_ERROP_RE_FCS: - stats->rx_fcs_errs++; + this_cpu_inc(nic->drv_stats->rx_fcs_errs); break; case CQ_RX_ERROP_RE_RX_CTL: - stats->rx_bgx_errs++; + this_cpu_inc(nic->drv_stats->rx_bgx_errs); break; case CQ_RX_ERROP_PREL2_ERR: - stats->rx_prel2_errs++; + this_cpu_inc(nic->drv_stats->rx_prel2_errs); break; case CQ_RX_ERROP_L2_MAL: - stats->rx_l2_hdr_malformed++; + this_cpu_inc(nic->drv_stats->rx_l2_hdr_malformed); break; case CQ_RX_ERROP_L2_OVERSIZE: - stats->rx_oversize++; + this_cpu_inc(nic->drv_stats->rx_oversize); break; case CQ_RX_ERROP_L2_UNDERSIZE: - stats->rx_undersize++; + this_cpu_inc(nic->drv_stats->rx_undersize); break; case CQ_RX_ERROP_L2_LENMISM: - stats->rx_l2_len_mismatch++; + this_cpu_inc(nic->drv_stats->rx_l2_len_mismatch); break; case CQ_RX_ERROP_L2_PCLP: - stats->rx_l2_pclp++; + this_cpu_inc(nic->drv_stats->rx_l2_pclp); break; case CQ_RX_ERROP_IP_NOT: - stats->rx_ip_ver_errs++; + this_cpu_inc(nic->drv_stats->rx_ip_ver_errs); break; case CQ_RX_ERROP_IP_CSUM_ERR: - stats->rx_ip_csum_errs++; + this_cpu_inc(nic->drv_stats->rx_ip_csum_errs); break; case CQ_RX_ERROP_IP_MAL: - stats->rx_ip_hdr_malformed++; + this_cpu_inc(nic->drv_stats->rx_ip_hdr_malformed); break; case CQ_RX_ERROP_IP_MALD: - stats->rx_ip_payload_malformed++; + this_cpu_inc(nic->drv_stats->rx_ip_payload_malformed); break; case CQ_RX_ERROP_IP_HOP: - stats->rx_ip_ttl_errs++; + this_cpu_inc(nic->drv_stats->rx_ip_ttl_errs); break; case CQ_RX_ERROP_L3_PCLP: - stats->rx_l3_pclp++; + this_cpu_inc(nic->drv_stats->rx_l3_pclp); break; case CQ_RX_ERROP_L4_MAL: - stats->rx_l4_malformed++; + this_cpu_inc(nic->drv_stats->rx_l4_malformed); break; case CQ_RX_ERROP_L4_CHK: - stats->rx_l4_csum_errs++; + this_cpu_inc(nic->drv_stats->rx_l4_csum_errs); break; case CQ_RX_ERROP_UDP_LEN: - stats->rx_udp_len_errs++; + this_cpu_inc(nic->drv_stats->rx_udp_len_errs); break; case CQ_RX_ERROP_L4_PORT: - stats->rx_l4_port_errs++; + this_cpu_inc(nic->drv_stats->rx_l4_port_errs); break; case CQ_RX_ERROP_TCP_FLAG: - stats->rx_tcp_flag_errs++; + this_cpu_inc(nic->drv_stats->rx_tcp_flag_errs); break; case CQ_RX_ERROP_TCP_OFFSET: - stats->rx_tcp_offset_errs++; + this_cpu_inc(nic->drv_stats->rx_tcp_offset_errs); break; case CQ_RX_ERROP_L4_PCLP: - stats->rx_l4_pclp++; + this_cpu_inc(nic->drv_stats->rx_l4_pclp); break; case CQ_RX_ERROP_RBDR_TRUNC: - stats->rx_truncated_pkts++; + this_cpu_inc(nic->drv_stats->rx_truncated_pkts); break; } @@ -1512,53 +1529,52 @@ int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx) } /* Check for errors in the send cmp.queue entry */ -int nicvf_check_cqe_tx_errs(struct nicvf *nic, - struct cmp_queue *cq, struct cqe_send_t *cqe_tx) +int nicvf_check_cqe_tx_errs(struct nicvf *nic, struct cqe_send_t *cqe_tx) { - struct cmp_queue_stats *stats = &cq->stats; - switch (cqe_tx->send_status) { case CQ_TX_ERROP_GOOD: - stats->tx.good++; return 0; case CQ_TX_ERROP_DESC_FAULT: - stats->tx.desc_fault++; + this_cpu_inc(nic->drv_stats->tx_desc_fault); break; case CQ_TX_ERROP_HDR_CONS_ERR: - stats->tx.hdr_cons_err++; + this_cpu_inc(nic->drv_stats->tx_hdr_cons_err); break; case CQ_TX_ERROP_SUBDC_ERR: - stats->tx.subdesc_err++; + this_cpu_inc(nic->drv_stats->tx_subdesc_err); + break; + case CQ_TX_ERROP_MAX_SIZE_VIOL: + this_cpu_inc(nic->drv_stats->tx_max_size_exceeded); break; case CQ_TX_ERROP_IMM_SIZE_OFLOW: - stats->tx.imm_size_oflow++; + this_cpu_inc(nic->drv_stats->tx_imm_size_oflow); break; case CQ_TX_ERROP_DATA_SEQUENCE_ERR: - stats->tx.data_seq_err++; + this_cpu_inc(nic->drv_stats->tx_data_seq_err); break; case CQ_TX_ERROP_MEM_SEQUENCE_ERR: - stats->tx.mem_seq_err++; + this_cpu_inc(nic->drv_stats->tx_mem_seq_err); break; case CQ_TX_ERROP_LOCK_VIOL: - stats->tx.lock_viol++; + this_cpu_inc(nic->drv_stats->tx_lock_viol); break; case CQ_TX_ERROP_DATA_FAULT: - stats->tx.data_fault++; + this_cpu_inc(nic->drv_stats->tx_data_fault); break; case CQ_TX_ERROP_TSTMP_CONFLICT: - stats->tx.tstmp_conflict++; + this_cpu_inc(nic->drv_stats->tx_tstmp_conflict); break; case CQ_TX_ERROP_TSTMP_TIMEOUT: - stats->tx.tstmp_timeout++; + this_cpu_inc(nic->drv_stats->tx_tstmp_timeout); break; case CQ_TX_ERROP_MEM_FAULT: - stats->tx.mem_fault++; + this_cpu_inc(nic->drv_stats->tx_mem_fault); break; case CQ_TX_ERROP_CK_OVERLAP: - stats->tx.csum_overlap++; + this_cpu_inc(nic->drv_stats->tx_csum_overlap); break; case CQ_TX_ERROP_CK_OFLOW: - stats->tx.csum_overflow++; + this_cpu_inc(nic->drv_stats->tx_csum_overflow); break; } diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h index 869f3386028b..2e3c940c1093 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h @@ -158,6 +158,7 @@ enum CQ_TX_ERROP_E { CQ_TX_ERROP_DESC_FAULT = 0x10, CQ_TX_ERROP_HDR_CONS_ERR = 0x11, CQ_TX_ERROP_SUBDC_ERR = 0x12, + CQ_TX_ERROP_MAX_SIZE_VIOL = 0x13, CQ_TX_ERROP_IMM_SIZE_OFLOW = 0x80, CQ_TX_ERROP_DATA_SEQUENCE_ERR = 0x81, CQ_TX_ERROP_MEM_SEQUENCE_ERR = 0x82, @@ -171,25 +172,6 @@ enum CQ_TX_ERROP_E { CQ_TX_ERROP_ENUM_LAST = 0x8a, }; -struct cmp_queue_stats { - struct tx_stats { - u64 good; - u64 desc_fault; - u64 hdr_cons_err; - u64 subdesc_err; - u64 imm_size_oflow; - u64 data_seq_err; - u64 mem_seq_err; - u64 lock_viol; - u64 data_fault; - u64 tstmp_conflict; - u64 tstmp_timeout; - u64 mem_fault; - u64 csum_overlap; - u64 csum_overflow; - } tx; -} ____cacheline_aligned_in_smp; - enum RQ_SQ_STATS { RQ_SQ_STATS_OCTS, RQ_SQ_STATS_PKTS, @@ -241,7 +223,6 @@ struct cmp_queue { spinlock_t lock; /* lock to serialize processing CQEs */ void *desc; struct q_desc_mem dmem; - struct cmp_queue_stats stats; int irq; } ____cacheline_aligned_in_smp; @@ -336,6 +317,5 @@ u64 nicvf_queue_reg_read(struct nicvf *nic, void nicvf_update_rq_stats(struct nicvf *nic, int rq_idx); void nicvf_update_sq_stats(struct nicvf *nic, int sq_idx); int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx); -int nicvf_check_cqe_tx_errs(struct nicvf *nic, - struct cmp_queue *cq, struct cqe_send_t *cqe_tx); +int nicvf_check_cqe_tx_errs(struct nicvf *nic, struct cqe_send_t *cqe_tx); #endif /* NICVF_QUEUES_H */ diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index 8bbaedbb7b94..050e21fbb147 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -1242,8 +1242,8 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pci_read_config_word(pdev, PCI_DEVICE_ID, &sdevid); if (sdevid != PCI_DEVICE_ID_THUNDER_RGX) { - bgx->bgx_id = - (pci_resource_start(pdev, PCI_CFG_REG_BAR_NUM) >> 24) & 1; + bgx->bgx_id = (pci_resource_start(pdev, + PCI_CFG_REG_BAR_NUM) >> 24) & BGX_ID_MASK; bgx->bgx_id += nic_get_node_id(pdev) * MAX_BGX_PER_NODE; bgx->max_lmac = MAX_LMAC_PER_BGX; bgx_vnic[bgx->bgx_id] = bgx; diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h index d59c71e4a000..01cc7c859131 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h @@ -28,6 +28,8 @@ #define MAX_DMAC_PER_LMAC 8 #define MAX_FRAME_SIZE 9216 +#define BGX_ID_MASK 0x3 + #define MAX_DMAC_PER_LMAC_TNS_BYPASS_MODE 2 /* Registers */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 57eb4e1345cb..19dc9e25aa72 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -4931,6 +4931,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) */ for_each_port(adapter, i) { pi = adap2pinfo(adapter, i); + adapter->port[i]->dev_port = pi->lport; netif_set_real_num_tx_queues(adapter->port[i], pi->nqsets); netif_set_real_num_rx_queues(adapter->port[i], pi->nqsets); diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index 1e74fd6085df..e19a0ca8e5dd 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -2951,7 +2951,6 @@ void free_rspq_fl(struct adapter *adap, struct sge_rspq *rq, rq->cntxt_id, fl_id, 0xffff); dma_free_coherent(adap->pdev_dev, (rq->size + 1) * rq->iqe_len, rq->desc, rq->phys_addr); - napi_hash_del(&rq->napi); netif_napi_del(&rq->napi); rq->netdev = NULL; rq->cntxt_id = rq->abs_id = 0; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 20dec85da63d..e8139514d32c 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -7851,7 +7851,6 @@ int t4_port_init(struct adapter *adap, int mbox, int pf, int vf) return ret; memcpy(adap->port[i]->dev_addr, addr, ETH_ALEN); - adap->port[i]->dev_port = j; j++; } return 0; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h index df1573c4a659..ecf3ccc257bc 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h @@ -168,6 +168,7 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN CH_PCI_ID_TABLE_FENTRY(0x509a), /* Custom T520-CR */ CH_PCI_ID_TABLE_FENTRY(0x509b), /* Custom T540-CR LOM */ CH_PCI_ID_TABLE_FENTRY(0x509c), /* Custom T520-CR*/ + CH_PCI_ID_TABLE_FENTRY(0x509d), /* Custom T540-CR*/ /* T6 adapters: */ diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index 100b2cc064a3..a37481c04a87 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -2969,6 +2969,7 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev, netdev->netdev_ops = &cxgb4vf_netdev_ops; netdev->ethtool_ops = &cxgb4vf_ethtool_ops; + netdev->dev_port = pi->port_id; /* * Initialize the hardware/software state for the port. diff --git a/drivers/net/ethernet/cirrus/ep93xx_eth.c b/drivers/net/ethernet/cirrus/ep93xx_eth.c index de9f7c97d916..9a161e981529 100644 --- a/drivers/net/ethernet/cirrus/ep93xx_eth.c +++ b/drivers/net/ethernet/cirrus/ep93xx_eth.c @@ -468,6 +468,9 @@ static void ep93xx_free_buffers(struct ep93xx_priv *ep) struct device *dev = ep->dev->dev.parent; int i; + if (!ep->descs) + return; + for (i = 0; i < RX_QUEUE_ENTRIES; i++) { dma_addr_t d; @@ -490,6 +493,7 @@ static void ep93xx_free_buffers(struct ep93xx_priv *ep) dma_free_coherent(dev, sizeof(struct ep93xx_descs), ep->descs, ep->descs_dma_addr); + ep->descs = NULL; } static int ep93xx_alloc_buffers(struct ep93xx_priv *ep) diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index 1fb5d7239254..0e74529a4209 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -90,7 +90,8 @@ static struct be_cmd_priv_map cmd_priv_map[] = { { OPCODE_COMMON_SET_HSW_CONFIG, CMD_SUBSYSTEM_COMMON, - BE_PRIV_DEVCFG | BE_PRIV_VHADM + BE_PRIV_DEVCFG | BE_PRIV_VHADM | + BE_PRIV_DEVSEC }, { OPCODE_COMMON_GET_EXT_FAT_CAPABILITIES, diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index cece8a08edca..93aa2939142a 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -2813,7 +2813,6 @@ static void be_evt_queues_destroy(struct be_adapter *adapter) if (eqo->q.created) { be_eq_clean(eqo); be_cmd_q_destroy(adapter, &eqo->q, QTYPE_EQ); - napi_hash_del(&eqo->napi); netif_napi_del(&eqo->napi); free_cpumask_var(eqo->affinity_mask); } diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h index c865135f3cb9..5ea740b4cf14 100644 --- a/drivers/net/ethernet/freescale/fec.h +++ b/drivers/net/ethernet/freescale/fec.h @@ -574,6 +574,8 @@ struct fec_enet_private { unsigned int reload_period; int pps_enable; unsigned int next_counter; + + u64 ethtool_stats[0]; }; void fec_ptp_init(struct platform_device *pdev); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 5aa9d4ded214..12aef1b15356 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -2313,14 +2313,26 @@ static const struct fec_stat { { "IEEE_rx_octets_ok", IEEE_R_OCTETS_OK }, }; -static void fec_enet_get_ethtool_stats(struct net_device *dev, - struct ethtool_stats *stats, u64 *data) +#define FEC_STATS_SIZE (ARRAY_SIZE(fec_stats) * sizeof(u64)) + +static void fec_enet_update_ethtool_stats(struct net_device *dev) { struct fec_enet_private *fep = netdev_priv(dev); int i; for (i = 0; i < ARRAY_SIZE(fec_stats); i++) - data[i] = readl(fep->hwp + fec_stats[i].offset); + fep->ethtool_stats[i] = readl(fep->hwp + fec_stats[i].offset); +} + +static void fec_enet_get_ethtool_stats(struct net_device *dev, + struct ethtool_stats *stats, u64 *data) +{ + struct fec_enet_private *fep = netdev_priv(dev); + + if (netif_running(dev)) + fec_enet_update_ethtool_stats(dev); + + memcpy(data, fep->ethtool_stats, FEC_STATS_SIZE); } static void fec_enet_get_strings(struct net_device *netdev, @@ -2345,6 +2357,12 @@ static int fec_enet_get_sset_count(struct net_device *dev, int sset) return -EOPNOTSUPP; } } + +#else /* !defined(CONFIG_M5272) */ +#define FEC_STATS_SIZE 0 +static inline void fec_enet_update_ethtool_stats(struct net_device *dev) +{ +} #endif /* !defined(CONFIG_M5272) */ static int fec_enet_nway_reset(struct net_device *dev) @@ -2874,6 +2892,8 @@ fec_enet_close(struct net_device *ndev) if (fep->quirks & FEC_QUIRK_ERR006687) imx6q_cpuidle_fec_irqs_unused(); + fec_enet_update_ethtool_stats(ndev); + fec_enet_clk_enable(ndev, false); pinctrl_pm_select_sleep_state(&fep->pdev->dev); pm_runtime_mark_last_busy(&fep->pdev->dev); @@ -3180,6 +3200,8 @@ static int fec_enet_init(struct net_device *ndev) fec_restart(ndev); + fec_enet_update_ethtool_stats(ndev); + return 0; } @@ -3278,8 +3300,8 @@ fec_probe(struct platform_device *pdev) fec_enet_get_queue_num(pdev, &num_tx_qs, &num_rx_qs); /* Init network device */ - ndev = alloc_etherdev_mqs(sizeof(struct fec_enet_private), - num_tx_qs, num_rx_qs); + ndev = alloc_etherdev_mqs(sizeof(struct fec_enet_private) + + FEC_STATS_SIZE, num_tx_qs, num_rx_qs); if (!ndev) return -ENOMEM; @@ -3475,6 +3497,8 @@ failed_regulator: failed_clk_ipg: fec_enet_clk_enable(ndev, false); failed_clk: + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); failed_phy: of_node_put(phy_node); failed_ioremap: @@ -3488,6 +3512,7 @@ fec_drv_remove(struct platform_device *pdev) { struct net_device *ndev = platform_get_drvdata(pdev); struct fec_enet_private *fep = netdev_priv(ndev); + struct device_node *np = pdev->dev.of_node; cancel_work_sync(&fep->tx_timeout_work); fec_ptp_stop(pdev); @@ -3495,6 +3520,8 @@ fec_drv_remove(struct platform_device *pdev) fec_enet_mii_remove(fep); if (fep->reg_phy) regulator_disable(fep->reg_phy); + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); of_node_put(fep->phy_node); free_netdev(ndev); diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c index 53ef51e3bd9e..71a5ded9d1de 100644 --- a/drivers/net/ethernet/freescale/fman/fman_memac.c +++ b/drivers/net/ethernet/freescale/fman/fman_memac.c @@ -1107,6 +1107,9 @@ int memac_free(struct fman_mac *memac) { free_init_resources(memac); + if (memac->pcsphy) + put_device(&memac->pcsphy->mdio.dev); + kfree(memac->memac_drv_param); kfree(memac); diff --git a/drivers/net/ethernet/freescale/fman/fman_tgec.c b/drivers/net/ethernet/freescale/fman/fman_tgec.c index efabb04a1ae8..4b0f3a50b293 100644 --- a/drivers/net/ethernet/freescale/fman/fman_tgec.c +++ b/drivers/net/ethernet/freescale/fman/fman_tgec.c @@ -722,9 +722,6 @@ int tgec_free(struct fman_mac *tgec) { free_init_resources(tgec); - if (tgec->cfg) - tgec->cfg = NULL; - kfree(tgec->cfg); kfree(tgec); diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c index 8fe6b3e253fa..736db9d9b0ad 100644 --- a/drivers/net/ethernet/freescale/fman/mac.c +++ b/drivers/net/ethernet/freescale/fman/mac.c @@ -892,6 +892,8 @@ static int mac_probe(struct platform_device *_of_dev) priv->fixed_link->duplex = phy->duplex; priv->fixed_link->pause = phy->pause; priv->fixed_link->asym_pause = phy->asym_pause; + + put_device(&phy->mdio.dev); } err = mac_dev->init(mac_dev); diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c index dc120c148d97..4b86260584a0 100644 --- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c +++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c @@ -980,7 +980,7 @@ static int fs_enet_probe(struct platform_device *ofdev) err = clk_prepare_enable(clk); if (err) { ret = err; - goto out_free_fpi; + goto out_deregister_fixed_link; } fpi->clk_per = clk; } @@ -1061,6 +1061,9 @@ out_put: of_node_put(fpi->phy_node); if (fpi->clk_per) clk_disable_unprepare(fpi->clk_per); +out_deregister_fixed_link: + if (of_phy_is_fixed_link(ofdev->dev.of_node)) + of_phy_deregister_fixed_link(ofdev->dev.of_node); out_free_fpi: kfree(fpi); return ret; @@ -1079,6 +1082,8 @@ static int fs_enet_remove(struct platform_device *ofdev) of_node_put(fep->fpi->phy_node); if (fep->fpi->clk_per) clk_disable_unprepare(fep->fpi->clk_per); + if (of_phy_is_fixed_link(ofdev->dev.of_node)) + of_phy_deregister_fixed_link(ofdev->dev.of_node); free_netdev(ndev); return 0; } diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 4b4f5bc0e279..9061c2f82b9c 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -1312,6 +1312,7 @@ static void gfar_init_addr_hash_table(struct gfar_private *priv) */ static int gfar_probe(struct platform_device *ofdev) { + struct device_node *np = ofdev->dev.of_node; struct net_device *dev = NULL; struct gfar_private *priv = NULL; int err = 0, i; @@ -1462,6 +1463,8 @@ static int gfar_probe(struct platform_device *ofdev) return 0; register_fail: + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); unmap_group_regs(priv); gfar_free_rx_queues(priv); gfar_free_tx_queues(priv); @@ -1474,11 +1477,16 @@ register_fail: static int gfar_remove(struct platform_device *ofdev) { struct gfar_private *priv = platform_get_drvdata(ofdev); + struct device_node *np = ofdev->dev.of_node; of_node_put(priv->phy_node); of_node_put(priv->tbi_node); unregister_netdev(priv->ndev); + + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); + unmap_group_regs(priv); gfar_free_rx_queues(priv); gfar_free_tx_queues(priv); diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c index 186ef8f16c80..f76d33279454 100644 --- a/drivers/net/ethernet/freescale/ucc_geth.c +++ b/drivers/net/ethernet/freescale/ucc_geth.c @@ -3868,9 +3868,8 @@ static int ucc_geth_probe(struct platform_device* ofdev) dev = alloc_etherdev(sizeof(*ugeth)); if (dev == NULL) { - of_node_put(ug_info->tbi_node); - of_node_put(ug_info->phy_node); - return -ENOMEM; + err = -ENOMEM; + goto err_deregister_fixed_link; } ugeth = netdev_priv(dev); @@ -3907,10 +3906,7 @@ static int ucc_geth_probe(struct platform_device* ofdev) if (netif_msg_probe(ugeth)) pr_err("%s: Cannot register net device, aborting\n", dev->name); - free_netdev(dev); - of_node_put(ug_info->tbi_node); - of_node_put(ug_info->phy_node); - return err; + goto err_free_netdev; } mac_addr = of_get_mac_address(np); @@ -3923,16 +3919,29 @@ static int ucc_geth_probe(struct platform_device* ofdev) ugeth->node = np; return 0; + +err_free_netdev: + free_netdev(dev); +err_deregister_fixed_link: + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); + of_node_put(ug_info->tbi_node); + of_node_put(ug_info->phy_node); + + return err; } static int ucc_geth_remove(struct platform_device* ofdev) { struct net_device *dev = platform_get_drvdata(ofdev); struct ucc_geth_private *ugeth = netdev_priv(dev); + struct device_node *np = ofdev->dev.of_node; unregister_netdev(dev); free_netdev(dev); ucc_geth_memclean(ugeth); + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); of_node_put(ugeth->ug_info->tbi_node); of_node_put(ugeth->ug_info->phy_node); diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index ebe60719e489..a36022ba4e42 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -58,7 +58,7 @@ static struct kobj_type ktype_veth_pool; static const char ibmveth_driver_name[] = "ibmveth"; static const char ibmveth_driver_string[] = "IBM Power Virtual Ethernet Driver"; -#define ibmveth_driver_version "1.05" +#define ibmveth_driver_version "1.06" MODULE_AUTHOR("Santiago Leon <santil@linux.vnet.ibm.com>"); MODULE_DESCRIPTION("IBM Power Virtual Ethernet Driver"); @@ -137,6 +137,11 @@ static inline int ibmveth_rxq_frame_offset(struct ibmveth_adapter *adapter) return ibmveth_rxq_flags(adapter) & IBMVETH_RXQ_OFF_MASK; } +static inline int ibmveth_rxq_large_packet(struct ibmveth_adapter *adapter) +{ + return ibmveth_rxq_flags(adapter) & IBMVETH_RXQ_LRG_PKT; +} + static inline int ibmveth_rxq_frame_length(struct ibmveth_adapter *adapter) { return be32_to_cpu(adapter->rx_queue.queue_addr[adapter->rx_queue.index].length); @@ -1174,6 +1179,45 @@ map_failed: goto retry_bounce; } +static void ibmveth_rx_mss_helper(struct sk_buff *skb, u16 mss, int lrg_pkt) +{ + int offset = 0; + + /* only TCP packets will be aggregated */ + if (skb->protocol == htons(ETH_P_IP)) { + struct iphdr *iph = (struct iphdr *)skb->data; + + if (iph->protocol == IPPROTO_TCP) { + offset = iph->ihl * 4; + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; + } else { + return; + } + } else if (skb->protocol == htons(ETH_P_IPV6)) { + struct ipv6hdr *iph6 = (struct ipv6hdr *)skb->data; + + if (iph6->nexthdr == IPPROTO_TCP) { + offset = sizeof(struct ipv6hdr); + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; + } else { + return; + } + } else { + return; + } + /* if mss is not set through Large Packet bit/mss in rx buffer, + * expect that the mss will be written to the tcp header checksum. + */ + if (lrg_pkt) { + skb_shinfo(skb)->gso_size = mss; + } else if (offset) { + struct tcphdr *tcph = (struct tcphdr *)(skb->data + offset); + + skb_shinfo(skb)->gso_size = ntohs(tcph->check); + tcph->check = 0; + } +} + static int ibmveth_poll(struct napi_struct *napi, int budget) { struct ibmveth_adapter *adapter = @@ -1182,6 +1226,7 @@ static int ibmveth_poll(struct napi_struct *napi, int budget) int frames_processed = 0; unsigned long lpar_rc; struct iphdr *iph; + u16 mss = 0; restart_poll: while (frames_processed < budget) { @@ -1199,9 +1244,21 @@ restart_poll: int length = ibmveth_rxq_frame_length(adapter); int offset = ibmveth_rxq_frame_offset(adapter); int csum_good = ibmveth_rxq_csum_good(adapter); + int lrg_pkt = ibmveth_rxq_large_packet(adapter); skb = ibmveth_rxq_get_buffer(adapter); + /* if the large packet bit is set in the rx queue + * descriptor, the mss will be written by PHYP eight + * bytes from the start of the rx buffer, which is + * skb->data at this stage + */ + if (lrg_pkt) { + __be64 *rxmss = (__be64 *)(skb->data + 8); + + mss = (u16)be64_to_cpu(*rxmss); + } + new_skb = NULL; if (length < rx_copybreak) new_skb = netdev_alloc_skb(netdev, length); @@ -1235,11 +1292,15 @@ restart_poll: if (iph->check == 0xffff) { iph->check = 0; iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); - adapter->rx_large_packets++; } } } + if (length > netdev->mtu + ETH_HLEN) { + ibmveth_rx_mss_helper(skb, mss, lrg_pkt); + adapter->rx_large_packets++; + } + napi_gro_receive(napi, skb); /* send it up */ netdev->stats.rx_packets++; diff --git a/drivers/net/ethernet/ibm/ibmveth.h b/drivers/net/ethernet/ibm/ibmveth.h index 4eade67fe30c..7acda04d034e 100644 --- a/drivers/net/ethernet/ibm/ibmveth.h +++ b/drivers/net/ethernet/ibm/ibmveth.h @@ -209,6 +209,7 @@ struct ibmveth_rx_q_entry { #define IBMVETH_RXQ_TOGGLE 0x80000000 #define IBMVETH_RXQ_TOGGLE_SHIFT 31 #define IBMVETH_RXQ_VALID 0x40000000 +#define IBMVETH_RXQ_LRG_PKT 0x04000000 #define IBMVETH_RXQ_NO_CSUM 0x02000000 #define IBMVETH_RXQ_CSUM_GOOD 0x01000000 #define IBMVETH_RXQ_OFF_MASK 0x0000FFFF diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 4f3281a03e7e..0fbf686f5e7c 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -74,7 +74,6 @@ #include <asm/iommu.h> #include <linux/uaccess.h> #include <asm/firmware.h> -#include <linux/seq_file.h> #include <linux/workqueue.h> #include "ibmvnic.h" diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index edc9a6ac5169..9affd7c198bd 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -4931,11 +4931,15 @@ static int igb_tso(struct igb_ring *tx_ring, /* initialize outer IP header fields */ if (ip.v4->version == 4) { + unsigned char *csum_start = skb_checksum_start(skb); + unsigned char *trans_start = ip.hdr + (ip.v4->ihl * 4); + /* IP header will have to cancel out any data that * is not a part of the outer IP header */ - ip.v4->check = csum_fold(csum_add(lco_csum(skb), - csum_unfold(l4.tcp->check))); + ip.v4->check = csum_fold(csum_partial(trans_start, + csum_start - trans_start, + 0)); type_tucmd |= E1000_ADVTXD_TUCMD_IPV4; ip.v4->tot_len = 0; diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index 12bb877df860..7dff7f6239cd 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -1965,11 +1965,15 @@ static int igbvf_tso(struct igbvf_ring *tx_ring, /* initialize outer IP header fields */ if (ip.v4->version == 4) { + unsigned char *csum_start = skb_checksum_start(skb); + unsigned char *trans_start = ip.hdr + (ip.v4->ihl * 4); + /* IP header will have to cancel out any data that * is not a part of the outer IP header */ - ip.v4->check = csum_fold(csum_add(lco_csum(skb), - csum_unfold(l4.tcp->check))); + ip.v4->check = csum_fold(csum_partial(trans_start, + csum_start - trans_start, + 0)); type_tucmd |= E1000_ADVTXD_TUCMD_IPV4; ip.v4->tot_len = 0; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index bd93d823cc25..fee1f2918ead 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -7277,11 +7277,15 @@ static int ixgbe_tso(struct ixgbe_ring *tx_ring, /* initialize outer IP header fields */ if (ip.v4->version == 4) { + unsigned char *csum_start = skb_checksum_start(skb); + unsigned char *trans_start = ip.hdr + (ip.v4->ihl * 4); + /* IP header will have to cancel out any data that * is not a part of the outer IP header */ - ip.v4->check = csum_fold(csum_add(lco_csum(skb), - csum_unfold(l4.tcp->check))); + ip.v4->check = csum_fold(csum_partial(trans_start, + csum_start - trans_start, + 0)); type_tucmd |= IXGBE_ADVTXD_TUCMD_IPV4; ip.v4->tot_len = 0; diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 7eaac3234049..cbf70fe4028a 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -3329,11 +3329,15 @@ static int ixgbevf_tso(struct ixgbevf_ring *tx_ring, /* initialize outer IP header fields */ if (ip.v4->version == 4) { + unsigned char *csum_start = skb_checksum_start(skb); + unsigned char *trans_start = ip.hdr + (ip.v4->ihl * 4); + /* IP header will have to cancel out any data that * is not a part of the outer IP header */ - ip.v4->check = csum_fold(csum_add(lco_csum(skb), - csum_unfold(l4.tcp->check))); + ip.v4->check = csum_fold(csum_partial(trans_start, + csum_start - trans_start, + 0)); type_tucmd |= IXGBE_ADVTXD_TUCMD_IPV4; ip.v4->tot_len = 0; diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c index 91e09d68b7e2..a167fd7ee13e 100644 --- a/drivers/net/ethernet/lantiq_etop.c +++ b/drivers/net/ethernet/lantiq_etop.c @@ -704,6 +704,7 @@ ltq_etop_probe(struct platform_device *pdev) priv->pldata = dev_get_platdata(&pdev->dev); priv->netdev = dev; spin_lock_init(&priv->lock); + SET_NETDEV_DEV(dev, &pdev->dev); for (i = 0; i < MAX_DMA_CHAN; i++) { if (IS_TX(i)) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 5cb07c2017bf..707bc4680b9b 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -4151,7 +4151,7 @@ static int mvneta_probe(struct platform_device *pdev) dev->features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO; dev->hw_features |= dev->features; dev->vlan_features |= dev->features; - dev->priv_flags |= IFF_UNICAST_FLT | IFF_LIVE_ADDR_CHANGE; + dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; dev->gso_max_segs = MVNETA_MAX_TSO_SEGS; err = register_netdev(dev); @@ -4191,6 +4191,8 @@ err_clk: clk_disable_unprepare(pp->clk); err_put_phy_node: of_node_put(phy_node); + if (of_phy_is_fixed_link(dn)) + of_phy_deregister_fixed_link(dn); err_free_irq: irq_dispose_mapping(dev->irq); err_free_netdev: @@ -4202,6 +4204,7 @@ err_free_netdev: static int mvneta_remove(struct platform_device *pdev) { struct net_device *dev = platform_get_drvdata(pdev); + struct device_node *dn = pdev->dev.of_node; struct mvneta_port *pp = netdev_priv(dev); unregister_netdev(dev); @@ -4209,6 +4212,8 @@ static int mvneta_remove(struct platform_device *pdev) clk_disable_unprepare(pp->clk); free_percpu(pp->ports); free_percpu(pp->stats); + if (of_phy_is_fixed_link(dn)) + of_phy_deregister_fixed_link(dn); irq_dispose_mapping(dev->irq); of_node_put(pp->phy_node); free_netdev(dev); diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index 60227a3452a4..1026c452e39d 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -3293,7 +3293,7 @@ static void mvpp2_cls_init(struct mvpp2 *priv) mvpp2_write(priv, MVPP2_CLS_MODE_REG, MVPP2_CLS_MODE_ACTIVE_MASK); /* Clear classifier flow table */ - memset(&fe.data, 0, MVPP2_CLS_FLOWS_TBL_DATA_WORDS); + memset(&fe.data, 0, sizeof(fe.data)); for (index = 0; index < MVPP2_CLS_FLOWS_TBL_SIZE; index++) { fe.index = index; mvpp2_cls_flow_write(priv, &fe); diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index f05ea56dcff2..941c8e2c944e 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -5220,6 +5220,19 @@ static SIMPLE_DEV_PM_OPS(sky2_pm_ops, sky2_suspend, sky2_resume); static void sky2_shutdown(struct pci_dev *pdev) { + struct sky2_hw *hw = pci_get_drvdata(pdev); + int port; + + for (port = 0; port < hw->ports; port++) { + struct net_device *ndev = hw->dev[port]; + + rtnl_lock(); + if (netif_running(ndev)) { + dev_close(ndev); + netif_device_detach(ndev); + } + rtnl_unlock(); + } sky2_suspend(&pdev->dev); pci_wake_from_d3(pdev, device_may_wakeup(&pdev->dev)); pci_set_power_state(pdev, PCI_D3hot); diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 4a62ffd7729d..86a89cbd3ec9 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -318,6 +318,8 @@ static int mtk_phy_connect(struct net_device *dev) return 0; err_phy: + if (of_phy_is_fixed_link(mac->of_node)) + of_phy_deregister_fixed_link(mac->of_node); of_node_put(np); dev_err(eth->dev, "%s: invalid phy\n", __func__); return -EINVAL; @@ -1923,6 +1925,8 @@ static void mtk_uninit(struct net_device *dev) struct mtk_eth *eth = mac->hw; phy_disconnect(dev->phydev); + if (of_phy_is_fixed_link(mac->of_node)) + of_phy_deregister_fixed_link(mac->of_node); mtk_irq_disable(eth, MTK_QDMA_INT_MASK, ~0); mtk_irq_disable(eth, MTK_PDMA_INT_MASK, ~0); } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 3a47e83d3e07..fb8bb027b69c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -129,6 +129,9 @@ static enum mlx4_net_trans_rule_id mlx4_ip_proto_to_trans_rule_id(u8 ip_proto) } }; +/* Must not acquire state_lock, as its corresponding work_sync + * is done under it. + */ static void mlx4_en_filter_work(struct work_struct *work) { struct mlx4_en_filter *filter = container_of(work, @@ -2076,13 +2079,6 @@ err: return -ENOMEM; } -static void mlx4_en_shutdown(struct net_device *dev) -{ - rtnl_lock(); - netif_device_detach(dev); - mlx4_en_close(dev); - rtnl_unlock(); -} static int mlx4_en_copy_priv(struct mlx4_en_priv *dst, struct mlx4_en_priv *src, @@ -2159,8 +2155,6 @@ void mlx4_en_destroy_netdev(struct net_device *dev) { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_en_dev *mdev = priv->mdev; - bool shutdown = mdev->dev->persist->interface_state & - MLX4_INTERFACE_STATE_SHUTDOWN; en_dbg(DRV, priv, "Destroying netdev on port:%d\n", priv->port); @@ -2168,10 +2162,7 @@ void mlx4_en_destroy_netdev(struct net_device *dev) if (priv->registered) { devlink_port_type_clear(mlx4_get_devlink_port(mdev->dev, priv->port)); - if (shutdown) - mlx4_en_shutdown(dev); - else - unregister_netdev(dev); + unregister_netdev(dev); } if (priv->allocated) @@ -2189,19 +2180,18 @@ void mlx4_en_destroy_netdev(struct net_device *dev) mutex_lock(&mdev->state_lock); mdev->pndev[priv->port] = NULL; mdev->upper[priv->port] = NULL; - mutex_unlock(&mdev->state_lock); #ifdef CONFIG_RFS_ACCEL mlx4_en_cleanup_filters(priv); #endif mlx4_en_free_resources(priv); + mutex_unlock(&mdev->state_lock); kfree(priv->tx_ring); kfree(priv->tx_cq); - if (!shutdown) - free_netdev(dev); + free_netdev(dev); } static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu) diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 6f4e67bc3538..75d07fa9d0b1 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -4147,11 +4147,8 @@ static void mlx4_shutdown(struct pci_dev *pdev) mlx4_info(persist->dev, "mlx4_shutdown was called\n"); mutex_lock(&persist->interface_state_mutex); - if (persist->interface_state & MLX4_INTERFACE_STATE_UP) { - /* Notify mlx4 clients that the kernel is being shut down */ - persist->interface_state |= MLX4_INTERFACE_STATE_SHUTDOWN; + if (persist->interface_state & MLX4_INTERFACE_STATE_UP) mlx4_unload_one(pdev); - } mutex_unlock(&persist->interface_state_mutex); } diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c index 94b891c118c1..1a670b681555 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mcg.c +++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c @@ -1457,7 +1457,12 @@ EXPORT_SYMBOL_GPL(mlx4_multicast_detach); int mlx4_flow_steer_promisc_add(struct mlx4_dev *dev, u8 port, u32 qpn, enum mlx4_net_trans_promisc_mode mode) { - struct mlx4_net_trans_rule rule; + struct mlx4_net_trans_rule rule = { + .queue_mode = MLX4_NET_TRANS_Q_FIFO, + .exclusive = 0, + .allow_loopback = 1, + }; + u64 *regid_p; switch (mode) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index aae46884bf93..521cfdb7d11e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -18,8 +18,6 @@ config MLX5_CORE_EN default n ---help--- Ethernet support in Mellanox Technologies ConnectX-4 NIC. - Ethernet and Infiniband support in ConnectX-4 are currently mutually - exclusive. config MLX5_CORE_EN_DCB bool "Data Center Bridging (DCB) Support" diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 1e639f886021..bfe410e8a469 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -268,11 +268,6 @@ static void dump_buf(void *buf, int size, int data_only, int offset) pr_debug("\n"); } -enum { - MLX5_DRIVER_STATUS_ABORTED = 0xfe, - MLX5_DRIVER_SYND = 0xbadd00de, -}; - static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op, u32 *synd, u8 *status) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 7a43502a89cc..71382df59fc0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -241,7 +241,7 @@ struct mlx5e_tstamp { }; enum { - MLX5E_RQ_STATE_FLUSH, + MLX5E_RQ_STATE_ENABLED, MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, MLX5E_RQ_STATE_AM, }; @@ -394,7 +394,7 @@ struct mlx5e_sq_dma { }; enum { - MLX5E_SQ_STATE_FLUSH, + MLX5E_SQ_STATE_ENABLED, MLX5E_SQ_STATE_BF_ENABLE, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 84e8b250e2af..246d98ebb588 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -759,6 +759,7 @@ static int mlx5e_open_rq(struct mlx5e_channel *c, if (err) goto err_destroy_rq; + set_bit(MLX5E_RQ_STATE_ENABLED, &rq->state); err = mlx5e_modify_rq_state(rq, MLX5_RQC_STATE_RST, MLX5_RQC_STATE_RDY); if (err) goto err_disable_rq; @@ -773,6 +774,7 @@ static int mlx5e_open_rq(struct mlx5e_channel *c, return 0; err_disable_rq: + clear_bit(MLX5E_RQ_STATE_ENABLED, &rq->state); mlx5e_disable_rq(rq); err_destroy_rq: mlx5e_destroy_rq(rq); @@ -782,7 +784,7 @@ err_destroy_rq: static void mlx5e_close_rq(struct mlx5e_rq *rq) { - set_bit(MLX5E_RQ_STATE_FLUSH, &rq->state); + clear_bit(MLX5E_RQ_STATE_ENABLED, &rq->state); napi_synchronize(&rq->channel->napi); /* prevent mlx5e_post_rx_wqes */ cancel_work_sync(&rq->am.work); @@ -1006,7 +1008,6 @@ static int mlx5e_enable_sq(struct mlx5e_sq *sq, struct mlx5e_sq_param *param) MLX5_SET(sqc, sqc, min_wqe_inline_mode, sq->min_inline_mode); MLX5_SET(sqc, sqc, state, MLX5_SQC_STATE_RST); MLX5_SET(sqc, sqc, tis_lst_sz, param->type == MLX5E_SQ_ICO ? 0 : 1); - MLX5_SET(sqc, sqc, flush_in_error_en, 1); MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_CYCLIC); MLX5_SET(wq, wq, uar_page, sq->uar.index); @@ -1083,6 +1084,7 @@ static int mlx5e_open_sq(struct mlx5e_channel *c, if (err) goto err_destroy_sq; + set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); err = mlx5e_modify_sq(sq, MLX5_SQC_STATE_RST, MLX5_SQC_STATE_RDY, false, 0); if (err) @@ -1096,6 +1098,7 @@ static int mlx5e_open_sq(struct mlx5e_channel *c, return 0; err_disable_sq: + clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); mlx5e_disable_sq(sq); err_destroy_sq: mlx5e_destroy_sq(sq); @@ -1112,7 +1115,7 @@ static inline void netif_tx_disable_queue(struct netdev_queue *txq) static void mlx5e_close_sq(struct mlx5e_sq *sq) { - set_bit(MLX5E_SQ_STATE_FLUSH, &sq->state); + clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); /* prevent netif_tx_wake_queue */ napi_synchronize(&sq->channel->napi); @@ -3092,7 +3095,7 @@ static void mlx5e_tx_timeout(struct net_device *dev) if (!netif_xmit_stopped(netdev_get_tx_queue(dev, i))) continue; sched_work = true; - set_bit(MLX5E_SQ_STATE_FLUSH, &sq->state); + clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); netdev_err(dev, "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x\n", i, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc); } @@ -3147,13 +3150,13 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog) for (i = 0; i < priv->params.num_channels; i++) { struct mlx5e_channel *c = priv->channel[i]; - set_bit(MLX5E_RQ_STATE_FLUSH, &c->rq.state); + clear_bit(MLX5E_RQ_STATE_ENABLED, &c->rq.state); napi_synchronize(&c->napi); /* prevent mlx5e_poll_rx_cq from accessing rq->xdp_prog */ old_prog = xchg(&c->rq.xdp_prog, prog); - clear_bit(MLX5E_RQ_STATE_FLUSH, &c->rq.state); + set_bit(MLX5E_RQ_STATE_ENABLED, &c->rq.state); /* napi_schedule in case we have missed anything */ set_bit(MLX5E_CHANNEL_NAPI_SCHED, &c->flags); napi_schedule(&c->napi); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index c6de6fba5843..33495d88aeb2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -340,7 +340,7 @@ static inline void mlx5e_post_umr_wqe(struct mlx5e_rq *rq, u16 ix) while ((pi = (sq->pc & wq->sz_m1)) > sq->edge) { sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_NOP; sq->db.ico_wqe[pi].num_wqebbs = 1; - mlx5e_send_nop(sq, true); + mlx5e_send_nop(sq, false); } wqe = mlx5_wq_cyc_get_wqe(wq, pi); @@ -412,7 +412,7 @@ void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq) clear_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state); - if (unlikely(test_bit(MLX5E_RQ_STATE_FLUSH, &rq->state))) { + if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state))) { mlx5e_free_rx_mpwqe(rq, &rq->mpwqe.info[wq->head]); return; } @@ -445,7 +445,7 @@ void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) } #define RQ_CANNOT_POST(rq) \ - (test_bit(MLX5E_RQ_STATE_FLUSH, &rq->state) || \ + (!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state) || \ test_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state)) bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq) @@ -924,7 +924,7 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) struct mlx5e_sq *xdp_sq = &rq->channel->xdp_sq; int work_done = 0; - if (unlikely(test_bit(MLX5E_RQ_STATE_FLUSH, &rq->state))) + if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state))) return 0; if (cq->decmprs_left) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 70a717382357..cfb68371c397 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -409,7 +409,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) sq = container_of(cq, struct mlx5e_sq, cq); - if (unlikely(test_bit(MLX5E_SQ_STATE_FLUSH, &sq->state))) + if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))) return false; npkts = 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index 5703f19a6a24..e5c12a732aa1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -56,7 +56,7 @@ static void mlx5e_poll_ico_cq(struct mlx5e_cq *cq) struct mlx5_cqe64 *cqe; u16 sqcc; - if (unlikely(test_bit(MLX5E_SQ_STATE_FLUSH, &sq->state))) + if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))) return; cqe = mlx5e_get_cqe(cq); @@ -113,7 +113,7 @@ static inline bool mlx5e_poll_xdp_tx_cq(struct mlx5e_cq *cq) sq = container_of(cq, struct mlx5e_sq, cq); - if (unlikely(test_bit(MLX5E_SQ_STATE_FLUSH, &sq->state))) + if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))) return false; /* sq->cc must be updated only after mlx5_cqwq_update_db_record(), diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 3eb931585b3e..ada24e103b02 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -46,7 +46,6 @@ #include <linux/mlx5/srq.h> #include <linux/debugfs.h> #include <linux/kmod.h> -#include <linux/delay.h> #include <linux/mlx5/mlx5_ifc.h> #ifdef CONFIG_RFS_ACCEL #include <linux/cpu_rmap.h> @@ -63,13 +62,13 @@ MODULE_DESCRIPTION("Mellanox Connect-IB, ConnectX-4 core driver"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_VERSION(DRIVER_VERSION); -int mlx5_core_debug_mask; -module_param_named(debug_mask, mlx5_core_debug_mask, int, 0644); +unsigned int mlx5_core_debug_mask; +module_param_named(debug_mask, mlx5_core_debug_mask, uint, 0644); MODULE_PARM_DESC(debug_mask, "debug mask: 1 = dump cmd data, 2 = dump cmd exec time, 3 = both. Default=0"); #define MLX5_DEFAULT_PROF 2 -static int prof_sel = MLX5_DEFAULT_PROF; -module_param_named(prof_sel, prof_sel, int, 0444); +static unsigned int prof_sel = MLX5_DEFAULT_PROF; +module_param_named(prof_sel, prof_sel, uint, 0444); MODULE_PARM_DESC(prof_sel, "profile selector. Valid range 0 - 2"); enum { @@ -733,13 +732,15 @@ static int mlx5_core_set_issi(struct mlx5_core_dev *dev) u8 status; mlx5_cmd_mbox_status(query_out, &status, &syndrome); - if (status == MLX5_CMD_STAT_BAD_OP_ERR) { - pr_debug("Only ISSI 0 is supported\n"); - return 0; + if (!status || syndrome == MLX5_DRIVER_SYND) { + mlx5_core_err(dev, "Failed to query ISSI err(%d) status(%d) synd(%d)\n", + err, status, syndrome); + return err; } - pr_err("failed to query ISSI err(%d)\n", err); - return err; + mlx5_core_warn(dev, "Query ISSI is not supported by FW, ISSI is 0\n"); + dev->issi = 0; + return 0; } sup_issi = MLX5_GET(query_issi_out, query_out, supported_issi_dw0); @@ -753,7 +754,8 @@ static int mlx5_core_set_issi(struct mlx5_core_dev *dev) err = mlx5_cmd_exec(dev, set_in, sizeof(set_in), set_out, sizeof(set_out)); if (err) { - pr_err("failed to set ISSI=1 err(%d)\n", err); + mlx5_core_err(dev, "Failed to set ISSI to 1 err(%d)\n", + err); return err; } @@ -1228,13 +1230,6 @@ static int init_one(struct pci_dev *pdev, dev->pdev = pdev; dev->event = mlx5_core_event; - - if (prof_sel < 0 || prof_sel >= ARRAY_SIZE(profile)) { - mlx5_core_warn(dev, - "selected profile out of range, selecting default (%d)\n", - MLX5_DEFAULT_PROF); - prof_sel = MLX5_DEFAULT_PROF; - } dev->profile = &profile[prof_sel]; INIT_LIST_HEAD(&priv->ctx_list); @@ -1451,10 +1446,22 @@ static struct pci_driver mlx5_core_driver = { .sriov_configure = mlx5_core_sriov_configure, }; +static void mlx5_core_verify_params(void) +{ + if (prof_sel >= ARRAY_SIZE(profile)) { + pr_warn("mlx5_core: WARNING: Invalid module parameter prof_sel %d, valid range 0-%zu, changing back to default(%d)\n", + prof_sel, + ARRAY_SIZE(profile) - 1, + MLX5_DEFAULT_PROF); + prof_sel = MLX5_DEFAULT_PROF; + } +} + static int __init init(void) { int err; + mlx5_core_verify_params(); mlx5_register_debugfs(); err = pci_register_driver(&mlx5_core_driver); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 187662c8ea96..63b9a0dba885 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -44,11 +44,11 @@ #define MLX5_TOTAL_VPORTS(mdev) (1 + pci_sriov_get_totalvfs(mdev->pdev)) -extern int mlx5_core_debug_mask; +extern uint mlx5_core_debug_mask; #define mlx5_core_dbg(__dev, format, ...) \ - dev_dbg(&(__dev)->pdev->dev, "%s:%s:%d:(pid %d): " format, \ - (__dev)->priv.name, __func__, __LINE__, current->pid, \ + dev_dbg(&(__dev)->pdev->dev, "%s:%d:(pid %d): " format, \ + __func__, __LINE__, current->pid, \ ##__VA_ARGS__) #define mlx5_core_dbg_mask(__dev, mask, format, ...) \ @@ -63,8 +63,8 @@ do { \ ##__VA_ARGS__) #define mlx5_core_warn(__dev, format, ...) \ - dev_warn(&(__dev)->pdev->dev, "%s:%s:%d:(pid %d): " format, \ - (__dev)->priv.name, __func__, __LINE__, current->pid, \ + dev_warn(&(__dev)->pdev->dev, "%s:%d:(pid %d): " format, \ + __func__, __LINE__, current->pid, \ ##__VA_ARGS__) #define mlx5_core_info(__dev, format, ...) \ @@ -75,6 +75,11 @@ enum { MLX5_CMD_TIME, /* print command execution time */ }; +enum { + MLX5_DRIVER_STATUS_ABORTED = 0xfe, + MLX5_DRIVER_SYND = 0xbadd00de, +}; + int mlx5_query_hca_caps(struct mlx5_core_dev *dev); int mlx5_query_board_id(struct mlx5_core_dev *dev); int mlx5_cmd_init_hca(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index f95385cbbd40..62ae55bd81b8 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -1730,6 +1730,7 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb) mapping))) { DP_NOTICE(cdev, "Unable to map frag - dropping packet\n"); + rc = -ENOMEM; goto err; } } else { diff --git a/drivers/net/ethernet/qualcomm/emac/emac-phy.c b/drivers/net/ethernet/qualcomm/emac/emac-phy.c index da4e90db4d98..99a14df28b96 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac-phy.c +++ b/drivers/net/ethernet/qualcomm/emac/emac-phy.c @@ -212,6 +212,7 @@ int emac_phy_config(struct platform_device *pdev, struct emac_adapter *adpt) phy_np = of_parse_phandle(np, "phy-handle", 0); adpt->phydev = of_phy_find_device(phy_np); + of_node_put(phy_np); } if (!adpt->phydev) { diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c index 4fede4b86538..57b35aeac51a 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac.c @@ -711,6 +711,8 @@ static int emac_probe(struct platform_device *pdev) err_undo_napi: netif_napi_del(&adpt->rx_q.napi); err_undo_mdiobus: + if (!has_acpi_companion(&pdev->dev)) + put_device(&adpt->phydev->mdio.dev); mdiobus_unregister(adpt->mii_bus); err_undo_clocks: emac_clks_teardown(adpt); @@ -730,6 +732,8 @@ static int emac_remove(struct platform_device *pdev) emac_clks_teardown(adpt); + if (!has_acpi_companion(&pdev->dev)) + put_device(&adpt->phydev->mdio.dev); mdiobus_unregister(adpt->mii_bus); free_netdev(netdev); diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 630536bc72f9..d6a217874a8b 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1008,20 +1008,18 @@ static int ravb_phy_init(struct net_device *ndev) of_node_put(pn); if (!phydev) { netdev_err(ndev, "failed to connect PHY\n"); - return -ENOENT; + err = -ENOENT; + goto err_deregister_fixed_link; } /* This driver only support 10/100Mbit speeds on Gen3 * at this time. */ if (priv->chip_id == RCAR_GEN3) { - int err; - err = phy_set_max_speed(phydev, SPEED_100); if (err) { netdev_err(ndev, "failed to limit PHY to 100Mbit/s\n"); - phy_disconnect(phydev); - return err; + goto err_phy_disconnect; } netdev_info(ndev, "limited PHY to 100Mbit/s\n"); @@ -1033,6 +1031,14 @@ static int ravb_phy_init(struct net_device *ndev) phy_attached_info(phydev); return 0; + +err_phy_disconnect: + phy_disconnect(phydev); +err_deregister_fixed_link: + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); + + return err; } /* PHY control start function */ @@ -1634,6 +1640,7 @@ static void ravb_set_rx_mode(struct net_device *ndev) /* Device close function for Ethernet AVB */ static int ravb_close(struct net_device *ndev) { + struct device_node *np = ndev->dev.parent->of_node; struct ravb_private *priv = netdev_priv(ndev); struct ravb_tstamp_skb *ts_skb, *ts_skb2; @@ -1663,6 +1670,8 @@ static int ravb_close(struct net_device *ndev) if (ndev->phydev) { phy_stop(ndev->phydev); phy_disconnect(ndev->phydev); + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); } if (priv->chip_id != RCAR_GEN2) { diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 05b0dc55de77..1a92de705199 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -518,7 +518,7 @@ static struct sh_eth_cpu_data r7s72100_data = { .ecsr_value = ECSR_ICD, .ecsipr_value = ECSIPR_ICDIP, - .eesipr_value = 0xff7f009f, + .eesipr_value = 0xe77f009f, .tx_check = EESR_TC1 | EESR_FTC, .eesr_err_check = EESR_TWB1 | EESR_TWB | EESR_TABT | EESR_RABT | diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c index e9b8579e6241..6fb2d15b5351 100644 --- a/drivers/net/ethernet/smsc/smsc911x.c +++ b/drivers/net/ethernet/smsc/smsc911x.c @@ -438,9 +438,16 @@ static int smsc911x_request_resources(struct platform_device *pdev) ret = regulator_bulk_get(&pdev->dev, ARRAY_SIZE(pdata->supplies), pdata->supplies); - if (ret) + if (ret) { + /* + * Retry on deferrals, else just report the error + * and try to continue. + */ + if (ret == -EPROBE_DEFER) + return ret; netdev_err(ndev, "couldn't get regulators %d\n", ret); + } /* Request optional RESET GPIO */ pdata->reset_gpiod = devm_gpiod_get_optional(&pdev->dev, @@ -2584,6 +2591,9 @@ static int smsc911x_suspend(struct device *dev) PMT_CTRL_PM_MODE_D1_ | PMT_CTRL_WOL_EN_ | PMT_CTRL_ED_EN_ | PMT_CTRL_PME_EN_); + pm_runtime_disable(dev); + pm_runtime_set_suspended(dev); + return 0; } @@ -2593,6 +2603,9 @@ static int smsc911x_resume(struct device *dev) struct smsc911x_data *pdata = netdev_priv(ndev); unsigned int to = 100; + pm_runtime_enable(dev); + pm_runtime_resume(dev); + /* Note 3.11 from the datasheet: * "When the LAN9220 is in a power saving state, a write of any * data to the BYTE_TEST register will wake-up the device." diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig index 3818c5e06eba..4b78168a5f3c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Kconfig +++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig @@ -107,7 +107,7 @@ config DWMAC_STI config DWMAC_STM32 tristate "STM32 DWMAC support" default ARCH_STM32 - depends on OF && HAS_IOMEM + depends on OF && HAS_IOMEM && (ARCH_STM32 || COMPILE_TEST) select MFD_SYSCON ---help--- Support for ethernet controller on STM32 SOCs. diff --git a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c index 2920e2ee3864..489ef146201e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c +++ b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c @@ -63,8 +63,8 @@ #define TSE_PCS_SGMII_LINK_TIMER_0 0x0D40 #define TSE_PCS_SGMII_LINK_TIMER_1 0x0003 #define TSE_PCS_SW_RESET_TIMEOUT 100 -#define TSE_PCS_USE_SGMII_AN_MASK BIT(2) -#define TSE_PCS_USE_SGMII_ENA BIT(1) +#define TSE_PCS_USE_SGMII_AN_MASK BIT(1) +#define TSE_PCS_USE_SGMII_ENA BIT(0) #define SGMII_ADAPTER_CTRL_REG 0x00 #define SGMII_ADAPTER_DISABLE 0x0001 diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index d3292c4a6eda..6d2de4e01f6d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -120,14 +120,17 @@ struct stmmac_extra_stats { unsigned long ip_csum_bypassed; unsigned long ipv4_pkt_rcvd; unsigned long ipv6_pkt_rcvd; - unsigned long rx_msg_type_ext_no_ptp; - unsigned long rx_msg_type_sync; - unsigned long rx_msg_type_follow_up; - unsigned long rx_msg_type_delay_req; - unsigned long rx_msg_type_delay_resp; - unsigned long rx_msg_type_pdelay_req; - unsigned long rx_msg_type_pdelay_resp; - unsigned long rx_msg_type_pdelay_follow_up; + unsigned long no_ptp_rx_msg_type_ext; + unsigned long ptp_rx_msg_type_sync; + unsigned long ptp_rx_msg_type_follow_up; + unsigned long ptp_rx_msg_type_delay_req; + unsigned long ptp_rx_msg_type_delay_resp; + unsigned long ptp_rx_msg_type_pdelay_req; + unsigned long ptp_rx_msg_type_pdelay_resp; + unsigned long ptp_rx_msg_type_pdelay_follow_up; + unsigned long ptp_rx_msg_type_announce; + unsigned long ptp_rx_msg_type_management; + unsigned long ptp_rx_msg_pkt_reserved_type; unsigned long ptp_frame_type; unsigned long ptp_ver; unsigned long timestamp_dropped; @@ -482,11 +485,12 @@ struct stmmac_ops { /* PTP and HW Timer helpers */ struct stmmac_hwtimestamp { void (*config_hw_tstamping) (void __iomem *ioaddr, u32 data); - u32 (*config_sub_second_increment) (void __iomem *ioaddr, u32 clk_rate); + u32 (*config_sub_second_increment)(void __iomem *ioaddr, u32 ptp_clock, + int gmac4); int (*init_systime) (void __iomem *ioaddr, u32 sec, u32 nsec); int (*config_addend) (void __iomem *ioaddr, u32 addend); int (*adjust_systime) (void __iomem *ioaddr, u32 sec, u32 nsec, - int add_sub); + int add_sub, int gmac4); u64(*get_systime) (void __iomem *ioaddr); }; diff --git a/drivers/net/ethernet/stmicro/stmmac/descs.h b/drivers/net/ethernet/stmicro/stmmac/descs.h index 2e4c171a2b41..e3c86d422109 100644 --- a/drivers/net/ethernet/stmicro/stmmac/descs.h +++ b/drivers/net/ethernet/stmicro/stmmac/descs.h @@ -155,14 +155,18 @@ #define ERDES4_L3_L4_FILT_NO_MATCH_MASK GENMASK(27, 26) /* Extended RDES4 message type definitions */ -#define RDES_EXT_NO_PTP 0 -#define RDES_EXT_SYNC 1 -#define RDES_EXT_FOLLOW_UP 2 -#define RDES_EXT_DELAY_REQ 3 -#define RDES_EXT_DELAY_RESP 4 -#define RDES_EXT_PDELAY_REQ 5 -#define RDES_EXT_PDELAY_RESP 6 -#define RDES_EXT_PDELAY_FOLLOW_UP 7 +#define RDES_EXT_NO_PTP 0x0 +#define RDES_EXT_SYNC 0x1 +#define RDES_EXT_FOLLOW_UP 0x2 +#define RDES_EXT_DELAY_REQ 0x3 +#define RDES_EXT_DELAY_RESP 0x4 +#define RDES_EXT_PDELAY_REQ 0x5 +#define RDES_EXT_PDELAY_RESP 0x6 +#define RDES_EXT_PDELAY_FOLLOW_UP 0x7 +#define RDES_PTP_ANNOUNCE 0x8 +#define RDES_PTP_MANAGEMENT 0x9 +#define RDES_PTP_SIGNALING 0xa +#define RDES_PTP_PKT_RESERVED_TYPE 0xf /* Basic descriptor structure for normal and alternate descriptors */ struct dma_desc { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c index b1e5f24708c9..e6e6c2fcc4b7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c @@ -50,10 +50,23 @@ static int dwmac_generic_probe(struct platform_device *pdev) if (plat_dat->init) { ret = plat_dat->init(pdev, plat_dat->bsp_priv); if (ret) - return ret; + goto err_remove_config_dt; } - return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + if (ret) + goto err_exit; + + return 0; + +err_exit: + if (plat_dat->exit) + plat_dat->exit(pdev, plat_dat->bsp_priv); +err_remove_config_dt: + if (pdev->dev.of_node) + stmmac_remove_config_dt(pdev, plat_dat); + + return ret; } static const struct of_device_id dwmac_generic_match[] = { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c index 36d3355f2fb0..866444b6c82f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c @@ -271,15 +271,17 @@ static int ipq806x_gmac_probe(struct platform_device *pdev) return PTR_ERR(plat_dat); gmac = devm_kzalloc(dev, sizeof(*gmac), GFP_KERNEL); - if (!gmac) - return -ENOMEM; + if (!gmac) { + err = -ENOMEM; + goto err_remove_config_dt; + } gmac->pdev = pdev; err = ipq806x_gmac_of_parse(gmac); if (err) { dev_err(dev, "device tree parsing error\n"); - return err; + goto err_remove_config_dt; } regmap_write(gmac->qsgmii_csr, QSGMII_PCS_CAL_LCKDT_CTL, @@ -300,7 +302,8 @@ static int ipq806x_gmac_probe(struct platform_device *pdev) default: dev_err(&pdev->dev, "Unsupported PHY mode: \"%s\"\n", phy_modes(gmac->phy_mode)); - return -EINVAL; + err = -EINVAL; + goto err_remove_config_dt; } regmap_write(gmac->nss_common, NSS_COMMON_GMAC_CTL(gmac->id), val); @@ -319,7 +322,8 @@ static int ipq806x_gmac_probe(struct platform_device *pdev) default: dev_err(&pdev->dev, "Unsupported PHY mode: \"%s\"\n", phy_modes(gmac->phy_mode)); - return -EINVAL; + err = -EINVAL; + goto err_remove_config_dt; } regmap_write(gmac->nss_common, NSS_COMMON_CLK_SRC_CTRL, val); @@ -346,7 +350,16 @@ static int ipq806x_gmac_probe(struct platform_device *pdev) plat_dat->bsp_priv = gmac; plat_dat->fix_mac_speed = ipq806x_gmac_fix_mac_speed; - return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + err = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + if (err) + goto err_remove_config_dt; + + return 0; + +err_remove_config_dt: + stmmac_remove_config_dt(pdev, plat_dat); + + return err; } static const struct of_device_id ipq806x_gmac_dwmac_match[] = { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c index 78e9d1861896..3d3f43d91b98 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c @@ -46,7 +46,8 @@ static int lpc18xx_dwmac_probe(struct platform_device *pdev) reg = syscon_regmap_lookup_by_compatible("nxp,lpc1850-creg"); if (IS_ERR(reg)) { dev_err(&pdev->dev, "syscon lookup failed\n"); - return PTR_ERR(reg); + ret = PTR_ERR(reg); + goto err_remove_config_dt; } if (plat_dat->interface == PHY_INTERFACE_MODE_MII) { @@ -55,13 +56,23 @@ static int lpc18xx_dwmac_probe(struct platform_device *pdev) ethmode = LPC18XX_CREG_CREG6_ETHMODE_RMII; } else { dev_err(&pdev->dev, "Only MII and RMII mode supported\n"); - return -EINVAL; + ret = -EINVAL; + goto err_remove_config_dt; } regmap_update_bits(reg, LPC18XX_CREG_CREG6, LPC18XX_CREG_CREG6_ETHMODE_MASK, ethmode); - return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + if (ret) + goto err_remove_config_dt; + + return 0; + +err_remove_config_dt: + stmmac_remove_config_dt(pdev, plat_dat); + + return ret; } static const struct of_device_id lpc18xx_dwmac_match[] = { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c index 309d99536a2c..7fdd1760a74c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c @@ -64,18 +64,31 @@ static int meson6_dwmac_probe(struct platform_device *pdev) return PTR_ERR(plat_dat); dwmac = devm_kzalloc(&pdev->dev, sizeof(*dwmac), GFP_KERNEL); - if (!dwmac) - return -ENOMEM; + if (!dwmac) { + ret = -ENOMEM; + goto err_remove_config_dt; + } res = platform_get_resource(pdev, IORESOURCE_MEM, 1); dwmac->reg = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(dwmac->reg)) - return PTR_ERR(dwmac->reg); + if (IS_ERR(dwmac->reg)) { + ret = PTR_ERR(dwmac->reg); + goto err_remove_config_dt; + } plat_dat->bsp_priv = dwmac; plat_dat->fix_mac_speed = meson6_dwmac_fix_mac_speed; - return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + if (ret) + goto err_remove_config_dt; + + return 0; + +err_remove_config_dt: + stmmac_remove_config_dt(pdev, plat_dat); + + return ret; } static const struct of_device_id meson6_dwmac_match[] = { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c index 250e4ceafc8d..ffaed1f35efe 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c @@ -264,32 +264,48 @@ static int meson8b_dwmac_probe(struct platform_device *pdev) return PTR_ERR(plat_dat); dwmac = devm_kzalloc(&pdev->dev, sizeof(*dwmac), GFP_KERNEL); - if (!dwmac) - return -ENOMEM; + if (!dwmac) { + ret = -ENOMEM; + goto err_remove_config_dt; + } res = platform_get_resource(pdev, IORESOURCE_MEM, 1); dwmac->regs = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(dwmac->regs)) - return PTR_ERR(dwmac->regs); + if (IS_ERR(dwmac->regs)) { + ret = PTR_ERR(dwmac->regs); + goto err_remove_config_dt; + } dwmac->pdev = pdev; dwmac->phy_mode = of_get_phy_mode(pdev->dev.of_node); if (dwmac->phy_mode < 0) { dev_err(&pdev->dev, "missing phy-mode property\n"); - return -EINVAL; + ret = -EINVAL; + goto err_remove_config_dt; } ret = meson8b_init_clk(dwmac); if (ret) - return ret; + goto err_remove_config_dt; ret = meson8b_init_prg_eth(dwmac); if (ret) - return ret; + goto err_remove_config_dt; plat_dat->bsp_priv = dwmac; - return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + if (ret) + goto err_clk_disable; + + return 0; + +err_clk_disable: + clk_disable_unprepare(dwmac->m25_div_clk); +err_remove_config_dt: + stmmac_remove_config_dt(pdev, plat_dat); + + return ret; } static int meson8b_dwmac_remove(struct platform_device *pdev) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c index 3740a4417fa0..d80c88bd2bba 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c @@ -981,14 +981,27 @@ static int rk_gmac_probe(struct platform_device *pdev) plat_dat->resume = rk_gmac_resume; plat_dat->bsp_priv = rk_gmac_setup(pdev, data); - if (IS_ERR(plat_dat->bsp_priv)) - return PTR_ERR(plat_dat->bsp_priv); + if (IS_ERR(plat_dat->bsp_priv)) { + ret = PTR_ERR(plat_dat->bsp_priv); + goto err_remove_config_dt; + } ret = rk_gmac_init(pdev, plat_dat->bsp_priv); if (ret) - return ret; + goto err_remove_config_dt; + + ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + if (ret) + goto err_gmac_exit; + + return 0; + +err_gmac_exit: + rk_gmac_exit(pdev, plat_dat->bsp_priv); +err_remove_config_dt: + stmmac_remove_config_dt(pdev, plat_dat); - return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + return ret; } static const struct of_device_id rk_gmac_dwmac_match[] = { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c index bec6963ac71e..0c420e97de1e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c @@ -304,6 +304,8 @@ static int socfpga_dwmac_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; int ret; struct socfpga_dwmac *dwmac; + struct net_device *ndev; + struct stmmac_priv *stpriv; ret = stmmac_get_platform_resources(pdev, &stmmac_res); if (ret) @@ -314,32 +316,43 @@ static int socfpga_dwmac_probe(struct platform_device *pdev) return PTR_ERR(plat_dat); dwmac = devm_kzalloc(dev, sizeof(*dwmac), GFP_KERNEL); - if (!dwmac) - return -ENOMEM; + if (!dwmac) { + ret = -ENOMEM; + goto err_remove_config_dt; + } ret = socfpga_dwmac_parse_data(dwmac, dev); if (ret) { dev_err(dev, "Unable to parse OF data\n"); - return ret; + goto err_remove_config_dt; } plat_dat->bsp_priv = dwmac; plat_dat->fix_mac_speed = socfpga_dwmac_fix_mac_speed; ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + if (ret) + goto err_remove_config_dt; - if (!ret) { - struct net_device *ndev = platform_get_drvdata(pdev); - struct stmmac_priv *stpriv = netdev_priv(ndev); + ndev = platform_get_drvdata(pdev); + stpriv = netdev_priv(ndev); - /* The socfpga driver needs to control the stmmac reset to - * set the phy mode. Create a copy of the core reset handel - * so it can be used by the driver later. - */ - dwmac->stmmac_rst = stpriv->stmmac_rst; + /* The socfpga driver needs to control the stmmac reset to set the phy + * mode. Create a copy of the core reset handle so it can be used by + * the driver later. + */ + dwmac->stmmac_rst = stpriv->stmmac_rst; - ret = socfpga_dwmac_set_phy_mode(dwmac); - } + ret = socfpga_dwmac_set_phy_mode(dwmac); + if (ret) + goto err_dvr_remove; + + return 0; + +err_dvr_remove: + stmmac_dvr_remove(&pdev->dev); +err_remove_config_dt: + stmmac_remove_config_dt(pdev, plat_dat); return ret; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c index 58c05acc2aab..060b98c37a85 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c @@ -345,13 +345,15 @@ static int sti_dwmac_probe(struct platform_device *pdev) return PTR_ERR(plat_dat); dwmac = devm_kzalloc(&pdev->dev, sizeof(*dwmac), GFP_KERNEL); - if (!dwmac) - return -ENOMEM; + if (!dwmac) { + ret = -ENOMEM; + goto err_remove_config_dt; + } ret = sti_dwmac_parse_data(dwmac, pdev); if (ret) { dev_err(&pdev->dev, "Unable to parse OF data\n"); - return ret; + goto err_remove_config_dt; } dwmac->fix_retime_src = data->fix_retime_src; @@ -363,9 +365,20 @@ static int sti_dwmac_probe(struct platform_device *pdev) ret = sti_dwmac_init(pdev, plat_dat->bsp_priv); if (ret) - return ret; + goto err_remove_config_dt; + + ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + if (ret) + goto err_dwmac_exit; + + return 0; + +err_dwmac_exit: + sti_dwmac_exit(pdev, plat_dat->bsp_priv); +err_remove_config_dt: + stmmac_remove_config_dt(pdev, plat_dat); - return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + return ret; } static const struct sti_dwmac_of_data stih4xx_dwmac_data = { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c index e5a926b8bee7..61cb24810d10 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c @@ -107,24 +107,33 @@ static int stm32_dwmac_probe(struct platform_device *pdev) return PTR_ERR(plat_dat); dwmac = devm_kzalloc(&pdev->dev, sizeof(*dwmac), GFP_KERNEL); - if (!dwmac) - return -ENOMEM; + if (!dwmac) { + ret = -ENOMEM; + goto err_remove_config_dt; + } ret = stm32_dwmac_parse_data(dwmac, &pdev->dev); if (ret) { dev_err(&pdev->dev, "Unable to parse OF data\n"); - return ret; + goto err_remove_config_dt; } plat_dat->bsp_priv = dwmac; ret = stm32_dwmac_init(plat_dat); if (ret) - return ret; + goto err_remove_config_dt; ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); if (ret) - stm32_dwmac_clk_disable(dwmac); + goto err_clk_disable; + + return 0; + +err_clk_disable: + stm32_dwmac_clk_disable(dwmac); +err_remove_config_dt: + stmmac_remove_config_dt(pdev, plat_dat); return ret; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c index adff46375a32..d07520fb969e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c @@ -120,22 +120,27 @@ static int sun7i_gmac_probe(struct platform_device *pdev) return PTR_ERR(plat_dat); gmac = devm_kzalloc(dev, sizeof(*gmac), GFP_KERNEL); - if (!gmac) - return -ENOMEM; + if (!gmac) { + ret = -ENOMEM; + goto err_remove_config_dt; + } gmac->interface = of_get_phy_mode(dev->of_node); gmac->tx_clk = devm_clk_get(dev, "allwinner_gmac_tx"); if (IS_ERR(gmac->tx_clk)) { dev_err(dev, "could not get tx clock\n"); - return PTR_ERR(gmac->tx_clk); + ret = PTR_ERR(gmac->tx_clk); + goto err_remove_config_dt; } /* Optional regulator for PHY */ gmac->regulator = devm_regulator_get_optional(dev, "phy"); if (IS_ERR(gmac->regulator)) { - if (PTR_ERR(gmac->regulator) == -EPROBE_DEFER) - return -EPROBE_DEFER; + if (PTR_ERR(gmac->regulator) == -EPROBE_DEFER) { + ret = -EPROBE_DEFER; + goto err_remove_config_dt; + } dev_info(dev, "no regulator found\n"); gmac->regulator = NULL; } @@ -151,11 +156,18 @@ static int sun7i_gmac_probe(struct platform_device *pdev) ret = sun7i_gmac_init(pdev, plat_dat->bsp_priv); if (ret) - return ret; + goto err_remove_config_dt; ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); if (ret) - sun7i_gmac_exit(pdev, plat_dat->bsp_priv); + goto err_gmac_exit; + + return 0; + +err_gmac_exit: + sun7i_gmac_exit(pdev, plat_dat->bsp_priv); +err_remove_config_dt: + stmmac_remove_config_dt(pdev, plat_dat); return ret; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c index 990746955216..f35385266fbf 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c @@ -43,9 +43,11 @@ static void dwmac1000_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi) if (axi->axi_xit_frm) value |= DMA_AXI_LPI_XIT_FRM; + value &= ~DMA_AXI_WR_OSR_LMT; value |= (axi->axi_wr_osr_lmt & DMA_AXI_WR_OSR_LMT_MASK) << DMA_AXI_WR_OSR_LMT_SHIFT; + value &= ~DMA_AXI_RD_OSR_LMT; value |= (axi->axi_rd_osr_lmt & DMA_AXI_RD_OSR_LMT_MASK) << DMA_AXI_RD_OSR_LMT_SHIFT; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c index a1b17cd7886b..a601f8d43b75 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c @@ -123,22 +123,29 @@ static int dwmac4_wrback_get_rx_status(void *data, struct stmmac_extra_stats *x, x->ipv4_pkt_rcvd++; if (rdes1 & RDES1_IPV6_HEADER) x->ipv6_pkt_rcvd++; - if (message_type == RDES_EXT_SYNC) - x->rx_msg_type_sync++; + + if (message_type == RDES_EXT_NO_PTP) + x->no_ptp_rx_msg_type_ext++; + else if (message_type == RDES_EXT_SYNC) + x->ptp_rx_msg_type_sync++; else if (message_type == RDES_EXT_FOLLOW_UP) - x->rx_msg_type_follow_up++; + x->ptp_rx_msg_type_follow_up++; else if (message_type == RDES_EXT_DELAY_REQ) - x->rx_msg_type_delay_req++; + x->ptp_rx_msg_type_delay_req++; else if (message_type == RDES_EXT_DELAY_RESP) - x->rx_msg_type_delay_resp++; + x->ptp_rx_msg_type_delay_resp++; else if (message_type == RDES_EXT_PDELAY_REQ) - x->rx_msg_type_pdelay_req++; + x->ptp_rx_msg_type_pdelay_req++; else if (message_type == RDES_EXT_PDELAY_RESP) - x->rx_msg_type_pdelay_resp++; + x->ptp_rx_msg_type_pdelay_resp++; else if (message_type == RDES_EXT_PDELAY_FOLLOW_UP) - x->rx_msg_type_pdelay_follow_up++; - else - x->rx_msg_type_ext_no_ptp++; + x->ptp_rx_msg_type_pdelay_follow_up++; + else if (message_type == RDES_PTP_ANNOUNCE) + x->ptp_rx_msg_type_announce++; + else if (message_type == RDES_PTP_MANAGEMENT) + x->ptp_rx_msg_type_management++; + else if (message_type == RDES_PTP_PKT_RESERVED_TYPE) + x->ptp_rx_msg_pkt_reserved_type++; if (rdes1 & RDES1_PTP_PACKET_TYPE) x->ptp_frame_type++; @@ -204,14 +211,18 @@ static void dwmac4_rd_enable_tx_timestamp(struct dma_desc *p) static int dwmac4_wrback_get_tx_timestamp_status(struct dma_desc *p) { - return (p->des3 & TDES3_TIMESTAMP_STATUS) - >> TDES3_TIMESTAMP_STATUS_SHIFT; + /* Context type from W/B descriptor must be zero */ + if (p->des3 & TDES3_CONTEXT_TYPE) + return -EINVAL; + + /* Tx Timestamp Status is 1 so des0 and des1'll have valid values */ + if (p->des3 & TDES3_TIMESTAMP_STATUS) + return 0; + + return 1; } -/* NOTE: For RX CTX bit has to be checked before - * HAVE a specific function for TX and another one for RX - */ -static u64 dwmac4_wrback_get_timestamp(void *desc, u32 ats) +static inline u64 dwmac4_get_timestamp(void *desc, u32 ats) { struct dma_desc *p = (struct dma_desc *)desc; u64 ns; @@ -223,12 +234,54 @@ static u64 dwmac4_wrback_get_timestamp(void *desc, u32 ats) return ns; } -static int dwmac4_context_get_rx_timestamp_status(void *desc, u32 ats) +static int dwmac4_rx_check_timestamp(void *desc) +{ + struct dma_desc *p = (struct dma_desc *)desc; + u32 own, ctxt; + int ret = 1; + + own = p->des3 & RDES3_OWN; + ctxt = ((p->des3 & RDES3_CONTEXT_DESCRIPTOR) + >> RDES3_CONTEXT_DESCRIPTOR_SHIFT); + + if (likely(!own && ctxt)) { + if ((p->des0 == 0xffffffff) && (p->des1 == 0xffffffff)) + /* Corrupted value */ + ret = -EINVAL; + else + /* A valid Timestamp is ready to be read */ + ret = 0; + } + + /* Timestamp not ready */ + return ret; +} + +static int dwmac4_wrback_get_rx_timestamp_status(void *desc, u32 ats) { struct dma_desc *p = (struct dma_desc *)desc; + int ret = -EINVAL; + + /* Get the status from normal w/b descriptor */ + if (likely(p->des3 & TDES3_RS1V)) { + if (likely(p->des1 & RDES1_TIMESTAMP_AVAILABLE)) { + int i = 0; + + /* Check if timestamp is OK from context descriptor */ + do { + ret = dwmac4_rx_check_timestamp(desc); + if (ret < 0) + goto exit; + i++; - return (p->des1 & RDES1_TIMESTAMP_AVAILABLE) - >> RDES1_TIMESTAMP_AVAILABLE_SHIFT; + } while ((ret == 1) || (i < 10)); + + if (i == 10) + ret = -EBUSY; + } + } +exit: + return ret; } static void dwmac4_rd_init_rx_desc(struct dma_desc *p, int disable_rx_ic, @@ -373,8 +426,8 @@ const struct stmmac_desc_ops dwmac4_desc_ops = { .get_rx_frame_len = dwmac4_wrback_get_rx_frame_len, .enable_tx_timestamp = dwmac4_rd_enable_tx_timestamp, .get_tx_timestamp_status = dwmac4_wrback_get_tx_timestamp_status, - .get_timestamp = dwmac4_wrback_get_timestamp, - .get_rx_timestamp_status = dwmac4_context_get_rx_timestamp_status, + .get_rx_timestamp_status = dwmac4_wrback_get_rx_timestamp_status, + .get_timestamp = dwmac4_get_timestamp, .set_tx_ic = dwmac4_rd_set_tx_ic, .prepare_tx_desc = dwmac4_rd_prepare_tx_desc, .prepare_tso_tx_desc = dwmac4_rd_prepare_tso_tx_desc, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h index 0902a2edeaa9..9736c505211a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h @@ -59,10 +59,13 @@ #define TDES3_CTXT_TCMSSV BIT(26) /* TDES3 Common */ +#define TDES3_RS1V BIT(26) +#define TDES3_RS1V_SHIFT 26 #define TDES3_LAST_DESCRIPTOR BIT(28) #define TDES3_LAST_DESCRIPTOR_SHIFT 28 #define TDES3_FIRST_DESCRIPTOR BIT(29) #define TDES3_CONTEXT_TYPE BIT(30) +#define TDES3_CONTEXT_TYPE_SHIFT 30 /* TDS3 use for both format (read and write back) */ #define TDES3_OWN BIT(31) @@ -117,6 +120,7 @@ #define RDES3_LAST_DESCRIPTOR BIT(28) #define RDES3_FIRST_DESCRIPTOR BIT(29) #define RDES3_CONTEXT_DESCRIPTOR BIT(30) +#define RDES3_CONTEXT_DESCRIPTOR_SHIFT 30 /* RDES3 (read format) */ #define RDES3_BUFFER1_VALID_ADDR BIT(24) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c index 116151cd6a95..32bc2fc73cdc 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c @@ -30,9 +30,11 @@ static void dwmac4_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi) if (axi->axi_xit_frm) value |= DMA_AXI_LPI_XIT_FRM; + value &= ~DMA_AXI_WR_OSR_LMT; value |= (axi->axi_wr_osr_lmt & DMA_AXI_OSR_MAX) << DMA_AXI_WR_OSR_LMT_SHIFT; + value &= ~DMA_AXI_RD_OSR_LMT; value |= (axi->axi_rd_osr_lmt & DMA_AXI_OSR_MAX) << DMA_AXI_RD_OSR_LMT_SHIFT; diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c index 38f19c99cf59..e75549327c34 100644 --- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c +++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c @@ -150,22 +150,30 @@ static void enh_desc_get_ext_status(void *data, struct stmmac_extra_stats *x, x->ipv4_pkt_rcvd++; if (rdes4 & ERDES4_IPV6_PKT_RCVD) x->ipv6_pkt_rcvd++; - if (message_type == RDES_EXT_SYNC) - x->rx_msg_type_sync++; + + if (message_type == RDES_EXT_NO_PTP) + x->no_ptp_rx_msg_type_ext++; + else if (message_type == RDES_EXT_SYNC) + x->ptp_rx_msg_type_sync++; else if (message_type == RDES_EXT_FOLLOW_UP) - x->rx_msg_type_follow_up++; + x->ptp_rx_msg_type_follow_up++; else if (message_type == RDES_EXT_DELAY_REQ) - x->rx_msg_type_delay_req++; + x->ptp_rx_msg_type_delay_req++; else if (message_type == RDES_EXT_DELAY_RESP) - x->rx_msg_type_delay_resp++; + x->ptp_rx_msg_type_delay_resp++; else if (message_type == RDES_EXT_PDELAY_REQ) - x->rx_msg_type_pdelay_req++; + x->ptp_rx_msg_type_pdelay_req++; else if (message_type == RDES_EXT_PDELAY_RESP) - x->rx_msg_type_pdelay_resp++; + x->ptp_rx_msg_type_pdelay_resp++; else if (message_type == RDES_EXT_PDELAY_FOLLOW_UP) - x->rx_msg_type_pdelay_follow_up++; - else - x->rx_msg_type_ext_no_ptp++; + x->ptp_rx_msg_type_pdelay_follow_up++; + else if (message_type == RDES_PTP_ANNOUNCE) + x->ptp_rx_msg_type_announce++; + else if (message_type == RDES_PTP_MANAGEMENT) + x->ptp_rx_msg_type_management++; + else if (message_type == RDES_PTP_PKT_RESERVED_TYPE) + x->ptp_rx_msg_pkt_reserved_type++; + if (rdes4 & ERDES4_PTP_FRAME_TYPE) x->ptp_frame_type++; if (rdes4 & ERDES4_PTP_VER) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index b15fc55f1b96..4d2a759b8465 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -129,6 +129,7 @@ struct stmmac_priv { int irq_wake; spinlock_t ptp_lock; void __iomem *mmcaddr; + void __iomem *ptpaddr; u32 rx_tail_addr; u32 tx_tail_addr; u32 mss; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 1e06173fc9d7..c5d0142adda2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -115,14 +115,17 @@ static const struct stmmac_stats stmmac_gstrings_stats[] = { STMMAC_STAT(ip_csum_bypassed), STMMAC_STAT(ipv4_pkt_rcvd), STMMAC_STAT(ipv6_pkt_rcvd), - STMMAC_STAT(rx_msg_type_ext_no_ptp), - STMMAC_STAT(rx_msg_type_sync), - STMMAC_STAT(rx_msg_type_follow_up), - STMMAC_STAT(rx_msg_type_delay_req), - STMMAC_STAT(rx_msg_type_delay_resp), - STMMAC_STAT(rx_msg_type_pdelay_req), - STMMAC_STAT(rx_msg_type_pdelay_resp), - STMMAC_STAT(rx_msg_type_pdelay_follow_up), + STMMAC_STAT(no_ptp_rx_msg_type_ext), + STMMAC_STAT(ptp_rx_msg_type_sync), + STMMAC_STAT(ptp_rx_msg_type_follow_up), + STMMAC_STAT(ptp_rx_msg_type_delay_req), + STMMAC_STAT(ptp_rx_msg_type_delay_resp), + STMMAC_STAT(ptp_rx_msg_type_pdelay_req), + STMMAC_STAT(ptp_rx_msg_type_pdelay_resp), + STMMAC_STAT(ptp_rx_msg_type_pdelay_follow_up), + STMMAC_STAT(ptp_rx_msg_type_announce), + STMMAC_STAT(ptp_rx_msg_type_management), + STMMAC_STAT(ptp_rx_msg_pkt_reserved_type), STMMAC_STAT(ptp_frame_type), STMMAC_STAT(ptp_ver), STMMAC_STAT(timestamp_dropped), diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c index a77f68918010..10d6059b2f26 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c @@ -34,21 +34,29 @@ static void stmmac_config_hw_tstamping(void __iomem *ioaddr, u32 data) } static u32 stmmac_config_sub_second_increment(void __iomem *ioaddr, - u32 ptp_clock) + u32 ptp_clock, int gmac4) { u32 value = readl(ioaddr + PTP_TCR); unsigned long data; - /* Convert the ptp_clock to nano second - * formula = (2/ptp_clock) * 1000000000 - * where, ptp_clock = 50MHz. + /* For GMAC3.x, 4.x versions, convert the ptp_clock to nano second + * formula = (1/ptp_clock) * 1000000000 + * where ptp_clock is 50MHz if fine method is used to update system */ - data = (2000000000ULL / ptp_clock); + if (value & PTP_TCR_TSCFUPDT) + data = (1000000000ULL / 50000000); + else + data = (1000000000ULL / ptp_clock); /* 0.465ns accuracy */ if (!(value & PTP_TCR_TSCTRLSSR)) data = (data * 1000) / 465; + data &= PTP_SSIR_SSINC_MASK; + + if (gmac4) + data = data << GMAC4_PTP_SSIR_SSINC_SHIFT; + writel(data, ioaddr + PTP_SSIR); return data; @@ -104,14 +112,30 @@ static int stmmac_config_addend(void __iomem *ioaddr, u32 addend) } static int stmmac_adjust_systime(void __iomem *ioaddr, u32 sec, u32 nsec, - int add_sub) + int add_sub, int gmac4) { u32 value; int limit; + if (add_sub) { + /* If the new sec value needs to be subtracted with + * the system time, then MAC_STSUR reg should be + * programmed with (2^32 – <new_sec_value>) + */ + if (gmac4) + sec = (100000000ULL - sec); + + value = readl(ioaddr + PTP_TCR); + if (value & PTP_TCR_TSCTRLSSR) + nsec = (PTP_DIGITAL_ROLLOVER_MODE - nsec); + else + nsec = (PTP_BINARY_ROLLOVER_MODE - nsec); + } + writel(sec, ioaddr + PTP_STSUR); - writel(((add_sub << PTP_STNSUR_ADDSUB_SHIFT) | nsec), - ioaddr + PTP_STNSUR); + value = (add_sub << PTP_STNSUR_ADDSUB_SHIFT) | nsec; + writel(value, ioaddr + PTP_STNSUR); + /* issue command to initialize the system time value */ value = readl(ioaddr + PTP_TCR); value |= PTP_TCR_TSUPDT; @@ -134,8 +158,9 @@ static u64 stmmac_get_systime(void __iomem *ioaddr) { u64 ns; + /* Get the TSSS value */ ns = readl(ioaddr + PTP_STNSR); - /* convert sec time value to nanosecond */ + /* Get the TSS and convert sec time value to nanosecond */ ns += readl(ioaddr + PTP_STSR) * 1000000000ULL; return ns; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index e2c94ec4edd0..caf069a465f2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -340,18 +340,17 @@ out: /* stmmac_get_tx_hwtstamp - get HW TX timestamps * @priv: driver private structure - * @entry : descriptor index to be used. + * @p : descriptor pointer * @skb : the socket buffer * Description : * This function will read timestamp from the descriptor & pass it to stack. * and also perform some sanity checks. */ static void stmmac_get_tx_hwtstamp(struct stmmac_priv *priv, - unsigned int entry, struct sk_buff *skb) + struct dma_desc *p, struct sk_buff *skb) { struct skb_shared_hwtstamps shhwtstamp; u64 ns; - void *desc = NULL; if (!priv->hwts_tx_en) return; @@ -360,58 +359,55 @@ static void stmmac_get_tx_hwtstamp(struct stmmac_priv *priv, if (likely(!skb || !(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS))) return; - if (priv->adv_ts) - desc = (priv->dma_etx + entry); - else - desc = (priv->dma_tx + entry); - /* check tx tstamp status */ - if (!priv->hw->desc->get_tx_timestamp_status((struct dma_desc *)desc)) - return; + if (!priv->hw->desc->get_tx_timestamp_status(p)) { + /* get the valid tstamp */ + ns = priv->hw->desc->get_timestamp(p, priv->adv_ts); - /* get the valid tstamp */ - ns = priv->hw->desc->get_timestamp(desc, priv->adv_ts); + memset(&shhwtstamp, 0, sizeof(struct skb_shared_hwtstamps)); + shhwtstamp.hwtstamp = ns_to_ktime(ns); - memset(&shhwtstamp, 0, sizeof(struct skb_shared_hwtstamps)); - shhwtstamp.hwtstamp = ns_to_ktime(ns); - /* pass tstamp to stack */ - skb_tstamp_tx(skb, &shhwtstamp); + netdev_info(priv->dev, "get valid TX hw timestamp %llu\n", ns); + /* pass tstamp to stack */ + skb_tstamp_tx(skb, &shhwtstamp); + } return; } /* stmmac_get_rx_hwtstamp - get HW RX timestamps * @priv: driver private structure - * @entry : descriptor index to be used. + * @p : descriptor pointer + * @np : next descriptor pointer * @skb : the socket buffer * Description : * This function will read received packet's timestamp from the descriptor * and pass it to stack. It also perform some sanity checks. */ -static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv, - unsigned int entry, struct sk_buff *skb) +static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv, struct dma_desc *p, + struct dma_desc *np, struct sk_buff *skb) { struct skb_shared_hwtstamps *shhwtstamp = NULL; u64 ns; - void *desc = NULL; if (!priv->hwts_rx_en) return; - if (priv->adv_ts) - desc = (priv->dma_erx + entry); - else - desc = (priv->dma_rx + entry); - - /* exit if rx tstamp is not valid */ - if (!priv->hw->desc->get_rx_timestamp_status(desc, priv->adv_ts)) - return; + /* Check if timestamp is available */ + if (!priv->hw->desc->get_rx_timestamp_status(p, priv->adv_ts)) { + /* For GMAC4, the valid timestamp is from CTX next desc. */ + if (priv->plat->has_gmac4) + ns = priv->hw->desc->get_timestamp(np, priv->adv_ts); + else + ns = priv->hw->desc->get_timestamp(p, priv->adv_ts); - /* get valid tstamp */ - ns = priv->hw->desc->get_timestamp(desc, priv->adv_ts); - shhwtstamp = skb_hwtstamps(skb); - memset(shhwtstamp, 0, sizeof(struct skb_shared_hwtstamps)); - shhwtstamp->hwtstamp = ns_to_ktime(ns); + netdev_info(priv->dev, "get valid RX hw timestamp %llu\n", ns); + shhwtstamp = skb_hwtstamps(skb); + memset(shhwtstamp, 0, sizeof(struct skb_shared_hwtstamps)); + shhwtstamp->hwtstamp = ns_to_ktime(ns); + } else { + netdev_err(priv->dev, "cannot get RX hw timestamp\n"); + } } /** @@ -598,17 +594,18 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr) priv->hwts_tx_en = config.tx_type == HWTSTAMP_TX_ON; if (!priv->hwts_tx_en && !priv->hwts_rx_en) - priv->hw->ptp->config_hw_tstamping(priv->ioaddr, 0); + priv->hw->ptp->config_hw_tstamping(priv->ptpaddr, 0); else { value = (PTP_TCR_TSENA | PTP_TCR_TSCFUPDT | PTP_TCR_TSCTRLSSR | tstamp_all | ptp_v2 | ptp_over_ethernet | ptp_over_ipv6_udp | ptp_over_ipv4_udp | ts_event_en | ts_master_en | snap_type_sel); - priv->hw->ptp->config_hw_tstamping(priv->ioaddr, value); + priv->hw->ptp->config_hw_tstamping(priv->ptpaddr, value); /* program Sub Second Increment reg */ sec_inc = priv->hw->ptp->config_sub_second_increment( - priv->ioaddr, priv->clk_ptp_rate); + priv->ptpaddr, priv->clk_ptp_rate, + priv->plat->has_gmac4); temp = div_u64(1000000000ULL, sec_inc); /* calculate default added value: @@ -618,14 +615,14 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr) */ temp = (u64)(temp << 32); priv->default_addend = div_u64(temp, priv->clk_ptp_rate); - priv->hw->ptp->config_addend(priv->ioaddr, + priv->hw->ptp->config_addend(priv->ptpaddr, priv->default_addend); /* initialize system time */ ktime_get_real_ts64(&now); /* lower 32 bits of tv_sec are safe until y2106 */ - priv->hw->ptp->init_systime(priv->ioaddr, (u32)now.tv_sec, + priv->hw->ptp->init_systime(priv->ptpaddr, (u32)now.tv_sec, now.tv_nsec); } @@ -1340,7 +1337,7 @@ static void stmmac_tx_clean(struct stmmac_priv *priv) priv->dev->stats.tx_packets++; priv->xstats.tx_pkt_n++; } - stmmac_get_tx_hwtstamp(priv, entry, skb); + stmmac_get_tx_hwtstamp(priv, p, skb); } if (likely(priv->tx_skbuff_dma[entry].buf)) { @@ -1486,10 +1483,13 @@ static void stmmac_mmc_setup(struct stmmac_priv *priv) unsigned int mode = MMC_CNTRL_RESET_ON_READ | MMC_CNTRL_COUNTER_RESET | MMC_CNTRL_PRESET | MMC_CNTRL_FULL_HALF_PRESET; - if (priv->synopsys_id >= DWMAC_CORE_4_00) + if (priv->synopsys_id >= DWMAC_CORE_4_00) { + priv->ptpaddr = priv->ioaddr + PTP_GMAC4_OFFSET; priv->mmcaddr = priv->ioaddr + MMC_GMAC4_OFFSET; - else + } else { + priv->ptpaddr = priv->ioaddr + PTP_GMAC3_X_OFFSET; priv->mmcaddr = priv->ioaddr + MMC_GMAC3_X_OFFSET; + } dwmac_mmc_intr_all_mask(priv->mmcaddr); @@ -2484,7 +2484,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit) if (netif_msg_rx_status(priv)) { void *rx_head; - pr_debug("%s: descriptor ring:\n", __func__); + pr_info(">>>>>> %s: descriptor ring:\n", __func__); if (priv->extend_desc) rx_head = (void *)priv->dma_erx; else @@ -2495,6 +2495,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit) while (count < limit) { int status; struct dma_desc *p; + struct dma_desc *np; if (priv->extend_desc) p = (struct dma_desc *)(priv->dma_erx + entry); @@ -2514,9 +2515,11 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit) next_entry = priv->cur_rx; if (priv->extend_desc) - prefetch(priv->dma_erx + next_entry); + np = (struct dma_desc *)(priv->dma_erx + next_entry); else - prefetch(priv->dma_rx + next_entry); + np = priv->dma_rx + next_entry; + + prefetch(np); if ((priv->extend_desc) && (priv->hw->desc->rx_extended_status)) priv->hw->desc->rx_extended_status(&priv->dev->stats, @@ -2568,7 +2571,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit) frame_len -= ETH_FCS_LEN; if (netif_msg_rx_status(priv)) { - pr_debug("\tdesc: %p [entry %d] buff=0x%x\n", + pr_info("\tdesc: %p [entry %d] buff=0x%x\n", p, entry, des); if (frame_len > ETH_FRAME_LEN) pr_debug("\tframe size %d, COE: %d\n", @@ -2625,13 +2628,13 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit) DMA_FROM_DEVICE); } - stmmac_get_rx_hwtstamp(priv, entry, skb); - if (netif_msg_pktdata(priv)) { pr_debug("frame received (%dbytes)", frame_len); print_pkt(skb->data, frame_len); } + stmmac_get_rx_hwtstamp(priv, p, np, skb); + stmmac_rx_vlan(priv->dev, skb); skb->protocol = eth_type_trans(skb, priv->dev); @@ -3413,7 +3416,6 @@ int stmmac_dvr_remove(struct device *dev) stmmac_set_mac(priv->ioaddr, false); netif_carrier_off(ndev); unregister_netdev(ndev); - of_node_put(priv->plat->phy_node); if (priv->stmmac_rst) reset_control_assert(priv->stmmac_rst); clk_disable_unprepare(priv->pclk); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 0a0d6a86f397..ac3d39c69509 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -126,8 +126,10 @@ static struct stmmac_axi *stmmac_axi_setup(struct platform_device *pdev) axi->axi_mb = of_property_read_bool(np, "snps,axi_mb"); axi->axi_rb = of_property_read_bool(np, "snps,axi_rb"); - of_property_read_u32(np, "snps,wr_osr_lmt", &axi->axi_wr_osr_lmt); - of_property_read_u32(np, "snps,rd_osr_lmt", &axi->axi_rd_osr_lmt); + if (of_property_read_u32(np, "snps,wr_osr_lmt", &axi->axi_wr_osr_lmt)) + axi->axi_wr_osr_lmt = 1; + if (of_property_read_u32(np, "snps,rd_osr_lmt", &axi->axi_rd_osr_lmt)) + axi->axi_rd_osr_lmt = 1; of_property_read_u32_array(np, "snps,blen", axi->axi_blen, AXI_BLEN); of_node_put(np); @@ -200,7 +202,6 @@ static int stmmac_dt_phy(struct plat_stmmacenet_data *plat, /** * stmmac_probe_config_dt - parse device-tree driver parameters * @pdev: platform_device structure - * @plat: driver data platform structure * @mac: MAC address to use * Description: * this function is to read the driver parameters from device-tree and @@ -306,7 +307,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) dma_cfg = devm_kzalloc(&pdev->dev, sizeof(*dma_cfg), GFP_KERNEL); if (!dma_cfg) { - of_node_put(plat->phy_node); + stmmac_remove_config_dt(pdev, plat); return ERR_PTR(-ENOMEM); } plat->dma_cfg = dma_cfg; @@ -329,14 +330,37 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) return plat; } + +/** + * stmmac_remove_config_dt - undo the effects of stmmac_probe_config_dt() + * @pdev: platform_device structure + * @plat: driver data platform structure + * + * Release resources claimed by stmmac_probe_config_dt(). + */ +void stmmac_remove_config_dt(struct platform_device *pdev, + struct plat_stmmacenet_data *plat) +{ + struct device_node *np = pdev->dev.of_node; + + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); + of_node_put(plat->phy_node); +} #else struct plat_stmmacenet_data * stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) { return ERR_PTR(-ENOSYS); } + +void stmmac_remove_config_dt(struct platform_device *pdev, + struct plat_stmmacenet_data *plat) +{ +} #endif /* CONFIG_OF */ EXPORT_SYMBOL_GPL(stmmac_probe_config_dt); +EXPORT_SYMBOL_GPL(stmmac_remove_config_dt); int stmmac_get_platform_resources(struct platform_device *pdev, struct stmmac_resources *stmmac_res) @@ -392,10 +416,13 @@ int stmmac_pltfr_remove(struct platform_device *pdev) { struct net_device *ndev = platform_get_drvdata(pdev); struct stmmac_priv *priv = netdev_priv(ndev); + struct plat_stmmacenet_data *plat = priv->plat; int ret = stmmac_dvr_remove(&pdev->dev); - if (priv->plat->exit) - priv->plat->exit(pdev, priv->plat->bsp_priv); + if (plat->exit) + plat->exit(pdev, plat->bsp_priv); + + stmmac_remove_config_dt(pdev, plat); return ret; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h index 64e147f53a9c..b72eb0de57b7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h @@ -23,6 +23,8 @@ struct plat_stmmacenet_data * stmmac_probe_config_dt(struct platform_device *pdev, const char **mac); +void stmmac_remove_config_dt(struct platform_device *pdev, + struct plat_stmmacenet_data *plat); int stmmac_get_platform_resources(struct platform_device *pdev, struct stmmac_resources *stmmac_res); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c index 1477471f8d44..3eb281d1db08 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c @@ -54,7 +54,7 @@ static int stmmac_adjust_freq(struct ptp_clock_info *ptp, s32 ppb) spin_lock_irqsave(&priv->ptp_lock, flags); - priv->hw->ptp->config_addend(priv->ioaddr, addend); + priv->hw->ptp->config_addend(priv->ptpaddr, addend); spin_unlock_irqrestore(&priv->ptp_lock, flags); @@ -89,7 +89,8 @@ static int stmmac_adjust_time(struct ptp_clock_info *ptp, s64 delta) spin_lock_irqsave(&priv->ptp_lock, flags); - priv->hw->ptp->adjust_systime(priv->ioaddr, sec, nsec, neg_adj); + priv->hw->ptp->adjust_systime(priv->ptpaddr, sec, nsec, neg_adj, + priv->plat->has_gmac4); spin_unlock_irqrestore(&priv->ptp_lock, flags); @@ -114,7 +115,7 @@ static int stmmac_get_time(struct ptp_clock_info *ptp, struct timespec64 *ts) spin_lock_irqsave(&priv->ptp_lock, flags); - ns = priv->hw->ptp->get_systime(priv->ioaddr); + ns = priv->hw->ptp->get_systime(priv->ptpaddr); spin_unlock_irqrestore(&priv->ptp_lock, flags); @@ -141,7 +142,7 @@ static int stmmac_set_time(struct ptp_clock_info *ptp, spin_lock_irqsave(&priv->ptp_lock, flags); - priv->hw->ptp->init_systime(priv->ioaddr, ts->tv_sec, ts->tv_nsec); + priv->hw->ptp->init_systime(priv->ptpaddr, ts->tv_sec, ts->tv_nsec); spin_unlock_irqrestore(&priv->ptp_lock, flags); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h index 4535df37c227..c06938c47af5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h @@ -22,51 +22,53 @@ Author: Rayagond Kokatanur <rayagond@vayavyalabs.com> ******************************************************************************/ -#ifndef __STMMAC_PTP_H__ -#define __STMMAC_PTP_H__ +#ifndef __STMMAC_PTP_H__ +#define __STMMAC_PTP_H__ -/* IEEE 1588 PTP register offsets */ -#define PTP_TCR 0x0700 /* Timestamp Control Reg */ -#define PTP_SSIR 0x0704 /* Sub-Second Increment Reg */ -#define PTP_STSR 0x0708 /* System Time – Seconds Regr */ -#define PTP_STNSR 0x070C /* System Time – Nanoseconds Reg */ -#define PTP_STSUR 0x0710 /* System Time – Seconds Update Reg */ -#define PTP_STNSUR 0x0714 /* System Time – Nanoseconds Update Reg */ -#define PTP_TAR 0x0718 /* Timestamp Addend Reg */ -#define PTP_TTSR 0x071C /* Target Time Seconds Reg */ -#define PTP_TTNSR 0x0720 /* Target Time Nanoseconds Reg */ -#define PTP_STHWSR 0x0724 /* System Time - Higher Word Seconds Reg */ -#define PTP_TSR 0x0728 /* Timestamp Status */ +#define PTP_GMAC4_OFFSET 0xb00 +#define PTP_GMAC3_X_OFFSET 0x700 -#define PTP_STNSUR_ADDSUB_SHIFT 31 +/* IEEE 1588 PTP register offsets */ +#define PTP_TCR 0x00 /* Timestamp Control Reg */ +#define PTP_SSIR 0x04 /* Sub-Second Increment Reg */ +#define PTP_STSR 0x08 /* System Time – Seconds Regr */ +#define PTP_STNSR 0x0c /* System Time – Nanoseconds Reg */ +#define PTP_STSUR 0x10 /* System Time – Seconds Update Reg */ +#define PTP_STNSUR 0x14 /* System Time – Nanoseconds Update Reg */ +#define PTP_TAR 0x18 /* Timestamp Addend Reg */ -/* PTP TCR defines */ -#define PTP_TCR_TSENA 0x00000001 /* Timestamp Enable */ -#define PTP_TCR_TSCFUPDT 0x00000002 /* Timestamp Fine/Coarse Update */ -#define PTP_TCR_TSINIT 0x00000004 /* Timestamp Initialize */ -#define PTP_TCR_TSUPDT 0x00000008 /* Timestamp Update */ -/* Timestamp Interrupt Trigger Enable */ -#define PTP_TCR_TSTRIG 0x00000010 -#define PTP_TCR_TSADDREG 0x00000020 /* Addend Reg Update */ -#define PTP_TCR_TSENALL 0x00000100 /* Enable Timestamp for All Frames */ -/* Timestamp Digital or Binary Rollover Control */ -#define PTP_TCR_TSCTRLSSR 0x00000200 +#define PTP_STNSUR_ADDSUB_SHIFT 31 +#define PTP_DIGITAL_ROLLOVER_MODE 0x3B9ACA00 /* 10e9-1 ns */ +#define PTP_BINARY_ROLLOVER_MODE 0x80000000 /* ~0.466 ns */ +/* PTP Timestamp control register defines */ +#define PTP_TCR_TSENA BIT(0) /* Timestamp Enable */ +#define PTP_TCR_TSCFUPDT BIT(1) /* Timestamp Fine/Coarse Update */ +#define PTP_TCR_TSINIT BIT(2) /* Timestamp Initialize */ +#define PTP_TCR_TSUPDT BIT(3) /* Timestamp Update */ +#define PTP_TCR_TSTRIG BIT(4) /* Timestamp Interrupt Trigger Enable */ +#define PTP_TCR_TSADDREG BIT(5) /* Addend Reg Update */ +#define PTP_TCR_TSENALL BIT(8) /* Enable Timestamp for All Frames */ +#define PTP_TCR_TSCTRLSSR BIT(9) /* Digital or Binary Rollover Control */ /* Enable PTP packet Processing for Version 2 Format */ -#define PTP_TCR_TSVER2ENA 0x00000400 +#define PTP_TCR_TSVER2ENA BIT(10) /* Enable Processing of PTP over Ethernet Frames */ -#define PTP_TCR_TSIPENA 0x00000800 +#define PTP_TCR_TSIPENA BIT(11) /* Enable Processing of PTP Frames Sent over IPv6-UDP */ -#define PTP_TCR_TSIPV6ENA 0x00001000 +#define PTP_TCR_TSIPV6ENA BIT(12) /* Enable Processing of PTP Frames Sent over IPv4-UDP */ -#define PTP_TCR_TSIPV4ENA 0x00002000 +#define PTP_TCR_TSIPV4ENA BIT(13) /* Enable Timestamp Snapshot for Event Messages */ -#define PTP_TCR_TSEVNTENA 0x00004000 +#define PTP_TCR_TSEVNTENA BIT(14) /* Enable Snapshot for Messages Relevant to Master */ -#define PTP_TCR_TSMSTRENA 0x00008000 +#define PTP_TCR_TSMSTRENA BIT(15) /* Select PTP packets for Taking Snapshots */ -#define PTP_TCR_SNAPTYPSEL_1 0x00010000 +#define PTP_TCR_SNAPTYPSEL_1 GENMASK(17, 16) /* Enable MAC address for PTP Frame Filtering */ -#define PTP_TCR_TSENMACADDR 0x00040000 +#define PTP_TCR_TSENMACADDR BIT(18) + +/* SSIR defines */ +#define PTP_SSIR_SSINC_MASK 0xff +#define GMAC4_PTP_SSIR_SSINC_SHIFT 16 -#endif /* __STMMAC_PTP_H__ */ +#endif /* __STMMAC_PTP_H__ */ diff --git a/drivers/net/ethernet/sun/sunbmac.c b/drivers/net/ethernet/sun/sunbmac.c index aa4f9d2d8fa9..02f452730d52 100644 --- a/drivers/net/ethernet/sun/sunbmac.c +++ b/drivers/net/ethernet/sun/sunbmac.c @@ -623,6 +623,7 @@ static int bigmac_init_hw(struct bigmac *bp, int from_irq) void __iomem *gregs = bp->gregs; void __iomem *cregs = bp->creg; void __iomem *bregs = bp->bregs; + __u32 bblk_dvma = (__u32)bp->bblock_dvma; unsigned char *e = &bp->dev->dev_addr[0]; /* Latch current counters into statistics. */ @@ -671,9 +672,9 @@ static int bigmac_init_hw(struct bigmac *bp, int from_irq) bregs + BMAC_XIFCFG); /* Tell the QEC where the ring descriptors are. */ - sbus_writel(bp->bblock_dvma + bib_offset(be_rxd, 0), + sbus_writel(bblk_dvma + bib_offset(be_rxd, 0), cregs + CREG_RXDS); - sbus_writel(bp->bblock_dvma + bib_offset(be_txd, 0), + sbus_writel(bblk_dvma + bib_offset(be_txd, 0), cregs + CREG_TXDS); /* Setup the FIFO pointers into QEC local memory. */ diff --git a/drivers/net/ethernet/sun/sunbmac.h b/drivers/net/ethernet/sun/sunbmac.h index 06dd21707353..532fc56830cf 100644 --- a/drivers/net/ethernet/sun/sunbmac.h +++ b/drivers/net/ethernet/sun/sunbmac.h @@ -291,7 +291,7 @@ struct bigmac { void __iomem *bregs; /* BigMAC Registers */ void __iomem *tregs; /* BigMAC Transceiver */ struct bmac_init_block *bmac_block; /* RX and TX descriptors */ - __u32 bblock_dvma; /* RX and TX descriptors */ + dma_addr_t bblock_dvma; /* RX and TX descriptors */ spinlock_t lock; diff --git a/drivers/net/ethernet/sun/sunqe.c b/drivers/net/ethernet/sun/sunqe.c index 9b825780b3be..9582948145c1 100644 --- a/drivers/net/ethernet/sun/sunqe.c +++ b/drivers/net/ethernet/sun/sunqe.c @@ -124,7 +124,7 @@ static void qe_init_rings(struct sunqe *qep) { struct qe_init_block *qb = qep->qe_block; struct sunqe_buffers *qbufs = qep->buffers; - __u32 qbufs_dvma = qep->buffers_dvma; + __u32 qbufs_dvma = (__u32)qep->buffers_dvma; int i; qep->rx_new = qep->rx_old = qep->tx_new = qep->tx_old = 0; @@ -144,6 +144,7 @@ static int qe_init(struct sunqe *qep, int from_irq) void __iomem *mregs = qep->mregs; void __iomem *gregs = qecp->gregs; unsigned char *e = &qep->dev->dev_addr[0]; + __u32 qblk_dvma = (__u32)qep->qblock_dvma; u32 tmp; int i; @@ -152,8 +153,8 @@ static int qe_init(struct sunqe *qep, int from_irq) return -EAGAIN; /* Setup initial rx/tx init block pointers. */ - sbus_writel(qep->qblock_dvma + qib_offset(qe_rxd, 0), cregs + CREG_RXDS); - sbus_writel(qep->qblock_dvma + qib_offset(qe_txd, 0), cregs + CREG_TXDS); + sbus_writel(qblk_dvma + qib_offset(qe_rxd, 0), cregs + CREG_RXDS); + sbus_writel(qblk_dvma + qib_offset(qe_txd, 0), cregs + CREG_TXDS); /* Enable/mask the various irq's. */ sbus_writel(0, cregs + CREG_RIMASK); @@ -413,7 +414,7 @@ static void qe_rx(struct sunqe *qep) struct net_device *dev = qep->dev; struct qe_rxd *this; struct sunqe_buffers *qbufs = qep->buffers; - __u32 qbufs_dvma = qep->buffers_dvma; + __u32 qbufs_dvma = (__u32)qep->buffers_dvma; int elem = qep->rx_new; u32 flags; @@ -572,7 +573,7 @@ static int qe_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct sunqe *qep = netdev_priv(dev); struct sunqe_buffers *qbufs = qep->buffers; - __u32 txbuf_dvma, qbufs_dvma = qep->buffers_dvma; + __u32 txbuf_dvma, qbufs_dvma = (__u32)qep->buffers_dvma; unsigned char *txbuf; int len, entry; diff --git a/drivers/net/ethernet/sun/sunqe.h b/drivers/net/ethernet/sun/sunqe.h index 581781b6b2fa..ae190b77431b 100644 --- a/drivers/net/ethernet/sun/sunqe.h +++ b/drivers/net/ethernet/sun/sunqe.h @@ -334,12 +334,12 @@ struct sunqe { void __iomem *qcregs; /* QEC per-channel Registers */ void __iomem *mregs; /* Per-channel MACE Registers */ struct qe_init_block *qe_block; /* RX and TX descriptors */ - __u32 qblock_dvma; /* RX and TX descriptors */ + dma_addr_t qblock_dvma; /* RX and TX descriptors */ spinlock_t lock; /* Protects txfull state */ int rx_new, rx_old; /* RX ring extents */ int tx_new, tx_old; /* TX ring extents */ struct sunqe_buffers *buffers; /* CPU visible address. */ - __u32 buffers_dvma; /* DVMA visible address. */ + dma_addr_t buffers_dvma; /* DVMA visible address. */ struct sunqec *parent; u8 mconfig; /* Base MACE mconfig value */ struct platform_device *op; /* QE's OF device struct */ diff --git a/drivers/net/ethernet/synopsys/dwc_eth_qos.c b/drivers/net/ethernet/synopsys/dwc_eth_qos.c index 5eedac495077..97d64bfed465 100644 --- a/drivers/net/ethernet/synopsys/dwc_eth_qos.c +++ b/drivers/net/ethernet/synopsys/dwc_eth_qos.c @@ -33,7 +33,6 @@ #include <linux/stat.h> #include <linux/types.h> -#include <linux/types.h> #include <linux/slab.h> #include <linux/delay.h> #include <linux/mm.h> @@ -43,7 +42,6 @@ #include <linux/phy.h> #include <linux/mii.h> -#include <linux/delay.h> #include <linux/dma-mapping.h> #include <linux/vmalloc.h> @@ -2883,7 +2881,7 @@ static int dwceqos_probe(struct platform_device *pdev) ret = of_get_phy_mode(lp->pdev->dev.of_node); if (ret < 0) { dev_err(&lp->pdev->dev, "error in getting phy i/f\n"); - goto err_out_clk_dis_phy; + goto err_out_deregister_fixed_link; } lp->phy_interface = ret; @@ -2891,14 +2889,14 @@ static int dwceqos_probe(struct platform_device *pdev) ret = dwceqos_mii_init(lp); if (ret) { dev_err(&lp->pdev->dev, "error in dwceqos_mii_init\n"); - goto err_out_clk_dis_phy; + goto err_out_deregister_fixed_link; } ret = dwceqos_mii_probe(ndev); if (ret != 0) { netdev_err(ndev, "mii_probe fail.\n"); ret = -ENXIO; - goto err_out_clk_dis_phy; + goto err_out_deregister_fixed_link; } dwceqos_set_umac_addr(lp, lp->ndev->dev_addr, 0); @@ -2916,7 +2914,7 @@ static int dwceqos_probe(struct platform_device *pdev) if (ret) { dev_err(&lp->pdev->dev, "Unable to retrieve DT, error %d\n", ret); - goto err_out_clk_dis_phy; + goto err_out_deregister_fixed_link; } dev_info(&lp->pdev->dev, "pdev->id %d, baseaddr 0x%08lx, irq %d\n", pdev->id, ndev->base_addr, ndev->irq); @@ -2926,7 +2924,7 @@ static int dwceqos_probe(struct platform_device *pdev) if (ret) { dev_err(&lp->pdev->dev, "Unable to request IRQ %d, error %d\n", ndev->irq, ret); - goto err_out_clk_dis_phy; + goto err_out_deregister_fixed_link; } if (netif_msg_probe(lp)) @@ -2937,11 +2935,14 @@ static int dwceqos_probe(struct platform_device *pdev) ret = register_netdev(ndev); if (ret) { dev_err(&pdev->dev, "Cannot register net device, aborting.\n"); - goto err_out_clk_dis_phy; + goto err_out_deregister_fixed_link; } return 0; +err_out_deregister_fixed_link: + if (of_phy_is_fixed_link(pdev->dev.of_node)) + of_phy_deregister_fixed_link(pdev->dev.of_node); err_out_clk_dis_phy: clk_disable_unprepare(lp->phy_ref_clk); err_out_clk_dis_aper: @@ -2961,8 +2962,11 @@ static int dwceqos_remove(struct platform_device *pdev) if (ndev) { lp = netdev_priv(ndev); - if (ndev->phydev) + if (ndev->phydev) { phy_disconnect(ndev->phydev); + if (of_phy_is_fixed_link(pdev->dev.of_node)) + of_phy_deregister_fixed_link(pdev->dev.of_node); + } mdiobus_unregister(lp->mii_bus); mdiobus_free(lp->mii_bus); diff --git a/drivers/net/ethernet/ti/cpmac.c b/drivers/net/ethernet/ti/cpmac.c index fa0cfda24fd9..28097be2ff28 100644 --- a/drivers/net/ethernet/ti/cpmac.c +++ b/drivers/net/ethernet/ti/cpmac.c @@ -1113,6 +1113,7 @@ static int cpmac_probe(struct platform_device *pdev) if (!dev) return -ENOMEM; + SET_NETDEV_DEV(dev, &pdev->dev); platform_set_drvdata(pdev, dev); priv = netdev_priv(dev); diff --git a/drivers/net/ethernet/ti/cpsw-phy-sel.c b/drivers/net/ethernet/ti/cpsw-phy-sel.c index ba1e45ff6aae..18013645e76c 100644 --- a/drivers/net/ethernet/ti/cpsw-phy-sel.c +++ b/drivers/net/ethernet/ti/cpsw-phy-sel.c @@ -81,6 +81,7 @@ static void cpsw_gmii_sel_am3352(struct cpsw_phy_sel_priv *priv, }; mask = GMII_SEL_MODE_MASK << (slave * 2) | BIT(slave + 6); + mask |= BIT(slave + 4); mode <<= slave * 2; if (priv->rmii_clock_external) { diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index c6cff3d2ff05..b9087b828eff 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -2375,8 +2375,11 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data, * to the PHY is the Ethernet MAC DT node. */ ret = of_phy_register_fixed_link(slave_node); - if (ret) + if (ret) { + if (ret != -EPROBE_DEFER) + dev_err(&pdev->dev, "failed to register fixed-link phy: %d\n", ret); return ret; + } slave_data->phy_node = of_node_get(slave_node); } else if (parp) { u32 phyid; @@ -2397,6 +2400,7 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data, } snprintf(slave_data->phy_id, sizeof(slave_data->phy_id), PHY_ID_FMT, mdio->name, phyid); + put_device(&mdio->dev); } else { dev_err(&pdev->dev, "No slave[%d] phy_id, phy-handle, or fixed-link property\n", @@ -2440,6 +2444,34 @@ no_phy_slave: return 0; } +static void cpsw_remove_dt(struct platform_device *pdev) +{ + struct net_device *ndev = platform_get_drvdata(pdev); + struct cpsw_common *cpsw = ndev_to_cpsw(ndev); + struct cpsw_platform_data *data = &cpsw->data; + struct device_node *node = pdev->dev.of_node; + struct device_node *slave_node; + int i = 0; + + for_each_available_child_of_node(node, slave_node) { + struct cpsw_slave_data *slave_data = &data->slave_data[i]; + + if (strcmp(slave_node->name, "slave")) + continue; + + if (of_phy_is_fixed_link(slave_node)) + of_phy_deregister_fixed_link(slave_node); + + of_node_put(slave_data->phy_node); + + i++; + if (i == data->slaves) + break; + } + + of_platform_depopulate(&pdev->dev); +} + static int cpsw_probe_dual_emac(struct cpsw_priv *priv) { struct cpsw_common *cpsw = priv->cpsw; @@ -2547,6 +2579,9 @@ static int cpsw_probe(struct platform_device *pdev) int irq; cpsw = devm_kzalloc(&pdev->dev, sizeof(struct cpsw_common), GFP_KERNEL); + if (!cpsw) + return -ENOMEM; + cpsw->dev = &pdev->dev; ndev = alloc_etherdev_mq(sizeof(struct cpsw_priv), CPSW_MAX_QUEUES); @@ -2584,11 +2619,19 @@ static int cpsw_probe(struct platform_device *pdev) /* Select default pin state */ pinctrl_pm_select_default_state(&pdev->dev); - if (cpsw_probe_dt(&cpsw->data, pdev)) { - dev_err(&pdev->dev, "cpsw: platform data missing\n"); - ret = -ENODEV; + /* Need to enable clocks with runtime PM api to access module + * registers + */ + ret = pm_runtime_get_sync(&pdev->dev); + if (ret < 0) { + pm_runtime_put_noidle(&pdev->dev); goto clean_runtime_disable_ret; } + + ret = cpsw_probe_dt(&cpsw->data, pdev); + if (ret) + goto clean_dt_ret; + data = &cpsw->data; cpsw->rx_ch_num = 1; cpsw->tx_ch_num = 1; @@ -2608,7 +2651,7 @@ static int cpsw_probe(struct platform_device *pdev) GFP_KERNEL); if (!cpsw->slaves) { ret = -ENOMEM; - goto clean_runtime_disable_ret; + goto clean_dt_ret; } for (i = 0; i < data->slaves; i++) cpsw->slaves[i].slave_num = i; @@ -2620,7 +2663,7 @@ static int cpsw_probe(struct platform_device *pdev) if (IS_ERR(clk)) { dev_err(priv->dev, "fck is not found\n"); ret = -ENODEV; - goto clean_runtime_disable_ret; + goto clean_dt_ret; } cpsw->bus_freq_mhz = clk_get_rate(clk) / 1000000; @@ -2628,26 +2671,17 @@ static int cpsw_probe(struct platform_device *pdev) ss_regs = devm_ioremap_resource(&pdev->dev, ss_res); if (IS_ERR(ss_regs)) { ret = PTR_ERR(ss_regs); - goto clean_runtime_disable_ret; + goto clean_dt_ret; } cpsw->regs = ss_regs; - /* Need to enable clocks with runtime PM api to access module - * registers - */ - ret = pm_runtime_get_sync(&pdev->dev); - if (ret < 0) { - pm_runtime_put_noidle(&pdev->dev); - goto clean_runtime_disable_ret; - } cpsw->version = readl(&cpsw->regs->id_ver); - pm_runtime_put_sync(&pdev->dev); res = platform_get_resource(pdev, IORESOURCE_MEM, 1); cpsw->wr_regs = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(cpsw->wr_regs)) { ret = PTR_ERR(cpsw->wr_regs); - goto clean_runtime_disable_ret; + goto clean_dt_ret; } memset(&dma_params, 0, sizeof(dma_params)); @@ -2684,7 +2718,7 @@ static int cpsw_probe(struct platform_device *pdev) default: dev_err(priv->dev, "unknown version 0x%08x\n", cpsw->version); ret = -ENODEV; - goto clean_runtime_disable_ret; + goto clean_dt_ret; } for (i = 0; i < cpsw->data.slaves; i++) { struct cpsw_slave *slave = &cpsw->slaves[i]; @@ -2713,7 +2747,7 @@ static int cpsw_probe(struct platform_device *pdev) if (!cpsw->dma) { dev_err(priv->dev, "error initializing dma\n"); ret = -ENOMEM; - goto clean_runtime_disable_ret; + goto clean_dt_ret; } cpsw->txch[0] = cpdma_chan_create(cpsw->dma, 0, cpsw_tx_handler, 0); @@ -2811,16 +2845,23 @@ static int cpsw_probe(struct platform_device *pdev) ret = cpsw_probe_dual_emac(priv); if (ret) { cpsw_err(priv, probe, "error probe slave 2 emac interface\n"); - goto clean_ale_ret; + goto clean_unregister_netdev_ret; } } + pm_runtime_put(&pdev->dev); + return 0; +clean_unregister_netdev_ret: + unregister_netdev(ndev); clean_ale_ret: cpsw_ale_destroy(cpsw->ale); clean_dma_ret: cpdma_ctlr_destroy(cpsw->dma); +clean_dt_ret: + cpsw_remove_dt(pdev); + pm_runtime_put_sync(&pdev->dev); clean_runtime_disable_ret: pm_runtime_disable(&pdev->dev); clean_ndev_ret: @@ -2846,7 +2887,7 @@ static int cpsw_remove(struct platform_device *pdev) cpsw_ale_destroy(cpsw->ale); cpdma_ctlr_destroy(cpsw->dma); - of_platform_depopulate(&pdev->dev); + cpsw_remove_dt(pdev); pm_runtime_put_sync(&pdev->dev); pm_runtime_disable(&pdev->dev); if (cpsw->data.dual_emac) @@ -2889,6 +2930,8 @@ static int cpsw_resume(struct device *dev) /* Select default pin state */ pinctrl_pm_select_default_state(dev); + /* shut up ASSERT_RTNL() warning in netif_set_real_num_tx/rx_queues */ + rtnl_lock(); if (cpsw->data.dual_emac) { int i; @@ -2900,6 +2943,8 @@ static int cpsw_resume(struct device *dev) if (netif_running(ndev)) cpsw_ndo_open(ndev); } + rtnl_unlock(); + return 0; } #endif diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c index 84fbe5714f8b..481c7bf0395b 100644 --- a/drivers/net/ethernet/ti/davinci_emac.c +++ b/drivers/net/ethernet/ti/davinci_emac.c @@ -1767,6 +1767,7 @@ static int davinci_emac_try_get_mac(struct platform_device *pdev, */ static int davinci_emac_probe(struct platform_device *pdev) { + struct device_node *np = pdev->dev.of_node; int rc = 0; struct resource *res, *res_ctrl; struct net_device *ndev; @@ -1805,7 +1806,7 @@ static int davinci_emac_probe(struct platform_device *pdev) if (!pdata) { dev_err(&pdev->dev, "no platform data\n"); rc = -ENODEV; - goto no_pdata; + goto err_free_netdev; } /* MAC addr and PHY mask , RMII enable info from platform_data */ @@ -1941,6 +1942,10 @@ no_cpdma_chan: cpdma_chan_destroy(priv->rxchan); cpdma_ctlr_destroy(priv->dma); no_pdata: + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); + of_node_put(priv->phy_node); +err_free_netdev: free_netdev(ndev); return rc; } @@ -1956,6 +1961,7 @@ static int davinci_emac_remove(struct platform_device *pdev) { struct net_device *ndev = platform_get_drvdata(pdev); struct emac_priv *priv = netdev_priv(ndev); + struct device_node *np = pdev->dev.of_node; dev_notice(&ndev->dev, "DaVinci EMAC: davinci_emac_remove()\n"); @@ -1968,6 +1974,8 @@ static int davinci_emac_remove(struct platform_device *pdev) unregister_netdev(ndev); of_node_put(priv->phy_node); pm_runtime_disable(&pdev->dev); + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); free_netdev(ndev); return 0; diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 42edd7b7902f..8b4822ad27cb 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -859,7 +859,6 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct geneve_dev *geneve = netdev_priv(dev); struct geneve_sock *gs4; struct rtable *rt = NULL; - const struct iphdr *iip; /* interior IP header */ int err = -EINVAL; struct flowi4 fl4; __u8 tos, ttl; @@ -890,8 +889,6 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); skb_reset_mac_header(skb); - iip = ip_hdr(skb); - if (info) { const struct ip_tunnel_key *key = &info->key; u8 *opts = NULL; @@ -911,7 +908,7 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, if (unlikely(err)) goto tx_error; - tos = ip_tunnel_ecn_encap(key->tos, iip, skb); + tos = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb); ttl = key->ttl; df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; } else { @@ -920,7 +917,7 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, if (unlikely(err)) goto tx_error; - tos = ip_tunnel_ecn_encap(fl4.flowi4_tos, iip, skb); + tos = ip_tunnel_ecn_encap(fl4.flowi4_tos, ip_hdr(skb), skb); ttl = geneve->ttl; if (!ttl && IN_MULTICAST(ntohl(fl4.daddr))) ttl = 1; @@ -952,7 +949,6 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, { struct geneve_dev *geneve = netdev_priv(dev); struct dst_entry *dst = NULL; - const struct iphdr *iip; /* interior IP header */ struct geneve_sock *gs6; int err = -EINVAL; struct flowi6 fl6; @@ -982,8 +978,6 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); skb_reset_mac_header(skb); - iip = ip_hdr(skb); - if (info) { const struct ip_tunnel_key *key = &info->key; u8 *opts = NULL; @@ -1004,7 +998,7 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, if (unlikely(err)) goto tx_error; - prio = ip_tunnel_ecn_encap(key->tos, iip, skb); + prio = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb); ttl = key->ttl; label = info->key.label; } else { @@ -1014,7 +1008,7 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, goto tx_error; prio = ip_tunnel_ecn_encap(ip6_tclass(fl6.flowlabel), - iip, skb); + ip_hdr(skb), skb); ttl = geneve->ttl; if (!ttl && ipv6_addr_is_multicast(&fl6.daddr)) ttl = 1; diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index f6382150b16a..c9140c3aeb67 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -47,6 +47,10 @@ NETIF_F_TSO | \ NETIF_F_TSO6 | \ NETIF_F_HW_CSUM) + +/* Restrict GSO size to account for NVGRE */ +#define NETVSC_GSO_MAX_SIZE 62768 + static int ring_size = 128; module_param(ring_size, int, S_IRUGO); MODULE_PARM_DESC(ring_size, "Ring buffer size (# of pages)"); @@ -1400,6 +1404,7 @@ static int netvsc_probe(struct hv_device *dev, nvdev = net_device_ctx->nvdev; netif_set_real_num_tx_queues(net, nvdev->num_chn); netif_set_real_num_rx_queues(net, nvdev->num_chn); + netif_set_gso_max_size(net, NETVSC_GSO_MAX_SIZE); ret = register_netdev(net); if (ret != 0) { diff --git a/drivers/net/ieee802154/adf7242.c b/drivers/net/ieee802154/adf7242.c index 9fa7ac9f8e68..f355df7cf84a 100644 --- a/drivers/net/ieee802154/adf7242.c +++ b/drivers/net/ieee802154/adf7242.c @@ -20,7 +20,6 @@ #include <linux/skbuff.h> #include <linux/of.h> #include <linux/irq.h> -#include <linux/delay.h> #include <linux/debugfs.h> #include <linux/bitops.h> #include <linux/ieee802154.h> diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index f442eb366863..dfbc4ef6d507 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -497,6 +497,7 @@ static int ipvlan_link_new(struct net *src_net, struct net_device *dev, struct net_device *phy_dev; int err; u16 mode = IPVLAN_MODE_L3; + bool create = false; if (!tb[IFLA_LINK]) return -EINVAL; @@ -513,6 +514,7 @@ static int ipvlan_link_new(struct net *src_net, struct net_device *dev, err = ipvlan_port_create(phy_dev); if (err < 0) return err; + create = true; } if (data && data[IFLA_IPVLAN_MODE]) @@ -536,22 +538,29 @@ static int ipvlan_link_new(struct net *src_net, struct net_device *dev, err = register_netdevice(dev); if (err < 0) - return err; + goto destroy_ipvlan_port; err = netdev_upper_dev_link(phy_dev, dev); if (err) { - unregister_netdevice(dev); - return err; + goto unregister_netdev; } err = ipvlan_set_port_mode(port, mode); if (err) { - unregister_netdevice(dev); - return err; + goto unlink_netdev; } list_add_tail_rcu(&ipvlan->pnode, &port->ipvlans); netif_stacked_transfer_operstate(phy_dev, dev); return 0; + +unlink_netdev: + netdev_upper_dev_unlink(phy_dev, dev); +unregister_netdev: + unregister_netdevice(dev); +destroy_ipvlan_port: + if (create) + ipvlan_port_destroy(phy_dev); + return err; } static void ipvlan_link_delete(struct net_device *dev, struct list_head *head) diff --git a/drivers/net/irda/irda-usb.c b/drivers/net/irda/irda-usb.c index a198946bc54f..8716b8c07feb 100644 --- a/drivers/net/irda/irda-usb.c +++ b/drivers/net/irda/irda-usb.c @@ -1723,6 +1723,7 @@ static int irda_usb_probe(struct usb_interface *intf, /* Don't change this buffer size and allocation without doing * some heavy and complete testing. Don't ask why :-( * Jean II */ + ret = -ENOMEM; self->speed_buff = kzalloc(IRDA_USB_SPEED_MTU, GFP_KERNEL); if (!self->speed_buff) goto err_out_3; diff --git a/drivers/net/irda/w83977af_ir.c b/drivers/net/irda/w83977af_ir.c index 4e3d2e7c697c..e8c3a8c32534 100644 --- a/drivers/net/irda/w83977af_ir.c +++ b/drivers/net/irda/w83977af_ir.c @@ -518,7 +518,9 @@ static netdev_tx_t w83977af_hard_xmit(struct sk_buff *skb, mtt = irda_get_mtt(skb); pr_debug("%s(%ld), mtt=%d\n", __func__ , jiffies, mtt); - if (mtt) + if (mtt > 1000) + mdelay(mtt/1000); + else if (mtt) udelay(mtt); /* Enable DMA interrupt */ diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index d2d6f12a112f..26d6f0bbe14b 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -623,7 +623,8 @@ hash_add: return 0; clear_multi: - dev_set_allmulti(lowerdev, -1); + if (dev->flags & IFF_ALLMULTI) + dev_set_allmulti(lowerdev, -1); del_unicast: dev_uc_del(lowerdev, dev->dev_addr); out: diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 070e3290aa6e..7869b0651576 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -491,7 +491,13 @@ static int macvtap_newlink(struct net *src_net, /* Don't put anything that may fail after macvlan_common_newlink * because we can't undo what it does. */ - return macvlan_common_newlink(src_net, dev, tb, data); + err = macvlan_common_newlink(src_net, dev, tb, data); + if (err) { + netdev_rx_handler_unregister(dev); + return err; + } + + return 0; } static void macvtap_dellink(struct net_device *dev, @@ -736,13 +742,8 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, if (zerocopy) err = zerocopy_sg_from_iter(skb, from); - else { + else err = skb_copy_datagram_from_iter(skb, 0, from, len); - if (!err && m && m->msg_control) { - struct ubuf_info *uarg = m->msg_control; - uarg->callback(uarg, false); - } - } if (err) goto err_kfree; @@ -773,7 +774,11 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, skb_shinfo(skb)->destructor_arg = m->msg_control; skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY; skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; + } else if (m && m->msg_control) { + struct ubuf_info *uarg = m->msg_control; + uarg->callback(uarg, false); } + if (vlan) { skb->dev = vlan->dev; dev_queue_xmit(skb); diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c index c649c101bbab..eb5167210681 100644 --- a/drivers/net/phy/fixed_phy.c +++ b/drivers/net/phy/fixed_phy.c @@ -279,7 +279,7 @@ EXPORT_SYMBOL_GPL(fixed_phy_register); void fixed_phy_unregister(struct phy_device *phy) { phy_device_remove(phy); - + of_node_put(phy->mdio.dev.of_node); fixed_phy_del(phy->mdio.addr); } EXPORT_SYMBOL_GPL(fixed_phy_unregister); diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 081df68d2ce1..ea92d524d5a8 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -318,12 +318,12 @@ static int ksz8041_config_init(struct phy_device *phydev) /* Limit supported and advertised modes in fiber mode */ if (of_property_read_bool(of_node, "micrel,fiber-mode")) { phydev->dev_flags |= MICREL_PHY_FXEN; - phydev->supported &= SUPPORTED_FIBRE | - SUPPORTED_100baseT_Full | + phydev->supported &= SUPPORTED_100baseT_Full | SUPPORTED_100baseT_Half; - phydev->advertising &= ADVERTISED_FIBRE | - ADVERTISED_100baseT_Full | + phydev->supported |= SUPPORTED_FIBRE; + phydev->advertising &= ADVERTISED_100baseT_Full | ADVERTISED_100baseT_Half; + phydev->advertising |= ADVERTISED_FIBRE; phydev->autoneg = AUTONEG_DISABLE; } diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 1a4bf8acad78..c4ceb082e970 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -857,11 +857,17 @@ EXPORT_SYMBOL(phy_attached_print); int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, u32 flags, phy_interface_t interface) { + struct module *ndev_owner = dev->dev.parent->driver->owner; struct mii_bus *bus = phydev->mdio.bus; struct device *d = &phydev->mdio.dev; int err; - if (!try_module_get(bus->owner)) { + /* For Ethernet device drivers that register their own MDIO bus, we + * will have bus->owner match ndev_mod, so we do not want to increment + * our own module->refcnt here, otherwise we would not be able to + * unload later on. + */ + if (ndev_owner != bus->owner && !try_module_get(bus->owner)) { dev_err(&dev->dev, "failed to get the bus module\n"); return -EIO; } @@ -921,7 +927,8 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, error: put_device(d); - module_put(bus->owner); + if (ndev_owner != bus->owner) + module_put(bus->owner); return err; } EXPORT_SYMBOL(phy_attach_direct); @@ -971,6 +978,8 @@ EXPORT_SYMBOL(phy_attach); */ void phy_detach(struct phy_device *phydev) { + struct net_device *dev = phydev->attached_dev; + struct module *ndev_owner = dev->dev.parent->driver->owner; struct mii_bus *bus; int i; @@ -998,7 +1007,8 @@ void phy_detach(struct phy_device *phydev) bus = phydev->mdio.bus; put_device(&phydev->mdio.dev); - module_put(bus->owner); + if (ndev_owner != bus->owner) + module_put(bus->owner); } EXPORT_SYMBOL(phy_detach); diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index aadd6e9f54ad..9cbe645e3d89 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -102,15 +102,19 @@ static int rtl8211f_config_init(struct phy_device *phydev) if (ret < 0) return ret; - if (phydev->interface == PHY_INTERFACE_MODE_RGMII) { - /* enable TXDLY */ - phy_write(phydev, RTL8211F_PAGE_SELECT, 0xd08); - reg = phy_read(phydev, 0x11); + phy_write(phydev, RTL8211F_PAGE_SELECT, 0xd08); + reg = phy_read(phydev, 0x11); + + /* enable TX-delay for rgmii-id and rgmii-txid, otherwise disable it */ + if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID || + phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID) reg |= RTL8211F_TX_DELAY; - phy_write(phydev, 0x11, reg); - /* restore to default page 0 */ - phy_write(phydev, RTL8211F_PAGE_SELECT, 0x0); - } + else + reg &= ~RTL8211F_TX_DELAY; + + phy_write(phydev, 0x11, reg); + /* restore to default page 0 */ + phy_write(phydev, RTL8211F_PAGE_SELECT, 0x0); return 0; } diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c index 2e37eb337d48..24b4a09468dd 100644 --- a/drivers/net/phy/vitesse.c +++ b/drivers/net/phy/vitesse.c @@ -62,6 +62,10 @@ /* Vitesse Extended Page Access Register */ #define MII_VSC82X4_EXT_PAGE_ACCESS 0x1f +/* Vitesse VSC8601 Extended PHY Control Register 1 */ +#define MII_VSC8601_EPHY_CTL 0x17 +#define MII_VSC8601_EPHY_CTL_RGMII_SKEW (1 << 8) + #define PHY_ID_VSC8234 0x000fc620 #define PHY_ID_VSC8244 0x000fc6c0 #define PHY_ID_VSC8514 0x00070670 @@ -111,6 +115,34 @@ static int vsc824x_config_init(struct phy_device *phydev) return err; } +/* This adds a skew for both TX and RX clocks, so the skew should only be + * applied to "rgmii-id" interfaces. It may not work as expected + * on "rgmii-txid", "rgmii-rxid" or "rgmii" interfaces. */ +static int vsc8601_add_skew(struct phy_device *phydev) +{ + int ret; + + ret = phy_read(phydev, MII_VSC8601_EPHY_CTL); + if (ret < 0) + return ret; + + ret |= MII_VSC8601_EPHY_CTL_RGMII_SKEW; + return phy_write(phydev, MII_VSC8601_EPHY_CTL, ret); +} + +static int vsc8601_config_init(struct phy_device *phydev) +{ + int ret = 0; + + if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID) + ret = vsc8601_add_skew(phydev); + + if (ret < 0) + return ret; + + return genphy_config_init(phydev); +} + static int vsc824x_ack_interrupt(struct phy_device *phydev) { int err = 0; @@ -275,7 +307,7 @@ static struct phy_driver vsc82xx_driver[] = { .phy_id_mask = 0x000ffff0, .features = PHY_GBIT_FEATURES, .flags = PHY_HAS_INTERRUPT, - .config_init = &genphy_config_init, + .config_init = &vsc8601_config_init, .config_aneg = &genphy_config_aneg, .read_status = &genphy_read_status, .ack_interrupt = &vsc824x_ack_interrupt, diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 8093e39ae263..db6acecabeaa 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1246,13 +1246,8 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, if (zerocopy) err = zerocopy_sg_from_iter(skb, from); - else { + else err = skb_copy_datagram_from_iter(skb, 0, from, len); - if (!err && msg_control) { - struct ubuf_info *uarg = msg_control; - uarg->callback(uarg, false); - } - } if (err) { this_cpu_inc(tun->pcpu_stats->rx_dropped); @@ -1298,6 +1293,9 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, skb_shinfo(skb)->destructor_arg = msg_control; skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY; skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; + } else if (msg_control) { + struct ubuf_info *uarg = msg_control; + uarg->callback(uarg, false); } skb_reset_network_header(skb); diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c index cce24950a0ab..dc7b6392e75a 100644 --- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -603,12 +603,12 @@ static void ax88772_suspend(struct usbnet *dev) u16 medium; /* Stop MAC operation */ - medium = asix_read_medium_status(dev, 0); + medium = asix_read_medium_status(dev, 1); medium &= ~AX_MEDIUM_RE; - asix_write_medium_mode(dev, medium, 0); + asix_write_medium_mode(dev, medium, 1); netdev_dbg(dev->net, "ax88772_suspend: medium=0x%04x\n", - asix_read_medium_status(dev, 0)); + asix_read_medium_status(dev, 1)); /* Preserve BMCR for restoring */ priv->presvd_phy_bmcr = diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index c47ec0a04c8e..dd623f674487 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -388,12 +388,6 @@ void usbnet_cdc_status(struct usbnet *dev, struct urb *urb) case USB_CDC_NOTIFY_NETWORK_CONNECTION: netif_dbg(dev, timer, dev->net, "CDC: carrier %s\n", event->wValue ? "on" : "off"); - - /* Work-around for devices with broken off-notifications */ - if (event->wValue && - !test_bit(__LINK_STATE_NOCARRIER, &dev->net->state)) - usbnet_link_change(dev, 0, 0); - usbnet_link_change(dev, !!event->wValue, 0); break; case USB_CDC_NOTIFY_SPEED_CHANGE: /* tx/rx rates */ @@ -466,6 +460,36 @@ static int usbnet_cdc_zte_rx_fixup(struct usbnet *dev, struct sk_buff *skb) return 1; } +/* Ensure correct link state + * + * Some devices (ZTE MF823/831/910) export two carrier on notifications when + * connected. This causes the link state to be incorrect. Work around this by + * always setting the state to off, then on. + */ +void usbnet_cdc_zte_status(struct usbnet *dev, struct urb *urb) +{ + struct usb_cdc_notification *event; + + if (urb->actual_length < sizeof(*event)) + return; + + event = urb->transfer_buffer; + + if (event->bNotificationType != USB_CDC_NOTIFY_NETWORK_CONNECTION) { + usbnet_cdc_status(dev, urb); + return; + } + + netif_dbg(dev, timer, dev->net, "CDC: carrier %s\n", + event->wValue ? "on" : "off"); + + if (event->wValue && + netif_carrier_ok(dev->net)) + netif_carrier_off(dev->net); + + usbnet_link_change(dev, !!event->wValue, 0); +} + static const struct driver_info cdc_info = { .description = "CDC Ethernet Device", .flags = FLAG_ETHER | FLAG_POINTTOPOINT, @@ -481,7 +505,7 @@ static const struct driver_info zte_cdc_info = { .flags = FLAG_ETHER | FLAG_POINTTOPOINT, .bind = usbnet_cdc_zte_bind, .unbind = usbnet_cdc_unbind, - .status = usbnet_cdc_status, + .status = usbnet_cdc_zte_status, .set_rx_mode = usbnet_cdc_update_filter, .manage_power = usbnet_manage_power, .rx_fixup = usbnet_cdc_zte_rx_fixup, diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c index 96a5028621c8..3a98f3762a4c 100644 --- a/drivers/net/usb/cdc_mbim.c +++ b/drivers/net/usb/cdc_mbim.c @@ -602,6 +602,21 @@ static const struct driver_info cdc_mbim_info_ndp_to_end = { .data = CDC_NCM_FLAG_NDP_TO_END, }; +/* Some modems (e.g. Telit LE922A6) do not work properly with altsetting + * toggle done in cdc_ncm_bind_common. CDC_MBIM_FLAG_AVOID_ALTSETTING_TOGGLE + * flag is used to avoid this procedure. + */ +static const struct driver_info cdc_mbim_info_avoid_altsetting_toggle = { + .description = "CDC MBIM", + .flags = FLAG_NO_SETINT | FLAG_MULTI_PACKET | FLAG_WWAN, + .bind = cdc_mbim_bind, + .unbind = cdc_mbim_unbind, + .manage_power = cdc_mbim_manage_power, + .rx_fixup = cdc_mbim_rx_fixup, + .tx_fixup = cdc_mbim_tx_fixup, + .data = CDC_MBIM_FLAG_AVOID_ALTSETTING_TOGGLE, +}; + static const struct usb_device_id mbim_devs[] = { /* This duplicate NCM entry is intentional. MBIM devices can * be disguised as NCM by default, and this is necessary to @@ -626,6 +641,12 @@ static const struct usb_device_id mbim_devs[] = { { USB_VENDOR_AND_INTERFACE_INFO(0x12d1, USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE), .driver_info = (unsigned long)&cdc_mbim_info_ndp_to_end, }, + + /* Telit LE922A6 in MBIM composition */ + { USB_DEVICE_AND_INTERFACE_INFO(0x1bc7, 0x1041, USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&cdc_mbim_info_avoid_altsetting_toggle, + }, + /* default entry */ { USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE), .driver_info = (unsigned long)&cdc_mbim_info_zlp, diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index 877c9516e781..afbfc0f656f3 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -839,11 +839,18 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_ iface_no = ctx->data->cur_altsetting->desc.bInterfaceNumber; + /* Device-specific flags */ + ctx->drvflags = drvflags; + /* Reset data interface. Some devices will not reset properly * unless they are configured first. Toggle the altsetting to - * force a reset + * force a reset. + * Some other devices do not work properly with this procedure + * that can be avoided using quirk CDC_MBIM_FLAG_AVOID_ALTSETTING_TOGGLE */ - usb_set_interface(dev->udev, iface_no, data_altsetting); + if (!(ctx->drvflags & CDC_MBIM_FLAG_AVOID_ALTSETTING_TOGGLE)) + usb_set_interface(dev->udev, iface_no, data_altsetting); + temp = usb_set_interface(dev->udev, iface_no, 0); if (temp) { dev_dbg(&intf->dev, "set interface failed\n"); @@ -890,9 +897,6 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_ /* finish setting up the device specific data */ cdc_ncm_setup(dev); - /* Device-specific flags */ - ctx->drvflags = drvflags; - /* Allocate the delayed NDP if needed. */ if (ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END) { ctx->delayed_ndp16 = kzalloc(ctx->max_ndp_size, GFP_KERNEL); diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index db558b8b32fe..f33460cec79f 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -3395,6 +3395,7 @@ static int lan78xx_probe(struct usb_interface *intf, if (buf) { dev->urb_intr = usb_alloc_urb(0, GFP_KERNEL); if (!dev->urb_intr) { + ret = -ENOMEM; kfree(buf); goto out3; } else { diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 3ff76c6db4f6..6fe1cdb0174f 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -894,6 +894,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1bbb, 0x0203, 2)}, /* Alcatel L800MA */ {QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */ {QMI_FIXED_INTF(0x2357, 0x9000, 4)}, /* TP-LINK MA260 */ + {QMI_QUIRK_SET_DTR(0x1bc7, 0x1040, 2)}, /* Telit LE922A */ {QMI_FIXED_INTF(0x1bc7, 0x1200, 5)}, /* Telit LE920 */ {QMI_FIXED_INTF(0x1bc7, 0x1201, 2)}, /* Telit LE920 */ {QMI_FIXED_INTF(0x1c9e, 0x9b01, 3)}, /* XS Stick W100-2 from 4G Systems */ diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index fd8b1e62301f..cbf1c613c67a 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -969,12 +969,17 @@ static int virtnet_set_mac_address(struct net_device *dev, void *p) struct virtnet_info *vi = netdev_priv(dev); struct virtio_device *vdev = vi->vdev; int ret; - struct sockaddr *addr = p; + struct sockaddr *addr; struct scatterlist sg; - ret = eth_prepare_mac_addr_change(dev, p); + addr = kmalloc(sizeof(*addr), GFP_KERNEL); + if (!addr) + return -ENOMEM; + memcpy(addr, p, sizeof(*addr)); + + ret = eth_prepare_mac_addr_change(dev, addr); if (ret) - return ret; + goto out; if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_MAC_ADDR)) { sg_init_one(&sg, addr->sa_data, dev->addr_len); @@ -982,7 +987,8 @@ static int virtnet_set_mac_address(struct net_device *dev, void *p) VIRTIO_NET_CTRL_MAC_ADDR_SET, &sg)) { dev_warn(&vdev->dev, "Failed to set mac address by vq command.\n"); - return -EINVAL; + ret = -EINVAL; + goto out; } } else if (virtio_has_feature(vdev, VIRTIO_NET_F_MAC) && !virtio_has_feature(vdev, VIRTIO_F_VERSION_1)) { @@ -996,8 +1002,11 @@ static int virtnet_set_mac_address(struct net_device *dev, void *p) } eth_commit_mac_addr_change(dev, p); + ret = 0; - return 0; +out: + kfree(addr); + return ret; } static struct rtnl_link_stats64 *virtnet_stats(struct net_device *dev, @@ -1497,6 +1506,11 @@ static void virtnet_free_queues(struct virtnet_info *vi) netif_napi_del(&vi->rq[i].napi); } + /* We called napi_hash_del() before netif_napi_del(), + * we need to respect an RCU grace period before freeing vi->rq + */ + synchronize_net(); + kfree(vi->rq); kfree(vi->sq); } diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 24532cdebb00..2ba01ca02c9c 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -611,6 +611,7 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan, struct vxlan_rdst *rd = NULL; struct vxlan_fdb *f; int notify = 0; + int rc; f = __vxlan_find_mac(vxlan, mac); if (f) { @@ -641,8 +642,7 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan, if ((flags & NLM_F_APPEND) && (is_multicast_ether_addr(f->eth_addr) || is_zero_ether_addr(f->eth_addr))) { - int rc = vxlan_fdb_append(f, ip, port, vni, ifindex, - &rd); + rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd); if (rc < 0) return rc; @@ -673,7 +673,11 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan, INIT_LIST_HEAD(&f->remotes); memcpy(f->eth_addr, mac, ETH_ALEN); - vxlan_fdb_append(f, ip, port, vni, ifindex, &rd); + rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd); + if (rc < 0) { + kfree(f); + return rc; + } ++vxlan->addrcnt; hlist_add_head_rcu(&f->hlist, diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 431f13b4faf6..d3bad5779376 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -826,7 +826,7 @@ static void mac80211_hwsim_set_tsf(struct ieee80211_hw *hw, data->bcn_delta = do_div(delta, bcn_int); } else { data->tsf_offset -= delta; - data->bcn_delta = -do_div(delta, bcn_int); + data->bcn_delta = -(s64)do_div(delta, bcn_int); } } diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c index 39ce76ad00bc..16241d21727b 100644 --- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c +++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c @@ -2222,8 +2222,9 @@ done: is_scanning_required = 1; } else { mwifiex_dbg(priv->adapter, MSG, - "info: trying to associate to '%s' bssid %pM\n", - (char *)req_ssid.ssid, bss->bssid); + "info: trying to associate to '%.*s' bssid %pM\n", + req_ssid.ssid_len, (char *)req_ssid.ssid, + bss->bssid); memcpy(&priv->cfg_bssid, bss->bssid, ETH_ALEN); break; } @@ -2283,8 +2284,8 @@ mwifiex_cfg80211_connect(struct wiphy *wiphy, struct net_device *dev, } mwifiex_dbg(adapter, INFO, - "info: Trying to associate to %s and bssid %pM\n", - (char *)sme->ssid, sme->bssid); + "info: Trying to associate to %.*s and bssid %pM\n", + (int)sme->ssid_len, (char *)sme->ssid, sme->bssid); if (!mwifiex_stop_bg_scan(priv)) cfg80211_sched_scan_stopped_rtnl(priv->wdev.wiphy); @@ -2417,8 +2418,8 @@ mwifiex_cfg80211_join_ibss(struct wiphy *wiphy, struct net_device *dev, } mwifiex_dbg(priv->adapter, MSG, - "info: trying to join to %s and bssid %pM\n", - (char *)params->ssid, params->bssid); + "info: trying to join to %.*s and bssid %pM\n", + params->ssid_len, (char *)params->ssid, params->bssid); mwifiex_set_ibss_params(priv, params); diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index a8b6949a8778..23d4a1728cdf 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -715,7 +715,7 @@ EXPORT_SYMBOL_GPL(nd_cmd_in_size); u32 nd_cmd_out_size(struct nvdimm *nvdimm, int cmd, const struct nd_cmd_desc *desc, int idx, const u32 *in_field, - const u32 *out_field) + const u32 *out_field, unsigned long remainder) { if (idx >= desc->out_num) return UINT_MAX; @@ -727,9 +727,24 @@ u32 nd_cmd_out_size(struct nvdimm *nvdimm, int cmd, return in_field[1]; else if (nvdimm && cmd == ND_CMD_VENDOR && idx == 2) return out_field[1]; - else if (!nvdimm && cmd == ND_CMD_ARS_STATUS && idx == 2) - return out_field[1] - 8; - else if (cmd == ND_CMD_CALL) { + else if (!nvdimm && cmd == ND_CMD_ARS_STATUS && idx == 2) { + /* + * Per table 9-276 ARS Data in ACPI 6.1, out_field[1] is + * "Size of Output Buffer in bytes, including this + * field." + */ + if (out_field[1] < 4) + return 0; + /* + * ACPI 6.1 is ambiguous if 'status' is included in the + * output size. If we encounter an output size that + * overshoots the remainder by 4 bytes, assume it was + * including 'status'. + */ + if (out_field[1] - 8 == remainder) + return remainder; + return out_field[1] - 4; + } else if (cmd == ND_CMD_CALL) { struct nd_cmd_pkg *pkg = (struct nd_cmd_pkg *) in_field; return pkg->nd_size_out; @@ -876,7 +891,7 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, /* process an output envelope */ for (i = 0; i < desc->out_num; i++) { u32 out_size = nd_cmd_out_size(nvdimm, cmd, desc, i, - (u32 *) in_env, (u32 *) out_env); + (u32 *) in_env, (u32 *) out_env, 0); u32 copy; if (out_size == UINT_MAX) { diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index b470f7e3521d..262281bd68fa 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -292,6 +292,7 @@ struct phy_device *of_phy_find_device(struct device_node *phy_np) mdiodev = to_mdio_device(d); if (mdiodev->flags & MDIO_DEVICE_FLAG_PHY) return to_phy_device(d); + put_device(d); } return NULL; @@ -456,8 +457,11 @@ int of_phy_register_fixed_link(struct device_node *np) status.link = 1; status.duplex = of_property_read_bool(fixed_link_node, "full-duplex"); - if (of_property_read_u32(fixed_link_node, "speed", &status.speed)) + if (of_property_read_u32(fixed_link_node, "speed", + &status.speed)) { + of_node_put(fixed_link_node); return -EINVAL; + } status.pause = of_property_read_bool(fixed_link_node, "pause"); status.asym_pause = of_property_read_bool(fixed_link_node, "asym-pause"); @@ -486,3 +490,18 @@ int of_phy_register_fixed_link(struct device_node *np) return -ENODEV; } EXPORT_SYMBOL(of_phy_register_fixed_link); + +void of_phy_deregister_fixed_link(struct device_node *np) +{ + struct phy_device *phydev; + + phydev = of_phy_find_device(np); + if (!phydev) + return; + + fixed_phy_unregister(phydev); + + put_device(&phydev->mdio.dev); /* of_phy_find_device() */ + phy_device_free(phydev); /* fixed_phy_register() */ +} +EXPORT_SYMBOL(of_phy_deregister_fixed_link); diff --git a/drivers/pci/host/pcie-designware-plat.c b/drivers/pci/host/pcie-designware-plat.c index 8df6312ed300..1a02038c4640 100644 --- a/drivers/pci/host/pcie-designware-plat.c +++ b/drivers/pci/host/pcie-designware-plat.c @@ -3,7 +3,7 @@ * * Copyright (C) 2015-2016 Synopsys, Inc. (www.synopsys.com) * - * Authors: Joao Pinto <jpmpinto@gmail.com> + * Authors: Joao Pinto <Joao.Pinto@synopsys.com> * * 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 diff --git a/drivers/pci/pcie/aer/aer_inject.c b/drivers/pci/pcie/aer/aer_inject.c index db553dc22c8e..2b6a59266689 100644 --- a/drivers/pci/pcie/aer/aer_inject.c +++ b/drivers/pci/pcie/aer/aer_inject.c @@ -307,20 +307,6 @@ out: return 0; } -static struct pci_dev *pcie_find_root_port(struct pci_dev *dev) -{ - while (1) { - if (!pci_is_pcie(dev)) - break; - if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT) - return dev; - if (!dev->bus->self) - break; - dev = dev->bus->self; - } - return NULL; -} - static int find_aer_device_iter(struct device *device, void *data) { struct pcie_device **result = data; diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index ab002671fa60..104c46d53121 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -1439,6 +1439,21 @@ static void program_hpp_type1(struct pci_dev *dev, struct hpp_type1 *hpp) dev_warn(&dev->dev, "PCI-X settings not supported\n"); } +static bool pcie_root_rcb_set(struct pci_dev *dev) +{ + struct pci_dev *rp = pcie_find_root_port(dev); + u16 lnkctl; + + if (!rp) + return false; + + pcie_capability_read_word(rp, PCI_EXP_LNKCTL, &lnkctl); + if (lnkctl & PCI_EXP_LNKCTL_RCB) + return true; + + return false; +} + static void program_hpp_type2(struct pci_dev *dev, struct hpp_type2 *hpp) { int pos; @@ -1468,9 +1483,20 @@ static void program_hpp_type2(struct pci_dev *dev, struct hpp_type2 *hpp) ~hpp->pci_exp_devctl_and, hpp->pci_exp_devctl_or); /* Initialize Link Control Register */ - if (pcie_cap_has_lnkctl(dev)) + if (pcie_cap_has_lnkctl(dev)) { + + /* + * If the Root Port supports Read Completion Boundary of + * 128, set RCB to 128. Otherwise, clear it. + */ + hpp->pci_exp_lnkctl_and |= PCI_EXP_LNKCTL_RCB; + hpp->pci_exp_lnkctl_or &= ~PCI_EXP_LNKCTL_RCB; + if (pcie_root_rcb_set(dev)) + hpp->pci_exp_lnkctl_or |= PCI_EXP_LNKCTL_RCB; + pcie_capability_clear_and_set_word(dev, PCI_EXP_LNKCTL, ~hpp->pci_exp_lnkctl_and, hpp->pci_exp_lnkctl_or); + } /* Find Advanced Error Reporting Enhanced Capability */ pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR); diff --git a/drivers/phy/phy-twl4030-usb.c b/drivers/phy/phy-twl4030-usb.c index 87e6334eab93..547ca7b3f098 100644 --- a/drivers/phy/phy-twl4030-usb.c +++ b/drivers/phy/phy-twl4030-usb.c @@ -459,8 +459,6 @@ static int twl4030_phy_power_off(struct phy *phy) struct twl4030_usb *twl = phy_get_drvdata(phy); dev_dbg(twl->dev, "%s\n", __func__); - pm_runtime_mark_last_busy(twl->dev); - pm_runtime_put_autosuspend(twl->dev); return 0; } @@ -472,6 +470,8 @@ static int twl4030_phy_power_on(struct phy *phy) dev_dbg(twl->dev, "%s\n", __func__); pm_runtime_get_sync(twl->dev); schedule_delayed_work(&twl->id_workaround_work, HZ); + pm_runtime_mark_last_busy(twl->dev); + pm_runtime_put_autosuspend(twl->dev); return 0; } diff --git a/drivers/power/avs/rockchip-io-domain.c b/drivers/power/avs/rockchip-io-domain.c index 01b6d3f9b8fb..56bce1908be2 100644 --- a/drivers/power/avs/rockchip-io-domain.c +++ b/drivers/power/avs/rockchip-io-domain.c @@ -143,7 +143,7 @@ static int rockchip_iodomain_notify(struct notifier_block *nb, if (ret && event == REGULATOR_EVENT_PRE_VOLTAGE_CHANGE) return NOTIFY_BAD; - dev_info(supply->iod->dev, "Setting to %d done\n", uV); + dev_dbg(supply->iod->dev, "Setting to %d done\n", uV); return NOTIFY_OK; } diff --git a/drivers/powercap/intel_rapl.c b/drivers/powercap/intel_rapl.c index 243b233ff31b..9a25110c4a46 100644 --- a/drivers/powercap/intel_rapl.c +++ b/drivers/powercap/intel_rapl.c @@ -189,14 +189,13 @@ struct rapl_package { unsigned int time_unit; struct rapl_domain *domains; /* array of domains, sized at runtime */ struct powercap_zone *power_zone; /* keep track of parent zone */ - int nr_cpus; /* active cpus on the package, topology info is lost during - * cpu hotplug. so we have to track ourselves. - */ unsigned long power_limit_irq; /* keep track of package power limit * notify interrupt enable status. */ struct list_head plist; int lead_cpu; /* one active cpu per package for access */ + /* Track active cpus */ + struct cpumask cpumask; }; struct rapl_defaults { @@ -275,18 +274,6 @@ static struct rapl_package *find_package_by_id(int id) return NULL; } -/* caller must hold cpu hotplug lock */ -static void rapl_cleanup_data(void) -{ - struct rapl_package *p, *tmp; - - list_for_each_entry_safe(p, tmp, &rapl_packages, plist) { - kfree(p->domains); - list_del(&p->plist); - kfree(p); - } -} - static int get_energy_counter(struct powercap_zone *power_zone, u64 *energy_raw) { struct rapl_domain *rd; @@ -442,6 +429,7 @@ static int contraint_to_pl(struct rapl_domain *rd, int cid) return i; } } + pr_err("Cannot find matching power limit for constraint %d\n", cid); return -EINVAL; } @@ -457,6 +445,10 @@ static int set_power_limit(struct powercap_zone *power_zone, int cid, get_online_cpus(); rd = power_zone_to_rapl_domain(power_zone); id = contraint_to_pl(rd, cid); + if (id < 0) { + ret = id; + goto set_exit; + } rp = rd->rp; @@ -496,6 +488,11 @@ static int get_current_power_limit(struct powercap_zone *power_zone, int cid, get_online_cpus(); rd = power_zone_to_rapl_domain(power_zone); id = contraint_to_pl(rd, cid); + if (id < 0) { + ret = id; + goto get_exit; + } + switch (rd->rpl[id].prim_id) { case PL1_ENABLE: prim = POWER_LIMIT1; @@ -512,6 +509,7 @@ static int get_current_power_limit(struct powercap_zone *power_zone, int cid, else *data = val; +get_exit: put_online_cpus(); return ret; @@ -527,6 +525,10 @@ static int set_time_window(struct powercap_zone *power_zone, int cid, get_online_cpus(); rd = power_zone_to_rapl_domain(power_zone); id = contraint_to_pl(rd, cid); + if (id < 0) { + ret = id; + goto set_time_exit; + } switch (rd->rpl[id].prim_id) { case PL1_ENABLE: @@ -538,6 +540,8 @@ static int set_time_window(struct powercap_zone *power_zone, int cid, default: ret = -EINVAL; } + +set_time_exit: put_online_cpus(); return ret; } @@ -552,6 +556,10 @@ static int get_time_window(struct powercap_zone *power_zone, int cid, u64 *data) get_online_cpus(); rd = power_zone_to_rapl_domain(power_zone); id = contraint_to_pl(rd, cid); + if (id < 0) { + ret = id; + goto get_time_exit; + } switch (rd->rpl[id].prim_id) { case PL1_ENABLE: @@ -566,6 +574,8 @@ static int get_time_window(struct powercap_zone *power_zone, int cid, u64 *data) } if (!ret) *data = val; + +get_time_exit: put_online_cpus(); return ret; @@ -707,7 +717,7 @@ static u64 rapl_unit_xlate(struct rapl_domain *rd, enum unit_type type, case ENERGY_UNIT: scale = ENERGY_UNIT_SCALE; /* per domain unit takes precedence */ - if (rd && rd->domain_energy_unit) + if (rd->domain_energy_unit) units = rd->domain_energy_unit; else units = rp->energy_unit; @@ -976,10 +986,20 @@ static void package_power_limit_irq_save(struct rapl_package *rp) smp_call_function_single(rp->lead_cpu, power_limit_irq_save_cpu, rp, 1); } -static void power_limit_irq_restore_cpu(void *info) +/* + * Restore per package power limit interrupt enable state. Called from cpu + * hotplug code on package removal. + */ +static void package_power_limit_irq_restore(struct rapl_package *rp) { - u32 l, h = 0; - struct rapl_package *rp = (struct rapl_package *)info; + u32 l, h; + + if (!boot_cpu_has(X86_FEATURE_PTS) || !boot_cpu_has(X86_FEATURE_PLN)) + return; + + /* irq enable state not saved, nothing to restore */ + if (!(rp->power_limit_irq & PACKAGE_PLN_INT_SAVED)) + return; rdmsr_safe(MSR_IA32_PACKAGE_THERM_INTERRUPT, &l, &h); @@ -991,19 +1011,6 @@ static void power_limit_irq_restore_cpu(void *info) wrmsr_safe(MSR_IA32_PACKAGE_THERM_INTERRUPT, l, h); } -/* restore per package power limit interrupt enable state */ -static void package_power_limit_irq_restore(struct rapl_package *rp) -{ - if (!boot_cpu_has(X86_FEATURE_PTS) || !boot_cpu_has(X86_FEATURE_PLN)) - return; - - /* irq enable state not saved, nothing to restore */ - if (!(rp->power_limit_irq & PACKAGE_PLN_INT_SAVED)) - return; - - smp_call_function_single(rp->lead_cpu, power_limit_irq_restore_cpu, rp, 1); -} - static void set_floor_freq_default(struct rapl_domain *rd, bool mode) { int nr_powerlimit = find_nr_power_limit(rd); @@ -1160,84 +1167,49 @@ static const struct x86_cpu_id rapl_ids[] __initconst = { RAPL_CPU(INTEL_FAM6_ATOM_DENVERTON, rapl_defaults_core), RAPL_CPU(INTEL_FAM6_XEON_PHI_KNL, rapl_defaults_hsw_server), + RAPL_CPU(INTEL_FAM6_XEON_PHI_KNM, rapl_defaults_hsw_server), {} }; MODULE_DEVICE_TABLE(x86cpu, rapl_ids); -/* read once for all raw primitive data for all packages, domains */ -static void rapl_update_domain_data(void) +/* Read once for all raw primitive data for domains */ +static void rapl_update_domain_data(struct rapl_package *rp) { int dmn, prim; u64 val; - struct rapl_package *rp; - list_for_each_entry(rp, &rapl_packages, plist) { - for (dmn = 0; dmn < rp->nr_domains; dmn++) { - pr_debug("update package %d domain %s data\n", rp->id, - rp->domains[dmn].name); - /* exclude non-raw primitives */ - for (prim = 0; prim < NR_RAW_PRIMITIVES; prim++) - if (!rapl_read_data_raw(&rp->domains[dmn], prim, - rpi[prim].unit, - &val)) - rp->domains[dmn].rdd.primitives[prim] = - val; + for (dmn = 0; dmn < rp->nr_domains; dmn++) { + pr_debug("update package %d domain %s data\n", rp->id, + rp->domains[dmn].name); + /* exclude non-raw primitives */ + for (prim = 0; prim < NR_RAW_PRIMITIVES; prim++) { + if (!rapl_read_data_raw(&rp->domains[dmn], prim, + rpi[prim].unit, &val)) + rp->domains[dmn].rdd.primitives[prim] = val; } } } -static int rapl_unregister_powercap(void) +static void rapl_unregister_powercap(void) { - struct rapl_package *rp; - struct rapl_domain *rd, *rd_package = NULL; - - /* unregister all active rapl packages from the powercap layer, - * hotplug lock held - */ - list_for_each_entry(rp, &rapl_packages, plist) { - package_power_limit_irq_restore(rp); - - for (rd = rp->domains; rd < rp->domains + rp->nr_domains; - rd++) { - pr_debug("remove package, undo power limit on %d: %s\n", - rp->id, rd->name); - rapl_write_data_raw(rd, PL1_ENABLE, 0); - rapl_write_data_raw(rd, PL1_CLAMP, 0); - if (find_nr_power_limit(rd) > 1) { - rapl_write_data_raw(rd, PL2_ENABLE, 0); - rapl_write_data_raw(rd, PL2_CLAMP, 0); - } - if (rd->id == RAPL_DOMAIN_PACKAGE) { - rd_package = rd; - continue; - } - powercap_unregister_zone(control_type, &rd->power_zone); - } - /* do the package zone last */ - if (rd_package) - powercap_unregister_zone(control_type, - &rd_package->power_zone); - } - if (platform_rapl_domain) { powercap_unregister_zone(control_type, &platform_rapl_domain->power_zone); kfree(platform_rapl_domain); } - powercap_unregister_control_type(control_type); - - return 0; } static int rapl_package_register_powercap(struct rapl_package *rp) { struct rapl_domain *rd; - int ret = 0; char dev_name[17]; /* max domain name = 7 + 1 + 8 for int + 1 for null*/ struct powercap_zone *power_zone = NULL; - int nr_pl; + int nr_pl, ret;; + + /* Update the domain data of the new package */ + rapl_update_domain_data(rp); /* first we register package domain as the parent zone*/ for (rd = rp->domains; rd < rp->domains + rp->nr_domains; rd++) { @@ -1257,8 +1229,7 @@ static int rapl_package_register_powercap(struct rapl_package *rp) if (IS_ERR(power_zone)) { pr_debug("failed to register package, %d\n", rp->id); - ret = PTR_ERR(power_zone); - goto exit_package; + return PTR_ERR(power_zone); } /* track parent zone in per package/socket data */ rp->power_zone = power_zone; @@ -1268,8 +1239,7 @@ static int rapl_package_register_powercap(struct rapl_package *rp) } if (!power_zone) { pr_err("no package domain found, unknown topology!\n"); - ret = -ENODEV; - goto exit_package; + return -ENODEV; } /* now register domains as children of the socket/package*/ for (rd = rp->domains; rd < rp->domains + rp->nr_domains; rd++) { @@ -1290,11 +1260,11 @@ static int rapl_package_register_powercap(struct rapl_package *rp) goto err_cleanup; } } + return 0; -exit_package: - return ret; err_cleanup: - /* clean up previously initialized domains within the package if we + /* + * Clean up previously initialized domains within the package if we * failed after the first domain setup. */ while (--rd >= rp->domains) { @@ -1305,7 +1275,7 @@ err_cleanup: return ret; } -static int rapl_register_psys(void) +static int __init rapl_register_psys(void) { struct rapl_domain *rd; struct powercap_zone *power_zone; @@ -1346,40 +1316,14 @@ static int rapl_register_psys(void) return 0; } -static int rapl_register_powercap(void) +static int __init rapl_register_powercap(void) { - struct rapl_domain *rd; - struct rapl_package *rp; - int ret = 0; - control_type = powercap_register_control_type(NULL, "intel-rapl", NULL); if (IS_ERR(control_type)) { pr_debug("failed to register powercap control_type.\n"); return PTR_ERR(control_type); } - /* read the initial data */ - rapl_update_domain_data(); - list_for_each_entry(rp, &rapl_packages, plist) - if (rapl_package_register_powercap(rp)) - goto err_cleanup_package; - - /* Don't bail out if PSys is not supported */ - rapl_register_psys(); - - return ret; - -err_cleanup_package: - /* clean up previously initialized packages */ - list_for_each_entry_continue_reverse(rp, &rapl_packages, plist) { - for (rd = rp->domains; rd < rp->domains + rp->nr_domains; - rd++) { - pr_debug("unregister zone/package %d, %s domain\n", - rp->id, rd->name); - powercap_unregister_zone(control_type, &rd->power_zone); - } - } - - return ret; + return 0; } static int rapl_check_domain(int cpu, int domain) @@ -1452,9 +1396,8 @@ static void rapl_detect_powerlimit(struct rapl_domain *rd) */ static int rapl_detect_domains(struct rapl_package *rp, int cpu) { - int i; - int ret = 0; struct rapl_domain *rd; + int i; for (i = 0; i < RAPL_DOMAIN_MAX; i++) { /* use physical package id to read counters */ @@ -1466,84 +1409,20 @@ static int rapl_detect_domains(struct rapl_package *rp, int cpu) rp->nr_domains = bitmap_weight(&rp->domain_map, RAPL_DOMAIN_MAX); if (!rp->nr_domains) { pr_debug("no valid rapl domains found in package %d\n", rp->id); - ret = -ENODEV; - goto done; + return -ENODEV; } pr_debug("found %d domains on package %d\n", rp->nr_domains, rp->id); rp->domains = kcalloc(rp->nr_domains + 1, sizeof(struct rapl_domain), GFP_KERNEL); - if (!rp->domains) { - ret = -ENOMEM; - goto done; - } + if (!rp->domains) + return -ENOMEM; + rapl_init_domains(rp); for (rd = rp->domains; rd < rp->domains + rp->nr_domains; rd++) rapl_detect_powerlimit(rd); - - -done: - return ret; -} - -static bool is_package_new(int package) -{ - struct rapl_package *rp; - - /* caller prevents cpu hotplug, there will be no new packages added - * or deleted while traversing the package list, no need for locking. - */ - list_for_each_entry(rp, &rapl_packages, plist) - if (package == rp->id) - return false; - - return true; -} - -/* RAPL interface can be made of a two-level hierarchy: package level and domain - * level. We first detect the number of packages then domains of each package. - * We have to consider the possiblity of CPU online/offline due to hotplug and - * other scenarios. - */ -static int rapl_detect_topology(void) -{ - int i; - int phy_package_id; - struct rapl_package *new_package, *rp; - - for_each_online_cpu(i) { - phy_package_id = topology_physical_package_id(i); - if (is_package_new(phy_package_id)) { - new_package = kzalloc(sizeof(*rp), GFP_KERNEL); - if (!new_package) { - rapl_cleanup_data(); - return -ENOMEM; - } - /* add the new package to the list */ - new_package->id = phy_package_id; - new_package->nr_cpus = 1; - /* use the first active cpu of the package to access */ - new_package->lead_cpu = i; - /* check if the package contains valid domains */ - if (rapl_detect_domains(new_package, i) || - rapl_defaults->check_unit(new_package, i)) { - kfree(new_package->domains); - kfree(new_package); - /* free up the packages already initialized */ - rapl_cleanup_data(); - return -ENODEV; - } - INIT_LIST_HEAD(&new_package->plist); - list_add(&new_package->plist, &rapl_packages); - } else { - rp = find_package_by_id(phy_package_id); - if (rp) - ++rp->nr_cpus; - } - } - return 0; } @@ -1552,12 +1431,21 @@ static void rapl_remove_package(struct rapl_package *rp) { struct rapl_domain *rd, *rd_package = NULL; + package_power_limit_irq_restore(rp); + for (rd = rp->domains; rd < rp->domains + rp->nr_domains; rd++) { + rapl_write_data_raw(rd, PL1_ENABLE, 0); + rapl_write_data_raw(rd, PL1_CLAMP, 0); + if (find_nr_power_limit(rd) > 1) { + rapl_write_data_raw(rd, PL2_ENABLE, 0); + rapl_write_data_raw(rd, PL2_CLAMP, 0); + } if (rd->id == RAPL_DOMAIN_PACKAGE) { rd_package = rd; continue; } - pr_debug("remove package %d, %s domain\n", rp->id, rd->name); + pr_debug("remove package, undo power limit on %d: %s\n", + rp->id, rd->name); powercap_unregister_zone(control_type, &rd->power_zone); } /* do parent zone last */ @@ -1567,20 +1455,17 @@ static void rapl_remove_package(struct rapl_package *rp) } /* called from CPU hotplug notifier, hotplug lock held */ -static int rapl_add_package(int cpu) +static struct rapl_package *rapl_add_package(int cpu, int pkgid) { - int ret = 0; - int phy_package_id; struct rapl_package *rp; + int ret; - phy_package_id = topology_physical_package_id(cpu); rp = kzalloc(sizeof(struct rapl_package), GFP_KERNEL); if (!rp) - return -ENOMEM; + return ERR_PTR(-ENOMEM); /* add the new package to the list */ - rp->id = phy_package_id; - rp->nr_cpus = 1; + rp->id = pkgid; rp->lead_cpu = cpu; /* check if the package contains valid domains */ @@ -1589,17 +1474,17 @@ static int rapl_add_package(int cpu) ret = -ENODEV; goto err_free_package; } - if (!rapl_package_register_powercap(rp)) { + ret = rapl_package_register_powercap(rp); + if (!ret) { INIT_LIST_HEAD(&rp->plist); list_add(&rp->plist, &rapl_packages); - return ret; + return rp; } err_free_package: kfree(rp->domains); kfree(rp); - - return ret; + return ERR_PTR(ret); } /* Handles CPU hotplug on multi-socket systems. @@ -1609,55 +1494,46 @@ err_free_package: * associated domains. Cooling devices are handled accordingly at * per-domain level. */ -static int rapl_cpu_callback(struct notifier_block *nfb, - unsigned long action, void *hcpu) +static int rapl_cpu_online(unsigned int cpu) { - unsigned long cpu = (unsigned long)hcpu; - int phy_package_id; + int pkgid = topology_physical_package_id(cpu); struct rapl_package *rp; - int lead_cpu; - phy_package_id = topology_physical_package_id(cpu); - switch (action) { - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - case CPU_DOWN_FAILED: - case CPU_DOWN_FAILED_FROZEN: - rp = find_package_by_id(phy_package_id); - if (rp) - ++rp->nr_cpus; - else - rapl_add_package(cpu); - break; - case CPU_DOWN_PREPARE: - case CPU_DOWN_PREPARE_FROZEN: - rp = find_package_by_id(phy_package_id); - if (!rp) - break; - if (--rp->nr_cpus == 0) - rapl_remove_package(rp); - else if (cpu == rp->lead_cpu) { - /* choose another active cpu in the package */ - lead_cpu = cpumask_any_but(topology_core_cpumask(cpu), cpu); - if (lead_cpu < nr_cpu_ids) - rp->lead_cpu = lead_cpu; - else /* should never go here */ - pr_err("no active cpu available for package %d\n", - phy_package_id); - } + rp = find_package_by_id(pkgid); + if (!rp) { + rp = rapl_add_package(cpu, pkgid); + if (IS_ERR(rp)) + return PTR_ERR(rp); } + cpumask_set_cpu(cpu, &rp->cpumask); + return 0; +} + +static int rapl_cpu_down_prep(unsigned int cpu) +{ + int pkgid = topology_physical_package_id(cpu); + struct rapl_package *rp; + int lead_cpu; + + rp = find_package_by_id(pkgid); + if (!rp) + return 0; - return NOTIFY_OK; + cpumask_clear_cpu(cpu, &rp->cpumask); + lead_cpu = cpumask_first(&rp->cpumask); + if (lead_cpu >= nr_cpu_ids) + rapl_remove_package(rp); + else if (rp->lead_cpu == cpu) + rp->lead_cpu = lead_cpu; + return 0; } -static struct notifier_block rapl_cpu_notifier = { - .notifier_call = rapl_cpu_callback, -}; +static enum cpuhp_state pcap_rapl_online; static int __init rapl_init(void) { - int ret = 0; const struct x86_cpu_id *id; + int ret; id = x86_match_cpu(rapl_ids); if (!id) { @@ -1669,36 +1545,29 @@ static int __init rapl_init(void) rapl_defaults = (struct rapl_defaults *)id->driver_data; - cpu_notifier_register_begin(); - - /* prevent CPU hotplug during detection */ - get_online_cpus(); - ret = rapl_detect_topology(); + ret = rapl_register_powercap(); if (ret) - goto done; + return ret; - if (rapl_register_powercap()) { - rapl_cleanup_data(); - ret = -ENODEV; - goto done; - } - __register_hotcpu_notifier(&rapl_cpu_notifier); -done: - put_online_cpus(); - cpu_notifier_register_done(); + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "powercap/rapl:online", + rapl_cpu_online, rapl_cpu_down_prep); + if (ret < 0) + goto err_unreg; + pcap_rapl_online = ret; + + /* Don't bail out if PSys is not supported */ + rapl_register_psys(); + return 0; +err_unreg: + rapl_unregister_powercap(); return ret; } static void __exit rapl_exit(void) { - cpu_notifier_register_begin(); - get_online_cpus(); - __unregister_hotcpu_notifier(&rapl_cpu_notifier); + cpuhp_remove_state(pcap_rapl_online); rapl_unregister_powercap(); - rapl_cleanup_data(); - put_online_cpus(); - cpu_notifier_register_done(); } module_init(rapl_init); diff --git a/drivers/pwm/pwm-meson.c b/drivers/pwm/pwm-meson.c index 381871b2bb46..9d5bd7d5c610 100644 --- a/drivers/pwm/pwm-meson.c +++ b/drivers/pwm/pwm-meson.c @@ -474,6 +474,7 @@ static int meson_pwm_probe(struct platform_device *pdev) if (IS_ERR(meson->base)) return PTR_ERR(meson->base); + spin_lock_init(&meson->lock); meson->chip.dev = &pdev->dev; meson->chip.ops = &meson_pwm_ops; meson->chip.base = -1; diff --git a/drivers/pwm/sysfs.c b/drivers/pwm/sysfs.c index 0296d8178ae2..a813239300c3 100644 --- a/drivers/pwm/sysfs.c +++ b/drivers/pwm/sysfs.c @@ -425,6 +425,8 @@ void pwmchip_sysfs_unexport_children(struct pwm_chip *chip) if (test_bit(PWMF_EXPORTED, &pwm->flags)) pwm_unexport_child(parent, pwm); } + + put_device(parent); } static int __init pwm_sysfs_init(void) diff --git a/drivers/scsi/be2iscsi/be_mgmt.c b/drivers/scsi/be2iscsi/be_mgmt.c index aebc4ddb3060..ac05317bba7f 100644 --- a/drivers/scsi/be2iscsi/be_mgmt.c +++ b/drivers/scsi/be2iscsi/be_mgmt.c @@ -1083,7 +1083,7 @@ unsigned int beiscsi_boot_get_sinfo(struct beiscsi_hba *phba) nonemb_cmd = &phba->boot_struct.nonemb_cmd; nonemb_cmd->size = sizeof(*resp); nonemb_cmd->va = pci_alloc_consistent(phba->ctrl.pdev, - sizeof(nonemb_cmd->size), + nonemb_cmd->size, &nonemb_cmd->dma); if (!nonemb_cmd->va) { mutex_unlock(&ctrl->mbox_lock); diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index d007ec18179a..a1d6ab76a514 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -2009,7 +2009,7 @@ static struct hpsa_scsi_dev_t *lookup_hpsa_scsi_dev(struct ctlr_info *h, static int hpsa_slave_alloc(struct scsi_device *sdev) { - struct hpsa_scsi_dev_t *sd; + struct hpsa_scsi_dev_t *sd = NULL; unsigned long flags; struct ctlr_info *h; @@ -2026,7 +2026,8 @@ static int hpsa_slave_alloc(struct scsi_device *sdev) sd->target = sdev_id(sdev); sd->lun = sdev->lun; } - } else + } + if (!sd) sd = lookup_hpsa_scsi_dev(h, sdev_channel(sdev), sdev_id(sdev), sdev->lun); @@ -3840,6 +3841,7 @@ static int hpsa_update_device_info(struct ctlr_info *h, sizeof(this_device->vendor)); memcpy(this_device->model, &inq_buff[16], sizeof(this_device->model)); + this_device->rev = inq_buff[2]; memset(this_device->device_id, 0, sizeof(this_device->device_id)); if (hpsa_get_device_id(h, scsi3addr, this_device->device_id, 8, @@ -3929,10 +3931,14 @@ static void figure_bus_target_lun(struct ctlr_info *h, if (!is_logical_dev_addr_mode(lunaddrbytes)) { /* physical device, target and lun filled in later */ - if (is_hba_lunid(lunaddrbytes)) + if (is_hba_lunid(lunaddrbytes)) { + int bus = HPSA_HBA_BUS; + + if (!device->rev) + bus = HPSA_LEGACY_HBA_BUS; hpsa_set_bus_target_lun(device, - HPSA_HBA_BUS, 0, lunid & 0x3fff); - else + bus, 0, lunid & 0x3fff); + } else /* defer target, lun assignment for physical devices */ hpsa_set_bus_target_lun(device, HPSA_PHYSICAL_DEVICE_BUS, -1, -1); diff --git a/drivers/scsi/hpsa.h b/drivers/scsi/hpsa.h index 82cdfad874f3..9ea162de80dc 100644 --- a/drivers/scsi/hpsa.h +++ b/drivers/scsi/hpsa.h @@ -69,6 +69,7 @@ struct hpsa_scsi_dev_t { u64 sas_address; unsigned char vendor[8]; /* bytes 8-15 of inquiry data */ unsigned char model[16]; /* bytes 16-31 of inquiry data */ + unsigned char rev; /* byte 2 of inquiry data */ unsigned char raid_level; /* from inquiry page 0xC1 */ unsigned char volume_offline; /* discovered via TUR or VPD */ u16 queue_depth; /* max queue_depth for this device */ @@ -402,6 +403,7 @@ struct offline_device_entry { #define HPSA_RAID_VOLUME_BUS 1 #define HPSA_EXTERNAL_RAID_VOLUME_BUS 2 #define HPSA_HBA_BUS 0 +#define HPSA_LEGACY_HBA_BUS 3 /* Send the command to the hardware diff --git a/drivers/scsi/libfc/fc_lport.c b/drivers/scsi/libfc/fc_lport.c index 04ce7cfb6d1b..50c71678a156 100644 --- a/drivers/scsi/libfc/fc_lport.c +++ b/drivers/scsi/libfc/fc_lport.c @@ -308,7 +308,7 @@ struct fc_host_statistics *fc_get_host_stats(struct Scsi_Host *shost) fc_stats = &lport->host_stats; memset(fc_stats, 0, sizeof(struct fc_host_statistics)); - fc_stats->seconds_since_last_reset = (lport->boot_time - jiffies) / HZ; + fc_stats->seconds_since_last_reset = (jiffies - lport->boot_time) / HZ; for_each_possible_cpu(cpu) { struct fc_stats *stats; diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index c5326055beee..f4f77c5b0c83 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -1323,18 +1323,20 @@ lpfc_sli_ringtxcmpl_put(struct lpfc_hba *phba, struct lpfc_sli_ring *pring, { lockdep_assert_held(&phba->hbalock); - BUG_ON(!piocb || !piocb->vport); + BUG_ON(!piocb); list_add_tail(&piocb->list, &pring->txcmplq); piocb->iocb_flag |= LPFC_IO_ON_TXCMPLQ; if ((unlikely(pring->ringno == LPFC_ELS_RING)) && (piocb->iocb.ulpCommand != CMD_ABORT_XRI_CN) && - (piocb->iocb.ulpCommand != CMD_CLOSE_XRI_CN) && - (!(piocb->vport->load_flag & FC_UNLOADING))) - mod_timer(&piocb->vport->els_tmofunc, - jiffies + - msecs_to_jiffies(1000 * (phba->fc_ratov << 1))); + (piocb->iocb.ulpCommand != CMD_CLOSE_XRI_CN)) { + BUG_ON(!piocb->vport); + if (!(piocb->vport->load_flag & FC_UNLOADING)) + mod_timer(&piocb->vport->els_tmofunc, + jiffies + + msecs_to_jiffies(1000 * (phba->fc_ratov << 1))); + } return 0; } diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index 8aa769a2d919..1c4744e78173 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -3885,6 +3885,11 @@ _scsih_temp_threshold_events(struct MPT3SAS_ADAPTER *ioc, } } +static inline bool ata_12_16_cmd(struct scsi_cmnd *scmd) +{ + return (scmd->cmnd[0] == ATA_12 || scmd->cmnd[0] == ATA_16); +} + /** * _scsih_flush_running_cmds - completing outstanding commands. * @ioc: per adapter object @@ -3906,6 +3911,9 @@ _scsih_flush_running_cmds(struct MPT3SAS_ADAPTER *ioc) if (!scmd) continue; count++; + if (ata_12_16_cmd(scmd)) + scsi_internal_device_unblock(scmd->device, + SDEV_RUNNING); mpt3sas_base_free_smid(ioc, smid); scsi_dma_unmap(scmd); if (ioc->pci_error_recovery) @@ -4010,8 +4018,6 @@ _scsih_eedp_error_handling(struct scsi_cmnd *scmd, u16 ioc_status) SAM_STAT_CHECK_CONDITION; } - - /** * scsih_qcmd - main scsi request entry point * @scmd: pointer to scsi command object @@ -4038,6 +4044,13 @@ scsih_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *scmd) if (ioc->logging_level & MPT_DEBUG_SCSI) scsi_print_command(scmd); + /* + * Lock the device for any subsequent command until command is + * done. + */ + if (ata_12_16_cmd(scmd)) + scsi_internal_device_block(scmd->device); + sas_device_priv_data = scmd->device->hostdata; if (!sas_device_priv_data || !sas_device_priv_data->sas_target) { scmd->result = DID_NO_CONNECT << 16; @@ -4613,6 +4626,9 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply) if (scmd == NULL) return 1; + if (ata_12_16_cmd(scmd)) + scsi_internal_device_unblock(scmd->device, SDEV_RUNNING); + mpi_request = mpt3sas_base_get_msg_frame(ioc, smid); if (mpi_reply == NULL) { diff --git a/drivers/scsi/mvsas/mv_sas.c b/drivers/scsi/mvsas/mv_sas.c index 86eb19902bac..c7cc8035eacb 100644 --- a/drivers/scsi/mvsas/mv_sas.c +++ b/drivers/scsi/mvsas/mv_sas.c @@ -791,8 +791,10 @@ static int mvs_task_prep(struct sas_task *task, struct mvs_info *mvi, int is_tmf slot->slot_tag = tag; slot->buf = pci_pool_alloc(mvi->dma_pool, GFP_ATOMIC, &slot->buf_dma); - if (!slot->buf) + if (!slot->buf) { + rc = -ENOMEM; goto err_out_tag; + } memset(slot->buf, 0, MVS_SLOT_BUF_SZ); tei.task = task; diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 567fa080e261..56d6142852a5 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -1456,15 +1456,20 @@ qla2x00_abort_all_cmds(scsi_qla_host_t *vha, int res) for (cnt = 1; cnt < req->num_outstanding_cmds; cnt++) { sp = req->outstanding_cmds[cnt]; if (sp) { - /* Get a reference to the sp and drop the lock. - * The reference ensures this sp->done() call - * - and not the call in qla2xxx_eh_abort() - - * ends the SCSI command (with result 'res'). + /* Don't abort commands in adapter during EEH + * recovery as it's not accessible/responding. */ - sp_get(sp); - spin_unlock_irqrestore(&ha->hardware_lock, flags); - qla2xxx_eh_abort(GET_CMD_SP(sp)); - spin_lock_irqsave(&ha->hardware_lock, flags); + if (!ha->flags.eeh_busy) { + /* Get a reference to the sp and drop the lock. + * The reference ensures this sp->done() call + * - and not the call in qla2xxx_eh_abort() - + * ends the SCSI command (with result 'res'). + */ + sp_get(sp); + spin_unlock_irqrestore(&ha->hardware_lock, flags); + qla2xxx_eh_abort(GET_CMD_SP(sp)); + spin_lock_irqsave(&ha->hardware_lock, flags); + } req->outstanding_cmds[cnt] = NULL; sp->done(vha, sp, res); } diff --git a/drivers/scsi/qlogicpti.h b/drivers/scsi/qlogicpti.h index 4377e87ee79c..892a0b058b99 100644 --- a/drivers/scsi/qlogicpti.h +++ b/drivers/scsi/qlogicpti.h @@ -356,8 +356,8 @@ struct qlogicpti { /* The rest of the elements are unimportant for performance. */ struct qlogicpti *next; - __u32 res_dvma; /* Ptr to RESPONSE bufs (DVMA)*/ - __u32 req_dvma; /* Ptr to REQUEST bufs (DVMA) */ + dma_addr_t res_dvma; /* Ptr to RESPONSE bufs (DVMA)*/ + dma_addr_t req_dvma; /* Ptr to REQUEST bufs (DVMA) */ u_char fware_majrev, fware_minrev, fware_micrev; struct Scsi_Host *qhost; int qpti_id; diff --git a/drivers/thermal/intel_powerclamp.c b/drivers/thermal/intel_powerclamp.c index 7a223074df3d..83e697186410 100644 --- a/drivers/thermal/intel_powerclamp.c +++ b/drivers/thermal/intel_powerclamp.c @@ -43,7 +43,6 @@ #include <linux/kernel.h> #include <linux/delay.h> #include <linux/kthread.h> -#include <linux/freezer.h> #include <linux/cpu.h> #include <linux/thermal.h> #include <linux/slab.h> @@ -86,11 +85,26 @@ static unsigned int control_cpu; /* The cpu assigned to collect stat and update */ static bool clamping; +static const struct sched_param sparam = { + .sched_priority = MAX_USER_RT_PRIO / 2, +}; +struct powerclamp_worker_data { + struct kthread_worker *worker; + struct kthread_work balancing_work; + struct kthread_delayed_work idle_injection_work; + unsigned int cpu; + unsigned int count; + unsigned int guard; + unsigned int window_size_now; + unsigned int target_ratio; + unsigned int duration_jiffies; + bool clamping; +}; -static struct task_struct * __percpu *powerclamp_thread; +static struct powerclamp_worker_data * __percpu worker_data; static struct thermal_cooling_device *cooling_dev; static unsigned long *cpu_clamping_mask; /* bit map for tracking per cpu - * clamping thread + * clamping kthread worker */ static unsigned int duration; @@ -262,11 +276,6 @@ static u64 pkg_state_counter(void) return count; } -static void noop_timer(unsigned long foo) -{ - /* empty... just the fact that we get the interrupt wakes us up */ -} - static unsigned int get_compensation(int ratio) { unsigned int comp = 0; @@ -368,103 +377,79 @@ static bool powerclamp_adjust_controls(unsigned int target_ratio, return set_target_ratio + guard <= current_ratio; } -static int clamp_thread(void *arg) +static void clamp_balancing_func(struct kthread_work *work) { - int cpunr = (unsigned long)arg; - DEFINE_TIMER(wakeup_timer, noop_timer, 0, 0); - static const struct sched_param param = { - .sched_priority = MAX_USER_RT_PRIO/2, - }; - unsigned int count = 0; - unsigned int target_ratio; + struct powerclamp_worker_data *w_data; + int sleeptime; + unsigned long target_jiffies; + unsigned int compensated_ratio; + int interval; /* jiffies to sleep for each attempt */ - set_bit(cpunr, cpu_clamping_mask); - set_freezable(); - init_timer_on_stack(&wakeup_timer); - sched_setscheduler(current, SCHED_FIFO, ¶m); - - while (true == clamping && !kthread_should_stop() && - cpu_online(cpunr)) { - int sleeptime; - unsigned long target_jiffies; - unsigned int guard; - unsigned int compensated_ratio; - int interval; /* jiffies to sleep for each attempt */ - unsigned int duration_jiffies = msecs_to_jiffies(duration); - unsigned int window_size_now; - - try_to_freeze(); - /* - * make sure user selected ratio does not take effect until - * the next round. adjust target_ratio if user has changed - * target such that we can converge quickly. - */ - target_ratio = set_target_ratio; - guard = 1 + target_ratio/20; - window_size_now = window_size; - count++; - - /* - * systems may have different ability to enter package level - * c-states, thus we need to compensate the injected idle ratio - * to achieve the actual target reported by the HW. - */ - compensated_ratio = target_ratio + - get_compensation(target_ratio); - if (compensated_ratio <= 0) - compensated_ratio = 1; - interval = duration_jiffies * 100 / compensated_ratio; - - /* align idle time */ - target_jiffies = roundup(jiffies, interval); - sleeptime = target_jiffies - jiffies; - if (sleeptime <= 0) - sleeptime = 1; - schedule_timeout_interruptible(sleeptime); - /* - * only elected controlling cpu can collect stats and update - * control parameters. - */ - if (cpunr == control_cpu && !(count%window_size_now)) { - should_skip = - powerclamp_adjust_controls(target_ratio, - guard, window_size_now); - smp_mb(); - } + w_data = container_of(work, struct powerclamp_worker_data, + balancing_work); - if (should_skip) - continue; - - target_jiffies = jiffies + duration_jiffies; - mod_timer(&wakeup_timer, target_jiffies); - if (unlikely(local_softirq_pending())) - continue; - /* - * stop tick sched during idle time, interrupts are still - * allowed. thus jiffies are updated properly. - */ - preempt_disable(); - /* mwait until target jiffies is reached */ - while (time_before(jiffies, target_jiffies)) { - unsigned long ecx = 1; - unsigned long eax = target_mwait; - - /* - * REVISIT: may call enter_idle() to notify drivers who - * can save power during cpu idle. same for exit_idle() - */ - local_touch_nmi(); - stop_critical_timings(); - mwait_idle_with_hints(eax, ecx); - start_critical_timings(); - atomic_inc(&idle_wakeup_counter); - } - preempt_enable(); + /* + * make sure user selected ratio does not take effect until + * the next round. adjust target_ratio if user has changed + * target such that we can converge quickly. + */ + w_data->target_ratio = READ_ONCE(set_target_ratio); + w_data->guard = 1 + w_data->target_ratio / 20; + w_data->window_size_now = window_size; + w_data->duration_jiffies = msecs_to_jiffies(duration); + w_data->count++; + + /* + * systems may have different ability to enter package level + * c-states, thus we need to compensate the injected idle ratio + * to achieve the actual target reported by the HW. + */ + compensated_ratio = w_data->target_ratio + + get_compensation(w_data->target_ratio); + if (compensated_ratio <= 0) + compensated_ratio = 1; + interval = w_data->duration_jiffies * 100 / compensated_ratio; + + /* align idle time */ + target_jiffies = roundup(jiffies, interval); + sleeptime = target_jiffies - jiffies; + if (sleeptime <= 0) + sleeptime = 1; + + if (clamping && w_data->clamping && cpu_online(w_data->cpu)) + kthread_queue_delayed_work(w_data->worker, + &w_data->idle_injection_work, + sleeptime); +} + +static void clamp_idle_injection_func(struct kthread_work *work) +{ + struct powerclamp_worker_data *w_data; + + w_data = container_of(work, struct powerclamp_worker_data, + idle_injection_work.work); + + /* + * only elected controlling cpu can collect stats and update + * control parameters. + */ + if (w_data->cpu == control_cpu && + !(w_data->count % w_data->window_size_now)) { + should_skip = + powerclamp_adjust_controls(w_data->target_ratio, + w_data->guard, + w_data->window_size_now); + smp_mb(); } - del_timer_sync(&wakeup_timer); - clear_bit(cpunr, cpu_clamping_mask); - return 0; + if (should_skip) + goto balance; + + play_idle(jiffies_to_msecs(w_data->duration_jiffies)); + +balance: + if (clamping && w_data->clamping && cpu_online(w_data->cpu)) + kthread_queue_work(w_data->worker, &w_data->balancing_work); } /* @@ -508,10 +493,60 @@ static void poll_pkg_cstate(struct work_struct *dummy) schedule_delayed_work(&poll_pkg_cstate_work, HZ); } +static void start_power_clamp_worker(unsigned long cpu) +{ + struct powerclamp_worker_data *w_data = per_cpu_ptr(worker_data, cpu); + struct kthread_worker *worker; + + worker = kthread_create_worker_on_cpu(cpu, 0, "kidle_inject/%ld", cpu); + if (IS_ERR(worker)) + return; + + w_data->worker = worker; + w_data->count = 0; + w_data->cpu = cpu; + w_data->clamping = true; + set_bit(cpu, cpu_clamping_mask); + sched_setscheduler(worker->task, SCHED_FIFO, &sparam); + kthread_init_work(&w_data->balancing_work, clamp_balancing_func); + kthread_init_delayed_work(&w_data->idle_injection_work, + clamp_idle_injection_func); + kthread_queue_work(w_data->worker, &w_data->balancing_work); +} + +static void stop_power_clamp_worker(unsigned long cpu) +{ + struct powerclamp_worker_data *w_data = per_cpu_ptr(worker_data, cpu); + + if (!w_data->worker) + return; + + w_data->clamping = false; + /* + * Make sure that all works that get queued after this point see + * the clamping disabled. The counter part is not needed because + * there is an implicit memory barrier when the queued work + * is proceed. + */ + smp_wmb(); + kthread_cancel_work_sync(&w_data->balancing_work); + kthread_cancel_delayed_work_sync(&w_data->idle_injection_work); + /* + * The balancing work still might be queued here because + * the handling of the "clapming" variable, cancel, and queue + * operations are not synchronized via a lock. But it is not + * a big deal. The balancing work is fast and destroy kthread + * will wait for it. + */ + clear_bit(w_data->cpu, cpu_clamping_mask); + kthread_destroy_worker(w_data->worker); + + w_data->worker = NULL; +} + static int start_power_clamp(void) { unsigned long cpu; - struct task_struct *thread; set_target_ratio = clamp(set_target_ratio, 0U, MAX_TARGET_RATIO - 1); /* prevent cpu hotplug */ @@ -525,22 +560,9 @@ static int start_power_clamp(void) clamping = true; schedule_delayed_work(&poll_pkg_cstate_work, 0); - /* start one thread per online cpu */ + /* start one kthread worker per online cpu */ for_each_online_cpu(cpu) { - struct task_struct **p = - per_cpu_ptr(powerclamp_thread, cpu); - - thread = kthread_create_on_node(clamp_thread, - (void *) cpu, - cpu_to_node(cpu), - "kidle_inject/%ld", cpu); - /* bind to cpu here */ - if (likely(!IS_ERR(thread))) { - kthread_bind(thread, cpu); - wake_up_process(thread); - *p = thread; - } - + start_power_clamp_worker(cpu); } put_online_cpus(); @@ -550,71 +572,49 @@ static int start_power_clamp(void) static void end_power_clamp(void) { int i; - struct task_struct *thread; - clamping = false; /* - * make clamping visible to other cpus and give per cpu clamping threads - * sometime to exit, or gets killed later. + * Block requeuing in all the kthread workers. They will flush and + * stop faster. */ - smp_mb(); - msleep(20); + clamping = false; if (bitmap_weight(cpu_clamping_mask, num_possible_cpus())) { for_each_set_bit(i, cpu_clamping_mask, num_possible_cpus()) { - pr_debug("clamping thread for cpu %d alive, kill\n", i); - thread = *per_cpu_ptr(powerclamp_thread, i); - kthread_stop(thread); + pr_debug("clamping worker for cpu %d alive, destroy\n", + i); + stop_power_clamp_worker(i); } } } -static int powerclamp_cpu_callback(struct notifier_block *nfb, - unsigned long action, void *hcpu) +static int powerclamp_cpu_online(unsigned int cpu) { - unsigned long cpu = (unsigned long)hcpu; - struct task_struct *thread; - struct task_struct **percpu_thread = - per_cpu_ptr(powerclamp_thread, cpu); - - if (false == clamping) - goto exit_ok; - - switch (action) { - case CPU_ONLINE: - thread = kthread_create_on_node(clamp_thread, - (void *) cpu, - cpu_to_node(cpu), - "kidle_inject/%lu", cpu); - if (likely(!IS_ERR(thread))) { - kthread_bind(thread, cpu); - wake_up_process(thread); - *percpu_thread = thread; - } - /* prefer BSP as controlling CPU */ - if (cpu == 0) { - control_cpu = 0; - smp_mb(); - } - break; - case CPU_DEAD: - if (test_bit(cpu, cpu_clamping_mask)) { - pr_err("cpu %lu dead but powerclamping thread is not\n", - cpu); - kthread_stop(*percpu_thread); - } - if (cpu == control_cpu) { - control_cpu = smp_processor_id(); - smp_mb(); - } + if (clamping == false) + return 0; + start_power_clamp_worker(cpu); + /* prefer BSP as controlling CPU */ + if (cpu == 0) { + control_cpu = 0; + smp_mb(); } - -exit_ok: - return NOTIFY_OK; + return 0; } -static struct notifier_block powerclamp_cpu_notifier = { - .notifier_call = powerclamp_cpu_callback, -}; +static int powerclamp_cpu_predown(unsigned int cpu) +{ + if (clamping == false) + return 0; + + stop_power_clamp_worker(cpu); + if (cpu != control_cpu) + return 0; + + control_cpu = cpumask_first(cpu_online_mask); + if (control_cpu == cpu) + control_cpu = cpumask_next(cpu, cpu_online_mask); + smp_mb(); + return 0; +} static int powerclamp_get_max_state(struct thermal_cooling_device *cdev, unsigned long *state) @@ -669,9 +669,16 @@ static struct thermal_cooling_device_ops powerclamp_cooling_ops = { .set_cur_state = powerclamp_set_cur_state, }; +static const struct x86_cpu_id __initconst intel_powerclamp_ids[] = { + { X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, X86_FEATURE_MWAIT }, + {} +}; +MODULE_DEVICE_TABLE(x86cpu, intel_powerclamp_ids); + static int __init powerclamp_probe(void) { - if (!boot_cpu_has(X86_FEATURE_MWAIT)) { + + if (!x86_match_cpu(intel_powerclamp_ids)) { pr_err("CPU does not support MWAIT"); return -ENODEV; } @@ -735,6 +742,8 @@ file_error: debugfs_remove_recursive(debug_dir); } +static enum cpuhp_state hp_state; + static int __init powerclamp_init(void) { int retval; @@ -752,10 +761,17 @@ static int __init powerclamp_init(void) /* set default limit, maybe adjusted during runtime based on feedback */ window_size = 2; - register_hotcpu_notifier(&powerclamp_cpu_notifier); + retval = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, + "thermal/intel_powerclamp:online", + powerclamp_cpu_online, + powerclamp_cpu_predown); + if (retval < 0) + goto exit_free; + + hp_state = retval; - powerclamp_thread = alloc_percpu(struct task_struct *); - if (!powerclamp_thread) { + worker_data = alloc_percpu(struct powerclamp_worker_data); + if (!worker_data) { retval = -ENOMEM; goto exit_unregister; } @@ -775,9 +791,9 @@ static int __init powerclamp_init(void) return 0; exit_free_thread: - free_percpu(powerclamp_thread); + free_percpu(worker_data); exit_unregister: - unregister_hotcpu_notifier(&powerclamp_cpu_notifier); + cpuhp_remove_state_nocalls(hp_state); exit_free: kfree(cpu_clamping_mask); return retval; @@ -786,9 +802,9 @@ module_init(powerclamp_init); static void __exit powerclamp_exit(void) { - unregister_hotcpu_notifier(&powerclamp_cpu_notifier); end_power_clamp(); - free_percpu(powerclamp_thread); + cpuhp_remove_state_nocalls(hp_state); + free_percpu(worker_data); thermal_cooling_device_unregister(cooling_dev); kfree(cpu_clamping_mask); diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c index 69426e644d17..3dbb4a21ab44 100644 --- a/drivers/usb/chipidea/core.c +++ b/drivers/usb/chipidea/core.c @@ -914,6 +914,7 @@ static int ci_hdrc_probe(struct platform_device *pdev) if (!ci) return -ENOMEM; + spin_lock_init(&ci->lock); ci->dev = dev; ci->platdata = dev_get_platdata(dev); ci->imx28_write_fix = !!(ci->platdata->flags & diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c index 661f43fe0f9e..c9e80ad48fdc 100644 --- a/drivers/usb/chipidea/udc.c +++ b/drivers/usb/chipidea/udc.c @@ -1889,8 +1889,6 @@ static int udc_start(struct ci_hdrc *ci) struct usb_otg_caps *otg_caps = &ci->platdata->ci_otg_caps; int retval = 0; - spin_lock_init(&ci->lock); - ci->gadget.ops = &usb_gadget_ops; ci->gadget.speed = USB_SPEED_UNKNOWN; ci->gadget.max_speed = USB_SPEED_HIGH; diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index e40d47d47d82..17989b72cdae 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -3225,11 +3225,11 @@ static bool ffs_func_req_match(struct usb_function *f, switch (creq->bRequestType & USB_RECIP_MASK) { case USB_RECIP_INTERFACE: - return ffs_func_revmap_intf(func, - le16_to_cpu(creq->wIndex) >= 0); + return (ffs_func_revmap_intf(func, + le16_to_cpu(creq->wIndex)) >= 0); case USB_RECIP_ENDPOINT: - return ffs_func_revmap_ep(func, - le16_to_cpu(creq->wIndex) >= 0); + return (ffs_func_revmap_ep(func, + le16_to_cpu(creq->wIndex)) >= 0); default: return (bool) (func->ffs->user_flags & FUNCTIONFS_ALL_CTRL_RECIP); diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c index e01116e4c067..c3e172e15ec3 100644 --- a/drivers/usb/musb/musb_core.c +++ b/drivers/usb/musb/musb_core.c @@ -986,7 +986,7 @@ b_host: } #endif - schedule_work(&musb->irq_work); + schedule_delayed_work(&musb->irq_work, 0); return handled; } @@ -1855,14 +1855,23 @@ static void musb_pm_runtime_check_session(struct musb *musb) MUSB_DEVCTL_HR; switch (devctl & ~s) { case MUSB_QUIRK_B_INVALID_VBUS_91: - if (!musb->session && !musb->quirk_invalid_vbus) { - musb->quirk_invalid_vbus = true; + if (musb->quirk_retries--) { musb_dbg(musb, - "First invalid vbus, assume no session"); + "Poll devctl on invalid vbus, assume no session"); + schedule_delayed_work(&musb->irq_work, + msecs_to_jiffies(1000)); + return; } - break; case MUSB_QUIRK_A_DISCONNECT_19: + if (musb->quirk_retries--) { + musb_dbg(musb, + "Poll devctl on possible host mode disconnect"); + schedule_delayed_work(&musb->irq_work, + msecs_to_jiffies(1000)); + + return; + } if (!musb->session) break; musb_dbg(musb, "Allow PM on possible host mode disconnect"); @@ -1886,9 +1895,9 @@ static void musb_pm_runtime_check_session(struct musb *musb) if (error < 0) dev_err(musb->controller, "Could not enable: %i\n", error); + musb->quirk_retries = 3; } else { musb_dbg(musb, "Allow PM with no session: %02x", devctl); - musb->quirk_invalid_vbus = false; pm_runtime_mark_last_busy(musb->controller); pm_runtime_put_autosuspend(musb->controller); } @@ -1899,7 +1908,7 @@ static void musb_pm_runtime_check_session(struct musb *musb) /* Only used to provide driver mode change events */ static void musb_irq_work(struct work_struct *data) { - struct musb *musb = container_of(data, struct musb, irq_work); + struct musb *musb = container_of(data, struct musb, irq_work.work); musb_pm_runtime_check_session(musb); @@ -1969,6 +1978,7 @@ static struct musb *allocate_instance(struct device *dev, INIT_LIST_HEAD(&musb->control); INIT_LIST_HEAD(&musb->in_bulk); INIT_LIST_HEAD(&musb->out_bulk); + INIT_LIST_HEAD(&musb->pending_list); musb->vbuserr_retry = VBUSERR_RETRY_COUNT; musb->a_wait_bcon = OTG_TIME_A_WAIT_BCON; @@ -2018,6 +2028,84 @@ static void musb_free(struct musb *musb) musb_host_free(musb); } +struct musb_pending_work { + int (*callback)(struct musb *musb, void *data); + void *data; + struct list_head node; +}; + +/* + * Called from musb_runtime_resume(), musb_resume(), and + * musb_queue_resume_work(). Callers must take musb->lock. + */ +static int musb_run_resume_work(struct musb *musb) +{ + struct musb_pending_work *w, *_w; + unsigned long flags; + int error = 0; + + spin_lock_irqsave(&musb->list_lock, flags); + list_for_each_entry_safe(w, _w, &musb->pending_list, node) { + if (w->callback) { + error = w->callback(musb, w->data); + if (error < 0) { + dev_err(musb->controller, + "resume callback %p failed: %i\n", + w->callback, error); + } + } + list_del(&w->node); + devm_kfree(musb->controller, w); + } + spin_unlock_irqrestore(&musb->list_lock, flags); + + return error; +} + +/* + * Called to run work if device is active or else queue the work to happen + * on resume. Caller must take musb->lock and must hold an RPM reference. + * + * Note that we cowardly refuse queuing work after musb PM runtime + * resume is done calling musb_run_resume_work() and return -EINPROGRESS + * instead. + */ +int musb_queue_resume_work(struct musb *musb, + int (*callback)(struct musb *musb, void *data), + void *data) +{ + struct musb_pending_work *w; + unsigned long flags; + int error; + + if (WARN_ON(!callback)) + return -EINVAL; + + if (pm_runtime_active(musb->controller)) + return callback(musb, data); + + w = devm_kzalloc(musb->controller, sizeof(*w), GFP_ATOMIC); + if (!w) + return -ENOMEM; + + w->callback = callback; + w->data = data; + spin_lock_irqsave(&musb->list_lock, flags); + if (musb->is_runtime_suspended) { + list_add_tail(&w->node, &musb->pending_list); + error = 0; + } else { + dev_err(musb->controller, "could not add resume work %p\n", + callback); + devm_kfree(musb->controller, w); + error = -EINPROGRESS; + } + spin_unlock_irqrestore(&musb->list_lock, flags); + + return error; +} +EXPORT_SYMBOL_GPL(musb_queue_resume_work); + static void musb_deassert_reset(struct work_struct *work) { struct musb *musb; @@ -2065,6 +2153,7 @@ musb_init_controller(struct device *dev, int nIrq, void __iomem *ctrl) } spin_lock_init(&musb->lock); + spin_lock_init(&musb->list_lock); musb->board_set_power = plat->set_power; musb->min_power = plat->min_power; musb->ops = plat->platform_ops; @@ -2208,7 +2297,7 @@ musb_init_controller(struct device *dev, int nIrq, void __iomem *ctrl) musb_generic_disable(musb); /* Init IRQ workqueue before request_irq */ - INIT_WORK(&musb->irq_work, musb_irq_work); + INIT_DELAYED_WORK(&musb->irq_work, musb_irq_work); INIT_DELAYED_WORK(&musb->deassert_reset_work, musb_deassert_reset); INIT_DELAYED_WORK(&musb->finish_resume_work, musb_host_finish_resume); @@ -2291,6 +2380,7 @@ musb_init_controller(struct device *dev, int nIrq, void __iomem *ctrl) if (status) goto fail5; + musb->is_initialized = 1; pm_runtime_mark_last_busy(musb->controller); pm_runtime_put_autosuspend(musb->controller); @@ -2304,7 +2394,7 @@ fail4: musb_host_cleanup(musb); fail3: - cancel_work_sync(&musb->irq_work); + cancel_delayed_work_sync(&musb->irq_work); cancel_delayed_work_sync(&musb->finish_resume_work); cancel_delayed_work_sync(&musb->deassert_reset_work); if (musb->dma_controller) @@ -2371,7 +2461,7 @@ static int musb_remove(struct platform_device *pdev) */ musb_exit_debugfs(musb); - cancel_work_sync(&musb->irq_work); + cancel_delayed_work_sync(&musb->irq_work); cancel_delayed_work_sync(&musb->finish_resume_work); cancel_delayed_work_sync(&musb->deassert_reset_work); pm_runtime_get_sync(musb->controller); @@ -2557,6 +2647,7 @@ static int musb_suspend(struct device *dev) musb_platform_disable(musb); musb_generic_disable(musb); + WARN_ON(!list_empty(&musb->pending_list)); spin_lock_irqsave(&musb->lock, flags); @@ -2578,9 +2669,11 @@ static int musb_suspend(struct device *dev) static int musb_resume(struct device *dev) { - struct musb *musb = dev_to_musb(dev); - u8 devctl; - u8 mask; + struct musb *musb = dev_to_musb(dev); + unsigned long flags; + int error; + u8 devctl; + u8 mask; /* * For static cmos like DaVinci, register values were preserved @@ -2614,6 +2707,13 @@ static int musb_resume(struct device *dev) musb_start(musb); + spin_lock_irqsave(&musb->lock, flags); + error = musb_run_resume_work(musb); + if (error) + dev_err(musb->controller, "resume work failed with %i\n", + error); + spin_unlock_irqrestore(&musb->lock, flags); + return 0; } @@ -2622,14 +2722,16 @@ static int musb_runtime_suspend(struct device *dev) struct musb *musb = dev_to_musb(dev); musb_save_context(musb); + musb->is_runtime_suspended = 1; return 0; } static int musb_runtime_resume(struct device *dev) { - struct musb *musb = dev_to_musb(dev); - static int first = 1; + struct musb *musb = dev_to_musb(dev); + unsigned long flags; + int error; /* * When pm_runtime_get_sync called for the first time in driver @@ -2640,9 +2742,10 @@ static int musb_runtime_resume(struct device *dev) * Also context restore without save does not make * any sense */ - if (!first) - musb_restore_context(musb); - first = 0; + if (!musb->is_initialized) + return 0; + + musb_restore_context(musb); if (musb->need_finish_resume) { musb->need_finish_resume = 0; @@ -2650,6 +2753,14 @@ static int musb_runtime_resume(struct device *dev) msecs_to_jiffies(USB_RESUME_TIMEOUT)); } + spin_lock_irqsave(&musb->lock, flags); + error = musb_run_resume_work(musb); + if (error) + dev_err(musb->controller, "resume work failed with %i\n", + error); + musb->is_runtime_suspended = 0; + spin_unlock_irqrestore(&musb->lock, flags); + return 0; } diff --git a/drivers/usb/musb/musb_core.h b/drivers/usb/musb/musb_core.h index 2cb88a498f8a..91817d77d59c 100644 --- a/drivers/usb/musb/musb_core.h +++ b/drivers/usb/musb/musb_core.h @@ -303,13 +303,14 @@ struct musb_context_registers { struct musb { /* device lock */ spinlock_t lock; + spinlock_t list_lock; /* resume work list lock */ struct musb_io io; const struct musb_platform_ops *ops; struct musb_context_registers context; irqreturn_t (*isr)(int, void *); - struct work_struct irq_work; + struct delayed_work irq_work; struct delayed_work deassert_reset_work; struct delayed_work finish_resume_work; struct delayed_work gadget_work; @@ -337,6 +338,7 @@ struct musb { struct list_head control; /* of musb_qh */ struct list_head in_bulk; /* of musb_qh */ struct list_head out_bulk; /* of musb_qh */ + struct list_head pending_list; /* pending work list */ struct timer_list otg_timer; struct notifier_block nb; @@ -379,12 +381,15 @@ struct musb { int port_mode; /* MUSB_PORT_MODE_* */ bool session; - bool quirk_invalid_vbus; + unsigned long quirk_retries; bool is_host; int a_wait_bcon; /* VBUS timeout in msecs */ unsigned long idle_timeout; /* Next timeout in jiffies */ + unsigned is_initialized:1; + unsigned is_runtime_suspended:1; + /* active means connected and not suspended */ unsigned is_active:1; @@ -540,6 +545,10 @@ extern irqreturn_t musb_interrupt(struct musb *); extern void musb_hnp_stop(struct musb *musb); +int musb_queue_resume_work(struct musb *musb, + int (*callback)(struct musb *musb, void *data), + void *data); + static inline void musb_platform_set_vbus(struct musb *musb, int is_on) { if (musb->ops->set_vbus) diff --git a/drivers/usb/musb/musb_dsps.c b/drivers/usb/musb/musb_dsps.c index 0f17d2140db6..feae1561b9ab 100644 --- a/drivers/usb/musb/musb_dsps.c +++ b/drivers/usb/musb/musb_dsps.c @@ -185,24 +185,19 @@ static void dsps_musb_disable(struct musb *musb) musb_writel(reg_base, wrp->coreintr_clear, wrp->usb_bitmap); musb_writel(reg_base, wrp->epintr_clear, wrp->txep_bitmap | wrp->rxep_bitmap); + del_timer_sync(&glue->timer); musb_writeb(musb->mregs, MUSB_DEVCTL, 0); } -static void otg_timer(unsigned long _musb) +/* Caller must take musb->lock */ +static int dsps_check_status(struct musb *musb, void *unused) { - struct musb *musb = (void *)_musb; void __iomem *mregs = musb->mregs; struct device *dev = musb->controller; struct dsps_glue *glue = dev_get_drvdata(dev->parent); const struct dsps_musb_wrapper *wrp = glue->wrp; u8 devctl; - unsigned long flags; int skip_session = 0; - int err; - - err = pm_runtime_get_sync(dev); - if (err < 0) - dev_err(dev, "Poll could not pm_runtime_get: %i\n", err); /* * We poll because DSPS IP's won't expose several OTG-critical @@ -212,7 +207,6 @@ static void otg_timer(unsigned long _musb) dev_dbg(musb->controller, "Poll devctl %02x (%s)\n", devctl, usb_otg_state_string(musb->xceiv->otg->state)); - spin_lock_irqsave(&musb->lock, flags); switch (musb->xceiv->otg->state) { case OTG_STATE_A_WAIT_VRISE: mod_timer(&glue->timer, jiffies + @@ -245,8 +239,30 @@ static void otg_timer(unsigned long _musb) default: break; } - spin_unlock_irqrestore(&musb->lock, flags); + return 0; +} + +static void otg_timer(unsigned long _musb) +{ + struct musb *musb = (void *)_musb; + struct device *dev = musb->controller; + unsigned long flags; + int err; + + err = pm_runtime_get(dev); + if ((err != -EINPROGRESS) && err < 0) { + dev_err(dev, "Poll could not pm_runtime_get: %i\n", err); + pm_runtime_put_noidle(dev); + + return; + } + + spin_lock_irqsave(&musb->lock, flags); + err = musb_queue_resume_work(musb, dsps_check_status, NULL); + if (err < 0) + dev_err(dev, "%s resume work: %i\n", __func__, err); + spin_unlock_irqrestore(&musb->lock, flags); pm_runtime_mark_last_busy(dev); pm_runtime_put_autosuspend(dev); } @@ -767,28 +783,13 @@ static int dsps_probe(struct platform_device *pdev) platform_set_drvdata(pdev, glue); pm_runtime_enable(&pdev->dev); - pm_runtime_use_autosuspend(&pdev->dev); - pm_runtime_set_autosuspend_delay(&pdev->dev, 200); - - ret = pm_runtime_get_sync(&pdev->dev); - if (ret < 0) { - dev_err(&pdev->dev, "pm_runtime_get_sync FAILED"); - goto err2; - } - ret = dsps_create_musb_pdev(glue, pdev); if (ret) - goto err3; - - pm_runtime_mark_last_busy(&pdev->dev); - pm_runtime_put_autosuspend(&pdev->dev); + goto err; return 0; -err3: - pm_runtime_put_sync(&pdev->dev); -err2: - pm_runtime_dont_use_autosuspend(&pdev->dev); +err: pm_runtime_disable(&pdev->dev); return ret; } @@ -799,9 +800,6 @@ static int dsps_remove(struct platform_device *pdev) platform_device_unregister(glue->musb); - /* disable usbss clocks */ - pm_runtime_dont_use_autosuspend(&pdev->dev); - pm_runtime_put_sync(&pdev->dev); pm_runtime_disable(&pdev->dev); return 0; diff --git a/drivers/usb/musb/musb_gadget.c b/drivers/usb/musb/musb_gadget.c index 4042ea017985..a55173c9e564 100644 --- a/drivers/usb/musb/musb_gadget.c +++ b/drivers/usb/musb/musb_gadget.c @@ -1114,7 +1114,7 @@ static int musb_gadget_enable(struct usb_ep *ep, musb_ep->dma ? "dma, " : "", musb_ep->packet_sz); - schedule_work(&musb->irq_work); + schedule_delayed_work(&musb->irq_work, 0); fail: spin_unlock_irqrestore(&musb->lock, flags); @@ -1158,7 +1158,7 @@ static int musb_gadget_disable(struct usb_ep *ep) musb_ep->desc = NULL; musb_ep->end_point.desc = NULL; - schedule_work(&musb->irq_work); + schedule_delayed_work(&musb->irq_work, 0); spin_unlock_irqrestore(&(musb->lock), flags); @@ -1222,13 +1222,22 @@ void musb_ep_restart(struct musb *musb, struct musb_request *req) rxstate(musb, req); } +static int musb_ep_restart_resume_work(struct musb *musb, void *data) +{ + struct musb_request *req = data; + + musb_ep_restart(musb, req); + + return 0; +} + static int musb_gadget_queue(struct usb_ep *ep, struct usb_request *req, gfp_t gfp_flags) { struct musb_ep *musb_ep; struct musb_request *request; struct musb *musb; - int status = 0; + int status; unsigned long lockflags; if (!ep || !req) @@ -1245,6 +1254,17 @@ static int musb_gadget_queue(struct usb_ep *ep, struct usb_request *req, if (request->ep != musb_ep) return -EINVAL; + status = pm_runtime_get(musb->controller); + if ((status != -EINPROGRESS) && status < 0) { + dev_err(musb->controller, + "pm runtime get failed in %s\n", + __func__); + pm_runtime_put_noidle(musb->controller); + + return status; + } + status = 0; + trace_musb_req_enq(request); /* request is mine now... */ @@ -1255,7 +1275,6 @@ static int musb_gadget_queue(struct usb_ep *ep, struct usb_request *req, map_dma_buffer(request, musb, musb_ep); - pm_runtime_get_sync(musb->controller); spin_lock_irqsave(&musb->lock, lockflags); /* don't queue if the ep is down */ @@ -1271,8 +1290,14 @@ static int musb_gadget_queue(struct usb_ep *ep, struct usb_request *req, list_add_tail(&request->list, &musb_ep->req_list); /* it this is the head of the queue, start i/o ... */ - if (!musb_ep->busy && &request->list == musb_ep->req_list.next) - musb_ep_restart(musb, request); + if (!musb_ep->busy && &request->list == musb_ep->req_list.next) { + status = musb_queue_resume_work(musb, + musb_ep_restart_resume_work, + request); + if (status < 0) + dev_err(musb->controller, "%s resume work: %i\n", + __func__, status); + } unlock: spin_unlock_irqrestore(&musb->lock, lockflags); @@ -1969,7 +1994,7 @@ static int musb_gadget_stop(struct usb_gadget *g) */ /* Force check of devctl register for PM runtime */ - schedule_work(&musb->irq_work); + schedule_delayed_work(&musb->irq_work, 0); pm_runtime_mark_last_busy(musb->controller); pm_runtime_put_autosuspend(musb->controller); diff --git a/drivers/usb/musb/omap2430.c b/drivers/usb/musb/omap2430.c index cc1225485509..e8be8e39ab8f 100644 --- a/drivers/usb/musb/omap2430.c +++ b/drivers/usb/musb/omap2430.c @@ -513,17 +513,18 @@ static int omap2430_probe(struct platform_device *pdev) } pm_runtime_enable(glue->dev); - pm_runtime_use_autosuspend(glue->dev); - pm_runtime_set_autosuspend_delay(glue->dev, 100); ret = platform_device_add(musb); if (ret) { dev_err(&pdev->dev, "failed to register musb device\n"); - goto err2; + goto err3; } return 0; +err3: + pm_runtime_disable(glue->dev); + err2: platform_device_put(musb); @@ -535,10 +536,7 @@ static int omap2430_remove(struct platform_device *pdev) { struct omap2430_glue *glue = platform_get_drvdata(pdev); - pm_runtime_get_sync(glue->dev); platform_device_unregister(glue->musb); - pm_runtime_put_sync(glue->dev); - pm_runtime_dont_use_autosuspend(glue->dev); pm_runtime_disable(glue->dev); return 0; diff --git a/drivers/usb/musb/tusb6010.c b/drivers/usb/musb/tusb6010.c index df7c9f46be54..e85cc8e4e7a9 100644 --- a/drivers/usb/musb/tusb6010.c +++ b/drivers/usb/musb/tusb6010.c @@ -724,7 +724,7 @@ tusb_otg_ints(struct musb *musb, u32 int_src, void __iomem *tbase) dev_dbg(musb->controller, "vbus change, %s, otg %03x\n", usb_otg_state_string(musb->xceiv->otg->state), otg_stat); idle_timeout = jiffies + (1 * HZ); - schedule_work(&musb->irq_work); + schedule_delayed_work(&musb->irq_work, 0); } else /* A-dev state machine */ { dev_dbg(musb->controller, "vbus change, %s, otg %03x\n", @@ -814,7 +814,7 @@ tusb_otg_ints(struct musb *musb, u32 int_src, void __iomem *tbase) break; } } - schedule_work(&musb->irq_work); + schedule_delayed_work(&musb->irq_work, 0); return idle_timeout; } @@ -864,7 +864,7 @@ static irqreturn_t tusb_musb_interrupt(int irq, void *__hci) musb_writel(tbase, TUSB_PRCM_WAKEUP_CLEAR, reg); if (reg & ~TUSB_PRCM_WNORCS) { musb->is_active = 1; - schedule_work(&musb->irq_work); + schedule_delayed_work(&musb->irq_work, 0); } dev_dbg(musb->controller, "wake %sactive %02x\n", musb->is_active ? "" : "in", reg); diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index f61477bed3a8..243ac5ebe46a 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -131,6 +131,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0x88A4) }, /* MMB Networks ZigBee USB Device */ { USB_DEVICE(0x10C4, 0x88A5) }, /* Planet Innovation Ingeni ZigBee USB Device */ { USB_DEVICE(0x10C4, 0x8946) }, /* Ketra N1 Wireless Interface */ + { USB_DEVICE(0x10C4, 0x8962) }, /* Brim Brothers charging dock */ { USB_DEVICE(0x10C4, 0x8977) }, /* CEL MeshWorks DevKit Device */ { USB_DEVICE(0x10C4, 0x8998) }, /* KCF Technologies PRN */ { USB_DEVICE(0x10C4, 0x8A2A) }, /* HubZ dual ZigBee and Z-Wave dongle */ diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index 0ff7f38d7800..6e9fc8bcc285 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -1012,6 +1012,8 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(ICPDAS_VID, ICPDAS_I7561U_PID) }, { USB_DEVICE(ICPDAS_VID, ICPDAS_I7563U_PID) }, { USB_DEVICE(WICED_VID, WICED_USB20706V2_PID) }, + { USB_DEVICE(TI_VID, TI_CC3200_LAUNCHPAD_PID), + .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, { } /* Terminating entry */ }; diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index 21011c0a4c64..48ee04c94a75 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -596,6 +596,12 @@ #define STK541_PID 0x2109 /* Zigbee Controller */ /* + * Texas Instruments + */ +#define TI_VID 0x0451 +#define TI_CC3200_LAUNCHPAD_PID 0xC32A /* SimpleLink Wi-Fi CC3200 LaunchPad */ + +/* * Blackfin gnICE JTAG * http://docs.blackfin.uclinux.org/doku.php?id=hw:jtag:gnice */ diff --git a/drivers/usb/storage/transport.c b/drivers/usb/storage/transport.c index ffd086733421..1a59f335b063 100644 --- a/drivers/usb/storage/transport.c +++ b/drivers/usb/storage/transport.c @@ -954,10 +954,15 @@ int usb_stor_CB_transport(struct scsi_cmnd *srb, struct us_data *us) /* COMMAND STAGE */ /* let's send the command via the control pipe */ + /* + * Command is sometime (f.e. after scsi_eh_prep_cmnd) on the stack. + * Stack may be vmallocated. So no DMA for us. Make a copy. + */ + memcpy(us->iobuf, srb->cmnd, srb->cmd_len); result = usb_stor_ctrl_transfer(us, us->send_ctrl_pipe, US_CBI_ADSC, USB_TYPE_CLASS | USB_RECIP_INTERFACE, 0, - us->ifnum, srb->cmnd, srb->cmd_len); + us->ifnum, us->iobuf, srb->cmd_len); /* check the return code for the command */ usb_stor_dbg(us, "Call to usb_stor_ctrl_transfer() returned %d\n", diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index e3b30ea9ece5..a504e2e003da 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -506,7 +506,7 @@ static void vhost_vsock_reset_orphans(struct sock *sk) * executing. */ - if (!vhost_vsock_get(vsk->local_addr.svm_cid)) { + if (!vhost_vsock_get(vsk->remote_addr.svm_cid)) { sock_set_flag(sk, SOCK_DONE); vsk->peer_shutdown = SHUTDOWN_MASK; sk->sk_state = SS_UNCONNECTED; diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig index fdd3228e0678..3eb58cb51e56 100644 --- a/drivers/watchdog/Kconfig +++ b/drivers/watchdog/Kconfig @@ -155,6 +155,7 @@ config TANGOX_WATCHDOG config WDAT_WDT tristate "ACPI Watchdog Action Table (WDAT)" depends on ACPI + select WATCHDOG_CORE select ACPI_WATCHDOG help This driver adds support for systems with ACPI Watchdog Action diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 78180d151730..a594c7879cc2 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1261,26 +1261,30 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags) return -ECHILD; op = ceph_snap(dir) == CEPH_SNAPDIR ? - CEPH_MDS_OP_LOOKUPSNAP : CEPH_MDS_OP_LOOKUP; + CEPH_MDS_OP_LOOKUPSNAP : CEPH_MDS_OP_GETATTR; req = ceph_mdsc_create_request(mdsc, op, USE_ANY_MDS); if (!IS_ERR(req)) { req->r_dentry = dget(dentry); - req->r_num_caps = 2; + req->r_num_caps = op == CEPH_MDS_OP_GETATTR ? 1 : 2; mask = CEPH_STAT_CAP_INODE | CEPH_CAP_AUTH_SHARED; if (ceph_security_xattr_wanted(dir)) mask |= CEPH_CAP_XATTR_SHARED; req->r_args.getattr.mask = mask; - req->r_locked_dir = dir; err = ceph_mdsc_do_request(mdsc, NULL, req); - if (err == 0 || err == -ENOENT) { - if (dentry == req->r_dentry) { - valid = !d_unhashed(dentry); - } else { - d_invalidate(req->r_dentry); - err = -EAGAIN; - } + switch (err) { + case 0: + if (d_really_is_positive(dentry) && + d_inode(dentry) == req->r_target_inode) + valid = 1; + break; + case -ENOENT: + if (d_really_is_negative(dentry)) + valid = 1; + /* Fallthrough */ + default: + break; } ceph_mdsc_put_request(req); dout("d_revalidate %p lookup result=%d\n", diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index 8347c90cf483..5eb04129f938 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -808,7 +808,11 @@ calc_seckey(struct cifs_ses *ses) struct crypto_skcipher *tfm_arc4; struct scatterlist sgin, sgout; struct skcipher_request *req; - unsigned char sec_key[CIFS_SESS_KEY_SIZE]; /* a nonce */ + unsigned char *sec_key; + + sec_key = kmalloc(CIFS_SESS_KEY_SIZE, GFP_KERNEL); + if (sec_key == NULL) + return -ENOMEM; get_random_bytes(sec_key, CIFS_SESS_KEY_SIZE); @@ -816,7 +820,7 @@ calc_seckey(struct cifs_ses *ses) if (IS_ERR(tfm_arc4)) { rc = PTR_ERR(tfm_arc4); cifs_dbg(VFS, "could not allocate crypto API arc4\n"); - return rc; + goto out; } rc = crypto_skcipher_setkey(tfm_arc4, ses->auth_key.response, @@ -854,7 +858,8 @@ calc_seckey(struct cifs_ses *ses) out_free_cipher: crypto_free_skcipher(tfm_arc4); - +out: + kfree(sec_key); return rc; } diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 3f3185febc58..e3fed9249a04 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -3427,6 +3427,7 @@ static __u16 ACL_to_cifs_posix(char *parm_data, const char *pACL, __u16 rc = 0; struct cifs_posix_acl *cifs_acl = (struct cifs_posix_acl *)parm_data; struct posix_acl_xattr_header *local_acl = (void *)pACL; + struct posix_acl_xattr_entry *ace = (void *)(local_acl + 1); int count; int i; @@ -3453,8 +3454,7 @@ static __u16 ACL_to_cifs_posix(char *parm_data, const char *pACL, return 0; } for (i = 0; i < count; i++) { - rc = convert_ace_to_cifs_ace(&cifs_acl->ace_array[i], - (struct posix_acl_xattr_entry *)(local_acl + 1)); + rc = convert_ace_to_cifs_ace(&cifs_acl->ace_array[i], &ace[i]); if (rc != 0) { /* ACE not converted */ break; diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index aab5227979e2..4547aeddd12b 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -412,6 +412,9 @@ cifs_reconnect(struct TCP_Server_Info *server) } } while (server->tcpStatus == CifsNeedReconnect); + if (server->tcpStatus == CifsNeedNegotiate) + mod_delayed_work(cifsiod_wq, &server->echo, 0); + return rc; } @@ -421,17 +424,25 @@ cifs_echo_request(struct work_struct *work) int rc; struct TCP_Server_Info *server = container_of(work, struct TCP_Server_Info, echo.work); - unsigned long echo_interval = server->echo_interval; + unsigned long echo_interval; + + /* + * If we need to renegotiate, set echo interval to zero to + * immediately call echo service where we can renegotiate. + */ + if (server->tcpStatus == CifsNeedNegotiate) + echo_interval = 0; + else + echo_interval = server->echo_interval; /* - * We cannot send an echo if it is disabled or until the - * NEGOTIATE_PROTOCOL request is done, which is indicated by - * server->ops->need_neg() == true. Also, no need to ping if - * we got a response recently. + * We cannot send an echo if it is disabled. + * Also, no need to ping if we got a response recently. */ if (server->tcpStatus == CifsNeedReconnect || - server->tcpStatus == CifsExiting || server->tcpStatus == CifsNew || + server->tcpStatus == CifsExiting || + server->tcpStatus == CifsNew || (server->ops->can_echo && !server->ops->can_echo(server)) || time_before(jiffies, server->lstrp + echo_interval - HZ)) goto requeue_echo; @@ -442,7 +453,7 @@ cifs_echo_request(struct work_struct *work) server->hostname); requeue_echo: - queue_delayed_work(cifsiod_wq, &server->echo, echo_interval); + queue_delayed_work(cifsiod_wq, &server->echo, server->echo_interval); } static bool diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index b3ebe512d64c..096f79997f75 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1739,8 +1739,6 @@ static int fuse_setattr(struct dentry *entry, struct iattr *attr) * This should be done on write(), truncate() and chown(). */ if (!fc->handle_killpriv) { - int kill; - /* * ia_mode calculation may have used stale i_mode. * Refresh and recalculate. @@ -1750,12 +1748,11 @@ static int fuse_setattr(struct dentry *entry, struct iattr *attr) return ret; attr->ia_mode = inode->i_mode; - kill = should_remove_suid(entry); - if (kill & ATTR_KILL_SUID) { + if (inode->i_mode & S_ISUID) { attr->ia_valid |= ATTR_MODE; attr->ia_mode &= ~S_ISUID; } - if (kill & ATTR_KILL_SGID) { + if ((inode->i_mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) { attr->ia_valid |= ATTR_MODE; attr->ia_mode &= ~S_ISGID; } diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c index 98b3eb7d8eaf..0ec137310320 100644 --- a/fs/isofs/rock.c +++ b/fs/isofs/rock.c @@ -377,9 +377,9 @@ repeat: { int p; for (p = 0; p < rr->u.ER.len_id; p++) - printk("%c", rr->u.ER.data[p]); + printk(KERN_CONT "%c", rr->u.ER.data[p]); } - printk("\n"); + printk(KERN_CONT "\n"); break; case SIG('P', 'X'): inode->i_mode = isonum_733(rr->u.PX.mode); diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 532d8e242d4d..484bebc20bca 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -197,7 +197,7 @@ static int nfs_callback_up_net(int minorversion, struct svc_serv *serv, } ret = -EPROTONOSUPPORT; - if (minorversion == 0) + if (!IS_ENABLED(CONFIG_NFS_V4_1) || minorversion == 0) ret = nfs4_callback_up_net(serv, net); else if (xprt->ops->bc_up) ret = xprt->ops->bc_up(serv, net); diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 9b3a82abab07..1452177c822d 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -542,6 +542,13 @@ static inline bool nfs4_valid_open_stateid(const struct nfs4_state *state) return test_bit(NFS_STATE_RECOVERY_FAILED, &state->flags) == 0; } +static inline bool nfs4_state_match_open_stateid_other(const struct nfs4_state *state, + const nfs4_stateid *stateid) +{ + return test_bit(NFS_OPEN_STATE, &state->flags) && + nfs4_stateid_match_other(&state->open_stateid, stateid); +} + #else #define nfs4_close_state(a, b) do { } while (0) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 7897826d7c51..241da19b7da4 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1451,7 +1451,6 @@ static void nfs_resync_open_stateid_locked(struct nfs4_state *state) } static void nfs_clear_open_stateid_locked(struct nfs4_state *state, - nfs4_stateid *arg_stateid, nfs4_stateid *stateid, fmode_t fmode) { clear_bit(NFS_O_RDWR_STATE, &state->flags); @@ -1469,10 +1468,9 @@ static void nfs_clear_open_stateid_locked(struct nfs4_state *state, } if (stateid == NULL) return; - /* Handle races with OPEN */ - if (!nfs4_stateid_match_other(arg_stateid, &state->open_stateid) || - (nfs4_stateid_match_other(stateid, &state->open_stateid) && - !nfs4_stateid_is_newer(stateid, &state->open_stateid))) { + /* Handle OPEN+OPEN_DOWNGRADE races */ + if (nfs4_stateid_match_other(stateid, &state->open_stateid) && + !nfs4_stateid_is_newer(stateid, &state->open_stateid)) { nfs_resync_open_stateid_locked(state); return; } @@ -1486,7 +1484,9 @@ static void nfs_clear_open_stateid(struct nfs4_state *state, nfs4_stateid *stateid, fmode_t fmode) { write_seqlock(&state->seqlock); - nfs_clear_open_stateid_locked(state, arg_stateid, stateid, fmode); + /* Ignore, if the CLOSE argment doesn't match the current stateid */ + if (nfs4_state_match_open_stateid_other(state, arg_stateid)) + nfs_clear_open_stateid_locked(state, stateid, fmode); write_sequnlock(&state->seqlock); if (test_bit(NFS_STATE_RECLAIM_NOGRACE, &state->flags)) nfs4_schedule_state_manager(state->owner->so_server->nfs_client); @@ -2564,15 +2564,23 @@ static void nfs41_check_delegation_stateid(struct nfs4_state *state) static int nfs41_check_expired_locks(struct nfs4_state *state) { int status, ret = NFS_OK; - struct nfs4_lock_state *lsp; + struct nfs4_lock_state *lsp, *prev = NULL; struct nfs_server *server = NFS_SERVER(state->inode); if (!test_bit(LK_STATE_IN_USE, &state->flags)) goto out; + + spin_lock(&state->state_lock); list_for_each_entry(lsp, &state->lock_states, ls_locks) { if (test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags)) { struct rpc_cred *cred = lsp->ls_state->owner->so_cred; + atomic_inc(&lsp->ls_count); + spin_unlock(&state->state_lock); + + nfs4_put_lock_state(prev); + prev = lsp; + status = nfs41_test_and_free_expired_stateid(server, &lsp->ls_stateid, cred); @@ -2585,10 +2593,14 @@ static int nfs41_check_expired_locks(struct nfs4_state *state) set_bit(NFS_LOCK_LOST, &lsp->ls_flags); } else if (status != NFS_OK) { ret = status; - break; + nfs4_put_lock_state(prev); + goto out; } + spin_lock(&state->state_lock); } - }; + } + spin_unlock(&state->state_lock); + nfs4_put_lock_state(prev); out: return ret; } @@ -3122,7 +3134,8 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data) } else if (is_rdwr) calldata->arg.fmode |= FMODE_READ|FMODE_WRITE; - if (!nfs4_valid_open_stateid(state)) + if (!nfs4_valid_open_stateid(state) || + test_bit(NFS_OPEN_STATE, &state->flags) == 0) call_close = 0; spin_unlock(&state->owner->so_lock); @@ -5569,6 +5582,7 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata) switch (task->tk_status) { case 0: renew_lease(data->res.server, data->timestamp); + break; case -NFS4ERR_ADMIN_REVOKED: case -NFS4ERR_DELEG_REVOKED: case -NFS4ERR_EXPIRED: @@ -5579,8 +5593,6 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata) case -NFS4ERR_OLD_STATEID: case -NFS4ERR_STALE_STATEID: task->tk_status = 0; - if (data->roc) - pnfs_roc_set_barrier(data->inode, data->roc_barrier); break; default: if (nfs4_async_handle_error(task, data->res.server, @@ -5590,6 +5602,8 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata) } } data->rpc_status = task->tk_status; + if (data->roc && data->rpc_status == 0) + pnfs_roc_set_barrier(data->inode, data->roc_barrier); } static void nfs4_delegreturn_release(void *calldata) diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 5f4281ec5f72..0959c9661662 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1547,6 +1547,7 @@ restart: ssleep(1); case -NFS4ERR_ADMIN_REVOKED: case -NFS4ERR_STALE_STATEID: + case -NFS4ERR_OLD_STATEID: case -NFS4ERR_BAD_STATEID: case -NFS4ERR_RECLAIM_BAD: case -NFS4ERR_RECLAIM_CONFLICT: diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index edd46a0e951d..0e100856c7b8 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -328,11 +328,11 @@ static struct dentry *ovl_d_real(struct dentry *dentry, if (!real) goto bug; + /* Handle recursion */ + real = d_real(real, inode, open_flags); + if (!inode || inode == d_inode(real)) return real; - - /* Handle recursion */ - return d_real(real, inode, open_flags); bug: WARN(1, "ovl_d_real(%pd4, %s:%lu): real dentry not found\n", dentry, inode ? inode->i_sb->s_id : "NULL", inode ? inode->i_ino : 0); diff --git a/fs/splice.c b/fs/splice.c index dcaf185a5731..5a7750bd2eea 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -408,7 +408,8 @@ static ssize_t default_file_splice_read(struct file *in, loff_t *ppos, if (res <= 0) return -ENOMEM; - nr_pages = res / PAGE_SIZE; + BUG_ON(dummy); + nr_pages = DIV_ROUND_UP(res, PAGE_SIZE); vec = __vec; if (nr_pages > PIPE_DEF_BUFFERS) { diff --git a/include/acpi/processor.h b/include/acpi/processor.h index f3db11c24654..c1ba00fc4888 100644 --- a/include/acpi/processor.h +++ b/include/acpi/processor.h @@ -249,6 +249,7 @@ extern int acpi_processor_register_performance(struct acpi_processor_performance *performance, unsigned int cpu); extern void acpi_processor_unregister_performance(unsigned int cpu); +int acpi_processor_pstate_control(void); /* note: this locks both the calling module and the processor module if a _PPC object exists, rmmod is disallowed then */ int acpi_processor_notify_smm(struct module *calling_module); @@ -294,7 +295,7 @@ static inline void acpi_processor_ffh_cstate_enter(struct acpi_processor_cx #ifdef CONFIG_CPU_FREQ void acpi_processor_ppc_init(void); void acpi_processor_ppc_exit(void); -int acpi_processor_ppc_has_changed(struct acpi_processor *pr, int event_flag); +void acpi_processor_ppc_has_changed(struct acpi_processor *pr, int event_flag); extern int acpi_processor_get_bios_limit(int cpu, unsigned int *limit); #else static inline void acpi_processor_ppc_init(void) diff --git a/include/crypto/drbg.h b/include/crypto/drbg.h index 61580b19f9f6..22f884c97387 100644 --- a/include/crypto/drbg.h +++ b/include/crypto/drbg.h @@ -124,6 +124,8 @@ struct drbg_state { struct skcipher_request *ctr_req; /* CTR mode request handle */ __u8 *ctr_null_value_buf; /* CTR mode unaligned buffer */ __u8 *ctr_null_value; /* CTR mode aligned zero buf */ + __u8 *outscratchpadbuf; /* CTR mode output scratchpad */ + __u8 *outscratchpad; /* CTR mode aligned outbuf */ struct completion ctr_completion; /* CTR mode async handler */ int ctr_async_err; /* CTR mode async error */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 7035b997aaa5..6aaf425cebc3 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -14,7 +14,7 @@ * are obviously wrong for any sort of memory access. */ #define BPF_REGISTER_MAX_RANGE (1024 * 1024 * 1024) -#define BPF_REGISTER_MIN_RANGE -(1024 * 1024 * 1024) +#define BPF_REGISTER_MIN_RANGE -1 struct bpf_reg_state { enum bpf_reg_type type; @@ -22,7 +22,8 @@ struct bpf_reg_state { * Used to determine if any memory access using this register will * result in a bad access. */ - u64 min_value, max_value; + s64 min_value; + u64 max_value; union { /* valid when type == CONST_IMM | PTR_TO_STACK | UNKNOWN_VALUE */ s64 imm; diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 432f5c97e18f..928e5ca0caee 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -263,7 +263,9 @@ #endif #endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP && !__CHECKER__ */ -#if GCC_VERSION >= 50000 +#if GCC_VERSION >= 70000 +#define KASAN_ABI_VERSION 5 +#elif GCC_VERSION >= 50000 #define KASAN_ABI_VERSION 4 #elif GCC_VERSION >= 40902 #define KASAN_ABI_VERSION 3 diff --git a/include/linux/cpu.h b/include/linux/cpu.h index b886dc17f2f3..ac0efae38072 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -245,6 +245,8 @@ void arch_cpu_idle_dead(void); int cpu_report_state(int cpu); int cpu_check_up_prepare(int cpu); void cpu_set_state_online(int cpu); +void play_idle(unsigned long duration_ms); + #ifdef CONFIG_HOTPLUG_CPU bool cpu_wait_death(unsigned int cpu, int seconds); bool cpu_report_death(void); diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 32dc0cbd51ca..7e05c5e4e45c 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -175,7 +175,7 @@ void disable_cpufreq(void); u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy); int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu); -int cpufreq_update_policy(unsigned int cpu); +void cpufreq_update_policy(unsigned int cpu); bool have_governor_per_policy(void); struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy); void cpufreq_enable_fast_switch(struct cpufreq_policy *policy); @@ -234,6 +234,10 @@ __ATTR(_name, _perm, show_##_name, NULL) static struct freq_attr _name = \ __ATTR(_name, 0644, show_##_name, store_##_name) +#define cpufreq_freq_attr_wo(_name) \ +static struct freq_attr _name = \ +__ATTR(_name, 0200, NULL, store_##_name) + struct global_attr { struct attribute attr; ssize_t (*show)(struct kobject *kobj, diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index bb31373c3478..da346f2817a8 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -74,6 +74,7 @@ struct cpuidle_driver_kobj; struct cpuidle_device { unsigned int registered:1; unsigned int enabled:1; + unsigned int use_deepest_state:1; unsigned int cpu; int last_residency; @@ -192,11 +193,12 @@ static inline struct cpuidle_driver *cpuidle_get_cpu_driver( static inline struct cpuidle_device *cpuidle_get_device(void) {return NULL; } #endif -#if defined(CONFIG_CPU_IDLE) && defined(CONFIG_SUSPEND) +#ifdef CONFIG_CPU_IDLE extern int cpuidle_find_deepest_state(struct cpuidle_driver *drv, struct cpuidle_device *dev); extern int cpuidle_enter_freeze(struct cpuidle_driver *drv, struct cpuidle_device *dev); +extern void cpuidle_use_deepest_state(bool enable); #else static inline int cpuidle_find_deepest_state(struct cpuidle_driver *drv, struct cpuidle_device *dev) @@ -204,6 +206,9 @@ static inline int cpuidle_find_deepest_state(struct cpuidle_driver *drv, static inline int cpuidle_enter_freeze(struct cpuidle_driver *drv, struct cpuidle_device *dev) {return -ENODEV; } +static inline void cpuidle_use_deepest_state(bool enable) +{ +} #endif /* kernel/sched/idle.c */ @@ -235,8 +240,6 @@ struct cpuidle_governor { int (*select) (struct cpuidle_driver *drv, struct cpuidle_device *dev); void (*reflect) (struct cpuidle_device *dev, int index); - - struct module *owner; }; #ifdef CONFIG_CPU_IDLE diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 2d9b650047a5..d49e26c6cdc7 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -429,6 +429,7 @@ struct intel_iommu { struct page_req_dsc *prq; unsigned char prq_name[16]; /* Name for PRQ interrupt */ struct idr pasid_idr; + u32 pasid_max; #endif struct q_inval *qi; /* Queued invalidation info */ u32 *iommu_state; /* Store iommu states between suspend and resume.*/ diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index f4947fda11e7..8458c5351e56 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -143,7 +143,7 @@ u32 nd_cmd_in_size(struct nvdimm *nvdimm, int cmd, const struct nd_cmd_desc *desc, int idx, void *buf); u32 nd_cmd_out_size(struct nvdimm *nvdimm, int cmd, const struct nd_cmd_desc *desc, int idx, const u32 *in_field, - const u32 *out_field); + const u32 *out_field, unsigned long remainder); int nvdimm_bus_check_dimm_count(struct nvdimm_bus *nvdimm_bus, int dimm_count); struct nd_region *nvdimm_pmem_region_create(struct nvdimm_bus *nvdimm_bus, struct nd_region_desc *ndr_desc); diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 3be7abd6e722..c9f379689dd0 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -476,7 +476,6 @@ enum { enum { MLX4_INTERFACE_STATE_UP = 1 << 0, MLX4_INTERFACE_STATE_DELETION = 1 << 1, - MLX4_INTERFACE_STATE_SHUTDOWN = 1 << 2, }; #define MSTR_SM_CHANGE_MASK (MLX4_EQ_PORT_INFO_MSTR_SM_SL_CHANGE_MASK | \ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index bf04a46f6d5b..e16a2a980ea8 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1619,7 +1619,7 @@ enum netdev_priv_flags { * @dcbnl_ops: Data Center Bridging netlink ops * @num_tc: Number of traffic classes in the net device * @tc_to_txq: XXX: need comments on this one - * @prio_tc_map XXX: need comments on this one + * @prio_tc_map: XXX: need comments on this one * * @fcoe_ddp_xid: Max exchange id for FCoE LRO by ddp * diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index 2ab233661ae5..a58cca8bcb29 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -29,6 +29,7 @@ struct phy_device *of_phy_attach(struct net_device *dev, extern struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np); extern int of_mdio_parse_addr(struct device *dev, const struct device_node *np); extern int of_phy_register_fixed_link(struct device_node *np); +extern void of_phy_deregister_fixed_link(struct device_node *np); extern bool of_phy_is_fixed_link(struct device_node *np); #else /* CONFIG_OF */ @@ -83,6 +84,9 @@ static inline int of_phy_register_fixed_link(struct device_node *np) { return -ENOSYS; } +static inline void of_phy_deregister_fixed_link(struct device_node *np) +{ +} static inline bool of_phy_is_fixed_link(struct device_node *np) { return false; diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index dd15d39e1985..7dbe9148b2f8 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -374,16 +374,13 @@ static inline struct page *read_mapping_page(struct address_space *mapping, } /* - * Get the offset in PAGE_SIZE. - * (TODO: hugepage should have ->index in PAGE_SIZE) + * Get index of the page with in radix-tree + * (TODO: remove once hugetlb pages will have ->index in PAGE_SIZE) */ -static inline pgoff_t page_to_pgoff(struct page *page) +static inline pgoff_t page_to_index(struct page *page) { pgoff_t pgoff; - if (unlikely(PageHeadHuge(page))) - return page->index << compound_order(page); - if (likely(!PageTransTail(page))) return page->index; @@ -397,6 +394,18 @@ static inline pgoff_t page_to_pgoff(struct page *page) } /* + * Get the offset in PAGE_SIZE. + * (TODO: hugepage should have ->index in PAGE_SIZE) + */ +static inline pgoff_t page_to_pgoff(struct page *page) +{ + if (unlikely(PageHeadHuge(page))) + return page->index << compound_order(page); + + return page_to_index(page); +} + +/* * Return byte-offset into filesystem object for page. */ static inline loff_t page_offset(struct page *page) diff --git a/include/linux/pci.h b/include/linux/pci.h index 0e49f70dbd9b..a38772a85588 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1928,6 +1928,20 @@ static inline int pci_pcie_type(const struct pci_dev *dev) return (pcie_caps_reg(dev) & PCI_EXP_FLAGS_TYPE) >> 4; } +static inline struct pci_dev *pcie_find_root_port(struct pci_dev *dev) +{ + while (1) { + if (!pci_is_pcie(dev)) + break; + if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT) + return dev; + if (!dev->bus->self) + break; + dev = dev->bus->self; + } + return NULL; +} + void pci_request_acs(void); bool pci_acs_enabled(struct pci_dev *pdev, u16 acs_flags); bool pci_acs_path_enabled(struct pci_dev *start, diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index a09fe5c009c8..81ece61075df 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -15,11 +15,11 @@ #include <linux/err.h> #include <linux/of.h> #include <linux/notifier.h> +#include <linux/spinlock.h> /* Defines used for the flags field in the struct generic_pm_domain */ #define GENPD_FLAG_PM_CLK (1U << 0) /* PM domain uses PM clk */ - -#define GENPD_MAX_NUM_STATES 8 /* Number of possible low power states */ +#define GENPD_FLAG_IRQ_SAFE (1U << 1) /* PM domain operates in atomic */ enum gpd_status { GPD_STATE_ACTIVE = 0, /* PM domain is active */ @@ -40,15 +40,18 @@ struct gpd_dev_ops { struct genpd_power_state { s64 power_off_latency_ns; s64 power_on_latency_ns; + s64 residency_ns; + struct fwnode_handle *fwnode; }; +struct genpd_lock_ops; + struct generic_pm_domain { struct dev_pm_domain domain; /* PM domain operations */ struct list_head gpd_list_node; /* Node in the global PM domains list */ struct list_head master_links; /* Links with PM domain as a master */ struct list_head slave_links; /* Links with PM domain as a slave */ struct list_head dev_list; /* List of devices */ - struct mutex lock; struct dev_power_governor *gov; struct work_struct power_off_work; struct fwnode_handle *provider; /* Identity of the domain provider */ @@ -70,9 +73,18 @@ struct generic_pm_domain { void (*detach_dev)(struct generic_pm_domain *domain, struct device *dev); unsigned int flags; /* Bit field of configs for genpd */ - struct genpd_power_state states[GENPD_MAX_NUM_STATES]; + struct genpd_power_state *states; unsigned int state_count; /* number of states */ unsigned int state_idx; /* state that genpd will go to when off */ + void *free; /* Free the state that was allocated for default */ + const struct genpd_lock_ops *lock_ops; + union { + struct mutex mlock; + struct { + spinlock_t slock; + unsigned long lock_flags; + }; + }; }; @@ -205,6 +217,8 @@ extern int of_genpd_add_device(struct of_phandle_args *args, extern int of_genpd_add_subdomain(struct of_phandle_args *parent, struct of_phandle_args *new_subdomain); extern struct generic_pm_domain *of_genpd_remove_last(struct device_node *np); +extern int of_genpd_parse_idle_states(struct device_node *dn, + struct genpd_power_state **states, int *n); int genpd_dev_pm_attach(struct device *dev); #else /* !CONFIG_PM_GENERIC_DOMAINS_OF */ @@ -234,6 +248,12 @@ static inline int of_genpd_add_subdomain(struct of_phandle_args *parent, return -ENODEV; } +static inline int of_genpd_parse_idle_states(struct device_node *dn, + struct genpd_power_state **states, int *n) +{ + return -ENODEV; +} + static inline int genpd_dev_pm_attach(struct device *dev) { return -ENODEV; diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index bca26157f5b6..0edd88f93904 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -17,13 +17,65 @@ #include <linux/err.h> #include <linux/notifier.h> +struct clk; +struct regulator; struct dev_pm_opp; struct device; +struct opp_table; enum dev_pm_opp_event { OPP_EVENT_ADD, OPP_EVENT_REMOVE, OPP_EVENT_ENABLE, OPP_EVENT_DISABLE, }; +/** + * struct dev_pm_opp_supply - Power supply voltage/current values + * @u_volt: Target voltage in microvolts corresponding to this OPP + * @u_volt_min: Minimum voltage in microvolts corresponding to this OPP + * @u_volt_max: Maximum voltage in microvolts corresponding to this OPP + * @u_amp: Maximum current drawn by the device in microamperes + * + * This structure stores the voltage/current values for a single power supply. + */ +struct dev_pm_opp_supply { + unsigned long u_volt; + unsigned long u_volt_min; + unsigned long u_volt_max; + unsigned long u_amp; +}; + +/** + * struct dev_pm_opp_info - OPP freq/voltage/current values + * @rate: Target clk rate in hz + * @supplies: Array of voltage/current values for all power supplies + * + * This structure stores the freq/voltage/current values for a single OPP. + */ +struct dev_pm_opp_info { + unsigned long rate; + struct dev_pm_opp_supply *supplies; +}; + +/** + * struct dev_pm_set_opp_data - Set OPP data + * @old_opp: Old OPP info + * @new_opp: New OPP info + * @regulators: Array of regulator pointers + * @regulator_count: Number of regulators + * @clk: Pointer to clk + * @dev: Pointer to the struct device + * + * This structure contains all information required for setting an OPP. + */ +struct dev_pm_set_opp_data { + struct dev_pm_opp_info old_opp; + struct dev_pm_opp_info new_opp; + + struct regulator **regulators; + unsigned int regulator_count; + struct clk *clk; + struct device *dev; +}; + #if defined(CONFIG_PM_OPP) unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp); @@ -62,8 +114,10 @@ int dev_pm_opp_set_supported_hw(struct device *dev, const u32 *versions, void dev_pm_opp_put_supported_hw(struct device *dev); int dev_pm_opp_set_prop_name(struct device *dev, const char *name); void dev_pm_opp_put_prop_name(struct device *dev); -int dev_pm_opp_set_regulator(struct device *dev, const char *name); -void dev_pm_opp_put_regulator(struct device *dev); +struct opp_table *dev_pm_opp_set_regulators(struct device *dev, const char * const names[], unsigned int count); +void dev_pm_opp_put_regulators(struct opp_table *opp_table); +int dev_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data)); +void dev_pm_opp_register_put_opp_helper(struct device *dev); int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq); int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, const struct cpumask *cpumask); int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask); @@ -163,6 +217,14 @@ static inline int dev_pm_opp_set_supported_hw(struct device *dev, static inline void dev_pm_opp_put_supported_hw(struct device *dev) {} +static inline int dev_pm_opp_register_set_opp_helper(struct device *dev, + int (*set_opp)(struct dev_pm_set_opp_data *data)) +{ + return -ENOTSUPP; +} + +static inline void dev_pm_opp_register_put_opp_helper(struct device *dev) {} + static inline int dev_pm_opp_set_prop_name(struct device *dev, const char *name) { return -ENOTSUPP; @@ -170,12 +232,12 @@ static inline int dev_pm_opp_set_prop_name(struct device *dev, const char *name) static inline void dev_pm_opp_put_prop_name(struct device *dev) {} -static inline int dev_pm_opp_set_regulator(struct device *dev, const char *name) +static inline struct opp_table *dev_pm_opp_set_regulators(struct device *dev, const char * const names[], unsigned int count) { - return -ENOTSUPP; + return ERR_PTR(-ENOTSUPP); } -static inline void dev_pm_opp_put_regulator(struct device *dev) {} +static inline void dev_pm_opp_put_regulators(struct opp_table *opp_table) {} static inline int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) { diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 2e14d2667b6c..4957fc185ea9 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -61,12 +61,6 @@ static inline void pm_suspend_ignore_children(struct device *dev, bool enable) dev->power.ignore_children = enable; } -static inline bool pm_children_suspended(struct device *dev) -{ - return dev->power.ignore_children - || !atomic_read(&dev->power.child_count); -} - static inline void pm_runtime_get_noresume(struct device *dev) { atomic_inc(&dev->power.usage_count); @@ -162,7 +156,6 @@ static inline void pm_runtime_allow(struct device *dev) {} static inline void pm_runtime_forbid(struct device *dev) {} static inline void pm_suspend_ignore_children(struct device *dev, bool enable) {} -static inline bool pm_children_suspended(struct device *dev) { return false; } static inline void pm_runtime_get_noresume(struct device *dev) {} static inline void pm_runtime_put_noidle(struct device *dev) {} static inline bool device_run_wake(struct device *dev) { return false; } @@ -265,9 +258,9 @@ static inline int pm_runtime_set_active(struct device *dev) return __pm_runtime_set_status(dev, RPM_ACTIVE); } -static inline void pm_runtime_set_suspended(struct device *dev) +static inline int pm_runtime_set_suspended(struct device *dev) { - __pm_runtime_set_status(dev, RPM_SUSPENDED); + return __pm_runtime_set_status(dev, RPM_SUSPENDED); } static inline void pm_runtime_disable(struct device *dev) diff --git a/include/linux/sched.h b/include/linux/sched.h index 348f51b0ec92..a3d338e15b17 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2254,6 +2254,7 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, /* * Per process flags */ +#define PF_IDLE 0x00000002 /* I am an IDLE thread */ #define PF_EXITING 0x00000004 /* getting shut down */ #define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */ #define PF_VCPU 0x00000010 /* I'm a virtual CPU */ @@ -2567,6 +2568,7 @@ extern void sched_autogroup_create_attach(struct task_struct *p); extern void sched_autogroup_detach(struct task_struct *p); extern void sched_autogroup_fork(struct signal_struct *sig); extern void sched_autogroup_exit(struct signal_struct *sig); +extern void sched_autogroup_exit_task(struct task_struct *p); #ifdef CONFIG_PROC_FS extern void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m); extern int proc_sched_autogroup_set_nice(struct task_struct *p, int nice); @@ -2576,6 +2578,7 @@ static inline void sched_autogroup_create_attach(struct task_struct *p) { } static inline void sched_autogroup_detach(struct task_struct *p) { } static inline void sched_autogroup_fork(struct signal_struct *sig) { } static inline void sched_autogroup_exit(struct signal_struct *sig) { } +static inline void sched_autogroup_exit_task(struct task_struct *p) { } #endif extern int yield_to(struct task_struct *p, bool preempt); @@ -2609,7 +2612,7 @@ extern struct task_struct *idle_task(int cpu); */ static inline bool is_idle_task(const struct task_struct *p) { - return p->pid == 0; + return !!(p->flags & PF_IDLE); } extern struct task_struct *curr_task(int cpu); extern void ia64_set_curr_task(int cpu, struct task_struct *p); diff --git a/include/linux/suspend.h b/include/linux/suspend.h index d9718378a8be..0c729c3c8549 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -194,6 +194,8 @@ struct platform_freeze_ops { }; #ifdef CONFIG_SUSPEND +extern suspend_state_t mem_sleep_default; + /** * suspend_set_ops - set platform dependent suspend operations * @ops: The new suspend operations to set. diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h index 3a375d07d0dc..00d232406f18 100644 --- a/include/linux/usb/cdc_ncm.h +++ b/include/linux/usb/cdc_ncm.h @@ -81,7 +81,8 @@ #define CDC_NCM_TIMER_INTERVAL_MAX (U32_MAX / NSEC_PER_USEC) /* Driver flags */ -#define CDC_NCM_FLAG_NDP_TO_END 0x02 /* NDP is placed at end of frame */ +#define CDC_NCM_FLAG_NDP_TO_END 0x02 /* NDP is placed at end of frame */ +#define CDC_MBIM_FLAG_AVOID_ALTSETTING_TOGGLE 0x04 /* Avoid altsetting toggle during init */ #define cdc_ncm_comm_intf_is_mbim(x) ((x)->desc.bInterfaceSubClass == USB_CDC_SUBCLASS_MBIM && \ (x)->desc.bInterfaceProtocol == USB_CDC_PROTO_NONE) diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index f00bf667ec33..554671c81f4a 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1018,7 +1018,7 @@ static inline void hci_set_drvdata(struct hci_dev *hdev, void *data) } struct hci_dev *hci_dev_get(int index); -struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src); +struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src, u8 src_type); struct hci_dev *hci_alloc_dev(void); void hci_free_dev(struct hci_dev *hdev); diff --git a/include/net/gro_cells.h b/include/net/gro_cells.h index d15214d673b2..2a1abbf8da74 100644 --- a/include/net/gro_cells.h +++ b/include/net/gro_cells.h @@ -68,6 +68,9 @@ static inline int gro_cells_init(struct gro_cells *gcells, struct net_device *de struct gro_cell *cell = per_cpu_ptr(gcells->cells, i); __skb_queue_head_init(&cell->napi_skbs); + + set_bit(NAPI_STATE_NO_BUSY_POLL, &cell->napi.state); + netif_napi_add(dev, &cell->napi, gro_cell_poll, 64); napi_enable(&cell->napi); } diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index b9314b48e39f..f390c3bb05c5 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -243,6 +243,7 @@ int fib_table_dump(struct fib_table *table, struct sk_buff *skb, struct netlink_callback *cb); int fib_table_flush(struct net *net, struct fib_table *table); struct fib_table *fib_trie_unmerge(struct fib_table *main_tb); +void fib_table_flush_external(struct fib_table *table); void fib_free_table(struct fib_table *tb); #ifndef CONFIG_IP_MULTIPLE_TABLES diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 8fed1cd78658..f11ca837361b 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -970,6 +970,8 @@ int compat_ipv6_setsockopt(struct sock *sk, int level, int optname, int compat_ipv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); +int __ip6_datagram_connect(struct sock *sk, struct sockaddr *addr, + int addr_len); int ip6_datagram_connect(struct sock *sk, struct sockaddr *addr, int addr_len); int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *addr, int addr_len); diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index fc4f757107df..0940598c002f 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -170,7 +170,7 @@ static inline struct net *copy_net_ns(unsigned long flags, extern struct list_head net_namespace_list; struct net *get_net_ns_by_pid(pid_t pid); -struct net *get_net_ns_by_fd(int pid); +struct net *get_net_ns_by_fd(int fd); #ifdef CONFIG_SYSCTL void ipx_register_sysctl(void); diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 50418052a520..d9d52c020a70 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -100,6 +100,9 @@ struct nf_conn { possible_net_t ct_net; +#if IS_ENABLED(CONFIG_NF_NAT) + struct rhlist_head nat_bysource; +#endif /* all members below initialized via memset */ u8 __nfct_init_offset[0]; @@ -117,9 +120,6 @@ struct nf_conn { /* Extensions */ struct nf_ct_ext *ext; -#if IS_ENABLED(CONFIG_NF_NAT) - struct rhash_head nat_bysource; -#endif /* Storage reserved for other modules, must be the last member */ union nf_conntrack_proto proto; }; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index d79d1e9b9546..b02af0bf5777 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -313,7 +313,7 @@ void nft_unregister_set(struct nft_set_ops *ops); * @size: maximum set size * @nelems: number of elements * @ndeact: number of deactivated elements queued for removal - * @timeout: default timeout value in msecs + * @timeout: default timeout value in jiffies * @gc_int: garbage collection interval in msecs * @policy: set parameterization (see enum nft_set_policies) * @udlen: user data length diff --git a/include/uapi/linux/can.h b/include/uapi/linux/can.h index 9692cda5f8fc..c48d93a28d1a 100644 --- a/include/uapi/linux/can.h +++ b/include/uapi/linux/can.h @@ -196,5 +196,6 @@ struct can_filter { }; #define CAN_INV_FILTER 0x20000000U /* to be set in can_filter.can_id */ +#define CAN_RAW_FILTER_MAX 512 /* maximum number of can_filter set via setsockopt() */ #endif /* !_UAPI_CAN_H */ diff --git a/include/uapi/linux/if.h b/include/uapi/linux/if.h index e601c8c3bdc7..1158a043342a 100644 --- a/include/uapi/linux/if.h +++ b/include/uapi/linux/if.h @@ -31,7 +31,7 @@ #include <linux/hdlc/ioctl.h> /* For glibc compatibility. An empty enum does not compile. */ -#if __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO != 0 && \ +#if __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO != 0 || \ __UAPI_DEF_IF_NET_DEVICE_FLAGS != 0 /** * enum net_device_flags - &struct net_device flags @@ -99,7 +99,7 @@ enum net_device_flags { IFF_ECHO = 1<<18, /* volatile */ #endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO */ }; -#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO != 0 && __UAPI_DEF_IF_NET_DEVICE_FLAGS != 0 */ +#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO != 0 || __UAPI_DEF_IF_NET_DEVICE_FLAGS != 0 */ /* for compatibility with glibc net/if.h */ #if __UAPI_DEF_IF_NET_DEVICE_FLAGS diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index d6d071fc3c56..3af60ee69053 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -640,7 +640,7 @@ * Control a data application associated with the currently viewed channel, * e.g. teletext or data broadcast application (MHEG, MHP, HbbTV, etc.) */ -#define KEY_DATA 0x275 +#define KEY_DATA 0x277 #define BTN_TRIGGER_HAPPY 0x2c0 #define BTN_TRIGGER_HAPPY1 0x2c0 diff --git a/include/uapi/linux/netfilter/Kbuild b/include/uapi/linux/netfilter/Kbuild index cd26d7a0fd07..03f194aeadc5 100644 --- a/include/uapi/linux/netfilter/Kbuild +++ b/include/uapi/linux/netfilter/Kbuild @@ -5,6 +5,7 @@ header-y += nf_conntrack_ftp.h header-y += nf_conntrack_sctp.h header-y += nf_conntrack_tcp.h header-y += nf_conntrack_tuple_common.h +header-y += nf_log.h header-y += nf_tables.h header-y += nf_tables_compat.h header-y += nf_nat.h diff --git a/include/uapi/linux/tc_act/Kbuild b/include/uapi/linux/tc_act/Kbuild index e3969bd939e4..e3db7403296f 100644 --- a/include/uapi/linux/tc_act/Kbuild +++ b/include/uapi/linux/tc_act/Kbuild @@ -11,3 +11,5 @@ header-y += tc_vlan.h header-y += tc_bpf.h header-y += tc_connmark.h header-y += tc_ife.h +header-y += tc_tunnel_key.h +header-y += tc_skbmod.h diff --git a/init/do_mounts_rd.c b/init/do_mounts_rd.c index 8a09b32e07d6..dd4104c9aa12 100644 --- a/init/do_mounts_rd.c +++ b/init/do_mounts_rd.c @@ -272,7 +272,7 @@ int __init rd_load_image(char *from) sys_write(out_fd, buf, BLOCK_SIZE); #if !defined(CONFIG_S390) if (!(i % 16)) { - printk("%c\b", rotator[rotate & 0x3]); + pr_cont("%c\b", rotator[rotate & 0x3]); rotate++; } #endif diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 99a7e5b388f2..8199821f54cf 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -216,8 +216,8 @@ static void print_verifier_state(struct bpf_verifier_state *state) reg->map_ptr->key_size, reg->map_ptr->value_size); if (reg->min_value != BPF_REGISTER_MIN_RANGE) - verbose(",min_value=%llu", - (unsigned long long)reg->min_value); + verbose(",min_value=%lld", + (long long)reg->min_value); if (reg->max_value != BPF_REGISTER_MAX_RANGE) verbose(",max_value=%llu", (unsigned long long)reg->max_value); @@ -758,7 +758,7 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off, * index'es we need to make sure that whatever we use * will have a set floor within our range. */ - if ((s64)reg->min_value < 0) { + if (reg->min_value < 0) { verbose("R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", regno); return -EACCES; @@ -1468,7 +1468,8 @@ static void check_reg_overflow(struct bpf_reg_state *reg) { if (reg->max_value > BPF_REGISTER_MAX_RANGE) reg->max_value = BPF_REGISTER_MAX_RANGE; - if ((s64)reg->min_value < BPF_REGISTER_MIN_RANGE) + if (reg->min_value < BPF_REGISTER_MIN_RANGE || + reg->min_value > BPF_REGISTER_MAX_RANGE) reg->min_value = BPF_REGISTER_MIN_RANGE; } @@ -1476,7 +1477,8 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env, struct bpf_insn *insn) { struct bpf_reg_state *regs = env->cur_state.regs, *dst_reg; - u64 min_val = BPF_REGISTER_MIN_RANGE, max_val = BPF_REGISTER_MAX_RANGE; + s64 min_val = BPF_REGISTER_MIN_RANGE; + u64 max_val = BPF_REGISTER_MAX_RANGE; bool min_set = false, max_set = false; u8 opcode = BPF_OP(insn->code); @@ -1512,22 +1514,43 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env, return; } + /* If one of our values was at the end of our ranges then we can't just + * do our normal operations to the register, we need to set the values + * to the min/max since they are undefined. + */ + if (min_val == BPF_REGISTER_MIN_RANGE) + dst_reg->min_value = BPF_REGISTER_MIN_RANGE; + if (max_val == BPF_REGISTER_MAX_RANGE) + dst_reg->max_value = BPF_REGISTER_MAX_RANGE; + switch (opcode) { case BPF_ADD: - dst_reg->min_value += min_val; - dst_reg->max_value += max_val; + if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE) + dst_reg->min_value += min_val; + if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) + dst_reg->max_value += max_val; break; case BPF_SUB: - dst_reg->min_value -= min_val; - dst_reg->max_value -= max_val; + if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE) + dst_reg->min_value -= min_val; + if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) + dst_reg->max_value -= max_val; break; case BPF_MUL: - dst_reg->min_value *= min_val; - dst_reg->max_value *= max_val; + if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE) + dst_reg->min_value *= min_val; + if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) + dst_reg->max_value *= max_val; break; case BPF_AND: - /* & is special since it could end up with 0 bits set. */ - dst_reg->min_value &= min_val; + /* Disallow AND'ing of negative numbers, ain't nobody got time + * for that. Otherwise the minimum is 0 and the max is the max + * value we could AND against. + */ + if (min_val < 0) + dst_reg->min_value = BPF_REGISTER_MIN_RANGE; + else + dst_reg->min_value = 0; dst_reg->max_value = max_val; break; case BPF_LSH: @@ -1537,24 +1560,25 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env, */ if (min_val > ilog2(BPF_REGISTER_MAX_RANGE)) dst_reg->min_value = BPF_REGISTER_MIN_RANGE; - else + else if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE) dst_reg->min_value <<= min_val; if (max_val > ilog2(BPF_REGISTER_MAX_RANGE)) dst_reg->max_value = BPF_REGISTER_MAX_RANGE; - else + else if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) dst_reg->max_value <<= max_val; break; case BPF_RSH: - dst_reg->min_value >>= min_val; - dst_reg->max_value >>= max_val; - break; - case BPF_MOD: - /* % is special since it is an unsigned modulus, so the floor - * will always be 0. + /* RSH by a negative number is undefined, and the BPF_RSH is an + * unsigned shift, so make the appropriate casts. */ - dst_reg->min_value = 0; - dst_reg->max_value = max_val - 1; + if (min_val < 0 || dst_reg->min_value < 0) + dst_reg->min_value = BPF_REGISTER_MIN_RANGE; + else + dst_reg->min_value = + (u64)(dst_reg->min_value) >> min_val; + if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) + dst_reg->max_value >>= max_val; break; default: reset_reg_range_values(regs, insn->dst_reg); @@ -2430,6 +2454,7 @@ static bool states_equal(struct bpf_verifier_env *env, struct bpf_verifier_state *old, struct bpf_verifier_state *cur) { + bool varlen_map_access = env->varlen_map_value_access; struct bpf_reg_state *rold, *rcur; int i; @@ -2443,12 +2468,17 @@ static bool states_equal(struct bpf_verifier_env *env, /* If the ranges were not the same, but everything else was and * we didn't do a variable access into a map then we are a-ok. */ - if (!env->varlen_map_value_access && + if (!varlen_map_access && rold->type == rcur->type && rold->imm == rcur->imm) continue; + /* If we didn't map access then again we don't care about the + * mismatched range values and it's ok if our old type was + * UNKNOWN and we didn't go to a NOT_INIT'ed reg. + */ if (rold->type == NOT_INIT || - (rold->type == UNKNOWN_VALUE && rcur->type != NOT_INIT)) + (!varlen_map_access && rold->type == UNKNOWN_VALUE && + rcur->type != NOT_INIT)) continue; if (rold->type == PTR_TO_PACKET && rcur->type == PTR_TO_PACKET && diff --git a/kernel/events/core.c b/kernel/events/core.c index 0e292132efac..02c8421f8c01 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -902,7 +902,15 @@ list_update_cgroup_event(struct perf_event *event, * this will always be called from the right CPU. */ cpuctx = __get_cpu_context(ctx); - cpuctx->cgrp = add ? event->cgrp : NULL; + + /* + * cpuctx->cgrp is NULL until a cgroup event is sched in or + * ctx->nr_cgroup == 0 . + */ + if (add && perf_cgroup_from_task(current, ctx) == event->cgrp) + cpuctx->cgrp = event->cgrp; + else if (!add) + cpuctx->cgrp = NULL; } #else /* !CONFIG_CGROUP_PERF */ @@ -8018,6 +8026,7 @@ restart: * if <size> is not specified, the range is treated as a single address. */ enum { + IF_ACT_NONE = -1, IF_ACT_FILTER, IF_ACT_START, IF_ACT_STOP, @@ -8041,6 +8050,7 @@ static const match_table_t if_tokens = { { IF_SRC_KERNEL, "%u/%u" }, { IF_SRC_FILEADDR, "%u@%s" }, { IF_SRC_KERNELADDR, "%u" }, + { IF_ACT_NONE, NULL }, }; /* diff --git a/kernel/exit.c b/kernel/exit.c index 9d68c45ebbe3..3076f3089919 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -836,6 +836,7 @@ void __noreturn do_exit(long code) */ perf_event_exit_task(tsk); + sched_autogroup_exit_task(tsk); cgroup_exit(tsk); /* diff --git a/kernel/fork.c b/kernel/fork.c index 997ac1d584f7..a8eb821d1d4b 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1540,7 +1540,7 @@ static __latent_entropy struct task_struct *copy_process( goto bad_fork_cleanup_count; delayacct_tsk_init(p); /* Must remain after dup_task_struct() */ - p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER); + p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER | PF_IDLE); p->flags |= PF_FORKNOEXEC; INIT_LIST_HEAD(&p->children); INIT_LIST_HEAD(&p->sibling); diff --git a/kernel/kcov.c b/kernel/kcov.c index 30e6d05aa5a9..3cbb0c879705 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -7,6 +7,7 @@ #include <linux/fs.h> #include <linux/mm.h> #include <linux/printk.h> +#include <linux/sched.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/vmalloc.h> diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 589d763a49b3..4d7ffc0a0d00 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -506,13 +506,13 @@ static void __print_lock_name(struct lock_class *class) name = class->name; if (!name) { name = __get_key_name(class->key, str); - printk("%s", name); + printk(KERN_CONT "%s", name); } else { - printk("%s", name); + printk(KERN_CONT "%s", name); if (class->name_version > 1) - printk("#%d", class->name_version); + printk(KERN_CONT "#%d", class->name_version); if (class->subclass) - printk("/%d", class->subclass); + printk(KERN_CONT "/%d", class->subclass); } } @@ -522,9 +522,9 @@ static void print_lock_name(struct lock_class *class) get_usage_chars(class, usage); - printk(" ("); + printk(KERN_CONT " ("); __print_lock_name(class); - printk("){%s}", usage); + printk(KERN_CONT "){%s}", usage); } static void print_lockdep_cache(struct lockdep_map *lock) @@ -536,7 +536,7 @@ static void print_lockdep_cache(struct lockdep_map *lock) if (!name) name = __get_key_name(lock->key->subkeys, str); - printk("%s", name); + printk(KERN_CONT "%s", name); } static void print_lock(struct held_lock *hlock) @@ -551,13 +551,13 @@ static void print_lock(struct held_lock *hlock) barrier(); if (!class_idx || (class_idx - 1) >= MAX_LOCKDEP_KEYS) { - printk("<RELEASED>\n"); + printk(KERN_CONT "<RELEASED>\n"); return; } print_lock_name(lock_classes + class_idx - 1); - printk(", at: "); - print_ip_sym(hlock->acquire_ip); + printk(KERN_CONT ", at: [<%p>] %pS\n", + (void *)hlock->acquire_ip, (void *)hlock->acquire_ip); } static void lockdep_print_held_locks(struct task_struct *curr) @@ -792,8 +792,8 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) printk("\nnew class %p: %s", class->key, class->name); if (class->name_version > 1) - printk("#%d", class->name_version); - printk("\n"); + printk(KERN_CONT "#%d", class->name_version); + printk(KERN_CONT "\n"); dump_stack(); if (!graph_lock()) { @@ -1071,7 +1071,7 @@ print_circular_bug_entry(struct lock_list *target, int depth) return 0; printk("\n-> #%u", depth); print_lock_name(target->class); - printk(":\n"); + printk(KERN_CONT ":\n"); print_stack_trace(&target->trace, 6); return 0; @@ -1102,11 +1102,11 @@ print_circular_lock_scenario(struct held_lock *src, if (parent != source) { printk("Chain exists of:\n "); __print_lock_name(source); - printk(" --> "); + printk(KERN_CONT " --> "); __print_lock_name(parent); - printk(" --> "); + printk(KERN_CONT " --> "); __print_lock_name(target); - printk("\n\n"); + printk(KERN_CONT "\n\n"); } printk(" Possible unsafe locking scenario:\n\n"); @@ -1114,16 +1114,16 @@ print_circular_lock_scenario(struct held_lock *src, printk(" ---- ----\n"); printk(" lock("); __print_lock_name(target); - printk(");\n"); + printk(KERN_CONT ");\n"); printk(" lock("); __print_lock_name(parent); - printk(");\n"); + printk(KERN_CONT ");\n"); printk(" lock("); __print_lock_name(target); - printk(");\n"); + printk(KERN_CONT ");\n"); printk(" lock("); __print_lock_name(source); - printk(");\n"); + printk(KERN_CONT ");\n"); printk("\n *** DEADLOCK ***\n\n"); } @@ -1359,22 +1359,22 @@ static void print_lock_class_header(struct lock_class *class, int depth) printk("%*s->", depth, ""); print_lock_name(class); - printk(" ops: %lu", class->ops); - printk(" {\n"); + printk(KERN_CONT " ops: %lu", class->ops); + printk(KERN_CONT " {\n"); for (bit = 0; bit < LOCK_USAGE_STATES; bit++) { if (class->usage_mask & (1 << bit)) { int len = depth; len += printk("%*s %s", depth, "", usage_str[bit]); - len += printk(" at:\n"); + len += printk(KERN_CONT " at:\n"); print_stack_trace(class->usage_traces + bit, len); } } printk("%*s }\n", depth, ""); - printk("%*s ... key at: ",depth,""); - print_ip_sym((unsigned long)class->key); + printk("%*s ... key at: [<%p>] %pS\n", + depth, "", class->key, class->key); } /* @@ -1437,11 +1437,11 @@ print_irq_lock_scenario(struct lock_list *safe_entry, if (middle_class != unsafe_class) { printk("Chain exists of:\n "); __print_lock_name(safe_class); - printk(" --> "); + printk(KERN_CONT " --> "); __print_lock_name(middle_class); - printk(" --> "); + printk(KERN_CONT " --> "); __print_lock_name(unsafe_class); - printk("\n\n"); + printk(KERN_CONT "\n\n"); } printk(" Possible interrupt unsafe locking scenario:\n\n"); @@ -1449,18 +1449,18 @@ print_irq_lock_scenario(struct lock_list *safe_entry, printk(" ---- ----\n"); printk(" lock("); __print_lock_name(unsafe_class); - printk(");\n"); + printk(KERN_CONT ");\n"); printk(" local_irq_disable();\n"); printk(" lock("); __print_lock_name(safe_class); - printk(");\n"); + printk(KERN_CONT ");\n"); printk(" lock("); __print_lock_name(middle_class); - printk(");\n"); + printk(KERN_CONT ");\n"); printk(" <Interrupt>\n"); printk(" lock("); __print_lock_name(safe_class); - printk(");\n"); + printk(KERN_CONT ");\n"); printk("\n *** DEADLOCK ***\n\n"); } @@ -1497,9 +1497,9 @@ print_bad_irq_dependency(struct task_struct *curr, print_lock(prev); printk("which would create a new lock dependency:\n"); print_lock_name(hlock_class(prev)); - printk(" ->"); + printk(KERN_CONT " ->"); print_lock_name(hlock_class(next)); - printk("\n"); + printk(KERN_CONT "\n"); printk("\nbut this new dependency connects a %s-irq-safe lock:\n", irqclass); @@ -1521,8 +1521,7 @@ print_bad_irq_dependency(struct task_struct *curr, lockdep_print_held_locks(curr); - printk("\nthe dependencies between %s-irq-safe lock", irqclass); - printk(" and the holding lock:\n"); + printk("\nthe dependencies between %s-irq-safe lock and the holding lock:\n", irqclass); if (!save_trace(&prev_root->trace)) return 0; print_shortest_lock_dependencies(backwards_entry, prev_root); @@ -1694,10 +1693,10 @@ print_deadlock_scenario(struct held_lock *nxt, printk(" ----\n"); printk(" lock("); __print_lock_name(prev); - printk(");\n"); + printk(KERN_CONT ");\n"); printk(" lock("); __print_lock_name(next); - printk(");\n"); + printk(KERN_CONT ");\n"); printk("\n *** DEADLOCK ***\n\n"); printk(" May be due to missing lock nesting notation\n\n"); } @@ -1891,9 +1890,9 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, graph_unlock(); printk("\n new dependency: "); print_lock_name(hlock_class(prev)); - printk(" => "); + printk(KERN_CONT " => "); print_lock_name(hlock_class(next)); - printk("\n"); + printk(KERN_CONT "\n"); dump_stack(); return graph_lock(); } @@ -2343,11 +2342,11 @@ print_usage_bug_scenario(struct held_lock *lock) printk(" ----\n"); printk(" lock("); __print_lock_name(class); - printk(");\n"); + printk(KERN_CONT ");\n"); printk(" <Interrupt>\n"); printk(" lock("); __print_lock_name(class); - printk(");\n"); + printk(KERN_CONT ");\n"); printk("\n *** DEADLOCK ***\n\n"); } @@ -2522,14 +2521,18 @@ check_usage_backwards(struct task_struct *curr, struct held_lock *this, void print_irqtrace_events(struct task_struct *curr) { printk("irq event stamp: %u\n", curr->irq_events); - printk("hardirqs last enabled at (%u): ", curr->hardirq_enable_event); - print_ip_sym(curr->hardirq_enable_ip); - printk("hardirqs last disabled at (%u): ", curr->hardirq_disable_event); - print_ip_sym(curr->hardirq_disable_ip); - printk("softirqs last enabled at (%u): ", curr->softirq_enable_event); - print_ip_sym(curr->softirq_enable_ip); - printk("softirqs last disabled at (%u): ", curr->softirq_disable_event); - print_ip_sym(curr->softirq_disable_ip); + printk("hardirqs last enabled at (%u): [<%p>] %pS\n", + curr->hardirq_enable_event, (void *)curr->hardirq_enable_ip, + (void *)curr->hardirq_enable_ip); + printk("hardirqs last disabled at (%u): [<%p>] %pS\n", + curr->hardirq_disable_event, (void *)curr->hardirq_disable_ip, + (void *)curr->hardirq_disable_ip); + printk("softirqs last enabled at (%u): [<%p>] %pS\n", + curr->softirq_enable_event, (void *)curr->softirq_enable_ip, + (void *)curr->softirq_enable_ip); + printk("softirqs last disabled at (%u): [<%p>] %pS\n", + curr->softirq_disable_event, (void *)curr->softirq_disable_ip, + (void *)curr->softirq_disable_ip); } static int HARDIRQ_verbose(struct lock_class *class) @@ -3235,8 +3238,8 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, if (very_verbose(class)) { printk("\nacquire class [%p] %s", class->key, class->name); if (class->name_version > 1) - printk("#%d", class->name_version); - printk("\n"); + printk(KERN_CONT "#%d", class->name_version); + printk(KERN_CONT "\n"); dump_stack(); } @@ -3378,7 +3381,7 @@ print_unlock_imbalance_bug(struct task_struct *curr, struct lockdep_map *lock, printk("%s/%d is trying to release lock (", curr->comm, task_pid_nr(curr)); print_lockdep_cache(lock); - printk(") at:\n"); + printk(KERN_CONT ") at:\n"); print_ip_sym(ip); printk("but there are no more locks to release!\n"); printk("\nother info that might help us debug this:\n"); @@ -3871,7 +3874,7 @@ print_lock_contention_bug(struct task_struct *curr, struct lockdep_map *lock, printk("%s/%d is trying to contend lock (", curr->comm, task_pid_nr(curr)); print_lockdep_cache(lock); - printk(") at:\n"); + printk(KERN_CONT ") at:\n"); print_ip_sym(ip); printk("but there are no locks held!\n"); printk("\nother info that might help us debug this:\n"); diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h index 51c4b24b6328..c2b88490d857 100644 --- a/kernel/locking/lockdep_internals.h +++ b/kernel/locking/lockdep_internals.h @@ -46,6 +46,14 @@ enum { (LOCKF_USED_IN_HARDIRQ_READ | LOCKF_USED_IN_SOFTIRQ_READ) /* + * CONFIG_PROVE_LOCKING_SMALL is defined for sparc. Sparc requires .text, + * .data and .bss to fit in required 32MB limit for the kernel. With + * PROVE_LOCKING we could go over this limit and cause system boot-up problems. + * So, reduce the static allocations for lockdeps related structures so that + * everything fits in current required size limit. + */ +#ifdef CONFIG_PROVE_LOCKING_SMALL +/* * MAX_LOCKDEP_ENTRIES is the maximum number of lock dependencies * we track. * @@ -54,18 +62,24 @@ enum { * table (if it's not there yet), and we check it for lock order * conflicts and deadlocks. */ +#define MAX_LOCKDEP_ENTRIES 16384UL +#define MAX_LOCKDEP_CHAINS_BITS 15 +#define MAX_STACK_TRACE_ENTRIES 262144UL +#else #define MAX_LOCKDEP_ENTRIES 32768UL #define MAX_LOCKDEP_CHAINS_BITS 16 -#define MAX_LOCKDEP_CHAINS (1UL << MAX_LOCKDEP_CHAINS_BITS) - -#define MAX_LOCKDEP_CHAIN_HLOCKS (MAX_LOCKDEP_CHAINS*5) /* * Stack-trace: tightly packed array of stack backtrace * addresses. Protected by the hash_lock. */ #define MAX_STACK_TRACE_ENTRIES 524288UL +#endif + +#define MAX_LOCKDEP_CHAINS (1UL << MAX_LOCKDEP_CHAINS_BITS) + +#define MAX_LOCKDEP_CHAIN_HLOCKS (MAX_LOCKDEP_CHAINS*5) extern struct list_head all_lock_classes; extern struct lock_chain lock_chains[]; diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 1ec0f48962b3..2c49d76f96c3 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -65,8 +65,72 @@ static inline void clear_rt_mutex_waiters(struct rt_mutex *lock) static void fixup_rt_mutex_waiters(struct rt_mutex *lock) { - if (!rt_mutex_has_waiters(lock)) - clear_rt_mutex_waiters(lock); + unsigned long owner, *p = (unsigned long *) &lock->owner; + + if (rt_mutex_has_waiters(lock)) + return; + + /* + * The rbtree has no waiters enqueued, now make sure that the + * lock->owner still has the waiters bit set, otherwise the + * following can happen: + * + * CPU 0 CPU 1 CPU2 + * l->owner=T1 + * rt_mutex_lock(l) + * lock(l->lock) + * l->owner = T1 | HAS_WAITERS; + * enqueue(T2) + * boost() + * unlock(l->lock) + * block() + * + * rt_mutex_lock(l) + * lock(l->lock) + * l->owner = T1 | HAS_WAITERS; + * enqueue(T3) + * boost() + * unlock(l->lock) + * block() + * signal(->T2) signal(->T3) + * lock(l->lock) + * dequeue(T2) + * deboost() + * unlock(l->lock) + * lock(l->lock) + * dequeue(T3) + * ==> wait list is empty + * deboost() + * unlock(l->lock) + * lock(l->lock) + * fixup_rt_mutex_waiters() + * if (wait_list_empty(l) { + * l->owner = owner + * owner = l->owner & ~HAS_WAITERS; + * ==> l->owner = T1 + * } + * lock(l->lock) + * rt_mutex_unlock(l) fixup_rt_mutex_waiters() + * if (wait_list_empty(l) { + * owner = l->owner & ~HAS_WAITERS; + * cmpxchg(l->owner, T1, NULL) + * ===> Success (l->owner = NULL) + * + * l->owner = owner + * ==> l->owner = T1 + * } + * + * With the check for the waiter bit in place T3 on CPU2 will not + * overwrite. All tasks fiddling with the waiters bit are + * serialized by l->lock, so nothing else can modify the waiters + * bit. If the bit is set then nothing can change l->owner either + * so the simple RMW is safe. The cmpxchg() will simply fail if it + * happens in the middle of the RMW because the waiters bit is + * still set. + */ + owner = READ_ONCE(*p); + if (owner & RT_MUTEX_HAS_WAITERS) + WRITE_ONCE(*p, owner & ~RT_MUTEX_HAS_WAITERS); } /* diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h index 4f5f83c7d2d3..e317e1cbb3eb 100644 --- a/kernel/locking/rtmutex_common.h +++ b/kernel/locking/rtmutex_common.h @@ -75,8 +75,9 @@ task_top_pi_waiter(struct task_struct *p) static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock) { - return (struct task_struct *) - ((unsigned long)lock->owner & ~RT_MUTEX_OWNER_MASKALL); + unsigned long owner = (unsigned long) READ_ONCE(lock->owner); + + return (struct task_struct *) (owner & ~RT_MUTEX_OWNER_MASKALL); } /* diff --git a/kernel/module.c b/kernel/module.c index f57dd63186e6..0e54d5bf0097 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1301,8 +1301,9 @@ static int check_version(Elf_Shdr *sechdrs, goto bad_version; } - pr_warn("%s: no symbol version for %s\n", mod->name, symname); - return 0; + /* Broken toolchain. Warn once, then let it go.. */ + pr_warn_once("%s: no symbol version for %s\n", mod->name, symname); + return 1; bad_version: pr_warn("%s: disagrees about version of symbol %s\n", diff --git a/kernel/power/main.c b/kernel/power/main.c index 281a697fd458..d401c21136d1 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -78,6 +78,78 @@ static ssize_t pm_async_store(struct kobject *kobj, struct kobj_attribute *attr, power_attr(pm_async); +#ifdef CONFIG_SUSPEND +static ssize_t mem_sleep_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + char *s = buf; + suspend_state_t i; + + for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++) + if (mem_sleep_states[i]) { + const char *label = mem_sleep_states[i]; + + if (mem_sleep_current == i) + s += sprintf(s, "[%s] ", label); + else + s += sprintf(s, "%s ", label); + } + + /* Convert the last space to a newline if needed. */ + if (s != buf) + *(s-1) = '\n'; + + return (s - buf); +} + +static suspend_state_t decode_suspend_state(const char *buf, size_t n) +{ + suspend_state_t state; + char *p; + int len; + + p = memchr(buf, '\n', n); + len = p ? p - buf : n; + + for (state = PM_SUSPEND_MIN; state < PM_SUSPEND_MAX; state++) { + const char *label = mem_sleep_states[state]; + + if (label && len == strlen(label) && !strncmp(buf, label, len)) + return state; + } + + return PM_SUSPEND_ON; +} + +static ssize_t mem_sleep_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t n) +{ + suspend_state_t state; + int error; + + error = pm_autosleep_lock(); + if (error) + return error; + + if (pm_autosleep_state() > PM_SUSPEND_ON) { + error = -EBUSY; + goto out; + } + + state = decode_suspend_state(buf, n); + if (state < PM_SUSPEND_MAX && state > PM_SUSPEND_ON) + mem_sleep_current = state; + else + error = -EINVAL; + + out: + pm_autosleep_unlock(); + return error ? error : n; +} + +power_attr(mem_sleep); +#endif /* CONFIG_SUSPEND */ + #ifdef CONFIG_PM_DEBUG int pm_test_level = TEST_NONE; @@ -368,12 +440,16 @@ static ssize_t state_store(struct kobject *kobj, struct kobj_attribute *attr, } state = decode_state(buf, n); - if (state < PM_SUSPEND_MAX) + if (state < PM_SUSPEND_MAX) { + if (state == PM_SUSPEND_MEM) + state = mem_sleep_current; + error = pm_suspend(state); - else if (state == PM_SUSPEND_MAX) + } else if (state == PM_SUSPEND_MAX) { error = hibernate(); - else + } else { error = -EINVAL; + } out: pm_autosleep_unlock(); @@ -485,6 +561,9 @@ static ssize_t autosleep_store(struct kobject *kobj, && strcmp(buf, "off") && strcmp(buf, "off\n")) return -EINVAL; + if (state == PM_SUSPEND_MEM) + state = mem_sleep_current; + error = pm_autosleep_set_state(state); return error ? error : n; } @@ -602,6 +681,9 @@ static struct attribute * g[] = { #ifdef CONFIG_PM_SLEEP &pm_async_attr.attr, &wakeup_count_attr.attr, +#ifdef CONFIG_SUSPEND + &mem_sleep_attr.attr, +#endif #ifdef CONFIG_PM_AUTOSLEEP &autosleep_attr.attr, #endif diff --git a/kernel/power/power.h b/kernel/power/power.h index 56d1d0dedf76..1dfa0da827d3 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -189,11 +189,15 @@ extern void swsusp_show_speed(ktime_t, ktime_t, unsigned int, char *); #ifdef CONFIG_SUSPEND /* kernel/power/suspend.c */ -extern const char *pm_labels[]; +extern const char * const pm_labels[]; extern const char *pm_states[]; +extern const char *mem_sleep_states[]; +extern suspend_state_t mem_sleep_current; extern int suspend_devices_and_enter(suspend_state_t state); #else /* !CONFIG_SUSPEND */ +#define mem_sleep_current PM_SUSPEND_ON + static inline int suspend_devices_and_enter(suspend_state_t state) { return -ENOSYS; diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 6ccb08f57fcb..f67ceb7768b8 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -32,8 +32,21 @@ #include "power.h" -const char *pm_labels[] = { "mem", "standby", "freeze", NULL }; +const char * const pm_labels[] = { + [PM_SUSPEND_FREEZE] = "freeze", + [PM_SUSPEND_STANDBY] = "standby", + [PM_SUSPEND_MEM] = "mem", +}; const char *pm_states[PM_SUSPEND_MAX]; +static const char * const mem_sleep_labels[] = { + [PM_SUSPEND_FREEZE] = "s2idle", + [PM_SUSPEND_STANDBY] = "shallow", + [PM_SUSPEND_MEM] = "deep", +}; +const char *mem_sleep_states[PM_SUSPEND_MAX]; + +suspend_state_t mem_sleep_current = PM_SUSPEND_FREEZE; +suspend_state_t mem_sleep_default = PM_SUSPEND_MAX; unsigned int pm_suspend_global_flags; EXPORT_SYMBOL_GPL(pm_suspend_global_flags); @@ -110,30 +123,32 @@ static bool valid_state(suspend_state_t state) return suspend_ops && suspend_ops->valid && suspend_ops->valid(state); } -/* - * If this is set, the "mem" label always corresponds to the deepest sleep state - * available, the "standby" label corresponds to the second deepest sleep state - * available (if any), and the "freeze" label corresponds to the remaining - * available sleep state (if there is one). - */ -static bool relative_states; - void __init pm_states_init(void) { + /* "mem" and "freeze" are always present in /sys/power/state. */ + pm_states[PM_SUSPEND_MEM] = pm_labels[PM_SUSPEND_MEM]; + pm_states[PM_SUSPEND_FREEZE] = pm_labels[PM_SUSPEND_FREEZE]; /* - * freeze state should be supported even without any suspend_ops, - * initialize pm_states accordingly here + * Suspend-to-idle should be supported even without any suspend_ops, + * initialize mem_sleep_states[] accordingly here. */ - pm_states[PM_SUSPEND_FREEZE] = pm_labels[relative_states ? 0 : 2]; + mem_sleep_states[PM_SUSPEND_FREEZE] = mem_sleep_labels[PM_SUSPEND_FREEZE]; } -static int __init sleep_states_setup(char *str) +static int __init mem_sleep_default_setup(char *str) { - relative_states = !strncmp(str, "1", 1); + suspend_state_t state; + + for (state = PM_SUSPEND_FREEZE; state <= PM_SUSPEND_MEM; state++) + if (mem_sleep_labels[state] && + !strcmp(str, mem_sleep_labels[state])) { + mem_sleep_default = state; + break; + } + return 1; } - -__setup("relative_sleep_states=", sleep_states_setup); +__setup("mem_sleep_default=", mem_sleep_default_setup); /** * suspend_set_ops - Set the global suspend method table. @@ -141,21 +156,21 @@ __setup("relative_sleep_states=", sleep_states_setup); */ void suspend_set_ops(const struct platform_suspend_ops *ops) { - suspend_state_t i; - int j = 0; - lock_system_sleep(); suspend_ops = ops; - for (i = PM_SUSPEND_MEM; i >= PM_SUSPEND_STANDBY; i--) - if (valid_state(i)) { - pm_states[i] = pm_labels[j++]; - } else if (!relative_states) { - pm_states[i] = NULL; - j++; - } - pm_states[PM_SUSPEND_FREEZE] = pm_labels[j]; + if (valid_state(PM_SUSPEND_STANDBY)) { + mem_sleep_states[PM_SUSPEND_STANDBY] = mem_sleep_labels[PM_SUSPEND_STANDBY]; + pm_states[PM_SUSPEND_STANDBY] = pm_labels[PM_SUSPEND_STANDBY]; + if (mem_sleep_default == PM_SUSPEND_STANDBY) + mem_sleep_current = PM_SUSPEND_STANDBY; + } + if (valid_state(PM_SUSPEND_MEM)) { + mem_sleep_states[PM_SUSPEND_MEM] = mem_sleep_labels[PM_SUSPEND_MEM]; + if (mem_sleep_default >= PM_SUSPEND_MEM) + mem_sleep_current = PM_SUSPEND_MEM; + } unlock_system_sleep(); } diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c index a5d966cb8891..da39489d2d80 100644 --- a/kernel/sched/auto_group.c +++ b/kernel/sched/auto_group.c @@ -111,10 +111,13 @@ bool task_wants_autogroup(struct task_struct *p, struct task_group *tg) { if (tg != &root_task_group) return false; - /* - * We can only assume the task group can't go away on us if - * autogroup_move_group() can see us on ->thread_group list. + * If we race with autogroup_move_group() the caller can use the old + * value of signal->autogroup but in this case sched_move_task() will + * be called again before autogroup_kref_put(). + * + * However, there is no way sched_autogroup_exit_task() could tell us + * to avoid autogroup->tg, so we abuse PF_EXITING flag for this case. */ if (p->flags & PF_EXITING) return false; @@ -122,6 +125,16 @@ bool task_wants_autogroup(struct task_struct *p, struct task_group *tg) return true; } +void sched_autogroup_exit_task(struct task_struct *p) +{ + /* + * We are going to call exit_notify() and autogroup_move_group() can't + * see this thread after that: we can no longer use signal->autogroup. + * See the PF_EXITING check in task_wants_autogroup(). + */ + sched_move_task(p); +} + static void autogroup_move_group(struct task_struct *p, struct autogroup *ag) { @@ -138,13 +151,20 @@ autogroup_move_group(struct task_struct *p, struct autogroup *ag) } p->signal->autogroup = autogroup_kref_get(ag); - - if (!READ_ONCE(sysctl_sched_autogroup_enabled)) - goto out; - + /* + * We can't avoid sched_move_task() after we changed signal->autogroup, + * this process can already run with task_group() == prev->tg or we can + * race with cgroup code which can read autogroup = prev under rq->lock. + * In the latter case for_each_thread() can not miss a migrating thread, + * cpu_cgroup_attach() must not be possible after cgroup_exit() and it + * can't be removed from thread list, we hold ->siglock. + * + * If an exiting thread was already removed from thread list we rely on + * sched_autogroup_exit_task(). + */ for_each_thread(p, t) sched_move_task(t); -out: + unlock_task_sighand(p, &flags); autogroup_kref_put(prev); } @@ -192,6 +212,7 @@ int proc_sched_autogroup_set_nice(struct task_struct *p, int nice) { static unsigned long next = INITIAL_JIFFIES; struct autogroup *ag; + unsigned long shares; int err; if (nice < MIN_NICE || nice > MAX_NICE) @@ -210,9 +231,10 @@ int proc_sched_autogroup_set_nice(struct task_struct *p, int nice) next = HZ / 10 + jiffies; ag = autogroup_task_get(p); + shares = scale_load(sched_prio_to_weight[nice + 20]); down_write(&ag->lock); - err = sched_group_set_shares(ag->tg, sched_prio_to_weight[nice + 20]); + err = sched_group_set_shares(ag->tg, shares); if (!err) ag->nice = nice; up_write(&ag->lock); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 154fd689fe02..c95fbcd9fe1f 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5279,6 +5279,7 @@ void init_idle(struct task_struct *idle, int cpu) __sched_fork(0, idle); idle->state = TASK_RUNNING; idle->se.exec_start = sched_clock(); + idle->flags |= PF_IDLE; kasan_unpoison_task_stack(idle); diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 69e06898997d..fd4659313640 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -12,11 +12,14 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/cpufreq.h> +#include <linux/kthread.h> #include <linux/slab.h> #include <trace/events/power.h> #include "sched.h" +#define SUGOV_KTHREAD_PRIORITY 50 + struct sugov_tunables { struct gov_attr_set attr_set; unsigned int rate_limit_us; @@ -35,8 +38,10 @@ struct sugov_policy { /* The next fields are only needed if fast switch cannot be used. */ struct irq_work irq_work; - struct work_struct work; + struct kthread_work work; struct mutex work_lock; + struct kthread_worker worker; + struct task_struct *thread; bool work_in_progress; bool need_freq_update; @@ -291,7 +296,7 @@ static void sugov_update_shared(struct update_util_data *hook, u64 time, raw_spin_unlock(&sg_policy->update_lock); } -static void sugov_work(struct work_struct *work) +static void sugov_work(struct kthread_work *work) { struct sugov_policy *sg_policy = container_of(work, struct sugov_policy, work); @@ -308,7 +313,21 @@ static void sugov_irq_work(struct irq_work *irq_work) struct sugov_policy *sg_policy; sg_policy = container_of(irq_work, struct sugov_policy, irq_work); - schedule_work_on(smp_processor_id(), &sg_policy->work); + + /* + * For RT and deadline tasks, the schedutil governor shoots the + * frequency to maximum. Special care must be taken to ensure that this + * kthread doesn't result in the same behavior. + * + * This is (mostly) guaranteed by the work_in_progress flag. The flag is + * updated only at the end of the sugov_work() function and before that + * the schedutil governor rejects all other frequency scaling requests. + * + * There is a very rare case though, where the RT thread yields right + * after the work_in_progress flag is cleared. The effects of that are + * neglected for now. + */ + kthread_queue_work(&sg_policy->worker, &sg_policy->work); } /************************** sysfs interface ************************/ @@ -371,19 +390,64 @@ static struct sugov_policy *sugov_policy_alloc(struct cpufreq_policy *policy) return NULL; sg_policy->policy = policy; - init_irq_work(&sg_policy->irq_work, sugov_irq_work); - INIT_WORK(&sg_policy->work, sugov_work); - mutex_init(&sg_policy->work_lock); raw_spin_lock_init(&sg_policy->update_lock); return sg_policy; } static void sugov_policy_free(struct sugov_policy *sg_policy) { - mutex_destroy(&sg_policy->work_lock); kfree(sg_policy); } +static int sugov_kthread_create(struct sugov_policy *sg_policy) +{ + struct task_struct *thread; + struct sched_param param = { .sched_priority = MAX_USER_RT_PRIO / 2 }; + struct cpufreq_policy *policy = sg_policy->policy; + int ret; + + /* kthread only required for slow path */ + if (policy->fast_switch_enabled) + return 0; + + kthread_init_work(&sg_policy->work, sugov_work); + kthread_init_worker(&sg_policy->worker); + thread = kthread_create(kthread_worker_fn, &sg_policy->worker, + "sugov:%d", + cpumask_first(policy->related_cpus)); + if (IS_ERR(thread)) { + pr_err("failed to create sugov thread: %ld\n", PTR_ERR(thread)); + return PTR_ERR(thread); + } + + ret = sched_setscheduler_nocheck(thread, SCHED_FIFO, ¶m); + if (ret) { + kthread_stop(thread); + pr_warn("%s: failed to set SCHED_FIFO\n", __func__); + return ret; + } + + sg_policy->thread = thread; + kthread_bind_mask(thread, policy->related_cpus); + init_irq_work(&sg_policy->irq_work, sugov_irq_work); + mutex_init(&sg_policy->work_lock); + + wake_up_process(thread); + + return 0; +} + +static void sugov_kthread_stop(struct sugov_policy *sg_policy) +{ + /* kthread only required for slow path */ + if (sg_policy->policy->fast_switch_enabled) + return; + + kthread_flush_worker(&sg_policy->worker); + kthread_stop(sg_policy->thread); + mutex_destroy(&sg_policy->work_lock); +} + static struct sugov_tunables *sugov_tunables_alloc(struct sugov_policy *sg_policy) { struct sugov_tunables *tunables; @@ -416,16 +480,24 @@ static int sugov_init(struct cpufreq_policy *policy) if (policy->governor_data) return -EBUSY; + cpufreq_enable_fast_switch(policy); + sg_policy = sugov_policy_alloc(policy); - if (!sg_policy) - return -ENOMEM; + if (!sg_policy) { + ret = -ENOMEM; + goto disable_fast_switch; + } + + ret = sugov_kthread_create(sg_policy); + if (ret) + goto free_sg_policy; mutex_lock(&global_tunables_lock); if (global_tunables) { if (WARN_ON(have_governor_per_policy())) { ret = -EINVAL; - goto free_sg_policy; + goto stop_kthread; } policy->governor_data = sg_policy; sg_policy->tunables = global_tunables; @@ -437,7 +509,7 @@ static int sugov_init(struct cpufreq_policy *policy) tunables = sugov_tunables_alloc(sg_policy); if (!tunables) { ret = -ENOMEM; - goto free_sg_policy; + goto stop_kthread; } tunables->rate_limit_us = LATENCY_MULTIPLIER; @@ -454,20 +526,25 @@ static int sugov_init(struct cpufreq_policy *policy) if (ret) goto fail; - out: +out: mutex_unlock(&global_tunables_lock); - - cpufreq_enable_fast_switch(policy); return 0; - fail: +fail: policy->governor_data = NULL; sugov_tunables_free(tunables); - free_sg_policy: +stop_kthread: + sugov_kthread_stop(sg_policy); + +free_sg_policy: mutex_unlock(&global_tunables_lock); sugov_policy_free(sg_policy); + +disable_fast_switch: + cpufreq_disable_fast_switch(policy); + pr_err("initialization failed (error %d)\n", ret); return ret; } @@ -478,8 +555,6 @@ static void sugov_exit(struct cpufreq_policy *policy) struct sugov_tunables *tunables = sg_policy->tunables; unsigned int count; - cpufreq_disable_fast_switch(policy); - mutex_lock(&global_tunables_lock); count = gov_attr_set_put(&tunables->attr_set, &sg_policy->tunables_hook); @@ -489,7 +564,9 @@ static void sugov_exit(struct cpufreq_policy *policy) mutex_unlock(&global_tunables_lock); + sugov_kthread_stop(sg_policy); sugov_policy_free(sg_policy); + cpufreq_disable_fast_switch(policy); } static int sugov_start(struct cpufreq_policy *policy) @@ -535,8 +612,10 @@ static void sugov_stop(struct cpufreq_policy *policy) synchronize_sched(); - irq_work_sync(&sg_policy->irq_work); - cancel_work_sync(&sg_policy->work); + if (!policy->fast_switch_enabled) { + irq_work_sync(&sg_policy->irq_work); + kthread_cancel_work_sync(&sg_policy->work); + } } static void sugov_limits(struct cpufreq_policy *policy) diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 1d8718d5300d..6a4bae0a649d 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -164,11 +164,14 @@ static void cpuidle_idle_call(void) * timekeeping to prevent timer interrupts from kicking us out of idle * until a proper wakeup interrupt happens. */ - if (idle_should_freeze()) { - entered_state = cpuidle_enter_freeze(drv, dev); - if (entered_state > 0) { - local_irq_enable(); - goto exit_idle; + + if (idle_should_freeze() || dev->use_deepest_state) { + if (idle_should_freeze()) { + entered_state = cpuidle_enter_freeze(drv, dev); + if (entered_state > 0) { + local_irq_enable(); + goto exit_idle; + } } next_state = cpuidle_find_deepest_state(drv, dev); @@ -202,76 +205,65 @@ exit_idle: * * Called with polling cleared. */ -static void cpu_idle_loop(void) +static void do_idle(void) { - int cpu = smp_processor_id(); - - while (1) { - /* - * If the arch has a polling bit, we maintain an invariant: - * - * Our polling bit is clear if we're not scheduled (i.e. if - * rq->curr != rq->idle). This means that, if rq->idle has - * the polling bit set, then setting need_resched is - * guaranteed to cause the cpu to reschedule. - */ - - __current_set_polling(); - quiet_vmstat(); - tick_nohz_idle_enter(); + /* + * If the arch has a polling bit, we maintain an invariant: + * + * Our polling bit is clear if we're not scheduled (i.e. if rq->curr != + * rq->idle). This means that, if rq->idle has the polling bit set, + * then setting need_resched is guaranteed to cause the CPU to + * reschedule. + */ - while (!need_resched()) { - check_pgt_cache(); - rmb(); + __current_set_polling(); + tick_nohz_idle_enter(); - if (cpu_is_offline(cpu)) { - cpuhp_report_idle_dead(); - arch_cpu_idle_dead(); - } + while (!need_resched()) { + check_pgt_cache(); + rmb(); - local_irq_disable(); - arch_cpu_idle_enter(); - - /* - * In poll mode we reenable interrupts and spin. - * - * Also if we detected in the wakeup from idle - * path that the tick broadcast device expired - * for us, we don't want to go deep idle as we - * know that the IPI is going to arrive right - * away - */ - if (cpu_idle_force_poll || tick_check_broadcast_expired()) - cpu_idle_poll(); - else - cpuidle_idle_call(); - - arch_cpu_idle_exit(); + if (cpu_is_offline(smp_processor_id())) { + cpuhp_report_idle_dead(); + arch_cpu_idle_dead(); } - /* - * Since we fell out of the loop above, we know - * TIF_NEED_RESCHED must be set, propagate it into - * PREEMPT_NEED_RESCHED. - * - * This is required because for polling idle loops we will - * not have had an IPI to fold the state for us. - */ - preempt_set_need_resched(); - tick_nohz_idle_exit(); - __current_clr_polling(); + local_irq_disable(); + arch_cpu_idle_enter(); /* - * We promise to call sched_ttwu_pending and reschedule - * if need_resched is set while polling is set. That - * means that clearing polling needs to be visible - * before doing these things. + * In poll mode we reenable interrupts and spin. Also if we + * detected in the wakeup from idle path that the tick + * broadcast device expired for us, we don't want to go deep + * idle as we know that the IPI is going to arrive right away. */ - smp_mb__after_atomic(); - - sched_ttwu_pending(); - schedule_preempt_disabled(); + if (cpu_idle_force_poll || tick_check_broadcast_expired()) + cpu_idle_poll(); + else + cpuidle_idle_call(); + arch_cpu_idle_exit(); } + + /* + * Since we fell out of the loop above, we know TIF_NEED_RESCHED must + * be set, propagate it into PREEMPT_NEED_RESCHED. + * + * This is required because for polling idle loops we will not have had + * an IPI to fold the state for us. + */ + preempt_set_need_resched(); + tick_nohz_idle_exit(); + __current_clr_polling(); + + /* + * We promise to call sched_ttwu_pending() and reschedule if + * need_resched() is set while polling is set. That means that clearing + * polling needs to be visible before doing these things. + */ + smp_mb__after_atomic(); + + sched_ttwu_pending(); + schedule_preempt_disabled(); } bool cpu_in_idle(unsigned long pc) @@ -280,6 +272,56 @@ bool cpu_in_idle(unsigned long pc) pc < (unsigned long)__cpuidle_text_end; } +struct idle_timer { + struct hrtimer timer; + int done; +}; + +static enum hrtimer_restart idle_inject_timer_fn(struct hrtimer *timer) +{ + struct idle_timer *it = container_of(timer, struct idle_timer, timer); + + WRITE_ONCE(it->done, 1); + set_tsk_need_resched(current); + + return HRTIMER_NORESTART; +} + +void play_idle(unsigned long duration_ms) +{ + struct idle_timer it; + + /* + * Only FIFO tasks can disable the tick since they don't need the forced + * preemption. + */ + WARN_ON_ONCE(current->policy != SCHED_FIFO); + WARN_ON_ONCE(current->nr_cpus_allowed != 1); + WARN_ON_ONCE(!(current->flags & PF_KTHREAD)); + WARN_ON_ONCE(!(current->flags & PF_NO_SETAFFINITY)); + WARN_ON_ONCE(!duration_ms); + + rcu_sleep_check(); + preempt_disable(); + current->flags |= PF_IDLE; + cpuidle_use_deepest_state(true); + + it.done = 0; + hrtimer_init_on_stack(&it.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + it.timer.function = idle_inject_timer_fn; + hrtimer_start(&it.timer, ms_to_ktime(duration_ms), HRTIMER_MODE_REL_PINNED); + + while (!READ_ONCE(it.done)) + do_idle(); + + cpuidle_use_deepest_state(false); + current->flags &= ~PF_IDLE; + + preempt_fold_need_resched(); + preempt_enable(); +} +EXPORT_SYMBOL_GPL(play_idle); + void cpu_startup_entry(enum cpuhp_state state) { /* @@ -299,5 +341,6 @@ void cpu_startup_entry(enum cpuhp_state state) #endif arch_cpu_idle_prepare(); cpuhp_online_idle(state); - cpu_idle_loop(); + while (1) + do_idle(); } diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index b01e547d4d04..a6c8db1d62f6 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1085,6 +1085,9 @@ config PROVE_LOCKING For more details, see Documentation/locking/lockdep-design.txt. +config PROVE_LOCKING_SMALL + bool + config LOCKDEP bool depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT diff --git a/lib/debugobjects.c b/lib/debugobjects.c index a8e12601eb37..056052dc8e91 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -362,6 +362,7 @@ void debug_object_init(void *addr, struct debug_obj_descr *descr) __debug_object_init(addr, descr, 0); } +EXPORT_SYMBOL_GPL(debug_object_init); /** * debug_object_init_on_stack - debug checks when an object on stack is @@ -376,6 +377,7 @@ void debug_object_init_on_stack(void *addr, struct debug_obj_descr *descr) __debug_object_init(addr, descr, 1); } +EXPORT_SYMBOL_GPL(debug_object_init_on_stack); /** * debug_object_activate - debug checks when an object is activated @@ -449,6 +451,7 @@ int debug_object_activate(void *addr, struct debug_obj_descr *descr) } return 0; } +EXPORT_SYMBOL_GPL(debug_object_activate); /** * debug_object_deactivate - debug checks when an object is deactivated @@ -496,6 +499,7 @@ void debug_object_deactivate(void *addr, struct debug_obj_descr *descr) raw_spin_unlock_irqrestore(&db->lock, flags); } +EXPORT_SYMBOL_GPL(debug_object_deactivate); /** * debug_object_destroy - debug checks when an object is destroyed @@ -542,6 +546,7 @@ void debug_object_destroy(void *addr, struct debug_obj_descr *descr) out_unlock: raw_spin_unlock_irqrestore(&db->lock, flags); } +EXPORT_SYMBOL_GPL(debug_object_destroy); /** * debug_object_free - debug checks when an object is freed @@ -582,6 +587,7 @@ void debug_object_free(void *addr, struct debug_obj_descr *descr) out_unlock: raw_spin_unlock_irqrestore(&db->lock, flags); } +EXPORT_SYMBOL_GPL(debug_object_free); /** * debug_object_assert_init - debug checks when object should be init-ed @@ -626,6 +632,7 @@ void debug_object_assert_init(void *addr, struct debug_obj_descr *descr) raw_spin_unlock_irqrestore(&db->lock, flags); } +EXPORT_SYMBOL_GPL(debug_object_assert_init); /** * debug_object_active_state - debug checks object usage state machine @@ -673,6 +680,7 @@ debug_object_active_state(void *addr, struct debug_obj_descr *descr, raw_spin_unlock_irqrestore(&db->lock, flags); } +EXPORT_SYMBOL_GPL(debug_object_active_state); #ifdef CONFIG_DEBUG_OBJECTS_FREE static void __debug_check_no_obj_freed(const void *address, unsigned long size) diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c index 872a15a2a637..f3a217ea0388 100644 --- a/lib/locking-selftest.c +++ b/lib/locking-selftest.c @@ -980,23 +980,23 @@ static void dotest(void (*testcase_fn)(void), int expected, int lockclass_mask) #ifndef CONFIG_PROVE_LOCKING if (expected == FAILURE && debug_locks) { expected_testcase_failures++; - printk("failed|"); + pr_cont("failed|"); } else #endif if (debug_locks != expected) { unexpected_testcase_failures++; - printk("FAILED|"); + pr_cont("FAILED|"); dump_stack(); } else { testcase_successes++; - printk(" ok |"); + pr_cont(" ok |"); } testcase_total++; if (debug_locks_verbose) - printk(" lockclass mask: %x, debug_locks: %d, expected: %d\n", + pr_cont(" lockclass mask: %x, debug_locks: %d, expected: %d\n", lockclass_mask, debug_locks, expected); /* * Some tests (e.g. double-unlock) might corrupt the preemption @@ -1021,26 +1021,26 @@ static inline void print_testname(const char *testname) #define DO_TESTCASE_1(desc, name, nr) \ print_testname(desc"/"#nr); \ dotest(name##_##nr, SUCCESS, LOCKTYPE_RWLOCK); \ - printk("\n"); + pr_cont("\n"); #define DO_TESTCASE_1B(desc, name, nr) \ print_testname(desc"/"#nr); \ dotest(name##_##nr, FAILURE, LOCKTYPE_RWLOCK); \ - printk("\n"); + pr_cont("\n"); #define DO_TESTCASE_3(desc, name, nr) \ print_testname(desc"/"#nr); \ dotest(name##_spin_##nr, FAILURE, LOCKTYPE_SPIN); \ dotest(name##_wlock_##nr, FAILURE, LOCKTYPE_RWLOCK); \ dotest(name##_rlock_##nr, SUCCESS, LOCKTYPE_RWLOCK); \ - printk("\n"); + pr_cont("\n"); #define DO_TESTCASE_3RW(desc, name, nr) \ print_testname(desc"/"#nr); \ dotest(name##_spin_##nr, FAILURE, LOCKTYPE_SPIN|LOCKTYPE_RWLOCK);\ dotest(name##_wlock_##nr, FAILURE, LOCKTYPE_RWLOCK); \ dotest(name##_rlock_##nr, SUCCESS, LOCKTYPE_RWLOCK); \ - printk("\n"); + pr_cont("\n"); #define DO_TESTCASE_6(desc, name) \ print_testname(desc); \ @@ -1050,7 +1050,7 @@ static inline void print_testname(const char *testname) dotest(name##_mutex, FAILURE, LOCKTYPE_MUTEX); \ dotest(name##_wsem, FAILURE, LOCKTYPE_RWSEM); \ dotest(name##_rsem, FAILURE, LOCKTYPE_RWSEM); \ - printk("\n"); + pr_cont("\n"); #define DO_TESTCASE_6_SUCCESS(desc, name) \ print_testname(desc); \ @@ -1060,7 +1060,7 @@ static inline void print_testname(const char *testname) dotest(name##_mutex, SUCCESS, LOCKTYPE_MUTEX); \ dotest(name##_wsem, SUCCESS, LOCKTYPE_RWSEM); \ dotest(name##_rsem, SUCCESS, LOCKTYPE_RWSEM); \ - printk("\n"); + pr_cont("\n"); /* * 'read' variant: rlocks must not trigger. @@ -1073,7 +1073,7 @@ static inline void print_testname(const char *testname) dotest(name##_mutex, FAILURE, LOCKTYPE_MUTEX); \ dotest(name##_wsem, FAILURE, LOCKTYPE_RWSEM); \ dotest(name##_rsem, FAILURE, LOCKTYPE_RWSEM); \ - printk("\n"); + pr_cont("\n"); #define DO_TESTCASE_2I(desc, name, nr) \ DO_TESTCASE_1("hard-"desc, name##_hard, nr); \ @@ -1726,25 +1726,25 @@ static void ww_tests(void) dotest(ww_test_fail_acquire, SUCCESS, LOCKTYPE_WW); dotest(ww_test_normal, SUCCESS, LOCKTYPE_WW); dotest(ww_test_unneeded_slow, FAILURE, LOCKTYPE_WW); - printk("\n"); + pr_cont("\n"); print_testname("ww contexts mixing"); dotest(ww_test_two_contexts, FAILURE, LOCKTYPE_WW); dotest(ww_test_diff_class, FAILURE, LOCKTYPE_WW); - printk("\n"); + pr_cont("\n"); print_testname("finishing ww context"); dotest(ww_test_context_done_twice, FAILURE, LOCKTYPE_WW); dotest(ww_test_context_unlock_twice, FAILURE, LOCKTYPE_WW); dotest(ww_test_context_fini_early, FAILURE, LOCKTYPE_WW); dotest(ww_test_context_lock_after_done, FAILURE, LOCKTYPE_WW); - printk("\n"); + pr_cont("\n"); print_testname("locking mismatches"); dotest(ww_test_object_unlock_twice, FAILURE, LOCKTYPE_WW); dotest(ww_test_object_lock_unbalanced, FAILURE, LOCKTYPE_WW); dotest(ww_test_object_lock_stale_context, FAILURE, LOCKTYPE_WW); - printk("\n"); + pr_cont("\n"); print_testname("EDEADLK handling"); dotest(ww_test_edeadlk_normal, SUCCESS, LOCKTYPE_WW); @@ -1757,11 +1757,11 @@ static void ww_tests(void) dotest(ww_test_edeadlk_acquire_more_edeadlk_slow, FAILURE, LOCKTYPE_WW); dotest(ww_test_edeadlk_acquire_wrong, FAILURE, LOCKTYPE_WW); dotest(ww_test_edeadlk_acquire_wrong_slow, FAILURE, LOCKTYPE_WW); - printk("\n"); + pr_cont("\n"); print_testname("spinlock nest unlocked"); dotest(ww_test_spin_nest_unlocked, FAILURE, LOCKTYPE_WW); - printk("\n"); + pr_cont("\n"); printk(" -----------------------------------------------------\n"); printk(" |block | try |context|\n"); @@ -1771,25 +1771,25 @@ static void ww_tests(void) dotest(ww_test_context_block, FAILURE, LOCKTYPE_WW); dotest(ww_test_context_try, SUCCESS, LOCKTYPE_WW); dotest(ww_test_context_context, SUCCESS, LOCKTYPE_WW); - printk("\n"); + pr_cont("\n"); print_testname("try"); dotest(ww_test_try_block, FAILURE, LOCKTYPE_WW); dotest(ww_test_try_try, SUCCESS, LOCKTYPE_WW); dotest(ww_test_try_context, FAILURE, LOCKTYPE_WW); - printk("\n"); + pr_cont("\n"); print_testname("block"); dotest(ww_test_block_block, FAILURE, LOCKTYPE_WW); dotest(ww_test_block_try, SUCCESS, LOCKTYPE_WW); dotest(ww_test_block_context, FAILURE, LOCKTYPE_WW); - printk("\n"); + pr_cont("\n"); print_testname("spinlock"); dotest(ww_test_spin_block, FAILURE, LOCKTYPE_WW); dotest(ww_test_spin_try, SUCCESS, LOCKTYPE_WW); dotest(ww_test_spin_context, FAILURE, LOCKTYPE_WW); - printk("\n"); + pr_cont("\n"); } void locking_selftest(void) @@ -1829,32 +1829,32 @@ void locking_selftest(void) printk(" --------------------------------------------------------------------------\n"); print_testname("recursive read-lock"); - printk(" |"); + pr_cont(" |"); dotest(rlock_AA1, SUCCESS, LOCKTYPE_RWLOCK); - printk(" |"); + pr_cont(" |"); dotest(rsem_AA1, FAILURE, LOCKTYPE_RWSEM); - printk("\n"); + pr_cont("\n"); print_testname("recursive read-lock #2"); - printk(" |"); + pr_cont(" |"); dotest(rlock_AA1B, SUCCESS, LOCKTYPE_RWLOCK); - printk(" |"); + pr_cont(" |"); dotest(rsem_AA1B, FAILURE, LOCKTYPE_RWSEM); - printk("\n"); + pr_cont("\n"); print_testname("mixed read-write-lock"); - printk(" |"); + pr_cont(" |"); dotest(rlock_AA2, FAILURE, LOCKTYPE_RWLOCK); - printk(" |"); + pr_cont(" |"); dotest(rsem_AA2, FAILURE, LOCKTYPE_RWSEM); - printk("\n"); + pr_cont("\n"); print_testname("mixed write-read-lock"); - printk(" |"); + pr_cont(" |"); dotest(rlock_AA3, FAILURE, LOCKTYPE_RWLOCK); - printk(" |"); + pr_cont(" |"); dotest(rsem_AA3, FAILURE, LOCKTYPE_RWSEM); - printk("\n"); + pr_cont("\n"); printk(" --------------------------------------------------------------------------\n"); diff --git a/lib/mpi/mpi-pow.c b/lib/mpi/mpi-pow.c index 5464c8744ea9..e24388a863a7 100644 --- a/lib/mpi/mpi-pow.c +++ b/lib/mpi/mpi-pow.c @@ -64,8 +64,13 @@ int mpi_powm(MPI res, MPI base, MPI exp, MPI mod) if (!esize) { /* Exponent is zero, result is 1 mod MOD, i.e., 1 or 0 * depending on if MOD equals 1. */ - rp[0] = 1; res->nlimbs = (msize == 1 && mod->d[0] == 1) ? 0 : 1; + if (res->nlimbs) { + if (mpi_resize(res, 1) < 0) + goto enomem; + rp = res->d; + rp[0] = 1; + } res->sign = 0; goto leave; } diff --git a/lib/test_kasan.c b/lib/test_kasan.c index 5e51872b3fc1..fbdf87920093 100644 --- a/lib/test_kasan.c +++ b/lib/test_kasan.c @@ -20,6 +20,11 @@ #include <linux/uaccess.h> #include <linux/module.h> +/* + * Note: test functions are marked noinline so that their names appear in + * reports. + */ + static noinline void __init kmalloc_oob_right(void) { char *ptr; @@ -411,6 +416,29 @@ static noinline void __init copy_user_test(void) kfree(kmem); } +static noinline void __init use_after_scope_test(void) +{ + volatile char *volatile p; + + pr_info("use-after-scope on int\n"); + { + int local = 0; + + p = (char *)&local; + } + p[0] = 1; + p[3] = 1; + + pr_info("use-after-scope on array\n"); + { + char local[1024] = {0}; + + p = local; + } + p[0] = 1; + p[1023] = 1; +} + static int __init kmalloc_tests_init(void) { kmalloc_oob_right(); @@ -436,6 +464,7 @@ static int __init kmalloc_tests_init(void) kasan_global_oob(); ksize_unpoisons_memory(); copy_user_test(); + use_after_scope_test(); return -EAGAIN; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index eff3de359d50..d4a6e4001512 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1456,9 +1456,9 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, new_ptl = pmd_lockptr(mm, new_pmd); if (new_ptl != old_ptl) spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING); - if (pmd_present(*old_pmd) && pmd_dirty(*old_pmd)) - force_flush = true; pmd = pmdp_huge_get_and_clear(mm, old_addr, old_pmd); + if (pmd_present(pmd) && pmd_dirty(pmd)) + force_flush = true; VM_BUG_ON(!pmd_none(*new_pmd)); if (pmd_move_must_withdraw(new_ptl, old_ptl) && diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c index 70c009741aab..b2a0cff2bb35 100644 --- a/mm/kasan/kasan.c +++ b/mm/kasan/kasan.c @@ -80,7 +80,14 @@ void kasan_unpoison_task_stack(struct task_struct *task) /* Unpoison the stack for the current task beyond a watermark sp value. */ asmlinkage void kasan_unpoison_task_stack_below(const void *watermark) { - __kasan_unpoison_stack(current, watermark); + /* + * Calculate the task stack base address. Avoid using 'current' + * because this function is called by early resume code which hasn't + * yet set up the percpu register (%gs). + */ + void *base = (void *)((unsigned long)watermark & ~(THREAD_SIZE - 1)); + + kasan_unpoison_shadow(base, watermark - base); } /* @@ -764,6 +771,25 @@ EXPORT_SYMBOL(__asan_storeN_noabort); void __asan_handle_no_return(void) {} EXPORT_SYMBOL(__asan_handle_no_return); +/* Emitted by compiler to poison large objects when they go out of scope. */ +void __asan_poison_stack_memory(const void *addr, size_t size) +{ + /* + * Addr is KASAN_SHADOW_SCALE_SIZE-aligned and the object is surrounded + * by redzones, so we simply round up size to simplify logic. + */ + kasan_poison_shadow(addr, round_up(size, KASAN_SHADOW_SCALE_SIZE), + KASAN_USE_AFTER_SCOPE); +} +EXPORT_SYMBOL(__asan_poison_stack_memory); + +/* Emitted by compiler to unpoison large objects when they go into scope. */ +void __asan_unpoison_stack_memory(const void *addr, size_t size) +{ + kasan_unpoison_shadow(addr, size); +} +EXPORT_SYMBOL(__asan_unpoison_stack_memory); + #ifdef CONFIG_MEMORY_HOTPLUG static int kasan_mem_notifier(struct notifier_block *nb, unsigned long action, void *data) diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index e5c2181fee6f..1c260e6b3b3c 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -21,6 +21,7 @@ #define KASAN_STACK_MID 0xF2 #define KASAN_STACK_RIGHT 0xF3 #define KASAN_STACK_PARTIAL 0xF4 +#define KASAN_USE_AFTER_SCOPE 0xF8 /* Don't break randconfig/all*config builds */ #ifndef KASAN_ABI_VERSION @@ -53,6 +54,9 @@ struct kasan_global { #if KASAN_ABI_VERSION >= 4 struct kasan_source_location *location; #endif +#if KASAN_ABI_VERSION >= 5 + char *odr_indicator; +#endif }; /** diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 24c1211fe9d5..073325aedc68 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -90,6 +90,9 @@ static void print_error_description(struct kasan_access_info *info) case KASAN_KMALLOC_FREE: bug_type = "use-after-free"; break; + case KASAN_USE_AFTER_SCOPE: + bug_type = "use-after-scope"; + break; } pr_err("BUG: KASAN: %s in %pS at addr %p\n", diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 728d7790dc2d..87e1a7ca3846 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -103,6 +103,7 @@ static struct khugepaged_scan khugepaged_scan = { .mm_head = LIST_HEAD_INIT(khugepaged_scan.mm_head), }; +#ifdef CONFIG_SYSFS static ssize_t scan_sleep_millisecs_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) @@ -295,6 +296,7 @@ struct attribute_group khugepaged_attr_group = { .attrs = khugepaged_attr, .name = "khugepaged", }; +#endif /* CONFIG_SYSFS */ #define VM_NO_KHUGEPAGED (VM_SPECIAL | VM_HUGETLB) diff --git a/mm/mlock.c b/mm/mlock.c index 145a4258ddbc..cdbed8aaa426 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -190,10 +190,13 @@ unsigned int munlock_vma_page(struct page *page) */ spin_lock_irq(zone_lru_lock(zone)); - nr_pages = hpage_nr_pages(page); - if (!TestClearPageMlocked(page)) + if (!TestClearPageMlocked(page)) { + /* Potentially, PTE-mapped THP: do not skip the rest PTEs */ + nr_pages = 1; goto unlock_out; + } + nr_pages = hpage_nr_pages(page); __mod_zone_page_state(zone, NR_MLOCK, -nr_pages); if (__munlock_isolate_lru_page(page, true)) { diff --git a/mm/mremap.c b/mm/mremap.c index 6ccecc03f56a..30d7d2482eea 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -149,14 +149,18 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, if (pte_none(*old_pte)) continue; + pte = ptep_get_and_clear(mm, old_addr, old_pte); /* - * We are remapping a dirty PTE, make sure to - * flush TLB before we drop the PTL for the + * If we are remapping a dirty PTE, make sure + * to flush TLB before we drop the PTL for the * old PTE or we may race with page_mkclean(). + * + * This check has to be done after we removed the + * old PTE from page tables or another thread may + * dirty it after the check and before the removal. */ - if (pte_present(*old_pte) && pte_dirty(*old_pte)) + if (pte_present(pte) && pte_dirty(pte)) force_flush = true; - pte = ptep_get_and_clear(mm, old_addr, old_pte); pte = move_pte(pte, new_vma->vm_page_prot, old_addr, new_addr); pte = move_soft_dirty_pte(pte); set_pte_at(mm, new_addr, new_pte, pte); diff --git a/mm/shmem.c b/mm/shmem.c index 166ebf5d2bce..9d32e1cb9f38 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1848,6 +1848,18 @@ unlock: return error; } +/* + * This is like autoremove_wake_function, but it removes the wait queue + * entry unconditionally - even if something else had already woken the + * target. + */ +static int synchronous_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key) +{ + int ret = default_wake_function(wait, mode, sync, key); + list_del_init(&wait->task_list); + return ret; +} + static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { struct inode *inode = file_inode(vma->vm_file); @@ -1883,7 +1895,7 @@ static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) vmf->pgoff >= shmem_falloc->start && vmf->pgoff < shmem_falloc->next) { wait_queue_head_t *shmem_falloc_waitq; - DEFINE_WAIT(shmem_fault_wait); + DEFINE_WAIT_FUNC(shmem_fault_wait, synchronous_wake_function); ret = VM_FAULT_NOPAGE; if ((vmf->flags & FAULT_FLAG_ALLOW_RETRY) && @@ -2665,6 +2677,7 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, spin_lock(&inode->i_lock); inode->i_private = NULL; wake_up_all(&shmem_falloc_waitq); + WARN_ON_ONCE(!list_empty(&shmem_falloc_waitq.task_list)); spin_unlock(&inode->i_lock); error = 0; goto out; diff --git a/mm/truncate.c b/mm/truncate.c index a01cce450a26..8d8c62d89e6d 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -283,7 +283,7 @@ void truncate_inode_pages_range(struct address_space *mapping, if (!trylock_page(page)) continue; - WARN_ON(page_to_pgoff(page) != index); + WARN_ON(page_to_index(page) != index); if (PageWriteback(page)) { unlock_page(page); continue; @@ -371,7 +371,7 @@ void truncate_inode_pages_range(struct address_space *mapping, } lock_page(page); - WARN_ON(page_to_pgoff(page) != index); + WARN_ON(page_to_index(page) != index); wait_on_page_writeback(page); truncate_inode_page(mapping, page); unlock_page(page); @@ -492,7 +492,7 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, if (!trylock_page(page)) continue; - WARN_ON(page_to_pgoff(page) != index); + WARN_ON(page_to_index(page) != index); /* Middle of THP: skip */ if (PageTransTail(page)) { @@ -612,7 +612,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping, } lock_page(page); - WARN_ON(page_to_pgoff(page) != index); + WARN_ON(page_to_index(page) != index); if (page->mapping != mapping) { unlock_page(page); continue; diff --git a/mm/vmscan.c b/mm/vmscan.c index 76fda2268148..d75cdf360730 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2354,6 +2354,8 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc } } + cond_resched(); + if (nr_reclaimed < nr_to_reclaim || scan_adjusted) continue; diff --git a/mm/workingset.c b/mm/workingset.c index 617475f529f4..fb1f9183d89a 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -348,7 +348,7 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker, shadow_nodes = list_lru_shrink_count(&workingset_shadow_nodes, sc); local_irq_enable(); - if (memcg_kmem_enabled()) { + if (sc->memcg) { pages = mem_cgroup_node_nr_lru_pages(sc->memcg, sc->nid, LRU_ALL_FILE); } else { diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index e034afbd1bb0..08ce36147c4c 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -652,6 +652,7 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface, batadv_softif_destroy_sysfs(hard_iface->soft_iface); } + hard_iface->soft_iface = NULL; batadv_hardif_put(hard_iface); out: diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c index 2333777f919d..8af1611b8ab2 100644 --- a/net/batman-adv/tp_meter.c +++ b/net/batman-adv/tp_meter.c @@ -837,6 +837,7 @@ static int batadv_tp_send(void *arg) primary_if = batadv_primary_if_get_selected(bat_priv); if (unlikely(!primary_if)) { err = BATADV_TP_REASON_DST_UNREACHABLE; + tp_vars->reason = err; goto out; } diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 7f663092f6de..0dc85eb1cb7a 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -3282,7 +3282,7 @@ static bool batadv_send_my_tt_response(struct batadv_priv *bat_priv, &tvlv_tt_data, &tt_change, &tt_len); - if (!tt_len) + if (!tt_len || !tvlv_len) goto unlock; /* Copy the last orig_node's OGM buffer */ @@ -3300,7 +3300,7 @@ static bool batadv_send_my_tt_response(struct batadv_priv *bat_priv, &tvlv_tt_data, &tt_change, &tt_len); - if (!tt_len) + if (!tt_len || !tvlv_len) goto out; /* fill the rest of the tvlv with the real TT entries */ diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index d020299baba4..1904a93f47d5 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -1090,7 +1090,6 @@ static int get_l2cap_conn(char *buf, bdaddr_t *addr, u8 *addr_type, { struct hci_conn *hcon; struct hci_dev *hdev; - bdaddr_t *src = BDADDR_ANY; int n; n = sscanf(buf, "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx %hhu", @@ -1101,7 +1100,8 @@ static int get_l2cap_conn(char *buf, bdaddr_t *addr, u8 *addr_type, if (n < 7) return -EINVAL; - hdev = hci_get_route(addr, src); + /* The LE_PUBLIC address type is ignored because of BDADDR_ANY */ + hdev = hci_get_route(addr, BDADDR_ANY, BDADDR_LE_PUBLIC); if (!hdev) return -ENOENT; diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 3809617aa98d..dc59eae54717 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -613,7 +613,7 @@ int hci_conn_del(struct hci_conn *conn) return 0; } -struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src) +struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src, uint8_t src_type) { int use_src = bacmp(src, BDADDR_ANY); struct hci_dev *hdev = NULL, *d; @@ -634,7 +634,29 @@ struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src) */ if (use_src) { - if (!bacmp(&d->bdaddr, src)) { + bdaddr_t id_addr; + u8 id_addr_type; + + if (src_type == BDADDR_BREDR) { + if (!lmp_bredr_capable(d)) + continue; + bacpy(&id_addr, &d->bdaddr); + id_addr_type = BDADDR_BREDR; + } else { + if (!lmp_le_capable(d)) + continue; + + hci_copy_identity_address(d, &id_addr, + &id_addr_type); + + /* Convert from HCI to three-value type */ + if (id_addr_type == ADDR_LE_DEV_PUBLIC) + id_addr_type = BDADDR_LE_PUBLIC; + else + id_addr_type = BDADDR_LE_RANDOM; + } + + if (!bacmp(&id_addr, src) && id_addr_type == src_type) { hdev = d; break; } } else { diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index d4cad29b033f..577f1c01454a 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -7060,7 +7060,7 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, BT_DBG("%pMR -> %pMR (type %u) psm 0x%2.2x", &chan->src, dst, dst_type, __le16_to_cpu(psm)); - hdev = hci_get_route(dst, &chan->src); + hdev = hci_get_route(dst, &chan->src, chan->src_type); if (!hdev) return -EHOSTUNREACH; diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index 8e385a0ae60e..2f2cb5e27cdd 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -178,7 +178,7 @@ static void rfcomm_reparent_device(struct rfcomm_dev *dev) struct hci_dev *hdev; struct hci_conn *conn; - hdev = hci_get_route(&dev->dst, &dev->src); + hdev = hci_get_route(&dev->dst, &dev->src, BDADDR_BREDR); if (!hdev) return; diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index f52bcbf2e58c..3125ce670c2f 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -219,7 +219,7 @@ static int sco_connect(struct sock *sk) BT_DBG("%pMR -> %pMR", &sco_pi(sk)->src, &sco_pi(sk)->dst); - hdev = hci_get_route(&sco_pi(sk)->dst, &sco_pi(sk)->src); + hdev = hci_get_route(&sco_pi(sk)->dst, &sco_pi(sk)->src, BDADDR_BREDR); if (!hdev) return -EHOSTUNREACH; diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c index e120307c6e36..f88c4df3f91e 100644 --- a/net/bridge/br_sysfs_br.c +++ b/net/bridge/br_sysfs_br.c @@ -898,6 +898,7 @@ int br_sysfs_addbr(struct net_device *dev) if (!br->ifobj) { pr_info("%s: can't add kobject (directory) %s/%s\n", __func__, dev->name, SYSFS_BRIDGE_PORT_SUBDIR); + err = -ENOMEM; goto out3; } return 0; diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index aa209b1066c9..92cbbd2afddb 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -1107,10 +1107,7 @@ static struct net_proto_family caif_family_ops = { static int __init caif_sktinit_module(void) { - int err = sock_register(&caif_family_ops); - if (!err) - return err; - return 0; + return sock_register(&caif_family_ops); } static void __exit caif_sktexit_module(void) diff --git a/net/can/bcm.c b/net/can/bcm.c index 8af9d25ff988..436a7537e6a9 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -77,7 +77,7 @@ (CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG) : \ (CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG)) -#define CAN_BCM_VERSION "20160617" +#define CAN_BCM_VERSION "20161123" MODULE_DESCRIPTION("PF_CAN broadcast manager protocol"); MODULE_LICENSE("Dual BSD/GPL"); @@ -109,8 +109,9 @@ struct bcm_op { u32 count; u32 nframes; u32 currframe; - struct canfd_frame *frames; - struct canfd_frame *last_frames; + /* void pointers to arrays of struct can[fd]_frame */ + void *frames; + void *last_frames; struct canfd_frame sframe; struct canfd_frame last_sframe; struct sock *sk; @@ -681,7 +682,7 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data) if (op->flags & RX_FILTER_ID) { /* the easiest case */ - bcm_rx_update_and_send(op, &op->last_frames[0], rxframe); + bcm_rx_update_and_send(op, op->last_frames, rxframe); goto rx_starttimer; } @@ -1068,7 +1069,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, if (msg_head->nframes) { /* update CAN frames content */ - err = memcpy_from_msg((u8 *)op->frames, msg, + err = memcpy_from_msg(op->frames, msg, msg_head->nframes * op->cfsiz); if (err < 0) return err; @@ -1118,7 +1119,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, } if (msg_head->nframes) { - err = memcpy_from_msg((u8 *)op->frames, msg, + err = memcpy_from_msg(op->frames, msg, msg_head->nframes * op->cfsiz); if (err < 0) { if (op->frames != &op->sframe) @@ -1163,6 +1164,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, /* check flags */ if (op->flags & RX_RTR_FRAME) { + struct canfd_frame *frame0 = op->frames; /* no timers in RTR-mode */ hrtimer_cancel(&op->thrtimer); @@ -1174,8 +1176,8 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, * prevent a full-load-loopback-test ... ;-] */ if ((op->flags & TX_CP_CAN_ID) || - (op->frames[0].can_id == op->can_id)) - op->frames[0].can_id = op->can_id & ~CAN_RTR_FLAG; + (frame0->can_id == op->can_id)) + frame0->can_id = op->can_id & ~CAN_RTR_FLAG; } else { if (op->flags & SETTIMER) { diff --git a/net/can/raw.c b/net/can/raw.c index 972c187d40ab..b075f028d7e2 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -499,6 +499,9 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, if (optlen % sizeof(struct can_filter) != 0) return -EINVAL; + if (optlen > CAN_RAW_FILTER_MAX * sizeof(struct can_filter)) + return -EINVAL; + count = optlen / sizeof(struct can_filter); if (count > 1) { diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 977489820eb9..047a1752ece1 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -2479,6 +2479,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_GET_TS_INFO: case ETHTOOL_GEEE: case ETHTOOL_GTUNABLE: + case ETHTOOL_GLINKSETTINGS: break; default: if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) diff --git a/net/core/flow.c b/net/core/flow.c index 3937b1b68d5b..18e8893d4be5 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -95,7 +95,6 @@ static void flow_cache_gc_task(struct work_struct *work) list_for_each_entry_safe(fce, n, &gc_list, u.gc_list) { flow_entry_kill(fce, xfrm); atomic_dec(&xfrm->flow_cache_gc_count); - WARN_ON(atomic_read(&xfrm->flow_cache_gc_count) < 0); } } @@ -236,9 +235,8 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir, if (fcp->hash_count > fc->high_watermark) flow_cache_shrink(fc, fcp); - if (fcp->hash_count > 2 * fc->high_watermark || - atomic_read(&net->xfrm.flow_cache_gc_count) > fc->high_watermark) { - atomic_inc(&net->xfrm.flow_cache_genid); + if (atomic_read(&net->xfrm.flow_cache_gc_count) > + 2 * num_online_cpus() * fc->high_watermark) { flo = ERR_PTR(-ENOBUFS); goto ret_object; } diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 69e4463a4b1b..c6d8207ffa7e 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -1013,4 +1013,4 @@ static int __init init_default_flow_dissectors(void) return 0; } -late_initcall_sync(init_default_flow_dissectors); +core_initcall(init_default_flow_dissectors); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index f61c0e02a413..7001da910c6b 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -219,6 +219,8 @@ int peernet2id_alloc(struct net *net, struct net *peer) bool alloc; int id; + if (atomic_read(&net->count) == 0) + return NETNSA_NSID_NOT_ASSIGNED; spin_lock_irqsave(&net->nsid_lock, flags); alloc = atomic_read(&peer->count) == 0 ? false : true; id = __peernet2id_alloc(net, peer, &alloc); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index db313ec7af32..a6196cf844f6 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -840,18 +840,20 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev, if (dev->dev.parent && dev_is_pci(dev->dev.parent) && (ext_filter_mask & RTEXT_FILTER_VF)) { int num_vfs = dev_num_vf(dev->dev.parent); - size_t size = nla_total_size(sizeof(struct nlattr)); - size += nla_total_size(num_vfs * sizeof(struct nlattr)); + size_t size = nla_total_size(0); size += num_vfs * - (nla_total_size(sizeof(struct ifla_vf_mac)) + - nla_total_size(MAX_VLAN_LIST_LEN * - sizeof(struct nlattr)) + + (nla_total_size(0) + + nla_total_size(sizeof(struct ifla_vf_mac)) + + nla_total_size(sizeof(struct ifla_vf_vlan)) + + nla_total_size(0) + /* nest IFLA_VF_VLAN_LIST */ nla_total_size(MAX_VLAN_LIST_LEN * sizeof(struct ifla_vf_vlan_info)) + nla_total_size(sizeof(struct ifla_vf_spoofchk)) + + nla_total_size(sizeof(struct ifla_vf_tx_rate)) + nla_total_size(sizeof(struct ifla_vf_rate)) + nla_total_size(sizeof(struct ifla_vf_link_state)) + nla_total_size(sizeof(struct ifla_vf_rss_query_en)) + + nla_total_size(0) + /* nest IFLA_VF_STATS */ /* IFLA_VF_STATS_RX_PACKETS */ nla_total_size_64bit(sizeof(__u64)) + /* IFLA_VF_STATS_TX_PACKETS */ @@ -899,7 +901,8 @@ static size_t rtnl_port_size(const struct net_device *dev, static size_t rtnl_xdp_size(const struct net_device *dev) { - size_t xdp_size = nla_total_size(1); /* XDP_ATTACHED */ + size_t xdp_size = nla_total_size(0) + /* nest IFLA_XDP */ + nla_total_size(1); /* XDP_ATTACHED */ if (!dev->netdev_ops->ndo_xdp) return 0; @@ -928,8 +931,8 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(4) /* IFLA_PROMISCUITY */ + nla_total_size(4) /* IFLA_NUM_TX_QUEUES */ + nla_total_size(4) /* IFLA_NUM_RX_QUEUES */ - + nla_total_size(4) /* IFLA_MAX_GSO_SEGS */ - + nla_total_size(4) /* IFLA_MAX_GSO_SIZE */ + + nla_total_size(4) /* IFLA_GSO_MAX_SEGS */ + + nla_total_size(4) /* IFLA_GSO_MAX_SIZE */ + nla_total_size(1) /* IFLA_OPERSTATE */ + nla_total_size(1) /* IFLA_LINKMODE */ + nla_total_size(4) /* IFLA_CARRIER_CHANGES */ @@ -1606,7 +1609,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) head = &net->dev_index_head[h]; hlist_for_each_entry(dev, head, index_hlist) { if (link_dump_filtered(dev, master_idx, kind_ops)) - continue; + goto cont; if (idx < s_idx) goto cont; err = rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, @@ -2734,7 +2737,7 @@ static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh) ext_filter_mask)); } - return min_ifinfo_dump_size; + return nlmsg_total_size(min_ifinfo_dump_size); } static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) @@ -2849,7 +2852,10 @@ nla_put_failure: static inline size_t rtnl_fdb_nlmsg_size(void) { - return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(ETH_ALEN); + return NLMSG_ALIGN(sizeof(struct ndmsg)) + + nla_total_size(ETH_ALEN) + /* NDA_LLADDR */ + nla_total_size(sizeof(u16)) + /* NDA_VLAN */ + 0; } static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, u16 vid, int type, diff --git a/net/core/sock.c b/net/core/sock.c index 5e3ca414357e..00a074dbfe9b 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -715,7 +715,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname, val = min_t(u32, val, sysctl_wmem_max); set_sndbuf: sk->sk_userlocks |= SOCK_SNDBUF_LOCK; - sk->sk_sndbuf = max_t(u32, val * 2, SOCK_MIN_SNDBUF); + sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF); /* Wake up sending tasks if we upped the value. */ sk->sk_write_space(sk); break; @@ -751,7 +751,7 @@ set_rcvbuf: * returning the value we actually used in getsockopt * is the most desirable behavior. */ - sk->sk_rcvbuf = max_t(u32, val * 2, SOCK_MIN_RCVBUF); + sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF); break; case SO_RCVBUFFORCE: diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 4f6c1862dfd2..3202d75329b5 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -1353,6 +1353,7 @@ static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev) dcb_unlock: spin_unlock_bh(&dcb_lock); nla_put_failure: + err = -EMSGSIZE; return err; } diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index b567c8725aea..edbe59d203ef 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -700,6 +700,7 @@ int dccp_invalid_packet(struct sk_buff *skb) { const struct dccp_hdr *dh; unsigned int cscov; + u8 dccph_doff; if (skb->pkt_type != PACKET_HOST) return 1; @@ -721,18 +722,19 @@ int dccp_invalid_packet(struct sk_buff *skb) /* * If P.Data Offset is too small for packet type, drop packet and return */ - if (dh->dccph_doff < dccp_hdr_len(skb) / sizeof(u32)) { - DCCP_WARN("P.Data Offset(%u) too small\n", dh->dccph_doff); + dccph_doff = dh->dccph_doff; + if (dccph_doff < dccp_hdr_len(skb) / sizeof(u32)) { + DCCP_WARN("P.Data Offset(%u) too small\n", dccph_doff); return 1; } /* * If P.Data Offset is too too large for packet, drop packet and return */ - if (!pskb_may_pull(skb, dh->dccph_doff * sizeof(u32))) { - DCCP_WARN("P.Data Offset(%u) too large\n", dh->dccph_doff); + if (!pskb_may_pull(skb, dccph_doff * sizeof(u32))) { + DCCP_WARN("P.Data Offset(%u) too large\n", dccph_doff); return 1; } - + dh = dccp_hdr(skb); /* * If P.type is not Data, Ack, or DataAck and P.X == 0 (the packet * has short sequence numbers), drop packet and return diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index a6902c1e2f28..7899919cd9f0 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -233,6 +233,8 @@ int dsa_cpu_dsa_setup(struct dsa_switch *ds, struct device *dev, genphy_read_status(phydev); if (ds->ops->adjust_link) ds->ops->adjust_link(ds, port, phydev); + + put_device(&phydev->mdio.dev); } return 0; @@ -504,15 +506,8 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index, void dsa_cpu_dsa_destroy(struct device_node *port_dn) { - struct phy_device *phydev; - - if (of_phy_is_fixed_link(port_dn)) { - phydev = of_phy_find_device(port_dn); - if (phydev) { - phy_device_free(phydev); - fixed_phy_unregister(phydev); - } - } + if (of_phy_is_fixed_link(port_dn)) + of_phy_deregister_fixed_link(port_dn); } static void dsa_switch_destroy(struct dsa_switch *ds) diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index f8a7d9aab437..5fff951a0a49 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -28,8 +28,10 @@ static struct dsa_switch_tree *dsa_get_dst(u32 tree) struct dsa_switch_tree *dst; list_for_each_entry(dst, &dsa_switch_trees, list) - if (dst->tree == tree) + if (dst->tree == tree) { + kref_get(&dst->refcount); return dst; + } return NULL; } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 6b1282c006b1..30e2e21d7619 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1125,7 +1125,7 @@ static int dsa_slave_phy_setup(struct dsa_slave_priv *p, p->phy_interface = mode; phy_dn = of_parse_phandle(port_dn, "phy-handle", 0); - if (of_phy_is_fixed_link(port_dn)) { + if (!phy_dn && of_phy_is_fixed_link(port_dn)) { /* In the case of a fixed PHY, the DT node associated * to the fixed PHY is the Port DT node */ @@ -1135,7 +1135,7 @@ static int dsa_slave_phy_setup(struct dsa_slave_priv *p, return ret; } phy_is_fixed = true; - phy_dn = port_dn; + phy_dn = of_node_get(port_dn); } if (ds->ops->get_phy_flags) @@ -1154,6 +1154,7 @@ static int dsa_slave_phy_setup(struct dsa_slave_priv *p, ret = dsa_slave_phy_connect(p, slave_dev, phy_id); if (ret) { netdev_err(slave_dev, "failed to connect to phy%d: %d\n", phy_id, ret); + of_node_put(phy_dn); return ret; } } else { @@ -1162,6 +1163,8 @@ static int dsa_slave_phy_setup(struct dsa_slave_priv *p, phy_flags, p->phy_interface); } + + of_node_put(phy_dn); } if (p->phy && phy_is_fixed) @@ -1174,6 +1177,8 @@ static int dsa_slave_phy_setup(struct dsa_slave_priv *p, ret = dsa_slave_phy_connect(p, slave_dev, p->port); if (ret) { netdev_err(slave_dev, "failed to connect to port %d: %d\n", p->port, ret); + if (phy_is_fixed) + of_phy_deregister_fixed_link(port_dn); return ret; } } @@ -1289,10 +1294,18 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent, void dsa_slave_destroy(struct net_device *slave_dev) { struct dsa_slave_priv *p = netdev_priv(slave_dev); + struct dsa_switch *ds = p->parent; + struct device_node *port_dn; + + port_dn = ds->ports[p->port].dn; netif_carrier_off(slave_dev); - if (p->phy) + if (p->phy) { phy_disconnect(p->phy); + + if (of_phy_is_fixed_link(port_dn)) + of_phy_deregister_fixed_link(port_dn); + } unregister_netdev(slave_dev); free_netdev(slave_dev); } diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 300b06888fdf..b54b3ca939db 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -715,6 +715,7 @@ config DEFAULT_TCP_CONG default "reno" if DEFAULT_RENO default "dctcp" if DEFAULT_DCTCP default "cdg" if DEFAULT_CDG + default "bbr" if DEFAULT_BBR default "cubic" config TCP_MD5SIG diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 5ddf5cda07f4..215143246e4b 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1233,7 +1233,7 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb, fixedid = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TCP_FIXEDID); /* fixed ID is invalid if DF bit is not set */ - if (fixedid && !(iph->frag_off & htons(IP_DF))) + if (fixedid && !(ip_hdr(skb)->frag_off & htons(IP_DF))) goto out; } diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index d95631d09248..20fb25e3027b 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -476,7 +476,7 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb) esph = (void *)skb_push(skb, 4); *seqhi = esph->spi; esph->spi = esph->seq_no; - esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.input.hi); + esph->seq_no = XFRM_SKB_CB(skb)->seq.input.hi; aead_request_set_callback(req, 0, esp_input_done_esn, skb); } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index c3b80478226e..161fc0f0d752 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -151,7 +151,7 @@ static void fib_replace_table(struct net *net, struct fib_table *old, int fib_unmerge(struct net *net) { - struct fib_table *old, *new; + struct fib_table *old, *new, *main_table; /* attempt to fetch local table if it has been allocated */ old = fib_get_table(net, RT_TABLE_LOCAL); @@ -162,11 +162,21 @@ int fib_unmerge(struct net *net) if (!new) return -ENOMEM; + /* table is already unmerged */ + if (new == old) + return 0; + /* replace merged table with clean table */ - if (new != old) { - fib_replace_table(net, old, new); - fib_free_table(old); - } + fib_replace_table(net, old, new); + fib_free_table(old); + + /* attempt to fetch main table if it has been allocated */ + main_table = fib_get_table(net, RT_TABLE_MAIN); + if (!main_table) + return 0; + + /* flush local entries from main table */ + fib_table_flush_external(main_table); return 0; } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 4cff74d4133f..e3665bf7a7f3 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -719,6 +719,13 @@ static unsigned char update_suffix(struct key_vector *tn) { unsigned char slen = tn->pos; unsigned long stride, i; + unsigned char slen_max; + + /* only vector 0 can have a suffix length greater than or equal to + * tn->pos + tn->bits, the second highest node will have a suffix + * length at most of tn->pos + tn->bits - 1 + */ + slen_max = min_t(unsigned char, tn->pos + tn->bits - 1, tn->slen); /* search though the list of children looking for nodes that might * have a suffix greater than the one we currently have. This is @@ -736,12 +743,8 @@ static unsigned char update_suffix(struct key_vector *tn) slen = n->slen; i &= ~(stride - 1); - /* if slen covers all but the last bit we can stop here - * there will be nothing longer than that since only node - * 0 and 1 << (bits - 1) could have that as their suffix - * length. - */ - if ((slen + 1) >= (tn->pos + tn->bits)) + /* stop searching if we have hit the maximum possible value */ + if (slen >= slen_max) break; } @@ -913,39 +916,27 @@ static struct key_vector *resize(struct trie *t, struct key_vector *tn) return collapse(t, tn); /* update parent in case halve failed */ - tp = node_parent(tn); - - /* Return if at least one deflate was run */ - if (max_work != MAX_WORK) - return tp; - - /* push the suffix length to the parent node */ - if (tn->slen > tn->pos) { - unsigned char slen = update_suffix(tn); - - if (slen > tp->slen) - tp->slen = slen; - } - - return tp; + return node_parent(tn); } -static void leaf_pull_suffix(struct key_vector *tp, struct key_vector *l) +static void node_pull_suffix(struct key_vector *tn, unsigned char slen) { - while ((tp->slen > tp->pos) && (tp->slen > l->slen)) { - if (update_suffix(tp) > l->slen) + unsigned char node_slen = tn->slen; + + while ((node_slen > tn->pos) && (node_slen > slen)) { + slen = update_suffix(tn); + if (node_slen == slen) break; - tp = node_parent(tp); + + tn = node_parent(tn); + node_slen = tn->slen; } } -static void leaf_push_suffix(struct key_vector *tn, struct key_vector *l) +static void node_push_suffix(struct key_vector *tn, unsigned char slen) { - /* if this is a new leaf then tn will be NULL and we can sort - * out parent suffix lengths as a part of trie_rebalance - */ - while (tn->slen < l->slen) { - tn->slen = l->slen; + while (tn->slen < slen) { + tn->slen = slen; tn = node_parent(tn); } } @@ -1066,6 +1057,7 @@ static int fib_insert_node(struct trie *t, struct key_vector *tp, } /* Case 3: n is NULL, and will just insert a new leaf */ + node_push_suffix(tp, new->fa_slen); NODE_INIT_PARENT(l, tp); put_child_root(tp, key, l); trie_rebalance(t, tp); @@ -1107,7 +1099,7 @@ static int fib_insert_alias(struct trie *t, struct key_vector *tp, /* if we added to the tail node then we need to update slen */ if (l->slen < new->fa_slen) { l->slen = new->fa_slen; - leaf_push_suffix(tp, l); + node_push_suffix(tp, new->fa_slen); } return 0; @@ -1499,6 +1491,8 @@ static void fib_remove_alias(struct trie *t, struct key_vector *tp, * out parent suffix lengths as a part of trie_rebalance */ if (hlist_empty(&l->leaf)) { + if (tp->slen == l->slen) + node_pull_suffix(tp, tp->pos); put_child_root(tp, l->key, NULL); node_free(l); trie_rebalance(t, tp); @@ -1511,7 +1505,7 @@ static void fib_remove_alias(struct trie *t, struct key_vector *tp, /* update the trie with the latest suffix length */ l->slen = fa->fa_slen; - leaf_pull_suffix(tp, l); + node_pull_suffix(tp, fa->fa_slen); } /* Caller must hold RTNL. */ @@ -1743,8 +1737,10 @@ struct fib_table *fib_trie_unmerge(struct fib_table *oldtb) local_l = fib_find_node(lt, &local_tp, l->key); if (fib_insert_alias(lt, local_tp, local_l, new_fa, - NULL, l->key)) + NULL, l->key)) { + kmem_cache_free(fn_alias_kmem, new_fa); goto out; + } } /* stop loop if key wrapped back to 0 */ @@ -1760,6 +1756,75 @@ out: return NULL; } +/* Caller must hold RTNL */ +void fib_table_flush_external(struct fib_table *tb) +{ + struct trie *t = (struct trie *)tb->tb_data; + struct key_vector *pn = t->kv; + unsigned long cindex = 1; + struct hlist_node *tmp; + struct fib_alias *fa; + + /* walk trie in reverse order */ + for (;;) { + unsigned char slen = 0; + struct key_vector *n; + + if (!(cindex--)) { + t_key pkey = pn->key; + + /* cannot resize the trie vector */ + if (IS_TRIE(pn)) + break; + + /* update the suffix to address pulled leaves */ + if (pn->slen > pn->pos) + update_suffix(pn); + + /* resize completed node */ + pn = resize(t, pn); + cindex = get_index(pkey, pn); + + continue; + } + + /* grab the next available node */ + n = get_child(pn, cindex); + if (!n) + continue; + + if (IS_TNODE(n)) { + /* record pn and cindex for leaf walking */ + pn = n; + cindex = 1ul << n->bits; + + continue; + } + + hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) { + /* if alias was cloned to local then we just + * need to remove the local copy from main + */ + if (tb->tb_id != fa->tb_id) { + hlist_del_rcu(&fa->fa_list); + alias_free_mem_rcu(fa); + continue; + } + + /* record local slen */ + slen = fa->fa_slen; + } + + /* update leaf slen */ + n->slen = slen; + + if (hlist_empty(&n->leaf)) { + put_child_root(pn, n->key, NULL); + node_free(n); + } + } +} + /* Caller must hold RTNL. */ int fib_table_flush(struct net *net, struct fib_table *tb) { @@ -1782,6 +1847,10 @@ int fib_table_flush(struct net *net, struct fib_table *tb) if (IS_TRIE(pn)) break; + /* update the suffix to address pulled leaves */ + if (pn->slen > pn->pos) + update_suffix(pn); + /* resize completed node */ pn = resize(t, pn); cindex = get_index(pkey, pn); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 606cc3e85d2b..15db786d50ed 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -162,7 +162,7 @@ static int unsolicited_report_interval(struct in_device *in_dev) } static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im); -static void igmpv3_del_delrec(struct in_device *in_dev, __be32 multiaddr); +static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im); static void igmpv3_clear_delrec(struct in_device *in_dev); static int sf_setstate(struct ip_mc_list *pmc); static void sf_markstate(struct ip_mc_list *pmc); @@ -1130,10 +1130,15 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im) spin_unlock_bh(&in_dev->mc_tomb_lock); } -static void igmpv3_del_delrec(struct in_device *in_dev, __be32 multiaddr) +/* + * restore ip_mc_list deleted records + */ +static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im) { struct ip_mc_list *pmc, *pmc_prev; - struct ip_sf_list *psf, *psf_next; + struct ip_sf_list *psf; + struct net *net = dev_net(in_dev->dev); + __be32 multiaddr = im->multiaddr; spin_lock_bh(&in_dev->mc_tomb_lock); pmc_prev = NULL; @@ -1149,16 +1154,26 @@ static void igmpv3_del_delrec(struct in_device *in_dev, __be32 multiaddr) in_dev->mc_tomb = pmc->next; } spin_unlock_bh(&in_dev->mc_tomb_lock); + + spin_lock_bh(&im->lock); if (pmc) { - for (psf = pmc->tomb; psf; psf = psf_next) { - psf_next = psf->sf_next; - kfree(psf); + im->interface = pmc->interface; + im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + im->sfmode = pmc->sfmode; + if (pmc->sfmode == MCAST_INCLUDE) { + im->tomb = pmc->tomb; + im->sources = pmc->sources; + for (psf = im->sources; psf; psf = psf->sf_next) + psf->sf_crcount = im->crcount; } in_dev_put(pmc->interface); - kfree(pmc); } + spin_unlock_bh(&im->lock); } +/* + * flush ip_mc_list deleted records + */ static void igmpv3_clear_delrec(struct in_device *in_dev) { struct ip_mc_list *pmc, *nextpmc; @@ -1366,7 +1381,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) ip_mc_hash_add(in_dev, im); #ifdef CONFIG_IP_MULTICAST - igmpv3_del_delrec(in_dev, im->multiaddr); + igmpv3_del_delrec(in_dev, im); #endif igmp_group_added(im); if (!in_dev->dead) @@ -1626,8 +1641,12 @@ void ip_mc_remap(struct in_device *in_dev) ASSERT_RTNL(); - for_each_pmc_rtnl(in_dev, pmc) + for_each_pmc_rtnl(in_dev, pmc) { +#ifdef CONFIG_IP_MULTICAST + igmpv3_del_delrec(in_dev, pmc); +#endif igmp_group_added(pmc); + } } /* Device going down */ @@ -1648,7 +1667,6 @@ void ip_mc_down(struct in_device *in_dev) in_dev->mr_gq_running = 0; if (del_timer(&in_dev->mr_gq_timer)) __in_dev_put(in_dev); - igmpv3_clear_delrec(in_dev); #endif ip_mc_dec_group(in_dev, IGMP_ALL_HOSTS); @@ -1688,8 +1706,12 @@ void ip_mc_up(struct in_device *in_dev) #endif ip_mc_inc_group(in_dev, IGMP_ALL_HOSTS); - for_each_pmc_rtnl(in_dev, pmc) + for_each_pmc_rtnl(in_dev, pmc) { +#ifdef CONFIG_IP_MULTICAST + igmpv3_del_delrec(in_dev, pmc); +#endif igmp_group_added(pmc); + } } /* @@ -1704,13 +1726,13 @@ void ip_mc_destroy_dev(struct in_device *in_dev) /* Deactivate timers */ ip_mc_down(in_dev); +#ifdef CONFIG_IP_MULTICAST + igmpv3_clear_delrec(in_dev); +#endif while ((i = rtnl_dereference(in_dev->mc_list)) != NULL) { in_dev->mc_list = i->next_rcu; in_dev->mc_count--; - - /* We've dropped the groups in ip_mc_down already */ - ip_mc_clear_src(i); ip_ma_put(i); } } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 105908d841a3..877bdb02e887 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -107,6 +107,8 @@ int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) if (unlikely(!skb)) return 0; + skb->protocol = htons(ETH_P_IP); + return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, dst_output); diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index c3776ff6749f..b3cc1335adbc 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -24,10 +24,11 @@ int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned int addr_t struct flowi4 fl4 = {}; __be32 saddr = iph->saddr; __u8 flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : 0; + struct net_device *dev = skb_dst(skb)->dev; unsigned int hh_len; if (addr_type == RTN_UNSPEC) - addr_type = inet_addr_type(net, saddr); + addr_type = inet_addr_type_dev_table(net, dev, saddr); if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST) flags |= FLOWI_FLAG_ANYSRC; else @@ -40,6 +41,8 @@ int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned int addr_t fl4.saddr = saddr; fl4.flowi4_tos = RT_TOS(iph->tos); fl4.flowi4_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0; + if (!fl4.flowi4_oif) + fl4.flowi4_oif = l3mdev_master_ifindex(dev); fl4.flowi4_mark = skb->mark; fl4.flowi4_flags = flags; rt = ip_route_output_key(net, &fl4); diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index b31df597fd37..697538464e6e 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -1201,8 +1201,8 @@ static int translate_compat_table(struct xt_table_info **pinfo, newinfo->number = compatr->num_entries; for (i = 0; i < NF_ARP_NUMHOOKS; i++) { - newinfo->hook_entry[i] = info->hook_entry[i]; - newinfo->underflow[i] = info->underflow[i]; + newinfo->hook_entry[i] = compatr->hook_entry[i]; + newinfo->underflow[i] = compatr->underflow[i]; } entry1 = newinfo->entries; pos = entry1; diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 205e2000d395..96b8e2b95731 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -657,6 +657,10 @@ int ping_common_sendmsg(int family, struct msghdr *msg, size_t len, if (len > 0xFFFF) return -EMSGSIZE; + /* Must have at least a full ICMP header. */ + if (len < icmph_len) + return -EINVAL; + /* * Check the flags. */ diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 1294af4e0127..f9038d6b109e 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -200,8 +200,10 @@ static void tcp_reinit_congestion_control(struct sock *sk, icsk->icsk_ca_ops = ca; icsk->icsk_ca_setsockopt = 1; - if (sk->sk_state != TCP_CLOSE) + if (sk->sk_state != TCP_CLOSE) { + memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); tcp_init_congestion_control(sk); + } } /* Manage refcounts on socket close. */ diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index a27b9c0e27c0..c71d49ce0c93 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -128,6 +128,23 @@ int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2; #define REXMIT_LOST 1 /* retransmit packets marked lost */ #define REXMIT_NEW 2 /* FRTO-style transmit of unsent/new packets */ +static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb) +{ + static bool __once __read_mostly; + + if (!__once) { + struct net_device *dev; + + __once = true; + + rcu_read_lock(); + dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif); + pr_warn("%s: Driver has suspect GRO implementation, TCP performance may be compromised.\n", + dev ? dev->name : "Unknown driver"); + rcu_read_unlock(); + } +} + /* Adapt the MSS value used to make delayed ack decision to the * real world. */ @@ -144,7 +161,10 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) */ len = skb_shinfo(skb)->gso_size ? : skb->len; if (len >= icsk->icsk_ack.rcv_mss) { - icsk->icsk_ack.rcv_mss = len; + icsk->icsk_ack.rcv_mss = min_t(unsigned int, len, + tcp_sk(sk)->advmss); + if (unlikely(icsk->icsk_ack.rcv_mss != len)) + tcp_gro_dev_warn(sk, skb); } else { /* Otherwise, we make more careful check taking into account, * that SACKs block is variable. diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index d123d68f4d1d..5bab6c3f7a2f 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1455,7 +1455,7 @@ static void udp_v4_rehash(struct sock *sk) udp_lib_rehash(sk, new_hash); } -static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { int rc; @@ -1652,10 +1652,10 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb, if (use_hash2) { hash2_any = udp4_portaddr_hash(net, htonl(INADDR_ANY), hnum) & - udp_table.mask; - hash2 = udp4_portaddr_hash(net, daddr, hnum) & udp_table.mask; + udptable->mask; + hash2 = udp4_portaddr_hash(net, daddr, hnum) & udptable->mask; start_lookup: - hslot = &udp_table.hash2[hash2]; + hslot = &udptable->hash2[hash2]; offset = offsetof(typeof(*sk), __sk_common.skc_portaddr_node); } diff --git a/net/ipv4/udp_impl.h b/net/ipv4/udp_impl.h index 7e0fe4bdd967..feb50a16398d 100644 --- a/net/ipv4/udp_impl.h +++ b/net/ipv4/udp_impl.h @@ -25,7 +25,7 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len); int udp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); -int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); +int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); void udp_destroy_sock(struct sock *sk); #ifdef CONFIG_PROC_FS diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index af817158d830..ff450c2aad9b 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -50,7 +50,7 @@ struct proto udplite_prot = { .sendmsg = udp_sendmsg, .recvmsg = udp_recvmsg, .sendpage = udp_sendpage, - .backlog_rcv = udp_queue_rcv_skb, + .backlog_rcv = __udp_queue_rcv_skb, .hash = udp_lib_hash, .unhash = udp_lib_unhash, .get_port = udp_v4_get_port, diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 060dd9922018..4bc5ba3ae452 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -183,7 +183,7 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, static void addrconf_dad_start(struct inet6_ifaddr *ifp); static void addrconf_dad_work(struct work_struct *w); -static void addrconf_dad_completed(struct inet6_ifaddr *ifp); +static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id); static void addrconf_dad_run(struct inet6_dev *idev); static void addrconf_rs_timer(unsigned long data); static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa); @@ -2898,6 +2898,7 @@ static void add_addr(struct inet6_dev *idev, const struct in6_addr *addr, spin_lock_bh(&ifp->lock); ifp->flags &= ~IFA_F_TENTATIVE; spin_unlock_bh(&ifp->lock); + rt_genid_bump_ipv6(dev_net(idev->dev)); ipv6_ifa_notify(RTM_NEWADDR, ifp); in6_ifa_put(ifp); } @@ -3740,7 +3741,7 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) { struct inet6_dev *idev = ifp->idev; struct net_device *dev = idev->dev; - bool notify = false; + bool bump_id, notify = false; addrconf_join_solict(dev, &ifp->addr); @@ -3755,11 +3756,12 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) idev->cnf.accept_dad < 1 || !(ifp->flags&IFA_F_TENTATIVE) || ifp->flags & IFA_F_NODAD) { + bump_id = ifp->flags & IFA_F_TENTATIVE; ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED); spin_unlock(&ifp->lock); read_unlock_bh(&idev->lock); - addrconf_dad_completed(ifp); + addrconf_dad_completed(ifp, bump_id); return; } @@ -3819,8 +3821,8 @@ static void addrconf_dad_work(struct work_struct *w) struct inet6_ifaddr, dad_work); struct inet6_dev *idev = ifp->idev; + bool bump_id, disable_ipv6 = false; struct in6_addr mcaddr; - bool disable_ipv6 = false; enum { DAD_PROCESS, @@ -3890,11 +3892,12 @@ static void addrconf_dad_work(struct work_struct *w) * DAD was successful */ + bump_id = ifp->flags & IFA_F_TENTATIVE; ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED); spin_unlock(&ifp->lock); write_unlock_bh(&idev->lock); - addrconf_dad_completed(ifp); + addrconf_dad_completed(ifp, bump_id); goto out; } @@ -3931,7 +3934,7 @@ static bool ipv6_lonely_lladdr(struct inet6_ifaddr *ifp) return true; } -static void addrconf_dad_completed(struct inet6_ifaddr *ifp) +static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id) { struct net_device *dev = ifp->idev->dev; struct in6_addr lladdr; @@ -3983,6 +3986,9 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp) spin_unlock(&ifp->lock); write_unlock_bh(&ifp->idev->lock); } + + if (bump_id) + rt_genid_bump_ipv6(dev_net(dev)); } static void addrconf_dad_run(struct inet6_dev *idev) diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 37874e2f30ed..ccf40550c475 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -139,7 +139,8 @@ void ip6_datagram_release_cb(struct sock *sk) } EXPORT_SYMBOL_GPL(ip6_datagram_release_cb); -static int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) +int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, + int addr_len) { struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr; struct inet_sock *inet = inet_sk(sk); @@ -252,6 +253,7 @@ ipv4_connected: out: return err; } +EXPORT_SYMBOL_GPL(__ip6_datagram_connect); int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 060a60b2f8a6..111ba55fd512 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -418,7 +418,7 @@ static int esp6_input(struct xfrm_state *x, struct sk_buff *skb) esph = (void *)skb_push(skb, 4); *seqhi = esph->spi; esph->spi = esph->seq_no; - esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.input.hi); + esph->seq_no = XFRM_SKB_CB(skb)->seq.input.hi; aead_request_set_callback(req, 0, esp_input_done_esn, skb); } diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 7370ad2e693a..2772004ba5a1 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -447,8 +447,10 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, if (__ipv6_addr_needs_scope_id(addr_type)) iif = skb->dev->ifindex; - else - iif = l3mdev_master_ifindex(skb_dst(skb)->dev); + else { + dst = skb_dst(skb); + iif = l3mdev_master_ifindex(dst ? dst->dev : skb->dev); + } /* * Must not send error if the source does not uniquely diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 1fcf61f1cbc3..89c59e656f44 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -99,7 +99,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, segs = ops->callbacks.gso_segment(skb, features); } - if (IS_ERR(segs)) + if (IS_ERR_OR_NULL(segs)) goto out; gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 87784560dc46..d76674efe523 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1034,6 +1034,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, int mtu; unsigned int psh_hlen = sizeof(struct ipv6hdr) + t->encap_hlen; unsigned int max_headroom = psh_hlen; + bool use_cache = false; u8 hop_limit; int err = -1; @@ -1066,7 +1067,15 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr)); neigh_release(neigh); - } else if (!fl6->flowi6_mark) + } else if (!(t->parms.flags & + (IP6_TNL_F_USE_ORIG_TCLASS | IP6_TNL_F_USE_ORIG_FWMARK))) { + /* enable the cache only only if the routing decision does + * not depend on the current inner header value + */ + use_cache = true; + } + + if (use_cache) dst = dst_cache_get(&t->dst_cache); if (!ip6_tnl_xmit_ctl(t, &fl6->saddr, &fl6->daddr)) @@ -1150,7 +1159,7 @@ route_lookup: if (t->encap.type != TUNNEL_ENCAP_NONE) goto tx_err_dst_release; } else { - if (!fl6->flowi6_mark && ndst) + if (use_cache && ndst) dst_cache_set_ip6(&t->dst_cache, ndst, &fl6->saddr); } skb_dst_set(skb, dst); @@ -1172,7 +1181,6 @@ route_lookup: if (err) return err; - skb->protocol = htons(ETH_P_IPV6); skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); ipv6h = ipv6_hdr(skb); diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 8a02ca8a11af..c299c1e2bbf0 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -1138,6 +1138,33 @@ static struct xfrm6_protocol vti_ipcomp6_protocol __read_mostly = { .priority = 100, }; +static bool is_vti6_tunnel(const struct net_device *dev) +{ + return dev->netdev_ops == &vti6_netdev_ops; +} + +static int vti6_device_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct ip6_tnl *t = netdev_priv(dev); + + if (!is_vti6_tunnel(dev)) + return NOTIFY_DONE; + + switch (event) { + case NETDEV_DOWN: + if (!net_eq(t->net, dev_net(dev))) + xfrm_garbage_collect(t->net); + break; + } + return NOTIFY_DONE; +} + +static struct notifier_block vti6_notifier_block __read_mostly = { + .notifier_call = vti6_device_event, +}; + /** * vti6_tunnel_init - register protocol and reserve needed resources * @@ -1148,6 +1175,8 @@ static int __init vti6_tunnel_init(void) const char *msg; int err; + register_netdevice_notifier(&vti6_notifier_block); + msg = "tunnel device"; err = register_pernet_device(&vti6_net_ops); if (err < 0) @@ -1180,6 +1209,7 @@ xfrm_proto_ah_failed: xfrm_proto_esp_failed: unregister_pernet_device(&vti6_net_ops); pernet_dev_failed: + unregister_netdevice_notifier(&vti6_notifier_block); pr_err("vti6 init: failed to register %s\n", msg); return err; } @@ -1194,6 +1224,7 @@ static void __exit vti6_tunnel_cleanup(void) xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH); xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP); unregister_pernet_device(&vti6_net_ops); + unregister_netdevice_notifier(&vti6_notifier_block); } module_init(vti6_tunnel_init); diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index e4347aeb2e65..9948b5ce52da 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -576,11 +576,11 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) /* Jumbo payload inhibits frag. header */ if (ipv6_hdr(skb)->payload_len == 0) { pr_debug("payload len = 0\n"); - return -EINVAL; + return 0; } if (find_prev_fhdr(skb, &prevhdr, &nhoff, &fhoff) < 0) - return -EINVAL; + return 0; if (!pskb_may_pull(skb, fhoff + sizeof(*fhdr))) return -ENOMEM; diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c index f7aab5ab93a5..f06b0471f39f 100644 --- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -69,7 +69,7 @@ static unsigned int ipv6_defrag(void *priv, if (err == -EINPROGRESS) return NF_STOLEN; - return NF_ACCEPT; + return err == 0 ? NF_ACCEPT : NF_DROP; } static struct nf_hook_ops ipv6_defrag_ops[] = { diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index a5400223fd74..10090400c72f 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -156,6 +156,7 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook) fl6.daddr = oip6h->saddr; fl6.fl6_sport = otcph->dest; fl6.fl6_dport = otcph->source; + fl6.flowi6_oif = l3mdev_master_ifindex(skb_dst(oldskb)->dev); security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6)); dst = ip6_route_output(net, NULL, &fl6); if (dst->error) { diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index 7cca8ac66fe9..cd4252346a32 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -155,6 +155,8 @@ int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) if (unlikely(!skb)) return 0; + skb->protocol = htons(ETH_P_IPV6); + return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, dst_output); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index b2ef061e6836..e4a8000d59ad 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -514,7 +514,7 @@ out: return; } -static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { int rc; @@ -706,10 +706,10 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb, if (use_hash2) { hash2_any = udp6_portaddr_hash(net, &in6addr_any, hnum) & - udp_table.mask; - hash2 = udp6_portaddr_hash(net, daddr, hnum) & udp_table.mask; + udptable->mask; + hash2 = udp6_portaddr_hash(net, daddr, hnum) & udptable->mask; start_lookup: - hslot = &udp_table.hash2[hash2]; + hslot = &udptable->hash2[hash2]; offset = offsetof(typeof(*sk), __sk_common.skc_portaddr_node); } diff --git a/net/ipv6/udp_impl.h b/net/ipv6/udp_impl.h index f6eb1ab34f4b..e78bdc76dcc3 100644 --- a/net/ipv6/udp_impl.h +++ b/net/ipv6/udp_impl.h @@ -26,7 +26,7 @@ int compat_udpv6_getsockopt(struct sock *sk, int level, int optname, int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len); int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len); -int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); +int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); void udpv6_destroy_sock(struct sock *sk); #ifdef CONFIG_PROC_FS diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index 47d0d2b87106..2f5101a12283 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -45,7 +45,7 @@ struct proto udplitev6_prot = { .getsockopt = udpv6_getsockopt, .sendmsg = udpv6_sendmsg, .recvmsg = udpv6_recvmsg, - .backlog_rcv = udpv6_queue_rcv_skb, + .backlog_rcv = __udpv6_queue_rcv_skb, .hash = udp_lib_hash, .unhash = udp_lib_unhash, .get_port = udp_v6_get_port, diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index fce25afb652a..8938b6ba57a0 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -61,7 +61,8 @@ static struct sock *__l2tp_ip_bind_lookup(struct net *net, __be32 laddr, int dif if ((l2tp->conn_id == tunnel_id) && net_eq(sock_net(sk), net) && !(inet->inet_rcv_saddr && inet->inet_rcv_saddr != laddr) && - !(sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)) + (!sk->sk_bound_dev_if || !dif || + sk->sk_bound_dev_if == dif)) goto found; } @@ -182,15 +183,17 @@ pass_up: struct iphdr *iph = (struct iphdr *) skb_network_header(skb); read_lock_bh(&l2tp_ip_lock); - sk = __l2tp_ip_bind_lookup(net, iph->daddr, 0, tunnel_id); + sk = __l2tp_ip_bind_lookup(net, iph->daddr, inet_iif(skb), + tunnel_id); + if (!sk) { + read_unlock_bh(&l2tp_ip_lock); + goto discard; + } + + sock_hold(sk); read_unlock_bh(&l2tp_ip_lock); } - if (sk == NULL) - goto discard; - - sock_hold(sk); - if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_put; @@ -251,22 +254,17 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) int ret; int chk_addr_ret; - if (!sock_flag(sk, SOCK_ZAPPED)) - return -EINVAL; if (addr_len < sizeof(struct sockaddr_l2tpip)) return -EINVAL; if (addr->l2tp_family != AF_INET) return -EINVAL; - ret = -EADDRINUSE; - read_lock_bh(&l2tp_ip_lock); - if (__l2tp_ip_bind_lookup(net, addr->l2tp_addr.s_addr, - sk->sk_bound_dev_if, addr->l2tp_conn_id)) - goto out_in_use; + lock_sock(sk); - read_unlock_bh(&l2tp_ip_lock); + ret = -EINVAL; + if (!sock_flag(sk, SOCK_ZAPPED)) + goto out; - lock_sock(sk); if (sk->sk_state != TCP_CLOSE || addr_len < sizeof(struct sockaddr_l2tpip)) goto out; @@ -280,14 +278,22 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_rcv_saddr = inet->inet_saddr = addr->l2tp_addr.s_addr; if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST) inet->inet_saddr = 0; /* Use device */ - sk_dst_reset(sk); + write_lock_bh(&l2tp_ip_lock); + if (__l2tp_ip_bind_lookup(net, addr->l2tp_addr.s_addr, + sk->sk_bound_dev_if, addr->l2tp_conn_id)) { + write_unlock_bh(&l2tp_ip_lock); + ret = -EADDRINUSE; + goto out; + } + + sk_dst_reset(sk); l2tp_ip_sk(sk)->conn_id = addr->l2tp_conn_id; - write_lock_bh(&l2tp_ip_lock); sk_add_bind_node(sk, &l2tp_ip_bind_table); sk_del_node_init(sk); write_unlock_bh(&l2tp_ip_lock); + ret = 0; sock_reset_flag(sk, SOCK_ZAPPED); @@ -295,11 +301,6 @@ out: release_sock(sk); return ret; - -out_in_use: - read_unlock_bh(&l2tp_ip_lock); - - return ret; } static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) @@ -307,21 +308,24 @@ static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len struct sockaddr_l2tpip *lsa = (struct sockaddr_l2tpip *) uaddr; int rc; - if (sock_flag(sk, SOCK_ZAPPED)) /* Must bind first - autobinding does not work */ - return -EINVAL; - if (addr_len < sizeof(*lsa)) return -EINVAL; if (ipv4_is_multicast(lsa->l2tp_addr.s_addr)) return -EINVAL; - rc = ip4_datagram_connect(sk, uaddr, addr_len); - if (rc < 0) - return rc; - lock_sock(sk); + /* Must bind first - autobinding does not work */ + if (sock_flag(sk, SOCK_ZAPPED)) { + rc = -EINVAL; + goto out_sk; + } + + rc = __ip4_datagram_connect(sk, uaddr, addr_len); + if (rc < 0) + goto out_sk; + l2tp_ip_sk(sk)->peer_conn_id = lsa->l2tp_conn_id; write_lock_bh(&l2tp_ip_lock); @@ -329,7 +333,9 @@ static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len sk_add_bind_node(sk, &l2tp_ip_bind_table); write_unlock_bh(&l2tp_ip_lock); +out_sk: release_sock(sk); + return rc; } diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index ad3468c32b53..aa821cb639e5 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -72,8 +72,9 @@ static struct sock *__l2tp_ip6_bind_lookup(struct net *net, if ((l2tp->conn_id == tunnel_id) && net_eq(sock_net(sk), net) && - !(addr && ipv6_addr_equal(addr, laddr)) && - !(sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)) + (!addr || ipv6_addr_equal(addr, laddr)) && + (!sk->sk_bound_dev_if || !dif || + sk->sk_bound_dev_if == dif)) goto found; } @@ -196,16 +197,17 @@ pass_up: struct ipv6hdr *iph = ipv6_hdr(skb); read_lock_bh(&l2tp_ip6_lock); - sk = __l2tp_ip6_bind_lookup(net, &iph->daddr, - 0, tunnel_id); + sk = __l2tp_ip6_bind_lookup(net, &iph->daddr, inet6_iif(skb), + tunnel_id); + if (!sk) { + read_unlock_bh(&l2tp_ip6_lock); + goto discard; + } + + sock_hold(sk); read_unlock_bh(&l2tp_ip6_lock); } - if (sk == NULL) - goto discard; - - sock_hold(sk); - if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_put; @@ -266,11 +268,10 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) struct sockaddr_l2tpip6 *addr = (struct sockaddr_l2tpip6 *) uaddr; struct net *net = sock_net(sk); __be32 v4addr = 0; + int bound_dev_if; int addr_type; int err; - if (!sock_flag(sk, SOCK_ZAPPED)) - return -EINVAL; if (addr->l2tp_family != AF_INET6) return -EINVAL; if (addr_len < sizeof(*addr)) @@ -286,41 +287,34 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (addr_type & IPV6_ADDR_MULTICAST) return -EADDRNOTAVAIL; - err = -EADDRINUSE; - read_lock_bh(&l2tp_ip6_lock); - if (__l2tp_ip6_bind_lookup(net, &addr->l2tp_addr, - sk->sk_bound_dev_if, addr->l2tp_conn_id)) - goto out_in_use; - read_unlock_bh(&l2tp_ip6_lock); - lock_sock(sk); err = -EINVAL; + if (!sock_flag(sk, SOCK_ZAPPED)) + goto out_unlock; + if (sk->sk_state != TCP_CLOSE) goto out_unlock; + bound_dev_if = sk->sk_bound_dev_if; + /* Check if the address belongs to the host. */ rcu_read_lock(); if (addr_type != IPV6_ADDR_ANY) { struct net_device *dev = NULL; if (addr_type & IPV6_ADDR_LINKLOCAL) { - if (addr_len >= sizeof(struct sockaddr_in6) && - addr->l2tp_scope_id) { - /* Override any existing binding, if another - * one is supplied by user. - */ - sk->sk_bound_dev_if = addr->l2tp_scope_id; - } + if (addr->l2tp_scope_id) + bound_dev_if = addr->l2tp_scope_id; /* Binding to link-local address requires an - interface */ - if (!sk->sk_bound_dev_if) + * interface. + */ + if (!bound_dev_if) goto out_unlock_rcu; err = -ENODEV; - dev = dev_get_by_index_rcu(sock_net(sk), - sk->sk_bound_dev_if); + dev = dev_get_by_index_rcu(sock_net(sk), bound_dev_if); if (!dev) goto out_unlock_rcu; } @@ -335,13 +329,22 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) } rcu_read_unlock(); - inet->inet_rcv_saddr = inet->inet_saddr = v4addr; + write_lock_bh(&l2tp_ip6_lock); + if (__l2tp_ip6_bind_lookup(net, &addr->l2tp_addr, bound_dev_if, + addr->l2tp_conn_id)) { + write_unlock_bh(&l2tp_ip6_lock); + err = -EADDRINUSE; + goto out_unlock; + } + + inet->inet_saddr = v4addr; + inet->inet_rcv_saddr = v4addr; + sk->sk_bound_dev_if = bound_dev_if; sk->sk_v6_rcv_saddr = addr->l2tp_addr; np->saddr = addr->l2tp_addr; l2tp_ip6_sk(sk)->conn_id = addr->l2tp_conn_id; - write_lock_bh(&l2tp_ip6_lock); sk_add_bind_node(sk, &l2tp_ip6_bind_table); sk_del_node_init(sk); write_unlock_bh(&l2tp_ip6_lock); @@ -354,10 +357,7 @@ out_unlock_rcu: rcu_read_unlock(); out_unlock: release_sock(sk); - return err; -out_in_use: - read_unlock_bh(&l2tp_ip6_lock); return err; } @@ -370,9 +370,6 @@ static int l2tp_ip6_connect(struct sock *sk, struct sockaddr *uaddr, int addr_type; int rc; - if (sock_flag(sk, SOCK_ZAPPED)) /* Must bind first - autobinding does not work */ - return -EINVAL; - if (addr_len < sizeof(*lsa)) return -EINVAL; @@ -389,10 +386,18 @@ static int l2tp_ip6_connect(struct sock *sk, struct sockaddr *uaddr, return -EINVAL; } - rc = ip6_datagram_connect(sk, uaddr, addr_len); - lock_sock(sk); + /* Must bind first - autobinding does not work */ + if (sock_flag(sk, SOCK_ZAPPED)) { + rc = -EINVAL; + goto out_sk; + } + + rc = __ip6_datagram_connect(sk, uaddr, addr_len); + if (rc < 0) + goto out_sk; + l2tp_ip6_sk(sk)->peer_conn_id = lsa->l2tp_conn_id; write_lock_bh(&l2tp_ip6_lock); @@ -400,6 +405,7 @@ static int l2tp_ip6_connect(struct sock *sk, struct sockaddr *uaddr, sk_add_bind_node(sk, &l2tp_ip6_bind_table); write_unlock_bh(&l2tp_ip6_lock); +out_sk: release_sock(sk); return rc; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 78e9ecbc96e6..8e05032689f0 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -688,7 +688,7 @@ static void __sta_info_recalc_tim(struct sta_info *sta, bool ignore_pending) } /* No need to do anything if the driver does all */ - if (!local->ops->set_tim) + if (ieee80211_hw_check(&local->hw, AP_LINK_PS)) return; if (sta->dead) diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 1c56abc49627..bd5f4be89435 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1501,7 +1501,6 @@ static bool ieee80211_queue_skb(struct ieee80211_local *local, struct sta_info *sta, struct sk_buff *skb) { - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct fq *fq = &local->fq; struct ieee80211_vif *vif; struct txq_info *txqi; @@ -1526,8 +1525,6 @@ static bool ieee80211_queue_skb(struct ieee80211_local *local, if (!txqi) return false; - info->control.vif = vif; - spin_lock_bh(&fq->lock); ieee80211_txq_enqueue(local, txqi, skb); spin_unlock_bh(&fq->lock); @@ -3213,7 +3210,6 @@ static void ieee80211_xmit_fast_finish(struct ieee80211_sub_if_data *sdata, if (hdr->frame_control & cpu_to_le16(IEEE80211_STYPE_QOS_DATA)) { tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK; - *ieee80211_get_qos_ctl(hdr) = tid; hdr->seq_ctrl = ieee80211_tx_next_seq(sta, tid); } else { info->flags |= IEEE80211_TX_CTL_ASSIGN_SEQ; @@ -3338,6 +3334,11 @@ static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata, (tid_tx ? IEEE80211_TX_CTL_AMPDU : 0); info->control.flags = IEEE80211_TX_CTRL_FAST_XMIT; + if (hdr->frame_control & cpu_to_le16(IEEE80211_STYPE_QOS_DATA)) { + tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK; + *ieee80211_get_qos_ctl(hdr) = tid; + } + __skb_queue_head_init(&tx.skbs); tx.flags = IEEE80211_TX_UNICAST; @@ -3426,6 +3427,11 @@ begin: goto begin; } + if (test_bit(IEEE80211_TXQ_AMPDU, &txqi->flags)) + info->flags |= IEEE80211_TX_CTL_AMPDU; + else + info->flags &= ~IEEE80211_TX_CTL_AMPDU; + if (info->control.flags & IEEE80211_TX_CTRL_FAST_XMIT) { struct sta_info *sta = container_of(txq->sta, struct sta_info, sta); diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index ee715764a828..6832bf6ab69f 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -270,6 +270,22 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, vht_cap->vht_mcs.tx_mcs_map |= cpu_to_le16(peer_tx << i * 2); } + /* + * This is a workaround for VHT-enabled STAs which break the spec + * and have the VHT-MCS Rx map filled in with value 3 for all eight + * spacial streams, an example is AR9462. + * + * As per spec, in section 22.1.1 Introduction to the VHT PHY + * A VHT STA shall support at least single spactial stream VHT-MCSs + * 0 to 7 (transmit and receive) in all supported channel widths. + */ + if (vht_cap->vht_mcs.rx_mcs_map == cpu_to_le16(0xFFFF)) { + vht_cap->vht_supported = false; + sdata_info(sdata, "Ignoring VHT IE from %pM due to invalid rx_mcs_map\n", + sta->addr); + return; + } + /* finally set up the bandwidth */ switch (vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK) { case IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ: diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 0e4334cbde17..15fe97644ffe 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -1252,7 +1252,7 @@ static int rtm_to_route_config(struct sk_buff *skb, struct nlmsghdr *nlh, if (!nla) continue; - switch(index) { + switch (index) { case RTA_OIF: cfg->rc_ifindex = nla_get_u32(nla); break; diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index bbb8f3df79f7..5b9c884a452e 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -42,7 +42,7 @@ struct nf_nat_conn_key { const struct nf_conntrack_zone *zone; }; -static struct rhashtable nf_nat_bysource_table; +static struct rhltable nf_nat_bysource_table; inline const struct nf_nat_l3proto * __nf_nat_l3proto_find(u8 family) @@ -193,9 +193,12 @@ static int nf_nat_bysource_cmp(struct rhashtable_compare_arg *arg, const struct nf_nat_conn_key *key = arg->key; const struct nf_conn *ct = obj; - return same_src(ct, key->tuple) && - net_eq(nf_ct_net(ct), key->net) && - nf_ct_zone_equal(ct, key->zone, IP_CT_DIR_ORIGINAL); + if (!same_src(ct, key->tuple) || + !net_eq(nf_ct_net(ct), key->net) || + !nf_ct_zone_equal(ct, key->zone, IP_CT_DIR_ORIGINAL)) + return 1; + + return 0; } static struct rhashtable_params nf_nat_bysource_params = { @@ -204,7 +207,6 @@ static struct rhashtable_params nf_nat_bysource_params = { .obj_cmpfn = nf_nat_bysource_cmp, .nelem_hint = 256, .min_size = 1024, - .nulls_base = (1U << RHT_BASE_SHIFT), }; /* Only called for SRC manip */ @@ -223,12 +225,15 @@ find_appropriate_src(struct net *net, .tuple = tuple, .zone = zone }; + struct rhlist_head *hl; - ct = rhashtable_lookup_fast(&nf_nat_bysource_table, &key, - nf_nat_bysource_params); - if (!ct) + hl = rhltable_lookup(&nf_nat_bysource_table, &key, + nf_nat_bysource_params); + if (!hl) return 0; + ct = container_of(hl, typeof(*ct), nat_bysource); + nf_ct_invert_tuplepr(result, &ct->tuplehash[IP_CT_DIR_REPLY].tuple); result->dst = tuple->dst; @@ -446,11 +451,17 @@ nf_nat_setup_info(struct nf_conn *ct, } if (maniptype == NF_NAT_MANIP_SRC) { + struct nf_nat_conn_key key = { + .net = nf_ct_net(ct), + .tuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, + .zone = nf_ct_zone(ct), + }; int err; - err = rhashtable_insert_fast(&nf_nat_bysource_table, - &ct->nat_bysource, - nf_nat_bysource_params); + err = rhltable_insert_key(&nf_nat_bysource_table, + &key, + &ct->nat_bysource, + nf_nat_bysource_params); if (err) return NF_DROP; } @@ -567,8 +578,8 @@ static int nf_nat_proto_clean(struct nf_conn *ct, void *data) * will delete entry from already-freed table. */ ct->status &= ~IPS_NAT_DONE_MASK; - rhashtable_remove_fast(&nf_nat_bysource_table, &ct->nat_bysource, - nf_nat_bysource_params); + rhltable_remove(&nf_nat_bysource_table, &ct->nat_bysource, + nf_nat_bysource_params); /* don't delete conntrack. Although that would make things a lot * simpler, we'd end up flushing all conntracks on nat rmmod. @@ -698,8 +709,8 @@ static void nf_nat_cleanup_conntrack(struct nf_conn *ct) if (!nat) return; - rhashtable_remove_fast(&nf_nat_bysource_table, &ct->nat_bysource, - nf_nat_bysource_params); + rhltable_remove(&nf_nat_bysource_table, &ct->nat_bysource, + nf_nat_bysource_params); } static struct nf_ct_ext_type nat_extend __read_mostly = { @@ -834,13 +845,13 @@ static int __init nf_nat_init(void) { int ret; - ret = rhashtable_init(&nf_nat_bysource_table, &nf_nat_bysource_params); + ret = rhltable_init(&nf_nat_bysource_table, &nf_nat_bysource_params); if (ret) return ret; ret = nf_ct_extend_register(&nat_extend); if (ret < 0) { - rhashtable_destroy(&nf_nat_bysource_table); + rhltable_destroy(&nf_nat_bysource_table); printk(KERN_ERR "nf_nat_core: Unable to register extension\n"); return ret; } @@ -864,7 +875,7 @@ static int __init nf_nat_init(void) return 0; cleanup_extend: - rhashtable_destroy(&nf_nat_bysource_table); + rhltable_destroy(&nf_nat_bysource_table); nf_ct_extend_unregister(&nat_extend); return ret; } @@ -883,7 +894,7 @@ static void __exit nf_nat_cleanup(void) for (i = 0; i < NFPROTO_NUMPROTO; i++) kfree(nf_nat_l4protos[i]); - rhashtable_destroy(&nf_nat_bysource_table); + rhltable_destroy(&nf_nat_bysource_table); } MODULE_LICENSE("GPL"); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 026581b04ea8..e5194f6f906c 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2570,7 +2570,8 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, } if (set->timeout && - nla_put_be64(skb, NFTA_SET_TIMEOUT, cpu_to_be64(set->timeout), + nla_put_be64(skb, NFTA_SET_TIMEOUT, + cpu_to_be64(jiffies_to_msecs(set->timeout)), NFTA_SET_PAD)) goto nla_put_failure; if (set->gc_int && @@ -2859,7 +2860,8 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, if (nla[NFTA_SET_TIMEOUT] != NULL) { if (!(flags & NFT_SET_TIMEOUT)) return -EINVAL; - timeout = be64_to_cpu(nla_get_be64(nla[NFTA_SET_TIMEOUT])); + timeout = msecs_to_jiffies(be64_to_cpu(nla_get_be64( + nla[NFTA_SET_TIMEOUT]))); } gc_int = 0; if (nla[NFTA_SET_GC_INTERVAL] != NULL) { @@ -3178,7 +3180,8 @@ static int nf_tables_fill_setelem(struct sk_buff *skb, if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) && nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT, - cpu_to_be64(*nft_set_ext_timeout(ext)), + cpu_to_be64(jiffies_to_msecs( + *nft_set_ext_timeout(ext))), NFTA_SET_ELEM_PAD)) goto nla_put_failure; @@ -3447,7 +3450,7 @@ void *nft_set_elem_init(const struct nft_set *set, memcpy(nft_set_ext_data(ext), data, set->dlen); if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) *nft_set_ext_expiration(ext) = - jiffies + msecs_to_jiffies(timeout); + jiffies + timeout; if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT)) *nft_set_ext_timeout(ext) = timeout; @@ -3535,7 +3538,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (nla[NFTA_SET_ELEM_TIMEOUT] != NULL) { if (!(set->flags & NFT_SET_TIMEOUT)) return -EINVAL; - timeout = be64_to_cpu(nla_get_be64(nla[NFTA_SET_ELEM_TIMEOUT])); + timeout = msecs_to_jiffies(be64_to_cpu(nla_get_be64( + nla[NFTA_SET_ELEM_TIMEOUT]))); } else if (set->flags & NFT_SET_TIMEOUT) { timeout = set->timeout; } diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index baf694de3935..d5447a22275c 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -53,6 +53,7 @@ static int nft_hash_init(const struct nft_ctx *ctx, { struct nft_hash *priv = nft_expr_priv(expr); u32 len; + int err; if (!tb[NFTA_HASH_SREG] || !tb[NFTA_HASH_DREG] || @@ -67,8 +68,10 @@ static int nft_hash_init(const struct nft_ctx *ctx, priv->sreg = nft_parse_register(tb[NFTA_HASH_SREG]); priv->dreg = nft_parse_register(tb[NFTA_HASH_DREG]); - len = ntohl(nla_get_be32(tb[NFTA_HASH_LEN])); - if (len == 0 || len > U8_MAX) + err = nft_parse_u32_check(tb[NFTA_HASH_LEN], U8_MAX, &len); + if (err < 0) + return err; + if (len == 0) return -ERANGE; priv->len = len; diff --git a/net/netfilter/nft_range.c b/net/netfilter/nft_range.c index fbc88009ca2e..8f0aaaea1376 100644 --- a/net/netfilter/nft_range.c +++ b/net/netfilter/nft_range.c @@ -59,6 +59,12 @@ static int nft_range_init(const struct nft_ctx *ctx, const struct nft_expr *expr int err; u32 op; + if (!tb[NFTA_RANGE_SREG] || + !tb[NFTA_RANGE_OP] || + !tb[NFTA_RANGE_FROM_DATA] || + !tb[NFTA_RANGE_TO_DATA]) + return -EINVAL; + err = nft_data_init(NULL, &priv->data_from, sizeof(priv->data_from), &desc_from, tb[NFTA_RANGE_FROM_DATA]); if (err < 0) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 62bea4591054..246f29d365c0 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -329,7 +329,6 @@ static void netlink_sock_destruct(struct sock *sk) if (nlk->cb_running) { if (nlk->cb.done) nlk->cb.done(&nlk->cb); - module_put(nlk->cb.module); kfree_skb(nlk->cb.skb); } @@ -346,6 +345,14 @@ static void netlink_sock_destruct(struct sock *sk) WARN_ON(nlk_sk(sk)->groups); } +static void netlink_sock_destruct_work(struct work_struct *work) +{ + struct netlink_sock *nlk = container_of(work, struct netlink_sock, + work); + + sk_free(&nlk->sk); +} + /* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it is _very_ bad on * SMP. Look, when several writers sleep and reader wakes them up, all but one * immediately hit write lock and grab all the cpus. Exclusive sleep solves @@ -648,8 +655,18 @@ out_module: static void deferred_put_nlk_sk(struct rcu_head *head) { struct netlink_sock *nlk = container_of(head, struct netlink_sock, rcu); + struct sock *sk = &nlk->sk; + + if (!atomic_dec_and_test(&sk->sk_refcnt)) + return; + + if (nlk->cb_running && nlk->cb.done) { + INIT_WORK(&nlk->work, netlink_sock_destruct_work); + schedule_work(&nlk->work); + return; + } - sock_put(&nlk->sk); + sk_free(sk); } static int netlink_release(struct socket *sock) diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h index 3cfd6cc60504..4fdb38318977 100644 --- a/net/netlink/af_netlink.h +++ b/net/netlink/af_netlink.h @@ -3,6 +3,7 @@ #include <linux/rhashtable.h> #include <linux/atomic.h> +#include <linux/workqueue.h> #include <net/sock.h> #define NLGRPSZ(x) (ALIGN(x, sizeof(unsigned long) * 8) / 8) @@ -33,6 +34,7 @@ struct netlink_sock { struct rhash_head node; struct rcu_head rcu; + struct work_struct work; }; static inline struct netlink_sock *nlk_sk(struct sock *sk) diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 31045ef44a82..fecefa2dc94e 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -370,8 +370,11 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key, skb_orphan(skb); memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm)); err = nf_ct_frag6_gather(net, skb, user); - if (err) + if (err) { + if (err != -EINPROGRESS) + kfree_skb(skb); return err; + } key->ip.proto = ipv6_hdr(skb)->nexthdr; ovs_cb.mru = IP6CB(skb)->frag_max_size; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index d2238b204691..dd2332390c45 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3648,19 +3648,25 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen != sizeof(val)) return -EINVAL; - if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) - return -EBUSY; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; switch (val) { case TPACKET_V1: case TPACKET_V2: case TPACKET_V3: - po->tp_version = val; - return 0; + break; default: return -EINVAL; } + lock_sock(sk); + if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { + ret = -EBUSY; + } else { + po->tp_version = val; + ret = 0; + } + release_sock(sk); + return ret; } case PACKET_RESERVE: { @@ -4164,6 +4170,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, /* Added to avoid minimal code churn */ struct tpacket_req *req = &req_u->req; + lock_sock(sk); /* Opening a Tx-ring is NOT supported in TPACKET_V3 */ if (!closing && tx_ring && (po->tp_version > TPACKET_V2)) { net_warn_ratelimited("Tx-ring is not supported.\n"); @@ -4245,7 +4252,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, goto out; } - lock_sock(sk); /* Detach socket from network */ spin_lock(&po->bind_lock); @@ -4294,11 +4300,11 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, if (!tx_ring) prb_shutdown_retire_blk_timer(po, rb_queue); } - release_sock(sk); if (pg_vec) free_pg_vec(pg_vec, order, req->tp_block_nr); out: + release_sock(sk); return err; } diff --git a/net/rds/tcp.c b/net/rds/tcp.c index fcddacc92e01..20e2923dc827 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -659,6 +659,8 @@ out_recv: out_pernet: unregister_pernet_subsys(&rds_tcp_net_ops); out_slab: + if (unregister_netdevice_notifier(&rds_tcp_dev_notifier)) + pr_warn("could not unregister rds_tcp_dev_notifier\n"); kmem_cache_destroy(rds_tcp_conn_slab); out: return ret; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index b54d56d4959b..cf9b2fe8eac6 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -108,6 +108,17 @@ static void tcf_pedit_cleanup(struct tc_action *a, int bind) kfree(keys); } +static bool offset_valid(struct sk_buff *skb, int offset) +{ + if (offset > 0 && offset > skb->len) + return false; + + if (offset < 0 && -offset > skb_headroom(skb)) + return false; + + return true; +} + static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { @@ -134,6 +145,11 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a, if (tkey->offmask) { char *d, _d; + if (!offset_valid(skb, off + tkey->at)) { + pr_info("tc filter pedit 'at' offset %d out of bounds\n", + off + tkey->at); + goto bad; + } d = skb_header_pointer(skb, off + tkey->at, 1, &_d); if (!d) @@ -146,10 +162,10 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a, " offset must be on 32 bit boundaries\n"); goto bad; } - if (offset > 0 && offset > skb->len) { - pr_info("tc filter pedit" - " offset %d can't exceed pkt length %d\n", - offset, skb->len); + + if (!offset_valid(skb, off + offset)) { + pr_info("tc filter pedit offset %d out of bounds\n", + offset); goto bad; } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 2b2a7974e4bb..b05d4a2155b0 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -430,7 +430,8 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb, if (!skb) return -ENOBUFS; - if (tcf_fill_node(net, skb, tp, fh, portid, n->nlmsg_seq, 0, event) <= 0) { + if (tcf_fill_node(net, skb, tp, fh, portid, n->nlmsg_seq, + n->nlmsg_flags, event) <= 0) { kfree_skb(skb); return -EINVAL; } diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index eb219b78cd49..5877f6061b57 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -62,9 +62,6 @@ static unsigned long basic_get(struct tcf_proto *tp, u32 handle) struct basic_head *head = rtnl_dereference(tp->root); struct basic_filter *f; - if (head == NULL) - return 0UL; - list_for_each_entry(f, &head->flist, link) { if (f->handle == handle) { l = (unsigned long) f; @@ -109,7 +106,6 @@ static bool basic_destroy(struct tcf_proto *tp, bool force) tcf_unbind_filter(tp, &f->res); call_rcu(&f->rcu, basic_delete_filter); } - RCU_INIT_POINTER(tp->root, NULL); kfree_rcu(head, rcu); return true; } diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index bb1d5a487081..0a47ba5e6109 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -292,7 +292,6 @@ static bool cls_bpf_destroy(struct tcf_proto *tp, bool force) call_rcu(&prog->rcu, __cls_bpf_delete_prog); } - RCU_INIT_POINTER(tp->root, NULL); kfree_rcu(head, rcu); return true; } @@ -303,9 +302,6 @@ static unsigned long cls_bpf_get(struct tcf_proto *tp, u32 handle) struct cls_bpf_prog *prog; unsigned long ret = 0UL; - if (head == NULL) - return 0UL; - list_for_each_entry(prog, &head->plist, link) { if (prog->handle == handle) { ret = (unsigned long) prog; diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index 85233c470035..c1f20077837f 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -137,11 +137,10 @@ static bool cls_cgroup_destroy(struct tcf_proto *tp, bool force) if (!force) return false; - - if (head) { - RCU_INIT_POINTER(tp->root, NULL); + /* Head can still be NULL due to cls_cgroup_init(). */ + if (head) call_rcu(&head->rcu, cls_cgroup_destroy_rcu); - } + return true; } diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index e39672394c7b..6575aba87630 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -596,7 +596,6 @@ static bool flow_destroy(struct tcf_proto *tp, bool force) list_del_rcu(&f->list); call_rcu(&f->rcu, flow_destroy_filter); } - RCU_INIT_POINTER(tp->root, NULL); kfree_rcu(head, rcu); return true; } diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index f6f40fba599b..904442421db3 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -13,6 +13,7 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/rhashtable.h> +#include <linux/workqueue.h> #include <linux/if_ether.h> #include <linux/in6.h> @@ -64,7 +65,10 @@ struct cls_fl_head { bool mask_assigned; struct list_head filters; struct rhashtable_params ht_params; - struct rcu_head rcu; + union { + struct work_struct work; + struct rcu_head rcu; + }; }; struct cls_fl_filter { @@ -269,6 +273,24 @@ static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f) dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, &tc); } +static void fl_destroy_sleepable(struct work_struct *work) +{ + struct cls_fl_head *head = container_of(work, struct cls_fl_head, + work); + if (head->mask_assigned) + rhashtable_destroy(&head->ht); + kfree(head); + module_put(THIS_MODULE); +} + +static void fl_destroy_rcu(struct rcu_head *rcu) +{ + struct cls_fl_head *head = container_of(rcu, struct cls_fl_head, rcu); + + INIT_WORK(&head->work, fl_destroy_sleepable); + schedule_work(&head->work); +} + static bool fl_destroy(struct tcf_proto *tp, bool force) { struct cls_fl_head *head = rtnl_dereference(tp->root); @@ -282,10 +304,9 @@ static bool fl_destroy(struct tcf_proto *tp, bool force) list_del_rcu(&f->list); call_rcu(&f->rcu, fl_destroy_filter); } - RCU_INIT_POINTER(tp->root, NULL); - if (head->mask_assigned) - rhashtable_destroy(&head->ht); - kfree_rcu(head, rcu); + + __module_get(THIS_MODULE); + call_rcu(&head->rcu, fl_destroy_rcu); return true; } @@ -711,8 +732,9 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, goto errout; if (fold) { - rhashtable_remove_fast(&head->ht, &fold->ht_node, - head->ht_params); + if (!tc_skip_sw(fold->flags)) + rhashtable_remove_fast(&head->ht, &fold->ht_node, + head->ht_params); fl_hw_destroy_filter(tp, (unsigned long)fold); } @@ -739,8 +761,9 @@ static int fl_delete(struct tcf_proto *tp, unsigned long arg) struct cls_fl_head *head = rtnl_dereference(tp->root); struct cls_fl_filter *f = (struct cls_fl_filter *) arg; - rhashtable_remove_fast(&head->ht, &f->ht_node, - head->ht_params); + if (!tc_skip_sw(f->flags)) + rhashtable_remove_fast(&head->ht, &f->ht_node, + head->ht_params); list_del_rcu(&f->list); fl_hw_destroy_filter(tp, (unsigned long)f); tcf_unbind_filter(tp, &f->res); diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index 25927b6c4436..f935429bd5ef 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -114,7 +114,6 @@ static bool mall_destroy(struct tcf_proto *tp, bool force) call_rcu(&f->rcu, mall_destroy_filter); } - RCU_INIT_POINTER(tp->root, NULL); kfree_rcu(head, rcu); return true; } diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index 4f05a19fb073..322438fb3ffc 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -152,7 +152,8 @@ static int rsvp_classify(struct sk_buff *skb, const struct tcf_proto *tp, return -1; nhptr = ip_hdr(skb); #endif - + if (unlikely(!head)) + return -1; restart: #if RSVP_DST_LEN == 4 diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index 96144bdf30db..0751245a6ace 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -543,7 +543,6 @@ static bool tcindex_destroy(struct tcf_proto *tp, bool force) walker.fn = tcindex_destroy_element; tcindex_walk(tp, &walker); - RCU_INIT_POINTER(tp->root, NULL); call_rcu(&p->rcu, __tcindex_destroy); return true; } diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 975dbeb60ab0..52d74760fb68 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -421,6 +421,10 @@ int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b, dev = dev_get_by_name(net, driver_name); if (!dev) return -ENODEV; + if (tipc_mtu_bad(dev, 0)) { + dev_put(dev); + return -EINVAL; + } /* Associate TIPC bearer with L2 bearer */ rcu_assign_pointer(b->media_ptr, dev); @@ -610,8 +614,6 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt, if (!b) return NOTIFY_DONE; - b->mtu = dev->mtu; - switch (evt) { case NETDEV_CHANGE: if (netif_carrier_ok(dev)) @@ -624,6 +626,11 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt, tipc_reset_bearer(net, b); break; case NETDEV_CHANGEMTU: + if (tipc_mtu_bad(dev, 0)) { + bearer_disable(net, b); + break; + } + b->mtu = dev->mtu; tipc_reset_bearer(net, b); break; case NETDEV_CHANGEADDR: diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 78892e2f53e3..278ff7f616f9 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -39,6 +39,7 @@ #include "netlink.h" #include "core.h" +#include "msg.h" #include <net/genetlink.h> #define MAX_MEDIA 3 @@ -59,6 +60,9 @@ #define TIPC_MEDIA_TYPE_IB 2 #define TIPC_MEDIA_TYPE_UDP 3 +/* minimum bearer MTU */ +#define TIPC_MIN_BEARER_MTU (MAX_H_SIZE + INT_H_SIZE) + /** * struct tipc_media_addr - destination address used by TIPC bearers * @value: address info (format defined by media) @@ -215,4 +219,13 @@ void tipc_bearer_xmit(struct net *net, u32 bearer_id, void tipc_bearer_bc_xmit(struct net *net, u32 bearer_id, struct sk_buff_head *xmitq); +/* check if device MTU is too low for tipc headers */ +static inline bool tipc_mtu_bad(struct net_device *dev, unsigned int reserve) +{ + if (dev->mtu >= TIPC_MIN_BEARER_MTU + reserve) + return false; + netdev_warn(dev, "MTU too low for tipc bearer\n"); + return true; +} + #endif /* _TIPC_BEARER_H */ diff --git a/net/tipc/link.c b/net/tipc/link.c index 1055164c6232..bda89bf9f4ff 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -47,8 +47,8 @@ #include <linux/pkt_sched.h> struct tipc_stats { - u32 sent_info; /* used in counting # sent packets */ - u32 recv_info; /* used in counting # recv'd packets */ + u32 sent_pkts; + u32 recv_pkts; u32 sent_states; u32 recv_states; u32 sent_probes; @@ -857,7 +857,6 @@ void tipc_link_reset(struct tipc_link *l) l->acked = 0; l->silent_intv_cnt = 0; l->rst_cnt = 0; - l->stats.recv_info = 0; l->stale_count = 0; l->bc_peer_is_up = false; memset(&l->mon_state, 0, sizeof(l->mon_state)); @@ -888,6 +887,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, struct sk_buff_head *transmq = &l->transmq; struct sk_buff_head *backlogq = &l->backlogq; struct sk_buff *skb, *_skb, *bskb; + int pkt_cnt = skb_queue_len(list); /* Match msg importance against this and all higher backlog limits: */ if (!skb_queue_empty(backlogq)) { @@ -901,6 +901,11 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, return -EMSGSIZE; } + if (pkt_cnt > 1) { + l->stats.sent_fragmented++; + l->stats.sent_fragments += pkt_cnt; + } + /* Prepare each packet for sending, and add to relevant queue: */ while (skb_queue_len(list)) { skb = skb_peek(list); @@ -920,6 +925,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, __skb_queue_tail(xmitq, _skb); TIPC_SKB_CB(skb)->ackers = l->ackers; l->rcv_unacked = 0; + l->stats.sent_pkts++; seqno++; continue; } @@ -968,6 +974,7 @@ void tipc_link_advance_backlog(struct tipc_link *l, struct sk_buff_head *xmitq) msg_set_ack(hdr, ack); msg_set_bcast_ack(hdr, bc_ack); l->rcv_unacked = 0; + l->stats.sent_pkts++; seqno++; } l->snd_nxt = seqno; @@ -1260,7 +1267,7 @@ int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb, /* Deliver packet */ l->rcv_nxt++; - l->stats.recv_info++; + l->stats.recv_pkts++; if (!tipc_data_input(l, skb, l->inputq)) rc |= tipc_link_input(l, skb, l->inputq); if (unlikely(++l->rcv_unacked >= TIPC_MIN_LINK_WIN)) @@ -1492,8 +1499,9 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL)) l->tolerance = peers_tol; - if (peers_prio && in_range(peers_prio, TIPC_MIN_LINK_PRI, - TIPC_MAX_LINK_PRI)) { + /* Update own prio if peer indicates a different value */ + if ((peers_prio != l->priority) && + in_range(peers_prio, 1, TIPC_MAX_LINK_PRI)) { l->priority = peers_prio; rc = tipc_link_fsm_evt(l, LINK_FAILURE_EVT); } @@ -1799,10 +1807,6 @@ void tipc_link_set_queue_limits(struct tipc_link *l, u32 win) void tipc_link_reset_stats(struct tipc_link *l) { memset(&l->stats, 0, sizeof(l->stats)); - if (!link_is_bc_sndlink(l)) { - l->stats.sent_info = l->snd_nxt; - l->stats.recv_info = l->rcv_nxt; - } } static void link_print(struct tipc_link *l, const char *str) @@ -1866,12 +1870,12 @@ static int __tipc_nl_add_stats(struct sk_buff *skb, struct tipc_stats *s) }; struct nla_map map[] = { - {TIPC_NLA_STATS_RX_INFO, s->recv_info}, + {TIPC_NLA_STATS_RX_INFO, 0}, {TIPC_NLA_STATS_RX_FRAGMENTS, s->recv_fragments}, {TIPC_NLA_STATS_RX_FRAGMENTED, s->recv_fragmented}, {TIPC_NLA_STATS_RX_BUNDLES, s->recv_bundles}, {TIPC_NLA_STATS_RX_BUNDLED, s->recv_bundled}, - {TIPC_NLA_STATS_TX_INFO, s->sent_info}, + {TIPC_NLA_STATS_TX_INFO, 0}, {TIPC_NLA_STATS_TX_FRAGMENTS, s->sent_fragments}, {TIPC_NLA_STATS_TX_FRAGMENTED, s->sent_fragmented}, {TIPC_NLA_STATS_TX_BUNDLES, s->sent_bundles}, @@ -1946,9 +1950,9 @@ int __tipc_nl_add_link(struct net *net, struct tipc_nl_msg *msg, goto attr_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_LINK_MTU, link->mtu)) goto attr_msg_full; - if (nla_put_u32(msg->skb, TIPC_NLA_LINK_RX, link->rcv_nxt)) + if (nla_put_u32(msg->skb, TIPC_NLA_LINK_RX, link->stats.recv_pkts)) goto attr_msg_full; - if (nla_put_u32(msg->skb, TIPC_NLA_LINK_TX, link->snd_nxt)) + if (nla_put_u32(msg->skb, TIPC_NLA_LINK_TX, link->stats.sent_pkts)) goto attr_msg_full; if (tipc_link_is_up(link)) @@ -2003,12 +2007,12 @@ static int __tipc_nl_add_bc_link_stat(struct sk_buff *skb, }; struct nla_map map[] = { - {TIPC_NLA_STATS_RX_INFO, stats->recv_info}, + {TIPC_NLA_STATS_RX_INFO, stats->recv_pkts}, {TIPC_NLA_STATS_RX_FRAGMENTS, stats->recv_fragments}, {TIPC_NLA_STATS_RX_FRAGMENTED, stats->recv_fragmented}, {TIPC_NLA_STATS_RX_BUNDLES, stats->recv_bundles}, {TIPC_NLA_STATS_RX_BUNDLED, stats->recv_bundled}, - {TIPC_NLA_STATS_TX_INFO, stats->sent_info}, + {TIPC_NLA_STATS_TX_INFO, stats->sent_pkts}, {TIPC_NLA_STATS_TX_FRAGMENTS, stats->sent_fragments}, {TIPC_NLA_STATS_TX_FRAGMENTED, stats->sent_fragmented}, {TIPC_NLA_STATS_TX_BUNDLES, stats->sent_bundles}, @@ -2075,9 +2079,9 @@ int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg) goto attr_msg_full; if (nla_put_string(msg->skb, TIPC_NLA_LINK_NAME, bcl->name)) goto attr_msg_full; - if (nla_put_u32(msg->skb, TIPC_NLA_LINK_RX, bcl->rcv_nxt)) + if (nla_put_u32(msg->skb, TIPC_NLA_LINK_RX, 0)) goto attr_msg_full; - if (nla_put_u32(msg->skb, TIPC_NLA_LINK_TX, bcl->snd_nxt)) + if (nla_put_u32(msg->skb, TIPC_NLA_LINK_TX, 0)) goto attr_msg_full; prop = nla_nest_start(msg->skb, TIPC_NLA_LINK_PROP); diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c index ed97a5876ebe..9e109bb1a207 100644 --- a/net/tipc/monitor.c +++ b/net/tipc/monitor.c @@ -455,14 +455,14 @@ void tipc_mon_rcv(struct net *net, void *data, u16 dlen, u32 addr, int i, applied_bef; state->probing = false; - if (!dlen) - return; /* Sanity check received domain record */ - if ((dlen < new_dlen) || ntohs(arrv_dom->len) != new_dlen) { - pr_warn_ratelimited("Received illegal domain record\n"); + if (dlen < dom_rec_len(arrv_dom, 0)) + return; + if (dlen != dom_rec_len(arrv_dom, new_member_cnt)) + return; + if ((dlen < new_dlen) || ntohs(arrv_dom->len) != new_dlen) return; - } /* Synch generation numbers with peer if link just came up */ if (!state->synched) { diff --git a/net/tipc/socket.c b/net/tipc/socket.c index f9f5f3c3dab5..41f013888f07 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1,7 +1,7 @@ /* * net/tipc/socket.c: TIPC socket API * - * Copyright (c) 2001-2007, 2012-2015, Ericsson AB + * Copyright (c) 2001-2007, 2012-2016, Ericsson AB * Copyright (c) 2004-2008, 2010-2013, Wind River Systems * All rights reserved. * @@ -129,54 +129,8 @@ static const struct proto_ops packet_ops; static const struct proto_ops stream_ops; static const struct proto_ops msg_ops; static struct proto tipc_proto; - static const struct rhashtable_params tsk_rht_params; -/* - * Revised TIPC socket locking policy: - * - * Most socket operations take the standard socket lock when they start - * and hold it until they finish (or until they need to sleep). Acquiring - * this lock grants the owner exclusive access to the fields of the socket - * data structures, with the exception of the backlog queue. A few socket - * operations can be done without taking the socket lock because they only - * read socket information that never changes during the life of the socket. - * - * Socket operations may acquire the lock for the associated TIPC port if they - * need to perform an operation on the port. If any routine needs to acquire - * both the socket lock and the port lock it must take the socket lock first - * to avoid the risk of deadlock. - * - * The dispatcher handling incoming messages cannot grab the socket lock in - * the standard fashion, since invoked it runs at the BH level and cannot block. - * Instead, it checks to see if the socket lock is currently owned by someone, - * and either handles the message itself or adds it to the socket's backlog - * queue; in the latter case the queued message is processed once the process - * owning the socket lock releases it. - * - * NOTE: Releasing the socket lock while an operation is sleeping overcomes - * the problem of a blocked socket operation preventing any other operations - * from occurring. However, applications must be careful if they have - * multiple threads trying to send (or receive) on the same socket, as these - * operations might interfere with each other. For example, doing a connect - * and a receive at the same time might allow the receive to consume the - * ACK message meant for the connect. While additional work could be done - * to try and overcome this, it doesn't seem to be worthwhile at the present. - * - * NOTE: Releasing the socket lock while an operation is sleeping also ensures - * that another operation that must be performed in a non-blocking manner is - * not delayed for very long because the lock has already been taken. - * - * NOTE: This code assumes that certain fields of a port/socket pair are - * constant over its lifetime; such fields can be examined without taking - * the socket lock and/or port lock, and do not need to be re-read even - * after resuming processing after waiting. These fields include: - * - socket type - * - pointer to socket sk structure (aka tipc_sock structure) - * - pointer to port structure - * - port reference - */ - static u32 tsk_own_node(struct tipc_sock *tsk) { return msg_prevnode(&tsk->phdr); @@ -232,7 +186,7 @@ static struct tipc_sock *tipc_sk(const struct sock *sk) static bool tsk_conn_cong(struct tipc_sock *tsk) { - return tsk->snt_unacked >= tsk->snd_win; + return tsk->snt_unacked > tsk->snd_win; } /* tsk_blocks(): translate a buffer size in bytes to number of diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 78cab9c5a445..b58dc95f3d35 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -697,6 +697,11 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, udp_conf.local_ip.s_addr = htonl(INADDR_ANY); udp_conf.use_udp_checksums = false; ub->ifindex = dev->ifindex; + if (tipc_mtu_bad(dev, sizeof(struct iphdr) + + sizeof(struct udphdr))) { + err = -EINVAL; + goto err; + } b->mtu = dev->mtu - sizeof(struct iphdr) - sizeof(struct udphdr); #if IS_ENABLED(CONFIG_IPV6) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 5d1c14a2f268..2358f2690ec5 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2199,7 +2199,8 @@ out: * Sleep until more data has arrived. But check for races.. */ static long unix_stream_data_wait(struct sock *sk, long timeo, - struct sk_buff *last, unsigned int last_len) + struct sk_buff *last, unsigned int last_len, + bool freezable) { struct sk_buff *tail; DEFINE_WAIT(wait); @@ -2220,7 +2221,10 @@ static long unix_stream_data_wait(struct sock *sk, long timeo, sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); unix_state_unlock(sk); - timeo = freezable_schedule_timeout(timeo); + if (freezable) + timeo = freezable_schedule_timeout(timeo); + else + timeo = schedule_timeout(timeo); unix_state_lock(sk); if (sock_flag(sk, SOCK_DEAD)) @@ -2250,7 +2254,8 @@ struct unix_stream_read_state { unsigned int splice_flags; }; -static int unix_stream_read_generic(struct unix_stream_read_state *state) +static int unix_stream_read_generic(struct unix_stream_read_state *state, + bool freezable) { struct scm_cookie scm; struct socket *sock = state->socket; @@ -2330,7 +2335,7 @@ again: mutex_unlock(&u->iolock); timeo = unix_stream_data_wait(sk, timeo, last, - last_len); + last_len, freezable); if (signal_pending(current)) { err = sock_intr_errno(timeo); @@ -2472,7 +2477,7 @@ static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg, .flags = flags }; - return unix_stream_read_generic(&state); + return unix_stream_read_generic(&state, true); } static int unix_stream_splice_actor(struct sk_buff *skb, @@ -2503,7 +2508,7 @@ static ssize_t unix_stream_splice_read(struct socket *sock, loff_t *ppos, flags & SPLICE_F_NONBLOCK) state.flags = MSG_DONTWAIT; - return unix_stream_read_generic(&state); + return unix_stream_read_generic(&state, false); } static int unix_shutdown(struct socket *sock, int mode) diff --git a/net/wireless/core.h b/net/wireless/core.h index 08d2e948c9ad..f0c0c8a48c92 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -71,6 +71,7 @@ struct cfg80211_registered_device { struct list_head bss_list; struct rb_root bss_tree; u32 bss_generation; + u32 bss_entries; struct cfg80211_scan_request *scan_req; /* protected by RTNL */ struct sk_buff *scan_msg; struct cfg80211_sched_scan_request __rcu *sched_scan_req; diff --git a/net/wireless/scan.c b/net/wireless/scan.c index b5bd58d0f731..35ad69fd0838 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -57,6 +57,19 @@ * also linked into the probe response struct. */ +/* + * Limit the number of BSS entries stored in mac80211. Each one is + * a bit over 4k at most, so this limits to roughly 4-5M of memory. + * If somebody wants to really attack this though, they'd likely + * use small beacons, and only one type of frame, limiting each of + * the entries to a much smaller size (in order to generate more + * entries in total, so overhead is bigger.) + */ +static int bss_entries_limit = 1000; +module_param(bss_entries_limit, int, 0644); +MODULE_PARM_DESC(bss_entries_limit, + "limit to number of scan BSS entries (per wiphy, default 1000)"); + #define IEEE80211_SCAN_RESULT_EXPIRE (30 * HZ) static void bss_free(struct cfg80211_internal_bss *bss) @@ -137,6 +150,10 @@ static bool __cfg80211_unlink_bss(struct cfg80211_registered_device *rdev, list_del_init(&bss->list); rb_erase(&bss->rbn, &rdev->bss_tree); + rdev->bss_entries--; + WARN_ONCE((rdev->bss_entries == 0) ^ list_empty(&rdev->bss_list), + "rdev bss entries[%d]/list[empty:%d] corruption\n", + rdev->bss_entries, list_empty(&rdev->bss_list)); bss_ref_put(rdev, bss); return true; } @@ -163,6 +180,40 @@ static void __cfg80211_bss_expire(struct cfg80211_registered_device *rdev, rdev->bss_generation++; } +static bool cfg80211_bss_expire_oldest(struct cfg80211_registered_device *rdev) +{ + struct cfg80211_internal_bss *bss, *oldest = NULL; + bool ret; + + lockdep_assert_held(&rdev->bss_lock); + + list_for_each_entry(bss, &rdev->bss_list, list) { + if (atomic_read(&bss->hold)) + continue; + + if (!list_empty(&bss->hidden_list) && + !bss->pub.hidden_beacon_bss) + continue; + + if (oldest && time_before(oldest->ts, bss->ts)) + continue; + oldest = bss; + } + + if (WARN_ON(!oldest)) + return false; + + /* + * The callers make sure to increase rdev->bss_generation if anything + * gets removed (and a new entry added), so there's no need to also do + * it here. + */ + + ret = __cfg80211_unlink_bss(rdev, oldest); + WARN_ON(!ret); + return ret; +} + void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev, bool send_message) { @@ -689,6 +740,7 @@ static bool cfg80211_combine_bsses(struct cfg80211_registered_device *rdev, const u8 *ie; int i, ssidlen; u8 fold = 0; + u32 n_entries = 0; ies = rcu_access_pointer(new->pub.beacon_ies); if (WARN_ON(!ies)) @@ -712,6 +764,12 @@ static bool cfg80211_combine_bsses(struct cfg80211_registered_device *rdev, /* This is the bad part ... */ list_for_each_entry(bss, &rdev->bss_list, list) { + /* + * we're iterating all the entries anyway, so take the + * opportunity to validate the list length accounting + */ + n_entries++; + if (!ether_addr_equal(bss->pub.bssid, new->pub.bssid)) continue; if (bss->pub.channel != new->pub.channel) @@ -740,6 +798,10 @@ static bool cfg80211_combine_bsses(struct cfg80211_registered_device *rdev, new->pub.beacon_ies); } + WARN_ONCE(n_entries != rdev->bss_entries, + "rdev bss entries[%d]/list[len:%d] corruption\n", + rdev->bss_entries, n_entries); + return true; } @@ -894,7 +956,14 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev, } } + if (rdev->bss_entries >= bss_entries_limit && + !cfg80211_bss_expire_oldest(rdev)) { + kfree(new); + goto drop; + } + list_add_tail(&new->list, &rdev->bss_list); + rdev->bss_entries++; rb_insert_bss(rdev, new); found = new; } diff --git a/net/wireless/util.c b/net/wireless/util.c index 5ea12afc7706..659b507b347d 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1158,7 +1158,8 @@ static u32 cfg80211_calculate_bitrate_vht(struct rate_info *rate) 58500000, 65000000, 78000000, - 0, + /* not in the spec, but some devices use this: */ + 86500000, }, { 13500000, 27000000, diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index fd6986634e6f..5bf7e1bfeac7 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1268,12 +1268,14 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, err = security_xfrm_policy_lookup(pol->security, fl->flowi_secid, policy_to_flow_dir(dir)); - if (!err && !xfrm_pol_hold_rcu(pol)) - goto again; - else if (err == -ESRCH) + if (!err) { + if (!xfrm_pol_hold_rcu(pol)) + goto again; + } else if (err == -ESRCH) { pol = NULL; - else + } else { pol = ERR_PTR(err); + } } else pol = NULL; } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 08892091cfe3..671a1d0333f0 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2450,7 +2450,7 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) #ifdef CONFIG_COMPAT if (in_compat_syscall()) - return -ENOTSUPP; + return -EOPNOTSUPP; #endif type = nlh->nlmsg_type; diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h index 90f44bd2045e..dadd5161bd91 100644 --- a/samples/bpf/bpf_helpers.h +++ b/samples/bpf/bpf_helpers.h @@ -113,7 +113,7 @@ static int (*bpf_skb_under_cgroup)(void *ctx, void *map, int index) = #define PT_REGS_FP(x) ((x)->gprs[11]) /* Works only with CONFIG_FRAME_POINTER */ #define PT_REGS_RC(x) ((x)->gprs[2]) #define PT_REGS_SP(x) ((x)->gprs[15]) -#define PT_REGS_IP(x) ((x)->ip) +#define PT_REGS_IP(x) ((x)->psw.addr) #elif defined(__aarch64__) diff --git a/samples/bpf/sampleip_kern.c b/samples/bpf/sampleip_kern.c index 774a681f374a..ceabf31079cf 100644 --- a/samples/bpf/sampleip_kern.c +++ b/samples/bpf/sampleip_kern.c @@ -25,7 +25,7 @@ int do_sample(struct bpf_perf_event_data *ctx) u64 ip; u32 *value, init_val = 1; - ip = ctx->regs.ip; + ip = PT_REGS_IP(&ctx->regs); value = bpf_map_lookup_elem(&ip_map, &ip); if (value) *value += 1; diff --git a/samples/bpf/trace_event_kern.c b/samples/bpf/trace_event_kern.c index 71a8ed32823e..41b6115a32eb 100644 --- a/samples/bpf/trace_event_kern.c +++ b/samples/bpf/trace_event_kern.c @@ -50,7 +50,7 @@ int bpf_prog1(struct bpf_perf_event_data *ctx) key.userstack = bpf_get_stackid(ctx, &stackmap, USER_STACKID_FLAGS); if ((int)key.kernstack < 0 && (int)key.userstack < 0) { bpf_trace_printk(fmt, sizeof(fmt), cpu, ctx->sample_period, - ctx->regs.ip); + PT_REGS_IP(&ctx->regs)); return 0; } diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile index ebced77deb9c..90a091b6ae4d 100644 --- a/scripts/kconfig/Makefile +++ b/scripts/kconfig/Makefile @@ -35,6 +35,8 @@ nconfig: $(obj)/nconf silentoldconfig: $(obj)/conf $(Q)mkdir -p include/config include/generated + $(Q)test -e include/generated/autoksyms.h || \ + touch include/generated/autoksyms.h $< $(silent) --$@ $(Kconfig) localyesconfig localmodconfig: $(obj)/streamline_config.pl $(obj)/conf diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c index fc3036b34e51..a4d90aa1045a 100644 --- a/security/apparmor/domain.c +++ b/security/apparmor/domain.c @@ -621,8 +621,8 @@ int aa_change_hat(const char *hats[], int count, u64 token, bool permtest) /* released below */ cred = get_current_cred(); cxt = cred_cxt(cred); - profile = aa_cred_profile(cred); - previous_profile = cxt->previous; + profile = aa_get_newest_profile(aa_cred_profile(cred)); + previous_profile = aa_get_newest_profile(cxt->previous); if (unconfined(profile)) { info = "unconfined"; @@ -718,6 +718,8 @@ audit: out: aa_put_profile(hat); kfree(name); + aa_put_profile(profile); + aa_put_profile(previous_profile); put_cred(cred); return error; diff --git a/sound/sparc/dbri.c b/sound/sparc/dbri.c index 0190cb6332f2..52063b262667 100644 --- a/sound/sparc/dbri.c +++ b/sound/sparc/dbri.c @@ -304,7 +304,7 @@ struct snd_dbri { spinlock_t lock; struct dbri_dma *dma; /* Pointer to our DMA block */ - u32 dma_dvma; /* DBRI visible DMA address */ + dma_addr_t dma_dvma; /* DBRI visible DMA address */ void __iomem *regs; /* dbri HW regs */ int dbri_irqp; /* intr queue pointer */ @@ -657,12 +657,14 @@ static void dbri_cmdwait(struct snd_dbri *dbri) */ static s32 *dbri_cmdlock(struct snd_dbri *dbri, int len) { + u32 dvma_addr = (u32)dbri->dma_dvma; + /* Space for 2 WAIT cmds (replaced later by 1 JUMP cmd) */ len += 2; spin_lock(&dbri->cmdlock); if (dbri->cmdptr - dbri->dma->cmd + len < DBRI_NO_CMDS - 2) return dbri->cmdptr + 2; - else if (len < sbus_readl(dbri->regs + REG8) - dbri->dma_dvma) + else if (len < sbus_readl(dbri->regs + REG8) - dvma_addr) return dbri->dma->cmd; else printk(KERN_ERR "DBRI: no space for commands."); @@ -680,6 +682,7 @@ static s32 *dbri_cmdlock(struct snd_dbri *dbri, int len) */ static void dbri_cmdsend(struct snd_dbri *dbri, s32 *cmd, int len) { + u32 dvma_addr = (u32)dbri->dma_dvma; s32 tmp, addr; static int wait_id = 0; @@ -689,7 +692,7 @@ static void dbri_cmdsend(struct snd_dbri *dbri, s32 *cmd, int len) *(cmd+1) = DBRI_CMD(D_WAIT, 1, wait_id); /* Replace the last command with JUMP */ - addr = dbri->dma_dvma + (cmd - len - dbri->dma->cmd) * sizeof(s32); + addr = dvma_addr + (cmd - len - dbri->dma->cmd) * sizeof(s32); *(dbri->cmdptr+1) = addr; *(dbri->cmdptr) = DBRI_CMD(D_JUMP, 0, 0); @@ -747,6 +750,7 @@ static void dbri_reset(struct snd_dbri *dbri) /* Lock must not be held before calling this */ static void dbri_initialize(struct snd_dbri *dbri) { + u32 dvma_addr = (u32)dbri->dma_dvma; s32 *cmd; u32 dma_addr; unsigned long flags; @@ -764,7 +768,7 @@ static void dbri_initialize(struct snd_dbri *dbri) /* * Initialize the interrupt ring buffer. */ - dma_addr = dbri->dma_dvma + dbri_dma_off(intr, 0); + dma_addr = dvma_addr + dbri_dma_off(intr, 0); dbri->dma->intr[0] = dma_addr; dbri->dbri_irqp = 1; /* @@ -778,7 +782,7 @@ static void dbri_initialize(struct snd_dbri *dbri) dbri->cmdptr = cmd; *(cmd++) = DBRI_CMD(D_WAIT, 1, 0); *(cmd++) = DBRI_CMD(D_WAIT, 1, 0); - dma_addr = dbri->dma_dvma + dbri_dma_off(cmd, 0); + dma_addr = dvma_addr + dbri_dma_off(cmd, 0); sbus_writel(dma_addr, dbri->regs + REG8); spin_unlock(&dbri->cmdlock); @@ -1077,6 +1081,7 @@ static void recv_fixed(struct snd_dbri *dbri, int pipe, volatile __u32 *ptr) static int setup_descs(struct snd_dbri *dbri, int streamno, unsigned int period) { struct dbri_streaminfo *info = &dbri->stream_info[streamno]; + u32 dvma_addr = (u32)dbri->dma_dvma; __u32 dvma_buffer; int desc; int len; @@ -1177,7 +1182,7 @@ static int setup_descs(struct snd_dbri *dbri, int streamno, unsigned int period) else { dbri->next_desc[last_desc] = desc; dbri->dma->desc[last_desc].nda = - dbri->dma_dvma + dbri_dma_off(desc, desc); + dvma_addr + dbri_dma_off(desc, desc); } last_desc = desc; @@ -1192,7 +1197,7 @@ static int setup_descs(struct snd_dbri *dbri, int streamno, unsigned int period) } dbri->dma->desc[last_desc].nda = - dbri->dma_dvma + dbri_dma_off(desc, first_desc); + dvma_addr + dbri_dma_off(desc, first_desc); dbri->next_desc[last_desc] = first_desc; dbri->pipes[info->pipe].first_desc = first_desc; dbri->pipes[info->pipe].desc = first_desc; @@ -1697,6 +1702,7 @@ interrupts are disabled. static void xmit_descs(struct snd_dbri *dbri) { struct dbri_streaminfo *info; + u32 dvma_addr; s32 *cmd; unsigned long flags; int first_td; @@ -1704,6 +1710,7 @@ static void xmit_descs(struct snd_dbri *dbri) if (dbri == NULL) return; /* Disabled */ + dvma_addr = (u32)dbri->dma_dvma; info = &dbri->stream_info[DBRI_REC]; spin_lock_irqsave(&dbri->lock, flags); @@ -1718,7 +1725,7 @@ static void xmit_descs(struct snd_dbri *dbri) *(cmd++) = DBRI_CMD(D_SDP, 0, dbri->pipes[info->pipe].sdp | D_SDP_P | D_SDP_EVERY | D_SDP_C); - *(cmd++) = dbri->dma_dvma + + *(cmd++) = dvma_addr + dbri_dma_off(desc, first_td); dbri_cmdsend(dbri, cmd, 2); @@ -1740,7 +1747,7 @@ static void xmit_descs(struct snd_dbri *dbri) *(cmd++) = DBRI_CMD(D_SDP, 0, dbri->pipes[info->pipe].sdp | D_SDP_P | D_SDP_EVERY | D_SDP_C); - *(cmd++) = dbri->dma_dvma + + *(cmd++) = dvma_addr + dbri_dma_off(desc, first_td); dbri_cmdsend(dbri, cmd, 2); @@ -2539,7 +2546,7 @@ static int snd_dbri_create(struct snd_card *card, if (!dbri->dma) return -ENOMEM; - dprintk(D_GEN, "DMA Cmd Block 0x%p (0x%08x)\n", + dprintk(D_GEN, "DMA Cmd Block 0x%p (%pad)\n", dbri->dma, dbri->dma_dvma); /* Map the registers into memory. */ diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index b63a31be1218..5e0dea2cdc01 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -99,7 +99,7 @@ int arch_decode_instruction(struct elf *elf, struct section *sec, break; case 0x8d: - if (insn.rex_prefix.bytes && + if (insn.rex_prefix.nbytes && insn.rex_prefix.bytes[0] == 0x48 && insn.modrm.nbytes && insn.modrm.bytes[0] == 0x2c && insn.sib.nbytes && insn.sib.bytes[0] == 0x24) diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild index 582db95127ed..405212be044a 100644 --- a/tools/testing/nvdimm/Kbuild +++ b/tools/testing/nvdimm/Kbuild @@ -14,6 +14,7 @@ ldflags-y += --wrap=devm_memremap_pages ldflags-y += --wrap=insert_resource ldflags-y += --wrap=remove_resource ldflags-y += --wrap=acpi_evaluate_object +ldflags-y += --wrap=acpi_evaluate_dsm DRIVERS := ../../../drivers NVDIMM_SRC := $(DRIVERS)/nvdimm diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c index 3ccef732fce9..64cae1a5deff 100644 --- a/tools/testing/nvdimm/test/iomap.c +++ b/tools/testing/nvdimm/test/iomap.c @@ -26,14 +26,17 @@ static LIST_HEAD(iomap_head); static struct iomap_ops { nfit_test_lookup_fn nfit_test_lookup; + nfit_test_evaluate_dsm_fn evaluate_dsm; struct list_head list; } iomap_ops = { .list = LIST_HEAD_INIT(iomap_ops.list), }; -void nfit_test_setup(nfit_test_lookup_fn lookup) +void nfit_test_setup(nfit_test_lookup_fn lookup, + nfit_test_evaluate_dsm_fn evaluate) { iomap_ops.nfit_test_lookup = lookup; + iomap_ops.evaluate_dsm = evaluate; list_add_rcu(&iomap_ops.list, &iomap_head); } EXPORT_SYMBOL(nfit_test_setup); @@ -367,4 +370,22 @@ acpi_status __wrap_acpi_evaluate_object(acpi_handle handle, acpi_string path, } EXPORT_SYMBOL(__wrap_acpi_evaluate_object); +union acpi_object * __wrap_acpi_evaluate_dsm(acpi_handle handle, const u8 *uuid, + u64 rev, u64 func, union acpi_object *argv4) +{ + union acpi_object *obj = ERR_PTR(-ENXIO); + struct iomap_ops *ops; + + rcu_read_lock(); + ops = list_first_or_null_rcu(&iomap_head, typeof(*ops), list); + if (ops) + obj = ops->evaluate_dsm(handle, uuid, rev, func, argv4); + rcu_read_unlock(); + + if (IS_ERR(obj)) + return acpi_evaluate_dsm(handle, uuid, rev, func, argv4); + return obj; +} +EXPORT_SYMBOL(__wrap_acpi_evaluate_dsm); + MODULE_LICENSE("GPL v2"); diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index c9a6458cb63e..71620fa95953 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -23,6 +23,7 @@ #include <linux/sizes.h> #include <linux/list.h> #include <linux/slab.h> +#include <nd-core.h> #include <nfit.h> #include <nd.h> #include "nfit_test.h" @@ -1506,6 +1507,225 @@ static int nfit_test_blk_do_io(struct nd_blk_region *ndbr, resource_size_t dpa, return 0; } +static unsigned long nfit_ctl_handle; + +union acpi_object *result; + +static union acpi_object *nfit_test_evaluate_dsm(acpi_handle handle, + const u8 *uuid, u64 rev, u64 func, union acpi_object *argv4) +{ + if (handle != &nfit_ctl_handle) + return ERR_PTR(-ENXIO); + + return result; +} + +static int setup_result(void *buf, size_t size) +{ + result = kmalloc(sizeof(union acpi_object) + size, GFP_KERNEL); + if (!result) + return -ENOMEM; + result->package.type = ACPI_TYPE_BUFFER, + result->buffer.pointer = (void *) (result + 1); + result->buffer.length = size; + memcpy(result->buffer.pointer, buf, size); + memset(buf, 0, size); + return 0; +} + +static int nfit_ctl_test(struct device *dev) +{ + int rc, cmd_rc; + struct nvdimm *nvdimm; + struct acpi_device *adev; + struct nfit_mem *nfit_mem; + struct nd_ars_record *record; + struct acpi_nfit_desc *acpi_desc; + const u64 test_val = 0x0123456789abcdefULL; + unsigned long mask, cmd_size, offset; + union { + struct nd_cmd_get_config_size cfg_size; + struct nd_cmd_ars_status ars_stat; + struct nd_cmd_ars_cap ars_cap; + char buf[sizeof(struct nd_cmd_ars_status) + + sizeof(struct nd_ars_record)]; + } cmds; + + adev = devm_kzalloc(dev, sizeof(*adev), GFP_KERNEL); + if (!adev) + return -ENOMEM; + *adev = (struct acpi_device) { + .handle = &nfit_ctl_handle, + .dev = { + .init_name = "test-adev", + }, + }; + + acpi_desc = devm_kzalloc(dev, sizeof(*acpi_desc), GFP_KERNEL); + if (!acpi_desc) + return -ENOMEM; + *acpi_desc = (struct acpi_nfit_desc) { + .nd_desc = { + .cmd_mask = 1UL << ND_CMD_ARS_CAP + | 1UL << ND_CMD_ARS_START + | 1UL << ND_CMD_ARS_STATUS + | 1UL << ND_CMD_CLEAR_ERROR, + .module = THIS_MODULE, + .provider_name = "ACPI.NFIT", + .ndctl = acpi_nfit_ctl, + }, + .dev = &adev->dev, + }; + + nfit_mem = devm_kzalloc(dev, sizeof(*nfit_mem), GFP_KERNEL); + if (!nfit_mem) + return -ENOMEM; + + mask = 1UL << ND_CMD_SMART | 1UL << ND_CMD_SMART_THRESHOLD + | 1UL << ND_CMD_DIMM_FLAGS | 1UL << ND_CMD_GET_CONFIG_SIZE + | 1UL << ND_CMD_GET_CONFIG_DATA | 1UL << ND_CMD_SET_CONFIG_DATA + | 1UL << ND_CMD_VENDOR; + *nfit_mem = (struct nfit_mem) { + .adev = adev, + .family = NVDIMM_FAMILY_INTEL, + .dsm_mask = mask, + }; + + nvdimm = devm_kzalloc(dev, sizeof(*nvdimm), GFP_KERNEL); + if (!nvdimm) + return -ENOMEM; + *nvdimm = (struct nvdimm) { + .provider_data = nfit_mem, + .cmd_mask = mask, + .dev = { + .init_name = "test-dimm", + }, + }; + + + /* basic checkout of a typical 'get config size' command */ + cmd_size = sizeof(cmds.cfg_size); + cmds.cfg_size = (struct nd_cmd_get_config_size) { + .status = 0, + .config_size = SZ_128K, + .max_xfer = SZ_4K, + }; + rc = setup_result(cmds.buf, cmd_size); + if (rc) + return rc; + rc = acpi_nfit_ctl(&acpi_desc->nd_desc, nvdimm, ND_CMD_GET_CONFIG_SIZE, + cmds.buf, cmd_size, &cmd_rc); + + if (rc < 0 || cmd_rc || cmds.cfg_size.status != 0 + || cmds.cfg_size.config_size != SZ_128K + || cmds.cfg_size.max_xfer != SZ_4K) { + dev_dbg(dev, "%s: failed at: %d rc: %d cmd_rc: %d\n", + __func__, __LINE__, rc, cmd_rc); + return -EIO; + } + + + /* test ars_status with zero output */ + cmd_size = offsetof(struct nd_cmd_ars_status, address); + cmds.ars_stat = (struct nd_cmd_ars_status) { + .out_length = 0, + }; + rc = setup_result(cmds.buf, cmd_size); + if (rc) + return rc; + rc = acpi_nfit_ctl(&acpi_desc->nd_desc, NULL, ND_CMD_ARS_STATUS, + cmds.buf, cmd_size, &cmd_rc); + + if (rc < 0 || cmd_rc) { + dev_dbg(dev, "%s: failed at: %d rc: %d cmd_rc: %d\n", + __func__, __LINE__, rc, cmd_rc); + return -EIO; + } + + + /* test ars_cap with benign extended status */ + cmd_size = sizeof(cmds.ars_cap); + cmds.ars_cap = (struct nd_cmd_ars_cap) { + .status = ND_ARS_PERSISTENT << 16, + }; + offset = offsetof(struct nd_cmd_ars_cap, status); + rc = setup_result(cmds.buf + offset, cmd_size - offset); + if (rc) + return rc; + rc = acpi_nfit_ctl(&acpi_desc->nd_desc, NULL, ND_CMD_ARS_CAP, + cmds.buf, cmd_size, &cmd_rc); + + if (rc < 0 || cmd_rc) { + dev_dbg(dev, "%s: failed at: %d rc: %d cmd_rc: %d\n", + __func__, __LINE__, rc, cmd_rc); + return -EIO; + } + + + /* test ars_status with 'status' trimmed from 'out_length' */ + cmd_size = sizeof(cmds.ars_stat) + sizeof(struct nd_ars_record); + cmds.ars_stat = (struct nd_cmd_ars_status) { + .out_length = cmd_size - 4, + }; + record = &cmds.ars_stat.records[0]; + *record = (struct nd_ars_record) { + .length = test_val, + }; + rc = setup_result(cmds.buf, cmd_size); + if (rc) + return rc; + rc = acpi_nfit_ctl(&acpi_desc->nd_desc, NULL, ND_CMD_ARS_STATUS, + cmds.buf, cmd_size, &cmd_rc); + + if (rc < 0 || cmd_rc || record->length != test_val) { + dev_dbg(dev, "%s: failed at: %d rc: %d cmd_rc: %d\n", + __func__, __LINE__, rc, cmd_rc); + return -EIO; + } + + + /* test ars_status with 'Output (Size)' including 'status' */ + cmd_size = sizeof(cmds.ars_stat) + sizeof(struct nd_ars_record); + cmds.ars_stat = (struct nd_cmd_ars_status) { + .out_length = cmd_size, + }; + record = &cmds.ars_stat.records[0]; + *record = (struct nd_ars_record) { + .length = test_val, + }; + rc = setup_result(cmds.buf, cmd_size); + if (rc) + return rc; + rc = acpi_nfit_ctl(&acpi_desc->nd_desc, NULL, ND_CMD_ARS_STATUS, + cmds.buf, cmd_size, &cmd_rc); + + if (rc < 0 || cmd_rc || record->length != test_val) { + dev_dbg(dev, "%s: failed at: %d rc: %d cmd_rc: %d\n", + __func__, __LINE__, rc, cmd_rc); + return -EIO; + } + + + /* test extended status for get_config_size results in failure */ + cmd_size = sizeof(cmds.cfg_size); + cmds.cfg_size = (struct nd_cmd_get_config_size) { + .status = 1 << 16, + }; + rc = setup_result(cmds.buf, cmd_size); + if (rc) + return rc; + rc = acpi_nfit_ctl(&acpi_desc->nd_desc, nvdimm, ND_CMD_GET_CONFIG_SIZE, + cmds.buf, cmd_size, &cmd_rc); + + if (rc < 0 || cmd_rc >= 0) { + dev_dbg(dev, "%s: failed at: %d rc: %d cmd_rc: %d\n", + __func__, __LINE__, rc, cmd_rc); + return -EIO; + } + + return 0; +} + static int nfit_test_probe(struct platform_device *pdev) { struct nvdimm_bus_descriptor *nd_desc; @@ -1516,6 +1736,12 @@ static int nfit_test_probe(struct platform_device *pdev) union acpi_object *obj; int rc; + if (strcmp(dev_name(&pdev->dev), "nfit_test.0") == 0) { + rc = nfit_ctl_test(&pdev->dev); + if (rc) + return rc; + } + nfit_test = to_nfit_test(&pdev->dev); /* common alloc */ @@ -1639,11 +1865,13 @@ static __init int nfit_test_init(void) { int rc, i; - nfit_test_dimm = class_create(THIS_MODULE, "nfit_test_dimm"); - if (IS_ERR(nfit_test_dimm)) - return PTR_ERR(nfit_test_dimm); + nfit_test_setup(nfit_test_lookup, nfit_test_evaluate_dsm); - nfit_test_setup(nfit_test_lookup); + nfit_test_dimm = class_create(THIS_MODULE, "nfit_test_dimm"); + if (IS_ERR(nfit_test_dimm)) { + rc = PTR_ERR(nfit_test_dimm); + goto err_register; + } for (i = 0; i < NUM_NFITS; i++) { struct nfit_test *nfit_test; diff --git a/tools/testing/nvdimm/test/nfit_test.h b/tools/testing/nvdimm/test/nfit_test.h index c281dd2e5e2d..f54c0032c6ff 100644 --- a/tools/testing/nvdimm/test/nfit_test.h +++ b/tools/testing/nvdimm/test/nfit_test.h @@ -31,11 +31,17 @@ struct nfit_test_resource { void *buf; }; +union acpi_object; +typedef void *acpi_handle; + typedef struct nfit_test_resource *(*nfit_test_lookup_fn)(resource_size_t); +typedef union acpi_object *(*nfit_test_evaluate_dsm_fn)(acpi_handle handle, + const u8 *uuid, u64 rev, u64 func, union acpi_object *argv4); void __iomem *__wrap_ioremap_nocache(resource_size_t offset, unsigned long size); void __wrap_iounmap(volatile void __iomem *addr); -void nfit_test_setup(nfit_test_lookup_fn lookup); +void nfit_test_setup(nfit_test_lookup_fn lookup, + nfit_test_evaluate_dsm_fn evaluate); void nfit_test_teardown(void); struct nfit_test_resource *get_nfit_res(resource_size_t resource); #endif diff --git a/virt/kvm/arm/vgic/vgic-v2.c b/virt/kvm/arm/vgic/vgic-v2.c index 0a063af40565..9bab86757fa4 100644 --- a/virt/kvm/arm/vgic/vgic-v2.c +++ b/virt/kvm/arm/vgic/vgic-v2.c @@ -50,8 +50,10 @@ void vgic_v2_process_maintenance(struct kvm_vcpu *vcpu) WARN_ON(cpuif->vgic_lr[lr] & GICH_LR_STATE); - kvm_notify_acked_irq(vcpu->kvm, 0, - intid - VGIC_NR_PRIVATE_IRQS); + /* Only SPIs require notification */ + if (vgic_valid_spi(vcpu->kvm, intid)) + kvm_notify_acked_irq(vcpu->kvm, 0, + intid - VGIC_NR_PRIVATE_IRQS); } } diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index 9f0dae397d9c..5c9f9745e6ca 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -41,8 +41,10 @@ void vgic_v3_process_maintenance(struct kvm_vcpu *vcpu) WARN_ON(cpuif->vgic_lr[lr] & ICH_LR_STATE); - kvm_notify_acked_irq(vcpu->kvm, 0, - intid - VGIC_NR_PRIVATE_IRQS); + /* Only SPIs require notification */ + if (vgic_valid_spi(vcpu->kvm, intid)) + kvm_notify_acked_irq(vcpu->kvm, 0, + intid - VGIC_NR_PRIVATE_IRQS); } /* diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 5c360347a1e9..7f9ee2929cfe 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2889,10 +2889,10 @@ static int kvm_ioctl_create_device(struct kvm *kvm, ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR | O_CLOEXEC); if (ret < 0) { - ops->destroy(dev); mutex_lock(&kvm->lock); list_del(&dev->vm_node); mutex_unlock(&kvm->lock); + ops->destroy(dev); return ret; } |