diff options
824 files changed, 21289 insertions, 9785 deletions
@@ -534,6 +534,7 @@ N: NeilBrown E: neil@brown.name P: 4096R/566281B9 1BC6 29EB D390 D870 7B5F 497A 39EC 9EDD 5662 81B9 D: NFSD Maintainer 2000-2007 +D: MD Maintainer 2001-2016 N: Zach Brown E: zab@zabbo.net diff --git a/Documentation/ABI/testing/sysfs-kernel-livepatch b/Documentation/ABI/testing/sysfs-kernel-livepatch index 5bf42a840b22..da87f43aec58 100644 --- a/Documentation/ABI/testing/sysfs-kernel-livepatch +++ b/Documentation/ABI/testing/sysfs-kernel-livepatch @@ -33,7 +33,7 @@ Description: The object directory contains subdirectories for each function that is patched within the object. -What: /sys/kernel/livepatch/<patch>/<object>/<function> +What: /sys/kernel/livepatch/<patch>/<object>/<function,sympos> Date: Nov 2014 KernelVersion: 3.19.0 Contact: live-patching@vger.kernel.org @@ -41,4 +41,8 @@ Description: The function directory contains attributes regarding the properties and state of the patched function. + The directory name contains the patched function name and a + sympos number corresponding to the nth occurrence of the symbol + name in kallsyms for the patched object. + There are currently no such attributes. diff --git a/Documentation/ABI/testing/sysfs-ptp b/Documentation/ABI/testing/sysfs-ptp index 44806a678f12..a17f817a9309 100644 --- a/Documentation/ABI/testing/sysfs-ptp +++ b/Documentation/ABI/testing/sysfs-ptp @@ -74,7 +74,7 @@ Description: assignment may be changed by two writing numbers into the file. -What: /sys/class/ptp/ptpN/pps_avaiable +What: /sys/class/ptp/ptpN/pps_available Date: September 2010 Contact: Richard Cochran <richardcochran@gmail.com> Description: diff --git a/Documentation/devicetree/bindings/arm/arm,scpi.txt b/Documentation/devicetree/bindings/arm/arm,scpi.txt index 86302de67c2c..313dabdc14f9 100644 --- a/Documentation/devicetree/bindings/arm/arm,scpi.txt +++ b/Documentation/devicetree/bindings/arm/arm,scpi.txt @@ -63,7 +63,7 @@ Required properties: - compatible : should be "arm,juno-sram-ns" for Non-secure SRAM on Juno The rest of the properties should follow the generic mmio-sram description -found in ../../misc/sysram.txt +found in ../../sram/sram.txt Each sub-node represents the reserved area for SCPI. diff --git a/Documentation/devicetree/bindings/arm/cpus.txt b/Documentation/devicetree/bindings/arm/cpus.txt index 6aca64f289b6..c352c11bd641 100644 --- a/Documentation/devicetree/bindings/arm/cpus.txt +++ b/Documentation/devicetree/bindings/arm/cpus.txt @@ -157,6 +157,7 @@ nodes to be present and contain the properties described below. "arm,cortex-a17" "arm,cortex-a53" "arm,cortex-a57" + "arm,cortex-a72" "arm,cortex-m0" "arm,cortex-m0+" "arm,cortex-m1" diff --git a/Documentation/devicetree/bindings/arm/psci.txt b/Documentation/devicetree/bindings/arm/psci.txt index a9adab84e2fe..a2c4f1d52492 100644 --- a/Documentation/devicetree/bindings/arm/psci.txt +++ b/Documentation/devicetree/bindings/arm/psci.txt @@ -23,17 +23,20 @@ Main node required properties: - compatible : should contain at least one of: - * "arm,psci" : for implementations complying to PSCI versions prior to - 0.2. For these cases function IDs must be provided. - - * "arm,psci-0.2" : for implementations complying to PSCI 0.2. Function - IDs are not required and should be ignored by an OS with PSCI 0.2 - support, but are permitted to be present for compatibility with - existing software when "arm,psci" is later in the compatible list. - - * "arm,psci-1.0" : for implementations complying to PSCI 1.0. PSCI 1.0 is - backward compatible with PSCI 0.2 with minor specification updates, - as defined in the PSCI specification[2]. + * "arm,psci" : For implementations complying to PSCI versions prior + to 0.2. + For these cases function IDs must be provided. + + * "arm,psci-0.2" : For implementations complying to PSCI 0.2. + Function IDs are not required and should be ignored by + an OS with PSCI 0.2 support, but are permitted to be + present for compatibility with existing software when + "arm,psci" is later in the compatible list. + + * "arm,psci-1.0" : For implementations complying to PSCI 1.0. + PSCI 1.0 is backward compatible with PSCI 0.2 with + minor specification updates, as defined in the PSCI + specification[2]. - method : The method of calling the PSCI firmware. Permitted values are: diff --git a/Documentation/devicetree/bindings/arm/secure.txt b/Documentation/devicetree/bindings/arm/secure.txt new file mode 100644 index 000000000000..e31303fb233a --- /dev/null +++ b/Documentation/devicetree/bindings/arm/secure.txt @@ -0,0 +1,53 @@ +* ARM Secure world bindings + +ARM CPUs with TrustZone support have two distinct address spaces, +"Normal" and "Secure". Most devicetree consumers (including the Linux +kernel) are not TrustZone aware and run entirely in either the Normal +world or the Secure world. However some devicetree consumers are +TrustZone aware and need to be able to determine whether devices are +visible only in the Secure address space, only in the Normal address +space, or visible in both. (One example of that situation would be a +virtual machine which boots Secure firmware and wants to tell the +firmware about the layout of the machine via devicetree.) + +The general principle of the naming scheme for Secure world bindings +is that any property that needs a different value in the Secure world +can be supported by prefixing the property name with "secure-". So for +instance "secure-foo" would override "foo". For property names with +a vendor prefix, the Secure variant of "vendor,foo" would be +"vendor,secure-foo". If there is no "secure-" property then the Secure +world value is the same as specified for the Normal world by the +non-prefixed property. However, only the properties listed below may +validly have "secure-" versions; this list will be enlarged on a +case-by-case basis. + +Defining the bindings in this way means that a device tree which has +been annotated to indicate the presence of Secure-only devices can +still be processed unmodified by existing Non-secure software (and in +particular by the kernel). + +Note that it is still valid for bindings intended for purely Secure +world consumers (like kernels that run entirely in Secure) to simply +describe the view of Secure world using the standard bindings. These +secure- bindings only need to be used where both the Secure and Normal +world views need to be described in a single device tree. + +Valid Secure world properties: + +- secure-status : specifies whether the device is present and usable + in the secure world. The combination of this with "status" allows + the various possible combinations of device visibility to be + specified. If "secure-status" is not specified it defaults to the + same value as "status"; if "status" is not specified either then + both default to "okay". This means the following combinations are + possible: + + /* Neither specified: default to visible in both S and NS */ + secure-status = "okay"; /* visible in both */ + status = "okay"; /* visible in both */ + status = "okay"; secure-status = "okay"; /* visible in both */ + secure-status = "disabled"; /* NS-only */ + status = "okay"; secure-status = "disabled"; /* NS-only */ + status = "disabled"; secure-status = "okay"; /* S-only */ + status = "disabled"; /* disabled in both */ + status = "disabled"; secure-status = "disabled"; /* disabled in both */ diff --git a/Documentation/devicetree/bindings/clock/samsung,s2mps11.txt b/Documentation/devicetree/bindings/clock/samsung,s2mps11.txt new file mode 100644 index 000000000000..2726c1d58a79 --- /dev/null +++ b/Documentation/devicetree/bindings/clock/samsung,s2mps11.txt @@ -0,0 +1,49 @@ +Binding for Samsung S2M and S5M family clock generator block +============================================================ + +This is a part of device tree bindings for S2M and S5M family multi-function +devices. +More information can be found in bindings/mfd/sec-core.txt file. + +The S2MPS11/13/15 and S5M8767 provide three(AP/CP/BT) buffered 32.768 kHz +outputs. The S2MPS14 provides two (AP/BT) buffered 32.768 KHz outputs. + +To register these as clocks with common clock framework instantiate under +main device node a sub-node named "clocks". + +It uses the common clock binding documented in: + - Documentation/devicetree/bindings/clock/clock-bindings.txt + + +Required properties of the "clocks" sub-node: + - #clock-cells: should be 1. + - compatible: Should be one of: "samsung,s2mps11-clk", "samsung,s2mps13-clk", + "samsung,s2mps14-clk", "samsung,s5m8767-clk" + The S2MPS15 uses the same compatible as S2MPS13, as both provides similar + clocks. + + +Each clock is assigned an identifier and client nodes use this identifier +to specify the clock which they consume. + Clock ID Devices + ---------------------------------------------------------- + 32KhzAP 0 S2MPS11/13/14/15, S5M8767 + 32KhzCP 1 S2MPS11/13/15, S5M8767 + 32KhzBT 2 S2MPS11/13/14/15, S5M8767 + +Include dt-bindings/clock/samsung,s2mps11.h file to use preprocessor defines +in device tree sources. + + +Example: + + s2mps11_pmic@66 { + compatible = "samsung,s2mps11-pmic"; + reg = <0x66>; + + s2m_osc: clocks { + compatible = "samsung,s2mps11-clk"; + #clock-cells = <1>; + clock-output-names = "xx", "yy", "zz"; + }; + }; diff --git a/Documentation/devicetree/bindings/cpufreq/arm_big_little_dt.txt b/Documentation/devicetree/bindings/cpufreq/arm_big_little_dt.txt index 0715695e94a9..2aa06ac0fac5 100644 --- a/Documentation/devicetree/bindings/cpufreq/arm_big_little_dt.txt +++ b/Documentation/devicetree/bindings/cpufreq/arm_big_little_dt.txt @@ -12,7 +12,7 @@ must be present contiguously. Generic DT driver will check only node 'x' for cpu:x. Required properties: -- operating-points: Refer to Documentation/devicetree/bindings/power/opp.txt +- operating-points: Refer to Documentation/devicetree/bindings/opp/opp.txt for details Optional properties: diff --git a/Documentation/devicetree/bindings/cpufreq/cpufreq-dt.txt b/Documentation/devicetree/bindings/cpufreq/cpufreq-dt.txt index e41c98ffbccb..dd3929e85dec 100644 --- a/Documentation/devicetree/bindings/cpufreq/cpufreq-dt.txt +++ b/Documentation/devicetree/bindings/cpufreq/cpufreq-dt.txt @@ -11,7 +11,7 @@ Required properties: - None Optional properties: -- operating-points: Refer to Documentation/devicetree/bindings/power/opp.txt for +- operating-points: Refer to Documentation/devicetree/bindings/opp/opp.txt for details. OPPs *must* be supplied either via DT, i.e. this property, or populated at runtime. - clock-latency: Specify the possible maximum transition latency for clock, diff --git a/Documentation/devicetree/bindings/display/bridge/tda998x.txt b/Documentation/devicetree/bindings/display/bridge/tda998x.txt index e9e4bce40760..e178e6b9f9ee 100644 --- a/Documentation/devicetree/bindings/display/bridge/tda998x.txt +++ b/Documentation/devicetree/bindings/display/bridge/tda998x.txt @@ -5,6 +5,10 @@ Required properties; - reg: I2C address +Required node: + - port: Input port node with endpoint definition, as described + in Documentation/devicetree/bindings/graph.txt + Optional properties: - interrupts: interrupt number and trigger type default: polling diff --git a/Documentation/devicetree/bindings/eeprom/eeprom.txt b/Documentation/devicetree/bindings/eeprom/eeprom.txt index 4342c10de1bf..735bc94444bb 100644 --- a/Documentation/devicetree/bindings/eeprom/eeprom.txt +++ b/Documentation/devicetree/bindings/eeprom/eeprom.txt @@ -2,11 +2,22 @@ EEPROMs (I2C) Required properties: - - compatible : should be "<manufacturer>,<type>" - If there is no specific driver for <manufacturer>, a generic - driver based on <type> is selected. Possible types are: - 24c00, 24c01, 24c02, 24c04, 24c08, 24c16, 24c32, 24c64, - 24c128, 24c256, 24c512, 24c1024, spd + - compatible : should be "<manufacturer>,<type>", like these: + + "atmel,24c00", "atmel,24c01", "atmel,24c02", "atmel,24c04", + "atmel,24c08", "atmel,24c16", "atmel,24c32", "atmel,24c64", + "atmel,24c128", "atmel,24c256", "atmel,24c512", "atmel,24c1024" + + "catalyst,24c32" + + "ramtron,24c64" + + "renesas,r1ex24002" + + If there is no specific driver for <manufacturer>, a generic + driver based on <type> is selected. Possible types are: + "24c00", "24c01", "24c02", "24c04", "24c08", "24c16", "24c32", "24c64", + "24c128", "24c256", "24c512", "24c1024", "spd" - reg : the I2C address of the EEPROM diff --git a/Documentation/devicetree/bindings/gpio/snps-dwapb-gpio.txt b/Documentation/devicetree/bindings/gpio/snps-dwapb-gpio.txt index dd5d2c0394b1..4d6c8cdc8586 100644 --- a/Documentation/devicetree/bindings/gpio/snps-dwapb-gpio.txt +++ b/Documentation/devicetree/bindings/gpio/snps-dwapb-gpio.txt @@ -24,7 +24,7 @@ controller. - #interrupt-cells : Specifies the number of cells needed to encode an interrupt. Shall be set to 2. The first cell defines the interrupt number, the second encodes the triger flags encoded as described in - Documentation/devicetree/bindings/interrupts.txt + Documentation/devicetree/bindings/interrupt-controller/interrupts.txt - interrupt-parent : The parent interrupt controller. - interrupts : The interrupt to the parent controller raised when GPIOs generate the interrupts. diff --git a/Documentation/devicetree/bindings/i2c/i2c-at91.txt b/Documentation/devicetree/bindings/i2c/i2c-at91.txt index 6e81dc153f3b..ef973a0343c7 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-at91.txt +++ b/Documentation/devicetree/bindings/i2c/i2c-at91.txt @@ -3,7 +3,7 @@ I2C for Atmel platforms Required properties : - compatible : Must be "atmel,at91rm9200-i2c", "atmel,at91sam9261-i2c", "atmel,at91sam9260-i2c", "atmel,at91sam9g20-i2c", "atmel,at91sam9g10-i2c", - "atmel,at91sam9x5-i2c" or "atmel,sama5d2-i2c" + "atmel,at91sam9x5-i2c", "atmel,sama5d4-i2c" or "atmel,sama5d2-i2c" - reg: physical base address of the controller and length of memory mapped region. - interrupts: interrupt number to the cpu. @@ -17,6 +17,8 @@ Optional properties: - dma-names: should contain "tx" and "rx". - atmel,fifo-size: maximum number of data the RX and TX FIFOs can store for FIFO capable I2C controllers. +- i2c-sda-hold-time-ns: TWD hold time, only available for "atmel,sama5d4-i2c" + and "atmel,sama5d2-i2c". - Child nodes conforming to i2c bus binding Examples : @@ -52,6 +54,7 @@ i2c0: i2c@f8034600 { #size-cells = <0>; clocks = <&flx0>; atmel,fifo-size = <16>; + i2c-sda-hold-time-ns = <336>; wm8731: wm8731@1a { compatible = "wm8731"; diff --git a/Documentation/devicetree/bindings/i2c/i2c-brcmstb.txt b/Documentation/devicetree/bindings/i2c/i2c-brcmstb.txt index d6f724efdcf2..aeceaceba3c5 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-brcmstb.txt +++ b/Documentation/devicetree/bindings/i2c/i2c-brcmstb.txt @@ -2,7 +2,7 @@ Broadcom stb bsc iic master controller Required properties: -- compatible: should be "brcm,brcmstb-i2c" +- compatible: should be "brcm,brcmstb-i2c" or "brcm,brcmper-i2c" - clock-frequency: 32-bit decimal value of iic master clock freqency in Hz valid values are 375000, 390000, 187500, 200000 93750, 97500, 46875 and 50000 diff --git a/Documentation/devicetree/bindings/i2c/i2c-rcar.txt b/Documentation/devicetree/bindings/i2c/i2c-rcar.txt index ea406eb20fa5..95e97223a71c 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-rcar.txt +++ b/Documentation/devicetree/bindings/i2c/i2c-rcar.txt @@ -20,6 +20,10 @@ Optional properties: propoerty indicates the default frequency 100 kHz. - clocks: clock specifier. +- i2c-scl-falling-time-ns: see i2c.txt +- i2c-scl-internal-delay-ns: see i2c.txt +- i2c-scl-rising-time-ns: see i2c.txt + Examples : i2c0: i2c@e6508000 { diff --git a/Documentation/devicetree/bindings/i2c/i2c.txt b/Documentation/devicetree/bindings/i2c/i2c.txt index 8a99150ac3a7..c8d977ed847f 100644 --- a/Documentation/devicetree/bindings/i2c/i2c.txt +++ b/Documentation/devicetree/bindings/i2c/i2c.txt @@ -29,12 +29,38 @@ Optional properties These properties may not be supported by all drivers. However, if a driver wants to support one of the below features, it should adapt the bindings below. -- clock-frequency - frequency of bus clock in Hz. -- wakeup-source - device can be used as a wakeup source. +- clock-frequency + frequency of bus clock in Hz. -- interrupts - interrupts used by the device. -- interrupt-names - "irq" and "wakeup" names are recognized by I2C core, - other names are left to individual drivers. +- i2c-scl-falling-time-ns + Number of nanoseconds the SCL signal takes to fall; t(f) in the I2C + specification. + +- i2c-scl-internal-delay-ns + Number of nanoseconds the IP core additionally needs to setup SCL. + +- i2c-scl-rising-time-ns + Number of nanoseconds the SCL signal takes to rise; t(r) in the I2C + specification. + +- i2c-sda-falling-time-ns + Number of nanoseconds the SDA signal takes to fall; t(f) in the I2C + specification. + +- interrupts + interrupts used by the device. + +- interrupt-names + "irq" and "wakeup" names are recognized by I2C core, other names are + left to individual drivers. + +- multi-master + states that there is another master active on this bus. The OS can use + this information to adapt power management to keep the arbitration awake + all the time, for example. + +- wakeup-source + device can be used as a wakeup source. Binding may contain optional "interrupts" property, describing interrupts used by the device. I2C core will assign "irq" interrupt (or the very first diff --git a/Documentation/devicetree/bindings/i2c/trivial-devices.txt b/Documentation/devicetree/bindings/i2c/trivial-devices.txt index f6fec952d683..539874490492 100644 --- a/Documentation/devicetree/bindings/i2c/trivial-devices.txt +++ b/Documentation/devicetree/bindings/i2c/trivial-devices.txt @@ -22,21 +22,9 @@ adi,adxl345 Three-Axis Digital Accelerometer adi,adxl346 Three-Axis Digital Accelerometer (backward-compatibility value "adi,adxl345" must be listed too) ams,iaq-core AMS iAQ-Core VOC Sensor at,24c08 i2c serial eeprom (24cxx) -atmel,24c00 i2c serial eeprom (24cxx) -atmel,24c01 i2c serial eeprom (24cxx) -atmel,24c02 i2c serial eeprom (24cxx) -atmel,24c04 i2c serial eeprom (24cxx) -atmel,24c16 i2c serial eeprom (24cxx) -atmel,24c32 i2c serial eeprom (24cxx) -atmel,24c64 i2c serial eeprom (24cxx) -atmel,24c128 i2c serial eeprom (24cxx) -atmel,24c256 i2c serial eeprom (24cxx) -atmel,24c512 i2c serial eeprom (24cxx) -atmel,24c1024 i2c serial eeprom (24cxx) atmel,at97sc3204t i2c trusted platform module (TPM) capella,cm32181 CM32181: Ambient Light Sensor capella,cm3232 CM3232: Ambient Light Sensor -catalyst,24c32 i2c serial eeprom cirrus,cs42l51 Cirrus Logic CS42L51 audio codec dallas,ds1307 64 x 8, Serial, I2C Real-Time Clock dallas,ds1338 I2C RTC with 56-Byte NV RAM @@ -50,11 +38,13 @@ dallas,ds4510 CPU Supervisor with Nonvolatile Memory and Programmable I/O dallas,ds75 Digital Thermometer and Thermostat dlg,da9053 DA9053: flexible system level PMIC with multicore support dlg,da9063 DA9063: system PMIC for quad-core application processors +epson,rx8010 I2C-BUS INTERFACE REAL TIME CLOCK MODULE epson,rx8025 High-Stability. I2C-Bus INTERFACE REAL TIME CLOCK MODULE epson,rx8581 I2C-BUS INTERFACE REAL TIME CLOCK MODULE fsl,mag3110 MAG3110: Xtrinsic High Accuracy, 3D Magnetometer fsl,mc13892 MC13892: Power Management Integrated Circuit (PMIC) for i.MX35/51 fsl,mma8450 MMA8450Q: Xtrinsic Low-power, 3-axis Xtrinsic Accelerometer +fsl,mpl3115 MPL3115: Absolute Digital Pressure Sensor fsl,mpr121 MPR121: Proximity Capacitive Touch Sensor Controller fsl,sgtl5000 SGTL5000: Ultra Low-Power Audio Codec gmt,g751 G751: Digital Temperature Sensor and Thermal Watchdog with Two-Wire Interface @@ -81,7 +71,6 @@ ovti,ov5642 OV5642: Color CMOS QSXGA (5-megapixel) Image Sensor with OmniBSI an pericom,pt7c4338 Real-time Clock Module plx,pex8648 48-Lane, 12-Port PCI Express Gen 2 (5.0 GT/s) Switch pulsedlight,lidar-lite-v2 Pulsedlight LIDAR range-finding sensor -ramtron,24c64 i2c serial eeprom (24cxx) ricoh,r2025sd I2C bus SERIAL INTERFACE REAL-TIME CLOCK IC ricoh,r2221tl I2C bus SERIAL INTERFACE REAL-TIME CLOCK IC ricoh,rs5c372a I2C bus SERIAL INTERFACE REAL-TIME CLOCK IC diff --git a/Documentation/devicetree/bindings/interrupt-controller/qca,ath79-misc-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/qca,ath79-misc-intc.txt index ec96b1f01478..475ae9bd562b 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/qca,ath79-misc-intc.txt +++ b/Documentation/devicetree/bindings/interrupt-controller/qca,ath79-misc-intc.txt @@ -22,7 +22,7 @@ Interrupt Controllers bindings used by client devices. Example: interrupt-controller@18060010 { - compatible = "qca,ar9132-misc-intc", qca,ar7100-misc-intc"; + compatible = "qca,ar9132-misc-intc", "qca,ar7100-misc-intc"; reg = <0x18060010 0x4>; interrupt-parent = <&cpuintc>; diff --git a/Documentation/devicetree/bindings/media/i2c/adp1653.txt b/Documentation/devicetree/bindings/media/i2c/adp1653.txt index 5ce66f2104e3..4cce0de40ee9 100644 --- a/Documentation/devicetree/bindings/media/i2c/adp1653.txt +++ b/Documentation/devicetree/bindings/media/i2c/adp1653.txt @@ -12,12 +12,13 @@ There are two LED outputs available - flash and indicator. One LED is represented by one child node, nodes need to be named "flash" and "indicator". Required properties of the LED child node: -- max-microamp : see Documentation/devicetree/bindings/leds/common.txt +- led-max-microamp : see Documentation/devicetree/bindings/leds/common.txt Required properties of the flash LED child node: - flash-max-microamp : see Documentation/devicetree/bindings/leds/common.txt - flash-timeout-us : see Documentation/devicetree/bindings/leds/common.txt +- led-max-microamp : see Documentation/devicetree/bindings/leds/common.txt Example: @@ -29,9 +30,9 @@ Example: flash { flash-timeout-us = <500000>; flash-max-microamp = <320000>; - max-microamp = <50000>; + led-max-microamp = <50000>; }; indicator { - max-microamp = <17500>; + led-max-microamp = <17500>; }; }; diff --git a/Documentation/devicetree/bindings/memory-controllers/ath79-ddr-controller.txt b/Documentation/devicetree/bindings/memory-controllers/ath79-ddr-controller.txt index efe35a065714..c81af75bcd88 100644 --- a/Documentation/devicetree/bindings/memory-controllers/ath79-ddr-controller.txt +++ b/Documentation/devicetree/bindings/memory-controllers/ath79-ddr-controller.txt @@ -1,6 +1,6 @@ Binding for Qualcomm Atheros AR7xxx/AR9xxx DDR controller -The DDR controller of the ARxxx and AR9xxx families provides an interface +The DDR controller of the AR7xxx and AR9xxx families provides an interface to flush the FIFO between various devices and the DDR. This is mainly used by the IRQ controller to flush the FIFO before running the interrupt handler of such devices. @@ -11,9 +11,9 @@ Required properties: "qca,[ar7100|ar7240]-ddr-controller" as fallback. On SoC with PCI support "qca,ar7100-ddr-controller" should be used as fallback, otherwise "qca,ar7240-ddr-controller" should be used. -- reg: Base address and size of the controllers memory area -- #qca,ddr-wb-channel-cells: has to be 1, the index of the write buffer - channel +- reg: Base address and size of the controller's memory area +- #qca,ddr-wb-channel-cells: Specifies the number of cells needed to encode + the write buffer channel index, should be 1. Example: diff --git a/Documentation/devicetree/bindings/mfd/arizona.txt b/Documentation/devicetree/bindings/mfd/arizona.txt index 18be0cbfb456..9b30011ecabe 100644 --- a/Documentation/devicetree/bindings/mfd/arizona.txt +++ b/Documentation/devicetree/bindings/mfd/arizona.txt @@ -1,4 +1,4 @@ -Wolfson Arizona class audio SoCs +Cirrus Logic/Wolfson Microelectronics Arizona class audio SoCs These devices are audio SoCs with extensive digital capabilites and a range of analogue I/O. @@ -6,12 +6,14 @@ of analogue I/O. Required properties: - compatible : One of the following chip-specific strings: + "cirrus,cs47l24" "wlf,wm5102" "wlf,wm5110" "wlf,wm8280" "wlf,wm8997" "wlf,wm8998" "wlf,wm1814" + "wlf,wm1831" - reg : I2C slave address when connected using I2C, chip select number when using SPI. @@ -24,7 +26,7 @@ Required properties: - #interrupt-cells: the number of cells to describe an IRQ, this should be 2. The first cell is the IRQ number. The second cell is the flags, encoded as the trigger masks from - Documentation/devicetree/bindings/interrupts.txt + Documentation/devicetree/bindings/interrupt-controller/interrupts.txt - gpio-controller : Indicates this device is a GPIO controller. - #gpio-cells : Must be 2. The first cell is the pin number and the @@ -41,10 +43,21 @@ Required properties: - SPKVDD-supply : Speaker driver power supply (wm8997) + - DCVDD-supply : Main power supply (cs47l24, wm1831) + + - MICVDD-supply : Microphone power supply (cs47l24, wm1831) + Optional properties: - wlf,reset : GPIO specifier for the GPIO controlling /RESET + - clocks: Should reference the clocks supplied on MCLK1 and MCLK2 + - clock-names: Should contains two strings: + "mclk1" for the clock supplied on MCLK1, recommended to be a high + quality audio reference clock + "mclk2" for the clock supplied on MCLK2, recommended to be an always on + 32k clock + - wlf,gpio-defaults : A list of GPIO configuration register values. Defines for the appropriate values can found in <dt-bindings/mfd/arizona.txt>. If absent, no configuration of these registers is performed. If any entry has @@ -59,6 +72,12 @@ Optional properties: that have not been specified are set to 0 by default. Entries are: <IN1, IN2, IN3, IN4> (wm5102, wm5110, wm8280, wm8997) <IN1A, IN2A, IN1B, IN2B> (wm8998, wm1814) + - wlf,out-mono : A list of boolean values indicating whether each output is + mono or stereo. Position within the list indicates the output affected + (eg. First entry in the list corresponds to output 1). A non-zero value + indicates a mono output. If present, the number of values should be less + than or equal to the number of outputs, if less values are supplied the + additional outputs will be treated as stereo. - wlf,dmic-ref : DMIC reference voltage source for each input, can be selected from either MICVDD or one of the MICBIAS's, defines @@ -69,6 +88,7 @@ Optional properties: - DCVDD-supply, MICVDD-supply : Power supplies, only need to be specified if they are being externally supplied. As covered in Documentation/devicetree/bindings/regulator/regulator.txt + (wm5102, wm5110, wm8280, wm8997, wm8998, wm1814) Also see child specific device properties: Regulator - ../regulator/arizona-regulator.txt diff --git a/Documentation/devicetree/bindings/mfd/palmas.txt b/Documentation/devicetree/bindings/mfd/palmas.txt index eda898978d33..8ae1a32bfb7e 100644 --- a/Documentation/devicetree/bindings/mfd/palmas.txt +++ b/Documentation/devicetree/bindings/mfd/palmas.txt @@ -24,7 +24,7 @@ and also the generic series names - #interrupt-cells : should be set to 2 for IRQ number and flags The first cell is the IRQ number. The second cell is the flags, encoded as the trigger masks from - Documentation/devicetree/bindings/interrupts.txt + Documentation/devicetree/bindings/interrupt-controller/interrupts.txt - interrupt-parent : The parent interrupt controller. Optional properties: diff --git a/Documentation/devicetree/bindings/mfd/s2mpa01.txt b/Documentation/devicetree/bindings/mfd/s2mpa01.txt deleted file mode 100644 index c13d3d8c3947..000000000000 --- a/Documentation/devicetree/bindings/mfd/s2mpa01.txt +++ /dev/null @@ -1,90 +0,0 @@ - -* Samsung S2MPA01 Voltage and Current Regulator - -The Samsung S2MPA01 is a multi-function device which includes high -efficiency buck converters including Dual-Phase buck converter, various LDOs, -and an RTC. It is interfaced to the host controller using an I2C interface. -Each sub-block is addressed by the host system using different I2C slave -addresses. - -Required properties: -- compatible: Should be "samsung,s2mpa01-pmic". -- reg: Specifies the I2C slave address of the PMIC block. It should be 0x66. - -Optional properties: -- interrupt-parent: Specifies the phandle of the interrupt controller to which - the interrupts from s2mpa01 are delivered to. -- interrupts: An interrupt specifier for the sole interrupt generated by the - device. - -Optional nodes: -- regulators: The regulators of s2mpa01 that have to be instantiated should be - included in a sub-node named 'regulators'. Regulator nodes and constraints - included in this sub-node use the standard regulator bindings which are - documented elsewhere. - -Properties for BUCK regulator nodes: -- regulator-ramp-delay: ramp delay in uV/us. May be 6250, 12500 - (default), 25000, or 50000. May be 0 for disabling the ramp delay on - BUCK{1,2,3,4}. - - In the absence of the regulator-ramp-delay property, the default ramp - delay will be used. - - NOTE: Some BUCKs share the ramp rate setting i.e. same ramp value will be set - for a particular group of BUCKs. So provide same regulator-ramp-delay=<value>. - - The following BUCKs share ramp settings: - * 1 and 6 - * 2 and 4 - * 8, 9, and 10 - -The following are the names of the regulators that the s2mpa01 PMIC block -supports. Note: The 'n' in LDOn and BUCKn represents the LDO or BUCK number -as per the datasheet of s2mpa01. - - - LDOn - - valid values for n are 1 to 26 - - Example: LDO1, LD02, LDO26 - - BUCKn - - valid values for n are 1 to 10. - - Example: BUCK1, BUCK2, BUCK9 - -Example: - - s2mpa01_pmic@66 { - compatible = "samsung,s2mpa01-pmic"; - reg = <0x66>; - - regulators { - ldo1_reg: LDO1 { - regulator-name = "VDD_ALIVE"; - regulator-min-microvolt = <1000000>; - regulator-max-microvolt = <1000000>; - }; - - ldo2_reg: LDO2 { - regulator-name = "VDDQ_MMC2"; - regulator-min-microvolt = <2800000>; - regulator-max-microvolt = <2800000>; - regulator-always-on; - }; - - buck1_reg: BUCK1 { - regulator-name = "vdd_mif"; - regulator-min-microvolt = <950000>; - regulator-max-microvolt = <1350000>; - regulator-always-on; - regulator-boot-on; - }; - - buck2_reg: BUCK2 { - regulator-name = "vdd_arm"; - regulator-min-microvolt = <950000>; - regulator-max-microvolt = <1350000>; - regulator-always-on; - regulator-boot-on; - regulator-ramp-delay = <50000>; - }; - }; - }; diff --git a/Documentation/devicetree/bindings/mfd/s2mps11.txt b/Documentation/devicetree/bindings/mfd/s2mps11.txt deleted file mode 100644 index 09b94c97faac..000000000000 --- a/Documentation/devicetree/bindings/mfd/s2mps11.txt +++ /dev/null @@ -1,153 +0,0 @@ - -* Samsung S2MPS11/13/14/15 and S2MPU02 Voltage and Current Regulator - -The Samsung S2MPS11 is a multi-function device which includes voltage and -current regulators, RTC, charger controller and other sub-blocks. It is -interfaced to the host controller using an I2C interface. Each sub-block is -addressed by the host system using different I2C slave addresses. - -Required properties: -- compatible: Should be one of the following - - "samsung,s2mps11-pmic" - - "samsung,s2mps13-pmic" - - "samsung,s2mps14-pmic" - - "samsung,s2mps15-pmic" - - "samsung,s2mpu02-pmic". -- reg: Specifies the I2C slave address of the pmic block. It should be 0x66. - -Optional properties: -- interrupt-parent: Specifies the phandle of the interrupt controller to which - the interrupts from s2mps11 are delivered to. -- interrupts: Interrupt specifiers for interrupt sources. -- samsung,s2mps11-wrstbi-ground: Indicates that WRSTBI pin of PMIC is pulled - down. When the system is suspended it will always go down thus triggerring - unwanted buck warm reset (setting buck voltages to default values). -- samsung,s2mps11-acokb-ground: Indicates that ACOKB pin of S2MPS11 PMIC is - connected to the ground so the PMIC must manually set PWRHOLD bit in CTRL1 - register to turn off the power. Usually the ACOKB is pulled up to VBATT so - when PWRHOLD pin goes low, the rising ACOKB will trigger power off. - -Optional nodes: -- clocks: s2mps11, s2mps13, s2mps15 and s5m8767 provide three(AP/CP/BT) buffered 32.768 - KHz outputs, so to register these as clocks with common clock framework - instantiate a sub-node named "clocks". It uses the common clock binding - documented in : - [Documentation/devicetree/bindings/clock/clock-bindings.txt] - The s2mps14 provides two (AP/BT) buffered 32.768 KHz outputs. - - #clock-cells: should be 1. - - - The following is the list of clocks generated by the controller. Each clock - is assigned an identifier and client nodes use this identifier to specify - the clock which they consume. - Clock ID Devices - ---------------------------------------------------------- - 32KhzAP 0 S2MPS11, S2MPS13, S2MPS14, S2MPS15, S5M8767 - 32KhzCP 1 S2MPS11, S2MPS13, S2MPS15, S5M8767 - 32KhzBT 2 S2MPS11, S2MPS13, S2MPS14, S2MPS15, S5M8767 - - - compatible: Should be one of: "samsung,s2mps11-clk", "samsung,s2mps13-clk", - "samsung,s2mps14-clk", "samsung,s5m8767-clk" - The s2msp15 uses the same compatible as s2mps13, as both provides similar clocks. - -- regulators: The regulators of s2mps11 that have to be instantiated should be -included in a sub-node named 'regulators'. Regulator nodes included in this -sub-node should be of the format as listed below. - - regulator_name { - [standard regulator constraints....]; - }; - - regulator-ramp-delay for BUCKs = [6250/12500/25000(default)/50000] uV/us - - BUCK[2/3/4/6] supports disabling ramp delay on hardware, so explicitly - regulator-ramp-delay = <0> can be used for them to disable ramp delay. - In the absence of the regulator-ramp-delay property, the default ramp - delay will be used. - -NOTE: Some BUCKs share the ramp rate setting i.e. same ramp value will be set -for a particular group of BUCKs. So provide same regulator-ramp-delay<value>. -Grouping of BUCKs sharing ramp rate setting is as follow : BUCK[1, 6], -BUCK[3, 4], and BUCK[7, 8, 10] - -On S2MPS14 the LDO10, LDO11 and LDO12 can be configured to external control -over GPIO. To turn this feature on this property must be added to the regulator -sub-node: - - samsung,ext-control-gpios: GPIO specifier for one GPIO - controlling this regulator (enable/disable); -Example: - LDO12 { - regulator-name = "V_EMMC_2.8V"; - regulator-min-microvolt = <2800000>; - regulator-max-microvolt = <2800000>; - samsung,ext-control-gpios = <&gpk0 2 0>; - }; - - -The regulator constraints inside the regulator nodes use the standard regulator -bindings which are documented elsewhere. - -The following are the names of the regulators that the s2mps11 pmic block -supports. Note: The 'n' in LDOn and BUCKn represents the LDO or BUCK number -as per the datasheet of s2mps11. - - - LDOn - - valid values for n are: - - S2MPS11: 1 to 38 - - S2MPS13: 1 to 40 - - S2MPS14: 1 to 25 - - S2MPS15: 1 to 27 - - S2MPU02: 1 to 28 - - Example: LDO1, LDO2, LDO28 - - BUCKn - - valid values for n are: - - S2MPS11: 1 to 10 - - S2MPS13: 1 to 10 - - S2MPS14: 1 to 5 - - S2MPS15: 1 to 10 - - S2MPU02: 1 to 7 - - Example: BUCK1, BUCK2, BUCK9 - -Example: - - s2mps11_pmic@66 { - compatible = "samsung,s2mps11-pmic"; - reg = <0x66>; - - s2m_osc: clocks { - compatible = "samsung,s2mps11-clk"; - #clock-cells = <1>; - clock-output-names = "xx", "yy", "zz"; - }; - - regulators { - ldo1_reg: LDO1 { - regulator-name = "VDD_ABB_3.3V"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - }; - - ldo2_reg: LDO2 { - regulator-name = "VDD_ALIVE_1.1V"; - regulator-min-microvolt = <1100000>; - regulator-max-microvolt = <1100000>; - regulator-always-on; - }; - - buck1_reg: BUCK1 { - regulator-name = "vdd_mif"; - regulator-min-microvolt = <950000>; - regulator-max-microvolt = <1350000>; - regulator-always-on; - regulator-boot-on; - }; - - buck2_reg: BUCK2 { - regulator-name = "vdd_arm"; - regulator-min-microvolt = <950000>; - regulator-max-microvolt = <1350000>; - regulator-always-on; - regulator-boot-on; - regulator-ramp-delay = <50000>; - }; - }; - }; diff --git a/Documentation/devicetree/bindings/mfd/samsung,sec-core.txt b/Documentation/devicetree/bindings/mfd/samsung,sec-core.txt new file mode 100644 index 000000000000..cdd079bfc287 --- /dev/null +++ b/Documentation/devicetree/bindings/mfd/samsung,sec-core.txt @@ -0,0 +1,88 @@ +Binding for Samsung S2M and S5M family multi-function device +============================================================ + +This is a part of device tree bindings for S2M and S5M family multi-function +devices. + +The Samsung S2MPA01, S2MPS11/13/14/15, S2MPU02 and S5M8767 is a family +of multi-function devices which include voltage and current regulators, RTC, +charger controller, clock outputs and other sub-blocks. It is interfaced +to the host controller using an I2C interface. Each sub-block is usually +addressed by the host system using different I2C slave addresses. + + +This document describes bindings for main device node. Optional sub-blocks +must be a sub-nodes to it. Bindings for them can be found in: + - bindings/regulator/samsung,s2mpa01.txt + - bindings/regulator/samsung,s2mps11.txt + - bindings/regulator/samsung,s5m8767.txt + - bindings/clock/samsung,s2mps11.txt + + +Required properties: + - compatible: Should be one of the following + - "samsung,s2mpa01-pmic", + - "samsung,s2mps11-pmic", + - "samsung,s2mps13-pmic", + - "samsung,s2mps14-pmic", + - "samsung,s2mps15-pmic", + - "samsung,s2mpu02-pmic", + - "samsung,s5m8767-pmic". + - reg: Specifies the I2C slave address of the pmic block. It should be 0x66. + +Optional properties: + - interrupt-parent: Specifies the phandle of the interrupt controller to which + the interrupts from s2mps11 are delivered to. + - interrupts: Interrupt specifiers for interrupt sources. + - samsung,s2mps11-wrstbi-ground: Indicates that WRSTBI pin of PMIC is pulled + down. When the system is suspended it will always go down thus triggerring + unwanted buck warm reset (setting buck voltages to default values). + - samsung,s2mps11-acokb-ground: Indicates that ACOKB pin of S2MPS11 PMIC is + connected to the ground so the PMIC must manually set PWRHOLD bit in CTRL1 + register to turn off the power. Usually the ACOKB is pulled up to VBATT so + when PWRHOLD pin goes low, the rising ACOKB will trigger power off. + +Example: + + s2mps11_pmic@66 { + compatible = "samsung,s2mps11-pmic"; + reg = <0x66>; + + s2m_osc: clocks { + compatible = "samsung,s2mps11-clk"; + #clock-cells = <1>; + clock-output-names = "xx", "yy", "zz"; + }; + + regulators { + ldo1_reg: LDO1 { + regulator-name = "VDD_ABB_3.3V"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; + + ldo2_reg: LDO2 { + regulator-name = "VDD_ALIVE_1.1V"; + regulator-min-microvolt = <1100000>; + regulator-max-microvolt = <1100000>; + regulator-always-on; + }; + + buck1_reg: BUCK1 { + regulator-name = "vdd_mif"; + regulator-min-microvolt = <950000>; + regulator-max-microvolt = <1350000>; + regulator-always-on; + regulator-boot-on; + }; + + buck2_reg: BUCK2 { + regulator-name = "vdd_arm"; + regulator-min-microvolt = <950000>; + regulator-max-microvolt = <1350000>; + regulator-always-on; + regulator-boot-on; + regulator-ramp-delay = <50000>; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/mfd/syscon.txt b/Documentation/devicetree/bindings/mfd/syscon.txt index fe8150bb3248..408f768686f1 100644 --- a/Documentation/devicetree/bindings/mfd/syscon.txt +++ b/Documentation/devicetree/bindings/mfd/syscon.txt @@ -13,6 +13,10 @@ Required properties: - compatible: Should contain "syscon". - reg: the register region can be accessed from syscon +Optional property: +- reg-io-width: the size (in bytes) of the IO accesses that should be + performed on the device. + Examples: gpr: iomuxc-gpr@020e0000 { compatible = "fsl,imx6q-iomuxc-gpr", "syscon"; diff --git a/Documentation/devicetree/bindings/mtd/fsl-quadspi.txt b/Documentation/devicetree/bindings/mtd/fsl-quadspi.txt index 862aa2f8837a..00c587b3d3ae 100644 --- a/Documentation/devicetree/bindings/mtd/fsl-quadspi.txt +++ b/Documentation/devicetree/bindings/mtd/fsl-quadspi.txt @@ -2,7 +2,8 @@ Required properties: - compatible : Should be "fsl,vf610-qspi", "fsl,imx6sx-qspi", - "fsl,imx7d-qspi", "fsl,imx6ul-qspi" + "fsl,imx7d-qspi", "fsl,imx6ul-qspi", + "fsl,ls1021-qspi" - reg : the first contains the register location and length, the second contains the memory mapping address and length - reg-names: Should contain the reg names "QuadSPI" and "QuadSPI-memory" diff --git a/Documentation/devicetree/bindings/net/cdns-emac.txt b/Documentation/devicetree/bindings/net/cdns-emac.txt deleted file mode 100644 index 4451ee973223..000000000000 --- a/Documentation/devicetree/bindings/net/cdns-emac.txt +++ /dev/null @@ -1,20 +0,0 @@ -* Cadence EMAC Ethernet controller - -Required properties: -- compatible: Should be "cdns,[<chip>-]{emac}" - Use "cdns,at91rm9200-emac" Atmel at91rm9200 SoC. - Use "cdns,zynq-gem" Xilinx Zynq-7xxx SoC. - Or the generic form: "cdns,emac". -- reg: Address and length of the register set for the device -- interrupts: Should contain macb interrupt -- phy-mode: see ethernet.txt file in the same directory. - -Examples: - - macb0: ethernet@fffc4000 { - compatible = "cdns,at91rm9200-emac"; - reg = <0xfffc4000 0x4000>; - interrupts = <21>; - phy-mode = "rmii"; - local-mac-address = [3a 0e 03 04 05 06]; - }; diff --git a/Documentation/devicetree/bindings/net/macb.txt b/Documentation/devicetree/bindings/net/macb.txt index 5c397ca14cfe..d2e243b1ec0e 100644 --- a/Documentation/devicetree/bindings/net/macb.txt +++ b/Documentation/devicetree/bindings/net/macb.txt @@ -2,6 +2,7 @@ Required properties: - compatible: Should be "cdns,[<chip>-]{macb|gem}" + Use "cdns,at91rm9200-emac" Atmel at91rm9200 SoC. Use "cdns,at91sam9260-macb" for Atmel at91sam9 SoCs or the 10/100Mbit IP available on sama5d3 SoCs. Use "cdns,np4-macb" for NP4 SoC devices. @@ -11,7 +12,9 @@ Required properties: Use "atmel,sama5d2-gem" for the GEM IP (10/100) available on Atmel sama5d2 SoCs. Use "atmel,sama5d3-gem" for the Gigabit IP available on Atmel sama5d3 SoCs. Use "atmel,sama5d4-gem" for the GEM IP (10/100) available on Atmel sama5d4 SoCs. + Use "cdns,zynq-gem" Xilinx Zynq-7xxx SoC. Use "cdns,zynqmp-gem" for Zynq Ultrascale+ MPSoC. + Or the generic form: "cdns,emac". - reg: Address and length of the register set for the device - interrupts: Should contain macb interrupt - phy-mode: See ethernet.txt file in the same directory. diff --git a/Documentation/devicetree/bindings/regulator/lm363x-regulator.txt b/Documentation/devicetree/bindings/regulator/lm363x-regulator.txt new file mode 100644 index 000000000000..8f14df9d1205 --- /dev/null +++ b/Documentation/devicetree/bindings/regulator/lm363x-regulator.txt @@ -0,0 +1,34 @@ +TI LMU LM363x regulator device tree bindings + +LM363x regulator driver supports LM3631 and LM3632. +LM3631 has five regulators and LM3632 supports three regulators. + +Required property: + - compatible: "ti,lm363x-regulator" + +Optional properties: + LM3632 has external enable pins for two LDOs. + - ti,lcm-en1-gpio: A GPIO specifier for Vpos control pin. + - ti,lcm-en2-gpio: A GPIO specifier for Vneg control pin. + +Child nodes: + LM3631 + - vboost + - vcont + - voref + - vpos + - vneg + + LM3632 + - vboost + - vpos + - vneg + + Optional properties of a child node: + Each sub-node should contain the constraints and initialization. + Please refer to [1]. + +Examples: Please refer to ti-lmu dt-bindings [2]. + +[1] ../regulator/regulator.txt +[2] ../mfd/ti-lmu.txt diff --git a/Documentation/devicetree/bindings/regulator/pv88060.txt b/Documentation/devicetree/bindings/regulator/pv88060.txt new file mode 100644 index 000000000000..10a6dadc008e --- /dev/null +++ b/Documentation/devicetree/bindings/regulator/pv88060.txt @@ -0,0 +1,124 @@ +* Powerventure Semiconductor PV88060 Voltage Regulator + +Required properties: +- compatible: "pvs,pv88060". +- reg: I2C slave address, usually 0x49. +- interrupts: the interrupt outputs of the controller +- regulators: A node that houses a sub-node for each regulator within the + device. Each sub-node is identified using the node's name, with valid + values listed below. The content of each sub-node is defined by the + standard binding for regulators; see regulator.txt. + BUCK1, LDO1, LDO2, LDO3, LDO4, LDO5, LDO6, LDO7, SW1, SW2, SW3, SW4, + SW5, and SW6. + +Optional properties: +- Any optional property defined in regulator.txt + +Example + + pmic: pv88060@49 { + compatible = "pvs,pv88060"; + reg = <0x49>; + interrupt-parent = <&gpio>; + interrupts = <24 24>; + + regulators { + BUCK1 { + regulator-name = "buck1"; + regulator-min-microvolt = <2800000>; + regulator-max-microvolt = <4387500>; + regulator-min-microamp = <1496000>; + regulator-max-microamp = <4189000>; + regulator-boot-on; + }; + + LDO1 { + regulator-name = "ldo1"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <3350000>; + regulator-boot-on; + }; + + LDO2 { + regulator-name = "ldo2"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <3350000>; + regulator-boot-on; + }; + + LDO3 { + regulator-name = "ldo3"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <3350000>; + regulator-boot-on; + }; + + LDO4 { + regulator-name = "ldo4"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <3350000>; + regulator-boot-on; + }; + + LDO5 { + regulator-name = "ldo5"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <3350000>; + regulator-boot-on; + }; + + LDO6 { + regulator-name = "ldo6"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <3350000>; + regulator-boot-on; + }; + + LDO7 { + regulator-name = "ldo7"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <3350000>; + regulator-boot-on; + }; + + SW1 { + regulator-name = "sw1"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + }; + + SW2 { + regulator-name = "sw2"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + regulator-boot-on; + }; + + SW3 { + regulator-name = "sw3"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + regulator-boot-on; + }; + + SW4 { + regulator-name = "sw4"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + regulator-boot-on; + }; + + SW5 { + regulator-name = "sw5"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + regulator-boot-on; + }; + + SW6 { + regulator-name = "sw6"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + }; + }; + };
\ No newline at end of file diff --git a/Documentation/devicetree/bindings/regulator/pv88090.txt b/Documentation/devicetree/bindings/regulator/pv88090.txt new file mode 100644 index 000000000000..e52b2a95cdde --- /dev/null +++ b/Documentation/devicetree/bindings/regulator/pv88090.txt @@ -0,0 +1,65 @@ +* Powerventure Semiconductor PV88090 Voltage Regulator + +Required properties: +- compatible: "pvs,pv88090". +- reg: I2C slave address, usually 0x48. +- interrupts: the interrupt outputs of the controller +- regulators: A node that houses a sub-node for each regulator within the + device. Each sub-node is identified using the node's name, with valid + values listed below. The content of each sub-node is defined by the + standard binding for regulators; see regulator.txt. + BUCK1, BUCK2, BUCK3, LDO1, and LDO2. + +Optional properties: +- Any optional property defined in regulator.txt + +Example + + pmic: pv88090@48 { + compatible = "pvs,pv88090"; + reg = <0x48>; + interrupt-parent = <&gpio>; + interrupts = <24 24>; + + regulators { + BUCK1 { + regulator-name = "buck1"; + regulator-min-microvolt = < 600000>; + regulator-max-microvolt = <1393750>; + regulator-min-microamp = < 220000>; + regulator-max-microamp = <7040000>; + regulator-boot-on; + }; + + BUCK2 { + regulator-name = "buck2"; + regulator-min-microvolt = < 600000>; + regulator-max-microvolt = <1393750>; + regulator-min-microamp = <1496000>; + regulator-max-microamp = <4189000>; + }; + + BUCK3 { + regulator-name = "buck3"; + regulator-min-microvolt = <600000>; + regulator-max-microvolt = <1393750>; + regulator-min-microamp = <1496000>; + regulator-max-microamp = <4189000>; + regulator-boot-on; + }; + + LDO1 { + regulator-name = "ldo1"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <4350000>; + regulator-boot-on; + }; + + LDO2 { + regulator-name = "ldo2"; + regulator-min-microvolt = < 650000>; + regulator-max-microvolt = <2225000>; + regulator-boot-on; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/soc/qcom,smd-rpm.txt b/Documentation/devicetree/bindings/regulator/qcom,smd-rpm-regulator.txt index e27f5c4c54fd..1f8d6f84b657 100644 --- a/Documentation/devicetree/bindings/soc/qcom,smd-rpm.txt +++ b/Documentation/devicetree/bindings/regulator/qcom,smd-rpm-regulator.txt @@ -1,27 +1,17 @@ -Qualcomm Resource Power Manager (RPM) over SMD +QCOM SMD RPM REGULATOR -This driver is used to interface with the Resource Power Manager (RPM) found in -various Qualcomm platforms. The RPM allows each component in the system to vote -for state of the system resources, such as clocks, regulators and bus -frequencies. +The Qualcomm RPM over SMD regulator is modelled as a subdevice of the RPM. +Because SMD is used as the communication transport mechanism, the RPM resides as +a subnode of the SMD. As such, the SMD-RPM regulator requires that the SMD and +RPM nodes be present. -- compatible: - Usage: required - Value type: <string> - Definition: must be one of: - "qcom,rpm-msm8974" +Please refer to Documentation/devicetree/bindings/soc/qcom/qcom,smd.txt for +information pertaining to the SMD node. -- qcom,smd-channels: - Usage: required - Value type: <stringlist> - Definition: Shared Memory channel used for communication with the RPM +Please refer to Documentation/devicetree/bindings/soc/qcom/qcom,smd-rpm.txt for +information regarding the RPM node. -= SUBDEVICES - -The RPM exposes resources to its subnodes. The below bindings specify the set -of valid subnodes that can operate on these resources. - -== Regulators +== Regulator Regulator nodes are identified by their compatible: @@ -30,7 +20,9 @@ Regulator nodes are identified by their compatible: Value type: <string> Definition: must be one of: "qcom,rpm-pm8841-regulators" + "qcom,rpm-pm8916-regulators" "qcom,rpm-pm8941-regulators" + "qcom,rpm-pma8084-regulators" - vdd_s1-supply: - vdd_s2-supply: @@ -48,6 +40,19 @@ Regulator nodes are identified by their compatible: - vdd_s1-supply: - vdd_s2-supply: - vdd_s3-supply: +- vdd_s4-supply: +- vdd_l1_l2_l3-supply: +- vdd_l4_l5_l6-supply: +- vdd_l7-supply: +- vdd_l8_l9_l10_l11_l12_l13_l14_l15_l16_l17_l18-supply: + Usage: optional (pm8916 only) + Value type: <phandle> + Definition: reference to regulator supplying the input pin, as + described in the data sheet + +- vdd_s1-supply: +- vdd_s2-supply: +- vdd_s3-supply: - vdd_l1_l3-supply: - vdd_l2_lvs1_2_3-supply: - vdd_l4_l11-supply: @@ -63,6 +68,35 @@ Regulator nodes are identified by their compatible: Definition: reference to regulator supplying the input pin, as described in the data sheet +- vdd_s1-supply: +- vdd_s2-supply: +- vdd_s3-supply: +- vdd_s4-supply: +- vdd_s5-supply: +- vdd_s6-supply: +- vdd_s7-supply: +- vdd_s8-supply: +- vdd_s9-supply: +- vdd_s10-supply: +- vdd_s11-supply: +- vdd_s12-supply: +- vdd_l1_l11-supply: +- vdd_l2_l3_l4_l27-supply: +- vdd_l5_l7-supply: +- vdd_l6_l12_l14_l15_l26-supply: +- vdd_l8-supply: +- vdd_l9_l10_l13_l20_l23_l24-supply: +- vdd_l16_l25-supply: +- vdd_l17-supply: +- vdd_l18-supply: +- vdd_l19-supply: +- vdd_l21-supply: +- vdd_l22-supply: + Usage: optional (pma8084 only) + Value type: <phandle> + Definition: reference to regulator supplying the input pin, as + described in the data sheet + The regulator node houses sub-nodes for each regulator within the device. Each sub-node is identified using the node's name, with valid values listed for each of the pmics below. @@ -70,11 +104,20 @@ of the pmics below. pm8841: s1, s2, s3, s4, s5, s6, s7, s8 +pm8916: + s1, s2, s3, s4, l1, l2, l3, l4, l5, l6, l7, l8, l9, l10, l11, l12, l13, + l14, l15, l16, l17, l18 + pm8941: s1, s2, s3, s4, l1, l2, l3, l4, l5, l6, l7, l8, l9, l10, l11, l12, l13, l14, l15, l16, l17, l18, l19, l20, l21, l22, l23, l24, lvs1, lvs2, lvs3, 5vs1, 5vs2 +pma8084: + s1, s2, s3, s4, s5, s6, s7, s8, s9, s10, s11, s12, l1, l2, l3, l4, l5, + l6, l7, l8, l9, l10, l11, l12, l13, l14, l15, l16, l17, l18, l19, l20, + l21, l22, l23, l24, l25, l26, l27, lvs1, lvs2, lvs3, lvs4, 5vs1 + The content of each sub-node is defined by the standard binding for regulators - see regulator.txt. @@ -114,4 +157,3 @@ see regulator.txt. }; }; }; - diff --git a/Documentation/devicetree/bindings/regulator/s5m8767-regulator.txt b/Documentation/devicetree/bindings/regulator/s5m8767-regulator.txt deleted file mode 100644 index 20191315e444..000000000000 --- a/Documentation/devicetree/bindings/regulator/s5m8767-regulator.txt +++ /dev/null @@ -1,163 +0,0 @@ -* Samsung S5M8767 Voltage and Current Regulator - -The Samsung S5M8767 is a multi-function device which includes voltage and -current regulators, rtc, charger controller and other sub-blocks. It is -interfaced to the host controller using a i2c interface. Each sub-block is -addressed by the host system using different i2c slave address. This document -describes the bindings for 'pmic' sub-block of s5m8767. - -Required properties: -- compatible: Should be "samsung,s5m8767-pmic". -- reg: Specifies the i2c slave address of the pmic block. It should be 0x66. - -- s5m8767,pmic-buck2-dvs-voltage: A set of 8 voltage values in micro-volt (uV) - units for buck2 when changing voltage using gpio dvs. Refer to [1] below - for additional information. - -- s5m8767,pmic-buck3-dvs-voltage: A set of 8 voltage values in micro-volt (uV) - units for buck3 when changing voltage using gpio dvs. Refer to [1] below - for additional information. - -- s5m8767,pmic-buck4-dvs-voltage: A set of 8 voltage values in micro-volt (uV) - units for buck4 when changing voltage using gpio dvs. Refer to [1] below - for additional information. - -- s5m8767,pmic-buck-ds-gpios: GPIO specifiers for three host gpio's used - for selecting GPIO DVS lines. It is one-to-one mapped to dvs gpio lines. - -[1] If none of the 's5m8767,pmic-buck[2/3/4]-uses-gpio-dvs' optional - property is specified, the 's5m8767,pmic-buck[2/3/4]-dvs-voltage' - property should specify atleast one voltage level (which would be a - safe operating voltage). - - If either of the 's5m8767,pmic-buck[2/3/4]-uses-gpio-dvs' optional - property is specified, then all the eight voltage values for the - 's5m8767,pmic-buck[2/3/4]-dvs-voltage' should be specified. - -Optional properties: -- interrupt-parent: Specifies the phandle of the interrupt controller to which - the interrupts from s5m8767 are delivered to. -- interrupts: Interrupt specifiers for two interrupt sources. - - First interrupt specifier is for 'irq1' interrupt. - - Second interrupt specifier is for 'alert' interrupt. -- s5m8767,pmic-buck2-uses-gpio-dvs: 'buck2' can be controlled by gpio dvs. -- s5m8767,pmic-buck3-uses-gpio-dvs: 'buck3' can be controlled by gpio dvs. -- s5m8767,pmic-buck4-uses-gpio-dvs: 'buck4' can be controlled by gpio dvs. - -Additional properties required if either of the optional properties are used: - -- s5m8767,pmic-buck234-default-dvs-idx: Default voltage setting selected from - the possible 8 options selectable by the dvs gpios. The value of this - property should be between 0 and 7. If not specified or if out of range, the - default value of this property is set to 0. - -- s5m8767,pmic-buck-dvs-gpios: GPIO specifiers for three host gpio's used - for dvs. The format of the gpio specifier depends in the gpio controller. - -Regulators: The regulators of s5m8767 that have to be instantiated should be -included in a sub-node named 'regulators'. Regulator nodes included in this -sub-node should be of the format as listed below. - - regulator_name { - ldo1_reg: LDO1 { - regulator-name = "VDD_ALIVE_1.0V"; - regulator-min-microvolt = <1100000>; - regulator-max-microvolt = <1100000>; - regulator-always-on; - regulator-boot-on; - op_mode = <1>; /* Normal Mode */ - }; - }; -The above regulator entries are defined in regulator bindings documentation -except these properties: - - op_mode: describes the different operating modes of the LDO's with - power mode change in SOC. The different possible values are, - 0 - always off mode - 1 - on in normal mode - 2 - low power mode - 3 - suspend mode - - s5m8767,pmic-ext-control-gpios: (optional) GPIO specifier for one - GPIO controlling this regulator (enable/disable); This is - valid only for buck9. - -The following are the names of the regulators that the s5m8767 pmic block -supports. Note: The 'n' in LDOn and BUCKn represents the LDO or BUCK number -as per the datasheet of s5m8767. - - - LDOn - - valid values for n are 1 to 28 - - Example: LDO1, LDO2, LDO28 - - BUCKn - - valid values for n are 1 to 9. - - Example: BUCK1, BUCK2, BUCK9 - -The bindings inside the regulator nodes use the standard regulator bindings -which are documented elsewhere. - -Example: - - s5m8767_pmic@66 { - compatible = "samsung,s5m8767-pmic"; - reg = <0x66>; - - s5m8767,pmic-buck2-uses-gpio-dvs; - s5m8767,pmic-buck3-uses-gpio-dvs; - s5m8767,pmic-buck4-uses-gpio-dvs; - - s5m8767,pmic-buck-default-dvs-idx = <0>; - - s5m8767,pmic-buck-dvs-gpios = <&gpx0 0 0>, /* DVS1 */ - <&gpx0 1 0>, /* DVS2 */ - <&gpx0 2 0>; /* DVS3 */ - - s5m8767,pmic-buck-ds-gpios = <&gpx2 3 0>, /* SET1 */ - <&gpx2 4 0>, /* SET2 */ - <&gpx2 5 0>; /* SET3 */ - - s5m8767,pmic-buck2-dvs-voltage = <1350000>, <1300000>, - <1250000>, <1200000>, - <1150000>, <1100000>, - <1000000>, <950000>; - - s5m8767,pmic-buck3-dvs-voltage = <1100000>, <1100000>, - <1100000>, <1100000>, - <1000000>, <1000000>, - <1000000>, <1000000>; - - s5m8767,pmic-buck4-dvs-voltage = <1200000>, <1200000>, - <1200000>, <1200000>, - <1200000>, <1200000>, - <1200000>, <1200000>; - - regulators { - ldo1_reg: LDO1 { - regulator-name = "VDD_ABB_3.3V"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - op_mode = <1>; /* Normal Mode */ - }; - - ldo2_reg: LDO2 { - regulator-name = "VDD_ALIVE_1.1V"; - regulator-min-microvolt = <1100000>; - regulator-max-microvolt = <1100000>; - regulator-always-on; - }; - - buck1_reg: BUCK1 { - regulator-name = "VDD_MIF_1.2V"; - regulator-min-microvolt = <950000>; - regulator-max-microvolt = <1350000>; - regulator-always-on; - regulator-boot-on; - }; - - vemmc_reg: BUCK9 { - regulator-name = "VMEM_VDD_2.8V"; - regulator-min-microvolt = <2800000>; - regulator-max-microvolt = <2800000>; - op_mode = <3>; /* Standby Mode */ - s5m8767,pmic-ext-control-gpios = <&gpk0 2 0>; - }; - }; - }; diff --git a/Documentation/devicetree/bindings/regulator/samsung,s2mpa01.txt b/Documentation/devicetree/bindings/regulator/samsung,s2mpa01.txt new file mode 100644 index 000000000000..bae3c7f838cf --- /dev/null +++ b/Documentation/devicetree/bindings/regulator/samsung,s2mpa01.txt @@ -0,0 +1,79 @@ +Binding for Samsung S2MPA01 regulator block +=========================================== + +This is a part of device tree bindings for S2M family multi-function devices. +More information can be found in bindings/mfd/sec-core.txt file. + +The S2MPA01 device provide buck and LDO regulators. + +To register these with regulator framework instantiate under main device node +a sub-node named "regulators" with more sub-nodes for each regulator using the +common regulator binding documented in: + - Documentation/devicetree/bindings/regulator/regulator.txt + + +Names of regulators supported by S2MPA01 device: + - LDOn + - valid values for n are 1 to 26 + - Example: LDO1, LD02, LDO26 + - BUCKn + - valid values for n are 1 to 10. + - Example: BUCK1, BUCK2, BUCK9 +Note: The 'n' in LDOn and BUCKn represents the LDO or BUCK number +as per the datasheet of device. + + +Optional properties of buck regulator nodes under "regulators" sub-node: + - regulator-ramp-delay: ramp delay in uV/us. May be 6250, 12500 + (default), 25000, or 50000. May be 0 for disabling the ramp delay on + BUCK{1,2,3,4}. + + In the absence of the regulator-ramp-delay property, the default ramp + delay will be used. + + Note: Some bucks share the ramp rate setting i.e. same ramp value + will be set for a particular group of bucks so provide the same + regulator-ramp-delay value for them. + Groups sharing ramp rate: + - buck{1,6}, + - buck{2,4}, + - buck{8,9,10}. + +Example: + + s2mpa01_pmic@66 { + compatible = "samsung,s2mpa01-pmic"; + reg = <0x66>; + + regulators { + ldo1_reg: LDO1 { + regulator-name = "VDD_ALIVE"; + regulator-min-microvolt = <1000000>; + regulator-max-microvolt = <1000000>; + }; + + ldo2_reg: LDO2 { + regulator-name = "VDDQ_MMC2"; + regulator-min-microvolt = <2800000>; + regulator-max-microvolt = <2800000>; + regulator-always-on; + }; + + buck1_reg: BUCK1 { + regulator-name = "vdd_mif"; + regulator-min-microvolt = <950000>; + regulator-max-microvolt = <1350000>; + regulator-always-on; + regulator-boot-on; + }; + + buck2_reg: BUCK2 { + regulator-name = "vdd_arm"; + regulator-min-microvolt = <950000>; + regulator-max-microvolt = <1350000>; + regulator-always-on; + regulator-boot-on; + regulator-ramp-delay = <50000>; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/regulator/samsung,s2mps11.txt b/Documentation/devicetree/bindings/regulator/samsung,s2mps11.txt new file mode 100644 index 000000000000..27a48bf1b185 --- /dev/null +++ b/Documentation/devicetree/bindings/regulator/samsung,s2mps11.txt @@ -0,0 +1,102 @@ +Binding for Samsung S2M family regulator block +============================================== + +This is a part of device tree bindings for S2M family multi-function devices. +More information can be found in bindings/mfd/sec-core.txt file. + +The S2MPS11/13/14/15 and S2MPU02 devices provide buck and LDO regulators. + +To register these with regulator framework instantiate under main device node +a sub-node named "regulators" with more sub-nodes for each regulator using the +common regulator binding documented in: + - Documentation/devicetree/bindings/regulator/regulator.txt + + +Names of regulators supported by different devices: + - LDOn + - valid values for n are: + - S2MPS11: 1 to 38 + - S2MPS13: 1 to 40 + - S2MPS14: 1 to 25 + - S2MPS15: 1 to 27 + - S2MPU02: 1 to 28 + - Example: LDO1, LDO2, LDO28 + - BUCKn + - valid values for n are: + - S2MPS11: 1 to 10 + - S2MPS13: 1 to 10 + - S2MPS14: 1 to 5 + - S2MPS15: 1 to 10 + - S2MPU02: 1 to 7 + - Example: BUCK1, BUCK2, BUCK9 +Note: The 'n' in LDOn and BUCKn represents the LDO or BUCK number +as per the datasheet of device. + + +Optional properties of the nodes under "regulators" sub-node: + - regulator-ramp-delay: ramp delay in uV/us. May be 6250, 12500, + 25000 (default) or 50000. + + Additionally S2MPS11 supports disabling ramp delay for BUCK{2,3,4,6} + by setting it to <0>. + + Note: On S2MPS11 some bucks share the ramp rate setting i.e. same ramp value + will be set for a particular group of bucks so provide the same + regulator-ramp-delay value for them. + Groups sharing ramp rate: + - buck{1,6}, + - buck{3,4}, + - buck{7,8,10}. + + - samsung,ext-control-gpios: On S2MPS14 the LDO10, LDO11 and LDO12 can be + configured to external control over GPIO. To turn this feature on this + property must be added to the regulator sub-node: + - samsung,ext-control-gpios: GPIO specifier for one GPIO + controlling this regulator (enable/disable) + Example: + LDO12 { + regulator-name = "V_EMMC_2.8V"; + regulator-min-microvolt = <2800000>; + regulator-max-microvolt = <2800000>; + samsung,ext-control-gpios = <&gpk0 2 0>; + }; + + +Example: + + s2mps11_pmic@66 { + compatible = "samsung,s2mps11-pmic"; + reg = <0x66>; + + regulators { + ldo1_reg: LDO1 { + regulator-name = "VDD_ABB_3.3V"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; + + ldo2_reg: LDO2 { + regulator-name = "VDD_ALIVE_1.1V"; + regulator-min-microvolt = <1100000>; + regulator-max-microvolt = <1100000>; + regulator-always-on; + }; + + buck1_reg: BUCK1 { + regulator-name = "vdd_mif"; + regulator-min-microvolt = <950000>; + regulator-max-microvolt = <1350000>; + regulator-always-on; + regulator-boot-on; + }; + + buck2_reg: BUCK2 { + regulator-name = "vdd_arm"; + regulator-min-microvolt = <950000>; + regulator-max-microvolt = <1350000>; + regulator-always-on; + regulator-boot-on; + regulator-ramp-delay = <50000>; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/regulator/samsung,s5m8767.txt b/Documentation/devicetree/bindings/regulator/samsung,s5m8767.txt new file mode 100644 index 000000000000..093edda0c8df --- /dev/null +++ b/Documentation/devicetree/bindings/regulator/samsung,s5m8767.txt @@ -0,0 +1,145 @@ +Binding for Samsung S5M8767 regulator block +=========================================== + +This is a part of device tree bindings for S5M family multi-function devices. +More information can be found in bindings/mfd/sec-core.txt file. + +The S5M8767 device provide buck and LDO regulators. + +To register these with regulator framework instantiate under main device node +a sub-node named "regulators" with more sub-nodes for each regulator using the +common regulator binding documented in: + - Documentation/devicetree/bindings/regulator/regulator.txt + + +Required properties of the main device node (the parent!): + - s5m8767,pmic-buck2-dvs-voltage: A set of 8 voltage values in micro-volt (uV) + units for buck2 when changing voltage using gpio dvs. Refer to [1] below + for additional information. + + - s5m8767,pmic-buck3-dvs-voltage: A set of 8 voltage values in micro-volt (uV) + units for buck3 when changing voltage using gpio dvs. Refer to [1] below + for additional information. + + - s5m8767,pmic-buck4-dvs-voltage: A set of 8 voltage values in micro-volt (uV) + units for buck4 when changing voltage using gpio dvs. Refer to [1] below + for additional information. + + - s5m8767,pmic-buck-ds-gpios: GPIO specifiers for three host gpio's used + for selecting GPIO DVS lines. It is one-to-one mapped to dvs gpio lines. + + [1] If none of the 's5m8767,pmic-buck[2/3/4]-uses-gpio-dvs' optional + property is specified, the 's5m8767,pmic-buck[2/3/4]-dvs-voltage' + property should specify atleast one voltage level (which would be a + safe operating voltage). + + If either of the 's5m8767,pmic-buck[2/3/4]-uses-gpio-dvs' optional + property is specified, then all the eight voltage values for the + 's5m8767,pmic-buck[2/3/4]-dvs-voltage' should be specified. + +Optional properties of the main device node (the parent!): + - s5m8767,pmic-buck2-uses-gpio-dvs: 'buck2' can be controlled by gpio dvs. + - s5m8767,pmic-buck3-uses-gpio-dvs: 'buck3' can be controlled by gpio dvs. + - s5m8767,pmic-buck4-uses-gpio-dvs: 'buck4' can be controlled by gpio dvs. + +Additional properties required if either of the optional properties are used: + + - s5m8767,pmic-buck234-default-dvs-idx: Default voltage setting selected from + the possible 8 options selectable by the dvs gpios. The value of this + property should be between 0 and 7. If not specified or if out of range, the + default value of this property is set to 0. + + - s5m8767,pmic-buck-dvs-gpios: GPIO specifiers for three host gpio's used + for dvs. The format of the gpio specifier depends in the gpio controller. + + +Names of regulators supported by S5M8767 device: + - LDOn + - valid values for n are 1 to 28 + - Example: LDO1, LDO2, LDO28 + - BUCKn + - valid values for n are 1 to 9. + - Example: BUCK1, BUCK2, BUCK9 +Note: The 'n' in LDOn and BUCKn represents the LDO or BUCK number +as per the datasheet of device. + + +Optional properties of the nodes under "regulators" sub-node: + - op_mode: describes the different operating modes of the LDO's with + power mode change in SOC. The different possible values are, + 0 - always off mode + 1 - on in normal mode + 2 - low power mode + 3 - suspend mode + - s5m8767,pmic-ext-control-gpios: (optional) GPIO specifier for one + GPIO controlling this regulator + (enable/disable); This is valid only + for buck9. + +Example: + + s5m8767_pmic@66 { + compatible = "samsung,s5m8767-pmic"; + reg = <0x66>; + + s5m8767,pmic-buck2-uses-gpio-dvs; + s5m8767,pmic-buck3-uses-gpio-dvs; + s5m8767,pmic-buck4-uses-gpio-dvs; + + s5m8767,pmic-buck-default-dvs-idx = <0>; + + s5m8767,pmic-buck-dvs-gpios = <&gpx0 0 0>, /* DVS1 */ + <&gpx0 1 0>, /* DVS2 */ + <&gpx0 2 0>; /* DVS3 */ + + s5m8767,pmic-buck-ds-gpios = <&gpx2 3 0>, /* SET1 */ + <&gpx2 4 0>, /* SET2 */ + <&gpx2 5 0>; /* SET3 */ + + s5m8767,pmic-buck2-dvs-voltage = <1350000>, <1300000>, + <1250000>, <1200000>, + <1150000>, <1100000>, + <1000000>, <950000>; + + s5m8767,pmic-buck3-dvs-voltage = <1100000>, <1100000>, + <1100000>, <1100000>, + <1000000>, <1000000>, + <1000000>, <1000000>; + + s5m8767,pmic-buck4-dvs-voltage = <1200000>, <1200000>, + <1200000>, <1200000>, + <1200000>, <1200000>, + <1200000>, <1200000>; + + regulators { + ldo1_reg: LDO1 { + regulator-name = "VDD_ABB_3.3V"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + op_mode = <1>; /* Normal Mode */ + }; + + ldo2_reg: LDO2 { + regulator-name = "VDD_ALIVE_1.1V"; + regulator-min-microvolt = <1100000>; + regulator-max-microvolt = <1100000>; + regulator-always-on; + }; + + buck1_reg: BUCK1 { + regulator-name = "VDD_MIF_1.2V"; + regulator-min-microvolt = <950000>; + regulator-max-microvolt = <1350000>; + regulator-always-on; + regulator-boot-on; + }; + + vemmc_reg: BUCK9 { + regulator-name = "VMEM_VDD_2.8V"; + regulator-min-microvolt = <2800000>; + regulator-max-microvolt = <2800000>; + op_mode = <3>; /* Standby Mode */ + s5m8767,pmic-ext-control-gpios = <&gpk0 2 0>; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/serial/8250.txt b/Documentation/devicetree/bindings/serial/8250.txt index 91d5ab0e60fc..936ab5b87324 100644 --- a/Documentation/devicetree/bindings/serial/8250.txt +++ b/Documentation/devicetree/bindings/serial/8250.txt @@ -14,7 +14,6 @@ Required properties: tegra132, or tegra210. - "nxp,lpc3220-uart" - "ralink,rt2880-uart" - - "ibm,qpace-nwp-serial" - "altr,16550-FIFO32" - "altr,16550-FIFO64" - "altr,16550-FIFO128" diff --git a/Documentation/devicetree/bindings/soc/qcom/qcom,smd-rpm.txt b/Documentation/devicetree/bindings/soc/qcom/qcom,smd-rpm.txt new file mode 100644 index 000000000000..a48049ccf6d0 --- /dev/null +++ b/Documentation/devicetree/bindings/soc/qcom/qcom,smd-rpm.txt @@ -0,0 +1,58 @@ +Qualcomm Resource Power Manager (RPM) over SMD + +This driver is used to interface with the Resource Power Manager (RPM) found in +various Qualcomm platforms. The RPM allows each component in the system to vote +for state of the system resources, such as clocks, regulators and bus +frequencies. + +The SMD information for the RPM edge should be filled out. See qcom,smd.txt for +the required edge properties. All SMD related properties will reside within the +RPM node itself. + += SUBDEVICES + +The RPM exposes resources to its subnodes. The rpm_requests node must be +present and this subnode may contain children that designate regulator +resources. + +- compatible: + Usage: required + Value type: <string> + Definition: must be one of: + "qcom,rpm-apq8084" + "qcom,rpm-msm8916" + "qcom,rpm-msm8974" + +- qcom,smd-channels: + Usage: required + Value type: <string> + Definition: must be "rpm_requests" + +Refer to Documentation/devicetree/bindings/regulator/qcom,smd-rpm-regulator.txt +for information on the regulator subnodes that can exist under the rpm_requests. + +Example: + + soc { + apcs: syscon@f9011000 { + compatible = "syscon"; + reg = <0xf9011000 0x1000>; + }; + }; + + smd { + compatible = "qcom,smd"; + + rpm { + interrupts = <0 168 1>; + qcom,ipc = <&apcs 8 0>; + qcom,smd-edge = <15>; + + rpm_requests { + compatible = "qcom,rpm-msm8974"; + qcom,smd-channels = "rpm_requests"; + + ... + }; + }; + }; diff --git a/Documentation/devicetree/bindings/sound/atmel-classd.txt b/Documentation/devicetree/bindings/sound/atmel-classd.txt index 0018451c4351..549e701cb7a1 100644 --- a/Documentation/devicetree/bindings/sound/atmel-classd.txt +++ b/Documentation/devicetree/bindings/sound/atmel-classd.txt @@ -16,6 +16,10 @@ Required properties: Required elements: "pclk", "gclk" and "aclk". - clocks Please refer to clock-bindings.txt. +- assigned-clocks + Should be <&classd_gclk>. +- assigned-clock-parents + Should be <&audio_pll_pmc>. Optional properties: - pinctrl-names, pinctrl-0 @@ -43,6 +47,8 @@ classd: classd@fc048000 { dma-names = "tx"; clocks = <&classd_clk>, <&classd_gclk>, <&audio_pll_pmc>; clock-names = "pclk", "gclk", "aclk"; + assigned-clocks = <&classd_gclk>; + assigned-clock-parents = <&audio_pll_pmc>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_classd_default>; diff --git a/Documentation/devicetree/bindings/sound/wm8994.txt b/Documentation/devicetree/bindings/sound/wm8994.txt index e045e90a0924..68c4e8d96bed 100644 --- a/Documentation/devicetree/bindings/sound/wm8994.txt +++ b/Documentation/devicetree/bindings/sound/wm8994.txt @@ -30,7 +30,7 @@ Optional properties: - #interrupt-cells: the number of cells to describe an IRQ, this should be 2. The first cell is the IRQ number. The second cell is the flags, encoded as the trigger masks from - Documentation/devicetree/bindings/interrupts.txt + Documentation/devicetree/bindings/interrupt-controller/interrupts.txt - clocks : A list of up to two phandle and clock specifier pairs - clock-names : A list of clock names sorted in the same order as clocks. diff --git a/Documentation/devicetree/bindings/arm/rockchip/pmu-sram.txt b/Documentation/devicetree/bindings/sram/rockchip-pmu-sram.txt index 6b42fda306ff..6b42fda306ff 100644 --- a/Documentation/devicetree/bindings/arm/rockchip/pmu-sram.txt +++ b/Documentation/devicetree/bindings/sram/rockchip-pmu-sram.txt diff --git a/Documentation/devicetree/bindings/arm/rockchip/smp-sram.txt b/Documentation/devicetree/bindings/sram/rockchip-smp-sram.txt index d9416fb8db6f..800701ecffca 100644 --- a/Documentation/devicetree/bindings/arm/rockchip/smp-sram.txt +++ b/Documentation/devicetree/bindings/sram/rockchip-smp-sram.txt @@ -12,7 +12,7 @@ Required sub-node properties: - compatible : should be "rockchip,rk3066-smp-sram" The rest of the properties should follow the generic mmio-sram discription -found in ../../misc/sram.txt +found in Documentation/devicetree/bindings/sram/sram.txt Example: diff --git a/Documentation/devicetree/bindings/arm/exynos/smp-sysram.txt b/Documentation/devicetree/bindings/sram/samsung-sram.txt index 4a0a4f70a0ce..6bc474b2b885 100644 --- a/Documentation/devicetree/bindings/arm/exynos/smp-sysram.txt +++ b/Documentation/devicetree/bindings/sram/samsung-sram.txt @@ -15,7 +15,7 @@ Required sub-node properties: "samsung,exynos4210-sysram-ns" : for Non-secure SYSRAM The rest of the properties should follow the generic mmio-sram discription -found in ../../misc/sysram.txt +found in Documentation/devicetree/bindings/sram/sram.txt Example: diff --git a/Documentation/devicetree/bindings/misc/sram.txt b/Documentation/devicetree/bindings/sram/sram.txt index 42ee9438b771..42ee9438b771 100644 --- a/Documentation/devicetree/bindings/misc/sram.txt +++ b/Documentation/devicetree/bindings/sram/sram.txt diff --git a/Documentation/devicetree/bindings/soc/sunxi/sram.txt b/Documentation/devicetree/bindings/sram/sunxi-sram.txt index 067698112f5f..8d5665468fe7 100644 --- a/Documentation/devicetree/bindings/soc/sunxi/sram.txt +++ b/Documentation/devicetree/bindings/sram/sunxi-sram.txt @@ -16,7 +16,7 @@ SRAM nodes ---------- Each SRAM is described using the mmio-sram bindings documented in -Documentation/devicetree/bindings/misc/sram.txt +Documentation/devicetree/bindings/sram/sram.txt Each SRAM will have SRAM sections that are going to be handled by the SRAM controller as subnodes. These sections are represented following diff --git a/Documentation/devicetree/bindings/thermal/qoriq-thermal.txt b/Documentation/devicetree/bindings/thermal/qoriq-thermal.txt new file mode 100644 index 000000000000..66223d561972 --- /dev/null +++ b/Documentation/devicetree/bindings/thermal/qoriq-thermal.txt @@ -0,0 +1,63 @@ +* Thermal Monitoring Unit (TMU) on Freescale QorIQ SoCs + +Required properties: +- compatible : Must include "fsl,qoriq-tmu". The version of the device is + determined by the TMU IP Block Revision Register (IPBRR0) at + offset 0x0BF8. + Table of correspondences between IPBRR0 values and example chips: + Value Device + ---------- ----- + 0x01900102 T1040 +- reg : Address range of TMU registers. +- interrupts : Contains the interrupt for TMU. +- fsl,tmu-range : The values to be programmed into TTRnCR, as specified by + the SoC reference manual. The first cell is TTR0CR, the second is + TTR1CR, etc. +- fsl,tmu-calibration : A list of cell pairs containing temperature + calibration data, as specified by the SoC reference manual. + The first cell of each pair is the value to be written to TTCFGR, + and the second is the value to be written to TSCFGR. + +Example: + +tmu@f0000 { + compatible = "fsl,qoriq-tmu"; + reg = <0xf0000 0x1000>; + interrupts = <18 2 0 0>; + fsl,tmu-range = <0x000a0000 0x00090026 0x0008004a 0x0001006a>; + fsl,tmu-calibration = <0x00000000 0x00000025 + 0x00000001 0x00000028 + 0x00000002 0x0000002d + 0x00000003 0x00000031 + 0x00000004 0x00000036 + 0x00000005 0x0000003a + 0x00000006 0x00000040 + 0x00000007 0x00000044 + 0x00000008 0x0000004a + 0x00000009 0x0000004f + 0x0000000a 0x00000054 + + 0x00010000 0x0000000d + 0x00010001 0x00000013 + 0x00010002 0x00000019 + 0x00010003 0x0000001f + 0x00010004 0x00000025 + 0x00010005 0x0000002d + 0x00010006 0x00000033 + 0x00010007 0x00000043 + 0x00010008 0x0000004b + 0x00010009 0x00000053 + + 0x00020000 0x00000010 + 0x00020001 0x00000017 + 0x00020002 0x0000001f + 0x00020003 0x00000029 + 0x00020004 0x00000031 + 0x00020005 0x0000003c + 0x00020006 0x00000042 + 0x00020007 0x0000004d + 0x00020008 0x00000056 + + 0x00030000 0x00000012 + 0x00030001 0x0000001d>; +}; diff --git a/Documentation/devicetree/bindings/usb/octeon-usb.txt b/Documentation/devicetree/bindings/usb/octeon-usb.txt new file mode 100644 index 000000000000..205c8d24d6e3 --- /dev/null +++ b/Documentation/devicetree/bindings/usb/octeon-usb.txt @@ -0,0 +1,62 @@ +OCTEON/OCTEON+ USB BLOCK + +1) Main node + + Required properties: + + - compatible: must be "cavium,octeon-5750-usbn" + + - reg: specifies the physical base address of the USBN block and + the length of the memory mapped region. + + - #address-cells: specifies the number of cells needed to encode an + address. The value must be 2. + + - #size-cells: specifies the number of cells used to represent the size + of an address. The value must be 2. + + - ranges: specifies the translation between child address space and parent + address space. + + - clock-frequency: speed of the USB reference clock. Allowed values are + 12000000, 24000000 or 48000000. + + - cavium,refclk-type: type of the USB reference clock. Allowed values are + "crystal" or "external". + + - refclk-frequency: deprecated, use "clock-frequency". + + - refclk-type: deprecated, use "cavium,refclk-type". + +2) Child node + + The main node must have one child node which describes the built-in + USB controller. + + Required properties: + + - compatible: must be "cavium,octeon-5750-usbc" + + - reg: specifies the physical base address of the USBC block and + the length of the memory mapped region. + + - interrupts: specifies the interrupt number for the USB controller. + +3) Example: + + usbn: usbn@1180068000000 { + compatible = "cavium,octeon-5750-usbn"; + reg = <0x11800 0x68000000 0x0 0x1000>; + ranges; /* Direct mapping */ + #address-cells = <2>; + #size-cells = <2>; + clock-frequency = <12000000>; + cavium,refclk-type = "crystal"; + + usbc@16f0010000000 { + compatible = "cavium,octeon-5750-usbc"; + reg = <0x16f00 0x10000000 0x0 0x80000>; + interrupts = <0 56>; + }; + }; + diff --git a/Documentation/devicetree/bindings/usb/usb3503.txt b/Documentation/devicetree/bindings/usb/usb3503.txt index 52493b1480e2..c1a0a9191d26 100644 --- a/Documentation/devicetree/bindings/usb/usb3503.txt +++ b/Documentation/devicetree/bindings/usb/usb3503.txt @@ -18,7 +18,8 @@ Optional properties: - refclk: Clock used for driving REFCLK signal (optional, if not provided the driver assumes that clock signal is always available, its rate is specified by REF_SEL pins and a value from the primary - reference clock frequencies table is used) + reference clock frequencies table is used). Use clocks and + clock-names in order to assign it - refclk-frequency: Frequency of the REFCLK signal as defined by REF_SEL pins (optional, if not provided, driver will not set rate of the REFCLK signal and assume that a value from the primary reference @@ -33,4 +34,6 @@ Examples: intn-gpios = <&gpx3 4 1>; reset-gpios = <&gpx3 5 1>; initial-mode = <1>; + clocks = <&clks 80>; + clock-names = "refclk"; }; diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt index 55df1d444e9f..a4f2035569ce 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.txt +++ b/Documentation/devicetree/bindings/vendor-prefixes.txt @@ -161,6 +161,7 @@ nuvoton Nuvoton Technology Corporation nvidia NVIDIA nxp NXP Semiconductors okaya Okaya Electric America, Inc. +olimex OLIMEX Ltd. onnn ON Semiconductor Corp. opencores OpenCores.org option Option NV diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting index 0f88e6020487..f1b87d8aa2da 100644 --- a/Documentation/filesystems/porting +++ b/Documentation/filesystems/porting @@ -508,7 +508,11 @@ in your dentry operations instead. [mandatory] any symlink that might use page_follow_link_light/page_put_link() must have inode_nohighmem(inode) called before anything might start playing with - its pagecache. + its pagecache. No highmem pages should end up in the pagecache of such + symlinks. That includes any preseeding that might be done during symlink + creation. __page_symlink() will honour the mapping gfp flags, so once + you've done inode_nohighmem() it's safe to use, but if you allocate and + insert the page manually, make sure to use the right gfp flags. -- [mandatory] ->follow_link() is replaced with ->get_link(); same API, except that diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index 402ab99e409f..e95aa1c6eadf 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -169,6 +169,9 @@ read the file /proc/PID/status: VmLck: 0 kB VmHWM: 476 kB VmRSS: 476 kB + RssAnon: 352 kB + RssFile: 120 kB + RssShmem: 4 kB VmData: 156 kB VmStk: 88 kB VmExe: 68 kB @@ -231,14 +234,20 @@ Table 1-2: Contents of the status files (as of 4.1) VmSize total program size VmLck locked memory size VmHWM peak resident set size ("high water mark") - VmRSS size of memory portions + VmRSS size of memory portions. It contains the three + following parts (VmRSS = RssAnon + RssFile + RssShmem) + RssAnon size of resident anonymous memory + RssFile size of resident file mappings + RssShmem size of resident shmem memory (includes SysV shm, + mapping of tmpfs and shared anonymous mappings) VmData size of data, stack, and text segments VmStk size of data, stack, and text segments VmExe size of text segment VmLib size of shared library code VmPTE size of page table entries VmPMD size of second level page tables - VmSwap size of swap usage (the number of referred swapents) + VmSwap amount of swap used by anonymous private data + (shmem swap usage is not included) HugetlbPages size of hugetlb memory portions Threads number of threads SigQ number of signals queued/max. number for queue @@ -265,7 +274,8 @@ Table 1-3: Contents of the statm files (as of 2.6.8-rc3) Field Content size total program size (pages) (same as VmSize in status) resident size of memory portions (pages) (same as VmRSS in status) - shared number of pages that are shared (i.e. backed by a file) + shared number of pages that are shared (i.e. backed by a file, same + as RssFile+RssShmem in status) trs number of pages that are 'code' (not including libs; broken, includes data segment) lrs number of pages of library (always 0 on 2.6) @@ -459,7 +469,10 @@ and a page is modified, the file page is replaced by a private anonymous copy. hugetlbfs page which is *not* counted in "RSS" or "PSS" field for historical reasons. And these are not included in {Shared,Private}_{Clean,Dirty} field. "Swap" shows how much would-be-anonymous memory is also used, but out on swap. -"SwapPss" shows proportional swap share of this mapping. +For shmem mappings, "Swap" includes also the size of the mapped (and not +replaced by copy-on-write) part of the underlying shmem object out on swap. +"SwapPss" shows proportional swap share of this mapping. Unlike "Swap", this +does not take into account swapped out page of underlying shmem objects. "Locked" indicates whether the mapping is locked in memory or not. "VmFlags" field deserves a separate description. This member represents the kernel @@ -842,6 +855,7 @@ Dirty: 968 kB Writeback: 0 kB AnonPages: 861800 kB Mapped: 280372 kB +Shmem: 644 kB Slab: 284364 kB SReclaimable: 159856 kB SUnreclaim: 124508 kB @@ -898,6 +912,7 @@ MemAvailable: An estimate of how much memory is available for starting new AnonPages: Non-file backed pages mapped into userspace page tables AnonHugePages: Non-file backed huge pages mapped into userspace page tables Mapped: files which have been mmaped, such as libraries + Shmem: Total memory used by shared memory (shmem) and tmpfs Slab: in-kernel data structures cache SReclaimable: Part of Slab, that might be reclaimed, such as caches SUnreclaim: Part of Slab, that cannot be reclaimed on memory pressure diff --git a/Documentation/filesystems/tmpfs.txt b/Documentation/filesystems/tmpfs.txt index 98ef55124158..d392e1505f17 100644 --- a/Documentation/filesystems/tmpfs.txt +++ b/Documentation/filesystems/tmpfs.txt @@ -17,10 +17,10 @@ RAM, where you have to create an ordinary filesystem on top. Ramdisks cannot swap and you do not have the possibility to resize them. Since tmpfs lives completely in the page cache and on swap, all tmpfs -pages currently in memory will show up as cached. It will not show up -as shared or something like that. Further on you can check the actual -RAM+swap use of a tmpfs instance with df(1) and du(1). - +pages will be shown as "Shmem" in /proc/meminfo and "Shared" in +free(1). Notice that these counters also include shared memory +(shmem, see ipcs(1)). The most reliable way to get the count is +using df(1) and du(1). tmpfs has the following uses: diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index b7d44871effc..5a6235ed3663 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -608,6 +608,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted. cut the overhead, others just disable the usage. So only cgroup_disable=memory is actually worthy} + cgroup.memory= [KNL] Pass options to the cgroup memory controller. + Format: <string> + nosocket -- Disable socket memory accounting. + checkreqprot [SELINUX] Set initial checkreqprot flag value. Format: { "0" | "1" } See security/selinux/Kconfig help text. @@ -2989,6 +2993,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted. may be specified. Format: <port>,<port>.... + ppc_strict_facility_enable + [PPC] This option catches any kernel floating point, + Altivec, VSX and SPE outside of regions specifically + allowed (eg kernel_enable_fpu()/kernel_disable_fpu()). + There is some performance impact when enabling this. + print-fatal-signals= [KNL] debug: print fatal signals diff --git a/Documentation/md-cluster.txt b/Documentation/md-cluster.txt index 1b794369e03a..c100c7163507 100644 --- a/Documentation/md-cluster.txt +++ b/Documentation/md-cluster.txt @@ -3,7 +3,7 @@ The cluster MD is a shared-device RAID for a cluster. 1. On-disk format -Separate write-intent-bitmap are used for each cluster node. +Separate write-intent-bitmaps are used for each cluster node. The bitmaps record all writes that may have been started on that node, and may not yet have finished. The on-disk layout is: @@ -14,117 +14,161 @@ and may not yet have finished. The on-disk layout is: | bm super[2] + bits | bm bits [2, contd] | bm super[3] + bits | | bm bits [3, contd] | | | -During "normal" functioning we assume the filesystem ensures that only one -node writes to any given block at a time, so a write -request will +During "normal" functioning we assume the filesystem ensures that only +one node writes to any given block at a time, so a write request will + - set the appropriate bit (if not already set) - commit the write to all mirrors - schedule the bit to be cleared after a timeout. -Reads are just handled normally. It is up to the filesystem to -ensure one node doesn't read from a location where another node (or the same +Reads are just handled normally. It is up to the filesystem to ensure +one node doesn't read from a location where another node (or the same node) is writing. 2. DLM Locks for management -There are two locks for managing the device: +There are three groups of locks for managing the device: 2.1 Bitmap lock resource (bm_lockres) - The bm_lockres protects individual node bitmaps. They are named in the - form bitmap001 for node 1, bitmap002 for node and so on. When a node - joins the cluster, it acquires the lock in PW mode and it stays so - during the lifetime the node is part of the cluster. The lock resource - number is based on the slot number returned by the DLM subsystem. Since - DLM starts node count from one and bitmap slots start from zero, one is - subtracted from the DLM slot number to arrive at the bitmap slot number. + The bm_lockres protects individual node bitmaps. They are named in + the form bitmap000 for node 1, bitmap001 for node 2 and so on. When a + node joins the cluster, it acquires the lock in PW mode and it stays + so during the lifetime the node is part of the cluster. The lock + resource number is based on the slot number returned by the DLM + subsystem. Since DLM starts node count from one and bitmap slots + start from zero, one is subtracted from the DLM slot number to arrive + at the bitmap slot number. + + The LVB of the bitmap lock for a particular node records the range + of sectors that are being re-synced by that node. No other + node may write to those sectors. This is used when a new nodes + joins the cluster. + +2.2 Message passing locks + + Each node has to communicate with other nodes when starting or ending + resync, and for metadata superblock updates. This communication is + managed through three locks: "token", "message", and "ack", together + with the Lock Value Block (LVB) of one of the "message" lock. + +2.3 new-device management + + A single lock: "no-new-dev" is used to co-ordinate the addition of + new devices - this must be synchronized across the array. + Normally all nodes hold a concurrent-read lock on this device. 3. Communication -Each node has to communicate with other nodes when starting or ending -resync, and metadata superblock updates. + Messages can be broadcast to all nodes, and the sender waits for all + other nodes to acknowledge the message before proceeding. Only one + message can be processed at a time. 3.1 Message Types - There are 3 types, of messages which are passed + There are six types of messages which are passed: - 3.1.1 METADATA_UPDATED: informs other nodes that the metadata has been - updated, and the node must re-read the md superblock. This is performed - synchronously. + 3.1.1 METADATA_UPDATED: informs other nodes that the metadata has + been updated, and the node must re-read the md superblock. This is + performed synchronously. It is primarily used to signal device + failure. - 3.1.2 RESYNC: informs other nodes that a resync is initiated or ended - so that each node may suspend or resume the region. + 3.1.2 RESYNCING: informs other nodes that a resync is initiated or + ended so that each node may suspend or resume the region. Each + RESYNCING message identifies a range of the devices that the + sending node is about to resync. This over-rides any pervious + notification from that node: only one ranged can be resynced at a + time per-node. + + 3.1.3 NEWDISK: informs other nodes that a device is being added to + the array. Message contains an identifier for that device. See + below for further details. + + 3.1.4 REMOVE: A failed or spare device is being removed from the + array. The slot-number of the device is included in the message. + + 3.1.5 RE_ADD: A failed device is being re-activated - the assumption + is that it has been determined to be working again. + + 3.1.6 BITMAP_NEEDS_SYNC: if a node is stopped locally but the bitmap + isn't clean, then another node is informed to take the ownership of + resync. 3.2 Communication mechanism The DLM LVB is used to communicate within nodes of the cluster. There are three resources used for the purpose: - 3.2.1 Token: The resource which protects the entire communication + 3.2.1 token: The resource which protects the entire communication system. The node having the token resource is allowed to communicate. - 3.2.2 Message: The lock resource which carries the data to + 3.2.2 message: The lock resource which carries the data to communicate. - 3.2.3 Ack: The resource, acquiring which means the message has been + 3.2.3 ack: The resource, acquiring which means the message has been acknowledged by all nodes in the cluster. The BAST of the resource - is used to inform the receive node that a node wants to communicate. + is used to inform the receiving node that a node wants to + communicate. The algorithm is: - 1. receive status + 1. receive status - all nodes have concurrent-reader lock on "ack". - sender receiver receiver - ACK:CR ACK:CR ACK:CR + sender receiver receiver + "ack":CR "ack":CR "ack":CR - 2. sender get EX of TOKEN - sender get EX of MESSAGE + 2. sender get EX on "token" + sender get EX on "message" sender receiver receiver - TOKEN:EX ACK:CR ACK:CR - MESSAGE:EX - ACK:CR + "token":EX "ack":CR "ack":CR + "message":EX + "ack":CR - Sender checks that it still needs to send a message. Messages received - or other events that happened while waiting for the TOKEN may have made - this message inappropriate or redundant. + Sender checks that it still needs to send a message. Messages + received or other events that happened while waiting for the + "token" may have made this message inappropriate or redundant. - 3. sender write LVB. - sender down-convert MESSAGE from EX to CW - sender try to get EX of ACK - [ wait until all receiver has *processed* the MESSAGE ] + 3. sender writes LVB. + sender down-convert "message" from EX to CW + sender try to get EX of "ack" + [ wait until all receivers have *processed* the "message" ] - [ triggered by bast of ACK ] - receiver get CR of MESSAGE + [ triggered by bast of "ack" ] + receiver get CR on "message" receiver read LVB receiver processes the message [ wait finish ] - receiver release ACK - - sender receiver receiver - TOKEN:EX MESSAGE:CR MESSAGE:CR - MESSAGE:CR - ACK:EX - - 4. triggered by grant of EX on ACK (indicating all receivers have processed - message) - sender down-convert ACK from EX to CR - sender release MESSAGE - sender release TOKEN - receiver upconvert to PR of MESSAGE - receiver get CR of ACK - receiver release MESSAGE + receiver releases "ack" + receiver tries to get PR on "message" + + sender receiver receiver + "token":EX "message":CR "message":CR + "message":CW + "ack":EX + + 4. triggered by grant of EX on "ack" (indicating all receivers + have processed message) + sender down-converts "ack" from EX to CR + sender releases "message" + sender releases "token" + receiver upconvert to PR on "message" + receiver get CR of "ack" + receiver release "message" sender receiver receiver - ACK:CR ACK:CR ACK:CR + "ack":CR "ack":CR "ack":CR 4. Handling Failures 4.1 Node Failure - When a node fails, the DLM informs the cluster with the slot. The node - starts a cluster recovery thread. The cluster recovery thread: + + When a node fails, the DLM informs the cluster with the slot + number. The node starts a cluster recovery thread. The cluster + recovery thread: + - acquires the bitmap<number> lock of the failed node - opens the bitmap - reads the bitmap of the failed node @@ -132,45 +176,143 @@ The algorithm is: - cleans the bitmap of the failed node - releases bitmap<number> lock of the failed node - initiates resync of the bitmap on the current node + md_check_recovery is invoked within recover_bitmaps, + then md_check_recovery -> metadata_update_start/finish, + it will lock the communication by lock_comm. + Which means when one node is resyncing it blocks all + other nodes from writing anywhere on the array. - The resync process, is the regular md resync. However, in a clustered + The resync process is the regular md resync. However, in a clustered environment when a resync is performed, it needs to tell other nodes of the areas which are suspended. Before a resync starts, the node - send out RESYNC_START with the (lo,hi) range of the area which needs - to be suspended. Each node maintains a suspend_list, which contains - the list of ranges which are currently suspended. On receiving - RESYNC_START, the node adds the range to the suspend_list. Similarly, - when the node performing resync finishes, it send RESYNC_FINISHED - to other nodes and other nodes remove the corresponding entry from - the suspend_list. + send out RESYNCING with the (lo,hi) range of the area which needs to + be suspended. Each node maintains a suspend_list, which contains the + list of ranges which are currently suspended. On receiving RESYNCING, + the node adds the range to the suspend_list. Similarly, when the node + performing resync finishes, it sends RESYNCING with an empty range to + other nodes and other nodes remove the corresponding entry from the + suspend_list. - A helper function, should_suspend() can be used to check if a particular - I/O range should be suspended or not. + A helper function, ->area_resyncing() can be used to check if a + particular I/O range should be suspended or not. 4.2 Device Failure + Device failures are handled and communicated with the metadata update - routine. + routine. When a node detects a device failure it does not allow + any further writes to that device until the failure has been + acknowledged by all other nodes. 5. Adding a new Device -For adding a new device, it is necessary that all nodes "see" the new device -to be added. For this, the following algorithm is used: + + For adding a new device, it is necessary that all nodes "see" the new + device to be added. For this, the following algorithm is used: 1. Node 1 issues mdadm --manage /dev/mdX --add /dev/sdYY which issues - ioctl(ADD_NEW_DISC with disc.state set to MD_DISK_CLUSTER_ADD) - 2. Node 1 sends NEWDISK with uuid and slot number + ioctl(ADD_NEW_DISK with disc.state set to MD_DISK_CLUSTER_ADD) + 2. Node 1 sends a NEWDISK message with uuid and slot number 3. Other nodes issue kobject_uevent_env with uuid and slot number (Steps 4,5 could be a udev rule) 4. In userspace, the node searches for the disk, perhaps using blkid -t SUB_UUID="" - 5. Other nodes issue either of the following depending on whether the disk - was found: + 5. Other nodes issue either of the following depending on whether + the disk was found: ioctl(ADD_NEW_DISK with disc.state set to MD_DISK_CANDIDATE and - disc.number set to slot number) + disc.number set to slot number) ioctl(CLUSTERED_DISK_NACK) - 6. Other nodes drop lock on no-new-devs (CR) if device is found - 7. Node 1 attempts EX lock on no-new-devs - 8. If node 1 gets the lock, it sends METADATA_UPDATED after unmarking the disk - as SpareLocal - 9. If not (get no-new-dev lock), it fails the operation and sends METADATA_UPDATED - 10. Other nodes get the information whether a disk is added or not - by the following METADATA_UPDATED. + 6. Other nodes drop lock on "no-new-devs" (CR) if device is found + 7. Node 1 attempts EX lock on "no-new-dev" + 8. If node 1 gets the lock, it sends METADATA_UPDATED after + unmarking the disk as SpareLocal + 9. If not (get "no-new-dev" lock), it fails the operation and sends + METADATA_UPDATED. + 10. Other nodes get the information whether a disk is added or not + by the following METADATA_UPDATED. + +6. Module interface. + + There are 17 call-backs which the md core can make to the cluster + module. Understanding these can give a good overview of the whole + process. + +6.1 join(nodes) and leave() + + These are called when an array is started with a clustered bitmap, + and when the array is stopped. join() ensures the cluster is + available and initializes the various resources. + Only the first 'nodes' nodes in the cluster can use the array. + +6.2 slot_number() + + Reports the slot number advised by the cluster infrastructure. + Range is from 0 to nodes-1. + +6.3 resync_info_update() + + This updates the resync range that is stored in the bitmap lock. + The starting point is updated as the resync progresses. The + end point is always the end of the array. + It does *not* send a RESYNCING message. + +6.4 resync_start(), resync_finish() + + These are called when resync/recovery/reshape starts or stops. + They update the resyncing range in the bitmap lock and also + send a RESYNCING message. resync_start reports the whole + array as resyncing, resync_finish reports none of it. + + resync_finish() also sends a BITMAP_NEEDS_SYNC message which + allows some other node to take over. + +6.5 metadata_update_start(), metadata_update_finish(), + metadata_update_cancel(). + + metadata_update_start is used to get exclusive access to + the metadata. If a change is still needed once that access is + gained, metadata_update_finish() will send a METADATA_UPDATE + message to all other nodes, otherwise metadata_update_cancel() + can be used to release the lock. + +6.6 area_resyncing() + + This combines two elements of functionality. + + Firstly, it will check if any node is currently resyncing + anything in a given range of sectors. If any resync is found, + then the caller will avoid writing or read-balancing in that + range. + + Secondly, while node recovery is happening it reports that + all areas are resyncing for READ requests. This avoids races + between the cluster-filesystem and the cluster-RAID handling + a node failure. + +6.7 add_new_disk_start(), add_new_disk_finish(), new_disk_ack() + + These are used to manage the new-disk protocol described above. + When a new device is added, add_new_disk_start() is called before + it is bound to the array and, if that succeeds, add_new_disk_finish() + is called the device is fully added. + + When a device is added in acknowledgement to a previous + request, or when the device is declared "unavailable", + new_disk_ack() is called. + +6.8 remove_disk() + + This is called when a spare or failed device is removed from + the array. It causes a REMOVE message to be send to other nodes. + +6.9 gather_bitmaps() + + This sends a RE_ADD message to all other nodes and then + gathers bitmap information from all bitmaps. This combined + bitmap is then used to recovery the re-added device. + +6.10 lock_all_bitmaps() and unlock_all_bitmaps() + + These are called when change bitmap to none. If a node plans + to clear the cluster raid's bitmap, it need to make sure no other + nodes are using the raid which is achieved by lock all bitmap + locks within the cluster, and also those locks are unlocked + accordingly. diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index f72370b440b1..89a887c76629 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -42,6 +42,8 @@ Currently, these files are in /proc/sys/vm: - min_slab_ratio - min_unmapped_ratio - mmap_min_addr +- mmap_rnd_bits +- mmap_rnd_compat_bits - nr_hugepages - nr_overcommit_hugepages - nr_trim_pages (only if CONFIG_MMU=n) @@ -135,7 +137,7 @@ Contains, as a percentage of total available memory that contains free pages and reclaimable pages, the number of pages at which the background kernel flusher threads will start writing out dirty data. -The total avaiable memory is not equal to total system memory. +The total available memory is not equal to total system memory. ============================================================== @@ -170,7 +172,7 @@ Contains, as a percentage of total available memory that contains free pages and reclaimable pages, the number of pages at which a process which is generating disk writes will itself start writing out dirty data. -The total avaiable memory is not equal to total system memory. +The total available memory is not equal to total system memory. ============================================================== @@ -485,6 +487,33 @@ against future potential kernel bugs. ============================================================== +mmap_rnd_bits: + +This value can be used to select the number of bits to use to +determine the random offset to the base address of vma regions +resulting from mmap allocations on architectures which support +tuning address space randomization. This value will be bounded +by the architecture's minimum and maximum supported values. + +This value can be changed after boot using the +/proc/sys/vm/mmap_rnd_bits tunable + +============================================================== + +mmap_rnd_compat_bits: + +This value can be used to select the number of bits to use to +determine the random offset to the base address of vma regions +resulting from mmap allocations for applications run in +compatibility mode on architectures which support tuning address +space randomization. This value will be bounded by the +architecture's minimum and maximum supported values. + +This value can be changed after boot using the +/proc/sys/vm/mmap_rnd_compat_bits tunable + +============================================================== + nr_hugepages Change the minimum size of the hugepage pool. diff --git a/MAINTAINERS b/MAINTAINERS index a2956eb7ca95..04d62b1e8b17 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4490,8 +4490,9 @@ F: include/linux/fs_enet_pd.h FREESCALE QUICC ENGINE LIBRARY L: linuxppc-dev@lists.ozlabs.org S: Orphan -F: arch/powerpc/sysdev/qe_lib/ -F: arch/powerpc/include/asm/*qe.h +F: drivers/soc/fsl/qe/ +F: include/soc/fsl/*qe*.h +F: include/soc/fsl/*ucc*.h FREESCALE USB PERIPHERAL DRIVERS M: Li Yang <leoli@freescale.com> @@ -4984,6 +4985,7 @@ F: arch/*/include/asm/suspend*.h HID CORE LAYER M: Jiri Kosina <jikos@kernel.org> +R: Benjamin Tissoires <benjamin.tissoires@redhat.com> L: linux-input@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/jikos/hid.git S: Maintained @@ -6443,7 +6445,7 @@ S: Maintained F: arch/powerpc/platforms/8xx/ LINUX FOR POWERPC EMBEDDED PPC83XX AND PPC85XX -M: Scott Wood <scottwood@freescale.com> +M: Scott Wood <oss@buserror.net> M: Kumar Gala <galak@kernel.crashing.org> W: http://www.penguinppc.org/ L: linuxppc-dev@lists.ozlabs.org @@ -9285,8 +9287,10 @@ F: drivers/regulator/s5m*.c F: drivers/clk/clk-s2mps11.c F: drivers/rtc/rtc-s5m.c F: include/linux/mfd/samsung/ -F: Documentation/devicetree/bindings/regulator/s5m8767-regulator.txt -F: Documentation/devicetree/bindings/mfd/s2mp*.txt +F: Documentation/devicetree/bindings/mfd/samsung,sec-core.txt +F: Documentation/devicetree/bindings/regulator/samsung,s2m*.txt +F: Documentation/devicetree/bindings/regulator/samsung,s5m*.txt +F: Documentation/devicetree/bindings/clock/samsung,s2mps11.txt SAMSUNG S5P/EXYNOS4 SOC SERIES CAMERA SUBSYSTEM DRIVERS M: Kyungmin Park <kyungmin.park@samsung.com> @@ -9996,7 +10000,6 @@ S: Supported F: drivers/media/pci/solo6x10/ SOFTWARE RAID (Multiple Disks) SUPPORT -M: Neil Brown <neilb@suse.com> L: linux-raid@vger.kernel.org S: Supported F: drivers/md/ @@ -11160,6 +11163,7 @@ F: include/linux/usb/gadget* USB HID/HIDBP DRIVERS (USB KEYBOARDS, MICE, REMOTE CONTROLS, ...) M: Jiri Kosina <jikos@kernel.org> +R: Benjamin Tissoires <benjamin.tissoires@redhat.com> L: linux-usb@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/jikos/hid.git S: Maintained @@ -11743,6 +11747,7 @@ F: drivers/input/touchscreen/wm831x-ts.c F: drivers/input/touchscreen/wm97*.c F: drivers/mfd/arizona* F: drivers/mfd/wm*.c +F: drivers/mfd/cs47l24* F: drivers/power/wm83*.c F: drivers/rtc/rtc-wm83*.c F: drivers/regulator/wm8*.c @@ -11756,6 +11761,7 @@ F: include/linux/wm97xx.h F: include/sound/wm????.h F: sound/soc/codecs/arizona.? F: sound/soc/codecs/wm* +F: sound/soc/codecs/cs47l24* WORKQUEUE M: Tejun Heo <tj@kernel.org> diff --git a/arch/Kconfig b/arch/Kconfig index 4e949e58b192..ba1b626bca00 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -511,6 +511,74 @@ config ARCH_HAS_ELF_RANDOMIZE - arch_mmap_rnd() - arch_randomize_brk() +config HAVE_ARCH_MMAP_RND_BITS + bool + help + An arch should select this symbol if it supports setting a variable + number of bits for use in establishing the base address for mmap + allocations, has MMU enabled and provides values for both: + - ARCH_MMAP_RND_BITS_MIN + - ARCH_MMAP_RND_BITS_MAX + +config ARCH_MMAP_RND_BITS_MIN + int + +config ARCH_MMAP_RND_BITS_MAX + int + +config ARCH_MMAP_RND_BITS_DEFAULT + int + +config ARCH_MMAP_RND_BITS + int "Number of bits to use for ASLR of mmap base address" if EXPERT + range ARCH_MMAP_RND_BITS_MIN ARCH_MMAP_RND_BITS_MAX + default ARCH_MMAP_RND_BITS_DEFAULT if ARCH_MMAP_RND_BITS_DEFAULT + default ARCH_MMAP_RND_BITS_MIN + depends on HAVE_ARCH_MMAP_RND_BITS + help + This value can be used to select the number of bits to use to + determine the random offset to the base address of vma regions + resulting from mmap allocations. This value will be bounded + by the architecture's minimum and maximum supported values. + + This value can be changed after boot using the + /proc/sys/vm/mmap_rnd_bits tunable + +config HAVE_ARCH_MMAP_RND_COMPAT_BITS + bool + help + An arch should select this symbol if it supports running applications + in compatibility mode, supports setting a variable number of bits for + use in establishing the base address for mmap allocations, has MMU + enabled and provides values for both: + - ARCH_MMAP_RND_COMPAT_BITS_MIN + - ARCH_MMAP_RND_COMPAT_BITS_MAX + +config ARCH_MMAP_RND_COMPAT_BITS_MIN + int + +config ARCH_MMAP_RND_COMPAT_BITS_MAX + int + +config ARCH_MMAP_RND_COMPAT_BITS_DEFAULT + int + +config ARCH_MMAP_RND_COMPAT_BITS + int "Number of bits to use for ASLR of mmap base address for compatible applications" if EXPERT + range ARCH_MMAP_RND_COMPAT_BITS_MIN ARCH_MMAP_RND_COMPAT_BITS_MAX + default ARCH_MMAP_RND_COMPAT_BITS_DEFAULT if ARCH_MMAP_RND_COMPAT_BITS_DEFAULT + default ARCH_MMAP_RND_COMPAT_BITS_MIN + depends on HAVE_ARCH_MMAP_RND_COMPAT_BITS + help + This value can be used to select the number of bits to use to + determine the random offset to the base address of vma regions + resulting from mmap allocations for compatible applications This + value will be bounded by the architecture's minimum and maximum + supported values. + + This value can be changed after boot using the + /proc/sys/vm/mmap_rnd_compat_bits tunable + config HAVE_COPY_THREAD_TLS bool help diff --git a/arch/alpha/kernel/module.c b/arch/alpha/kernel/module.c index 2fd00b7077e4..936bc8f89a67 100644 --- a/arch/alpha/kernel/module.c +++ b/arch/alpha/kernel/module.c @@ -160,7 +160,7 @@ apply_relocate_add(Elf64_Shdr *sechdrs, const char *strtab, /* The small sections were sorted to the end of the segment. The following should definitely cover them. */ - gp = (u64)me->module_core + me->core_size - 0x8000; + gp = (u64)me->core_layout.base + me->core_layout.size - 0x8000; got = sechdrs[me->arch.gotsecindex].sh_addr; for (i = 0; i < n; i++) { diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c index 5eb707640e9c..0587bf121d11 100644 --- a/arch/arc/kernel/unwind.c +++ b/arch/arc/kernel/unwind.c @@ -385,8 +385,8 @@ void *unwind_add_table(struct module *module, const void *table_start, return NULL; init_unwind_table(table, module->name, - module->module_core, module->core_size, - module->module_init, module->init_size, + module->core_layout.base, module->core_layout.size, + module->init_layout.base, module->init_layout.size, table_start, table_size, NULL, 0); diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 84b1b21b08ae..4e489cc5c45e 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -37,6 +37,7 @@ config ARM select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6 select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU + select HAVE_ARCH_MMAP_RND_BITS if MMU select HAVE_ARCH_SECCOMP_FILTER if (AEABI && !OABI_COMPAT) select HAVE_ARCH_TRACEHOOK select HAVE_ARM_SMCCC if CPU_V7 @@ -311,6 +312,14 @@ config MMU Select if you want MMU-based virtualised addressing space support by paged memory management. If unsure, say 'Y'. +config ARCH_MMAP_RND_BITS_MIN + default 8 + +config ARCH_MMAP_RND_BITS_MAX + default 14 if PAGE_OFFSET=0x40000000 + default 15 if PAGE_OFFSET=0x80000000 + default 16 + # # The "ARM system type" choice list is ordered alphabetically by option # text. Please add new entries in the option alphabetic order. diff --git a/arch/arm/kernel/module-plts.c b/arch/arm/kernel/module-plts.c index 097e2e201b9f..0c7efc3446c0 100644 --- a/arch/arm/kernel/module-plts.c +++ b/arch/arm/kernel/module-plts.c @@ -32,7 +32,7 @@ struct plt_entries { static bool in_init(const struct module *mod, u32 addr) { - return addr - (u32)mod->module_init < mod->init_size; + return addr - (u32)mod->init_layout.base < mod->init_layout.size; } u32 get_module_plt(struct module *mod, unsigned long loc, Elf32_Addr val) diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c index 407dc786583a..4b4058db0781 100644 --- a/arch/arm/mm/mmap.c +++ b/arch/arm/mm/mmap.c @@ -173,8 +173,7 @@ unsigned long arch_mmap_rnd(void) { unsigned long rnd; - /* 8 bits of randomness in 20 address space bits */ - rnd = (unsigned long)get_random_int() % (1 << 8); + rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1); return rnd << PAGE_SHIFT; } diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 4d5b416e2e4b..6be3fa2310ee 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -52,6 +52,8 @@ config ARM64 select HAVE_ARCH_JUMP_LABEL select HAVE_ARCH_KASAN if SPARSEMEM_VMEMMAP && !(ARM64_16K_PAGES && ARM64_VA_BITS_48) select HAVE_ARCH_KGDB + select HAVE_ARCH_MMAP_RND_BITS + select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK select HAVE_BPF_JIT @@ -107,6 +109,33 @@ config ARCH_PHYS_ADDR_T_64BIT config MMU def_bool y +config ARCH_MMAP_RND_BITS_MIN + default 14 if ARM64_64K_PAGES + default 16 if ARM64_16K_PAGES + default 18 + +# max bits determined by the following formula: +# VA_BITS - PAGE_SHIFT - 3 +config ARCH_MMAP_RND_BITS_MAX + default 19 if ARM64_VA_BITS=36 + default 24 if ARM64_VA_BITS=39 + default 27 if ARM64_VA_BITS=42 + default 30 if ARM64_VA_BITS=47 + default 29 if ARM64_VA_BITS=48 && ARM64_64K_PAGES + default 31 if ARM64_VA_BITS=48 && ARM64_16K_PAGES + default 33 if ARM64_VA_BITS=48 + default 14 if ARM64_64K_PAGES + default 16 if ARM64_16K_PAGES + default 18 + +config ARCH_MMAP_RND_COMPAT_BITS_MIN + default 7 if ARM64_64K_PAGES + default 9 if ARM64_16K_PAGES + default 11 + +config ARCH_MMAP_RND_COMPAT_BITS_MAX + default 16 + config NO_IOPORT_MAP def_bool y if !PCI diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c index ed177475dd8c..4c893b5189dd 100644 --- a/arch/arm64/mm/mmap.c +++ b/arch/arm64/mm/mmap.c @@ -51,8 +51,12 @@ unsigned long arch_mmap_rnd(void) { unsigned long rnd; - rnd = (unsigned long)get_random_int() & STACK_RND_MASK; - +#ifdef CONFIG_COMPAT + if (test_thread_flag(TIF_32BIT)) + rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_compat_bits) - 1); + else +#endif + rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1); return rnd << PAGE_SHIFT; } diff --git a/arch/avr32/kernel/module.c b/arch/avr32/kernel/module.c index 164efa009e5b..2b4c54c04cb6 100644 --- a/arch/avr32/kernel/module.c +++ b/arch/avr32/kernel/module.c @@ -118,9 +118,9 @@ int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, * Increase core size to make room for GOT and set start * offset for GOT. */ - module->core_size = ALIGN(module->core_size, 4); - module->arch.got_offset = module->core_size; - module->core_size += module->arch.got_size; + module->core_layout.size = ALIGN(module->core_layout.size, 4); + module->arch.got_offset = module->core_layout.size; + module->core_layout.size += module->arch.got_size; return 0; @@ -177,7 +177,7 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, const char *strtab, if (!info->got_initialized) { Elf32_Addr *gotent; - gotent = (module->module_core + gotent = (module->core_layout.base + module->arch.got_offset + info->got_offset); *gotent = relocation; @@ -255,8 +255,8 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, const char *strtab, */ pr_debug("GOTPC: PC=0x%x, got_offset=0x%lx, core=0x%p\n", relocation, module->arch.got_offset, - module->module_core); - relocation -= ((unsigned long)module->module_core + module->core_layout.base); + relocation -= ((unsigned long)module->core_layout.base + module->arch.got_offset); *location = relocation; break; diff --git a/arch/ia64/kernel/module.c b/arch/ia64/kernel/module.c index b15933c31b2f..6ab0ae7d6535 100644 --- a/arch/ia64/kernel/module.c +++ b/arch/ia64/kernel/module.c @@ -486,13 +486,13 @@ module_frob_arch_sections (Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, char *secstrings, static inline int in_init (const struct module *mod, uint64_t addr) { - return addr - (uint64_t) mod->module_init < mod->init_size; + return addr - (uint64_t) mod->init_layout.base < mod->init_layout.size; } static inline int in_core (const struct module *mod, uint64_t addr) { - return addr - (uint64_t) mod->module_core < mod->core_size; + return addr - (uint64_t) mod->core_layout.base < mod->core_layout.size; } static inline int @@ -675,7 +675,7 @@ do_reloc (struct module *mod, uint8_t r_type, Elf64_Sym *sym, uint64_t addend, break; case RV_BDREL: - val -= (uint64_t) (in_init(mod, val) ? mod->module_init : mod->module_core); + val -= (uint64_t) (in_init(mod, val) ? mod->init_layout.base : mod->core_layout.base); break; case RV_LTV: @@ -810,15 +810,15 @@ apply_relocate_add (Elf64_Shdr *sechdrs, const char *strtab, unsigned int symind * addresses have been selected... */ uint64_t gp; - if (mod->core_size > MAX_LTOFF) + if (mod->core_layout.size > MAX_LTOFF) /* * This takes advantage of fact that SHF_ARCH_SMALL gets allocated * at the end of the module. */ - gp = mod->core_size - MAX_LTOFF / 2; + gp = mod->core_layout.size - MAX_LTOFF / 2; else - gp = mod->core_size / 2; - gp = (uint64_t) mod->module_core + ((gp + 7) & -8); + gp = mod->core_layout.size / 2; + gp = (uint64_t) mod->core_layout.base + ((gp + 7) & -8); mod->arch.gp = gp; DEBUGP("%s: placing gp at 0x%lx\n", __func__, gp); } diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index 60e02f7747ff..9cd607b06964 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -2332,8 +2332,7 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t */ insert_vm_struct(mm, vma); - vm_stat_account(vma->vm_mm, vma->vm_flags, vma->vm_file, - vma_pages(vma)); + vm_stat_account(vma->vm_mm, vma->vm_flags, vma_pages(vma)); up_write(&task->mm->mmap_sem); /* diff --git a/arch/m32r/kernel/setup.c b/arch/m32r/kernel/setup.c index 0392112a5d70..a5ecef7188ba 100644 --- a/arch/m32r/kernel/setup.c +++ b/arch/m32r/kernel/setup.c @@ -81,7 +81,10 @@ static struct resource code_resource = { }; unsigned long memory_start; +EXPORT_SYMBOL(memory_start); + unsigned long memory_end; +EXPORT_SYMBOL(memory_end); void __init setup_arch(char **); int get_cpuinfo(char *); diff --git a/arch/metag/kernel/module.c b/arch/metag/kernel/module.c index 986331cd0a52..bb8dfba9a763 100644 --- a/arch/metag/kernel/module.c +++ b/arch/metag/kernel/module.c @@ -176,8 +176,8 @@ static uint32_t do_plt_call(void *location, Elf32_Addr val, tramp[1] = 0xac000001 | ((val & 0x0000ffff) << 3); /* Init, or core PLT? */ - if (location >= mod->module_core - && location < mod->module_core + mod->core_size) + if (location >= mod->core_layout.base + && location < mod->core_layout.base + mod->core_layout.size) entry = (void *)sechdrs[mod->arch.core_plt_section].sh_addr; else entry = (void *)sechdrs[mod->arch.init_plt_section].sh_addr; diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c index 9067b651c7a2..544ea21bfef9 100644 --- a/arch/mips/kernel/vpe.c +++ b/arch/mips/kernel/vpe.c @@ -205,11 +205,11 @@ static void layout_sections(struct module *mod, const Elf_Ehdr *hdr, || s->sh_entsize != ~0UL) continue; s->sh_entsize = - get_offset((unsigned long *)&mod->core_size, s); + get_offset((unsigned long *)&mod->core_layout.size, s); } if (m == 0) - mod->core_text_size = mod->core_size; + mod->core_layout.text_size = mod->core_layout.size; } } @@ -641,7 +641,7 @@ static int vpe_elfload(struct vpe *v) layout_sections(&mod, hdr, sechdrs, secstrings); } - v->load_addr = alloc_progmem(mod.core_size); + v->load_addr = alloc_progmem(mod.core_layout.size); if (!v->load_addr) return -ENOMEM; diff --git a/arch/parisc/kernel/module.c b/arch/parisc/kernel/module.c index 3c63a820fcda..b9d75d9fa9ac 100644 --- a/arch/parisc/kernel/module.c +++ b/arch/parisc/kernel/module.c @@ -42,9 +42,9 @@ * We are not doing SEGREL32 handling correctly. According to the ABI, we * should do a value offset, like this: * if (in_init(me, (void *)val)) - * val -= (uint32_t)me->module_init; + * val -= (uint32_t)me->init_layout.base; * else - * val -= (uint32_t)me->module_core; + * val -= (uint32_t)me->core_layout.base; * However, SEGREL32 is used only for PARISC unwind entries, and we want * those entries to have an absolute address, and not just an offset. * @@ -100,14 +100,14 @@ * or init pieces the location is */ static inline int in_init(struct module *me, void *loc) { - return (loc >= me->module_init && - loc <= (me->module_init + me->init_size)); + return (loc >= me->init_layout.base && + loc <= (me->init_layout.base + me->init_layout.size)); } static inline int in_core(struct module *me, void *loc) { - return (loc >= me->module_core && - loc <= (me->module_core + me->core_size)); + return (loc >= me->core_layout.base && + loc <= (me->core_layout.base + me->core_layout.size)); } static inline int in_local(struct module *me, void *loc) @@ -367,13 +367,13 @@ int module_frob_arch_sections(CONST Elf_Ehdr *hdr, } /* align things a bit */ - me->core_size = ALIGN(me->core_size, 16); - me->arch.got_offset = me->core_size; - me->core_size += gots * sizeof(struct got_entry); + me->core_layout.size = ALIGN(me->core_layout.size, 16); + me->arch.got_offset = me->core_layout.size; + me->core_layout.size += gots * sizeof(struct got_entry); - me->core_size = ALIGN(me->core_size, 16); - me->arch.fdesc_offset = me->core_size; - me->core_size += fdescs * sizeof(Elf_Fdesc); + me->core_layout.size = ALIGN(me->core_layout.size, 16); + me->arch.fdesc_offset = me->core_layout.size; + me->core_layout.size += fdescs * sizeof(Elf_Fdesc); me->arch.got_max = gots; me->arch.fdesc_max = fdescs; @@ -391,7 +391,7 @@ static Elf64_Word get_got(struct module *me, unsigned long value, long addend) BUG_ON(value == 0); - got = me->module_core + me->arch.got_offset; + got = me->core_layout.base + me->arch.got_offset; for (i = 0; got[i].addr; i++) if (got[i].addr == value) goto out; @@ -409,7 +409,7 @@ static Elf64_Word get_got(struct module *me, unsigned long value, long addend) #ifdef CONFIG_64BIT static Elf_Addr get_fdesc(struct module *me, unsigned long value) { - Elf_Fdesc *fdesc = me->module_core + me->arch.fdesc_offset; + Elf_Fdesc *fdesc = me->core_layout.base + me->arch.fdesc_offset; if (!value) { printk(KERN_ERR "%s: zero OPD requested!\n", me->name); @@ -427,7 +427,7 @@ static Elf_Addr get_fdesc(struct module *me, unsigned long value) /* Create new one */ fdesc->addr = value; - fdesc->gp = (Elf_Addr)me->module_core + me->arch.got_offset; + fdesc->gp = (Elf_Addr)me->core_layout.base + me->arch.got_offset; return (Elf_Addr)fdesc; } #endif /* CONFIG_64BIT */ @@ -839,7 +839,7 @@ register_unwind_table(struct module *me, table = (unsigned char *)sechdrs[me->arch.unwind_section].sh_addr; end = table + sechdrs[me->arch.unwind_section].sh_size; - gp = (Elf_Addr)me->module_core + me->arch.got_offset; + gp = (Elf_Addr)me->core_layout.base + me->arch.got_offset; DEBUGP("register_unwind_table(), sect = %d at 0x%p - 0x%p (gp=0x%lx)\n", me->arch.unwind_section, table, end, gp); diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 85eabc49de61..7d5a8350f913 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -560,6 +560,7 @@ choice config PPC_4K_PAGES bool "4k page size" + select HAVE_ARCH_SOFT_DIRTY if CHECKPOINT_RESTORE && PPC_BOOK3S config PPC_16K_PAGES bool "16k page size" @@ -568,6 +569,7 @@ config PPC_16K_PAGES config PPC_64K_PAGES bool "64k page size" depends on !PPC_FSL_BOOK3E && (44x || PPC_STD_MMU_64 || PPC_BOOK3E_64) + select HAVE_ARCH_SOFT_DIRTY if CHECKPOINT_RESTORE && PPC_BOOK3S config PPC_256K_PAGES bool "256k page size" @@ -1075,8 +1077,6 @@ source "drivers/Kconfig" source "fs/Kconfig" -source "arch/powerpc/sysdev/qe_lib/Kconfig" - source "lib/Kconfig" source "arch/powerpc/Kconfig.debug" diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug index a0e44a9c456f..638f9ce740f5 100644 --- a/arch/powerpc/Kconfig.debug +++ b/arch/powerpc/Kconfig.debug @@ -64,17 +64,17 @@ config PPC_EMULATED_STATS emulated. config CODE_PATCHING_SELFTEST - bool "Run self-tests of the code-patching code." + bool "Run self-tests of the code-patching code" depends on DEBUG_KERNEL default n config FTR_FIXUP_SELFTEST - bool "Run self-tests of the feature-fixup code." + bool "Run self-tests of the feature-fixup code" depends on DEBUG_KERNEL default n config MSI_BITMAP_SELFTEST - bool "Run self-tests of the MSI bitmap code." + bool "Run self-tests of the MSI bitmap code" depends on DEBUG_KERNEL default n diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 99e4487248ff..61165101342c 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -113,7 +113,6 @@ src-plat-$(CONFIG_EPAPR_BOOT) += epapr.c epapr-wrapper.c src-plat-$(CONFIG_PPC_PSERIES) += pseries-head.S src-plat-$(CONFIG_PPC_POWERNV) += pseries-head.S src-plat-$(CONFIG_PPC_IBM_CELL_BLADE) += pseries-head.S -src-plat-$(CONFIG_PPC_CELL_QPACE) += pseries-head.S src-wlib := $(sort $(src-wlib-y)) src-plat := $(sort $(src-plat-y)) @@ -217,7 +216,6 @@ image-$(CONFIG_PPC_POWERNV) += zImage.pseries image-$(CONFIG_PPC_MAPLE) += zImage.maple image-$(CONFIG_PPC_IBM_CELL_BLADE) += zImage.pseries image-$(CONFIG_PPC_PS3) += dtbImage.ps3 -image-$(CONFIG_PPC_CELL_QPACE) += zImage.pseries image-$(CONFIG_PPC_CHRP) += zImage.chrp image-$(CONFIG_PPC_EFIKA) += zImage.chrp image-$(CONFIG_PPC_PMAC) += zImage.pmac diff --git a/arch/powerpc/boot/dts/fsl/b4si-post.dtsi b/arch/powerpc/boot/dts/fsl/b4si-post.dtsi index 74866ac52f39..1b33f5157c8a 100644 --- a/arch/powerpc/boot/dts/fsl/b4si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/b4si-post.dtsi @@ -474,6 +474,11 @@ fman@400000 { interrupts = <96 2 0 0>, <16 2 1 30>; + muram@0 { + compatible = "fsl,fman-muram"; + reg = <0x0 0x80000>; + }; + enet0: ethernet@e0000 { }; diff --git a/arch/powerpc/boot/dts/fsl/bsc9132qds.dts b/arch/powerpc/boot/dts/fsl/bsc9132qds.dts index 70882ade606d..56e6f1337e96 100644 --- a/arch/powerpc/boot/dts/fsl/bsc9132qds.dts +++ b/arch/powerpc/boot/dts/fsl/bsc9132qds.dts @@ -29,6 +29,21 @@ soc: soc@ff700000 { ranges = <0x0 0x0 0xff700000 0x100000>; }; + + pci0: pcie@ff70a000 { + reg = <0 0xff70a000 0 0x1000>; + ranges = <0x2000000 0x0 0x90000000 0 0x90000000 0x0 0x20000000 + 0x1000000 0x0 0x00000000 0 0xc0010000 0x0 0x10000>; + pcie@0 { + ranges = <0x2000000 0x0 0x90000000 + 0x2000000 0x0 0x90000000 + 0x0 0x20000000 + + 0x1000000 0x0 0x0 + 0x1000000 0x0 0x0 + 0x0 0x100000>; + }; + }; }; /include/ "bsc9132qds.dtsi" diff --git a/arch/powerpc/boot/dts/fsl/bsc9132si-post.dtsi b/arch/powerpc/boot/dts/fsl/bsc9132si-post.dtsi index c72307198140..b5f071574e83 100644 --- a/arch/powerpc/boot/dts/fsl/bsc9132si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/bsc9132si-post.dtsi @@ -40,6 +40,34 @@ interrupts = <16 2 0 0 20 2 0 0>; }; +/* controller at 0xa000 */ +&pci0 { + compatible = "fsl,bsc9132-pcie", "fsl,qoriq-pcie-v2.2"; + device_type = "pci"; + #size-cells = <2>; + #address-cells = <3>; + bus-range = <0 255>; + interrupts = <16 2 0 0>; + + pcie@0 { + reg = <0 0 0 0 0>; + #interrupt-cells = <1>; + #size-cells = <2>; + #address-cells = <3>; + device_type = "pci"; + interrupts = <16 2 0 0>; + interrupt-map-mask = <0xf800 0 0 7>; + + interrupt-map = < + /* IDSEL 0x0 */ + 0000 0x0 0x0 0x1 &mpic 0x0 0x2 0x0 0x0 + 0000 0x0 0x0 0x2 &mpic 0x1 0x2 0x0 0x0 + 0000 0x0 0x0 0x3 &mpic 0x2 0x2 0x0 0x0 + 0000 0x0 0x0 0x4 &mpic 0x3 0x2 0x0 0x0 + >; + }; +}; + &soc { #address-cells = <1>; #size-cells = <1>; diff --git a/arch/powerpc/boot/dts/fsl/bsc9132si-pre.dtsi b/arch/powerpc/boot/dts/fsl/bsc9132si-pre.dtsi index 301a9dba5790..90f7949fe312 100644 --- a/arch/powerpc/boot/dts/fsl/bsc9132si-pre.dtsi +++ b/arch/powerpc/boot/dts/fsl/bsc9132si-pre.dtsi @@ -45,6 +45,7 @@ serial0 = &serial0; ethernet0 = &enet0; ethernet1 = &enet1; + pci0 = &pci0; }; cpus { diff --git a/arch/powerpc/boot/dts/fsl/p1010rdb.dtsi b/arch/powerpc/boot/dts/fsl/p1010rdb.dtsi index 0f0ced69835a..14b629505038 100644 --- a/arch/powerpc/boot/dts/fsl/p1010rdb.dtsi +++ b/arch/powerpc/boot/dts/fsl/p1010rdb.dtsi @@ -215,3 +215,19 @@ phy-connection-type = "sgmii"; }; }; + +&pci0 { + pcie@0 { + interrupt-map = < + /* IDSEL 0x0 */ + /* + *irq[4:5] are active-high + *irq[6:7] are active-low + */ + 0000 0x0 0x0 0x1 &mpic 0x4 0x2 0x0 0x0 + 0000 0x0 0x0 0x2 &mpic 0x5 0x2 0x0 0x0 + 0000 0x0 0x0 0x3 &mpic 0x6 0x1 0x0 0x0 + 0000 0x0 0x0 0x4 &mpic 0x7 0x1 0x0 0x0 + >; + }; +}; diff --git a/arch/powerpc/boot/dts/fsl/t1023rdb.dts b/arch/powerpc/boot/dts/fsl/t1023rdb.dts index 2b2fff4a12a2..6bd842beb1dc 100644 --- a/arch/powerpc/boot/dts/fsl/t1023rdb.dts +++ b/arch/powerpc/boot/dts/fsl/t1023rdb.dts @@ -159,4 +159,4 @@ }; }; -/include/ "t1023si-post.dtsi" +#include "t1023si-post.dtsi" diff --git a/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi index 518ddaa8da2d..99e421df79d4 100644 --- a/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi @@ -32,6 +32,8 @@ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ +#include <dt-bindings/thermal/thermal.h> + &ifc { #address-cells = <2>; #size-cells = <1>; @@ -275,6 +277,90 @@ reg = <0xea000 0x4000>; }; + tmu: tmu@f0000 { + compatible = "fsl,qoriq-tmu"; + reg = <0xf0000 0x1000>; + interrupts = <18 2 0 0>; + fsl,tmu-range = <0xb0000 0xa0026 0x80048 0x30061>; + fsl,tmu-calibration = <0x00000000 0x0000000f + 0x00000001 0x00000017 + 0x00000002 0x0000001e + 0x00000003 0x00000026 + 0x00000004 0x0000002e + 0x00000005 0x00000035 + 0x00000006 0x0000003d + 0x00000007 0x00000044 + 0x00000008 0x0000004c + 0x00000009 0x00000053 + 0x0000000a 0x0000005b + 0x0000000b 0x00000064 + + 0x00010000 0x00000011 + 0x00010001 0x0000001c + 0x00010002 0x00000024 + 0x00010003 0x0000002b + 0x00010004 0x00000034 + 0x00010005 0x00000039 + 0x00010006 0x00000042 + 0x00010007 0x0000004c + 0x00010008 0x00000051 + 0x00010009 0x0000005a + 0x0001000a 0x00000063 + + 0x00020000 0x00000013 + 0x00020001 0x00000019 + 0x00020002 0x00000024 + 0x00020003 0x0000002c + 0x00020004 0x00000035 + 0x00020005 0x0000003d + 0x00020006 0x00000046 + 0x00020007 0x00000050 + 0x00020008 0x00000059 + + 0x00030000 0x00000002 + 0x00030001 0x0000000d + 0x00030002 0x00000019 + 0x00030003 0x00000024>; + #thermal-sensor-cells = <0>; + }; + + thermal-zones { + cpu_thermal: cpu-thermal { + polling-delay-passive = <1000>; + polling-delay = <5000>; + + thermal-sensors = <&tmu>; + + trips { + cpu_alert: cpu-alert { + temperature = <85000>; + hysteresis = <2000>; + type = "passive"; + }; + cpu_crit: cpu-crit { + temperature = <95000>; + hysteresis = <2000>; + type = "critical"; + }; + }; + + cooling-maps { + map0 { + trip = <&cpu_alert>; + cooling-device = + <&cpu0 THERMAL_NO_LIMIT + THERMAL_NO_LIMIT>; + }; + map1 { + trip = <&cpu_alert>; + cooling-device = + <&cpu1 THERMAL_NO_LIMIT + THERMAL_NO_LIMIT>; + }; + }; + }; + }; + scfg: global-utilities@fc000 { compatible = "fsl,t1023-scfg"; reg = <0xfc000 0x1000>; diff --git a/arch/powerpc/boot/dts/fsl/t1024qds.dts b/arch/powerpc/boot/dts/fsl/t1024qds.dts index 43cd5b50cd0a..6a3581b8e1f8 100644 --- a/arch/powerpc/boot/dts/fsl/t1024qds.dts +++ b/arch/powerpc/boot/dts/fsl/t1024qds.dts @@ -248,4 +248,4 @@ }; }; -/include/ "t1024si-post.dtsi" +#include "t1024si-post.dtsi" diff --git a/arch/powerpc/boot/dts/fsl/t1024rdb.dts b/arch/powerpc/boot/dts/fsl/t1024rdb.dts index 429d8c73650a..0ccc7d03335e 100644 --- a/arch/powerpc/boot/dts/fsl/t1024rdb.dts +++ b/arch/powerpc/boot/dts/fsl/t1024rdb.dts @@ -188,4 +188,4 @@ }; }; -/include/ "t1024si-post.dtsi" +#include "t1024si-post.dtsi" diff --git a/arch/powerpc/boot/dts/fsl/t1024si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1024si-post.dtsi index 95e3af8d768e..bb480346a58d 100644 --- a/arch/powerpc/boot/dts/fsl/t1024si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/t1024si-post.dtsi @@ -32,7 +32,7 @@ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ -/include/ "t1023si-post.dtsi" +#include "t1023si-post.dtsi" / { aliases { diff --git a/arch/powerpc/boot/dts/fsl/t102xsi-pre.dtsi b/arch/powerpc/boot/dts/fsl/t102xsi-pre.dtsi index 3e1528abf3f4..9d08a363bab3 100644 --- a/arch/powerpc/boot/dts/fsl/t102xsi-pre.dtsi +++ b/arch/powerpc/boot/dts/fsl/t102xsi-pre.dtsi @@ -76,6 +76,7 @@ reg = <0>; clocks = <&mux0>; next-level-cache = <&L2_1>; + #cooling-cells = <2>; L2_1: l2-cache { next-level-cache = <&cpc>; }; @@ -85,6 +86,7 @@ reg = <1>; clocks = <&mux1>; next-level-cache = <&L2_2>; + #cooling-cells = <2>; L2_2: l2-cache { next-level-cache = <&cpc>; }; diff --git a/arch/powerpc/boot/dts/fsl/t1040d4rdb.dts b/arch/powerpc/boot/dts/fsl/t1040d4rdb.dts index 681746efd31d..fb6bc02ebb60 100644 --- a/arch/powerpc/boot/dts/fsl/t1040d4rdb.dts +++ b/arch/powerpc/boot/dts/fsl/t1040d4rdb.dts @@ -43,4 +43,4 @@ interrupt-parent = <&mpic>; }; -/include/ "t1040si-post.dtsi" +#include "t1040si-post.dtsi" diff --git a/arch/powerpc/boot/dts/fsl/t1040qds.dts b/arch/powerpc/boot/dts/fsl/t1040qds.dts index 4d298659468c..5f76edc7838c 100644 --- a/arch/powerpc/boot/dts/fsl/t1040qds.dts +++ b/arch/powerpc/boot/dts/fsl/t1040qds.dts @@ -43,4 +43,4 @@ interrupt-parent = <&mpic>; }; -/include/ "t1040si-post.dtsi" +#include "t1040si-post.dtsi" diff --git a/arch/powerpc/boot/dts/fsl/t1040rdb.dts b/arch/powerpc/boot/dts/fsl/t1040rdb.dts index 8f9e65b47515..cf194154bbdc 100644 --- a/arch/powerpc/boot/dts/fsl/t1040rdb.dts +++ b/arch/powerpc/boot/dts/fsl/t1040rdb.dts @@ -45,4 +45,4 @@ }; }; -/include/ "t1040si-post.dtsi" +#include "t1040si-post.dtsi" diff --git a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi index d30b3de1cfc5..e0f4da554774 100644 --- a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi @@ -32,6 +32,8 @@ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ +#include <dt-bindings/thermal/thermal.h> + &bman_fbpr { compatible = "fsl,bman-fbpr"; alloc-ranges = <0 0 0x10000 0>; @@ -484,6 +486,98 @@ reg = <0xea000 0x4000>; }; + tmu: tmu@f0000 { + compatible = "fsl,qoriq-tmu"; + reg = <0xf0000 0x1000>; + interrupts = <18 2 0 0>; + fsl,tmu-range = <0xa0000 0x90026 0x8004a 0x1006a>; + fsl,tmu-calibration = <0x00000000 0x00000025 + 0x00000001 0x00000028 + 0x00000002 0x0000002d + 0x00000003 0x00000031 + 0x00000004 0x00000036 + 0x00000005 0x0000003a + 0x00000006 0x00000040 + 0x00000007 0x00000044 + 0x00000008 0x0000004a + 0x00000009 0x0000004f + 0x0000000a 0x00000054 + + 0x00010000 0x0000000d + 0x00010001 0x00000013 + 0x00010002 0x00000019 + 0x00010003 0x0000001f + 0x00010004 0x00000025 + 0x00010005 0x0000002d + 0x00010006 0x00000033 + 0x00010007 0x00000043 + 0x00010008 0x0000004b + 0x00010009 0x00000053 + + 0x00020000 0x00000010 + 0x00020001 0x00000017 + 0x00020002 0x0000001f + 0x00020003 0x00000029 + 0x00020004 0x00000031 + 0x00020005 0x0000003c + 0x00020006 0x00000042 + 0x00020007 0x0000004d + 0x00020008 0x00000056 + + 0x00030000 0x00000012 + 0x00030001 0x0000001d>; + #thermal-sensor-cells = <0>; + }; + + thermal-zones { + cpu_thermal: cpu-thermal { + polling-delay-passive = <1000>; + polling-delay = <5000>; + + thermal-sensors = <&tmu>; + + trips { + cpu_alert: cpu-alert { + temperature = <85000>; + hysteresis = <2000>; + type = "passive"; + }; + cpu_crit: cpu-crit { + temperature = <95000>; + hysteresis = <2000>; + type = "critical"; + }; + }; + + cooling-maps { + map0 { + trip = <&cpu_alert>; + cooling-device = + <&cpu0 THERMAL_NO_LIMIT + THERMAL_NO_LIMIT>; + }; + map1 { + trip = <&cpu_alert>; + cooling-device = + <&cpu1 THERMAL_NO_LIMIT + THERMAL_NO_LIMIT>; + }; + map2 { + trip = <&cpu_alert>; + cooling-device = + <&cpu2 THERMAL_NO_LIMIT + THERMAL_NO_LIMIT>; + }; + map3 { + trip = <&cpu_alert>; + cooling-device = + <&cpu3 THERMAL_NO_LIMIT + THERMAL_NO_LIMIT>; + }; + }; + }; + }; + scfg: global-utilities@fc000 { compatible = "fsl,t1040-scfg"; reg = <0xfc000 0x1000>; diff --git a/arch/powerpc/boot/dts/fsl/t1042d4rdb.dts b/arch/powerpc/boot/dts/fsl/t1042d4rdb.dts index b245b31b8279..2a5a90dd272e 100644 --- a/arch/powerpc/boot/dts/fsl/t1042d4rdb.dts +++ b/arch/powerpc/boot/dts/fsl/t1042d4rdb.dts @@ -50,4 +50,4 @@ }; }; -/include/ "t1040si-post.dtsi" +#include "t1042si-post.dtsi" diff --git a/arch/powerpc/boot/dts/fsl/t1042qds.dts b/arch/powerpc/boot/dts/fsl/t1042qds.dts index 4ab9bbe7c5c5..90a4a73bb905 100644 --- a/arch/powerpc/boot/dts/fsl/t1042qds.dts +++ b/arch/powerpc/boot/dts/fsl/t1042qds.dts @@ -43,4 +43,4 @@ interrupt-parent = <&mpic>; }; -/include/ "t1042si-post.dtsi" +#include "t1042si-post.dtsi" diff --git a/arch/powerpc/boot/dts/fsl/t1042rdb.dts b/arch/powerpc/boot/dts/fsl/t1042rdb.dts index 67af56bc5ee9..8d908e795e4d 100644 --- a/arch/powerpc/boot/dts/fsl/t1042rdb.dts +++ b/arch/powerpc/boot/dts/fsl/t1042rdb.dts @@ -45,4 +45,4 @@ }; }; -/include/ "t1042si-post.dtsi" +#include "t1042si-post.dtsi" diff --git a/arch/powerpc/boot/dts/fsl/t1042rdb_pi.dts b/arch/powerpc/boot/dts/fsl/t1042rdb_pi.dts index 2f67677530a4..98c001019d6a 100644 --- a/arch/powerpc/boot/dts/fsl/t1042rdb_pi.dts +++ b/arch/powerpc/boot/dts/fsl/t1042rdb_pi.dts @@ -54,4 +54,4 @@ }; }; -/include/ "t1042si-post.dtsi" +#include "t1042si-post.dtsi" diff --git a/arch/powerpc/boot/dts/fsl/t1042si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1042si-post.dtsi index 319b74f29724..a5544f93689c 100644 --- a/arch/powerpc/boot/dts/fsl/t1042si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/t1042si-post.dtsi @@ -32,6 +32,6 @@ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ -/include/ "t1040si-post.dtsi" +#include "t1040si-post.dtsi" /* Place holder for ethernet related device tree nodes */ diff --git a/arch/powerpc/boot/dts/fsl/t104xsi-pre.dtsi b/arch/powerpc/boot/dts/fsl/t104xsi-pre.dtsi index fcfa38ae5e02..6db0ee8b1384 100644 --- a/arch/powerpc/boot/dts/fsl/t104xsi-pre.dtsi +++ b/arch/powerpc/boot/dts/fsl/t104xsi-pre.dtsi @@ -76,6 +76,7 @@ reg = <0>; clocks = <&mux0>; next-level-cache = <&L2_1>; + #cooling-cells = <2>; L2_1: l2-cache { next-level-cache = <&cpc>; }; @@ -85,6 +86,7 @@ reg = <1>; clocks = <&mux1>; next-level-cache = <&L2_2>; + #cooling-cells = <2>; L2_2: l2-cache { next-level-cache = <&cpc>; }; @@ -94,6 +96,7 @@ reg = <2>; clocks = <&mux2>; next-level-cache = <&L2_3>; + #cooling-cells = <2>; L2_3: l2-cache { next-level-cache = <&cpc>; }; @@ -103,6 +106,7 @@ reg = <3>; clocks = <&mux3>; next-level-cache = <&L2_4>; + #cooling-cells = <2>; L2_4: l2-cache { next-level-cache = <&cpc>; }; diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper index ceaa75d5a684..6a19fcef5596 100755 --- a/arch/powerpc/boot/wrapper +++ b/arch/powerpc/boot/wrapper @@ -154,7 +154,7 @@ if [ -z "$kernel" ]; then kernel=vmlinux fi -elfformat="`${CROSS}objdump -p "$kernel" | grep 'file format' | awk '{print $4}'`" +LANG=C elfformat="`${CROSS}objdump -p "$kernel" | grep 'file format' | awk '{print $4}'`" case "$elfformat" in elf64-powerpcle) format=elf64lppc ;; elf64-powerpc) format=elf32ppc ;; diff --git a/arch/powerpc/configs/mpc85xx_basic_defconfig b/arch/powerpc/configs/mpc85xx_basic_defconfig index 850bd195d0e8..b1593fe6f70b 100644 --- a/arch/powerpc/configs/mpc85xx_basic_defconfig +++ b/arch/powerpc/configs/mpc85xx_basic_defconfig @@ -12,6 +12,7 @@ CONFIG_P1010_RDB=y CONFIG_P1022_DS=y CONFIG_P1022_RDK=y CONFIG_P1023_RDB=y +CONFIG_TWR_P102x=y CONFIG_SBC8548=y CONFIG_SOCRATES=y CONFIG_STX_GP3=y diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 2c041b535a64..b041fb607376 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -36,7 +36,6 @@ CONFIG_PS3_ROM=m CONFIG_PS3_FLASH=m CONFIG_PS3_LPM=m CONFIG_PPC_IBM_CELL_BLADE=y -CONFIG_PPC_CELL_QPACE=y CONFIG_RTAS_FLASH=m CONFIG_IBMEBUS=y CONFIG_CPU_FREQ_PMAC64=y diff --git a/arch/powerpc/crypto/aes-spe-glue.c b/arch/powerpc/crypto/aes-spe-glue.c index bd5e63f72ad4..93ee046d12cd 100644 --- a/arch/powerpc/crypto/aes-spe-glue.c +++ b/arch/powerpc/crypto/aes-spe-glue.c @@ -85,6 +85,7 @@ static void spe_begin(void) static void spe_end(void) { + disable_kernel_spe(); /* reenable preemption */ preempt_enable(); } diff --git a/arch/powerpc/crypto/sha1-spe-glue.c b/arch/powerpc/crypto/sha1-spe-glue.c index 3e1d22212521..f9ebc38d3fe7 100644 --- a/arch/powerpc/crypto/sha1-spe-glue.c +++ b/arch/powerpc/crypto/sha1-spe-glue.c @@ -46,6 +46,7 @@ static void spe_begin(void) static void spe_end(void) { + disable_kernel_spe(); /* reenable preemption */ preempt_enable(); } diff --git a/arch/powerpc/crypto/sha256-spe-glue.c b/arch/powerpc/crypto/sha256-spe-glue.c index f4a616fe1a82..718a079dcdbf 100644 --- a/arch/powerpc/crypto/sha256-spe-glue.c +++ b/arch/powerpc/crypto/sha256-spe-glue.c @@ -47,6 +47,7 @@ static void spe_begin(void) static void spe_end(void) { + disable_kernel_spe(); /* reenable preemption */ preempt_enable(); } diff --git a/arch/powerpc/include/asm/pte-hash32.h b/arch/powerpc/include/asm/book3s/32/hash.h index 62cfb0c663bb..264b754d65b0 100644 --- a/arch/powerpc/include/asm/pte-hash32.h +++ b/arch/powerpc/include/asm/book3s/32/hash.h @@ -1,5 +1,5 @@ -#ifndef _ASM_POWERPC_PTE_HASH32_H -#define _ASM_POWERPC_PTE_HASH32_H +#ifndef _ASM_POWERPC_BOOK3S_32_HASH_H +#define _ASM_POWERPC_BOOK3S_32_HASH_H #ifdef __KERNEL__ /* @@ -43,4 +43,4 @@ #define PTE_ATOMIC_UPDATES 1 #endif /* __KERNEL__ */ -#endif /* _ASM_POWERPC_PTE_HASH32_H */ +#endif /* _ASM_POWERPC_BOOK3S_32_HASH_H */ diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h new file mode 100644 index 000000000000..38b33dcfcc9d --- /dev/null +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -0,0 +1,482 @@ +#ifndef _ASM_POWERPC_BOOK3S_32_PGTABLE_H +#define _ASM_POWERPC_BOOK3S_32_PGTABLE_H + +#include <asm-generic/pgtable-nopmd.h> + +#include <asm/book3s/32/hash.h> + +/* And here we include common definitions */ +#include <asm/pte-common.h> + +/* + * The normal case is that PTEs are 32-bits and we have a 1-page + * 1024-entry pgdir pointing to 1-page 1024-entry PTE pages. -- paulus + * + * For any >32-bit physical address platform, we can use the following + * two level page table layout where the pgdir is 8KB and the MS 13 bits + * are an index to the second level table. The combined pgdir/pmd first + * level has 2048 entries and the second level has 512 64-bit PTE entries. + * -Matt + */ +/* PGDIR_SHIFT determines what a top-level page table entry can map */ +#define PGDIR_SHIFT (PAGE_SHIFT + PTE_SHIFT) +#define PGDIR_SIZE (1UL << PGDIR_SHIFT) +#define PGDIR_MASK (~(PGDIR_SIZE-1)) + +#define PTRS_PER_PTE (1 << PTE_SHIFT) +#define PTRS_PER_PMD 1 +#define PTRS_PER_PGD (1 << (32 - PGDIR_SHIFT)) + +#define USER_PTRS_PER_PGD (TASK_SIZE / PGDIR_SIZE) +/* + * This is the bottom of the PKMAP area with HIGHMEM or an arbitrary + * value (for now) on others, from where we can start layout kernel + * virtual space that goes below PKMAP and FIXMAP + */ +#ifdef CONFIG_HIGHMEM +#define KVIRT_TOP PKMAP_BASE +#else +#define KVIRT_TOP (0xfe000000UL) /* for now, could be FIXMAP_BASE ? */ +#endif + +/* + * ioremap_bot starts at that address. Early ioremaps move down from there, + * until mem_init() at which point this becomes the top of the vmalloc + * and ioremap space + */ +#ifdef CONFIG_NOT_COHERENT_CACHE +#define IOREMAP_TOP ((KVIRT_TOP - CONFIG_CONSISTENT_SIZE) & PAGE_MASK) +#else +#define IOREMAP_TOP KVIRT_TOP +#endif + +/* + * Just any arbitrary offset to the start of the vmalloc VM area: the + * current 16MB value just means that there will be a 64MB "hole" after the + * physical memory until the kernel virtual memory starts. That means that + * any out-of-bounds memory accesses will hopefully be caught. + * The vmalloc() routines leaves a hole of 4kB between each vmalloced + * area for the same reason. ;) + * + * We no longer map larger than phys RAM with the BATs so we don't have + * to worry about the VMALLOC_OFFSET causing problems. We do have to worry + * about clashes between our early calls to ioremap() that start growing down + * from ioremap_base being run into the VM area allocations (growing upwards + * from VMALLOC_START). For this reason we have ioremap_bot to check when + * we actually run into our mappings setup in the early boot with the VM + * system. This really does become a problem for machines with good amounts + * of RAM. -- Cort + */ +#define VMALLOC_OFFSET (0x1000000) /* 16M */ +#ifdef PPC_PIN_SIZE +#define VMALLOC_START (((_ALIGN((long)high_memory, PPC_PIN_SIZE) + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1))) +#else +#define VMALLOC_START ((((long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1))) +#endif +#define VMALLOC_END ioremap_bot + +#ifndef __ASSEMBLY__ +#include <linux/sched.h> +#include <linux/threads.h> +#include <asm/io.h> /* For sub-arch specific PPC_PIN_SIZE */ + +extern unsigned long ioremap_bot; + +/* + * entries per page directory level: our page-table tree is two-level, so + * we don't really have any PMD directory. + */ +#define PTE_TABLE_SIZE (sizeof(pte_t) << PTE_SHIFT) +#define PGD_TABLE_SIZE (sizeof(pgd_t) << (32 - PGDIR_SHIFT)) + +#define pte_ERROR(e) \ + pr_err("%s:%d: bad pte %llx.\n", __FILE__, __LINE__, \ + (unsigned long long)pte_val(e)) +#define pgd_ERROR(e) \ + pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e)) +/* + * Bits in a linux-style PTE. These match the bits in the + * (hardware-defined) PowerPC PTE as closely as possible. + */ + +#define pte_clear(mm, addr, ptep) \ + do { pte_update(ptep, ~_PAGE_HASHPTE, 0); } while (0) + +#define pmd_none(pmd) (!pmd_val(pmd)) +#define pmd_bad(pmd) (pmd_val(pmd) & _PMD_BAD) +#define pmd_present(pmd) (pmd_val(pmd) & _PMD_PRESENT_MASK) +static inline void pmd_clear(pmd_t *pmdp) +{ + *pmdp = __pmd(0); +} + + +/* + * When flushing the tlb entry for a page, we also need to flush the hash + * table entry. flush_hash_pages is assembler (for speed) in hashtable.S. + */ +extern int flush_hash_pages(unsigned context, unsigned long va, + unsigned long pmdval, int count); + +/* Add an HPTE to the hash table */ +extern void add_hash_page(unsigned context, unsigned long va, + unsigned long pmdval); + +/* Flush an entry from the TLB/hash table */ +extern void flush_hash_entry(struct mm_struct *mm, pte_t *ptep, + unsigned long address); + +/* + * PTE updates. This function is called whenever an existing + * valid PTE is updated. This does -not- include set_pte_at() + * which nowadays only sets a new PTE. + * + * Depending on the type of MMU, we may need to use atomic updates + * and the PTE may be either 32 or 64 bit wide. In the later case, + * when using atomic updates, only the low part of the PTE is + * accessed atomically. + * + * In addition, on 44x, we also maintain a global flag indicating + * that an executable user mapping was modified, which is needed + * to properly flush the virtually tagged instruction cache of + * those implementations. + */ +#ifndef CONFIG_PTE_64BIT +static inline unsigned long pte_update(pte_t *p, + unsigned long clr, + unsigned long set) +{ + unsigned long old, tmp; + + __asm__ __volatile__("\ +1: lwarx %0,0,%3\n\ + andc %1,%0,%4\n\ + or %1,%1,%5\n" + PPC405_ERR77(0,%3) +" stwcx. %1,0,%3\n\ + bne- 1b" + : "=&r" (old), "=&r" (tmp), "=m" (*p) + : "r" (p), "r" (clr), "r" (set), "m" (*p) + : "cc" ); + + return old; +} +#else /* CONFIG_PTE_64BIT */ +static inline unsigned long long pte_update(pte_t *p, + unsigned long clr, + unsigned long set) +{ + unsigned long long old; + unsigned long tmp; + + __asm__ __volatile__("\ +1: lwarx %L0,0,%4\n\ + lwzx %0,0,%3\n\ + andc %1,%L0,%5\n\ + or %1,%1,%6\n" + PPC405_ERR77(0,%3) +" stwcx. %1,0,%4\n\ + bne- 1b" + : "=&r" (old), "=&r" (tmp), "=m" (*p) + : "r" (p), "r" ((unsigned long)(p) + 4), "r" (clr), "r" (set), "m" (*p) + : "cc" ); + + return old; +} +#endif /* CONFIG_PTE_64BIT */ + +/* + * 2.6 calls this without flushing the TLB entry; this is wrong + * for our hash-based implementation, we fix that up here. + */ +#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG +static inline int __ptep_test_and_clear_young(unsigned int context, unsigned long addr, pte_t *ptep) +{ + unsigned long old; + old = pte_update(ptep, _PAGE_ACCESSED, 0); + if (old & _PAGE_HASHPTE) { + unsigned long ptephys = __pa(ptep) & PAGE_MASK; + flush_hash_pages(context, addr, ptephys, 1); + } + return (old & _PAGE_ACCESSED) != 0; +} +#define ptep_test_and_clear_young(__vma, __addr, __ptep) \ + __ptep_test_and_clear_young((__vma)->vm_mm->context.id, __addr, __ptep) + +#define __HAVE_ARCH_PTEP_GET_AND_CLEAR +static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + return __pte(pte_update(ptep, ~_PAGE_HASHPTE, 0)); +} + +#define __HAVE_ARCH_PTEP_SET_WRPROTECT +static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + pte_update(ptep, (_PAGE_RW | _PAGE_HWWRITE), _PAGE_RO); +} +static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + ptep_set_wrprotect(mm, addr, ptep); +} + + +static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry) +{ + unsigned long set = pte_val(entry) & + (_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC); + unsigned long clr = ~pte_val(entry) & _PAGE_RO; + + pte_update(ptep, clr, set); +} + +#define __HAVE_ARCH_PTE_SAME +#define pte_same(A,B) (((pte_val(A) ^ pte_val(B)) & ~_PAGE_HASHPTE) == 0) + +/* + * Note that on Book E processors, the pmd contains the kernel virtual + * (lowmem) address of the pte page. The physical address is less useful + * because everything runs with translation enabled (even the TLB miss + * handler). On everything else the pmd contains the physical address + * of the pte page. -- paulus + */ +#ifndef CONFIG_BOOKE +#define pmd_page_vaddr(pmd) \ + ((unsigned long) __va(pmd_val(pmd) & PAGE_MASK)) +#define pmd_page(pmd) \ + pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT) +#else +#define pmd_page_vaddr(pmd) \ + ((unsigned long) (pmd_val(pmd) & PAGE_MASK)) +#define pmd_page(pmd) \ + pfn_to_page((__pa(pmd_val(pmd)) >> PAGE_SHIFT)) +#endif + +/* to find an entry in a kernel page-table-directory */ +#define pgd_offset_k(address) pgd_offset(&init_mm, address) + +/* to find an entry in a page-table-directory */ +#define pgd_index(address) ((address) >> PGDIR_SHIFT) +#define pgd_offset(mm, address) ((mm)->pgd + pgd_index(address)) + +/* Find an entry in the third-level page table.. */ +#define pte_index(address) \ + (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) +#define pte_offset_kernel(dir, addr) \ + ((pte_t *) pmd_page_vaddr(*(dir)) + pte_index(addr)) +#define pte_offset_map(dir, addr) \ + ((pte_t *) kmap_atomic(pmd_page(*(dir))) + pte_index(addr)) +#define pte_unmap(pte) kunmap_atomic(pte) + +/* + * Encode and decode a swap entry. + * Note that the bits we use in a PTE for representing a swap entry + * must not include the _PAGE_PRESENT bit or the _PAGE_HASHPTE bit (if used). + * -- paulus + */ +#define __swp_type(entry) ((entry).val & 0x1f) +#define __swp_offset(entry) ((entry).val >> 5) +#define __swp_entry(type, offset) ((swp_entry_t) { (type) | ((offset) << 5) }) +#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) >> 3 }) +#define __swp_entry_to_pte(x) ((pte_t) { (x).val << 3 }) + +#ifndef CONFIG_PPC_4K_PAGES +void pgtable_cache_init(void); +#else +/* + * No page table caches to initialise + */ +#define pgtable_cache_init() do { } while (0) +#endif + +extern int get_pteptr(struct mm_struct *mm, unsigned long addr, pte_t **ptep, + pmd_t **pmdp); + +/* Generic accessors to PTE bits */ +static inline int pte_write(pte_t pte) { return !!(pte_val(pte) & _PAGE_RW);} +static inline int pte_dirty(pte_t pte) { return !!(pte_val(pte) & _PAGE_DIRTY); } +static inline int pte_young(pte_t pte) { return !!(pte_val(pte) & _PAGE_ACCESSED); } +static inline int pte_special(pte_t pte) { return !!(pte_val(pte) & _PAGE_SPECIAL); } +static inline int pte_none(pte_t pte) { return (pte_val(pte) & ~_PTE_NONE_MASK) == 0; } +static inline pgprot_t pte_pgprot(pte_t pte) { return __pgprot(pte_val(pte) & PAGE_PROT_BITS); } + +static inline int pte_present(pte_t pte) +{ + return pte_val(pte) & _PAGE_PRESENT; +} + +/* Conversion functions: convert a page and protection to a page entry, + * and a page entry and page directory to the page they refer to. + * + * Even if PTEs can be unsigned long long, a PFN is always an unsigned + * long for now. + */ +static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot) +{ + return __pte(((pte_basic_t)(pfn) << PTE_RPN_SHIFT) | + pgprot_val(pgprot)); +} + +static inline unsigned long pte_pfn(pte_t pte) +{ + return pte_val(pte) >> PTE_RPN_SHIFT; +} + +/* Generic modifiers for PTE bits */ +static inline pte_t pte_wrprotect(pte_t pte) +{ + return __pte(pte_val(pte) & ~_PAGE_RW); +} + +static inline pte_t pte_mkclean(pte_t pte) +{ + return __pte(pte_val(pte) & ~_PAGE_DIRTY); +} + +static inline pte_t pte_mkold(pte_t pte) +{ + return __pte(pte_val(pte) & ~_PAGE_ACCESSED); +} + +static inline pte_t pte_mkwrite(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_RW); +} + +static inline pte_t pte_mkdirty(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_DIRTY); +} + +static inline pte_t pte_mkyoung(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_ACCESSED); +} + +static inline pte_t pte_mkspecial(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_SPECIAL); +} + +static inline pte_t pte_mkhuge(pte_t pte) +{ + return pte; +} + +static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) +{ + return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot)); +} + + + +/* This low level function performs the actual PTE insertion + * Setting the PTE depends on the MMU type and other factors. It's + * an horrible mess that I'm not going to try to clean up now but + * I'm keeping it in one place rather than spread around + */ +static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte, int percpu) +{ +#if defined(CONFIG_PPC_STD_MMU_32) && defined(CONFIG_SMP) && !defined(CONFIG_PTE_64BIT) + /* First case is 32-bit Hash MMU in SMP mode with 32-bit PTEs. We use the + * helper pte_update() which does an atomic update. We need to do that + * because a concurrent invalidation can clear _PAGE_HASHPTE. If it's a + * per-CPU PTE such as a kmap_atomic, we do a simple update preserving + * the hash bits instead (ie, same as the non-SMP case) + */ + if (percpu) + *ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE) + | (pte_val(pte) & ~_PAGE_HASHPTE)); + else + pte_update(ptep, ~_PAGE_HASHPTE, pte_val(pte)); + +#elif defined(CONFIG_PPC32) && defined(CONFIG_PTE_64BIT) + /* Second case is 32-bit with 64-bit PTE. In this case, we + * can just store as long as we do the two halves in the right order + * with a barrier in between. This is possible because we take care, + * in the hash code, to pre-invalidate if the PTE was already hashed, + * which synchronizes us with any concurrent invalidation. + * In the percpu case, we also fallback to the simple update preserving + * the hash bits + */ + if (percpu) { + *ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE) + | (pte_val(pte) & ~_PAGE_HASHPTE)); + return; + } + if (pte_val(*ptep) & _PAGE_HASHPTE) + flush_hash_entry(mm, ptep, addr); + __asm__ __volatile__("\ + stw%U0%X0 %2,%0\n\ + eieio\n\ + stw%U0%X0 %L2,%1" + : "=m" (*ptep), "=m" (*((unsigned char *)ptep+4)) + : "r" (pte) : "memory"); + +#elif defined(CONFIG_PPC_STD_MMU_32) + /* Third case is 32-bit hash table in UP mode, we need to preserve + * the _PAGE_HASHPTE bit since we may not have invalidated the previous + * translation in the hash yet (done in a subsequent flush_tlb_xxx()) + * and see we need to keep track that this PTE needs invalidating + */ + *ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE) + | (pte_val(pte) & ~_PAGE_HASHPTE)); + +#else +#error "Not supported " +#endif +} + +/* + * Macro to mark a page protection value as "uncacheable". + */ + +#define _PAGE_CACHE_CTL (_PAGE_COHERENT | _PAGE_GUARDED | _PAGE_NO_CACHE | \ + _PAGE_WRITETHRU) + +#define pgprot_noncached pgprot_noncached +static inline pgprot_t pgprot_noncached(pgprot_t prot) +{ + return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | + _PAGE_NO_CACHE | _PAGE_GUARDED); +} + +#define pgprot_noncached_wc pgprot_noncached_wc +static inline pgprot_t pgprot_noncached_wc(pgprot_t prot) +{ + return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | + _PAGE_NO_CACHE); +} + +#define pgprot_cached pgprot_cached +static inline pgprot_t pgprot_cached(pgprot_t prot) +{ + return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | + _PAGE_COHERENT); +} + +#define pgprot_cached_wthru pgprot_cached_wthru +static inline pgprot_t pgprot_cached_wthru(pgprot_t prot) +{ + return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | + _PAGE_COHERENT | _PAGE_WRITETHRU); +} + +#define pgprot_cached_noncoherent pgprot_cached_noncoherent +static inline pgprot_t pgprot_cached_noncoherent(pgprot_t prot) +{ + return __pgprot(pgprot_val(prot) & ~_PAGE_CACHE_CTL); +} + +#define pgprot_writecombine pgprot_writecombine +static inline pgprot_t pgprot_writecombine(pgprot_t prot) +{ + return pgprot_noncached_wc(prot); +} + +#endif /* !__ASSEMBLY__ */ + +#endif /* _ASM_POWERPC_BOOK3S_32_PGTABLE_H */ diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h new file mode 100644 index 000000000000..ea0414d6659e --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h @@ -0,0 +1,132 @@ +#ifndef _ASM_POWERPC_BOOK3S_64_HASH_4K_H +#define _ASM_POWERPC_BOOK3S_64_HASH_4K_H +/* + * Entries per page directory level. The PTE level must use a 64b record + * for each page table entry. The PMD and PGD level use a 32b record for + * each entry by assuming that each entry is page aligned. + */ +#define PTE_INDEX_SIZE 9 +#define PMD_INDEX_SIZE 7 +#define PUD_INDEX_SIZE 9 +#define PGD_INDEX_SIZE 9 + +#ifndef __ASSEMBLY__ +#define PTE_TABLE_SIZE (sizeof(pte_t) << PTE_INDEX_SIZE) +#define PMD_TABLE_SIZE (sizeof(pmd_t) << PMD_INDEX_SIZE) +#define PUD_TABLE_SIZE (sizeof(pud_t) << PUD_INDEX_SIZE) +#define PGD_TABLE_SIZE (sizeof(pgd_t) << PGD_INDEX_SIZE) +#endif /* __ASSEMBLY__ */ + +#define PTRS_PER_PTE (1 << PTE_INDEX_SIZE) +#define PTRS_PER_PMD (1 << PMD_INDEX_SIZE) +#define PTRS_PER_PUD (1 << PUD_INDEX_SIZE) +#define PTRS_PER_PGD (1 << PGD_INDEX_SIZE) + +/* PMD_SHIFT determines what a second-level page table entry can map */ +#define PMD_SHIFT (PAGE_SHIFT + PTE_INDEX_SIZE) +#define PMD_SIZE (1UL << PMD_SHIFT) +#define PMD_MASK (~(PMD_SIZE-1)) + +/* With 4k base page size, hugepage PTEs go at the PMD level */ +#define MIN_HUGEPTE_SHIFT PMD_SHIFT + +/* PUD_SHIFT determines what a third-level page table entry can map */ +#define PUD_SHIFT (PMD_SHIFT + PMD_INDEX_SIZE) +#define PUD_SIZE (1UL << PUD_SHIFT) +#define PUD_MASK (~(PUD_SIZE-1)) + +/* PGDIR_SHIFT determines what a fourth-level page table entry can map */ +#define PGDIR_SHIFT (PUD_SHIFT + PUD_INDEX_SIZE) +#define PGDIR_SIZE (1UL << PGDIR_SHIFT) +#define PGDIR_MASK (~(PGDIR_SIZE-1)) + +/* Bits to mask out from a PMD to get to the PTE page */ +#define PMD_MASKED_BITS 0 +/* Bits to mask out from a PUD to get to the PMD page */ +#define PUD_MASKED_BITS 0 +/* Bits to mask out from a PGD to get to the PUD page */ +#define PGD_MASKED_BITS 0 + +/* PTE flags to conserve for HPTE identification */ +#define _PAGE_HPTEFLAGS (_PAGE_BUSY | _PAGE_HASHPTE | \ + _PAGE_F_SECOND | _PAGE_F_GIX) + +/* shift to put page number into pte */ +#define PTE_RPN_SHIFT (18) + +#define _PAGE_4K_PFN 0 +#ifndef __ASSEMBLY__ +/* + * 4-level page tables related bits + */ + +#define pgd_none(pgd) (!pgd_val(pgd)) +#define pgd_bad(pgd) (pgd_val(pgd) == 0) +#define pgd_present(pgd) (pgd_val(pgd) != 0) +#define pgd_page_vaddr(pgd) (pgd_val(pgd) & ~PGD_MASKED_BITS) + +static inline void pgd_clear(pgd_t *pgdp) +{ + *pgdp = __pgd(0); +} + +static inline pte_t pgd_pte(pgd_t pgd) +{ + return __pte(pgd_val(pgd)); +} + +static inline pgd_t pte_pgd(pte_t pte) +{ + return __pgd(pte_val(pte)); +} +extern struct page *pgd_page(pgd_t pgd); + +#define pud_offset(pgdp, addr) \ + (((pud_t *) pgd_page_vaddr(*(pgdp))) + \ + (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))) + +#define pud_ERROR(e) \ + pr_err("%s:%d: bad pud %08lx.\n", __FILE__, __LINE__, pud_val(e)) + +/* + * On all 4K setups, remap_4k_pfn() equates to remap_pfn_range() */ +#define remap_4k_pfn(vma, addr, pfn, prot) \ + remap_pfn_range((vma), (addr), (pfn), PAGE_SIZE, (prot)) + +#ifdef CONFIG_HUGETLB_PAGE +/* + * For 4k page size, we support explicit hugepage via hugepd + */ +static inline int pmd_huge(pmd_t pmd) +{ + return 0; +} + +static inline int pud_huge(pud_t pud) +{ + return 0; +} + +static inline int pgd_huge(pgd_t pgd) +{ + return 0; +} +#define pgd_huge pgd_huge + +static inline int hugepd_ok(hugepd_t hpd) +{ + /* + * if it is not a pte and have hugepd shift mask + * set, then it is a hugepd directory pointer + */ + if (!(hpd.pd & _PAGE_PTE) && + ((hpd.pd & HUGEPD_SHIFT_MASK) != 0)) + return true; + return false; +} +#define is_hugepd(hpd) (hugepd_ok(hpd)) +#endif + +#endif /* !__ASSEMBLY__ */ + +#endif /* _ASM_POWERPC_BOOK3S_64_HASH_4K_H */ diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h new file mode 100644 index 000000000000..9e55e3b1fef0 --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h @@ -0,0 +1,312 @@ +#ifndef _ASM_POWERPC_BOOK3S_64_HASH_64K_H +#define _ASM_POWERPC_BOOK3S_64_HASH_64K_H + +#include <asm-generic/pgtable-nopud.h> + +#define PTE_INDEX_SIZE 8 +#define PMD_INDEX_SIZE 10 +#define PUD_INDEX_SIZE 0 +#define PGD_INDEX_SIZE 12 + +#define PTRS_PER_PTE (1 << PTE_INDEX_SIZE) +#define PTRS_PER_PMD (1 << PMD_INDEX_SIZE) +#define PTRS_PER_PGD (1 << PGD_INDEX_SIZE) + +/* With 4k base page size, hugepage PTEs go at the PMD level */ +#define MIN_HUGEPTE_SHIFT PAGE_SHIFT + +/* PMD_SHIFT determines what a second-level page table entry can map */ +#define PMD_SHIFT (PAGE_SHIFT + PTE_INDEX_SIZE) +#define PMD_SIZE (1UL << PMD_SHIFT) +#define PMD_MASK (~(PMD_SIZE-1)) + +/* PGDIR_SHIFT determines what a third-level page table entry can map */ +#define PGDIR_SHIFT (PMD_SHIFT + PMD_INDEX_SIZE) +#define PGDIR_SIZE (1UL << PGDIR_SHIFT) +#define PGDIR_MASK (~(PGDIR_SIZE-1)) + +#define _PAGE_COMBO 0x00040000 /* this is a combo 4k page */ +#define _PAGE_4K_PFN 0x00080000 /* PFN is for a single 4k page */ +/* + * Used to track subpage group valid if _PAGE_COMBO is set + * This overloads _PAGE_F_GIX and _PAGE_F_SECOND + */ +#define _PAGE_COMBO_VALID (_PAGE_F_GIX | _PAGE_F_SECOND) + +/* PTE flags to conserve for HPTE identification */ +#define _PAGE_HPTEFLAGS (_PAGE_BUSY | _PAGE_F_SECOND | \ + _PAGE_F_GIX | _PAGE_HASHPTE | _PAGE_COMBO) + +/* Shift to put page number into pte. + * + * That gives us a max RPN of 34 bits, which means a max of 50 bits + * of addressable physical space, or 46 bits for the special 4k PFNs. + */ +#define PTE_RPN_SHIFT (30) +/* + * we support 16 fragments per PTE page of 64K size. + */ +#define PTE_FRAG_NR 16 +/* + * We use a 2K PTE page fragment and another 2K for storing + * real_pte_t hash index + */ +#define PTE_FRAG_SIZE_SHIFT 12 +#define PTE_FRAG_SIZE (1UL << PTE_FRAG_SIZE_SHIFT) + +/* + * Bits to mask out from a PMD to get to the PTE page + * PMDs point to PTE table fragments which are PTE_FRAG_SIZE aligned. + */ +#define PMD_MASKED_BITS (PTE_FRAG_SIZE - 1) +/* Bits to mask out from a PGD/PUD to get to the PMD page */ +#define PUD_MASKED_BITS 0x1ff + +#ifndef __ASSEMBLY__ + +/* + * With 64K pages on hash table, we have a special PTE format that + * uses a second "half" of the page table to encode sub-page information + * in order to deal with 64K made of 4K HW pages. Thus we override the + * generic accessors and iterators here + */ +#define __real_pte __real_pte +static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep) +{ + real_pte_t rpte; + unsigned long *hidxp; + + rpte.pte = pte; + rpte.hidx = 0; + if (pte_val(pte) & _PAGE_COMBO) { + /* + * Make sure we order the hidx load against the _PAGE_COMBO + * check. The store side ordering is done in __hash_page_4K + */ + smp_rmb(); + hidxp = (unsigned long *)(ptep + PTRS_PER_PTE); + rpte.hidx = *hidxp; + } + return rpte; +} + +static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index) +{ + if ((pte_val(rpte.pte) & _PAGE_COMBO)) + return (rpte.hidx >> (index<<2)) & 0xf; + return (pte_val(rpte.pte) >> _PAGE_F_GIX_SHIFT) & 0xf; +} + +#define __rpte_to_pte(r) ((r).pte) +extern bool __rpte_sub_valid(real_pte_t rpte, unsigned long index); +/* + * Trick: we set __end to va + 64k, which happens works for + * a 16M page as well as we want only one iteration + */ +#define pte_iterate_hashed_subpages(rpte, psize, vpn, index, shift) \ + do { \ + unsigned long __end = vpn + (1UL << (PAGE_SHIFT - VPN_SHIFT)); \ + unsigned __split = (psize == MMU_PAGE_4K || \ + psize == MMU_PAGE_64K_AP); \ + shift = mmu_psize_defs[psize].shift; \ + for (index = 0; vpn < __end; index++, \ + vpn += (1L << (shift - VPN_SHIFT))) { \ + if (!__split || __rpte_sub_valid(rpte, index)) \ + do { + +#define pte_iterate_hashed_end() } while(0); } } while(0) + +#define pte_pagesize_index(mm, addr, pte) \ + (((pte) & _PAGE_COMBO)? MMU_PAGE_4K: MMU_PAGE_64K) + +#define remap_4k_pfn(vma, addr, pfn, prot) \ + (WARN_ON(((pfn) >= (1UL << (64 - PTE_RPN_SHIFT)))) ? -EINVAL : \ + remap_pfn_range((vma), (addr), (pfn), PAGE_SIZE, \ + __pgprot(pgprot_val((prot)) | _PAGE_4K_PFN))) + +#define PTE_TABLE_SIZE PTE_FRAG_SIZE +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define PMD_TABLE_SIZE ((sizeof(pmd_t) << PMD_INDEX_SIZE) + (sizeof(unsigned long) << PMD_INDEX_SIZE)) +#else +#define PMD_TABLE_SIZE (sizeof(pmd_t) << PMD_INDEX_SIZE) +#endif +#define PGD_TABLE_SIZE (sizeof(pgd_t) << PGD_INDEX_SIZE) + +#define pgd_pte(pgd) (pud_pte(((pud_t){ pgd }))) +#define pte_pgd(pte) ((pgd_t)pte_pud(pte)) + +#ifdef CONFIG_HUGETLB_PAGE +/* + * We have PGD_INDEX_SIZ = 12 and PTE_INDEX_SIZE = 8, so that we can have + * 16GB hugepage pte in PGD and 16MB hugepage pte at PMD; + * + * Defined in such a way that we can optimize away code block at build time + * if CONFIG_HUGETLB_PAGE=n. + */ +static inline int pmd_huge(pmd_t pmd) +{ + /* + * leaf pte for huge page + */ + return !!(pmd_val(pmd) & _PAGE_PTE); +} + +static inline int pud_huge(pud_t pud) +{ + /* + * leaf pte for huge page + */ + return !!(pud_val(pud) & _PAGE_PTE); +} + +static inline int pgd_huge(pgd_t pgd) +{ + /* + * leaf pte for huge page + */ + return !!(pgd_val(pgd) & _PAGE_PTE); +} +#define pgd_huge pgd_huge + +#ifdef CONFIG_DEBUG_VM +extern int hugepd_ok(hugepd_t hpd); +#define is_hugepd(hpd) (hugepd_ok(hpd)) +#else +/* + * With 64k page size, we have hugepage ptes in the pgd and pmd entries. We don't + * need to setup hugepage directory for them. Our pte and page directory format + * enable us to have this enabled. + */ +static inline int hugepd_ok(hugepd_t hpd) +{ + return 0; +} +#define is_hugepd(pdep) 0 +#endif /* CONFIG_DEBUG_VM */ + +#endif /* CONFIG_HUGETLB_PAGE */ + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +extern unsigned long pmd_hugepage_update(struct mm_struct *mm, + unsigned long addr, + pmd_t *pmdp, + unsigned long clr, + unsigned long set); +static inline char *get_hpte_slot_array(pmd_t *pmdp) +{ + /* + * The hpte hindex is stored in the pgtable whose address is in the + * second half of the PMD + * + * Order this load with the test for pmd_trans_huge in the caller + */ + smp_rmb(); + return *(char **)(pmdp + PTRS_PER_PMD); + + +} +/* + * The linux hugepage PMD now include the pmd entries followed by the address + * to the stashed pgtable_t. The stashed pgtable_t contains the hpte bits. + * [ 1 bit secondary | 3 bit hidx | 1 bit valid | 000]. We use one byte per + * each HPTE entry. With 16MB hugepage and 64K HPTE we need 256 entries and + * with 4K HPTE we need 4096 entries. Both will fit in a 4K pgtable_t. + * + * The last three bits are intentionally left to zero. This memory location + * are also used as normal page PTE pointers. So if we have any pointers + * left around while we collapse a hugepage, we need to make sure + * _PAGE_PRESENT bit of that is zero when we look at them + */ +static inline unsigned int hpte_valid(unsigned char *hpte_slot_array, int index) +{ + return (hpte_slot_array[index] >> 3) & 0x1; +} + +static inline unsigned int hpte_hash_index(unsigned char *hpte_slot_array, + int index) +{ + return hpte_slot_array[index] >> 4; +} + +static inline void mark_hpte_slot_valid(unsigned char *hpte_slot_array, + unsigned int index, unsigned int hidx) +{ + hpte_slot_array[index] = hidx << 4 | 0x1 << 3; +} + +/* + * + * For core kernel code by design pmd_trans_huge is never run on any hugetlbfs + * page. The hugetlbfs page table walking and mangling paths are totally + * separated form the core VM paths and they're differentiated by + * VM_HUGETLB being set on vm_flags well before any pmd_trans_huge could run. + * + * pmd_trans_huge() is defined as false at build time if + * CONFIG_TRANSPARENT_HUGEPAGE=n to optimize away code blocks at build + * time in such case. + * + * For ppc64 we need to differntiate from explicit hugepages from THP, because + * for THP we also track the subpage details at the pmd level. We don't do + * that for explicit huge pages. + * + */ +static inline int pmd_trans_huge(pmd_t pmd) +{ + return !!((pmd_val(pmd) & (_PAGE_PTE | _PAGE_THP_HUGE)) == + (_PAGE_PTE | _PAGE_THP_HUGE)); +} + +static inline int pmd_trans_splitting(pmd_t pmd) +{ + if (pmd_trans_huge(pmd)) + return pmd_val(pmd) & _PAGE_SPLITTING; + return 0; +} + +static inline int pmd_large(pmd_t pmd) +{ + return !!(pmd_val(pmd) & _PAGE_PTE); +} + +static inline pmd_t pmd_mknotpresent(pmd_t pmd) +{ + return __pmd(pmd_val(pmd) & ~_PAGE_PRESENT); +} + +static inline pmd_t pmd_mksplitting(pmd_t pmd) +{ + return __pmd(pmd_val(pmd) | _PAGE_SPLITTING); +} + +#define __HAVE_ARCH_PMD_SAME +static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b) +{ + return (((pmd_val(pmd_a) ^ pmd_val(pmd_b)) & ~_PAGE_HPTEFLAGS) == 0); +} + +static inline int __pmdp_test_and_clear_young(struct mm_struct *mm, + unsigned long addr, pmd_t *pmdp) +{ + unsigned long old; + + if ((pmd_val(*pmdp) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0) + return 0; + old = pmd_hugepage_update(mm, addr, pmdp, _PAGE_ACCESSED, 0); + return ((old & _PAGE_ACCESSED) != 0); +} + +#define __HAVE_ARCH_PMDP_SET_WRPROTECT +static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp) +{ + + if ((pmd_val(*pmdp) & _PAGE_RW) == 0) + return; + + pmd_hugepage_update(mm, addr, pmdp, _PAGE_RW, 0); +} + +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#endif /* __ASSEMBLY__ */ + +#endif /* _ASM_POWERPC_BOOK3S_64_HASH_64K_H */ diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h new file mode 100644 index 000000000000..2ff8b3df553d --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/hash.h @@ -0,0 +1,551 @@ +#ifndef _ASM_POWERPC_BOOK3S_64_HASH_H +#define _ASM_POWERPC_BOOK3S_64_HASH_H +#ifdef __KERNEL__ + +/* + * Common bits between 4K and 64K pages in a linux-style PTE. + * These match the bits in the (hardware-defined) PowerPC PTE as closely + * as possible. Additional bits may be defined in pgtable-hash64-*.h + * + * Note: We only support user read/write permissions. Supervisor always + * have full read/write to pages above PAGE_OFFSET (pages below that + * always use the user access permissions). + * + * We could create separate kernel read-only if we used the 3 PP bits + * combinations that newer processors provide but we currently don't. + */ +#define _PAGE_PTE 0x00001 +#define _PAGE_PRESENT 0x00002 /* software: pte contains a translation */ +#define _PAGE_BIT_SWAP_TYPE 2 +#define _PAGE_USER 0x00004 /* matches one of the PP bits */ +#define _PAGE_EXEC 0x00008 /* No execute on POWER4 and newer (we invert) */ +#define _PAGE_GUARDED 0x00010 +/* We can derive Memory coherence from _PAGE_NO_CACHE */ +#define _PAGE_COHERENT 0x0 +#define _PAGE_NO_CACHE 0x00020 /* I: cache inhibit */ +#define _PAGE_WRITETHRU 0x00040 /* W: cache write-through */ +#define _PAGE_DIRTY 0x00080 /* C: page changed */ +#define _PAGE_ACCESSED 0x00100 /* R: page referenced */ +#define _PAGE_RW 0x00200 /* software: user write access allowed */ +#define _PAGE_HASHPTE 0x00400 /* software: pte has an associated HPTE */ +#define _PAGE_BUSY 0x00800 /* software: PTE & hash are busy */ +#define _PAGE_F_GIX 0x07000 /* full page: hidx bits */ +#define _PAGE_F_GIX_SHIFT 12 +#define _PAGE_F_SECOND 0x08000 /* Whether to use secondary hash or not */ +#define _PAGE_SPECIAL 0x10000 /* software: special page */ + +#ifdef CONFIG_MEM_SOFT_DIRTY +#define _PAGE_SOFT_DIRTY 0x20000 /* software: software dirty tracking */ +#else +#define _PAGE_SOFT_DIRTY 0x00000 +#endif + +/* + * THP pages can't be special. So use the _PAGE_SPECIAL + */ +#define _PAGE_SPLITTING _PAGE_SPECIAL + +/* + * We need to differentiate between explicit huge page and THP huge + * page, since THP huge page also need to track real subpage details + */ +#define _PAGE_THP_HUGE _PAGE_4K_PFN + +/* + * set of bits not changed in pmd_modify. + */ +#define _HPAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS | \ + _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_SPLITTING | \ + _PAGE_THP_HUGE | _PAGE_PTE | _PAGE_SOFT_DIRTY) + +#ifdef CONFIG_PPC_64K_PAGES +#include <asm/book3s/64/hash-64k.h> +#else +#include <asm/book3s/64/hash-4k.h> +#endif + +/* + * Size of EA range mapped by our pagetables. + */ +#define PGTABLE_EADDR_SIZE (PTE_INDEX_SIZE + PMD_INDEX_SIZE + \ + PUD_INDEX_SIZE + PGD_INDEX_SIZE + PAGE_SHIFT) +#define PGTABLE_RANGE (ASM_CONST(1) << PGTABLE_EADDR_SIZE) + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define PMD_CACHE_INDEX (PMD_INDEX_SIZE + 1) +#else +#define PMD_CACHE_INDEX PMD_INDEX_SIZE +#endif +/* + * Define the address range of the kernel non-linear virtual area + */ +#define KERN_VIRT_START ASM_CONST(0xD000000000000000) +#define KERN_VIRT_SIZE ASM_CONST(0x0000100000000000) + +/* + * The vmalloc space starts at the beginning of that region, and + * occupies half of it on hash CPUs and a quarter of it on Book3E + * (we keep a quarter for the virtual memmap) + */ +#define VMALLOC_START KERN_VIRT_START +#define VMALLOC_SIZE (KERN_VIRT_SIZE >> 1) +#define VMALLOC_END (VMALLOC_START + VMALLOC_SIZE) + +/* + * Region IDs + */ +#define REGION_SHIFT 60UL +#define REGION_MASK (0xfUL << REGION_SHIFT) +#define REGION_ID(ea) (((unsigned long)(ea)) >> REGION_SHIFT) + +#define VMALLOC_REGION_ID (REGION_ID(VMALLOC_START)) +#define KERNEL_REGION_ID (REGION_ID(PAGE_OFFSET)) +#define VMEMMAP_REGION_ID (0xfUL) /* Server only */ +#define USER_REGION_ID (0UL) + +/* + * Defines the address of the vmemap area, in its own region on + * hash table CPUs. + */ +#define VMEMMAP_BASE (VMEMMAP_REGION_ID << REGION_SHIFT) + +#ifdef CONFIG_PPC_MM_SLICES +#define HAVE_ARCH_UNMAPPED_AREA +#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN +#endif /* CONFIG_PPC_MM_SLICES */ + +/* No separate kernel read-only */ +#define _PAGE_KERNEL_RW (_PAGE_RW | _PAGE_DIRTY) /* user access blocked by key */ +#define _PAGE_KERNEL_RO _PAGE_KERNEL_RW +#define _PAGE_KERNEL_RWX (_PAGE_DIRTY | _PAGE_RW | _PAGE_EXEC) + +/* Strong Access Ordering */ +#define _PAGE_SAO (_PAGE_WRITETHRU | _PAGE_NO_CACHE | _PAGE_COHERENT) + +/* No page size encoding in the linux PTE */ +#define _PAGE_PSIZE 0 + +/* PTEIDX nibble */ +#define _PTEIDX_SECONDARY 0x8 +#define _PTEIDX_GROUP_IX 0x7 + +/* Hash table based platforms need atomic updates of the linux PTE */ +#define PTE_ATOMIC_UPDATES 1 +#define _PTE_NONE_MASK _PAGE_HPTEFLAGS +/* + * The mask convered by the RPN must be a ULL on 32-bit platforms with + * 64-bit PTEs + */ +#define PTE_RPN_MASK (~((1UL << PTE_RPN_SHIFT) - 1)) +/* + * _PAGE_CHG_MASK masks of bits that are to be preserved across + * pgprot changes + */ +#define _PAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS | _PAGE_DIRTY | \ + _PAGE_ACCESSED | _PAGE_SPECIAL | _PAGE_PTE | \ + _PAGE_SOFT_DIRTY) +/* + * Mask of bits returned by pte_pgprot() + */ +#define PAGE_PROT_BITS (_PAGE_GUARDED | _PAGE_COHERENT | _PAGE_NO_CACHE | \ + _PAGE_WRITETHRU | _PAGE_4K_PFN | \ + _PAGE_USER | _PAGE_ACCESSED | \ + _PAGE_RW | _PAGE_DIRTY | _PAGE_EXEC | \ + _PAGE_SOFT_DIRTY) +/* + * We define 2 sets of base prot bits, one for basic pages (ie, + * cacheable kernel and user pages) and one for non cacheable + * pages. We always set _PAGE_COHERENT when SMP is enabled or + * the processor might need it for DMA coherency. + */ +#define _PAGE_BASE_NC (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_PSIZE) +#define _PAGE_BASE (_PAGE_BASE_NC | _PAGE_COHERENT) + +/* Permission masks used to generate the __P and __S table, + * + * Note:__pgprot is defined in arch/powerpc/include/asm/page.h + * + * Write permissions imply read permissions for now (we could make write-only + * pages on BookE but we don't bother for now). Execute permission control is + * possible on platforms that define _PAGE_EXEC + * + * Note due to the way vm flags are laid out, the bits are XWR + */ +#define PAGE_NONE __pgprot(_PAGE_BASE) +#define PAGE_SHARED __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW) +#define PAGE_SHARED_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW | \ + _PAGE_EXEC) +#define PAGE_COPY __pgprot(_PAGE_BASE | _PAGE_USER ) +#define PAGE_COPY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) +#define PAGE_READONLY __pgprot(_PAGE_BASE | _PAGE_USER ) +#define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) + +#define __P000 PAGE_NONE +#define __P001 PAGE_READONLY +#define __P010 PAGE_COPY +#define __P011 PAGE_COPY +#define __P100 PAGE_READONLY_X +#define __P101 PAGE_READONLY_X +#define __P110 PAGE_COPY_X +#define __P111 PAGE_COPY_X + +#define __S000 PAGE_NONE +#define __S001 PAGE_READONLY +#define __S010 PAGE_SHARED +#define __S011 PAGE_SHARED +#define __S100 PAGE_READONLY_X +#define __S101 PAGE_READONLY_X +#define __S110 PAGE_SHARED_X +#define __S111 PAGE_SHARED_X + +/* Permission masks used for kernel mappings */ +#define PAGE_KERNEL __pgprot(_PAGE_BASE | _PAGE_KERNEL_RW) +#define PAGE_KERNEL_NC __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | \ + _PAGE_NO_CACHE) +#define PAGE_KERNEL_NCG __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | \ + _PAGE_NO_CACHE | _PAGE_GUARDED) +#define PAGE_KERNEL_X __pgprot(_PAGE_BASE | _PAGE_KERNEL_RWX) +#define PAGE_KERNEL_RO __pgprot(_PAGE_BASE | _PAGE_KERNEL_RO) +#define PAGE_KERNEL_ROX __pgprot(_PAGE_BASE | _PAGE_KERNEL_ROX) + +/* Protection used for kernel text. We want the debuggers to be able to + * set breakpoints anywhere, so don't write protect the kernel text + * on platforms where such control is possible. + */ +#if defined(CONFIG_KGDB) || defined(CONFIG_XMON) || defined(CONFIG_BDI_SWITCH) ||\ + defined(CONFIG_KPROBES) || defined(CONFIG_DYNAMIC_FTRACE) +#define PAGE_KERNEL_TEXT PAGE_KERNEL_X +#else +#define PAGE_KERNEL_TEXT PAGE_KERNEL_ROX +#endif + +/* Make modules code happy. We don't set RO yet */ +#define PAGE_KERNEL_EXEC PAGE_KERNEL_X +#define PAGE_AGP (PAGE_KERNEL_NC) + +#define PMD_BAD_BITS (PTE_TABLE_SIZE-1) +#define PUD_BAD_BITS (PMD_TABLE_SIZE-1) + +#ifndef __ASSEMBLY__ +#define pmd_bad(pmd) (!is_kernel_addr(pmd_val(pmd)) \ + || (pmd_val(pmd) & PMD_BAD_BITS)) +#define pmd_page_vaddr(pmd) (pmd_val(pmd) & ~PMD_MASKED_BITS) + +#define pud_bad(pud) (!is_kernel_addr(pud_val(pud)) \ + || (pud_val(pud) & PUD_BAD_BITS)) +#define pud_page_vaddr(pud) (pud_val(pud) & ~PUD_MASKED_BITS) + +#define pgd_index(address) (((address) >> (PGDIR_SHIFT)) & (PTRS_PER_PGD - 1)) +#define pmd_index(address) (((address) >> (PMD_SHIFT)) & (PTRS_PER_PMD - 1)) +#define pte_index(address) (((address) >> (PAGE_SHIFT)) & (PTRS_PER_PTE - 1)) + +extern void hpte_need_flush(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, unsigned long pte, int huge); +extern unsigned long htab_convert_pte_flags(unsigned long pteflags); +/* Atomic PTE updates */ +static inline unsigned long pte_update(struct mm_struct *mm, + unsigned long addr, + pte_t *ptep, unsigned long clr, + unsigned long set, + int huge) +{ + unsigned long old, tmp; + + __asm__ __volatile__( + "1: ldarx %0,0,%3 # pte_update\n\ + andi. %1,%0,%6\n\ + bne- 1b \n\ + andc %1,%0,%4 \n\ + or %1,%1,%7\n\ + stdcx. %1,0,%3 \n\ + bne- 1b" + : "=&r" (old), "=&r" (tmp), "=m" (*ptep) + : "r" (ptep), "r" (clr), "m" (*ptep), "i" (_PAGE_BUSY), "r" (set) + : "cc" ); + /* huge pages use the old page table lock */ + if (!huge) + assert_pte_locked(mm, addr); + + if (old & _PAGE_HASHPTE) + hpte_need_flush(mm, addr, ptep, old, huge); + + return old; +} + +static inline int __ptep_test_and_clear_young(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + unsigned long old; + + if ((pte_val(*ptep) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0) + return 0; + old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0); + return (old & _PAGE_ACCESSED) != 0; +} +#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG +#define ptep_test_and_clear_young(__vma, __addr, __ptep) \ +({ \ + int __r; \ + __r = __ptep_test_and_clear_young((__vma)->vm_mm, __addr, __ptep); \ + __r; \ +}) + +#define __HAVE_ARCH_PTEP_SET_WRPROTECT +static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + + if ((pte_val(*ptep) & _PAGE_RW) == 0) + return; + + pte_update(mm, addr, ptep, _PAGE_RW, 0, 0); +} + +static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + if ((pte_val(*ptep) & _PAGE_RW) == 0) + return; + + pte_update(mm, addr, ptep, _PAGE_RW, 0, 1); +} + +/* + * We currently remove entries from the hashtable regardless of whether + * the entry was young or dirty. The generic routines only flush if the + * entry was young or dirty which is not good enough. + * + * We should be more intelligent about this but for the moment we override + * these functions and force a tlb flush unconditionally + */ +#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH +#define ptep_clear_flush_young(__vma, __address, __ptep) \ +({ \ + int __young = __ptep_test_and_clear_young((__vma)->vm_mm, __address, \ + __ptep); \ + __young; \ +}) + +#define __HAVE_ARCH_PTEP_GET_AND_CLEAR +static inline pte_t ptep_get_and_clear(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + unsigned long old = pte_update(mm, addr, ptep, ~0UL, 0, 0); + return __pte(old); +} + +static inline void pte_clear(struct mm_struct *mm, unsigned long addr, + pte_t * ptep) +{ + pte_update(mm, addr, ptep, ~0UL, 0, 0); +} + + +/* Set the dirty and/or accessed bits atomically in a linux PTE, this + * function doesn't need to flush the hash entry + */ +static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry) +{ + unsigned long bits = pte_val(entry) & + (_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC | + _PAGE_SOFT_DIRTY); + + unsigned long old, tmp; + + __asm__ __volatile__( + "1: ldarx %0,0,%4\n\ + andi. %1,%0,%6\n\ + bne- 1b \n\ + or %0,%3,%0\n\ + stdcx. %0,0,%4\n\ + bne- 1b" + :"=&r" (old), "=&r" (tmp), "=m" (*ptep) + :"r" (bits), "r" (ptep), "m" (*ptep), "i" (_PAGE_BUSY) + :"cc"); +} + +#define __HAVE_ARCH_PTE_SAME +#define pte_same(A,B) (((pte_val(A) ^ pte_val(B)) & ~_PAGE_HPTEFLAGS) == 0) + +/* Generic accessors to PTE bits */ +static inline int pte_write(pte_t pte) { return !!(pte_val(pte) & _PAGE_RW);} +static inline int pte_dirty(pte_t pte) { return !!(pte_val(pte) & _PAGE_DIRTY); } +static inline int pte_young(pte_t pte) { return !!(pte_val(pte) & _PAGE_ACCESSED); } +static inline int pte_special(pte_t pte) { return !!(pte_val(pte) & _PAGE_SPECIAL); } +static inline int pte_none(pte_t pte) { return (pte_val(pte) & ~_PTE_NONE_MASK) == 0; } +static inline pgprot_t pte_pgprot(pte_t pte) { return __pgprot(pte_val(pte) & PAGE_PROT_BITS); } + +#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY +static inline bool pte_soft_dirty(pte_t pte) +{ + return !!(pte_val(pte) & _PAGE_SOFT_DIRTY); +} +static inline pte_t pte_mksoft_dirty(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_SOFT_DIRTY); +} + +static inline pte_t pte_clear_soft_dirty(pte_t pte) +{ + return __pte(pte_val(pte) & ~_PAGE_SOFT_DIRTY); +} +#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ + +#ifdef CONFIG_NUMA_BALANCING +/* + * These work without NUMA balancing but the kernel does not care. See the + * comment in include/asm-generic/pgtable.h . On powerpc, this will only + * work for user pages and always return true for kernel pages. + */ +static inline int pte_protnone(pte_t pte) +{ + return (pte_val(pte) & + (_PAGE_PRESENT | _PAGE_USER)) == _PAGE_PRESENT; +} +#endif /* CONFIG_NUMA_BALANCING */ + +static inline int pte_present(pte_t pte) +{ + return pte_val(pte) & _PAGE_PRESENT; +} + +/* Conversion functions: convert a page and protection to a page entry, + * and a page entry and page directory to the page they refer to. + * + * Even if PTEs can be unsigned long long, a PFN is always an unsigned + * long for now. + */ +static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot) +{ + return __pte(((pte_basic_t)(pfn) << PTE_RPN_SHIFT) | + pgprot_val(pgprot)); +} + +static inline unsigned long pte_pfn(pte_t pte) +{ + return pte_val(pte) >> PTE_RPN_SHIFT; +} + +/* Generic modifiers for PTE bits */ +static inline pte_t pte_wrprotect(pte_t pte) +{ + return __pte(pte_val(pte) & ~_PAGE_RW); +} + +static inline pte_t pte_mkclean(pte_t pte) +{ + return __pte(pte_val(pte) & ~_PAGE_DIRTY); +} + +static inline pte_t pte_mkold(pte_t pte) +{ + return __pte(pte_val(pte) & ~_PAGE_ACCESSED); +} + +static inline pte_t pte_mkwrite(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_RW); +} + +static inline pte_t pte_mkdirty(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_DIRTY | _PAGE_SOFT_DIRTY); +} + +static inline pte_t pte_mkyoung(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_ACCESSED); +} + +static inline pte_t pte_mkspecial(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_SPECIAL); +} + +static inline pte_t pte_mkhuge(pte_t pte) +{ + return pte; +} + +static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) +{ + return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot)); +} + +/* This low level function performs the actual PTE insertion + * Setting the PTE depends on the MMU type and other factors. It's + * an horrible mess that I'm not going to try to clean up now but + * I'm keeping it in one place rather than spread around + */ +static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte, int percpu) +{ + /* + * Anything else just stores the PTE normally. That covers all 64-bit + * cases, and 32-bit non-hash with 32-bit PTEs. + */ + *ptep = pte; +} + +/* + * Macro to mark a page protection value as "uncacheable". + */ + +#define _PAGE_CACHE_CTL (_PAGE_COHERENT | _PAGE_GUARDED | _PAGE_NO_CACHE | \ + _PAGE_WRITETHRU) + +#define pgprot_noncached pgprot_noncached +static inline pgprot_t pgprot_noncached(pgprot_t prot) +{ + return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | + _PAGE_NO_CACHE | _PAGE_GUARDED); +} + +#define pgprot_noncached_wc pgprot_noncached_wc +static inline pgprot_t pgprot_noncached_wc(pgprot_t prot) +{ + return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | + _PAGE_NO_CACHE); +} + +#define pgprot_cached pgprot_cached +static inline pgprot_t pgprot_cached(pgprot_t prot) +{ + return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | + _PAGE_COHERENT); +} + +#define pgprot_cached_wthru pgprot_cached_wthru +static inline pgprot_t pgprot_cached_wthru(pgprot_t prot) +{ + return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | + _PAGE_COHERENT | _PAGE_WRITETHRU); +} + +#define pgprot_cached_noncoherent pgprot_cached_noncoherent +static inline pgprot_t pgprot_cached_noncoherent(pgprot_t prot) +{ + return __pgprot(pgprot_val(prot) & ~_PAGE_CACHE_CTL); +} + +#define pgprot_writecombine pgprot_writecombine +static inline pgprot_t pgprot_writecombine(pgprot_t prot) +{ + return pgprot_noncached_wc(prot); +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +extern void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp, unsigned long old_pmd); +#else +static inline void hpte_do_hugepage_flush(struct mm_struct *mm, + unsigned long addr, pmd_t *pmdp, + unsigned long old_pmd) +{ + WARN(1, "%s called with THP disabled\n", __func__); +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +#endif /* !__ASSEMBLY__ */ +#endif /* __KERNEL__ */ +#endif /* _ASM_POWERPC_BOOK3S_64_HASH_H */ diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h new file mode 100644 index 000000000000..b3a5badab69f --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -0,0 +1,300 @@ +#ifndef _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ +#define _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ +/* + * This file contains the functions and defines necessary to modify and use + * the ppc64 hashed page table. + */ + +#include <asm/book3s/64/hash.h> +#include <asm/barrier.h> + +/* + * The second half of the kernel virtual space is used for IO mappings, + * it's itself carved into the PIO region (ISA and PHB IO space) and + * the ioremap space + * + * ISA_IO_BASE = KERN_IO_START, 64K reserved area + * PHB_IO_BASE = ISA_IO_BASE + 64K to ISA_IO_BASE + 2G, PHB IO spaces + * IOREMAP_BASE = ISA_IO_BASE + 2G to VMALLOC_START + PGTABLE_RANGE + */ +#define KERN_IO_START (KERN_VIRT_START + (KERN_VIRT_SIZE >> 1)) +#define FULL_IO_SIZE 0x80000000ul +#define ISA_IO_BASE (KERN_IO_START) +#define ISA_IO_END (KERN_IO_START + 0x10000ul) +#define PHB_IO_BASE (ISA_IO_END) +#define PHB_IO_END (KERN_IO_START + FULL_IO_SIZE) +#define IOREMAP_BASE (PHB_IO_END) +#define IOREMAP_END (KERN_VIRT_START + KERN_VIRT_SIZE) + +#define vmemmap ((struct page *)VMEMMAP_BASE) + +/* Advertise special mapping type for AGP */ +#define HAVE_PAGE_AGP + +/* Advertise support for _PAGE_SPECIAL */ +#define __HAVE_ARCH_PTE_SPECIAL + +#ifndef __ASSEMBLY__ + +/* + * This is the default implementation of various PTE accessors, it's + * used in all cases except Book3S with 64K pages where we have a + * concept of sub-pages + */ +#ifndef __real_pte + +#ifdef CONFIG_STRICT_MM_TYPECHECKS +#define __real_pte(e,p) ((real_pte_t){(e)}) +#define __rpte_to_pte(r) ((r).pte) +#else +#define __real_pte(e,p) (e) +#define __rpte_to_pte(r) (__pte(r)) +#endif +#define __rpte_to_hidx(r,index) (pte_val(__rpte_to_pte(r)) >>_PAGE_F_GIX_SHIFT) + +#define pte_iterate_hashed_subpages(rpte, psize, va, index, shift) \ + do { \ + index = 0; \ + shift = mmu_psize_defs[psize].shift; \ + +#define pte_iterate_hashed_end() } while(0) + +/* + * We expect this to be called only for user addresses or kernel virtual + * addresses other than the linear mapping. + */ +#define pte_pagesize_index(mm, addr, pte) MMU_PAGE_4K + +#endif /* __real_pte */ + +static inline void pmd_set(pmd_t *pmdp, unsigned long val) +{ + *pmdp = __pmd(val); +} + +static inline void pmd_clear(pmd_t *pmdp) +{ + *pmdp = __pmd(0); +} + +#define pmd_none(pmd) (!pmd_val(pmd)) +#define pmd_present(pmd) (!pmd_none(pmd)) + +static inline void pud_set(pud_t *pudp, unsigned long val) +{ + *pudp = __pud(val); +} + +static inline void pud_clear(pud_t *pudp) +{ + *pudp = __pud(0); +} + +#define pud_none(pud) (!pud_val(pud)) +#define pud_present(pud) (pud_val(pud) != 0) + +extern struct page *pud_page(pud_t pud); +extern struct page *pmd_page(pmd_t pmd); +static inline pte_t pud_pte(pud_t pud) +{ + return __pte(pud_val(pud)); +} + +static inline pud_t pte_pud(pte_t pte) +{ + return __pud(pte_val(pte)); +} +#define pud_write(pud) pte_write(pud_pte(pud)) +#define pgd_write(pgd) pte_write(pgd_pte(pgd)) +static inline void pgd_set(pgd_t *pgdp, unsigned long val) +{ + *pgdp = __pgd(val); +} + +/* + * Find an entry in a page-table-directory. We combine the address region + * (the high order N bits) and the pgd portion of the address. + */ + +#define pgd_offset(mm, address) ((mm)->pgd + pgd_index(address)) + +#define pmd_offset(pudp,addr) \ + (((pmd_t *) pud_page_vaddr(*(pudp))) + pmd_index(addr)) + +#define pte_offset_kernel(dir,addr) \ + (((pte_t *) pmd_page_vaddr(*(dir))) + pte_index(addr)) + +#define pte_offset_map(dir,addr) pte_offset_kernel((dir), (addr)) +#define pte_unmap(pte) do { } while(0) + +/* to find an entry in a kernel page-table-directory */ +/* This now only contains the vmalloc pages */ +#define pgd_offset_k(address) pgd_offset(&init_mm, address) + +#define pte_ERROR(e) \ + pr_err("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e)) +#define pmd_ERROR(e) \ + pr_err("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e)) +#define pgd_ERROR(e) \ + pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e)) + +/* Encode and de-code a swap entry */ +#define MAX_SWAPFILES_CHECK() do { \ + BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS); \ + /* \ + * Don't have overlapping bits with _PAGE_HPTEFLAGS \ + * We filter HPTEFLAGS on set_pte. \ + */ \ + BUILD_BUG_ON(_PAGE_HPTEFLAGS & (0x1f << _PAGE_BIT_SWAP_TYPE)); \ + BUILD_BUG_ON(_PAGE_HPTEFLAGS & _PAGE_SWP_SOFT_DIRTY); \ + } while (0) +/* + * on pte we don't need handle RADIX_TREE_EXCEPTIONAL_SHIFT; + */ +#define SWP_TYPE_BITS 5 +#define __swp_type(x) (((x).val >> _PAGE_BIT_SWAP_TYPE) \ + & ((1UL << SWP_TYPE_BITS) - 1)) +#define __swp_offset(x) ((x).val >> PTE_RPN_SHIFT) +#define __swp_entry(type, offset) ((swp_entry_t) { \ + ((type) << _PAGE_BIT_SWAP_TYPE) \ + | ((offset) << PTE_RPN_SHIFT) }) +/* + * swp_entry_t must be independent of pte bits. We build a swp_entry_t from + * swap type and offset we get from swap and convert that to pte to find a + * matching pte in linux page table. + * Clear bits not found in swap entries here. + */ +#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val((pte)) & ~_PAGE_PTE }) +#define __swp_entry_to_pte(x) __pte((x).val | _PAGE_PTE) + +#ifdef CONFIG_MEM_SOFT_DIRTY +#define _PAGE_SWP_SOFT_DIRTY (1UL << (SWP_TYPE_BITS + _PAGE_BIT_SWAP_TYPE)) +#else +#define _PAGE_SWP_SOFT_DIRTY 0UL +#endif /* CONFIG_MEM_SOFT_DIRTY */ + +#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY +static inline pte_t pte_swp_mksoft_dirty(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_SWP_SOFT_DIRTY); +} +static inline bool pte_swp_soft_dirty(pte_t pte) +{ + return !!(pte_val(pte) & _PAGE_SWP_SOFT_DIRTY); +} +static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) +{ + return __pte(pte_val(pte) & ~_PAGE_SWP_SOFT_DIRTY); +} +#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ + +void pgtable_cache_add(unsigned shift, void (*ctor)(void *)); +void pgtable_cache_init(void); + +struct page *realmode_pfn_to_page(unsigned long pfn); + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +extern pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot); +extern pmd_t mk_pmd(struct page *page, pgprot_t pgprot); +extern pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot); +extern void set_pmd_at(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp, pmd_t pmd); +extern void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmd); +extern int has_transparent_hugepage(void); +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + + +static inline pte_t pmd_pte(pmd_t pmd) +{ + return __pte(pmd_val(pmd)); +} + +static inline pmd_t pte_pmd(pte_t pte) +{ + return __pmd(pte_val(pte)); +} + +static inline pte_t *pmdp_ptep(pmd_t *pmd) +{ + return (pte_t *)pmd; +} + +#define pmd_pfn(pmd) pte_pfn(pmd_pte(pmd)) +#define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd)) +#define pmd_young(pmd) pte_young(pmd_pte(pmd)) +#define pmd_mkold(pmd) pte_pmd(pte_mkold(pmd_pte(pmd))) +#define pmd_wrprotect(pmd) pte_pmd(pte_wrprotect(pmd_pte(pmd))) +#define pmd_mkdirty(pmd) pte_pmd(pte_mkdirty(pmd_pte(pmd))) +#define pmd_mkyoung(pmd) pte_pmd(pte_mkyoung(pmd_pte(pmd))) +#define pmd_mkwrite(pmd) pte_pmd(pte_mkwrite(pmd_pte(pmd))) + +#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY +#define pmd_soft_dirty(pmd) pte_soft_dirty(pmd_pte(pmd)) +#define pmd_mksoft_dirty(pmd) pte_pmd(pte_mksoft_dirty(pmd_pte(pmd))) +#define pmd_clear_soft_dirty(pmd) pte_pmd(pte_clear_soft_dirty(pmd_pte(pmd))) +#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ + +#ifdef CONFIG_NUMA_BALANCING +static inline int pmd_protnone(pmd_t pmd) +{ + return pte_protnone(pmd_pte(pmd)); +} +#endif /* CONFIG_NUMA_BALANCING */ + +#define __HAVE_ARCH_PMD_WRITE +#define pmd_write(pmd) pte_write(pmd_pte(pmd)) + +static inline pmd_t pmd_mkhuge(pmd_t pmd) +{ + return __pmd(pmd_val(pmd) | (_PAGE_PTE | _PAGE_THP_HUGE)); +} + +#define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS +extern int pmdp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp, + pmd_t entry, int dirty); + +#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG +extern int pmdp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp); +#define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH +extern int pmdp_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp); + +#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR +extern pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, + unsigned long addr, pmd_t *pmdp); + +#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH +extern void pmdp_splitting_flush(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp); + +extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp); +#define pmdp_collapse_flush pmdp_collapse_flush + +#define __HAVE_ARCH_PGTABLE_DEPOSIT +extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, + pgtable_t pgtable); +#define __HAVE_ARCH_PGTABLE_WITHDRAW +extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); + +#define __HAVE_ARCH_PMDP_INVALIDATE +extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmdp); + +#define pmd_move_must_withdraw pmd_move_must_withdraw +struct spinlock; +static inline int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl, + struct spinlock *old_pmd_ptl) +{ + /* + * Archs like ppc64 use pgtable to store per pmd + * specific information. So when we switch the pmd, + * we should also withdraw and deposit the pgtable + */ + return true; +} +#endif /* __ASSEMBLY__ */ +#endif /* _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ */ diff --git a/arch/powerpc/include/asm/book3s/pgtable.h b/arch/powerpc/include/asm/book3s/pgtable.h new file mode 100644 index 000000000000..8b0f4a29259a --- /dev/null +++ b/arch/powerpc/include/asm/book3s/pgtable.h @@ -0,0 +1,29 @@ +#ifndef _ASM_POWERPC_BOOK3S_PGTABLE_H +#define _ASM_POWERPC_BOOK3S_PGTABLE_H + +#ifdef CONFIG_PPC64 +#include <asm/book3s/64/pgtable.h> +#else +#include <asm/book3s/32/pgtable.h> +#endif + +#define FIRST_USER_ADDRESS 0UL +#ifndef __ASSEMBLY__ +/* Insert a PTE, top-level function is out of line. It uses an inline + * low level function in the respective pgtable-* files + */ +extern void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, + pte_t pte); + + +#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS +extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, + pte_t *ptep, pte_t entry, int dirty); + +struct file; +extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, + unsigned long size, pgprot_t vma_prot); +#define __HAVE_PHYS_MEM_ACCESS_PROT + +#endif /* __ASSEMBLY__ */ +#endif diff --git a/arch/powerpc/include/asm/cmpxchg.h b/arch/powerpc/include/asm/cmpxchg.h index ad6263cffb0f..d1a8d93cccfd 100644 --- a/arch/powerpc/include/asm/cmpxchg.h +++ b/arch/powerpc/include/asm/cmpxchg.h @@ -18,12 +18,12 @@ __xchg_u32(volatile void *p, unsigned long val) unsigned long prev; __asm__ __volatile__( - PPC_RELEASE_BARRIER + PPC_ATOMIC_ENTRY_BARRIER "1: lwarx %0,0,%2 \n" PPC405_ERR77(0,%2) " stwcx. %3,0,%2 \n\ bne- 1b" - PPC_ACQUIRE_BARRIER + PPC_ATOMIC_EXIT_BARRIER : "=&r" (prev), "+m" (*(volatile unsigned int *)p) : "r" (p), "r" (val) : "cc", "memory"); @@ -61,12 +61,12 @@ __xchg_u64(volatile void *p, unsigned long val) unsigned long prev; __asm__ __volatile__( - PPC_RELEASE_BARRIER + PPC_ATOMIC_ENTRY_BARRIER "1: ldarx %0,0,%2 \n" PPC405_ERR77(0,%2) " stdcx. %3,0,%2 \n\ bne- 1b" - PPC_ACQUIRE_BARRIER + PPC_ATOMIC_EXIT_BARRIER : "=&r" (prev), "+m" (*(volatile unsigned long *)p) : "r" (p), "r" (val) : "cc", "memory"); @@ -151,14 +151,14 @@ __cmpxchg_u32(volatile unsigned int *p, unsigned long old, unsigned long new) unsigned int prev; __asm__ __volatile__ ( - PPC_RELEASE_BARRIER + PPC_ATOMIC_ENTRY_BARRIER "1: lwarx %0,0,%2 # __cmpxchg_u32\n\ cmpw 0,%0,%3\n\ bne- 2f\n" PPC405_ERR77(0,%2) " stwcx. %4,0,%2\n\ bne- 1b" - PPC_ACQUIRE_BARRIER + PPC_ATOMIC_EXIT_BARRIER "\n\ 2:" : "=&r" (prev), "+m" (*p) @@ -197,13 +197,13 @@ __cmpxchg_u64(volatile unsigned long *p, unsigned long old, unsigned long new) unsigned long prev; __asm__ __volatile__ ( - PPC_RELEASE_BARRIER + PPC_ATOMIC_ENTRY_BARRIER "1: ldarx %0,0,%2 # __cmpxchg_u64\n\ cmpd 0,%0,%3\n\ bne- 2f\n\ stdcx. %4,0,%2\n\ bne- 1b" - PPC_ACQUIRE_BARRIER + PPC_ATOMIC_EXIT_BARRIER "\n\ 2:" : "=&r" (prev), "+m" (*p) diff --git a/arch/powerpc/include/asm/cpm.h b/arch/powerpc/include/asm/cpm.h index 4398a6cdcf53..2c5c5b476804 100644 --- a/arch/powerpc/include/asm/cpm.h +++ b/arch/powerpc/include/asm/cpm.h @@ -5,6 +5,7 @@ #include <linux/types.h> #include <linux/errno.h> #include <linux/of.h> +#include <soc/fsl/qe/qe.h> /* * SPI Parameter RAM common to QE and CPM. @@ -155,49 +156,6 @@ typedef struct cpm_buf_desc { */ #define BD_I2C_START (0x0400) -int cpm_muram_init(void); - -#if defined(CONFIG_CPM) || defined(CONFIG_QUICC_ENGINE) -unsigned long cpm_muram_alloc(unsigned long size, unsigned long align); -int cpm_muram_free(unsigned long offset); -unsigned long cpm_muram_alloc_fixed(unsigned long offset, unsigned long size); -void __iomem *cpm_muram_addr(unsigned long offset); -unsigned long cpm_muram_offset(void __iomem *addr); -dma_addr_t cpm_muram_dma(void __iomem *addr); -#else -static inline unsigned long cpm_muram_alloc(unsigned long size, - unsigned long align) -{ - return -ENOSYS; -} - -static inline int cpm_muram_free(unsigned long offset) -{ - return -ENOSYS; -} - -static inline unsigned long cpm_muram_alloc_fixed(unsigned long offset, - unsigned long size) -{ - return -ENOSYS; -} - -static inline void __iomem *cpm_muram_addr(unsigned long offset) -{ - return NULL; -} - -static inline unsigned long cpm_muram_offset(void __iomem *addr) -{ - return -ENOSYS; -} - -static inline dma_addr_t cpm_muram_dma(void __iomem *addr) -{ - return 0; -} -#endif /* defined(CONFIG_CPM) || defined(CONFIG_QUICC_ENGINE) */ - #ifdef CONFIG_CPM int cpm_command(u32 command, u8 opcode); #else diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index 77f52b26dad6..93ae809fe5ea 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -130,15 +130,6 @@ BEGIN_FTR_SECTION_NESTED(941) \ END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,941) /* - * Increase the priority on systems where PPR save/restore is not - * implemented/ supported. - */ -#define HMT_MEDIUM_PPR_DISCARD \ -BEGIN_FTR_SECTION_NESTED(942) \ - HMT_MEDIUM; \ -END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,0,942) /*non P7*/ - -/* * Get an SPR into a register if the CPU has the given feature */ #define OPT_GET_SPR(ra, spr, ftr) \ @@ -263,17 +254,6 @@ do_kvm_##n: \ #define KVM_HANDLER_SKIP(area, h, n) #endif -#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE -#define KVMTEST_PR(n) __KVMTEST(n) -#define KVM_HANDLER_PR(area, h, n) __KVM_HANDLER(area, h, n) -#define KVM_HANDLER_PR_SKIP(area, h, n) __KVM_HANDLER_SKIP(area, h, n) - -#else -#define KVMTEST_PR(n) -#define KVM_HANDLER_PR(area, h, n) -#define KVM_HANDLER_PR_SKIP(area, h, n) -#endif - #define NOTEST(n) /* @@ -353,27 +333,25 @@ do_kvm_##n: \ /* * Exception vectors. */ -#define STD_EXCEPTION_PSERIES(loc, vec, label) \ - . = loc; \ +#define STD_EXCEPTION_PSERIES(vec, label) \ + . = vec; \ .globl label##_pSeries; \ label##_pSeries: \ - HMT_MEDIUM_PPR_DISCARD; \ SET_SCRATCH0(r13); /* save r13 */ \ EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common, \ - EXC_STD, KVMTEST_PR, vec) + EXC_STD, KVMTEST, vec) /* Version of above for when we have to branch out-of-line */ #define STD_EXCEPTION_PSERIES_OOL(vec, label) \ .globl label##_pSeries; \ label##_pSeries: \ - EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST_PR, vec); \ + EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST, vec); \ EXCEPTION_PROLOG_PSERIES_1(label##_common, EXC_STD) #define STD_EXCEPTION_HV(loc, vec, label) \ . = loc; \ .globl label##_hv; \ label##_hv: \ - HMT_MEDIUM_PPR_DISCARD; \ SET_SCRATCH0(r13); /* save r13 */ \ EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common, \ EXC_HV, KVMTEST, vec) @@ -389,7 +367,6 @@ label##_hv: \ . = loc; \ .globl label##_relon_pSeries; \ label##_relon_pSeries: \ - HMT_MEDIUM_PPR_DISCARD; \ /* No guest interrupts come through here */ \ SET_SCRATCH0(r13); /* save r13 */ \ EXCEPTION_RELON_PROLOG_PSERIES(PACA_EXGEN, label##_common, \ @@ -405,7 +382,6 @@ label##_relon_pSeries: \ . = loc; \ .globl label##_relon_hv; \ label##_relon_hv: \ - HMT_MEDIUM_PPR_DISCARD; \ /* No guest interrupts come through here */ \ SET_SCRATCH0(r13); /* save r13 */ \ EXCEPTION_RELON_PROLOG_PSERIES(PACA_EXGEN, label##_common, \ @@ -436,17 +412,13 @@ label##_relon_hv: \ #define _SOFTEN_TEST(h, vec) __SOFTEN_TEST(h, vec) #define SOFTEN_TEST_PR(vec) \ - KVMTEST_PR(vec); \ + KVMTEST(vec); \ _SOFTEN_TEST(EXC_STD, vec) #define SOFTEN_TEST_HV(vec) \ KVMTEST(vec); \ _SOFTEN_TEST(EXC_HV, vec) -#define SOFTEN_TEST_HV_201(vec) \ - KVMTEST(vec); \ - _SOFTEN_TEST(EXC_STD, vec) - #define SOFTEN_NOTEST_PR(vec) _SOFTEN_TEST(EXC_STD, vec) #define SOFTEN_NOTEST_HV(vec) _SOFTEN_TEST(EXC_HV, vec) @@ -463,7 +435,6 @@ label##_relon_hv: \ . = loc; \ .globl label##_pSeries; \ label##_pSeries: \ - HMT_MEDIUM_PPR_DISCARD; \ _MASKABLE_EXCEPTION_PSERIES(vec, label, \ EXC_STD, SOFTEN_TEST_PR) @@ -481,7 +452,6 @@ label##_hv: \ EXCEPTION_PROLOG_PSERIES_1(label##_common, EXC_HV); #define __MASKABLE_RELON_EXCEPTION_PSERIES(vec, label, h, extra) \ - HMT_MEDIUM_PPR_DISCARD; \ SET_SCRATCH0(r13); /* save r13 */ \ EXCEPTION_PROLOG_0(PACA_EXGEN); \ __EXCEPTION_PROLOG_1(PACA_EXGEN, extra, vec); \ diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h index e05808a328db..b0629249778b 100644 --- a/arch/powerpc/include/asm/firmware.h +++ b/arch/powerpc/include/asm/firmware.h @@ -47,12 +47,10 @@ #define FW_FEATURE_VPHN ASM_CONST(0x0000000004000000) #define FW_FEATURE_XCMO ASM_CONST(0x0000000008000000) #define FW_FEATURE_OPAL ASM_CONST(0x0000000010000000) -#define FW_FEATURE_OPALv2 ASM_CONST(0x0000000020000000) #define FW_FEATURE_SET_MODE ASM_CONST(0x0000000040000000) #define FW_FEATURE_BEST_ENERGY ASM_CONST(0x0000000080000000) #define FW_FEATURE_TYPE1_AFFINITY ASM_CONST(0x0000000100000000) #define FW_FEATURE_PRRN ASM_CONST(0x0000000200000000) -#define FW_FEATURE_OPALv3 ASM_CONST(0x0000000400000000) #ifndef __ASSEMBLY__ @@ -70,8 +68,7 @@ enum { FW_FEATURE_SET_MODE | FW_FEATURE_BEST_ENERGY | FW_FEATURE_TYPE1_AFFINITY | FW_FEATURE_PRRN, FW_FEATURE_PSERIES_ALWAYS = 0, - FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL | FW_FEATURE_OPALv2 | - FW_FEATURE_OPALv3, + FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL, FW_FEATURE_POWERNV_ALWAYS = 0, FW_FEATURE_PS3_POSSIBLE = FW_FEATURE_LPAR | FW_FEATURE_PS3_LV1, FW_FEATURE_PS3_ALWAYS = FW_FEATURE_LPAR | FW_FEATURE_PS3_LV1, diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index 5879fde56f3c..6c1297ec374c 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -385,6 +385,17 @@ static inline void __raw_writeq(unsigned long v, volatile void __iomem *addr) { *(volatile unsigned long __force *)PCI_FIX_ADDR(addr) = v; } + +/* + * Real mode version of the above. stdcix is only supposed to be used + * in hypervisor real mode as per the architecture spec. + */ +static inline void __raw_rm_writeq(u64 val, volatile void __iomem *paddr) +{ + __asm__ __volatile__("stdcix %0,0,%1" + : : "r" (val), "r" (paddr) : "memory"); +} + #endif /* __powerpc64__ */ /* diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h index ba3342bbdbda..7352d3f212df 100644 --- a/arch/powerpc/include/asm/mmu-hash64.h +++ b/arch/powerpc/include/asm/mmu-hash64.h @@ -21,7 +21,7 @@ * need for various slices related matters. Note that this isn't the * complete pgtable.h but only a portion of it. */ -#include <asm/pgtable-ppc64.h> +#include <asm/book3s/64/pgtable.h> #include <asm/bug.h> #include <asm/processor.h> diff --git a/arch/powerpc/include/asm/pgtable-ppc32.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index 9c326565d498..c82cbf52d19e 100644 --- a/arch/powerpc/include/asm/pgtable-ppc32.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -1,5 +1,5 @@ -#ifndef _ASM_POWERPC_PGTABLE_PPC32_H -#define _ASM_POWERPC_PGTABLE_PPC32_H +#ifndef _ASM_POWERPC_NOHASH_32_PGTABLE_H +#define _ASM_POWERPC_NOHASH_32_PGTABLE_H #include <asm-generic/pgtable-nopmd.h> @@ -106,17 +106,15 @@ extern int icache_44x_need_flush; */ #if defined(CONFIG_40x) -#include <asm/pte-40x.h> +#include <asm/nohash/32/pte-40x.h> #elif defined(CONFIG_44x) -#include <asm/pte-44x.h> +#include <asm/nohash/32/pte-44x.h> #elif defined(CONFIG_FSL_BOOKE) && defined(CONFIG_PTE_64BIT) -#include <asm/pte-book3e.h> +#include <asm/nohash/pte-book3e.h> #elif defined(CONFIG_FSL_BOOKE) -#include <asm/pte-fsl-booke.h> +#include <asm/nohash/32/pte-fsl-booke.h> #elif defined(CONFIG_8xx) -#include <asm/pte-8xx.h> -#else /* CONFIG_6xx */ -#include <asm/pte-hash32.h> +#include <asm/nohash/32/pte-8xx.h> #endif /* And here we include common definitions */ @@ -130,7 +128,12 @@ extern int icache_44x_need_flush; #define pmd_none(pmd) (!pmd_val(pmd)) #define pmd_bad(pmd) (pmd_val(pmd) & _PMD_BAD) #define pmd_present(pmd) (pmd_val(pmd) & _PMD_PRESENT_MASK) -#define pmd_clear(pmdp) do { pmd_val(*(pmdp)) = 0; } while (0) +static inline void pmd_clear(pmd_t *pmdp) +{ + *pmdp = __pmd(0); +} + + /* * When flushing the tlb entry for a page, we also need to flush the hash @@ -337,4 +340,4 @@ extern int get_pteptr(struct mm_struct *mm, unsigned long addr, pte_t **ptep, #endif /* !__ASSEMBLY__ */ -#endif /* _ASM_POWERPC_PGTABLE_PPC32_H */ +#endif /* __ASM_POWERPC_NOHASH_32_PGTABLE_H */ diff --git a/arch/powerpc/include/asm/pte-40x.h b/arch/powerpc/include/asm/nohash/32/pte-40x.h index 486b1ef81338..9624ebdacc47 100644 --- a/arch/powerpc/include/asm/pte-40x.h +++ b/arch/powerpc/include/asm/nohash/32/pte-40x.h @@ -1,5 +1,5 @@ -#ifndef _ASM_POWERPC_PTE_40x_H -#define _ASM_POWERPC_PTE_40x_H +#ifndef _ASM_POWERPC_NOHASH_32_PTE_40x_H +#define _ASM_POWERPC_NOHASH_32_PTE_40x_H #ifdef __KERNEL__ /* @@ -61,4 +61,4 @@ #define PTE_ATOMIC_UPDATES 1 #endif /* __KERNEL__ */ -#endif /* _ASM_POWERPC_PTE_40x_H */ +#endif /* _ASM_POWERPC_NOHASH_32_PTE_40x_H */ diff --git a/arch/powerpc/include/asm/pte-44x.h b/arch/powerpc/include/asm/nohash/32/pte-44x.h index 36f75fab23f5..fdab41c654ef 100644 --- a/arch/powerpc/include/asm/pte-44x.h +++ b/arch/powerpc/include/asm/nohash/32/pte-44x.h @@ -1,5 +1,5 @@ -#ifndef _ASM_POWERPC_PTE_44x_H -#define _ASM_POWERPC_PTE_44x_H +#ifndef _ASM_POWERPC_NOHASH_32_PTE_44x_H +#define _ASM_POWERPC_NOHASH_32_PTE_44x_H #ifdef __KERNEL__ /* @@ -94,4 +94,4 @@ #endif /* __KERNEL__ */ -#endif /* _ASM_POWERPC_PTE_44x_H */ +#endif /* _ASM_POWERPC_NOHASH_32_PTE_44x_H */ diff --git a/arch/powerpc/include/asm/pte-8xx.h b/arch/powerpc/include/asm/nohash/32/pte-8xx.h index a0e2ba960976..3742b1919661 100644 --- a/arch/powerpc/include/asm/pte-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/pte-8xx.h @@ -1,5 +1,5 @@ -#ifndef _ASM_POWERPC_PTE_8xx_H -#define _ASM_POWERPC_PTE_8xx_H +#ifndef _ASM_POWERPC_NOHASH_32_PTE_8xx_H +#define _ASM_POWERPC_NOHASH_32_PTE_8xx_H #ifdef __KERNEL__ /* @@ -62,4 +62,4 @@ _PAGE_HWWRITE | _PAGE_EXEC) #endif /* __KERNEL__ */ -#endif /* _ASM_POWERPC_PTE_8xx_H */ +#endif /* _ASM_POWERPC_NOHASH_32_PTE_8xx_H */ diff --git a/arch/powerpc/include/asm/pte-fsl-booke.h b/arch/powerpc/include/asm/nohash/32/pte-fsl-booke.h index 9f5c3d04a1a3..5422d00c6145 100644 --- a/arch/powerpc/include/asm/pte-fsl-booke.h +++ b/arch/powerpc/include/asm/nohash/32/pte-fsl-booke.h @@ -1,5 +1,5 @@ -#ifndef _ASM_POWERPC_PTE_FSL_BOOKE_H -#define _ASM_POWERPC_PTE_FSL_BOOKE_H +#ifndef _ASM_POWERPC_NOHASH_32_PTE_FSL_BOOKE_H +#define _ASM_POWERPC_NOHASH_32_PTE_FSL_BOOKE_H #ifdef __KERNEL__ /* PTE bit definitions for Freescale BookE SW loaded TLB MMU based @@ -37,4 +37,4 @@ #define PTE_WIMGE_SHIFT (6) #endif /* __KERNEL__ */ -#endif /* _ASM_POWERPC_PTE_FSL_BOOKE_H */ +#endif /* _ASM_POWERPC_NOHASH_32_PTE_FSL_BOOKE_H */ diff --git a/arch/powerpc/include/asm/pgtable-ppc64-4k.h b/arch/powerpc/include/asm/nohash/64/pgtable-4k.h index 132ee1d482c2..fc7d51753f81 100644 --- a/arch/powerpc/include/asm/pgtable-ppc64-4k.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable-4k.h @@ -1,5 +1,5 @@ -#ifndef _ASM_POWERPC_PGTABLE_PPC64_4K_H -#define _ASM_POWERPC_PGTABLE_PPC64_4K_H +#ifndef _ASM_POWERPC_NOHASH_64_PGTABLE_4K_H +#define _ASM_POWERPC_NOHASH_64_PGTABLE_4K_H /* * Entries per page directory level. The PTE level must use a 64b record * for each page table entry. The PMD and PGD level use a 32b record for @@ -55,11 +55,15 @@ #define pgd_none(pgd) (!pgd_val(pgd)) #define pgd_bad(pgd) (pgd_val(pgd) == 0) #define pgd_present(pgd) (pgd_val(pgd) != 0) -#define pgd_clear(pgdp) (pgd_val(*(pgdp)) = 0) #define pgd_page_vaddr(pgd) (pgd_val(pgd) & ~PGD_MASKED_BITS) #ifndef __ASSEMBLY__ +static inline void pgd_clear(pgd_t *pgdp) +{ + *pgdp = __pgd(0); +} + static inline pte_t pgd_pte(pgd_t pgd) { return __pte(pgd_val(pgd)); @@ -85,4 +89,4 @@ extern struct page *pgd_page(pgd_t pgd); #define remap_4k_pfn(vma, addr, pfn, prot) \ remap_pfn_range((vma), (addr), (pfn), PAGE_SIZE, (prot)) -#endif /* _ASM_POWERPC_PGTABLE_PPC64_4K_H */ +#endif /* _ _ASM_POWERPC_NOHASH_64_PGTABLE_4K_H */ diff --git a/arch/powerpc/include/asm/pgtable-ppc64-64k.h b/arch/powerpc/include/asm/nohash/64/pgtable-64k.h index 1de35bbd02a6..570fb30be21c 100644 --- a/arch/powerpc/include/asm/pgtable-ppc64-64k.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable-64k.h @@ -1,5 +1,5 @@ -#ifndef _ASM_POWERPC_PGTABLE_PPC64_64K_H -#define _ASM_POWERPC_PGTABLE_PPC64_64K_H +#ifndef _ASM_POWERPC_NOHASH_64_PGTABLE_64K_H +#define _ASM_POWERPC_NOHASH_64_PGTABLE_64K_H #include <asm-generic/pgtable-nopud.h> @@ -9,8 +9,19 @@ #define PUD_INDEX_SIZE 0 #define PGD_INDEX_SIZE 12 +/* + * we support 32 fragments per PTE page of 64K size + */ +#define PTE_FRAG_NR 32 +/* + * We use a 2K PTE page fragment and another 2K for storing + * real_pte_t hash index + */ +#define PTE_FRAG_SIZE_SHIFT 11 +#define PTE_FRAG_SIZE (1UL << PTE_FRAG_SIZE_SHIFT) + #ifndef __ASSEMBLY__ -#define PTE_TABLE_SIZE (sizeof(real_pte_t) << PTE_INDEX_SIZE) +#define PTE_TABLE_SIZE PTE_FRAG_SIZE #define PMD_TABLE_SIZE (sizeof(pmd_t) << PMD_INDEX_SIZE) #define PGD_TABLE_SIZE (sizeof(pgd_t) << PGD_INDEX_SIZE) #endif /* __ASSEMBLY__ */ @@ -32,13 +43,15 @@ #define PGDIR_SIZE (1UL << PGDIR_SHIFT) #define PGDIR_MASK (~(PGDIR_SIZE-1)) -/* Bits to mask out from a PMD to get to the PTE page */ -/* PMDs point to PTE table fragments which are 4K aligned. */ -#define PMD_MASKED_BITS 0xfff +/* + * Bits to mask out from a PMD to get to the PTE page + * PMDs point to PTE table fragments which are PTE_FRAG_SIZE aligned. + */ +#define PMD_MASKED_BITS (PTE_FRAG_SIZE - 1) /* Bits to mask out from a PGD/PUD to get to the PMD page */ #define PUD_MASKED_BITS 0x1ff #define pgd_pte(pgd) (pud_pte(((pud_t){ pgd }))) #define pte_pgd(pte) ((pgd_t)pte_pud(pte)) -#endif /* _ASM_POWERPC_PGTABLE_PPC64_64K_H */ +#endif /* _ASM_POWERPC_NOHASH_64_PGTABLE_64K_H */ diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/nohash/64/pgtable.h index 3245f2d96d4f..b9f734dd5b81 100644 --- a/arch/powerpc/include/asm/pgtable-ppc64.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h @@ -1,14 +1,14 @@ -#ifndef _ASM_POWERPC_PGTABLE_PPC64_H_ -#define _ASM_POWERPC_PGTABLE_PPC64_H_ +#ifndef _ASM_POWERPC_NOHASH_64_PGTABLE_H +#define _ASM_POWERPC_NOHASH_64_PGTABLE_H /* * This file contains the functions and defines necessary to modify and use * the ppc64 hashed page table. */ #ifdef CONFIG_PPC_64K_PAGES -#include <asm/pgtable-ppc64-64k.h> +#include <asm/nohash/64/pgtable-64k.h> #else -#include <asm/pgtable-ppc64-4k.h> +#include <asm/nohash/64/pgtable-4k.h> #endif #include <asm/barrier.h> @@ -18,7 +18,7 @@ * Size of EA range mapped by our pagetables. */ #define PGTABLE_EADDR_SIZE (PTE_INDEX_SIZE + PMD_INDEX_SIZE + \ - PUD_INDEX_SIZE + PGD_INDEX_SIZE + PAGE_SHIFT) + PUD_INDEX_SIZE + PGD_INDEX_SIZE + PAGE_SHIFT) #define PGTABLE_RANGE (ASM_CONST(1) << PGTABLE_EADDR_SIZE) #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -97,11 +97,7 @@ /* * Include the PTE bits definitions */ -#ifdef CONFIG_PPC_BOOK3S -#include <asm/pte-hash64.h> -#else -#include <asm/pte-book3e.h> -#endif +#include <asm/nohash/pte-book3e.h> #include <asm/pte-common.h> #ifdef CONFIG_PPC_MM_SLICES @@ -110,59 +106,47 @@ #endif /* CONFIG_PPC_MM_SLICES */ #ifndef __ASSEMBLY__ - -/* - * This is the default implementation of various PTE accessors, it's - * used in all cases except Book3S with 64K pages where we have a - * concept of sub-pages - */ -#ifndef __real_pte - -#ifdef CONFIG_STRICT_MM_TYPECHECKS -#define __real_pte(e,p) ((real_pte_t){(e)}) -#define __rpte_to_pte(r) ((r).pte) -#else -#define __real_pte(e,p) (e) -#define __rpte_to_pte(r) (__pte(r)) -#endif -#define __rpte_to_hidx(r,index) (pte_val(__rpte_to_pte(r)) >> 12) - -#define pte_iterate_hashed_subpages(rpte, psize, va, index, shift) \ - do { \ - index = 0; \ - shift = mmu_psize_defs[psize].shift; \ - -#define pte_iterate_hashed_end() } while(0) - -/* - * We expect this to be called only for user addresses or kernel virtual - * addresses other than the linear mapping. - */ -#define pte_pagesize_index(mm, addr, pte) MMU_PAGE_4K - -#endif /* __real_pte */ - - /* pte_clear moved to later in this file */ #define PMD_BAD_BITS (PTE_TABLE_SIZE-1) #define PUD_BAD_BITS (PMD_TABLE_SIZE-1) -#define pmd_set(pmdp, pmdval) (pmd_val(*(pmdp)) = (pmdval)) +static inline void pmd_set(pmd_t *pmdp, unsigned long val) +{ + *pmdp = __pmd(val); +} + +static inline void pmd_clear(pmd_t *pmdp) +{ + *pmdp = __pmd(0); +} + +static inline pte_t pmd_pte(pmd_t pmd) +{ + return __pte(pmd_val(pmd)); +} + #define pmd_none(pmd) (!pmd_val(pmd)) #define pmd_bad(pmd) (!is_kernel_addr(pmd_val(pmd)) \ || (pmd_val(pmd) & PMD_BAD_BITS)) #define pmd_present(pmd) (!pmd_none(pmd)) -#define pmd_clear(pmdp) (pmd_val(*(pmdp)) = 0) #define pmd_page_vaddr(pmd) (pmd_val(pmd) & ~PMD_MASKED_BITS) extern struct page *pmd_page(pmd_t pmd); -#define pud_set(pudp, pudval) (pud_val(*(pudp)) = (pudval)) +static inline void pud_set(pud_t *pudp, unsigned long val) +{ + *pudp = __pud(val); +} + +static inline void pud_clear(pud_t *pudp) +{ + *pudp = __pud(0); +} + #define pud_none(pud) (!pud_val(pud)) #define pud_bad(pud) (!is_kernel_addr(pud_val(pud)) \ || (pud_val(pud) & PUD_BAD_BITS)) #define pud_present(pud) (pud_val(pud) != 0) -#define pud_clear(pudp) (pud_val(*(pudp)) = 0) #define pud_page_vaddr(pud) (pud_val(pud) & ~PUD_MASKED_BITS) extern struct page *pud_page(pud_t pud); @@ -177,9 +161,13 @@ static inline pud_t pte_pud(pte_t pte) return __pud(pte_val(pte)); } #define pud_write(pud) pte_write(pud_pte(pud)) -#define pgd_set(pgdp, pudp) ({pgd_val(*(pgdp)) = (unsigned long)(pudp);}) #define pgd_write(pgd) pte_write(pgd_pte(pgd)) +static inline void pgd_set(pgd_t *pgdp, unsigned long val) +{ + *pgdp = __pgd(val); +} + /* * Find an entry in a page-table-directory. We combine the address region * (the high order N bits) and the pgd portion of the address. @@ -373,254 +361,4 @@ void pgtable_cache_add(unsigned shift, void (*ctor)(void *)); void pgtable_cache_init(void); #endif /* __ASSEMBLY__ */ -/* - * THP pages can't be special. So use the _PAGE_SPECIAL - */ -#define _PAGE_SPLITTING _PAGE_SPECIAL - -/* - * We need to differentiate between explicit huge page and THP huge - * page, since THP huge page also need to track real subpage details - */ -#define _PAGE_THP_HUGE _PAGE_4K_PFN - -/* - * set of bits not changed in pmd_modify. - */ -#define _HPAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS | \ - _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_SPLITTING | \ - _PAGE_THP_HUGE) - -#ifndef __ASSEMBLY__ -/* - * The linux hugepage PMD now include the pmd entries followed by the address - * to the stashed pgtable_t. The stashed pgtable_t contains the hpte bits. - * [ 1 bit secondary | 3 bit hidx | 1 bit valid | 000]. We use one byte per - * each HPTE entry. With 16MB hugepage and 64K HPTE we need 256 entries and - * with 4K HPTE we need 4096 entries. Both will fit in a 4K pgtable_t. - * - * The last three bits are intentionally left to zero. This memory location - * are also used as normal page PTE pointers. So if we have any pointers - * left around while we collapse a hugepage, we need to make sure - * _PAGE_PRESENT bit of that is zero when we look at them - */ -static inline unsigned int hpte_valid(unsigned char *hpte_slot_array, int index) -{ - return (hpte_slot_array[index] >> 3) & 0x1; -} - -static inline unsigned int hpte_hash_index(unsigned char *hpte_slot_array, - int index) -{ - return hpte_slot_array[index] >> 4; -} - -static inline void mark_hpte_slot_valid(unsigned char *hpte_slot_array, - unsigned int index, unsigned int hidx) -{ - hpte_slot_array[index] = hidx << 4 | 0x1 << 3; -} - -struct page *realmode_pfn_to_page(unsigned long pfn); - -static inline char *get_hpte_slot_array(pmd_t *pmdp) -{ - /* - * The hpte hindex is stored in the pgtable whose address is in the - * second half of the PMD - * - * Order this load with the test for pmd_trans_huge in the caller - */ - smp_rmb(); - return *(char **)(pmdp + PTRS_PER_PMD); - - -} - -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -extern void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr, - pmd_t *pmdp, unsigned long old_pmd); -extern pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot); -extern pmd_t mk_pmd(struct page *page, pgprot_t pgprot); -extern pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot); -extern void set_pmd_at(struct mm_struct *mm, unsigned long addr, - pmd_t *pmdp, pmd_t pmd); -extern void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr, - pmd_t *pmd); -/* - * - * For core kernel code by design pmd_trans_huge is never run on any hugetlbfs - * page. The hugetlbfs page table walking and mangling paths are totally - * separated form the core VM paths and they're differentiated by - * VM_HUGETLB being set on vm_flags well before any pmd_trans_huge could run. - * - * pmd_trans_huge() is defined as false at build time if - * CONFIG_TRANSPARENT_HUGEPAGE=n to optimize away code blocks at build - * time in such case. - * - * For ppc64 we need to differntiate from explicit hugepages from THP, because - * for THP we also track the subpage details at the pmd level. We don't do - * that for explicit huge pages. - * - */ -static inline int pmd_trans_huge(pmd_t pmd) -{ - /* - * leaf pte for huge page, bottom two bits != 00 - */ - return (pmd_val(pmd) & 0x3) && (pmd_val(pmd) & _PAGE_THP_HUGE); -} - -static inline int pmd_trans_splitting(pmd_t pmd) -{ - if (pmd_trans_huge(pmd)) - return pmd_val(pmd) & _PAGE_SPLITTING; - return 0; -} - -extern int has_transparent_hugepage(void); -#else -static inline void hpte_do_hugepage_flush(struct mm_struct *mm, - unsigned long addr, pmd_t *pmdp, - unsigned long old_pmd) -{ - - WARN(1, "%s called with THP disabled\n", __func__); -} -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ - -static inline int pmd_large(pmd_t pmd) -{ - /* - * leaf pte for huge page, bottom two bits != 00 - */ - return ((pmd_val(pmd) & 0x3) != 0x0); -} - -static inline pte_t pmd_pte(pmd_t pmd) -{ - return __pte(pmd_val(pmd)); -} - -static inline pmd_t pte_pmd(pte_t pte) -{ - return __pmd(pte_val(pte)); -} - -static inline pte_t *pmdp_ptep(pmd_t *pmd) -{ - return (pte_t *)pmd; -} - -#define pmd_pfn(pmd) pte_pfn(pmd_pte(pmd)) -#define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd)) -#define pmd_young(pmd) pte_young(pmd_pte(pmd)) -#define pmd_mkold(pmd) pte_pmd(pte_mkold(pmd_pte(pmd))) -#define pmd_wrprotect(pmd) pte_pmd(pte_wrprotect(pmd_pte(pmd))) -#define pmd_mkdirty(pmd) pte_pmd(pte_mkdirty(pmd_pte(pmd))) -#define pmd_mkyoung(pmd) pte_pmd(pte_mkyoung(pmd_pte(pmd))) -#define pmd_mkwrite(pmd) pte_pmd(pte_mkwrite(pmd_pte(pmd))) - -#define __HAVE_ARCH_PMD_WRITE -#define pmd_write(pmd) pte_write(pmd_pte(pmd)) - -static inline pmd_t pmd_mkhuge(pmd_t pmd) -{ - /* Do nothing, mk_pmd() does this part. */ - return pmd; -} - -static inline pmd_t pmd_mknotpresent(pmd_t pmd) -{ - pmd_val(pmd) &= ~_PAGE_PRESENT; - return pmd; -} - -static inline pmd_t pmd_mksplitting(pmd_t pmd) -{ - pmd_val(pmd) |= _PAGE_SPLITTING; - return pmd; -} - -#define __HAVE_ARCH_PMD_SAME -static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b) -{ - return (((pmd_val(pmd_a) ^ pmd_val(pmd_b)) & ~_PAGE_HPTEFLAGS) == 0); -} - -#define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS -extern int pmdp_set_access_flags(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmdp, - pmd_t entry, int dirty); - -extern unsigned long pmd_hugepage_update(struct mm_struct *mm, - unsigned long addr, - pmd_t *pmdp, - unsigned long clr, - unsigned long set); - -static inline int __pmdp_test_and_clear_young(struct mm_struct *mm, - unsigned long addr, pmd_t *pmdp) -{ - unsigned long old; - - if ((pmd_val(*pmdp) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0) - return 0; - old = pmd_hugepage_update(mm, addr, pmdp, _PAGE_ACCESSED, 0); - return ((old & _PAGE_ACCESSED) != 0); -} - -#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG -extern int pmdp_test_and_clear_young(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmdp); -#define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH -extern int pmdp_clear_flush_young(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmdp); - -#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR -extern pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, - unsigned long addr, pmd_t *pmdp); - -#define __HAVE_ARCH_PMDP_SET_WRPROTECT -static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr, - pmd_t *pmdp) -{ - - if ((pmd_val(*pmdp) & _PAGE_RW) == 0) - return; - - pmd_hugepage_update(mm, addr, pmdp, _PAGE_RW, 0); -} - -#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH -extern void pmdp_splitting_flush(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmdp); - -extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmdp); -#define pmdp_collapse_flush pmdp_collapse_flush - -#define __HAVE_ARCH_PGTABLE_DEPOSIT -extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, - pgtable_t pgtable); -#define __HAVE_ARCH_PGTABLE_WITHDRAW -extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); - -#define __HAVE_ARCH_PMDP_INVALIDATE -extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, - pmd_t *pmdp); - -#define pmd_move_must_withdraw pmd_move_must_withdraw -struct spinlock; -static inline int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl, - struct spinlock *old_pmd_ptl) -{ - /* - * Archs like ppc64 use pgtable to store per pmd - * specific information. So when we switch the pmd, - * we should also withdraw and deposit the pgtable - */ - return true; -} -#endif /* __ASSEMBLY__ */ -#endif /* _ASM_POWERPC_PGTABLE_PPC64_H_ */ +#endif /* _ASM_POWERPC_NOHASH_64_PGTABLE_H */ diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h new file mode 100644 index 000000000000..1263c22d60d8 --- /dev/null +++ b/arch/powerpc/include/asm/nohash/pgtable.h @@ -0,0 +1,252 @@ +#ifndef _ASM_POWERPC_NOHASH_PGTABLE_H +#define _ASM_POWERPC_NOHASH_PGTABLE_H + +#if defined(CONFIG_PPC64) +#include <asm/nohash/64/pgtable.h> +#else +#include <asm/nohash/32/pgtable.h> +#endif + +#ifndef __ASSEMBLY__ + +/* Generic accessors to PTE bits */ +static inline int pte_write(pte_t pte) +{ + return (pte_val(pte) & (_PAGE_RW | _PAGE_RO)) != _PAGE_RO; +} +static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY; } +static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED; } +static inline int pte_special(pte_t pte) { return pte_val(pte) & _PAGE_SPECIAL; } +static inline int pte_none(pte_t pte) { return (pte_val(pte) & ~_PTE_NONE_MASK) == 0; } +static inline pgprot_t pte_pgprot(pte_t pte) { return __pgprot(pte_val(pte) & PAGE_PROT_BITS); } + +#ifdef CONFIG_NUMA_BALANCING +/* + * These work without NUMA balancing but the kernel does not care. See the + * comment in include/asm-generic/pgtable.h . On powerpc, this will only + * work for user pages and always return true for kernel pages. + */ +static inline int pte_protnone(pte_t pte) +{ + return (pte_val(pte) & + (_PAGE_PRESENT | _PAGE_USER)) == _PAGE_PRESENT; +} + +static inline int pmd_protnone(pmd_t pmd) +{ + return pte_protnone(pmd_pte(pmd)); +} +#endif /* CONFIG_NUMA_BALANCING */ + +static inline int pte_present(pte_t pte) +{ + return pte_val(pte) & _PAGE_PRESENT; +} + +/* Conversion functions: convert a page and protection to a page entry, + * and a page entry and page directory to the page they refer to. + * + * Even if PTEs can be unsigned long long, a PFN is always an unsigned + * long for now. + */ +static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot) { + return __pte(((pte_basic_t)(pfn) << PTE_RPN_SHIFT) | + pgprot_val(pgprot)); } +static inline unsigned long pte_pfn(pte_t pte) { + return pte_val(pte) >> PTE_RPN_SHIFT; } + +/* Generic modifiers for PTE bits */ +static inline pte_t pte_wrprotect(pte_t pte) +{ + pte_basic_t ptev; + + ptev = pte_val(pte) & ~(_PAGE_RW | _PAGE_HWWRITE); + ptev |= _PAGE_RO; + return __pte(ptev); +} + +static inline pte_t pte_mkclean(pte_t pte) +{ + return __pte(pte_val(pte) & ~(_PAGE_DIRTY | _PAGE_HWWRITE)); +} + +static inline pte_t pte_mkold(pte_t pte) +{ + return __pte(pte_val(pte) & ~_PAGE_ACCESSED); +} + +static inline pte_t pte_mkwrite(pte_t pte) +{ + pte_basic_t ptev; + + ptev = pte_val(pte) & ~_PAGE_RO; + ptev |= _PAGE_RW; + return __pte(ptev); +} + +static inline pte_t pte_mkdirty(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_DIRTY); +} + +static inline pte_t pte_mkyoung(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_ACCESSED); +} + +static inline pte_t pte_mkspecial(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_SPECIAL); +} + +static inline pte_t pte_mkhuge(pte_t pte) +{ + return pte; +} + +static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) +{ + return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot)); +} + +/* Insert a PTE, top-level function is out of line. It uses an inline + * low level function in the respective pgtable-* files + */ +extern void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, + pte_t pte); + +/* This low level function performs the actual PTE insertion + * Setting the PTE depends on the MMU type and other factors. It's + * an horrible mess that I'm not going to try to clean up now but + * I'm keeping it in one place rather than spread around + */ +static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte, int percpu) +{ +#if defined(CONFIG_PPC_STD_MMU_32) && defined(CONFIG_SMP) && !defined(CONFIG_PTE_64BIT) + /* First case is 32-bit Hash MMU in SMP mode with 32-bit PTEs. We use the + * helper pte_update() which does an atomic update. We need to do that + * because a concurrent invalidation can clear _PAGE_HASHPTE. If it's a + * per-CPU PTE such as a kmap_atomic, we do a simple update preserving + * the hash bits instead (ie, same as the non-SMP case) + */ + if (percpu) + *ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE) + | (pte_val(pte) & ~_PAGE_HASHPTE)); + else + pte_update(ptep, ~_PAGE_HASHPTE, pte_val(pte)); + +#elif defined(CONFIG_PPC32) && defined(CONFIG_PTE_64BIT) + /* Second case is 32-bit with 64-bit PTE. In this case, we + * can just store as long as we do the two halves in the right order + * with a barrier in between. This is possible because we take care, + * in the hash code, to pre-invalidate if the PTE was already hashed, + * which synchronizes us with any concurrent invalidation. + * In the percpu case, we also fallback to the simple update preserving + * the hash bits + */ + if (percpu) { + *ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE) + | (pte_val(pte) & ~_PAGE_HASHPTE)); + return; + } +#if _PAGE_HASHPTE != 0 + if (pte_val(*ptep) & _PAGE_HASHPTE) + flush_hash_entry(mm, ptep, addr); +#endif + __asm__ __volatile__("\ + stw%U0%X0 %2,%0\n\ + eieio\n\ + stw%U0%X0 %L2,%1" + : "=m" (*ptep), "=m" (*((unsigned char *)ptep+4)) + : "r" (pte) : "memory"); + +#elif defined(CONFIG_PPC_STD_MMU_32) + /* Third case is 32-bit hash table in UP mode, we need to preserve + * the _PAGE_HASHPTE bit since we may not have invalidated the previous + * translation in the hash yet (done in a subsequent flush_tlb_xxx()) + * and see we need to keep track that this PTE needs invalidating + */ + *ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE) + | (pte_val(pte) & ~_PAGE_HASHPTE)); + +#else + /* Anything else just stores the PTE normally. That covers all 64-bit + * cases, and 32-bit non-hash with 32-bit PTEs. + */ + *ptep = pte; + +#ifdef CONFIG_PPC_BOOK3E_64 + /* + * With hardware tablewalk, a sync is needed to ensure that + * subsequent accesses see the PTE we just wrote. Unlike userspace + * mappings, we can't tolerate spurious faults, so make sure + * the new PTE will be seen the first time. + */ + if (is_kernel_addr(addr)) + mb(); +#endif +#endif +} + + +#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS +extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, + pte_t *ptep, pte_t entry, int dirty); + +/* + * Macro to mark a page protection value as "uncacheable". + */ + +#define _PAGE_CACHE_CTL (_PAGE_COHERENT | _PAGE_GUARDED | _PAGE_NO_CACHE | \ + _PAGE_WRITETHRU) + +#define pgprot_noncached(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \ + _PAGE_NO_CACHE | _PAGE_GUARDED)) + +#define pgprot_noncached_wc(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \ + _PAGE_NO_CACHE)) + +#define pgprot_cached(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \ + _PAGE_COHERENT)) + +#define pgprot_cached_wthru(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \ + _PAGE_COHERENT | _PAGE_WRITETHRU)) + +#define pgprot_cached_noncoherent(prot) \ + (__pgprot(pgprot_val(prot) & ~_PAGE_CACHE_CTL)) + +#define pgprot_writecombine pgprot_noncached_wc + +struct file; +extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, + unsigned long size, pgprot_t vma_prot); +#define __HAVE_PHYS_MEM_ACCESS_PROT + +#ifdef CONFIG_HUGETLB_PAGE +static inline int hugepd_ok(hugepd_t hpd) +{ + return (hpd.pd > 0); +} + +static inline int pmd_huge(pmd_t pmd) +{ + return 0; +} + +static inline int pud_huge(pud_t pud) +{ + return 0; +} + +static inline int pgd_huge(pgd_t pgd) +{ + return 0; +} +#define pgd_huge pgd_huge + +#define is_hugepd(hpd) (hugepd_ok(hpd)) +#endif + +#endif /* __ASSEMBLY__ */ +#endif diff --git a/arch/powerpc/include/asm/pte-book3e.h b/arch/powerpc/include/asm/nohash/pte-book3e.h index 8d8473278d91..e16807b78edf 100644 --- a/arch/powerpc/include/asm/pte-book3e.h +++ b/arch/powerpc/include/asm/nohash/pte-book3e.h @@ -1,5 +1,5 @@ -#ifndef _ASM_POWERPC_PTE_BOOK3E_H -#define _ASM_POWERPC_PTE_BOOK3E_H +#ifndef _ASM_POWERPC_NOHASH_PTE_BOOK3E_H +#define _ASM_POWERPC_NOHASH_PTE_BOOK3E_H #ifdef __KERNEL__ /* PTE bit definitions for processors compliant to the Book3E @@ -84,4 +84,4 @@ #endif #endif /* __KERNEL__ */ -#endif /* _ASM_POWERPC_PTE_FSL_BOOKE_H */ +#endif /* _ASM_POWERPC_NOHASH_PTE_BOOK3E_H */ diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h index 8374afed9d0a..f8faaaeeca1e 100644 --- a/arch/powerpc/include/asm/opal-api.h +++ b/arch/powerpc/include/asm/opal-api.h @@ -157,7 +157,8 @@ #define OPAL_LEDS_GET_INDICATOR 114 #define OPAL_LEDS_SET_INDICATOR 115 #define OPAL_CEC_REBOOT2 116 -#define OPAL_LAST 116 +#define OPAL_CONSOLE_FLUSH 117 +#define OPAL_LAST 117 /* Device tree flags */ diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 800115910e43..07a99e638449 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -35,6 +35,7 @@ int64_t opal_console_read(int64_t term_number, __be64 *length, uint8_t *buffer); int64_t opal_console_write_buffer_space(int64_t term_number, __be64 *length); +int64_t opal_console_flush(int64_t term_number); int64_t opal_rtc_read(__be32 *year_month_day, __be64 *hour_minute_second_millisecond); int64_t opal_rtc_write(uint32_t year_month_day, @@ -262,6 +263,8 @@ extern int opal_resync_timebase(void); extern void opal_lpc_init(void); +extern void opal_kmsg_init(void); + extern int opal_event_request(unsigned int opal_event_nr); struct opal_sg_list *opal_vmalloc_to_sg_list(void *vmalloc_addr, diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 70bd4381f8e6..546540b91095 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -16,6 +16,7 @@ #ifdef CONFIG_PPC64 +#include <linux/string.h> #include <asm/types.h> #include <asm/lppaca.h> #include <asm/mmu.h> @@ -131,7 +132,16 @@ struct paca_struct { struct tlb_core_data tcd; #endif /* CONFIG_PPC_BOOK3E */ - mm_context_t context; +#ifdef CONFIG_PPC_BOOK3S + mm_context_id_t mm_ctx_id; +#ifdef CONFIG_PPC_MM_SLICES + u64 mm_ctx_low_slices_psize; + unsigned char mm_ctx_high_slices_psize[SLICE_ARRAY_SIZE]; +#else + u16 mm_ctx_user_psize; + u16 mm_ctx_sllp; +#endif +#endif /* * then miscellaneous read-write fields @@ -194,6 +204,23 @@ struct paca_struct { #endif }; +#ifdef CONFIG_PPC_BOOK3S +static inline void copy_mm_to_paca(mm_context_t *context) +{ + get_paca()->mm_ctx_id = context->id; +#ifdef CONFIG_PPC_MM_SLICES + get_paca()->mm_ctx_low_slices_psize = context->low_slices_psize; + memcpy(&get_paca()->mm_ctx_high_slices_psize, + &context->high_slices_psize, SLICE_ARRAY_SIZE); +#else + get_paca()->mm_ctx_user_psize = context->user_psize; + get_paca()->mm_ctx_sllp = context->sllp; +#endif +} +#else +static inline void copy_mm_to_paca(mm_context_t *context){} +#endif + extern struct paca_struct *paca; extern void initialise_paca(struct paca_struct *new_paca, int cpu); extern void setup_paca(struct paca_struct *new_paca); diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index 3140c19c448c..e34124f6fbf2 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -286,8 +286,11 @@ extern long long virt_phys_offset; /* PTE level */ typedef struct { pte_basic_t pte; } pte_t; -#define pte_val(x) ((x).pte) #define __pte(x) ((pte_t) { (x) }) +static inline pte_basic_t pte_val(pte_t x) +{ + return x.pte; +} /* 64k pages additionally define a bigger "real PTE" type that gathers * the "second half" part of the PTE for pseudo 64k pages @@ -301,21 +304,30 @@ typedef struct { pte_t pte; } real_pte_t; /* PMD level */ #ifdef CONFIG_PPC64 typedef struct { unsigned long pmd; } pmd_t; -#define pmd_val(x) ((x).pmd) #define __pmd(x) ((pmd_t) { (x) }) +static inline unsigned long pmd_val(pmd_t x) +{ + return x.pmd; +} /* PUD level exusts only on 4k pages */ #ifndef CONFIG_PPC_64K_PAGES typedef struct { unsigned long pud; } pud_t; -#define pud_val(x) ((x).pud) #define __pud(x) ((pud_t) { (x) }) +static inline unsigned long pud_val(pud_t x) +{ + return x.pud; +} #endif /* !CONFIG_PPC_64K_PAGES */ #endif /* CONFIG_PPC64 */ /* PGD level */ typedef struct { unsigned long pgd; } pgd_t; -#define pgd_val(x) ((x).pgd) #define __pgd(x) ((pgd_t) { (x) }) +static inline unsigned long pgd_val(pgd_t x) +{ + return x.pgd; +} /* Page protection bits */ typedef struct { unsigned long pgprot; } pgprot_t; @@ -329,8 +341,11 @@ typedef struct { unsigned long pgprot; } pgprot_t; */ typedef pte_basic_t pte_t; -#define pte_val(x) (x) #define __pte(x) (x) +static inline pte_basic_t pte_val(pte_t pte) +{ + return pte; +} #if defined(CONFIG_PPC_64K_PAGES) && defined(CONFIG_PPC_STD_MMU_64) typedef struct { pte_t pte; unsigned long hidx; } real_pte_t; @@ -341,67 +356,42 @@ typedef pte_t real_pte_t; #ifdef CONFIG_PPC64 typedef unsigned long pmd_t; -#define pmd_val(x) (x) #define __pmd(x) (x) +static inline unsigned long pmd_val(pmd_t pmd) +{ + return pmd; +} #ifndef CONFIG_PPC_64K_PAGES typedef unsigned long pud_t; -#define pud_val(x) (x) #define __pud(x) (x) +static inline unsigned long pud_val(pud_t pud) +{ + return pud; +} #endif /* !CONFIG_PPC_64K_PAGES */ #endif /* CONFIG_PPC64 */ typedef unsigned long pgd_t; -#define pgd_val(x) (x) -#define pgprot_val(x) (x) +#define __pgd(x) (x) +static inline unsigned long pgd_val(pgd_t pgd) +{ + return pgd; +} typedef unsigned long pgprot_t; -#define __pgd(x) (x) +#define pgprot_val(x) (x) #define __pgprot(x) (x) #endif typedef struct { signed long pd; } hugepd_t; -#ifdef CONFIG_HUGETLB_PAGE -#ifdef CONFIG_PPC_BOOK3S_64 -#ifdef CONFIG_PPC_64K_PAGES -/* - * With 64k page size, we have hugepage ptes in the pgd and pmd entries. We don't - * need to setup hugepage directory for them. Our pte and page directory format - * enable us to have this enabled. But to avoid errors when implementing new - * features disable hugepd for 64K. We enable a debug version here, So we catch - * wrong usage. - */ -#ifdef CONFIG_DEBUG_VM -extern int hugepd_ok(hugepd_t hpd); -#else -#define hugepd_ok(x) (0) -#endif -#else -static inline int hugepd_ok(hugepd_t hpd) -{ - /* - * hugepd pointer, bottom two bits == 00 and next 4 bits - * indicate size of table - */ - return (((hpd.pd & 0x3) == 0x0) && ((hpd.pd & HUGEPD_SHIFT_MASK) != 0)); -} -#endif -#else -static inline int hugepd_ok(hugepd_t hpd) -{ - return (hpd.pd > 0); -} -#endif - -#define is_hugepd(hpd) (hugepd_ok(hpd)) -#define pgd_huge pgd_huge -int pgd_huge(pgd_t pgd); -#else /* CONFIG_HUGETLB_PAGE */ -#define is_hugepd(pdep) 0 -#define pgd_huge(pgd) 0 +#ifndef CONFIG_HUGETLB_PAGE +#define is_hugepd(pdep) (0) +#define pgd_huge(pgd) (0) #endif /* CONFIG_HUGETLB_PAGE */ + #define __hugepd(x) ((hugepd_t) { (x) }) struct page; diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index 37fc53587bb4..54843ca5fa2b 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -205,6 +205,7 @@ struct pci_dn { int pci_ext_config_space; /* for pci devices */ + struct pci_dev *pcidev; /* back-pointer to the pci device */ #ifdef CONFIG_EEH struct eeh_dev *edev; /* eeh device */ #endif diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h index 3453bd8dc18f..6f8065a7d487 100644 --- a/arch/powerpc/include/asm/pci.h +++ b/arch/powerpc/include/asm/pci.h @@ -149,4 +149,8 @@ extern void pcibios_setup_phb_io_space(struct pci_controller *hose); extern void pcibios_scan_phb(struct pci_controller *hose); #endif /* __KERNEL__ */ + +extern struct pci_dev *pnv_pci_get_gpu_dev(struct pci_dev *npdev); +extern struct pci_dev *pnv_pci_get_npu_dev(struct pci_dev *gpdev, int index); + #endif /* __ASM_POWERPC_PCI_H */ diff --git a/arch/powerpc/include/asm/pgalloc-32.h b/arch/powerpc/include/asm/pgalloc-32.h index 842846c1b711..76d6b9e0c8a9 100644 --- a/arch/powerpc/include/asm/pgalloc-32.h +++ b/arch/powerpc/include/asm/pgalloc-32.h @@ -21,16 +21,34 @@ extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); /* #define pgd_populate(mm, pmd, pte) BUG() */ #ifndef CONFIG_BOOKE -#define pmd_populate_kernel(mm, pmd, pte) \ - (pmd_val(*(pmd)) = __pa(pte) | _PMD_PRESENT) -#define pmd_populate(mm, pmd, pte) \ - (pmd_val(*(pmd)) = (page_to_pfn(pte) << PAGE_SHIFT) | _PMD_PRESENT) + +static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, + pte_t *pte) +{ + *pmdp = __pmd(__pa(pte) | _PMD_PRESENT); +} + +static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmdp, + pgtable_t pte_page) +{ + *pmdp = __pmd((page_to_pfn(pte_page) << PAGE_SHIFT) | _PMD_PRESENT); +} + #define pmd_pgtable(pmd) pmd_page(pmd) #else -#define pmd_populate_kernel(mm, pmd, pte) \ - (pmd_val(*(pmd)) = (unsigned long)pte | _PMD_PRESENT) -#define pmd_populate(mm, pmd, pte) \ - (pmd_val(*(pmd)) = (unsigned long)lowmem_page_address(pte) | _PMD_PRESENT) + +static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, + pte_t *pte) +{ + *pmdp = __pmd((unsigned long)pte | _PMD_PRESENT); +} + +static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmdp, + pgtable_t pte_page) +{ + *pmdp = __pmd((unsigned long)lowmem_page_address(pte_page) | _PMD_PRESENT); +} + #define pmd_pgtable(pmd) pmd_page(pmd) #endif diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h index 4b0be20fcbfd..69ef28a81733 100644 --- a/arch/powerpc/include/asm/pgalloc-64.h +++ b/arch/powerpc/include/asm/pgalloc-64.h @@ -53,7 +53,7 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) #ifndef CONFIG_PPC_64K_PAGES -#define pgd_populate(MM, PGD, PUD) pgd_set(PGD, PUD) +#define pgd_populate(MM, PGD, PUD) pgd_set(PGD, (unsigned long)PUD) static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) { @@ -71,9 +71,18 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) pud_set(pud, (unsigned long)pmd); } -#define pmd_populate(mm, pmd, pte_page) \ - pmd_populate_kernel(mm, pmd, page_address(pte_page)) -#define pmd_populate_kernel(mm, pmd, pte) pmd_set(pmd, (unsigned long)(pte)) +static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, + pte_t *pte) +{ + pmd_set(pmd, (unsigned long)pte); +} + +static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, + pgtable_t pte_page) +{ + pmd_set(pmd, (unsigned long)page_address(pte_page)); +} + #define pmd_pgtable(pmd) pmd_page(pmd) static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, @@ -154,16 +163,6 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table, } #else /* if CONFIG_PPC_64K_PAGES */ -/* - * we support 16 fragments per PTE page. - */ -#define PTE_FRAG_NR 16 -/* - * We use a 2K PTE page fragment and another 2K for storing - * real_pte_t hash index - */ -#define PTE_FRAG_SIZE_SHIFT 12 -#define PTE_FRAG_SIZE (2 * PTRS_PER_PTE * sizeof(pte_t)) extern pte_t *page_table_alloc(struct mm_struct *, unsigned long, int); extern void page_table_free(struct mm_struct *, unsigned long *, int); diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index b64b4212b71f..ac9fb114e25d 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -1,6 +1,5 @@ #ifndef _ASM_POWERPC_PGTABLE_H #define _ASM_POWERPC_PGTABLE_H -#ifdef __KERNEL__ #ifndef __ASSEMBLY__ #include <linux/mmdebug.h> @@ -13,210 +12,20 @@ struct mm_struct; #endif /* !__ASSEMBLY__ */ -#if defined(CONFIG_PPC64) -# include <asm/pgtable-ppc64.h> +#ifdef CONFIG_PPC_BOOK3S +#include <asm/book3s/pgtable.h> #else -# include <asm/pgtable-ppc32.h> -#endif - -/* - * We save the slot number & secondary bit in the second half of the - * PTE page. We use the 8 bytes per each pte entry. - */ -#define PTE_PAGE_HIDX_OFFSET (PTRS_PER_PTE * 8) +#include <asm/nohash/pgtable.h> +#endif /* !CONFIG_PPC_BOOK3S */ #ifndef __ASSEMBLY__ #include <asm/tlbflush.h> -/* Generic accessors to PTE bits */ -static inline int pte_write(pte_t pte) -{ return (pte_val(pte) & (_PAGE_RW | _PAGE_RO)) != _PAGE_RO; } -static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY; } -static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED; } -static inline int pte_special(pte_t pte) { return pte_val(pte) & _PAGE_SPECIAL; } -static inline int pte_none(pte_t pte) { return (pte_val(pte) & ~_PTE_NONE_MASK) == 0; } -static inline pgprot_t pte_pgprot(pte_t pte) { return __pgprot(pte_val(pte) & PAGE_PROT_BITS); } - -#ifdef CONFIG_NUMA_BALANCING -/* - * These work without NUMA balancing but the kernel does not care. See the - * comment in include/asm-generic/pgtable.h . On powerpc, this will only - * work for user pages and always return true for kernel pages. - */ -static inline int pte_protnone(pte_t pte) -{ - return (pte_val(pte) & - (_PAGE_PRESENT | _PAGE_USER)) == _PAGE_PRESENT; -} - -static inline int pmd_protnone(pmd_t pmd) -{ - return pte_protnone(pmd_pte(pmd)); -} -#endif /* CONFIG_NUMA_BALANCING */ - -static inline int pte_present(pte_t pte) -{ - return pte_val(pte) & _PAGE_PRESENT; -} - -/* Conversion functions: convert a page and protection to a page entry, - * and a page entry and page directory to the page they refer to. - * - * Even if PTEs can be unsigned long long, a PFN is always an unsigned - * long for now. - */ -static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot) { - return __pte(((pte_basic_t)(pfn) << PTE_RPN_SHIFT) | - pgprot_val(pgprot)); } -static inline unsigned long pte_pfn(pte_t pte) { - return pte_val(pte) >> PTE_RPN_SHIFT; } - /* Keep these as a macros to avoid include dependency mess */ #define pte_page(x) pfn_to_page(pte_pfn(x)) #define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot)) -/* Generic modifiers for PTE bits */ -static inline pte_t pte_wrprotect(pte_t pte) { - pte_val(pte) &= ~(_PAGE_RW | _PAGE_HWWRITE); - pte_val(pte) |= _PAGE_RO; return pte; } -static inline pte_t pte_mkclean(pte_t pte) { - pte_val(pte) &= ~(_PAGE_DIRTY | _PAGE_HWWRITE); return pte; } -static inline pte_t pte_mkold(pte_t pte) { - pte_val(pte) &= ~_PAGE_ACCESSED; return pte; } -static inline pte_t pte_mkwrite(pte_t pte) { - pte_val(pte) &= ~_PAGE_RO; - pte_val(pte) |= _PAGE_RW; return pte; } -static inline pte_t pte_mkdirty(pte_t pte) { - pte_val(pte) |= _PAGE_DIRTY; return pte; } -static inline pte_t pte_mkyoung(pte_t pte) { - pte_val(pte) |= _PAGE_ACCESSED; return pte; } -static inline pte_t pte_mkspecial(pte_t pte) { - pte_val(pte) |= _PAGE_SPECIAL; return pte; } -static inline pte_t pte_mkhuge(pte_t pte) { - return pte; } -static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) -{ - pte_val(pte) = (pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot); - return pte; -} - - -/* Insert a PTE, top-level function is out of line. It uses an inline - * low level function in the respective pgtable-* files - */ -extern void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, - pte_t pte); - -/* This low level function performs the actual PTE insertion - * Setting the PTE depends on the MMU type and other factors. It's - * an horrible mess that I'm not going to try to clean up now but - * I'm keeping it in one place rather than spread around - */ -static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte, int percpu) -{ -#if defined(CONFIG_PPC_STD_MMU_32) && defined(CONFIG_SMP) && !defined(CONFIG_PTE_64BIT) - /* First case is 32-bit Hash MMU in SMP mode with 32-bit PTEs. We use the - * helper pte_update() which does an atomic update. We need to do that - * because a concurrent invalidation can clear _PAGE_HASHPTE. If it's a - * per-CPU PTE such as a kmap_atomic, we do a simple update preserving - * the hash bits instead (ie, same as the non-SMP case) - */ - if (percpu) - *ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE) - | (pte_val(pte) & ~_PAGE_HASHPTE)); - else - pte_update(ptep, ~_PAGE_HASHPTE, pte_val(pte)); - -#elif defined(CONFIG_PPC32) && defined(CONFIG_PTE_64BIT) - /* Second case is 32-bit with 64-bit PTE. In this case, we - * can just store as long as we do the two halves in the right order - * with a barrier in between. This is possible because we take care, - * in the hash code, to pre-invalidate if the PTE was already hashed, - * which synchronizes us with any concurrent invalidation. - * In the percpu case, we also fallback to the simple update preserving - * the hash bits - */ - if (percpu) { - *ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE) - | (pte_val(pte) & ~_PAGE_HASHPTE)); - return; - } -#if _PAGE_HASHPTE != 0 - if (pte_val(*ptep) & _PAGE_HASHPTE) - flush_hash_entry(mm, ptep, addr); -#endif - __asm__ __volatile__("\ - stw%U0%X0 %2,%0\n\ - eieio\n\ - stw%U0%X0 %L2,%1" - : "=m" (*ptep), "=m" (*((unsigned char *)ptep+4)) - : "r" (pte) : "memory"); - -#elif defined(CONFIG_PPC_STD_MMU_32) - /* Third case is 32-bit hash table in UP mode, we need to preserve - * the _PAGE_HASHPTE bit since we may not have invalidated the previous - * translation in the hash yet (done in a subsequent flush_tlb_xxx()) - * and see we need to keep track that this PTE needs invalidating - */ - *ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE) - | (pte_val(pte) & ~_PAGE_HASHPTE)); - -#else - /* Anything else just stores the PTE normally. That covers all 64-bit - * cases, and 32-bit non-hash with 32-bit PTEs. - */ - *ptep = pte; - -#ifdef CONFIG_PPC_BOOK3E_64 - /* - * With hardware tablewalk, a sync is needed to ensure that - * subsequent accesses see the PTE we just wrote. Unlike userspace - * mappings, we can't tolerate spurious faults, so make sure - * the new PTE will be seen the first time. - */ - if (is_kernel_addr(addr)) - mb(); -#endif -#endif -} - - -#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS -extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, - pte_t *ptep, pte_t entry, int dirty); - -/* - * Macro to mark a page protection value as "uncacheable". - */ - -#define _PAGE_CACHE_CTL (_PAGE_COHERENT | _PAGE_GUARDED | _PAGE_NO_CACHE | \ - _PAGE_WRITETHRU) - -#define pgprot_noncached(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \ - _PAGE_NO_CACHE | _PAGE_GUARDED)) - -#define pgprot_noncached_wc(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \ - _PAGE_NO_CACHE)) - -#define pgprot_cached(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \ - _PAGE_COHERENT)) - -#define pgprot_cached_wthru(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \ - _PAGE_COHERENT | _PAGE_WRITETHRU)) - -#define pgprot_cached_noncoherent(prot) \ - (__pgprot(pgprot_val(prot) & ~_PAGE_CACHE_CTL)) - -#define pgprot_writecombine pgprot_noncached_wc - -struct file; -extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, - unsigned long size, pgprot_t vma_prot); -#define __HAVE_PHYS_MEM_ACCESS_PROT - /* * ZERO_PAGE is a global shared page that is always zero: used * for zero-mapped memory areas etc.. @@ -271,5 +80,4 @@ static inline pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, } #endif /* __ASSEMBLY__ */ -#endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_PGTABLE_H */ diff --git a/arch/powerpc/include/asm/plpar_wrappers.h b/arch/powerpc/include/asm/plpar_wrappers.h index 67859edbf8fd..1b394247afc2 100644 --- a/arch/powerpc/include/asm/plpar_wrappers.h +++ b/arch/powerpc/include/asm/plpar_wrappers.h @@ -202,6 +202,23 @@ static inline long plpar_pte_read_raw(unsigned long flags, unsigned long ptex, } /* + * ptes must be 8*sizeof(unsigned long) + */ +static inline long plpar_pte_read_4(unsigned long flags, unsigned long ptex, + unsigned long *ptes) + +{ + long rc; + unsigned long retbuf[PLPAR_HCALL9_BUFSIZE]; + + rc = plpar_hcall9(H_READ, retbuf, flags | H_READ_4, ptex); + + memcpy(ptes, retbuf, 8*sizeof(unsigned long)); + + return rc; +} + +/* * plpar_pte_read_4_raw can be called in real mode. * ptes must be 8*sizeof(unsigned long) */ diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index dd0fc18d8103..499d9f89435a 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -413,24 +413,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601) FTR_SECTION_ELSE_NESTED(848); \ mtocrf (FXM), RS; \ ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_NOEXECUTE, 848) - -/* - * PPR restore macros used in entry_64.S - * Used for P7 or later processors - */ -#define HMT_MEDIUM_LOW_HAS_PPR \ -BEGIN_FTR_SECTION_NESTED(944) \ - HMT_MEDIUM_LOW; \ -END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,944) - -#define SET_DEFAULT_THREAD_PPR(ra, rb) \ -BEGIN_FTR_SECTION_NESTED(945) \ - lis ra,INIT_PPR@highest; /* default ppr=3 */ \ - ld rb,PACACURRENT(r13); \ - sldi ra,ra,32; /* 11- 13 bits are used for ppr */ \ - std ra,TASKTHREADPPR(rb); \ -END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,945) - #endif /* diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 5afea361beaa..ac2330820b9a 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -88,12 +88,6 @@ struct task_struct; void start_thread(struct pt_regs *regs, unsigned long fdptr, unsigned long sp); void release_thread(struct task_struct *); -/* Lazy FPU handling on uni-processor */ -extern struct task_struct *last_task_used_math; -extern struct task_struct *last_task_used_altivec; -extern struct task_struct *last_task_used_vsx; -extern struct task_struct *last_task_used_spe; - #ifdef CONFIG_PPC32 #if CONFIG_TASK_SIZE > CONFIG_KERNEL_START @@ -294,6 +288,7 @@ struct thread_struct { #endif #ifdef CONFIG_PPC64 unsigned long dscr; + unsigned long fscr; /* * This member element dscr_inherit indicates that the process * has explicitly attempted and changed the DSCR register value @@ -385,8 +380,6 @@ extern int set_endian(struct task_struct *tsk, unsigned int val); extern int get_unalign_ctl(struct task_struct *tsk, unsigned long adr); extern int set_unalign_ctl(struct task_struct *tsk, unsigned int val); -extern void fp_enable(void); -extern void vec_enable(void); extern void load_fp_state(struct thread_fp_state *fp); extern void store_fp_state(struct thread_fp_state *fp); extern void load_vr_state(struct thread_vr_state *vr); diff --git a/arch/powerpc/include/asm/pte-common.h b/arch/powerpc/include/asm/pte-common.h index 71537a319fc8..1ec67b043065 100644 --- a/arch/powerpc/include/asm/pte-common.h +++ b/arch/powerpc/include/asm/pte-common.h @@ -40,6 +40,11 @@ #else #define _PAGE_RW 0 #endif + +#ifndef _PAGE_PTE +#define _PAGE_PTE 0 +#endif + #ifndef _PMD_PRESENT_MASK #define _PMD_PRESENT_MASK _PMD_PRESENT #endif diff --git a/arch/powerpc/include/asm/pte-hash64-4k.h b/arch/powerpc/include/asm/pte-hash64-4k.h deleted file mode 100644 index c134e809aac3..000000000000 --- a/arch/powerpc/include/asm/pte-hash64-4k.h +++ /dev/null @@ -1,17 +0,0 @@ -/* To be include by pgtable-hash64.h only */ - -/* PTE bits */ -#define _PAGE_HASHPTE 0x0400 /* software: pte has an associated HPTE */ -#define _PAGE_SECONDARY 0x8000 /* software: HPTE is in secondary group */ -#define _PAGE_GROUP_IX 0x7000 /* software: HPTE index within group */ -#define _PAGE_F_SECOND _PAGE_SECONDARY -#define _PAGE_F_GIX _PAGE_GROUP_IX -#define _PAGE_SPECIAL 0x10000 /* software: special page */ - -/* PTE flags to conserve for HPTE identification */ -#define _PAGE_HPTEFLAGS (_PAGE_BUSY | _PAGE_HASHPTE | \ - _PAGE_SECONDARY | _PAGE_GROUP_IX) - -/* shift to put page number into pte */ -#define PTE_RPN_SHIFT (17) - diff --git a/arch/powerpc/include/asm/pte-hash64-64k.h b/arch/powerpc/include/asm/pte-hash64-64k.h deleted file mode 100644 index 4f4ec2ab45c9..000000000000 --- a/arch/powerpc/include/asm/pte-hash64-64k.h +++ /dev/null @@ -1,102 +0,0 @@ -/* To be include by pgtable-hash64.h only */ - -/* Additional PTE bits (don't change without checking asm in hash_low.S) */ -#define _PAGE_SPECIAL 0x00000400 /* software: special page */ -#define _PAGE_HPTE_SUB 0x0ffff000 /* combo only: sub pages HPTE bits */ -#define _PAGE_HPTE_SUB0 0x08000000 /* combo only: first sub page */ -#define _PAGE_COMBO 0x10000000 /* this is a combo 4k page */ -#define _PAGE_4K_PFN 0x20000000 /* PFN is for a single 4k page */ - -/* For 64K page, we don't have a separate _PAGE_HASHPTE bit. Instead, - * we set that to be the whole sub-bits mask. The C code will only - * test this, so a multi-bit mask will work. For combo pages, this - * is equivalent as effectively, the old _PAGE_HASHPTE was an OR of - * all the sub bits. For real 64k pages, we now have the assembly set - * _PAGE_HPTE_SUB0 in addition to setting the HIDX bits which overlap - * that mask. This is fine as long as the HIDX bits are never set on - * a PTE that isn't hashed, which is the case today. - * - * A little nit is for the huge page C code, which does the hashing - * in C, we need to provide which bit to use. - */ -#define _PAGE_HASHPTE _PAGE_HPTE_SUB - -/* Note the full page bits must be in the same location as for normal - * 4k pages as the same assembly will be used to insert 64K pages - * whether the kernel has CONFIG_PPC_64K_PAGES or not - */ -#define _PAGE_F_SECOND 0x00008000 /* full page: hidx bits */ -#define _PAGE_F_GIX 0x00007000 /* full page: hidx bits */ - -/* PTE flags to conserve for HPTE identification */ -#define _PAGE_HPTEFLAGS (_PAGE_BUSY | _PAGE_HASHPTE | _PAGE_COMBO) - -/* Shift to put page number into pte. - * - * That gives us a max RPN of 34 bits, which means a max of 50 bits - * of addressable physical space, or 46 bits for the special 4k PFNs. - */ -#define PTE_RPN_SHIFT (30) - -#ifndef __ASSEMBLY__ - -/* - * With 64K pages on hash table, we have a special PTE format that - * uses a second "half" of the page table to encode sub-page information - * in order to deal with 64K made of 4K HW pages. Thus we override the - * generic accessors and iterators here - */ -#define __real_pte __real_pte -static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep) -{ - real_pte_t rpte; - - rpte.pte = pte; - rpte.hidx = 0; - if (pte_val(pte) & _PAGE_COMBO) { - /* - * Make sure we order the hidx load against the _PAGE_COMBO - * check. The store side ordering is done in __hash_page_4K - */ - smp_rmb(); - rpte.hidx = pte_val(*((ptep) + PTRS_PER_PTE)); - } - return rpte; -} - -static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index) -{ - if ((pte_val(rpte.pte) & _PAGE_COMBO)) - return (rpte.hidx >> (index<<2)) & 0xf; - return (pte_val(rpte.pte) >> 12) & 0xf; -} - -#define __rpte_to_pte(r) ((r).pte) -#define __rpte_sub_valid(rpte, index) \ - (pte_val(rpte.pte) & (_PAGE_HPTE_SUB0 >> (index))) - -/* Trick: we set __end to va + 64k, which happens works for - * a 16M page as well as we want only one iteration - */ -#define pte_iterate_hashed_subpages(rpte, psize, vpn, index, shift) \ - do { \ - unsigned long __end = vpn + (1UL << (PAGE_SHIFT - VPN_SHIFT)); \ - unsigned __split = (psize == MMU_PAGE_4K || \ - psize == MMU_PAGE_64K_AP); \ - shift = mmu_psize_defs[psize].shift; \ - for (index = 0; vpn < __end; index++, \ - vpn += (1L << (shift - VPN_SHIFT))) { \ - if (!__split || __rpte_sub_valid(rpte, index)) \ - do { - -#define pte_iterate_hashed_end() } while(0); } } while(0) - -#define pte_pagesize_index(mm, addr, pte) \ - (((pte) & _PAGE_COMBO)? MMU_PAGE_4K: MMU_PAGE_64K) - -#define remap_4k_pfn(vma, addr, pfn, prot) \ - (WARN_ON(((pfn) >= (1UL << (64 - PTE_RPN_SHIFT)))) ? -EINVAL : \ - remap_pfn_range((vma), (addr), (pfn), PAGE_SIZE, \ - __pgprot(pgprot_val((prot)) | _PAGE_4K_PFN))) - -#endif /* __ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/pte-hash64.h b/arch/powerpc/include/asm/pte-hash64.h deleted file mode 100644 index ef612c160da7..000000000000 --- a/arch/powerpc/include/asm/pte-hash64.h +++ /dev/null @@ -1,54 +0,0 @@ -#ifndef _ASM_POWERPC_PTE_HASH64_H -#define _ASM_POWERPC_PTE_HASH64_H -#ifdef __KERNEL__ - -/* - * Common bits between 4K and 64K pages in a linux-style PTE. - * These match the bits in the (hardware-defined) PowerPC PTE as closely - * as possible. Additional bits may be defined in pgtable-hash64-*.h - * - * Note: We only support user read/write permissions. Supervisor always - * have full read/write to pages above PAGE_OFFSET (pages below that - * always use the user access permissions). - * - * We could create separate kernel read-only if we used the 3 PP bits - * combinations that newer processors provide but we currently don't. - */ -#define _PAGE_PRESENT 0x0001 /* software: pte contains a translation */ -#define _PAGE_USER 0x0002 /* matches one of the PP bits */ -#define _PAGE_BIT_SWAP_TYPE 2 -#define _PAGE_EXEC 0x0004 /* No execute on POWER4 and newer (we invert) */ -#define _PAGE_GUARDED 0x0008 -/* We can derive Memory coherence from _PAGE_NO_CACHE */ -#define _PAGE_NO_CACHE 0x0020 /* I: cache inhibit */ -#define _PAGE_WRITETHRU 0x0040 /* W: cache write-through */ -#define _PAGE_DIRTY 0x0080 /* C: page changed */ -#define _PAGE_ACCESSED 0x0100 /* R: page referenced */ -#define _PAGE_RW 0x0200 /* software: user write access allowed */ -#define _PAGE_BUSY 0x0800 /* software: PTE & hash are busy */ - -/* No separate kernel read-only */ -#define _PAGE_KERNEL_RW (_PAGE_RW | _PAGE_DIRTY) /* user access blocked by key */ -#define _PAGE_KERNEL_RO _PAGE_KERNEL_RW - -/* Strong Access Ordering */ -#define _PAGE_SAO (_PAGE_WRITETHRU | _PAGE_NO_CACHE | _PAGE_COHERENT) - -/* No page size encoding in the linux PTE */ -#define _PAGE_PSIZE 0 - -/* PTEIDX nibble */ -#define _PTEIDX_SECONDARY 0x8 -#define _PTEIDX_GROUP_IX 0x7 - -/* Hash table based platforms need atomic updates of the linux PTE */ -#define PTE_ATOMIC_UPDATES 1 - -#ifdef CONFIG_PPC_64K_PAGES -#include <asm/pte-hash64-64k.h> -#else -#include <asm/pte-hash64-4k.h> -#endif - -#endif /* __KERNEL__ */ -#endif /* _ASM_POWERPC_PTE_HASH64_H */ diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 2220f7a60def..c4cb2ffc624e 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -1194,12 +1194,20 @@ #define __mtmsrd(v, l) asm volatile("mtmsrd %0," __stringify(l) \ : : "r" (v) : "memory") #define mtmsr(v) __mtmsrd((v), 0) +#define __MTMSR "mtmsrd" #else #define mtmsr(v) asm volatile("mtmsr %0" : \ : "r" ((unsigned long)(v)) \ : "memory") +#define __MTMSR "mtmsr" #endif +static inline void mtmsr_isync(unsigned long val) +{ + asm volatile(__MTMSR " %0; " ASM_FTR_IFCLR("isync", "nop", %1) : : + "r" (val), "i" (CPU_FTR_ARCH_206) : "memory"); +} + #define mfspr(rn) ({unsigned long rval; \ asm volatile("mfspr %0," __stringify(rn) \ : "=r" (rval)); rval;}) @@ -1207,6 +1215,15 @@ : "r" ((unsigned long)(v)) \ : "memory") +extern void msr_check_and_set(unsigned long bits); +extern bool strict_msr_control; +extern void __msr_check_and_clear(unsigned long bits); +static inline void msr_check_and_clear(unsigned long bits) +{ + if (strict_msr_control) + __msr_check_and_clear(bits); +} + static inline unsigned long mfvtb (void) { #ifdef CONFIG_PPC_BOOK3S_64 diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h index b77ef369c0f0..51400baa8d48 100644 --- a/arch/powerpc/include/asm/rtas.h +++ b/arch/powerpc/include/asm/rtas.h @@ -334,10 +334,11 @@ extern void (*rtas_flash_term_hook)(int); extern struct rtas_t rtas; -extern void enter_rtas(unsigned long); extern int rtas_token(const char *service); extern int rtas_service_present(const char *service); extern int rtas_call(int token, int, int, int *, ...); +void rtas_call_unlocked(struct rtas_args *args, int token, int nargs, + int nret, ...); extern void rtas_restart(char *cmd); extern void rtas_power_off(void); extern void rtas_halt(void); diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h index 15cca17cba4b..5b268b6be74c 100644 --- a/arch/powerpc/include/asm/switch_to.h +++ b/arch/powerpc/include/asm/switch_to.h @@ -4,6 +4,8 @@ #ifndef _ASM_POWERPC_SWITCH_TO_H #define _ASM_POWERPC_SWITCH_TO_H +#include <asm/reg.h> + struct thread_struct; struct task_struct; struct pt_regs; @@ -12,74 +14,59 @@ extern struct task_struct *__switch_to(struct task_struct *, struct task_struct *); #define switch_to(prev, next, last) ((last) = __switch_to((prev), (next))) -struct thread_struct; extern struct task_struct *_switch(struct thread_struct *prev, struct thread_struct *next); -#ifdef CONFIG_PPC_BOOK3S_64 -static inline void save_early_sprs(struct thread_struct *prev) -{ - if (cpu_has_feature(CPU_FTR_ARCH_207S)) - prev->tar = mfspr(SPRN_TAR); - if (cpu_has_feature(CPU_FTR_DSCR)) - prev->dscr = mfspr(SPRN_DSCR); -} -#else -static inline void save_early_sprs(struct thread_struct *prev) {} -#endif -extern void enable_kernel_fp(void); -extern void enable_kernel_altivec(void); -extern void enable_kernel_vsx(void); -extern int emulate_altivec(struct pt_regs *); -extern void __giveup_vsx(struct task_struct *); -extern void giveup_vsx(struct task_struct *); -extern void enable_kernel_spe(void); -extern void giveup_spe(struct task_struct *); -extern void load_up_spe(struct task_struct *); extern void switch_booke_debug_regs(struct debug_reg *new_debug); -#ifndef CONFIG_SMP -extern void discard_lazy_cpu_state(void); -#else -static inline void discard_lazy_cpu_state(void) -{ -} -#endif +extern int emulate_altivec(struct pt_regs *); + +extern void flush_all_to_thread(struct task_struct *); +extern void giveup_all(struct task_struct *); #ifdef CONFIG_PPC_FPU +extern void enable_kernel_fp(void); extern void flush_fp_to_thread(struct task_struct *); extern void giveup_fpu(struct task_struct *); +extern void __giveup_fpu(struct task_struct *); +static inline void disable_kernel_fp(void) +{ + msr_check_and_clear(MSR_FP); +} #else static inline void flush_fp_to_thread(struct task_struct *t) { } -static inline void giveup_fpu(struct task_struct *t) { } #endif #ifdef CONFIG_ALTIVEC +extern void enable_kernel_altivec(void); extern void flush_altivec_to_thread(struct task_struct *); extern void giveup_altivec(struct task_struct *); -extern void giveup_altivec_notask(void); -#else -static inline void flush_altivec_to_thread(struct task_struct *t) -{ -} -static inline void giveup_altivec(struct task_struct *t) +extern void __giveup_altivec(struct task_struct *); +static inline void disable_kernel_altivec(void) { + msr_check_and_clear(MSR_VEC); } #endif #ifdef CONFIG_VSX +extern void enable_kernel_vsx(void); extern void flush_vsx_to_thread(struct task_struct *); -#else -static inline void flush_vsx_to_thread(struct task_struct *t) +extern void giveup_vsx(struct task_struct *); +extern void __giveup_vsx(struct task_struct *); +static inline void disable_kernel_vsx(void) { + msr_check_and_clear(MSR_FP|MSR_VEC|MSR_VSX); } #endif #ifdef CONFIG_SPE +extern void enable_kernel_spe(void); extern void flush_spe_to_thread(struct task_struct *); -#else -static inline void flush_spe_to_thread(struct task_struct *t) +extern void giveup_spe(struct task_struct *); +extern void __giveup_spe(struct task_struct *); +static inline void disable_kernel_spe(void) { + msr_check_and_clear(MSR_SPE); } #endif diff --git a/arch/powerpc/include/asm/synch.h b/arch/powerpc/include/asm/synch.h index e682a7143edb..c50868681f9e 100644 --- a/arch/powerpc/include/asm/synch.h +++ b/arch/powerpc/include/asm/synch.h @@ -44,7 +44,7 @@ static inline void isync(void) MAKE_LWSYNC_SECTION_ENTRY(97, __lwsync_fixup); #define PPC_ACQUIRE_BARRIER "\n" stringify_in_c(__PPC_ACQUIRE_BARRIER) #define PPC_RELEASE_BARRIER stringify_in_c(LWSYNC) "\n" -#define PPC_ATOMIC_ENTRY_BARRIER "\n" stringify_in_c(LWSYNC) "\n" +#define PPC_ATOMIC_ENTRY_BARRIER "\n" stringify_in_c(sync) "\n" #define PPC_ATOMIC_EXIT_BARRIER "\n" stringify_in_c(sync) "\n" #else #define PPC_ACQUIRE_BARRIER diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h index 10fc784a2ad4..2d7109a8d296 100644 --- a/arch/powerpc/include/asm/time.h +++ b/arch/powerpc/include/asm/time.h @@ -27,7 +27,6 @@ extern struct clock_event_device decrementer_clockevent; struct rtc_time; extern void to_tm(int tim, struct rtc_time * tm); -extern void GregorianDay(struct rtc_time *tm); extern void tick_broadcast_ipi_handler(void); extern void generic_calibrate_decr(void); diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index 4b6b8ace18e0..6a5ace5fa0c8 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -12,10 +12,9 @@ #include <uapi/asm/unistd.h> -#define __NR_syscalls 379 +#define NR_syscalls 379 #define __NR__exit __NR_exit -#define NR_syscalls __NR_syscalls #ifndef __ASSEMBLY__ diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h index b73a8199f161..1afe90ade595 100644 --- a/arch/powerpc/include/asm/vdso_datapage.h +++ b/arch/powerpc/include/asm/vdso_datapage.h @@ -41,7 +41,7 @@ #include <linux/unistd.h> #include <linux/time.h> -#define SYSCALL_MAP_SIZE ((__NR_syscalls + 31) / 32) +#define SYSCALL_MAP_SIZE ((NR_syscalls + 31) / 32) /* * So here is the ppc64 backward compatible version diff --git a/arch/powerpc/include/uapi/asm/cputable.h b/arch/powerpc/include/uapi/asm/cputable.h index 43686043e297..8dde19962a5b 100644 --- a/arch/powerpc/include/uapi/asm/cputable.h +++ b/arch/powerpc/include/uapi/asm/cputable.h @@ -43,5 +43,7 @@ #define PPC_FEATURE2_TAR 0x04000000 #define PPC_FEATURE2_VEC_CRYPTO 0x02000000 #define PPC_FEATURE2_HTM_NOSC 0x01000000 +#define PPC_FEATURE2_ARCH_3_00 0x00800000 /* ISA 3.00 */ +#define PPC_FEATURE2_HAS_IEEE128 0x00400000 /* VSX IEEE Binary Float 128-bit */ #endif /* _UAPI__ASM_POWERPC_CPUTABLE_H */ diff --git a/arch/powerpc/include/uapi/asm/elf.h b/arch/powerpc/include/uapi/asm/elf.h index 59dad113897b..c2d21d11c2d2 100644 --- a/arch/powerpc/include/uapi/asm/elf.h +++ b/arch/powerpc/include/uapi/asm/elf.h @@ -295,6 +295,8 @@ do { \ #define R_PPC64_TLSLD 108 #define R_PPC64_TOCSAVE 109 +#define R_PPC64_ENTRY 118 + #define R_PPC64_REL16 249 #define R_PPC64_REL16_LO 250 #define R_PPC64_REL16_HI 251 diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c index 86150fbb42c3..8e7cb8e2b21a 100644 --- a/arch/powerpc/kernel/align.c +++ b/arch/powerpc/kernel/align.c @@ -960,6 +960,7 @@ int fix_alignment(struct pt_regs *regs) preempt_disable(); enable_kernel_fp(); cvt_df(&data.dd, (float *)&data.x32.low32); + disable_kernel_fp(); preempt_enable(); #else return 0; @@ -1000,6 +1001,7 @@ int fix_alignment(struct pt_regs *regs) preempt_disable(); enable_kernel_fp(); cvt_fd((float *)&data.x32.low32, &data.dd); + disable_kernel_fp(); preempt_enable(); #else return 0; diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 221d584d089f..07cebc3514f3 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -185,14 +185,16 @@ int main(void) DEFINE(PACAKMSR, offsetof(struct paca_struct, kernel_msr)); DEFINE(PACASOFTIRQEN, offsetof(struct paca_struct, soft_enabled)); DEFINE(PACAIRQHAPPENED, offsetof(struct paca_struct, irq_happened)); - DEFINE(PACACONTEXTID, offsetof(struct paca_struct, context.id)); +#ifdef CONFIG_PPC_BOOK3S + DEFINE(PACACONTEXTID, offsetof(struct paca_struct, mm_ctx_id)); #ifdef CONFIG_PPC_MM_SLICES DEFINE(PACALOWSLICESPSIZE, offsetof(struct paca_struct, - context.low_slices_psize)); + mm_ctx_low_slices_psize)); DEFINE(PACAHIGHSLICEPSIZE, offsetof(struct paca_struct, - context.high_slices_psize)); + mm_ctx_high_slices_psize)); DEFINE(MMUPSIZEDEFSIZE, sizeof(struct mmu_psize_def)); #endif /* CONFIG_PPC_MM_SLICES */ +#endif #ifdef CONFIG_PPC_BOOK3E DEFINE(PACAPGD, offsetof(struct paca_struct, pgd)); @@ -222,7 +224,7 @@ int main(void) #ifdef CONFIG_PPC_MM_SLICES DEFINE(MMUPSIZESLLP, offsetof(struct mmu_psize_def, sllp)); #else - DEFINE(PACACONTEXTSLLP, offsetof(struct paca_struct, context.sllp)); + DEFINE(PACACONTEXTSLLP, offsetof(struct paca_struct, mm_ctx_sllp)); #endif /* CONFIG_PPC_MM_SLICES */ DEFINE(PACA_EXGEN, offsetof(struct paca_struct, exgen)); DEFINE(PACA_EXMC, offsetof(struct paca_struct, exmc)); diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index a94f155db78e..0d525ce3717f 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -223,7 +223,11 @@ END_FTR_SECTION_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS) beq- 1f ACCOUNT_CPU_USER_EXIT(r11, r12) - HMT_MEDIUM_LOW_HAS_PPR + +BEGIN_FTR_SECTION + HMT_MEDIUM_LOW +END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) + ld r13,GPR13(r1) /* only restore r13 if returning to usermode */ 1: ld r2,GPR2(r1) ld r1,GPR1(r1) @@ -312,7 +316,13 @@ syscall_exit_work: subi r12,r12,TI_FLAGS 4: /* Anything else left to do? */ - SET_DEFAULT_THREAD_PPR(r3, r10) /* Set thread.ppr = 3 */ +BEGIN_FTR_SECTION + lis r3,INIT_PPR@highest /* Set thread.ppr = 3 */ + ld r10,PACACURRENT(r13) + sldi r3,r3,32 /* bits 11-13 are used for ppr */ + std r3,TASKTHREADPPR(r10) +END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) + andi. r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP) beq ret_from_except_lite @@ -452,43 +462,11 @@ _GLOBAL(_switch) /* r3-r13 are caller saved -- Cort */ SAVE_8GPRS(14, r1) SAVE_10GPRS(22, r1) - mflr r20 /* Return to switch caller */ - mfmsr r22 - li r0, MSR_FP -#ifdef CONFIG_VSX -BEGIN_FTR_SECTION - oris r0,r0,MSR_VSX@h /* Disable VSX */ -END_FTR_SECTION_IFSET(CPU_FTR_VSX) -#endif /* CONFIG_VSX */ -#ifdef CONFIG_ALTIVEC -BEGIN_FTR_SECTION - oris r0,r0,MSR_VEC@h /* Disable altivec */ - mfspr r24,SPRN_VRSAVE /* save vrsave register value */ - std r24,THREAD_VRSAVE(r3) -END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) -#endif /* CONFIG_ALTIVEC */ - and. r0,r0,r22 - beq+ 1f - andc r22,r22,r0 - MTMSRD(r22) - isync -1: std r20,_NIP(r1) + std r0,_NIP(r1) /* Return to switch caller */ mfcr r23 std r23,_CCR(r1) std r1,KSP(r3) /* Set old stack pointer */ -#ifdef CONFIG_PPC_BOOK3S_64 -BEGIN_FTR_SECTION - /* Event based branch registers */ - mfspr r0, SPRN_BESCR - std r0, THREAD_BESCR(r3) - mfspr r0, SPRN_EBBHR - std r0, THREAD_EBBHR(r3) - mfspr r0, SPRN_EBBRR - std r0, THREAD_EBBRR(r3) -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) -#endif - #ifdef CONFIG_SMP /* We need a sync somewhere here to make sure that if the * previous task gets rescheduled on another CPU, it sees all @@ -576,47 +554,6 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) mr r1,r8 /* start using new stack pointer */ std r7,PACAKSAVE(r13) -#ifdef CONFIG_PPC_BOOK3S_64 -BEGIN_FTR_SECTION - /* Event based branch registers */ - ld r0, THREAD_BESCR(r4) - mtspr SPRN_BESCR, r0 - ld r0, THREAD_EBBHR(r4) - mtspr SPRN_EBBHR, r0 - ld r0, THREAD_EBBRR(r4) - mtspr SPRN_EBBRR, r0 - - ld r0,THREAD_TAR(r4) - mtspr SPRN_TAR,r0 -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) -#endif - -#ifdef CONFIG_ALTIVEC -BEGIN_FTR_SECTION - ld r0,THREAD_VRSAVE(r4) - mtspr SPRN_VRSAVE,r0 /* if G4, restore VRSAVE reg */ -END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) -#endif /* CONFIG_ALTIVEC */ -#ifdef CONFIG_PPC64 -BEGIN_FTR_SECTION - lwz r6,THREAD_DSCR_INHERIT(r4) - ld r0,THREAD_DSCR(r4) - cmpwi r6,0 - bne 1f - ld r0,PACA_DSCR_DEFAULT(r13) -1: -BEGIN_FTR_SECTION_NESTED(70) - mfspr r8, SPRN_FSCR - rldimi r8, r6, FSCR_DSCR_LG, (63 - FSCR_DSCR_LG) - mtspr SPRN_FSCR, r8 -END_FTR_SECTION_NESTED(CPU_FTR_ARCH_207S, CPU_FTR_ARCH_207S, 70) - cmpd r0,r25 - beq 2f - mtspr SPRN_DSCR,r0 -2: -END_FTR_SECTION_IFSET(CPU_FTR_DSCR) -#endif - ld r6,_CCR(r1) mtcrf 0xFF,r6 diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 0a0399c2af11..7716cebf4b8e 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -96,7 +96,6 @@ __start_interrupts: .globl system_reset_pSeries; system_reset_pSeries: - HMT_MEDIUM_PPR_DISCARD SET_SCRATCH0(r13) #ifdef CONFIG_PPC_P7_NAP BEGIN_FTR_SECTION @@ -164,7 +163,6 @@ machine_check_pSeries_1: * some code path might still want to branch into the original * vector */ - HMT_MEDIUM_PPR_DISCARD SET_SCRATCH0(r13) /* save r13 */ #ifdef CONFIG_PPC_P7_NAP BEGIN_FTR_SECTION @@ -199,7 +197,6 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE) . = 0x300 .globl data_access_pSeries data_access_pSeries: - HMT_MEDIUM_PPR_DISCARD SET_SCRATCH0(r13) EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common, EXC_STD, KVMTEST, 0x300) @@ -207,7 +204,6 @@ data_access_pSeries: . = 0x380 .globl data_access_slb_pSeries data_access_slb_pSeries: - HMT_MEDIUM_PPR_DISCARD SET_SCRATCH0(r13) EXCEPTION_PROLOG_0(PACA_EXSLB) EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST, 0x380) @@ -234,15 +230,14 @@ data_access_slb_pSeries: bctr #endif - STD_EXCEPTION_PSERIES(0x400, 0x400, instruction_access) + STD_EXCEPTION_PSERIES(0x400, instruction_access) . = 0x480 .globl instruction_access_slb_pSeries instruction_access_slb_pSeries: - HMT_MEDIUM_PPR_DISCARD SET_SCRATCH0(r13) EXCEPTION_PROLOG_0(PACA_EXSLB) - EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x480) + EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST, 0x480) std r3,PACA_EXSLB+EX_R3(r13) mfspr r3,SPRN_SRR0 /* SRR0 is faulting address */ #ifdef __DISABLED__ @@ -269,25 +264,24 @@ instruction_access_slb_pSeries: .globl hardware_interrupt_hv; hardware_interrupt_pSeries: hardware_interrupt_hv: - HMT_MEDIUM_PPR_DISCARD BEGIN_FTR_SECTION _MASKABLE_EXCEPTION_PSERIES(0x502, hardware_interrupt, EXC_HV, SOFTEN_TEST_HV) KVM_HANDLER(PACA_EXGEN, EXC_HV, 0x502) FTR_SECTION_ELSE _MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt, - EXC_STD, SOFTEN_TEST_HV_201) + EXC_STD, SOFTEN_TEST_PR) KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x500) ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) - STD_EXCEPTION_PSERIES(0x600, 0x600, alignment) - KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x600) + STD_EXCEPTION_PSERIES(0x600, alignment) + KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x600) - STD_EXCEPTION_PSERIES(0x700, 0x700, program_check) - KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x700) + STD_EXCEPTION_PSERIES(0x700, program_check) + KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x700) - STD_EXCEPTION_PSERIES(0x800, 0x800, fp_unavailable) - KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x800) + STD_EXCEPTION_PSERIES(0x800, fp_unavailable) + KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x800) . = 0x900 .globl decrementer_pSeries @@ -297,10 +291,10 @@ decrementer_pSeries: STD_EXCEPTION_HV(0x980, 0x982, hdecrementer) MASKABLE_EXCEPTION_PSERIES(0xa00, 0xa00, doorbell_super) - KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xa00) + KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xa00) - STD_EXCEPTION_PSERIES(0xb00, 0xb00, trap_0b) - KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xb00) + STD_EXCEPTION_PSERIES(0xb00, trap_0b) + KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xb00) . = 0xc00 .globl system_call_pSeries @@ -331,8 +325,8 @@ system_call_pSeries: SYSCALL_PSERIES_3 KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xc00) - STD_EXCEPTION_PSERIES(0xd00, 0xd00, single_step) - KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xd00) + STD_EXCEPTION_PSERIES(0xd00, single_step) + KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xd00) /* At 0xe??? we have a bunch of hypervisor exceptions, we branch * out of line to handle them @@ -407,13 +401,12 @@ hv_facility_unavailable_trampoline: KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1202) #endif /* CONFIG_CBE_RAS */ - STD_EXCEPTION_PSERIES(0x1300, 0x1300, instruction_breakpoint) - KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_STD, 0x1300) + STD_EXCEPTION_PSERIES(0x1300, instruction_breakpoint) + KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x1300) . = 0x1500 .global denorm_exception_hv denorm_exception_hv: - HMT_MEDIUM_PPR_DISCARD mtspr SPRN_SPRG_HSCRATCH0,r13 EXCEPTION_PROLOG_0(PACA_EXGEN) EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, 0x1500) @@ -435,8 +428,8 @@ denorm_exception_hv: KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1602) #endif /* CONFIG_CBE_RAS */ - STD_EXCEPTION_PSERIES(0x1700, 0x1700, altivec_assist) - KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x1700) + STD_EXCEPTION_PSERIES(0x1700, altivec_assist) + KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x1700) #ifdef CONFIG_CBE_RAS STD_EXCEPTION_HV(0x1800, 0x1802, cbe_thermal) @@ -527,7 +520,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) machine_check_pSeries: .globl machine_check_fwnmi machine_check_fwnmi: - HMT_MEDIUM_PPR_DISCARD SET_SCRATCH0(r13) /* save r13 */ EXCEPTION_PROLOG_0(PACA_EXMC) machine_check_pSeries_0: @@ -536,9 +528,9 @@ machine_check_pSeries_0: KVM_HANDLER_SKIP(PACA_EXMC, EXC_STD, 0x200) KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x300) KVM_HANDLER_SKIP(PACA_EXSLB, EXC_STD, 0x380) - KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x400) - KVM_HANDLER_PR(PACA_EXSLB, EXC_STD, 0x480) - KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x900) + KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x400) + KVM_HANDLER(PACA_EXSLB, EXC_STD, 0x480) + KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x900) KVM_HANDLER(PACA_EXGEN, EXC_HV, 0x982) #ifdef CONFIG_PPC_DENORMALISATION @@ -621,13 +613,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) /* moved from 0xf00 */ STD_EXCEPTION_PSERIES_OOL(0xf00, performance_monitor) - KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf00) + KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf00) STD_EXCEPTION_PSERIES_OOL(0xf20, altivec_unavailable) - KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf20) + KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf20) STD_EXCEPTION_PSERIES_OOL(0xf40, vsx_unavailable) - KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf40) + KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf40) STD_EXCEPTION_PSERIES_OOL(0xf60, facility_unavailable) - KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf60) + KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf60) STD_EXCEPTION_HV_OOL(0xf82, facility_unavailable) KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xf82) @@ -711,7 +703,6 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE) .globl system_reset_fwnmi .align 7 system_reset_fwnmi: - HMT_MEDIUM_PPR_DISCARD SET_SCRATCH0(r13) /* save r13 */ EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD, NOTEST, 0x100) @@ -1556,29 +1547,19 @@ do_hash_page: lwz r0,TI_PREEMPT(r11) /* If we're in an "NMI" */ andis. r0,r0,NMI_MASK@h /* (i.e. an irq when soft-disabled) */ bne 77f /* then don't call hash_page now */ - /* - * We need to set the _PAGE_USER bit if MSR_PR is set or if we are - * accessing a userspace segment (even from the kernel). We assume - * kernel addresses always have the high bit set. - */ - rlwinm r4,r4,32-25+9,31-9,31-9 /* DSISR_STORE -> _PAGE_RW */ - rotldi r0,r3,15 /* Move high bit into MSR_PR posn */ - orc r0,r12,r0 /* MSR_PR | ~high_bit */ - rlwimi r4,r0,32-13,30,30 /* becomes _PAGE_USER access bit */ - ori r4,r4,1 /* add _PAGE_PRESENT */ - rlwimi r4,r5,22+2,31-2,31-2 /* Set _PAGE_EXEC if trap is 0x400 */ /* * r3 contains the faulting address - * r4 contains the required access permissions + * r4 msr * r5 contains the trap number * r6 contains dsisr * * at return r3 = 0 for success, 1 for page fault, negative for error */ + mr r4,r12 ld r6,_DSISR(r1) - bl hash_page /* build HPTE if possible */ - cmpdi r3,0 /* see if hash_page succeeded */ + bl __hash_page /* build HPTE if possible */ + cmpdi r3,0 /* see if __hash_page succeeded */ /* Success */ beq fast_exc_return_irq /* Return from exception on success */ diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S index 9ad236e5d2c9..2117eaca3d28 100644 --- a/arch/powerpc/kernel/fpu.S +++ b/arch/powerpc/kernel/fpu.S @@ -73,30 +73,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX) MTFSF_L(fr0) REST_32FPVSRS(0, R4, R7) - /* FP/VSX off again */ - MTMSRD(r6) - SYNC - blr #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ /* - * Enable use of the FPU, and VSX if possible, for the caller. - */ -_GLOBAL(fp_enable) - mfmsr r3 - ori r3,r3,MSR_FP -#ifdef CONFIG_VSX -BEGIN_FTR_SECTION - oris r3,r3,MSR_VSX@h -END_FTR_SECTION_IFSET(CPU_FTR_VSX) -#endif - SYNC - MTMSRD(r3) - isync /* (not necessary for arch 2.02 and later) */ - blr - -/* * Load state from memory into FP registers including FPSCR. * Assumes the caller has enabled FP in the MSR. */ @@ -136,31 +116,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX) SYNC MTMSRD(r5) /* enable use of fpu now */ isync -/* - * For SMP, we don't do lazy FPU switching because it just gets too - * horrendously complex, especially when a task switches from one CPU - * to another. Instead we call giveup_fpu in switch_to. - */ -#ifndef CONFIG_SMP - LOAD_REG_ADDRBASE(r3, last_task_used_math) - toreal(r3) - PPC_LL r4,ADDROFF(last_task_used_math)(r3) - PPC_LCMPI 0,r4,0 - beq 1f - toreal(r4) - addi r4,r4,THREAD /* want last_task_used_math->thread */ - addi r10,r4,THREAD_FPSTATE - SAVE_32FPVSRS(0, R5, R10) - mffs fr0 - stfd fr0,FPSTATE_FPSCR(r10) - PPC_LL r5,PT_REGS(r4) - toreal(r5) - PPC_LL r4,_MSR-STACK_FRAME_OVERHEAD(r5) - li r10,MSR_FP|MSR_FE0|MSR_FE1 - andc r4,r4,r10 /* disable FP for previous task */ - PPC_STL r4,_MSR-STACK_FRAME_OVERHEAD(r5) -1: -#endif /* CONFIG_SMP */ /* enable use of FP after return */ #ifdef CONFIG_PPC32 mfspr r5,SPRN_SPRG_THREAD /* current task's THREAD (phys) */ @@ -179,36 +134,17 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX) lfd fr0,FPSTATE_FPSCR(r10) MTFSF_L(fr0) REST_32FPVSRS(0, R4, R10) -#ifndef CONFIG_SMP - subi r4,r5,THREAD - fromreal(r4) - PPC_STL r4,ADDROFF(last_task_used_math)(r3) -#endif /* CONFIG_SMP */ /* restore registers and return */ /* we haven't used ctr or xer or lr */ blr /* - * giveup_fpu(tsk) + * __giveup_fpu(tsk) * Disable FP for the task given as the argument, * and save the floating-point registers in its thread_struct. * Enables the FPU for use in the kernel on return. */ -_GLOBAL(giveup_fpu) - mfmsr r5 - ori r5,r5,MSR_FP -#ifdef CONFIG_VSX -BEGIN_FTR_SECTION - oris r5,r5,MSR_VSX@h -END_FTR_SECTION_IFSET(CPU_FTR_VSX) -#endif - SYNC_601 - ISYNC_601 - MTMSRD(r5) /* enable use of fpu now */ - SYNC_601 - isync - PPC_LCMPI 0,r3,0 - beqlr- /* if no previous owner, done */ +_GLOBAL(__giveup_fpu) addi r3,r3,THREAD /* want THREAD of task */ PPC_LL r6,THREAD_FPSAVEAREA(r3) PPC_LL r5,PT_REGS(r3) @@ -230,11 +166,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX) andc r4,r4,r3 /* disable FP for previous task */ PPC_STL r4,_MSR-STACK_FRAME_OVERHEAD(r5) 1: -#ifndef CONFIG_SMP - li r5,0 - LOAD_REG_ADDRBASE(r4,last_task_used_math) - PPC_STL r5,ADDROFF(last_task_used_math)(r4) -#endif /* CONFIG_SMP */ blr /* diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index fffd1f96bb1d..f705171b924b 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -857,29 +857,6 @@ _GLOBAL(load_up_spe) oris r5,r5,MSR_SPE@h mtmsr r5 /* enable use of SPE now */ isync -/* - * For SMP, we don't do lazy SPE switching because it just gets too - * horrendously complex, especially when a task switches from one CPU - * to another. Instead we call giveup_spe in switch_to. - */ -#ifndef CONFIG_SMP - lis r3,last_task_used_spe@ha - lwz r4,last_task_used_spe@l(r3) - cmpi 0,r4,0 - beq 1f - addi r4,r4,THREAD /* want THREAD of last_task_used_spe */ - SAVE_32EVRS(0,r10,r4,THREAD_EVR0) - evxor evr10, evr10, evr10 /* clear out evr10 */ - evmwumiaa evr10, evr10, evr10 /* evr10 <- ACC = 0 * 0 + ACC */ - li r5,THREAD_ACC - evstddx evr10, r4, r5 /* save off accumulator */ - lwz r5,PT_REGS(r4) - lwz r4,_MSR-STACK_FRAME_OVERHEAD(r5) - lis r10,MSR_SPE@h - andc r4,r4,r10 /* disable SPE for previous task */ - stw r4,_MSR-STACK_FRAME_OVERHEAD(r5) -1: -#endif /* !CONFIG_SMP */ /* enable use of SPE after return */ oris r9,r9,MSR_SPE@h mfspr r5,SPRN_SPRG_THREAD /* current task's THREAD (phys) */ @@ -889,10 +866,6 @@ _GLOBAL(load_up_spe) evlddx evr4,r10,r5 evmra evr4,evr4 REST_32EVRS(0,r10,r5,THREAD_EVR0) -#ifndef CONFIG_SMP - subi r4,r5,THREAD - stw r4,last_task_used_spe@l(r3) -#endif /* !CONFIG_SMP */ blr /* @@ -1011,16 +984,10 @@ _GLOBAL(__setup_ehv_ivors) #ifdef CONFIG_SPE /* - * extern void giveup_spe(struct task_struct *prev) + * extern void __giveup_spe(struct task_struct *prev) * */ -_GLOBAL(giveup_spe) - mfmsr r5 - oris r5,r5,MSR_SPE@h - mtmsr r5 /* enable use of SPE now */ - isync - cmpi 0,r3,0 - beqlr- /* if no previous owner, done */ +_GLOBAL(__giveup_spe) addi r3,r3,THREAD /* want THREAD of task */ lwz r5,PT_REGS(r3) cmpi 0,r5,0 @@ -1035,11 +1002,6 @@ _GLOBAL(giveup_spe) andc r4,r4,r3 /* disable SPE for previous task */ stw r4,_MSR-STACK_FRAME_OVERHEAD(r5) 1: -#ifndef CONFIG_SMP - li r5,0 - lis r4,last_task_used_spe@ha - stw r5,last_task_used_spe@l(r4) -#endif /* !CONFIG_SMP */ blr #endif /* CONFIG_SPE */ diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S index 112ccf497562..cf4fb5429cf1 100644 --- a/arch/powerpc/kernel/idle_power7.S +++ b/arch/powerpc/kernel/idle_power7.S @@ -89,13 +89,6 @@ _GLOBAL(power7_powersave_common) std r0,_LINK(r1) std r0,_NIP(r1) -#ifndef CONFIG_SMP - /* Make sure FPU, VSX etc... are flushed as we may lose - * state when going to nap mode - */ - bl discard_lazy_cpu_state -#endif /* CONFIG_SMP */ - /* Hard disable interrupts */ mfmsr r9 rldicl r9,r9,48,1 diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index ed3ab509faca..be8edd67f05b 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -743,6 +743,8 @@ relocate_new_kernel: /* Check for 47x cores */ mfspr r3,SPRN_PVR srwi r3,r3,16 + cmplwi cr0,r3,PVR_476FPE@h + beq setup_map_47x cmplwi cr0,r3,PVR_476@h beq setup_map_47x cmplwi cr0,r3,PVR_476_ISS@h diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c index c94d2e018d84..2c01665eb410 100644 --- a/arch/powerpc/kernel/module_32.c +++ b/arch/powerpc/kernel/module_32.c @@ -188,8 +188,8 @@ static uint32_t do_plt_call(void *location, pr_debug("Doing plt for call to 0x%x at 0x%x\n", val, (unsigned int)location); /* Init, or core PLT? */ - if (location >= mod->module_core - && location < mod->module_core + mod->core_size) + if (location >= mod->core_layout.base + && location < mod->core_layout.base + mod->core_layout.size) entry = (void *)sechdrs[mod->arch.core_plt_section].sh_addr; else entry = (void *)sechdrs[mod->arch.init_plt_section].sh_addr; @@ -296,7 +296,7 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, } #ifdef CONFIG_DYNAMIC_FTRACE module->arch.tramp = - do_plt_call(module->module_core, + do_plt_call(module->core_layout.base, (unsigned long)ftrace_caller, sechdrs, module); #endif diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 68384514506b..59663af9315f 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -635,6 +635,33 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, */ break; + case R_PPC64_ENTRY: + /* + * Optimize ELFv2 large code model entry point if + * the TOC is within 2GB range of current location. + */ + value = my_r2(sechdrs, me) - (unsigned long)location; + if (value + 0x80008000 > 0xffffffff) + break; + /* + * Check for the large code model prolog sequence: + * ld r2, ...(r12) + * add r2, r2, r12 + */ + if ((((uint32_t *)location)[0] & ~0xfffc) + != 0xe84c0000) + break; + if (((uint32_t *)location)[1] != 0x7c426214) + break; + /* + * If found, replace it with: + * addis r2, r12, (.TOC.-func)@ha + * addi r2, r12, (.TOC.-func)@l + */ + ((uint32_t *)location)[0] = 0x3c4c0000 + PPC_HA(value); + ((uint32_t *)location)[1] = 0x38420000 + PPC_LO(value); + break; + case R_PPC64_REL16_HA: /* Subtract location pointer */ value -= (unsigned long)location; diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index 202963ee013a..41e1607e800c 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -19,13 +19,11 @@ EXPORT_SYMBOL(_mcount); #endif #ifdef CONFIG_PPC_FPU -EXPORT_SYMBOL(giveup_fpu); EXPORT_SYMBOL(load_fp_state); EXPORT_SYMBOL(store_fp_state); #endif #ifdef CONFIG_ALTIVEC -EXPORT_SYMBOL(giveup_altivec); EXPORT_SYMBOL(load_vr_state); EXPORT_SYMBOL(store_vr_state); #endif @@ -34,10 +32,6 @@ EXPORT_SYMBOL(store_vr_state); EXPORT_SYMBOL_GPL(__giveup_vsx); #endif -#ifdef CONFIG_SPE -EXPORT_SYMBOL(giveup_spe); -#endif - #ifdef CONFIG_EPAPR_PARAVIRT EXPORT_SYMBOL(epapr_hypercall_start); #endif diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 646bf4d222c1..dccc87e8fee5 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -67,15 +67,8 @@ extern unsigned long _get_SP(void); -#ifndef CONFIG_SMP -struct task_struct *last_task_used_math = NULL; -struct task_struct *last_task_used_altivec = NULL; -struct task_struct *last_task_used_vsx = NULL; -struct task_struct *last_task_used_spe = NULL; -#endif - #ifdef CONFIG_PPC_TRANSACTIONAL_MEM -void giveup_fpu_maybe_transactional(struct task_struct *tsk) +static void check_if_tm_restore_required(struct task_struct *tsk) { /* * If we are saving the current thread's registers, and the @@ -89,34 +82,67 @@ void giveup_fpu_maybe_transactional(struct task_struct *tsk) tsk->thread.ckpt_regs.msr = tsk->thread.regs->msr; set_thread_flag(TIF_RESTORE_TM); } +} +#else +static inline void check_if_tm_restore_required(struct task_struct *tsk) { } +#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ + +bool strict_msr_control; +EXPORT_SYMBOL(strict_msr_control); + +static int __init enable_strict_msr_control(char *str) +{ + strict_msr_control = true; + pr_info("Enabling strict facility control\n"); - giveup_fpu(tsk); + return 0; } +early_param("ppc_strict_facility_enable", enable_strict_msr_control); -void giveup_altivec_maybe_transactional(struct task_struct *tsk) +void msr_check_and_set(unsigned long bits) { - /* - * If we are saving the current thread's registers, and the - * thread is in a transactional state, set the TIF_RESTORE_TM - * bit so that we know to restore the registers before - * returning to userspace. - */ - if (tsk == current && tsk->thread.regs && - MSR_TM_ACTIVE(tsk->thread.regs->msr) && - !test_thread_flag(TIF_RESTORE_TM)) { - tsk->thread.ckpt_regs.msr = tsk->thread.regs->msr; - set_thread_flag(TIF_RESTORE_TM); - } + unsigned long oldmsr = mfmsr(); + unsigned long newmsr; - giveup_altivec(tsk); + newmsr = oldmsr | bits; + +#ifdef CONFIG_VSX + if (cpu_has_feature(CPU_FTR_VSX) && (bits & MSR_FP)) + newmsr |= MSR_VSX; +#endif + + if (oldmsr != newmsr) + mtmsr_isync(newmsr); } -#else -#define giveup_fpu_maybe_transactional(tsk) giveup_fpu(tsk) -#define giveup_altivec_maybe_transactional(tsk) giveup_altivec(tsk) -#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ +void __msr_check_and_clear(unsigned long bits) +{ + unsigned long oldmsr = mfmsr(); + unsigned long newmsr; + + newmsr = oldmsr & ~bits; + +#ifdef CONFIG_VSX + if (cpu_has_feature(CPU_FTR_VSX) && (bits & MSR_FP)) + newmsr &= ~MSR_VSX; +#endif + + if (oldmsr != newmsr) + mtmsr_isync(newmsr); +} +EXPORT_SYMBOL(__msr_check_and_clear); #ifdef CONFIG_PPC_FPU +void giveup_fpu(struct task_struct *tsk) +{ + check_if_tm_restore_required(tsk); + + msr_check_and_set(MSR_FP); + __giveup_fpu(tsk); + msr_check_and_clear(MSR_FP); +} +EXPORT_SYMBOL(giveup_fpu); + /* * Make sure the floating-point register state in the * the thread_struct is up to date for task tsk. @@ -134,52 +160,56 @@ void flush_fp_to_thread(struct task_struct *tsk) */ preempt_disable(); if (tsk->thread.regs->msr & MSR_FP) { -#ifdef CONFIG_SMP /* * This should only ever be called for current or * for a stopped child process. Since we save away - * the FP register state on context switch on SMP, + * the FP register state on context switch, * there is something wrong if a stopped child appears * to still have its FP state in the CPU registers. */ BUG_ON(tsk != current); -#endif - giveup_fpu_maybe_transactional(tsk); + giveup_fpu(tsk); } preempt_enable(); } } EXPORT_SYMBOL_GPL(flush_fp_to_thread); -#endif /* CONFIG_PPC_FPU */ void enable_kernel_fp(void) { WARN_ON(preemptible()); -#ifdef CONFIG_SMP - if (current->thread.regs && (current->thread.regs->msr & MSR_FP)) - giveup_fpu_maybe_transactional(current); - else - giveup_fpu(NULL); /* just enables FP for kernel */ -#else - giveup_fpu_maybe_transactional(last_task_used_math); -#endif /* CONFIG_SMP */ + msr_check_and_set(MSR_FP); + + if (current->thread.regs && (current->thread.regs->msr & MSR_FP)) { + check_if_tm_restore_required(current); + __giveup_fpu(current); + } } EXPORT_SYMBOL(enable_kernel_fp); +#endif /* CONFIG_PPC_FPU */ #ifdef CONFIG_ALTIVEC +void giveup_altivec(struct task_struct *tsk) +{ + check_if_tm_restore_required(tsk); + + msr_check_and_set(MSR_VEC); + __giveup_altivec(tsk); + msr_check_and_clear(MSR_VEC); +} +EXPORT_SYMBOL(giveup_altivec); + void enable_kernel_altivec(void) { WARN_ON(preemptible()); -#ifdef CONFIG_SMP - if (current->thread.regs && (current->thread.regs->msr & MSR_VEC)) - giveup_altivec_maybe_transactional(current); - else - giveup_altivec_notask(); -#else - giveup_altivec_maybe_transactional(last_task_used_altivec); -#endif /* CONFIG_SMP */ + msr_check_and_set(MSR_VEC); + + if (current->thread.regs && (current->thread.regs->msr & MSR_VEC)) { + check_if_tm_restore_required(current); + __giveup_altivec(current); + } } EXPORT_SYMBOL(enable_kernel_altivec); @@ -192,10 +222,8 @@ void flush_altivec_to_thread(struct task_struct *tsk) if (tsk->thread.regs) { preempt_disable(); if (tsk->thread.regs->msr & MSR_VEC) { -#ifdef CONFIG_SMP BUG_ON(tsk != current); -#endif - giveup_altivec_maybe_transactional(tsk); + giveup_altivec(tsk); } preempt_enable(); } @@ -204,37 +232,43 @@ EXPORT_SYMBOL_GPL(flush_altivec_to_thread); #endif /* CONFIG_ALTIVEC */ #ifdef CONFIG_VSX -void enable_kernel_vsx(void) +void giveup_vsx(struct task_struct *tsk) { - WARN_ON(preemptible()); + check_if_tm_restore_required(tsk); -#ifdef CONFIG_SMP - if (current->thread.regs && (current->thread.regs->msr & MSR_VSX)) - giveup_vsx(current); - else - giveup_vsx(NULL); /* just enable vsx for kernel - force */ -#else - giveup_vsx(last_task_used_vsx); -#endif /* CONFIG_SMP */ + msr_check_and_set(MSR_FP|MSR_VEC|MSR_VSX); + if (tsk->thread.regs->msr & MSR_FP) + __giveup_fpu(tsk); + if (tsk->thread.regs->msr & MSR_VEC) + __giveup_altivec(tsk); + __giveup_vsx(tsk); + msr_check_and_clear(MSR_FP|MSR_VEC|MSR_VSX); } -EXPORT_SYMBOL(enable_kernel_vsx); +EXPORT_SYMBOL(giveup_vsx); -void giveup_vsx(struct task_struct *tsk) +void enable_kernel_vsx(void) { - giveup_fpu_maybe_transactional(tsk); - giveup_altivec_maybe_transactional(tsk); - __giveup_vsx(tsk); + WARN_ON(preemptible()); + + msr_check_and_set(MSR_FP|MSR_VEC|MSR_VSX); + + if (current->thread.regs && (current->thread.regs->msr & MSR_VSX)) { + check_if_tm_restore_required(current); + if (current->thread.regs->msr & MSR_FP) + __giveup_fpu(current); + if (current->thread.regs->msr & MSR_VEC) + __giveup_altivec(current); + __giveup_vsx(current); + } } -EXPORT_SYMBOL(giveup_vsx); +EXPORT_SYMBOL(enable_kernel_vsx); void flush_vsx_to_thread(struct task_struct *tsk) { if (tsk->thread.regs) { preempt_disable(); if (tsk->thread.regs->msr & MSR_VSX) { -#ifdef CONFIG_SMP BUG_ON(tsk != current); -#endif giveup_vsx(tsk); } preempt_enable(); @@ -244,19 +278,26 @@ EXPORT_SYMBOL_GPL(flush_vsx_to_thread); #endif /* CONFIG_VSX */ #ifdef CONFIG_SPE +void giveup_spe(struct task_struct *tsk) +{ + check_if_tm_restore_required(tsk); + + msr_check_and_set(MSR_SPE); + __giveup_spe(tsk); + msr_check_and_clear(MSR_SPE); +} +EXPORT_SYMBOL(giveup_spe); void enable_kernel_spe(void) { WARN_ON(preemptible()); -#ifdef CONFIG_SMP - if (current->thread.regs && (current->thread.regs->msr & MSR_SPE)) - giveup_spe(current); - else - giveup_spe(NULL); /* just enable SPE for kernel - force */ -#else - giveup_spe(last_task_used_spe); -#endif /* __SMP __ */ + msr_check_and_set(MSR_SPE); + + if (current->thread.regs && (current->thread.regs->msr & MSR_SPE)) { + check_if_tm_restore_required(current); + __giveup_spe(current); + } } EXPORT_SYMBOL(enable_kernel_spe); @@ -265,9 +306,7 @@ void flush_spe_to_thread(struct task_struct *tsk) if (tsk->thread.regs) { preempt_disable(); if (tsk->thread.regs->msr & MSR_SPE) { -#ifdef CONFIG_SMP BUG_ON(tsk != current); -#endif tsk->thread.spefscr = mfspr(SPRN_SPEFSCR); giveup_spe(tsk); } @@ -276,31 +315,81 @@ void flush_spe_to_thread(struct task_struct *tsk) } #endif /* CONFIG_SPE */ -#ifndef CONFIG_SMP -/* - * If we are doing lazy switching of CPU state (FP, altivec or SPE), - * and the current task has some state, discard it. - */ -void discard_lazy_cpu_state(void) +static unsigned long msr_all_available; + +static int __init init_msr_all_available(void) { - preempt_disable(); - if (last_task_used_math == current) - last_task_used_math = NULL; +#ifdef CONFIG_PPC_FPU + msr_all_available |= MSR_FP; +#endif #ifdef CONFIG_ALTIVEC - if (last_task_used_altivec == current) - last_task_used_altivec = NULL; -#endif /* CONFIG_ALTIVEC */ + if (cpu_has_feature(CPU_FTR_ALTIVEC)) + msr_all_available |= MSR_VEC; +#endif #ifdef CONFIG_VSX - if (last_task_used_vsx == current) - last_task_used_vsx = NULL; -#endif /* CONFIG_VSX */ + if (cpu_has_feature(CPU_FTR_VSX)) + msr_all_available |= MSR_VSX; +#endif #ifdef CONFIG_SPE - if (last_task_used_spe == current) - last_task_used_spe = NULL; + if (cpu_has_feature(CPU_FTR_SPE)) + msr_all_available |= MSR_SPE; #endif - preempt_enable(); + + return 0; +} +early_initcall(init_msr_all_available); + +void giveup_all(struct task_struct *tsk) +{ + unsigned long usermsr; + + if (!tsk->thread.regs) + return; + + usermsr = tsk->thread.regs->msr; + + if ((usermsr & msr_all_available) == 0) + return; + + msr_check_and_set(msr_all_available); + +#ifdef CONFIG_PPC_FPU + if (usermsr & MSR_FP) + __giveup_fpu(tsk); +#endif +#ifdef CONFIG_ALTIVEC + if (usermsr & MSR_VEC) + __giveup_altivec(tsk); +#endif +#ifdef CONFIG_VSX + if (usermsr & MSR_VSX) + __giveup_vsx(tsk); +#endif +#ifdef CONFIG_SPE + if (usermsr & MSR_SPE) + __giveup_spe(tsk); +#endif + + msr_check_and_clear(msr_all_available); +} +EXPORT_SYMBOL(giveup_all); + +void flush_all_to_thread(struct task_struct *tsk) +{ + if (tsk->thread.regs) { + preempt_disable(); + BUG_ON(tsk != current); + giveup_all(tsk); + +#ifdef CONFIG_SPE + if (tsk->thread.regs->msr & MSR_SPE) + tsk->thread.spefscr = mfspr(SPRN_SPEFSCR); +#endif + + preempt_enable(); + } } -#endif /* CONFIG_SMP */ +EXPORT_SYMBOL(flush_all_to_thread); #ifdef CONFIG_PPC_ADV_DEBUG_REGS void do_send_trap(struct pt_regs *regs, unsigned long address, @@ -744,13 +833,15 @@ void restore_tm_state(struct pt_regs *regs) msr_diff = current->thread.ckpt_regs.msr & ~regs->msr; msr_diff &= MSR_FP | MSR_VEC | MSR_VSX; if (msr_diff & MSR_FP) { - fp_enable(); + msr_check_and_set(MSR_FP); load_fp_state(¤t->thread.fp_state); + msr_check_and_clear(MSR_FP); regs->msr |= current->thread.fpexc_mode; } if (msr_diff & MSR_VEC) { - vec_enable(); + msr_check_and_set(MSR_VEC); load_vr_state(¤t->thread.vr_state); + msr_check_and_clear(MSR_VEC); } regs->msr |= msr_diff; } @@ -760,112 +851,87 @@ void restore_tm_state(struct pt_regs *regs) #define __switch_to_tm(prev) #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ -struct task_struct *__switch_to(struct task_struct *prev, - struct task_struct *new) +static inline void save_sprs(struct thread_struct *t) { - struct thread_struct *new_thread, *old_thread; - struct task_struct *last; -#ifdef CONFIG_PPC_BOOK3S_64 - struct ppc64_tlb_batch *batch; +#ifdef CONFIG_ALTIVEC + if (cpu_has_feature(cpu_has_feature(CPU_FTR_ALTIVEC))) + t->vrsave = mfspr(SPRN_VRSAVE); #endif +#ifdef CONFIG_PPC_BOOK3S_64 + if (cpu_has_feature(CPU_FTR_DSCR)) + t->dscr = mfspr(SPRN_DSCR); - WARN_ON(!irqs_disabled()); + if (cpu_has_feature(CPU_FTR_ARCH_207S)) { + t->bescr = mfspr(SPRN_BESCR); + t->ebbhr = mfspr(SPRN_EBBHR); + t->ebbrr = mfspr(SPRN_EBBRR); - /* Back up the TAR and DSCR across context switches. - * Note that the TAR is not available for use in the kernel. (To - * provide this, the TAR should be backed up/restored on exception - * entry/exit instead, and be in pt_regs. FIXME, this should be in - * pt_regs anyway (for debug).) - * Save the TAR and DSCR here before we do treclaim/trecheckpoint as - * these will change them. - */ - save_early_sprs(&prev->thread); + t->fscr = mfspr(SPRN_FSCR); - __switch_to_tm(prev); + /* + * Note that the TAR is not available for use in the kernel. + * (To provide this, the TAR should be backed up/restored on + * exception entry/exit instead, and be in pt_regs. FIXME, + * this should be in pt_regs anyway (for debug).) + */ + t->tar = mfspr(SPRN_TAR); + } +#endif +} -#ifdef CONFIG_SMP - /* avoid complexity of lazy save/restore of fpu - * by just saving it every time we switch out if - * this task used the fpu during the last quantum. - * - * If it tries to use the fpu again, it'll trap and - * reload its fp regs. So we don't have to do a restore - * every switch, just a save. - * -- Cort - */ - if (prev->thread.regs && (prev->thread.regs->msr & MSR_FP)) - giveup_fpu(prev); +static inline void restore_sprs(struct thread_struct *old_thread, + struct thread_struct *new_thread) +{ #ifdef CONFIG_ALTIVEC - /* - * If the previous thread used altivec in the last quantum - * (thus changing altivec regs) then save them. - * We used to check the VRSAVE register but not all apps - * set it, so we don't rely on it now (and in fact we need - * to save & restore VSCR even if VRSAVE == 0). -- paulus - * - * On SMP we always save/restore altivec regs just to avoid the - * complexity of changing processors. - * -- Cort - */ - if (prev->thread.regs && (prev->thread.regs->msr & MSR_VEC)) - giveup_altivec(prev); -#endif /* CONFIG_ALTIVEC */ -#ifdef CONFIG_VSX - if (prev->thread.regs && (prev->thread.regs->msr & MSR_VSX)) - /* VMX and FPU registers are already save here */ - __giveup_vsx(prev); -#endif /* CONFIG_VSX */ -#ifdef CONFIG_SPE - /* - * If the previous thread used spe in the last quantum - * (thus changing spe regs) then save them. - * - * On SMP we always save/restore spe regs just to avoid the - * complexity of changing processors. - */ - if ((prev->thread.regs && (prev->thread.regs->msr & MSR_SPE))) - giveup_spe(prev); -#endif /* CONFIG_SPE */ + if (cpu_has_feature(CPU_FTR_ALTIVEC) && + old_thread->vrsave != new_thread->vrsave) + mtspr(SPRN_VRSAVE, new_thread->vrsave); +#endif +#ifdef CONFIG_PPC_BOOK3S_64 + if (cpu_has_feature(CPU_FTR_DSCR)) { + u64 dscr = get_paca()->dscr_default; + u64 fscr = old_thread->fscr & ~FSCR_DSCR; -#else /* CONFIG_SMP */ -#ifdef CONFIG_ALTIVEC - /* Avoid the trap. On smp this this never happens since - * we don't set last_task_used_altivec -- Cort - */ - if (new->thread.regs && last_task_used_altivec == new) - new->thread.regs->msr |= MSR_VEC; -#endif /* CONFIG_ALTIVEC */ -#ifdef CONFIG_VSX - if (new->thread.regs && last_task_used_vsx == new) - new->thread.regs->msr |= MSR_VSX; -#endif /* CONFIG_VSX */ -#ifdef CONFIG_SPE - /* Avoid the trap. On smp this this never happens since - * we don't set last_task_used_spe - */ - if (new->thread.regs && last_task_used_spe == new) - new->thread.regs->msr |= MSR_SPE; -#endif /* CONFIG_SPE */ + if (new_thread->dscr_inherit) { + dscr = new_thread->dscr; + fscr |= FSCR_DSCR; + } -#endif /* CONFIG_SMP */ + if (old_thread->dscr != dscr) + mtspr(SPRN_DSCR, dscr); -#ifdef CONFIG_PPC_ADV_DEBUG_REGS - switch_booke_debug_regs(&new->thread.debug); -#else -/* - * For PPC_BOOK3S_64, we use the hw-breakpoint interfaces that would - * schedule DABR - */ -#ifndef CONFIG_HAVE_HW_BREAKPOINT - if (unlikely(!hw_brk_match(this_cpu_ptr(¤t_brk), &new->thread.hw_brk))) - __set_breakpoint(&new->thread.hw_brk); -#endif /* CONFIG_HAVE_HW_BREAKPOINT */ + if (old_thread->fscr != fscr) + mtspr(SPRN_FSCR, fscr); + } + + if (cpu_has_feature(CPU_FTR_ARCH_207S)) { + if (old_thread->bescr != new_thread->bescr) + mtspr(SPRN_BESCR, new_thread->bescr); + if (old_thread->ebbhr != new_thread->ebbhr) + mtspr(SPRN_EBBHR, new_thread->ebbhr); + if (old_thread->ebbrr != new_thread->ebbrr) + mtspr(SPRN_EBBRR, new_thread->ebbrr); + + if (old_thread->tar != new_thread->tar) + mtspr(SPRN_TAR, new_thread->tar); + } #endif +} +struct task_struct *__switch_to(struct task_struct *prev, + struct task_struct *new) +{ + struct thread_struct *new_thread, *old_thread; + struct task_struct *last; +#ifdef CONFIG_PPC_BOOK3S_64 + struct ppc64_tlb_batch *batch; +#endif new_thread = &new->thread; old_thread = ¤t->thread; + WARN_ON(!irqs_disabled()); + #ifdef CONFIG_PPC64 /* * Collect processor utilization data per process @@ -890,6 +956,30 @@ struct task_struct *__switch_to(struct task_struct *prev, } #endif /* CONFIG_PPC_BOOK3S_64 */ +#ifdef CONFIG_PPC_ADV_DEBUG_REGS + switch_booke_debug_regs(&new->thread.debug); +#else +/* + * For PPC_BOOK3S_64, we use the hw-breakpoint interfaces that would + * schedule DABR + */ +#ifndef CONFIG_HAVE_HW_BREAKPOINT + if (unlikely(!hw_brk_match(this_cpu_ptr(¤t_brk), &new->thread.hw_brk))) + __set_breakpoint(&new->thread.hw_brk); +#endif /* CONFIG_HAVE_HW_BREAKPOINT */ +#endif + + /* + * We need to save SPRs before treclaim/trecheckpoint as these will + * change a number of them. + */ + save_sprs(&prev->thread); + + __switch_to_tm(prev); + + /* Save FPU, Altivec, VSX and SPE state */ + giveup_all(prev); + /* * We can't take a PMU exception inside _switch() since there is a * window where the kernel stack SLB and the kernel stack are out @@ -899,6 +989,15 @@ struct task_struct *__switch_to(struct task_struct *prev, tm_recheckpoint_new_task(new); + /* + * Call restore_sprs() before calling _switch(). If we move it after + * _switch() then we miss out on calling it for new tasks. The reason + * for this is we manually create a stack frame for new tasks that + * directly returns through ret_from_fork() or + * ret_from_kernel_thread(). See copy_thread() for details. + */ + restore_sprs(old_thread, new_thread); + last = _switch(old_thread, new_thread); #ifdef CONFIG_PPC_BOOK3S_64 @@ -952,10 +1051,12 @@ static void show_instructions(struct pt_regs *regs) printk("\n"); } -static struct regbit { +struct regbit { unsigned long bit; const char *name; -} msr_bits[] = { +}; + +static struct regbit msr_bits[] = { #if defined(CONFIG_PPC64) && !defined(CONFIG_BOOKE) {MSR_SF, "SF"}, {MSR_HV, "HV"}, @@ -985,16 +1086,49 @@ static struct regbit { {0, NULL} }; -static void printbits(unsigned long val, struct regbit *bits) +static void print_bits(unsigned long val, struct regbit *bits, const char *sep) { - const char *sep = ""; + const char *s = ""; - printk("<"); for (; bits->bit; ++bits) if (val & bits->bit) { - printk("%s%s", sep, bits->name); - sep = ","; + printk("%s%s", s, bits->name); + s = sep; } +} + +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +static struct regbit msr_tm_bits[] = { + {MSR_TS_T, "T"}, + {MSR_TS_S, "S"}, + {MSR_TM, "E"}, + {0, NULL} +}; + +static void print_tm_bits(unsigned long val) +{ +/* + * This only prints something if at least one of the TM bit is set. + * Inside the TM[], the output means: + * E: Enabled (bit 32) + * S: Suspended (bit 33) + * T: Transactional (bit 34) + */ + if (val & (MSR_TM | MSR_TS_S | MSR_TS_T)) { + printk(",TM["); + print_bits(val, msr_tm_bits, ""); + printk("]"); + } +} +#else +static void print_tm_bits(unsigned long val) {} +#endif + +static void print_msr_bits(unsigned long val) +{ + printk("<"); + print_bits(val, msr_bits, ","); + print_tm_bits(val); printk(">"); } @@ -1019,7 +1153,7 @@ void show_regs(struct pt_regs * regs) printk("REGS: %p TRAP: %04lx %s (%s)\n", regs, regs->trap, print_tainted(), init_utsname()->release); printk("MSR: "REG" ", regs->msr); - printbits(regs->msr, msr_bits); + print_msr_bits(regs->msr); printk(" CR: %08lx XER: %08lx\n", regs->ccr, regs->xer); trap = TRAP(regs); if ((regs->trap != 0xc00) && cpu_has_feature(CPU_FTR_CFAR)) @@ -1061,13 +1195,10 @@ void show_regs(struct pt_regs * regs) void exit_thread(void) { - discard_lazy_cpu_state(); } void flush_thread(void) { - discard_lazy_cpu_state(); - #ifdef CONFIG_HAVE_HW_BREAKPOINT flush_ptrace_hw_breakpoint(current); #else /* CONFIG_HAVE_HW_BREAKPOINT */ @@ -1086,10 +1217,7 @@ release_thread(struct task_struct *t) */ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { - flush_fp_to_thread(src); - flush_altivec_to_thread(src); - flush_vsx_to_thread(src); - flush_spe_to_thread(src); + flush_all_to_thread(src); /* * Flush TM state out so we can copy it. __switch_to_tm() does this * flush but it removes the checkpointed state from the current CPU and @@ -1212,7 +1340,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, #ifdef CONFIG_PPC64 if (cpu_has_feature(CPU_FTR_DSCR)) { p->thread.dscr_inherit = current->thread.dscr_inherit; - p->thread.dscr = current->thread.dscr; + p->thread.dscr = mfspr(SPRN_DSCR); } if (cpu_has_feature(CPU_FTR_HAS_PPR)) p->thread.ppr = INIT_PPR; @@ -1305,7 +1433,6 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) regs->msr = MSR_USER32; } #endif - discard_lazy_cpu_state(); #ifdef CONFIG_VSX current->thread.used_vsr = 0; #endif diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 92dea8df6b26..da5192590c44 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -389,6 +389,7 @@ static void __init prom_printf(const char *format, ...) break; } } + va_end(args); } diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 737c0d0b53ac..30a03c03fe73 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -60,6 +60,7 @@ struct pt_regs_offset { #define STR(s) #s /* convert to string */ #define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)} #define GPR_OFFSET_NAME(num) \ + {.name = STR(r##num), .offset = offsetof(struct pt_regs, gpr[num])}, \ {.name = STR(gpr##num), .offset = offsetof(struct pt_regs, gpr[num])} #define REG_OFFSET_END {.name = NULL, .offset = 0} diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 5a753fae8265..28736ff27fea 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -44,6 +44,9 @@ #include <asm/mmu.h> #include <asm/topology.h> +/* This is here deliberately so it's only used in this file */ +void enter_rtas(unsigned long); + struct rtas_t rtas = { .lock = __ARCH_SPIN_LOCK_UNLOCKED }; @@ -93,21 +96,13 @@ static void unlock_rtas(unsigned long flags) */ static void call_rtas_display_status(unsigned char c) { - struct rtas_args *args = &rtas.args; unsigned long s; if (!rtas.base) return; - s = lock_rtas(); - - args->token = cpu_to_be32(10); - args->nargs = cpu_to_be32(1); - args->nret = cpu_to_be32(1); - args->rets = &(args->args[1]); - args->args[0] = cpu_to_be32(c); - - enter_rtas(__pa(args)); + s = lock_rtas(); + rtas_call_unlocked(&rtas.args, 10, 1, 1, NULL, c); unlock_rtas(s); } @@ -418,6 +413,36 @@ static char *__fetch_rtas_last_error(char *altbuf) #define get_errorlog_buffer() NULL #endif + +static void +va_rtas_call_unlocked(struct rtas_args *args, int token, int nargs, int nret, + va_list list) +{ + int i; + + args->token = cpu_to_be32(token); + args->nargs = cpu_to_be32(nargs); + args->nret = cpu_to_be32(nret); + args->rets = &(args->args[nargs]); + + for (i = 0; i < nargs; ++i) + args->args[i] = cpu_to_be32(va_arg(list, __u32)); + + for (i = 0; i < nret; ++i) + args->rets[i] = 0; + + enter_rtas(__pa(args)); +} + +void rtas_call_unlocked(struct rtas_args *args, int token, int nargs, int nret, ...) +{ + va_list list; + + va_start(list, nret); + va_rtas_call_unlocked(args, token, nargs, nret, list); + va_end(list); +} + int rtas_call(int token, int nargs, int nret, int *outputs, ...) { va_list list; @@ -431,22 +456,14 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...) return -1; s = lock_rtas(); + + /* We use the global rtas args buffer */ rtas_args = &rtas.args; - rtas_args->token = cpu_to_be32(token); - rtas_args->nargs = cpu_to_be32(nargs); - rtas_args->nret = cpu_to_be32(nret); - rtas_args->rets = &(rtas_args->args[nargs]); va_start(list, outputs); - for (i = 0; i < nargs; ++i) - rtas_args->args[i] = cpu_to_be32(va_arg(list, __u32)); + va_rtas_call_unlocked(rtas_args, token, nargs, nret, list); va_end(list); - for (i = 0; i < nret; ++i) - rtas_args->rets[i] = 0; - - enter_rtas(__pa(rtas_args)); - /* A -1 return code indicates that the last command couldn't be completed due to a hardware error. */ if (be32_to_cpu(rtas_args->rets[0]) == -1) diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index ef7c24e84a62..b6aa378aff63 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -458,7 +458,7 @@ static int save_user_regs(struct pt_regs *regs, struct mcontext __user *frame, * contains valid data */ if (current->thread.used_vsr && ctx_has_vsx_region) { - __giveup_vsx(current); + flush_vsx_to_thread(current); if (copy_vsx_to_user(&frame->mc_vsregs, current)) return 1; msr |= MSR_VSX; @@ -606,7 +606,7 @@ static int save_tm_user_regs(struct pt_regs *regs, * contains valid data */ if (current->thread.used_vsr) { - __giveup_vsx(current); + flush_vsx_to_thread(current); if (copy_vsx_to_user(&frame->mc_vsregs, current)) return 1; if (msr & MSR_VSX) { @@ -687,15 +687,6 @@ static long restore_user_regs(struct pt_regs *regs, if (sig) regs->msr = (regs->msr & ~MSR_LE) | (msr & MSR_LE); - /* - * Do this before updating the thread state in - * current->thread.fpr/vr/evr. That way, if we get preempted - * and another task grabs the FPU/Altivec/SPE, it won't be - * tempted to save the current CPU state into the thread_struct - * and corrupt what we are writing there. - */ - discard_lazy_cpu_state(); - #ifdef CONFIG_ALTIVEC /* * Force the process to reload the altivec registers from @@ -798,15 +789,6 @@ static long restore_tm_user_regs(struct pt_regs *regs, /* Restore the previous little-endian mode */ regs->msr = (regs->msr & ~MSR_LE) | (msr & MSR_LE); - /* - * Do this before updating the thread state in - * current->thread.fpr/vr/evr. That way, if we get preempted - * and another task grabs the FPU/Altivec/SPE, it won't be - * tempted to save the current CPU state into the thread_struct - * and corrupt what we are writing there. - */ - discard_lazy_cpu_state(); - #ifdef CONFIG_ALTIVEC regs->msr &= ~MSR_VEC; if (msr & MSR_VEC) { diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index c676ecec0869..25520794aa37 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -147,7 +147,7 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs, * VMX data. */ if (current->thread.used_vsr && ctx_has_vsx_region) { - __giveup_vsx(current); + flush_vsx_to_thread(current); v_regs += ELF_NVRREG; err |= copy_vsx_to_user(v_regs, current); /* set MSR_VSX in the MSR value in the frame to @@ -270,7 +270,7 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc, * VMX data. */ if (current->thread.used_vsr) { - __giveup_vsx(current); + flush_vsx_to_thread(current); v_regs += ELF_NVRREG; tm_v_regs += ELF_NVRREG; @@ -350,15 +350,6 @@ static long restore_sigcontext(struct pt_regs *regs, sigset_t *set, int sig, err |= __get_user(set->sig[0], &sc->oldmask); /* - * Do this before updating the thread state in - * current->thread.fpr/vr. That way, if we get preempted - * and another task grabs the FPU/Altivec, it won't be - * tempted to save the current CPU state into the thread_struct - * and corrupt what we are writing there. - */ - discard_lazy_cpu_state(); - - /* * Force reload of FP/VEC. * This has to be done before copying stuff into current->thread.fpr/vr * for the reasons explained in the previous comment. @@ -469,15 +460,6 @@ static long restore_tm_sigcontexts(struct pt_regs *regs, err |= __get_user(regs->result, &sc->gp_regs[PT_RESULT]); /* - * Do this before updating the thread state in - * current->thread.fpr/vr. That way, if we get preempted - * and another task grabs the FPU/Altivec, it won't be - * tempted to save the current CPU state into the thread_struct - * and corrupt what we are writing there. - */ - discard_lazy_cpu_state(); - - /* * Force reload of FP/VEC. * This has to be done before copying stuff into current->thread.fpr/vr * for the reasons explained in the previous comment. diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c index ea43a347a104..4f24606afc3f 100644 --- a/arch/powerpc/kernel/stacktrace.c +++ b/arch/powerpc/kernel/stacktrace.c @@ -61,3 +61,10 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) save_context_stack(trace, tsk->thread.ksp, tsk, 0); } EXPORT_SYMBOL_GPL(save_stack_trace_tsk); + +void +save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace) +{ + save_context_stack(trace, regs->gpr[1], current, 0); +} +EXPORT_SYMBOL_GPL(save_stack_trace_regs); diff --git a/arch/powerpc/kernel/swsusp.c b/arch/powerpc/kernel/swsusp.c index eae33e10b65f..6669b1752512 100644 --- a/arch/powerpc/kernel/swsusp.c +++ b/arch/powerpc/kernel/swsusp.c @@ -20,9 +20,7 @@ void save_processor_state(void) * flush out all the special registers so we don't need * to save them in the snapshot */ - flush_fp_to_thread(current); - flush_altivec_to_thread(current); - flush_spe_to_thread(current); + flush_all_to_thread(current); #ifdef CONFIG_PPC64 hard_irq_disable(); diff --git a/arch/powerpc/kernel/systbl_chk.c b/arch/powerpc/kernel/systbl_chk.c index 2384129f5893..55323a620cfe 100644 --- a/arch/powerpc/kernel/systbl_chk.c +++ b/arch/powerpc/kernel/systbl_chk.c @@ -57,4 +57,4 @@ START_TABLE #include <asm/systbl.h> -END_TABLE __NR_syscalls +END_TABLE NR_syscalls diff --git a/arch/powerpc/kernel/systbl_chk.sh b/arch/powerpc/kernel/systbl_chk.sh index 19415e7674a5..31b6e7c358ca 100644 --- a/arch/powerpc/kernel/systbl_chk.sh +++ b/arch/powerpc/kernel/systbl_chk.sh @@ -16,7 +16,7 @@ awk 'BEGIN { num = -1; } # Ignore the beginning of the file /^START_TABLE/ { num = 0; next; } /^END_TABLE/ { if (num != $2) { - printf "__NR_syscalls (%s) is not one more than the last syscall (%s)\n", + printf "NR_syscalls (%s) is not one more than the last syscall (%s)\n", $2, num - 1; exit(1); } diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 1be1092c7204..81b0900a39ee 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -1002,38 +1002,6 @@ static int month_days[12] = { 31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31 }; -/* - * This only works for the Gregorian calendar - i.e. after 1752 (in the UK) - */ -void GregorianDay(struct rtc_time * tm) -{ - int leapsToDate; - int lastYear; - int day; - int MonthOffset[] = { 0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334 }; - - lastYear = tm->tm_year - 1; - - /* - * Number of leap corrections to apply up to end of last year - */ - leapsToDate = lastYear / 4 - lastYear / 100 + lastYear / 400; - - /* - * This year is a leap year if it is divisible by 4 except when it is - * divisible by 100 unless it is divisible by 400 - * - * e.g. 1904 was a leap year, 1900 was not, 1996 is, and 2000 was - */ - day = tm->tm_mon > 2 && leapyear(tm->tm_year); - - day += lastYear*365 + leapsToDate + MonthOffset[tm->tm_mon-1] + - tm->tm_mday; - - tm->tm_wday = day % 7; -} -EXPORT_SYMBOL_GPL(GregorianDay); - void to_tm(int tim, struct rtc_time * tm) { register int i; @@ -1064,9 +1032,9 @@ void to_tm(int tim, struct rtc_time * tm) tm->tm_mday = day + 1; /* - * Determine the day of week + * No-one uses the day of the week. */ - GregorianDay(tm); + tm->tm_wday = -1; } EXPORT_SYMBOL(to_tm); diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 37de90f8a845..b6becc795bb5 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -1313,13 +1313,6 @@ void nonrecoverable_exception(struct pt_regs *regs) die("nonrecoverable exception", regs, SIGKILL); } -void trace_syscall(struct pt_regs *regs) -{ - printk("Task: %p(%d), PC: %08lX/%08lX, Syscall: %3ld, Result: %s%ld %s\n", - current, task_pid_nr(current), regs->nip, regs->link, regs->gpr[0], - regs->ccr&0x10000000?"Error=":"", regs->gpr[3], print_tainted()); -} - void kernel_fp_unavailable_exception(struct pt_regs *regs) { enum ctx_state prev_state = exception_enter(); diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index b457bfa28436..def1b8b5e6c1 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -671,7 +671,7 @@ static void __init vdso_setup_syscall_map(void) extern unsigned long sys_ni_syscall; - for (i = 0; i < __NR_syscalls; i++) { + for (i = 0; i < NR_syscalls; i++) { #ifdef CONFIG_PPC64 if (sys_call_table[i*2] != sys_ni_syscall) vdso_data->syscall_map_64[i >> 5] |= diff --git a/arch/powerpc/kernel/vdso32/datapage.S b/arch/powerpc/kernel/vdso32/datapage.S index 59cf5f452879..3745113fcc65 100644 --- a/arch/powerpc/kernel/vdso32/datapage.S +++ b/arch/powerpc/kernel/vdso32/datapage.S @@ -61,7 +61,7 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map) addi r3,r3,CFG_SYSCALL_MAP32 cmpli cr0,r4,0 beqlr - li r0,__NR_syscalls + li r0,NR_syscalls stw r0,0(r4) crclr cr0*4+so blr diff --git a/arch/powerpc/kernel/vdso64/datapage.S b/arch/powerpc/kernel/vdso64/datapage.S index 2f01c4a0d8a0..184a6ba7f283 100644 --- a/arch/powerpc/kernel/vdso64/datapage.S +++ b/arch/powerpc/kernel/vdso64/datapage.S @@ -62,7 +62,7 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map) cmpli cr0,r4,0 crclr cr0*4+so beqlr - li r0,__NR_syscalls + li r0,NR_syscalls stw r0,0(r4) blr .cfi_endproc diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S index f5c80d567d8d..162d0f714941 100644 --- a/arch/powerpc/kernel/vector.S +++ b/arch/powerpc/kernel/vector.S @@ -29,24 +29,10 @@ _GLOBAL(do_load_up_transact_altivec) addi r10,r3,THREAD_TRANSACT_VRSTATE REST_32VRS(0,r4,r10) - /* Disable VEC again. */ - MTMSRD(r6) - isync - blr #endif /* - * Enable use of VMX/Altivec for the caller. - */ -_GLOBAL(vec_enable) - mfmsr r3 - oris r3,r3,MSR_VEC@h - MTMSRD(r3) - isync - blr - -/* * Load state from memory into VMX registers including VSCR. * Assumes the caller has enabled VMX in the MSR. */ @@ -84,39 +70,6 @@ _GLOBAL(load_up_altivec) MTMSRD(r5) /* enable use of AltiVec now */ isync -/* - * For SMP, we don't do lazy VMX switching because it just gets too - * horrendously complex, especially when a task switches from one CPU - * to another. Instead we call giveup_altvec in switch_to. - * VRSAVE isn't dealt with here, that is done in the normal context - * switch code. Note that we could rely on vrsave value to eventually - * avoid saving all of the VREGs here... - */ -#ifndef CONFIG_SMP - LOAD_REG_ADDRBASE(r3, last_task_used_altivec) - toreal(r3) - PPC_LL r4,ADDROFF(last_task_used_altivec)(r3) - PPC_LCMPI 0,r4,0 - beq 1f - - /* Save VMX state to last_task_used_altivec's THREAD struct */ - toreal(r4) - addi r4,r4,THREAD - addi r6,r4,THREAD_VRSTATE - SAVE_32VRS(0,r5,r6) - mfvscr v0 - li r10,VRSTATE_VSCR - stvx v0,r10,r6 - /* Disable VMX for last_task_used_altivec */ - PPC_LL r5,PT_REGS(r4) - toreal(r5) - PPC_LL r4,_MSR-STACK_FRAME_OVERHEAD(r5) - lis r10,MSR_VEC@h - andc r4,r4,r10 - PPC_STL r4,_MSR-STACK_FRAME_OVERHEAD(r5) -1: -#endif /* CONFIG_SMP */ - /* Hack: if we get an altivec unavailable trap with VRSAVE * set to all zeros, we assume this is a broken application * that fails to set it properly, and thus we switch it to @@ -145,39 +98,15 @@ _GLOBAL(load_up_altivec) lvx v0,r10,r6 mtvscr v0 REST_32VRS(0,r4,r6) -#ifndef CONFIG_SMP - /* Update last_task_used_altivec to 'current' */ - subi r4,r5,THREAD /* Back to 'current' */ - fromreal(r4) - PPC_STL r4,ADDROFF(last_task_used_altivec)(r3) -#endif /* CONFIG_SMP */ /* restore registers and return */ blr -_GLOBAL(giveup_altivec_notask) - mfmsr r3 - andis. r4,r3,MSR_VEC@h - bnelr /* Already enabled? */ - oris r3,r3,MSR_VEC@h - SYNC - MTMSRD(r3) /* enable use of VMX now */ - isync - blr - /* - * giveup_altivec(tsk) + * __giveup_altivec(tsk) * Disable VMX for the task given as the argument, * and save the vector registers in its thread_struct. - * Enables the VMX for use in the kernel on return. */ -_GLOBAL(giveup_altivec) - mfmsr r5 - oris r5,r5,MSR_VEC@h - SYNC - MTMSRD(r5) /* enable use of VMX now */ - isync - PPC_LCMPI 0,r3,0 - beqlr /* if no previous owner, done */ +_GLOBAL(__giveup_altivec) addi r3,r3,THREAD /* want THREAD of task */ PPC_LL r7,THREAD_VRSAVEAREA(r3) PPC_LL r5,PT_REGS(r3) @@ -203,11 +132,6 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_VSX) andc r4,r4,r3 /* disable FP for previous task */ PPC_STL r4,_MSR-STACK_FRAME_OVERHEAD(r5) 1: -#ifndef CONFIG_SMP - li r5,0 - LOAD_REG_ADDRBASE(r4,last_task_used_altivec) - PPC_STL r5,ADDROFF(last_task_used_altivec)(r4) -#endif /* CONFIG_SMP */ blr #ifdef CONFIG_VSX @@ -230,20 +154,6 @@ _GLOBAL(load_up_vsx) andis. r5,r12,MSR_VEC@h beql+ load_up_altivec /* skip if already loaded */ -#ifndef CONFIG_SMP - ld r3,last_task_used_vsx@got(r2) - ld r4,0(r3) - cmpdi 0,r4,0 - beq 1f - /* Disable VSX for last_task_used_vsx */ - addi r4,r4,THREAD - ld r5,PT_REGS(r4) - ld r4,_MSR-STACK_FRAME_OVERHEAD(r5) - lis r6,MSR_VSX@h - andc r6,r4,r6 - std r6,_MSR-STACK_FRAME_OVERHEAD(r5) -1: -#endif /* CONFIG_SMP */ ld r4,PACACURRENT(r13) addi r4,r4,THREAD /* Get THREAD */ li r6,1 @@ -251,27 +161,14 @@ _GLOBAL(load_up_vsx) /* enable use of VSX after return */ oris r12,r12,MSR_VSX@h std r12,_MSR(r1) -#ifndef CONFIG_SMP - /* Update last_task_used_vsx to 'current' */ - ld r4,PACACURRENT(r13) - std r4,0(r3) -#endif /* CONFIG_SMP */ b fast_exception_return /* * __giveup_vsx(tsk) * Disable VSX for the task given as the argument. * Does NOT save vsx registers. - * Enables the VSX for use in the kernel on return. */ _GLOBAL(__giveup_vsx) - mfmsr r5 - oris r5,r5,MSR_VSX@h - mtmsrd r5 /* enable use of VSX now */ - isync - - cmpdi 0,r3,0 - beqlr- /* if no previous owner, done */ addi r3,r3,THREAD /* want THREAD of task */ ld r5,PT_REGS(r3) cmpdi 0,r5,0 @@ -281,11 +178,6 @@ _GLOBAL(__giveup_vsx) andc r4,r4,r3 /* disable VSX for previous task */ std r4,_MSR-STACK_FRAME_OVERHEAD(r5) 1: -#ifndef CONFIG_SMP - li r5,0 - ld r4,last_task_used_vsx@got(r2) - std r5,0(r4) -#endif /* CONFIG_SMP */ blr #endif /* CONFIG_VSX */ diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 6b352691b8c9..cff207b72c46 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -2700,9 +2700,8 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu) goto out; } - flush_fp_to_thread(current); - flush_altivec_to_thread(current); - flush_vsx_to_thread(current); + flush_all_to_thread(current); + vcpu->arch.wqp = &vcpu->arch.vcore->wq; vcpu->arch.pgdir = current->mm->pgd; vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST; diff --git a/arch/powerpc/kvm/book3s_paired_singles.c b/arch/powerpc/kvm/book3s_paired_singles.c index a759d9adb0b6..eab96cfe82fa 100644 --- a/arch/powerpc/kvm/book3s_paired_singles.c +++ b/arch/powerpc/kvm/book3s_paired_singles.c @@ -1265,6 +1265,7 @@ int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu) if (rcomp) kvmppc_set_cr(vcpu, cr); + disable_kernel_fp(); preempt_enable(); return emulated; diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index 70fb08da416d..95bceca8f40e 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -751,6 +751,7 @@ static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr, preempt_disable(); enable_kernel_fp(); load_fp_state(&vcpu->arch.fp); + disable_kernel_fp(); t->fp_save_area = &vcpu->arch.fp; preempt_enable(); } @@ -760,6 +761,7 @@ static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr, preempt_disable(); enable_kernel_altivec(); load_vr_state(&vcpu->arch.vr); + disable_kernel_altivec(); t->vr_save_area = &vcpu->arch.vr; preempt_enable(); #endif @@ -788,6 +790,7 @@ static void kvmppc_handle_lost_ext(struct kvm_vcpu *vcpu) preempt_disable(); enable_kernel_fp(); load_fp_state(&vcpu->arch.fp); + disable_kernel_fp(); preempt_enable(); } #ifdef CONFIG_ALTIVEC @@ -795,6 +798,7 @@ static void kvmppc_handle_lost_ext(struct kvm_vcpu *vcpu) preempt_disable(); enable_kernel_altivec(); load_vr_state(&vcpu->arch.vr); + disable_kernel_altivec(); preempt_enable(); } #endif @@ -1486,21 +1490,8 @@ static int kvmppc_vcpu_run_pr(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) goto out; /* interrupts now hard-disabled */ - /* Save FPU state in thread_struct */ - if (current->thread.regs->msr & MSR_FP) - giveup_fpu(current); - -#ifdef CONFIG_ALTIVEC - /* Save Altivec state in thread_struct */ - if (current->thread.regs->msr & MSR_VEC) - giveup_altivec(current); -#endif - -#ifdef CONFIG_VSX - /* Save VSX state in thread_struct */ - if (current->thread.regs->msr & MSR_VSX) - __giveup_vsx(current); -#endif + /* Save FPU, Altivec and VSX state */ + giveup_all(current); /* Preload FPU if it's enabled */ if (kvmppc_get_msr(vcpu) & MSR_FP) diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index fd5875179e5c..778ef86e187e 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -98,6 +98,7 @@ void kvmppc_vcpu_disable_spe(struct kvm_vcpu *vcpu) preempt_disable(); enable_kernel_spe(); kvmppc_save_guest_spe(vcpu); + disable_kernel_spe(); vcpu->arch.shadow_msr &= ~MSR_SPE; preempt_enable(); } @@ -107,6 +108,7 @@ static void kvmppc_vcpu_enable_spe(struct kvm_vcpu *vcpu) preempt_disable(); enable_kernel_spe(); kvmppc_load_guest_spe(vcpu); + disable_kernel_spe(); vcpu->arch.shadow_msr |= MSR_SPE; preempt_enable(); } @@ -141,6 +143,7 @@ static inline void kvmppc_load_guest_fp(struct kvm_vcpu *vcpu) if (!(current->thread.regs->msr & MSR_FP)) { enable_kernel_fp(); load_fp_state(&vcpu->arch.fp); + disable_kernel_fp(); current->thread.fp_save_area = &vcpu->arch.fp; current->thread.regs->msr |= MSR_FP; } @@ -182,6 +185,7 @@ static inline void kvmppc_load_guest_altivec(struct kvm_vcpu *vcpu) if (!(current->thread.regs->msr & MSR_VEC)) { enable_kernel_altivec(); load_vr_state(&vcpu->arch.vr); + disable_kernel_altivec(); current->thread.vr_save_area = &vcpu->arch.vr; current->thread.regs->msr |= MSR_VEC; } diff --git a/arch/powerpc/lib/vmx-helper.c b/arch/powerpc/lib/vmx-helper.c index ac93a3bd2730..b27e030fc9f8 100644 --- a/arch/powerpc/lib/vmx-helper.c +++ b/arch/powerpc/lib/vmx-helper.c @@ -46,6 +46,7 @@ int enter_vmx_usercopy(void) */ int exit_vmx_usercopy(void) { + disable_kernel_altivec(); pagefault_enable(); preempt_enable(); return 0; @@ -70,6 +71,7 @@ int enter_vmx_copy(void) */ void *exit_vmx_copy(void *dest) { + disable_kernel_altivec(); preempt_enable(); return dest; } diff --git a/arch/powerpc/lib/xor_vmx.c b/arch/powerpc/lib/xor_vmx.c index e905f7c2ea7b..07f49f1568e5 100644 --- a/arch/powerpc/lib/xor_vmx.c +++ b/arch/powerpc/lib/xor_vmx.c @@ -74,6 +74,7 @@ void xor_altivec_2(unsigned long bytes, unsigned long *v1_in, v2 += 4; } while (--lines > 0); + disable_kernel_altivec(); preempt_enable(); } EXPORT_SYMBOL(xor_altivec_2); @@ -102,6 +103,7 @@ void xor_altivec_3(unsigned long bytes, unsigned long *v1_in, v3 += 4; } while (--lines > 0); + disable_kernel_altivec(); preempt_enable(); } EXPORT_SYMBOL(xor_altivec_3); @@ -135,6 +137,7 @@ void xor_altivec_4(unsigned long bytes, unsigned long *v1_in, v4 += 4; } while (--lines > 0); + disable_kernel_altivec(); preempt_enable(); } EXPORT_SYMBOL(xor_altivec_4); @@ -172,6 +175,7 @@ void xor_altivec_5(unsigned long bytes, unsigned long *v1_in, v5 += 4; } while (--lines > 0); + disable_kernel_altivec(); preempt_enable(); } EXPORT_SYMBOL(xor_altivec_5); diff --git a/arch/powerpc/mm/40x_mmu.c b/arch/powerpc/mm/40x_mmu.c index 5810967511d4..31a5d42df8c9 100644 --- a/arch/powerpc/mm/40x_mmu.c +++ b/arch/powerpc/mm/40x_mmu.c @@ -110,10 +110,10 @@ unsigned long __init mmu_mapin_ram(unsigned long top) unsigned long val = p | _PMD_SIZE_16M | _PAGE_EXEC | _PAGE_HWWRITE; pmdp = pmd_offset(pud_offset(pgd_offset_k(v), v), v); - pmd_val(*pmdp++) = val; - pmd_val(*pmdp++) = val; - pmd_val(*pmdp++) = val; - pmd_val(*pmdp++) = val; + *pmdp++ = __pmd(val); + *pmdp++ = __pmd(val); + *pmdp++ = __pmd(val); + *pmdp++ = __pmd(val); v += LARGE_PAGE_SIZE_16M; p += LARGE_PAGE_SIZE_16M; @@ -125,7 +125,7 @@ unsigned long __init mmu_mapin_ram(unsigned long top) unsigned long val = p | _PMD_SIZE_4M | _PAGE_EXEC | _PAGE_HWWRITE; pmdp = pmd_offset(pud_offset(pgd_offset_k(v), v), v); - pmd_val(*pmdp) = val; + *pmdp = __pmd(val); v += LARGE_PAGE_SIZE_4M; p += LARGE_PAGE_SIZE_4M; diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile index 3eb73a38220d..1ffeda85c086 100644 --- a/arch/powerpc/mm/Makefile +++ b/arch/powerpc/mm/Makefile @@ -14,10 +14,13 @@ obj-$(CONFIG_PPC_MMU_NOHASH) += mmu_context_nohash.o tlb_nohash.o \ obj-$(CONFIG_PPC_BOOK3E) += tlb_low_$(CONFIG_WORD_SIZE)e.o hash64-$(CONFIG_PPC_NATIVE) := hash_native_64.o obj-$(CONFIG_PPC_STD_MMU_64) += hash_utils_64.o slb_low.o slb.o $(hash64-y) -obj-$(CONFIG_PPC_STD_MMU_32) += ppc_mmu_32.o -obj-$(CONFIG_PPC_STD_MMU) += hash_low_$(CONFIG_WORD_SIZE).o \ - tlb_hash$(CONFIG_WORD_SIZE).o \ +obj-$(CONFIG_PPC_STD_MMU_32) += ppc_mmu_32.o hash_low_32.o +obj-$(CONFIG_PPC_STD_MMU) += tlb_hash$(CONFIG_WORD_SIZE).o \ mmu_context_hash$(CONFIG_WORD_SIZE).o +ifeq ($(CONFIG_PPC_STD_MMU_64),y) +obj-$(CONFIG_PPC_4K_PAGES) += hash64_4k.o +obj-$(CONFIG_PPC_64K_PAGES) += hash64_64k.o +endif obj-$(CONFIG_PPC_ICSWX) += icswx.o obj-$(CONFIG_PPC_ICSWX_PID) += icswx_pid.o obj-$(CONFIG_40x) += 40x_mmu.o diff --git a/arch/powerpc/mm/hash64_4k.c b/arch/powerpc/mm/hash64_4k.c new file mode 100644 index 000000000000..e7c04542ba62 --- /dev/null +++ b/arch/powerpc/mm/hash64_4k.c @@ -0,0 +1,123 @@ +/* + * Copyright IBM Corporation, 2015 + * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2 of the GNU Lesser General Public License + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it would be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + * + */ + +#include <linux/mm.h> +#include <asm/machdep.h> +#include <asm/mmu.h> + +int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid, + pte_t *ptep, unsigned long trap, unsigned long flags, + int ssize, int subpg_prot) +{ + unsigned long hpte_group; + unsigned long rflags, pa; + unsigned long old_pte, new_pte; + unsigned long vpn, hash, slot; + unsigned long shift = mmu_psize_defs[MMU_PAGE_4K].shift; + + /* + * atomically mark the linux large page PTE busy and dirty + */ + do { + pte_t pte = READ_ONCE(*ptep); + + old_pte = pte_val(pte); + /* If PTE busy, retry the access */ + if (unlikely(old_pte & _PAGE_BUSY)) + return 0; + /* If PTE permissions don't match, take page fault */ + if (unlikely(access & ~old_pte)) + return 1; + /* + * Try to lock the PTE, add ACCESSED and DIRTY if it was + * a write access. Since this is 4K insert of 64K page size + * also add _PAGE_COMBO + */ + new_pte = old_pte | _PAGE_BUSY | _PAGE_ACCESSED | _PAGE_HASHPTE; + if (access & _PAGE_RW) + new_pte |= _PAGE_DIRTY; + } while (old_pte != __cmpxchg_u64((unsigned long *)ptep, + old_pte, new_pte)); + /* + * PP bits. _PAGE_USER is already PP bit 0x2, so we only + * need to add in 0x1 if it's a read-only user page + */ + rflags = htab_convert_pte_flags(new_pte); + + 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); + + vpn = hpt_vpn(ea, vsid, ssize); + if (unlikely(old_pte & _PAGE_HASHPTE)) { + /* + * There MIGHT be an HPTE for this pte + */ + hash = hpt_hash(vpn, shift, ssize); + if (old_pte & _PAGE_F_SECOND) + hash = ~hash; + slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; + slot += (old_pte & _PAGE_F_GIX) >> _PAGE_F_GIX_SHIFT; + + if (ppc_md.hpte_updatepp(slot, rflags, vpn, MMU_PAGE_4K, + MMU_PAGE_4K, ssize, flags) == -1) + old_pte &= ~_PAGE_HPTEFLAGS; + } + + if (likely(!(old_pte & _PAGE_HASHPTE))) { + + pa = pte_pfn(__pte(old_pte)) << PAGE_SHIFT; + hash = hpt_hash(vpn, shift, ssize); + +repeat: + hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL; + + /* Insert into the hash table, primary slot */ + slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, 0, + MMU_PAGE_4K, MMU_PAGE_4K, ssize); + /* + * Primary is full, try the secondary + */ + if (unlikely(slot == -1)) { + hpte_group = ((~hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL; + slot = ppc_md.hpte_insert(hpte_group, vpn, pa, + rflags, HPTE_V_SECONDARY, + MMU_PAGE_4K, MMU_PAGE_4K, ssize); + if (slot == -1) { + if (mftb() & 0x1) + hpte_group = ((hash & htab_hash_mask) * + HPTES_PER_GROUP) & ~0x7UL; + ppc_md.hpte_remove(hpte_group); + /* + * FIXME!! Should be try the group from which we removed ? + */ + goto repeat; + } + } + /* + * Hypervisor failure. Restore old pmd and return -1 + * similar to __hash_page_* + */ + if (unlikely(slot == -2)) { + *ptep = __pte(old_pte); + hash_failure_debug(ea, access, vsid, trap, ssize, + MMU_PAGE_4K, MMU_PAGE_4K, old_pte); + return -1; + } + new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | _PAGE_HASHPTE; + new_pte |= (slot << _PAGE_F_GIX_SHIFT) & (_PAGE_F_SECOND | _PAGE_F_GIX); + } + *ptep = __pte(new_pte & ~_PAGE_BUSY); + return 0; +} diff --git a/arch/powerpc/mm/hash64_64k.c b/arch/powerpc/mm/hash64_64k.c new file mode 100644 index 000000000000..0762c1e08c88 --- /dev/null +++ b/arch/powerpc/mm/hash64_64k.c @@ -0,0 +1,322 @@ +/* + * Copyright IBM Corporation, 2015 + * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2 of the GNU Lesser General Public License + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it would be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + * + */ + +#include <linux/mm.h> +#include <asm/machdep.h> +#include <asm/mmu.h> +/* + * index from 0 - 15 + */ +bool __rpte_sub_valid(real_pte_t rpte, unsigned long index) +{ + unsigned long g_idx; + unsigned long ptev = pte_val(rpte.pte); + + g_idx = (ptev & _PAGE_COMBO_VALID) >> _PAGE_F_GIX_SHIFT; + index = index >> 2; + if (g_idx & (0x1 << index)) + return true; + else + return false; +} +/* + * index from 0 - 15 + */ +static unsigned long mark_subptegroup_valid(unsigned long ptev, unsigned long index) +{ + unsigned long g_idx; + + if (!(ptev & _PAGE_COMBO)) + return ptev; + index = index >> 2; + g_idx = 0x1 << index; + + return ptev | (g_idx << _PAGE_F_GIX_SHIFT); +} + +int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid, + pte_t *ptep, unsigned long trap, unsigned long flags, + int ssize, int subpg_prot) +{ + real_pte_t rpte; + unsigned long *hidxp; + unsigned long hpte_group; + unsigned int subpg_index; + unsigned long rflags, pa, hidx; + unsigned long old_pte, new_pte, subpg_pte; + unsigned long vpn, hash, slot; + unsigned long shift = mmu_psize_defs[MMU_PAGE_4K].shift; + + /* + * atomically mark the linux large page PTE busy and dirty + */ + do { + pte_t pte = READ_ONCE(*ptep); + + old_pte = pte_val(pte); + /* If PTE busy, retry the access */ + if (unlikely(old_pte & _PAGE_BUSY)) + return 0; + /* If PTE permissions don't match, take page fault */ + if (unlikely(access & ~old_pte)) + return 1; + /* + * Try to lock the PTE, add ACCESSED and DIRTY if it was + * a write access. Since this is 4K insert of 64K page size + * also add _PAGE_COMBO + */ + new_pte = old_pte | _PAGE_BUSY | _PAGE_ACCESSED | _PAGE_COMBO; + if (access & _PAGE_RW) + new_pte |= _PAGE_DIRTY; + } while (old_pte != __cmpxchg_u64((unsigned long *)ptep, + old_pte, new_pte)); + /* + * Handle the subpage protection bits + */ + subpg_pte = new_pte & ~subpg_prot; + rflags = htab_convert_pte_flags(subpg_pte); + + if (!cpu_has_feature(CPU_FTR_NOEXECUTE) && + !cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) { + + /* + * No CPU has hugepages but lacks no execute, so we + * don't need to worry about that case + */ + rflags = hash_page_do_lazy_icache(rflags, __pte(old_pte), trap); + } + + subpg_index = (ea & (PAGE_SIZE - 1)) >> shift; + vpn = hpt_vpn(ea, vsid, ssize); + rpte = __real_pte(__pte(old_pte), ptep); + /* + *None of the sub 4k page is hashed + */ + if (!(old_pte & _PAGE_HASHPTE)) + goto htab_insert_hpte; + /* + * Check if the pte was already inserted into the hash table + * as a 64k HW page, and invalidate the 64k HPTE if so. + */ + if (!(old_pte & _PAGE_COMBO)) { + flush_hash_page(vpn, rpte, MMU_PAGE_64K, ssize, flags); + old_pte &= ~_PAGE_HASHPTE | _PAGE_F_GIX | _PAGE_F_SECOND; + goto htab_insert_hpte; + } + /* + * Check for sub page valid and update + */ + if (__rpte_sub_valid(rpte, subpg_index)) { + int ret; + + hash = hpt_hash(vpn, shift, ssize); + hidx = __rpte_to_hidx(rpte, subpg_index); + if (hidx & _PTEIDX_SECONDARY) + hash = ~hash; + slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; + slot += hidx & _PTEIDX_GROUP_IX; + + ret = ppc_md.hpte_updatepp(slot, rflags, vpn, + MMU_PAGE_4K, MMU_PAGE_4K, + ssize, flags); + /* + *if we failed because typically the HPTE wasn't really here + * we try an insertion. + */ + if (ret == -1) + goto htab_insert_hpte; + + *ptep = __pte(new_pte & ~_PAGE_BUSY); + return 0; + } + +htab_insert_hpte: + /* + * handle _PAGE_4K_PFN case + */ + if (old_pte & _PAGE_4K_PFN) { + /* + * All the sub 4k page have the same + * physical address. + */ + pa = pte_pfn(__pte(old_pte)) << HW_PAGE_SHIFT; + } else { + pa = pte_pfn(__pte(old_pte)) << PAGE_SHIFT; + pa += (subpg_index << shift); + } + hash = hpt_hash(vpn, shift, ssize); +repeat: + hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL; + + /* Insert into the hash table, primary slot */ + slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, 0, + MMU_PAGE_4K, MMU_PAGE_4K, ssize); + /* + * Primary is full, try the secondary + */ + if (unlikely(slot == -1)) { + hpte_group = ((~hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL; + slot = ppc_md.hpte_insert(hpte_group, vpn, pa, + rflags, HPTE_V_SECONDARY, + MMU_PAGE_4K, MMU_PAGE_4K, ssize); + if (slot == -1) { + if (mftb() & 0x1) + hpte_group = ((hash & htab_hash_mask) * + HPTES_PER_GROUP) & ~0x7UL; + ppc_md.hpte_remove(hpte_group); + /* + * FIXME!! Should be try the group from which we removed ? + */ + goto repeat; + } + } + /* + * Hypervisor failure. Restore old pmd and return -1 + * similar to __hash_page_* + */ + if (unlikely(slot == -2)) { + *ptep = __pte(old_pte); + hash_failure_debug(ea, access, vsid, trap, ssize, + MMU_PAGE_4K, MMU_PAGE_4K, old_pte); + return -1; + } + /* + * Insert slot number & secondary bit in PTE second half, + * clear _PAGE_BUSY and set appropriate HPTE slot bit + * Since we have _PAGE_BUSY set on ptep, we can be sure + * nobody is undating hidx. + */ + hidxp = (unsigned long *)(ptep + PTRS_PER_PTE); + rpte.hidx &= ~(0xfUL << (subpg_index << 2)); + *hidxp = rpte.hidx | (slot << (subpg_index << 2)); + new_pte = mark_subptegroup_valid(new_pte, subpg_index); + new_pte |= _PAGE_HASHPTE; + /* + * check __real_pte for details on matching smp_rmb() + */ + smp_wmb(); + *ptep = __pte(new_pte & ~_PAGE_BUSY); + return 0; +} + +int __hash_page_64K(unsigned long ea, unsigned long access, + unsigned long vsid, pte_t *ptep, unsigned long trap, + unsigned long flags, int ssize) +{ + + unsigned long hpte_group; + unsigned long rflags, pa; + unsigned long old_pte, new_pte; + unsigned long vpn, hash, slot; + unsigned long shift = mmu_psize_defs[MMU_PAGE_64K].shift; + + /* + * atomically mark the linux large page PTE busy and dirty + */ + do { + pte_t pte = READ_ONCE(*ptep); + + old_pte = pte_val(pte); + /* If PTE busy, retry the access */ + if (unlikely(old_pte & _PAGE_BUSY)) + return 0; + /* If PTE permissions don't match, take page fault */ + if (unlikely(access & ~old_pte)) + return 1; + /* + * Check if PTE has the cache-inhibit bit set + * If so, bail out and refault as a 4k page + */ + if (!mmu_has_feature(MMU_FTR_CI_LARGE_PAGE) && + unlikely(old_pte & _PAGE_NO_CACHE)) + return 0; + /* + * Try to lock the PTE, add ACCESSED and DIRTY if it was + * a write access. Since this is 4K insert of 64K page size + * also add _PAGE_COMBO + */ + new_pte = old_pte | _PAGE_BUSY | _PAGE_ACCESSED; + if (access & _PAGE_RW) + new_pte |= _PAGE_DIRTY; + } while (old_pte != __cmpxchg_u64((unsigned long *)ptep, + old_pte, new_pte)); + + rflags = htab_convert_pte_flags(new_pte); + + 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); + + vpn = hpt_vpn(ea, vsid, ssize); + if (unlikely(old_pte & _PAGE_HASHPTE)) { + /* + * There MIGHT be an HPTE for this pte + */ + hash = hpt_hash(vpn, shift, ssize); + if (old_pte & _PAGE_F_SECOND) + hash = ~hash; + slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; + slot += (old_pte & _PAGE_F_GIX) >> _PAGE_F_GIX_SHIFT; + + if (ppc_md.hpte_updatepp(slot, rflags, vpn, MMU_PAGE_64K, + MMU_PAGE_64K, ssize, flags) == -1) + old_pte &= ~_PAGE_HPTEFLAGS; + } + + if (likely(!(old_pte & _PAGE_HASHPTE))) { + + pa = pte_pfn(__pte(old_pte)) << PAGE_SHIFT; + hash = hpt_hash(vpn, shift, ssize); + +repeat: + hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL; + + /* Insert into the hash table, primary slot */ + slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, 0, + MMU_PAGE_64K, MMU_PAGE_64K, ssize); + /* + * Primary is full, try the secondary + */ + if (unlikely(slot == -1)) { + hpte_group = ((~hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL; + slot = ppc_md.hpte_insert(hpte_group, vpn, pa, + rflags, HPTE_V_SECONDARY, + MMU_PAGE_64K, MMU_PAGE_64K, ssize); + if (slot == -1) { + if (mftb() & 0x1) + hpte_group = ((hash & htab_hash_mask) * + HPTES_PER_GROUP) & ~0x7UL; + ppc_md.hpte_remove(hpte_group); + /* + * FIXME!! Should be try the group from which we removed ? + */ + goto repeat; + } + } + /* + * Hypervisor failure. Restore old pmd and return -1 + * similar to __hash_page_* + */ + if (unlikely(slot == -2)) { + *ptep = __pte(old_pte); + hash_failure_debug(ea, access, vsid, trap, ssize, + MMU_PAGE_64K, MMU_PAGE_64K, old_pte); + return -1; + } + new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | _PAGE_HASHPTE; + new_pte |= (slot << _PAGE_F_GIX_SHIFT) & (_PAGE_F_SECOND | _PAGE_F_GIX); + } + *ptep = __pte(new_pte & ~_PAGE_BUSY); + return 0; +} diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S deleted file mode 100644 index 3b49e3295901..000000000000 --- a/arch/powerpc/mm/hash_low_64.S +++ /dev/null @@ -1,1003 +0,0 @@ -/* - * ppc64 MMU hashtable management routines - * - * (c) Copyright IBM Corp. 2003, 2005 - * - * Maintained by: Benjamin Herrenschmidt - * <benh@kernel.crashing.org> - * - * This file is covered by the GNU Public Licence v2 as - * described in the kernel's COPYING file. - */ - -#include <asm/reg.h> -#include <asm/pgtable.h> -#include <asm/mmu.h> -#include <asm/page.h> -#include <asm/types.h> -#include <asm/ppc_asm.h> -#include <asm/asm-offsets.h> -#include <asm/cputable.h> - - .text - -/* - * Stackframe: - * - * +-> Back chain (SP + 256) - * | General register save area (SP + 112) - * | Parameter save area (SP + 48) - * | TOC save area (SP + 40) - * | link editor doubleword (SP + 32) - * | compiler doubleword (SP + 24) - * | LR save area (SP + 16) - * | CR save area (SP + 8) - * SP ---> +-- Back chain (SP + 0) - */ - -#ifndef CONFIG_PPC_64K_PAGES - -/***************************************************************************** - * * - * 4K SW & 4K HW pages implementation * - * * - *****************************************************************************/ - - -/* - * _hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid, - * pte_t *ptep, unsigned long trap, unsigned long flags, - * int ssize) - * - * Adds a 4K page to the hash table in a segment of 4K pages only - */ - -_GLOBAL(__hash_page_4K) - mflr r0 - std r0,16(r1) - stdu r1,-STACKFRAMESIZE(r1) - /* Save all params that we need after a function call */ - std r6,STK_PARAM(R6)(r1) - std r8,STK_PARAM(R8)(r1) - std r9,STK_PARAM(R9)(r1) - - /* Save non-volatile registers. - * r31 will hold "old PTE" - * r30 is "new PTE" - * r29 is vpn - * r28 is a hash value - * r27 is hashtab mask (maybe dynamic patched instead ?) - */ - std r27,STK_REG(R27)(r1) - std r28,STK_REG(R28)(r1) - std r29,STK_REG(R29)(r1) - std r30,STK_REG(R30)(r1) - std r31,STK_REG(R31)(r1) - - /* Step 1: - * - * Check permissions, atomically mark the linux PTE busy - * and hashed. - */ -1: - ldarx r31,0,r6 - /* Check access rights (access & ~(pte_val(*ptep))) */ - andc. r0,r4,r31 - bne- htab_wrong_access - /* Check if PTE is busy */ - andi. r0,r31,_PAGE_BUSY - /* If so, just bail out and refault if needed. Someone else - * is changing this PTE anyway and might hash it. - */ - bne- htab_bail_ok - - /* Prepare new PTE value (turn access RW into DIRTY, then - * add BUSY,HASHPTE and ACCESSED) - */ - rlwinm r30,r4,32-9+7,31-7,31-7 /* _PAGE_RW -> _PAGE_DIRTY */ - or r30,r30,r31 - ori r30,r30,_PAGE_BUSY | _PAGE_ACCESSED | _PAGE_HASHPTE - /* Write the linux PTE atomically (setting busy) */ - stdcx. r30,0,r6 - bne- 1b - isync - - /* Step 2: - * - * Insert/Update the HPTE in the hash table. At this point, - * r4 (access) is re-useable, we use it for the new HPTE flags - */ - -BEGIN_FTR_SECTION - cmpdi r9,0 /* check segment size */ - bne 3f -END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) - /* Calc vpn and put it in r29 */ - sldi r29,r5,SID_SHIFT - VPN_SHIFT - rldicl r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT - VPN_SHIFT) - or r29,r28,r29 - /* - * Calculate hash value for primary slot and store it in r28 - * r3 = va, r5 = vsid - * r0 = (va >> 12) & ((1ul << (28 - 12)) -1) - */ - rldicl r0,r3,64-12,48 - xor r28,r5,r0 /* hash */ - b 4f - -3: /* Calc vpn and put it in r29 */ - sldi r29,r5,SID_SHIFT_1T - VPN_SHIFT - rldicl r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT_1T - VPN_SHIFT) - or r29,r28,r29 - - /* - * calculate hash value for primary slot and - * store it in r28 for 1T segment - * r3 = va, r5 = vsid - */ - sldi r28,r5,25 /* vsid << 25 */ - /* r0 = (va >> 12) & ((1ul << (40 - 12)) -1) */ - rldicl r0,r3,64-12,36 - xor r28,r28,r5 /* vsid ^ ( vsid << 25) */ - xor r28,r28,r0 /* hash */ - - /* Convert linux PTE bits into HW equivalents */ -4: andi. r3,r30,0x1fe /* Get basic set of flags */ - xori r3,r3,HPTE_R_N /* _PAGE_EXEC -> NOEXEC */ - rlwinm r0,r30,32-9+1,30,30 /* _PAGE_RW -> _PAGE_USER (r0) */ - rlwinm r4,r30,32-7+1,30,30 /* _PAGE_DIRTY -> _PAGE_USER (r4) */ - and r0,r0,r4 /* _PAGE_RW & _PAGE_DIRTY ->r0 bit 30*/ - andc r0,r30,r0 /* r0 = pte & ~r0 */ - rlwimi r3,r0,32-1,31,31 /* Insert result into PP lsb */ - /* - * Always add "C" bit for perf. Memory coherence is always enabled - */ - ori r3,r3,HPTE_R_C | HPTE_R_M - - /* We eventually do the icache sync here (maybe inline that - * code rather than call a C function...) - */ -BEGIN_FTR_SECTION - mr r4,r30 - mr r5,r7 - bl hash_page_do_lazy_icache -END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE) - - /* At this point, r3 contains new PP bits, save them in - * place of "access" in the param area (sic) - */ - std r3,STK_PARAM(R4)(r1) - - /* Get htab_hash_mask */ - ld r4,htab_hash_mask@got(2) - ld r27,0(r4) /* htab_hash_mask -> r27 */ - - /* Check if we may already be in the hashtable, in this case, we - * go to out-of-line code to try to modify the HPTE - */ - andi. r0,r31,_PAGE_HASHPTE - bne htab_modify_pte - -htab_insert_pte: - /* Clear hpte bits in new pte (we also clear BUSY btw) and - * add _PAGE_HASHPTE - */ - lis r0,_PAGE_HPTEFLAGS@h - ori r0,r0,_PAGE_HPTEFLAGS@l - andc r30,r30,r0 - ori r30,r30,_PAGE_HASHPTE - - /* physical address r5 */ - rldicl r5,r31,64-PTE_RPN_SHIFT,PTE_RPN_SHIFT - sldi r5,r5,PAGE_SHIFT - - /* Calculate primary group hash */ - and r0,r28,r27 - rldicr r3,r0,3,63-3 /* r3 = (hash & mask) << 3 */ - - /* Call ppc_md.hpte_insert */ - ld r6,STK_PARAM(R4)(r1) /* Retrieve new pp bits */ - mr r4,r29 /* Retrieve vpn */ - li r7,0 /* !bolted, !secondary */ - li r8,MMU_PAGE_4K /* page size */ - li r9,MMU_PAGE_4K /* actual page size */ - ld r10,STK_PARAM(R9)(r1) /* segment size */ -.globl htab_call_hpte_insert1 -htab_call_hpte_insert1: - bl . /* Patched by htab_finish_init() */ - cmpdi 0,r3,0 - bge htab_pte_insert_ok /* Insertion successful */ - cmpdi 0,r3,-2 /* Critical failure */ - beq- htab_pte_insert_failure - - /* Now try secondary slot */ - - /* physical address r5 */ - rldicl r5,r31,64-PTE_RPN_SHIFT,PTE_RPN_SHIFT - sldi r5,r5,PAGE_SHIFT - - /* Calculate secondary group hash */ - andc r0,r27,r28 - rldicr r3,r0,3,63-3 /* r0 = (~hash & mask) << 3 */ - - /* Call ppc_md.hpte_insert */ - ld r6,STK_PARAM(R4)(r1) /* Retrieve new pp bits */ - mr r4,r29 /* Retrieve vpn */ - li r7,HPTE_V_SECONDARY /* !bolted, secondary */ - li r8,MMU_PAGE_4K /* page size */ - li r9,MMU_PAGE_4K /* actual page size */ - ld r10,STK_PARAM(R9)(r1) /* segment size */ -.globl htab_call_hpte_insert2 -htab_call_hpte_insert2: - bl . /* Patched by htab_finish_init() */ - cmpdi 0,r3,0 - bge+ htab_pte_insert_ok /* Insertion successful */ - cmpdi 0,r3,-2 /* Critical failure */ - beq- htab_pte_insert_failure - - /* Both are full, we need to evict something */ - mftb r0 - /* Pick a random group based on TB */ - andi. r0,r0,1 - mr r5,r28 - bne 2f - not r5,r5 -2: and r0,r5,r27 - rldicr r3,r0,3,63-3 /* r0 = (hash & mask) << 3 */ - /* Call ppc_md.hpte_remove */ -.globl htab_call_hpte_remove -htab_call_hpte_remove: - bl . /* Patched by htab_finish_init() */ - - /* Try all again */ - b htab_insert_pte - -htab_bail_ok: - li r3,0 - b htab_bail - -htab_pte_insert_ok: - /* Insert slot number & secondary bit in PTE */ - rldimi r30,r3,12,63-15 - - /* Write out the PTE with a normal write - * (maybe add eieio may be good still ?) - */ -htab_write_out_pte: - ld r6,STK_PARAM(R6)(r1) - std r30,0(r6) - li r3, 0 -htab_bail: - ld r27,STK_REG(R27)(r1) - ld r28,STK_REG(R28)(r1) - ld r29,STK_REG(R29)(r1) - ld r30,STK_REG(R30)(r1) - ld r31,STK_REG(R31)(r1) - addi r1,r1,STACKFRAMESIZE - ld r0,16(r1) - mtlr r0 - blr - -htab_modify_pte: - /* Keep PP bits in r4 and slot idx from the PTE around in r3 */ - mr r4,r3 - rlwinm r3,r31,32-12,29,31 - - /* Secondary group ? if yes, get a inverted hash value */ - mr r5,r28 - andi. r0,r31,_PAGE_SECONDARY - beq 1f - not r5,r5 -1: - /* Calculate proper slot value for ppc_md.hpte_updatepp */ - and r0,r5,r27 - rldicr r0,r0,3,63-3 /* r0 = (hash & mask) << 3 */ - add r3,r0,r3 /* add slot idx */ - - /* Call ppc_md.hpte_updatepp */ - mr r5,r29 /* vpn */ - li r6,MMU_PAGE_4K /* base page size */ - li r7,MMU_PAGE_4K /* actual page size */ - ld r8,STK_PARAM(R9)(r1) /* segment size */ - ld r9,STK_PARAM(R8)(r1) /* get "flags" param */ -.globl htab_call_hpte_updatepp -htab_call_hpte_updatepp: - bl . /* Patched by htab_finish_init() */ - - /* if we failed because typically the HPTE wasn't really here - * we try an insertion. - */ - cmpdi 0,r3,-1 - beq- htab_insert_pte - - /* Clear the BUSY bit and Write out the PTE */ - li r0,_PAGE_BUSY - andc r30,r30,r0 - b htab_write_out_pte - -htab_wrong_access: - /* Bail out clearing reservation */ - stdcx. r31,0,r6 - li r3,1 - b htab_bail - -htab_pte_insert_failure: - /* Bail out restoring old PTE */ - ld r6,STK_PARAM(R6)(r1) - std r31,0(r6) - li r3,-1 - b htab_bail - - -#else /* CONFIG_PPC_64K_PAGES */ - - -/***************************************************************************** - * * - * 64K SW & 4K or 64K HW in a 4K segment pages implementation * - * * - *****************************************************************************/ - -/* _hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid, - * pte_t *ptep, unsigned long trap, unsigned local flags, - * int ssize, int subpg_prot) - */ - -/* - * For now, we do NOT implement Admixed pages - */ -_GLOBAL(__hash_page_4K) - mflr r0 - std r0,16(r1) - stdu r1,-STACKFRAMESIZE(r1) - /* Save all params that we need after a function call */ - std r6,STK_PARAM(R6)(r1) - std r8,STK_PARAM(R8)(r1) - std r9,STK_PARAM(R9)(r1) - - /* Save non-volatile registers. - * r31 will hold "old PTE" - * r30 is "new PTE" - * r29 is vpn - * r28 is a hash value - * r27 is hashtab mask (maybe dynamic patched instead ?) - * r26 is the hidx mask - * r25 is the index in combo page - */ - std r25,STK_REG(R25)(r1) - std r26,STK_REG(R26)(r1) - std r27,STK_REG(R27)(r1) - std r28,STK_REG(R28)(r1) - std r29,STK_REG(R29)(r1) - std r30,STK_REG(R30)(r1) - std r31,STK_REG(R31)(r1) - - /* Step 1: - * - * Check permissions, atomically mark the linux PTE busy - * and hashed. - */ -1: - ldarx r31,0,r6 - /* Check access rights (access & ~(pte_val(*ptep))) */ - andc. r0,r4,r31 - bne- htab_wrong_access - /* Check if PTE is busy */ - andi. r0,r31,_PAGE_BUSY - /* If so, just bail out and refault if needed. Someone else - * is changing this PTE anyway and might hash it. - */ - bne- htab_bail_ok - /* Prepare new PTE value (turn access RW into DIRTY, then - * add BUSY and ACCESSED) - */ - rlwinm r30,r4,32-9+7,31-7,31-7 /* _PAGE_RW -> _PAGE_DIRTY */ - or r30,r30,r31 - ori r30,r30,_PAGE_BUSY | _PAGE_ACCESSED - oris r30,r30,_PAGE_COMBO@h - /* Write the linux PTE atomically (setting busy) */ - stdcx. r30,0,r6 - bne- 1b - isync - - /* Step 2: - * - * Insert/Update the HPTE in the hash table. At this point, - * r4 (access) is re-useable, we use it for the new HPTE flags - */ - - /* Load the hidx index */ - rldicl r25,r3,64-12,60 - -BEGIN_FTR_SECTION - cmpdi r9,0 /* check segment size */ - bne 3f -END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) - /* Calc vpn and put it in r29 */ - sldi r29,r5,SID_SHIFT - VPN_SHIFT - /* - * clrldi r3,r3,64 - SID_SHIFT --> ea & 0xfffffff - * srdi r28,r3,VPN_SHIFT - */ - rldicl r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT - VPN_SHIFT) - or r29,r28,r29 - /* - * Calculate hash value for primary slot and store it in r28 - * r3 = va, r5 = vsid - * r0 = (va >> 12) & ((1ul << (28 - 12)) -1) - */ - rldicl r0,r3,64-12,48 - xor r28,r5,r0 /* hash */ - b 4f - -3: /* Calc vpn and put it in r29 */ - sldi r29,r5,SID_SHIFT_1T - VPN_SHIFT - /* - * clrldi r3,r3,64 - SID_SHIFT_1T --> ea & 0xffffffffff - * srdi r28,r3,VPN_SHIFT - */ - rldicl r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT_1T - VPN_SHIFT) - or r29,r28,r29 - - /* - * Calculate hash value for primary slot and - * store it in r28 for 1T segment - * r3 = va, r5 = vsid - */ - sldi r28,r5,25 /* vsid << 25 */ - /* r0 = (va >> 12) & ((1ul << (40 - 12)) -1) */ - rldicl r0,r3,64-12,36 - xor r28,r28,r5 /* vsid ^ ( vsid << 25) */ - xor r28,r28,r0 /* hash */ - - /* Convert linux PTE bits into HW equivalents */ -4: -#ifdef CONFIG_PPC_SUBPAGE_PROT - andc r10,r30,r10 - andi. r3,r10,0x1fe /* Get basic set of flags */ - rlwinm r0,r10,32-9+1,30,30 /* _PAGE_RW -> _PAGE_USER (r0) */ -#else - andi. r3,r30,0x1fe /* Get basic set of flags */ - rlwinm r0,r30,32-9+1,30,30 /* _PAGE_RW -> _PAGE_USER (r0) */ -#endif - xori r3,r3,HPTE_R_N /* _PAGE_EXEC -> NOEXEC */ - rlwinm r4,r30,32-7+1,30,30 /* _PAGE_DIRTY -> _PAGE_USER (r4) */ - and r0,r0,r4 /* _PAGE_RW & _PAGE_DIRTY ->r0 bit 30*/ - andc r0,r3,r0 /* r0 = pte & ~r0 */ - rlwimi r3,r0,32-1,31,31 /* Insert result into PP lsb */ - /* - * Always add "C" bit for perf. Memory coherence is always enabled - */ - ori r3,r3,HPTE_R_C | HPTE_R_M - - /* We eventually do the icache sync here (maybe inline that - * code rather than call a C function...) - */ -BEGIN_FTR_SECTION - mr r4,r30 - mr r5,r7 - bl hash_page_do_lazy_icache -END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE) - - /* At this point, r3 contains new PP bits, save them in - * place of "access" in the param area (sic) - */ - std r3,STK_PARAM(R4)(r1) - - /* Get htab_hash_mask */ - ld r4,htab_hash_mask@got(2) - ld r27,0(r4) /* htab_hash_mask -> r27 */ - - /* Check if we may already be in the hashtable, in this case, we - * go to out-of-line code to try to modify the HPTE. We look for - * the bit at (1 >> (index + 32)) - */ - rldicl. r0,r31,64-12,48 - li r26,0 /* Default hidx */ - beq htab_insert_pte - - /* - * Check if the pte was already inserted into the hash table - * as a 64k HW page, and invalidate the 64k HPTE if so. - */ - andis. r0,r31,_PAGE_COMBO@h - beq htab_inval_old_hpte - - ld r6,STK_PARAM(R6)(r1) - ori r26,r6,PTE_PAGE_HIDX_OFFSET /* Load the hidx mask. */ - ld r26,0(r26) - addi r5,r25,36 /* Check actual HPTE_SUB bit, this */ - rldcr. r0,r31,r5,0 /* must match pgtable.h definition */ - bne htab_modify_pte - -htab_insert_pte: - /* real page number in r5, PTE RPN value + index */ - andis. r0,r31,_PAGE_4K_PFN@h - srdi r5,r31,PTE_RPN_SHIFT - bne- htab_special_pfn - sldi r5,r5,PAGE_FACTOR - add r5,r5,r25 -htab_special_pfn: - sldi r5,r5,HW_PAGE_SHIFT - - /* Calculate primary group hash */ - and r0,r28,r27 - rldicr r3,r0,3,63-3 /* r0 = (hash & mask) << 3 */ - - /* Call ppc_md.hpte_insert */ - ld r6,STK_PARAM(R4)(r1) /* Retrieve new pp bits */ - mr r4,r29 /* Retrieve vpn */ - li r7,0 /* !bolted, !secondary */ - li r8,MMU_PAGE_4K /* page size */ - li r9,MMU_PAGE_4K /* actual page size */ - ld r10,STK_PARAM(R9)(r1) /* segment size */ -.globl htab_call_hpte_insert1 -htab_call_hpte_insert1: - bl . /* patched by htab_finish_init() */ - cmpdi 0,r3,0 - bge htab_pte_insert_ok /* Insertion successful */ - cmpdi 0,r3,-2 /* Critical failure */ - beq- htab_pte_insert_failure - - /* Now try secondary slot */ - - /* real page number in r5, PTE RPN value + index */ - andis. r0,r31,_PAGE_4K_PFN@h - srdi r5,r31,PTE_RPN_SHIFT - bne- 3f - sldi r5,r5,PAGE_FACTOR - add r5,r5,r25 -3: sldi r5,r5,HW_PAGE_SHIFT - - /* Calculate secondary group hash */ - andc r0,r27,r28 - rldicr r3,r0,3,63-3 /* r0 = (~hash & mask) << 3 */ - - /* Call ppc_md.hpte_insert */ - ld r6,STK_PARAM(R4)(r1) /* Retrieve new pp bits */ - mr r4,r29 /* Retrieve vpn */ - li r7,HPTE_V_SECONDARY /* !bolted, secondary */ - li r8,MMU_PAGE_4K /* page size */ - li r9,MMU_PAGE_4K /* actual page size */ - ld r10,STK_PARAM(R9)(r1) /* segment size */ -.globl htab_call_hpte_insert2 -htab_call_hpte_insert2: - bl . /* patched by htab_finish_init() */ - cmpdi 0,r3,0 - bge+ htab_pte_insert_ok /* Insertion successful */ - cmpdi 0,r3,-2 /* Critical failure */ - beq- htab_pte_insert_failure - - /* Both are full, we need to evict something */ - mftb r0 - /* Pick a random group based on TB */ - andi. r0,r0,1 - mr r5,r28 - bne 2f - not r5,r5 -2: and r0,r5,r27 - rldicr r3,r0,3,63-3 /* r0 = (hash & mask) << 3 */ - /* Call ppc_md.hpte_remove */ -.globl htab_call_hpte_remove -htab_call_hpte_remove: - bl . /* patched by htab_finish_init() */ - - /* Try all again */ - b htab_insert_pte - - /* - * Call out to C code to invalidate an 64k HW HPTE that is - * useless now that the segment has been switched to 4k pages. - */ -htab_inval_old_hpte: - mr r3,r29 /* vpn */ - mr r4,r31 /* PTE.pte */ - li r5,0 /* PTE.hidx */ - li r6,MMU_PAGE_64K /* psize */ - ld r7,STK_PARAM(R9)(r1) /* ssize */ - ld r8,STK_PARAM(R8)(r1) /* flags */ - bl flush_hash_page - /* Clear out _PAGE_HPTE_SUB bits in the new linux PTE */ - lis r0,_PAGE_HPTE_SUB@h - ori r0,r0,_PAGE_HPTE_SUB@l - andc r30,r30,r0 - b htab_insert_pte - -htab_bail_ok: - li r3,0 - b htab_bail - -htab_pte_insert_ok: - /* Insert slot number & secondary bit in PTE second half, - * clear _PAGE_BUSY and set approriate HPTE slot bit - */ - ld r6,STK_PARAM(R6)(r1) - li r0,_PAGE_BUSY - andc r30,r30,r0 - /* HPTE SUB bit */ - li r0,1 - subfic r5,r25,27 /* Must match bit position in */ - sld r0,r0,r5 /* pgtable.h */ - or r30,r30,r0 - /* hindx */ - sldi r5,r25,2 - sld r3,r3,r5 - li r4,0xf - sld r4,r4,r5 - andc r26,r26,r4 - or r26,r26,r3 - ori r5,r6,PTE_PAGE_HIDX_OFFSET - std r26,0(r5) - lwsync - std r30,0(r6) - li r3, 0 -htab_bail: - ld r25,STK_REG(R25)(r1) - ld r26,STK_REG(R26)(r1) - ld r27,STK_REG(R27)(r1) - ld r28,STK_REG(R28)(r1) - ld r29,STK_REG(R29)(r1) - ld r30,STK_REG(R30)(r1) - ld r31,STK_REG(R31)(r1) - addi r1,r1,STACKFRAMESIZE - ld r0,16(r1) - mtlr r0 - blr - -htab_modify_pte: - /* Keep PP bits in r4 and slot idx from the PTE around in r3 */ - mr r4,r3 - sldi r5,r25,2 - srd r3,r26,r5 - - /* Secondary group ? if yes, get a inverted hash value */ - mr r5,r28 - andi. r0,r3,0x8 /* page secondary ? */ - beq 1f - not r5,r5 -1: andi. r3,r3,0x7 /* extract idx alone */ - - /* Calculate proper slot value for ppc_md.hpte_updatepp */ - and r0,r5,r27 - rldicr r0,r0,3,63-3 /* r0 = (hash & mask) << 3 */ - add r3,r0,r3 /* add slot idx */ - - /* Call ppc_md.hpte_updatepp */ - mr r5,r29 /* vpn */ - li r6,MMU_PAGE_4K /* base page size */ - li r7,MMU_PAGE_4K /* actual page size */ - ld r8,STK_PARAM(R9)(r1) /* segment size */ - ld r9,STK_PARAM(R8)(r1) /* get "flags" param */ -.globl htab_call_hpte_updatepp -htab_call_hpte_updatepp: - bl . /* patched by htab_finish_init() */ - - /* if we failed because typically the HPTE wasn't really here - * we try an insertion. - */ - cmpdi 0,r3,-1 - beq- htab_insert_pte - - /* Clear the BUSY bit and Write out the PTE */ - li r0,_PAGE_BUSY - andc r30,r30,r0 - ld r6,STK_PARAM(R6)(r1) - std r30,0(r6) - li r3,0 - b htab_bail - -htab_wrong_access: - /* Bail out clearing reservation */ - stdcx. r31,0,r6 - li r3,1 - b htab_bail - -htab_pte_insert_failure: - /* Bail out restoring old PTE */ - ld r6,STK_PARAM(R6)(r1) - std r31,0(r6) - li r3,-1 - b htab_bail - -#endif /* CONFIG_PPC_64K_PAGES */ - -#ifdef CONFIG_PPC_64K_PAGES - -/***************************************************************************** - * * - * 64K SW & 64K HW in a 64K segment pages implementation * - * * - *****************************************************************************/ - -_GLOBAL(__hash_page_64K) - mflr r0 - std r0,16(r1) - stdu r1,-STACKFRAMESIZE(r1) - /* Save all params that we need after a function call */ - std r6,STK_PARAM(R6)(r1) - std r8,STK_PARAM(R8)(r1) - std r9,STK_PARAM(R9)(r1) - - /* Save non-volatile registers. - * r31 will hold "old PTE" - * r30 is "new PTE" - * r29 is vpn - * r28 is a hash value - * r27 is hashtab mask (maybe dynamic patched instead ?) - */ - std r27,STK_REG(R27)(r1) - std r28,STK_REG(R28)(r1) - std r29,STK_REG(R29)(r1) - std r30,STK_REG(R30)(r1) - std r31,STK_REG(R31)(r1) - - /* Step 1: - * - * Check permissions, atomically mark the linux PTE busy - * and hashed. - */ -1: - ldarx r31,0,r6 - /* Check access rights (access & ~(pte_val(*ptep))) */ - andc. r0,r4,r31 - bne- ht64_wrong_access - /* Check if PTE is busy */ - andi. r0,r31,_PAGE_BUSY - /* If so, just bail out and refault if needed. Someone else - * is changing this PTE anyway and might hash it. - */ - bne- ht64_bail_ok -BEGIN_FTR_SECTION - /* Check if PTE has the cache-inhibit bit set */ - andi. r0,r31,_PAGE_NO_CACHE - /* If so, bail out and refault as a 4k page */ - bne- ht64_bail_ok -END_MMU_FTR_SECTION_IFCLR(MMU_FTR_CI_LARGE_PAGE) - /* Prepare new PTE value (turn access RW into DIRTY, then - * add BUSY and ACCESSED) - */ - rlwinm r30,r4,32-9+7,31-7,31-7 /* _PAGE_RW -> _PAGE_DIRTY */ - or r30,r30,r31 - ori r30,r30,_PAGE_BUSY | _PAGE_ACCESSED - /* Write the linux PTE atomically (setting busy) */ - stdcx. r30,0,r6 - bne- 1b - isync - - /* Step 2: - * - * Insert/Update the HPTE in the hash table. At this point, - * r4 (access) is re-useable, we use it for the new HPTE flags - */ - -BEGIN_FTR_SECTION - cmpdi r9,0 /* check segment size */ - bne 3f -END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) - /* Calc vpn and put it in r29 */ - sldi r29,r5,SID_SHIFT - VPN_SHIFT - rldicl r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT - VPN_SHIFT) - or r29,r28,r29 - - /* Calculate hash value for primary slot and store it in r28 - * r3 = va, r5 = vsid - * r0 = (va >> 16) & ((1ul << (28 - 16)) -1) - */ - rldicl r0,r3,64-16,52 - xor r28,r5,r0 /* hash */ - b 4f - -3: /* Calc vpn and put it in r29 */ - sldi r29,r5,SID_SHIFT_1T - VPN_SHIFT - rldicl r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT_1T - VPN_SHIFT) - or r29,r28,r29 - /* - * calculate hash value for primary slot and - * store it in r28 for 1T segment - * r3 = va, r5 = vsid - */ - sldi r28,r5,25 /* vsid << 25 */ - /* r0 = (va >> 16) & ((1ul << (40 - 16)) -1) */ - rldicl r0,r3,64-16,40 - xor r28,r28,r5 /* vsid ^ ( vsid << 25) */ - xor r28,r28,r0 /* hash */ - - /* Convert linux PTE bits into HW equivalents */ -4: andi. r3,r30,0x1fe /* Get basic set of flags */ - xori r3,r3,HPTE_R_N /* _PAGE_EXEC -> NOEXEC */ - rlwinm r0,r30,32-9+1,30,30 /* _PAGE_RW -> _PAGE_USER (r0) */ - rlwinm r4,r30,32-7+1,30,30 /* _PAGE_DIRTY -> _PAGE_USER (r4) */ - and r0,r0,r4 /* _PAGE_RW & _PAGE_DIRTY ->r0 bit 30*/ - andc r0,r30,r0 /* r0 = pte & ~r0 */ - rlwimi r3,r0,32-1,31,31 /* Insert result into PP lsb */ - /* - * Always add "C" bit for perf. Memory coherence is always enabled - */ - ori r3,r3,HPTE_R_C | HPTE_R_M - - /* We eventually do the icache sync here (maybe inline that - * code rather than call a C function...) - */ -BEGIN_FTR_SECTION - mr r4,r30 - mr r5,r7 - bl hash_page_do_lazy_icache -END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE) - - /* At this point, r3 contains new PP bits, save them in - * place of "access" in the param area (sic) - */ - std r3,STK_PARAM(R4)(r1) - - /* Get htab_hash_mask */ - ld r4,htab_hash_mask@got(2) - ld r27,0(r4) /* htab_hash_mask -> r27 */ - - /* Check if we may already be in the hashtable, in this case, we - * go to out-of-line code to try to modify the HPTE - */ - rldicl. r0,r31,64-12,48 - bne ht64_modify_pte - -ht64_insert_pte: - /* Clear hpte bits in new pte (we also clear BUSY btw) and - * add _PAGE_HPTE_SUB0 - */ - lis r0,_PAGE_HPTEFLAGS@h - ori r0,r0,_PAGE_HPTEFLAGS@l - andc r30,r30,r0 -#ifdef CONFIG_PPC_64K_PAGES - oris r30,r30,_PAGE_HPTE_SUB0@h -#else - ori r30,r30,_PAGE_HASHPTE -#endif - /* Phyical address in r5 */ - rldicl r5,r31,64-PTE_RPN_SHIFT,PTE_RPN_SHIFT - sldi r5,r5,PAGE_SHIFT - - /* Calculate primary group hash */ - and r0,r28,r27 - rldicr r3,r0,3,63-3 /* r0 = (hash & mask) << 3 */ - - /* Call ppc_md.hpte_insert */ - ld r6,STK_PARAM(R4)(r1) /* Retrieve new pp bits */ - mr r4,r29 /* Retrieve vpn */ - li r7,0 /* !bolted, !secondary */ - li r8,MMU_PAGE_64K - li r9,MMU_PAGE_64K /* actual page size */ - ld r10,STK_PARAM(R9)(r1) /* segment size */ -.globl ht64_call_hpte_insert1 -ht64_call_hpte_insert1: - bl . /* patched by htab_finish_init() */ - cmpdi 0,r3,0 - bge ht64_pte_insert_ok /* Insertion successful */ - cmpdi 0,r3,-2 /* Critical failure */ - beq- ht64_pte_insert_failure - - /* Now try secondary slot */ - - /* Phyical address in r5 */ - rldicl r5,r31,64-PTE_RPN_SHIFT,PTE_RPN_SHIFT - sldi r5,r5,PAGE_SHIFT - - /* Calculate secondary group hash */ - andc r0,r27,r28 - rldicr r3,r0,3,63-3 /* r0 = (~hash & mask) << 3 */ - - /* Call ppc_md.hpte_insert */ - ld r6,STK_PARAM(R4)(r1) /* Retrieve new pp bits */ - mr r4,r29 /* Retrieve vpn */ - li r7,HPTE_V_SECONDARY /* !bolted, secondary */ - li r8,MMU_PAGE_64K - li r9,MMU_PAGE_64K /* actual page size */ - ld r10,STK_PARAM(R9)(r1) /* segment size */ -.globl ht64_call_hpte_insert2 -ht64_call_hpte_insert2: - bl . /* patched by htab_finish_init() */ - cmpdi 0,r3,0 - bge+ ht64_pte_insert_ok /* Insertion successful */ - cmpdi 0,r3,-2 /* Critical failure */ - beq- ht64_pte_insert_failure - - /* Both are full, we need to evict something */ - mftb r0 - /* Pick a random group based on TB */ - andi. r0,r0,1 - mr r5,r28 - bne 2f - not r5,r5 -2: and r0,r5,r27 - rldicr r3,r0,3,63-3 /* r0 = (hash & mask) << 3 */ - /* Call ppc_md.hpte_remove */ -.globl ht64_call_hpte_remove -ht64_call_hpte_remove: - bl . /* patched by htab_finish_init() */ - - /* Try all again */ - b ht64_insert_pte - -ht64_bail_ok: - li r3,0 - b ht64_bail - -ht64_pte_insert_ok: - /* Insert slot number & secondary bit in PTE */ - rldimi r30,r3,12,63-15 - - /* Write out the PTE with a normal write - * (maybe add eieio may be good still ?) - */ -ht64_write_out_pte: - ld r6,STK_PARAM(R6)(r1) - std r30,0(r6) - li r3, 0 -ht64_bail: - ld r27,STK_REG(R27)(r1) - ld r28,STK_REG(R28)(r1) - ld r29,STK_REG(R29)(r1) - ld r30,STK_REG(R30)(r1) - ld r31,STK_REG(R31)(r1) - addi r1,r1,STACKFRAMESIZE - ld r0,16(r1) - mtlr r0 - blr - -ht64_modify_pte: - /* Keep PP bits in r4 and slot idx from the PTE around in r3 */ - mr r4,r3 - rlwinm r3,r31,32-12,29,31 - - /* Secondary group ? if yes, get a inverted hash value */ - mr r5,r28 - andi. r0,r31,_PAGE_F_SECOND - beq 1f - not r5,r5 -1: - /* Calculate proper slot value for ppc_md.hpte_updatepp */ - and r0,r5,r27 - rldicr r0,r0,3,63-3 /* r0 = (hash & mask) << 3 */ - add r3,r0,r3 /* add slot idx */ - - /* Call ppc_md.hpte_updatepp */ - mr r5,r29 /* vpn */ - li r6,MMU_PAGE_64K /* base page size */ - li r7,MMU_PAGE_64K /* actual page size */ - ld r8,STK_PARAM(R9)(r1) /* segment size */ - ld r9,STK_PARAM(R8)(r1) /* get "flags" param */ -.globl ht64_call_hpte_updatepp -ht64_call_hpte_updatepp: - bl . /* patched by htab_finish_init() */ - - /* if we failed because typically the HPTE wasn't really here - * we try an insertion. - */ - cmpdi 0,r3,-1 - beq- ht64_insert_pte - - /* Clear the BUSY bit and Write out the PTE */ - li r0,_PAGE_BUSY - andc r30,r30,r0 - b ht64_write_out_pte - -ht64_wrong_access: - /* Bail out clearing reservation */ - stdcx. r31,0,r6 - li r3,1 - b ht64_bail - -ht64_pte_insert_failure: - /* Bail out restoring old PTE */ - ld r6,STK_PARAM(R6)(r1) - std r31,0(r6) - li r3,-1 - b ht64_bail - - -#endif /* CONFIG_PPC_64K_PAGES */ - - -/***************************************************************************** - * * - * Huge pages implementation is in hugetlbpage.c * - * * - *****************************************************************************/ diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c index c8822af10a58..8eaac81347fd 100644 --- a/arch/powerpc/mm/hash_native_64.c +++ b/arch/powerpc/mm/hash_native_64.c @@ -429,6 +429,7 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn, local_irq_restore(flags); } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE static void native_hugepage_invalidate(unsigned long vsid, unsigned long addr, unsigned char *hpte_slot_array, @@ -482,6 +483,15 @@ static void native_hugepage_invalidate(unsigned long vsid, } local_irq_restore(flags); } +#else +static void native_hugepage_invalidate(unsigned long vsid, + unsigned long addr, + unsigned char *hpte_slot_array, + int psize, int ssize, int local) +{ + WARN(1, "%s called without THP support\n", __func__); +} +#endif static inline int __hpte_actual_psize(unsigned int lp, int psize) { diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 7f9616f7c479..ba59d5977f34 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -159,24 +159,41 @@ static struct mmu_psize_def mmu_psize_defaults_gp[] = { }, }; -static unsigned long htab_convert_pte_flags(unsigned long pteflags) +unsigned long htab_convert_pte_flags(unsigned long pteflags) { - unsigned long rflags = pteflags & 0x1fa; + unsigned long rflags = 0; /* _PAGE_EXEC -> NOEXEC */ if ((pteflags & _PAGE_EXEC) == 0) rflags |= HPTE_R_N; - - /* PP bits. PAGE_USER is already PP bit 0x2, so we only - * need to add in 0x1 if it's a read-only user page + /* + * PP bits: + * Linux use slb key 0 for kernel and 1 for user. + * kernel areas are mapped by PP bits 00 + * and and there is no kernel RO (_PAGE_KERNEL_RO). + * User area mapped by 0x2 and read only use by + * 0x3. */ - if ((pteflags & _PAGE_USER) && !((pteflags & _PAGE_RW) && - (pteflags & _PAGE_DIRTY))) - rflags |= 1; + if (pteflags & _PAGE_USER) { + rflags |= 0x2; + if (!((pteflags & _PAGE_RW) && (pteflags & _PAGE_DIRTY))) + rflags |= 0x1; + } /* * Always add "C" bit for perf. Memory coherence is always enabled */ - return rflags | HPTE_R_C | HPTE_R_M; + rflags |= HPTE_R_C | HPTE_R_M; + /* + * Add in WIG bits + */ + if (pteflags & _PAGE_WRITETHRU) + rflags |= HPTE_R_W; + if (pteflags & _PAGE_NO_CACHE) + rflags |= HPTE_R_I; + if (pteflags & _PAGE_GUARDED) + rflags |= HPTE_R_G; + + return rflags; } int htab_bolt_mapping(unsigned long vstart, unsigned long vend, @@ -629,46 +646,6 @@ int remove_section_mapping(unsigned long start, unsigned long end) } #endif /* CONFIG_MEMORY_HOTPLUG */ -extern u32 htab_call_hpte_insert1[]; -extern u32 htab_call_hpte_insert2[]; -extern u32 htab_call_hpte_remove[]; -extern u32 htab_call_hpte_updatepp[]; -extern u32 ht64_call_hpte_insert1[]; -extern u32 ht64_call_hpte_insert2[]; -extern u32 ht64_call_hpte_remove[]; -extern u32 ht64_call_hpte_updatepp[]; - -static void __init htab_finish_init(void) -{ -#ifdef CONFIG_PPC_64K_PAGES - patch_branch(ht64_call_hpte_insert1, - ppc_function_entry(ppc_md.hpte_insert), - BRANCH_SET_LINK); - patch_branch(ht64_call_hpte_insert2, - ppc_function_entry(ppc_md.hpte_insert), - BRANCH_SET_LINK); - patch_branch(ht64_call_hpte_remove, - ppc_function_entry(ppc_md.hpte_remove), - BRANCH_SET_LINK); - patch_branch(ht64_call_hpte_updatepp, - ppc_function_entry(ppc_md.hpte_updatepp), - BRANCH_SET_LINK); -#endif /* CONFIG_PPC_64K_PAGES */ - - patch_branch(htab_call_hpte_insert1, - ppc_function_entry(ppc_md.hpte_insert), - BRANCH_SET_LINK); - patch_branch(htab_call_hpte_insert2, - ppc_function_entry(ppc_md.hpte_insert), - BRANCH_SET_LINK); - patch_branch(htab_call_hpte_remove, - ppc_function_entry(ppc_md.hpte_remove), - BRANCH_SET_LINK); - patch_branch(htab_call_hpte_updatepp, - ppc_function_entry(ppc_md.hpte_updatepp), - BRANCH_SET_LINK); -} - static void __init htab_initialize(void) { unsigned long table; @@ -815,7 +792,6 @@ static void __init htab_initialize(void) mmu_linear_psize, mmu_kernel_ssize)); } - htab_finish_init(); DBG(" <- htab_initialize()\n"); } @@ -877,11 +853,11 @@ static unsigned int get_paca_psize(unsigned long addr) unsigned long index, mask_index; if (addr < SLICE_LOW_TOP) { - lpsizes = get_paca()->context.low_slices_psize; + lpsizes = get_paca()->mm_ctx_low_slices_psize; index = GET_LOW_SLICE_INDEX(addr); return (lpsizes >> (index * 4)) & 0xF; } - hpsizes = get_paca()->context.high_slices_psize; + hpsizes = get_paca()->mm_ctx_high_slices_psize; index = GET_HIGH_SLICE_INDEX(addr); mask_index = index & 0x1; return (hpsizes[index >> 1] >> (mask_index * 4)) & 0xF; @@ -890,7 +866,7 @@ static unsigned int get_paca_psize(unsigned long addr) #else unsigned int get_paca_psize(unsigned long addr) { - return get_paca()->context.user_psize; + return get_paca()->mm_ctx_user_psize; } #endif @@ -906,7 +882,8 @@ void demote_segment_4k(struct mm_struct *mm, unsigned long addr) slice_set_range_psize(mm, addr, 1, MMU_PAGE_4K); copro_flush_all_slbs(mm); if ((get_paca_psize(addr) != MMU_PAGE_4K) && (current->mm == mm)) { - get_paca()->context = mm->context; + + copy_mm_to_paca(&mm->context); slb_flush_and_rebolt(); } } @@ -973,7 +950,7 @@ static void check_paca_psize(unsigned long ea, struct mm_struct *mm, { if (user_region) { if (psize != get_paca_psize(ea)) { - get_paca()->context = mm->context; + copy_mm_to_paca(&mm->context); slb_flush_and_rebolt(); } } else if (get_paca()->vmalloc_sllp != @@ -1148,9 +1125,10 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea, } } +#endif /* CONFIG_PPC_64K_PAGES */ + if (current->mm == mm) check_paca_psize(ea, mm, psize, user_region); -#endif /* CONFIG_PPC_64K_PAGES */ #ifdef CONFIG_PPC_64K_PAGES if (psize == MMU_PAGE_64K) @@ -1203,6 +1181,35 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap, } EXPORT_SYMBOL_GPL(hash_page); +int __hash_page(unsigned long ea, unsigned long msr, unsigned long trap, + unsigned long dsisr) +{ + unsigned long access = _PAGE_PRESENT; + unsigned long flags = 0; + struct mm_struct *mm = current->mm; + + if (REGION_ID(ea) == VMALLOC_REGION_ID) + mm = &init_mm; + + if (dsisr & DSISR_NOHPTE) + flags |= HPTE_NOHPTE_UPDATE; + + if (dsisr & DSISR_ISSTORE) + access |= _PAGE_RW; + /* + * We need to set the _PAGE_USER bit if MSR_PR is set or if we are + * accessing a userspace segment (even from the kernel). We assume + * kernel addresses always have the high bit set. + */ + if ((msr & MSR_PR) || (REGION_ID(ea) == USER_REGION_ID)) + access |= _PAGE_USER; + + if (trap == 0x400) + access |= _PAGE_EXEC; + + return hash_page_mm(mm, ea, access, trap, flags); +} + void hash_preload(struct mm_struct *mm, unsigned long ea, unsigned long access, unsigned long trap) { diff --git a/arch/powerpc/mm/hugepage-hash64.c b/arch/powerpc/mm/hugepage-hash64.c index 4d87122cf6a7..baf1301ded0c 100644 --- a/arch/powerpc/mm/hugepage-hash64.c +++ b/arch/powerpc/mm/hugepage-hash64.c @@ -54,18 +54,7 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid, new_pmd |= _PAGE_DIRTY; } while (old_pmd != __cmpxchg_u64((unsigned long *)pmdp, old_pmd, new_pmd)); - /* - * PP bits. _PAGE_USER is already PP bit 0x2, so we only - * need to add in 0x1 if it's a read-only user page - */ - rflags = new_pmd & _PAGE_USER; - if ((new_pmd & _PAGE_USER) && !((new_pmd & _PAGE_RW) && - (new_pmd & _PAGE_DIRTY))) - rflags |= 0x1; - /* - * _PAGE_EXEC -> HW_NO_EXEC since it's inverted - */ - rflags |= ((new_pmd & _PAGE_EXEC) ? 0 : HPTE_R_N); + rflags = htab_convert_pte_flags(new_pmd); #if 0 if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) { @@ -82,7 +71,7 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid, */ shift = mmu_psize_defs[psize].shift; index = (ea & ~HPAGE_PMD_MASK) >> shift; - BUG_ON(index >= 4096); + BUG_ON(index >= PTE_FRAG_SIZE); vpn = hpt_vpn(ea, vsid, ssize); hpte_slot_array = get_hpte_slot_array(pmdp); @@ -131,13 +120,6 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid, pa = pmd_pfn(__pmd(old_pmd)) << PAGE_SHIFT; new_pmd |= _PAGE_HASHPTE; - /* Add in WIMG bits */ - rflags |= (new_pmd & (_PAGE_WRITETHRU | _PAGE_NO_CACHE | - _PAGE_GUARDED)); - /* - * enable the memory coherence always - */ - rflags |= HPTE_R_M; repeat: hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL; diff --git a/arch/powerpc/mm/hugetlbpage-book3e.c b/arch/powerpc/mm/hugetlbpage-book3e.c index ba47aaf33a4b..7e6d0880813f 100644 --- a/arch/powerpc/mm/hugetlbpage-book3e.c +++ b/arch/powerpc/mm/hugetlbpage-book3e.c @@ -51,6 +51,48 @@ static inline int mmu_get_tsize(int psize) return mmu_psize_defs[psize].enc; } +#if defined(CONFIG_PPC_FSL_BOOK3E) && defined(CONFIG_PPC64) +#include <asm/paca.h> + +static inline void book3e_tlb_lock(void) +{ + struct paca_struct *paca = get_paca(); + unsigned long tmp; + int token = smp_processor_id() + 1; + + asm volatile("1: lbarx %0, 0, %1;" + "cmpwi %0, 0;" + "bne 2f;" + "stbcx. %2, 0, %1;" + "bne 1b;" + "b 3f;" + "2: lbzx %0, 0, %1;" + "cmpwi %0, 0;" + "bne 2b;" + "b 1b;" + "3:" + : "=&r" (tmp) + : "r" (&paca->tcd_ptr->lock), "r" (token) + : "memory"); +} + +static inline void book3e_tlb_unlock(void) +{ + struct paca_struct *paca = get_paca(); + + isync(); + paca->tcd_ptr->lock = 0; +} +#else +static inline void book3e_tlb_lock(void) +{ +} + +static inline void book3e_tlb_unlock(void) +{ +} +#endif + static inline int book3e_tlb_exists(unsigned long ea, unsigned long pid) { int found = 0; @@ -109,7 +151,10 @@ void book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea, */ local_irq_save(flags); + book3e_tlb_lock(); + if (unlikely(book3e_tlb_exists(ea, mm->context.id))) { + book3e_tlb_unlock(); local_irq_restore(flags); return; } @@ -141,6 +186,7 @@ void book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea, asm volatile ("tlbwe"); + book3e_tlb_unlock(); local_irq_restore(flags); } diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c index d94b1af53a93..e2138c7ae70f 100644 --- a/arch/powerpc/mm/hugetlbpage-hash64.c +++ b/arch/powerpc/mm/hugetlbpage-hash64.c @@ -59,10 +59,8 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, new_pte |= _PAGE_DIRTY; } while(old_pte != __cmpxchg_u64((unsigned long *)ptep, old_pte, new_pte)); + rflags = htab_convert_pte_flags(new_pte); - rflags = 0x2 | (!(new_pte & _PAGE_RW)); - /* _PAGE_EXEC -> HW_NO_EXEC since it's inverted */ - rflags |= ((new_pte & _PAGE_EXEC) ? 0 : HPTE_R_N); sz = ((1UL) << shift); if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) /* No CPU has hugepages but lacks no execute, so we @@ -91,18 +89,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, pa = pte_pfn(__pte(old_pte)) << PAGE_SHIFT; /* clear HPTE slot informations in new PTE */ -#ifdef CONFIG_PPC_64K_PAGES - new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | _PAGE_HPTE_SUB0; -#else new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | _PAGE_HASHPTE; -#endif - /* Add in WIMG bits */ - rflags |= (new_pte & (_PAGE_WRITETHRU | _PAGE_NO_CACHE | - _PAGE_COHERENT | _PAGE_GUARDED)); - /* - * enable the memory coherence always - */ - rflags |= HPTE_R_M; slot = hpte_insert_repeating(hash, vpn, pa, rflags, 0, mmu_psize, ssize); @@ -127,3 +114,21 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, *ptep = __pte(new_pte & ~_PAGE_BUSY); return 0; } + +#if defined(CONFIG_PPC_64K_PAGES) && defined(CONFIG_DEBUG_VM) +/* + * This enables us to catch the wrong page directory format + * Moved here so that we can use WARN() in the call. + */ +int hugepd_ok(hugepd_t hpd) +{ + bool is_hugepd; + + /* + * We should not find this format in page directory, warn otherwise. + */ + is_hugepd = (((hpd.pd & 0x3) == 0x0) && ((hpd.pd & HUGEPD_SHIFT_MASK) != 0)); + WARN(is_hugepd, "Found wrong page directory format\n"); + return 0; +} +#endif diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 9833fee493ec..61b8b7ccea4f 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -53,78 +53,6 @@ static unsigned nr_gpages; #define hugepd_none(hpd) ((hpd).pd == 0) -#ifdef CONFIG_PPC_BOOK3S_64 -/* - * At this point we do the placement change only for BOOK3S 64. This would - * possibly work on other subarchs. - */ - -/* - * We have PGD_INDEX_SIZ = 12 and PTE_INDEX_SIZE = 8, so that we can have - * 16GB hugepage pte in PGD and 16MB hugepage pte at PMD; - * - * Defined in such a way that we can optimize away code block at build time - * if CONFIG_HUGETLB_PAGE=n. - */ -int pmd_huge(pmd_t pmd) -{ - /* - * leaf pte for huge page, bottom two bits != 00 - */ - return ((pmd_val(pmd) & 0x3) != 0x0); -} - -int pud_huge(pud_t pud) -{ - /* - * leaf pte for huge page, bottom two bits != 00 - */ - return ((pud_val(pud) & 0x3) != 0x0); -} - -int pgd_huge(pgd_t pgd) -{ - /* - * leaf pte for huge page, bottom two bits != 00 - */ - return ((pgd_val(pgd) & 0x3) != 0x0); -} - -#if defined(CONFIG_PPC_64K_PAGES) && defined(CONFIG_DEBUG_VM) -/* - * This enables us to catch the wrong page directory format - * Moved here so that we can use WARN() in the call. - */ -int hugepd_ok(hugepd_t hpd) -{ - bool is_hugepd; - - /* - * We should not find this format in page directory, warn otherwise. - */ - is_hugepd = (((hpd.pd & 0x3) == 0x0) && ((hpd.pd & HUGEPD_SHIFT_MASK) != 0)); - WARN(is_hugepd, "Found wrong page directory format\n"); - return 0; -} -#endif - -#else -int pmd_huge(pmd_t pmd) -{ - return 0; -} - -int pud_huge(pud_t pud) -{ - return 0; -} - -int pgd_huge(pgd_t pgd) -{ - return 0; -} -#endif - pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) { /* Only called for hugetlbfs pages, hence can ignore THP */ @@ -966,8 +894,8 @@ void flush_dcache_icache_hugepage(struct page *page) * We have 4 cases for pgds and pmds: * (1) invalid (all zeroes) * (2) pointer to next table, as normal; bottom 6 bits == 0 - * (3) leaf pte for huge page, bottom two bits != 00 - * (4) hugepd pointer, bottom two bits == 00, next 4 bits indicate size of table + * (3) leaf pte for huge page _PAGE_PTE set + * (4) hugepd pointer, _PAGE_PTE = 0 and bits [2..6] indicate size of table * * So long as we atomically load page table pointers we are safe against teardown, * we can follow the address down to the the page and take a ref on it. diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index d747dd7bc90b..379a6a90644b 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -87,11 +87,7 @@ static void pgd_ctor(void *addr) static void pmd_ctor(void *addr) { -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - memset(addr, 0, PMD_TABLE_SIZE * 2); -#else memset(addr, 0, PMD_TABLE_SIZE); -#endif } struct kmem_cache *pgtable_cache[MAX_PGTABLE_INDEX_SIZE]; diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c index 83dfcb55ffef..83dfd7925c72 100644 --- a/arch/powerpc/mm/pgtable.c +++ b/arch/powerpc/mm/pgtable.c @@ -179,6 +179,10 @@ void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, */ VM_WARN_ON((pte_val(*ptep) & (_PAGE_PRESENT | _PAGE_USER)) == (_PAGE_PRESENT | _PAGE_USER)); + /* + * Add the pte bit when tryint set a pte + */ + pte = __pte(pte_val(pte) | _PAGE_PTE); /* Note: mm->context.id might not yet have been assigned as * this context might not have been activated yet when this diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index e92cb2146b18..ea6bc31debb0 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -359,7 +359,7 @@ struct page *pud_page(pud_t pud) struct page *pmd_page(pmd_t pmd) { if (pmd_trans_huge(pmd) || pmd_huge(pmd)) - return pfn_to_page(pmd_pfn(pmd)); + return pte_page(pmd_pte(pmd)); return virt_to_page(pmd_page_vaddr(pmd)); } @@ -625,7 +625,7 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, "1: ldarx %0,0,%3\n\ andi. %1,%0,%6\n\ bne- 1b \n\ - ori %1,%0,%4 \n\ + oris %1,%0,%4@h \n\ stdcx. %1,0,%3 \n\ bne- 1b" : "=&r" (old), "=&r" (tmp), "=m" (*pmdp) @@ -759,22 +759,15 @@ void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr, static pmd_t pmd_set_protbits(pmd_t pmd, pgprot_t pgprot) { - pmd_val(pmd) |= pgprot_val(pgprot); - return pmd; + return __pmd(pmd_val(pmd) | pgprot_val(pgprot)); } pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot) { - pmd_t pmd; - /* - * For a valid pte, we would have _PAGE_PRESENT always - * set. We use this to check THP page at pmd level. - * leaf pte for huge page, bottom two bits != 00 - */ - pmd_val(pmd) = pfn << PTE_RPN_SHIFT; - pmd_val(pmd) |= _PAGE_THP_HUGE; - pmd = pmd_set_protbits(pmd, pgprot); - return pmd; + unsigned long pmdv; + + pmdv = pfn << PTE_RPN_SHIFT; + return pmd_set_protbits(__pmd(pmdv), pgprot); } pmd_t mk_pmd(struct page *page, pgprot_t pgprot) @@ -784,10 +777,11 @@ pmd_t mk_pmd(struct page *page, pgprot_t pgprot) pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) { + unsigned long pmdv; - pmd_val(pmd) &= _HPAGE_CHG_MASK; - pmd = pmd_set_protbits(pmd, newprot); - return pmd; + pmdv = pmd_val(pmd); + pmdv &= _HPAGE_CHG_MASK; + return pmd_set_protbits(__pmd(pmdv), newprot); } /* diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c index 515730e499fe..825b6873391f 100644 --- a/arch/powerpc/mm/slb.c +++ b/arch/powerpc/mm/slb.c @@ -228,7 +228,7 @@ void switch_slb(struct task_struct *tsk, struct mm_struct *mm) asm volatile("slbie %0" : : "r" (slbie_data)); get_paca()->slb_cache_ptr = 0; - get_paca()->context = mm->context; + copy_mm_to_paca(&mm->context); /* * preload some userspace segments into the SLB. diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c index 0f432a702870..42954f0b47ac 100644 --- a/arch/powerpc/mm/slice.c +++ b/arch/powerpc/mm/slice.c @@ -185,8 +185,7 @@ static void slice_flush_segments(void *parm) if (mm != current->active_mm) return; - /* update the paca copy of the context struct */ - get_paca()->context = current->active_mm->context; + copy_mm_to_paca(¤t->active_mm->context); local_irq_save(flags); slb_flush_and_rebolt(); diff --git a/arch/powerpc/platforms/83xx/km83xx.c b/arch/powerpc/platforms/83xx/km83xx.c index bf4c4473abb9..4bc6bbbe9ada 100644 --- a/arch/powerpc/platforms/83xx/km83xx.c +++ b/arch/powerpc/platforms/83xx/km83xx.c @@ -37,8 +37,8 @@ #include <asm/udbg.h> #include <sysdev/fsl_soc.h> #include <sysdev/fsl_pci.h> -#include <asm/qe.h> -#include <asm/qe_ic.h> +#include <soc/fsl/qe/qe.h> +#include <soc/fsl/qe/qe_ic.h> #include "mpc83xx.h" @@ -136,8 +136,6 @@ static void __init mpc83xx_km_setup_arch(void) mpc83xx_setup_pci(); #ifdef CONFIG_QUICC_ENGINE - qe_reset(); - np = of_find_node_by_name(NULL, "par_io"); if (np != NULL) { par_io_init(np); diff --git a/arch/powerpc/platforms/83xx/misc.c b/arch/powerpc/platforms/83xx/misc.c index ef9d01a049c1..7e923cad56cf 100644 --- a/arch/powerpc/platforms/83xx/misc.c +++ b/arch/powerpc/platforms/83xx/misc.c @@ -17,7 +17,7 @@ #include <asm/io.h> #include <asm/hw_irq.h> #include <asm/ipic.h> -#include <asm/qe_ic.h> +#include <soc/fsl/qe/qe_ic.h> #include <sysdev/fsl_soc.h> #include <sysdev/fsl_pci.h> diff --git a/arch/powerpc/platforms/83xx/mpc832x_mds.c b/arch/powerpc/platforms/83xx/mpc832x_mds.c index 8d762203eeff..a973b2ae5df6 100644 --- a/arch/powerpc/platforms/83xx/mpc832x_mds.c +++ b/arch/powerpc/platforms/83xx/mpc832x_mds.c @@ -36,8 +36,8 @@ #include <asm/udbg.h> #include <sysdev/fsl_soc.h> #include <sysdev/fsl_pci.h> -#include <asm/qe.h> -#include <asm/qe_ic.h> +#include <soc/fsl/qe/qe.h> +#include <soc/fsl/qe/qe_ic.h> #include "mpc83xx.h" @@ -74,8 +74,6 @@ static void __init mpc832x_sys_setup_arch(void) mpc83xx_setup_pci(); #ifdef CONFIG_QUICC_ENGINE - qe_reset(); - if ((np = of_find_node_by_name(NULL, "par_io")) != NULL) { par_io_init(np); of_node_put(np); diff --git a/arch/powerpc/platforms/83xx/mpc832x_rdb.c b/arch/powerpc/platforms/83xx/mpc832x_rdb.c index eff5baabc3fb..ea2b87d202ca 100644 --- a/arch/powerpc/platforms/83xx/mpc832x_rdb.c +++ b/arch/powerpc/platforms/83xx/mpc832x_rdb.c @@ -25,8 +25,8 @@ #include <asm/time.h> #include <asm/ipic.h> #include <asm/udbg.h> -#include <asm/qe.h> -#include <asm/qe_ic.h> +#include <soc/fsl/qe/qe.h> +#include <soc/fsl/qe/qe_ic.h> #include <sysdev/fsl_soc.h> #include <sysdev/fsl_pci.h> @@ -203,8 +203,6 @@ static void __init mpc832x_rdb_setup_arch(void) mpc83xx_setup_pci(); #ifdef CONFIG_QUICC_ENGINE - qe_reset(); - if ((np = of_find_node_by_name(NULL, "par_io")) != NULL) { par_io_init(np); of_node_put(np); diff --git a/arch/powerpc/platforms/83xx/mpc836x_mds.c b/arch/powerpc/platforms/83xx/mpc836x_mds.c index 1a26d2f83401..dd70b85f56d4 100644 --- a/arch/powerpc/platforms/83xx/mpc836x_mds.c +++ b/arch/powerpc/platforms/83xx/mpc836x_mds.c @@ -44,8 +44,8 @@ #include <sysdev/fsl_soc.h> #include <sysdev/fsl_pci.h> #include <sysdev/simple_gpio.h> -#include <asm/qe.h> -#include <asm/qe_ic.h> +#include <soc/fsl/qe/qe.h> +#include <soc/fsl/qe/qe_ic.h> #include "mpc83xx.h" @@ -82,8 +82,6 @@ static void __init mpc836x_mds_setup_arch(void) mpc83xx_setup_pci(); #ifdef CONFIG_QUICC_ENGINE - qe_reset(); - if ((np = of_find_node_by_name(NULL, "par_io")) != NULL) { par_io_init(np); of_node_put(np); diff --git a/arch/powerpc/platforms/83xx/mpc836x_rdk.c b/arch/powerpc/platforms/83xx/mpc836x_rdk.c index b63b42d11d6c..4cd7153a6c88 100644 --- a/arch/powerpc/platforms/83xx/mpc836x_rdk.c +++ b/arch/powerpc/platforms/83xx/mpc836x_rdk.c @@ -20,8 +20,8 @@ #include <asm/time.h> #include <asm/ipic.h> #include <asm/udbg.h> -#include <asm/qe.h> -#include <asm/qe_ic.h> +#include <soc/fsl/qe/qe.h> +#include <soc/fsl/qe/qe_ic.h> #include <sysdev/fsl_soc.h> #include <sysdev/fsl_pci.h> @@ -35,9 +35,6 @@ static void __init mpc836x_rdk_setup_arch(void) ppc_md.progress("mpc836x_rdk_setup_arch()", 0); mpc83xx_setup_pci(); -#ifdef CONFIG_QUICC_ENGINE - qe_reset(); -#endif } /* diff --git a/arch/powerpc/platforms/85xx/bsc913x_qds.c b/arch/powerpc/platforms/85xx/bsc913x_qds.c index f0927e58af25..dcfafd6b91ee 100644 --- a/arch/powerpc/platforms/85xx/bsc913x_qds.c +++ b/arch/powerpc/platforms/85xx/bsc913x_qds.c @@ -17,6 +17,7 @@ #include <linux/pci.h> #include <asm/mpic.h> #include <sysdev/fsl_soc.h> +#include <sysdev/fsl_pci.h> #include <asm/udbg.h> #include "mpc85xx.h" @@ -46,10 +47,12 @@ static void __init bsc913x_qds_setup_arch(void) mpc85xx_smp_init(); #endif + fsl_pci_assign_primary(); + pr_info("bsc913x board from Freescale Semiconductor\n"); } -machine_device_initcall(bsc9132_qds, mpc85xx_common_publish_devices); +machine_arch_initcall(bsc9132_qds, mpc85xx_common_publish_devices); /* * Called very early, device-tree isn't unflattened @@ -67,6 +70,9 @@ define_machine(bsc9132_qds) { .probe = bsc9132_qds_probe, .setup_arch = bsc913x_qds_setup_arch, .init_IRQ = bsc913x_qds_pic_init, +#ifdef CONFIG_PCI + .pcibios_fixup_bus = fsl_pcibios_fixup_bus, +#endif .get_irq = mpic_get_irq, .restart = fsl_rstcr_restart, .calibrate_decr = generic_calibrate_decr, diff --git a/arch/powerpc/platforms/85xx/common.c b/arch/powerpc/platforms/85xx/common.c index 23791de7b688..949f22c86e61 100644 --- a/arch/powerpc/platforms/85xx/common.c +++ b/arch/powerpc/platforms/85xx/common.c @@ -9,7 +9,7 @@ #include <linux/of_irq.h> #include <linux/of_platform.h> -#include <asm/qe.h> +#include <soc/fsl/qe/qe.h> #include <sysdev/cpm2_pic.h> #include "mpc85xx.h" @@ -105,7 +105,6 @@ void __init mpc85xx_qe_init(void) return; } - qe_reset(); of_node_put(np); } diff --git a/arch/powerpc/platforms/85xx/corenet_generic.c b/arch/powerpc/platforms/85xx/corenet_generic.c index 46d05c94add6..a2b0bc859de0 100644 --- a/arch/powerpc/platforms/85xx/corenet_generic.c +++ b/arch/powerpc/platforms/85xx/corenet_generic.c @@ -27,7 +27,7 @@ #include <asm/udbg.h> #include <asm/mpic.h> #include <asm/ehv_pic.h> -#include <asm/qe_ic.h> +#include <soc/fsl/qe/qe_ic.h> #include <linux/of_platform.h> #include <sysdev/fsl_soc.h> diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ads.c b/arch/powerpc/platforms/85xx/mpc85xx_ads.c index 7d12a19aa7ee..de72a5f464b1 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_ads.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_ads.c @@ -36,17 +36,6 @@ #include "mpc85xx.h" -#ifdef CONFIG_PCI -static int mpc85xx_exclude_device(struct pci_controller *hose, - u_char bus, u_char devfn) -{ - if (bus == 0 && PCI_SLOT(devfn) == 0) - return PCIBIOS_DEVICE_NOT_FOUND; - else - return PCIBIOS_SUCCESSFUL; -} -#endif /* CONFIG_PCI */ - static void __init mpc85xx_ads_pic_init(void) { struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN, @@ -145,10 +134,6 @@ static void __init mpc85xx_ads_setup_arch(void) init_ioports(); #endif -#ifdef CONFIG_PCI - ppc_md.pci_exclude_device = mpc85xx_exclude_device; -#endif - fsl_pci_assign_primary(); } diff --git a/arch/powerpc/platforms/85xx/mpc85xx_mds.c b/arch/powerpc/platforms/85xx/mpc85xx_mds.c index f0be439ceaaa..f61cbe235581 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c @@ -48,8 +48,8 @@ #include <sysdev/fsl_soc.h> #include <sysdev/fsl_pci.h> #include <sysdev/simple_gpio.h> -#include <asm/qe.h> -#include <asm/qe_ic.h> +#include <soc/fsl/qe/qe.h> +#include <soc/fsl/qe/qe_ic.h> #include <asm/mpic.h> #include <asm/swiotlb.h> #include "smp.h" diff --git a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c index 50dcc00a0f5a..3f4dad133338 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c @@ -26,8 +26,8 @@ #include <asm/prom.h> #include <asm/udbg.h> #include <asm/mpic.h> -#include <asm/qe.h> -#include <asm/qe_ic.h> +#include <soc/fsl/qe/qe.h> +#include <soc/fsl/qe/qe_ic.h> #include <sysdev/fsl_soc.h> #include <sysdev/fsl_pci.h> diff --git a/arch/powerpc/platforms/85xx/twr_p102x.c b/arch/powerpc/platforms/85xx/twr_p102x.c index 892e613519cc..71bc255b4324 100644 --- a/arch/powerpc/platforms/85xx/twr_p102x.c +++ b/arch/powerpc/platforms/85xx/twr_p102x.c @@ -22,8 +22,8 @@ #include <asm/pci-bridge.h> #include <asm/udbg.h> #include <asm/mpic.h> -#include <asm/qe.h> -#include <asm/qe_ic.h> +#include <soc/fsl/qe/qe.h> +#include <soc/fsl/qe/qe_ic.h> #include <sysdev/fsl_soc.h> #include <sysdev/fsl_pci.h> diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index b7f9c408bf24..46a3533d3acb 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -272,17 +272,6 @@ config TAU_AVERAGE If in doubt, say N here. -config QUICC_ENGINE - bool "Freescale QUICC Engine (QE) Support" - depends on FSL_SOC && PPC32 - select PPC_LIB_RHEAP - select CRC32 - help - The QUICC Engine (QE) is a new generation of communications - coprocessors on Freescale embedded CPUs (akin to CPM in older chips). - Selecting this option means that you wish to build a kernel - for a machine with a QE coprocessor. - config QE_GPIO bool "QE GPIO support" depends on QUICC_ENGINE @@ -295,7 +284,6 @@ config CPM2 bool "Enable support for the CPM2 (Communications Processor Module)" depends on (FSL_SOC_BOOKE && PPC32) || 8260 select CPM - select PPC_LIB_RHEAP select PPC_PCI_CHOICE select ARCH_REQUIRE_GPIOLIB help @@ -325,6 +313,7 @@ config FSL_ULI1575 config CPM bool + select GENERIC_ALLOCATOR config OF_RTC bool diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig index 429fc59d2a47..d9088f0b8fcc 100644 --- a/arch/powerpc/platforms/cell/Kconfig +++ b/arch/powerpc/platforms/cell/Kconfig @@ -33,11 +33,6 @@ config PPC_IBM_CELL_BLADE select PPC_UDBG_16550 select UDBG_RTAS_CONSOLE -config PPC_CELL_QPACE - bool "IBM Cell - QPACE" - depends on PPC64 && PPC_BOOK3S && CPU_BIG_ENDIAN - select PPC_CELL_COMMON - config AXON_MSI bool depends on PPC_IBM_CELL_BLADE && PCI_MSI diff --git a/arch/powerpc/platforms/cell/Makefile b/arch/powerpc/platforms/cell/Makefile index 34699bddfddd..00464305763d 100644 --- a/arch/powerpc/platforms/cell/Makefile +++ b/arch/powerpc/platforms/cell/Makefile @@ -11,7 +11,6 @@ obj-$(CONFIG_PPC_IBM_CELL_POWERBUTTON) += cbe_powerbutton.o ifeq ($(CONFIG_SMP),y) obj-$(CONFIG_PPC_CELL_NATIVE) += smp.o -obj-$(CONFIG_PPC_CELL_QPACE) += smp.o endif # needed only when building loadable spufs.ko @@ -26,6 +25,3 @@ obj-$(CONFIG_SPU_BASE) += spu_callbacks.o spu_base.o \ spufs/ obj-$(CONFIG_AXON_MSI) += axon_msi.o - -# qpace setup -obj-$(CONFIG_PPC_CELL_QPACE) += qpace_setup.o diff --git a/arch/powerpc/platforms/cell/qpace_setup.c b/arch/powerpc/platforms/cell/qpace_setup.c deleted file mode 100644 index d328140dc6f5..000000000000 --- a/arch/powerpc/platforms/cell/qpace_setup.c +++ /dev/null @@ -1,148 +0,0 @@ -/* - * linux/arch/powerpc/platforms/cell/qpace_setup.c - * - * Copyright (C) 1995 Linus Torvalds - * Adapted from 'alpha' version by Gary Thomas - * Modified by Cort Dougan (cort@cs.nmt.edu) - * Modified by PPC64 Team, IBM Corp - * Modified by Cell Team, IBM Deutschland Entwicklung GmbH - * Modified by Benjamin Krill <ben@codiert.org>, IBM Corp. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include <linux/sched.h> -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/export.h> -#include <linux/delay.h> -#include <linux/irq.h> -#include <linux/console.h> -#include <linux/of_platform.h> - -#include <asm/mmu.h> -#include <asm/processor.h> -#include <asm/io.h> -#include <asm/kexec.h> -#include <asm/pgtable.h> -#include <asm/prom.h> -#include <asm/rtas.h> -#include <asm/dma.h> -#include <asm/machdep.h> -#include <asm/time.h> -#include <asm/cputable.h> -#include <asm/irq.h> -#include <asm/spu.h> -#include <asm/spu_priv1.h> -#include <asm/udbg.h> -#include <asm/cell-regs.h> - -#include "interrupt.h" -#include "pervasive.h" -#include "ras.h" - -static void qpace_show_cpuinfo(struct seq_file *m) -{ - struct device_node *root; - const char *model = ""; - - root = of_find_node_by_path("/"); - if (root) - model = of_get_property(root, "model", NULL); - seq_printf(m, "machine\t\t: CHRP %s\n", model); - of_node_put(root); -} - -static void qpace_progress(char *s, unsigned short hex) -{ - printk("*** %04x : %s\n", hex, s ? s : ""); -} - -static const struct of_device_id qpace_bus_ids[] __initconst = { - { .type = "soc", }, - { .compatible = "soc", }, - { .type = "spider", }, - { .type = "axon", }, - { .type = "plb5", }, - { .type = "plb4", }, - { .type = "opb", }, - { .type = "ebc", }, - {}, -}; - -static int __init qpace_publish_devices(void) -{ - int node; - - /* Publish OF platform devices for southbridge IOs */ - of_platform_bus_probe(NULL, qpace_bus_ids, NULL); - - /* There is no device for the MIC memory controller, thus we create - * a platform device for it to attach the EDAC driver to. - */ - for_each_online_node(node) { - if (cbe_get_cpu_mic_tm_regs(cbe_node_to_cpu(node)) == NULL) - continue; - platform_device_register_simple("cbe-mic", node, NULL, 0); - } - - return 0; -} -machine_subsys_initcall(qpace, qpace_publish_devices); - -static void __init qpace_setup_arch(void) -{ -#ifdef CONFIG_SPU_BASE - spu_priv1_ops = &spu_priv1_mmio_ops; - spu_management_ops = &spu_management_of_ops; -#endif - - cbe_regs_init(); - -#ifdef CONFIG_CBE_RAS - cbe_ras_init(); -#endif - -#ifdef CONFIG_SMP - smp_init_cell(); -#endif - - /* init to some ~sane value until calibrate_delay() runs */ - loops_per_jiffy = 50000000; - - cbe_pervasive_init(); -#ifdef CONFIG_DUMMY_CONSOLE - conswitchp = &dummy_con; -#endif -} - -static int __init qpace_probe(void) -{ - unsigned long root = of_get_flat_dt_root(); - - if (!of_flat_dt_is_compatible(root, "IBM,QPACE")) - return 0; - - hpte_init_native(); - pm_power_off = rtas_power_off; - - return 1; -} - -define_machine(qpace) { - .name = "QPACE", - .probe = qpace_probe, - .setup_arch = qpace_setup_arch, - .show_cpuinfo = qpace_show_cpuinfo, - .restart = rtas_restart, - .halt = rtas_halt, - .get_boot_time = rtas_get_boot_time, - .get_rtc_time = rtas_get_rtc_time, - .set_rtc_time = rtas_set_rtc_time, - .calibrate_decr = generic_calibrate_decr, - .progress = qpace_progress, - .init_IRQ = iic_init_IRQ, -}; diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index 11634fa7ab3c..ad4840f86be1 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -767,7 +767,7 @@ static int __init spufs_init(void) ret = -ENOMEM; spufs_inode_cache = kmem_cache_create("spufs_inode_cache", sizeof(struct spufs_inode_info), 0, - SLAB_HWCACHE_ALIGN, spufs_init_once); + SLAB_HWCACHE_ALIGN|SLAB_ACCOUNT, spufs_init_once); if (!spufs_inode_cache) goto out; diff --git a/arch/powerpc/platforms/cell/spufs/run.c b/arch/powerpc/platforms/cell/spufs/run.c index 4ddf769a64e5..9f79004e6d6f 100644 --- a/arch/powerpc/platforms/cell/spufs/run.c +++ b/arch/powerpc/platforms/cell/spufs/run.c @@ -326,7 +326,7 @@ static int spu_process_callback(struct spu_context *ctx) spu_ret = -ENOSYS; npc += 4; - if (s.nr_ret < __NR_syscalls) { + if (s.nr_ret < NR_syscalls) { spu_release(ctx); /* do actual system call from here */ spu_ret = spu_sys_callback(&s); diff --git a/arch/powerpc/platforms/maple/time.c b/arch/powerpc/platforms/maple/time.c index b4a369dac3a8..81799d70a1ee 100644 --- a/arch/powerpc/platforms/maple/time.c +++ b/arch/powerpc/platforms/maple/time.c @@ -77,7 +77,7 @@ void maple_get_rtc_time(struct rtc_time *tm) if ((tm->tm_year + 1900) < 1970) tm->tm_year += 100; - GregorianDay(tm); + tm->tm_wday = -1; } int maple_set_rtc_time(struct rtc_time *tm) diff --git a/arch/powerpc/platforms/powermac/bootx_init.c b/arch/powerpc/platforms/powermac/bootx_init.c index 76f5013c35e5..c3c9bbb3573a 100644 --- a/arch/powerpc/platforms/powermac/bootx_init.c +++ b/arch/powerpc/platforms/powermac/bootx_init.c @@ -84,6 +84,7 @@ static void __init bootx_printf(const char *format, ...) break; } } + va_end(args); } #else /* CONFIG_BOOTX_TEXT */ static void __init bootx_printf(const char *format, ...) {} diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c index 6f4f8b060def..981546345033 100644 --- a/arch/powerpc/platforms/powermac/pic.c +++ b/arch/powerpc/platforms/powermac/pic.c @@ -258,13 +258,14 @@ static unsigned int pmac_pic_get_irq(void) #ifdef CONFIG_XMON static struct irqaction xmon_action = { .handler = xmon_irq, - .flags = 0, + .flags = IRQF_NO_THREAD, .name = "NMI - XMON" }; #endif static struct irqaction gatwick_cascade_action = { .handler = gatwick_action, + .flags = IRQF_NO_THREAD, .name = "cascade", }; diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile index 1c8cdb6250e7..f1516b5ecec9 100644 --- a/arch/powerpc/platforms/powernv/Makefile +++ b/arch/powerpc/platforms/powernv/Makefile @@ -2,9 +2,10 @@ obj-y += setup.o opal-wrappers.o opal.o opal-async.o idle.o obj-y += opal-rtc.o opal-nvram.o opal-lpc.o opal-flash.o obj-y += rng.o opal-elog.o opal-dump.o opal-sysparam.o opal-sensor.o obj-y += opal-msglog.o opal-hmi.o opal-power.o opal-irqchip.o +obj-y += opal-kmsg.o obj-$(CONFIG_SMP) += smp.o subcore.o subcore-asm.o -obj-$(CONFIG_PCI) += pci.o pci-p5ioc2.o pci-ioda.o +obj-$(CONFIG_PCI) += pci.o pci-p5ioc2.o pci-ioda.o npu-dma.o obj-$(CONFIG_EEH) += eeh-powernv.o obj-$(CONFIG_PPC_SCOM) += opal-xscom.o obj-$(CONFIG_MEMORY_FAILURE) += opal-memory-errors.o diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index e1c90725522a..5f152b95ca0c 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -48,8 +48,8 @@ static int pnv_eeh_init(void) struct pci_controller *hose; struct pnv_phb *phb; - if (!firmware_has_feature(FW_FEATURE_OPALv3)) { - pr_warn("%s: OPALv3 is required !\n", + if (!firmware_has_feature(FW_FEATURE_OPAL)) { + pr_warn("%s: OPAL is required !\n", __func__); return -EINVAL; } diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c index 59d735d2e5c0..15bfbcd5debc 100644 --- a/arch/powerpc/platforms/powernv/idle.c +++ b/arch/powerpc/platforms/powernv/idle.c @@ -242,7 +242,7 @@ static int __init pnv_init_idle_states(void) if (cpuidle_disable != IDLE_NO_OVERRIDE) goto out; - if (!firmware_has_feature(FW_FEATURE_OPALv3)) + if (!firmware_has_feature(FW_FEATURE_OPAL)) goto out; power_mgt = of_find_node_by_path("/ibm,opal/power-mgt"); diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c new file mode 100644 index 000000000000..e85aa900f5c0 --- /dev/null +++ b/arch/powerpc/platforms/powernv/npu-dma.c @@ -0,0 +1,348 @@ +/* + * This file implements the DMA operations for NVLink devices. The NPU + * devices all point to the same iommu table as the parent PCI device. + * + * Copyright Alistair Popple, IBM Corporation 2015. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ + +#include <linux/export.h> +#include <linux/pci.h> +#include <linux/memblock.h> + +#include <asm/iommu.h> +#include <asm/pnv-pci.h> +#include <asm/msi_bitmap.h> +#include <asm/opal.h> + +#include "powernv.h" +#include "pci.h" + +/* + * Other types of TCE cache invalidation are not functional in the + * hardware. + */ +#define TCE_KILL_INVAL_ALL PPC_BIT(0) + +static struct pci_dev *get_pci_dev(struct device_node *dn) +{ + return PCI_DN(dn)->pcidev; +} + +/* Given a NPU device get the associated PCI device. */ +struct pci_dev *pnv_pci_get_gpu_dev(struct pci_dev *npdev) +{ + struct device_node *dn; + struct pci_dev *gpdev; + + /* Get assoicated PCI device */ + dn = of_parse_phandle(npdev->dev.of_node, "ibm,gpu", 0); + if (!dn) + return NULL; + + gpdev = get_pci_dev(dn); + of_node_put(dn); + + return gpdev; +} +EXPORT_SYMBOL(pnv_pci_get_gpu_dev); + +/* Given the real PCI device get a linked NPU device. */ +struct pci_dev *pnv_pci_get_npu_dev(struct pci_dev *gpdev, int index) +{ + struct device_node *dn; + struct pci_dev *npdev; + + /* Get assoicated PCI device */ + dn = of_parse_phandle(gpdev->dev.of_node, "ibm,npu", index); + if (!dn) + return NULL; + + npdev = get_pci_dev(dn); + of_node_put(dn); + + return npdev; +} +EXPORT_SYMBOL(pnv_pci_get_npu_dev); + +#define NPU_DMA_OP_UNSUPPORTED() \ + dev_err_once(dev, "%s operation unsupported for NVLink devices\n", \ + __func__) + +static void *dma_npu_alloc(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t flag, + struct dma_attrs *attrs) +{ + NPU_DMA_OP_UNSUPPORTED(); + return NULL; +} + +static void dma_npu_free(struct device *dev, size_t size, + void *vaddr, dma_addr_t dma_handle, + struct dma_attrs *attrs) +{ + NPU_DMA_OP_UNSUPPORTED(); +} + +static dma_addr_t dma_npu_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction direction, + struct dma_attrs *attrs) +{ + NPU_DMA_OP_UNSUPPORTED(); + return 0; +} + +static int dma_npu_map_sg(struct device *dev, struct scatterlist *sglist, + int nelems, enum dma_data_direction direction, + struct dma_attrs *attrs) +{ + NPU_DMA_OP_UNSUPPORTED(); + return 0; +} + +static int dma_npu_dma_supported(struct device *dev, u64 mask) +{ + NPU_DMA_OP_UNSUPPORTED(); + return 0; +} + +static u64 dma_npu_get_required_mask(struct device *dev) +{ + NPU_DMA_OP_UNSUPPORTED(); + return 0; +} + +struct dma_map_ops dma_npu_ops = { + .map_page = dma_npu_map_page, + .map_sg = dma_npu_map_sg, + .alloc = dma_npu_alloc, + .free = dma_npu_free, + .dma_supported = dma_npu_dma_supported, + .get_required_mask = dma_npu_get_required_mask, +}; + +/* + * Returns the PE assoicated with the PCI device of the given + * NPU. Returns the linked pci device if pci_dev != NULL. + */ +static struct pnv_ioda_pe *get_gpu_pci_dev_and_pe(struct pnv_ioda_pe *npe, + struct pci_dev **gpdev) +{ + struct pnv_phb *phb; + struct pci_controller *hose; + struct pci_dev *pdev; + struct pnv_ioda_pe *pe; + struct pci_dn *pdn; + + if (npe->flags & PNV_IODA_PE_PEER) { + pe = npe->peers[0]; + pdev = pe->pdev; + } else { + pdev = pnv_pci_get_gpu_dev(npe->pdev); + if (!pdev) + return NULL; + + pdn = pci_get_pdn(pdev); + if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE)) + return NULL; + + hose = pci_bus_to_host(pdev->bus); + phb = hose->private_data; + pe = &phb->ioda.pe_array[pdn->pe_number]; + } + + if (gpdev) + *gpdev = pdev; + + return pe; +} + +void pnv_npu_tce_invalidate_entire(struct pnv_ioda_pe *npe) +{ + struct pnv_phb *phb = npe->phb; + + if (WARN_ON(phb->type != PNV_PHB_NPU || + !phb->ioda.tce_inval_reg || + !(npe->flags & PNV_IODA_PE_DEV))) + return; + + mb(); /* Ensure previous TCE table stores are visible */ + __raw_writeq(cpu_to_be64(TCE_KILL_INVAL_ALL), + phb->ioda.tce_inval_reg); +} + +void pnv_npu_tce_invalidate(struct pnv_ioda_pe *npe, + struct iommu_table *tbl, + unsigned long index, + unsigned long npages, + bool rm) +{ + struct pnv_phb *phb = npe->phb; + + /* We can only invalidate the whole cache on NPU */ + unsigned long val = TCE_KILL_INVAL_ALL; + + if (WARN_ON(phb->type != PNV_PHB_NPU || + !phb->ioda.tce_inval_reg || + !(npe->flags & PNV_IODA_PE_DEV))) + return; + + mb(); /* Ensure previous TCE table stores are visible */ + if (rm) + __raw_rm_writeq(cpu_to_be64(val), + (__be64 __iomem *) phb->ioda.tce_inval_reg_phys); + else + __raw_writeq(cpu_to_be64(val), + phb->ioda.tce_inval_reg); +} + +void pnv_npu_init_dma_pe(struct pnv_ioda_pe *npe) +{ + struct pnv_ioda_pe *gpe; + struct pci_dev *gpdev; + int i, avail = -1; + + if (!npe->pdev || !(npe->flags & PNV_IODA_PE_DEV)) + return; + + gpe = get_gpu_pci_dev_and_pe(npe, &gpdev); + if (!gpe) + return; + + for (i = 0; i < PNV_IODA_MAX_PEER_PES; i++) { + /* Nothing to do if the PE is already connected. */ + if (gpe->peers[i] == npe) + return; + + if (!gpe->peers[i]) + avail = i; + } + + if (WARN_ON(avail < 0)) + return; + + gpe->peers[avail] = npe; + gpe->flags |= PNV_IODA_PE_PEER; + + /* + * We assume that the NPU devices only have a single peer PE + * (the GPU PCIe device PE). + */ + npe->peers[0] = gpe; + npe->flags |= PNV_IODA_PE_PEER; +} + +/* + * For the NPU we want to point the TCE table at the same table as the + * real PCI device. + */ +static void pnv_npu_disable_bypass(struct pnv_ioda_pe *npe) +{ + struct pnv_phb *phb = npe->phb; + struct pci_dev *gpdev; + struct pnv_ioda_pe *gpe; + void *addr; + unsigned int size; + int64_t rc; + + /* + * Find the assoicated PCI devices and get the dma window + * information from there. + */ + if (!npe->pdev || !(npe->flags & PNV_IODA_PE_DEV)) + return; + + gpe = get_gpu_pci_dev_and_pe(npe, &gpdev); + if (!gpe) + return; + + addr = (void *)gpe->table_group.tables[0]->it_base; + size = gpe->table_group.tables[0]->it_size << 3; + rc = opal_pci_map_pe_dma_window(phb->opal_id, npe->pe_number, + npe->pe_number, 1, __pa(addr), + size, 0x1000); + if (rc != OPAL_SUCCESS) + pr_warn("%s: Error %lld setting DMA window on PHB#%d-PE#%d\n", + __func__, rc, phb->hose->global_number, npe->pe_number); + + /* + * We don't initialise npu_pe->tce32_table as we always use + * dma_npu_ops which are nops. + */ + set_dma_ops(&npe->pdev->dev, &dma_npu_ops); +} + +/* + * Enable/disable bypass mode on the NPU. The NPU only supports one + * window per link, so bypass needs to be explicity enabled or + * disabled. Unlike for a PHB3 bypass and non-bypass modes can't be + * active at the same time. + */ +int pnv_npu_dma_set_bypass(struct pnv_ioda_pe *npe, bool enable) +{ + struct pnv_phb *phb = npe->phb; + int64_t rc = 0; + + if (phb->type != PNV_PHB_NPU || !npe->pdev) + return -EINVAL; + + if (enable) { + /* Enable the bypass window */ + phys_addr_t top = memblock_end_of_DRAM(); + + npe->tce_bypass_base = 0; + top = roundup_pow_of_two(top); + dev_info(&npe->pdev->dev, "Enabling bypass for PE %d\n", + npe->pe_number); + rc = opal_pci_map_pe_dma_window_real(phb->opal_id, + npe->pe_number, npe->pe_number, + npe->tce_bypass_base, top); + } else { + /* + * Disable the bypass window by replacing it with the + * TCE32 window. + */ + pnv_npu_disable_bypass(npe); + } + + return rc; +} + +int pnv_npu_dma_set_mask(struct pci_dev *npdev, u64 dma_mask) +{ + struct pci_controller *hose = pci_bus_to_host(npdev->bus); + struct pnv_phb *phb = hose->private_data; + struct pci_dn *pdn = pci_get_pdn(npdev); + struct pnv_ioda_pe *npe, *gpe; + struct pci_dev *gpdev; + uint64_t top; + bool bypass = false; + + if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE)) + return -ENXIO; + + /* We only do bypass if it's enabled on the linked device */ + npe = &phb->ioda.pe_array[pdn->pe_number]; + gpe = get_gpu_pci_dev_and_pe(npe, &gpdev); + if (!gpe) + return -ENODEV; + + if (gpe->tce_bypass_enabled) { + top = gpe->tce_bypass_base + memblock_end_of_DRAM() - 1; + bypass = (dma_mask >= top); + } + + if (bypass) + dev_info(&npdev->dev, "Using 64-bit DMA iommu bypass\n"); + else + dev_info(&npdev->dev, "Using 32-bit DMA via iommu\n"); + + pnv_npu_dma_set_bypass(npe, bypass); + *npdev->dev.dma_mask = dma_mask; + + return 0; +} diff --git a/arch/powerpc/platforms/powernv/opal-kmsg.c b/arch/powerpc/platforms/powernv/opal-kmsg.c new file mode 100644 index 000000000000..6f1214d4de92 --- /dev/null +++ b/arch/powerpc/platforms/powernv/opal-kmsg.c @@ -0,0 +1,75 @@ +/* + * kmsg dumper that ensures the OPAL console fully flushes panic messages + * + * Author: Russell Currey <ruscur@russell.cc> + * + * Copyright 2015 IBM Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include <linux/kmsg_dump.h> + +#include <asm/opal.h> +#include <asm/opal-api.h> + +/* + * Console output is controlled by OPAL firmware. The kernel regularly calls + * OPAL_POLL_EVENTS, which flushes some console output. In a panic state, + * however, the kernel no longer calls OPAL_POLL_EVENTS and the panic message + * may not be completely printed. This function does not actually dump the + * message, it just ensures that OPAL completely flushes the console buffer. + */ +static void force_opal_console_flush(struct kmsg_dumper *dumper, + enum kmsg_dump_reason reason) +{ + int i; + int64_t ret; + + /* + * Outside of a panic context the pollers will continue to run, + * so we don't need to do any special flushing. + */ + if (reason != KMSG_DUMP_PANIC) + return; + + if (opal_check_token(OPAL_CONSOLE_FLUSH)) { + ret = opal_console_flush(0); + + if (ret == OPAL_UNSUPPORTED || ret == OPAL_PARAMETER) + return; + + /* Incrementally flush until there's nothing left */ + while (opal_console_flush(0) != OPAL_SUCCESS); + } else { + /* + * If OPAL_CONSOLE_FLUSH is not implemented in the firmware, + * the console can still be flushed by calling the polling + * function enough times to flush the buffer. We don't know + * how much output still needs to be flushed, but we can be + * generous since the kernel is in panic and doesn't need + * to do much else. + */ + printk(KERN_NOTICE "opal: OPAL_CONSOLE_FLUSH missing.\n"); + for (i = 0; i < 1024; i++) { + opal_poll_events(NULL); + } + } +} + +static struct kmsg_dumper opal_kmsg_dumper = { + .dump = force_opal_console_flush +}; + +void __init opal_kmsg_init(void) +{ + int rc; + + /* Add our dumper to the list */ + rc = kmsg_dump_register(&opal_kmsg_dumper); + if (rc != 0) + pr_err("opal: kmsg_dump_register failed; returned %d\n", rc); +} diff --git a/arch/powerpc/platforms/powernv/opal-prd.c b/arch/powerpc/platforms/powernv/opal-prd.c index 4ece8e40dd54..e315e704cca7 100644 --- a/arch/powerpc/platforms/powernv/opal-prd.c +++ b/arch/powerpc/platforms/powernv/opal-prd.c @@ -434,7 +434,6 @@ static const struct of_device_id opal_prd_match[] = { static struct platform_driver opal_prd_driver = { .driver = { .name = "opal-prd", - .owner = THIS_MODULE, .of_match_table = opal_prd_match, }, .probe = opal_prd_probe, diff --git a/arch/powerpc/platforms/powernv/opal-rtc.c b/arch/powerpc/platforms/powernv/opal-rtc.c index 37dbee15769f..f8868864f373 100644 --- a/arch/powerpc/platforms/powernv/opal-rtc.c +++ b/arch/powerpc/platforms/powernv/opal-rtc.c @@ -31,8 +31,7 @@ static void opal_to_tm(u32 y_m_d, u64 h_m_s_ms, struct rtc_time *tm) tm->tm_hour = bcd2bin((h_m_s_ms >> 56) & 0xff); tm->tm_min = bcd2bin((h_m_s_ms >> 48) & 0xff); tm->tm_sec = bcd2bin((h_m_s_ms >> 40) & 0xff); - - GregorianDay(tm); + tm->tm_wday = -1; } unsigned long __init opal_get_boot_time(void) @@ -51,7 +50,7 @@ unsigned long __init opal_get_boot_time(void) rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms); if (rc == OPAL_BUSY_EVENT) opal_poll_events(NULL); - else + else if (rc == OPAL_BUSY) mdelay(10); } if (rc != OPAL_SUCCESS) diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index b7a464fef7a7..e45b88a5d7e0 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -301,3 +301,4 @@ OPAL_CALL(opal_flash_erase, OPAL_FLASH_ERASE); OPAL_CALL(opal_prd_msg, OPAL_PRD_MSG); OPAL_CALL(opal_leds_get_ind, OPAL_LEDS_GET_INDICATOR); OPAL_CALL(opal_leds_set_ind, OPAL_LEDS_SET_INDICATOR); +OPAL_CALL(opal_console_flush, OPAL_CONSOLE_FLUSH); diff --git a/arch/powerpc/platforms/powernv/opal-xscom.c b/arch/powerpc/platforms/powernv/opal-xscom.c index 7634d1c62299..d0ac535cf5d7 100644 --- a/arch/powerpc/platforms/powernv/opal-xscom.c +++ b/arch/powerpc/platforms/powernv/opal-xscom.c @@ -126,7 +126,7 @@ static const struct scom_controller opal_scom_controller = { static int opal_xscom_init(void) { - if (firmware_has_feature(FW_FEATURE_OPALv3)) + if (firmware_has_feature(FW_FEATURE_OPAL)) scom_init(&opal_scom_controller); return 0; } diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 57cffb80bc36..4e0da5af94a1 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -98,16 +98,11 @@ int __init early_init_dt_scan_opal(unsigned long node, pr_debug("OPAL Entry = 0x%llx (sizep=%p runtimesz=%d)\n", opal.size, sizep, runtimesz); - powerpc_firmware_features |= FW_FEATURE_OPAL; if (of_flat_dt_is_compatible(node, "ibm,opal-v3")) { - powerpc_firmware_features |= FW_FEATURE_OPALv2; - powerpc_firmware_features |= FW_FEATURE_OPALv3; - pr_info("OPAL V3 detected !\n"); - } else if (of_flat_dt_is_compatible(node, "ibm,opal-v2")) { - powerpc_firmware_features |= FW_FEATURE_OPALv2; - pr_info("OPAL V2 detected !\n"); + powerpc_firmware_features |= FW_FEATURE_OPAL; + pr_info("OPAL detected !\n"); } else { - pr_info("OPAL V1 detected !\n"); + panic("OPAL != V3 detected, no longer supported.\n"); } /* Reinit all cores with the right endian */ @@ -352,17 +347,15 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len) * enough room and be done with it */ spin_lock_irqsave(&opal_write_lock, flags); - if (firmware_has_feature(FW_FEATURE_OPALv2)) { - rc = opal_console_write_buffer_space(vtermno, &olen); - len = be64_to_cpu(olen); - if (rc || len < total_len) { - spin_unlock_irqrestore(&opal_write_lock, flags); - /* Closed -> drop characters */ - if (rc) - return total_len; - opal_poll_events(NULL); - return -EAGAIN; - } + rc = opal_console_write_buffer_space(vtermno, &olen); + len = be64_to_cpu(olen); + if (rc || len < total_len) { + spin_unlock_irqrestore(&opal_write_lock, flags); + /* Closed -> drop characters */ + if (rc) + return total_len; + opal_poll_events(NULL); + return -EAGAIN; } /* We still try to handle partial completions, though they @@ -555,7 +548,7 @@ bool opal_mce_check_early_recovery(struct pt_regs *regs) goto out; if ((regs->nip >= opal.base) && - (regs->nip <= (opal.base + opal.size))) + (regs->nip < (opal.base + opal.size))) recover_addr = find_recovery_address(regs->nip); /* @@ -696,10 +689,7 @@ static int __init opal_init(void) } /* Register OPAL consoles if any ports */ - if (firmware_has_feature(FW_FEATURE_OPALv2)) - consoles = of_find_node_by_path("/ibm,opal/consoles"); - else - consoles = of_node_get(opal_node); + consoles = of_find_node_by_path("/ibm,opal/consoles"); if (consoles) { for_each_child_of_node(consoles, np) { if (strcmp(np->name, "serial")) @@ -758,6 +748,9 @@ static int __init opal_init(void) opal_pdev_init(opal_node, "ibm,opal-flash"); opal_pdev_init(opal_node, "ibm,opal-prd"); + /* Initialise OPAL kmsg dumper for flushing console on panic */ + opal_kmsg_init(); + return 0; } machine_subsys_initcall(powernv, opal_init); diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 414fd1a00fda..573ae1994097 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -116,16 +116,6 @@ static int __init iommu_setup(char *str) } early_param("iommu", iommu_setup); -/* - * stdcix is only supposed to be used in hypervisor real mode as per - * the architecture spec - */ -static inline void __raw_rm_writeq(u64 val, volatile void __iomem *paddr) -{ - __asm__ __volatile__("stdcix %0,0,%1" - : : "r" (val), "r" (paddr) : "memory"); -} - static inline bool pnv_pci_is_mem_pref_64(unsigned long flags) { return ((flags & (IORESOURCE_MEM_64 | IORESOURCE_PREFETCH)) == @@ -344,7 +334,7 @@ static void __init pnv_ioda_parse_m64_window(struct pnv_phb *phb) return; } - if (!firmware_has_feature(FW_FEATURE_OPALv3)) { + if (!firmware_has_feature(FW_FEATURE_OPAL)) { pr_info(" Firmware too old to support M64 window\n"); return; } @@ -357,6 +347,7 @@ static void __init pnv_ioda_parse_m64_window(struct pnv_phb *phb) } res = &hose->mem_resources[1]; + res->name = dn->full_name; res->start = of_translate_address(dn, r + 2); res->end = res->start + of_read_number(r + 4, 2) - 1; res->flags = (IORESOURCE_MEM | IORESOURCE_MEM_64 | IORESOURCE_PREFETCH); @@ -780,8 +771,12 @@ static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) return -ENXIO; } - /* Configure PELTV */ - pnv_ioda_set_peltv(phb, pe, true); + /* + * Configure PELTV. NPUs don't have a PELTV table so skip + * configuration on them. + */ + if (phb->type != PNV_PHB_NPU) + pnv_ioda_set_peltv(phb, pe, true); /* Setup reverse map */ for (rid = pe->rid; rid < rid_end; rid++) @@ -924,7 +919,6 @@ static int pnv_pci_vf_resource_shift(struct pci_dev *dev, int offset) } #endif /* CONFIG_PCI_IOV */ -#if 0 static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev) { struct pci_controller *hose = pci_bus_to_host(dev->bus); @@ -941,11 +935,7 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev) if (pdn->pe_number != IODA_INVALID_PE) return NULL; - /* PE#0 has been pre-set */ - if (dev->bus->number == 0) - pe_num = 0; - else - pe_num = pnv_ioda_alloc_pe(phb); + pe_num = pnv_ioda_alloc_pe(phb); if (pe_num == IODA_INVALID_PE) { pr_warning("%s: Not enough PE# available, disabling device\n", pci_name(dev)); @@ -963,6 +953,7 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev) pci_dev_get(dev); pdn->pcidev = dev; pdn->pe_number = pe_num; + pe->flags = PNV_IODA_PE_DEV; pe->pdev = dev; pe->pbus = NULL; pe->tce32_seg = -1; @@ -993,7 +984,6 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev) return pe; } -#endif /* Useful for SRIOV case */ static void pnv_ioda_setup_same_PE(struct pci_bus *bus, struct pnv_ioda_pe *pe) { @@ -1007,6 +997,7 @@ static void pnv_ioda_setup_same_PE(struct pci_bus *bus, struct pnv_ioda_pe *pe) pci_name(dev)); continue; } + pdn->pcidev = dev; pdn->pe_number = pe->pe_number; pe->dma_weight += pnv_ioda_dma_weight(dev); if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate) @@ -1083,6 +1074,77 @@ static void pnv_ioda_setup_bus_PE(struct pci_bus *bus, bool all) pnv_ioda_link_pe_by_weight(phb, pe); } +static struct pnv_ioda_pe *pnv_ioda_setup_npu_PE(struct pci_dev *npu_pdev) +{ + int pe_num, found_pe = false, rc; + long rid; + struct pnv_ioda_pe *pe; + struct pci_dev *gpu_pdev; + struct pci_dn *npu_pdn; + struct pci_controller *hose = pci_bus_to_host(npu_pdev->bus); + struct pnv_phb *phb = hose->private_data; + + /* + * Due to a hardware errata PE#0 on the NPU is reserved for + * error handling. This means we only have three PEs remaining + * which need to be assigned to four links, implying some + * links must share PEs. + * + * To achieve this we assign PEs such that NPUs linking the + * same GPU get assigned the same PE. + */ + gpu_pdev = pnv_pci_get_gpu_dev(npu_pdev); + for (pe_num = 0; pe_num < phb->ioda.total_pe; pe_num++) { + pe = &phb->ioda.pe_array[pe_num]; + if (!pe->pdev) + continue; + + if (pnv_pci_get_gpu_dev(pe->pdev) == gpu_pdev) { + /* + * This device has the same peer GPU so should + * be assigned the same PE as the existing + * peer NPU. + */ + dev_info(&npu_pdev->dev, + "Associating to existing PE %d\n", pe_num); + pci_dev_get(npu_pdev); + npu_pdn = pci_get_pdn(npu_pdev); + rid = npu_pdev->bus->number << 8 | npu_pdn->devfn; + npu_pdn->pcidev = npu_pdev; + npu_pdn->pe_number = pe_num; + pe->dma_weight += pnv_ioda_dma_weight(npu_pdev); + phb->ioda.pe_rmap[rid] = pe->pe_number; + + /* Map the PE to this link */ + rc = opal_pci_set_pe(phb->opal_id, pe_num, rid, + OpalPciBusAll, + OPAL_COMPARE_RID_DEVICE_NUMBER, + OPAL_COMPARE_RID_FUNCTION_NUMBER, + OPAL_MAP_PE); + WARN_ON(rc != OPAL_SUCCESS); + found_pe = true; + break; + } + } + + if (!found_pe) + /* + * Could not find an existing PE so allocate a new + * one. + */ + return pnv_ioda_setup_dev_PE(npu_pdev); + else + return pe; +} + +static void pnv_ioda_setup_npu_PEs(struct pci_bus *bus) +{ + struct pci_dev *pdev; + + list_for_each_entry(pdev, &bus->devices, bus_list) + pnv_ioda_setup_npu_PE(pdev); +} + static void pnv_ioda_setup_PEs(struct pci_bus *bus) { struct pci_dev *dev; @@ -1119,7 +1181,17 @@ static void pnv_pci_ioda_setup_PEs(void) if (phb->reserve_m64_pe) phb->reserve_m64_pe(hose->bus, NULL, true); - pnv_ioda_setup_PEs(hose->bus); + /* + * On NPU PHB, we expect separate PEs for individual PCI + * functions. PCI bus dependent PEs are required for the + * remaining types of PHBs. + */ + if (phb->type == PNV_PHB_NPU) { + /* PE#0 is needed for error reporting */ + pnv_ioda_reserve_pe(phb, 0); + pnv_ioda_setup_npu_PEs(hose->bus); + } else + pnv_ioda_setup_PEs(hose->bus); } } @@ -1578,6 +1650,8 @@ static int pnv_pci_ioda_dma_set_mask(struct pci_dev *pdev, u64 dma_mask) struct pnv_ioda_pe *pe; uint64_t top; bool bypass = false; + struct pci_dev *linked_npu_dev; + int i; if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE)) return -ENODEV;; @@ -1596,6 +1670,18 @@ static int pnv_pci_ioda_dma_set_mask(struct pci_dev *pdev, u64 dma_mask) set_dma_ops(&pdev->dev, &dma_iommu_ops); } *pdev->dev.dma_mask = dma_mask; + + /* Update peer npu devices */ + if (pe->flags & PNV_IODA_PE_PEER) + for (i = 0; i < PNV_IODA_MAX_PEER_PES; i++) { + if (!pe->peers[i]) + continue; + + linked_npu_dev = pe->peers[i]->pdev; + if (dma_get_mask(&linked_npu_dev->dev) != dma_mask) + dma_set_mask(&linked_npu_dev->dev, dma_mask); + } + return 0; } @@ -1740,12 +1826,23 @@ static inline void pnv_pci_ioda2_tce_invalidate_entire(struct pnv_ioda_pe *pe) /* 01xb - invalidate TCEs that match the specified PE# */ unsigned long val = (0x4ull << 60) | (pe->pe_number & 0xFF); struct pnv_phb *phb = pe->phb; + struct pnv_ioda_pe *npe; + int i; if (!phb->ioda.tce_inval_reg) return; mb(); /* Ensure above stores are visible */ __raw_writeq(cpu_to_be64(val), phb->ioda.tce_inval_reg); + + if (pe->flags & PNV_IODA_PE_PEER) + for (i = 0; i < PNV_IODA_MAX_PEER_PES; i++) { + npe = pe->peers[i]; + if (!npe || npe->phb->type != PNV_PHB_NPU) + continue; + + pnv_npu_tce_invalidate_entire(npe); + } } static void pnv_pci_ioda2_do_tce_invalidate(unsigned pe_number, bool rm, @@ -1780,15 +1877,28 @@ static void pnv_pci_ioda2_tce_invalidate(struct iommu_table *tbl, struct iommu_table_group_link *tgl; list_for_each_entry_rcu(tgl, &tbl->it_group_list, next) { + struct pnv_ioda_pe *npe; struct pnv_ioda_pe *pe = container_of(tgl->table_group, struct pnv_ioda_pe, table_group); __be64 __iomem *invalidate = rm ? (__be64 __iomem *)pe->phb->ioda.tce_inval_reg_phys : pe->phb->ioda.tce_inval_reg; + int i; pnv_pci_ioda2_do_tce_invalidate(pe->pe_number, rm, invalidate, tbl->it_page_shift, index, npages); + + if (pe->flags & PNV_IODA_PE_PEER) + /* Invalidate PEs using the same TCE table */ + for (i = 0; i < PNV_IODA_MAX_PEER_PES; i++) { + npe = pe->peers[i]; + if (!npe || npe->phb->type != PNV_PHB_NPU) + continue; + + pnv_npu_tce_invalidate(npe, tbl, index, + npages, rm); + } } } @@ -2436,10 +2546,17 @@ static void pnv_ioda_setup_dma(struct pnv_phb *phb) pe_info(pe, "DMA weight %d, assigned %d DMA32 segments\n", pe->dma_weight, segs); pnv_pci_ioda_setup_dma_pe(phb, pe, base, segs); - } else { + } else if (phb->type == PNV_PHB_IODA2) { pe_info(pe, "Assign DMA32 space\n"); segs = 0; pnv_pci_ioda2_setup_dma_pe(phb, pe); + } else if (phb->type == PNV_PHB_NPU) { + /* + * We initialise the DMA space for an NPU PHB + * after setup of the PHB is complete as we + * point the NPU TVT to the the same location + * as the PHB3 TVT. + */ } remaining -= segs; @@ -2881,6 +2998,11 @@ static void pnv_pci_ioda_setup_seg(void) list_for_each_entry_safe(hose, tmp, &hose_list, list_node) { phb = hose->private_data; + + /* NPU PHB does not support IO or MMIO segmentation */ + if (phb->type == PNV_PHB_NPU) + continue; + list_for_each_entry(pe, &phb->ioda.pe_list, list) { pnv_ioda_setup_pe_seg(hose, pe); } @@ -2920,6 +3042,27 @@ static void pnv_pci_ioda_create_dbgfs(void) #endif /* CONFIG_DEBUG_FS */ } +static void pnv_npu_ioda_fixup(void) +{ + bool enable_bypass; + struct pci_controller *hose, *tmp; + struct pnv_phb *phb; + struct pnv_ioda_pe *pe; + + list_for_each_entry_safe(hose, tmp, &hose_list, list_node) { + phb = hose->private_data; + if (phb->type != PNV_PHB_NPU) + continue; + + list_for_each_entry(pe, &phb->ioda.pe_dma_list, dma_link) { + enable_bypass = dma_get_mask(&pe->pdev->dev) == + DMA_BIT_MASK(64); + pnv_npu_init_dma_pe(pe); + pnv_npu_dma_set_bypass(pe, enable_bypass); + } + } +} + static void pnv_pci_ioda_fixup(void) { pnv_pci_ioda_setup_PEs(); @@ -2932,6 +3075,9 @@ static void pnv_pci_ioda_fixup(void) eeh_init(); eeh_addr_cache_build(); #endif + + /* Link NPU IODA tables to their PCI devices. */ + pnv_npu_ioda_fixup(); } /* @@ -3046,6 +3192,19 @@ static const struct pci_controller_ops pnv_pci_ioda_controller_ops = { .shutdown = pnv_pci_ioda_shutdown, }; +static const struct pci_controller_ops pnv_npu_ioda_controller_ops = { + .dma_dev_setup = pnv_pci_dma_dev_setup, +#ifdef CONFIG_PCI_MSI + .setup_msi_irqs = pnv_setup_msi_irqs, + .teardown_msi_irqs = pnv_teardown_msi_irqs, +#endif + .enable_device_hook = pnv_pci_enable_device_hook, + .window_alignment = pnv_pci_window_alignment, + .reset_secondary_bus = pnv_pci_reset_secondary_bus, + .dma_set_mask = pnv_npu_dma_set_mask, + .shutdown = pnv_pci_ioda_shutdown, +}; + static void __init pnv_pci_init_ioda_phb(struct device_node *np, u64 hub_id, int ioda_type) { @@ -3101,6 +3260,8 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, phb->model = PNV_PHB_MODEL_P7IOC; else if (of_device_is_compatible(np, "ibm,power8-pciex")) phb->model = PNV_PHB_MODEL_PHB3; + else if (of_device_is_compatible(np, "ibm,power8-npu-pciex")) + phb->model = PNV_PHB_MODEL_NPU; else phb->model = PNV_PHB_MODEL_UNKNOWN; @@ -3201,7 +3362,11 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, * the child P2P bridges) can form individual PE. */ ppc_md.pcibios_fixup = pnv_pci_ioda_fixup; - hose->controller_ops = pnv_pci_ioda_controller_ops; + + if (phb->type == PNV_PHB_NPU) + hose->controller_ops = pnv_npu_ioda_controller_ops; + else + hose->controller_ops = pnv_pci_ioda_controller_ops; #ifdef CONFIG_PCI_IOV ppc_md.pcibios_fixup_sriov = pnv_pci_ioda_fixup_iov_resources; @@ -3236,6 +3401,11 @@ void __init pnv_pci_init_ioda2_phb(struct device_node *np) pnv_pci_init_ioda_phb(np, 0, PNV_PHB_IODA2); } +void __init pnv_pci_init_npu_phb(struct device_node *np) +{ + pnv_pci_init_ioda_phb(np, 0, PNV_PHB_NPU); +} + void __init pnv_pci_init_ioda_hub(struct device_node *np) { struct device_node *phbn; diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index f2dd77234240..2f55c86df703 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -1,8 +1,6 @@ /* * Support PCI/PCIe on PowerNV platforms * - * Currently supports only P5IOC2 - * * Copyright 2011 Benjamin Herrenschmidt, IBM Corp. * * This program is free software; you can redistribute it and/or @@ -807,6 +805,10 @@ void __init pnv_pci_init(void) for_each_compatible_node(np, NULL, "ibm,ioda2-phb") pnv_pci_init_ioda2_phb(np); + /* Look for NPU PHBs */ + for_each_compatible_node(np, NULL, "ibm,ioda2-npu-phb") + pnv_pci_init_npu_phb(np); + /* Setup the linkage between OF nodes and PHBs */ pci_devs_phb_init(); diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index c8ff50e90766..7f56313e8d72 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -7,6 +7,7 @@ enum pnv_phb_type { PNV_PHB_P5IOC2 = 0, PNV_PHB_IODA1 = 1, PNV_PHB_IODA2 = 2, + PNV_PHB_NPU = 3, }; /* Precise PHB model for error management */ @@ -15,6 +16,7 @@ enum pnv_phb_model { PNV_PHB_MODEL_P5IOC2, PNV_PHB_MODEL_P7IOC, PNV_PHB_MODEL_PHB3, + PNV_PHB_MODEL_NPU, }; #define PNV_PCI_DIAG_BUF_SIZE 8192 @@ -24,6 +26,7 @@ enum pnv_phb_model { #define PNV_IODA_PE_MASTER (1 << 3) /* Master PE in compound case */ #define PNV_IODA_PE_SLAVE (1 << 4) /* Slave PE in compound case */ #define PNV_IODA_PE_VF (1 << 5) /* PE for one VF */ +#define PNV_IODA_PE_PEER (1 << 6) /* PE has peers */ /* Data associated with a PE, including IOMMU tracking etc.. */ struct pnv_phb; @@ -31,6 +34,9 @@ struct pnv_ioda_pe { unsigned long flags; struct pnv_phb *phb; +#define PNV_IODA_MAX_PEER_PES 8 + struct pnv_ioda_pe *peers[PNV_IODA_MAX_PEER_PES]; + /* A PE can be associated with a single device or an * entire bus (& children). In the former case, pdev * is populated, in the later case, pbus is. @@ -229,6 +235,7 @@ extern void pnv_pci_setup_iommu_table(struct iommu_table *tbl, extern void pnv_pci_init_p5ioc2_hub(struct device_node *np); extern void pnv_pci_init_ioda_hub(struct device_node *np); extern void pnv_pci_init_ioda2_phb(struct device_node *np); +extern void pnv_pci_init_npu_phb(struct device_node *np); extern void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl, __be64 *startp, __be64 *endp, bool rm); extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev); @@ -238,4 +245,16 @@ extern void pnv_pci_dma_dev_setup(struct pci_dev *pdev); extern int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type); extern void pnv_teardown_msi_irqs(struct pci_dev *pdev); +/* Nvlink functions */ +extern void pnv_npu_tce_invalidate_entire(struct pnv_ioda_pe *npe); +extern void pnv_npu_tce_invalidate(struct pnv_ioda_pe *npe, + struct iommu_table *tbl, + unsigned long index, + unsigned long npages, + bool rm); +extern void pnv_npu_init_dma_pe(struct pnv_ioda_pe *npe); +extern void pnv_npu_setup_dma_pe(struct pnv_ioda_pe *npe); +extern int pnv_npu_dma_set_bypass(struct pnv_ioda_pe *npe, bool enabled); +extern int pnv_npu_dma_set_mask(struct pci_dev *npdev, u64 dma_mask); + #endif /* __POWERNV_PCI_H */ diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index a9a8fa37a555..1acb0c72d923 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -90,12 +90,8 @@ static void pnv_show_cpuinfo(struct seq_file *m) if (root) model = of_get_property(root, "model", NULL); seq_printf(m, "machine\t\t: PowerNV %s\n", model); - if (firmware_has_feature(FW_FEATURE_OPALv3)) - seq_printf(m, "firmware\t: OPAL v3\n"); - else if (firmware_has_feature(FW_FEATURE_OPALv2)) - seq_printf(m, "firmware\t: OPAL v2\n"); - else if (firmware_has_feature(FW_FEATURE_OPAL)) - seq_printf(m, "firmware\t: OPAL v1\n"); + if (firmware_has_feature(FW_FEATURE_OPAL)) + seq_printf(m, "firmware\t: OPAL\n"); else seq_printf(m, "firmware\t: BML\n"); of_node_put(root); @@ -224,9 +220,9 @@ static void pnv_kexec_cpu_down(int crash_shutdown, int secondary) { xics_kexec_teardown_cpu(secondary); - /* On OPAL v3, we return all CPUs to firmware */ + /* On OPAL, we return all CPUs to firmware */ - if (!firmware_has_feature(FW_FEATURE_OPALv3)) + if (!firmware_has_feature(FW_FEATURE_OPAL)) return; if (secondary) { diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index ca264833ee64..ad7b1a3dbed0 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -61,14 +61,15 @@ static int pnv_smp_kick_cpu(int nr) unsigned long start_here = __pa(ppc_function_entry(generic_secondary_smp_init)); long rc; + uint8_t status; BUG_ON(nr < 0 || nr >= NR_CPUS); /* - * If we already started or OPALv2 is not supported, we just + * If we already started or OPAL is not supported, we just * kick the CPU via the PACA */ - if (paca[nr].cpu_start || !firmware_has_feature(FW_FEATURE_OPALv2)) + if (paca[nr].cpu_start || !firmware_has_feature(FW_FEATURE_OPAL)) goto kick; /* @@ -77,55 +78,42 @@ static int pnv_smp_kick_cpu(int nr) * first time. OPAL v3 allows us to query OPAL to know if it * has the CPUs, so we do that */ - if (firmware_has_feature(FW_FEATURE_OPALv3)) { - uint8_t status; - - rc = opal_query_cpu_status(pcpu, &status); - if (rc != OPAL_SUCCESS) { - pr_warn("OPAL Error %ld querying CPU %d state\n", - rc, nr); - return -ENODEV; - } + rc = opal_query_cpu_status(pcpu, &status); + if (rc != OPAL_SUCCESS) { + pr_warn("OPAL Error %ld querying CPU %d state\n", rc, nr); + return -ENODEV; + } - /* - * Already started, just kick it, probably coming from - * kexec and spinning - */ - if (status == OPAL_THREAD_STARTED) - goto kick; + /* + * Already started, just kick it, probably coming from + * kexec and spinning + */ + if (status == OPAL_THREAD_STARTED) + goto kick; - /* - * Available/inactive, let's kick it - */ - if (status == OPAL_THREAD_INACTIVE) { - pr_devel("OPAL: Starting CPU %d (HW 0x%x)...\n", - nr, pcpu); - rc = opal_start_cpu(pcpu, start_here); - if (rc != OPAL_SUCCESS) { - pr_warn("OPAL Error %ld starting CPU %d\n", - rc, nr); - return -ENODEV; - } - } else { - /* - * An unavailable CPU (or any other unknown status) - * shouldn't be started. It should also - * not be in the possible map but currently it can - * happen - */ - pr_devel("OPAL: CPU %d (HW 0x%x) is unavailable" - " (status %d)...\n", nr, pcpu, status); + /* + * Available/inactive, let's kick it + */ + if (status == OPAL_THREAD_INACTIVE) { + pr_devel("OPAL: Starting CPU %d (HW 0x%x)...\n", nr, pcpu); + rc = opal_start_cpu(pcpu, start_here); + if (rc != OPAL_SUCCESS) { + pr_warn("OPAL Error %ld starting CPU %d\n", rc, nr); return -ENODEV; } } else { /* - * On OPAL v2, we just kick it and hope for the best, - * we must not test the error from opal_start_cpu() or - * we would fail to get CPUs from kexec. + * An unavailable CPU (or any other unknown status) + * shouldn't be started. It should also + * not be in the possible map but currently it can + * happen */ - opal_start_cpu(pcpu, start_here); + pr_devel("OPAL: CPU %d (HW 0x%x) is unavailable" + " (status %d)...\n", nr, pcpu, status); + return -ENODEV; } - kick: + +kick: return smp_generic_kick_cpu(nr); } diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index f244dcb4f2cf..2b93ae8d557a 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -20,7 +20,6 @@ #include <linux/of.h> #include "of_helpers.h" -#include "offline_states.h" #include "pseries.h" #include <asm/prom.h> @@ -338,185 +337,6 @@ int dlpar_release_drc(u32 drc_index) return 0; } -#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE - -static int dlpar_online_cpu(struct device_node *dn) -{ - int rc = 0; - unsigned int cpu; - int len, nthreads, i; - const __be32 *intserv; - u32 thread; - - intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s", &len); - if (!intserv) - return -EINVAL; - - nthreads = len / sizeof(u32); - - cpu_maps_update_begin(); - for (i = 0; i < nthreads; i++) { - thread = be32_to_cpu(intserv[i]); - for_each_present_cpu(cpu) { - if (get_hard_smp_processor_id(cpu) != thread) - continue; - BUG_ON(get_cpu_current_state(cpu) - != CPU_STATE_OFFLINE); - cpu_maps_update_done(); - rc = device_online(get_cpu_device(cpu)); - if (rc) - goto out; - cpu_maps_update_begin(); - - break; - } - if (cpu == num_possible_cpus()) - printk(KERN_WARNING "Could not find cpu to online " - "with physical id 0x%x\n", thread); - } - cpu_maps_update_done(); - -out: - return rc; - -} - -static ssize_t dlpar_cpu_probe(const char *buf, size_t count) -{ - struct device_node *dn, *parent; - u32 drc_index; - int rc; - - rc = kstrtou32(buf, 0, &drc_index); - if (rc) - return -EINVAL; - - rc = dlpar_acquire_drc(drc_index); - if (rc) - return -EINVAL; - - parent = of_find_node_by_path("/cpus"); - if (!parent) - return -ENODEV; - - dn = dlpar_configure_connector(cpu_to_be32(drc_index), parent); - of_node_put(parent); - if (!dn) { - dlpar_release_drc(drc_index); - return -EINVAL; - } - - rc = dlpar_attach_node(dn); - if (rc) { - dlpar_release_drc(drc_index); - dlpar_free_cc_nodes(dn); - return rc; - } - - rc = dlpar_online_cpu(dn); - if (rc) - return rc; - - return count; -} - -static int dlpar_offline_cpu(struct device_node *dn) -{ - int rc = 0; - unsigned int cpu; - int len, nthreads, i; - const __be32 *intserv; - u32 thread; - - intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s", &len); - if (!intserv) - return -EINVAL; - - nthreads = len / sizeof(u32); - - cpu_maps_update_begin(); - for (i = 0; i < nthreads; i++) { - thread = be32_to_cpu(intserv[i]); - for_each_present_cpu(cpu) { - if (get_hard_smp_processor_id(cpu) != thread) - continue; - - if (get_cpu_current_state(cpu) == CPU_STATE_OFFLINE) - break; - - if (get_cpu_current_state(cpu) == CPU_STATE_ONLINE) { - set_preferred_offline_state(cpu, CPU_STATE_OFFLINE); - cpu_maps_update_done(); - rc = device_offline(get_cpu_device(cpu)); - if (rc) - goto out; - cpu_maps_update_begin(); - break; - - } - - /* - * The cpu is in CPU_STATE_INACTIVE. - * Upgrade it's state to CPU_STATE_OFFLINE. - */ - set_preferred_offline_state(cpu, CPU_STATE_OFFLINE); - BUG_ON(plpar_hcall_norets(H_PROD, thread) - != H_SUCCESS); - __cpu_die(cpu); - break; - } - if (cpu == num_possible_cpus()) - printk(KERN_WARNING "Could not find cpu to offline " - "with physical id 0x%x\n", thread); - } - cpu_maps_update_done(); - -out: - return rc; - -} - -static ssize_t dlpar_cpu_release(const char *buf, size_t count) -{ - struct device_node *dn; - u32 drc_index; - int rc; - - dn = of_find_node_by_path(buf); - if (!dn) - return -EINVAL; - - rc = of_property_read_u32(dn, "ibm,my-drc-index", &drc_index); - if (rc) { - of_node_put(dn); - return -EINVAL; - } - - rc = dlpar_offline_cpu(dn); - if (rc) { - of_node_put(dn); - return -EINVAL; - } - - rc = dlpar_release_drc(drc_index); - if (rc) { - of_node_put(dn); - return rc; - } - - rc = dlpar_detach_node(dn); - if (rc) { - dlpar_acquire_drc(drc_index); - return rc; - } - - of_node_put(dn); - - return count; -} - -#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */ - static int handle_dlpar_errorlog(struct pseries_hp_errorlog *hp_elog) { int rc; @@ -536,6 +356,9 @@ static int handle_dlpar_errorlog(struct pseries_hp_errorlog *hp_elog) case PSERIES_HP_ELOG_RESOURCE_MEM: rc = dlpar_memory(hp_elog); break; + case PSERIES_HP_ELOG_RESOURCE_CPU: + rc = dlpar_cpu(hp_elog); + break; default: pr_warn_ratelimited("Invalid resource (%d) specified\n", hp_elog->resource); @@ -565,6 +388,9 @@ static ssize_t dlpar_store(struct class *class, struct class_attribute *attr, if (!strncmp(arg, "memory", 6)) { hp_elog->resource = PSERIES_HP_ELOG_RESOURCE_MEM; arg += strlen("memory "); + } else if (!strncmp(arg, "cpu", 3)) { + hp_elog->resource = PSERIES_HP_ELOG_RESOURCE_CPU; + arg += strlen("cpu "); } else { pr_err("Invalid resource specified: \"%s\"\n", buf); rc = -EINVAL; @@ -624,16 +450,7 @@ static CLASS_ATTR(dlpar, S_IWUSR, NULL, dlpar_store); static int __init pseries_dlpar_init(void) { - int rc; - -#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE - ppc_md.cpu_probe = dlpar_cpu_probe; - ppc_md.cpu_release = dlpar_cpu_release; -#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */ - - rc = sysfs_create_file(kernel_kobj, &class_attr_dlpar.attr); - - return rc; + return sysfs_create_file(kernel_kobj, &class_attr_dlpar.attr); } machine_device_initcall(pseries, pseries_dlpar_init); diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index 62475440fd45..32274f72fe3f 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -18,12 +18,15 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) "pseries-hotplug-cpu: " fmt + #include <linux/kernel.h> #include <linux/interrupt.h> #include <linux/delay.h> #include <linux/sched.h> /* for idle_task_exit */ #include <linux/cpu.h> #include <linux/of.h> +#include <linux/slab.h> #include <asm/prom.h> #include <asm/rtas.h> #include <asm/firmware.h> @@ -32,6 +35,7 @@ #include <asm/xics.h> #include <asm/plpar_wrappers.h> +#include "pseries.h" #include "offline_states.h" /* This version can't take the spinlock, because it never returns */ @@ -88,13 +92,7 @@ void set_default_offline_state(int cpu) static void rtas_stop_self(void) { - static struct rtas_args args = { - .nargs = 0, - .nret = cpu_to_be32(1), - .rets = &args.args[0], - }; - - args.token = cpu_to_be32(rtas_stop_self_token); + static struct rtas_args args; local_irq_disable(); @@ -102,7 +100,8 @@ static void rtas_stop_self(void) printk("cpu %u (hwid %u) Ready to die...\n", smp_processor_id(), hard_smp_processor_id()); - enter_rtas(__pa(&args)); + + rtas_call_unlocked(&args, rtas_stop_self_token, 0, 1, NULL); panic("Alas, I survived.\n"); } @@ -339,6 +338,536 @@ static void pseries_remove_processor(struct device_node *np) cpu_maps_update_done(); } +static int dlpar_online_cpu(struct device_node *dn) +{ + int rc = 0; + unsigned int cpu; + int len, nthreads, i; + const __be32 *intserv; + u32 thread; + + intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s", &len); + if (!intserv) + return -EINVAL; + + nthreads = len / sizeof(u32); + + cpu_maps_update_begin(); + for (i = 0; i < nthreads; i++) { + thread = be32_to_cpu(intserv[i]); + for_each_present_cpu(cpu) { + if (get_hard_smp_processor_id(cpu) != thread) + continue; + BUG_ON(get_cpu_current_state(cpu) + != CPU_STATE_OFFLINE); + cpu_maps_update_done(); + rc = device_online(get_cpu_device(cpu)); + if (rc) + goto out; + cpu_maps_update_begin(); + + break; + } + if (cpu == num_possible_cpus()) + printk(KERN_WARNING "Could not find cpu to online " + "with physical id 0x%x\n", thread); + } + cpu_maps_update_done(); + +out: + return rc; + +} + +static bool dlpar_cpu_exists(struct device_node *parent, u32 drc_index) +{ + struct device_node *child = NULL; + u32 my_drc_index; + bool found; + int rc; + + /* Assume cpu doesn't exist */ + found = false; + + for_each_child_of_node(parent, child) { + rc = of_property_read_u32(child, "ibm,my-drc-index", + &my_drc_index); + if (rc) + continue; + + if (my_drc_index == drc_index) { + of_node_put(child); + found = true; + break; + } + } + + return found; +} + +static bool valid_cpu_drc_index(struct device_node *parent, u32 drc_index) +{ + bool found = false; + int rc, index; + + index = 0; + while (!found) { + u32 drc; + + rc = of_property_read_u32_index(parent, "ibm,drc-indexes", + index++, &drc); + if (rc) + break; + + if (drc == drc_index) + found = true; + } + + return found; +} + +static ssize_t dlpar_cpu_add(u32 drc_index) +{ + struct device_node *dn, *parent; + int rc, saved_rc; + + pr_debug("Attempting to add CPU, drc index: %x\n", drc_index); + + parent = of_find_node_by_path("/cpus"); + if (!parent) { + pr_warn("Failed to find CPU root node \"/cpus\"\n"); + return -ENODEV; + } + + if (dlpar_cpu_exists(parent, drc_index)) { + of_node_put(parent); + pr_warn("CPU with drc index %x already exists\n", drc_index); + return -EINVAL; + } + + if (!valid_cpu_drc_index(parent, drc_index)) { + of_node_put(parent); + pr_warn("Cannot find CPU (drc index %x) to add.\n", drc_index); + return -EINVAL; + } + + rc = dlpar_acquire_drc(drc_index); + if (rc) { + pr_warn("Failed to acquire DRC, rc: %d, drc index: %x\n", + rc, drc_index); + of_node_put(parent); + return -EINVAL; + } + + dn = dlpar_configure_connector(cpu_to_be32(drc_index), parent); + of_node_put(parent); + if (!dn) { + pr_warn("Failed call to configure-connector, drc index: %x\n", + drc_index); + dlpar_release_drc(drc_index); + return -EINVAL; + } + + rc = dlpar_attach_node(dn); + if (rc) { + saved_rc = rc; + pr_warn("Failed to attach node %s, rc: %d, drc index: %x\n", + dn->name, rc, drc_index); + + rc = dlpar_release_drc(drc_index); + if (!rc) + dlpar_free_cc_nodes(dn); + + return saved_rc; + } + + rc = dlpar_online_cpu(dn); + if (rc) { + saved_rc = rc; + pr_warn("Failed to online cpu %s, rc: %d, drc index: %x\n", + dn->name, rc, drc_index); + + rc = dlpar_detach_node(dn); + if (!rc) + dlpar_release_drc(drc_index); + + return saved_rc; + } + + pr_debug("Successfully added CPU %s, drc index: %x\n", dn->name, + drc_index); + return rc; +} + +static int dlpar_offline_cpu(struct device_node *dn) +{ + int rc = 0; + unsigned int cpu; + int len, nthreads, i; + const __be32 *intserv; + u32 thread; + + intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s", &len); + if (!intserv) + return -EINVAL; + + nthreads = len / sizeof(u32); + + cpu_maps_update_begin(); + for (i = 0; i < nthreads; i++) { + thread = be32_to_cpu(intserv[i]); + for_each_present_cpu(cpu) { + if (get_hard_smp_processor_id(cpu) != thread) + continue; + + if (get_cpu_current_state(cpu) == CPU_STATE_OFFLINE) + break; + + if (get_cpu_current_state(cpu) == CPU_STATE_ONLINE) { + set_preferred_offline_state(cpu, + CPU_STATE_OFFLINE); + cpu_maps_update_done(); + rc = device_offline(get_cpu_device(cpu)); + if (rc) + goto out; + cpu_maps_update_begin(); + break; + + } + + /* + * The cpu is in CPU_STATE_INACTIVE. + * Upgrade it's state to CPU_STATE_OFFLINE. + */ + set_preferred_offline_state(cpu, CPU_STATE_OFFLINE); + BUG_ON(plpar_hcall_norets(H_PROD, thread) + != H_SUCCESS); + __cpu_die(cpu); + break; + } + if (cpu == num_possible_cpus()) + printk(KERN_WARNING "Could not find cpu to offline with physical id 0x%x\n", thread); + } + cpu_maps_update_done(); + +out: + return rc; + +} + +static ssize_t dlpar_cpu_remove(struct device_node *dn, u32 drc_index) +{ + int rc; + + pr_debug("Attemping to remove CPU %s, drc index: %x\n", + dn->name, drc_index); + + rc = dlpar_offline_cpu(dn); + if (rc) { + pr_warn("Failed to offline CPU %s, rc: %d\n", dn->name, rc); + return -EINVAL; + } + + rc = dlpar_release_drc(drc_index); + if (rc) { + pr_warn("Failed to release drc (%x) for CPU %s, rc: %d\n", + drc_index, dn->name, rc); + dlpar_online_cpu(dn); + return rc; + } + + rc = dlpar_detach_node(dn); + if (rc) { + int saved_rc = rc; + + pr_warn("Failed to detach CPU %s, rc: %d", dn->name, rc); + + rc = dlpar_acquire_drc(drc_index); + if (!rc) + dlpar_online_cpu(dn); + + return saved_rc; + } + + pr_debug("Successfully removed CPU, drc index: %x\n", drc_index); + return 0; +} + +static struct device_node *cpu_drc_index_to_dn(u32 drc_index) +{ + struct device_node *dn; + u32 my_index; + int rc; + + for_each_node_by_type(dn, "cpu") { + rc = of_property_read_u32(dn, "ibm,my-drc-index", &my_index); + if (rc) + continue; + + if (my_index == drc_index) + break; + } + + return dn; +} + +static int dlpar_cpu_remove_by_index(u32 drc_index) +{ + struct device_node *dn; + int rc; + + dn = cpu_drc_index_to_dn(drc_index); + if (!dn) { + pr_warn("Cannot find CPU (drc index %x) to remove\n", + drc_index); + return -ENODEV; + } + + rc = dlpar_cpu_remove(dn, drc_index); + of_node_put(dn); + return rc; +} + +static int find_dlpar_cpus_to_remove(u32 *cpu_drcs, int cpus_to_remove) +{ + struct device_node *dn; + int cpus_found = 0; + int rc; + + /* We want to find cpus_to_remove + 1 CPUs to ensure we do not + * remove the last CPU. + */ + for_each_node_by_type(dn, "cpu") { + cpus_found++; + + if (cpus_found > cpus_to_remove) { + of_node_put(dn); + break; + } + + /* Note that cpus_found is always 1 ahead of the index + * into the cpu_drcs array, so we use cpus_found - 1 + */ + rc = of_property_read_u32(dn, "ibm,my-drc-index", + &cpu_drcs[cpus_found - 1]); + if (rc) { + pr_warn("Error occurred getting drc-index for %s\n", + dn->name); + of_node_put(dn); + return -1; + } + } + + if (cpus_found < cpus_to_remove) { + pr_warn("Failed to find enough CPUs (%d of %d) to remove\n", + cpus_found, cpus_to_remove); + } else if (cpus_found == cpus_to_remove) { + pr_warn("Cannot remove all CPUs\n"); + } + + return cpus_found; +} + +static int dlpar_cpu_remove_by_count(u32 cpus_to_remove) +{ + u32 *cpu_drcs; + int cpus_found; + int cpus_removed = 0; + int i, rc; + + pr_debug("Attempting to hot-remove %d CPUs\n", cpus_to_remove); + + cpu_drcs = kcalloc(cpus_to_remove, sizeof(*cpu_drcs), GFP_KERNEL); + if (!cpu_drcs) + return -EINVAL; + + cpus_found = find_dlpar_cpus_to_remove(cpu_drcs, cpus_to_remove); + if (cpus_found <= cpus_to_remove) { + kfree(cpu_drcs); + return -EINVAL; + } + + for (i = 0; i < cpus_to_remove; i++) { + rc = dlpar_cpu_remove_by_index(cpu_drcs[i]); + if (rc) + break; + + cpus_removed++; + } + + if (cpus_removed != cpus_to_remove) { + pr_warn("CPU hot-remove failed, adding back removed CPUs\n"); + + for (i = 0; i < cpus_removed; i++) + dlpar_cpu_add(cpu_drcs[i]); + + rc = -EINVAL; + } else { + rc = 0; + } + + kfree(cpu_drcs); + return rc; +} + +static int find_dlpar_cpus_to_add(u32 *cpu_drcs, u32 cpus_to_add) +{ + struct device_node *parent; + int cpus_found = 0; + int index, rc; + + parent = of_find_node_by_path("/cpus"); + if (!parent) { + pr_warn("Could not find CPU root node in device tree\n"); + kfree(cpu_drcs); + return -1; + } + + /* Search the ibm,drc-indexes array for possible CPU drcs to + * add. Note that the format of the ibm,drc-indexes array is + * the number of entries in the array followed by the array + * of drc values so we start looking at index = 1. + */ + index = 1; + while (cpus_found < cpus_to_add) { + u32 drc; + + rc = of_property_read_u32_index(parent, "ibm,drc-indexes", + index++, &drc); + if (rc) + break; + + if (dlpar_cpu_exists(parent, drc)) + continue; + + cpu_drcs[cpus_found++] = drc; + } + + of_node_put(parent); + return cpus_found; +} + +static int dlpar_cpu_add_by_count(u32 cpus_to_add) +{ + u32 *cpu_drcs; + int cpus_added = 0; + int cpus_found; + int i, rc; + + pr_debug("Attempting to hot-add %d CPUs\n", cpus_to_add); + + cpu_drcs = kcalloc(cpus_to_add, sizeof(*cpu_drcs), GFP_KERNEL); + if (!cpu_drcs) + return -EINVAL; + + cpus_found = find_dlpar_cpus_to_add(cpu_drcs, cpus_to_add); + if (cpus_found < cpus_to_add) { + pr_warn("Failed to find enough CPUs (%d of %d) to add\n", + cpus_found, cpus_to_add); + kfree(cpu_drcs); + return -EINVAL; + } + + for (i = 0; i < cpus_to_add; i++) { + rc = dlpar_cpu_add(cpu_drcs[i]); + if (rc) + break; + + cpus_added++; + } + + if (cpus_added < cpus_to_add) { + pr_warn("CPU hot-add failed, removing any added CPUs\n"); + + for (i = 0; i < cpus_added; i++) + dlpar_cpu_remove_by_index(cpu_drcs[i]); + + rc = -EINVAL; + } else { + rc = 0; + } + + kfree(cpu_drcs); + return rc; +} + +int dlpar_cpu(struct pseries_hp_errorlog *hp_elog) +{ + u32 count, drc_index; + int rc; + + count = hp_elog->_drc_u.drc_count; + drc_index = hp_elog->_drc_u.drc_index; + + lock_device_hotplug(); + + switch (hp_elog->action) { + case PSERIES_HP_ELOG_ACTION_REMOVE: + if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_COUNT) + rc = dlpar_cpu_remove_by_count(count); + else if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_INDEX) + rc = dlpar_cpu_remove_by_index(drc_index); + else + rc = -EINVAL; + break; + case PSERIES_HP_ELOG_ACTION_ADD: + if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_COUNT) + rc = dlpar_cpu_add_by_count(count); + else if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_INDEX) + rc = dlpar_cpu_add(drc_index); + else + rc = -EINVAL; + break; + default: + pr_err("Invalid action (%d) specified\n", hp_elog->action); + rc = -EINVAL; + break; + } + + unlock_device_hotplug(); + return rc; +} + +#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE + +static ssize_t dlpar_cpu_probe(const char *buf, size_t count) +{ + u32 drc_index; + int rc; + + rc = kstrtou32(buf, 0, &drc_index); + if (rc) + return -EINVAL; + + rc = dlpar_cpu_add(drc_index); + + return rc ? rc : count; +} + +static ssize_t dlpar_cpu_release(const char *buf, size_t count) +{ + struct device_node *dn; + u32 drc_index; + int rc; + + dn = of_find_node_by_path(buf); + if (!dn) + return -EINVAL; + + rc = of_property_read_u32(dn, "ibm,my-drc-index", &drc_index); + if (rc) { + of_node_put(dn); + return -EINVAL; + } + + rc = dlpar_cpu_remove(dn, drc_index); + of_node_put(dn); + + return rc ? rc : count; +} + +#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */ + static int pseries_smp_notifier(struct notifier_block *nb, unsigned long action, void *data) { @@ -385,6 +914,11 @@ static int __init pseries_cpu_hotplug_init(void) int cpu; int qcss_tok; +#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE + ppc_md.cpu_probe = dlpar_cpu_probe; + ppc_md.cpu_release = dlpar_cpu_release; +#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */ + for_each_node_by_name(np, "interrupt-controller") { typep = of_get_property(np, "compatible", NULL); if (strstr(typep, "open-pic")) { diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index b7a67e3d2201..477290ad855e 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -315,48 +315,48 @@ static long pSeries_lpar_hpte_updatepp(unsigned long slot, return 0; } -static unsigned long pSeries_lpar_hpte_getword0(unsigned long slot) +static long __pSeries_lpar_hpte_find(unsigned long want_v, unsigned long hpte_group) { - unsigned long dword0; - unsigned long lpar_rc; - unsigned long dummy_word1; - unsigned long flags; + long lpar_rc; + unsigned long i, j; + struct { + unsigned long pteh; + unsigned long ptel; + } ptes[4]; - /* Read 1 pte at a time */ - /* Do not need RPN to logical page translation */ - /* No cross CEC PFT access */ - flags = 0; + for (i = 0; i < HPTES_PER_GROUP; i += 4, hpte_group += 4) { - lpar_rc = plpar_pte_read(flags, slot, &dword0, &dummy_word1); + lpar_rc = plpar_pte_read_4(0, hpte_group, (void *)ptes); + if (lpar_rc != H_SUCCESS) + continue; - BUG_ON(lpar_rc != H_SUCCESS); + for (j = 0; j < 4; j++) { + if (HPTE_V_COMPARE(ptes[j].pteh, want_v) && + (ptes[j].pteh & HPTE_V_VALID)) + return i + j; + } + } - return dword0; + return -1; } static long pSeries_lpar_hpte_find(unsigned long vpn, int psize, int ssize) { - unsigned long hash; - unsigned long i; long slot; - unsigned long want_v, hpte_v; + unsigned long hash; + unsigned long want_v; + unsigned long hpte_group; hash = hpt_hash(vpn, mmu_psize_defs[psize].shift, ssize); want_v = hpte_encode_avpn(vpn, psize, ssize); /* Bolted entries are always in the primary group */ - slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; - for (i = 0; i < HPTES_PER_GROUP; i++) { - hpte_v = pSeries_lpar_hpte_getword0(slot); - - if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID)) - /* HPTE matches */ - return slot; - ++slot; - } - - return -1; -} + hpte_group = (hash & htab_hash_mask) * HPTES_PER_GROUP; + slot = __pSeries_lpar_hpte_find(want_v, hpte_group); + if (slot < 0) + return -1; + return hpte_group + slot; +} static void pSeries_lpar_hpte_updateboltedpp(unsigned long newpp, unsigned long ea, @@ -396,6 +396,7 @@ static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn, BUG_ON(lpar_rc != H_SUCCESS); } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * Limit iterations holding pSeries_lpar_tlbie_lock to 3. We also need * to make sure that we avoid bouncing the hypervisor tlbie lock. @@ -494,6 +495,15 @@ static void pSeries_lpar_hugepage_invalidate(unsigned long vsid, __pSeries_lpar_hugepage_invalidate(slot_array, vpn_array, index, psize, ssize); } +#else +static void pSeries_lpar_hugepage_invalidate(unsigned long vsid, + unsigned long addr, + unsigned char *hpte_slot_array, + int psize, int ssize, int local) +{ + WARN(1, "%s called without THP support\n", __func__); +} +#endif static void pSeries_lpar_hpte_removebolted(unsigned long ea, int psize, int ssize) diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h index 8411c27293e4..7aa83f00ac62 100644 --- a/arch/powerpc/platforms/pseries/pseries.h +++ b/arch/powerpc/platforms/pseries/pseries.h @@ -73,6 +73,15 @@ static inline int dlpar_memory(struct pseries_hp_errorlog *hp_elog) } #endif +#ifdef CONFIG_HOTPLUG_CPU +int dlpar_cpu(struct pseries_hp_errorlog *hp_elog); +#else +static inline int dlpar_cpu(struct pseries_hp_errorlog *hp_elog) +{ + return -EOPNOTSUPP; +} +#endif + /* PCI root bridge prepare function override for pseries */ struct pci_host_bridge; int pseries_root_bridge_prepare(struct pci_host_bridge *bridge); diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index 3b6647e574b6..9a3e27b863ce 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -40,6 +40,9 @@ static int ras_check_exception_token; #define EPOW_SENSOR_TOKEN 9 #define EPOW_SENSOR_INDEX 0 +/* EPOW events counter variable */ +static int num_epow_events; + static irqreturn_t ras_epow_interrupt(int irq, void *dev_id); static irqreturn_t ras_error_interrupt(int irq, void *dev_id); @@ -82,32 +85,30 @@ static void handle_system_shutdown(char event_modifier) { switch (event_modifier) { case EPOW_SHUTDOWN_NORMAL: - pr_emerg("Firmware initiated power off"); + pr_emerg("Power off requested\n"); orderly_poweroff(true); break; case EPOW_SHUTDOWN_ON_UPS: - pr_emerg("Loss of power reported by firmware, system is " - "running on UPS/battery"); - pr_emerg("Check RTAS error log for details"); + pr_emerg("Loss of system power detected. System is running on" + " UPS/battery. Check RTAS error log for details\n"); orderly_poweroff(true); break; case EPOW_SHUTDOWN_LOSS_OF_CRITICAL_FUNCTIONS: - pr_emerg("Loss of system critical functions reported by " - "firmware"); - pr_emerg("Check RTAS error log for details"); + pr_emerg("Loss of system critical functions detected. Check" + " RTAS error log for details\n"); orderly_poweroff(true); break; case EPOW_SHUTDOWN_AMBIENT_TEMPERATURE_TOO_HIGH: - pr_emerg("Ambient temperature too high reported by firmware"); - pr_emerg("Check RTAS error log for details"); + pr_emerg("High ambient temperature detected. Check RTAS" + " error log for details\n"); orderly_poweroff(true); break; default: - pr_err("Unknown power/cooling shutdown event (modifier %d)", + pr_err("Unknown power/cooling shutdown event (modifier = %d)\n", event_modifier); } } @@ -145,17 +146,20 @@ static void rtas_parse_epow_errlog(struct rtas_error_log *log) switch (action_code) { case EPOW_RESET: - pr_err("Non critical power or cooling issue cleared"); + if (num_epow_events) { + pr_info("Non critical power/cooling issue cleared\n"); + num_epow_events--; + } break; case EPOW_WARN_COOLING: - pr_err("Non critical cooling issue reported by firmware"); - pr_err("Check RTAS error log for details"); + pr_info("Non-critical cooling issue detected. Check RTAS error" + " log for details\n"); break; case EPOW_WARN_POWER: - pr_err("Non critical power issue reported by firmware"); - pr_err("Check RTAS error log for details"); + pr_info("Non-critical power issue detected. Check RTAS error" + " log for details\n"); break; case EPOW_SYSTEM_SHUTDOWN: @@ -163,23 +167,27 @@ static void rtas_parse_epow_errlog(struct rtas_error_log *log) break; case EPOW_SYSTEM_HALT: - pr_emerg("Firmware initiated power off"); + pr_emerg("Critical power/cooling issue detected. Check RTAS" + " error log for details. Powering off.\n"); orderly_poweroff(true); break; case EPOW_MAIN_ENCLOSURE: case EPOW_POWER_OFF: - pr_emerg("Critical power/cooling issue reported by firmware"); - pr_emerg("Check RTAS error log for details"); - pr_emerg("Immediate power off"); + pr_emerg("System about to lose power. Check RTAS error log " + " for details. Powering off immediately.\n"); emergency_sync(); kernel_power_off(); break; default: - pr_err("Unknown power/cooling event (action code %d)", + pr_err("Unknown power/cooling event (action code = %d)\n", action_code); } + + /* Increment epow events counter variable */ + if (action_code != EPOW_RESET) + num_epow_events++; } /* Handle environmental and power warning (EPOW) interrupts. */ @@ -249,13 +257,12 @@ static irqreturn_t ras_error_interrupt(int irq, void *dev_id) log_error(ras_log_buf, ERR_TYPE_RTAS_LOG, fatal); if (fatal) { - pr_emerg("Fatal hardware error reported by firmware"); - pr_emerg("Check RTAS error log for details"); - pr_emerg("Immediate power off"); + pr_emerg("Fatal hardware error detected. Check RTAS error" + " log for details. Powering off immediately\n"); emergency_sync(); kernel_power_off(); } else { - pr_err("Recoverable hardware error reported by firmware"); + pr_err("Recoverable hardware error detected\n"); } spin_unlock(&ras_log_buf_lock); diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile index 5b492a6438ff..bd6bd729969c 100644 --- a/arch/powerpc/sysdev/Makefile +++ b/arch/powerpc/sysdev/Makefile @@ -26,7 +26,6 @@ obj-$(CONFIG_FSL_85XX_CACHE_SRAM) += fsl_85xx_l2ctlr.o fsl_85xx_cache_sram.o obj-$(CONFIG_SIMPLE_GPIO) += simple_gpio.o obj-$(CONFIG_FSL_RIO) += fsl_rio.o fsl_rmu.o obj-$(CONFIG_TSI108_BRIDGE) += tsi108_pci.o tsi108_dev.o -obj-$(CONFIG_QUICC_ENGINE) += qe_lib/ mv64x60-$(CONFIG_PCI) += mv64x60_pci.o obj-$(CONFIG_MV64X60) += $(mv64x60-y) mv64x60_pic.o mv64x60_dev.o \ mv64x60_udbg.o diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c index 7a399b4d60a0..c713b349d967 100644 --- a/arch/powerpc/sysdev/axonram.c +++ b/arch/powerpc/sysdev/axonram.c @@ -313,6 +313,7 @@ static const struct of_device_id axon_ram_device_id[] = { }, {} }; +MODULE_DEVICE_TABLE(of, axon_ram_device_id); static struct platform_driver axon_ram_driver = { .probe = axon_ram_probe, diff --git a/arch/powerpc/sysdev/cpm_common.c b/arch/powerpc/sysdev/cpm_common.c index e00a5ee58fd7..9d32465eddb1 100644 --- a/arch/powerpc/sysdev/cpm_common.c +++ b/arch/powerpc/sysdev/cpm_common.c @@ -27,8 +27,8 @@ #include <asm/udbg.h> #include <asm/io.h> -#include <asm/rheap.h> #include <asm/cpm.h> +#include <soc/fsl/qe/qe.h> #include <mm/mmu_decl.h> @@ -65,162 +65,6 @@ void __init udbg_init_cpm(void) } #endif -static spinlock_t cpm_muram_lock; -static rh_block_t cpm_boot_muram_rh_block[16]; -static rh_info_t cpm_muram_info; -static u8 __iomem *muram_vbase; -static phys_addr_t muram_pbase; - -/* Max address size we deal with */ -#define OF_MAX_ADDR_CELLS 4 - -int cpm_muram_init(void) -{ - struct device_node *np; - struct resource r; - u32 zero[OF_MAX_ADDR_CELLS] = {}; - resource_size_t max = 0; - int i = 0; - int ret = 0; - - if (muram_pbase) - return 0; - - spin_lock_init(&cpm_muram_lock); - /* initialize the info header */ - rh_init(&cpm_muram_info, 1, - sizeof(cpm_boot_muram_rh_block) / - sizeof(cpm_boot_muram_rh_block[0]), - cpm_boot_muram_rh_block); - - np = of_find_compatible_node(NULL, NULL, "fsl,cpm-muram-data"); - if (!np) { - /* try legacy bindings */ - np = of_find_node_by_name(NULL, "data-only"); - if (!np) { - printk(KERN_ERR "Cannot find CPM muram data node"); - ret = -ENODEV; - goto out; - } - } - - muram_pbase = of_translate_address(np, zero); - if (muram_pbase == (phys_addr_t)OF_BAD_ADDR) { - printk(KERN_ERR "Cannot translate zero through CPM muram node"); - ret = -ENODEV; - goto out; - } - - while (of_address_to_resource(np, i++, &r) == 0) { - if (r.end > max) - max = r.end; - - rh_attach_region(&cpm_muram_info, r.start - muram_pbase, - resource_size(&r)); - } - - muram_vbase = ioremap(muram_pbase, max - muram_pbase + 1); - if (!muram_vbase) { - printk(KERN_ERR "Cannot map CPM muram"); - ret = -ENOMEM; - } - -out: - of_node_put(np); - return ret; -} - -/** - * cpm_muram_alloc - allocate the requested size worth of multi-user ram - * @size: number of bytes to allocate - * @align: requested alignment, in bytes - * - * This function returns an offset into the muram area. - * Use cpm_dpram_addr() to get the virtual address of the area. - * Use cpm_muram_free() to free the allocation. - */ -unsigned long cpm_muram_alloc(unsigned long size, unsigned long align) -{ - unsigned long start; - unsigned long flags; - - spin_lock_irqsave(&cpm_muram_lock, flags); - cpm_muram_info.alignment = align; - start = rh_alloc(&cpm_muram_info, size, "commproc"); - if (!IS_ERR_VALUE(start)) - memset_io(cpm_muram_addr(start), 0, size); - spin_unlock_irqrestore(&cpm_muram_lock, flags); - - return start; -} -EXPORT_SYMBOL(cpm_muram_alloc); - -/** - * cpm_muram_free - free a chunk of multi-user ram - * @offset: The beginning of the chunk as returned by cpm_muram_alloc(). - */ -int cpm_muram_free(unsigned long offset) -{ - int ret; - unsigned long flags; - - spin_lock_irqsave(&cpm_muram_lock, flags); - ret = rh_free(&cpm_muram_info, offset); - spin_unlock_irqrestore(&cpm_muram_lock, flags); - - return ret; -} -EXPORT_SYMBOL(cpm_muram_free); - -/** - * cpm_muram_alloc_fixed - reserve a specific region of multi-user ram - * @offset: the offset into the muram area to reserve - * @size: the number of bytes to reserve - * - * This function returns "start" on success, -ENOMEM on failure. - * Use cpm_dpram_addr() to get the virtual address of the area. - * Use cpm_muram_free() to free the allocation. - */ -unsigned long cpm_muram_alloc_fixed(unsigned long offset, unsigned long size) -{ - unsigned long start; - unsigned long flags; - - spin_lock_irqsave(&cpm_muram_lock, flags); - cpm_muram_info.alignment = 1; - start = rh_alloc_fixed(&cpm_muram_info, offset, size, "commproc"); - spin_unlock_irqrestore(&cpm_muram_lock, flags); - - return start; -} -EXPORT_SYMBOL(cpm_muram_alloc_fixed); - -/** - * cpm_muram_addr - turn a muram offset into a virtual address - * @offset: muram offset to convert - */ -void __iomem *cpm_muram_addr(unsigned long offset) -{ - return muram_vbase + offset; -} -EXPORT_SYMBOL(cpm_muram_addr); - -unsigned long cpm_muram_offset(void __iomem *addr) -{ - return addr - (void __iomem *)muram_vbase; -} -EXPORT_SYMBOL(cpm_muram_offset); - -/** - * cpm_muram_dma - turn a muram virtual address into a DMA address - * @offset: virtual address from cpm_muram_addr() to convert - */ -dma_addr_t cpm_muram_dma(void __iomem *addr) -{ - return muram_pbase + ((u8 __iomem *)addr - muram_vbase); -} -EXPORT_SYMBOL(cpm_muram_dma); - #if defined(CONFIG_CPM2) || defined(CONFIG_8xx_GPIO) struct cpm2_ioports { diff --git a/arch/powerpc/sysdev/fsl_lbc.c b/arch/powerpc/sysdev/fsl_lbc.c index 38138cf8d33e..47f781059eeb 100644 --- a/arch/powerpc/sysdev/fsl_lbc.c +++ b/arch/powerpc/sysdev/fsl_lbc.c @@ -243,8 +243,6 @@ static irqreturn_t fsl_lbc_ctrl_irq(int irqno, void *data) if (status & LTESR_CS) dev_err(ctrl->dev, "Chip select error: " "LTESR 0x%08X\n", status); - if (status & LTESR_UPM) - ; if (status & LTESR_FCT) { dev_err(ctrl->dev, "FCM command time-out: " "LTESR 0x%08X\n", status); diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c index a1ac80b3041a..c69e88e91459 100644 --- a/arch/powerpc/sysdev/fsl_pci.c +++ b/arch/powerpc/sysdev/fsl_pci.c @@ -218,6 +218,19 @@ static void setup_pci_atmu(struct pci_controller *hose) */ setup_inbound = !is_kdump(); + if (of_device_is_compatible(hose->dn, "fsl,bsc9132-pcie")) { + /* + * BSC9132 Rev1.0 has an issue where all the PEX inbound + * windows have implemented the default target value as 0xf + * for CCSR space.In all Freescale legacy devices the target + * of 0xf is reserved for local memory space. 9132 Rev1.0 + * now has local mempry space mapped to target 0x0 instead of + * 0xf. Hence adding a workaround to remove the target 0xf + * defined for memory space from Inbound window attributes. + */ + piwar &= ~PIWAR_TGI_LOCAL; + } + if (early_find_capability(hose, 0, 0, PCI_CAP_ID_EXP)) { if (in_be32(&pci->block_rev1) >= PCIE_IP_REV_2_2) { win_idx = 2; diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 786bf01691c9..07a8508cb7fa 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -320,6 +320,7 @@ static inline void disable_surveillance(void) #ifdef CONFIG_PPC_PSERIES /* Since this can't be a module, args should end up below 4GB. */ static struct rtas_args args; + int token; /* * At this point we have got all the cpus we can into @@ -328,17 +329,12 @@ static inline void disable_surveillance(void) * If we did try to take rtas.lock there would be a * real possibility of deadlock. */ - args.token = rtas_token("set-indicator"); - if (args.token == RTAS_UNKNOWN_SERVICE) + token = rtas_token("set-indicator"); + if (token == RTAS_UNKNOWN_SERVICE) return; - args.token = cpu_to_be32(args.token); - args.nargs = cpu_to_be32(3); - args.nret = cpu_to_be32(1); - args.rets = &args.args[3]; - args.args[0] = cpu_to_be32(SURVEILLANCE_TOKEN); - args.args[1] = 0; - args.args[2] = 0; - enter_rtas(__pa(&args)); + + rtas_call_unlocked(&args, token, 3, 1, NULL, SURVEILLANCE_TOKEN, 0, 0); + #endif /* CONFIG_PPC_PSERIES */ } @@ -1522,6 +1518,8 @@ static void excprint(struct pt_regs *fp) if (trap == 0x700) print_bug_trap(fp); + + printf(linux_banner); } static void prregs(struct pt_regs *fp) diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index 0c1a679314dd..7873e171457c 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -159,11 +159,11 @@ int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, /* Increase core size by size of got & plt and set start offsets for got and plt. */ - me->core_size = ALIGN(me->core_size, 4); - me->arch.got_offset = me->core_size; - me->core_size += me->arch.got_size; - me->arch.plt_offset = me->core_size; - me->core_size += me->arch.plt_size; + me->core_layout.size = ALIGN(me->core_layout.size, 4); + me->arch.got_offset = me->core_layout.size; + me->core_layout.size += me->arch.got_size; + me->arch.plt_offset = me->core_layout.size; + me->core_layout.size += me->arch.plt_size; return 0; } @@ -279,7 +279,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, if (info->got_initialized == 0) { Elf_Addr *gotent; - gotent = me->module_core + me->arch.got_offset + + gotent = me->core_layout.base + me->arch.got_offset + info->got_offset; *gotent = val; info->got_initialized = 1; @@ -302,7 +302,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, rc = apply_rela_bits(loc, val, 0, 64, 0); else if (r_type == R_390_GOTENT || r_type == R_390_GOTPLTENT) { - val += (Elf_Addr) me->module_core - loc; + val += (Elf_Addr) me->core_layout.base - loc; rc = apply_rela_bits(loc, val, 1, 32, 1); } break; @@ -315,7 +315,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, case R_390_PLTOFF64: /* 16 bit offset from GOT to PLT. */ if (info->plt_initialized == 0) { unsigned int *ip; - ip = me->module_core + me->arch.plt_offset + + ip = me->core_layout.base + me->arch.plt_offset + info->plt_offset; ip[0] = 0x0d10e310; /* basr 1,0; lg 1,10(1); br 1 */ ip[1] = 0x100a0004; @@ -334,7 +334,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, val - loc + 0xffffUL < 0x1ffffeUL) || (r_type == R_390_PLT32DBL && val - loc + 0xffffffffULL < 0x1fffffffeULL))) - val = (Elf_Addr) me->module_core + + val = (Elf_Addr) me->core_layout.base + me->arch.plt_offset + info->plt_offset; val += rela->r_addend - loc; @@ -356,7 +356,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, case R_390_GOTOFF32: /* 32 bit offset to GOT. */ case R_390_GOTOFF64: /* 64 bit offset to GOT. */ val = val + rela->r_addend - - ((Elf_Addr) me->module_core + me->arch.got_offset); + ((Elf_Addr) me->core_layout.base + me->arch.got_offset); if (r_type == R_390_GOTOFF16) rc = apply_rela_bits(loc, val, 0, 16, 0); else if (r_type == R_390_GOTOFF32) @@ -366,7 +366,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, break; case R_390_GOTPC: /* 32 bit PC relative offset to GOT. */ case R_390_GOTPCDBL: /* 32 bit PC rel. off. to GOT shifted by 1. */ - val = (Elf_Addr) me->module_core + me->arch.got_offset + + val = (Elf_Addr) me->core_layout.base + me->arch.got_offset + rela->r_addend - loc; if (r_type == R_390_GOTPC) rc = apply_rela_bits(loc, val, 1, 32, 0); diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 63b039899a5e..aa34af0a0b26 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -603,10 +603,7 @@ static void gmap_zap_swap_entry(swp_entry_t entry, struct mm_struct *mm) else if (is_migration_entry(entry)) { struct page *page = migration_entry_to_page(entry); - if (PageAnon(page)) - dec_mm_counter(mm, MM_ANONPAGES); - else - dec_mm_counter(mm, MM_FILEPAGES); + dec_mm_counter(mm, mm_counter(page)); } free_swap_and_cache(entry); } diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 5d2293417946..24f362bf3ec6 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -83,6 +83,8 @@ config X86 select HAVE_ARCH_KASAN if X86_64 && SPARSEMEM_VMEMMAP select HAVE_ARCH_KGDB select HAVE_ARCH_KMEMCHECK + select HAVE_ARCH_MMAP_RND_BITS if MMU + select HAVE_ARCH_MMAP_RND_COMPAT_BITS if MMU && COMPAT select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_SOFT_DIRTY if X86_64 select HAVE_ARCH_TRACEHOOK @@ -184,6 +186,20 @@ config HAVE_LATENCYTOP_SUPPORT config MMU def_bool y +config ARCH_MMAP_RND_BITS_MIN + default 28 if 64BIT + default 8 + +config ARCH_MMAP_RND_BITS_MAX + default 32 if 64BIT + default 16 + +config ARCH_MMAP_RND_COMPAT_BITS_MIN + default 8 + +config ARCH_MMAP_RND_COMPAT_BITS_MAX + default 16 + config SBUS bool diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c index 8602f06c759f..1a50e09c945b 100644 --- a/arch/x86/entry/vdso/vclock_gettime.c +++ b/arch/x86/entry/vdso/vclock_gettime.c @@ -126,23 +126,23 @@ static notrace cycle_t vread_pvclock(int *mode) * * On Xen, we don't appear to have that guarantee, but Xen still * supplies a valid seqlock using the version field. - + * * We only do pvclock vdso timing at all if * PVCLOCK_TSC_STABLE_BIT is set, and we interpret that bit to * mean that all vCPUs have matching pvti and that the TSC is * synced, so we can just look at vCPU 0's pvti. */ - if (unlikely(!(pvti->flags & PVCLOCK_TSC_STABLE_BIT))) { - *mode = VCLOCK_NONE; - return 0; - } - do { version = pvti->version; smp_rmb(); + if (unlikely(!(pvti->flags & PVCLOCK_TSC_STABLE_BIT))) { + *mode = VCLOCK_NONE; + return 0; + } + tsc = rdtsc_ordered(); pvti_tsc_to_system_mul = pvti->tsc_to_system_mul; pvti_tsc_shift = pvti->tsc_shift; diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h index 4fa687a47a62..6b8d6e8cd449 100644 --- a/arch/x86/include/asm/boot.h +++ b/arch/x86/include/asm/boot.h @@ -27,7 +27,7 @@ #define BOOT_HEAP_SIZE 0x400000 #else /* !CONFIG_KERNEL_BZIP2 */ -#define BOOT_HEAP_SIZE 0x8000 +#define BOOT_HEAP_SIZE 0x10000 #endif /* !CONFIG_KERNEL_BZIP2 */ diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index eadcdd5bb946..0fd440df63f1 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -42,6 +42,7 @@ extern void fpu__init_cpu_xstate(void); extern void fpu__init_system(struct cpuinfo_x86 *c); extern void fpu__init_check_bugs(void); extern void fpu__resume_cpu(void); +extern u64 fpu__get_supported_xfeatures_mask(void); /* * Debugging facility: diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index 3a6c89b70307..af30fdeb140d 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -20,15 +20,16 @@ /* Supported features which support lazy state saving */ #define XFEATURE_MASK_LAZY (XFEATURE_MASK_FP | \ - XFEATURE_MASK_SSE | \ + XFEATURE_MASK_SSE) + +/* Supported features which require eager state saving */ +#define XFEATURE_MASK_EAGER (XFEATURE_MASK_BNDREGS | \ + XFEATURE_MASK_BNDCSR | \ XFEATURE_MASK_YMM | \ - XFEATURE_MASK_OPMASK | \ + XFEATURE_MASK_OPMASK | \ XFEATURE_MASK_ZMM_Hi256 | \ XFEATURE_MASK_Hi16_ZMM) -/* Supported features which require eager state saving */ -#define XFEATURE_MASK_EAGER (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR) - /* All currently supported features */ #define XCNTXT_MASK (XFEATURE_MASK_LAZY | XFEATURE_MASK_EAGER) diff --git a/arch/x86/include/asm/lguest.h b/arch/x86/include/asm/lguest.h index 3bbc07a57a31..73d0c9b92087 100644 --- a/arch/x86/include/asm/lguest.h +++ b/arch/x86/include/asm/lguest.h @@ -12,7 +12,9 @@ #define GUEST_PL 1 /* Page for Switcher text itself, then two pages per cpu */ -#define TOTAL_SWITCHER_PAGES (1 + 2 * nr_cpu_ids) +#define SWITCHER_TEXT_PAGES (1) +#define SWITCHER_STACK_PAGES (2 * nr_cpu_ids) +#define TOTAL_SWITCHER_PAGES (SWITCHER_TEXT_PAGES + SWITCHER_STACK_PAGES) /* Where we map the Switcher, in both Host and Guest. */ extern unsigned long switcher_addr; diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 379cd3658799..bfd9b2a35a0b 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -116,8 +116,36 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, #endif cpumask_set_cpu(cpu, mm_cpumask(next)); - /* Re-load page tables */ + /* + * Re-load page tables. + * + * This logic has an ordering constraint: + * + * CPU 0: Write to a PTE for 'next' + * CPU 0: load bit 1 in mm_cpumask. if nonzero, send IPI. + * CPU 1: set bit 1 in next's mm_cpumask + * CPU 1: load from the PTE that CPU 0 writes (implicit) + * + * We need to prevent an outcome in which CPU 1 observes + * the new PTE value and CPU 0 observes bit 1 clear in + * mm_cpumask. (If that occurs, then the IPI will never + * be sent, and CPU 0's TLB will contain a stale entry.) + * + * The bad outcome can occur if either CPU's load is + * reordered before that CPU's store, so both CPUs must + * execute full barriers to prevent this from happening. + * + * Thus, switch_mm needs a full barrier between the + * store to mm_cpumask and any operation that could load + * from next->pgd. TLB fills are special and can happen + * due to instruction fetches or for no reason at all, + * and neither LOCK nor MFENCE orders them. + * Fortunately, load_cr3() is serializing and gives the + * ordering guarantee we need. + * + */ load_cr3(next->pgd); + trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); /* Stop flush ipis for the previous mm */ @@ -156,10 +184,14 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, * schedule, protecting us from simultaneous changes. */ cpumask_set_cpu(cpu, mm_cpumask(next)); + /* * We were in lazy tlb mode and leave_mm disabled * tlb flush IPI delivery. We must reload CR3 * to make sure to use no freed page tables. + * + * As above, load_cr3() is serializing and orders TLB + * fills with respect to the mm_cpumask write. */ load_cr3(next->pgd); trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index e678ddeed030..a07956a08936 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -434,8 +434,7 @@ static void srat_detect_node(struct cpuinfo_x86 *c) */ int ht_nodeid = c->initial_apicid; - if (ht_nodeid >= 0 && - __apicid_to_node[ht_nodeid] != NUMA_NO_NODE) + if (__apicid_to_node[ht_nodeid] != NUMA_NO_NODE) node = __apicid_to_node[ht_nodeid]; /* Pick a nearby node */ if (!node_online(node)) diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 7b2978ab30df..6d9f0a7ef4c8 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -3,8 +3,11 @@ */ #include <asm/fpu/internal.h> #include <asm/tlbflush.h> +#include <asm/setup.h> +#include <asm/cmdline.h> #include <linux/sched.h> +#include <linux/init.h> /* * Initialize the TS bit in CR0 according to the style of context-switches @@ -270,20 +273,52 @@ static void __init fpu__init_system_xstate_size_legacy(void) */ static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO; -static int __init eager_fpu_setup(char *s) +/* + * Find supported xfeatures based on cpu features and command-line input. + * This must be called after fpu__init_parse_early_param() is called and + * xfeatures_mask is enumerated. + */ +u64 __init fpu__get_supported_xfeatures_mask(void) { - if (!strcmp(s, "on")) - eagerfpu = ENABLE; - else if (!strcmp(s, "off")) - eagerfpu = DISABLE; - else if (!strcmp(s, "auto")) - eagerfpu = AUTO; - return 1; + /* Support all xfeatures known to us */ + if (eagerfpu != DISABLE) + return XCNTXT_MASK; + + /* Warning of xfeatures being disabled for no eagerfpu mode */ + if (xfeatures_mask & XFEATURE_MASK_EAGER) { + pr_err("x86/fpu: eagerfpu switching disabled, disabling the following xstate features: 0x%llx.\n", + xfeatures_mask & XFEATURE_MASK_EAGER); + } + + /* Return a mask that masks out all features requiring eagerfpu mode */ + return ~XFEATURE_MASK_EAGER; +} + +/* + * Disable features dependent on eagerfpu. + */ +static void __init fpu__clear_eager_fpu_features(void) +{ + setup_clear_cpu_cap(X86_FEATURE_MPX); + setup_clear_cpu_cap(X86_FEATURE_AVX); + setup_clear_cpu_cap(X86_FEATURE_AVX2); + setup_clear_cpu_cap(X86_FEATURE_AVX512F); + setup_clear_cpu_cap(X86_FEATURE_AVX512PF); + setup_clear_cpu_cap(X86_FEATURE_AVX512ER); + setup_clear_cpu_cap(X86_FEATURE_AVX512CD); } -__setup("eagerfpu=", eager_fpu_setup); /* * Pick the FPU context switching strategy: + * + * When eagerfpu is AUTO or ENABLE, we ensure it is ENABLE if either of + * the following is true: + * + * (1) the cpu has xsaveopt, as it has the optimization and doing eager + * FPU switching has a relatively low cost compared to a plain xsave; + * (2) the cpu has xsave features (e.g. MPX) that depend on eager FPU + * switching. Should the kernel boot with noxsaveopt, we support MPX + * with eager FPU switching at a higher cost. */ static void __init fpu__init_system_ctx_switch(void) { @@ -295,19 +330,11 @@ static void __init fpu__init_system_ctx_switch(void) WARN_ON_FPU(current->thread.fpu.fpstate_active); current_thread_info()->status = 0; - /* Auto enable eagerfpu for xsaveopt */ if (boot_cpu_has(X86_FEATURE_XSAVEOPT) && eagerfpu != DISABLE) eagerfpu = ENABLE; - if (xfeatures_mask & XFEATURE_MASK_EAGER) { - if (eagerfpu == DISABLE) { - pr_err("x86/fpu: eagerfpu switching disabled, disabling the following xstate features: 0x%llx.\n", - xfeatures_mask & XFEATURE_MASK_EAGER); - xfeatures_mask &= ~XFEATURE_MASK_EAGER; - } else { - eagerfpu = ENABLE; - } - } + if (xfeatures_mask & XFEATURE_MASK_EAGER) + eagerfpu = ENABLE; if (eagerfpu == ENABLE) setup_force_cpu_cap(X86_FEATURE_EAGER_FPU); @@ -316,11 +343,48 @@ static void __init fpu__init_system_ctx_switch(void) } /* + * We parse fpu parameters early because fpu__init_system() is executed + * before parse_early_param(). + */ +static void __init fpu__init_parse_early_param(void) +{ + /* + * No need to check "eagerfpu=auto" again, since it is the + * initial default. + */ + if (cmdline_find_option_bool(boot_command_line, "eagerfpu=off")) { + eagerfpu = DISABLE; + fpu__clear_eager_fpu_features(); + } else if (cmdline_find_option_bool(boot_command_line, "eagerfpu=on")) { + eagerfpu = ENABLE; + } + + if (cmdline_find_option_bool(boot_command_line, "no387")) + setup_clear_cpu_cap(X86_FEATURE_FPU); + + if (cmdline_find_option_bool(boot_command_line, "nofxsr")) { + setup_clear_cpu_cap(X86_FEATURE_FXSR); + setup_clear_cpu_cap(X86_FEATURE_FXSR_OPT); + setup_clear_cpu_cap(X86_FEATURE_XMM); + } + + if (cmdline_find_option_bool(boot_command_line, "noxsave")) + fpu__xstate_clear_all_cpu_caps(); + + if (cmdline_find_option_bool(boot_command_line, "noxsaveopt")) + setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); + + if (cmdline_find_option_bool(boot_command_line, "noxsaves")) + setup_clear_cpu_cap(X86_FEATURE_XSAVES); +} + +/* * Called on the boot CPU once per system bootup, to set up the initial * FPU state that is later cloned into all processes: */ void __init fpu__init_system(struct cpuinfo_x86 *c) { + fpu__init_parse_early_param(); fpu__init_system_early_generic(c); /* @@ -344,62 +408,3 @@ void __init fpu__init_system(struct cpuinfo_x86 *c) fpu__init_system_ctx_switch(); } - -/* - * Boot parameter to turn off FPU support and fall back to math-emu: - */ -static int __init no_387(char *s) -{ - setup_clear_cpu_cap(X86_FEATURE_FPU); - return 1; -} -__setup("no387", no_387); - -/* - * Disable all xstate CPU features: - */ -static int __init x86_noxsave_setup(char *s) -{ - if (strlen(s)) - return 0; - - fpu__xstate_clear_all_cpu_caps(); - - return 1; -} -__setup("noxsave", x86_noxsave_setup); - -/* - * Disable the XSAVEOPT instruction specifically: - */ -static int __init x86_noxsaveopt_setup(char *s) -{ - setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); - - return 1; -} -__setup("noxsaveopt", x86_noxsaveopt_setup); - -/* - * Disable the XSAVES instruction: - */ -static int __init x86_noxsaves_setup(char *s) -{ - setup_clear_cpu_cap(X86_FEATURE_XSAVES); - - return 1; -} -__setup("noxsaves", x86_noxsaves_setup); - -/* - * Disable FX save/restore and SSE support: - */ -static int __init x86_nofxsr_setup(char *s) -{ - setup_clear_cpu_cap(X86_FEATURE_FXSR); - setup_clear_cpu_cap(X86_FEATURE_FXSR_OPT); - setup_clear_cpu_cap(X86_FEATURE_XMM); - - return 1; -} -__setup("nofxsr", x86_nofxsr_setup); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 40f100285984..d425cda5ae6d 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -52,6 +52,7 @@ void fpu__xstate_clear_all_cpu_caps(void) setup_clear_cpu_cap(X86_FEATURE_AVX512ER); setup_clear_cpu_cap(X86_FEATURE_AVX512CD); setup_clear_cpu_cap(X86_FEATURE_MPX); + setup_clear_cpu_cap(X86_FEATURE_XGETBV1); } /* @@ -632,8 +633,7 @@ void __init fpu__init_system_xstate(void) BUG(); } - /* Support only the state known to the OS: */ - xfeatures_mask = xfeatures_mask & XCNTXT_MASK; + xfeatures_mask &= fpu__get_supported_xfeatures_mask(); /* Enable xstate instructions to be able to continue with initialization: */ fpu__init_cpu_xstate(); diff --git a/arch/x86/kernel/livepatch.c b/arch/x86/kernel/livepatch.c index d1d35ccffed3..92fc1a51f994 100644 --- a/arch/x86/kernel/livepatch.c +++ b/arch/x86/kernel/livepatch.c @@ -20,8 +20,6 @@ #include <linux/module.h> #include <linux/uaccess.h> -#include <asm/cacheflush.h> -#include <asm/page_types.h> #include <asm/elf.h> #include <asm/livepatch.h> @@ -38,11 +36,10 @@ int klp_write_module_reloc(struct module *mod, unsigned long type, unsigned long loc, unsigned long value) { - int ret, numpages, size = 4; - bool readonly; + size_t size = 4; unsigned long val; - unsigned long core = (unsigned long)mod->module_core; - unsigned long core_size = mod->core_size; + unsigned long core = (unsigned long)mod->core_layout.base; + unsigned long core_size = mod->core_layout.size; switch (type) { case R_X86_64_NONE: @@ -69,23 +66,5 @@ int klp_write_module_reloc(struct module *mod, unsigned long type, /* loc does not point to any symbol inside the module */ return -EINVAL; - readonly = false; - -#ifdef CONFIG_DEBUG_SET_MODULE_RONX - if (loc < core + mod->core_ro_size) - readonly = true; -#endif - - /* determine if the relocation spans a page boundary */ - numpages = ((loc & PAGE_MASK) == ((loc + size) & PAGE_MASK)) ? 1 : 2; - - if (readonly) - set_memory_rw(loc & PAGE_MASK, numpages); - - ret = probe_kernel_write((void *)loc, &val, size); - - if (readonly) - set_memory_ro(loc & PAGE_MASK, numpages); - - return ret; + return probe_kernel_write((void *)loc, &val, size); } diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index d64889aa2d46..ab0adc0fa5db 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -182,6 +182,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "iMac9,1"), }, }, + { /* Handle problems with rebooting on the iMac10,1. */ + .callback = set_pci_reboot, + .ident = "Apple iMac10,1", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "iMac10,1"), + }, + }, /* ASRock */ { /* Handle problems with rebooting on ASRock Q1900DC-ITX */ diff --git a/arch/x86/kernel/verify_cpu.S b/arch/x86/kernel/verify_cpu.S index 4cf401f581e7..07efb35ee4bc 100644 --- a/arch/x86/kernel/verify_cpu.S +++ b/arch/x86/kernel/verify_cpu.S @@ -48,31 +48,31 @@ verify_cpu: pushfl popl %eax cmpl %eax,%ebx - jz verify_cpu_no_longmode # cpu has no cpuid + jz .Lverify_cpu_no_longmode # cpu has no cpuid #endif movl $0x0,%eax # See if cpuid 1 is implemented cpuid cmpl $0x1,%eax - jb verify_cpu_no_longmode # no cpuid 1 + jb .Lverify_cpu_no_longmode # no cpuid 1 xor %di,%di cmpl $0x68747541,%ebx # AuthenticAMD - jnz verify_cpu_noamd + jnz .Lverify_cpu_noamd cmpl $0x69746e65,%edx - jnz verify_cpu_noamd + jnz .Lverify_cpu_noamd cmpl $0x444d4163,%ecx - jnz verify_cpu_noamd + jnz .Lverify_cpu_noamd mov $1,%di # cpu is from AMD - jmp verify_cpu_check + jmp .Lverify_cpu_check -verify_cpu_noamd: +.Lverify_cpu_noamd: cmpl $0x756e6547,%ebx # GenuineIntel? - jnz verify_cpu_check + jnz .Lverify_cpu_check cmpl $0x49656e69,%edx - jnz verify_cpu_check + jnz .Lverify_cpu_check cmpl $0x6c65746e,%ecx - jnz verify_cpu_check + jnz .Lverify_cpu_check # only call IA32_MISC_ENABLE when: # family > 6 || (family == 6 && model >= 0xd) @@ -83,59 +83,59 @@ verify_cpu_noamd: andl $0x0ff00f00, %eax # mask family and extended family shrl $8, %eax cmpl $6, %eax - ja verify_cpu_clear_xd # family > 6, ok - jb verify_cpu_check # family < 6, skip + ja .Lverify_cpu_clear_xd # family > 6, ok + jb .Lverify_cpu_check # family < 6, skip andl $0x000f00f0, %ecx # mask model and extended model shrl $4, %ecx cmpl $0xd, %ecx - jb verify_cpu_check # family == 6, model < 0xd, skip + jb .Lverify_cpu_check # family == 6, model < 0xd, skip -verify_cpu_clear_xd: +.Lverify_cpu_clear_xd: movl $MSR_IA32_MISC_ENABLE, %ecx rdmsr btrl $2, %edx # clear MSR_IA32_MISC_ENABLE_XD_DISABLE - jnc verify_cpu_check # only write MSR if bit was changed + jnc .Lverify_cpu_check # only write MSR if bit was changed wrmsr -verify_cpu_check: +.Lverify_cpu_check: movl $0x1,%eax # Does the cpu have what it takes cpuid andl $REQUIRED_MASK0,%edx xorl $REQUIRED_MASK0,%edx - jnz verify_cpu_no_longmode + jnz .Lverify_cpu_no_longmode movl $0x80000000,%eax # See if extended cpuid is implemented cpuid cmpl $0x80000001,%eax - jb verify_cpu_no_longmode # no extended cpuid + jb .Lverify_cpu_no_longmode # no extended cpuid movl $0x80000001,%eax # Does the cpu have what it takes cpuid andl $REQUIRED_MASK1,%edx xorl $REQUIRED_MASK1,%edx - jnz verify_cpu_no_longmode + jnz .Lverify_cpu_no_longmode -verify_cpu_sse_test: +.Lverify_cpu_sse_test: movl $1,%eax cpuid andl $SSE_MASK,%edx cmpl $SSE_MASK,%edx - je verify_cpu_sse_ok + je .Lverify_cpu_sse_ok test %di,%di - jz verify_cpu_no_longmode # only try to force SSE on AMD + jz .Lverify_cpu_no_longmode # only try to force SSE on AMD movl $MSR_K7_HWCR,%ecx rdmsr btr $15,%eax # enable SSE wrmsr xor %di,%di # don't loop - jmp verify_cpu_sse_test # try again + jmp .Lverify_cpu_sse_test # try again -verify_cpu_no_longmode: +.Lverify_cpu_no_longmode: popf # Restore caller passed flags movl $1,%eax ret -verify_cpu_sse_ok: +.Lverify_cpu_sse_ok: popf # Restore caller passed flags xorl %eax, %eax ret diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index ec081fe0ce2c..8829482d69ec 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -814,8 +814,7 @@ remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end, if (phys_addr < (phys_addr_t)0x40000000) return; - if (IS_ALIGNED(addr, PAGE_SIZE) && - IS_ALIGNED(next, PAGE_SIZE)) { + if (PAGE_ALIGNED(addr) && PAGE_ALIGNED(next)) { /* * Do not free direct mapping pages since they were * freed when offlining, or simplely not in use. diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 844b06d67df4..96bd1e2bffaf 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -69,14 +69,14 @@ unsigned long arch_mmap_rnd(void) { unsigned long rnd; - /* - * 8 bits of randomness in 32bit mmaps, 20 address space bits - * 28 bits of randomness in 64bit mmaps, 40 address space bits - */ if (mmap_is_ia32()) - rnd = (unsigned long)get_random_int() % (1<<8); +#ifdef CONFIG_COMPAT + rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_compat_bits) - 1); +#else + rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1); +#endif else - rnd = (unsigned long)get_random_int() % (1<<28); + rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1); return rnd << PAGE_SHIFT; } diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 6000ad7f560c..fc6a4c8f6e2a 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -66,6 +66,9 @@ void update_page_count(int level, unsigned long pages) static void split_page_count(int level) { + if (direct_pages_count[level] == 0) + return; + direct_pages_count[level]--; direct_pages_count[level - 1] += PTRS_PER_PTE; } diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 8ddb5d0d66fb..8f4cc3dfac32 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -161,7 +161,10 @@ void flush_tlb_current_task(void) preempt_disable(); count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); + + /* This is an implicit full barrier that synchronizes with switch_mm. */ local_flush_tlb(); + trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL); if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL); @@ -188,17 +191,29 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, unsigned long base_pages_to_flush = TLB_FLUSH_ALL; preempt_disable(); - if (current->active_mm != mm) + if (current->active_mm != mm) { + /* Synchronize with switch_mm. */ + smp_mb(); + goto out; + } if (!current->mm) { leave_mm(smp_processor_id()); + + /* Synchronize with switch_mm. */ + smp_mb(); + goto out; } if ((end != TLB_FLUSH_ALL) && !(vmflag & VM_HUGETLB)) base_pages_to_flush = (end - start) >> PAGE_SHIFT; + /* + * Both branches below are implicit full barriers (MOV to CR or + * INVLPG) that synchronize with switch_mm. + */ if (base_pages_to_flush > tlb_single_page_flush_ceiling) { base_pages_to_flush = TLB_FLUSH_ALL; count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); @@ -228,10 +243,18 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long start) preempt_disable(); if (current->active_mm == mm) { - if (current->mm) + if (current->mm) { + /* + * Implicit full barrier (INVLPG) that synchronizes + * with switch_mm. + */ __flush_tlb_one(start); - else + } else { leave_mm(smp_processor_id()); + + /* Synchronize with switch_mm. */ + smp_mb(); + } } if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) diff --git a/drivers/Makefile b/drivers/Makefile index 795d0ca714bf..8f5d076baeb0 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -106,7 +106,7 @@ obj-y += i2c/ media/ obj-$(CONFIG_PPS) += pps/ obj-$(CONFIG_PTP_1588_CLOCK) += ptp/ obj-$(CONFIG_W1) += w1/ -obj-$(CONFIG_POWER_SUPPLY) += power/ +obj-y += power/ obj-$(CONFIG_HWMON) += hwmon/ obj-$(CONFIG_THERMAL) += thermal/ obj-$(CONFIG_WATCHDOG) += watchdog/ diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 25425d3f2575..619fe584a44c 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -450,8 +450,7 @@ memory_probe_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { u64 phys_addr; - int nid; - int i, ret; + int nid, ret; unsigned long pages_per_block = PAGES_PER_SECTION * sections_per_block; ret = kstrtoull(buf, 0, &phys_addr); @@ -461,15 +460,12 @@ memory_probe_store(struct device *dev, struct device_attribute *attr, if (phys_addr & ((pages_per_block << PAGE_SHIFT) - 1)) return -EINVAL; - for (i = 0; i < sections_per_block; i++) { - nid = memory_add_physaddr_to_nid(phys_addr); - ret = add_memory(nid, phys_addr, - PAGES_PER_SECTION << PAGE_SHIFT); - if (ret) - goto out; + nid = memory_add_physaddr_to_nid(phys_addr); + ret = add_memory(nid, phys_addr, + MIN_MEMORY_BLOCK_SIZE * sections_per_block); - phys_addr += MIN_MEMORY_BLOCK_SIZE; - } + if (ret) + goto out; ret = count; out: @@ -618,7 +614,6 @@ static int init_memory_block(struct memory_block **memory, base_memory_block_id(scn_nr) * sections_per_block; mem->end_section_nr = mem->start_section_nr + sections_per_block - 1; mem->state = state; - mem->section_count++; start_pfn = section_nr_to_pfn(mem->start_section_nr); mem->phys_device = arch_get_memory_phys_device(start_pfn); @@ -672,6 +667,7 @@ int register_new_memory(int nid, struct mem_section *section) ret = init_memory_block(&mem, section, MEM_OFFLINE); if (ret) goto out; + mem->section_count++; } if (mem->section_count == sections_per_block) @@ -692,7 +688,7 @@ unregister_memory(struct memory_block *memory) device_unregister(&memory->dev); } -static int remove_memory_block(unsigned long node_id, +static int remove_memory_section(unsigned long node_id, struct mem_section *section, int phys_device) { struct memory_block *mem; @@ -716,7 +712,7 @@ int unregister_memory_section(struct mem_section *section) if (!present_section(section)) return -EINVAL; - return remove_memory_block(0, section, 0); + return remove_memory_section(0, section, 0); } #endif /* CONFIG_MEMORY_HOTREMOVE */ diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 331363e7de0f..9e251201dd48 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -3585,7 +3585,7 @@ static void __init config_types(void) unsigned int type = UDP->cmos; struct floppy_drive_params *params; const char *name = NULL; - static char temparea[32]; + char temparea[32]; if (type < ARRAY_SIZE(default_drive_params)) { params = &default_drive_params[type].params; @@ -3596,7 +3596,8 @@ static void __init config_types(void) allowed_drive_mask &= ~(1 << drive); } else { params = &default_drive_params[0].params; - sprintf(temparea, "unknown type %d (usb?)", type); + snprintf(temparea, sizeof(temparea), + "unknown type %d (usb?)", type); name = temparea; } if (name) { diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c index 5cb13ca3a3ac..3ef42e563bb5 100644 --- a/drivers/block/zram/zcomp.c +++ b/drivers/block/zram/zcomp.c @@ -74,18 +74,18 @@ static void zcomp_strm_free(struct zcomp *comp, struct zcomp_strm *zstrm) * allocate new zcomp_strm structure with ->private initialized by * backend, return NULL on error */ -static struct zcomp_strm *zcomp_strm_alloc(struct zcomp *comp) +static struct zcomp_strm *zcomp_strm_alloc(struct zcomp *comp, gfp_t flags) { - struct zcomp_strm *zstrm = kmalloc(sizeof(*zstrm), GFP_KERNEL); + struct zcomp_strm *zstrm = kmalloc(sizeof(*zstrm), flags); if (!zstrm) return NULL; - zstrm->private = comp->backend->create(); + zstrm->private = comp->backend->create(flags); /* * allocate 2 pages. 1 for compressed data, plus 1 extra for the * case when compressed size is larger than the original one */ - zstrm->buffer = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 1); + zstrm->buffer = (void *)__get_free_pages(flags | __GFP_ZERO, 1); if (!zstrm->private || !zstrm->buffer) { zcomp_strm_free(comp, zstrm); zstrm = NULL; @@ -120,8 +120,16 @@ static struct zcomp_strm *zcomp_strm_multi_find(struct zcomp *comp) /* allocate new zstrm stream */ zs->avail_strm++; spin_unlock(&zs->strm_lock); - - zstrm = zcomp_strm_alloc(comp); + /* + * This function can be called in swapout/fs write path + * so we can't use GFP_FS|IO. And it assumes we already + * have at least one stream in zram initialization so we + * don't do best effort to allocate more stream in here. + * A default stream will work well without further multiple + * streams. That's why we use NORETRY | NOWARN. + */ + zstrm = zcomp_strm_alloc(comp, GFP_NOIO | __GFP_NORETRY | + __GFP_NOWARN); if (!zstrm) { spin_lock(&zs->strm_lock); zs->avail_strm--; @@ -209,7 +217,7 @@ static int zcomp_strm_multi_create(struct zcomp *comp, int max_strm) zs->max_strm = max_strm; zs->avail_strm = 1; - zstrm = zcomp_strm_alloc(comp); + zstrm = zcomp_strm_alloc(comp, GFP_KERNEL); if (!zstrm) { kfree(zs); return -ENOMEM; @@ -259,7 +267,7 @@ static int zcomp_strm_single_create(struct zcomp *comp) comp->stream = zs; mutex_init(&zs->strm_lock); - zs->zstrm = zcomp_strm_alloc(comp); + zs->zstrm = zcomp_strm_alloc(comp, GFP_KERNEL); if (!zs->zstrm) { kfree(zs); return -ENOMEM; diff --git a/drivers/block/zram/zcomp.h b/drivers/block/zram/zcomp.h index 46e2b9f8f1f0..b7d2a4bcae54 100644 --- a/drivers/block/zram/zcomp.h +++ b/drivers/block/zram/zcomp.h @@ -33,7 +33,7 @@ struct zcomp_backend { int (*decompress)(const unsigned char *src, size_t src_len, unsigned char *dst); - void *(*create)(void); + void *(*create)(gfp_t flags); void (*destroy)(void *private); const char *name; diff --git a/drivers/block/zram/zcomp_lz4.c b/drivers/block/zram/zcomp_lz4.c index f2afb7e988c3..0110086accba 100644 --- a/drivers/block/zram/zcomp_lz4.c +++ b/drivers/block/zram/zcomp_lz4.c @@ -10,17 +10,26 @@ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/lz4.h> +#include <linux/vmalloc.h> +#include <linux/mm.h> #include "zcomp_lz4.h" -static void *zcomp_lz4_create(void) +static void *zcomp_lz4_create(gfp_t flags) { - return kzalloc(LZ4_MEM_COMPRESS, GFP_KERNEL); + void *ret; + + ret = kmalloc(LZ4_MEM_COMPRESS, flags); + if (!ret) + ret = __vmalloc(LZ4_MEM_COMPRESS, + flags | __GFP_HIGHMEM, + PAGE_KERNEL); + return ret; } static void zcomp_lz4_destroy(void *private) { - kfree(private); + kvfree(private); } static int zcomp_lz4_compress(const unsigned char *src, unsigned char *dst, diff --git a/drivers/block/zram/zcomp_lzo.c b/drivers/block/zram/zcomp_lzo.c index da1bc47d588e..ed7a1f0549ec 100644 --- a/drivers/block/zram/zcomp_lzo.c +++ b/drivers/block/zram/zcomp_lzo.c @@ -10,17 +10,26 @@ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/lzo.h> +#include <linux/vmalloc.h> +#include <linux/mm.h> #include "zcomp_lzo.h" -static void *lzo_create(void) +static void *lzo_create(gfp_t flags) { - return kzalloc(LZO1X_MEM_COMPRESS, GFP_KERNEL); + void *ret; + + ret = kmalloc(LZO1X_MEM_COMPRESS, flags); + if (!ret) + ret = __vmalloc(LZO1X_MEM_COMPRESS, + flags | __GFP_HIGHMEM, + PAGE_KERNEL); + return ret; } static void lzo_destroy(void *private) { - kfree(private); + kvfree(private); } static int lzo_compress(const unsigned char *src, unsigned char *dst, diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig index b251013eef0a..56777f04d2d9 100644 --- a/drivers/clocksource/Kconfig +++ b/drivers/clocksource/Kconfig @@ -152,7 +152,7 @@ config CLKSRC_EFM32 config CLKSRC_LPC32XX bool "Clocksource for LPC32XX" if COMPILE_TEST - depends on GENERIC_CLOCKEVENTS + depends on GENERIC_CLOCKEVENTS && HAS_IOMEM select CLKSRC_MMIO select CLKSRC_OF help @@ -160,6 +160,7 @@ config CLKSRC_LPC32XX config CLKSRC_PISTACHIO bool "Clocksource for Pistachio SoC" if COMPILE_TEST + depends on HAS_IOMEM select CLKSRC_OF help Enables the clocksource for the Pistachio SoC. @@ -256,6 +257,7 @@ config CLKSRC_SAMSUNG_PWM config FSL_FTM_TIMER bool "Freescale FlexTimer Module driver" if COMPILE_TEST depends on GENERIC_CLOCKEVENTS + select CLKSRC_MMIO help Support for Freescale FlexTimer Module (FTM) timer. @@ -269,7 +271,7 @@ config SYS_SUPPORTS_SH_CMT config MTK_TIMER bool "Mediatek timer driver" if COMPILE_TEST - depends on GENERIC_CLOCKEVENTS + depends on GENERIC_CLOCKEVENTS && HAS_IOMEM select CLKSRC_OF select CLKSRC_MMIO help @@ -365,20 +367,20 @@ config CLKSRC_PXA config H8300_TMR8 bool "Clockevent timer for the H8300 platform" if COMPILE_TEST - depends on GENERIC_CLOCKEVENTS + depends on GENERIC_CLOCKEVENTS && HAS_IOMEM help This enables the 8 bits timer for the H8300 platform. config H8300_TMR16 bool "Clockevent timer for the H83069 platform" if COMPILE_TEST - depends on GENERIC_CLOCKEVENTS + depends on GENERIC_CLOCKEVENTS && HAS_IOMEM help This enables the 16 bits timer for the H8300 platform with the H83069 cpu. config H8300_TPU bool "Clocksource for the H8300 platform" if COMPILE_TEST - depends on GENERIC_CLOCKEVENTS + depends on GENERIC_CLOCKEVENTS && HAS_IOMEM help This enables the clocksource for the H8300 platform with the H8S2678 cpu. @@ -391,6 +393,7 @@ config CLKSRC_IMX_GPT config CLKSRC_ST_LPC bool "Low power clocksource found in the LPC" if COMPILE_TEST select CLKSRC_OF if OF + depends on HAS_IOMEM help Enable this option to use the Low Power controller timer as clocksource. diff --git a/drivers/clocksource/vt8500_timer.c b/drivers/clocksource/vt8500_timer.c index de49805fbb09..ddb409274f45 100644 --- a/drivers/clocksource/vt8500_timer.c +++ b/drivers/clocksource/vt8500_timer.c @@ -49,6 +49,8 @@ #define msecs_to_loops(t) (loops_per_jiffy / 1000 * HZ * t) +#define MIN_OSCR_DELTA 16 + static void __iomem *regbase; static cycle_t vt8500_timer_read(struct clocksource *cs) @@ -79,7 +81,7 @@ static int vt8500_timer_set_next_event(unsigned long cycles, cpu_relax(); writel((unsigned long)alarm, regbase + TIMER_MATCH_VAL); - if ((signed)(alarm - clocksource.read(&clocksource)) <= 16) + if ((signed)(alarm - clocksource.read(&clocksource)) <= MIN_OSCR_DELTA) return -ETIME; writel(1, regbase + TIMER_IER_VAL); @@ -150,7 +152,7 @@ static void __init vt8500_timer_init(struct device_node *np) pr_err("%s: setup_irq failed for %s\n", __func__, clockevent.name); clockevents_config_and_register(&clockevent, VT8500_TIMER_HZ, - 4, 0xf0000000); + MIN_OSCR_DELTA * 2, 0xf0000000); } CLOCKSOURCE_OF_DECLARE(vt8500, "via,vt8500-timer", vt8500_timer_init); diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c index cb501386eb6e..547890fd9572 100644 --- a/drivers/cpufreq/powernv-cpufreq.c +++ b/drivers/cpufreq/powernv-cpufreq.c @@ -586,7 +586,7 @@ static int __init powernv_cpufreq_init(void) int rc = 0; /* Don't probe on pseries (guest) platforms */ - if (!firmware_has_feature(FW_FEATURE_OPALv3)) + if (!firmware_has_feature(FW_FEATURE_OPAL)) return -ENODEV; /* Discover pstates from device tree and init */ diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c index 845bafcfa792..e12dc30d8864 100644 --- a/drivers/cpuidle/cpuidle-powernv.c +++ b/drivers/cpuidle/cpuidle-powernv.c @@ -264,7 +264,7 @@ static int powernv_idle_probe(void) if (cpuidle_disable != IDLE_NO_OVERRIDE) return -ENODEV; - if (firmware_has_feature(FW_FEATURE_OPALv3)) { + if (firmware_has_feature(FW_FEATURE_OPAL)) { cpuidle_state_table = powernv_states; /* Device tree can indicate more idle states */ max_idle_state = powernv_add_idle_states(); diff --git a/drivers/crypto/vmx/aes.c b/drivers/crypto/vmx/aes.c index 263af709e536..022c7ab7351a 100644 --- a/drivers/crypto/vmx/aes.c +++ b/drivers/crypto/vmx/aes.c @@ -83,10 +83,10 @@ static int p8_aes_setkey(struct crypto_tfm *tfm, const u8 *key, preempt_disable(); pagefault_disable(); - enable_kernel_altivec(); enable_kernel_vsx(); ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key); ret += aes_p8_set_decrypt_key(key, keylen * 8, &ctx->dec_key); + disable_kernel_vsx(); pagefault_enable(); preempt_enable(); @@ -103,9 +103,9 @@ static void p8_aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) } else { preempt_disable(); pagefault_disable(); - enable_kernel_altivec(); enable_kernel_vsx(); aes_p8_encrypt(src, dst, &ctx->enc_key); + disable_kernel_vsx(); pagefault_enable(); preempt_enable(); } @@ -120,9 +120,9 @@ static void p8_aes_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) } else { preempt_disable(); pagefault_disable(); - enable_kernel_altivec(); enable_kernel_vsx(); aes_p8_decrypt(src, dst, &ctx->dec_key); + disable_kernel_vsx(); pagefault_enable(); preempt_enable(); } diff --git a/drivers/crypto/vmx/aes_cbc.c b/drivers/crypto/vmx/aes_cbc.c index 78a978613ca8..495577b6d31b 100644 --- a/drivers/crypto/vmx/aes_cbc.c +++ b/drivers/crypto/vmx/aes_cbc.c @@ -84,10 +84,10 @@ static int p8_aes_cbc_setkey(struct crypto_tfm *tfm, const u8 *key, preempt_disable(); pagefault_disable(); - enable_kernel_altivec(); enable_kernel_vsx(); ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key); ret += aes_p8_set_decrypt_key(key, keylen * 8, &ctx->dec_key); + disable_kernel_vsx(); pagefault_enable(); preempt_enable(); @@ -115,7 +115,6 @@ static int p8_aes_cbc_encrypt(struct blkcipher_desc *desc, } else { preempt_disable(); pagefault_disable(); - enable_kernel_altivec(); enable_kernel_vsx(); blkcipher_walk_init(&walk, dst, src, nbytes); @@ -129,6 +128,7 @@ static int p8_aes_cbc_encrypt(struct blkcipher_desc *desc, ret = blkcipher_walk_done(desc, &walk, nbytes); } + disable_kernel_vsx(); pagefault_enable(); preempt_enable(); } @@ -156,7 +156,6 @@ static int p8_aes_cbc_decrypt(struct blkcipher_desc *desc, } else { preempt_disable(); pagefault_disable(); - enable_kernel_altivec(); enable_kernel_vsx(); blkcipher_walk_init(&walk, dst, src, nbytes); @@ -170,6 +169,7 @@ static int p8_aes_cbc_decrypt(struct blkcipher_desc *desc, ret = blkcipher_walk_done(desc, &walk, nbytes); } + disable_kernel_vsx(); pagefault_enable(); preempt_enable(); } diff --git a/drivers/crypto/vmx/aes_ctr.c b/drivers/crypto/vmx/aes_ctr.c index 1febc4f1d9af..0a3c1b04cf3c 100644 --- a/drivers/crypto/vmx/aes_ctr.c +++ b/drivers/crypto/vmx/aes_ctr.c @@ -81,9 +81,9 @@ static int p8_aes_ctr_setkey(struct crypto_tfm *tfm, const u8 *key, struct p8_aes_ctr_ctx *ctx = crypto_tfm_ctx(tfm); pagefault_disable(); - enable_kernel_altivec(); enable_kernel_vsx(); ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key); + disable_kernel_vsx(); pagefault_enable(); ret += crypto_blkcipher_setkey(ctx->fallback, key, keylen); @@ -100,9 +100,9 @@ static void p8_aes_ctr_final(struct p8_aes_ctr_ctx *ctx, unsigned int nbytes = walk->nbytes; pagefault_disable(); - enable_kernel_altivec(); enable_kernel_vsx(); aes_p8_encrypt(ctrblk, keystream, &ctx->enc_key); + disable_kernel_vsx(); pagefault_enable(); crypto_xor(keystream, src, nbytes); @@ -133,7 +133,6 @@ static int p8_aes_ctr_crypt(struct blkcipher_desc *desc, ret = blkcipher_walk_virt_block(desc, &walk, AES_BLOCK_SIZE); while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) { pagefault_disable(); - enable_kernel_altivec(); enable_kernel_vsx(); aes_p8_ctr32_encrypt_blocks(walk.src.virt.addr, walk.dst.virt.addr, @@ -142,6 +141,7 @@ static int p8_aes_ctr_crypt(struct blkcipher_desc *desc, AES_BLOCK_SIZE, &ctx->enc_key, walk.iv); + disable_kernel_vsx(); pagefault_enable(); /* We need to update IV mostly for last bytes/round */ diff --git a/drivers/crypto/vmx/ghash.c b/drivers/crypto/vmx/ghash.c index 2183a2e77641..6c999cb01b80 100644 --- a/drivers/crypto/vmx/ghash.c +++ b/drivers/crypto/vmx/ghash.c @@ -118,10 +118,9 @@ static int p8_ghash_setkey(struct crypto_shash *tfm, const u8 *key, preempt_disable(); pagefault_disable(); - enable_kernel_altivec(); enable_kernel_vsx(); - enable_kernel_fp(); gcm_init_p8(ctx->htable, (const u64 *) key); + disable_kernel_vsx(); pagefault_enable(); preempt_enable(); return crypto_shash_setkey(ctx->fallback, key, keylen); @@ -149,11 +148,10 @@ static int p8_ghash_update(struct shash_desc *desc, GHASH_DIGEST_SIZE - dctx->bytes); preempt_disable(); pagefault_disable(); - enable_kernel_altivec(); enable_kernel_vsx(); - enable_kernel_fp(); gcm_ghash_p8(dctx->shash, ctx->htable, dctx->buffer, GHASH_DIGEST_SIZE); + disable_kernel_vsx(); pagefault_enable(); preempt_enable(); src += GHASH_DIGEST_SIZE - dctx->bytes; @@ -164,10 +162,9 @@ static int p8_ghash_update(struct shash_desc *desc, if (len) { preempt_disable(); pagefault_disable(); - enable_kernel_altivec(); enable_kernel_vsx(); - enable_kernel_fp(); gcm_ghash_p8(dctx->shash, ctx->htable, src, len); + disable_kernel_vsx(); pagefault_enable(); preempt_enable(); src += len; @@ -195,11 +192,10 @@ static int p8_ghash_final(struct shash_desc *desc, u8 *out) dctx->buffer[i] = 0; preempt_disable(); pagefault_disable(); - enable_kernel_altivec(); enable_kernel_vsx(); - enable_kernel_fp(); gcm_ghash_p8(dctx->shash, ctx->htable, dctx->buffer, GHASH_DIGEST_SIZE); + disable_kernel_vsx(); pagefault_enable(); preempt_enable(); dctx->bytes = 0; diff --git a/drivers/firmware/efi/libstub/fdt.c b/drivers/firmware/efi/libstub/fdt.c index b62e2f5dcab3..cf7b7d46302a 100644 --- a/drivers/firmware/efi/libstub/fdt.c +++ b/drivers/firmware/efi/libstub/fdt.c @@ -253,7 +253,7 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table, sys_table->boottime->free_pool(memory_map); new_fdt_size += EFI_PAGE_SIZE; } else { - pr_efi_err(sys_table, "Unable to constuct new device tree.\n"); + pr_efi_err(sys_table, "Unable to construct new device tree.\n"); goto fail_free_mmap; } } diff --git a/drivers/gpio/gpio-arizona.c b/drivers/gpio/gpio-arizona.c index ca002739616a..624ea5421995 100644 --- a/drivers/gpio/gpio-arizona.c +++ b/drivers/gpio/gpio-arizona.c @@ -122,6 +122,10 @@ static int arizona_gpio_probe(struct platform_device *pdev) case WM1814: arizona_gpio->gpio_chip.ngpio = 5; break; + case WM1831: + case CS47L24: + arizona_gpio->gpio_chip.ngpio = 2; + break; default: dev_err(&pdev->dev, "Unknown chip variant %d\n", arizona->type); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index d321222fd92e..d2b49c026cf6 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -558,8 +558,7 @@ static int kfd_ioctl_dbg_address_watch(struct file *filep, return -EINVAL; /* this is the actual buffer to work with */ - - args_buff = memdup_user(args_buff, + args_buff = memdup_user(cmd_from_user, args->buf_size_in_bytes - sizeof(*args)); if (IS_ERR(args_buff)) return PTR_ERR(args_buff); diff --git a/drivers/gpu/drm/exynos/exynos_drm_fb.h b/drivers/gpu/drm/exynos/exynos_drm_fb.h index 726a2d44371f..cf39f9816a87 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fb.h +++ b/drivers/gpu/drm/exynos/exynos_drm_fb.h @@ -12,7 +12,7 @@ */ #ifndef _EXYNOS_DRM_FB_H_ -#define _EXYNOS_DRM_FB_H +#define _EXYNOS_DRM_FB_H_ #include "exynos_drm_gem.h" diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index c6f7a694f67a..7e89288b1537 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -625,7 +625,7 @@ static void hid_close_report(struct hid_device *device) static void hid_device_release(struct device *dev) { - struct hid_device *hid = container_of(dev, struct hid_device, dev); + struct hid_device *hid = to_hid_device(dev); hid_close_report(hid); kfree(hid->dev_rdesc); @@ -1571,8 +1571,8 @@ read_report_descriptor(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) { - struct device *dev = container_of(kobj, struct device, kobj); - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct device *dev = kobj_to_dev(kobj); + struct hid_device *hdev = to_hid_device(dev); if (off >= hdev->rsize) return 0; @@ -1589,7 +1589,7 @@ static ssize_t show_country(struct device *dev, struct device_attribute *attr, char *buf) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); return sprintf(buf, "%02x\n", hdev->country & 0xff); } @@ -1691,11 +1691,6 @@ int hid_connect(struct hid_device *hdev, unsigned int connect_mask) hid_warn(hdev, "can't create sysfs country code attribute err: %d\n", ret); - ret = device_create_bin_file(&hdev->dev, &dev_bin_attr_report_desc); - if (ret) - hid_warn(hdev, - "can't create sysfs report descriptor attribute err: %d\n", ret); - hid_info(hdev, "%s: %s HID v%x.%02x %s [%s] on %s\n", buf, bus, hdev->version >> 8, hdev->version & 0xff, type, hdev->name, hdev->phys); @@ -1707,7 +1702,6 @@ EXPORT_SYMBOL_GPL(hid_connect); void hid_disconnect(struct hid_device *hdev) { device_remove_file(&hdev->dev, &dev_attr_country); - device_remove_bin_file(&hdev->dev, &dev_bin_attr_report_desc); if (hdev->claimed & HID_CLAIMED_INPUT) hidinput_disconnect(hdev); if (hdev->claimed & HID_CLAIMED_HIDDEV) @@ -1902,6 +1896,7 @@ static const struct hid_device_id hid_have_special_driver[] = { { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_RUMBLEPAD) }, { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_RUMBLEPAD2_2) }, { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_G29_WHEEL) }, + { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_G920_WHEEL) }, { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_WINGMAN_F3D) }, { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_WINGMAN_FFG ) }, { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_FORCE3D_PRO) }, @@ -2076,7 +2071,7 @@ struct hid_dynid { static ssize_t store_new_id(struct device_driver *drv, const char *buf, size_t count) { - struct hid_driver *hdrv = container_of(drv, struct hid_driver, driver); + struct hid_driver *hdrv = to_hid_driver(drv); struct hid_dynid *dynid; __u32 bus, vendor, product; unsigned long driver_data = 0; @@ -2138,17 +2133,16 @@ static const struct hid_device_id *hid_match_device(struct hid_device *hdev, static int hid_bus_match(struct device *dev, struct device_driver *drv) { - struct hid_driver *hdrv = container_of(drv, struct hid_driver, driver); - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_driver *hdrv = to_hid_driver(drv); + struct hid_device *hdev = to_hid_device(dev); return hid_match_device(hdev, hdrv) != NULL; } static int hid_device_probe(struct device *dev) { - struct hid_driver *hdrv = container_of(dev->driver, - struct hid_driver, driver); - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_driver *hdrv = to_hid_driver(dev->driver); + struct hid_device *hdev = to_hid_device(dev); const struct hid_device_id *id; int ret = 0; @@ -2190,7 +2184,7 @@ unlock_driver_lock: static int hid_device_remove(struct device *dev) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct hid_driver *hdrv; int ret = 0; @@ -2223,12 +2217,9 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *a, char *buf) { struct hid_device *hdev = container_of(dev, struct hid_device, dev); - int len; - - len = snprintf(buf, PAGE_SIZE, "hid:b%04Xg%04Xv%08Xp%08X\n", - hdev->bus, hdev->group, hdev->vendor, hdev->product); - return (len >= PAGE_SIZE) ? (PAGE_SIZE - 1) : len; + return scnprintf(buf, PAGE_SIZE, "hid:b%04Xg%04Xv%08Xp%08X\n", + hdev->bus, hdev->group, hdev->vendor, hdev->product); } static DEVICE_ATTR_RO(modalias); @@ -2236,11 +2227,19 @@ static struct attribute *hid_dev_attrs[] = { &dev_attr_modalias.attr, NULL, }; -ATTRIBUTE_GROUPS(hid_dev); +static struct bin_attribute *hid_dev_bin_attrs[] = { + &dev_bin_attr_report_desc, + NULL +}; +static const struct attribute_group hid_dev_group = { + .attrs = hid_dev_attrs, + .bin_attrs = hid_dev_bin_attrs, +}; +__ATTRIBUTE_GROUPS(hid_dev); static int hid_uevent(struct device *dev, struct kobj_uevent_env *env) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); if (add_uevent_var(env, "HID_ID=%04X:%08X:%08X", hdev->bus, hdev->vendor, hdev->product)) @@ -2408,6 +2407,7 @@ static const struct hid_device_id hid_ignore_list[] = { { HID_USB_DEVICE(USB_VENDOR_ID_MICROCHIP, USB_DEVICE_ID_PICKIT1) }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROCHIP, USB_DEVICE_ID_PICKIT2) }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROCHIP, USB_DEVICE_ID_PICK16F1454) }, + { HID_USB_DEVICE(USB_VENDOR_ID_MICROCHIP, USB_DEVICE_ID_PICK16F1454_V2) }, { HID_USB_DEVICE(USB_VENDOR_ID_NATIONAL_SEMICONDUCTOR, USB_DEVICE_ID_N_S_HARMONY) }, { HID_USB_DEVICE(USB_VENDOR_ID_ONTRAK, USB_DEVICE_ID_ONTRAK_ADU100) }, { HID_USB_DEVICE(USB_VENDOR_ID_ONTRAK, USB_DEVICE_ID_ONTRAK_ADU100 + 20) }, @@ -2660,6 +2660,7 @@ struct hid_device *hid_allocate_device(void) device_initialize(&hdev->dev); hdev->dev.release = hid_device_release; hdev->dev.bus = &hid_bus_type; + device_enable_async_suspend(&hdev->dev); hid_close_report(hdev); diff --git a/drivers/hid/hid-corsair.c b/drivers/hid/hid-corsair.c index bcefb9ebb026..58551964ce86 100644 --- a/drivers/hid/hid-corsair.c +++ b/drivers/hid/hid-corsair.c @@ -655,18 +655,7 @@ static struct hid_driver corsair_driver = { .input_mapping = corsair_input_mapping, }; -static int __init corsair_init(void) -{ - return hid_register_driver(&corsair_driver); -} - -static void corsair_exit(void) -{ - hid_unregister_driver(&corsair_driver); -} - -module_init(corsair_init); -module_exit(corsair_exit); +module_hid_driver(corsair_driver); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Clement Vuchener"); diff --git a/drivers/hid/hid-cp2112.c b/drivers/hid/hid-cp2112.c index 7afc3fcc122c..7c38bfa05fac 100644 --- a/drivers/hid/hid-cp2112.c +++ b/drivers/hid/hid-cp2112.c @@ -807,7 +807,7 @@ static ssize_t name##_store(struct device *kdev, \ struct device_attribute *attr, const char *buf, \ size_t count) \ { \ - struct hid_device *hdev = container_of(kdev, struct hid_device, dev); \ + struct hid_device *hdev = to_hid_device(kdev); \ struct cp2112_usb_config_report cfg; \ int ret = cp2112_get_usb_config(hdev, &cfg); \ if (ret) \ @@ -822,7 +822,7 @@ static ssize_t name##_store(struct device *kdev, \ static ssize_t name##_show(struct device *kdev, \ struct device_attribute *attr, char *buf) \ { \ - struct hid_device *hdev = container_of(kdev, struct hid_device, dev); \ + struct hid_device *hdev = to_hid_device(kdev); \ struct cp2112_usb_config_report cfg; \ int ret = cp2112_get_usb_config(hdev, &cfg); \ if (ret) \ @@ -887,7 +887,7 @@ static ssize_t pstr_store(struct device *kdev, struct device_attribute *kattr, const char *buf, size_t count) { - struct hid_device *hdev = container_of(kdev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(kdev); struct cp2112_pstring_attribute *attr = container_of(kattr, struct cp2112_pstring_attribute, attr); struct cp2112_string_report report; @@ -918,7 +918,7 @@ static ssize_t pstr_store(struct device *kdev, static ssize_t pstr_show(struct device *kdev, struct device_attribute *kattr, char *buf) { - struct hid_device *hdev = container_of(kdev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(kdev); struct cp2112_pstring_attribute *attr = container_of(kattr, struct cp2112_pstring_attribute, attr); struct cp2112_string_report report; diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c index 2886b645ced7..acfb522a432a 100644 --- a/drivers/hid/hid-debug.c +++ b/drivers/hid/hid-debug.c @@ -659,13 +659,13 @@ EXPORT_SYMBOL_GPL(hid_dump_device); /* enqueue string to 'events' ring buffer */ void hid_debug_event(struct hid_device *hdev, char *buf) { - int i; + unsigned i; struct hid_debug_list *list; unsigned long flags; spin_lock_irqsave(&hdev->debug_list_lock, flags); list_for_each_entry(list, &hdev->debug_list, node) { - for (i = 0; i < strlen(buf); i++) + for (i = 0; buf[i]; i++) list->hid_debug_buf[(list->tail + i) % HID_DEBUG_BUFSIZE] = buf[i]; list->tail = (list->tail + i) % HID_DEBUG_BUFSIZE; diff --git a/drivers/hid/hid-gt683r.c b/drivers/hid/hid-gt683r.c index 0d6f135e266c..a298fbd8db6b 100644 --- a/drivers/hid/hid-gt683r.c +++ b/drivers/hid/hid-gt683r.c @@ -70,7 +70,7 @@ static void gt683r_brightness_set(struct led_classdev *led_cdev, { int i; struct device *dev = led_cdev->dev->parent; - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct gt683r_led *led = hid_get_drvdata(hdev); for (i = 0; i < GT683R_LED_COUNT; i++) { @@ -89,8 +89,7 @@ static ssize_t mode_show(struct device *dev, char *buf) { u8 sysfs_mode; - struct hid_device *hdev = container_of(dev->parent, - struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev->parent); struct gt683r_led *led = hid_get_drvdata(hdev); if (led->mode == GT683R_LED_NORMAL) @@ -108,8 +107,7 @@ static ssize_t mode_store(struct device *dev, const char *buf, size_t count) { u8 sysfs_mode; - struct hid_device *hdev = container_of(dev->parent, - struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev->parent); struct gt683r_led *led = hid_get_drvdata(hdev); diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 8b78a7f1f779..b6ff6e78ac54 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -510,6 +510,7 @@ #define USB_VENDOR_ID_ITE 0x048d #define USB_DEVICE_ID_ITE_LENOVO_YOGA 0x8386 #define USB_DEVICE_ID_ITE_LENOVO_YOGA2 0x8350 +#define USB_DEVICE_ID_ITE_LENOVO_YOGA900 0x8396 #define USB_VENDOR_ID_JABRA 0x0b0e #define USB_DEVICE_ID_JABRA_SPEAK_410 0x0412 @@ -615,6 +616,7 @@ #define USB_DEVICE_ID_LOGITECH_RUMBLEPAD2 0xc218 #define USB_DEVICE_ID_LOGITECH_RUMBLEPAD2_2 0xc219 #define USB_DEVICE_ID_LOGITECH_G29_WHEEL 0xc24f +#define USB_DEVICE_ID_LOGITECH_G920_WHEEL 0xc262 #define USB_DEVICE_ID_LOGITECH_WINGMAN_F3D 0xc283 #define USB_DEVICE_ID_LOGITECH_FORCE3D_PRO 0xc286 #define USB_DEVICE_ID_LOGITECH_FLIGHT_SYSTEM_G940 0xc287 @@ -664,6 +666,7 @@ #define USB_DEVICE_ID_PICOLCD 0xc002 #define USB_DEVICE_ID_PICOLCD_BOOTLOADER 0xf002 #define USB_DEVICE_ID_PICK16F1454 0x0042 +#define USB_DEVICE_ID_PICK16F1454_V2 0xf2f7 #define USB_VENDOR_ID_MICROSOFT 0x045e #define USB_DEVICE_ID_SIDEWINDER_GV 0x003b diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 2ba6bf69b7d0..bcfaf32d9e5e 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -303,6 +303,7 @@ static enum power_supply_property hidinput_battery_props[] = { #define HID_BATTERY_QUIRK_PERCENT (1 << 0) /* always reports percent */ #define HID_BATTERY_QUIRK_FEATURE (1 << 1) /* ask for feature report */ +#define HID_BATTERY_QUIRK_IGNORE (1 << 2) /* completely ignore the battery */ static const struct hid_device_id hid_battery_quirks[] = { { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, @@ -320,6 +321,9 @@ static const struct hid_device_id hid_battery_quirks[] = { { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_ANSI), HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE }, + { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_ELECOM, + USB_DEVICE_ID_ELECOM_BM084), + HID_BATTERY_QUIRK_IGNORE }, {} }; @@ -408,6 +412,14 @@ static bool hidinput_setup_battery(struct hid_device *dev, unsigned report_type, if (dev->battery != NULL) goto out; /* already initialized? */ + quirks = find_battery_quirk(dev); + + hid_dbg(dev, "device %x:%x:%x %d quirks %d\n", + dev->bus, dev->vendor, dev->product, dev->version, quirks); + + if (quirks & HID_BATTERY_QUIRK_IGNORE) + goto out; + psy_desc = kzalloc(sizeof(*psy_desc), GFP_KERNEL); if (psy_desc == NULL) goto out; @@ -424,11 +436,6 @@ static bool hidinput_setup_battery(struct hid_device *dev, unsigned report_type, psy_desc->use_for_apm = 0; psy_desc->get_property = hidinput_get_battery_property; - quirks = find_battery_quirk(dev); - - hid_dbg(dev, "device %x:%x:%x %d quirks %d\n", - dev->bus, dev->vendor, dev->product, dev->version, quirks); - min = field->logical_minimum; max = field->logical_maximum; @@ -960,6 +967,10 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel goto ignore; case HID_UP_LOGIVENDOR: + /* intentional fallback */ + case HID_UP_LOGIVENDOR2: + /* intentional fallback */ + case HID_UP_LOGIVENDOR3: goto ignore; case HID_UP_PID: diff --git a/drivers/hid/hid-lenovo.c b/drivers/hid/hid-lenovo.c index 8979f1fd5208..0125e356bd8d 100644 --- a/drivers/hid/hid-lenovo.c +++ b/drivers/hid/hid-lenovo.c @@ -220,7 +220,7 @@ static ssize_t attr_fn_lock_show_cptkbd(struct device *dev, struct device_attribute *attr, char *buf) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct lenovo_drvdata_cptkbd *cptkbd_data = hid_get_drvdata(hdev); return snprintf(buf, PAGE_SIZE, "%u\n", cptkbd_data->fn_lock); @@ -231,7 +231,7 @@ static ssize_t attr_fn_lock_store_cptkbd(struct device *dev, const char *buf, size_t count) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct lenovo_drvdata_cptkbd *cptkbd_data = hid_get_drvdata(hdev); int value; @@ -250,7 +250,7 @@ static ssize_t attr_sensitivity_show_cptkbd(struct device *dev, struct device_attribute *attr, char *buf) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct lenovo_drvdata_cptkbd *cptkbd_data = hid_get_drvdata(hdev); return snprintf(buf, PAGE_SIZE, "%u\n", @@ -262,7 +262,7 @@ static ssize_t attr_sensitivity_store_cptkbd(struct device *dev, const char *buf, size_t count) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct lenovo_drvdata_cptkbd *cptkbd_data = hid_get_drvdata(hdev); int value; @@ -387,7 +387,7 @@ static ssize_t attr_press_to_select_show_tpkbd(struct device *dev, struct device_attribute *attr, char *buf) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct lenovo_drvdata_tpkbd *data_pointer = hid_get_drvdata(hdev); return snprintf(buf, PAGE_SIZE, "%u\n", data_pointer->press_to_select); @@ -398,7 +398,7 @@ static ssize_t attr_press_to_select_store_tpkbd(struct device *dev, const char *buf, size_t count) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct lenovo_drvdata_tpkbd *data_pointer = hid_get_drvdata(hdev); int value; @@ -417,7 +417,7 @@ static ssize_t attr_dragging_show_tpkbd(struct device *dev, struct device_attribute *attr, char *buf) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct lenovo_drvdata_tpkbd *data_pointer = hid_get_drvdata(hdev); return snprintf(buf, PAGE_SIZE, "%u\n", data_pointer->dragging); @@ -428,7 +428,7 @@ static ssize_t attr_dragging_store_tpkbd(struct device *dev, const char *buf, size_t count) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct lenovo_drvdata_tpkbd *data_pointer = hid_get_drvdata(hdev); int value; @@ -447,7 +447,7 @@ static ssize_t attr_release_to_select_show_tpkbd(struct device *dev, struct device_attribute *attr, char *buf) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct lenovo_drvdata_tpkbd *data_pointer = hid_get_drvdata(hdev); return snprintf(buf, PAGE_SIZE, "%u\n", data_pointer->release_to_select); @@ -458,7 +458,7 @@ static ssize_t attr_release_to_select_store_tpkbd(struct device *dev, const char *buf, size_t count) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct lenovo_drvdata_tpkbd *data_pointer = hid_get_drvdata(hdev); int value; @@ -477,7 +477,7 @@ static ssize_t attr_select_right_show_tpkbd(struct device *dev, struct device_attribute *attr, char *buf) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct lenovo_drvdata_tpkbd *data_pointer = hid_get_drvdata(hdev); return snprintf(buf, PAGE_SIZE, "%u\n", data_pointer->select_right); @@ -488,7 +488,7 @@ static ssize_t attr_select_right_store_tpkbd(struct device *dev, const char *buf, size_t count) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct lenovo_drvdata_tpkbd *data_pointer = hid_get_drvdata(hdev); int value; @@ -507,7 +507,7 @@ static ssize_t attr_sensitivity_show_tpkbd(struct device *dev, struct device_attribute *attr, char *buf) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct lenovo_drvdata_tpkbd *data_pointer = hid_get_drvdata(hdev); return snprintf(buf, PAGE_SIZE, "%u\n", @@ -519,7 +519,7 @@ static ssize_t attr_sensitivity_store_tpkbd(struct device *dev, const char *buf, size_t count) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct lenovo_drvdata_tpkbd *data_pointer = hid_get_drvdata(hdev); int value; @@ -536,7 +536,7 @@ static ssize_t attr_press_speed_show_tpkbd(struct device *dev, struct device_attribute *attr, char *buf) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct lenovo_drvdata_tpkbd *data_pointer = hid_get_drvdata(hdev); return snprintf(buf, PAGE_SIZE, "%u\n", @@ -548,7 +548,7 @@ static ssize_t attr_press_speed_store_tpkbd(struct device *dev, const char *buf, size_t count) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct lenovo_drvdata_tpkbd *data_pointer = hid_get_drvdata(hdev); int value; @@ -609,7 +609,7 @@ static enum led_brightness lenovo_led_brightness_get_tpkbd( struct led_classdev *led_cdev) { struct device *dev = led_cdev->dev->parent; - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct lenovo_drvdata_tpkbd *data_pointer = hid_get_drvdata(hdev); int led_nr = 0; @@ -625,7 +625,7 @@ static void lenovo_led_brightness_set_tpkbd(struct led_classdev *led_cdev, enum led_brightness value) { struct device *dev = led_cdev->dev->parent; - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct lenovo_drvdata_tpkbd *data_pointer = hid_get_drvdata(hdev); struct hid_report *report; int led_nr = 0; diff --git a/drivers/hid/hid-lg4ff.c b/drivers/hid/hid-lg4ff.c index fbddcb37ae98..af3a8ec8a746 100644 --- a/drivers/hid/hid-lg4ff.c +++ b/drivers/hid/hid-lg4ff.c @@ -33,8 +33,6 @@ #include "hid-lg4ff.h" #include "hid-ids.h" -#define to_hid_device(pdev) container_of(pdev, struct hid_device, dev) - #define LG4FF_MMODE_IS_MULTIMODE 0 #define LG4FF_MMODE_SWITCHED 1 #define LG4FF_MMODE_NOT_MULTIMODE 2 @@ -1020,7 +1018,7 @@ static void lg4ff_led_set_brightness(struct led_classdev *led_cdev, enum led_brightness value) { struct device *dev = led_cdev->dev->parent; - struct hid_device *hid = container_of(dev, struct hid_device, dev); + struct hid_device *hid = to_hid_device(dev); struct lg_drv_data *drv_data = hid_get_drvdata(hid); struct lg4ff_device_entry *entry; int i, state = 0; @@ -1055,7 +1053,7 @@ static void lg4ff_led_set_brightness(struct led_classdev *led_cdev, static enum led_brightness lg4ff_led_get_brightness(struct led_classdev *led_cdev) { struct device *dev = led_cdev->dev->parent; - struct hid_device *hid = container_of(dev, struct hid_device, dev); + struct hid_device *hid = to_hid_device(dev); struct lg_drv_data *drv_data = hid_get_drvdata(hid); struct lg4ff_device_entry *entry; int i, value = 0; diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index 5fd97860aec4..bd2ab476c65e 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -40,18 +40,22 @@ MODULE_PARM_DESC(disable_tap_to_click, #define REPORT_ID_HIDPP_SHORT 0x10 #define REPORT_ID_HIDPP_LONG 0x11 +#define REPORT_ID_HIDPP_VERY_LONG 0x12 #define HIDPP_REPORT_SHORT_LENGTH 7 #define HIDPP_REPORT_LONG_LENGTH 20 +#define HIDPP_REPORT_VERY_LONG_LENGTH 64 #define HIDPP_QUIRK_CLASS_WTP BIT(0) #define HIDPP_QUIRK_CLASS_M560 BIT(1) #define HIDPP_QUIRK_CLASS_K400 BIT(2) +#define HIDPP_QUIRK_CLASS_G920 BIT(3) /* bits 2..20 are reserved for classes */ #define HIDPP_QUIRK_CONNECT_EVENTS BIT(21) #define HIDPP_QUIRK_WTP_PHYSICAL_BUTTONS BIT(22) #define HIDPP_QUIRK_NO_HIDINPUT BIT(23) +#define HIDPP_QUIRK_FORCE_OUTPUT_REPORTS BIT(24) #define HIDPP_QUIRK_DELAYED_INIT (HIDPP_QUIRK_NO_HIDINPUT | \ HIDPP_QUIRK_CONNECT_EVENTS) @@ -81,13 +85,13 @@ MODULE_PARM_DESC(disable_tap_to_click, struct fap { u8 feature_index; u8 funcindex_clientid; - u8 params[HIDPP_REPORT_LONG_LENGTH - 4U]; + u8 params[HIDPP_REPORT_VERY_LONG_LENGTH - 4U]; }; struct rap { u8 sub_id; u8 reg_address; - u8 params[HIDPP_REPORT_LONG_LENGTH - 4U]; + u8 params[HIDPP_REPORT_VERY_LONG_LENGTH - 4U]; }; struct hidpp_report { @@ -144,8 +148,11 @@ static void hidpp_connect_event(struct hidpp_device *hidpp_dev); static int __hidpp_send_report(struct hid_device *hdev, struct hidpp_report *hidpp_report) { + struct hidpp_device *hidpp = hid_get_drvdata(hdev); int fields_count, ret; + hidpp = hid_get_drvdata(hdev); + switch (hidpp_report->report_id) { case REPORT_ID_HIDPP_SHORT: fields_count = HIDPP_REPORT_SHORT_LENGTH; @@ -153,6 +160,9 @@ static int __hidpp_send_report(struct hid_device *hdev, case REPORT_ID_HIDPP_LONG: fields_count = HIDPP_REPORT_LONG_LENGTH; break; + case REPORT_ID_HIDPP_VERY_LONG: + fields_count = HIDPP_REPORT_VERY_LONG_LENGTH; + break; default: return -ENODEV; } @@ -163,9 +173,13 @@ static int __hidpp_send_report(struct hid_device *hdev, */ hidpp_report->device_index = 0xff; - ret = hid_hw_raw_request(hdev, hidpp_report->report_id, - (u8 *)hidpp_report, fields_count, HID_OUTPUT_REPORT, - HID_REQ_SET_REPORT); + if (hidpp->quirks & HIDPP_QUIRK_FORCE_OUTPUT_REPORTS) { + ret = hid_hw_output_report(hdev, (u8 *)hidpp_report, fields_count); + } else { + ret = hid_hw_raw_request(hdev, hidpp_report->report_id, + (u8 *)hidpp_report, fields_count, HID_OUTPUT_REPORT, + HID_REQ_SET_REPORT); + } return ret == fields_count ? 0 : -1; } @@ -217,8 +231,9 @@ static int hidpp_send_message_sync(struct hidpp_device *hidpp, goto exit; } - if (response->report_id == REPORT_ID_HIDPP_LONG && - response->fap.feature_index == HIDPP20_ERROR) { + if ((response->report_id == REPORT_ID_HIDPP_LONG || + response->report_id == REPORT_ID_HIDPP_VERY_LONG) && + response->fap.feature_index == HIDPP20_ERROR) { ret = response->fap.params[1]; dbg_hid("%s:got hidpp 2.0 error %02X\n", __func__, ret); goto exit; @@ -243,7 +258,11 @@ static int hidpp_send_fap_command_sync(struct hidpp_device *hidpp, message = kzalloc(sizeof(struct hidpp_report), GFP_KERNEL); if (!message) return -ENOMEM; - message->report_id = REPORT_ID_HIDPP_LONG; + + if (param_count > (HIDPP_REPORT_LONG_LENGTH - 4)) + message->report_id = REPORT_ID_HIDPP_VERY_LONG; + else + message->report_id = REPORT_ID_HIDPP_LONG; message->fap.feature_index = feat_index; message->fap.funcindex_clientid = funcindex_clientid; memcpy(&message->fap.params, params, param_count); @@ -258,13 +277,23 @@ static int hidpp_send_rap_command_sync(struct hidpp_device *hidpp_dev, struct hidpp_report *response) { struct hidpp_report *message; - int ret; + int ret, max_count; - if ((report_id != REPORT_ID_HIDPP_SHORT) && - (report_id != REPORT_ID_HIDPP_LONG)) + switch (report_id) { + case REPORT_ID_HIDPP_SHORT: + max_count = HIDPP_REPORT_SHORT_LENGTH - 4; + break; + case REPORT_ID_HIDPP_LONG: + max_count = HIDPP_REPORT_LONG_LENGTH - 4; + break; + case REPORT_ID_HIDPP_VERY_LONG: + max_count = HIDPP_REPORT_VERY_LONG_LENGTH - 4; + break; + default: return -EINVAL; + } - if (param_count > sizeof(message->rap.params)) + if (param_count > max_count) return -EINVAL; message = kzalloc(sizeof(struct hidpp_report), GFP_KERNEL); @@ -508,10 +537,19 @@ static int hidpp_devicenametype_get_device_name(struct hidpp_device *hidpp, if (ret) return ret; - if (response.report_id == REPORT_ID_HIDPP_LONG) + switch (response.report_id) { + case REPORT_ID_HIDPP_VERY_LONG: + count = HIDPP_REPORT_VERY_LONG_LENGTH - 4; + break; + case REPORT_ID_HIDPP_LONG: count = HIDPP_REPORT_LONG_LENGTH - 4; - else + break; + case REPORT_ID_HIDPP_SHORT: count = HIDPP_REPORT_SHORT_LENGTH - 4; + break; + default: + return -EPROTO; + } if (len_buf < count) count = len_buf; @@ -1257,6 +1295,131 @@ static int k400_connect(struct hid_device *hdev, bool connected) return k400_disable_tap_to_click(hidpp); } +/* ------------------------------------------------------------------------- */ +/* Logitech G920 Driving Force Racing Wheel for Xbox One */ +/* ------------------------------------------------------------------------- */ + +#define HIDPP_PAGE_G920_FORCE_FEEDBACK 0x8123 + +/* Using session ID = 1 */ +#define CMD_G920_FORCE_GET_APERTURE 0x51 +#define CMD_G920_FORCE_SET_APERTURE 0x61 + +struct g920_private_data { + u8 force_feature; + u16 range; +}; + +static ssize_t g920_range_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct hid_device *hid = to_hid_device(dev); + struct hidpp_device *hidpp = hid_get_drvdata(hid); + struct g920_private_data *pdata; + + pdata = hidpp->private_data; + if (!pdata) { + hid_err(hid, "Private driver data not found!\n"); + return -EINVAL; + } + + return scnprintf(buf, PAGE_SIZE, "%u\n", pdata->range); +} + +static ssize_t g920_range_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct hid_device *hid = to_hid_device(dev); + struct hidpp_device *hidpp = hid_get_drvdata(hid); + struct g920_private_data *pdata; + struct hidpp_report response; + u8 params[2]; + int ret; + u16 range = simple_strtoul(buf, NULL, 10); + + pdata = hidpp->private_data; + if (!pdata) { + hid_err(hid, "Private driver data not found!\n"); + return -EINVAL; + } + + if (range < 180) + range = 180; + else if (range > 900) + range = 900; + + params[0] = range >> 8; + params[1] = range & 0x00FF; + + ret = hidpp_send_fap_command_sync(hidpp, pdata->force_feature, + CMD_G920_FORCE_SET_APERTURE, params, 2, &response); + if (ret) + return ret; + + pdata->range = range; + return count; +} + +static DEVICE_ATTR(range, S_IRUSR | S_IWUSR | S_IRGRP | S_IWGRP | S_IROTH, g920_range_show, g920_range_store); + +static int g920_allocate(struct hid_device *hdev) +{ + struct hidpp_device *hidpp = hid_get_drvdata(hdev); + struct g920_private_data *pdata; + + pdata = devm_kzalloc(&hdev->dev, sizeof(struct g920_private_data), + GFP_KERNEL); + if (!pdata) + return -ENOMEM; + + hidpp->private_data = pdata; + + return 0; +} + +static int g920_get_config(struct hidpp_device *hidpp) +{ + struct g920_private_data *pdata = hidpp->private_data; + struct hidpp_report response; + u8 feature_type; + u8 feature_index; + int ret; + + pdata = hidpp->private_data; + if (!pdata) { + hid_err(hidpp->hid_dev, "Private driver data not found!\n"); + return -EINVAL; + } + + /* Find feature and store for later use */ + ret = hidpp_root_get_feature(hidpp, HIDPP_PAGE_G920_FORCE_FEEDBACK, + &feature_index, &feature_type); + if (ret) + return ret; + + pdata->force_feature = feature_index; + + /* Read current Range */ + ret = hidpp_send_fap_command_sync(hidpp, feature_index, + CMD_G920_FORCE_GET_APERTURE, NULL, 0, &response); + if (ret > 0) { + hid_err(hidpp->hid_dev, "%s: received protocol error 0x%02x\n", + __func__, ret); + return -EPROTO; + } + if (ret) + return ret; + + pdata->range = get_unaligned_be16(&response.fap.params[0]); + + /* Create sysfs interface */ + ret = device_create_file(&(hidpp->hid_dev->dev), &dev_attr_range); + if (ret) + hid_warn(hidpp->hid_dev, "Unable to create sysfs interface for \"range\", errno %d\n", ret); + + return 0; +} + /* -------------------------------------------------------------------------- */ /* Generic HID++ devices */ /* -------------------------------------------------------------------------- */ @@ -1276,6 +1439,25 @@ static int hidpp_input_mapping(struct hid_device *hdev, struct hid_input *hi, return 0; } +static int hidpp_input_mapped(struct hid_device *hdev, struct hid_input *hi, + struct hid_field *field, struct hid_usage *usage, + unsigned long **bit, int *max) +{ + struct hidpp_device *hidpp = hid_get_drvdata(hdev); + + /* Ensure that Logitech G920 is not given a default fuzz/flat value */ + if (hidpp->quirks & HIDPP_QUIRK_CLASS_G920) { + if (usage->type == EV_ABS && (usage->code == ABS_X || + usage->code == ABS_Y || usage->code == ABS_Z || + usage->code == ABS_RZ)) { + field->application = HID_GD_MULTIAXIS; + } + } + + return 0; +} + + static void hidpp_populate_input(struct hidpp_device *hidpp, struct input_dev *input, bool origin_is_hid_core) { @@ -1347,6 +1529,14 @@ static int hidpp_raw_event(struct hid_device *hdev, struct hid_report *report, /* Generic HID++ processing. */ switch (data[0]) { + case REPORT_ID_HIDPP_VERY_LONG: + if (size != HIDPP_REPORT_VERY_LONG_LENGTH) { + hid_err(hdev, "received hid++ report of bad size (%d)", + size); + return 1; + } + ret = hidpp_raw_hidpp_event(hidpp, data, size); + break; case REPORT_ID_HIDPP_LONG: if (size != HIDPP_REPORT_LONG_LENGTH) { hid_err(hdev, "received hid++ report of bad size (%d)", @@ -1393,10 +1583,12 @@ static void hidpp_overwrite_name(struct hid_device *hdev, bool use_unifying) else name = hidpp_get_device_name(hidpp); - if (!name) + if (!name) { hid_err(hdev, "unable to retrieve the name of the device"); - else + } else { + dbg_hid("HID++: Got name: %s\n", name); snprintf(hdev->name, sizeof(hdev->name), "%s", name); + } kfree(name); } @@ -1547,6 +1739,10 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id) ret = k400_allocate(hdev); if (ret) goto allocate_fail; + } else if (hidpp->quirks & HIDPP_QUIRK_CLASS_G920) { + ret = g920_allocate(hdev); + if (ret) + goto allocate_fail; } INIT_WORK(&hidpp->work, delayed_work_cb); @@ -1559,6 +1755,25 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id) goto hid_parse_fail; } + if (hidpp->quirks & HIDPP_QUIRK_NO_HIDINPUT) + connect_mask &= ~HID_CONNECT_HIDINPUT; + + if (hidpp->quirks & HIDPP_QUIRK_CLASS_G920) { + ret = hid_hw_start(hdev, connect_mask); + if (ret) { + hid_err(hdev, "hw start failed\n"); + goto hid_hw_start_fail; + } + ret = hid_hw_open(hdev); + if (ret < 0) { + dev_err(&hdev->dev, "%s:hid_hw_open returned error:%d\n", + __func__, ret); + hid_hw_stop(hdev); + goto hid_hw_start_fail; + } + } + + /* Allow incoming packets */ hid_device_io_start(hdev); @@ -1567,8 +1782,7 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id) if (!connected) { ret = -ENODEV; hid_err(hdev, "Device not connected"); - hid_device_io_stop(hdev); - goto hid_parse_fail; + goto hid_hw_open_failed; } hid_info(hdev, "HID++ %u.%u device connected.\n", @@ -1581,19 +1795,22 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id) if (connected && (hidpp->quirks & HIDPP_QUIRK_CLASS_WTP)) { ret = wtp_get_config(hidpp); if (ret) - goto hid_parse_fail; + goto hid_hw_open_failed; + } else if (connected && (hidpp->quirks & HIDPP_QUIRK_CLASS_G920)) { + ret = g920_get_config(hidpp); + if (ret) + goto hid_hw_open_failed; } /* Block incoming packets */ hid_device_io_stop(hdev); - if (hidpp->quirks & HIDPP_QUIRK_NO_HIDINPUT) - connect_mask &= ~HID_CONNECT_HIDINPUT; - - ret = hid_hw_start(hdev, connect_mask); - if (ret) { - hid_err(hdev, "%s:hid_hw_start returned error\n", __func__); - goto hid_hw_start_fail; + if (!(hidpp->quirks & HIDPP_QUIRK_CLASS_G920)) { + ret = hid_hw_start(hdev, connect_mask); + if (ret) { + hid_err(hdev, "%s:hid_hw_start returned error\n", __func__); + goto hid_hw_start_fail; + } } if (hidpp->quirks & HIDPP_QUIRK_CONNECT_EVENTS) { @@ -1605,6 +1822,13 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id) return ret; +hid_hw_open_failed: + hid_device_io_stop(hdev); + if (hidpp->quirks & HIDPP_QUIRK_CLASS_G920) { + device_remove_file(&hdev->dev, &dev_attr_range); + hid_hw_close(hdev); + hid_hw_stop(hdev); + } hid_hw_start_fail: hid_parse_fail: cancel_work_sync(&hidpp->work); @@ -1618,9 +1842,13 @@ static void hidpp_remove(struct hid_device *hdev) { struct hidpp_device *hidpp = hid_get_drvdata(hdev); + if (hidpp->quirks & HIDPP_QUIRK_CLASS_G920) { + device_remove_file(&hdev->dev, &dev_attr_range); + hid_hw_close(hdev); + } + hid_hw_stop(hdev); cancel_work_sync(&hidpp->work); mutex_destroy(&hidpp->send_mutex); - hid_hw_stop(hdev); } static const struct hid_device_id hidpp_devices[] = { @@ -1648,6 +1876,9 @@ static const struct hid_device_id hidpp_devices[] = { { HID_DEVICE(BUS_USB, HID_GROUP_LOGITECH_DJ_DEVICE, USB_VENDOR_ID_LOGITECH, HID_ANY_ID)}, + + { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_G920_WHEEL), + .driver_data = HIDPP_QUIRK_CLASS_G920 | HIDPP_QUIRK_FORCE_OUTPUT_REPORTS}, {} }; @@ -1661,6 +1892,7 @@ static struct hid_driver hidpp_driver = { .raw_event = hidpp_raw_event, .input_configured = hidpp_input_configured, .input_mapping = hidpp_input_mapping, + .input_mapped = hidpp_input_mapped, }; module_hid_driver(hidpp_driver); diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 3d664d01305e..296d4991560e 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -272,7 +272,7 @@ static ssize_t mt_show_quirks(struct device *dev, struct device_attribute *attr, char *buf) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct mt_device *td = hid_get_drvdata(hdev); return sprintf(buf, "%u\n", td->mtclass.quirks); @@ -282,7 +282,7 @@ static ssize_t mt_set_quirks(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct mt_device *td = hid_get_drvdata(hdev); unsigned long val; @@ -357,8 +357,19 @@ static void mt_feature_mapping(struct hid_device *hdev, break; } - td->inputmode = field->report->id; - td->inputmode_index = usage->usage_index; + if (td->inputmode < 0) { + td->inputmode = field->report->id; + td->inputmode_index = usage->usage_index; + } else { + /* + * Some elan panels wrongly declare 2 input mode + * features, and silently ignore when we set the + * value in the second field. Skip the second feature + * and hope for the best. + */ + dev_info(&hdev->dev, + "Ignoring the extra HID_DG_INPUTMODE\n"); + } break; case HID_DG_CONTACTMAX: @@ -486,6 +497,11 @@ static int mt_touch_input_mapping(struct hid_device *hdev, struct hid_input *hi, mt_store_field(usage, td, hi); return 1; case HID_DG_CONFIDENCE: + if (cls->name == MT_CLS_WIN_8 && + field->application == HID_DG_TOUCHPAD) { + cls->quirks &= ~MT_QUIRK_ALWAYS_VALID; + cls->quirks |= MT_QUIRK_VALID_IS_CONFIDENCE; + } mt_store_field(usage, td, hi); return 1; case HID_DG_TIPSWITCH: diff --git a/drivers/hid/hid-ntrig.c b/drivers/hid/hid-ntrig.c index 756d1ef9bd99..1b0084d4af2e 100644 --- a/drivers/hid/hid-ntrig.c +++ b/drivers/hid/hid-ntrig.c @@ -173,7 +173,7 @@ static ssize_t show_phys_width(struct device *dev, struct device_attribute *attr, char *buf) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct ntrig_data *nd = hid_get_drvdata(hdev); return sprintf(buf, "%d\n", nd->sensor_physical_width); @@ -185,7 +185,7 @@ static ssize_t show_phys_height(struct device *dev, struct device_attribute *attr, char *buf) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct ntrig_data *nd = hid_get_drvdata(hdev); return sprintf(buf, "%d\n", nd->sensor_physical_height); @@ -197,7 +197,7 @@ static ssize_t show_log_width(struct device *dev, struct device_attribute *attr, char *buf) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct ntrig_data *nd = hid_get_drvdata(hdev); return sprintf(buf, "%d\n", nd->sensor_logical_width); @@ -209,7 +209,7 @@ static ssize_t show_log_height(struct device *dev, struct device_attribute *attr, char *buf) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct ntrig_data *nd = hid_get_drvdata(hdev); return sprintf(buf, "%d\n", nd->sensor_logical_height); @@ -221,7 +221,7 @@ static ssize_t show_min_width(struct device *dev, struct device_attribute *attr, char *buf) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct ntrig_data *nd = hid_get_drvdata(hdev); return sprintf(buf, "%d\n", nd->min_width * @@ -233,7 +233,7 @@ static ssize_t set_min_width(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct ntrig_data *nd = hid_get_drvdata(hdev); unsigned long val; @@ -256,7 +256,7 @@ static ssize_t show_min_height(struct device *dev, struct device_attribute *attr, char *buf) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct ntrig_data *nd = hid_get_drvdata(hdev); return sprintf(buf, "%d\n", nd->min_height * @@ -268,7 +268,7 @@ static ssize_t set_min_height(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct ntrig_data *nd = hid_get_drvdata(hdev); unsigned long val; @@ -292,7 +292,7 @@ static ssize_t show_activate_slack(struct device *dev, struct device_attribute *attr, char *buf) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct ntrig_data *nd = hid_get_drvdata(hdev); return sprintf(buf, "%d\n", nd->activate_slack); @@ -302,7 +302,7 @@ static ssize_t set_activate_slack(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct ntrig_data *nd = hid_get_drvdata(hdev); unsigned long val; @@ -325,7 +325,7 @@ static ssize_t show_activation_width(struct device *dev, struct device_attribute *attr, char *buf) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct ntrig_data *nd = hid_get_drvdata(hdev); return sprintf(buf, "%d\n", nd->activation_width * @@ -337,7 +337,7 @@ static ssize_t set_activation_width(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct ntrig_data *nd = hid_get_drvdata(hdev); unsigned long val; @@ -361,7 +361,7 @@ static ssize_t show_activation_height(struct device *dev, struct device_attribute *attr, char *buf) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct ntrig_data *nd = hid_get_drvdata(hdev); return sprintf(buf, "%d\n", nd->activation_height * @@ -373,7 +373,7 @@ static ssize_t set_activation_height(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct ntrig_data *nd = hid_get_drvdata(hdev); unsigned long val; @@ -397,7 +397,7 @@ static ssize_t show_deactivate_slack(struct device *dev, struct device_attribute *attr, char *buf) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct ntrig_data *nd = hid_get_drvdata(hdev); return sprintf(buf, "%d\n", -nd->deactivate_slack); @@ -407,7 +407,7 @@ static ssize_t set_deactivate_slack(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct ntrig_data *nd = hid_get_drvdata(hdev); unsigned long val; diff --git a/drivers/hid/hid-picolcd_leds.c b/drivers/hid/hid-picolcd_leds.c index e994f9c29012..a802b4f49c7b 100644 --- a/drivers/hid/hid-picolcd_leds.c +++ b/drivers/hid/hid-picolcd_leds.c @@ -66,7 +66,7 @@ static void picolcd_led_set_brightness(struct led_classdev *led_cdev, int i, state = 0; dev = led_cdev->dev->parent; - hdev = container_of(dev, struct hid_device, dev); + hdev = to_hid_device(dev); data = hid_get_drvdata(hdev); if (!data) return; @@ -93,7 +93,7 @@ static enum led_brightness picolcd_led_get_brightness(struct led_classdev *led_c int i, value = 0; dev = led_cdev->dev->parent; - hdev = container_of(dev, struct hid_device, dev); + hdev = to_hid_device(dev); data = hid_get_drvdata(hdev); for (i = 0; i < 8; i++) if (led_cdev == data->led[i]) { diff --git a/drivers/hid/hid-prodikeys.c b/drivers/hid/hid-prodikeys.c index 3a207c0ac0e3..f095bf8a3aa9 100644 --- a/drivers/hid/hid-prodikeys.c +++ b/drivers/hid/hid-prodikeys.c @@ -103,7 +103,7 @@ MODULE_PARM_DESC(enable, "Enable for the PC-MIDI virtual audio driver"); static ssize_t show_channel(struct device *dev, struct device_attribute *attr, char *buf) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct pk_device *pk = hid_get_drvdata(hdev); dbg_hid("pcmidi sysfs read channel=%u\n", pk->pm->midi_channel); @@ -116,7 +116,7 @@ static ssize_t show_channel(struct device *dev, static ssize_t store_channel(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct pk_device *pk = hid_get_drvdata(hdev); unsigned channel = 0; @@ -140,7 +140,7 @@ static struct device_attribute *sysfs_device_attr_channel = { static ssize_t show_sustain(struct device *dev, struct device_attribute *attr, char *buf) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct pk_device *pk = hid_get_drvdata(hdev); dbg_hid("pcmidi sysfs read sustain=%u\n", pk->pm->midi_sustain); @@ -153,7 +153,7 @@ static ssize_t show_sustain(struct device *dev, static ssize_t store_sustain(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct pk_device *pk = hid_get_drvdata(hdev); unsigned sustain = 0; @@ -179,7 +179,7 @@ static struct device_attribute *sysfs_device_attr_sustain = { static ssize_t show_octave(struct device *dev, struct device_attribute *attr, char *buf) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct pk_device *pk = hid_get_drvdata(hdev); dbg_hid("pcmidi sysfs read octave=%d\n", pk->pm->midi_octave); @@ -192,7 +192,7 @@ static ssize_t show_octave(struct device *dev, static ssize_t store_octave(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct pk_device *pk = hid_get_drvdata(hdev); int octave = 0; diff --git a/drivers/hid/hid-roccat-arvo.c b/drivers/hid/hid-roccat-arvo.c index 1948208fe038..329c5d1270f9 100644 --- a/drivers/hid/hid-roccat-arvo.c +++ b/drivers/hid/hid-roccat-arvo.c @@ -191,8 +191,7 @@ static ssize_t arvo_sysfs_write(struct file *fp, struct kobject *kobj, void const *buf, loff_t off, size_t count, size_t real_size, uint command) { - struct device *dev = - container_of(kobj, struct device, kobj)->parent->parent; + struct device *dev = kobj_to_dev(kobj)->parent->parent; struct arvo_device *arvo = hid_get_drvdata(dev_get_drvdata(dev)); struct usb_device *usb_dev = interface_to_usbdev(to_usb_interface(dev)); int retval; @@ -211,8 +210,7 @@ static ssize_t arvo_sysfs_read(struct file *fp, struct kobject *kobj, void *buf, loff_t off, size_t count, size_t real_size, uint command) { - struct device *dev = - container_of(kobj, struct device, kobj)->parent->parent; + struct device *dev = kobj_to_dev(kobj)->parent->parent; struct arvo_device *arvo = hid_get_drvdata(dev_get_drvdata(dev)); struct usb_device *usb_dev = interface_to_usbdev(to_usb_interface(dev)); int retval; diff --git a/drivers/hid/hid-roccat-common.c b/drivers/hid/hid-roccat-common.c index 02e28e9f4ea7..8155ac5fede2 100644 --- a/drivers/hid/hid-roccat-common.c +++ b/drivers/hid/hid-roccat-common.c @@ -134,8 +134,7 @@ ssize_t roccat_common2_sysfs_read(struct file *fp, struct kobject *kobj, char *buf, loff_t off, size_t count, size_t real_size, uint command) { - struct device *dev = - container_of(kobj, struct device, kobj)->parent->parent; + struct device *dev = kobj_to_dev(kobj)->parent->parent; struct roccat_common2_device *roccat_dev = hid_get_drvdata(dev_get_drvdata(dev)); struct usb_device *usb_dev = interface_to_usbdev(to_usb_interface(dev)); int retval; @@ -158,8 +157,7 @@ ssize_t roccat_common2_sysfs_write(struct file *fp, struct kobject *kobj, void const *buf, loff_t off, size_t count, size_t real_size, uint command) { - struct device *dev = - container_of(kobj, struct device, kobj)->parent->parent; + struct device *dev = kobj_to_dev(kobj)->parent->parent; struct roccat_common2_device *roccat_dev = hid_get_drvdata(dev_get_drvdata(dev)); struct usb_device *usb_dev = interface_to_usbdev(to_usb_interface(dev)); int retval; diff --git a/drivers/hid/hid-roccat-isku.c b/drivers/hid/hid-roccat-isku.c index bc62ed91e451..02db537f8f3e 100644 --- a/drivers/hid/hid-roccat-isku.c +++ b/drivers/hid/hid-roccat-isku.c @@ -121,8 +121,7 @@ static ssize_t isku_sysfs_read(struct file *fp, struct kobject *kobj, char *buf, loff_t off, size_t count, size_t real_size, uint command) { - struct device *dev = - container_of(kobj, struct device, kobj)->parent->parent; + struct device *dev = kobj_to_dev(kobj)->parent->parent; struct isku_device *isku = hid_get_drvdata(dev_get_drvdata(dev)); struct usb_device *usb_dev = interface_to_usbdev(to_usb_interface(dev)); int retval; @@ -144,8 +143,7 @@ static ssize_t isku_sysfs_write(struct file *fp, struct kobject *kobj, void const *buf, loff_t off, size_t count, size_t real_size, uint command) { - struct device *dev = - container_of(kobj, struct device, kobj)->parent->parent; + struct device *dev = kobj_to_dev(kobj)->parent->parent; struct isku_device *isku = hid_get_drvdata(dev_get_drvdata(dev)); struct usb_device *usb_dev = interface_to_usbdev(to_usb_interface(dev)); int retval; diff --git a/drivers/hid/hid-roccat-kone.c b/drivers/hid/hid-roccat-kone.c index c29265055ac1..bf4675a27396 100644 --- a/drivers/hid/hid-roccat-kone.c +++ b/drivers/hid/hid-roccat-kone.c @@ -269,8 +269,7 @@ static int kone_get_firmware_version(struct usb_device *usb_dev, int *result) static ssize_t kone_sysfs_read_settings(struct file *fp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) { - struct device *dev = - container_of(kobj, struct device, kobj)->parent->parent; + struct device *dev = kobj_to_dev(kobj)->parent->parent; struct kone_device *kone = hid_get_drvdata(dev_get_drvdata(dev)); if (off >= sizeof(struct kone_settings)) @@ -294,8 +293,7 @@ static ssize_t kone_sysfs_read_settings(struct file *fp, struct kobject *kobj, static ssize_t kone_sysfs_write_settings(struct file *fp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) { - struct device *dev = - container_of(kobj, struct device, kobj)->parent->parent; + struct device *dev = kobj_to_dev(kobj)->parent->parent; struct kone_device *kone = hid_get_drvdata(dev_get_drvdata(dev)); struct usb_device *usb_dev = interface_to_usbdev(to_usb_interface(dev)); int retval = 0, difference, old_profile; @@ -332,8 +330,7 @@ static BIN_ATTR(settings, 0660, kone_sysfs_read_settings, static ssize_t kone_sysfs_read_profilex(struct file *fp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) { - struct device *dev = - container_of(kobj, struct device, kobj)->parent->parent; + struct device *dev = kobj_to_dev(kobj)->parent->parent; struct kone_device *kone = hid_get_drvdata(dev_get_drvdata(dev)); if (off >= sizeof(struct kone_profile)) @@ -353,8 +350,7 @@ static ssize_t kone_sysfs_read_profilex(struct file *fp, static ssize_t kone_sysfs_write_profilex(struct file *fp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) { - struct device *dev = - container_of(kobj, struct device, kobj)->parent->parent; + struct device *dev = kobj_to_dev(kobj)->parent->parent; struct kone_device *kone = hid_get_drvdata(dev_get_drvdata(dev)); struct usb_device *usb_dev = interface_to_usbdev(to_usb_interface(dev)); struct kone_profile *profile; diff --git a/drivers/hid/hid-roccat-koneplus.c b/drivers/hid/hid-roccat-koneplus.c index 5e99fcdc71b9..09e8fc72aa1d 100644 --- a/drivers/hid/hid-roccat-koneplus.c +++ b/drivers/hid/hid-roccat-koneplus.c @@ -87,8 +87,7 @@ static ssize_t koneplus_sysfs_read(struct file *fp, struct kobject *kobj, char *buf, loff_t off, size_t count, size_t real_size, uint command) { - struct device *dev = - container_of(kobj, struct device, kobj)->parent->parent; + struct device *dev = kobj_to_dev(kobj)->parent->parent; struct koneplus_device *koneplus = hid_get_drvdata(dev_get_drvdata(dev)); struct usb_device *usb_dev = interface_to_usbdev(to_usb_interface(dev)); int retval; @@ -113,8 +112,7 @@ static ssize_t koneplus_sysfs_write(struct file *fp, struct kobject *kobj, void const *buf, loff_t off, size_t count, size_t real_size, uint command) { - struct device *dev = - container_of(kobj, struct device, kobj)->parent->parent; + struct device *dev = kobj_to_dev(kobj)->parent->parent; struct koneplus_device *koneplus = hid_get_drvdata(dev_get_drvdata(dev)); struct usb_device *usb_dev = interface_to_usbdev(to_usb_interface(dev)); int retval; @@ -193,8 +191,7 @@ static ssize_t koneplus_sysfs_read_profilex_settings(struct file *fp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) { - struct device *dev = - container_of(kobj, struct device, kobj)->parent->parent; + struct device *dev = kobj_to_dev(kobj)->parent->parent; struct usb_device *usb_dev = interface_to_usbdev(to_usb_interface(dev)); ssize_t retval; @@ -212,8 +209,7 @@ static ssize_t koneplus_sysfs_read_profilex_buttons(struct file *fp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) { - struct device *dev = - container_of(kobj, struct device, kobj)->parent->parent; + struct device *dev = kobj_to_dev(kobj)->parent->parent; struct usb_device *usb_dev = interface_to_usbdev(to_usb_interface(dev)); ssize_t retval; diff --git a/drivers/hid/hid-roccat-kovaplus.c b/drivers/hid/hid-roccat-kovaplus.c index 966047711fbf..43617fb28b87 100644 --- a/drivers/hid/hid-roccat-kovaplus.c +++ b/drivers/hid/hid-roccat-kovaplus.c @@ -128,8 +128,7 @@ static ssize_t kovaplus_sysfs_read(struct file *fp, struct kobject *kobj, char *buf, loff_t off, size_t count, size_t real_size, uint command) { - struct device *dev = - container_of(kobj, struct device, kobj)->parent->parent; + struct device *dev = kobj_to_dev(kobj)->parent->parent; struct kovaplus_device *kovaplus = hid_get_drvdata(dev_get_drvdata(dev)); struct usb_device *usb_dev = interface_to_usbdev(to_usb_interface(dev)); int retval; @@ -154,8 +153,7 @@ static ssize_t kovaplus_sysfs_write(struct file *fp, struct kobject *kobj, void const *buf, loff_t off, size_t count, size_t real_size, uint command) { - struct device *dev = - container_of(kobj, struct device, kobj)->parent->parent; + struct device *dev = kobj_to_dev(kobj)->parent->parent; struct kovaplus_device *kovaplus = hid_get_drvdata(dev_get_drvdata(dev)); struct usb_device *usb_dev = interface_to_usbdev(to_usb_interface(dev)); int retval; @@ -221,8 +219,7 @@ static ssize_t kovaplus_sysfs_read_profilex_settings(struct file *fp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) { - struct device *dev = - container_of(kobj, struct device, kobj)->parent->parent; + struct device *dev = kobj_to_dev(kobj)->parent->parent; struct usb_device *usb_dev = interface_to_usbdev(to_usb_interface(dev)); ssize_t retval; @@ -240,8 +237,7 @@ static ssize_t kovaplus_sysfs_read_profilex_buttons(struct file *fp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) { - struct device *dev = - container_of(kobj, struct device, kobj)->parent->parent; + struct device *dev = kobj_to_dev(kobj)->parent->parent; struct usb_device *usb_dev = interface_to_usbdev(to_usb_interface(dev)); ssize_t retval; diff --git a/drivers/hid/hid-roccat-lua.c b/drivers/hid/hid-roccat-lua.c index 65e2e76bf2fe..ac1a7313e259 100644 --- a/drivers/hid/hid-roccat-lua.c +++ b/drivers/hid/hid-roccat-lua.c @@ -30,7 +30,7 @@ static ssize_t lua_sysfs_read(struct file *fp, struct kobject *kobj, char *buf, loff_t off, size_t count, size_t real_size, uint command) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct lua_device *lua = hid_get_drvdata(dev_get_drvdata(dev)); struct usb_device *usb_dev = interface_to_usbdev(to_usb_interface(dev)); int retval; @@ -52,7 +52,7 @@ static ssize_t lua_sysfs_write(struct file *fp, struct kobject *kobj, void const *buf, loff_t off, size_t count, size_t real_size, uint command) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct lua_device *lua = hid_get_drvdata(dev_get_drvdata(dev)); struct usb_device *usb_dev = interface_to_usbdev(to_usb_interface(dev)); int retval; diff --git a/drivers/hid/hid-roccat-pyra.c b/drivers/hid/hid-roccat-pyra.c index 47d7e74231e5..b30aa7b82bf8 100644 --- a/drivers/hid/hid-roccat-pyra.c +++ b/drivers/hid/hid-roccat-pyra.c @@ -90,8 +90,7 @@ static ssize_t pyra_sysfs_read(struct file *fp, struct kobject *kobj, char *buf, loff_t off, size_t count, size_t real_size, uint command) { - struct device *dev = - container_of(kobj, struct device, kobj)->parent->parent; + struct device *dev = kobj_to_dev(kobj)->parent->parent; struct pyra_device *pyra = hid_get_drvdata(dev_get_drvdata(dev)); struct usb_device *usb_dev = interface_to_usbdev(to_usb_interface(dev)); int retval; @@ -116,8 +115,7 @@ static ssize_t pyra_sysfs_write(struct file *fp, struct kobject *kobj, void const *buf, loff_t off, size_t count, size_t real_size, uint command) { - struct device *dev = - container_of(kobj, struct device, kobj)->parent->parent; + struct device *dev = kobj_to_dev(kobj)->parent->parent; struct pyra_device *pyra = hid_get_drvdata(dev_get_drvdata(dev)); struct usb_device *usb_dev = interface_to_usbdev(to_usb_interface(dev)); int retval; @@ -191,8 +189,7 @@ static ssize_t pyra_sysfs_read_profilex_settings(struct file *fp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) { - struct device *dev = - container_of(kobj, struct device, kobj)->parent->parent; + struct device *dev = kobj_to_dev(kobj)->parent->parent; struct usb_device *usb_dev = interface_to_usbdev(to_usb_interface(dev)); ssize_t retval; @@ -210,8 +207,7 @@ static ssize_t pyra_sysfs_read_profilex_buttons(struct file *fp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) { - struct device *dev = - container_of(kobj, struct device, kobj)->parent->parent; + struct device *dev = kobj_to_dev(kobj)->parent->parent; struct usb_device *usb_dev = interface_to_usbdev(to_usb_interface(dev)); ssize_t retval; @@ -248,8 +244,7 @@ static ssize_t pyra_sysfs_write_settings(struct file *fp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) { - struct device *dev = - container_of(kobj, struct device, kobj)->parent->parent; + struct device *dev = kobj_to_dev(kobj)->parent->parent; struct pyra_device *pyra = hid_get_drvdata(dev_get_drvdata(dev)); struct usb_device *usb_dev = interface_to_usbdev(to_usb_interface(dev)); int retval = 0; diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c index 92870cdb52d9..58ed8f25ab21 100644 --- a/drivers/hid/hid-sensor-hub.c +++ b/drivers/hid/hid-sensor-hub.c @@ -794,6 +794,9 @@ static const struct hid_device_id sensor_hub_devices[] = { { HID_DEVICE(HID_BUS_ANY, HID_GROUP_SENSOR_HUB, USB_VENDOR_ID_ITE, USB_DEVICE_ID_ITE_LENOVO_YOGA2), .driver_data = HID_SENSOR_HUB_ENUM_QUIRK}, + { HID_DEVICE(HID_BUS_ANY, HID_GROUP_SENSOR_HUB, USB_VENDOR_ID_ITE, + USB_DEVICE_ID_ITE_LENOVO_YOGA900), + .driver_data = HID_SENSOR_HUB_ENUM_QUIRK}, { HID_DEVICE(HID_BUS_ANY, HID_GROUP_SENSOR_HUB, HID_ANY_ID, HID_ANY_ID) }, { } diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c index 774cd2210566..9b8db0e0ef1c 100644 --- a/drivers/hid/hid-sony.c +++ b/drivers/hid/hid-sony.c @@ -1028,6 +1028,7 @@ struct sony_sc { struct led_classdev *leds[MAX_LEDS]; unsigned long quirks; struct work_struct state_worker; + void(*send_output_report)(struct sony_sc*); struct power_supply *battery; struct power_supply_desc battery_desc; int device_id; @@ -1044,6 +1045,7 @@ struct sony_sc { __u8 battery_charging; __u8 battery_capacity; __u8 led_state[MAX_LEDS]; + __u8 resume_led_state[MAX_LEDS]; __u8 led_delay_on[MAX_LEDS]; __u8 led_delay_off[MAX_LEDS]; __u8 led_count; @@ -1137,11 +1139,11 @@ static __u8 *sony_report_fixup(struct hid_device *hdev, __u8 *rdesc, * the gyroscope values to corresponding axes so we need a * modified one. */ - if ((sc->quirks & DUALSHOCK4_CONTROLLER_USB) && *rsize == 467) { + if (sc->quirks & DUALSHOCK4_CONTROLLER_USB) { hid_info(hdev, "Using modified Dualshock 4 report descriptor with gyroscope axes\n"); rdesc = dualshock4_usb_rdesc; *rsize = sizeof(dualshock4_usb_rdesc); - } else if ((sc->quirks & DUALSHOCK4_CONTROLLER_BT) && *rsize == 357) { + } else if (sc->quirks & DUALSHOCK4_CONTROLLER_BT) { hid_info(hdev, "Using modified Dualshock 4 Bluetooth report descriptor\n"); rdesc = dualshock4_bt_rdesc; *rsize = sizeof(dualshock4_bt_rdesc); @@ -1549,7 +1551,7 @@ static void sony_led_set_brightness(struct led_classdev *led, enum led_brightness value) { struct device *dev = led->dev->parent; - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct sony_sc *drv_data; int n; @@ -1591,7 +1593,7 @@ static void sony_led_set_brightness(struct led_classdev *led, static enum led_brightness sony_led_get_brightness(struct led_classdev *led) { struct device *dev = led->dev->parent; - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct sony_sc *drv_data; int n; @@ -1614,7 +1616,7 @@ static int sony_led_blink_set(struct led_classdev *led, unsigned long *delay_on, unsigned long *delay_off) { struct device *dev = led->dev->parent; - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct sony_sc *drv_data = hid_get_drvdata(hdev); int n; __u8 new_on, new_off; @@ -1789,7 +1791,7 @@ error_leds: return ret; } -static void sixaxis_state_worker(struct work_struct *work) +static void sixaxis_send_output_report(struct sony_sc *sc) { static const union sixaxis_output_report_01 default_report = { .buf = { @@ -1803,7 +1805,6 @@ static void sixaxis_state_worker(struct work_struct *work) 0x00, 0x00, 0x00, 0x00, 0x00 } }; - struct sony_sc *sc = container_of(work, struct sony_sc, state_worker); struct sixaxis_output_report *report = (struct sixaxis_output_report *)sc->output_report_dmabuf; int n; @@ -1846,9 +1847,8 @@ static void sixaxis_state_worker(struct work_struct *work) HID_OUTPUT_REPORT, HID_REQ_SET_REPORT); } -static void dualshock4_state_worker(struct work_struct *work) +static void dualshock4_send_output_report(struct sony_sc *sc) { - struct sony_sc *sc = container_of(work, struct sony_sc, state_worker); struct hid_device *hdev = sc->hdev; __u8 *buf = sc->output_report_dmabuf; int offset; @@ -1893,9 +1893,8 @@ static void dualshock4_state_worker(struct work_struct *work) HID_OUTPUT_REPORT, HID_REQ_SET_REPORT); } -static void motion_state_worker(struct work_struct *work) +static void motion_send_output_report(struct sony_sc *sc) { - struct sony_sc *sc = container_of(work, struct sony_sc, state_worker); struct hid_device *hdev = sc->hdev; struct motion_output_report_02 *report = (struct motion_output_report_02 *)sc->output_report_dmabuf; @@ -1914,6 +1913,18 @@ static void motion_state_worker(struct work_struct *work) hid_hw_output_report(hdev, (__u8 *)report, MOTION_REPORT_0x02_SIZE); } +static inline void sony_send_output_report(struct sony_sc *sc) +{ + if (sc->send_output_report) + sc->send_output_report(sc); +} + +static void sony_state_worker(struct work_struct *work) +{ + struct sony_sc *sc = container_of(work, struct sony_sc, state_worker); + sc->send_output_report(sc); +} + static int sony_allocate_output_report(struct sony_sc *sc) { if ((sc->quirks & SIXAXIS_CONTROLLER) || @@ -2241,11 +2252,13 @@ static void sony_release_device_id(struct sony_sc *sc) } } -static inline void sony_init_work(struct sony_sc *sc, - void (*worker)(struct work_struct *)) +static inline void sony_init_output_report(struct sony_sc *sc, + void(*send_output_report)(struct sony_sc*)) { + sc->send_output_report = send_output_report; + if (!sc->worker_initialized) - INIT_WORK(&sc->state_worker, worker); + INIT_WORK(&sc->state_worker, sony_state_worker); sc->worker_initialized = 1; } @@ -2319,7 +2332,7 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id) hdev->quirks |= HID_QUIRK_NO_OUTPUT_REPORTS_ON_INTR_EP; hdev->quirks |= HID_QUIRK_SKIP_OUTPUT_REPORT_ID; ret = sixaxis_set_operational_usb(hdev); - sony_init_work(sc, sixaxis_state_worker); + sony_init_output_report(sc, sixaxis_send_output_report); } else if ((sc->quirks & SIXAXIS_CONTROLLER_BT) || (sc->quirks & NAVIGATION_CONTROLLER_BT)) { /* @@ -2328,7 +2341,7 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id) */ hdev->quirks |= HID_QUIRK_NO_OUTPUT_REPORTS_ON_INTR_EP; ret = sixaxis_set_operational_bt(hdev); - sony_init_work(sc, sixaxis_state_worker); + sony_init_output_report(sc, sixaxis_send_output_report); } else if (sc->quirks & DUALSHOCK4_CONTROLLER) { if (sc->quirks & DUALSHOCK4_CONTROLLER_BT) { /* @@ -2343,9 +2356,9 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id) } } - sony_init_work(sc, dualshock4_state_worker); + sony_init_output_report(sc, dualshock4_send_output_report); } else if (sc->quirks & MOTION_CONTROLLER) { - sony_init_work(sc, motion_state_worker); + sony_init_output_report(sc, motion_send_output_report); } else { ret = 0; } @@ -2421,6 +2434,56 @@ static void sony_remove(struct hid_device *hdev) hid_hw_stop(hdev); } +#ifdef CONFIG_PM + +static int sony_suspend(struct hid_device *hdev, pm_message_t message) +{ + /* + * On suspend save the current LED state, + * stop running force-feedback and blank the LEDS. + */ + if (SONY_LED_SUPPORT || SONY_FF_SUPPORT) { + struct sony_sc *sc = hid_get_drvdata(hdev); + +#ifdef CONFIG_SONY_FF + sc->left = sc->right = 0; +#endif + + memcpy(sc->resume_led_state, sc->led_state, + sizeof(sc->resume_led_state)); + memset(sc->led_state, 0, sizeof(sc->led_state)); + + sony_send_output_report(sc); + } + + return 0; +} + +static int sony_resume(struct hid_device *hdev) +{ + /* Restore the state of controller LEDs on resume */ + if (SONY_LED_SUPPORT) { + struct sony_sc *sc = hid_get_drvdata(hdev); + + memcpy(sc->led_state, sc->resume_led_state, + sizeof(sc->led_state)); + + /* + * The Sixaxis and navigation controllers on USB need to be + * reinitialized on resume or they won't behave properly. + */ + if ((sc->quirks & SIXAXIS_CONTROLLER_USB) || + (sc->quirks & NAVIGATION_CONTROLLER_USB)) + sixaxis_set_operational_usb(sc->hdev); + + sony_set_leds(sc); + } + + return 0; +} + +#endif + static const struct hid_device_id sony_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS3_CONTROLLER), .driver_data = SIXAXIS_CONTROLLER_USB }, @@ -2470,7 +2533,13 @@ static struct hid_driver sony_driver = { .probe = sony_probe, .remove = sony_remove, .report_fixup = sony_report_fixup, - .raw_event = sony_raw_event + .raw_event = sony_raw_event, + +#ifdef CONFIG_PM + .suspend = sony_suspend, + .resume = sony_resume, + .reset_resume = sony_resume, +#endif }; static int __init sony_init(void) diff --git a/drivers/hid/hid-steelseries.c b/drivers/hid/hid-steelseries.c index 3edd4ac36494..ec18768b124a 100644 --- a/drivers/hid/hid-steelseries.c +++ b/drivers/hid/hid-steelseries.c @@ -141,7 +141,7 @@ static void steelseries_srws1_led_all_set_brightness(struct led_classdev *led_cd enum led_brightness value) { struct device *dev = led_cdev->dev->parent; - struct hid_device *hid = container_of(dev, struct hid_device, dev); + struct hid_device *hid = to_hid_device(dev); struct steelseries_srws1_data *drv_data = hid_get_drvdata(hid); if (!drv_data) { @@ -160,7 +160,7 @@ static void steelseries_srws1_led_all_set_brightness(struct led_classdev *led_cd static enum led_brightness steelseries_srws1_led_all_get_brightness(struct led_classdev *led_cdev) { struct device *dev = led_cdev->dev->parent; - struct hid_device *hid = container_of(dev, struct hid_device, dev); + struct hid_device *hid = to_hid_device(dev); struct steelseries_srws1_data *drv_data; drv_data = hid_get_drvdata(hid); @@ -177,7 +177,7 @@ static void steelseries_srws1_led_set_brightness(struct led_classdev *led_cdev, enum led_brightness value) { struct device *dev = led_cdev->dev->parent; - struct hid_device *hid = container_of(dev, struct hid_device, dev); + struct hid_device *hid = to_hid_device(dev); struct steelseries_srws1_data *drv_data = hid_get_drvdata(hid); int i, state = 0; @@ -205,7 +205,7 @@ static void steelseries_srws1_led_set_brightness(struct led_classdev *led_cdev, static enum led_brightness steelseries_srws1_led_get_brightness(struct led_classdev *led_cdev) { struct device *dev = led_cdev->dev->parent; - struct hid_device *hid = container_of(dev, struct hid_device, dev); + struct hid_device *hid = to_hid_device(dev); struct steelseries_srws1_data *drv_data; int i, value = 0; diff --git a/drivers/hid/hid-wiimote-modules.c b/drivers/hid/hid-wiimote-modules.c index 05e23c417d50..4390eee2ce84 100644 --- a/drivers/hid/hid-wiimote-modules.c +++ b/drivers/hid/hid-wiimote-modules.c @@ -296,14 +296,12 @@ static const struct wiimod_ops wiimod_battery = { static enum led_brightness wiimod_led_get(struct led_classdev *led_dev) { - struct wiimote_data *wdata; struct device *dev = led_dev->dev->parent; + struct wiimote_data *wdata = dev_to_wii(dev); int i; unsigned long flags; bool value = false; - wdata = hid_get_drvdata(container_of(dev, struct hid_device, dev)); - for (i = 0; i < 4; ++i) { if (wdata->leds[i] == led_dev) { spin_lock_irqsave(&wdata->state.lock, flags); @@ -319,14 +317,12 @@ static enum led_brightness wiimod_led_get(struct led_classdev *led_dev) static void wiimod_led_set(struct led_classdev *led_dev, enum led_brightness value) { - struct wiimote_data *wdata; struct device *dev = led_dev->dev->parent; + struct wiimote_data *wdata = dev_to_wii(dev); int i; unsigned long flags; __u8 state, flag; - wdata = hid_get_drvdata(container_of(dev, struct hid_device, dev)); - for (i = 0; i < 4; ++i) { if (wdata->leds[i] == led_dev) { flag = WIIPROTO_FLAG_LED(i + 1); diff --git a/drivers/hid/hid-wiimote.h b/drivers/hid/hid-wiimote.h index 875694d43e4d..510ca77fe14e 100644 --- a/drivers/hid/hid-wiimote.h +++ b/drivers/hid/hid-wiimote.h @@ -256,8 +256,7 @@ enum wiiproto_reqs { WIIPROTO_REQ_MAX }; -#define dev_to_wii(pdev) hid_get_drvdata(container_of(pdev, struct hid_device, \ - dev)) +#define dev_to_wii(pdev) hid_get_drvdata(to_hid_device(pdev)) void __wiimote_schedule(struct wiimote_data *wdata); diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c index 10bd8e6e4c9c..b9216938a718 100644 --- a/drivers/hid/i2c-hid/i2c-hid.c +++ b/drivers/hid/i2c-hid/i2c-hid.c @@ -151,6 +151,7 @@ struct i2c_hid { struct i2c_hid_platform_data pdata; bool irq_wake_enabled; + struct mutex reset_lock; }; static int __i2c_hid_command(struct i2c_client *client, @@ -356,9 +357,16 @@ static int i2c_hid_hwreset(struct i2c_client *client) i2c_hid_dbg(ihid, "%s\n", __func__); + /* + * This prevents sending feature reports while the device is + * being reset. Otherwise we may lose the reset complete + * interrupt. + */ + mutex_lock(&ihid->reset_lock); + ret = i2c_hid_set_power(client, I2C_HID_PWR_ON); if (ret) - return ret; + goto out_unlock; i2c_hid_dbg(ihid, "resetting...\n"); @@ -366,10 +374,11 @@ static int i2c_hid_hwreset(struct i2c_client *client) if (ret) { dev_err(&client->dev, "failed to reset device.\n"); i2c_hid_set_power(client, I2C_HID_PWR_SLEEP); - return ret; } - return 0; +out_unlock: + mutex_unlock(&ihid->reset_lock); + return ret; } static void i2c_hid_get_input(struct i2c_hid *ihid) @@ -587,12 +596,15 @@ static int i2c_hid_output_raw_report(struct hid_device *hid, __u8 *buf, size_t count, unsigned char report_type, bool use_data) { struct i2c_client *client = hid->driver_data; + struct i2c_hid *ihid = i2c_get_clientdata(client); int report_id = buf[0]; int ret; if (report_type == HID_INPUT_REPORT) return -EINVAL; + mutex_lock(&ihid->reset_lock); + if (report_id) { buf++; count--; @@ -605,6 +617,8 @@ static int i2c_hid_output_raw_report(struct hid_device *hid, __u8 *buf, if (report_id && ret >= 0) ret++; /* add report_id to the number of transfered bytes */ + mutex_unlock(&ihid->reset_lock); + return ret; } @@ -990,6 +1004,7 @@ static int i2c_hid_probe(struct i2c_client *client, ihid->wHIDDescRegister = cpu_to_le16(hidRegister); init_waitqueue_head(&ihid->wait); + mutex_init(&ihid->reset_lock); /* we need to allocate the command buffer without knowing the maximum * size of the reports. Let's use HID_MIN_BUFFER_SIZE, then we do the @@ -1184,7 +1199,6 @@ MODULE_DEVICE_TABLE(i2c, i2c_hid_id_table); static struct i2c_driver i2c_hid_driver = { .driver = { .name = "i2c_hid", - .owner = THIS_MODULE, .pm = &i2c_hid_pm, .acpi_match_table = ACPI_PTR(i2c_hid_acpi_match), .of_match_table = of_match_ptr(i2c_hid_of_match), diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c index 36712e9f56c2..ad71160b9ea4 100644 --- a/drivers/hid/usbhid/hid-core.c +++ b/drivers/hid/usbhid/hid-core.c @@ -274,10 +274,10 @@ static void hid_irq_in(struct urb *urb) switch (urb->status) { case 0: /* success */ - usbhid_mark_busy(usbhid); usbhid->retry_delay = 0; if ((hid->quirks & HID_QUIRK_ALWAYS_POLL) && !hid->open) break; + usbhid_mark_busy(usbhid); if (!test_bit(HID_RESUME_RUNNING, &usbhid->iofl)) { hid_input_report(urb->context, HID_INPUT_REPORT, urb->transfer_buffer, @@ -477,8 +477,6 @@ static void hid_ctrl(struct urb *urb) struct usbhid_device *usbhid = hid->driver_data; int unplug = 0, status = urb->status; - spin_lock(&usbhid->lock); - switch (status) { case 0: /* success */ if (usbhid->ctrl[usbhid->ctrltail].dir == USB_DIR_IN) @@ -498,6 +496,8 @@ static void hid_ctrl(struct urb *urb) hid_warn(urb->dev, "ctrl urb status %d received\n", status); } + spin_lock(&usbhid->lock); + if (unplug) { usbhid->ctrltail = usbhid->ctrlhead; } else { diff --git a/drivers/hid/usbhid/usbhid.h b/drivers/hid/usbhid/usbhid.h index 807922b49aa4..fa47d666cfcf 100644 --- a/drivers/hid/usbhid/usbhid.h +++ b/drivers/hid/usbhid/usbhid.h @@ -96,7 +96,7 @@ struct usbhid_device { }; #define hid_to_usb_dev(hid_dev) \ - container_of(hid_dev->dev.parent->parent, struct usb_device, dev) + to_usb_device(hid_dev->dev.parent->parent) #endif diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index e06af5b9f59e..5cb21dd91094 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -686,7 +686,7 @@ out: static ssize_t wacom_led_select_store(struct device *dev, int set_id, const char *buf, size_t count) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct wacom *wacom = hid_get_drvdata(hdev); unsigned int id; int err; @@ -714,7 +714,7 @@ static ssize_t wacom_led##SET_ID##_select_store(struct device *dev, \ static ssize_t wacom_led##SET_ID##_select_show(struct device *dev, \ struct device_attribute *attr, char *buf) \ { \ - struct hid_device *hdev = container_of(dev, struct hid_device, dev);\ + struct hid_device *hdev = to_hid_device(dev);\ struct wacom *wacom = hid_get_drvdata(hdev); \ return scnprintf(buf, PAGE_SIZE, "%d\n", \ wacom->led.select[SET_ID]); \ @@ -750,7 +750,7 @@ static ssize_t wacom_luminance_store(struct wacom *wacom, u8 *dest, static ssize_t wacom_##name##_luminance_store(struct device *dev, \ struct device_attribute *attr, const char *buf, size_t count) \ { \ - struct hid_device *hdev = container_of(dev, struct hid_device, dev);\ + struct hid_device *hdev = to_hid_device(dev);\ struct wacom *wacom = hid_get_drvdata(hdev); \ \ return wacom_luminance_store(wacom, &wacom->led.field, \ @@ -773,7 +773,7 @@ DEVICE_LUMINANCE_ATTR(buttons, img_lum); static ssize_t wacom_button_image_store(struct device *dev, int button_id, const char *buf, size_t count) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct wacom *wacom = hid_get_drvdata(hdev); int err; unsigned len; @@ -1097,7 +1097,7 @@ static ssize_t wacom_show_speed(struct device *dev, struct device_attribute *attr, char *buf) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct wacom *wacom = hid_get_drvdata(hdev); return snprintf(buf, PAGE_SIZE, "%i\n", wacom->wacom_wac.bt_high_speed); @@ -1107,7 +1107,7 @@ static ssize_t wacom_store_speed(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct hid_device *hdev = to_hid_device(dev); struct wacom *wacom = hid_get_drvdata(hdev); u8 new_speed; @@ -1130,8 +1130,8 @@ static ssize_t wacom_show_remote_mode(struct kobject *kobj, struct kobj_attribute *kattr, char *buf, int index) { - struct device *dev = container_of(kobj->parent, struct device, kobj); - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct device *dev = kobj_to_dev(kobj->parent); + struct hid_device *hdev = to_hid_device(dev); struct wacom *wacom = hid_get_drvdata(hdev); u8 mode; @@ -1241,8 +1241,8 @@ static ssize_t wacom_store_unpair_remote(struct kobject *kobj, const char *buf, size_t count) { unsigned char selector = 0; - struct device *dev = container_of(kobj->parent, struct device, kobj); - struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct device *dev = kobj_to_dev(kobj->parent); + struct hid_device *hdev = to_hid_device(dev); struct wacom *wacom = hid_get_drvdata(hdev); int err; @@ -1353,8 +1353,7 @@ static void wacom_clean_inputs(struct wacom *wacom) else input_free_device(wacom->wacom_wac.pad_input); } - if (wacom->remote_dir) - kobject_put(wacom->remote_dir); + kobject_put(wacom->remote_dir); wacom->wacom_wac.pen_input = NULL; wacom->wacom_wac.touch_input = NULL; wacom->wacom_wac.pad_input = NULL; diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 01a4f05c1642..99ef77fcfb80 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -34,6 +34,9 @@ */ #define WACOM_CONTACT_AREA_SCALE 2607 +static void wacom_report_numbered_buttons(struct input_dev *input_dev, + int button_count, int mask); + /* * Percent of battery capacity for Graphire. * 8th value means AC online and show 100% capacity. @@ -436,16 +439,142 @@ exit: static void wacom_intuos_schedule_prox_event(struct wacom_wac *wacom_wac) { struct wacom *wacom = container_of(wacom_wac, struct wacom, wacom_wac); + struct wacom_features *features = &wacom_wac->features; struct hid_report *r; struct hid_report_enum *re; re = &(wacom->hdev->report_enum[HID_FEATURE_REPORT]); - r = re->report_id_hash[WACOM_REPORT_INTUOSREAD]; + if (features->type == INTUOSHT2) + r = re->report_id_hash[WACOM_REPORT_INTUOSHT2_ID]; + else + r = re->report_id_hash[WACOM_REPORT_INTUOS_ID1]; if (r) { hid_hw_request(wacom->hdev, r, HID_REQ_GET_REPORT); } } +static int wacom_intuos_pad(struct wacom_wac *wacom) +{ + struct wacom_features *features = &wacom->features; + unsigned char *data = wacom->data; + struct input_dev *input = wacom->pad_input; + int i; + int buttons = 0, nbuttons = features->numbered_buttons; + int keys = 0, nkeys = 0; + int ring1 = 0, ring2 = 0; + int strip1 = 0, strip2 = 0; + bool prox = false; + + /* pad packets. Works as a second tool and is always in prox */ + if (!(data[0] == WACOM_REPORT_INTUOSPAD || data[0] == WACOM_REPORT_INTUOS5PAD || + data[0] == WACOM_REPORT_CINTIQPAD)) + return 0; + + if (features->type >= INTUOS4S && features->type <= INTUOS4L) { + buttons = (data[3] << 1) | (data[2] & 0x01); + ring1 = data[1]; + } else if (features->type == DTK) { + buttons = data[6]; + } else if (features->type == WACOM_13HD) { + buttons = (data[4] << 1) | (data[3] & 0x01); + } else if (features->type == WACOM_24HD) { + buttons = (data[8] << 8) | data[6]; + ring1 = data[1]; + ring2 = data[2]; + + /* + * Three "buttons" are available on the 24HD which are + * physically implemented as a touchstrip. Each button + * is approximately 3 bits wide with a 2 bit spacing. + * The raw touchstrip bits are stored at: + * ((data[3] & 0x1f) << 8) | data[4]) + */ + nkeys = 3; + keys = ((data[3] & 0x1C) ? 1<<2 : 0) | + ((data[4] & 0xE0) ? 1<<1 : 0) | + ((data[4] & 0x07) ? 1<<0 : 0); + } else if (features->type == WACOM_27QHD) { + nkeys = 3; + keys = data[2] & 0x07; + + input_report_abs(input, ABS_X, be16_to_cpup((__be16 *)&data[4])); + input_report_abs(input, ABS_Y, be16_to_cpup((__be16 *)&data[6])); + input_report_abs(input, ABS_Z, be16_to_cpup((__be16 *)&data[8])); + } else if (features->type == CINTIQ_HYBRID) { + /* + * Do not send hardware buttons under Android. They + * are already sent to the system through GPIO (and + * have different meaning). + * + * d-pad right -> data[4] & 0x10 + * d-pad up -> data[4] & 0x20 + * d-pad left -> data[4] & 0x40 + * d-pad down -> data[4] & 0x80 + * d-pad center -> data[3] & 0x01 + */ + buttons = (data[4] << 1) | (data[3] & 0x01); + } else if (features->type == CINTIQ_COMPANION_2) { + /* d-pad right -> data[4] & 0x10 + * d-pad up -> data[4] & 0x20 + * d-pad left -> data[4] & 0x40 + * d-pad down -> data[4] & 0x80 + * d-pad center -> data[3] & 0x01 + */ + buttons = ((data[2] >> 4) << 7) | + ((data[1] & 0x04) << 6) | + ((data[2] & 0x0F) << 2) | + (data[1] & 0x03); + } else if (features->type >= INTUOS5S && features->type <= INTUOSPL) { + /* + * ExpressKeys on Intuos5/Intuos Pro have a capacitive sensor in + * addition to the mechanical switch. Switch data is + * stored in data[4], capacitive data in data[5]. + * + * Touch ring mode switch (data[3]) has no capacitive sensor + */ + buttons = (data[4] << 1) | (data[3] & 0x01); + ring1 = data[2]; + } else { + if (features->type == WACOM_21UX2 || features->type == WACOM_22HD) { + buttons = (data[8] << 10) | ((data[7] & 0x01) << 9) | + (data[6] << 1) | (data[5] & 0x01); + + if (features->type == WACOM_22HD) { + nkeys = 3; + keys = data[9] & 0x07; + } + } else { + buttons = ((data[6] & 0x10) << 10) | + ((data[5] & 0x10) << 9) | + ((data[6] & 0x0F) << 4) | + (data[5] & 0x0F); + } + strip1 = ((data[1] & 0x1f) << 8) | data[2]; + strip2 = ((data[3] & 0x1f) << 8) | data[4]; + } + + prox = (buttons & ~(~0 << nbuttons)) | (keys & ~(~0 << nkeys)) | + (ring1 & 0x80) | (ring2 & 0x80) | strip1 | strip2; + + wacom_report_numbered_buttons(input, nbuttons, buttons); + + for (i = 0; i < nkeys; i++) + input_report_key(input, KEY_PROG1 + i, keys & (1 << i)); + + input_report_abs(input, ABS_RX, strip1); + input_report_abs(input, ABS_RY, strip2); + + input_report_abs(input, ABS_WHEEL, (ring1 & 0x80) ? (ring1 & 0x7f) : 0); + input_report_abs(input, ABS_THROTTLE, (ring2 & 0x80) ? (ring2 & 0x7f) : 0); + + input_report_key(input, wacom->tool[1], prox ? 1 : 0); + input_report_abs(input, ABS_MISC, prox ? PAD_DEVICE_ID : 0); + + input_event(input, EV_MSC, MSC_SERIAL, 0xffffffff); + + return 1; +} + static int wacom_intuos_inout(struct wacom_wac *wacom) { struct wacom_features *features = &wacom->features; @@ -755,19 +884,40 @@ static int wacom_remote_status_irq(struct wacom_wac *wacom_wac, size_t len) return 0; } -static void wacom_intuos_general(struct wacom_wac *wacom) +static int wacom_intuos_general(struct wacom_wac *wacom) { struct wacom_features *features = &wacom->features; unsigned char *data = wacom->data; struct input_dev *input = wacom->pen_input; - unsigned int t; + int idx = (features->type == INTUOS) ? (data[1] & 0x01) : 0; + unsigned char type = (data[1] >> 1) & 0x0F; + unsigned int x, y, distance, t; - /* general pen packet */ - if ((data[1] & 0xb8) == 0xa0) { - t = (data[6] << 2) | ((data[7] >> 6) & 3); - if (features->pressure_max == 2047) { - t = (t << 1) | (data[1] & 1); - } + if (data[0] != WACOM_REPORT_PENABLED && data[0] != WACOM_REPORT_CINTIQ && + data[0] != WACOM_REPORT_INTUOS_PEN) + return 0; + + x = (be16_to_cpup((__be16 *)&data[2]) << 1) | ((data[9] >> 1) & 1); + y = (be16_to_cpup((__be16 *)&data[4]) << 1) | (data[9] & 1); + distance = data[9] >> 2; + if (features->type < INTUOS3S) { + x >>= 1; + y >>= 1; + distance >>= 1; + } + input_report_abs(input, ABS_X, x); + input_report_abs(input, ABS_Y, y); + input_report_abs(input, ABS_DISTANCE, distance); + + switch (type) { + case 0x00: + case 0x01: + case 0x02: + case 0x03: + /* general pen packet */ + t = (data[6] << 3) | ((data[7] & 0xC0) >> 5) | (data[1] & 1); + if (features->pressure_max < 2047) + t >>= 1; input_report_abs(input, ABS_PRESSURE, t); if (features->type != INTUOSHT2) { input_report_abs(input, ABS_TILT_X, @@ -777,29 +927,112 @@ static void wacom_intuos_general(struct wacom_wac *wacom) input_report_key(input, BTN_STYLUS, data[1] & 2); input_report_key(input, BTN_STYLUS2, data[1] & 4); input_report_key(input, BTN_TOUCH, t > 10); - } + break; - /* airbrush second packet */ - if ((data[1] & 0xbc) == 0xb4) { + case 0x0a: + /* airbrush second packet */ input_report_abs(input, ABS_WHEEL, (data[6] << 2) | ((data[7] >> 6) & 3)); input_report_abs(input, ABS_TILT_X, (((data[7] << 1) & 0x7e) | (data[8] >> 7)) - 64); input_report_abs(input, ABS_TILT_Y, (data[8] & 0x7f) - 64); + break; + + case 0x05: + /* Rotation packet */ + if (features->type >= INTUOS3S) { + /* I3 marker pen rotation */ + t = (data[6] << 3) | ((data[7] >> 5) & 7); + t = (data[7] & 0x20) ? ((t > 900) ? ((t-1) / 2 - 1350) : + ((t-1) / 2 + 450)) : (450 - t / 2) ; + input_report_abs(input, ABS_Z, t); + } else { + /* 4D mouse 2nd packet */ + t = (data[6] << 3) | ((data[7] >> 5) & 7); + input_report_abs(input, ABS_RZ, (data[7] & 0x20) ? + ((t - 1) / 2) : -t / 2); + } + break; + + case 0x04: + /* 4D mouse 1st packet */ + input_report_key(input, BTN_LEFT, data[8] & 0x01); + input_report_key(input, BTN_MIDDLE, data[8] & 0x02); + input_report_key(input, BTN_RIGHT, data[8] & 0x04); + + input_report_key(input, BTN_SIDE, data[8] & 0x20); + input_report_key(input, BTN_EXTRA, data[8] & 0x10); + t = (data[6] << 2) | ((data[7] >> 6) & 3); + input_report_abs(input, ABS_THROTTLE, (data[8] & 0x08) ? -t : t); + break; + + case 0x06: + /* I4 mouse */ + input_report_key(input, BTN_LEFT, data[6] & 0x01); + input_report_key(input, BTN_MIDDLE, data[6] & 0x02); + input_report_key(input, BTN_RIGHT, data[6] & 0x04); + input_report_rel(input, REL_WHEEL, ((data[7] & 0x80) >> 7) + - ((data[7] & 0x40) >> 6)); + input_report_key(input, BTN_SIDE, data[6] & 0x08); + input_report_key(input, BTN_EXTRA, data[6] & 0x10); + + input_report_abs(input, ABS_TILT_X, + (((data[7] << 1) & 0x7e) | (data[8] >> 7)) - 64); + input_report_abs(input, ABS_TILT_Y, (data[8] & 0x7f) - 64); + break; + + case 0x08: + if (wacom->tool[idx] == BTN_TOOL_MOUSE) { + /* 2D mouse packet */ + input_report_key(input, BTN_LEFT, data[8] & 0x04); + input_report_key(input, BTN_MIDDLE, data[8] & 0x08); + input_report_key(input, BTN_RIGHT, data[8] & 0x10); + input_report_rel(input, REL_WHEEL, (data[8] & 0x01) + - ((data[8] & 0x02) >> 1)); + + /* I3 2D mouse side buttons */ + if (features->type >= INTUOS3S && features->type <= INTUOS3L) { + input_report_key(input, BTN_SIDE, data[8] & 0x40); + input_report_key(input, BTN_EXTRA, data[8] & 0x20); + } + } + else if (wacom->tool[idx] == BTN_TOOL_LENS) { + /* Lens cursor packets */ + input_report_key(input, BTN_LEFT, data[8] & 0x01); + input_report_key(input, BTN_MIDDLE, data[8] & 0x02); + input_report_key(input, BTN_RIGHT, data[8] & 0x04); + input_report_key(input, BTN_SIDE, data[8] & 0x10); + input_report_key(input, BTN_EXTRA, data[8] & 0x08); + } + break; + + case 0x07: + case 0x09: + case 0x0b: + case 0x0c: + case 0x0d: + case 0x0e: + case 0x0f: + /* unhandled */ + break; } + + input_report_abs(input, ABS_MISC, wacom->id[idx]); /* report tool id */ + input_report_key(input, wacom->tool[idx], 1); + input_event(input, EV_MSC, MSC_SERIAL, wacom->serial[idx]); + wacom->reporting_data = true; + return 2; } static int wacom_intuos_irq(struct wacom_wac *wacom) { - struct wacom_features *features = &wacom->features; unsigned char *data = wacom->data; struct input_dev *input = wacom->pen_input; - unsigned int t; - int idx = 0, result; + int result; if (data[0] != WACOM_REPORT_PENABLED && - data[0] != WACOM_REPORT_INTUOSREAD && - data[0] != WACOM_REPORT_INTUOSWRITE && + data[0] != WACOM_REPORT_INTUOS_ID1 && + data[0] != WACOM_REPORT_INTUOS_ID2 && data[0] != WACOM_REPORT_INTUOSPAD && data[0] != WACOM_REPORT_INTUOS_PEN && data[0] != WACOM_REPORT_CINTIQ && @@ -810,339 +1043,22 @@ static int wacom_intuos_irq(struct wacom_wac *wacom) return 0; } - /* tool number */ - if (features->type == INTUOS) - idx = data[1] & 0x01; - - /* pad packets. Works as a second tool and is always in prox */ - if (data[0] == WACOM_REPORT_INTUOSPAD || data[0] == WACOM_REPORT_INTUOS5PAD || - data[0] == WACOM_REPORT_CINTIQPAD) { - input = wacom->pad_input; - if (features->type >= INTUOS4S && features->type <= INTUOS4L) { - input_report_key(input, BTN_0, (data[2] & 0x01)); - input_report_key(input, BTN_1, (data[3] & 0x01)); - input_report_key(input, BTN_2, (data[3] & 0x02)); - input_report_key(input, BTN_3, (data[3] & 0x04)); - input_report_key(input, BTN_4, (data[3] & 0x08)); - input_report_key(input, BTN_5, (data[3] & 0x10)); - input_report_key(input, BTN_6, (data[3] & 0x20)); - if (data[1] & 0x80) { - input_report_abs(input, ABS_WHEEL, (data[1] & 0x7f)); - } else { - /* Out of proximity, clear wheel value. */ - input_report_abs(input, ABS_WHEEL, 0); - } - if (features->type != INTUOS4S) { - input_report_key(input, BTN_7, (data[3] & 0x40)); - input_report_key(input, BTN_8, (data[3] & 0x80)); - } - if (data[1] | (data[2] & 0x01) | data[3]) { - input_report_abs(input, ABS_MISC, PAD_DEVICE_ID); - } else { - input_report_abs(input, ABS_MISC, 0); - } - } else if (features->type == DTK) { - input_report_key(input, BTN_0, (data[6] & 0x01)); - input_report_key(input, BTN_1, (data[6] & 0x02)); - input_report_key(input, BTN_2, (data[6] & 0x04)); - input_report_key(input, BTN_3, (data[6] & 0x08)); - input_report_key(input, BTN_4, (data[6] & 0x10)); - input_report_key(input, BTN_5, (data[6] & 0x20)); - if (data[6] & 0x3f) { - input_report_abs(input, ABS_MISC, PAD_DEVICE_ID); - } else { - input_report_abs(input, ABS_MISC, 0); - } - } else if (features->type == WACOM_13HD) { - input_report_key(input, BTN_0, (data[3] & 0x01)); - input_report_key(input, BTN_1, (data[4] & 0x01)); - input_report_key(input, BTN_2, (data[4] & 0x02)); - input_report_key(input, BTN_3, (data[4] & 0x04)); - input_report_key(input, BTN_4, (data[4] & 0x08)); - input_report_key(input, BTN_5, (data[4] & 0x10)); - input_report_key(input, BTN_6, (data[4] & 0x20)); - input_report_key(input, BTN_7, (data[4] & 0x40)); - input_report_key(input, BTN_8, (data[4] & 0x80)); - if ((data[3] & 0x01) | data[4]) { - input_report_abs(input, ABS_MISC, PAD_DEVICE_ID); - } else { - input_report_abs(input, ABS_MISC, 0); - } - } else if (features->type == WACOM_24HD) { - input_report_key(input, BTN_0, (data[6] & 0x01)); - input_report_key(input, BTN_1, (data[6] & 0x02)); - input_report_key(input, BTN_2, (data[6] & 0x04)); - input_report_key(input, BTN_3, (data[6] & 0x08)); - input_report_key(input, BTN_4, (data[6] & 0x10)); - input_report_key(input, BTN_5, (data[6] & 0x20)); - input_report_key(input, BTN_6, (data[6] & 0x40)); - input_report_key(input, BTN_7, (data[6] & 0x80)); - input_report_key(input, BTN_8, (data[8] & 0x01)); - input_report_key(input, BTN_9, (data[8] & 0x02)); - input_report_key(input, BTN_A, (data[8] & 0x04)); - input_report_key(input, BTN_B, (data[8] & 0x08)); - input_report_key(input, BTN_C, (data[8] & 0x10)); - input_report_key(input, BTN_X, (data[8] & 0x20)); - input_report_key(input, BTN_Y, (data[8] & 0x40)); - input_report_key(input, BTN_Z, (data[8] & 0x80)); - - /* - * Three "buttons" are available on the 24HD which are - * physically implemented as a touchstrip. Each button - * is approximately 3 bits wide with a 2 bit spacing. - * The raw touchstrip bits are stored at: - * ((data[3] & 0x1f) << 8) | data[4]) - */ - input_report_key(input, KEY_PROG1, data[4] & 0x07); - input_report_key(input, KEY_PROG2, data[4] & 0xE0); - input_report_key(input, KEY_PROG3, data[3] & 0x1C); - - if (data[1] & 0x80) { - input_report_abs(input, ABS_WHEEL, (data[1] & 0x7f)); - } else { - /* Out of proximity, clear wheel value. */ - input_report_abs(input, ABS_WHEEL, 0); - } - - if (data[2] & 0x80) { - input_report_abs(input, ABS_THROTTLE, (data[2] & 0x7f)); - } else { - /* Out of proximity, clear second wheel value. */ - input_report_abs(input, ABS_THROTTLE, 0); - } - - if (data[1] | data[2] | (data[3] & 0x1f) | data[4] | data[6] | data[8]) { - input_report_abs(input, ABS_MISC, PAD_DEVICE_ID); - } else { - input_report_abs(input, ABS_MISC, 0); - } - } else if (features->type == WACOM_27QHD) { - input_report_key(input, KEY_PROG1, data[2] & 0x01); - input_report_key(input, KEY_PROG2, data[2] & 0x02); - input_report_key(input, KEY_PROG3, data[2] & 0x04); - - input_report_abs(input, ABS_X, be16_to_cpup((__be16 *)&data[4])); - input_report_abs(input, ABS_Y, be16_to_cpup((__be16 *)&data[6])); - input_report_abs(input, ABS_Z, be16_to_cpup((__be16 *)&data[8])); - if ((data[2] & 0x07) | data[4] | data[5] | data[6] | data[7] | data[8] | data[9]) { - input_report_abs(input, ABS_MISC, PAD_DEVICE_ID); - } else { - input_report_abs(input, ABS_MISC, 0); - } - } else if (features->type == CINTIQ_HYBRID) { - /* - * Do not send hardware buttons under Android. They - * are already sent to the system through GPIO (and - * have different meaning). - */ - input_report_key(input, BTN_1, (data[4] & 0x01)); - input_report_key(input, BTN_2, (data[4] & 0x02)); - input_report_key(input, BTN_3, (data[4] & 0x04)); - input_report_key(input, BTN_4, (data[4] & 0x08)); - - input_report_key(input, BTN_5, (data[4] & 0x10)); /* Right */ - input_report_key(input, BTN_6, (data[4] & 0x20)); /* Up */ - input_report_key(input, BTN_7, (data[4] & 0x40)); /* Left */ - input_report_key(input, BTN_8, (data[4] & 0x80)); /* Down */ - input_report_key(input, BTN_0, (data[3] & 0x01)); /* Center */ - - if (data[4] | (data[3] & 0x01)) { - input_report_abs(input, ABS_MISC, PAD_DEVICE_ID); - } else { - input_report_abs(input, ABS_MISC, 0); - } - - } else if (features->type == CINTIQ_COMPANION_2) { - input_report_key(input, BTN_1, (data[1] & 0x02)); - input_report_key(input, BTN_2, (data[2] & 0x01)); - input_report_key(input, BTN_3, (data[2] & 0x02)); - input_report_key(input, BTN_4, (data[2] & 0x04)); - input_report_key(input, BTN_5, (data[2] & 0x08)); - input_report_key(input, BTN_6, (data[1] & 0x04)); - - input_report_key(input, BTN_7, (data[2] & 0x10)); /* Right */ - input_report_key(input, BTN_8, (data[2] & 0x20)); /* Up */ - input_report_key(input, BTN_9, (data[2] & 0x40)); /* Left */ - input_report_key(input, BTN_A, (data[2] & 0x80)); /* Down */ - input_report_key(input, BTN_0, (data[1] & 0x01)); /* Center */ - - if (data[2] | (data[1] & 0x07)) { - input_report_abs(input, ABS_MISC, PAD_DEVICE_ID); - } else { - input_report_abs(input, ABS_MISC, 0); - } - - } else if (features->type >= INTUOS5S && features->type <= INTUOSPL) { - int i; - - /* Touch ring mode switch has no capacitive sensor */ - input_report_key(input, BTN_0, (data[3] & 0x01)); - - /* - * ExpressKeys on Intuos5/Intuos Pro have a capacitive sensor in - * addition to the mechanical switch. Switch data is - * stored in data[4], capacitive data in data[5]. - */ - for (i = 0; i < 8; i++) - input_report_key(input, BTN_1 + i, data[4] & (1 << i)); - - if (data[2] & 0x80) { - input_report_abs(input, ABS_WHEEL, (data[2] & 0x7f)); - } else { - /* Out of proximity, clear wheel value. */ - input_report_abs(input, ABS_WHEEL, 0); - } - - if (data[2] | (data[3] & 0x01) | data[4] | data[5]) { - input_report_abs(input, ABS_MISC, PAD_DEVICE_ID); - } else { - input_report_abs(input, ABS_MISC, 0); - } - } else { - if (features->type == WACOM_21UX2 || features->type == WACOM_22HD) { - input_report_key(input, BTN_0, (data[5] & 0x01)); - input_report_key(input, BTN_1, (data[6] & 0x01)); - input_report_key(input, BTN_2, (data[6] & 0x02)); - input_report_key(input, BTN_3, (data[6] & 0x04)); - input_report_key(input, BTN_4, (data[6] & 0x08)); - input_report_key(input, BTN_5, (data[6] & 0x10)); - input_report_key(input, BTN_6, (data[6] & 0x20)); - input_report_key(input, BTN_7, (data[6] & 0x40)); - input_report_key(input, BTN_8, (data[6] & 0x80)); - input_report_key(input, BTN_9, (data[7] & 0x01)); - input_report_key(input, BTN_A, (data[8] & 0x01)); - input_report_key(input, BTN_B, (data[8] & 0x02)); - input_report_key(input, BTN_C, (data[8] & 0x04)); - input_report_key(input, BTN_X, (data[8] & 0x08)); - input_report_key(input, BTN_Y, (data[8] & 0x10)); - input_report_key(input, BTN_Z, (data[8] & 0x20)); - input_report_key(input, BTN_BASE, (data[8] & 0x40)); - input_report_key(input, BTN_BASE2, (data[8] & 0x80)); - - if (features->type == WACOM_22HD) { - input_report_key(input, KEY_PROG1, data[9] & 0x01); - input_report_key(input, KEY_PROG2, data[9] & 0x02); - input_report_key(input, KEY_PROG3, data[9] & 0x04); - } - } else { - input_report_key(input, BTN_0, (data[5] & 0x01)); - input_report_key(input, BTN_1, (data[5] & 0x02)); - input_report_key(input, BTN_2, (data[5] & 0x04)); - input_report_key(input, BTN_3, (data[5] & 0x08)); - input_report_key(input, BTN_4, (data[6] & 0x01)); - input_report_key(input, BTN_5, (data[6] & 0x02)); - input_report_key(input, BTN_6, (data[6] & 0x04)); - input_report_key(input, BTN_7, (data[6] & 0x08)); - input_report_key(input, BTN_8, (data[5] & 0x10)); - input_report_key(input, BTN_9, (data[6] & 0x10)); - } - input_report_abs(input, ABS_RX, ((data[1] & 0x1f) << 8) | data[2]); - input_report_abs(input, ABS_RY, ((data[3] & 0x1f) << 8) | data[4]); - - if ((data[5] & 0x1f) | data[6] | (data[1] & 0x1f) | - data[2] | (data[3] & 0x1f) | data[4] | data[8] | - (data[7] & 0x01)) { - input_report_abs(input, ABS_MISC, PAD_DEVICE_ID); - } else { - input_report_abs(input, ABS_MISC, 0); - } - } - return 1; - } + /* process pad events */ + result = wacom_intuos_pad(wacom); + if (result) + return result; /* process in/out prox events */ result = wacom_intuos_inout(wacom); if (result) - return result - 1; - - if (features->type >= INTUOS3S) { - input_report_abs(input, ABS_X, (data[2] << 9) | (data[3] << 1) | ((data[9] >> 1) & 1)); - input_report_abs(input, ABS_Y, (data[4] << 9) | (data[5] << 1) | (data[9] & 1)); - input_report_abs(input, ABS_DISTANCE, ((data[9] >> 2) & 0x3f)); - } else { - input_report_abs(input, ABS_X, be16_to_cpup((__be16 *)&data[2])); - input_report_abs(input, ABS_Y, be16_to_cpup((__be16 *)&data[4])); - input_report_abs(input, ABS_DISTANCE, ((data[9] >> 3) & 0x1f)); - } + return result - 1; /* process general packets */ - wacom_intuos_general(wacom); - - /* 4D mouse, 2D mouse, marker pen rotation, tilt mouse, or Lens cursor packets */ - if ((data[1] & 0xbc) == 0xa8 || (data[1] & 0xbe) == 0xb0 || (data[1] & 0xbc) == 0xac) { - - if (data[1] & 0x02) { - /* Rotation packet */ - if (features->type >= INTUOS3S) { - /* I3 marker pen rotation */ - t = (data[6] << 3) | ((data[7] >> 5) & 7); - t = (data[7] & 0x20) ? ((t > 900) ? ((t-1) / 2 - 1350) : - ((t-1) / 2 + 450)) : (450 - t / 2) ; - input_report_abs(input, ABS_Z, t); - } else { - /* 4D mouse rotation packet */ - t = (data[6] << 3) | ((data[7] >> 5) & 7); - input_report_abs(input, ABS_RZ, (data[7] & 0x20) ? - ((t - 1) / 2) : -t / 2); - } - - } else if (!(data[1] & 0x10) && features->type < INTUOS3S) { - /* 4D mouse packet */ - input_report_key(input, BTN_LEFT, data[8] & 0x01); - input_report_key(input, BTN_MIDDLE, data[8] & 0x02); - input_report_key(input, BTN_RIGHT, data[8] & 0x04); - - input_report_key(input, BTN_SIDE, data[8] & 0x20); - input_report_key(input, BTN_EXTRA, data[8] & 0x10); - t = (data[6] << 2) | ((data[7] >> 6) & 3); - input_report_abs(input, ABS_THROTTLE, (data[8] & 0x08) ? -t : t); - - } else if (wacom->tool[idx] == BTN_TOOL_MOUSE) { - /* I4 mouse */ - if (features->type >= INTUOS4S && features->type <= INTUOSPL) { - input_report_key(input, BTN_LEFT, data[6] & 0x01); - input_report_key(input, BTN_MIDDLE, data[6] & 0x02); - input_report_key(input, BTN_RIGHT, data[6] & 0x04); - input_report_rel(input, REL_WHEEL, ((data[7] & 0x80) >> 7) - - ((data[7] & 0x40) >> 6)); - input_report_key(input, BTN_SIDE, data[6] & 0x08); - input_report_key(input, BTN_EXTRA, data[6] & 0x10); - - input_report_abs(input, ABS_TILT_X, - (((data[7] << 1) & 0x7e) | (data[8] >> 7)) - 64); - input_report_abs(input, ABS_TILT_Y, (data[8] & 0x7f) - 64); - } else { - /* 2D mouse packet */ - input_report_key(input, BTN_LEFT, data[8] & 0x04); - input_report_key(input, BTN_MIDDLE, data[8] & 0x08); - input_report_key(input, BTN_RIGHT, data[8] & 0x10); - input_report_rel(input, REL_WHEEL, (data[8] & 0x01) - - ((data[8] & 0x02) >> 1)); - - /* I3 2D mouse side buttons */ - if (features->type >= INTUOS3S && features->type <= INTUOS3L) { - input_report_key(input, BTN_SIDE, data[8] & 0x40); - input_report_key(input, BTN_EXTRA, data[8] & 0x20); - } - } - } else if ((features->type < INTUOS3S || features->type == INTUOS3L || - features->type == INTUOS4L || features->type == INTUOS5L || - features->type == INTUOSPL) && - wacom->tool[idx] == BTN_TOOL_LENS) { - /* Lens cursor packets */ - input_report_key(input, BTN_LEFT, data[8] & 0x01); - input_report_key(input, BTN_MIDDLE, data[8] & 0x02); - input_report_key(input, BTN_RIGHT, data[8] & 0x04); - input_report_key(input, BTN_SIDE, data[8] & 0x10); - input_report_key(input, BTN_EXTRA, data[8] & 0x08); - } - } + result = wacom_intuos_general(wacom); + if (result) + return result - 1; - input_report_abs(input, ABS_MISC, wacom->id[idx]); /* report tool id */ - input_report_key(input, wacom->tool[idx], 1); - input_event(input, EV_MSC, MSC_SERIAL, wacom->serial[idx]); - wacom->reporting_data = true; - return 1; + return 0; } static int int_dist(int x1, int y1, int x2, int y2) @@ -2509,7 +2425,7 @@ void wacom_setup_device_quirks(struct wacom *wacom) features->quirks |= WACOM_QUIRK_BATTERY; /* quirk for bamboo touch with 2 low res touches */ - if (features->type == BAMBOO_PT && + if ((features->type == BAMBOO_PT || features->type == BAMBOO_TOUCH) && features->pktlen == WACOM_PKGLEN_BBTOUCH) { features->x_max <<= 5; features->y_max <<= 5; @@ -2806,6 +2722,19 @@ static void wacom_setup_numbered_buttons(struct input_dev *input_dev, __set_bit(BTN_BASE + (i-16), input_dev->keybit); } +static void wacom_report_numbered_buttons(struct input_dev *input_dev, + int button_count, int mask) +{ + int i; + + for (i = 0; i < button_count && i < 10; i++) + input_report_key(input_dev, BTN_0 + i, mask & (1 << i)); + for (i = 10; i < button_count && i < 16; i++) + input_report_key(input_dev, BTN_A + (i-10), mask & (1 << i)); + for (i = 16; i < button_count && i < 18; i++) + input_report_key(input_dev, BTN_BASE + (i-16), mask & (1 << i)); +} + int wacom_setup_pad_input_capabilities(struct input_dev *input_dev, struct wacom_wac *wacom_wac) { diff --git a/drivers/hid/wacom_wac.h b/drivers/hid/wacom_wac.h index 877c24a5df94..25baa7f29599 100644 --- a/drivers/hid/wacom_wac.h +++ b/drivers/hid/wacom_wac.h @@ -47,8 +47,8 @@ /* wacom data packet report IDs */ #define WACOM_REPORT_PENABLED 2 #define WACOM_REPORT_PENABLED_BT 3 -#define WACOM_REPORT_INTUOSREAD 5 -#define WACOM_REPORT_INTUOSWRITE 6 +#define WACOM_REPORT_INTUOS_ID1 5 +#define WACOM_REPORT_INTUOS_ID2 6 #define WACOM_REPORT_INTUOSPAD 12 #define WACOM_REPORT_INTUOS5PAD 3 #define WACOM_REPORT_DTUSPAD 21 @@ -70,6 +70,7 @@ #define WACOM_REPORT_DEVICE_LIST 16 #define WACOM_REPORT_INTUOS_PEN 16 #define WACOM_REPORT_REMOTE 17 +#define WACOM_REPORT_INTUOSHT2_ID 8 /* device quirks */ #define WACOM_QUIRK_BBTOUCH_LOWRES 0x0001 diff --git a/drivers/hsi/controllers/omap_ssi.c b/drivers/hsi/controllers/omap_ssi.c index f6d3100b7a32..27b91f14ba7a 100644 --- a/drivers/hsi/controllers/omap_ssi.c +++ b/drivers/hsi/controllers/omap_ssi.c @@ -323,11 +323,10 @@ static int __init ssi_add_controller(struct hsi_controller *ssi, return -ENOMEM; } - ssi->id = ida_simple_get(&platform_omap_ssi_ida, 0, 0, GFP_KERNEL); - if (ssi->id < 0) { - err = ssi->id; + err = ida_simple_get(&platform_omap_ssi_ida, 0, 0, GFP_KERNEL); + if (err < 0) goto out_err; - } + ssi->id = err; ssi->owner = THIS_MODULE; ssi->device.parent = &pd->dev; diff --git a/drivers/hsi/controllers/omap_ssi_port.c b/drivers/hsi/controllers/omap_ssi_port.c index 02e66032ae73..e80a66e20998 100644 --- a/drivers/hsi/controllers/omap_ssi_port.c +++ b/drivers/hsi/controllers/omap_ssi_port.c @@ -1147,13 +1147,13 @@ static int __init ssi_port_probe(struct platform_device *pd) goto error; } - cawake_gpio = of_get_named_gpio(np, "ti,ssi-cawake-gpio", 0); - if (cawake_gpio < 0) { + err = of_get_named_gpio(np, "ti,ssi-cawake-gpio", 0); + if (err < 0) { dev_err(&pd->dev, "DT data is missing cawake gpio (err=%d)\n", - cawake_gpio); - err = -ENODEV; + err); goto error; } + cawake_gpio = err; err = devm_gpio_request_one(&port->device, cawake_gpio, GPIOF_DIR_IN, "cawake"); diff --git a/drivers/i2c/algos/i2c-algo-bit.c b/drivers/i2c/algos/i2c-algo-bit.c index 899bede81b31..9d233bbde5e1 100644 --- a/drivers/i2c/algos/i2c-algo-bit.c +++ b/drivers/i2c/algos/i2c-algo-bit.c @@ -617,6 +617,10 @@ const struct i2c_algorithm i2c_bit_algo = { }; EXPORT_SYMBOL(i2c_bit_algo); +const struct i2c_adapter_quirks i2c_bit_quirk_no_clk_stretch = { + .flags = I2C_AQ_NO_CLK_STRETCH, +}; + /* * registering functions to load algorithms at runtime */ @@ -635,6 +639,8 @@ static int __i2c_bit_add_bus(struct i2c_adapter *adap, /* register new adapter to i2c module... */ adap->algo = &i2c_bit_algo; adap->retries = 3; + if (bit_adap->getscl == NULL) + adap->quirks = &i2c_bit_quirk_no_clk_stretch; ret = add_adapter(adap); if (ret < 0) diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index 7b0aa82ea38b..0299dfa746a3 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -516,7 +516,7 @@ config I2C_EFM32 config I2C_EG20T tristate "Intel EG20T PCH/LAPIS Semicon IOH(ML7213/ML7223/ML7831) I2C" - depends on PCI && (X86_32 || COMPILE_TEST) + depends on PCI && (X86_32 || MIPS || COMPILE_TEST) help This driver is for PCH(Platform controller Hub) I2C of EG20T which is an IOH(Input/Output Hub) for x86 embedded processor. @@ -532,6 +532,7 @@ config I2C_EG20T config I2C_EMEV2 tristate "EMMA Mobile series I2C adapter" depends on HAVE_CLK + select I2C_SLAVE help If you say yes to this option, support will be included for the I2C interface on the Renesas Electronics EM/EV family of processors. @@ -963,11 +964,11 @@ config I2C_XILINX will be called xilinx_i2c. config I2C_XLR - tristate "XLR I2C support" - depends on CPU_XLR + tristate "Netlogic XLR and Sigma Designs I2C support" + depends on CPU_XLR || ARCH_TANGOX help This driver enables support for the on-chip I2C interface of - the Netlogic XLR/XLS MIPS processors. + the Netlogic XLR/XLS MIPS processors and Sigma Designs SOCs. This driver can also be built as a module. If so, the module will be called i2c-xlr. diff --git a/drivers/i2c/busses/i2c-at91.c b/drivers/i2c/busses/i2c-at91.c index 10835d1f559b..921d32bfcda8 100644 --- a/drivers/i2c/busses/i2c-at91.c +++ b/drivers/i2c/busses/i2c-at91.c @@ -64,6 +64,8 @@ #define AT91_TWI_IADR 0x000c /* Internal Address Register */ #define AT91_TWI_CWGR 0x0010 /* Clock Waveform Generator Reg */ +#define AT91_TWI_CWGR_HOLD_MAX 0x1f +#define AT91_TWI_CWGR_HOLD(x) (((x) & AT91_TWI_CWGR_HOLD_MAX) << 24) #define AT91_TWI_SR 0x0020 /* Status Register */ #define AT91_TWI_TXCOMP BIT(0) /* Transmission Complete */ @@ -110,6 +112,7 @@ struct at91_twi_pdata { unsigned clk_offset; bool has_unre_flag; bool has_alt_cmd; + bool has_hold_field; struct at_dma_slave dma_slave; }; @@ -187,10 +190,11 @@ static void at91_init_twi_bus(struct at91_twi_dev *dev) */ static void at91_calc_twi_clock(struct at91_twi_dev *dev, int twi_clk) { - int ckdiv, cdiv, div; + int ckdiv, cdiv, div, hold = 0; struct at91_twi_pdata *pdata = dev->pdata; int offset = pdata->clk_offset; int max_ckdiv = pdata->clk_max_div; + u32 twd_hold_time_ns = 0; div = max(0, (int)DIV_ROUND_UP(clk_get_rate(dev->clk), 2 * twi_clk) - offset); @@ -204,8 +208,33 @@ static void at91_calc_twi_clock(struct at91_twi_dev *dev, int twi_clk) cdiv = 255; } - dev->twi_cwgr_reg = (ckdiv << 16) | (cdiv << 8) | cdiv; - dev_dbg(dev->dev, "cdiv %d ckdiv %d\n", cdiv, ckdiv); + if (pdata->has_hold_field) { + of_property_read_u32(dev->dev->of_node, "i2c-sda-hold-time-ns", + &twd_hold_time_ns); + + /* + * hold time = HOLD + 3 x T_peripheral_clock + * Use clk rate in kHz to prevent overflows when computing + * hold. + */ + hold = DIV_ROUND_UP(twd_hold_time_ns + * (clk_get_rate(dev->clk) / 1000), 1000000); + hold -= 3; + if (hold < 0) + hold = 0; + if (hold > AT91_TWI_CWGR_HOLD_MAX) { + dev_warn(dev->dev, + "HOLD field set to its maximum value (%d instead of %d)\n", + AT91_TWI_CWGR_HOLD_MAX, hold); + hold = AT91_TWI_CWGR_HOLD_MAX; + } + } + + dev->twi_cwgr_reg = (ckdiv << 16) | (cdiv << 8) | cdiv + | AT91_TWI_CWGR_HOLD(hold); + + dev_dbg(dev->dev, "cdiv %d ckdiv %d hold %d (%d ns)\n", + cdiv, ckdiv, hold, twd_hold_time_ns); } static void at91_twi_dma_cleanup(struct at91_twi_dev *dev) @@ -797,6 +826,7 @@ static struct at91_twi_pdata at91rm9200_config = { .clk_offset = 3, .has_unre_flag = true, .has_alt_cmd = false, + .has_hold_field = false, }; static struct at91_twi_pdata at91sam9261_config = { @@ -804,6 +834,7 @@ static struct at91_twi_pdata at91sam9261_config = { .clk_offset = 4, .has_unre_flag = false, .has_alt_cmd = false, + .has_hold_field = false, }; static struct at91_twi_pdata at91sam9260_config = { @@ -811,6 +842,7 @@ static struct at91_twi_pdata at91sam9260_config = { .clk_offset = 4, .has_unre_flag = false, .has_alt_cmd = false, + .has_hold_field = false, }; static struct at91_twi_pdata at91sam9g20_config = { @@ -818,6 +850,7 @@ static struct at91_twi_pdata at91sam9g20_config = { .clk_offset = 4, .has_unre_flag = false, .has_alt_cmd = false, + .has_hold_field = false, }; static struct at91_twi_pdata at91sam9g10_config = { @@ -825,6 +858,7 @@ static struct at91_twi_pdata at91sam9g10_config = { .clk_offset = 4, .has_unre_flag = false, .has_alt_cmd = false, + .has_hold_field = false, }; static const struct platform_device_id at91_twi_devtypes[] = { @@ -854,6 +888,15 @@ static struct at91_twi_pdata at91sam9x5_config = { .clk_offset = 4, .has_unre_flag = false, .has_alt_cmd = false, + .has_hold_field = false, +}; + +static struct at91_twi_pdata sama5d4_config = { + .clk_max_div = 7, + .clk_offset = 4, + .has_unre_flag = false, + .has_alt_cmd = false, + .has_hold_field = true, }; static struct at91_twi_pdata sama5d2_config = { @@ -861,6 +904,7 @@ static struct at91_twi_pdata sama5d2_config = { .clk_offset = 4, .has_unre_flag = true, .has_alt_cmd = true, + .has_hold_field = true, }; static const struct of_device_id atmel_twi_dt_ids[] = { @@ -883,6 +927,9 @@ static const struct of_device_id atmel_twi_dt_ids[] = { .compatible = "atmel,at91sam9x5-i2c", .data = &at91sam9x5_config, }, { + .compatible = "atmel,sama5d4-i2c", + .data = &sama5d4_config, + }, { .compatible = "atmel,sama5d2-i2c", .data = &sama5d2_config, }, { diff --git a/drivers/i2c/busses/i2c-bcm2835.c b/drivers/i2c/busses/i2c-bcm2835.c index 3032b89ac60b..818b051d25e6 100644 --- a/drivers/i2c/busses/i2c-bcm2835.c +++ b/drivers/i2c/busses/i2c-bcm2835.c @@ -222,6 +222,15 @@ static const struct i2c_algorithm bcm2835_i2c_algo = { .functionality = bcm2835_i2c_func, }; +/* + * This HW was reported to have problems with clock stretching: + * http://www.advamation.com/knowhow/raspberrypi/rpi-i2c-bug.html + * https://www.raspberrypi.org/forums/viewtopic.php?p=146272 + */ +static const struct i2c_adapter_quirks bcm2835_i2c_quirks = { + .flags = I2C_AQ_NO_CLK_STRETCH, +}; + static int bcm2835_i2c_probe(struct platform_device *pdev) { struct bcm2835_i2c_dev *i2c_dev; @@ -293,6 +302,7 @@ static int bcm2835_i2c_probe(struct platform_device *pdev) adap->algo = &bcm2835_i2c_algo; adap->dev.parent = &pdev->dev; adap->dev.of_node = pdev->dev.of_node; + adap->quirks = &bcm2835_i2c_quirks; bcm2835_i2c_writel(i2c_dev, BCM2835_I2C_C, 0); diff --git a/drivers/i2c/busses/i2c-brcmstb.c b/drivers/i2c/busses/i2c-brcmstb.c index 8e9637eea512..3711df1d4526 100644 --- a/drivers/i2c/busses/i2c-brcmstb.c +++ b/drivers/i2c/busses/i2c-brcmstb.c @@ -25,13 +25,16 @@ #include <linux/version.h> #define N_DATA_REGS 8 -#define N_DATA_BYTES (N_DATA_REGS * 4) -/* BSC count register field definitions */ -#define BSC_CNT_REG1_MASK 0x0000003f -#define BSC_CNT_REG1_SHIFT 0 -#define BSC_CNT_REG2_MASK 0x00000fc0 -#define BSC_CNT_REG2_SHIFT 6 +/* + * PER_I2C/BSC count register mask depends on 1 byte/4 byte data register + * size. Cable modem and DSL SoCs with Peripheral i2c cores use 1 byte per + * data register whereas STB SoCs use 4 byte per data register transfer, + * account for this difference in total count per transaction and mask to + * use. + */ +#define BSC_CNT_REG1_MASK(nb) (nb == 1 ? GENMASK(3, 0) : GENMASK(5, 0)) +#define BSC_CNT_REG1_SHIFT 0 /* BSC CTL register field definitions */ #define BSC_CTL_REG_DTF_MASK 0x00000003 @@ -41,7 +44,7 @@ #define BSC_CTL_REG_INT_EN_SHIFT 6 #define BSC_CTL_REG_DIV_CLK_MASK 0x00000080 -/* BSC_IIC_ENABLE r/w enable and interrupt field defintions */ +/* BSC_IIC_ENABLE r/w enable and interrupt field definitions */ #define BSC_IIC_EN_RESTART_MASK 0x00000040 #define BSC_IIC_EN_NOSTART_MASK 0x00000020 #define BSC_IIC_EN_NOSTOP_MASK 0x00000010 @@ -169,6 +172,7 @@ struct brcmstb_i2c_dev { struct completion done; bool is_suspended; u32 clk_freq_hz; + int data_regsz; }; /* register accessors for both be and le cpu arch */ @@ -186,6 +190,16 @@ struct brcmstb_i2c_dev { #define bsc_writel(_dev, _val, _reg) \ __bsc_writel(_val, _dev->base + offsetof(struct bsc_regs, _reg)) +static inline int brcmstb_i2c_get_xfersz(struct brcmstb_i2c_dev *dev) +{ + return (N_DATA_REGS * dev->data_regsz); +} + +static inline int brcmstb_i2c_get_data_regsz(struct brcmstb_i2c_dev *dev) +{ + return dev->data_regsz; +} + static void brcmstb_i2c_enable_disable_irq(struct brcmstb_i2c_dev *dev, bool int_en) { @@ -323,14 +337,16 @@ static int brcmstb_i2c_xfer_bsc_data(struct brcmstb_i2c_dev *dev, u8 *buf, unsigned int len, struct i2c_msg *pmsg) { - int cnt, byte, rc; + int cnt, byte, i, rc; enum bsc_xfer_cmd cmd; u32 ctl_reg; struct bsc_regs *pi2creg = dev->bsc_regmap; int no_ack = pmsg->flags & I2C_M_IGNORE_NAK; + int data_regsz = brcmstb_i2c_get_data_regsz(dev); + int xfersz = brcmstb_i2c_get_xfersz(dev); /* see if the transaction needs to check NACK conditions */ - if (no_ack || len <= N_DATA_BYTES) { + if (no_ack || len <= xfersz) { cmd = (pmsg->flags & I2C_M_RD) ? CMD_RD_NOACK : CMD_WR_NOACK; pi2creg->ctlhi_reg |= BSC_CTLHI_REG_IGNORE_ACK_MASK; @@ -348,20 +364,22 @@ static int brcmstb_i2c_xfer_bsc_data(struct brcmstb_i2c_dev *dev, pi2creg->ctl_reg = ctl_reg | DTF_RD_MASK; /* set the read/write length */ - bsc_writel(dev, BSC_CNT_REG1_MASK & (len << BSC_CNT_REG1_SHIFT), - cnt_reg); + bsc_writel(dev, BSC_CNT_REG1_MASK(data_regsz) & + (len << BSC_CNT_REG1_SHIFT), cnt_reg); /* Write data into data_in register */ + if (cmd == CMD_WR || cmd == CMD_WR_NOACK) { - for (cnt = 0; cnt < len; cnt += 4) { + for (cnt = 0, i = 0; cnt < len; cnt += data_regsz, i++) { u32 word = 0; - for (byte = 0; byte < 4; byte++) { - word >>= 8; + for (byte = 0; byte < data_regsz; byte++) { + word >>= BITS_PER_BYTE; if ((cnt + byte) < len) - word |= buf[cnt + byte] << 24; + word |= buf[cnt + byte] << + (BITS_PER_BYTE * (data_regsz - 1)); } - bsc_writel(dev, word, data_in[cnt >> 2]); + bsc_writel(dev, word, data_in[i]); } } @@ -373,14 +391,15 @@ static int brcmstb_i2c_xfer_bsc_data(struct brcmstb_i2c_dev *dev, return rc; } + /* Read data from data_out register */ if (cmd == CMD_RD || cmd == CMD_RD_NOACK) { - for (cnt = 0; cnt < len; cnt += 4) { - u32 data = bsc_readl(dev, data_out[cnt >> 2]); + for (cnt = 0, i = 0; cnt < len; cnt += data_regsz, i++) { + u32 data = bsc_readl(dev, data_out[i]); - for (byte = 0; byte < 4 && + for (byte = 0; byte < data_regsz && (byte + cnt) < len; byte++) { buf[cnt + byte] = data & 0xff; - data >>= 8; + data >>= BITS_PER_BYTE; } } } @@ -448,6 +467,7 @@ static int brcmstb_i2c_xfer(struct i2c_adapter *adapter, int bytes_to_xfer; u8 *tmp_buf; int len = 0; + int xfersz = brcmstb_i2c_get_xfersz(dev); if (dev->is_suspended) return -EBUSY; @@ -482,9 +502,9 @@ static int brcmstb_i2c_xfer(struct i2c_adapter *adapter, /* Perform data transfer */ while (len) { - bytes_to_xfer = min(len, N_DATA_BYTES); + bytes_to_xfer = min(len, xfersz); - if (len <= N_DATA_BYTES && i == (num - 1)) + if (len <= xfersz && i == (num - 1)) brcmstb_set_i2c_start_stop(dev, ~(COND_START_STOP)); @@ -542,8 +562,12 @@ static void brcmstb_i2c_set_bus_speed(struct brcmstb_i2c_dev *dev) static void brcmstb_i2c_set_bsc_reg_defaults(struct brcmstb_i2c_dev *dev) { - /* 4 byte data register */ - dev->bsc_regmap->ctlhi_reg = BSC_CTLHI_REG_DATAREG_SIZE_MASK; + if (brcmstb_i2c_get_data_regsz(dev) == sizeof(u32)) + /* set 4 byte data in/out xfers */ + dev->bsc_regmap->ctlhi_reg = BSC_CTLHI_REG_DATAREG_SIZE_MASK; + else + dev->bsc_regmap->ctlhi_reg &= ~BSC_CTLHI_REG_DATAREG_SIZE_MASK; + bsc_writel(dev, dev->bsc_regmap->ctlhi_reg, ctlhi_reg); /* set bus speed */ brcmstb_i2c_set_bus_speed(dev); @@ -608,6 +632,13 @@ static int brcmstb_i2c_probe(struct platform_device *pdev) dev->clk_freq_hz = bsc_clk[0].hz; } + /* set the data in/out register size for compatible SoCs */ + if (of_device_is_compatible(dev->device->of_node, + "brcmstb,brcmper-i2c")) + dev->data_regsz = sizeof(u8); + else + dev->data_regsz = sizeof(u32); + brcmstb_i2c_set_bsc_reg_defaults(dev); /* Add the i2c adapter */ @@ -674,6 +705,7 @@ static SIMPLE_DEV_PM_OPS(brcmstb_i2c_pm, brcmstb_i2c_suspend, static const struct of_device_id brcmstb_i2c_of_match[] = { {.compatible = "brcm,brcmstb-i2c"}, + {.compatible = "brcm,brcmper-i2c"}, {}, }; MODULE_DEVICE_TABLE(of, brcmstb_i2c_of_match); diff --git a/drivers/i2c/busses/i2c-cadence.c b/drivers/i2c/busses/i2c-cadence.c index 84deed6571bd..6b08d1607b7a 100644 --- a/drivers/i2c/busses/i2c-cadence.c +++ b/drivers/i2c/busses/i2c-cadence.c @@ -18,6 +18,7 @@ #include <linux/module.h> #include <linux/platform_device.h> #include <linux/of.h> +#include <linux/pm_runtime.h> /* Register offsets for the I2C device. */ #define CDNS_I2C_CR_OFFSET 0x00 /* Control Register, RW */ @@ -96,6 +97,8 @@ CDNS_I2C_IXR_COMP) #define CDNS_I2C_TIMEOUT msecs_to_jiffies(1000) +/* timeout for pm runtime autosuspend */ +#define CNDS_I2C_PM_TIMEOUT 1000 /* ms */ #define CDNS_I2C_FIFO_DEPTH 16 /* FIFO depth at which the DATA interrupt occurs */ @@ -128,7 +131,6 @@ * @xfer_done: Transfer complete status * @p_send_buf: Pointer to transmit buffer * @p_recv_buf: Pointer to receive buffer - * @suspended: Flag holding the device's PM status * @send_count: Number of bytes still expected to send * @recv_count: Number of bytes still expected to receive * @curr_recv_count: Number of bytes to be received in current transfer @@ -141,6 +143,7 @@ * @quirks: flag for broken hold bit usage in r1p10 */ struct cdns_i2c { + struct device *dev; void __iomem *membase; struct i2c_adapter adap; struct i2c_msg *p_msg; @@ -148,7 +151,6 @@ struct cdns_i2c { struct completion xfer_done; unsigned char *p_send_buf; unsigned char *p_recv_buf; - u8 suspended; unsigned int send_count; unsigned int recv_count; unsigned int curr_recv_count; @@ -569,9 +571,14 @@ static int cdns_i2c_master_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, struct cdns_i2c *id = adap->algo_data; bool hold_quirk; + ret = pm_runtime_get_sync(id->dev); + if (ret < 0) + return ret; /* Check if the bus is free */ - if (cdns_i2c_readreg(CDNS_I2C_SR_OFFSET) & CDNS_I2C_SR_BA) - return -EAGAIN; + if (cdns_i2c_readreg(CDNS_I2C_SR_OFFSET) & CDNS_I2C_SR_BA) { + ret = -EAGAIN; + goto out; + } hold_quirk = !!(id->quirks & CDNS_I2C_BROKEN_HOLD_BIT); /* @@ -590,7 +597,8 @@ static int cdns_i2c_master_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, if (msgs[count].flags & I2C_M_RD) { dev_warn(adap->dev.parent, "Can't do repeated start after a receive message\n"); - return -EOPNOTSUPP; + ret = -EOPNOTSUPP; + goto out; } } id->bus_hold_flag = 1; @@ -608,20 +616,26 @@ static int cdns_i2c_master_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, ret = cdns_i2c_process_msg(id, msgs, adap); if (ret) - return ret; + goto out; /* Report the other error interrupts to application */ if (id->err_status) { cdns_i2c_master_reset(adap); - if (id->err_status & CDNS_I2C_IXR_NACK) - return -ENXIO; - - return -EIO; + if (id->err_status & CDNS_I2C_IXR_NACK) { + ret = -ENXIO; + goto out; + } + ret = -EIO; + goto out; } } - return num; + ret = num; +out: + pm_runtime_mark_last_busy(id->dev); + pm_runtime_put_autosuspend(id->dev); + return ret; } /** @@ -760,7 +774,7 @@ static int cdns_i2c_clk_notifier_cb(struct notifier_block *nb, unsigned long struct clk_notifier_data *ndata = data; struct cdns_i2c *id = to_cdns_i2c(nb); - if (id->suspended) + if (pm_runtime_suspended(id->dev)) return NOTIFY_OK; switch (event) { @@ -808,14 +822,12 @@ static int cdns_i2c_clk_notifier_cb(struct notifier_block *nb, unsigned long * * Return: 0 always */ -static int __maybe_unused cdns_i2c_suspend(struct device *_dev) +static int __maybe_unused cdns_i2c_runtime_suspend(struct device *dev) { - struct platform_device *pdev = container_of(_dev, - struct platform_device, dev); + struct platform_device *pdev = to_platform_device(dev); struct cdns_i2c *xi2c = platform_get_drvdata(pdev); clk_disable(xi2c->clk); - xi2c->suspended = 1; return 0; } @@ -828,26 +840,25 @@ static int __maybe_unused cdns_i2c_suspend(struct device *_dev) * * Return: 0 on success and error value on error */ -static int __maybe_unused cdns_i2c_resume(struct device *_dev) +static int __maybe_unused cdns_i2c_runtime_resume(struct device *dev) { - struct platform_device *pdev = container_of(_dev, - struct platform_device, dev); + struct platform_device *pdev = to_platform_device(dev); struct cdns_i2c *xi2c = platform_get_drvdata(pdev); int ret; ret = clk_enable(xi2c->clk); if (ret) { - dev_err(_dev, "Cannot enable clock.\n"); + dev_err(dev, "Cannot enable clock.\n"); return ret; } - xi2c->suspended = 0; - return 0; } -static SIMPLE_DEV_PM_OPS(cdns_i2c_dev_pm_ops, cdns_i2c_suspend, - cdns_i2c_resume); +static const struct dev_pm_ops cdns_i2c_dev_pm_ops = { + SET_RUNTIME_PM_OPS(cdns_i2c_runtime_suspend, + cdns_i2c_runtime_resume, NULL) +}; static const struct cdns_platform_data r1p10_i2c_def = { .quirks = CDNS_I2C_BROKEN_HOLD_BIT, @@ -881,6 +892,7 @@ static int cdns_i2c_probe(struct platform_device *pdev) if (!id) return -ENOMEM; + id->dev = &pdev->dev; platform_set_drvdata(pdev, id); match = of_match_node(cdns_i2c_of_match, pdev->dev.of_node); @@ -913,10 +925,14 @@ static int cdns_i2c_probe(struct platform_device *pdev) return PTR_ERR(id->clk); } ret = clk_prepare_enable(id->clk); - if (ret) { + if (ret) dev_err(&pdev->dev, "Unable to enable clock.\n"); - return ret; - } + + pm_runtime_enable(id->dev); + pm_runtime_set_autosuspend_delay(id->dev, CNDS_I2C_PM_TIMEOUT); + pm_runtime_use_autosuspend(id->dev); + pm_runtime_set_active(id->dev); + id->clk_rate_change_nb.notifier_call = cdns_i2c_clk_notifier_cb; if (clk_notifier_register(id->clk, &id->clk_rate_change_nb)) dev_warn(&pdev->dev, "Unable to register clock notifier.\n"); @@ -966,6 +982,8 @@ static int cdns_i2c_probe(struct platform_device *pdev) err_clk_dis: clk_disable_unprepare(id->clk); + pm_runtime_set_suspended(&pdev->dev); + pm_runtime_disable(&pdev->dev); return ret; } @@ -984,6 +1002,7 @@ static int cdns_i2c_remove(struct platform_device *pdev) i2c_del_adapter(&id->adap); clk_notifier_unregister(id->clk, &id->clk_rate_change_nb); clk_disable_unprepare(id->clk); + pm_runtime_disable(&pdev->dev); return 0; } diff --git a/drivers/i2c/busses/i2c-designware-core.c b/drivers/i2c/busses/i2c-designware-core.c index de7fbbb374cd..ba9732c236c5 100644 --- a/drivers/i2c/busses/i2c-designware-core.c +++ b/drivers/i2c/busses/i2c-designware-core.c @@ -271,6 +271,17 @@ static void __i2c_dw_enable(struct dw_i2c_dev *dev, bool enable) enable ? "en" : "dis"); } +static unsigned long i2c_dw_clk_rate(struct dw_i2c_dev *dev) +{ + /* + * Clock is not necessary if we got LCNT/HCNT values directly from + * the platform code. + */ + if (WARN_ON_ONCE(!dev->get_clk_rate_khz)) + return 0; + return dev->get_clk_rate_khz(dev); +} + /** * i2c_dw_init() - initialize the designware i2c master hardware * @dev: device private data @@ -281,7 +292,6 @@ static void __i2c_dw_enable(struct dw_i2c_dev *dev, bool enable) */ int i2c_dw_init(struct dw_i2c_dev *dev) { - u32 input_clock_khz; u32 hcnt, lcnt; u32 reg; u32 sda_falling_time, scl_falling_time; @@ -295,8 +305,6 @@ int i2c_dw_init(struct dw_i2c_dev *dev) } } - input_clock_khz = dev->get_clk_rate_khz(dev); - reg = dw_readl(dev, DW_IC_COMP_TYPE); if (reg == ___constant_swab32(DW_IC_COMP_TYPE_VALUE)) { /* Configure register endianess access */ @@ -325,12 +333,12 @@ int i2c_dw_init(struct dw_i2c_dev *dev) hcnt = dev->ss_hcnt; lcnt = dev->ss_lcnt; } else { - hcnt = i2c_dw_scl_hcnt(input_clock_khz, + hcnt = i2c_dw_scl_hcnt(i2c_dw_clk_rate(dev), 4000, /* tHD;STA = tHIGH = 4.0 us */ sda_falling_time, 0, /* 0: DW default, 1: Ideal */ 0); /* No offset */ - lcnt = i2c_dw_scl_lcnt(input_clock_khz, + lcnt = i2c_dw_scl_lcnt(i2c_dw_clk_rate(dev), 4700, /* tLOW = 4.7 us */ scl_falling_time, 0); /* No offset */ @@ -344,12 +352,12 @@ int i2c_dw_init(struct dw_i2c_dev *dev) hcnt = dev->fs_hcnt; lcnt = dev->fs_lcnt; } else { - hcnt = i2c_dw_scl_hcnt(input_clock_khz, + hcnt = i2c_dw_scl_hcnt(i2c_dw_clk_rate(dev), 600, /* tHD;STA = tHIGH = 0.6 us */ sda_falling_time, 0, /* 0: DW default, 1: Ideal */ 0); /* No offset */ - lcnt = i2c_dw_scl_lcnt(input_clock_khz, + lcnt = i2c_dw_scl_lcnt(i2c_dw_clk_rate(dev), 1300, /* tLOW = 1.3 us */ scl_falling_time, 0); /* No offset */ @@ -860,6 +868,7 @@ int i2c_dw_probe(struct dw_i2c_dev *dev) snprintf(adap->name, sizeof(adap->name), "Synopsys DesignWare I2C adapter"); + adap->retries = 3; adap->algo = &i2c_dw_algo; adap->dev.parent = dev->dev; i2c_set_adapdata(adap, dev); diff --git a/drivers/i2c/busses/i2c-designware-pcidrv.c b/drivers/i2c/busses/i2c-designware-pcidrv.c index 1543d35d228d..7368be000c96 100644 --- a/drivers/i2c/busses/i2c-designware-pcidrv.c +++ b/drivers/i2c/busses/i2c-designware-pcidrv.c @@ -162,7 +162,7 @@ static struct dw_pci_controller dw_pci_controllers[] = { #ifdef CONFIG_PM static int i2c_dw_pci_suspend(struct device *dev) { - struct pci_dev *pdev = container_of(dev, struct pci_dev, dev); + struct pci_dev *pdev = to_pci_dev(dev); i2c_dw_disable(pci_get_drvdata(pdev)); return 0; @@ -170,7 +170,7 @@ static int i2c_dw_pci_suspend(struct device *dev) static int i2c_dw_pci_resume(struct device *dev) { - struct pci_dev *pdev = container_of(dev, struct pci_dev, dev); + struct pci_dev *pdev = to_pci_dev(dev); return i2c_dw_init(pci_get_drvdata(pdev)); } diff --git a/drivers/i2c/busses/i2c-designware-platdrv.c b/drivers/i2c/busses/i2c-designware-platdrv.c index bf72ae740fc1..438f1b4964c0 100644 --- a/drivers/i2c/busses/i2c-designware-platdrv.c +++ b/drivers/i2c/busses/i2c-designware-platdrv.c @@ -123,6 +123,7 @@ static const struct acpi_device_id dw_i2c_acpi_match[] = { { "80860F41", 0 }, { "808622C1", 0 }, { "AMD0010", ACCESS_INTR_MASK }, + { "AMDI0510", 0 }, { "APMC0D0F", 0 }, { } }; @@ -134,6 +135,18 @@ static inline int dw_i2c_acpi_configure(struct platform_device *pdev) } #endif +static int i2c_dw_plat_prepare_clk(struct dw_i2c_dev *i_dev, bool prepare) +{ + if (IS_ERR(i_dev->clk)) + return PTR_ERR(i_dev->clk); + + if (prepare) + return clk_prepare_enable(i_dev->clk); + + clk_disable_unprepare(i_dev->clk); + return 0; +} + static int dw_i2c_plat_probe(struct platform_device *pdev) { struct dw_i2c_platform_data *pdata = dev_get_platdata(&pdev->dev); @@ -206,16 +219,13 @@ static int dw_i2c_plat_probe(struct platform_device *pdev) DW_IC_CON_RESTART_EN | DW_IC_CON_SPEED_FAST; dev->clk = devm_clk_get(&pdev->dev, NULL); - dev->get_clk_rate_khz = i2c_dw_get_clk_rate_khz; - if (IS_ERR(dev->clk)) - return PTR_ERR(dev->clk); - clk_prepare_enable(dev->clk); + if (!i2c_dw_plat_prepare_clk(dev, true)) { + dev->get_clk_rate_khz = i2c_dw_get_clk_rate_khz; - if (!dev->sda_hold_time && ht) { - u32 ic_clk = dev->get_clk_rate_khz(dev); - - dev->sda_hold_time = div_u64((u64)ic_clk * ht + 500000, - 1000000); + if (!dev->sda_hold_time && ht) + dev->sda_hold_time = div_u64( + (u64)dev->get_clk_rate_khz(dev) * ht + 500000, + 1000000); } if (!dev->tx_fifo_depth) { @@ -297,7 +307,7 @@ static int dw_i2c_plat_suspend(struct device *dev) struct dw_i2c_dev *i_dev = platform_get_drvdata(pdev); i2c_dw_disable(i_dev); - clk_disable_unprepare(i_dev->clk); + i2c_dw_plat_prepare_clk(i_dev, false); return 0; } @@ -307,7 +317,7 @@ static int dw_i2c_plat_resume(struct device *dev) struct platform_device *pdev = to_platform_device(dev); struct dw_i2c_dev *i_dev = platform_get_drvdata(pdev); - clk_prepare_enable(i_dev->clk); + i2c_dw_plat_prepare_clk(i_dev, true); if (!i_dev->pm_runtime_disabled) i2c_dw_init(i_dev); diff --git a/drivers/i2c/busses/i2c-eg20t.c b/drivers/i2c/busses/i2c-eg20t.c index 76e699f9ed97..137125b5eae7 100644 --- a/drivers/i2c/busses/i2c-eg20t.c +++ b/drivers/i2c/busses/i2c-eg20t.c @@ -795,6 +795,7 @@ static int pch_i2c_probe(struct pci_dev *pdev, /* base_addr + offset; */ adap_info->pch_data[i].pch_base_address = base_addr + 0x100 * i; + pch_adap->dev.of_node = pdev->dev.of_node; pch_adap->dev.parent = &pdev->dev; pch_i2c_init(&adap_info->pch_data[i]); diff --git a/drivers/i2c/busses/i2c-emev2.c b/drivers/i2c/busses/i2c-emev2.c index 192ef6b50c79..96bb4e749012 100644 --- a/drivers/i2c/busses/i2c-emev2.c +++ b/drivers/i2c/busses/i2c-emev2.c @@ -71,6 +71,7 @@ struct em_i2c_device { struct i2c_adapter adap; struct completion msg_done; struct clk *sclk; + struct i2c_client *slave; }; static inline void em_clear_set_bit(struct em_i2c_device *priv, u8 clear, u8 set, u8 reg) @@ -226,22 +227,131 @@ static int em_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, return num; } +static bool em_i2c_slave_irq(struct em_i2c_device *priv) +{ + u8 status, value; + enum i2c_slave_event event; + int ret; + + if (!priv->slave) + return false; + + status = readb(priv->base + I2C_OFS_IICSE0); + + /* Extension code, do not participate */ + if (status & I2C_BIT_EXC0) { + em_clear_set_bit(priv, 0, I2C_BIT_LREL0, I2C_OFS_IICC0); + return true; + } + + /* Stop detected, we don't know if it's for slave or master */ + if (status & I2C_BIT_SPD0) { + /* Notify slave device */ + i2c_slave_event(priv->slave, I2C_SLAVE_STOP, &value); + /* Pretend we did not handle the interrupt */ + return false; + } + + /* Only handle interrupts addressed to us */ + if (!(status & I2C_BIT_COI0)) + return false; + + /* Enable stop interrupts */ + em_clear_set_bit(priv, 0, I2C_BIT_SPIE0, I2C_OFS_IICC0); + + /* Transmission or Reception */ + if (status & I2C_BIT_TRC0) { + if (status & I2C_BIT_ACKD0) { + /* 9 bit interrupt mode */ + em_clear_set_bit(priv, 0, I2C_BIT_WTIM0, I2C_OFS_IICC0); + + /* Send data */ + event = status & I2C_BIT_STD0 ? + I2C_SLAVE_READ_REQUESTED : + I2C_SLAVE_READ_PROCESSED; + i2c_slave_event(priv->slave, event, &value); + writeb(value, priv->base + I2C_OFS_IIC0); + } else { + /* NACK, stop transmitting */ + em_clear_set_bit(priv, 0, I2C_BIT_LREL0, I2C_OFS_IICC0); + } + } else { + /* 8 bit interrupt mode */ + em_clear_set_bit(priv, I2C_BIT_WTIM0, I2C_BIT_ACKE0, + I2C_OFS_IICC0); + em_clear_set_bit(priv, I2C_BIT_WTIM0, I2C_BIT_WREL0, + I2C_OFS_IICC0); + + if (status & I2C_BIT_STD0) { + i2c_slave_event(priv->slave, I2C_SLAVE_WRITE_REQUESTED, + &value); + } else { + /* Recv data */ + value = readb(priv->base + I2C_OFS_IIC0); + ret = i2c_slave_event(priv->slave, + I2C_SLAVE_WRITE_RECEIVED, &value); + if (ret < 0) + em_clear_set_bit(priv, I2C_BIT_ACKE0, 0, + I2C_OFS_IICC0); + } + } + + return true; +} + static irqreturn_t em_i2c_irq_handler(int this_irq, void *dev_id) { struct em_i2c_device *priv = dev_id; + if (em_i2c_slave_irq(priv)) + return IRQ_HANDLED; + complete(&priv->msg_done); + return IRQ_HANDLED; } static u32 em_i2c_func(struct i2c_adapter *adap) { - return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL; + return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL | I2C_FUNC_SLAVE; +} + +static int em_i2c_reg_slave(struct i2c_client *slave) +{ + struct em_i2c_device *priv = i2c_get_adapdata(slave->adapter); + + if (priv->slave) + return -EBUSY; + + if (slave->flags & I2C_CLIENT_TEN) + return -EAFNOSUPPORT; + + priv->slave = slave; + + /* Set slave address */ + writeb(slave->addr << 1, priv->base + I2C_OFS_SVA0); + + return 0; +} + +static int em_i2c_unreg_slave(struct i2c_client *slave) +{ + struct em_i2c_device *priv = i2c_get_adapdata(slave->adapter); + + WARN_ON(!priv->slave); + + writeb(0, priv->base + I2C_OFS_SVA0); + + priv->slave = NULL; + + return 0; } static struct i2c_algorithm em_i2c_algo = { .master_xfer = em_i2c_xfer, .functionality = em_i2c_func, + .reg_slave = em_i2c_reg_slave, + .unreg_slave = em_i2c_unreg_slave, }; static int em_i2c_probe(struct platform_device *pdev) diff --git a/drivers/i2c/busses/i2c-ibm_iic.c b/drivers/i2c/busses/i2c-ibm_iic.c index ab492301581a..b6c080334297 100644 --- a/drivers/i2c/busses/i2c-ibm_iic.c +++ b/drivers/i2c/busses/i2c-ibm_iic.c @@ -99,7 +99,7 @@ static void dump_iic_regs(const char* header, struct ibm_iic_private* dev) #endif /* Bus timings (in ns) for bit-banging */ -static struct i2c_timings { +static struct ibm_iic_timings { unsigned int hd_sta; unsigned int su_sto; unsigned int low; @@ -241,7 +241,7 @@ static int iic_dc_wait(volatile struct iic_regs __iomem *iic, u8 mask) static int iic_smbus_quick(struct ibm_iic_private* dev, const struct i2c_msg* p) { volatile struct iic_regs __iomem *iic = dev->vaddr; - const struct i2c_timings* t = &timings[dev->fast_mode ? 1 : 0]; + const struct ibm_iic_timings *t = &timings[dev->fast_mode ? 1 : 0]; u8 mask, v, sda; int i, res; diff --git a/drivers/i2c/busses/i2c-img-scb.c b/drivers/i2c/busses/i2c-img-scb.c index 3795fe130ef2..379ef9c31664 100644 --- a/drivers/i2c/busses/i2c-img-scb.c +++ b/drivers/i2c/busses/i2c-img-scb.c @@ -151,10 +151,11 @@ #define INT_FIFO_EMPTYING BIT(12) #define INT_TRANSACTION_DONE BIT(15) #define INT_SLAVE_EVENT BIT(16) +#define INT_MASTER_HALTED BIT(17) #define INT_TIMING BIT(18) +#define INT_STOP_DETECTED BIT(19) #define INT_FIFO_FULL_FILLING (INT_FIFO_FULL | INT_FIFO_FILLING) -#define INT_FIFO_EMPTY_EMPTYING (INT_FIFO_EMPTY | INT_FIFO_EMPTYING) /* Level interrupts need clearing after handling instead of before */ #define INT_LEVEL 0x01e00 @@ -177,7 +178,8 @@ INT_FIFO_FULL | \ INT_FIFO_FILLING | \ INT_FIFO_EMPTY | \ - INT_FIFO_EMPTYING) + INT_MASTER_HALTED | \ + INT_STOP_DETECTED) #define INT_ENABLE_MASK_WAITSTOP (INT_SLAVE_EVENT | \ INT_ADDR_ACK_ERR | \ @@ -511,7 +513,17 @@ static void img_i2c_soft_reset(struct img_i2c *i2c) SCB_CONTROL_CLK_ENABLE | SCB_CONTROL_SOFT_RESET); } -/* enable or release transaction halt for control of repeated starts */ +/* + * Enable or release transaction halt for control of repeated starts. + * In version 3.3 of the IP when transaction halt is set, an interrupt + * will be generated after each byte of a transfer instead of after + * every transfer but before the stop bit. + * Due to this behaviour we have to be careful that every time we + * release the transaction halt we have to re-enable it straight away + * so that we only process a single byte, not doing so will result in + * all remaining bytes been processed and a stop bit being issued, + * which will prevent us having a repeated start. + */ static void img_i2c_transaction_halt(struct img_i2c *i2c, bool t_halt) { u32 val; @@ -580,7 +592,6 @@ static void img_i2c_read(struct img_i2c *i2c) img_i2c_writel(i2c, SCB_READ_ADDR_REG, i2c->msg.addr); img_i2c_writel(i2c, SCB_READ_COUNT_REG, i2c->msg.len); - img_i2c_transaction_halt(i2c, false); mod_timer(&i2c->check_timer, jiffies + msecs_to_jiffies(1)); } @@ -594,7 +605,6 @@ static void img_i2c_write(struct img_i2c *i2c) img_i2c_writel(i2c, SCB_WRITE_ADDR_REG, i2c->msg.addr); img_i2c_writel(i2c, SCB_WRITE_COUNT_REG, i2c->msg.len); - img_i2c_transaction_halt(i2c, false); mod_timer(&i2c->check_timer, jiffies + msecs_to_jiffies(1)); img_i2c_write_fifo(i2c); @@ -750,7 +760,9 @@ static unsigned int img_i2c_atomic(struct img_i2c *i2c, next_cmd = CMD_RET_ACK; break; case CMD_RET_ACK: - if (i2c->line_status & LINESTAT_ACK_DET) { + if (i2c->line_status & LINESTAT_ACK_DET || + (i2c->line_status & LINESTAT_NACK_DET && + i2c->msg.flags & I2C_M_IGNORE_NAK)) { if (i2c->msg.len == 0) { next_cmd = CMD_GEN_STOP; } else if (i2c->msg.flags & I2C_M_RD) { @@ -858,34 +870,42 @@ static unsigned int img_i2c_auto(struct img_i2c *i2c, /* Enable transaction halt on start bit */ if (!i2c->last_msg && line_status & LINESTAT_START_BIT_DET) { - img_i2c_transaction_halt(i2c, true); + img_i2c_transaction_halt(i2c, !i2c->last_msg); /* we're no longer interested in the slave event */ i2c->int_enable &= ~INT_SLAVE_EVENT; } mod_timer(&i2c->check_timer, jiffies + msecs_to_jiffies(1)); + if (int_status & INT_STOP_DETECTED) { + /* Drain remaining data in FIFO and complete transaction */ + if (i2c->msg.flags & I2C_M_RD) + img_i2c_read_fifo(i2c); + return ISR_COMPLETE(0); + } + if (i2c->msg.flags & I2C_M_RD) { - if (int_status & INT_FIFO_FULL_FILLING) { + if (int_status & (INT_FIFO_FULL_FILLING | INT_MASTER_HALTED)) { img_i2c_read_fifo(i2c); if (i2c->msg.len == 0) return ISR_WAITSTOP; } } else { - if (int_status & INT_FIFO_EMPTY_EMPTYING) { - /* - * The write fifo empty indicates that we're in the - * last byte so it's safe to start a new write - * transaction without losing any bytes from the - * previous one. - * see 2.3.7 Repeated Start Transactions. - */ + if (int_status & (INT_FIFO_EMPTY | INT_MASTER_HALTED)) { if ((int_status & INT_FIFO_EMPTY) && i2c->msg.len == 0) return ISR_WAITSTOP; img_i2c_write_fifo(i2c); } } + if (int_status & INT_MASTER_HALTED) { + /* + * Release and then enable transaction halt, to + * allow only a single byte to proceed. + */ + img_i2c_transaction_halt(i2c, false); + img_i2c_transaction_halt(i2c, !i2c->last_msg); + } return 0; } @@ -1017,20 +1037,23 @@ static int img_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, return -EIO; for (i = 0; i < num; i++) { - if (likely(msgs[i].len)) - continue; /* * 0 byte reads are not possible because the slave could try * and pull the data line low, preventing a stop bit. */ - if (unlikely(msgs[i].flags & I2C_M_RD)) + if (!msgs[i].len && msgs[i].flags & I2C_M_RD) return -EIO; /* * 0 byte writes are possible and used for probing, but we * cannot do them in automatic mode, so use atomic mode * instead. + * + * Also, the I2C_M_IGNORE_NAK mode can only be implemented + * in atomic mode. */ - atomic = true; + if (!msgs[i].len || + (msgs[i].flags & I2C_M_IGNORE_NAK)) + atomic = true; } ret = clk_prepare_enable(i2c->scb_clk); @@ -1069,12 +1092,31 @@ static int img_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, img_i2c_writel(i2c, SCB_INT_CLEAR_REG, ~0); img_i2c_writel(i2c, SCB_CLEAR_REG, ~0); - if (atomic) + if (atomic) { img_i2c_atomic_start(i2c); - else if (msg->flags & I2C_M_RD) - img_i2c_read(i2c); - else - img_i2c_write(i2c); + } else { + /* + * Enable transaction halt if not the last message in + * the queue so that we can control repeated starts. + */ + img_i2c_transaction_halt(i2c, !i2c->last_msg); + + if (msg->flags & I2C_M_RD) + img_i2c_read(i2c); + else + img_i2c_write(i2c); + + /* + * Release and then enable transaction halt, to + * allow only a single byte to proceed. + * This doesn't have an effect on the initial transfer + * but will allow the following transfers to start + * processing if the previous transfer was marked as + * complete while the i2c block was halted. + */ + img_i2c_transaction_halt(i2c, false); + img_i2c_transaction_halt(i2c, !i2c->last_msg); + } spin_unlock_irqrestore(&i2c->lock, flags); time_left = wait_for_completion_timeout(&i2c->msg_complete, diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index d4d853680ae4..a2b132cef717 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -29,9 +29,6 @@ * */ -/** Includes ******************************************************************* -*******************************************************************************/ - #include <linux/clk.h> #include <linux/completion.h> #include <linux/delay.h> @@ -53,12 +50,10 @@ #include <linux/pinctrl/consumer.h> #include <linux/platform_data/i2c-imx.h> #include <linux/platform_device.h> +#include <linux/pm_runtime.h> #include <linux/sched.h> #include <linux/slab.h> -/** Defines ******************************************************************** -*******************************************************************************/ - /* This will be the driver name the kernel reports */ #define DRIVER_NAME "imx-i2c" @@ -120,8 +115,7 @@ #define I2CR_IEN_OPCODE_0 0x0 #define I2CR_IEN_OPCODE_1 I2CR_IEN -/** Variables ****************************************************************** -*******************************************************************************/ +#define I2C_PM_TIMEOUT 10 /* ms */ /* * sorted list of clock divider, register value pairs @@ -346,7 +340,7 @@ fail_tx: dma_release_channel(dma->chan_tx); fail_al: devm_kfree(dev, dma); - dev_info(dev, "can't use DMA\n"); + dev_info(dev, "can't use DMA, using PIO instead.\n"); } static void i2c_imx_dma_callback(void *arg) @@ -393,6 +387,7 @@ static int i2c_imx_dma_xfer(struct imx_i2c_struct *i2c_imx, return 0; err_submit: + dmaengine_terminate_all(dma->chan_using); err_desc: dma_unmap_single(chan_dev, dma->dma_buf, dma->dma_len, dma->dma_data_dir); @@ -416,9 +411,6 @@ static void i2c_imx_dma_free(struct imx_i2c_struct *i2c_imx) dma->chan_using = NULL; } -/** Functions for IMX I2C adapter driver *************************************** -*******************************************************************************/ - static int i2c_imx_bus_busy(struct imx_i2c_struct *i2c_imx, int for_busy) { unsigned long orig_jiffies = jiffies; @@ -527,9 +519,6 @@ static int i2c_imx_start(struct imx_i2c_struct *i2c_imx) i2c_imx_set_clk(i2c_imx); - result = clk_prepare_enable(i2c_imx->clk); - if (result) - return result; imx_i2c_write_reg(i2c_imx->ifdr, i2c_imx, IMX_I2C_IFDR); /* Enable I2C controller */ imx_i2c_write_reg(i2c_imx->hwdata->i2sr_clr_opcode, i2c_imx, IMX_I2C_I2SR); @@ -582,7 +571,6 @@ static void i2c_imx_stop(struct imx_i2c_struct *i2c_imx) /* Disable I2C controller */ temp = i2c_imx->hwdata->i2cr_ien_opcode ^ I2CR_IEN, imx_i2c_write_reg(temp, i2c_imx, IMX_I2C_I2CR); - clk_disable_unprepare(i2c_imx->clk); } static irqreturn_t i2c_imx_isr(int irq, void *dev_id) @@ -901,6 +889,10 @@ static int i2c_imx_xfer(struct i2c_adapter *adapter, dev_dbg(&i2c_imx->adapter.dev, "<%s>\n", __func__); + result = pm_runtime_get_sync(i2c_imx->adapter.dev.parent); + if (result < 0) + goto out; + /* Start I2C transfer */ result = i2c_imx_start(i2c_imx); if (result) { @@ -964,6 +956,10 @@ fail0: /* Stop I2C transfer */ i2c_imx_stop(i2c_imx); + pm_runtime_mark_last_busy(i2c_imx->adapter.dev.parent); + pm_runtime_put_autosuspend(i2c_imx->adapter.dev.parent); + +out: dev_dbg(&i2c_imx->adapter.dev, "<%s> exit with: %s: %d\n", __func__, (result < 0) ? "error" : "success msg", (result < 0) ? result : num); @@ -997,10 +993,8 @@ static void i2c_imx_init_recovery_info(struct imx_i2c_struct *i2c_imx, PINCTRL_STATE_DEFAULT); i2c_imx->pinctrl_pins_gpio = pinctrl_lookup_state(i2c_imx->pinctrl, "gpio"); - rinfo->sda_gpio = of_get_named_gpio_flags(pdev->dev.of_node, - "sda-gpios", 0, NULL); - rinfo->scl_gpio = of_get_named_gpio_flags(pdev->dev.of_node, - "scl-gpios", 0, NULL); + rinfo->sda_gpio = of_get_named_gpio(pdev->dev.of_node, "sda-gpios", 0); + rinfo->scl_gpio = of_get_named_gpio(pdev->dev.of_node, "scl-gpios", 0); if (!gpio_is_valid(rinfo->sda_gpio) || !gpio_is_valid(rinfo->scl_gpio) || @@ -1083,7 +1077,7 @@ static int i2c_imx_probe(struct platform_device *pdev) ret = clk_prepare_enable(i2c_imx->clk); if (ret) { - dev_err(&pdev->dev, "can't enable I2C clock\n"); + dev_err(&pdev->dev, "can't enable I2C clock, ret=%d\n", ret); return ret; } @@ -1107,6 +1101,18 @@ static int i2c_imx_probe(struct platform_device *pdev) /* Set up adapter data */ i2c_set_adapdata(&i2c_imx->adapter, i2c_imx); + /* Set up platform driver data */ + platform_set_drvdata(pdev, i2c_imx); + + pm_runtime_set_autosuspend_delay(&pdev->dev, I2C_PM_TIMEOUT); + pm_runtime_use_autosuspend(&pdev->dev); + pm_runtime_set_active(&pdev->dev); + pm_runtime_enable(&pdev->dev); + + ret = pm_runtime_get_sync(&pdev->dev); + if (ret < 0) + goto rpm_disable; + /* Set up clock divider */ i2c_imx->bitrate = IMX_I2C_BIT_RATE; ret = of_property_read_u32(pdev->dev.of_node, @@ -1125,12 +1131,11 @@ static int i2c_imx_probe(struct platform_device *pdev) ret = i2c_add_numbered_adapter(&i2c_imx->adapter); if (ret < 0) { dev_err(&pdev->dev, "registration failed\n"); - goto clk_disable; + goto rpm_disable; } - /* Set up platform driver data */ - platform_set_drvdata(pdev, i2c_imx); - clk_disable_unprepare(i2c_imx->clk); + pm_runtime_mark_last_busy(&pdev->dev); + pm_runtime_put_autosuspend(&pdev->dev); dev_dbg(&i2c_imx->adapter.dev, "claimed irq %d\n", irq); dev_dbg(&i2c_imx->adapter.dev, "device resources: %pR\n", res); @@ -1143,6 +1148,12 @@ static int i2c_imx_probe(struct platform_device *pdev) return 0; /* Return OK */ +rpm_disable: + pm_runtime_put_noidle(&pdev->dev); + pm_runtime_disable(&pdev->dev); + pm_runtime_set_suspended(&pdev->dev); + pm_runtime_dont_use_autosuspend(&pdev->dev); + clk_disable: clk_disable_unprepare(i2c_imx->clk); return ret; @@ -1151,6 +1162,11 @@ clk_disable: static int i2c_imx_remove(struct platform_device *pdev) { struct imx_i2c_struct *i2c_imx = platform_get_drvdata(pdev); + int ret; + + ret = pm_runtime_get_sync(&pdev->dev); + if (ret < 0) + return ret; /* remove adapter */ dev_dbg(&i2c_imx->adapter.dev, "adapter removed\n"); @@ -1165,17 +1181,54 @@ static int i2c_imx_remove(struct platform_device *pdev) imx_i2c_write_reg(0, i2c_imx, IMX_I2C_I2CR); imx_i2c_write_reg(0, i2c_imx, IMX_I2C_I2SR); + clk_disable_unprepare(i2c_imx->clk); + + pm_runtime_put_noidle(&pdev->dev); + pm_runtime_disable(&pdev->dev); + + return 0; +} + +#ifdef CONFIG_PM +static int i2c_imx_runtime_suspend(struct device *dev) +{ + struct imx_i2c_struct *i2c_imx = dev_get_drvdata(dev); + + clk_disable_unprepare(i2c_imx->clk); + return 0; } +static int i2c_imx_runtime_resume(struct device *dev) +{ + struct imx_i2c_struct *i2c_imx = dev_get_drvdata(dev); + int ret; + + ret = clk_prepare_enable(i2c_imx->clk); + if (ret) + dev_err(dev, "can't enable I2C clock, ret=%d\n", ret); + + return ret; +} + +static const struct dev_pm_ops i2c_imx_pm_ops = { + SET_RUNTIME_PM_OPS(i2c_imx_runtime_suspend, + i2c_imx_runtime_resume, NULL) +}; +#define I2C_IMX_PM_OPS (&i2c_imx_pm_ops) +#else +#define I2C_IMX_PM_OPS NULL +#endif /* CONFIG_PM */ + static struct platform_driver i2c_imx_driver = { .probe = i2c_imx_probe, .remove = i2c_imx_remove, - .driver = { - .name = DRIVER_NAME, + .driver = { + .name = DRIVER_NAME, + .pm = I2C_IMX_PM_OPS, .of_match_table = i2c_imx_dt_ids, }, - .id_table = imx_i2c_devtype, + .id_table = imx_i2c_devtype, }; static int __init i2c_adap_imx_init(void) diff --git a/drivers/i2c/busses/i2c-mt65xx.c b/drivers/i2c/busses/i2c-mt65xx.c index 9b867169142f..aec8e6ce38a4 100644 --- a/drivers/i2c/busses/i2c-mt65xx.c +++ b/drivers/i2c/busses/i2c-mt65xx.c @@ -132,6 +132,7 @@ struct mtk_i2c_compatible { unsigned char pmic_i2c: 1; unsigned char dcm: 1; unsigned char auto_restart: 1; + unsigned char aux_len_reg: 1; }; struct mtk_i2c { @@ -153,6 +154,8 @@ struct mtk_i2c { enum mtk_trans_op op; u16 timing_reg; u16 high_speed_reg; + unsigned char auto_restart; + bool ignore_restart_irq; const struct mtk_i2c_compatible *dev_comp; }; @@ -178,6 +181,7 @@ static const struct mtk_i2c_compatible mt6577_compat = { .pmic_i2c = 0, .dcm = 1, .auto_restart = 0, + .aux_len_reg = 0, }; static const struct mtk_i2c_compatible mt6589_compat = { @@ -185,6 +189,7 @@ static const struct mtk_i2c_compatible mt6589_compat = { .pmic_i2c = 1, .dcm = 0, .auto_restart = 0, + .aux_len_reg = 0, }; static const struct mtk_i2c_compatible mt8173_compat = { @@ -192,6 +197,7 @@ static const struct mtk_i2c_compatible mt8173_compat = { .pmic_i2c = 0, .dcm = 1, .auto_restart = 1, + .aux_len_reg = 1, }; static const struct of_device_id mtk_i2c_of_match[] = { @@ -373,7 +379,7 @@ static int mtk_i2c_do_transfer(struct mtk_i2c *i2c, struct i2c_msg *msgs, i2c->irq_stat = 0; - if (i2c->dev_comp->auto_restart) + if (i2c->auto_restart) restart_flag = I2C_RS_TRANSFER; reinit_completion(&i2c->msg_complete); @@ -411,8 +417,14 @@ static int mtk_i2c_do_transfer(struct mtk_i2c *i2c, struct i2c_msg *msgs, /* Set transfer and transaction len */ if (i2c->op == I2C_MASTER_WRRD) { - writew(msgs->len | ((msgs + 1)->len) << 8, - i2c->base + OFFSET_TRANSFER_LEN); + if (i2c->dev_comp->aux_len_reg) { + writew(msgs->len, i2c->base + OFFSET_TRANSFER_LEN); + writew((msgs + 1)->len, i2c->base + + OFFSET_TRANSFER_LEN_AUX); + } else { + writew(msgs->len | ((msgs + 1)->len) << 8, + i2c->base + OFFSET_TRANSFER_LEN); + } writew(I2C_WRRD_TRANAC_VALUE, i2c->base + OFFSET_TRANSAC_LEN); } else { writew(msgs->len, i2c->base + OFFSET_TRANSFER_LEN); @@ -461,7 +473,7 @@ static int mtk_i2c_do_transfer(struct mtk_i2c *i2c, struct i2c_msg *msgs, writel(I2C_DMA_START_EN, i2c->pdmabase + OFFSET_EN); - if (!i2c->dev_comp->auto_restart) { + if (!i2c->auto_restart) { start_reg = I2C_TRANSAC_START; } else { start_reg = I2C_TRANSAC_START | I2C_RS_MUL_TRIG; @@ -518,6 +530,24 @@ static int mtk_i2c_transfer(struct i2c_adapter *adap, if (ret) return ret; + i2c->auto_restart = i2c->dev_comp->auto_restart; + + /* checking if we can skip restart and optimize using WRRD mode */ + if (i2c->auto_restart && num == 2) { + if (!(msgs[0].flags & I2C_M_RD) && (msgs[1].flags & I2C_M_RD) && + msgs[0].addr == msgs[1].addr) { + i2c->auto_restart = 0; + } + } + + if (i2c->auto_restart && num >= 2 && i2c->speed_hz > MAX_FS_MODE_SPEED) + /* ignore the first restart irq after the master code, + * otherwise the first transfer will be discarded. + */ + i2c->ignore_restart_irq = true; + else + i2c->ignore_restart_irq = false; + while (left_num--) { if (!msgs->buf) { dev_dbg(i2c->dev, "data buffer is NULL.\n"); @@ -530,7 +560,7 @@ static int mtk_i2c_transfer(struct i2c_adapter *adap, else i2c->op = I2C_MASTER_WR; - if (!i2c->dev_comp->auto_restart) { + if (!i2c->auto_restart) { if (num > 1) { /* combined two messages into one transaction */ i2c->op = I2C_MASTER_WRRD; @@ -559,7 +589,7 @@ static irqreturn_t mtk_i2c_irq(int irqno, void *dev_id) u16 restart_flag = 0; u16 intr_stat; - if (i2c->dev_comp->auto_restart) + if (i2c->auto_restart) restart_flag = I2C_RS_TRANSFER; intr_stat = readw(i2c->base + OFFSET_INTR_STAT); @@ -571,8 +601,16 @@ static irqreturn_t mtk_i2c_irq(int irqno, void *dev_id) * i2c->irq_stat need keep the two interrupt value. */ i2c->irq_stat |= intr_stat; - if (i2c->irq_stat & (I2C_TRANSAC_COMP | restart_flag)) - complete(&i2c->msg_complete); + + if (i2c->ignore_restart_irq && (i2c->irq_stat & restart_flag)) { + i2c->ignore_restart_irq = false; + i2c->irq_stat = 0; + writew(I2C_RS_MUL_CNFG | I2C_RS_MUL_TRIG | I2C_TRANSAC_START, + i2c->base + OFFSET_START); + } else { + if (i2c->irq_stat & (I2C_TRANSAC_COMP | restart_flag)) + complete(&i2c->msg_complete); + } return IRQ_HANDLED; } diff --git a/drivers/i2c/busses/i2c-piix4.c b/drivers/i2c/busses/i2c-piix4.c index 630bce68bf38..e04598595073 100644 --- a/drivers/i2c/busses/i2c-piix4.c +++ b/drivers/i2c/busses/i2c-piix4.c @@ -23,6 +23,9 @@ Note: we assume there can only be one device, with one or more SMBus interfaces. + The device can register multiple i2c_adapters (up to PIIX4_MAX_ADAPTERS). + For devices supporting multiple ports the i2c_adapter should provide + an i2c_algorithm to access them. */ #include <linux/module.h> @@ -37,6 +40,7 @@ #include <linux/dmi.h> #include <linux/acpi.h> #include <linux/io.h> +#include <linux/mutex.h> /* PIIX4 SMBus address offsets */ @@ -75,6 +79,16 @@ #define PIIX4_WORD_DATA 0x0C #define PIIX4_BLOCK_DATA 0x14 +/* Multi-port constants */ +#define PIIX4_MAX_ADAPTERS 4 + +/* SB800 constants */ +#define SB800_PIIX4_SMB_IDX 0xcd6 + +/* SB800 port is selected by bits 2:1 of the smb_en register (0x2c) */ +#define SB800_PIIX4_PORT_IDX 0x2c +#define SB800_PIIX4_PORT_IDX_MASK 0x06 + /* insmod parameters */ /* If force is set to anything different from 0, we forcibly enable the @@ -122,8 +136,19 @@ static const struct dmi_system_id piix4_dmi_ibm[] = { { }, }; +/* SB800 globals */ +static const char *piix4_main_port_names_sb800[PIIX4_MAX_ADAPTERS] = { + "SDA0", "SDA2", "SDA3", "SDA4" +}; +static const char *piix4_aux_port_name_sb800 = "SDA1"; + struct i2c_piix4_adapdata { unsigned short smba; + + /* SB800 */ + bool sb800_main; + unsigned short port; + struct mutex *mutex; }; static int piix4_setup(struct pci_dev *PIIX4_dev, @@ -229,7 +254,6 @@ static int piix4_setup_sb800(struct pci_dev *PIIX4_dev, const struct pci_device_id *id, u8 aux) { unsigned short piix4_smba; - unsigned short smba_idx = 0xcd6; u8 smba_en_lo, smba_en_hi, smb_en, smb_en_status; u8 i2ccfg, i2ccfg_offset = 0x10; @@ -251,16 +275,10 @@ static int piix4_setup_sb800(struct pci_dev *PIIX4_dev, else smb_en = (aux) ? 0x28 : 0x2c; - if (!request_region(smba_idx, 2, "smba_idx")) { - dev_err(&PIIX4_dev->dev, "SMBus base address index region " - "0x%x already in use!\n", smba_idx); - return -EBUSY; - } - outb_p(smb_en, smba_idx); - smba_en_lo = inb_p(smba_idx + 1); - outb_p(smb_en + 1, smba_idx); - smba_en_hi = inb_p(smba_idx + 1); - release_region(smba_idx, 2); + outb_p(smb_en, SB800_PIIX4_SMB_IDX); + smba_en_lo = inb_p(SB800_PIIX4_SMB_IDX + 1); + outb_p(smb_en + 1, SB800_PIIX4_SMB_IDX); + smba_en_hi = inb_p(SB800_PIIX4_SMB_IDX + 1); if (!smb_en) { smb_en_status = smba_en_lo & 0x10; @@ -483,7 +501,7 @@ static s32 piix4_access(struct i2c_adapter * adap, u16 addr, if (len == 0 || len > I2C_SMBUS_BLOCK_MAX) return -EINVAL; outb_p(len, SMBHSTDAT0); - i = inb_p(SMBHSTCNT); /* Reset SMBBLKDAT */ + inb_p(SMBHSTCNT); /* Reset SMBBLKDAT */ for (i = 1; i <= len; i++) outb_p(data->block[i], SMBBLKDAT); } @@ -516,7 +534,7 @@ static s32 piix4_access(struct i2c_adapter * adap, u16 addr, data->block[0] = inb_p(SMBHSTDAT0); if (data->block[0] == 0 || data->block[0] > I2C_SMBUS_BLOCK_MAX) return -EPROTO; - i = inb_p(SMBHSTCNT); /* Reset SMBBLKDAT */ + inb_p(SMBHSTCNT); /* Reset SMBBLKDAT */ for (i = 1; i <= data->block[0]; i++) data->block[i] = inb_p(SMBBLKDAT); break; @@ -524,6 +542,43 @@ static s32 piix4_access(struct i2c_adapter * adap, u16 addr, return 0; } +/* + * Handles access to multiple SMBus ports on the SB800. + * The port is selected by bits 2:1 of the smb_en register (0x2c). + * Returns negative errno on error. + * + * Note: The selected port must be returned to the initial selection to avoid + * problems on certain systems. + */ +static s32 piix4_access_sb800(struct i2c_adapter *adap, u16 addr, + unsigned short flags, char read_write, + u8 command, int size, union i2c_smbus_data *data) +{ + struct i2c_piix4_adapdata *adapdata = i2c_get_adapdata(adap); + u8 smba_en_lo; + u8 port; + int retval; + + mutex_lock(adapdata->mutex); + + outb_p(SB800_PIIX4_PORT_IDX, SB800_PIIX4_SMB_IDX); + smba_en_lo = inb_p(SB800_PIIX4_SMB_IDX + 1); + + port = adapdata->port; + if ((smba_en_lo & SB800_PIIX4_PORT_IDX_MASK) != (port << 1)) + outb_p((smba_en_lo & ~SB800_PIIX4_PORT_IDX_MASK) | (port << 1), + SB800_PIIX4_SMB_IDX + 1); + + retval = piix4_access(adap, addr, flags, read_write, + command, size, data); + + outb_p(smba_en_lo, SB800_PIIX4_SMB_IDX + 1); + + mutex_unlock(adapdata->mutex); + + return retval; +} + static u32 piix4_func(struct i2c_adapter *adapter) { return I2C_FUNC_SMBUS_QUICK | I2C_FUNC_SMBUS_BYTE | @@ -536,6 +591,11 @@ static const struct i2c_algorithm smbus_algorithm = { .functionality = piix4_func, }; +static const struct i2c_algorithm piix4_smbus_algorithm_sb800 = { + .smbus_xfer = piix4_access_sb800, + .functionality = piix4_func, +}; + static const struct pci_device_id piix4_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82371AB_3) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82443MX_3) }, @@ -561,11 +621,11 @@ static const struct pci_device_id piix4_ids[] = { MODULE_DEVICE_TABLE (pci, piix4_ids); -static struct i2c_adapter *piix4_main_adapter; +static struct i2c_adapter *piix4_main_adapters[PIIX4_MAX_ADAPTERS]; static struct i2c_adapter *piix4_aux_adapter; static int piix4_add_adapter(struct pci_dev *dev, unsigned short smba, - struct i2c_adapter **padap) + const char *name, struct i2c_adapter **padap) { struct i2c_adapter *adap; struct i2c_piix4_adapdata *adapdata; @@ -594,7 +654,7 @@ static int piix4_add_adapter(struct pci_dev *dev, unsigned short smba, adap->dev.parent = &dev->dev; snprintf(adap->name, sizeof(adap->name), - "SMBus PIIX4 adapter at %04x", smba); + "SMBus PIIX4 adapter %s at %04x", name, smba); i2c_set_adapdata(adap, adapdata); @@ -611,6 +671,54 @@ static int piix4_add_adapter(struct pci_dev *dev, unsigned short smba, return 0; } +static int piix4_add_adapters_sb800(struct pci_dev *dev, unsigned short smba) +{ + struct mutex *mutex; + struct i2c_piix4_adapdata *adapdata; + int port; + int retval; + + mutex = kzalloc(sizeof(*mutex), GFP_KERNEL); + if (mutex == NULL) + return -ENOMEM; + + mutex_init(mutex); + + for (port = 0; port < PIIX4_MAX_ADAPTERS; port++) { + retval = piix4_add_adapter(dev, smba, + piix4_main_port_names_sb800[port], + &piix4_main_adapters[port]); + if (retval < 0) + goto error; + + piix4_main_adapters[port]->algo = &piix4_smbus_algorithm_sb800; + + adapdata = i2c_get_adapdata(piix4_main_adapters[port]); + adapdata->sb800_main = true; + adapdata->port = port; + adapdata->mutex = mutex; + } + + return retval; + +error: + dev_err(&dev->dev, + "Error setting up SB800 adapters. Unregistering!\n"); + while (--port >= 0) { + adapdata = i2c_get_adapdata(piix4_main_adapters[port]); + if (adapdata->smba) { + i2c_del_adapter(piix4_main_adapters[port]); + kfree(adapdata); + kfree(piix4_main_adapters[port]); + piix4_main_adapters[port] = NULL; + } + } + + kfree(mutex); + + return retval; +} + static int piix4_probe(struct pci_dev *dev, const struct pci_device_id *id) { int retval; @@ -618,20 +726,41 @@ static int piix4_probe(struct pci_dev *dev, const struct pci_device_id *id) if ((dev->vendor == PCI_VENDOR_ID_ATI && dev->device == PCI_DEVICE_ID_ATI_SBX00_SMBUS && dev->revision >= 0x40) || - dev->vendor == PCI_VENDOR_ID_AMD) + dev->vendor == PCI_VENDOR_ID_AMD) { + if (!request_region(SB800_PIIX4_SMB_IDX, 2, "smba_idx")) { + dev_err(&dev->dev, + "SMBus base address index region 0x%x already in use!\n", + SB800_PIIX4_SMB_IDX); + return -EBUSY; + } + /* base address location etc changed in SB800 */ retval = piix4_setup_sb800(dev, id, 0); - else - retval = piix4_setup(dev, id); + if (retval < 0) { + release_region(SB800_PIIX4_SMB_IDX, 2); + return retval; + } - /* If no main SMBus found, give up */ - if (retval < 0) - return retval; + /* + * Try to register multiplexed main SMBus adapter, + * give up if we can't + */ + retval = piix4_add_adapters_sb800(dev, retval); + if (retval < 0) { + release_region(SB800_PIIX4_SMB_IDX, 2); + return retval; + } + } else { + retval = piix4_setup(dev, id); + if (retval < 0) + return retval; - /* Try to register main SMBus adapter, give up if we can't */ - retval = piix4_add_adapter(dev, retval, &piix4_main_adapter); - if (retval < 0) - return retval; + /* Try to register main SMBus adapter, give up if we can't */ + retval = piix4_add_adapter(dev, retval, "main", + &piix4_main_adapters[0]); + if (retval < 0) + return retval; + } /* Check for auxiliary SMBus on some AMD chipsets */ retval = -ENODEV; @@ -654,7 +783,8 @@ static int piix4_probe(struct pci_dev *dev, const struct pci_device_id *id) if (retval > 0) { /* Try to add the aux adapter if it exists, * piix4_add_adapter will clean up if this fails */ - piix4_add_adapter(dev, retval, &piix4_aux_adapter); + piix4_add_adapter(dev, retval, piix4_aux_port_name_sb800, + &piix4_aux_adapter); } return 0; @@ -666,7 +796,13 @@ static void piix4_adap_remove(struct i2c_adapter *adap) if (adapdata->smba) { i2c_del_adapter(adap); - release_region(adapdata->smba, SMBIOSIZE); + if (adapdata->port == 0) { + release_region(adapdata->smba, SMBIOSIZE); + if (adapdata->sb800_main) { + kfree(adapdata->mutex); + release_region(SB800_PIIX4_SMB_IDX, 2); + } + } kfree(adapdata); kfree(adap); } @@ -674,9 +810,13 @@ static void piix4_adap_remove(struct i2c_adapter *adap) static void piix4_remove(struct pci_dev *dev) { - if (piix4_main_adapter) { - piix4_adap_remove(piix4_main_adapter); - piix4_main_adapter = NULL; + int port = PIIX4_MAX_ADAPTERS; + + while (--port >= 0) { + if (piix4_main_adapters[port]) { + piix4_adap_remove(piix4_main_adapters[port]); + piix4_main_adapters[port] = NULL; + } } if (piix4_aux_adapter) { diff --git a/drivers/i2c/busses/i2c-rcar.c b/drivers/i2c/busses/i2c-rcar.c index 599c0d7bd906..1abeadc8ab79 100644 --- a/drivers/i2c/busses/i2c-rcar.c +++ b/drivers/i2c/busses/i2c-rcar.c @@ -1,7 +1,8 @@ /* * Driver for the Renesas RCar I2C unit * - * Copyright (C) 2014 Wolfram Sang <wsa@sang-engineering.com> + * Copyright (C) 2014-15 Wolfram Sang <wsa@sang-engineering.com> + * Copyright (C) 2011-2015 Renesas Electronics Corporation * * Copyright (C) 2012-14 Renesas Solutions Corp. * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> @@ -9,9 +10,6 @@ * This file is based on the drivers/i2c/busses/i2c-sh7760.c * (c) 2005-2008 MSC Vertriebsges.m.b.H, Manuel Lauss <mlau@msc-ge.com> * - * This file used out-of-tree driver i2c-rcar.c - * Copyright (C) 2011-2012 Renesas Electronics Corporation - * * 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 of the License. @@ -33,7 +31,6 @@ #include <linux/platform_device.h> #include <linux/pm_runtime.h> #include <linux/slab.h> -#include <linux/spinlock.h> /* register offsets */ #define ICSCR 0x00 /* slave ctrl */ @@ -84,6 +81,7 @@ #define RCAR_BUS_PHASE_START (MDBS | MIE | ESG) #define RCAR_BUS_PHASE_DATA (MDBS | MIE) +#define RCAR_BUS_MASK_DATA (~(ESG | FSB) & 0xFF) #define RCAR_BUS_PHASE_STOP (MDBS | MIE | FSB) #define RCAR_IRQ_SEND (MNR | MAL | MST | MAT | MDE) @@ -94,10 +92,13 @@ #define RCAR_IRQ_ACK_RECV (~(MAT | MDR) & 0xFF) #define ID_LAST_MSG (1 << 0) -#define ID_IOERROR (1 << 1) +#define ID_FIRST_MSG (1 << 1) #define ID_DONE (1 << 2) #define ID_ARBLOST (1 << 3) #define ID_NACK (1 << 4) +/* persistent flags */ +#define ID_P_PM_BLOCKED (1 << 31) +#define ID_P_MASK ID_P_PM_BLOCKED enum rcar_i2c_type { I2C_RCAR_GEN1, @@ -108,10 +109,10 @@ enum rcar_i2c_type { struct rcar_i2c_priv { void __iomem *io; struct i2c_adapter adap; - struct i2c_msg *msg; + struct i2c_msg *msg; + int msgs_left; struct clk *clk; - spinlock_t lock; wait_queue_head_t wait; int pos; @@ -124,9 +125,6 @@ struct rcar_i2c_priv { #define rcar_i2c_priv_to_dev(p) ((p)->adap.dev.parent) #define rcar_i2c_is_recv(p) ((p)->msg->flags & I2C_M_RD) -#define rcar_i2c_flags_set(p, f) ((p)->flags |= (f)) -#define rcar_i2c_flags_has(p, f) ((p)->flags & (f)) - #define LOOP_TIMEOUT 1024 @@ -144,9 +142,10 @@ static void rcar_i2c_init(struct rcar_i2c_priv *priv) { /* reset master mode */ rcar_i2c_write(priv, ICMIER, 0); - rcar_i2c_write(priv, ICMCR, 0); + rcar_i2c_write(priv, ICMCR, MDBS); rcar_i2c_write(priv, ICMSR, 0); - rcar_i2c_write(priv, ICMAR, 0); + /* start clock */ + rcar_i2c_write(priv, ICCCR, priv->icccr); } static int rcar_i2c_bus_barrier(struct rcar_i2c_priv *priv) @@ -163,15 +162,17 @@ static int rcar_i2c_bus_barrier(struct rcar_i2c_priv *priv) return -EBUSY; } -static int rcar_i2c_clock_calculate(struct rcar_i2c_priv *priv, - u32 bus_speed, - struct device *dev) +static int rcar_i2c_clock_calculate(struct rcar_i2c_priv *priv, struct i2c_timings *t) { - u32 scgd, cdf; - u32 round, ick; - u32 scl; - u32 cdf_width; + u32 scgd, cdf, round, ick, sum, scl, cdf_width; unsigned long rate; + struct device *dev = rcar_i2c_priv_to_dev(priv); + + /* Fall back to previously used values if not supplied */ + t->bus_freq_hz = t->bus_freq_hz ?: 100000; + t->scl_fall_ns = t->scl_fall_ns ?: 35; + t->scl_rise_ns = t->scl_rise_ns ?: 200; + t->scl_int_delay_ns = t->scl_int_delay_ns ?: 50; switch (priv->devtype) { case I2C_RCAR_GEN1: @@ -195,9 +196,9 @@ static int rcar_i2c_clock_calculate(struct rcar_i2c_priv *priv, * SCL = ick / (20 + SCGD * 8 + F[(ticf + tr + intd) * ick]) * * ick : I2C internal clock < 20 MHz - * ticf : I2C SCL falling time = 35 ns here - * tr : I2C SCL rising time = 200 ns here - * intd : LSI internal delay = 50 ns here + * ticf : I2C SCL falling time + * tr : I2C SCL rising time + * intd : LSI internal delay * clkp : peripheral_clk * F[] : integer up-valuation */ @@ -213,12 +214,12 @@ static int rcar_i2c_clock_calculate(struct rcar_i2c_priv *priv, * it is impossible to calculate large scale * number on u32. separate it * - * F[(ticf + tr + intd) * ick] - * = F[(35 + 200 + 50)ns * ick] - * = F[285 * ick / 1000000000] - * = F[(ick / 1000000) * 285 / 1000] + * F[(ticf + tr + intd) * ick] with sum = (ticf + tr + intd) + * = F[sum * ick / 1000000000] + * = F[(ick / 1000000) * sum / 1000] */ - round = (ick + 500000) / 1000000 * 285; + sum = t->scl_fall_ns + t->scl_rise_ns + t->scl_int_delay_ns; + round = (ick + 500000) / 1000000 * sum; round = (round + 500) / 1000; /* @@ -235,7 +236,7 @@ static int rcar_i2c_clock_calculate(struct rcar_i2c_priv *priv, */ for (scgd = 0; scgd < 0x40; scgd++) { scl = ick / (20 + (scgd * 8) + round); - if (scl <= bus_speed) + if (scl <= t->bus_freq_hz) goto scgd_find; } dev_err(dev, "it is impossible to calculate best SCL\n"); @@ -243,11 +244,9 @@ static int rcar_i2c_clock_calculate(struct rcar_i2c_priv *priv, scgd_find: dev_dbg(dev, "clk %d/%d(%lu), round %u, CDF:0x%x, SCGD: 0x%x\n", - scl, bus_speed, clk_get_rate(priv->clk), round, cdf, scgd); + scl, t->bus_freq_hz, clk_get_rate(priv->clk), round, cdf, scgd); - /* - * keep icccr value - */ + /* keep icccr value */ priv->icccr = scgd << cdf_width | cdf; return 0; @@ -257,33 +256,44 @@ static void rcar_i2c_prepare_msg(struct rcar_i2c_priv *priv) { int read = !!rcar_i2c_is_recv(priv); + priv->pos = 0; + if (priv->msgs_left == 1) + priv->flags |= ID_LAST_MSG; + rcar_i2c_write(priv, ICMAR, (priv->msg->addr << 1) | read); - rcar_i2c_write(priv, ICMSR, 0); - rcar_i2c_write(priv, ICMCR, RCAR_BUS_PHASE_START); + /* + * We don't have a testcase but the HW engineers say that the write order + * of ICMSR and ICMCR depends on whether we issue START or REP_START. Since + * it didn't cause a drawback for me, let's rather be safe than sorry. + */ + if (priv->flags & ID_FIRST_MSG) { + rcar_i2c_write(priv, ICMSR, 0); + rcar_i2c_write(priv, ICMCR, RCAR_BUS_PHASE_START); + } else { + rcar_i2c_write(priv, ICMCR, RCAR_BUS_PHASE_START); + rcar_i2c_write(priv, ICMSR, 0); + } rcar_i2c_write(priv, ICMIER, read ? RCAR_IRQ_RECV : RCAR_IRQ_SEND); } +static void rcar_i2c_next_msg(struct rcar_i2c_priv *priv) +{ + priv->msg++; + priv->msgs_left--; + priv->flags &= ID_P_MASK; + rcar_i2c_prepare_msg(priv); +} + /* * interrupt functions */ -static int rcar_i2c_irq_send(struct rcar_i2c_priv *priv, u32 msr) +static void rcar_i2c_irq_send(struct rcar_i2c_priv *priv, u32 msr) { struct i2c_msg *msg = priv->msg; - /* - * FIXME - * sometimes, unknown interrupt happened. - * Do nothing - */ + /* FIXME: sometimes, unknown interrupt happened. Do nothing */ if (!(msr & MDE)) - return 0; - - /* - * If address transfer phase finished, - * goto data phase. - */ - if (msr & MAT) - rcar_i2c_write(priv, ICMCR, RCAR_BUS_PHASE_DATA); + return; if (priv->pos < msg->len) { /* @@ -305,67 +315,50 @@ static int rcar_i2c_irq_send(struct rcar_i2c_priv *priv, u32 msr) * [ICRXTX] -> [SHIFT] -> [I2C bus] */ - if (priv->flags & ID_LAST_MSG) + if (priv->flags & ID_LAST_MSG) { /* * If current msg is the _LAST_ msg, * prepare stop condition here. * ID_DONE will be set on STOP irq. */ rcar_i2c_write(priv, ICMCR, RCAR_BUS_PHASE_STOP); - else - /* - * If current msg is _NOT_ last msg, - * it doesn't call stop phase. - * thus, there is no STOP irq. - * return ID_DONE here. - */ - return ID_DONE; + } else { + rcar_i2c_next_msg(priv); + return; + } } rcar_i2c_write(priv, ICMSR, RCAR_IRQ_ACK_SEND); - - return 0; } -static int rcar_i2c_irq_recv(struct rcar_i2c_priv *priv, u32 msr) +static void rcar_i2c_irq_recv(struct rcar_i2c_priv *priv, u32 msr) { struct i2c_msg *msg = priv->msg; - /* - * FIXME - * sometimes, unknown interrupt happened. - * Do nothing - */ + /* FIXME: sometimes, unknown interrupt happened. Do nothing */ if (!(msr & MDR)) - return 0; + return; if (msr & MAT) { - /* - * Address transfer phase finished, - * but, there is no data at this point. - * Do nothing. - */ + /* Address transfer phase finished, but no data at this point. */ } else if (priv->pos < msg->len) { - /* - * get received data - */ + /* get received data */ msg->buf[priv->pos] = rcar_i2c_read(priv, ICRXTX); priv->pos++; } /* - * If next received data is the _LAST_, - * go to STOP phase, - * otherwise, go to DATA phase. + * If next received data is the _LAST_, go to STOP phase. Might be + * overwritten by REP START when setting up a new msg. Not elegant + * but the only stable sequence for REP START I have found so far. */ if (priv->pos + 1 >= msg->len) rcar_i2c_write(priv, ICMCR, RCAR_BUS_PHASE_STOP); - else - rcar_i2c_write(priv, ICMCR, RCAR_BUS_PHASE_DATA); - - rcar_i2c_write(priv, ICMSR, RCAR_IRQ_ACK_RECV); - return 0; + if (priv->pos == msg->len && !(priv->flags & ID_LAST_MSG)) + rcar_i2c_next_msg(priv); + else + rcar_i2c_write(priv, ICMSR, RCAR_IRQ_ACK_RECV); } static bool rcar_i2c_slave_irq(struct rcar_i2c_priv *priv) @@ -426,62 +419,57 @@ static bool rcar_i2c_slave_irq(struct rcar_i2c_priv *priv) static irqreturn_t rcar_i2c_irq(int irq, void *ptr) { struct rcar_i2c_priv *priv = ptr; - irqreturn_t result = IRQ_HANDLED; - u32 msr; - - /*-------------- spin lock -----------------*/ - spin_lock(&priv->lock); + u32 msr, val; - if (rcar_i2c_slave_irq(priv)) - goto exit; + /* Clear START or STOP as soon as we can */ + val = rcar_i2c_read(priv, ICMCR); + rcar_i2c_write(priv, ICMCR, val & RCAR_BUS_MASK_DATA); msr = rcar_i2c_read(priv, ICMSR); /* Only handle interrupts that are currently enabled */ msr &= rcar_i2c_read(priv, ICMIER); if (!msr) { - result = IRQ_NONE; - goto exit; + if (rcar_i2c_slave_irq(priv)) + return IRQ_HANDLED; + + return IRQ_NONE; } /* Arbitration lost */ if (msr & MAL) { - rcar_i2c_flags_set(priv, (ID_DONE | ID_ARBLOST)); + priv->flags |= ID_DONE | ID_ARBLOST; goto out; } /* Nack */ if (msr & MNR) { - /* go to stop phase */ - rcar_i2c_write(priv, ICMCR, RCAR_BUS_PHASE_STOP); + /* HW automatically sends STOP after received NACK */ rcar_i2c_write(priv, ICMIER, RCAR_IRQ_STOP); - rcar_i2c_flags_set(priv, ID_NACK); + priv->flags |= ID_NACK; goto out; } /* Stop */ if (msr & MST) { - rcar_i2c_flags_set(priv, ID_DONE); + priv->msgs_left--; /* The last message also made it */ + priv->flags |= ID_DONE; goto out; } if (rcar_i2c_is_recv(priv)) - rcar_i2c_flags_set(priv, rcar_i2c_irq_recv(priv, msr)); + rcar_i2c_irq_recv(priv, msr); else - rcar_i2c_flags_set(priv, rcar_i2c_irq_send(priv, msr)); + rcar_i2c_irq_send(priv, msr); out: - if (rcar_i2c_flags_has(priv, ID_DONE)) { + if (priv->flags & ID_DONE) { rcar_i2c_write(priv, ICMIER, 0); rcar_i2c_write(priv, ICMSR, 0); wake_up(&priv->wait); } -exit: - spin_unlock(&priv->lock); - /*-------------- spin unlock -----------------*/ - - return result; + return IRQ_HANDLED; } static int rcar_i2c_master_xfer(struct i2c_adapter *adap, @@ -490,22 +478,11 @@ static int rcar_i2c_master_xfer(struct i2c_adapter *adap, { struct rcar_i2c_priv *priv = i2c_get_adapdata(adap); struct device *dev = rcar_i2c_priv_to_dev(priv); - unsigned long flags; int i, ret; - long timeout; + long time_left; pm_runtime_get_sync(dev); - /*-------------- spin lock -----------------*/ - spin_lock_irqsave(&priv->lock, flags); - - rcar_i2c_init(priv); - /* start clock */ - rcar_i2c_write(priv, ICCCR, priv->icccr); - - spin_unlock_irqrestore(&priv->lock, flags); - /*-------------- spin unlock -----------------*/ - ret = rcar_i2c_bus_barrier(priv); if (ret < 0) goto out; @@ -514,48 +491,27 @@ static int rcar_i2c_master_xfer(struct i2c_adapter *adap, /* This HW can't send STOP after address phase */ if (msgs[i].len == 0) { ret = -EOPNOTSUPP; - break; - } - - /*-------------- spin lock -----------------*/ - spin_lock_irqsave(&priv->lock, flags); - - /* init each data */ - priv->msg = &msgs[i]; - priv->pos = 0; - priv->flags = 0; - if (i == num - 1) - rcar_i2c_flags_set(priv, ID_LAST_MSG); - - rcar_i2c_prepare_msg(priv); - - spin_unlock_irqrestore(&priv->lock, flags); - /*-------------- spin unlock -----------------*/ - - timeout = wait_event_timeout(priv->wait, - rcar_i2c_flags_has(priv, ID_DONE), - adap->timeout); - if (!timeout) { - ret = -ETIMEDOUT; - break; - } - - if (rcar_i2c_flags_has(priv, ID_NACK)) { - ret = -ENXIO; - break; - } - - if (rcar_i2c_flags_has(priv, ID_ARBLOST)) { - ret = -EAGAIN; - break; - } - - if (rcar_i2c_flags_has(priv, ID_IOERROR)) { - ret = -EIO; - break; + goto out; } + } - ret = i + 1; /* The number of transfer */ + /* init first message */ + priv->msg = msgs; + priv->msgs_left = num; + priv->flags = (priv->flags & ID_P_MASK) | ID_FIRST_MSG; + rcar_i2c_prepare_msg(priv); + + time_left = wait_event_timeout(priv->wait, priv->flags & ID_DONE, + num * adap->timeout); + if (!time_left) { + rcar_i2c_init(priv); + ret = -ETIMEDOUT; + } else if (priv->flags & ID_NACK) { + ret = -ENXIO; + } else if (priv->flags & ID_ARBLOST) { + ret = -EAGAIN; + } else { + ret = num - priv->msgs_left; /* The number of transfer */ } out: pm_runtime_put(dev); @@ -637,7 +593,7 @@ static int rcar_i2c_probe(struct platform_device *pdev) struct i2c_adapter *adap; struct resource *res; struct device *dev = &pdev->dev; - u32 bus_speed; + struct i2c_timings i2c_t; int irq, ret; priv = devm_kzalloc(dev, sizeof(struct rcar_i2c_priv), GFP_KERNEL); @@ -650,23 +606,13 @@ static int rcar_i2c_probe(struct platform_device *pdev) return PTR_ERR(priv->clk); } - bus_speed = 100000; /* default 100 kHz */ - of_property_read_u32(dev->of_node, "clock-frequency", &bus_speed); - - priv->devtype = (enum rcar_i2c_type)of_match_device(rcar_i2c_dt_ids, dev)->data; - - ret = rcar_i2c_clock_calculate(priv, bus_speed, dev); - if (ret < 0) - return ret; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); priv->io = devm_ioremap_resource(dev, res); if (IS_ERR(priv->io)) return PTR_ERR(priv->io); - irq = platform_get_irq(pdev, 0); + priv->devtype = (enum rcar_i2c_type)of_match_device(rcar_i2c_dt_ids, dev)->data; init_waitqueue_head(&priv->wait); - spin_lock_init(&priv->lock); adap = &priv->adap; adap->nr = pdev->id; @@ -678,26 +624,47 @@ static int rcar_i2c_probe(struct platform_device *pdev) i2c_set_adapdata(adap, priv); strlcpy(adap->name, pdev->name, sizeof(adap->name)); - ret = devm_request_irq(dev, irq, rcar_i2c_irq, 0, - dev_name(dev), priv); + i2c_parse_fw_timings(dev, &i2c_t, false); + + pm_runtime_enable(dev); + pm_runtime_get_sync(dev); + ret = rcar_i2c_clock_calculate(priv, &i2c_t); + if (ret < 0) + goto out_pm_put; + + rcar_i2c_init(priv); + + /* Don't suspend when multi-master to keep arbitration working */ + if (of_property_read_bool(dev->of_node, "multi-master")) + priv->flags |= ID_P_PM_BLOCKED; + else + pm_runtime_put(dev); + + + irq = platform_get_irq(pdev, 0); + ret = devm_request_irq(dev, irq, rcar_i2c_irq, 0, dev_name(dev), priv); if (ret < 0) { dev_err(dev, "cannot get irq %d\n", irq); - return ret; + goto out_pm_disable; } - pm_runtime_enable(dev); platform_set_drvdata(pdev, priv); ret = i2c_add_numbered_adapter(adap); if (ret < 0) { dev_err(dev, "reg adap failed: %d\n", ret); - pm_runtime_disable(dev); - return ret; + goto out_pm_disable; } dev_info(dev, "probed\n"); return 0; + + out_pm_put: + pm_runtime_put(dev); + out_pm_disable: + pm_runtime_disable(dev); + return ret; } static int rcar_i2c_remove(struct platform_device *pdev) @@ -706,6 +673,8 @@ static int rcar_i2c_remove(struct platform_device *pdev) struct device *dev = &pdev->dev; i2c_del_adapter(&priv->adap); + if (priv->flags & ID_P_PM_BLOCKED) + pm_runtime_put(dev); pm_runtime_disable(dev); return 0; diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c index 5df819610d52..362a6de54833 100644 --- a/drivers/i2c/busses/i2c-s3c2410.c +++ b/drivers/i2c/busses/i2c-s3c2410.c @@ -784,7 +784,6 @@ static int s3c24xx_i2c_xfer(struct i2c_adapter *adap, int retry; int ret; - pm_runtime_get_sync(&adap->dev); ret = clk_enable(i2c->clk); if (ret) return ret; @@ -795,7 +794,6 @@ static int s3c24xx_i2c_xfer(struct i2c_adapter *adap, if (ret != -EAGAIN) { clk_disable(i2c->clk); - pm_runtime_put(&adap->dev); return ret; } @@ -805,7 +803,6 @@ static int s3c24xx_i2c_xfer(struct i2c_adapter *adap, } clk_disable(i2c->clk); - pm_runtime_put(&adap->dev); return -EREMOTEIO; } @@ -1256,8 +1253,6 @@ static int s3c24xx_i2c_probe(struct platform_device *pdev) return ret; } - pm_runtime_enable(&i2c->adap.dev); - dev_info(&pdev->dev, "%s: S3C I2C adapter\n", dev_name(&i2c->adap.dev)); return 0; } @@ -1273,7 +1268,6 @@ static int s3c24xx_i2c_remove(struct platform_device *pdev) clk_unprepare(i2c->clk); - pm_runtime_disable(&i2c->adap.dev); pm_runtime_disable(&pdev->dev); s3c24xx_i2c_deregister_cpufreq(i2c); diff --git a/drivers/i2c/busses/i2c-st.c b/drivers/i2c/busses/i2c-st.c index 25020ec777c9..6ee77159ac57 100644 --- a/drivers/i2c/busses/i2c-st.c +++ b/drivers/i2c/busses/i2c-st.c @@ -708,8 +708,7 @@ static int st_i2c_xfer(struct i2c_adapter *i2c_adap, #ifdef CONFIG_PM_SLEEP static int st_i2c_suspend(struct device *dev) { - struct platform_device *pdev = - container_of(dev, struct platform_device, dev); + struct platform_device *pdev = to_platform_device(dev); struct st_i2c_dev *i2c_dev = platform_get_drvdata(pdev); if (i2c_dev->busy) diff --git a/drivers/i2c/busses/i2c-taos-evm.c b/drivers/i2c/busses/i2c-taos-evm.c index 4c7fc2d47014..210ca82f8aa0 100644 --- a/drivers/i2c/busses/i2c-taos-evm.c +++ b/drivers/i2c/busses/i2c-taos-evm.c @@ -130,7 +130,13 @@ static int taos_smbus_xfer(struct i2c_adapter *adapter, u16 addr, return 0; } else { if (p[0] == 'x') { - data->byte = simple_strtol(p + 1, NULL, 16); + /* + * Voluntarily dropping error code of kstrtou8 since all + * error code that it could return are invalid according + * to Documentation/i2c/fault-codes. + */ + if (kstrtou8(p + 1, 16, &data->byte)) + return -EPROTO; return 0; } } diff --git a/drivers/i2c/busses/i2c-uniphier-f.c b/drivers/i2c/busses/i2c-uniphier-f.c index e8d03bcfe3e0..f3e5ff8522f0 100644 --- a/drivers/i2c/busses/i2c-uniphier-f.c +++ b/drivers/i2c/busses/i2c-uniphier-f.c @@ -466,6 +466,11 @@ static int uniphier_fi2c_clk_init(struct device *dev, if (of_property_read_u32(np, "clock-frequency", &bus_speed)) bus_speed = UNIPHIER_FI2C_DEFAULT_SPEED; + if (!bus_speed) { + dev_err(dev, "clock-freqyency should not be zero\n"); + return -EINVAL; + } + if (bus_speed > UNIPHIER_FI2C_MAX_SPEED) bus_speed = UNIPHIER_FI2C_MAX_SPEED; @@ -481,6 +486,10 @@ static int uniphier_fi2c_clk_init(struct device *dev, return ret; clk_rate = clk_get_rate(priv->clk); + if (!clk_rate) { + dev_err(dev, "input clock rate should not be zero\n"); + return -EINVAL; + } uniphier_fi2c_reset(priv); @@ -531,7 +540,7 @@ static int uniphier_fi2c_probe(struct platform_device *pdev) ret = uniphier_fi2c_clk_init(dev, priv); if (ret) - return ret; + goto err; ret = devm_request_irq(dev, irq, uniphier_fi2c_interrupt, 0, pdev->name, priv); diff --git a/drivers/i2c/busses/i2c-uniphier.c b/drivers/i2c/busses/i2c-uniphier.c index e3c3861c3325..1f4f3f53819c 100644 --- a/drivers/i2c/busses/i2c-uniphier.c +++ b/drivers/i2c/busses/i2c-uniphier.c @@ -327,6 +327,11 @@ static int uniphier_i2c_clk_init(struct device *dev, if (of_property_read_u32(np, "clock-frequency", &bus_speed)) bus_speed = UNIPHIER_I2C_DEFAULT_SPEED; + if (!bus_speed) { + dev_err(dev, "clock-freqyency should not be zero\n"); + return -EINVAL; + } + if (bus_speed > UNIPHIER_I2C_MAX_SPEED) bus_speed = UNIPHIER_I2C_MAX_SPEED; @@ -342,6 +347,10 @@ static int uniphier_i2c_clk_init(struct device *dev, return ret; clk_rate = clk_get_rate(priv->clk); + if (!clk_rate) { + dev_err(dev, "input clock rate should not be zero\n"); + return -EINVAL; + } uniphier_i2c_reset(priv, true); @@ -388,7 +397,7 @@ static int uniphier_i2c_probe(struct platform_device *pdev) ret = uniphier_i2c_clk_init(dev, priv); if (ret) - return ret; + goto err; ret = devm_request_irq(dev, irq, uniphier_i2c_interrupt, 0, pdev->name, priv); diff --git a/drivers/i2c/busses/i2c-xiic.c b/drivers/i2c/busses/i2c-xiic.c index 0b20449e48cf..6efd20095d5d 100644 --- a/drivers/i2c/busses/i2c-xiic.c +++ b/drivers/i2c/busses/i2c-xiic.c @@ -70,7 +70,7 @@ struct xiic_i2c { wait_queue_head_t wait; struct i2c_adapter adap; struct i2c_msg *tx_msg; - spinlock_t lock; + struct mutex lock; unsigned int tx_pos; unsigned int nmsgs; enum xilinx_i2c_state state; @@ -369,7 +369,7 @@ static irqreturn_t xiic_process(int irq, void *dev_id) * To find which interrupts are pending; AND interrupts pending with * interrupts masked. */ - spin_lock(&i2c->lock); + mutex_lock(&i2c->lock); isr = xiic_getreg32(i2c, XIIC_IISR_OFFSET); ier = xiic_getreg32(i2c, XIIC_IIER_OFFSET); pend = isr & ier; @@ -497,7 +497,7 @@ out: dev_dbg(i2c->adap.dev.parent, "%s clr: 0x%x\n", __func__, clr); xiic_setreg32(i2c, XIIC_IISR_OFFSET, clr); - spin_unlock(&i2c->lock); + mutex_unlock(&i2c->lock); return IRQ_HANDLED; } @@ -662,10 +662,10 @@ static void __xiic_start_xfer(struct xiic_i2c *i2c) static void xiic_start_xfer(struct xiic_i2c *i2c) { - spin_lock(&i2c->lock); + mutex_lock(&i2c->lock); xiic_reinit(i2c); __xiic_start_xfer(i2c); - spin_unlock(&i2c->lock); + mutex_unlock(&i2c->lock); } static int xiic_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) @@ -745,7 +745,7 @@ static int xiic_i2c_probe(struct platform_device *pdev) i2c->adap.dev.parent = &pdev->dev; i2c->adap.dev.of_node = pdev->dev.of_node; - spin_lock_init(&i2c->lock); + mutex_init(&i2c->lock); init_waitqueue_head(&i2c->wait); ret = devm_request_threaded_irq(&pdev->dev, irq, xiic_isr, diff --git a/drivers/i2c/busses/i2c-xlr.c b/drivers/i2c/busses/i2c-xlr.c index 8b36bcfd952d..613c3a4f2c51 100644 --- a/drivers/i2c/busses/i2c-xlr.c +++ b/drivers/i2c/busses/i2c-xlr.c @@ -17,6 +17,10 @@ #include <linux/i2c.h> #include <linux/io.h> #include <linux/platform_device.h> +#include <linux/of_device.h> +#include <linux/clk.h> +#include <linux/interrupt.h> +#include <linux/wait.h> /* XLR I2C REGISTERS */ #define XLR_I2C_CFG 0x00 @@ -30,6 +34,10 @@ #define XLR_I2C_BYTECNT 0x08 #define XLR_I2C_HDSTATIM 0x09 +/* Sigma Designs additional registers */ +#define XLR_I2C_INT_EN 0x09 +#define XLR_I2C_INT_STAT 0x0a + /* XLR I2C REGISTERS FLAGS */ #define XLR_I2C_BUS_BUSY 0x01 #define XLR_I2C_SDOEMPTY 0x02 @@ -63,11 +71,98 @@ static inline u32 xlr_i2c_rdreg(u32 __iomem *base, unsigned int reg) return __raw_readl(base + reg); } +#define XLR_I2C_FLAG_IRQ 1 + +struct xlr_i2c_config { + u32 flags; /* optional feature support */ + u32 status_busy; /* value of STATUS[0] when busy */ + u32 cfg_extra; /* extra CFG bits to set */ +}; + struct xlr_i2c_private { struct i2c_adapter adap; u32 __iomem *iobase; + int irq; + int pos; + struct i2c_msg *msg; + const struct xlr_i2c_config *cfg; + wait_queue_head_t wait; + struct clk *clk; }; +static int xlr_i2c_busy(struct xlr_i2c_private *priv, u32 status) +{ + return (status & XLR_I2C_BUS_BUSY) == priv->cfg->status_busy; +} + +static int xlr_i2c_idle(struct xlr_i2c_private *priv) +{ + return !xlr_i2c_busy(priv, xlr_i2c_rdreg(priv->iobase, XLR_I2C_STATUS)); +} + +static int xlr_i2c_wait(struct xlr_i2c_private *priv, unsigned long timeout) +{ + int status; + int t; + + t = wait_event_timeout(priv->wait, xlr_i2c_idle(priv), + msecs_to_jiffies(timeout)); + if (!t) + return -ETIMEDOUT; + + status = xlr_i2c_rdreg(priv->iobase, XLR_I2C_STATUS); + + return status & XLR_I2C_ACK_ERR ? -EIO : 0; +} + +static void xlr_i2c_tx_irq(struct xlr_i2c_private *priv, u32 status) +{ + struct i2c_msg *msg = priv->msg; + + if (status & XLR_I2C_SDOEMPTY) + xlr_i2c_wreg(priv->iobase, XLR_I2C_DATAOUT, + msg->buf[priv->pos++]); +} + +static void xlr_i2c_rx_irq(struct xlr_i2c_private *priv, u32 status) +{ + struct i2c_msg *msg = priv->msg; + + if (status & XLR_I2C_RXRDY) + msg->buf[priv->pos++] = + xlr_i2c_rdreg(priv->iobase, XLR_I2C_DATAIN); +} + +static irqreturn_t xlr_i2c_irq(int irq, void *dev_id) +{ + struct xlr_i2c_private *priv = dev_id; + struct i2c_msg *msg = priv->msg; + u32 int_stat, status; + + int_stat = xlr_i2c_rdreg(priv->iobase, XLR_I2C_INT_STAT); + if (!int_stat) + return IRQ_NONE; + + xlr_i2c_wreg(priv->iobase, XLR_I2C_INT_STAT, int_stat); + + if (!msg) + return IRQ_HANDLED; + + status = xlr_i2c_rdreg(priv->iobase, XLR_I2C_STATUS); + + if (priv->pos < msg->len) { + if (msg->flags & I2C_M_RD) + xlr_i2c_rx_irq(priv, status); + else + xlr_i2c_tx_irq(priv, status); + } + + if (!xlr_i2c_busy(priv, status)) + wake_up(&priv->wait); + + return IRQ_HANDLED; +} + static int xlr_i2c_tx(struct xlr_i2c_private *priv, u16 len, u8 *buf, u16 addr) { @@ -75,37 +170,48 @@ static int xlr_i2c_tx(struct xlr_i2c_private *priv, u16 len, unsigned long timeout, stoptime, checktime; u32 i2c_status; int pos, timedout; - u8 offset, byte; + u8 offset; + u32 xfer; + + if (!len) + return -EOPNOTSUPP; offset = buf[0]; xlr_i2c_wreg(priv->iobase, XLR_I2C_ADDR, offset); xlr_i2c_wreg(priv->iobase, XLR_I2C_DEVADDR, addr); - xlr_i2c_wreg(priv->iobase, XLR_I2C_CFG, XLR_I2C_CFG_ADDR); - xlr_i2c_wreg(priv->iobase, XLR_I2C_BYTECNT, len - 1); + xlr_i2c_wreg(priv->iobase, XLR_I2C_CFG, + XLR_I2C_CFG_ADDR | priv->cfg->cfg_extra); timeout = msecs_to_jiffies(XLR_I2C_TIMEOUT); stoptime = jiffies + timeout; timedout = 0; - pos = 1; -retry: + if (len == 1) { - xlr_i2c_wreg(priv->iobase, XLR_I2C_STARTXFR, - XLR_I2C_STARTXFR_ND); + xlr_i2c_wreg(priv->iobase, XLR_I2C_BYTECNT, len - 1); + xfer = XLR_I2C_STARTXFR_ND; + pos = 1; } else { - xlr_i2c_wreg(priv->iobase, XLR_I2C_DATAOUT, buf[pos]); - xlr_i2c_wreg(priv->iobase, XLR_I2C_STARTXFR, - XLR_I2C_STARTXFR_WR); + xlr_i2c_wreg(priv->iobase, XLR_I2C_BYTECNT, len - 2); + xlr_i2c_wreg(priv->iobase, XLR_I2C_DATAOUT, buf[1]); + xfer = XLR_I2C_STARTXFR_WR; + pos = 2; } + priv->pos = pos; + +retry: + /* retry can only happen on the first byte */ + xlr_i2c_wreg(priv->iobase, XLR_I2C_STARTXFR, xfer); + + if (priv->irq > 0) + return xlr_i2c_wait(priv, XLR_I2C_TIMEOUT * len); + while (!timedout) { checktime = jiffies; i2c_status = xlr_i2c_rdreg(priv->iobase, XLR_I2C_STATUS); - if (i2c_status & XLR_I2C_SDOEMPTY) { - pos++; - /* need to do a empty dataout after the last byte */ - byte = (pos < len) ? buf[pos] : 0; - xlr_i2c_wreg(priv->iobase, XLR_I2C_DATAOUT, byte); + if ((i2c_status & XLR_I2C_SDOEMPTY) && pos < len) { + xlr_i2c_wreg(priv->iobase, XLR_I2C_DATAOUT, buf[pos++]); /* reset timeout on successful xmit */ stoptime = jiffies + timeout; @@ -121,7 +227,7 @@ retry: if (i2c_status & XLR_I2C_ACK_ERR) return -EIO; - if ((i2c_status & XLR_I2C_BUS_BUSY) == 0 && pos >= len) + if (!xlr_i2c_busy(priv, i2c_status) && pos >= len) return 0; } dev_err(&adap->dev, "I2C transmit timeout\n"); @@ -134,12 +240,17 @@ static int xlr_i2c_rx(struct xlr_i2c_private *priv, u16 len, u8 *buf, u16 addr) u32 i2c_status; unsigned long timeout, stoptime, checktime; int nbytes, timedout; - u8 byte; - xlr_i2c_wreg(priv->iobase, XLR_I2C_CFG, XLR_I2C_CFG_NOADDR); - xlr_i2c_wreg(priv->iobase, XLR_I2C_BYTECNT, len); + if (!len) + return -EOPNOTSUPP; + + xlr_i2c_wreg(priv->iobase, XLR_I2C_CFG, + XLR_I2C_CFG_NOADDR | priv->cfg->cfg_extra); + xlr_i2c_wreg(priv->iobase, XLR_I2C_BYTECNT, len - 1); xlr_i2c_wreg(priv->iobase, XLR_I2C_DEVADDR, addr); + priv->pos = 0; + timeout = msecs_to_jiffies(XLR_I2C_TIMEOUT); stoptime = jiffies + timeout; timedout = 0; @@ -147,18 +258,18 @@ static int xlr_i2c_rx(struct xlr_i2c_private *priv, u16 len, u8 *buf, u16 addr) retry: xlr_i2c_wreg(priv->iobase, XLR_I2C_STARTXFR, XLR_I2C_STARTXFR_RD); + if (priv->irq > 0) + return xlr_i2c_wait(priv, XLR_I2C_TIMEOUT * len); + while (!timedout) { checktime = jiffies; i2c_status = xlr_i2c_rdreg(priv->iobase, XLR_I2C_STATUS); if (i2c_status & XLR_I2C_RXRDY) { - if (nbytes > len) + if (nbytes >= len) return -EIO; /* should not happen */ - /* we need to do a dummy datain when nbytes == len */ - byte = xlr_i2c_rdreg(priv->iobase, XLR_I2C_DATAIN); - if (nbytes < len) - buf[nbytes] = byte; - nbytes++; + buf[nbytes++] = + xlr_i2c_rdreg(priv->iobase, XLR_I2C_DATAIN); /* reset timeout on successful read */ stoptime = jiffies + timeout; @@ -174,7 +285,7 @@ retry: if (i2c_status & XLR_I2C_ACK_ERR) return -EIO; - if ((i2c_status & XLR_I2C_BUS_BUSY) == 0) + if (!xlr_i2c_busy(priv, i2c_status)) return 0; } @@ -190,8 +301,17 @@ static int xlr_i2c_xfer(struct i2c_adapter *adap, int ret = 0; struct xlr_i2c_private *priv = i2c_get_adapdata(adap); + ret = clk_enable(priv->clk); + if (ret) + return ret; + + if (priv->irq) + xlr_i2c_wreg(priv->iobase, XLR_I2C_INT_EN, 0xf); + + for (i = 0; ret == 0 && i < num; i++) { msg = &msgs[i]; + priv->msg = msg; if (msg->flags & I2C_M_RD) ret = xlr_i2c_rx(priv, msg->len, &msg->buf[0], msg->addr); @@ -200,13 +320,19 @@ static int xlr_i2c_xfer(struct i2c_adapter *adap, msg->addr); } + if (priv->irq) + xlr_i2c_wreg(priv->iobase, XLR_I2C_INT_EN, 0); + + clk_disable(priv->clk); + priv->msg = NULL; + return (ret != 0) ? ret : num; } static u32 xlr_func(struct i2c_adapter *adap) { /* Emulate SMBUS over I2C */ - return I2C_FUNC_SMBUS_EMUL | I2C_FUNC_I2C; + return (I2C_FUNC_SMBUS_EMUL & ~I2C_FUNC_SMBUS_QUICK) | I2C_FUNC_I2C; } static struct i2c_algorithm xlr_i2c_algo = { @@ -214,22 +340,89 @@ static struct i2c_algorithm xlr_i2c_algo = { .functionality = xlr_func, }; +static const struct xlr_i2c_config xlr_i2c_config_default = { + .status_busy = XLR_I2C_BUS_BUSY, + .cfg_extra = 0, +}; + +static const struct xlr_i2c_config xlr_i2c_config_tangox = { + .flags = XLR_I2C_FLAG_IRQ, + .status_busy = 0, + .cfg_extra = 1 << 8, +}; + +static const struct of_device_id xlr_i2c_dt_ids[] = { + { + .compatible = "sigma,smp8642-i2c", + .data = &xlr_i2c_config_tangox, + }, + { } +}; + static int xlr_i2c_probe(struct platform_device *pdev) { + const struct of_device_id *match; struct xlr_i2c_private *priv; struct resource *res; + struct clk *clk; + unsigned long clk_rate; + unsigned long clk_div; + u32 busfreq; + int irq; int ret; priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; + match = of_match_device(xlr_i2c_dt_ids, &pdev->dev); + if (match) + priv->cfg = match->data; + else + priv->cfg = &xlr_i2c_config_default; + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); priv->iobase = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(priv->iobase)) return PTR_ERR(priv->iobase); + irq = platform_get_irq(pdev, 0); + + if (irq > 0 && (priv->cfg->flags & XLR_I2C_FLAG_IRQ)) { + priv->irq = irq; + + xlr_i2c_wreg(priv->iobase, XLR_I2C_INT_EN, 0); + xlr_i2c_wreg(priv->iobase, XLR_I2C_INT_STAT, 0xf); + + ret = devm_request_irq(&pdev->dev, priv->irq, xlr_i2c_irq, + IRQF_SHARED, dev_name(&pdev->dev), + priv); + if (ret) + return ret; + + init_waitqueue_head(&priv->wait); + } + + if (of_property_read_u32(pdev->dev.of_node, "clock-frequency", + &busfreq)) + busfreq = 100000; + + clk = devm_clk_get(&pdev->dev, NULL); + if (!IS_ERR(clk)) { + ret = clk_prepare_enable(clk); + if (ret) + return ret; + + clk_rate = clk_get_rate(clk); + clk_div = DIV_ROUND_UP(clk_rate, 2 * busfreq); + xlr_i2c_wreg(priv->iobase, XLR_I2C_CLKDIV, clk_div); + + clk_disable(clk); + priv->clk = clk; + } + priv->adap.dev.parent = &pdev->dev; + priv->adap.dev.of_node = pdev->dev.of_node; priv->adap.owner = THIS_MODULE; priv->adap.algo_data = priv; priv->adap.algo = &xlr_i2c_algo; @@ -255,6 +448,8 @@ static int xlr_i2c_remove(struct platform_device *pdev) priv = platform_get_drvdata(pdev); i2c_del_adapter(&priv->adap); + clk_unprepare(priv->clk); + return 0; } @@ -263,6 +458,7 @@ static struct platform_driver xlr_i2c_driver = { .remove = xlr_i2c_remove, .driver = { .name = "xlr-i2cbus", + .of_match_table = xlr_i2c_dt_ids, }, }; diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c index ba8eb087f224..ffe715d346d8 100644 --- a/drivers/i2c/i2c-core.c +++ b/drivers/i2c/i2c-core.c @@ -53,6 +53,7 @@ #include <linux/jump_label.h> #include <asm/uaccess.h> #include <linux/err.h> +#include <linux/property.h> #include "i2c-core.h" @@ -1563,6 +1564,7 @@ static int i2c_register_adapter(struct i2c_adapter *adap) dev_dbg(&adap->dev, "adapter [%s] registered\n", adap->name); pm_runtime_no_callbacks(&adap->dev); + pm_runtime_enable(&adap->dev); #ifdef CONFIG_I2C_COMPAT res = class_compat_create_link(i2c_adapter_compat_class, &adap->dev, @@ -1817,6 +1819,8 @@ void i2c_del_adapter(struct i2c_adapter *adap) /* device name is gone after device_unregister */ dev_dbg(&adap->dev, "adapter [%s] unregistered\n", adap->name); + pm_runtime_disable(&adap->dev); + /* wait until all references to the device are gone * * FIXME: This is old code and should ideally be replaced by an @@ -1839,6 +1843,58 @@ void i2c_del_adapter(struct i2c_adapter *adap) } EXPORT_SYMBOL(i2c_del_adapter); +/** + * i2c_parse_fw_timings - get I2C related timing parameters from firmware + * @dev: The device to scan for I2C timing properties + * @t: the i2c_timings struct to be filled with values + * @use_defaults: bool to use sane defaults derived from the I2C specification + * when properties are not found, otherwise use 0 + * + * Scan the device for the generic I2C properties describing timing parameters + * for the signal and fill the given struct with the results. If a property was + * not found and use_defaults was true, then maximum timings are assumed which + * are derived from the I2C specification. If use_defaults is not used, the + * results will be 0, so drivers can apply their own defaults later. The latter + * is mainly intended for avoiding regressions of existing drivers which want + * to switch to this function. New drivers almost always should use the defaults. + */ + +void i2c_parse_fw_timings(struct device *dev, struct i2c_timings *t, bool use_defaults) +{ + int ret; + + memset(t, 0, sizeof(*t)); + + ret = device_property_read_u32(dev, "clock-frequency", &t->bus_freq_hz); + if (ret && use_defaults) + t->bus_freq_hz = 100000; + + ret = device_property_read_u32(dev, "i2c-scl-rising-time-ns", &t->scl_rise_ns); + if (ret && use_defaults) { + if (t->bus_freq_hz <= 100000) + t->scl_rise_ns = 1000; + else if (t->bus_freq_hz <= 400000) + t->scl_rise_ns = 300; + else + t->scl_rise_ns = 120; + } + + ret = device_property_read_u32(dev, "i2c-scl-falling-time-ns", &t->scl_fall_ns); + if (ret && use_defaults) { + if (t->bus_freq_hz <= 400000) + t->scl_fall_ns = 300; + else + t->scl_fall_ns = 120; + } + + device_property_read_u32(dev, "i2c-scl-internal-delay-ns", &t->scl_int_delay_ns); + + ret = device_property_read_u32(dev, "i2c-sda-falling-time-ns", &t->sda_fall_ns); + if (ret && use_defaults) + t->sda_fall_ns = t->scl_fall_ns; +} +EXPORT_SYMBOL_GPL(i2c_parse_fw_timings); + /* ------------------------------------------------------------------------- */ int i2c_for_each_dev(void *data, int (*fn)(struct device *, void *)) diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index c9cffced00ca..326d07d823a5 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -449,7 +449,7 @@ static void act_open_req_arp_failure(void *handle, struct sk_buff *skb) { struct c4iw_ep *ep = handle; - printk(KERN_ERR MOD "ARP failure duing connect\n"); + printk(KERN_ERR MOD "ARP failure during connect\n"); kfree_skb(skb); connect_reply_upcall(ep, -EHOSTUNREACH); state_set(&ep->com, DEAD); diff --git a/drivers/lguest/core.c b/drivers/lguest/core.c index 312ffd3d0017..9e385b38debf 100644 --- a/drivers/lguest/core.c +++ b/drivers/lguest/core.c @@ -22,7 +22,8 @@ unsigned long switcher_addr; struct page **lg_switcher_pages; -static struct vm_struct *switcher_vma; +static struct vm_struct *switcher_text_vma; +static struct vm_struct *switcher_stacks_vma; /* This One Big lock protects all inter-guest data structures. */ DEFINE_MUTEX(lguest_lock); @@ -83,54 +84,80 @@ static __init int map_switcher(void) } /* + * Copy in the compiled-in Switcher code (from x86/switcher_32.S). + * It goes in the first page, which we map in momentarily. + */ + memcpy(kmap(lg_switcher_pages[0]), start_switcher_text, + end_switcher_text - start_switcher_text); + kunmap(lg_switcher_pages[0]); + + /* * We place the Switcher underneath the fixmap area, which is the * highest virtual address we can get. This is important, since we * tell the Guest it can't access this memory, so we want its ceiling * as high as possible. */ - switcher_addr = FIXADDR_START - (TOTAL_SWITCHER_PAGES+1)*PAGE_SIZE; + switcher_addr = FIXADDR_START - TOTAL_SWITCHER_PAGES*PAGE_SIZE; /* - * Now we reserve the "virtual memory area" we want. We might - * not get it in theory, but in practice it's worked so far. - * The end address needs +1 because __get_vm_area allocates an - * extra guard page, so we need space for that. + * Now we reserve the "virtual memory area"s we want. We might + * not get them in theory, but in practice it's worked so far. + * + * We want the switcher text to be read-only and executable, and + * the stacks to be read-write and non-executable. */ - switcher_vma = __get_vm_area(TOTAL_SWITCHER_PAGES * PAGE_SIZE, - VM_ALLOC, switcher_addr, switcher_addr - + (TOTAL_SWITCHER_PAGES+1) * PAGE_SIZE); - if (!switcher_vma) { + switcher_text_vma = __get_vm_area(PAGE_SIZE, VM_ALLOC|VM_NO_GUARD, + switcher_addr, + switcher_addr + PAGE_SIZE); + + if (!switcher_text_vma) { err = -ENOMEM; printk("lguest: could not map switcher pages high\n"); goto free_pages; } + switcher_stacks_vma = __get_vm_area(SWITCHER_STACK_PAGES * PAGE_SIZE, + VM_ALLOC|VM_NO_GUARD, + switcher_addr + PAGE_SIZE, + switcher_addr + TOTAL_SWITCHER_PAGES * PAGE_SIZE); + if (!switcher_stacks_vma) { + err = -ENOMEM; + printk("lguest: could not map switcher pages high\n"); + goto free_text_vma; + } + /* * This code actually sets up the pages we've allocated to appear at * switcher_addr. map_vm_area() takes the vma we allocated above, the - * kind of pages we're mapping (kernel pages), and a pointer to our - * array of struct pages. + * kind of pages we're mapping (kernel text pages and kernel writable + * pages respectively), and a pointer to our array of struct pages. */ - err = map_vm_area(switcher_vma, PAGE_KERNEL_EXEC, lg_switcher_pages); + err = map_vm_area(switcher_text_vma, PAGE_KERNEL_RX, lg_switcher_pages); + if (err) { + printk("lguest: text map_vm_area failed: %i\n", err); + goto free_vmas; + } + + err = map_vm_area(switcher_stacks_vma, PAGE_KERNEL, + lg_switcher_pages + SWITCHER_TEXT_PAGES); if (err) { - printk("lguest: map_vm_area failed: %i\n", err); - goto free_vma; + printk("lguest: stacks map_vm_area failed: %i\n", err); + goto free_vmas; } /* * Now the Switcher is mapped at the right address, we can't fail! - * Copy in the compiled-in Switcher code (from x86/switcher_32.S). */ - memcpy(switcher_vma->addr, start_switcher_text, - end_switcher_text - start_switcher_text); - printk(KERN_INFO "lguest: mapped switcher at %p\n", - switcher_vma->addr); + switcher_text_vma->addr); /* And we succeeded... */ return 0; -free_vma: - vunmap(switcher_vma->addr); +free_vmas: + /* Undoes map_vm_area and __get_vm_area */ + vunmap(switcher_stacks_vma->addr); +free_text_vma: + vunmap(switcher_text_vma->addr); free_pages: i = TOTAL_SWITCHER_PAGES; free_some_pages: @@ -148,7 +175,8 @@ static void unmap_switcher(void) unsigned int i; /* vunmap() undoes *both* map_vm_area() and __get_vm_area(). */ - vunmap(switcher_vma->addr); + vunmap(switcher_text_vma->addr); + vunmap(switcher_stacks_vma->addr); /* Now we just need to free the pages we copied the switcher into */ for (i = 0; i < TOTAL_SWITCHER_PAGES; i++) __free_pages(lg_switcher_pages[i], 0); diff --git a/drivers/macintosh/rack-meter.c b/drivers/macintosh/rack-meter.c index 048901a1111a..caaec654d7ea 100644 --- a/drivers/macintosh/rack-meter.c +++ b/drivers/macintosh/rack-meter.c @@ -582,6 +582,7 @@ static struct of_device_id rackmeter_match[] = { { .name = "i2s" }, { } }; +MODULE_DEVICE_TABLE(of, rackmeter_match); static struct macio_driver rackmeter_driver = { .driver = { diff --git a/drivers/macintosh/via-pmu.c b/drivers/macintosh/via-pmu.c index f9512bfa6c3c..01ee736fe0ef 100644 --- a/drivers/macintosh/via-pmu.c +++ b/drivers/macintosh/via-pmu.c @@ -425,8 +425,9 @@ static int __init via_pmu_start(void) gpio_irq = irq_of_parse_and_map(gpio_node, 0); if (gpio_irq != NO_IRQ) { - if (request_irq(gpio_irq, gpio1_interrupt, IRQF_TIMER, - "GPIO1 ADB", (void *)0)) + if (request_irq(gpio_irq, gpio1_interrupt, + IRQF_NO_SUSPEND, "GPIO1 ADB", + (void *)0)) printk(KERN_ERR "pmu: can't get irq %d" " (GPIO1)\n", gpio_irq); else diff --git a/drivers/mailbox/mailbox-sti.c b/drivers/mailbox/mailbox-sti.c index 4835817c5365..2394cfe892b6 100644 --- a/drivers/mailbox/mailbox-sti.c +++ b/drivers/mailbox/mailbox-sti.c @@ -384,7 +384,7 @@ static struct mbox_chan *sti_mbox_xlate(struct mbox_controller *mbox, return chan; } -static struct mbox_chan_ops sti_mbox_ops = { +static const struct mbox_chan_ops sti_mbox_ops = { .startup = sti_mbox_startup_chan, .shutdown = sti_mbox_shutdown_chan, .send_data = sti_mbox_send_data, diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c index d6a1126d85ce..0ded8e97751d 100644 --- a/drivers/md/md-cluster.c +++ b/drivers/md/md-cluster.c @@ -48,13 +48,29 @@ struct resync_info { #define MD_CLUSTER_SUSPEND_READ_BALANCING 2 #define MD_CLUSTER_BEGIN_JOIN_CLUSTER 3 +/* Lock the send communication. This is done through + * bit manipulation as opposed to a mutex in order to + * accomodate lock and hold. See next comment. + */ +#define MD_CLUSTER_SEND_LOCK 4 +/* If cluster operations (such as adding a disk) must lock the + * communication channel, so as to perform extra operations + * (update metadata) and no other operation is allowed on the + * MD. Token needs to be locked and held until the operation + * completes witha md_update_sb(), which would eventually release + * the lock. + */ +#define MD_CLUSTER_SEND_LOCKED_ALREADY 5 + struct md_cluster_info { /* dlm lock space and resources for clustered raid. */ dlm_lockspace_t *lockspace; int slot_number; struct completion completion; + struct mutex recv_mutex; struct dlm_lock_resource *bitmap_lockres; + struct dlm_lock_resource **other_bitmap_lockres; struct dlm_lock_resource *resync_lockres; struct list_head suspend_list; spinlock_t suspend_lock; @@ -67,6 +83,7 @@ struct md_cluster_info { struct dlm_lock_resource *no_new_dev_lockres; struct md_thread *recv_thread; struct completion newdisk_completion; + wait_queue_head_t wait; unsigned long state; }; @@ -431,8 +448,10 @@ static void process_add_new_disk(struct mddev *mddev, struct cluster_msg *cmsg) static void process_metadata_update(struct mddev *mddev, struct cluster_msg *msg) { struct md_cluster_info *cinfo = mddev->cluster_info; - md_reload_sb(mddev, le32_to_cpu(msg->raid_slot)); + mddev->good_device_nr = le32_to_cpu(msg->raid_slot); + set_bit(MD_RELOAD_SB, &mddev->flags); dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_CR); + md_wakeup_thread(mddev->thread); } static void process_remove_disk(struct mddev *mddev, struct cluster_msg *msg) @@ -440,8 +459,11 @@ static void process_remove_disk(struct mddev *mddev, struct cluster_msg *msg) struct md_rdev *rdev = md_find_rdev_nr_rcu(mddev, le32_to_cpu(msg->raid_slot)); - if (rdev) - md_kick_rdev_from_array(rdev); + if (rdev) { + set_bit(ClusterRemove, &rdev->flags); + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); + md_wakeup_thread(mddev->thread); + } else pr_warn("%s: %d Could not find disk(%d) to REMOVE\n", __func__, __LINE__, le32_to_cpu(msg->raid_slot)); @@ -502,9 +524,11 @@ static void recv_daemon(struct md_thread *thread) struct cluster_msg msg; int ret; + mutex_lock(&cinfo->recv_mutex); /*get CR on Message*/ if (dlm_lock_sync(message_lockres, DLM_LOCK_CR)) { pr_err("md/raid1:failed to get CR on MESSAGE\n"); + mutex_unlock(&cinfo->recv_mutex); return; } @@ -528,33 +552,45 @@ static void recv_daemon(struct md_thread *thread) ret = dlm_unlock_sync(message_lockres); if (unlikely(ret != 0)) pr_info("unlock msg failed return %d\n", ret); + mutex_unlock(&cinfo->recv_mutex); } -/* lock_comm() +/* lock_token() * Takes the lock on the TOKEN lock resource so no other * node can communicate while the operation is underway. - * If called again, and the TOKEN lock is alread in EX mode - * return success. However, care must be taken that unlock_comm() - * is called only once. */ -static int lock_comm(struct md_cluster_info *cinfo) +static int lock_token(struct md_cluster_info *cinfo) { int error; - if (cinfo->token_lockres->mode == DLM_LOCK_EX) - return 0; - error = dlm_lock_sync(cinfo->token_lockres, DLM_LOCK_EX); if (error) pr_err("md-cluster(%s:%d): failed to get EX on TOKEN (%d)\n", __func__, __LINE__, error); + + /* Lock the receive sequence */ + mutex_lock(&cinfo->recv_mutex); return error; } +/* lock_comm() + * Sets the MD_CLUSTER_SEND_LOCK bit to lock the send channel. + */ +static int lock_comm(struct md_cluster_info *cinfo) +{ + wait_event(cinfo->wait, + !test_and_set_bit(MD_CLUSTER_SEND_LOCK, &cinfo->state)); + + return lock_token(cinfo); +} + static void unlock_comm(struct md_cluster_info *cinfo) { WARN_ON(cinfo->token_lockres->mode != DLM_LOCK_EX); + mutex_unlock(&cinfo->recv_mutex); dlm_unlock_sync(cinfo->token_lockres); + clear_bit(MD_CLUSTER_SEND_LOCK, &cinfo->state); + wake_up(&cinfo->wait); } /* __sendmsg() @@ -707,6 +743,8 @@ static int join(struct mddev *mddev, int nodes) spin_lock_init(&cinfo->suspend_lock); init_completion(&cinfo->completion); set_bit(MD_CLUSTER_BEGIN_JOIN_CLUSTER, &cinfo->state); + init_waitqueue_head(&cinfo->wait); + mutex_init(&cinfo->recv_mutex); mddev->cluster_info = cinfo; @@ -800,6 +838,7 @@ static void resync_bitmap(struct mddev *mddev) __func__, __LINE__, err); } +static void unlock_all_bitmaps(struct mddev *mddev); static int leave(struct mddev *mddev) { struct md_cluster_info *cinfo = mddev->cluster_info; @@ -820,6 +859,7 @@ static int leave(struct mddev *mddev) lockres_free(cinfo->ack_lockres); lockres_free(cinfo->no_new_dev_lockres); lockres_free(cinfo->bitmap_lockres); + unlock_all_bitmaps(mddev); dlm_release_lockspace(cinfo->lockspace, 2); return 0; } @@ -835,9 +875,25 @@ static int slot_number(struct mddev *mddev) return cinfo->slot_number - 1; } +/* + * Check if the communication is already locked, else lock the communication + * channel. + * If it is already locked, token is in EX mode, and hence lock_token() + * should not be called. + */ static int metadata_update_start(struct mddev *mddev) { - return lock_comm(mddev->cluster_info); + struct md_cluster_info *cinfo = mddev->cluster_info; + + wait_event(cinfo->wait, + !test_and_set_bit(MD_CLUSTER_SEND_LOCK, &cinfo->state) || + test_and_clear_bit(MD_CLUSTER_SEND_LOCKED_ALREADY, &cinfo->state)); + + /* If token is already locked, return 0 */ + if (cinfo->token_lockres->mode == DLM_LOCK_EX) + return 0; + + return lock_token(cinfo); } static int metadata_update_finish(struct mddev *mddev) @@ -862,6 +918,7 @@ static int metadata_update_finish(struct mddev *mddev) ret = __sendmsg(cinfo, &cmsg); } else pr_warn("md-cluster: No good device id found to send\n"); + clear_bit(MD_CLUSTER_SEND_LOCKED_ALREADY, &cinfo->state); unlock_comm(cinfo); return ret; } @@ -869,6 +926,7 @@ static int metadata_update_finish(struct mddev *mddev) static void metadata_update_cancel(struct mddev *mddev) { struct md_cluster_info *cinfo = mddev->cluster_info; + clear_bit(MD_CLUSTER_SEND_LOCKED_ALREADY, &cinfo->state); unlock_comm(cinfo); } @@ -882,8 +940,16 @@ static int resync_start(struct mddev *mddev) static int resync_info_update(struct mddev *mddev, sector_t lo, sector_t hi) { struct md_cluster_info *cinfo = mddev->cluster_info; + struct resync_info ri; struct cluster_msg cmsg = {0}; + /* do not send zero again, if we have sent before */ + if (hi == 0) { + memcpy(&ri, cinfo->bitmap_lockres->lksb.sb_lvbptr, sizeof(struct resync_info)); + if (le64_to_cpu(ri.hi) == 0) + return 0; + } + add_resync_info(cinfo->bitmap_lockres, lo, hi); /* Re-acquire the lock to refresh LVB */ dlm_lock_sync(cinfo->bitmap_lockres, DLM_LOCK_PW); @@ -954,14 +1020,30 @@ static int add_new_disk(struct mddev *mddev, struct md_rdev *rdev) ret = -ENOENT; if (ret) unlock_comm(cinfo); - else + else { dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_CR); + /* Since MD_CHANGE_DEVS will be set in add_bound_rdev which + * will run soon after add_new_disk, the below path will be + * invoked: + * md_wakeup_thread(mddev->thread) + * -> conf->thread (raid1d) + * -> md_check_recovery -> md_update_sb + * -> metadata_update_start/finish + * MD_CLUSTER_SEND_LOCKED_ALREADY will be cleared eventually. + * + * For other failure cases, metadata_update_cancel and + * add_new_disk_cancel also clear below bit as well. + * */ + set_bit(MD_CLUSTER_SEND_LOCKED_ALREADY, &cinfo->state); + wake_up(&cinfo->wait); + } return ret; } static void add_new_disk_cancel(struct mddev *mddev) { struct md_cluster_info *cinfo = mddev->cluster_info; + clear_bit(MD_CLUSTER_SEND_LOCKED_ALREADY, &cinfo->state); unlock_comm(cinfo); } @@ -986,7 +1068,59 @@ static int remove_disk(struct mddev *mddev, struct md_rdev *rdev) struct md_cluster_info *cinfo = mddev->cluster_info; cmsg.type = cpu_to_le32(REMOVE); cmsg.raid_slot = cpu_to_le32(rdev->desc_nr); - return __sendmsg(cinfo, &cmsg); + return sendmsg(cinfo, &cmsg); +} + +static int lock_all_bitmaps(struct mddev *mddev) +{ + int slot, my_slot, ret, held = 1, i = 0; + char str[64]; + struct md_cluster_info *cinfo = mddev->cluster_info; + + cinfo->other_bitmap_lockres = kzalloc((mddev->bitmap_info.nodes - 1) * + sizeof(struct dlm_lock_resource *), + GFP_KERNEL); + if (!cinfo->other_bitmap_lockres) { + pr_err("md: can't alloc mem for other bitmap locks\n"); + return 0; + } + + my_slot = slot_number(mddev); + for (slot = 0; slot < mddev->bitmap_info.nodes; slot++) { + if (slot == my_slot) + continue; + + memset(str, '\0', 64); + snprintf(str, 64, "bitmap%04d", slot); + cinfo->other_bitmap_lockres[i] = lockres_init(mddev, str, NULL, 1); + if (!cinfo->other_bitmap_lockres[i]) + return -ENOMEM; + + cinfo->other_bitmap_lockres[i]->flags |= DLM_LKF_NOQUEUE; + ret = dlm_lock_sync(cinfo->other_bitmap_lockres[i], DLM_LOCK_PW); + if (ret) + held = -1; + i++; + } + + return held; +} + +static void unlock_all_bitmaps(struct mddev *mddev) +{ + struct md_cluster_info *cinfo = mddev->cluster_info; + int i; + + /* release other node's bitmap lock if they are existed */ + if (cinfo->other_bitmap_lockres) { + for (i = 0; i < mddev->bitmap_info.nodes - 1; i++) { + if (cinfo->other_bitmap_lockres[i]) { + dlm_unlock_sync(cinfo->other_bitmap_lockres[i]); + lockres_free(cinfo->other_bitmap_lockres[i]); + } + } + kfree(cinfo->other_bitmap_lockres); + } } static int gather_bitmaps(struct md_rdev *rdev) @@ -1034,6 +1168,8 @@ static struct md_cluster_operations cluster_ops = { .new_disk_ack = new_disk_ack, .remove_disk = remove_disk, .gather_bitmaps = gather_bitmaps, + .lock_all_bitmaps = lock_all_bitmaps, + .unlock_all_bitmaps = unlock_all_bitmaps, }; static int __init cluster_init(void) diff --git a/drivers/md/md-cluster.h b/drivers/md/md-cluster.h index e75ea2613184..45ce6c97d8bd 100644 --- a/drivers/md/md-cluster.h +++ b/drivers/md/md-cluster.h @@ -24,6 +24,8 @@ struct md_cluster_operations { int (*new_disk_ack)(struct mddev *mddev, bool ack); int (*remove_disk)(struct mddev *mddev, struct md_rdev *rdev); int (*gather_bitmaps)(struct md_rdev *rdev); + int (*lock_all_bitmaps)(struct mddev *mddev); + void (*unlock_all_bitmaps)(struct mddev *mddev); }; #endif /* _MD_CLUSTER_H */ diff --git a/drivers/md/md.c b/drivers/md/md.c index 31b595479aa5..e55e6cf9ec17 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -206,15 +206,6 @@ void md_new_event(struct mddev *mddev) } EXPORT_SYMBOL_GPL(md_new_event); -/* Alternate version that can be called from interrupts - * when calling sysfs_notify isn't needed. - */ -static void md_new_event_inintr(struct mddev *mddev) -{ - atomic_inc(&md_event_count); - wake_up(&md_event_waiters); -} - /* * Enables to iterate over all existing md arrays * all_mddevs_lock protects this list. @@ -260,8 +251,7 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio) blk_queue_split(q, &bio, q->bio_split); - if (mddev == NULL || mddev->pers == NULL - || !mddev->ready) { + if (mddev == NULL || mddev->pers == NULL) { bio_io_error(bio); return BLK_QC_T_NONE; } @@ -1026,8 +1016,9 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor * (not needed for Linear and RAID0 as metadata doesn't * record this size) */ - if (rdev->sectors >= (2ULL << 32) && sb->level >= 1) - rdev->sectors = (2ULL << 32) - 2; + if (IS_ENABLED(CONFIG_LBDAF) && (u64)rdev->sectors >= (2ULL << 32) && + sb->level >= 1) + rdev->sectors = (sector_t)(2ULL << 32) - 2; if (rdev->sectors < ((sector_t)sb->size) * 2 && sb->level >= 1) /* "this cannot possibly happen" ... */ @@ -1199,13 +1190,13 @@ static void super_90_sync(struct mddev *mddev, struct md_rdev *rdev) memcpy(&sb->set_uuid2, mddev->uuid+8, 4); memcpy(&sb->set_uuid3, mddev->uuid+12,4); - sb->ctime = mddev->ctime; + sb->ctime = clamp_t(time64_t, mddev->ctime, 0, U32_MAX); sb->level = mddev->level; sb->size = mddev->dev_sectors / 2; sb->raid_disks = mddev->raid_disks; sb->md_minor = mddev->md_minor; sb->not_persistent = 0; - sb->utime = mddev->utime; + sb->utime = clamp_t(time64_t, mddev->utime, 0, U32_MAX); sb->state = 0; sb->events_hi = (mddev->events>>32); sb->events_lo = (u32)mddev->events; @@ -1320,8 +1311,9 @@ super_90_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors) /* Limit to 4TB as metadata cannot record more than that. * 4TB == 2^32 KB, or 2*2^32 sectors. */ - if (num_sectors >= (2ULL << 32) && rdev->mddev->level >= 1) - num_sectors = (2ULL << 32) - 2; + if (IS_ENABLED(CONFIG_LBDAF) && (u64)num_sectors >= (2ULL << 32) && + rdev->mddev->level >= 1) + num_sectors = (sector_t)(2ULL << 32) - 2; md_super_write(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size, rdev->sb_page); md_super_wait(rdev->mddev); @@ -1542,8 +1534,8 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev) mddev->patch_version = 0; mddev->external = 0; mddev->chunk_sectors = le32_to_cpu(sb->chunksize); - mddev->ctime = le64_to_cpu(sb->ctime) & ((1ULL << 32)-1); - mddev->utime = le64_to_cpu(sb->utime) & ((1ULL << 32)-1); + mddev->ctime = le64_to_cpu(sb->ctime); + mddev->utime = le64_to_cpu(sb->utime); mddev->level = le32_to_cpu(sb->level); mddev->clevel[0] = 0; mddev->layout = le32_to_cpu(sb->layout); @@ -1602,6 +1594,11 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev) mddev->new_chunk_sectors = mddev->chunk_sectors; } + if (le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL) { + set_bit(MD_HAS_JOURNAL, &mddev->flags); + if (mddev->recovery_cp == MaxSector) + set_bit(MD_JOURNAL_CLEAN, &mddev->flags); + } } else if (mddev->pers == NULL) { /* Insist of good event counter while assembling, except for * spares (which don't need an event count) */ @@ -1648,8 +1645,6 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev) } set_bit(Journal, &rdev->flags); rdev->journal_tail = le64_to_cpu(sb->journal_tail); - if (mddev->recovery_cp == MaxSector) - set_bit(MD_JOURNAL_CLEAN, &mddev->flags); rdev->raid_disk = 0; break; default: @@ -1669,8 +1664,6 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev) set_bit(WriteMostly, &rdev->flags); if (le32_to_cpu(sb->feature_map) & MD_FEATURE_REPLACEMENT) set_bit(Replacement, &rdev->flags); - if (le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL) - set_bit(MD_HAS_JOURNAL, &mddev->flags); } else /* MULTIPATH are always insync */ set_bit(In_sync, &rdev->flags); @@ -2014,28 +2007,32 @@ int md_integrity_register(struct mddev *mddev) } EXPORT_SYMBOL(md_integrity_register); -/* Disable data integrity if non-capable/non-matching disk is being added */ -void md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev) +/* + * Attempt to add an rdev, but only if it is consistent with the current + * integrity profile + */ +int md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev) { struct blk_integrity *bi_rdev; struct blk_integrity *bi_mddev; + char name[BDEVNAME_SIZE]; if (!mddev->gendisk) - return; + return 0; bi_rdev = bdev_get_integrity(rdev->bdev); bi_mddev = blk_get_integrity(mddev->gendisk); if (!bi_mddev) /* nothing to do */ - return; - if (rdev->raid_disk < 0) /* skip spares */ - return; - if (bi_rdev && blk_integrity_compare(mddev->gendisk, - rdev->bdev->bd_disk) >= 0) - return; - WARN_ON_ONCE(!mddev->suspended); - printk(KERN_NOTICE "disabling data integrity on %s\n", mdname(mddev)); - blk_integrity_unregister(mddev->gendisk); + return 0; + + if (blk_integrity_compare(mddev->gendisk, rdev->bdev->bd_disk) != 0) { + printk(KERN_NOTICE "%s: incompatible integrity profile for %s\n", + mdname(mddev), bdevname(rdev->bdev, name)); + return -ENXIO; + } + + return 0; } EXPORT_SYMBOL(md_integrity_add_rdev); @@ -2050,8 +2047,9 @@ static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev) return -EEXIST; /* make sure rdev->sectors exceeds mddev->dev_sectors */ - if (rdev->sectors && (mddev->dev_sectors == 0 || - rdev->sectors < mddev->dev_sectors)) { + if (!test_bit(Journal, &rdev->flags) && + rdev->sectors && + (mddev->dev_sectors == 0 || rdev->sectors < mddev->dev_sectors)) { if (mddev->pers) { /* Cannot change size, so fail * If mddev->level <= 0, then we don't care @@ -2082,7 +2080,8 @@ static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev) } } rcu_read_unlock(); - if (mddev->max_disks && rdev->desc_nr >= mddev->max_disks) { + if (!test_bit(Journal, &rdev->flags) && + mddev->max_disks && rdev->desc_nr >= mddev->max_disks) { printk(KERN_WARNING "md: %s: array is limited to %d devices\n", mdname(mddev), mddev->max_disks); return -EBUSY; @@ -2331,7 +2330,7 @@ repeat: spin_lock(&mddev->lock); - mddev->utime = get_seconds(); + mddev->utime = ktime_get_real_seconds(); if (test_and_clear_bit(MD_CHANGE_DEVS, &mddev->flags)) force_change = 1; @@ -2457,15 +2456,20 @@ static int add_bound_rdev(struct md_rdev *rdev) { struct mddev *mddev = rdev->mddev; int err = 0; + bool add_journal = test_bit(Journal, &rdev->flags); - if (!mddev->pers->hot_remove_disk) { + if (!mddev->pers->hot_remove_disk || add_journal) { /* If there is hot_add_disk but no hot_remove_disk * then added disks for geometry changes, * and should be added immediately. */ super_types[mddev->major_version]. validate_super(mddev, rdev); + if (add_journal) + mddev_suspend(mddev); err = mddev->pers->hot_add_disk(mddev, rdev); + if (add_journal) + mddev_resume(mddev); if (err) { unbind_rdev_from_array(rdev); export_rdev(rdev); @@ -5299,7 +5303,6 @@ int md_run(struct mddev *mddev) smp_wmb(); spin_lock(&mddev->lock); mddev->pers = pers; - mddev->ready = 1; spin_unlock(&mddev->lock); rdev_for_each(rdev, mddev) if (rdev->raid_disk >= 0) @@ -5499,7 +5502,6 @@ static void __md_stop(struct mddev *mddev) /* Ensure ->event_work is done */ flush_workqueue(md_misc_wq); spin_lock(&mddev->lock); - mddev->ready = 0; mddev->pers = NULL; spin_unlock(&mddev->lock); pers->free(mddev, mddev->private); @@ -5837,7 +5839,7 @@ static int get_array_info(struct mddev *mddev, void __user *arg) info.major_version = mddev->major_version; info.minor_version = mddev->minor_version; info.patch_version = MD_PATCHLEVEL_VERSION; - info.ctime = mddev->ctime; + info.ctime = clamp_t(time64_t, mddev->ctime, 0, U32_MAX); info.level = mddev->level; info.size = mddev->dev_sectors / 2; if (info.size != mddev->dev_sectors / 2) /* overflow */ @@ -5847,7 +5849,7 @@ static int get_array_info(struct mddev *mddev, void __user *arg) info.md_minor = mddev->md_minor; info.not_persistent= !mddev->persistent; - info.utime = mddev->utime; + info.utime = clamp_t(time64_t, mddev->utime, 0, U32_MAX); info.state = 0; if (mddev->in_sync) info.state = (1<<MD_SB_CLEAN); @@ -6038,8 +6040,23 @@ static int add_new_disk(struct mddev *mddev, mdu_disk_info_t *info) else clear_bit(WriteMostly, &rdev->flags); - if (info->state & (1<<MD_DISK_JOURNAL)) + if (info->state & (1<<MD_DISK_JOURNAL)) { + struct md_rdev *rdev2; + bool has_journal = false; + + /* make sure no existing journal disk */ + rdev_for_each(rdev2, mddev) { + if (test_bit(Journal, &rdev2->flags)) { + has_journal = true; + break; + } + } + if (has_journal) { + export_rdev(rdev); + return -EBUSY; + } set_bit(Journal, &rdev->flags); + } /* * check whether the device shows up in other nodes */ @@ -6130,15 +6147,11 @@ static int hot_remove_disk(struct mddev *mddev, dev_t dev) { char b[BDEVNAME_SIZE]; struct md_rdev *rdev; - int ret = -1; rdev = find_rdev(mddev, dev); if (!rdev) return -ENXIO; - if (mddev_is_clustered(mddev)) - ret = md_cluster_ops->metadata_update_start(mddev); - if (rdev->raid_disk < 0) goto kick_rdev; @@ -6149,7 +6162,7 @@ static int hot_remove_disk(struct mddev *mddev, dev_t dev) goto busy; kick_rdev: - if (mddev_is_clustered(mddev) && ret == 0) + if (mddev_is_clustered(mddev)) md_cluster_ops->remove_disk(mddev, rdev); md_kick_rdev_from_array(rdev); @@ -6158,9 +6171,6 @@ kick_rdev: return 0; busy: - if (mddev_is_clustered(mddev) && ret == 0) - md_cluster_ops->metadata_update_cancel(mddev); - printk(KERN_WARNING "md: cannot remove active disk %s from %s ...\n", bdevname(rdev->bdev,b), mdname(mddev)); return -EBUSY; @@ -6354,13 +6364,13 @@ static int set_array_info(struct mddev *mddev, mdu_array_info_t *info) /* ensure mddev_put doesn't delete this now that there * is some minimal configuration. */ - mddev->ctime = get_seconds(); + mddev->ctime = ktime_get_real_seconds(); return 0; } mddev->major_version = MD_MAJOR_VERSION; mddev->minor_version = MD_MINOR_VERSION; mddev->patch_version = MD_PATCHLEVEL_VERSION; - mddev->ctime = get_seconds(); + mddev->ctime = ktime_get_real_seconds(); mddev->level = info->level; mddev->clevel[0] = 0; @@ -6602,6 +6612,19 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info) rv = -EINVAL; goto err; } + if (mddev->bitmap_info.nodes) { + /* hold PW on all the bitmap lock */ + if (md_cluster_ops->lock_all_bitmaps(mddev) <= 0) { + printk("md: can't change bitmap to none since the" + " array is in use by more than one node\n"); + rv = -EPERM; + md_cluster_ops->unlock_all_bitmaps(mddev); + goto err; + } + + mddev->bitmap_info.nodes = 0; + md_cluster_ops->leave(mddev); + } mddev->pers->quiesce(mddev, 1); bitmap_destroy(mddev); mddev->pers->quiesce(mddev, 0); @@ -7180,7 +7203,7 @@ void md_error(struct mddev *mddev, struct md_rdev *rdev) md_wakeup_thread(mddev->thread); if (mddev->event_work.func) queue_work(md_misc_wq, &mddev->event_work); - md_new_event_inintr(mddev); + md_new_event(mddev); } EXPORT_SYMBOL(md_error); @@ -7704,7 +7727,7 @@ EXPORT_SYMBOL(md_write_end); * attempting a GFP_KERNEL allocation while holding the mddev lock. * Must be called with mddev_lock held. * - * In the ->external case MD_CHANGE_CLEAN can not be cleared until mddev->lock + * In the ->external case MD_CHANGE_PENDING can not be cleared until mddev->lock * is dropped, so return -EAGAIN after notifying userspace. */ int md_allow_write(struct mddev *mddev) @@ -8169,19 +8192,20 @@ static int remove_and_add_spares(struct mddev *mddev, continue; if (test_bit(Faulty, &rdev->flags)) continue; - if (test_bit(Journal, &rdev->flags)) - continue; - if (mddev->ro && - ! (rdev->saved_raid_disk >= 0 && - !test_bit(Bitmap_sync, &rdev->flags))) - continue; + if (!test_bit(Journal, &rdev->flags)) { + if (mddev->ro && + ! (rdev->saved_raid_disk >= 0 && + !test_bit(Bitmap_sync, &rdev->flags))) + continue; - rdev->recovery_offset = 0; + rdev->recovery_offset = 0; + } if (mddev->pers-> hot_add_disk(mddev, rdev) == 0) { if (sysfs_link_rdev(mddev, rdev)) /* failure here is OK */; - spares++; + if (!test_bit(Journal, &rdev->flags)) + spares++; md_new_event(mddev); set_bit(MD_CHANGE_DEVS, &mddev->flags); } @@ -8276,6 +8300,7 @@ void md_check_recovery(struct mddev *mddev) (mddev->flags & MD_UPDATE_SB_FLAGS & ~ (1<<MD_CHANGE_PENDING)) || test_bit(MD_RECOVERY_NEEDED, &mddev->recovery) || test_bit(MD_RECOVERY_DONE, &mddev->recovery) || + test_bit(MD_RELOAD_SB, &mddev->flags) || (mddev->external == 0 && mddev->safemode == 1) || (mddev->safemode == 2 && ! atomic_read(&mddev->writes_pending) && !mddev->in_sync && mddev->recovery_cp == MaxSector) @@ -8314,6 +8339,21 @@ void md_check_recovery(struct mddev *mddev) goto unlock; } + if (mddev_is_clustered(mddev)) { + struct md_rdev *rdev; + /* kick the device if another node issued a + * remove disk. + */ + rdev_for_each(rdev, mddev) { + if (test_and_clear_bit(ClusterRemove, &rdev->flags) && + rdev->raid_disk < 0) + md_kick_rdev_from_array(rdev); + } + + if (test_and_clear_bit(MD_RELOAD_SB, &mddev->flags)) + md_reload_sb(mddev, mddev->good_device_nr); + } + if (!mddev->external) { int did_change = 0; spin_lock(&mddev->lock); @@ -8635,7 +8675,6 @@ static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev) ret = remove_and_add_spares(mddev, rdev2); pr_info("Activated spare: %s\n", bdevname(rdev2->bdev,b)); - continue; } /* device faulty * We just want to do the minimum to mark the disk diff --git a/drivers/md/md.h b/drivers/md/md.h index 75b9aaacb03f..b5c4be73e6e4 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -162,6 +162,7 @@ enum flag_bits { * Usually, this device should be faster * than other devices in the array */ + ClusterRemove, }; static inline int is_badblock(struct md_rdev *rdev, sector_t s, int sectors, @@ -200,6 +201,9 @@ struct mddev { */ #define MD_JOURNAL_CLEAN 5 /* A raid with journal is already clean */ #define MD_HAS_JOURNAL 6 /* The raid array has journal feature set */ +#define MD_RELOAD_SB 7 /* Reload the superblock because another node + * updated it. + */ int suspended; atomic_t active_io; @@ -208,8 +212,6 @@ struct mddev { * are happening, so run/ * takeover/stop are not safe */ - int ready; /* See when safe to pass - * IO requests down */ struct gendisk *gendisk; struct kobject kobj; @@ -226,7 +228,7 @@ struct mddev { * managed externally */ char metadata_type[17]; /* externally set*/ int chunk_sectors; - time_t ctime, utime; + time64_t ctime, utime; int level, layout; char clevel[16]; int raid_disks; @@ -430,6 +432,7 @@ struct mddev { struct work_struct event_work; /* used by dm to report failure event */ void (*sync_super)(struct mddev *mddev, struct md_rdev *rdev); struct md_cluster_info *cluster_info; + unsigned int good_device_nr; /* good device num within cluster raid */ }; static inline int __must_check mddev_lock(struct mddev *mddev) @@ -623,7 +626,7 @@ extern void md_wait_for_blocked_rdev(struct md_rdev *rdev, struct mddev *mddev); extern void md_set_array_sectors(struct mddev *mddev, sector_t array_sectors); extern int md_check_no_bitmap(struct mddev *mddev); extern int md_integrity_register(struct mddev *mddev); -extern void md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev); +extern int md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev); extern int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale); extern void mddev_init(struct mddev *mddev); diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c index 7331a80d89f1..0a72ab6e6c20 100644 --- a/drivers/md/multipath.c +++ b/drivers/md/multipath.c @@ -257,6 +257,9 @@ static int multipath_add_disk(struct mddev *mddev, struct md_rdev *rdev) disk_stack_limits(mddev->gendisk, rdev->bdev, rdev->data_offset << 9); + err = md_integrity_add_rdev(rdev, mddev); + if (err) + break; spin_lock_irq(&conf->device_lock); mddev->degraded--; rdev->raid_disk = path; @@ -264,9 +267,6 @@ static int multipath_add_disk(struct mddev *mddev, struct md_rdev *rdev) spin_unlock_irq(&conf->device_lock); rcu_assign_pointer(p->rdev, rdev); err = 0; - mddev_suspend(mddev); - md_integrity_add_rdev(rdev, mddev); - mddev_resume(mddev); break; } diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index f8e5db0cb5aa..2ea12c6bf659 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -549,13 +549,13 @@ static void *raid0_takeover_raid10(struct mddev *mddev) * - all mirrors must be already degraded */ if (mddev->layout != ((1 << 8) + 2)) { - printk(KERN_ERR "md/raid0:%s:: Raid0 cannot takover layout: 0x%x\n", + printk(KERN_ERR "md/raid0:%s:: Raid0 cannot takeover layout: 0x%x\n", mdname(mddev), mddev->layout); return ERR_PTR(-EINVAL); } if (mddev->raid_disks & 1) { - printk(KERN_ERR "md/raid0:%s: Raid0 cannot takover Raid10 with odd disk number.\n", + printk(KERN_ERR "md/raid0:%s: Raid0 cannot takeover Raid10 with odd disk number.\n", mdname(mddev)); return ERR_PTR(-EINVAL); } diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index e2169ff6e0f0..c4b913409226 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1589,6 +1589,9 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev) if (mddev->recovery_disabled == conf->recovery_disabled) return -EBUSY; + if (md_integrity_add_rdev(rdev, mddev)) + return -ENXIO; + if (rdev->raid_disk >= 0) first = last = rdev->raid_disk; @@ -1632,9 +1635,6 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev) break; } } - mddev_suspend(mddev); - md_integrity_add_rdev(rdev, mddev); - mddev_resume(mddev); if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev))) queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue); print_conf(conf); diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 84e597e1c489..ce959b4ae4df 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1698,6 +1698,9 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev) if (rdev->saved_raid_disk < 0 && !_enough(conf, 1, -1)) return -EINVAL; + if (md_integrity_add_rdev(rdev, mddev)) + return -ENXIO; + if (rdev->raid_disk >= 0) first = last = rdev->raid_disk; @@ -1739,9 +1742,6 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev) rcu_assign_pointer(p->rdev, rdev); break; } - mddev_suspend(mddev); - md_integrity_add_rdev(rdev, mddev); - mddev_resume(mddev); if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev))) queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue); diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index b887e04d7e5c..9531f5f05b93 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -34,6 +34,12 @@ #define RECLAIM_MAX_FREE_SPACE (10 * 1024 * 1024 * 2) /* sector */ #define RECLAIM_MAX_FREE_SPACE_SHIFT (2) +/* + * We only need 2 bios per I/O unit to make progress, but ensure we + * have a few more available to not get too tight. + */ +#define R5L_POOL_SIZE 4 + struct r5l_log { struct md_rdev *rdev; @@ -69,7 +75,12 @@ struct r5l_log { struct list_head finished_ios; /* io_units which settle down in log disk */ struct bio flush_bio; + struct list_head no_mem_stripes; /* pending stripes, -ENOMEM */ + struct kmem_cache *io_kc; + mempool_t *io_pool; + struct bio_set *bs; + mempool_t *meta_pool; struct md_thread *reclaim_thread; unsigned long reclaim_target; /* number of space that need to be @@ -150,27 +161,6 @@ static bool r5l_has_free_space(struct r5l_log *log, sector_t size) return log->device_size > used_size + size; } -static void r5l_free_io_unit(struct r5l_log *log, struct r5l_io_unit *io) -{ - __free_page(io->meta_page); - kmem_cache_free(log->io_kc, io); -} - -static void r5l_move_io_unit_list(struct list_head *from, struct list_head *to, - enum r5l_io_unit_state state) -{ - struct r5l_io_unit *io; - - while (!list_empty(from)) { - io = list_first_entry(from, struct r5l_io_unit, log_sibling); - /* don't change list order */ - if (io->state >= state) - list_move_tail(&io->log_sibling, to); - else - break; - } -} - static void __r5l_set_io_unit_state(struct r5l_io_unit *io, enum r5l_io_unit_state state) { @@ -206,6 +196,20 @@ static void r5l_log_run_stripes(struct r5l_log *log) } } +static void r5l_move_to_end_ios(struct r5l_log *log) +{ + struct r5l_io_unit *io, *next; + + assert_spin_locked(&log->io_list_lock); + + list_for_each_entry_safe(io, next, &log->running_ios, log_sibling) { + /* don't change list order */ + if (io->state < IO_UNIT_IO_END) + break; + list_move_tail(&io->log_sibling, &log->io_end_ios); + } +} + static void r5l_log_endio(struct bio *bio) { struct r5l_io_unit *io = bio->bi_private; @@ -216,12 +220,12 @@ static void r5l_log_endio(struct bio *bio) md_error(log->rdev->mddev, log->rdev); bio_put(bio); + mempool_free(io->meta_page, log->meta_pool); spin_lock_irqsave(&log->io_list_lock, flags); __r5l_set_io_unit_state(io, IO_UNIT_IO_END); if (log->need_cache_flush) - r5l_move_io_unit_list(&log->running_ios, &log->io_end_ios, - IO_UNIT_IO_END); + r5l_move_to_end_ios(log); else r5l_log_run_stripes(log); spin_unlock_irqrestore(&log->io_list_lock, flags); @@ -255,7 +259,7 @@ static void r5l_submit_current_io(struct r5l_log *log) static struct bio *r5l_bio_alloc(struct r5l_log *log) { - struct bio *bio = bio_kmalloc(GFP_NOIO | __GFP_NOFAIL, BIO_MAX_PAGES); + struct bio *bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_PAGES, log->bs); bio->bi_rw = WRITE; bio->bi_bdev = log->rdev->bdev; @@ -286,15 +290,19 @@ static struct r5l_io_unit *r5l_new_meta(struct r5l_log *log) struct r5l_io_unit *io; struct r5l_meta_block *block; - /* We can't handle memory allocate failure so far */ - io = kmem_cache_zalloc(log->io_kc, GFP_NOIO | __GFP_NOFAIL); + io = mempool_alloc(log->io_pool, GFP_ATOMIC); + if (!io) + return NULL; + memset(io, 0, sizeof(*io)); + io->log = log; INIT_LIST_HEAD(&io->log_sibling); INIT_LIST_HEAD(&io->stripe_list); io->state = IO_UNIT_RUNNING; - io->meta_page = alloc_page(GFP_NOIO | __GFP_NOFAIL | __GFP_ZERO); + io->meta_page = mempool_alloc(log->meta_pool, GFP_NOIO); block = page_address(io->meta_page); + clear_page(block); block->magic = cpu_to_le32(R5LOG_MAGIC); block->version = R5LOG_VERSION; block->seq = cpu_to_le64(log->seq); @@ -324,8 +332,12 @@ static int r5l_get_meta(struct r5l_log *log, unsigned int payload_size) log->current_io->meta_offset + payload_size > PAGE_SIZE) r5l_submit_current_io(log); - if (!log->current_io) + if (!log->current_io) { log->current_io = r5l_new_meta(log); + if (!log->current_io) + return -ENOMEM; + } + return 0; } @@ -370,11 +382,12 @@ static void r5l_append_payload_page(struct r5l_log *log, struct page *page) r5_reserve_log_entry(log, io); } -static void r5l_log_stripe(struct r5l_log *log, struct stripe_head *sh, +static int r5l_log_stripe(struct r5l_log *log, struct stripe_head *sh, int data_pages, int parity_pages) { int i; int meta_size; + int ret; struct r5l_io_unit *io; meta_size = @@ -383,7 +396,10 @@ static void r5l_log_stripe(struct r5l_log *log, struct stripe_head *sh, sizeof(struct r5l_payload_data_parity) + sizeof(__le32) * parity_pages; - r5l_get_meta(log, meta_size); + ret = r5l_get_meta(log, meta_size); + if (ret) + return ret; + io = log->current_io; for (i = 0; i < sh->disks; i++) { @@ -413,6 +429,8 @@ static void r5l_log_stripe(struct r5l_log *log, struct stripe_head *sh, list_add_tail(&sh->log_list, &io->stripe_list); atomic_inc(&io->pending_stripe); sh->log_io = io; + + return 0; } static void r5l_wake_reclaim(struct r5l_log *log, sector_t space); @@ -427,6 +445,7 @@ int r5l_write_stripe(struct r5l_log *log, struct stripe_head *sh) int meta_size; int reserve; int i; + int ret = 0; if (!log) return -EAGAIN; @@ -475,17 +494,22 @@ int r5l_write_stripe(struct r5l_log *log, struct stripe_head *sh) mutex_lock(&log->io_mutex); /* meta + data */ reserve = (1 + write_disks) << (PAGE_SHIFT - 9); - if (r5l_has_free_space(log, reserve)) - r5l_log_stripe(log, sh, data_pages, parity_pages); - else { + if (!r5l_has_free_space(log, reserve)) { spin_lock(&log->no_space_stripes_lock); list_add_tail(&sh->log_list, &log->no_space_stripes); spin_unlock(&log->no_space_stripes_lock); r5l_wake_reclaim(log, reserve); + } else { + ret = r5l_log_stripe(log, sh, data_pages, parity_pages); + if (ret) { + spin_lock_irq(&log->io_list_lock); + list_add_tail(&sh->log_list, &log->no_mem_stripes); + spin_unlock_irq(&log->io_list_lock); + } } - mutex_unlock(&log->io_mutex); + mutex_unlock(&log->io_mutex); return 0; } @@ -538,6 +562,21 @@ static sector_t r5l_reclaimable_space(struct r5l_log *log) log->next_checkpoint); } +static void r5l_run_no_mem_stripe(struct r5l_log *log) +{ + struct stripe_head *sh; + + assert_spin_locked(&log->io_list_lock); + + if (!list_empty(&log->no_mem_stripes)) { + sh = list_first_entry(&log->no_mem_stripes, + struct stripe_head, log_list); + list_del_init(&sh->log_list); + set_bit(STRIPE_HANDLE, &sh->state); + raid5_release_stripe(sh); + } +} + static bool r5l_complete_finished_ios(struct r5l_log *log) { struct r5l_io_unit *io, *next; @@ -554,7 +593,8 @@ static bool r5l_complete_finished_ios(struct r5l_log *log) log->next_cp_seq = io->seq; list_del(&io->log_sibling); - r5l_free_io_unit(log, io); + mempool_free(io, log->io_pool); + r5l_run_no_mem_stripe(log); found = true; } @@ -787,6 +827,13 @@ void r5l_quiesce(struct r5l_log *log, int state) return; if (state == 0) { log->in_teardown = 0; + /* + * This is a special case for hotadd. In suspend, the array has + * no journal. In resume, journal is initialized as well as the + * reclaim thread. + */ + if (log->reclaim_thread) + return; log->reclaim_thread = md_register_thread(r5l_reclaim_thread, log->rdev->mddev, "reclaim"); } else if (state == 1) { @@ -806,10 +853,18 @@ void r5l_quiesce(struct r5l_log *log, int state) bool r5l_log_disk_error(struct r5conf *conf) { + struct r5l_log *log; + bool ret; /* don't allow write if journal disk is missing */ - if (!conf->log) - return test_bit(MD_HAS_JOURNAL, &conf->mddev->flags); - return test_bit(Faulty, &conf->log->rdev->flags); + rcu_read_lock(); + log = rcu_dereference(conf->log); + + if (!log) + ret = test_bit(MD_HAS_JOURNAL, &conf->mddev->flags); + else + ret = test_bit(Faulty, &log->rdev->flags); + rcu_read_unlock(); + return ret; } struct r5l_recovery_ctx { @@ -1160,23 +1215,45 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev) if (!log->io_kc) goto io_kc; + log->io_pool = mempool_create_slab_pool(R5L_POOL_SIZE, log->io_kc); + if (!log->io_pool) + goto io_pool; + + log->bs = bioset_create(R5L_POOL_SIZE, 0); + if (!log->bs) + goto io_bs; + + log->meta_pool = mempool_create_page_pool(R5L_POOL_SIZE, 0); + if (!log->meta_pool) + goto out_mempool; + log->reclaim_thread = md_register_thread(r5l_reclaim_thread, log->rdev->mddev, "reclaim"); if (!log->reclaim_thread) goto reclaim_thread; init_waitqueue_head(&log->iounit_wait); + INIT_LIST_HEAD(&log->no_mem_stripes); + INIT_LIST_HEAD(&log->no_space_stripes); spin_lock_init(&log->no_space_stripes_lock); if (r5l_load_log(log)) goto error; - conf->log = log; + rcu_assign_pointer(conf->log, log); + set_bit(MD_HAS_JOURNAL, &conf->mddev->flags); return 0; + error: md_unregister_thread(&log->reclaim_thread); reclaim_thread: + mempool_destroy(log->meta_pool); +out_mempool: + bioset_free(log->bs); +io_bs: + mempool_destroy(log->io_pool); +io_pool: kmem_cache_destroy(log->io_kc); io_kc: kfree(log); @@ -1186,6 +1263,9 @@ io_kc: void r5l_exit_log(struct r5l_log *log) { md_unregister_thread(&log->reclaim_thread); + mempool_destroy(log->meta_pool); + bioset_free(log->bs); + mempool_destroy(log->io_pool); kmem_cache_destroy(log->io_kc); kfree(log); } diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 704ef7fcfbf8..a086014dcd49 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -772,8 +772,6 @@ static void stripe_add_to_batch_list(struct r5conf *conf, struct stripe_head *sh int hash; int dd_idx; - if (!stripe_can_batch(sh)) - return; /* Don't cross chunks, so stripe pd_idx/qd_idx is the same */ tmp_sec = sh->sector; if (!sector_div(tmp_sec, conf->chunk_sectors)) @@ -7141,14 +7139,19 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev) struct disk_info *p = conf->disks + number; print_raid5_conf(conf); - if (test_bit(Journal, &rdev->flags)) { + if (test_bit(Journal, &rdev->flags) && conf->log) { + struct r5l_log *log; /* - * journal disk is not removable, but we need give a chance to - * update superblock of other disks. Otherwise journal disk - * will be considered as 'fresh' + * we can't wait pending write here, as this is called in + * raid5d, wait will deadlock. */ - set_bit(MD_CHANGE_DEVS, &mddev->flags); - return -EINVAL; + if (atomic_read(&mddev->writes_pending)) + return -EBUSY; + log = conf->log; + conf->log = NULL; + synchronize_rcu(); + r5l_exit_log(log); + return 0; } if (rdev == p->rdev) rdevp = &p->rdev; @@ -7212,8 +7215,21 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev) int first = 0; int last = conf->raid_disks - 1; - if (test_bit(Journal, &rdev->flags)) - return -EINVAL; + if (test_bit(Journal, &rdev->flags)) { + char b[BDEVNAME_SIZE]; + if (conf->log) + return -EBUSY; + + rdev->raid_disk = 0; + /* + * The array is in readonly mode if journal is missing, so no + * write requests running. We should be safe + */ + r5l_init_log(conf, rdev); + printk(KERN_INFO"md/raid:%s: using device %s as journal\n", + mdname(mddev), bdevname(rdev->bdev, b)); + return 0; + } if (mddev->recovery_disabled == conf->recovery_disabled) return -EBUSY; diff --git a/drivers/media/common/saa7146/saa7146_video.c b/drivers/media/common/saa7146/saa7146_video.c index d5837be3e8cf..ea2f3bf7368b 100644 --- a/drivers/media/common/saa7146/saa7146_video.c +++ b/drivers/media/common/saa7146/saa7146_video.c @@ -502,7 +502,7 @@ static int vidioc_s_fbuf(struct file *file, void *fh, const struct v4l2_framebuf /* check if overlay is running */ if (IS_OVERLAY_ACTIVE(fh) != 0) { if (vv->video_fh != fh) { - DEB_D("refusing to change framebuffer informations while overlay is active in another open\n"); + DEB_D("refusing to change framebuffer information while overlay is active in another open\n"); return -EBUSY; } } diff --git a/drivers/media/dvb-frontends/m88ds3103.c b/drivers/media/dvb-frontends/m88ds3103.c index feeeb70d841e..ce73a5ec6036 100644 --- a/drivers/media/dvb-frontends/m88ds3103.c +++ b/drivers/media/dvb-frontends/m88ds3103.c @@ -685,7 +685,7 @@ static int m88ds3103_init(struct dvb_frontend *fe) /* request the firmware, this will block and timeout */ ret = request_firmware(&fw, fw_file, &client->dev); if (ret) { - dev_err(&client->dev, "firmare file '%s' not found\n", fw_file); + dev_err(&client->dev, "firmware file '%s' not found\n", fw_file); goto err; } diff --git a/drivers/media/dvb-frontends/si2165.c b/drivers/media/dvb-frontends/si2165.c index 1cf6e52e0105..2b93241d4bc1 100644 --- a/drivers/media/dvb-frontends/si2165.c +++ b/drivers/media/dvb-frontends/si2165.c @@ -541,7 +541,7 @@ static int si2165_upload_firmware(struct si2165_state *state) &offset, block_count); if (ret < 0) { dev_err(&state->i2c->dev, - "%s: firmare could not be uploaded\n", + "%s: firmware could not be uploaded\n", KBUILD_MODNAME); goto error; } @@ -565,7 +565,7 @@ static int si2165_upload_firmware(struct si2165_state *state) if (len != offset) { dev_err(&state->i2c->dev, - "%s: firmare len mismatch %04x != %04x\n", + "%s: firmware len mismatch %04x != %04x\n", KBUILD_MODNAME, len, offset); ret = -EINVAL; goto error; diff --git a/drivers/media/pci/netup_unidvb/netup_unidvb_core.c b/drivers/media/pci/netup_unidvb/netup_unidvb_core.c index 81e1a5e26efb..525ebfefeee8 100644 --- a/drivers/media/pci/netup_unidvb/netup_unidvb_core.c +++ b/drivers/media/pci/netup_unidvb/netup_unidvb_core.c @@ -387,7 +387,7 @@ static int netup_unidvb_dvb_init(struct netup_unidvb_dev *ndev, vb2_dvb_alloc_frontend( &ndev->frontends[num], 3) == NULL) { dev_dbg(&ndev->pci_dev->dev, - "%s(): unable to to alllocate vb2_dvb_frontend\n", + "%s(): unable to allocate vb2_dvb_frontend\n", __func__); return -ENOMEM; } diff --git a/drivers/mfd/88pm80x.c b/drivers/mfd/88pm80x.c index 63445ea6b0bf..3f24ecbe2576 100644 --- a/drivers/mfd/88pm80x.c +++ b/drivers/mfd/88pm80x.c @@ -135,7 +135,7 @@ EXPORT_SYMBOL_GPL(pm80x_deinit); #ifdef CONFIG_PM_SLEEP static int pm80x_suspend(struct device *dev) { - struct i2c_client *client = container_of(dev, struct i2c_client, dev); + struct i2c_client *client = to_i2c_client(dev); struct pm80x_chip *chip = i2c_get_clientdata(client); if (chip && chip->wu_flag) @@ -147,7 +147,7 @@ static int pm80x_suspend(struct device *dev) static int pm80x_resume(struct device *dev) { - struct i2c_client *client = container_of(dev, struct i2c_client, dev); + struct i2c_client *client = to_i2c_client(dev); struct pm80x_chip *chip = i2c_get_clientdata(client); if (chip && chip->wu_flag) diff --git a/drivers/mfd/88pm860x-core.c b/drivers/mfd/88pm860x-core.c index 3269a9990b24..25e1aafae60c 100644 --- a/drivers/mfd/88pm860x-core.c +++ b/drivers/mfd/88pm860x-core.c @@ -705,10 +705,12 @@ int pm8606_osc_disable(struct pm860x_chip *chip, unsigned short client) chip->osc_status); mutex_lock(&chip->osc_lock); - /*Update voting status */ + /* Update voting status */ chip->osc_vote &= ~(client); - /* If reference group is off and this is the last client to release - * - turn off */ + /* + * If reference group is off and this is the last client to release + * - turn off + */ if ((chip->osc_status != PM8606_REF_GP_OSC_OFF) && (chip->osc_vote == REF_GP_NO_CLIENTS)) { chip->osc_status = PM8606_REF_GP_OSC_UNKNOWN; @@ -1218,7 +1220,7 @@ static int pm860x_remove(struct i2c_client *client) #ifdef CONFIG_PM_SLEEP static int pm860x_suspend(struct device *dev) { - struct i2c_client *client = container_of(dev, struct i2c_client, dev); + struct i2c_client *client = to_i2c_client(dev); struct pm860x_chip *chip = i2c_get_clientdata(client); if (device_may_wakeup(dev) && chip->wakeup_flag) @@ -1228,7 +1230,7 @@ static int pm860x_suspend(struct device *dev) static int pm860x_resume(struct device *dev) { - struct i2c_client *client = container_of(dev, struct i2c_client, dev); + struct i2c_client *client = to_i2c_client(dev); struct pm860x_chip *chip = i2c_get_clientdata(client); if (device_may_wakeup(dev) && chip->wakeup_flag) @@ -1265,6 +1267,7 @@ static struct i2c_driver pm860x_driver = { static int __init pm860x_i2c_init(void) { int ret; + ret = i2c_add_driver(&pm860x_driver); if (ret != 0) pr_err("Failed to register 88PM860x I2C driver: %d\n", ret); diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index 4d92df6ef9fe..9ca66de0c1c1 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -211,7 +211,7 @@ config MFD_DA9062 of the device. config MFD_DA9063 - bool "Dialog Semiconductor DA9063 PMIC Support" + tristate "Dialog Semiconductor DA9063 PMIC Support" select MFD_CORE select REGMAP_I2C select REGMAP_IRQ @@ -1370,24 +1370,30 @@ config MFD_ARIZONA bool config MFD_ARIZONA_I2C - tristate "Wolfson Microelectronics Arizona platform with I2C" + tristate "Cirrus Logic/Wolfson Microelectronics Arizona platform with I2C" select MFD_ARIZONA select MFD_CORE select REGMAP_I2C depends on I2C help - Support for the Wolfson Microelectronics Arizona platform audio SoC - core functionality controlled via I2C. + Support for the Cirrus Logic/Wolfson Microelectronics Arizona platform + audio SoC core functionality controlled via I2C. config MFD_ARIZONA_SPI - tristate "Wolfson Microelectronics Arizona platform with SPI" + tristate "Cirrus Logic/Wolfson Microelectronics Arizona platform with SPI" select MFD_ARIZONA select MFD_CORE select REGMAP_SPI depends on SPI_MASTER help - Support for the Wolfson Microelectronics Arizona platform audio SoC - core functionality controlled via I2C. + Support for the Cirrus Logic/Wolfson Microelectronics Arizona platform + audio SoC core functionality controlled via I2C. + +config MFD_CS47L24 + bool "Cirrus Logic CS47L24 and WM1831" + depends on MFD_ARIZONA + help + Support for Cirrus Logic CS47L24 and WM1831 low power audio SoC config MFD_WM5102 bool "Wolfson Microelectronics WM5102" diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile index a8b76b81b467..0f230a6103f8 100644 --- a/drivers/mfd/Makefile +++ b/drivers/mfd/Makefile @@ -51,6 +51,9 @@ endif ifeq ($(CONFIG_MFD_WM8998),y) obj-$(CONFIG_MFD_ARIZONA) += wm8998-tables.o endif +ifeq ($(CONFIG_MFD_CS47L24),y) +obj-$(CONFIG_MFD_ARIZONA) += cs47l24-tables.o +endif obj-$(CONFIG_MFD_WM8400) += wm8400-core.o wm831x-objs := wm831x-core.o wm831x-irq.o wm831x-otp.o wm831x-objs += wm831x-auxadc.o @@ -61,7 +64,8 @@ wm8350-objs := wm8350-core.o wm8350-regmap.o wm8350-gpio.o wm8350-objs += wm8350-irq.o obj-$(CONFIG_MFD_WM8350) += wm8350.o obj-$(CONFIG_MFD_WM8350_I2C) += wm8350-i2c.o -obj-$(CONFIG_MFD_WM8994) += wm8994-core.o wm8994-irq.o wm8994-regmap.o +wm8994-objs := wm8994-core.o wm8994-irq.o wm8994-regmap.o +obj-$(CONFIG_MFD_WM8994) += wm8994.o obj-$(CONFIG_TPS6105X) += tps6105x.o obj-$(CONFIG_TPS65010) += tps65010.o diff --git a/drivers/mfd/aat2870-core.c b/drivers/mfd/aat2870-core.c index 29b6a2d4ac72..3ba19a45f199 100644 --- a/drivers/mfd/aat2870-core.c +++ b/drivers/mfd/aat2870-core.c @@ -373,11 +373,8 @@ static int aat2870_i2c_probe(struct i2c_client *client, aat2870 = devm_kzalloc(&client->dev, sizeof(struct aat2870_data), GFP_KERNEL); - if (!aat2870) { - dev_err(&client->dev, - "Failed to allocate memory for aat2870\n"); + if (!aat2870) return -ENOMEM; - } aat2870->dev = &client->dev; dev_set_drvdata(aat2870->dev, aat2870); diff --git a/drivers/mfd/ab3100-core.c b/drivers/mfd/ab3100-core.c index f0afb44271f8..6a5a98806cb8 100644 --- a/drivers/mfd/ab3100-core.c +++ b/drivers/mfd/ab3100-core.c @@ -381,9 +381,11 @@ static int ab3100_event_registers_startup_state_get(struct device *dev, u8 *event) { struct ab3100 *ab3100 = dev_get_drvdata(dev->parent); + if (!ab3100->startup_events_read) return -EAGAIN; /* Try again later */ memcpy(event, ab3100->startup_events, 3); + return 0; } @@ -858,10 +860,8 @@ static int ab3100_probe(struct i2c_client *client, int i; ab3100 = devm_kzalloc(&client->dev, sizeof(struct ab3100), GFP_KERNEL); - if (!ab3100) { - dev_err(&client->dev, "could not allocate AB3100 device\n"); + if (!ab3100) return -ENOMEM; - } /* Initialize data structure */ mutex_init(&ab3100->access_mutex); @@ -883,20 +883,17 @@ static int ab3100_probe(struct i2c_client *client, for (i = 0; ids[i].id != 0x0; i++) { if (ids[i].id == ab3100->chip_id) { - if (ids[i].name != NULL) { - snprintf(&ab3100->chip_name[0], - sizeof(ab3100->chip_name) - 1, - "AB3100 %s", - ids[i].name); + if (ids[i].name) break; - } else { - dev_err(&client->dev, - "AB3000 is not supported\n"); - goto exit_no_detect; - } + + dev_err(&client->dev, "AB3000 is not supported\n"); + goto exit_no_detect; } } + snprintf(&ab3100->chip_name[0], + sizeof(ab3100->chip_name) - 1, "AB3100 %s", ids[i].name); + if (ids[i].id == 0x0) { dev_err(&client->dev, "unknown analog baseband chip id: 0x%x\n", ab3100->chip_id); diff --git a/drivers/mfd/ab3100-otp.c b/drivers/mfd/ab3100-otp.c index f391c5fee1b0..55b207a4b336 100644 --- a/drivers/mfd/ab3100-otp.c +++ b/drivers/mfd/ab3100-otp.c @@ -188,10 +188,9 @@ static int __init ab3100_otp_probe(struct platform_device *pdev) int i; otp = devm_kzalloc(&pdev->dev, sizeof(struct ab3100_otp), GFP_KERNEL); - if (!otp) { - dev_err(&pdev->dev, "could not allocate AB3100 OTP device\n"); + if (!otp) return -ENOMEM; - } + otp->dev = &pdev->dev; /* Replace platform data coming in with a local struct */ diff --git a/drivers/mfd/ab8500-core.c b/drivers/mfd/ab8500-core.c index fefbe4cfa61d..f3d689176fc2 100644 --- a/drivers/mfd/ab8500-core.c +++ b/drivers/mfd/ab8500-core.c @@ -113,7 +113,7 @@ #define AB8500_SWITCH_OFF_STATUS 0x00 #define AB8500_TURN_ON_STATUS 0x00 -#define AB8505_TURN_ON_STATUS_2 0x04 +#define AB8505_TURN_ON_STATUS_2 0x04 #define AB8500_CH_USBCH_STAT1_REG 0x02 #define VBUS_DET_DBNC100 0x02 @@ -211,7 +211,7 @@ static int set_register_interruptible(struct ab8500 *ab8500, u8 bank, /* * Put the u8 bank and u8 register together into a an u16. * The bank on higher 8 bits and register in lower 8 bits. - * */ + */ u16 addr = ((u16)bank) << 8 | reg; dev_vdbg(ab8500->dev, "wr: addr %#x <= %#x\n", addr, data); @@ -243,8 +243,6 @@ static int get_register_interruptible(struct ab8500 *ab8500, u8 bank, u8 reg, u8 *value) { int ret; - /* put the u8 bank and u8 reg together into a an u16. - * bank on higher 8 bits and reg in lower */ u16 addr = ((u16)bank) << 8 | reg; mutex_lock(&ab8500->lock); @@ -278,8 +276,6 @@ static int mask_and_set_register_interruptible(struct ab8500 *ab8500, u8 bank, u8 reg, u8 bitmask, u8 bitvalues) { int ret; - /* put the u8 bank and u8 reg together into a an u16. - * bank on higher 8 bits and reg in lower */ u16 addr = ((u16)bank) << 8 | reg; mutex_lock(&ab8500->lock); @@ -449,12 +445,12 @@ static void update_latch_offset(u8 *offset, int i) { /* Fix inconsistent ITFromLatch25 bit mapping... */ if (unlikely(*offset == 17)) - *offset = 24; + *offset = 24; /* Fix inconsistent ab8540 bit mapping... */ if (unlikely(*offset == 16)) - *offset = 25; + *offset = 25; if ((i == 3) && (*offset >= 24)) - *offset += 2; + *offset += 2; } static int ab8500_handle_hierarchical_line(struct ab8500 *ab8500, @@ -590,12 +586,12 @@ static int ab8500_irq_init(struct ab8500 *ab8500, struct device_node *np) /* If ->irq_base is zero this will give a linear mapping */ ab8500->domain = irq_domain_add_simple(ab8500->dev->of_node, - num_irqs, 0, - &ab8500_irq_ops, ab8500); + num_irqs, 0, + &ab8500_irq_ops, ab8500); if (!ab8500->domain) { dev_err(ab8500->dev, "Failed to create irqdomain\n"); - return -ENOSYS; + return -ENODEV; } return 0; @@ -609,442 +605,28 @@ int ab8500_suspend(struct ab8500 *ab8500) return 0; } -static struct resource ab8500_gpadc_resources[] = { - { - .name = "HW_CONV_END", - .start = AB8500_INT_GP_HW_ADC_CONV_END, - .end = AB8500_INT_GP_HW_ADC_CONV_END, - .flags = IORESOURCE_IRQ, - }, - { - .name = "SW_CONV_END", - .start = AB8500_INT_GP_SW_ADC_CONV_END, - .end = AB8500_INT_GP_SW_ADC_CONV_END, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct resource ab8505_gpadc_resources[] = { - { - .name = "SW_CONV_END", - .start = AB8500_INT_GP_SW_ADC_CONV_END, - .end = AB8500_INT_GP_SW_ADC_CONV_END, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct resource ab8500_rtc_resources[] = { - { - .name = "60S", - .start = AB8500_INT_RTC_60S, - .end = AB8500_INT_RTC_60S, - .flags = IORESOURCE_IRQ, - }, - { - .name = "ALARM", - .start = AB8500_INT_RTC_ALARM, - .end = AB8500_INT_RTC_ALARM, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct resource ab8540_rtc_resources[] = { - { - .name = "1S", - .start = AB8540_INT_RTC_1S, - .end = AB8540_INT_RTC_1S, - .flags = IORESOURCE_IRQ, - }, - { - .name = "ALARM", - .start = AB8500_INT_RTC_ALARM, - .end = AB8500_INT_RTC_ALARM, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct resource ab8500_poweronkey_db_resources[] = { - { - .name = "ONKEY_DBF", - .start = AB8500_INT_PON_KEY1DB_F, - .end = AB8500_INT_PON_KEY1DB_F, - .flags = IORESOURCE_IRQ, - }, - { - .name = "ONKEY_DBR", - .start = AB8500_INT_PON_KEY1DB_R, - .end = AB8500_INT_PON_KEY1DB_R, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct resource ab8500_av_acc_detect_resources[] = { - { - .name = "ACC_DETECT_1DB_F", - .start = AB8500_INT_ACC_DETECT_1DB_F, - .end = AB8500_INT_ACC_DETECT_1DB_F, - .flags = IORESOURCE_IRQ, - }, - { - .name = "ACC_DETECT_1DB_R", - .start = AB8500_INT_ACC_DETECT_1DB_R, - .end = AB8500_INT_ACC_DETECT_1DB_R, - .flags = IORESOURCE_IRQ, - }, - { - .name = "ACC_DETECT_21DB_F", - .start = AB8500_INT_ACC_DETECT_21DB_F, - .end = AB8500_INT_ACC_DETECT_21DB_F, - .flags = IORESOURCE_IRQ, - }, - { - .name = "ACC_DETECT_21DB_R", - .start = AB8500_INT_ACC_DETECT_21DB_R, - .end = AB8500_INT_ACC_DETECT_21DB_R, - .flags = IORESOURCE_IRQ, - }, - { - .name = "ACC_DETECT_22DB_F", - .start = AB8500_INT_ACC_DETECT_22DB_F, - .end = AB8500_INT_ACC_DETECT_22DB_F, - .flags = IORESOURCE_IRQ, - }, - { - .name = "ACC_DETECT_22DB_R", - .start = AB8500_INT_ACC_DETECT_22DB_R, - .end = AB8500_INT_ACC_DETECT_22DB_R, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct resource ab8500_charger_resources[] = { - { - .name = "MAIN_CH_UNPLUG_DET", - .start = AB8500_INT_MAIN_CH_UNPLUG_DET, - .end = AB8500_INT_MAIN_CH_UNPLUG_DET, - .flags = IORESOURCE_IRQ, - }, - { - .name = "MAIN_CHARGE_PLUG_DET", - .start = AB8500_INT_MAIN_CH_PLUG_DET, - .end = AB8500_INT_MAIN_CH_PLUG_DET, - .flags = IORESOURCE_IRQ, - }, - { - .name = "VBUS_DET_R", - .start = AB8500_INT_VBUS_DET_R, - .end = AB8500_INT_VBUS_DET_R, - .flags = IORESOURCE_IRQ, - }, - { - .name = "VBUS_DET_F", - .start = AB8500_INT_VBUS_DET_F, - .end = AB8500_INT_VBUS_DET_F, - .flags = IORESOURCE_IRQ, - }, - { - .name = "USB_LINK_STATUS", - .start = AB8500_INT_USB_LINK_STATUS, - .end = AB8500_INT_USB_LINK_STATUS, - .flags = IORESOURCE_IRQ, - }, - { - .name = "VBUS_OVV", - .start = AB8500_INT_VBUS_OVV, - .end = AB8500_INT_VBUS_OVV, - .flags = IORESOURCE_IRQ, - }, - { - .name = "USB_CH_TH_PROT_R", - .start = AB8500_INT_USB_CH_TH_PROT_R, - .end = AB8500_INT_USB_CH_TH_PROT_R, - .flags = IORESOURCE_IRQ, - }, - { - .name = "USB_CH_TH_PROT_F", - .start = AB8500_INT_USB_CH_TH_PROT_F, - .end = AB8500_INT_USB_CH_TH_PROT_F, - .flags = IORESOURCE_IRQ, - }, - { - .name = "MAIN_EXT_CH_NOT_OK", - .start = AB8500_INT_MAIN_EXT_CH_NOT_OK, - .end = AB8500_INT_MAIN_EXT_CH_NOT_OK, - .flags = IORESOURCE_IRQ, - }, - { - .name = "MAIN_CH_TH_PROT_R", - .start = AB8500_INT_MAIN_CH_TH_PROT_R, - .end = AB8500_INT_MAIN_CH_TH_PROT_R, - .flags = IORESOURCE_IRQ, - }, - { - .name = "MAIN_CH_TH_PROT_F", - .start = AB8500_INT_MAIN_CH_TH_PROT_F, - .end = AB8500_INT_MAIN_CH_TH_PROT_F, - .flags = IORESOURCE_IRQ, - }, - { - .name = "USB_CHARGER_NOT_OKR", - .start = AB8500_INT_USB_CHARGER_NOT_OKR, - .end = AB8500_INT_USB_CHARGER_NOT_OKR, - .flags = IORESOURCE_IRQ, - }, - { - .name = "CH_WD_EXP", - .start = AB8500_INT_CH_WD_EXP, - .end = AB8500_INT_CH_WD_EXP, - .flags = IORESOURCE_IRQ, - }, - { - .name = "VBUS_CH_DROP_END", - .start = AB8500_INT_VBUS_CH_DROP_END, - .end = AB8500_INT_VBUS_CH_DROP_END, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct resource ab8500_btemp_resources[] = { - { - .name = "BAT_CTRL_INDB", - .start = AB8500_INT_BAT_CTRL_INDB, - .end = AB8500_INT_BAT_CTRL_INDB, - .flags = IORESOURCE_IRQ, - }, - { - .name = "BTEMP_LOW", - .start = AB8500_INT_BTEMP_LOW, - .end = AB8500_INT_BTEMP_LOW, - .flags = IORESOURCE_IRQ, - }, - { - .name = "BTEMP_HIGH", - .start = AB8500_INT_BTEMP_HIGH, - .end = AB8500_INT_BTEMP_HIGH, - .flags = IORESOURCE_IRQ, - }, - { - .name = "BTEMP_LOW_MEDIUM", - .start = AB8500_INT_BTEMP_LOW_MEDIUM, - .end = AB8500_INT_BTEMP_LOW_MEDIUM, - .flags = IORESOURCE_IRQ, - }, - { - .name = "BTEMP_MEDIUM_HIGH", - .start = AB8500_INT_BTEMP_MEDIUM_HIGH, - .end = AB8500_INT_BTEMP_MEDIUM_HIGH, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct resource ab8500_fg_resources[] = { - { - .name = "NCONV_ACCU", - .start = AB8500_INT_CCN_CONV_ACC, - .end = AB8500_INT_CCN_CONV_ACC, - .flags = IORESOURCE_IRQ, - }, - { - .name = "BATT_OVV", - .start = AB8500_INT_BATT_OVV, - .end = AB8500_INT_BATT_OVV, - .flags = IORESOURCE_IRQ, - }, - { - .name = "LOW_BAT_F", - .start = AB8500_INT_LOW_BAT_F, - .end = AB8500_INT_LOW_BAT_F, - .flags = IORESOURCE_IRQ, - }, - { - .name = "LOW_BAT_R", - .start = AB8500_INT_LOW_BAT_R, - .end = AB8500_INT_LOW_BAT_R, - .flags = IORESOURCE_IRQ, - }, - { - .name = "CC_INT_CALIB", - .start = AB8500_INT_CC_INT_CALIB, - .end = AB8500_INT_CC_INT_CALIB, - .flags = IORESOURCE_IRQ, - }, - { - .name = "CCEOC", - .start = AB8500_INT_CCEOC, - .end = AB8500_INT_CCEOC, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct resource ab8500_chargalg_resources[] = {}; - -#ifdef CONFIG_DEBUG_FS -static struct resource ab8500_debug_resources[] = { - { - .name = "IRQ_AB8500", - /* - * Number will be filled in. NOTE: this is deliberately - * not flagged as an IRQ in ordet to avoid remapping using - * the irqdomain in the MFD core, so that this IRQ passes - * unremapped to the debug code. - */ - }, - { - .name = "IRQ_FIRST", - .start = AB8500_INT_MAIN_EXT_CH_NOT_OK, - .end = AB8500_INT_MAIN_EXT_CH_NOT_OK, - .flags = IORESOURCE_IRQ, - }, - { - .name = "IRQ_LAST", - .start = AB8500_INT_XTAL32K_KO, - .end = AB8500_INT_XTAL32K_KO, - .flags = IORESOURCE_IRQ, - }, -}; -#endif - -static struct resource ab8500_usb_resources[] = { - { - .name = "ID_WAKEUP_R", - .start = AB8500_INT_ID_WAKEUP_R, - .end = AB8500_INT_ID_WAKEUP_R, - .flags = IORESOURCE_IRQ, - }, - { - .name = "ID_WAKEUP_F", - .start = AB8500_INT_ID_WAKEUP_F, - .end = AB8500_INT_ID_WAKEUP_F, - .flags = IORESOURCE_IRQ, - }, - { - .name = "VBUS_DET_F", - .start = AB8500_INT_VBUS_DET_F, - .end = AB8500_INT_VBUS_DET_F, - .flags = IORESOURCE_IRQ, - }, - { - .name = "VBUS_DET_R", - .start = AB8500_INT_VBUS_DET_R, - .end = AB8500_INT_VBUS_DET_R, - .flags = IORESOURCE_IRQ, - }, - { - .name = "USB_LINK_STATUS", - .start = AB8500_INT_USB_LINK_STATUS, - .end = AB8500_INT_USB_LINK_STATUS, - .flags = IORESOURCE_IRQ, - }, - { - .name = "USB_ADP_PROBE_PLUG", - .start = AB8500_INT_ADP_PROBE_PLUG, - .end = AB8500_INT_ADP_PROBE_PLUG, - .flags = IORESOURCE_IRQ, - }, - { - .name = "USB_ADP_PROBE_UNPLUG", - .start = AB8500_INT_ADP_PROBE_UNPLUG, - .end = AB8500_INT_ADP_PROBE_UNPLUG, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct resource ab8505_iddet_resources[] = { - { - .name = "KeyDeglitch", - .start = AB8505_INT_KEYDEGLITCH, - .end = AB8505_INT_KEYDEGLITCH, - .flags = IORESOURCE_IRQ, - }, - { - .name = "KP", - .start = AB8505_INT_KP, - .end = AB8505_INT_KP, - .flags = IORESOURCE_IRQ, - }, - { - .name = "IKP", - .start = AB8505_INT_IKP, - .end = AB8505_INT_IKP, - .flags = IORESOURCE_IRQ, - }, - { - .name = "IKR", - .start = AB8505_INT_IKR, - .end = AB8505_INT_IKR, - .flags = IORESOURCE_IRQ, - }, - { - .name = "KeyStuck", - .start = AB8505_INT_KEYSTUCK, - .end = AB8505_INT_KEYSTUCK, - .flags = IORESOURCE_IRQ, - }, - { - .name = "VBUS_DET_R", - .start = AB8500_INT_VBUS_DET_R, - .end = AB8500_INT_VBUS_DET_R, - .flags = IORESOURCE_IRQ, - }, - { - .name = "VBUS_DET_F", - .start = AB8500_INT_VBUS_DET_F, - .end = AB8500_INT_VBUS_DET_F, - .flags = IORESOURCE_IRQ, - }, - { - .name = "ID_DET_PLUGR", - .start = AB8500_INT_ID_DET_PLUGR, - .end = AB8500_INT_ID_DET_PLUGR, - .flags = IORESOURCE_IRQ, - }, - { - .name = "ID_DET_PLUGF", - .start = AB8500_INT_ID_DET_PLUGF, - .end = AB8500_INT_ID_DET_PLUGF, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct resource ab8500_temp_resources[] = { - { - .name = "ABX500_TEMP_WARM", - .start = AB8500_INT_TEMP_WARM, - .end = AB8500_INT_TEMP_WARM, - .flags = IORESOURCE_IRQ, - }, -}; - static const struct mfd_cell ab8500_bm_devs[] = { { .name = "ab8500-charger", .of_compatible = "stericsson,ab8500-charger", - .num_resources = ARRAY_SIZE(ab8500_charger_resources), - .resources = ab8500_charger_resources, .platform_data = &ab8500_bm_data, .pdata_size = sizeof(ab8500_bm_data), }, { .name = "ab8500-btemp", .of_compatible = "stericsson,ab8500-btemp", - .num_resources = ARRAY_SIZE(ab8500_btemp_resources), - .resources = ab8500_btemp_resources, .platform_data = &ab8500_bm_data, .pdata_size = sizeof(ab8500_bm_data), }, { .name = "ab8500-fg", .of_compatible = "stericsson,ab8500-fg", - .num_resources = ARRAY_SIZE(ab8500_fg_resources), - .resources = ab8500_fg_resources, .platform_data = &ab8500_bm_data, .pdata_size = sizeof(ab8500_bm_data), }, { .name = "ab8500-chargalg", .of_compatible = "stericsson,ab8500-chargalg", - .num_resources = ARRAY_SIZE(ab8500_chargalg_resources), - .resources = ab8500_chargalg_resources, .platform_data = &ab8500_bm_data, .pdata_size = sizeof(ab8500_bm_data), }, @@ -1055,8 +637,6 @@ static const struct mfd_cell ab8500_devs[] = { { .name = "ab8500-debug", .of_compatible = "stericsson,ab8500-debug", - .num_resources = ARRAY_SIZE(ab8500_debug_resources), - .resources = ab8500_debug_resources, }, #endif { @@ -1078,27 +658,19 @@ static const struct mfd_cell ab8500_devs[] = { { .name = "ab8500-gpadc", .of_compatible = "stericsson,ab8500-gpadc", - .num_resources = ARRAY_SIZE(ab8500_gpadc_resources), - .resources = ab8500_gpadc_resources, }, { .name = "ab8500-rtc", .of_compatible = "stericsson,ab8500-rtc", - .num_resources = ARRAY_SIZE(ab8500_rtc_resources), - .resources = ab8500_rtc_resources, }, { .name = "ab8500-acc-det", .of_compatible = "stericsson,ab8500-acc-det", - .num_resources = ARRAY_SIZE(ab8500_av_acc_detect_resources), - .resources = ab8500_av_acc_detect_resources, }, { .name = "ab8500-poweron-key", .of_compatible = "stericsson,ab8500-poweron-key", - .num_resources = ARRAY_SIZE(ab8500_poweronkey_db_resources), - .resources = ab8500_poweronkey_db_resources, }, { .name = "ab8500-pwm", @@ -1126,14 +698,10 @@ static const struct mfd_cell ab8500_devs[] = { { .name = "abx500-temp", .of_compatible = "stericsson,abx500-temp", - .num_resources = ARRAY_SIZE(ab8500_temp_resources), - .resources = ab8500_temp_resources, }, { .name = "ab8500-usb", .of_compatible = "stericsson,ab8500-usb", - .num_resources = ARRAY_SIZE(ab8500_usb_resources), - .resources = ab8500_usb_resources, }, { .name = "ab8500-codec", @@ -1145,8 +713,6 @@ static const struct mfd_cell ab9540_devs[] = { #ifdef CONFIG_DEBUG_FS { .name = "ab8500-debug", - .num_resources = ARRAY_SIZE(ab8500_debug_resources), - .resources = ab8500_debug_resources, }, #endif { @@ -1165,23 +731,15 @@ static const struct mfd_cell ab9540_devs[] = { { .name = "ab8500-gpadc", .of_compatible = "stericsson,ab8500-gpadc", - .num_resources = ARRAY_SIZE(ab8500_gpadc_resources), - .resources = ab8500_gpadc_resources, }, { .name = "ab8500-rtc", - .num_resources = ARRAY_SIZE(ab8500_rtc_resources), - .resources = ab8500_rtc_resources, }, { .name = "ab8500-acc-det", - .num_resources = ARRAY_SIZE(ab8500_av_acc_detect_resources), - .resources = ab8500_av_acc_detect_resources, }, { .name = "ab8500-poweron-key", - .num_resources = ARRAY_SIZE(ab8500_poweronkey_db_resources), - .resources = ab8500_poweronkey_db_resources, }, { .name = "ab8500-pwm", @@ -1189,8 +747,6 @@ static const struct mfd_cell ab9540_devs[] = { }, { .name = "abx500-temp", - .num_resources = ARRAY_SIZE(ab8500_temp_resources), - .resources = ab8500_temp_resources, }, { .name = "pinctrl-ab9540", @@ -1198,16 +754,12 @@ static const struct mfd_cell ab9540_devs[] = { }, { .name = "ab9540-usb", - .num_resources = ARRAY_SIZE(ab8500_usb_resources), - .resources = ab8500_usb_resources, }, { .name = "ab9540-codec", }, { .name = "ab-iddet", - .num_resources = ARRAY_SIZE(ab8505_iddet_resources), - .resources = ab8505_iddet_resources, }, }; @@ -1216,8 +768,6 @@ static const struct mfd_cell ab8505_devs[] = { #ifdef CONFIG_DEBUG_FS { .name = "ab8500-debug", - .num_resources = ARRAY_SIZE(ab8500_debug_resources), - .resources = ab8500_debug_resources, }, #endif { @@ -1233,23 +783,15 @@ static const struct mfd_cell ab8505_devs[] = { { .name = "ab8500-gpadc", .of_compatible = "stericsson,ab8500-gpadc", - .num_resources = ARRAY_SIZE(ab8505_gpadc_resources), - .resources = ab8505_gpadc_resources, }, { .name = "ab8500-rtc", - .num_resources = ARRAY_SIZE(ab8500_rtc_resources), - .resources = ab8500_rtc_resources, }, { .name = "ab8500-acc-det", - .num_resources = ARRAY_SIZE(ab8500_av_acc_detect_resources), - .resources = ab8500_av_acc_detect_resources, }, { .name = "ab8500-poweron-key", - .num_resources = ARRAY_SIZE(ab8500_poweronkey_db_resources), - .resources = ab8500_poweronkey_db_resources, }, { .name = "ab8500-pwm", @@ -1260,16 +802,12 @@ static const struct mfd_cell ab8505_devs[] = { }, { .name = "ab8500-usb", - .num_resources = ARRAY_SIZE(ab8500_usb_resources), - .resources = ab8500_usb_resources, }, { .name = "ab8500-codec", }, { .name = "ab-iddet", - .num_resources = ARRAY_SIZE(ab8505_iddet_resources), - .resources = ab8505_iddet_resources, }, }; @@ -1277,8 +815,6 @@ static const struct mfd_cell ab8540_devs[] = { #ifdef CONFIG_DEBUG_FS { .name = "ab8500-debug", - .num_resources = ARRAY_SIZE(ab8500_debug_resources), - .resources = ab8500_debug_resources, }, #endif { @@ -1297,18 +833,12 @@ static const struct mfd_cell ab8540_devs[] = { { .name = "ab8500-gpadc", .of_compatible = "stericsson,ab8500-gpadc", - .num_resources = ARRAY_SIZE(ab8505_gpadc_resources), - .resources = ab8505_gpadc_resources, }, { .name = "ab8500-acc-det", - .num_resources = ARRAY_SIZE(ab8500_av_acc_detect_resources), - .resources = ab8500_av_acc_detect_resources, }, { .name = "ab8500-poweron-key", - .num_resources = ARRAY_SIZE(ab8500_poweronkey_db_resources), - .resources = ab8500_poweronkey_db_resources, }, { .name = "ab8500-pwm", @@ -1316,24 +846,18 @@ static const struct mfd_cell ab8540_devs[] = { }, { .name = "abx500-temp", - .num_resources = ARRAY_SIZE(ab8500_temp_resources), - .resources = ab8500_temp_resources, }, { .name = "pinctrl-ab8540", }, { .name = "ab8540-usb", - .num_resources = ARRAY_SIZE(ab8500_usb_resources), - .resources = ab8500_usb_resources, }, { .name = "ab8540-codec", }, { .name = "ab-iddet", - .num_resources = ARRAY_SIZE(ab8505_iddet_resources), - .resources = ab8505_iddet_resources, }, }; @@ -1341,8 +865,6 @@ static const struct mfd_cell ab8540_cut1_devs[] = { { .name = "ab8500-rtc", .of_compatible = "stericsson,ab8500-rtc", - .num_resources = ARRAY_SIZE(ab8500_rtc_resources), - .resources = ab8500_rtc_resources, }, }; @@ -1350,8 +872,6 @@ static const struct mfd_cell ab8540_cut2_devs[] = { { .name = "ab8540-rtc", .of_compatible = "stericsson,ab8540-rtc", - .num_resources = ARRAY_SIZE(ab8540_rtc_resources), - .resources = ab8540_rtc_resources, }, }; @@ -1549,7 +1069,7 @@ static struct attribute_group ab9540_attr_group = { static int ab8500_probe(struct platform_device *pdev) { - static const char *switch_off_status[] = { + static const char * const switch_off_status[] = { "Swoff bit programming", "Thermal protection activation", "Vbat lower then BattOk falling threshold", @@ -1558,7 +1078,7 @@ static int ab8500_probe(struct platform_device *pdev) "Battery level lower than power on reset threshold", "Power on key 1 pressed longer than 10 seconds", "DB8500 thermal shutdown"}; - static const char *turn_on_status[] = { + static const char * const turn_on_status[] = { "Battery rising (Vbat)", "Power On Key 1 dbF", "Power On Key 2 dbF", @@ -1750,12 +1270,6 @@ static int ab8500_probe(struct platform_device *pdev) if (ret) return ret; -#ifdef CONFIG_DEBUG_FS - /* Pass to debugfs */ - ab8500_debug_resources[0].start = ab8500->irq; - ab8500_debug_resources[0].end = ab8500->irq; -#endif - if (is_ab9540(ab8500)) ret = mfd_add_devices(ab8500->dev, 0, ab9540_devs, ARRAY_SIZE(ab9540_devs), NULL, diff --git a/drivers/mfd/ab8500-debugfs.c b/drivers/mfd/ab8500-debugfs.c index 0236cd7cdce4..69d9fffe5b5c 100644 --- a/drivers/mfd/ab8500-debugfs.c +++ b/drivers/mfd/ab8500-debugfs.c @@ -242,8 +242,10 @@ static struct ab8500_prcmu_ranges ab8500_debug_ranges[AB8500_NUM_BANKS] = { .first = 0x40, .last = 0x44, }, - /* 0x80-0x8B is SIM registers and should - * not be accessed from here */ + /* + * 0x80-0x8B are SIM registers and should + * not be accessed from here + */ }, }, [AB8500_USB] = { @@ -587,8 +589,10 @@ static struct ab8500_prcmu_ranges ab8505_debug_ranges[AB8500_NUM_BANKS] = { .first = 0x40, .last = 0x48, }, - /* 0x80-0x8B is SIM registers and should - * not be accessed from here */ + /* + * 0x80-0x8B are SIM registers and should + * not be accessed from here + */ }, }, [AB8500_USB] = { @@ -1306,8 +1310,10 @@ static int ab8500_registers_print(struct device *dev, u32 bank, if (s) { seq_printf(s, " [0x%02X/0x%02X]: 0x%02X\n", bank, reg, value); - /* Error is not returned here since - * the output is wanted in any case */ + /* + * Error is not returned here since + * the output is wanted in any case + */ if (seq_has_overflowed(s)) return 0; } else { @@ -2740,10 +2746,9 @@ static ssize_t hwreg_common_write(char *b, struct hwreg_cfg *cfg, *cfg = loc; #ifdef ABB_HWREG_DEBUG - pr_warn("HWREG request: %s, %s,\n" - " addr=0x%08X, mask=0x%X, shift=%d" "value=0x%X\n", - (write) ? "write" : "read", - REG_FMT_DEC(cfg) ? "decimal" : "hexa", + pr_warn("HWREG request: %s, %s,\n", (write) ? "write" : "read", + REG_FMT_DEC(cfg) ? "decimal" : "hexa"); + pr_warn(" addr=0x%08X, mask=0x%X, shift=%d" "value=0x%X\n", cfg->addr, cfg->mask, cfg->shift, val); #endif diff --git a/drivers/mfd/ab8500-gpadc.c b/drivers/mfd/ab8500-gpadc.c index c51c1b188d64..97dcadc8fa8b 100644 --- a/drivers/mfd/ab8500-gpadc.c +++ b/drivers/mfd/ab8500-gpadc.c @@ -49,61 +49,61 @@ * OTP register offsets * Bank : 0x15 */ -#define AB8500_GPADC_CAL_1 0x0F -#define AB8500_GPADC_CAL_2 0x10 -#define AB8500_GPADC_CAL_3 0x11 -#define AB8500_GPADC_CAL_4 0x12 -#define AB8500_GPADC_CAL_5 0x13 -#define AB8500_GPADC_CAL_6 0x14 -#define AB8500_GPADC_CAL_7 0x15 +#define AB8500_GPADC_CAL_1 0x0F +#define AB8500_GPADC_CAL_2 0x10 +#define AB8500_GPADC_CAL_3 0x11 +#define AB8500_GPADC_CAL_4 0x12 +#define AB8500_GPADC_CAL_5 0x13 +#define AB8500_GPADC_CAL_6 0x14 +#define AB8500_GPADC_CAL_7 0x15 /* New calibration for 8540 */ #define AB8540_GPADC_OTP4_REG_7 0x38 #define AB8540_GPADC_OTP4_REG_6 0x39 #define AB8540_GPADC_OTP4_REG_5 0x3A /* gpadc constants */ -#define EN_VINTCORE12 0x04 -#define EN_VTVOUT 0x02 -#define EN_GPADC 0x01 -#define DIS_GPADC 0x00 -#define AVG_1 0x00 -#define AVG_4 0x20 -#define AVG_8 0x40 -#define AVG_16 0x60 -#define ADC_SW_CONV 0x04 -#define EN_ICHAR 0x80 -#define BTEMP_PULL_UP 0x08 -#define EN_BUF 0x40 -#define DIS_ZERO 0x00 -#define GPADC_BUSY 0x01 -#define EN_FALLING 0x10 -#define EN_TRIG_EDGE 0x02 -#define EN_VBIAS_XTAL_TEMP 0x02 +#define EN_VINTCORE12 0x04 +#define EN_VTVOUT 0x02 +#define EN_GPADC 0x01 +#define DIS_GPADC 0x00 +#define AVG_1 0x00 +#define AVG_4 0x20 +#define AVG_8 0x40 +#define AVG_16 0x60 +#define ADC_SW_CONV 0x04 +#define EN_ICHAR 0x80 +#define BTEMP_PULL_UP 0x08 +#define EN_BUF 0x40 +#define DIS_ZERO 0x00 +#define GPADC_BUSY 0x01 +#define EN_FALLING 0x10 +#define EN_TRIG_EDGE 0x02 +#define EN_VBIAS_XTAL_TEMP 0x02 /* GPADC constants from AB8500 spec, UM0836 */ -#define ADC_RESOLUTION 1024 -#define ADC_CH_BTEMP_MIN 0 -#define ADC_CH_BTEMP_MAX 1350 -#define ADC_CH_DIETEMP_MIN 0 -#define ADC_CH_DIETEMP_MAX 1350 -#define ADC_CH_CHG_V_MIN 0 -#define ADC_CH_CHG_V_MAX 20030 -#define ADC_CH_ACCDET2_MIN 0 -#define ADC_CH_ACCDET2_MAX 2500 -#define ADC_CH_VBAT_MIN 2300 -#define ADC_CH_VBAT_MAX 4800 -#define ADC_CH_CHG_I_MIN 0 -#define ADC_CH_CHG_I_MAX 1500 -#define ADC_CH_BKBAT_MIN 0 -#define ADC_CH_BKBAT_MAX 3200 +#define ADC_RESOLUTION 1024 +#define ADC_CH_BTEMP_MIN 0 +#define ADC_CH_BTEMP_MAX 1350 +#define ADC_CH_DIETEMP_MIN 0 +#define ADC_CH_DIETEMP_MAX 1350 +#define ADC_CH_CHG_V_MIN 0 +#define ADC_CH_CHG_V_MAX 20030 +#define ADC_CH_ACCDET2_MIN 0 +#define ADC_CH_ACCDET2_MAX 2500 +#define ADC_CH_VBAT_MIN 2300 +#define ADC_CH_VBAT_MAX 4800 +#define ADC_CH_CHG_I_MIN 0 +#define ADC_CH_CHG_I_MAX 1500 +#define ADC_CH_BKBAT_MIN 0 +#define ADC_CH_BKBAT_MAX 3200 /* GPADC constants from AB8540 spec */ -#define ADC_CH_IBAT_MIN (-6000) /* mA range measured by ADC for ibat*/ -#define ADC_CH_IBAT_MAX 6000 -#define ADC_CH_IBAT_MIN_V (-60) /* mV range measured by ADC for ibat*/ -#define ADC_CH_IBAT_MAX_V 60 -#define IBAT_VDROP_L (-56) /* mV */ -#define IBAT_VDROP_H 56 +#define ADC_CH_IBAT_MIN (-6000) /* mA range measured by ADC for ibat */ +#define ADC_CH_IBAT_MAX 6000 +#define ADC_CH_IBAT_MIN_V (-60) /* mV range measured by ADC for ibat */ +#define ADC_CH_IBAT_MAX_V 60 +#define IBAT_VDROP_L (-56) /* mV */ +#define IBAT_VDROP_H 56 /* This is used to not lose precision when dividing to get gain and offset */ #define CALIB_SCALE 1000 @@ -179,7 +179,7 @@ struct ab8500_gpadc *ab8500_gpadc_get(char *name) list_for_each_entry(gpadc, &ab8500_gpadc_list, node) { if (!strcmp(name, dev_name(gpadc->dev))) - return gpadc; + return gpadc; } return ERR_PTR(-ENOENT); @@ -315,11 +315,12 @@ int ab8500_gpadc_sw_hw_convert(struct ab8500_gpadc *gpadc, u8 channel, ad_value = ab8500_gpadc_read_raw(gpadc, channel, avg_sample, trig_edge, trig_timer, conv_type); -/* On failure retry a second time */ + + /* On failure retry a second time */ if (ad_value < 0) ad_value = ab8500_gpadc_read_raw(gpadc, channel, avg_sample, trig_edge, trig_timer, conv_type); -if (ad_value < 0) { + if (ad_value < 0) { dev_err(gpadc->dev, "GPADC raw value failed ch: %d\n", channel); return ad_value; @@ -327,8 +328,9 @@ if (ad_value < 0) { voltage = ab8500_gpadc_ad_to_voltage(gpadc, channel, ad_value); if (voltage < 0) - dev_err(gpadc->dev, "GPADC to voltage conversion failed ch:" - " %d AD: 0x%x\n", channel, ad_value); + dev_err(gpadc->dev, + "GPADC to voltage conversion failed ch: %d AD: 0x%x\n", + channel, ad_value); return voltage; } @@ -348,10 +350,9 @@ EXPORT_SYMBOL(ab8500_gpadc_sw_hw_convert); int ab8500_gpadc_read_raw(struct ab8500_gpadc *gpadc, u8 channel, u8 avg_sample, u8 trig_edge, u8 trig_timer, u8 conv_type) { - int raw_data; - raw_data = ab8500_gpadc_double_read_raw(gpadc, channel, - avg_sample, trig_edge, trig_timer, conv_type, NULL); - return raw_data; + return ab8500_gpadc_double_read_raw(gpadc, channel, avg_sample, + trig_edge, trig_timer, conv_type, + NULL); } int ab8500_gpadc_double_read_raw(struct ab8500_gpadc *gpadc, u8 channel, @@ -388,7 +389,7 @@ int ab8500_gpadc_double_read_raw(struct ab8500_gpadc *gpadc, u8 channel, goto out; if (!(val & GPADC_BUSY)) break; - msleep(10); + msleep(20); } while (++looplimit < 10); if (looplimit >= 10 && (val & GPADC_BUSY)) { dev_err(gpadc->dev, "gpadc_conversion: GPADC busy"); @@ -421,8 +422,7 @@ int ab8500_gpadc_double_read_raw(struct ab8500_gpadc *gpadc, u8 channel, val_reg1 |= EN_TRIG_EDGE; if (trig_edge) val_reg1 |= EN_FALLING; - } - else + } else ret = abx500_set_register_interruptible(gpadc->dev, AB8500_GPADC, AB8500_GPADC_CTRL2_REG, val); if (ret < 0) { @@ -449,7 +449,7 @@ int ab8500_gpadc_double_read_raw(struct ab8500_gpadc *gpadc, u8 channel, * remove when hardware will be availible */ delay_min = 1000; /* Delay in micro seconds */ - delay_max = 10000; /* large range to optimise sleep mode */ + delay_max = 10000; /* large range optimises sleepmode */ break; } /* Intentional fallthrough */ @@ -785,9 +785,10 @@ static void ab8500_gpadc_read_calibration_data(struct ab8500_gpadc *gpadc) << CALIB_SHIFT_IBAT) / (ADC_CH_IBAT_MAX_V - ADC_CH_IBAT_MIN_V); - gpadc->cal_data[ADC_INPUT_IBAT].gain = V_gain * V2A_gain; - gpadc->cal_data[ADC_INPUT_IBAT].offset = V_offset * - V2A_gain + V2A_offset; + gpadc->cal_data[ADC_INPUT_IBAT].gain = + V_gain * V2A_gain; + gpadc->cal_data[ADC_INPUT_IBAT].offset = + V_offset * V2A_gain + V2A_offset; } else { gpadc->cal_data[ADC_INPUT_IBAT].gain = 0; } @@ -923,11 +924,10 @@ static int ab8500_gpadc_probe(struct platform_device *pdev) int ret = 0; struct ab8500_gpadc *gpadc; - gpadc = devm_kzalloc(&pdev->dev, sizeof(struct ab8500_gpadc), GFP_KERNEL); - if (!gpadc) { - dev_err(&pdev->dev, "Error: No memory\n"); + gpadc = devm_kzalloc(&pdev->dev, + sizeof(struct ab8500_gpadc), GFP_KERNEL); + if (!gpadc) return -ENOMEM; - } gpadc->irq_sw = platform_get_irq_byname(pdev, "SW_CONV_END"); if (gpadc->irq_sw < 0) @@ -1072,18 +1072,19 @@ void ab8540_gpadc_get_otp(struct ab8500_gpadc *gpadc, *vmain_h = gpadc->cal_data[ADC_INPUT_VMAIN].otp_calib_hi; *btemp_l = gpadc->cal_data[ADC_INPUT_BTEMP].otp_calib_lo; *btemp_h = gpadc->cal_data[ADC_INPUT_BTEMP].otp_calib_hi; - *vbat_l = gpadc->cal_data[ADC_INPUT_VBAT].otp_calib_lo; - *vbat_h = gpadc->cal_data[ADC_INPUT_VBAT].otp_calib_hi; - *ibat_l = gpadc->cal_data[ADC_INPUT_IBAT].otp_calib_lo; - *ibat_h = gpadc->cal_data[ADC_INPUT_IBAT].otp_calib_hi; - return ; + *vbat_l = gpadc->cal_data[ADC_INPUT_VBAT].otp_calib_lo; + *vbat_h = gpadc->cal_data[ADC_INPUT_VBAT].otp_calib_hi; + *ibat_l = gpadc->cal_data[ADC_INPUT_IBAT].otp_calib_lo; + *ibat_h = gpadc->cal_data[ADC_INPUT_IBAT].otp_calib_hi; } subsys_initcall_sync(ab8500_gpadc_init); module_exit(ab8500_gpadc_exit); MODULE_LICENSE("GPL v2"); -MODULE_AUTHOR("Arun R Murthy, Daniel Willerud, Johan Palsson," - "M'boumba Cedric Madianga"); +MODULE_AUTHOR("Arun R Murthy"); +MODULE_AUTHOR("Daniel Willerud"); +MODULE_AUTHOR("Johan Palsson"); +MODULE_AUTHOR("M'boumba Cedric Madianga"); MODULE_ALIAS("platform:ab8500_gpadc"); MODULE_DESCRIPTION("AB8500 GPADC driver"); diff --git a/drivers/mfd/ab8500-sysctrl.c b/drivers/mfd/ab8500-sysctrl.c index 0d1825696153..b9f0010309f9 100644 --- a/drivers/mfd/ab8500-sysctrl.c +++ b/drivers/mfd/ab8500-sysctrl.c @@ -27,7 +27,7 @@ static void ab8500_power_off(void) { sigset_t old; sigset_t all; - static char *pss[] = {"ab8500_ac", "pm2301", "ab8500_usb"}; + static const char * const pss[] = {"ab8500_ac", "pm2301", "ab8500_usb"}; int i; bool charger_present = false; union power_supply_propval val; @@ -68,10 +68,9 @@ static void ab8500_power_off(void) ret = power_supply_get_property(psy, POWER_SUPPLY_PROP_TECHNOLOGY, &val); if (!ret && val.intval != POWER_SUPPLY_TECHNOLOGY_UNKNOWN) { - printk(KERN_INFO - "Charger \"%s\" is connected with known battery." - " Rebooting.\n", - pss[i]); + pr_info("Charger '%s' is connected with known battery", + pss[i]); + pr_info(" - Rebooting.\n"); machine_restart("charging"); } power_supply_put(psy); @@ -161,8 +160,8 @@ static int ab8500_sysctrl_probe(struct platform_device *pdev) pdata->initial_req_buf_config[j]); if (ret < 0) { dev_err(&pdev->dev, - "unable to set sysClkReq%dRfClkBuf: " - "%d\n", j + 1, ret); + "Can't set sysClkReq%dRfClkBuf: %d\n", + j + 1, ret); } } } diff --git a/drivers/mfd/adp5520.c b/drivers/mfd/adp5520.c index ae88654595dc..d817f202da5b 100644 --- a/drivers/mfd/adp5520.c +++ b/drivers/mfd/adp5520.c @@ -9,10 +9,10 @@ * * Derived from da903x: * Copyright (C) 2008 Compulab, Ltd. - * Mike Rapoport <mike@compulab.co.il> + * Mike Rapoport <mike@compulab.co.il> * * Copyright (C) 2006-2008 Marvell International Ltd. - * Eric Miao <eric.miao@marvell.com> + * Eric Miao <eric.miao@marvell.com> * * Licensed under the GPL-2 or later. */ @@ -355,7 +355,7 @@ static struct i2c_driver adp5520_driver = { }, .probe = adp5520_probe, .remove = adp5520_remove, - .id_table = adp5520_id, + .id_table = adp5520_id, }; module_i2c_driver(adp5520_driver); diff --git a/drivers/mfd/arizona-core.c b/drivers/mfd/arizona-core.c index d474732cc65c..5319f252790b 100644 --- a/drivers/mfd/arizona-core.c +++ b/drivers/mfd/arizona-core.c @@ -238,7 +238,7 @@ static int arizona_poll_reg(struct arizona *arizona, if ((val & mask) == target) return 0; - msleep(1); + usleep_range(1000, 5000); } dev_err(arizona->dev, "Polling reg %u timed out: %x\n", reg, val); @@ -279,14 +279,14 @@ static void arizona_disable_reset(struct arizona *arizona) case WM5110: case WM8280: /* Meet requirements for minimum reset duration */ - msleep(5); + usleep_range(5000, 10000); break; default: break; } gpio_set_value_cansleep(arizona->pdata.reset, 1); - msleep(1); + usleep_range(1000, 5000); } } @@ -598,6 +598,12 @@ static int arizona_runtime_resume(struct device *dev) goto err; } break; + case WM1831: + case CS47L24: + ret = arizona_wait_for_boot(arizona); + if (ret != 0) + goto err; + break; default: ret = arizona_wait_for_boot(arizona); if (ret != 0) @@ -682,6 +688,9 @@ static int arizona_runtime_suspend(struct device *dev) } } break; + case WM1831: + case CS47L24: + break; default: jd_active = arizona_is_jack_det_active(arizona); if (jd_active < 0) @@ -852,6 +861,16 @@ static int arizona_of_get_core_pdata(struct arizona *arizona) count++; } + count = 0; + of_property_for_each_u32(arizona->dev->of_node, "wlf,out-mono", prop, + cur, val) { + if (count == ARRAY_SIZE(pdata->out_mono)) + break; + + pdata->out_mono[count] = !!val; + count++; + } + return 0; } @@ -862,6 +881,8 @@ const struct of_device_id arizona_of_match[] = { { .compatible = "wlf,wm8997", .data = (void *)WM8997 }, { .compatible = "wlf,wm8998", .data = (void *)WM8998 }, { .compatible = "wlf,wm1814", .data = (void *)WM1814 }, + { .compatible = "wlf,wm1831", .data = (void *)WM1831 }, + { .compatible = "cirrus,cs47l24", .data = (void *)CS47L24 }, {}, }; EXPORT_SYMBOL_GPL(arizona_of_match); @@ -919,6 +940,23 @@ static const struct mfd_cell wm5110_devs[] = { }, }; +static const char * const cs47l24_supplies[] = { + "MICVDD", + "CPVDD", + "SPKVDD", +}; + +static const struct mfd_cell cs47l24_devs[] = { + { .name = "arizona-gpio" }, + { .name = "arizona-haptics" }, + { .name = "arizona-pwm" }, + { + .name = "cs47l24-codec", + .parent_supplies = cs47l24_supplies, + .num_parent_supplies = ARRAY_SIZE(cs47l24_supplies), + }, +}; + static const char * const wm8997_supplies[] = { "MICVDD", "DBVDD2", @@ -963,7 +1001,7 @@ static const struct mfd_cell wm8998_devs[] = { int arizona_dev_init(struct arizona *arizona) { struct device *dev = arizona->dev; - const char *type_name; + const char *type_name = NULL; unsigned int reg, val, mask; int (*apply_patch)(struct arizona *) = NULL; const struct mfd_cell *subdevs = NULL; @@ -987,6 +1025,8 @@ int arizona_dev_init(struct arizona *arizona) case WM8997: case WM8998: case WM1814: + case WM1831: + case CS47L24: for (i = 0; i < ARRAY_SIZE(wm5102_core_supplies); i++) arizona->core_supplies[i].supply = wm5102_core_supplies[i]; @@ -1001,11 +1041,18 @@ int arizona_dev_init(struct arizona *arizona) /* Mark DCVDD as external, LDO1 driver will clear if internal */ arizona->external_dcvdd = true; - ret = mfd_add_devices(arizona->dev, -1, early_devs, - ARRAY_SIZE(early_devs), NULL, 0, NULL); - if (ret != 0) { - dev_err(dev, "Failed to add early children: %d\n", ret); - return ret; + switch (arizona->type) { + case WM1831: + case CS47L24: + break; /* No LDO1 regulator */ + default: + ret = mfd_add_devices(arizona->dev, -1, early_devs, + ARRAY_SIZE(early_devs), NULL, 0, NULL); + if (ret != 0) { + dev_err(dev, "Failed to add early children: %d\n", ret); + return ret; + } + break; } ret = devm_regulator_bulk_get(dev, arizona->num_core_supplies, @@ -1069,6 +1116,7 @@ int arizona_dev_init(struct arizona *arizona) case 0x5102: case 0x5110: case 0x6349: + case 0x6363: case 0x8997: break; default: @@ -1084,7 +1132,7 @@ int arizona_dev_init(struct arizona *arizona) goto err_reset; } - msleep(1); + usleep_range(1000, 5000); } /* Ensure device startup is complete */ @@ -1167,6 +1215,30 @@ int arizona_dev_init(struct arizona *arizona) n_subdevs = ARRAY_SIZE(wm5110_devs); } break; + case 0x6363: + if (IS_ENABLED(CONFIG_MFD_CS47L24)) { + switch (arizona->type) { + case CS47L24: + type_name = "CS47L24"; + break; + + case WM1831: + type_name = "WM1831"; + break; + + default: + dev_warn(arizona->dev, + "CS47L24 registered as %d\n", + arizona->type); + arizona->type = CS47L24; + break; + } + + apply_patch = cs47l24_patch; + subdevs = cs47l24_devs; + n_subdevs = ARRAY_SIZE(cs47l24_devs); + } + break; case 0x8997: if (IS_ENABLED(CONFIG_MFD_WM8997)) { type_name = "WM8997"; diff --git a/drivers/mfd/arizona-i2c.c b/drivers/mfd/arizona-i2c.c index 4e3afd1861fc..5fe12961cfe5 100644 --- a/drivers/mfd/arizona-i2c.c +++ b/drivers/mfd/arizona-i2c.c @@ -88,7 +88,9 @@ static int arizona_i2c_probe(struct i2c_client *i2c, static int arizona_i2c_remove(struct i2c_client *i2c) { struct arizona *arizona = dev_get_drvdata(&i2c->dev); + arizona_dev_exit(arizona); + return 0; } diff --git a/drivers/mfd/arizona-irq.c b/drivers/mfd/arizona-irq.c index 3d425e93ce84..5fef014920a3 100644 --- a/drivers/mfd/arizona-irq.c +++ b/drivers/mfd/arizona-irq.c @@ -30,11 +30,13 @@ static int arizona_map_irq(struct arizona *arizona, int irq) { int ret; - ret = regmap_irq_get_virq(arizona->aod_irq_chip, irq); - if (ret < 0) - ret = regmap_irq_get_virq(arizona->irq_chip, irq); + if (arizona->aod_irq_chip) { + ret = regmap_irq_get_virq(arizona->aod_irq_chip, irq); + if (ret >= 0) + return ret; + } - return ret; + return regmap_irq_get_virq(arizona->irq_chip, irq); } int arizona_request_irq(struct arizona *arizona, int irq, char *name, @@ -107,8 +109,8 @@ static irqreturn_t arizona_irq_thread(int irq, void *data) do { poll = false; - /* Always handle the AoD domain */ - handle_nested_irq(irq_find_mapping(arizona->virq, 0)); + if (arizona->aod_irq_chip) + handle_nested_irq(irq_find_mapping(arizona->virq, 0)); /* * Check if one of the main interrupts is asserted and only @@ -219,6 +221,15 @@ int arizona_irq_init(struct arizona *arizona) arizona->ctrlif_error = false; break; #endif +#ifdef CONFIG_MFD_CS47L24 + case WM1831: + case CS47L24: + aod = NULL; + irq = &cs47l24_irq; + + arizona->ctrlif_error = false; + break; +#endif #ifdef CONFIG_MFD_WM8997 case WM8997: aod = &wm8997_aod; @@ -291,13 +302,16 @@ int arizona_irq_init(struct arizona *arizona) goto err; } - ret = regmap_add_irq_chip(arizona->regmap, - irq_create_mapping(arizona->virq, 0), - IRQF_ONESHOT, 0, aod, - &arizona->aod_irq_chip); - if (ret != 0) { - dev_err(arizona->dev, "Failed to add AOD IRQs: %d\n", ret); - goto err_domain; + if (aod) { + ret = regmap_add_irq_chip(arizona->regmap, + irq_create_mapping(arizona->virq, 0), + IRQF_ONESHOT, 0, aod, + &arizona->aod_irq_chip); + if (ret != 0) { + dev_err(arizona->dev, + "Failed to add AOD IRQs: %d\n", ret); + goto err; + } } ret = regmap_add_irq_chip(arizona->regmap, @@ -309,30 +323,6 @@ int arizona_irq_init(struct arizona *arizona) goto err_aod; } - /* Make sure the boot done IRQ is unmasked for resumes */ - i = arizona_map_irq(arizona, ARIZONA_IRQ_BOOT_DONE); - ret = request_threaded_irq(i, NULL, arizona_boot_done, IRQF_ONESHOT, - "Boot done", arizona); - if (ret != 0) { - dev_err(arizona->dev, "Failed to request boot done %d: %d\n", - arizona->irq, ret); - goto err_boot_done; - } - - /* Handle control interface errors in the core */ - if (arizona->ctrlif_error) { - i = arizona_map_irq(arizona, ARIZONA_IRQ_CTRLIF_ERR); - ret = request_threaded_irq(i, NULL, arizona_ctrlif_err, - IRQF_ONESHOT, - "Control interface error", arizona); - if (ret != 0) { - dev_err(arizona->dev, - "Failed to request CTRLIF_ERR %d: %d\n", - arizona->irq, ret); - goto err_ctrlif; - } - } - /* Used to emulate edge trigger and to work around broken pinmux */ if (arizona->pdata.irq_gpio) { if (gpio_to_irq(arizona->pdata.irq_gpio) != arizona->irq) { @@ -362,21 +352,42 @@ int arizona_irq_init(struct arizona *arizona) goto err_main_irq; } + /* Make sure the boot done IRQ is unmasked for resumes */ + i = arizona_map_irq(arizona, ARIZONA_IRQ_BOOT_DONE); + ret = request_threaded_irq(i, NULL, arizona_boot_done, IRQF_ONESHOT, + "Boot done", arizona); + if (ret != 0) { + dev_err(arizona->dev, "Failed to request boot done %d: %d\n", + arizona->irq, ret); + goto err_boot_done; + } + + /* Handle control interface errors in the core */ + if (arizona->ctrlif_error) { + i = arizona_map_irq(arizona, ARIZONA_IRQ_CTRLIF_ERR); + ret = request_threaded_irq(i, NULL, arizona_ctrlif_err, + IRQF_ONESHOT, + "Control interface error", arizona); + if (ret != 0) { + dev_err(arizona->dev, + "Failed to request CTRLIF_ERR %d: %d\n", + arizona->irq, ret); + goto err_ctrlif; + } + } + return 0; -err_main_irq: - if (arizona->ctrlif_error) - free_irq(arizona_map_irq(arizona, ARIZONA_IRQ_CTRLIF_ERR), - arizona); err_ctrlif: free_irq(arizona_map_irq(arizona, ARIZONA_IRQ_BOOT_DONE), arizona); err_boot_done: + free_irq(arizona->irq, arizona); +err_main_irq: regmap_del_irq_chip(irq_create_mapping(arizona->virq, 1), arizona->irq_chip); err_aod: regmap_del_irq_chip(irq_create_mapping(arizona->virq, 0), arizona->aod_irq_chip); -err_domain: err: return ret; } diff --git a/drivers/mfd/arizona-spi.c b/drivers/mfd/arizona-spi.c index befbc89bfd34..5c1ccdeb9b70 100644 --- a/drivers/mfd/arizona-spi.c +++ b/drivers/mfd/arizona-spi.c @@ -46,6 +46,11 @@ static int arizona_spi_probe(struct spi_device *spi) if (IS_ENABLED(CONFIG_MFD_WM5110)) regmap_config = &wm5110_spi_regmap; break; + case WM1831: + case CS47L24: + if (IS_ENABLED(CONFIG_MFD_CS47L24)) + regmap_config = &cs47l24_spi_regmap; + break; default: dev_err(&spi->dev, "Unknown device type %ld\n", type); return -EINVAL; @@ -89,6 +94,8 @@ static const struct spi_device_id arizona_spi_ids[] = { { "wm5102", WM5102 }, { "wm5110", WM5110 }, { "wm8280", WM8280 }, + { "wm1831", WM1831 }, + { "cs47l24", CS47L24 }, { }, }; MODULE_DEVICE_TABLE(spi, arizona_spi_ids); diff --git a/drivers/mfd/arizona.h b/drivers/mfd/arizona.h index 3af12e938f57..198e9cea77f9 100644 --- a/drivers/mfd/arizona.h +++ b/drivers/mfd/arizona.h @@ -25,6 +25,8 @@ extern const struct regmap_config wm5102_spi_regmap; extern const struct regmap_config wm5110_i2c_regmap; extern const struct regmap_config wm5110_spi_regmap; +extern const struct regmap_config cs47l24_spi_regmap; + extern const struct regmap_config wm8997_i2c_regmap; extern const struct regmap_config wm8998_i2c_regmap; @@ -40,6 +42,8 @@ extern const struct regmap_irq_chip wm5110_aod; extern const struct regmap_irq_chip wm5110_irq; extern const struct regmap_irq_chip wm5110_revd_irq; +extern const struct regmap_irq_chip cs47l24_irq; + extern const struct regmap_irq_chip wm8997_aod; extern const struct regmap_irq_chip wm8997_irq; diff --git a/drivers/mfd/as3711.c b/drivers/mfd/as3711.c index d001f7e238f5..94d67a6e1eb7 100644 --- a/drivers/mfd/as3711.c +++ b/drivers/mfd/as3711.c @@ -136,17 +136,13 @@ static int as3711_i2c_probe(struct i2c_client *client, } else { pdata = devm_kzalloc(&client->dev, sizeof(*pdata), GFP_KERNEL); - if (!pdata) { - dev_err(&client->dev, "Failed to allocate pdata\n"); + if (!pdata) return -ENOMEM; - } } as3711 = devm_kzalloc(&client->dev, sizeof(struct as3711), GFP_KERNEL); - if (!as3711) { - dev_err(&client->dev, "Memory allocation failed\n"); + if (!as3711) return -ENOMEM; - } as3711->dev = &client->dev; i2c_set_clientdata(client, as3711); @@ -157,7 +153,8 @@ static int as3711_i2c_probe(struct i2c_client *client, as3711->regmap = devm_regmap_init_i2c(client, &as3711_regmap_config); if (IS_ERR(as3711->regmap)) { ret = PTR_ERR(as3711->regmap); - dev_err(&client->dev, "regmap initialization failed: %d\n", ret); + dev_err(&client->dev, + "regmap initialization failed: %d\n", ret); return ret; } @@ -172,12 +169,19 @@ static int as3711_i2c_probe(struct i2c_client *client, return -ENODEV; dev_info(as3711->dev, "AS3711 detected: %x:%x\n", id1, id2); - /* We can reuse as3711_subdevs[], it will be copied in mfd_add_devices() */ + /* + * We can reuse as3711_subdevs[], + * it will be copied in mfd_add_devices() + */ if (pdata) { - as3711_subdevs[AS3711_REGULATOR].platform_data = &pdata->regulator; - as3711_subdevs[AS3711_REGULATOR].pdata_size = sizeof(pdata->regulator); - as3711_subdevs[AS3711_BACKLIGHT].platform_data = &pdata->backlight; - as3711_subdevs[AS3711_BACKLIGHT].pdata_size = sizeof(pdata->backlight); + as3711_subdevs[AS3711_REGULATOR].platform_data = + &pdata->regulator; + as3711_subdevs[AS3711_REGULATOR].pdata_size = + sizeof(pdata->regulator); + as3711_subdevs[AS3711_BACKLIGHT].platform_data = + &pdata->backlight; + as3711_subdevs[AS3711_BACKLIGHT].pdata_size = + sizeof(pdata->backlight); } else { as3711_subdevs[AS3711_REGULATOR].platform_data = NULL; as3711_subdevs[AS3711_REGULATOR].pdata_size = 0; diff --git a/drivers/mfd/as3722.c b/drivers/mfd/as3722.c index 924ea90494ae..e1f597f97f86 100644 --- a/drivers/mfd/as3722.c +++ b/drivers/mfd/as3722.c @@ -405,6 +405,8 @@ static int as3722_i2c_probe(struct i2c_client *i2c, goto scrub; } + device_init_wakeup(as3722->dev, true); + dev_dbg(as3722->dev, "AS3722 core driver initialized successfully\n"); return 0; @@ -422,6 +424,29 @@ static int as3722_i2c_remove(struct i2c_client *i2c) return 0; } +static int __maybe_unused as3722_i2c_suspend(struct device *dev) +{ + struct as3722 *as3722 = dev_get_drvdata(dev); + + if (device_may_wakeup(dev)) + enable_irq_wake(as3722->chip_irq); + disable_irq(as3722->chip_irq); + + return 0; +} + +static int __maybe_unused as3722_i2c_resume(struct device *dev) +{ + struct as3722 *as3722 = dev_get_drvdata(dev); + + enable_irq(as3722->chip_irq); + + if (device_may_wakeup(dev)) + disable_irq_wake(as3722->chip_irq); + + return 0; +} + static const struct of_device_id as3722_of_match[] = { { .compatible = "ams,as3722", }, {}, @@ -434,10 +459,15 @@ static const struct i2c_device_id as3722_i2c_id[] = { }; MODULE_DEVICE_TABLE(i2c, as3722_i2c_id); +static const struct dev_pm_ops as3722_pm_ops = { + SET_SYSTEM_SLEEP_PM_OPS(as3722_i2c_suspend, as3722_i2c_resume) +}; + static struct i2c_driver as3722_i2c_driver = { .driver = { .name = "as3722", .of_match_table = as3722_of_match, + .pm = &as3722_pm_ops, }, .probe = as3722_i2c_probe, .remove = as3722_i2c_remove, diff --git a/drivers/mfd/asic3.c b/drivers/mfd/asic3.c index a726f01e3b02..4dca6bc61f5b 100644 --- a/drivers/mfd/asic3.c +++ b/drivers/mfd/asic3.c @@ -167,7 +167,6 @@ static void asic3_irq_demux(struct irq_desc *desc) base = ASIC3_GPIO_A_BASE + bank * ASIC3_GPIO_BASE_INCR; - spin_lock_irqsave(&asic->lock, flags); istat = asic3_read_register(asic, base + @@ -502,7 +501,8 @@ static int asic3_gpio_get(struct gpio_chip *chip, return -EINVAL; } - return asic3_read_register(asic, gpio_base + ASIC3_GPIO_STATUS) & mask; + return !!(asic3_read_register(asic, + gpio_base + ASIC3_GPIO_STATUS) & mask); } static void asic3_gpio_set(struct gpio_chip *chip, @@ -536,8 +536,6 @@ static void asic3_gpio_set(struct gpio_chip *chip, asic3_write_register(asic, gpio_base + ASIC3_GPIO_OUT, out_reg); spin_unlock_irqrestore(&asic->lock, flags); - - return; } static int asic3_gpio_to_irq(struct gpio_chip *chip, unsigned offset) @@ -665,18 +663,18 @@ static int ds1wm_enable(struct platform_device *pdev) asic3_clk_enable(asic, &asic->clocks[ASIC3_CLOCK_EX0]); asic3_clk_enable(asic, &asic->clocks[ASIC3_CLOCK_EX1]); asic3_clk_enable(asic, &asic->clocks[ASIC3_CLOCK_OWM]); - msleep(1); + usleep_range(1000, 5000); /* Reset and enable DS1WM */ asic3_set_register(asic, ASIC3_OFFSET(EXTCF, RESET), ASIC3_EXTCF_OWM_RESET, 1); - msleep(1); + usleep_range(1000, 5000); asic3_set_register(asic, ASIC3_OFFSET(EXTCF, RESET), ASIC3_EXTCF_OWM_RESET, 0); - msleep(1); + usleep_range(1000, 5000); asic3_set_register(asic, ASIC3_OFFSET(EXTCF, SELECT), ASIC3_EXTCF_OWM_EN, 1); - msleep(1); + usleep_range(1000, 5000); return 0; } @@ -757,7 +755,7 @@ static int asic3_mmc_enable(struct platform_device *pdev) * when HCLK is stopped. */ asic3_clk_enable(asic, &asic->clocks[ASIC3_CLOCK_EX1]); - msleep(1); + usleep_range(1000, 5000); /* HCLK 24.576 MHz, BCLK 12.288 MHz: */ asic3_write_register(asic, ASIC3_OFFSET(CLOCK, SEL), @@ -765,7 +763,7 @@ static int asic3_mmc_enable(struct platform_device *pdev) asic3_clk_enable(asic, &asic->clocks[ASIC3_CLOCK_SD_HOST]); asic3_clk_enable(asic, &asic->clocks[ASIC3_CLOCK_SD_BUS]); - msleep(1); + usleep_range(1000, 5000); asic3_set_register(asic, ASIC3_OFFSET(EXTCF, SELECT), ASIC3_EXTCF_SD_MEM_ENABLE, 1); @@ -841,7 +839,7 @@ static int asic3_leds_suspend(struct platform_device *pdev) struct asic3 *asic = dev_get_drvdata(pdev->dev.parent); while (asic3_gpio_get(&asic->gpio, ASIC3_GPIO(C, cell->id)) != 0) - msleep(1); + usleep_range(1000, 5000); asic3_clk_disable(asic, &asic->clocks[clock_ledn[cell->id]]); @@ -900,8 +898,8 @@ static int __init asic3_mfd_probe(struct platform_device *pdev, /* MMC */ if (mem_sdio) { - asic->tmio_cnf = ioremap((ASIC3_SD_CONFIG_BASE >> asic->bus_shift) + - mem_sdio->start, + asic->tmio_cnf = ioremap((ASIC3_SD_CONFIG_BASE >> + asic->bus_shift) + mem_sdio->start, ASIC3_SD_CONFIG_SIZE >> asic->bus_shift); if (!asic->tmio_cnf) { ret = -ENOMEM; @@ -962,10 +960,8 @@ static int __init asic3_probe(struct platform_device *pdev) asic = devm_kzalloc(&pdev->dev, sizeof(struct asic3), GFP_KERNEL); - if (asic == NULL) { - printk(KERN_ERR "kzalloc failed\n"); + if (!asic) return -ENOMEM; - } spin_lock_init(&asic->lock); platform_set_drvdata(pdev, asic); @@ -1074,7 +1070,9 @@ static struct platform_driver asic3_device_driver = { static int __init asic3_init(void) { int retval = 0; + retval = platform_driver_probe(&asic3_device_driver, asic3_probe); + return retval; } diff --git a/drivers/mfd/cros_ec_i2c.c b/drivers/mfd/cros_ec_i2c.c index 56a466469664..9f70de1e4c70 100644 --- a/drivers/mfd/cros_ec_i2c.c +++ b/drivers/mfd/cros_ec_i2c.c @@ -292,7 +292,7 @@ static int cros_ec_i2c_probe(struct i2c_client *client, struct cros_ec_device *ec_dev = NULL; int err; - ec_dev = devm_kzalloc(dev, sizeof(*ec_dev), GFP_KERNEL); + ec_dev = devm_kzalloc(dev, sizeof(*ec_dev), GFP_KERNEL); if (!ec_dev) return -ENOMEM; diff --git a/drivers/mfd/cros_ec_spi.c b/drivers/mfd/cros_ec_spi.c index 6a0f6ec67c6b..ebe9b9477cb2 100644 --- a/drivers/mfd/cros_ec_spi.c +++ b/drivers/mfd/cros_ec_spi.c @@ -113,7 +113,7 @@ static int terminate_request(struct cros_ec_device *ec_dev) trans.delay_usecs = ec_spi->end_of_msg_delay; spi_message_add_tail(&trans, &msg); - ret = spi_sync(ec_spi->spi, &msg); + ret = spi_sync_locked(ec_spi->spi, &msg); /* Reset end-of-response timer */ ec_spi->last_transfer_ns = ktime_get_ns(); @@ -147,7 +147,7 @@ static int receive_n_bytes(struct cros_ec_device *ec_dev, u8 *buf, int n) spi_message_init(&msg); spi_message_add_tail(&trans, &msg); - ret = spi_sync(ec_spi->spi, &msg); + ret = spi_sync_locked(ec_spi->spi, &msg); if (ret < 0) dev_err(ec_dev->dev, "spi transfer failed: %d\n", ret); @@ -175,7 +175,7 @@ static int cros_ec_spi_receive_packet(struct cros_ec_device *ec_dev, unsigned long deadline; int todo; - BUG_ON(EC_MSG_PREAMBLE_COUNT > ec_dev->din_size); + BUG_ON(ec_dev->din_size < EC_MSG_PREAMBLE_COUNT); /* Receive data until we see the header byte */ deadline = jiffies + msecs_to_jiffies(EC_MSG_DEADLINE_MS); @@ -283,7 +283,7 @@ static int cros_ec_spi_receive_response(struct cros_ec_device *ec_dev, unsigned long deadline; int todo; - BUG_ON(EC_MSG_PREAMBLE_COUNT > ec_dev->din_size); + BUG_ON(ec_dev->din_size < EC_MSG_PREAMBLE_COUNT); /* Receive data until we see the header byte */ deadline = jiffies + msecs_to_jiffies(EC_MSG_DEADLINE_MS); @@ -391,10 +391,10 @@ static int cros_ec_pkt_xfer_spi(struct cros_ec_device *ec_dev, } rx_buf = kzalloc(len, GFP_KERNEL); - if (!rx_buf) { - ret = -ENOMEM; - goto exit; - } + if (!rx_buf) + return -ENOMEM; + + spi_bus_lock(ec_spi->spi->master); /* * Leave a gap between CS assertion and clocking of data to allow the @@ -414,7 +414,7 @@ static int cros_ec_pkt_xfer_spi(struct cros_ec_device *ec_dev, trans.len = len; trans.cs_change = 1; spi_message_add_tail(&trans, &msg); - ret = spi_sync(ec_spi->spi, &msg); + ret = spi_sync_locked(ec_spi->spi, &msg); /* Get the response */ if (!ret) { @@ -440,6 +440,9 @@ static int cros_ec_pkt_xfer_spi(struct cros_ec_device *ec_dev, } final_ret = terminate_request(ec_dev); + + spi_bus_unlock(ec_spi->spi->master); + if (!ret) ret = final_ret; if (ret < 0) @@ -520,10 +523,10 @@ static int cros_ec_cmd_xfer_spi(struct cros_ec_device *ec_dev, } rx_buf = kzalloc(len, GFP_KERNEL); - if (!rx_buf) { - ret = -ENOMEM; - goto exit; - } + if (!rx_buf) + return -ENOMEM; + + spi_bus_lock(ec_spi->spi->master); /* Transmit phase - send our message */ debug_packet(ec_dev->dev, "out", ec_dev->dout, len); @@ -534,7 +537,7 @@ static int cros_ec_cmd_xfer_spi(struct cros_ec_device *ec_dev, trans.cs_change = 1; spi_message_init(&msg); spi_message_add_tail(&trans, &msg); - ret = spi_sync(ec_spi->spi, &msg); + ret = spi_sync_locked(ec_spi->spi, &msg); /* Get the response */ if (!ret) { @@ -560,6 +563,9 @@ static int cros_ec_cmd_xfer_spi(struct cros_ec_device *ec_dev, } final_ret = terminate_request(ec_dev); + + spi_bus_unlock(ec_spi->spi->master); + if (!ret) ret = final_ret; if (ret < 0) diff --git a/drivers/mfd/cs47l24-tables.c b/drivers/mfd/cs47l24-tables.c new file mode 100644 index 000000000000..870800657594 --- /dev/null +++ b/drivers/mfd/cs47l24-tables.c @@ -0,0 +1,1629 @@ +/* + * Data tables for CS47L24 codec + * + * Copyright 2015 Cirrus Logic, Inc. + * + * Author: Richard Fitzgerald <rf@opensource.wolfsonmicro.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 + * published by the Free Software Foundation. + */ + +#include <linux/module.h> + +#include <linux/mfd/arizona/core.h> +#include <linux/mfd/arizona/registers.h> +#include <linux/device.h> + +#include "arizona.h" + +#define CS47L24_NUM_ISR 5 + +static const struct reg_sequence cs47l24_reva_patch[] = { + { 0x80, 0x3 }, + { 0x27C, 0x0010 }, + { 0x221, 0x0070 }, + { 0x80, 0x0 }, +}; + +int cs47l24_patch(struct arizona *arizona) +{ + return regmap_register_patch(arizona->regmap, + cs47l24_reva_patch, + ARRAY_SIZE(cs47l24_reva_patch)); +} +EXPORT_SYMBOL_GPL(cs47l24_patch); + +static const struct regmap_irq cs47l24_irqs[ARIZONA_NUM_IRQ] = { + [ARIZONA_IRQ_GP2] = { .reg_offset = 0, .mask = ARIZONA_GP2_EINT1 }, + [ARIZONA_IRQ_GP1] = { .reg_offset = 0, .mask = ARIZONA_GP1_EINT1 }, + + [ARIZONA_IRQ_DSP3_RAM_RDY] = { + .reg_offset = 1, .mask = ARIZONA_DSP3_RAM_RDY_EINT1 + }, + [ARIZONA_IRQ_DSP2_RAM_RDY] = { + .reg_offset = 1, .mask = ARIZONA_DSP2_RAM_RDY_EINT1 + }, + [ARIZONA_IRQ_DSP_IRQ8] = { + .reg_offset = 1, .mask = ARIZONA_DSP_IRQ8_EINT1 + }, + [ARIZONA_IRQ_DSP_IRQ7] = { + .reg_offset = 1, .mask = ARIZONA_DSP_IRQ7_EINT1 + }, + [ARIZONA_IRQ_DSP_IRQ6] = { + .reg_offset = 1, .mask = ARIZONA_DSP_IRQ6_EINT1 + }, + [ARIZONA_IRQ_DSP_IRQ5] = { + .reg_offset = 1, .mask = ARIZONA_DSP_IRQ5_EINT1 + }, + [ARIZONA_IRQ_DSP_IRQ4] = { + .reg_offset = 1, .mask = ARIZONA_DSP_IRQ4_EINT1 + }, + [ARIZONA_IRQ_DSP_IRQ3] = { + .reg_offset = 1, .mask = ARIZONA_DSP_IRQ3_EINT1 + }, + [ARIZONA_IRQ_DSP_IRQ2] = { + .reg_offset = 1, .mask = ARIZONA_DSP_IRQ2_EINT1 + }, + [ARIZONA_IRQ_DSP_IRQ1] = { + .reg_offset = 1, .mask = ARIZONA_DSP_IRQ1_EINT1 + }, + + [ARIZONA_IRQ_SPK_OVERHEAT_WARN] = { + .reg_offset = 2, .mask = ARIZONA_SPK_OVERHEAT_WARN_EINT1 + }, + [ARIZONA_IRQ_SPK_OVERHEAT] = { + .reg_offset = 2, .mask = ARIZONA_SPK_OVERHEAT_EINT1 + }, + [ARIZONA_IRQ_WSEQ_DONE] = { + .reg_offset = 2, .mask = ARIZONA_WSEQ_DONE_EINT1 + }, + [ARIZONA_IRQ_DRC2_SIG_DET] = { + .reg_offset = 2, .mask = ARIZONA_DRC2_SIG_DET_EINT1 + }, + [ARIZONA_IRQ_DRC1_SIG_DET] = { + .reg_offset = 2, .mask = ARIZONA_DRC1_SIG_DET_EINT1 + }, + [ARIZONA_IRQ_ASRC2_LOCK] = { + .reg_offset = 2, .mask = ARIZONA_ASRC2_LOCK_EINT1 + }, + [ARIZONA_IRQ_ASRC1_LOCK] = { + .reg_offset = 2, .mask = ARIZONA_ASRC1_LOCK_EINT1 + }, + [ARIZONA_IRQ_UNDERCLOCKED] = { + .reg_offset = 2, .mask = ARIZONA_UNDERCLOCKED_EINT1 + }, + [ARIZONA_IRQ_OVERCLOCKED] = { + .reg_offset = 2, .mask = ARIZONA_OVERCLOCKED_EINT1 + }, + [ARIZONA_IRQ_FLL2_LOCK] = { + .reg_offset = 2, .mask = ARIZONA_FLL2_LOCK_EINT1 + }, + [ARIZONA_IRQ_FLL1_LOCK] = { + .reg_offset = 2, .mask = ARIZONA_FLL1_LOCK_EINT1 + }, + [ARIZONA_IRQ_CLKGEN_ERR] = { + .reg_offset = 2, .mask = ARIZONA_CLKGEN_ERR_EINT1 + }, + [ARIZONA_IRQ_CLKGEN_ERR_ASYNC] = { + .reg_offset = 2, .mask = ARIZONA_CLKGEN_ERR_ASYNC_EINT1 + }, + + [ARIZONA_IRQ_CTRLIF_ERR] = { + .reg_offset = 3, .mask = ARIZONA_V2_CTRLIF_ERR_EINT1 + }, + [ARIZONA_IRQ_MIXER_DROPPED_SAMPLES] = { + .reg_offset = 3, .mask = ARIZONA_V2_MIXER_DROPPED_SAMPLE_EINT1 + }, + [ARIZONA_IRQ_ASYNC_CLK_ENA_LOW] = { + .reg_offset = 3, .mask = ARIZONA_V2_ASYNC_CLK_ENA_LOW_EINT1 + }, + [ARIZONA_IRQ_SYSCLK_ENA_LOW] = { + .reg_offset = 3, .mask = ARIZONA_V2_SYSCLK_ENA_LOW_EINT1 + }, + [ARIZONA_IRQ_ISRC1_CFG_ERR] = { + .reg_offset = 3, .mask = ARIZONA_V2_ISRC1_CFG_ERR_EINT1 + }, + [ARIZONA_IRQ_ISRC2_CFG_ERR] = { + .reg_offset = 3, .mask = ARIZONA_V2_ISRC2_CFG_ERR_EINT1 + }, + [ARIZONA_IRQ_ISRC3_CFG_ERR] = { + .reg_offset = 3, .mask = ARIZONA_V2_ISRC3_CFG_ERR_EINT1 + }, + [ARIZONA_IRQ_HP1R_DONE] = { + .reg_offset = 3, .mask = ARIZONA_HP1R_DONE_EINT1 + }, + [ARIZONA_IRQ_HP1L_DONE] = { + .reg_offset = 3, .mask = ARIZONA_HP1L_DONE_EINT1 + }, + + [ARIZONA_IRQ_BOOT_DONE] = { + .reg_offset = 4, .mask = ARIZONA_BOOT_DONE_EINT1 + }, + [ARIZONA_IRQ_ASRC_CFG_ERR] = { + .reg_offset = 4, .mask = ARIZONA_V2_ASRC_CFG_ERR_EINT1 + }, + [ARIZONA_IRQ_FLL2_CLOCK_OK] = { + .reg_offset = 4, .mask = ARIZONA_FLL2_CLOCK_OK_EINT1 + }, + [ARIZONA_IRQ_FLL1_CLOCK_OK] = { + .reg_offset = 4, .mask = ARIZONA_FLL1_CLOCK_OK_EINT1 + }, + + [ARIZONA_IRQ_DSP_SHARED_WR_COLL] = { + .reg_offset = 5, .mask = ARIZONA_DSP_SHARED_WR_COLL_EINT1 + }, + [ARIZONA_IRQ_SPK_SHUTDOWN] = { + .reg_offset = 5, .mask = ARIZONA_SPK_SHUTDOWN_EINT1 + }, + [ARIZONA_IRQ_SPK1R_SHORT] = { + .reg_offset = 5, .mask = ARIZONA_SPK1R_SHORT_EINT1 + }, + [ARIZONA_IRQ_SPK1L_SHORT] = { + .reg_offset = 5, .mask = ARIZONA_SPK1L_SHORT_EINT1 + }, + [ARIZONA_IRQ_HP1R_SC_POS] = { + .reg_offset = 5, .mask = ARIZONA_HP1R_SC_POS_EINT1 + }, + [ARIZONA_IRQ_HP1L_SC_POS] = { + .reg_offset = 5, .mask = ARIZONA_HP1L_SC_POS_EINT1 + }, +}; + +const struct regmap_irq_chip cs47l24_irq = { + .name = "cs47l24 IRQ", + .status_base = ARIZONA_INTERRUPT_STATUS_1, + .mask_base = ARIZONA_INTERRUPT_STATUS_1_MASK, + .ack_base = ARIZONA_INTERRUPT_STATUS_1, + .num_regs = 6, + .irqs = cs47l24_irqs, + .num_irqs = ARRAY_SIZE(cs47l24_irqs), +}; +EXPORT_SYMBOL_GPL(cs47l24_irq); + +static const struct reg_default cs47l24_reg_default[] = { + { 0x00000008, 0x0019 }, /* R8 - Ctrl IF SPI CFG 1 */ + { 0x00000020, 0x0000 }, /* R32 - Tone Generator 1 */ + { 0x00000021, 0x1000 }, /* R33 - Tone Generator 2 */ + { 0x00000022, 0x0000 }, /* R34 - Tone Generator 3 */ + { 0x00000023, 0x1000 }, /* R35 - Tone Generator 4 */ + { 0x00000024, 0x0000 }, /* R36 - Tone Generator 5 */ + { 0x00000030, 0x0000 }, /* R48 - PWM Drive 1 */ + { 0x00000031, 0x0100 }, /* R49 - PWM Drive 2 */ + { 0x00000032, 0x0100 }, /* R50 - PWM Drive 3 */ + { 0x00000041, 0x0000 }, /* R65 - Sequence control */ + { 0x00000061, 0x01FF }, /* R97 - Sample Rate Sequence Select 1 */ + { 0x00000062, 0x01FF }, /* R98 - Sample Rate Sequence Select 2 */ + { 0x00000063, 0x01FF }, /* R99 - Sample Rate Sequence Select 3 */ + { 0x00000064, 0x01FF }, /* R100 - Sample Rate Sequence Select 4 */ + { 0x00000070, 0x0000 }, /* R112 - Comfort Noise Generator */ + { 0x00000090, 0x0000 }, /* R144 - Haptics Control 1 */ + { 0x00000091, 0x7FFF }, /* R145 - Haptics Control 2 */ + { 0x00000092, 0x0000 }, /* R146 - Haptics phase 1 intensity */ + { 0x00000093, 0x0000 }, /* R147 - Haptics phase 1 duration */ + { 0x00000094, 0x0000 }, /* R148 - Haptics phase 2 intensity */ + { 0x00000095, 0x0000 }, /* R149 - Haptics phase 2 duration */ + { 0x00000096, 0x0000 }, /* R150 - Haptics phase 3 intensity */ + { 0x00000097, 0x0000 }, /* R151 - Haptics phase 3 duration */ + { 0x00000100, 0x0002 }, /* R256 - Clock 32k 1 */ + { 0x00000101, 0x0504 }, /* R257 - System Clock 1 */ + { 0x00000102, 0x0011 }, /* R258 - Sample rate 1 */ + { 0x00000103, 0x0011 }, /* R259 - Sample rate 2 */ + { 0x00000104, 0x0011 }, /* R260 - Sample rate 3 */ + { 0x00000112, 0x0305 }, /* R274 - Async clock 1 */ + { 0x00000113, 0x0011 }, /* R275 - Async sample rate 1 */ + { 0x00000114, 0x0011 }, /* R276 - Async sample rate 2 */ + { 0x00000149, 0x0000 }, /* R329 - Output system clock */ + { 0x0000014A, 0x0000 }, /* R330 - Output async clock */ + { 0x00000152, 0x0000 }, /* R338 - Rate Estimator 1 */ + { 0x00000153, 0x0000 }, /* R339 - Rate Estimator 2 */ + { 0x00000154, 0x0000 }, /* R340 - Rate Estimator 3 */ + { 0x00000155, 0x0000 }, /* R341 - Rate Estimator 4 */ + { 0x00000156, 0x0000 }, /* R342 - Rate Estimator 5 */ + { 0x00000171, 0x0002 }, /* R369 - FLL1 Control 1 */ + { 0x00000172, 0x0008 }, /* R370 - FLL1 Control 2 */ + { 0x00000173, 0x0018 }, /* R371 - FLL1 Control 3 */ + { 0x00000174, 0x007D }, /* R372 - FLL1 Control 4 */ + { 0x00000175, 0x0006 }, /* R373 - FLL1 Control 5 */ + { 0x00000176, 0x0000 }, /* R374 - FLL1 Control 6 */ + { 0x00000177, 0x0281 }, /* R375 - FLL1 Loop Filter Test 1 */ + { 0x00000178, 0x0000 }, /* R376 - FLL1 NCO Test 0 */ + { 0x00000179, 0x0000 }, /* R376 - FLL1 Control 7 */ + { 0x00000181, 0x0000 }, /* R385 - FLL1 Synchroniser 1 */ + { 0x00000182, 0x0000 }, /* R386 - FLL1 Synchroniser 2 */ + { 0x00000183, 0x0000 }, /* R387 - FLL1 Synchroniser 3 */ + { 0x00000184, 0x0000 }, /* R388 - FLL1 Synchroniser 4 */ + { 0x00000185, 0x0000 }, /* R389 - FLL1 Synchroniser 5 */ + { 0x00000186, 0x0000 }, /* R390 - FLL1 Synchroniser 6 */ + { 0x00000187, 0x0001 }, /* R390 - FLL1 Synchroniser 7 */ + { 0x00000189, 0x0000 }, /* R393 - FLL1 Spread Spectrum */ + { 0x0000018A, 0x000C }, /* R394 - FLL1 GPIO Clock */ + { 0x00000191, 0x0002 }, /* R401 - FLL2 Control 1 */ + { 0x00000192, 0x0008 }, /* R402 - FLL2 Control 2 */ + { 0x00000193, 0x0018 }, /* R403 - FLL2 Control 3 */ + { 0x00000194, 0x007D }, /* R404 - FLL2 Control 4 */ + { 0x00000195, 0x000C }, /* R405 - FLL2 Control 5 */ + { 0x00000196, 0x0000 }, /* R406 - FLL2 Control 6 */ + { 0x00000197, 0x0000 }, /* R407 - FLL2 Loop Filter Test 1 */ + { 0x00000198, 0x0000 }, /* R408 - FLL2 NCO Test 0 */ + { 0x00000199, 0x0000 }, /* R408 - FLL2 Control 7 */ + { 0x000001A1, 0x0000 }, /* R417 - FLL2 Synchroniser 1 */ + { 0x000001A2, 0x0000 }, /* R418 - FLL2 Synchroniser 2 */ + { 0x000001A3, 0x0000 }, /* R419 - FLL2 Synchroniser 3 */ + { 0x000001A4, 0x0000 }, /* R420 - FLL2 Synchroniser 4 */ + { 0x000001A5, 0x0000 }, /* R421 - FLL2 Synchroniser 5 */ + { 0x000001A6, 0x0000 }, /* R422 - FLL2 Synchroniser 6 */ + { 0x000001A7, 0x0001 }, /* R422 - FLL2 Synchroniser 7 */ + { 0x000001A9, 0x0000 }, /* R425 - FLL2 Spread Spectrum */ + { 0x000001AA, 0x000C }, /* R426 - FLL2 GPIO Clock */ + { 0x00000218, 0x00E6 }, /* R536 - Mic Bias Ctrl 1 */ + { 0x00000219, 0x00E6 }, /* R537 - Mic Bias Ctrl 2 */ + { 0x00000300, 0x0000 }, /* R768 - Input Enables */ + { 0x00000308, 0x0000 }, /* R776 - Input Rate */ + { 0x00000309, 0x0022 }, /* R777 - Input Volume Ramp */ + { 0x0000030C, 0x0002 }, /* R780 - HPF Control */ + { 0x00000310, 0x2000 }, /* R784 - IN1L Control */ + { 0x00000311, 0x0180 }, /* R785 - ADC Digital Volume 1L */ + { 0x00000312, 0x0000 }, /* R786 - DMIC1L Control */ + { 0x00000314, 0x0000 }, /* R788 - IN1R Control */ + { 0x00000315, 0x0180 }, /* R789 - ADC Digital Volume 1R */ + { 0x00000316, 0x0000 }, /* R790 - DMIC1R Control */ + { 0x00000318, 0x2000 }, /* R792 - IN2L Control */ + { 0x00000319, 0x0180 }, /* R793 - ADC Digital Volume 2L */ + { 0x0000031A, 0x0000 }, /* R794 - DMIC2L Control */ + { 0x0000031C, 0x0000 }, /* R796 - IN2R Control */ + { 0x0000031D, 0x0180 }, /* R797 - ADC Digital Volume 2R */ + { 0x0000031E, 0x0000 }, /* R798 - DMIC2R Control */ + { 0x00000400, 0x0000 }, /* R1024 - Output Enables 1 */ + { 0x00000408, 0x0000 }, /* R1032 - Output Rate 1 */ + { 0x00000409, 0x0022 }, /* R1033 - Output Volume Ramp */ + { 0x00000410, 0x0080 }, /* R1040 - Output Path Config 1L */ + { 0x00000411, 0x0180 }, /* R1041 - DAC Digital Volume 1L */ + { 0x00000412, 0x0081 }, /* R1042 - DAC Volume Limit 1L */ + { 0x00000413, 0x0001 }, /* R1043 - Noise Gate Select 1L */ + { 0x00000415, 0x0180 }, /* R1045 - DAC Digital Volume 1R */ + { 0x00000416, 0x0081 }, /* R1046 - DAC Volume Limit 1R */ + { 0x00000417, 0x0002 }, /* R1047 - Noise Gate Select 1R */ + { 0x00000429, 0x0180 }, /* R1065 - DAC Digital Volume 4L */ + { 0x0000042A, 0x0081 }, /* R1066 - Out Volume 4L */ + { 0x0000042B, 0x0040 }, /* R1067 - Noise Gate Select 4L */ + { 0x00000450, 0x0000 }, /* R1104 - DAC AEC Control 1 */ + { 0x00000458, 0x0000 }, /* R1112 - Noise Gate Control */ + { 0x000004A0, 0x3480 }, /* R1184 - HP1 Short Circuit Ctrl */ + { 0x00000500, 0x000C }, /* R1280 - AIF1 BCLK Ctrl */ + { 0x00000501, 0x0008 }, /* R1281 - AIF1 Tx Pin Ctrl */ + { 0x00000502, 0x0000 }, /* R1282 - AIF1 Rx Pin Ctrl */ + { 0x00000503, 0x0000 }, /* R1283 - AIF1 Rate Ctrl */ + { 0x00000504, 0x0000 }, /* R1284 - AIF1 Format */ + { 0x00000506, 0x0040 }, /* R1286 - AIF1 Rx BCLK Rate */ + { 0x00000507, 0x1818 }, /* R1287 - AIF1 Frame Ctrl 1 */ + { 0x00000508, 0x1818 }, /* R1288 - AIF1 Frame Ctrl 2 */ + { 0x00000509, 0x0000 }, /* R1289 - AIF1 Frame Ctrl 3 */ + { 0x0000050A, 0x0001 }, /* R1290 - AIF1 Frame Ctrl 4 */ + { 0x0000050B, 0x0002 }, /* R1291 - AIF1 Frame Ctrl 5 */ + { 0x0000050C, 0x0003 }, /* R1292 - AIF1 Frame Ctrl 6 */ + { 0x0000050D, 0x0004 }, /* R1293 - AIF1 Frame Ctrl 7 */ + { 0x0000050E, 0x0005 }, /* R1294 - AIF1 Frame Ctrl 8 */ + { 0x0000050F, 0x0006 }, /* R1295 - AIF1 Frame Ctrl 9 */ + { 0x00000510, 0x0007 }, /* R1296 - AIF1 Frame Ctrl 10 */ + { 0x00000511, 0x0000 }, /* R1297 - AIF1 Frame Ctrl 11 */ + { 0x00000512, 0x0001 }, /* R1298 - AIF1 Frame Ctrl 12 */ + { 0x00000513, 0x0002 }, /* R1299 - AIF1 Frame Ctrl 13 */ + { 0x00000514, 0x0003 }, /* R1300 - AIF1 Frame Ctrl 14 */ + { 0x00000515, 0x0004 }, /* R1301 - AIF1 Frame Ctrl 15 */ + { 0x00000516, 0x0005 }, /* R1302 - AIF1 Frame Ctrl 16 */ + { 0x00000517, 0x0006 }, /* R1303 - AIF1 Frame Ctrl 17 */ + { 0x00000518, 0x0007 }, /* R1304 - AIF1 Frame Ctrl 18 */ + { 0x00000519, 0x0000 }, /* R1305 - AIF1 Tx Enables */ + { 0x0000051A, 0x0000 }, /* R1306 - AIF1 Rx Enables */ + { 0x00000540, 0x000C }, /* R1344 - AIF2 BCLK Ctrl */ + { 0x00000541, 0x0008 }, /* R1345 - AIF2 Tx Pin Ctrl */ + { 0x00000542, 0x0000 }, /* R1346 - AIF2 Rx Pin Ctrl */ + { 0x00000543, 0x0000 }, /* R1347 - AIF2 Rate Ctrl */ + { 0x00000544, 0x0000 }, /* R1348 - AIF2 Format */ + { 0x00000546, 0x0040 }, /* R1350 - AIF2 Rx BCLK Rate */ + { 0x00000547, 0x1818 }, /* R1351 - AIF2 Frame Ctrl 1 */ + { 0x00000548, 0x1818 }, /* R1352 - AIF2 Frame Ctrl 2 */ + { 0x00000549, 0x0000 }, /* R1353 - AIF2 Frame Ctrl 3 */ + { 0x0000054A, 0x0001 }, /* R1354 - AIF2 Frame Ctrl 4 */ + { 0x0000054B, 0x0002 }, /* R1355 - AIF2 Frame Ctrl 5 */ + { 0x0000054C, 0x0003 }, /* R1356 - AIF2 Frame Ctrl 6 */ + { 0x0000054D, 0x0004 }, /* R1357 - AIF2 Frame Ctrl 7 */ + { 0x0000054E, 0x0005 }, /* R1358 - AIF2 Frame Ctrl 8 */ + { 0x00000551, 0x0000 }, /* R1361 - AIF2 Frame Ctrl 11 */ + { 0x00000552, 0x0001 }, /* R1362 - AIF2 Frame Ctrl 12 */ + { 0x00000553, 0x0002 }, /* R1363 - AIF2 Frame Ctrl 13 */ + { 0x00000554, 0x0003 }, /* R1364 - AIF2 Frame Ctrl 14 */ + { 0x00000555, 0x0004 }, /* R1365 - AIF2 Frame Ctrl 15 */ + { 0x00000556, 0x0005 }, /* R1366 - AIF2 Frame Ctrl 16 */ + { 0x00000559, 0x0000 }, /* R1369 - AIF2 Tx Enables */ + { 0x0000055A, 0x0000 }, /* R1370 - AIF2 Rx Enables */ + { 0x00000580, 0x000C }, /* R1408 - AIF3 BCLK Ctrl */ + { 0x00000581, 0x0008 }, /* R1409 - AIF3 Tx Pin Ctrl */ + { 0x00000582, 0x0000 }, /* R1410 - AIF3 Rx Pin Ctrl */ + { 0x00000583, 0x0000 }, /* R1411 - AIF3 Rate Ctrl */ + { 0x00000584, 0x0000 }, /* R1412 - AIF3 Format */ + { 0x00000586, 0x0040 }, /* R1414 - AIF3 Rx BCLK Rate */ + { 0x00000587, 0x1818 }, /* R1415 - AIF3 Frame Ctrl 1 */ + { 0x00000588, 0x1818 }, /* R1416 - AIF3 Frame Ctrl 2 */ + { 0x00000589, 0x0000 }, /* R1417 - AIF3 Frame Ctrl 3 */ + { 0x0000058A, 0x0001 }, /* R1418 - AIF3 Frame Ctrl 4 */ + { 0x00000591, 0x0000 }, /* R1425 - AIF3 Frame Ctrl 11 */ + { 0x00000592, 0x0001 }, /* R1426 - AIF3 Frame Ctrl 12 */ + { 0x00000599, 0x0000 }, /* R1433 - AIF3 Tx Enables */ + { 0x0000059A, 0x0000 }, /* R1434 - AIF3 Rx Enables */ + { 0x00000640, 0x0000 }, /* R1600 - PWM1MIX Input 1 Source */ + { 0x00000641, 0x0080 }, /* R1601 - PWM1MIX Input 1 Volume */ + { 0x00000642, 0x0000 }, /* R1602 - PWM1MIX Input 2 Source */ + { 0x00000643, 0x0080 }, /* R1603 - PWM1MIX Input 2 Volume */ + { 0x00000644, 0x0000 }, /* R1604 - PWM1MIX Input 3 Source */ + { 0x00000645, 0x0080 }, /* R1605 - PWM1MIX Input 3 Volume */ + { 0x00000646, 0x0000 }, /* R1606 - PWM1MIX Input 4 Source */ + { 0x00000647, 0x0080 }, /* R1607 - PWM1MIX Input 4 Volume */ + { 0x00000648, 0x0000 }, /* R1608 - PWM2MIX Input 1 Source */ + { 0x00000649, 0x0080 }, /* R1609 - PWM2MIX Input 1 Volume */ + { 0x0000064A, 0x0000 }, /* R1610 - PWM2MIX Input 2 Source */ + { 0x0000064B, 0x0080 }, /* R1611 - PWM2MIX Input 2 Volume */ + { 0x0000064C, 0x0000 }, /* R1612 - PWM2MIX Input 3 Source */ + { 0x0000064D, 0x0080 }, /* R1613 - PWM2MIX Input 3 Volume */ + { 0x0000064E, 0x0000 }, /* R1614 - PWM2MIX Input 4 Source */ + { 0x0000064F, 0x0080 }, /* R1615 - PWM2MIX Input 4 Volume */ + { 0x00000680, 0x0000 }, /* R1664 - OUT1LMIX Input 1 Source */ + { 0x00000681, 0x0080 }, /* R1665 - OUT1LMIX Input 1 Volume */ + { 0x00000682, 0x0000 }, /* R1666 - OUT1LMIX Input 2 Source */ + { 0x00000683, 0x0080 }, /* R1667 - OUT1LMIX Input 2 Volume */ + { 0x00000684, 0x0000 }, /* R1668 - OUT1LMIX Input 3 Source */ + { 0x00000685, 0x0080 }, /* R1669 - OUT1LMIX Input 3 Volume */ + { 0x00000686, 0x0000 }, /* R1670 - OUT1LMIX Input 4 Source */ + { 0x00000687, 0x0080 }, /* R1671 - OUT1LMIX Input 4 Volume */ + { 0x00000688, 0x0000 }, /* R1672 - OUT1RMIX Input 1 Source */ + { 0x00000689, 0x0080 }, /* R1673 - OUT1RMIX Input 1 Volume */ + { 0x0000068A, 0x0000 }, /* R1674 - OUT1RMIX Input 2 Source */ + { 0x0000068B, 0x0080 }, /* R1675 - OUT1RMIX Input 2 Volume */ + { 0x0000068C, 0x0000 }, /* R1676 - OUT1RMIX Input 3 Source */ + { 0x0000068D, 0x0080 }, /* R1677 - OUT1RMIX Input 3 Volume */ + { 0x0000068E, 0x0000 }, /* R1678 - OUT1RMIX Input 4 Source */ + { 0x0000068F, 0x0080 }, /* R1679 - OUT1RMIX Input 4 Volume */ + { 0x000006B0, 0x0000 }, /* R1712 - OUT4LMIX Input 1 Source */ + { 0x000006B1, 0x0080 }, /* R1713 - OUT4LMIX Input 1 Volume */ + { 0x000006B2, 0x0000 }, /* R1714 - OUT4LMIX Input 2 Source */ + { 0x000006B3, 0x0080 }, /* R1715 - OUT4LMIX Input 2 Volume */ + { 0x000006B4, 0x0000 }, /* R1716 - OUT4LMIX Input 3 Source */ + { 0x000006B5, 0x0080 }, /* R1717 - OUT4LMIX Input 3 Volume */ + { 0x000006B6, 0x0000 }, /* R1718 - OUT4LMIX Input 4 Source */ + { 0x000006B7, 0x0080 }, /* R1719 - OUT4LMIX Input 4 Volume */ + { 0x00000700, 0x0000 }, /* R1792 - AIF1TX1MIX Input 1 Source */ + { 0x00000701, 0x0080 }, /* R1793 - AIF1TX1MIX Input 1 Volume */ + { 0x00000702, 0x0000 }, /* R1794 - AIF1TX1MIX Input 2 Source */ + { 0x00000703, 0x0080 }, /* R1795 - AIF1TX1MIX Input 2 Volume */ + { 0x00000704, 0x0000 }, /* R1796 - AIF1TX1MIX Input 3 Source */ + { 0x00000705, 0x0080 }, /* R1797 - AIF1TX1MIX Input 3 Volume */ + { 0x00000706, 0x0000 }, /* R1798 - AIF1TX1MIX Input 4 Source */ + { 0x00000707, 0x0080 }, /* R1799 - AIF1TX1MIX Input 4 Volume */ + { 0x00000708, 0x0000 }, /* R1800 - AIF1TX2MIX Input 1 Source */ + { 0x00000709, 0x0080 }, /* R1801 - AIF1TX2MIX Input 1 Volume */ + { 0x0000070A, 0x0000 }, /* R1802 - AIF1TX2MIX Input 2 Source */ + { 0x0000070B, 0x0080 }, /* R1803 - AIF1TX2MIX Input 2 Volume */ + { 0x0000070C, 0x0000 }, /* R1804 - AIF1TX2MIX Input 3 Source */ + { 0x0000070D, 0x0080 }, /* R1805 - AIF1TX2MIX Input 3 Volume */ + { 0x0000070E, 0x0000 }, /* R1806 - AIF1TX2MIX Input 4 Source */ + { 0x0000070F, 0x0080 }, /* R1807 - AIF1TX2MIX Input 4 Volume */ + { 0x00000710, 0x0000 }, /* R1808 - AIF1TX3MIX Input 1 Source */ + { 0x00000711, 0x0080 }, /* R1809 - AIF1TX3MIX Input 1 Volume */ + { 0x00000712, 0x0000 }, /* R1810 - AIF1TX3MIX Input 2 Source */ + { 0x00000713, 0x0080 }, /* R1811 - AIF1TX3MIX Input 2 Volume */ + { 0x00000714, 0x0000 }, /* R1812 - AIF1TX3MIX Input 3 Source */ + { 0x00000715, 0x0080 }, /* R1813 - AIF1TX3MIX Input 3 Volume */ + { 0x00000716, 0x0000 }, /* R1814 - AIF1TX3MIX Input 4 Source */ + { 0x00000717, 0x0080 }, /* R1815 - AIF1TX3MIX Input 4 Volume */ + { 0x00000718, 0x0000 }, /* R1816 - AIF1TX4MIX Input 1 Source */ + { 0x00000719, 0x0080 }, /* R1817 - AIF1TX4MIX Input 1 Volume */ + { 0x0000071A, 0x0000 }, /* R1818 - AIF1TX4MIX Input 2 Source */ + { 0x0000071B, 0x0080 }, /* R1819 - AIF1TX4MIX Input 2 Volume */ + { 0x0000071C, 0x0000 }, /* R1820 - AIF1TX4MIX Input 3 Source */ + { 0x0000071D, 0x0080 }, /* R1821 - AIF1TX4MIX Input 3 Volume */ + { 0x0000071E, 0x0000 }, /* R1822 - AIF1TX4MIX Input 4 Source */ + { 0x0000071F, 0x0080 }, /* R1823 - AIF1TX4MIX Input 4 Volume */ + { 0x00000720, 0x0000 }, /* R1824 - AIF1TX5MIX Input 1 Source */ + { 0x00000721, 0x0080 }, /* R1825 - AIF1TX5MIX Input 1 Volume */ + { 0x00000722, 0x0000 }, /* R1826 - AIF1TX5MIX Input 2 Source */ + { 0x00000723, 0x0080 }, /* R1827 - AIF1TX5MIX Input 2 Volume */ + { 0x00000724, 0x0000 }, /* R1828 - AIF1TX5MIX Input 3 Source */ + { 0x00000725, 0x0080 }, /* R1829 - AIF1TX5MIX Input 3 Volume */ + { 0x00000726, 0x0000 }, /* R1830 - AIF1TX5MIX Input 4 Source */ + { 0x00000727, 0x0080 }, /* R1831 - AIF1TX5MIX Input 4 Volume */ + { 0x00000728, 0x0000 }, /* R1832 - AIF1TX6MIX Input 1 Source */ + { 0x00000729, 0x0080 }, /* R1833 - AIF1TX6MIX Input 1 Volume */ + { 0x0000072A, 0x0000 }, /* R1834 - AIF1TX6MIX Input 2 Source */ + { 0x0000072B, 0x0080 }, /* R1835 - AIF1TX6MIX Input 2 Volume */ + { 0x0000072C, 0x0000 }, /* R1836 - AIF1TX6MIX Input 3 Source */ + { 0x0000072D, 0x0080 }, /* R1837 - AIF1TX6MIX Input 3 Volume */ + { 0x0000072E, 0x0000 }, /* R1838 - AIF1TX6MIX Input 4 Source */ + { 0x0000072F, 0x0080 }, /* R1839 - AIF1TX6MIX Input 4 Volume */ + { 0x00000730, 0x0000 }, /* R1840 - AIF1TX7MIX Input 1 Source */ + { 0x00000731, 0x0080 }, /* R1841 - AIF1TX7MIX Input 1 Volume */ + { 0x00000732, 0x0000 }, /* R1842 - AIF1TX7MIX Input 2 Source */ + { 0x00000733, 0x0080 }, /* R1843 - AIF1TX7MIX Input 2 Volume */ + { 0x00000734, 0x0000 }, /* R1844 - AIF1TX7MIX Input 3 Source */ + { 0x00000735, 0x0080 }, /* R1845 - AIF1TX7MIX Input 3 Volume */ + { 0x00000736, 0x0000 }, /* R1846 - AIF1TX7MIX Input 4 Source */ + { 0x00000737, 0x0080 }, /* R1847 - AIF1TX7MIX Input 4 Volume */ + { 0x00000738, 0x0000 }, /* R1848 - AIF1TX8MIX Input 1 Source */ + { 0x00000739, 0x0080 }, /* R1849 - AIF1TX8MIX Input 1 Volume */ + { 0x0000073A, 0x0000 }, /* R1850 - AIF1TX8MIX Input 2 Source */ + { 0x0000073B, 0x0080 }, /* R1851 - AIF1TX8MIX Input 2 Volume */ + { 0x0000073C, 0x0000 }, /* R1852 - AIF1TX8MIX Input 3 Source */ + { 0x0000073D, 0x0080 }, /* R1853 - AIF1TX8MIX Input 3 Volume */ + { 0x0000073E, 0x0000 }, /* R1854 - AIF1TX8MIX Input 4 Source */ + { 0x0000073F, 0x0080 }, /* R1855 - AIF1TX8MIX Input 4 Volume */ + { 0x00000740, 0x0000 }, /* R1856 - AIF2TX1MIX Input 1 Source */ + { 0x00000741, 0x0080 }, /* R1857 - AIF2TX1MIX Input 1 Volume */ + { 0x00000742, 0x0000 }, /* R1858 - AIF2TX1MIX Input 2 Source */ + { 0x00000743, 0x0080 }, /* R1859 - AIF2TX1MIX Input 2 Volume */ + { 0x00000744, 0x0000 }, /* R1860 - AIF2TX1MIX Input 3 Source */ + { 0x00000745, 0x0080 }, /* R1861 - AIF2TX1MIX Input 3 Volume */ + { 0x00000746, 0x0000 }, /* R1862 - AIF2TX1MIX Input 4 Source */ + { 0x00000747, 0x0080 }, /* R1863 - AIF2TX1MIX Input 4 Volume */ + { 0x00000748, 0x0000 }, /* R1864 - AIF2TX2MIX Input 1 Source */ + { 0x00000749, 0x0080 }, /* R1865 - AIF2TX2MIX Input 1 Volume */ + { 0x0000074A, 0x0000 }, /* R1866 - AIF2TX2MIX Input 2 Source */ + { 0x0000074B, 0x0080 }, /* R1867 - AIF2TX2MIX Input 2 Volume */ + { 0x0000074C, 0x0000 }, /* R1868 - AIF2TX2MIX Input 3 Source */ + { 0x0000074D, 0x0080 }, /* R1869 - AIF2TX2MIX Input 3 Volume */ + { 0x0000074E, 0x0000 }, /* R1870 - AIF2TX2MIX Input 4 Source */ + { 0x0000074F, 0x0080 }, /* R1871 - AIF2TX2MIX Input 4 Volume */ + { 0x00000750, 0x0000 }, /* R1872 - AIF2TX3MIX Input 1 Source */ + { 0x00000751, 0x0080 }, /* R1873 - AIF2TX3MIX Input 1 Volume */ + { 0x00000752, 0x0000 }, /* R1874 - AIF2TX3MIX Input 2 Source */ + { 0x00000753, 0x0080 }, /* R1875 - AIF2TX3MIX Input 2 Volume */ + { 0x00000754, 0x0000 }, /* R1876 - AIF2TX3MIX Input 3 Source */ + { 0x00000755, 0x0080 }, /* R1877 - AIF2TX3MIX Input 3 Volume */ + { 0x00000756, 0x0000 }, /* R1878 - AIF2TX3MIX Input 4 Source */ + { 0x00000757, 0x0080 }, /* R1879 - AIF2TX3MIX Input 4 Volume */ + { 0x00000758, 0x0000 }, /* R1880 - AIF2TX4MIX Input 1 Source */ + { 0x00000759, 0x0080 }, /* R1881 - AIF2TX4MIX Input 1 Volume */ + { 0x0000075A, 0x0000 }, /* R1882 - AIF2TX4MIX Input 2 Source */ + { 0x0000075B, 0x0080 }, /* R1883 - AIF2TX4MIX Input 2 Volume */ + { 0x0000075C, 0x0000 }, /* R1884 - AIF2TX4MIX Input 3 Source */ + { 0x0000075D, 0x0080 }, /* R1885 - AIF2TX4MIX Input 3 Volume */ + { 0x0000075E, 0x0000 }, /* R1886 - AIF2TX4MIX Input 4 Source */ + { 0x0000075F, 0x0080 }, /* R1887 - AIF2TX4MIX Input 4 Volume */ + { 0x00000760, 0x0000 }, /* R1888 - AIF2TX5MIX Input 1 Source */ + { 0x00000761, 0x0080 }, /* R1889 - AIF2TX5MIX Input 1 Volume */ + { 0x00000762, 0x0000 }, /* R1890 - AIF2TX5MIX Input 2 Source */ + { 0x00000763, 0x0080 }, /* R1891 - AIF2TX5MIX Input 2 Volume */ + { 0x00000764, 0x0000 }, /* R1892 - AIF2TX5MIX Input 3 Source */ + { 0x00000765, 0x0080 }, /* R1893 - AIF2TX5MIX Input 3 Volume */ + { 0x00000766, 0x0000 }, /* R1894 - AIF2TX5MIX Input 4 Source */ + { 0x00000767, 0x0080 }, /* R1895 - AIF2TX5MIX Input 4 Volume */ + { 0x00000768, 0x0000 }, /* R1896 - AIF2TX6MIX Input 1 Source */ + { 0x00000769, 0x0080 }, /* R1897 - AIF2TX6MIX Input 1 Volume */ + { 0x0000076A, 0x0000 }, /* R1898 - AIF2TX6MIX Input 2 Source */ + { 0x0000076B, 0x0080 }, /* R1899 - AIF2TX6MIX Input 2 Volume */ + { 0x0000076C, 0x0000 }, /* R1900 - AIF2TX6MIX Input 3 Source */ + { 0x0000076D, 0x0080 }, /* R1901 - AIF2TX6MIX Input 3 Volume */ + { 0x0000076E, 0x0000 }, /* R1902 - AIF2TX6MIX Input 4 Source */ + { 0x0000076F, 0x0080 }, /* R1903 - AIF2TX6MIX Input 4 Volume */ + { 0x00000780, 0x0000 }, /* R1920 - AIF3TX1MIX Input 1 Source */ + { 0x00000781, 0x0080 }, /* R1921 - AIF3TX1MIX Input 1 Volume */ + { 0x00000782, 0x0000 }, /* R1922 - AIF3TX1MIX Input 2 Source */ + { 0x00000783, 0x0080 }, /* R1923 - AIF3TX1MIX Input 2 Volume */ + { 0x00000784, 0x0000 }, /* R1924 - AIF3TX1MIX Input 3 Source */ + { 0x00000785, 0x0080 }, /* R1925 - AIF3TX1MIX Input 3 Volume */ + { 0x00000786, 0x0000 }, /* R1926 - AIF3TX1MIX Input 4 Source */ + { 0x00000787, 0x0080 }, /* R1927 - AIF3TX1MIX Input 4 Volume */ + { 0x00000788, 0x0000 }, /* R1928 - AIF3TX2MIX Input 1 Source */ + { 0x00000789, 0x0080 }, /* R1929 - AIF3TX2MIX Input 1 Volume */ + { 0x0000078A, 0x0000 }, /* R1930 - AIF3TX2MIX Input 2 Source */ + { 0x0000078B, 0x0080 }, /* R1931 - AIF3TX2MIX Input 2 Volume */ + { 0x0000078C, 0x0000 }, /* R1932 - AIF3TX2MIX Input 3 Source */ + { 0x0000078D, 0x0080 }, /* R1933 - AIF3TX2MIX Input 3 Volume */ + { 0x0000078E, 0x0000 }, /* R1934 - AIF3TX2MIX Input 4 Source */ + { 0x0000078F, 0x0080 }, /* R1935 - AIF3TX2MIX Input 4 Volume */ + { 0x00000880, 0x0000 }, /* R2176 - EQ1MIX Input 1 Source */ + { 0x00000881, 0x0080 }, /* R2177 - EQ1MIX Input 1 Volume */ + { 0x00000882, 0x0000 }, /* R2178 - EQ1MIX Input 2 Source */ + { 0x00000883, 0x0080 }, /* R2179 - EQ1MIX Input 2 Volume */ + { 0x00000884, 0x0000 }, /* R2180 - EQ1MIX Input 3 Source */ + { 0x00000885, 0x0080 }, /* R2181 - EQ1MIX Input 3 Volume */ + { 0x00000886, 0x0000 }, /* R2182 - EQ1MIX Input 4 Source */ + { 0x00000887, 0x0080 }, /* R2183 - EQ1MIX Input 4 Volume */ + { 0x00000888, 0x0000 }, /* R2184 - EQ2MIX Input 1 Source */ + { 0x00000889, 0x0080 }, /* R2185 - EQ2MIX Input 1 Volume */ + { 0x0000088A, 0x0000 }, /* R2186 - EQ2MIX Input 2 Source */ + { 0x0000088B, 0x0080 }, /* R2187 - EQ2MIX Input 2 Volume */ + { 0x0000088C, 0x0000 }, /* R2188 - EQ2MIX Input 3 Source */ + { 0x0000088D, 0x0080 }, /* R2189 - EQ2MIX Input 3 Volume */ + { 0x0000088E, 0x0000 }, /* R2190 - EQ2MIX Input 4 Source */ + { 0x0000088F, 0x0080 }, /* R2191 - EQ2MIX Input 4 Volume */ + { 0x000008C0, 0x0000 }, /* R2240 - DRC1LMIX Input 1 Source */ + { 0x000008C1, 0x0080 }, /* R2241 - DRC1LMIX Input 1 Volume */ + { 0x000008C2, 0x0000 }, /* R2242 - DRC1LMIX Input 2 Source */ + { 0x000008C3, 0x0080 }, /* R2243 - DRC1LMIX Input 2 Volume */ + { 0x000008C4, 0x0000 }, /* R2244 - DRC1LMIX Input 3 Source */ + { 0x000008C5, 0x0080 }, /* R2245 - DRC1LMIX Input 3 Volume */ + { 0x000008C6, 0x0000 }, /* R2246 - DRC1LMIX Input 4 Source */ + { 0x000008C7, 0x0080 }, /* R2247 - DRC1LMIX Input 4 Volume */ + { 0x000008C8, 0x0000 }, /* R2248 - DRC1RMIX Input 1 Source */ + { 0x000008C9, 0x0080 }, /* R2249 - DRC1RMIX Input 1 Volume */ + { 0x000008CA, 0x0000 }, /* R2250 - DRC1RMIX Input 2 Source */ + { 0x000008CB, 0x0080 }, /* R2251 - DRC1RMIX Input 2 Volume */ + { 0x000008CC, 0x0000 }, /* R2252 - DRC1RMIX Input 3 Source */ + { 0x000008CD, 0x0080 }, /* R2253 - DRC1RMIX Input 3 Volume */ + { 0x000008CE, 0x0000 }, /* R2254 - DRC1RMIX Input 4 Source */ + { 0x000008CF, 0x0080 }, /* R2255 - DRC1RMIX Input 4 Volume */ + { 0x000008D0, 0x0000 }, /* R2256 - DRC2LMIX Input 1 Source */ + { 0x000008D1, 0x0080 }, /* R2257 - DRC2LMIX Input 1 Volume */ + { 0x000008D2, 0x0000 }, /* R2258 - DRC2LMIX Input 2 Source */ + { 0x000008D3, 0x0080 }, /* R2259 - DRC2LMIX Input 2 Volume */ + { 0x000008D4, 0x0000 }, /* R2260 - DRC2LMIX Input 3 Source */ + { 0x000008D5, 0x0080 }, /* R2261 - DRC2LMIX Input 3 Volume */ + { 0x000008D6, 0x0000 }, /* R2262 - DRC2LMIX Input 4 Source */ + { 0x000008D7, 0x0080 }, /* R2263 - DRC2LMIX Input 4 Volume */ + { 0x000008D8, 0x0000 }, /* R2264 - DRC2RMIX Input 1 Source */ + { 0x000008D9, 0x0080 }, /* R2265 - DRC2RMIX Input 1 Volume */ + { 0x000008DA, 0x0000 }, /* R2266 - DRC2RMIX Input 2 Source */ + { 0x000008DB, 0x0080 }, /* R2267 - DRC2RMIX Input 2 Volume */ + { 0x000008DC, 0x0000 }, /* R2268 - DRC2RMIX Input 3 Source */ + { 0x000008DD, 0x0080 }, /* R2269 - DRC2RMIX Input 3 Volume */ + { 0x000008DE, 0x0000 }, /* R2270 - DRC2RMIX Input 4 Source */ + { 0x000008DF, 0x0080 }, /* R2271 - DRC2RMIX Input 4 Volume */ + { 0x00000900, 0x0000 }, /* R2304 - HPLP1MIX Input 1 Source */ + { 0x00000901, 0x0080 }, /* R2305 - HPLP1MIX Input 1 Volume */ + { 0x00000902, 0x0000 }, /* R2306 - HPLP1MIX Input 2 Source */ + { 0x00000903, 0x0080 }, /* R2307 - HPLP1MIX Input 2 Volume */ + { 0x00000904, 0x0000 }, /* R2308 - HPLP1MIX Input 3 Source */ + { 0x00000905, 0x0080 }, /* R2309 - HPLP1MIX Input 3 Volume */ + { 0x00000906, 0x0000 }, /* R2310 - HPLP1MIX Input 4 Source */ + { 0x00000907, 0x0080 }, /* R2311 - HPLP1MIX Input 4 Volume */ + { 0x00000908, 0x0000 }, /* R2312 - HPLP2MIX Input 1 Source */ + { 0x00000909, 0x0080 }, /* R2313 - HPLP2MIX Input 1 Volume */ + { 0x0000090A, 0x0000 }, /* R2314 - HPLP2MIX Input 2 Source */ + { 0x0000090B, 0x0080 }, /* R2315 - HPLP2MIX Input 2 Volume */ + { 0x0000090C, 0x0000 }, /* R2316 - HPLP2MIX Input 3 Source */ + { 0x0000090D, 0x0080 }, /* R2317 - HPLP2MIX Input 3 Volume */ + { 0x0000090E, 0x0000 }, /* R2318 - HPLP2MIX Input 4 Source */ + { 0x0000090F, 0x0080 }, /* R2319 - HPLP2MIX Input 4 Volume */ + { 0x00000910, 0x0000 }, /* R2320 - HPLP3MIX Input 1 Source */ + { 0x00000911, 0x0080 }, /* R2321 - HPLP3MIX Input 1 Volume */ + { 0x00000912, 0x0000 }, /* R2322 - HPLP3MIX Input 2 Source */ + { 0x00000913, 0x0080 }, /* R2323 - HPLP3MIX Input 2 Volume */ + { 0x00000914, 0x0000 }, /* R2324 - HPLP3MIX Input 3 Source */ + { 0x00000915, 0x0080 }, /* R2325 - HPLP3MIX Input 3 Volume */ + { 0x00000916, 0x0000 }, /* R2326 - HPLP3MIX Input 4 Source */ + { 0x00000917, 0x0080 }, /* R2327 - HPLP3MIX Input 4 Volume */ + { 0x00000918, 0x0000 }, /* R2328 - HPLP4MIX Input 1 Source */ + { 0x00000919, 0x0080 }, /* R2329 - HPLP4MIX Input 1 Volume */ + { 0x0000091A, 0x0000 }, /* R2330 - HPLP4MIX Input 2 Source */ + { 0x0000091B, 0x0080 }, /* R2331 - HPLP4MIX Input 2 Volume */ + { 0x0000091C, 0x0000 }, /* R2332 - HPLP4MIX Input 3 Source */ + { 0x0000091D, 0x0080 }, /* R2333 - HPLP4MIX Input 3 Volume */ + { 0x0000091E, 0x0000 }, /* R2334 - HPLP4MIX Input 4 Source */ + { 0x0000091F, 0x0080 }, /* R2335 - HPLP4MIX Input 4 Volume */ + { 0x00000980, 0x0000 }, /* R2432 - DSP2LMIX Input 1 Source */ + { 0x00000981, 0x0080 }, /* R2433 - DSP2LMIX Input 1 Volume */ + { 0x00000982, 0x0000 }, /* R2434 - DSP2LMIX Input 2 Source */ + { 0x00000983, 0x0080 }, /* R2435 - DSP2LMIX Input 2 Volume */ + { 0x00000984, 0x0000 }, /* R2436 - DSP2LMIX Input 3 Source */ + { 0x00000985, 0x0080 }, /* R2437 - DSP2LMIX Input 3 Volume */ + { 0x00000986, 0x0000 }, /* R2438 - DSP2LMIX Input 4 Source */ + { 0x00000987, 0x0080 }, /* R2439 - DSP2LMIX Input 4 Volume */ + { 0x00000988, 0x0000 }, /* R2440 - DSP2RMIX Input 1 Source */ + { 0x00000989, 0x0080 }, /* R2441 - DSP2RMIX Input 1 Volume */ + { 0x0000098A, 0x0000 }, /* R2442 - DSP2RMIX Input 2 Source */ + { 0x0000098B, 0x0080 }, /* R2443 - DSP2RMIX Input 2 Volume */ + { 0x0000098C, 0x0000 }, /* R2444 - DSP2RMIX Input 3 Source */ + { 0x0000098D, 0x0080 }, /* R2445 - DSP2RMIX Input 3 Volume */ + { 0x0000098E, 0x0000 }, /* R2446 - DSP2RMIX Input 4 Source */ + { 0x0000098F, 0x0080 }, /* R2447 - DSP2RMIX Input 4 Volume */ + { 0x00000990, 0x0000 }, /* R2448 - DSP2AUX1MIX Input 1 Source */ + { 0x00000998, 0x0000 }, /* R2456 - DSP2AUX2MIX Input 1 Source */ + { 0x000009A0, 0x0000 }, /* R2464 - DSP2AUX3MIX Input 1 Source */ + { 0x000009A8, 0x0000 }, /* R2472 - DSP2AUX4MIX Input 1 Source */ + { 0x000009B0, 0x0000 }, /* R2480 - DSP2AUX5MIX Input 1 Source */ + { 0x000009B8, 0x0000 }, /* R2488 - DSP2AUX6MIX Input 1 Source */ + { 0x000009C0, 0x0000 }, /* R2496 - DSP3LMIX Input 1 Source */ + { 0x000009C1, 0x0080 }, /* R2497 - DSP3LMIX Input 1 Volume */ + { 0x000009C2, 0x0000 }, /* R2498 - DSP3LMIX Input 2 Source */ + { 0x000009C3, 0x0080 }, /* R2499 - DSP3LMIX Input 2 Volume */ + { 0x000009C4, 0x0000 }, /* R2500 - DSP3LMIX Input 3 Source */ + { 0x000009C5, 0x0080 }, /* R2501 - DSP3LMIX Input 3 Volume */ + { 0x000009C6, 0x0000 }, /* R2502 - DSP3LMIX Input 4 Source */ + { 0x000009C7, 0x0080 }, /* R2503 - DSP3LMIX Input 4 Volume */ + { 0x000009C8, 0x0000 }, /* R2504 - DSP3RMIX Input 1 Source */ + { 0x000009C9, 0x0080 }, /* R2505 - DSP3RMIX Input 1 Volume */ + { 0x000009CA, 0x0000 }, /* R2506 - DSP3RMIX Input 2 Source */ + { 0x000009CB, 0x0080 }, /* R2507 - DSP3RMIX Input 2 Volume */ + { 0x000009CC, 0x0000 }, /* R2508 - DSP3RMIX Input 3 Source */ + { 0x000009CD, 0x0080 }, /* R2509 - DSP3RMIX Input 3 Volume */ + { 0x000009CE, 0x0000 }, /* R2510 - DSP3RMIX Input 4 Source */ + { 0x000009CF, 0x0080 }, /* R2511 - DSP3RMIX Input 4 Volume */ + { 0x000009D0, 0x0000 }, /* R2512 - DSP3AUX1MIX Input 1 Source */ + { 0x000009D8, 0x0000 }, /* R2520 - DSP3AUX2MIX Input 1 Source */ + { 0x000009E0, 0x0000 }, /* R2528 - DSP3AUX3MIX Input 1 Source */ + { 0x000009E8, 0x0000 }, /* R2536 - DSP3AUX4MIX Input 1 Source */ + { 0x000009F0, 0x0000 }, /* R2544 - DSP3AUX5MIX Input 1 Source */ + { 0x000009F8, 0x0000 }, /* R2552 - DSP3AUX6MIX Input 1 Source */ + { 0x00000A80, 0x0000 }, /* R2688 - ASRC1LMIX Input 1 Source */ + { 0x00000A88, 0x0000 }, /* R2696 - ASRC1RMIX Input 1 Source */ + { 0x00000A90, 0x0000 }, /* R2704 - ASRC2LMIX Input 1 Source */ + { 0x00000A98, 0x0000 }, /* R2712 - ASRC2RMIX Input 1 Source */ + { 0x00000B00, 0x0000 }, /* R2816 - ISRC1DEC1MIX Input 1 Source */ + { 0x00000B08, 0x0000 }, /* R2824 - ISRC1DEC2MIX Input 1 Source */ + { 0x00000B10, 0x0000 }, /* R2832 - ISRC1DEC3MIX Input 1 Source */ + { 0x00000B18, 0x0000 }, /* R2840 - ISRC1DEC4MIX Input 1 Source */ + { 0x00000B20, 0x0000 }, /* R2848 - ISRC1INT1MIX Input 1 Source */ + { 0x00000B28, 0x0000 }, /* R2856 - ISRC1INT2MIX Input 1 Source */ + { 0x00000B30, 0x0000 }, /* R2864 - ISRC1INT3MIX Input 1 Source */ + { 0x00000B38, 0x0000 }, /* R2872 - ISRC1INT4MIX Input 1 Source */ + { 0x00000B40, 0x0000 }, /* R2880 - ISRC2DEC1MIX Input 1 Source */ + { 0x00000B48, 0x0000 }, /* R2888 - ISRC2DEC2MIX Input 1 Source */ + { 0x00000B50, 0x0000 }, /* R2896 - ISRC2DEC3MIX Input 1 Source */ + { 0x00000B58, 0x0000 }, /* R2904 - ISRC2DEC4MIX Input 1 Source */ + { 0x00000B60, 0x0000 }, /* R2912 - ISRC2INT1MIX Input 1 Source */ + { 0x00000B68, 0x0000 }, /* R2920 - ISRC2INT2MIX Input 1 Source */ + { 0x00000B70, 0x0000 }, /* R2928 - ISRC2INT3MIX Input 1 Source */ + { 0x00000B78, 0x0000 }, /* R2936 - ISRC2INT4MIX Input 1 Source */ + { 0x00000B80, 0x0000 }, /* R2944 - ISRC3DEC1MIX Input 1 Source */ + { 0x00000B88, 0x0000 }, /* R2952 - ISRC3DEC2MIX Input 1 Source */ + { 0x00000B90, 0x0000 }, /* R2960 - ISRC3DEC3MIX Input 1 Source */ + { 0x00000B98, 0x0000 }, /* R2968 - ISRC3DEC4MIX Input 1 Source */ + { 0x00000BA0, 0x0000 }, /* R2976 - ISRC3INT1MIX Input 1 Source */ + { 0x00000BA8, 0x0000 }, /* R2984 - ISRC3INT2MIX Input 1 Source */ + { 0x00000BB0, 0x0000 }, /* R2992 - ISRC3INT3MIX Input 1 Source */ + { 0x00000BB8, 0x0000 }, /* R3000 - ISRC3INT4MIX Input 1 Source */ + { 0x00000C00, 0xA101 }, /* R3072 - GPIO1 CTRL */ + { 0x00000C01, 0xA101 }, /* R3073 - GPIO2 CTRL */ + { 0x00000C0F, 0x0400 }, /* R3087 - IRQ CTRL 1 */ + { 0x00000C10, 0x1000 }, /* R3088 - GPIO Debounce Config */ + { 0x00000C20, 0x0002 }, /* R3104 - Misc Pad Ctrl 1 */ + { 0x00000C21, 0x8001 }, /* R3105 - Misc Pad Ctrl 2 */ + { 0x00000C22, 0x0000 }, /* R3106 - Misc Pad Ctrl 3 */ + { 0x00000C23, 0x0000 }, /* R3107 - Misc Pad Ctrl 4 */ + { 0x00000C24, 0x0000 }, /* R3108 - Misc Pad Ctrl 5 */ + { 0x00000C25, 0x0000 }, /* R3109 - Misc Pad Ctrl 6 */ + { 0x00000C30, 0x0404 }, /* R3120 - Misc Pad Ctrl 7 */ + { 0x00000C32, 0x0404 }, /* R3122 - Misc Pad Ctrl 9 */ + { 0x00000C33, 0x0404 }, /* R3123 - Misc Pad Ctrl 10 */ + { 0x00000C34, 0x0404 }, /* R3124 - Misc Pad Ctrl 11 */ + { 0x00000C35, 0x0404 }, /* R3125 - Misc Pad Ctrl 12 */ + { 0x00000C36, 0x0400 }, /* R3126 - Misc Pad Ctrl 13 */ + { 0x00000C37, 0x0404 }, /* R3127 - Misc Pad Ctrl 14 */ + { 0x00000C39, 0x0400 }, /* R3129 - Misc Pad Ctrl 16 */ + { 0x00000D08, 0x0007 }, /* R3336 - Interrupt Status 1 Mask */ + { 0x00000D09, 0x06FF }, /* R3337 - Interrupt Status 2 Mask */ + { 0x00000D0A, 0xCFEF }, /* R3338 - Interrupt Status 3 Mask */ + { 0x00000D0B, 0xFFC3 }, /* R3339 - Interrupt Status 4 Mask */ + { 0x00000D0C, 0x000B }, /* R3340 - Interrupt Status 5 Mask */ + { 0x00000D0D, 0xD005 }, /* R3341 - Interrupt Status 6 Mask */ + { 0x00000D0F, 0x0000 }, /* R3343 - Interrupt Control */ + { 0x00000D18, 0x0007 }, /* R3352 - IRQ2 Status 1 Mask */ + { 0x00000D19, 0x06FF }, /* R3353 - IRQ2 Status 2 Mask */ + { 0x00000D1A, 0xCFEF }, /* R3354 - IRQ2 Status 3 Mask */ + { 0x00000D1B, 0xFFC3 }, /* R3355 - IRQ2 Status 4 Mask */ + { 0x00000D1C, 0x000B }, /* R3356 - IRQ2 Status 5 Mask */ + { 0x00000D1D, 0xD005 }, /* R3357 - IRQ2 Status 6 Mask */ + { 0x00000D1F, 0x0000 }, /* R3359 - IRQ2 Control */ + { 0x00000E00, 0x0000 }, /* R3584 - FX_Ctrl1 */ + { 0x00000E10, 0x6318 }, /* R3600 - EQ1_1 */ + { 0x00000E11, 0x6300 }, /* R3601 - EQ1_2 */ + { 0x00000E12, 0x0FC8 }, /* R3602 - EQ1_3 */ + { 0x00000E13, 0x03FE }, /* R3603 - EQ1_4 */ + { 0x00000E14, 0x00E0 }, /* R3604 - EQ1_5 */ + { 0x00000E15, 0x1EC4 }, /* R3605 - EQ1_6 */ + { 0x00000E16, 0xF136 }, /* R3606 - EQ1_7 */ + { 0x00000E17, 0x0409 }, /* R3607 - EQ1_8 */ + { 0x00000E18, 0x04CC }, /* R3608 - EQ1_9 */ + { 0x00000E19, 0x1C9B }, /* R3609 - EQ1_10 */ + { 0x00000E1A, 0xF337 }, /* R3610 - EQ1_11 */ + { 0x00000E1B, 0x040B }, /* R3611 - EQ1_12 */ + { 0x00000E1C, 0x0CBB }, /* R3612 - EQ1_13 */ + { 0x00000E1D, 0x16F8 }, /* R3613 - EQ1_14 */ + { 0x00000E1E, 0xF7D9 }, /* R3614 - EQ1_15 */ + { 0x00000E1F, 0x040A }, /* R3615 - EQ1_16 */ + { 0x00000E20, 0x1F14 }, /* R3616 - EQ1_17 */ + { 0x00000E21, 0x058C }, /* R3617 - EQ1_18 */ + { 0x00000E22, 0x0563 }, /* R3618 - EQ1_19 */ + { 0x00000E23, 0x4000 }, /* R3619 - EQ1_20 */ + { 0x00000E24, 0x0B75 }, /* R3620 - EQ1_21 */ + { 0x00000E26, 0x6318 }, /* R3622 - EQ2_1 */ + { 0x00000E27, 0x6300 }, /* R3623 - EQ2_2 */ + { 0x00000E28, 0x0FC8 }, /* R3624 - EQ2_3 */ + { 0x00000E29, 0x03FE }, /* R3625 - EQ2_4 */ + { 0x00000E2A, 0x00E0 }, /* R3626 - EQ2_5 */ + { 0x00000E2B, 0x1EC4 }, /* R3627 - EQ2_6 */ + { 0x00000E2C, 0xF136 }, /* R3628 - EQ2_7 */ + { 0x00000E2D, 0x0409 }, /* R3629 - EQ2_8 */ + { 0x00000E2E, 0x04CC }, /* R3630 - EQ2_9 */ + { 0x00000E2F, 0x1C9B }, /* R3631 - EQ2_10 */ + { 0x00000E30, 0xF337 }, /* R3632 - EQ2_11 */ + { 0x00000E31, 0x040B }, /* R3633 - EQ2_12 */ + { 0x00000E32, 0x0CBB }, /* R3634 - EQ2_13 */ + { 0x00000E33, 0x16F8 }, /* R3635 - EQ2_14 */ + { 0x00000E34, 0xF7D9 }, /* R3636 - EQ2_15 */ + { 0x00000E35, 0x040A }, /* R3637 - EQ2_16 */ + { 0x00000E36, 0x1F14 }, /* R3638 - EQ2_17 */ + { 0x00000E37, 0x058C }, /* R3639 - EQ2_18 */ + { 0x00000E38, 0x0563 }, /* R3640 - EQ2_19 */ + { 0x00000E39, 0x4000 }, /* R3641 - EQ2_20 */ + { 0x00000E3A, 0x0B75 }, /* R3642 - EQ2_21 */ + { 0x00000E80, 0x0018 }, /* R3712 - DRC1 ctrl1 */ + { 0x00000E81, 0x0933 }, /* R3713 - DRC1 ctrl2 */ + { 0x00000E82, 0x0018 }, /* R3714 - DRC1 ctrl3 */ + { 0x00000E83, 0x0000 }, /* R3715 - DRC1 ctrl4 */ + { 0x00000E84, 0x0000 }, /* R3716 - DRC1 ctrl5 */ + { 0x00000E89, 0x0018 }, /* R3721 - DRC2 ctrl1 */ + { 0x00000E8A, 0x0933 }, /* R3722 - DRC2 ctrl2 */ + { 0x00000E8B, 0x0018 }, /* R3723 - DRC2 ctrl3 */ + { 0x00000E8C, 0x0000 }, /* R3724 - DRC2 ctrl4 */ + { 0x00000E8D, 0x0000 }, /* R3725 - DRC2 ctrl5 */ + { 0x00000EC0, 0x0000 }, /* R3776 - HPLPF1_1 */ + { 0x00000EC1, 0x0000 }, /* R3777 - HPLPF1_2 */ + { 0x00000EC4, 0x0000 }, /* R3780 - HPLPF2_1 */ + { 0x00000EC5, 0x0000 }, /* R3781 - HPLPF2_2 */ + { 0x00000EC8, 0x0000 }, /* R3784 - HPLPF3_1 */ + { 0x00000EC9, 0x0000 }, /* R3785 - HPLPF3_2 */ + { 0x00000ECC, 0x0000 }, /* R3788 - HPLPF4_1 */ + { 0x00000ECD, 0x0000 }, /* R3789 - HPLPF4_2 */ + { 0x00000EE0, 0x0000 }, /* R3808 - ASRC_ENABLE */ + { 0x00000EE2, 0x0000 }, /* R3810 - ASRC_RATE1 */ + { 0x00000EE3, 0x4000 }, /* R3811 - ASRC_RATE2 */ + { 0x00000EF0, 0x0000 }, /* R3824 - ISRC 1 CTRL 1 */ + { 0x00000EF1, 0x0000 }, /* R3825 - ISRC 1 CTRL 2 */ + { 0x00000EF2, 0x0000 }, /* R3826 - ISRC 1 CTRL 3 */ + { 0x00000EF3, 0x0000 }, /* R3827 - ISRC 2 CTRL 1 */ + { 0x00000EF4, 0x0000 }, /* R3828 - ISRC 2 CTRL 2 */ + { 0x00000EF5, 0x0000 }, /* R3829 - ISRC 2 CTRL 3 */ + { 0x00000EF6, 0x0000 }, /* R3830 - ISRC 3 CTRL 1 */ + { 0x00000EF7, 0x0000 }, /* R3831 - ISRC 3 CTRL 2 */ + { 0x00000EF8, 0x0000 }, /* R3832 - ISRC 3 CTRL 3 */ + { 0x00001200, 0x0010 }, /* R4608 - DSP2 Control 1 */ + { 0x00001300, 0x0010 }, /* R4864 - DSP3 Control 1 */ +}; + +static bool cs47l24_is_adsp_memory(unsigned int reg) +{ + switch (reg) { + case 0x200000 ... 0x205fff: /* DSP2 PM */ + case 0x280000 ... 0x281fff: /* DSP2 ZM */ + case 0x290000 ... 0x2a7fff: /* DSP2 XM */ + case 0x2a8000 ... 0x2b3fff: /* DSP2 YM */ + case 0x300000 ... 0x308fff: /* DSP3 PM */ + case 0x380000 ... 0x381fff: /* DSP3 ZM */ + case 0x390000 ... 0x3a7fff: /* DSP3 XM */ + case 0x3a8000 ... 0x3b3fff: /* DSP3 YM */ + return true; + default: + return false; + } +} + +static bool cs47l24_readable_register(struct device *dev, unsigned int reg) +{ + switch (reg) { + case ARIZONA_SOFTWARE_RESET: + case ARIZONA_DEVICE_REVISION: + case ARIZONA_CTRL_IF_SPI_CFG_1: + case ARIZONA_WRITE_SEQUENCER_CTRL_0: + case ARIZONA_WRITE_SEQUENCER_CTRL_1: + case ARIZONA_WRITE_SEQUENCER_CTRL_2: + case ARIZONA_TONE_GENERATOR_1: + case ARIZONA_TONE_GENERATOR_2: + case ARIZONA_TONE_GENERATOR_3: + case ARIZONA_TONE_GENERATOR_4: + case ARIZONA_TONE_GENERATOR_5: + case ARIZONA_PWM_DRIVE_1: + case ARIZONA_PWM_DRIVE_2: + case ARIZONA_PWM_DRIVE_3: + case ARIZONA_SEQUENCE_CONTROL: + case ARIZONA_SAMPLE_RATE_SEQUENCE_SELECT_1: + case ARIZONA_SAMPLE_RATE_SEQUENCE_SELECT_2: + case ARIZONA_SAMPLE_RATE_SEQUENCE_SELECT_3: + case ARIZONA_SAMPLE_RATE_SEQUENCE_SELECT_4: + case ARIZONA_COMFORT_NOISE_GENERATOR: + case ARIZONA_HAPTICS_CONTROL_1: + case ARIZONA_HAPTICS_CONTROL_2: + case ARIZONA_HAPTICS_PHASE_1_INTENSITY: + case ARIZONA_HAPTICS_PHASE_1_DURATION: + case ARIZONA_HAPTICS_PHASE_2_INTENSITY: + case ARIZONA_HAPTICS_PHASE_2_DURATION: + case ARIZONA_HAPTICS_PHASE_3_INTENSITY: + case ARIZONA_HAPTICS_PHASE_3_DURATION: + case ARIZONA_HAPTICS_STATUS: + case ARIZONA_CLOCK_32K_1: + case ARIZONA_SYSTEM_CLOCK_1: + case ARIZONA_SAMPLE_RATE_1: + case ARIZONA_SAMPLE_RATE_2: + case ARIZONA_SAMPLE_RATE_3: + case ARIZONA_SAMPLE_RATE_1_STATUS: + case ARIZONA_SAMPLE_RATE_2_STATUS: + case ARIZONA_SAMPLE_RATE_3_STATUS: + case ARIZONA_ASYNC_CLOCK_1: + case ARIZONA_ASYNC_SAMPLE_RATE_1: + case ARIZONA_ASYNC_SAMPLE_RATE_1_STATUS: + case ARIZONA_ASYNC_SAMPLE_RATE_2: + case ARIZONA_ASYNC_SAMPLE_RATE_2_STATUS: + case ARIZONA_OUTPUT_SYSTEM_CLOCK: + case ARIZONA_OUTPUT_ASYNC_CLOCK: + case ARIZONA_RATE_ESTIMATOR_1: + case ARIZONA_RATE_ESTIMATOR_2: + case ARIZONA_RATE_ESTIMATOR_3: + case ARIZONA_RATE_ESTIMATOR_4: + case ARIZONA_RATE_ESTIMATOR_5: + case ARIZONA_FLL1_CONTROL_1: + case ARIZONA_FLL1_CONTROL_2: + case ARIZONA_FLL1_CONTROL_3: + case ARIZONA_FLL1_CONTROL_4: + case ARIZONA_FLL1_CONTROL_5: + case ARIZONA_FLL1_CONTROL_6: + case ARIZONA_FLL1_CONTROL_7: + case ARIZONA_FLL1_LOOP_FILTER_TEST_1: + case ARIZONA_FLL1_NCO_TEST_0: + case ARIZONA_FLL1_SYNCHRONISER_1: + case ARIZONA_FLL1_SYNCHRONISER_2: + case ARIZONA_FLL1_SYNCHRONISER_3: + case ARIZONA_FLL1_SYNCHRONISER_4: + case ARIZONA_FLL1_SYNCHRONISER_5: + case ARIZONA_FLL1_SYNCHRONISER_6: + case ARIZONA_FLL1_SYNCHRONISER_7: + case ARIZONA_FLL1_SPREAD_SPECTRUM: + case ARIZONA_FLL1_GPIO_CLOCK: + case ARIZONA_FLL2_CONTROL_1: + case ARIZONA_FLL2_CONTROL_2: + case ARIZONA_FLL2_CONTROL_3: + case ARIZONA_FLL2_CONTROL_4: + case ARIZONA_FLL2_CONTROL_5: + case ARIZONA_FLL2_CONTROL_6: + case ARIZONA_FLL2_CONTROL_7: + case ARIZONA_FLL2_LOOP_FILTER_TEST_1: + case ARIZONA_FLL2_NCO_TEST_0: + case ARIZONA_FLL2_SYNCHRONISER_1: + case ARIZONA_FLL2_SYNCHRONISER_2: + case ARIZONA_FLL2_SYNCHRONISER_3: + case ARIZONA_FLL2_SYNCHRONISER_4: + case ARIZONA_FLL2_SYNCHRONISER_5: + case ARIZONA_FLL2_SYNCHRONISER_6: + case ARIZONA_FLL2_SYNCHRONISER_7: + case ARIZONA_FLL2_SPREAD_SPECTRUM: + case ARIZONA_FLL2_GPIO_CLOCK: + case ARIZONA_MIC_BIAS_CTRL_1: + case ARIZONA_MIC_BIAS_CTRL_2: + case ARIZONA_HP_CTRL_1L: + case ARIZONA_HP_CTRL_1R: + case ARIZONA_INPUT_ENABLES: + case ARIZONA_INPUT_ENABLES_STATUS: + case ARIZONA_INPUT_RATE: + case ARIZONA_INPUT_VOLUME_RAMP: + case ARIZONA_HPF_CONTROL: + case ARIZONA_IN1L_CONTROL: + case ARIZONA_ADC_DIGITAL_VOLUME_1L: + case ARIZONA_DMIC1L_CONTROL: + case ARIZONA_IN1R_CONTROL: + case ARIZONA_ADC_DIGITAL_VOLUME_1R: + case ARIZONA_DMIC1R_CONTROL: + case ARIZONA_IN2L_CONTROL: + case ARIZONA_ADC_DIGITAL_VOLUME_2L: + case ARIZONA_DMIC2L_CONTROL: + case ARIZONA_IN2R_CONTROL: + case ARIZONA_ADC_DIGITAL_VOLUME_2R: + case ARIZONA_DMIC2R_CONTROL: + case ARIZONA_OUTPUT_ENABLES_1: + case ARIZONA_OUTPUT_STATUS_1: + case ARIZONA_RAW_OUTPUT_STATUS_1: + case ARIZONA_OUTPUT_RATE_1: + case ARIZONA_OUTPUT_VOLUME_RAMP: + case ARIZONA_OUTPUT_PATH_CONFIG_1L: + case ARIZONA_DAC_DIGITAL_VOLUME_1L: + case ARIZONA_DAC_VOLUME_LIMIT_1L: + case ARIZONA_NOISE_GATE_SELECT_1L: + case ARIZONA_DAC_DIGITAL_VOLUME_1R: + case ARIZONA_DAC_VOLUME_LIMIT_1R: + case ARIZONA_NOISE_GATE_SELECT_1R: + case ARIZONA_DAC_DIGITAL_VOLUME_4L: + case ARIZONA_OUT_VOLUME_4L: + case ARIZONA_NOISE_GATE_SELECT_4L: + case ARIZONA_DAC_AEC_CONTROL_1: + case ARIZONA_NOISE_GATE_CONTROL: + case ARIZONA_HP1_SHORT_CIRCUIT_CTRL: + case ARIZONA_AIF1_BCLK_CTRL: + case ARIZONA_AIF1_TX_PIN_CTRL: + case ARIZONA_AIF1_RX_PIN_CTRL: + case ARIZONA_AIF1_RATE_CTRL: + case ARIZONA_AIF1_FORMAT: + case ARIZONA_AIF1_RX_BCLK_RATE: + case ARIZONA_AIF1_FRAME_CTRL_1: + case ARIZONA_AIF1_FRAME_CTRL_2: + case ARIZONA_AIF1_FRAME_CTRL_3: + case ARIZONA_AIF1_FRAME_CTRL_4: + case ARIZONA_AIF1_FRAME_CTRL_5: + case ARIZONA_AIF1_FRAME_CTRL_6: + case ARIZONA_AIF1_FRAME_CTRL_7: + case ARIZONA_AIF1_FRAME_CTRL_8: + case ARIZONA_AIF1_FRAME_CTRL_9: + case ARIZONA_AIF1_FRAME_CTRL_10: + case ARIZONA_AIF1_FRAME_CTRL_11: + case ARIZONA_AIF1_FRAME_CTRL_12: + case ARIZONA_AIF1_FRAME_CTRL_13: + case ARIZONA_AIF1_FRAME_CTRL_14: + case ARIZONA_AIF1_FRAME_CTRL_15: + case ARIZONA_AIF1_FRAME_CTRL_16: + case ARIZONA_AIF1_FRAME_CTRL_17: + case ARIZONA_AIF1_FRAME_CTRL_18: + case ARIZONA_AIF1_TX_ENABLES: + case ARIZONA_AIF1_RX_ENABLES: + case ARIZONA_AIF2_BCLK_CTRL: + case ARIZONA_AIF2_TX_PIN_CTRL: + case ARIZONA_AIF2_RX_PIN_CTRL: + case ARIZONA_AIF2_RATE_CTRL: + case ARIZONA_AIF2_FORMAT: + case ARIZONA_AIF2_RX_BCLK_RATE: + case ARIZONA_AIF2_FRAME_CTRL_1: + case ARIZONA_AIF2_FRAME_CTRL_2: + case ARIZONA_AIF2_FRAME_CTRL_3: + case ARIZONA_AIF2_FRAME_CTRL_4: + case ARIZONA_AIF2_FRAME_CTRL_5: + case ARIZONA_AIF2_FRAME_CTRL_6: + case ARIZONA_AIF2_FRAME_CTRL_7: + case ARIZONA_AIF2_FRAME_CTRL_8: + case ARIZONA_AIF2_FRAME_CTRL_11: + case ARIZONA_AIF2_FRAME_CTRL_12: + case ARIZONA_AIF2_FRAME_CTRL_13: + case ARIZONA_AIF2_FRAME_CTRL_14: + case ARIZONA_AIF2_FRAME_CTRL_15: + case ARIZONA_AIF2_FRAME_CTRL_16: + case ARIZONA_AIF2_TX_ENABLES: + case ARIZONA_AIF2_RX_ENABLES: + case ARIZONA_AIF3_BCLK_CTRL: + case ARIZONA_AIF3_TX_PIN_CTRL: + case ARIZONA_AIF3_RX_PIN_CTRL: + case ARIZONA_AIF3_RATE_CTRL: + case ARIZONA_AIF3_FORMAT: + case ARIZONA_AIF3_RX_BCLK_RATE: + case ARIZONA_AIF3_FRAME_CTRL_1: + case ARIZONA_AIF3_FRAME_CTRL_2: + case ARIZONA_AIF3_FRAME_CTRL_3: + case ARIZONA_AIF3_FRAME_CTRL_4: + case ARIZONA_AIF3_FRAME_CTRL_11: + case ARIZONA_AIF3_FRAME_CTRL_12: + case ARIZONA_AIF3_TX_ENABLES: + case ARIZONA_AIF3_RX_ENABLES: + case ARIZONA_PWM1MIX_INPUT_1_SOURCE: + case ARIZONA_PWM1MIX_INPUT_1_VOLUME: + case ARIZONA_PWM1MIX_INPUT_2_SOURCE: + case ARIZONA_PWM1MIX_INPUT_2_VOLUME: + case ARIZONA_PWM1MIX_INPUT_3_SOURCE: + case ARIZONA_PWM1MIX_INPUT_3_VOLUME: + case ARIZONA_PWM1MIX_INPUT_4_SOURCE: + case ARIZONA_PWM1MIX_INPUT_4_VOLUME: + case ARIZONA_PWM2MIX_INPUT_1_SOURCE: + case ARIZONA_PWM2MIX_INPUT_1_VOLUME: + case ARIZONA_PWM2MIX_INPUT_2_SOURCE: + case ARIZONA_PWM2MIX_INPUT_2_VOLUME: + case ARIZONA_PWM2MIX_INPUT_3_SOURCE: + case ARIZONA_PWM2MIX_INPUT_3_VOLUME: + case ARIZONA_PWM2MIX_INPUT_4_SOURCE: + case ARIZONA_PWM2MIX_INPUT_4_VOLUME: + case ARIZONA_OUT1LMIX_INPUT_1_SOURCE: + case ARIZONA_OUT1LMIX_INPUT_1_VOLUME: + case ARIZONA_OUT1LMIX_INPUT_2_SOURCE: + case ARIZONA_OUT1LMIX_INPUT_2_VOLUME: + case ARIZONA_OUT1LMIX_INPUT_3_SOURCE: + case ARIZONA_OUT1LMIX_INPUT_3_VOLUME: + case ARIZONA_OUT1LMIX_INPUT_4_SOURCE: + case ARIZONA_OUT1LMIX_INPUT_4_VOLUME: + case ARIZONA_OUT1RMIX_INPUT_1_SOURCE: + case ARIZONA_OUT1RMIX_INPUT_1_VOLUME: + case ARIZONA_OUT1RMIX_INPUT_2_SOURCE: + case ARIZONA_OUT1RMIX_INPUT_2_VOLUME: + case ARIZONA_OUT1RMIX_INPUT_3_SOURCE: + case ARIZONA_OUT1RMIX_INPUT_3_VOLUME: + case ARIZONA_OUT1RMIX_INPUT_4_SOURCE: + case ARIZONA_OUT1RMIX_INPUT_4_VOLUME: + case ARIZONA_OUT4LMIX_INPUT_1_SOURCE: + case ARIZONA_OUT4LMIX_INPUT_1_VOLUME: + case ARIZONA_OUT4LMIX_INPUT_2_SOURCE: + case ARIZONA_OUT4LMIX_INPUT_2_VOLUME: + case ARIZONA_OUT4LMIX_INPUT_3_SOURCE: + case ARIZONA_OUT4LMIX_INPUT_3_VOLUME: + case ARIZONA_OUT4LMIX_INPUT_4_SOURCE: + case ARIZONA_OUT4LMIX_INPUT_4_VOLUME: + case ARIZONA_AIF1TX1MIX_INPUT_1_SOURCE: + case ARIZONA_AIF1TX1MIX_INPUT_1_VOLUME: + case ARIZONA_AIF1TX1MIX_INPUT_2_SOURCE: + case ARIZONA_AIF1TX1MIX_INPUT_2_VOLUME: + case ARIZONA_AIF1TX1MIX_INPUT_3_SOURCE: + case ARIZONA_AIF1TX1MIX_INPUT_3_VOLUME: + case ARIZONA_AIF1TX1MIX_INPUT_4_SOURCE: + case ARIZONA_AIF1TX1MIX_INPUT_4_VOLUME: + case ARIZONA_AIF1TX2MIX_INPUT_1_SOURCE: + case ARIZONA_AIF1TX2MIX_INPUT_1_VOLUME: + case ARIZONA_AIF1TX2MIX_INPUT_2_SOURCE: + case ARIZONA_AIF1TX2MIX_INPUT_2_VOLUME: + case ARIZONA_AIF1TX2MIX_INPUT_3_SOURCE: + case ARIZONA_AIF1TX2MIX_INPUT_3_VOLUME: + case ARIZONA_AIF1TX2MIX_INPUT_4_SOURCE: + case ARIZONA_AIF1TX2MIX_INPUT_4_VOLUME: + case ARIZONA_AIF1TX3MIX_INPUT_1_SOURCE: + case ARIZONA_AIF1TX3MIX_INPUT_1_VOLUME: + case ARIZONA_AIF1TX3MIX_INPUT_2_SOURCE: + case ARIZONA_AIF1TX3MIX_INPUT_2_VOLUME: + case ARIZONA_AIF1TX3MIX_INPUT_3_SOURCE: + case ARIZONA_AIF1TX3MIX_INPUT_3_VOLUME: + case ARIZONA_AIF1TX3MIX_INPUT_4_SOURCE: + case ARIZONA_AIF1TX3MIX_INPUT_4_VOLUME: + case ARIZONA_AIF1TX4MIX_INPUT_1_SOURCE: + case ARIZONA_AIF1TX4MIX_INPUT_1_VOLUME: + case ARIZONA_AIF1TX4MIX_INPUT_2_SOURCE: + case ARIZONA_AIF1TX4MIX_INPUT_2_VOLUME: + case ARIZONA_AIF1TX4MIX_INPUT_3_SOURCE: + case ARIZONA_AIF1TX4MIX_INPUT_3_VOLUME: + case ARIZONA_AIF1TX4MIX_INPUT_4_SOURCE: + case ARIZONA_AIF1TX4MIX_INPUT_4_VOLUME: + case ARIZONA_AIF1TX5MIX_INPUT_1_SOURCE: + case ARIZONA_AIF1TX5MIX_INPUT_1_VOLUME: + case ARIZONA_AIF1TX5MIX_INPUT_2_SOURCE: + case ARIZONA_AIF1TX5MIX_INPUT_2_VOLUME: + case ARIZONA_AIF1TX5MIX_INPUT_3_SOURCE: + case ARIZONA_AIF1TX5MIX_INPUT_3_VOLUME: + case ARIZONA_AIF1TX5MIX_INPUT_4_SOURCE: + case ARIZONA_AIF1TX5MIX_INPUT_4_VOLUME: + case ARIZONA_AIF1TX6MIX_INPUT_1_SOURCE: + case ARIZONA_AIF1TX6MIX_INPUT_1_VOLUME: + case ARIZONA_AIF1TX6MIX_INPUT_2_SOURCE: + case ARIZONA_AIF1TX6MIX_INPUT_2_VOLUME: + case ARIZONA_AIF1TX6MIX_INPUT_3_SOURCE: + case ARIZONA_AIF1TX6MIX_INPUT_3_VOLUME: + case ARIZONA_AIF1TX6MIX_INPUT_4_SOURCE: + case ARIZONA_AIF1TX6MIX_INPUT_4_VOLUME: + case ARIZONA_AIF1TX7MIX_INPUT_1_SOURCE: + case ARIZONA_AIF1TX7MIX_INPUT_1_VOLUME: + case ARIZONA_AIF1TX7MIX_INPUT_2_SOURCE: + case ARIZONA_AIF1TX7MIX_INPUT_2_VOLUME: + case ARIZONA_AIF1TX7MIX_INPUT_3_SOURCE: + case ARIZONA_AIF1TX7MIX_INPUT_3_VOLUME: + case ARIZONA_AIF1TX7MIX_INPUT_4_SOURCE: + case ARIZONA_AIF1TX7MIX_INPUT_4_VOLUME: + case ARIZONA_AIF1TX8MIX_INPUT_1_SOURCE: + case ARIZONA_AIF1TX8MIX_INPUT_1_VOLUME: + case ARIZONA_AIF1TX8MIX_INPUT_2_SOURCE: + case ARIZONA_AIF1TX8MIX_INPUT_2_VOLUME: + case ARIZONA_AIF1TX8MIX_INPUT_3_SOURCE: + case ARIZONA_AIF1TX8MIX_INPUT_3_VOLUME: + case ARIZONA_AIF1TX8MIX_INPUT_4_SOURCE: + case ARIZONA_AIF1TX8MIX_INPUT_4_VOLUME: + case ARIZONA_AIF2TX1MIX_INPUT_1_SOURCE: + case ARIZONA_AIF2TX1MIX_INPUT_1_VOLUME: + case ARIZONA_AIF2TX1MIX_INPUT_2_SOURCE: + case ARIZONA_AIF2TX1MIX_INPUT_2_VOLUME: + case ARIZONA_AIF2TX1MIX_INPUT_3_SOURCE: + case ARIZONA_AIF2TX1MIX_INPUT_3_VOLUME: + case ARIZONA_AIF2TX1MIX_INPUT_4_SOURCE: + case ARIZONA_AIF2TX1MIX_INPUT_4_VOLUME: + case ARIZONA_AIF2TX2MIX_INPUT_1_SOURCE: + case ARIZONA_AIF2TX2MIX_INPUT_1_VOLUME: + case ARIZONA_AIF2TX2MIX_INPUT_2_SOURCE: + case ARIZONA_AIF2TX2MIX_INPUT_2_VOLUME: + case ARIZONA_AIF2TX2MIX_INPUT_3_SOURCE: + case ARIZONA_AIF2TX2MIX_INPUT_3_VOLUME: + case ARIZONA_AIF2TX2MIX_INPUT_4_SOURCE: + case ARIZONA_AIF2TX2MIX_INPUT_4_VOLUME: + case ARIZONA_AIF2TX3MIX_INPUT_1_SOURCE: + case ARIZONA_AIF2TX3MIX_INPUT_1_VOLUME: + case ARIZONA_AIF2TX3MIX_INPUT_2_SOURCE: + case ARIZONA_AIF2TX3MIX_INPUT_2_VOLUME: + case ARIZONA_AIF2TX3MIX_INPUT_3_SOURCE: + case ARIZONA_AIF2TX3MIX_INPUT_3_VOLUME: + case ARIZONA_AIF2TX3MIX_INPUT_4_SOURCE: + case ARIZONA_AIF2TX3MIX_INPUT_4_VOLUME: + case ARIZONA_AIF2TX4MIX_INPUT_1_SOURCE: + case ARIZONA_AIF2TX4MIX_INPUT_1_VOLUME: + case ARIZONA_AIF2TX4MIX_INPUT_2_SOURCE: + case ARIZONA_AIF2TX4MIX_INPUT_2_VOLUME: + case ARIZONA_AIF2TX4MIX_INPUT_3_SOURCE: + case ARIZONA_AIF2TX4MIX_INPUT_3_VOLUME: + case ARIZONA_AIF2TX4MIX_INPUT_4_SOURCE: + case ARIZONA_AIF2TX4MIX_INPUT_4_VOLUME: + case ARIZONA_AIF2TX5MIX_INPUT_1_SOURCE: + case ARIZONA_AIF2TX5MIX_INPUT_1_VOLUME: + case ARIZONA_AIF2TX5MIX_INPUT_2_SOURCE: + case ARIZONA_AIF2TX5MIX_INPUT_2_VOLUME: + case ARIZONA_AIF2TX5MIX_INPUT_3_SOURCE: + case ARIZONA_AIF2TX5MIX_INPUT_3_VOLUME: + case ARIZONA_AIF2TX5MIX_INPUT_4_SOURCE: + case ARIZONA_AIF2TX5MIX_INPUT_4_VOLUME: + case ARIZONA_AIF2TX6MIX_INPUT_1_SOURCE: + case ARIZONA_AIF2TX6MIX_INPUT_1_VOLUME: + case ARIZONA_AIF2TX6MIX_INPUT_2_SOURCE: + case ARIZONA_AIF2TX6MIX_INPUT_2_VOLUME: + case ARIZONA_AIF2TX6MIX_INPUT_3_SOURCE: + case ARIZONA_AIF2TX6MIX_INPUT_3_VOLUME: + case ARIZONA_AIF2TX6MIX_INPUT_4_SOURCE: + case ARIZONA_AIF2TX6MIX_INPUT_4_VOLUME: + case ARIZONA_AIF3TX1MIX_INPUT_1_SOURCE: + case ARIZONA_AIF3TX1MIX_INPUT_1_VOLUME: + case ARIZONA_AIF3TX1MIX_INPUT_2_SOURCE: + case ARIZONA_AIF3TX1MIX_INPUT_2_VOLUME: + case ARIZONA_AIF3TX1MIX_INPUT_3_SOURCE: + case ARIZONA_AIF3TX1MIX_INPUT_3_VOLUME: + case ARIZONA_AIF3TX1MIX_INPUT_4_SOURCE: + case ARIZONA_AIF3TX1MIX_INPUT_4_VOLUME: + case ARIZONA_AIF3TX2MIX_INPUT_1_SOURCE: + case ARIZONA_AIF3TX2MIX_INPUT_1_VOLUME: + case ARIZONA_AIF3TX2MIX_INPUT_2_SOURCE: + case ARIZONA_AIF3TX2MIX_INPUT_2_VOLUME: + case ARIZONA_AIF3TX2MIX_INPUT_3_SOURCE: + case ARIZONA_AIF3TX2MIX_INPUT_3_VOLUME: + case ARIZONA_AIF3TX2MIX_INPUT_4_SOURCE: + case ARIZONA_AIF3TX2MIX_INPUT_4_VOLUME: + case ARIZONA_EQ1MIX_INPUT_1_SOURCE: + case ARIZONA_EQ1MIX_INPUT_1_VOLUME: + case ARIZONA_EQ1MIX_INPUT_2_SOURCE: + case ARIZONA_EQ1MIX_INPUT_2_VOLUME: + case ARIZONA_EQ1MIX_INPUT_3_SOURCE: + case ARIZONA_EQ1MIX_INPUT_3_VOLUME: + case ARIZONA_EQ1MIX_INPUT_4_SOURCE: + case ARIZONA_EQ1MIX_INPUT_4_VOLUME: + case ARIZONA_EQ2MIX_INPUT_1_SOURCE: + case ARIZONA_EQ2MIX_INPUT_1_VOLUME: + case ARIZONA_EQ2MIX_INPUT_2_SOURCE: + case ARIZONA_EQ2MIX_INPUT_2_VOLUME: + case ARIZONA_EQ2MIX_INPUT_3_SOURCE: + case ARIZONA_EQ2MIX_INPUT_3_VOLUME: + case ARIZONA_EQ2MIX_INPUT_4_SOURCE: + case ARIZONA_EQ2MIX_INPUT_4_VOLUME: + case ARIZONA_DRC1LMIX_INPUT_1_SOURCE: + case ARIZONA_DRC1LMIX_INPUT_1_VOLUME: + case ARIZONA_DRC1LMIX_INPUT_2_SOURCE: + case ARIZONA_DRC1LMIX_INPUT_2_VOLUME: + case ARIZONA_DRC1LMIX_INPUT_3_SOURCE: + case ARIZONA_DRC1LMIX_INPUT_3_VOLUME: + case ARIZONA_DRC1LMIX_INPUT_4_SOURCE: + case ARIZONA_DRC1LMIX_INPUT_4_VOLUME: + case ARIZONA_DRC1RMIX_INPUT_1_SOURCE: + case ARIZONA_DRC1RMIX_INPUT_1_VOLUME: + case ARIZONA_DRC1RMIX_INPUT_2_SOURCE: + case ARIZONA_DRC1RMIX_INPUT_2_VOLUME: + case ARIZONA_DRC1RMIX_INPUT_3_SOURCE: + case ARIZONA_DRC1RMIX_INPUT_3_VOLUME: + case ARIZONA_DRC1RMIX_INPUT_4_SOURCE: + case ARIZONA_DRC1RMIX_INPUT_4_VOLUME: + case ARIZONA_DRC2LMIX_INPUT_1_SOURCE: + case ARIZONA_DRC2LMIX_INPUT_1_VOLUME: + case ARIZONA_DRC2LMIX_INPUT_2_SOURCE: + case ARIZONA_DRC2LMIX_INPUT_2_VOLUME: + case ARIZONA_DRC2LMIX_INPUT_3_SOURCE: + case ARIZONA_DRC2LMIX_INPUT_3_VOLUME: + case ARIZONA_DRC2LMIX_INPUT_4_SOURCE: + case ARIZONA_DRC2LMIX_INPUT_4_VOLUME: + case ARIZONA_DRC2RMIX_INPUT_1_SOURCE: + case ARIZONA_DRC2RMIX_INPUT_1_VOLUME: + case ARIZONA_DRC2RMIX_INPUT_2_SOURCE: + case ARIZONA_DRC2RMIX_INPUT_2_VOLUME: + case ARIZONA_DRC2RMIX_INPUT_3_SOURCE: + case ARIZONA_DRC2RMIX_INPUT_3_VOLUME: + case ARIZONA_DRC2RMIX_INPUT_4_SOURCE: + case ARIZONA_DRC2RMIX_INPUT_4_VOLUME: + case ARIZONA_HPLP1MIX_INPUT_1_SOURCE: + case ARIZONA_HPLP1MIX_INPUT_1_VOLUME: + case ARIZONA_HPLP1MIX_INPUT_2_SOURCE: + case ARIZONA_HPLP1MIX_INPUT_2_VOLUME: + case ARIZONA_HPLP1MIX_INPUT_3_SOURCE: + case ARIZONA_HPLP1MIX_INPUT_3_VOLUME: + case ARIZONA_HPLP1MIX_INPUT_4_SOURCE: + case ARIZONA_HPLP1MIX_INPUT_4_VOLUME: + case ARIZONA_HPLP2MIX_INPUT_1_SOURCE: + case ARIZONA_HPLP2MIX_INPUT_1_VOLUME: + case ARIZONA_HPLP2MIX_INPUT_2_SOURCE: + case ARIZONA_HPLP2MIX_INPUT_2_VOLUME: + case ARIZONA_HPLP2MIX_INPUT_3_SOURCE: + case ARIZONA_HPLP2MIX_INPUT_3_VOLUME: + case ARIZONA_HPLP2MIX_INPUT_4_SOURCE: + case ARIZONA_HPLP2MIX_INPUT_4_VOLUME: + case ARIZONA_HPLP3MIX_INPUT_1_SOURCE: + case ARIZONA_HPLP3MIX_INPUT_1_VOLUME: + case ARIZONA_HPLP3MIX_INPUT_2_SOURCE: + case ARIZONA_HPLP3MIX_INPUT_2_VOLUME: + case ARIZONA_HPLP3MIX_INPUT_3_SOURCE: + case ARIZONA_HPLP3MIX_INPUT_3_VOLUME: + case ARIZONA_HPLP3MIX_INPUT_4_SOURCE: + case ARIZONA_HPLP3MIX_INPUT_4_VOLUME: + case ARIZONA_HPLP4MIX_INPUT_1_SOURCE: + case ARIZONA_HPLP4MIX_INPUT_1_VOLUME: + case ARIZONA_HPLP4MIX_INPUT_2_SOURCE: + case ARIZONA_HPLP4MIX_INPUT_2_VOLUME: + case ARIZONA_HPLP4MIX_INPUT_3_SOURCE: + case ARIZONA_HPLP4MIX_INPUT_3_VOLUME: + case ARIZONA_HPLP4MIX_INPUT_4_SOURCE: + case ARIZONA_HPLP4MIX_INPUT_4_VOLUME: + case ARIZONA_DSP2LMIX_INPUT_1_SOURCE: + case ARIZONA_DSP2LMIX_INPUT_1_VOLUME: + case ARIZONA_DSP2LMIX_INPUT_2_SOURCE: + case ARIZONA_DSP2LMIX_INPUT_2_VOLUME: + case ARIZONA_DSP2LMIX_INPUT_3_SOURCE: + case ARIZONA_DSP2LMIX_INPUT_3_VOLUME: + case ARIZONA_DSP2LMIX_INPUT_4_SOURCE: + case ARIZONA_DSP2LMIX_INPUT_4_VOLUME: + case ARIZONA_DSP2RMIX_INPUT_1_SOURCE: + case ARIZONA_DSP2RMIX_INPUT_1_VOLUME: + case ARIZONA_DSP2RMIX_INPUT_2_SOURCE: + case ARIZONA_DSP2RMIX_INPUT_2_VOLUME: + case ARIZONA_DSP2RMIX_INPUT_3_SOURCE: + case ARIZONA_DSP2RMIX_INPUT_3_VOLUME: + case ARIZONA_DSP2RMIX_INPUT_4_SOURCE: + case ARIZONA_DSP2RMIX_INPUT_4_VOLUME: + case ARIZONA_DSP2AUX1MIX_INPUT_1_SOURCE: + case ARIZONA_DSP2AUX2MIX_INPUT_1_SOURCE: + case ARIZONA_DSP2AUX3MIX_INPUT_1_SOURCE: + case ARIZONA_DSP2AUX4MIX_INPUT_1_SOURCE: + case ARIZONA_DSP2AUX5MIX_INPUT_1_SOURCE: + case ARIZONA_DSP2AUX6MIX_INPUT_1_SOURCE: + case ARIZONA_DSP3LMIX_INPUT_1_SOURCE: + case ARIZONA_DSP3LMIX_INPUT_1_VOLUME: + case ARIZONA_DSP3LMIX_INPUT_2_SOURCE: + case ARIZONA_DSP3LMIX_INPUT_2_VOLUME: + case ARIZONA_DSP3LMIX_INPUT_3_SOURCE: + case ARIZONA_DSP3LMIX_INPUT_3_VOLUME: + case ARIZONA_DSP3LMIX_INPUT_4_SOURCE: + case ARIZONA_DSP3LMIX_INPUT_4_VOLUME: + case ARIZONA_DSP3RMIX_INPUT_1_SOURCE: + case ARIZONA_DSP3RMIX_INPUT_1_VOLUME: + case ARIZONA_DSP3RMIX_INPUT_2_SOURCE: + case ARIZONA_DSP3RMIX_INPUT_2_VOLUME: + case ARIZONA_DSP3RMIX_INPUT_3_SOURCE: + case ARIZONA_DSP3RMIX_INPUT_3_VOLUME: + case ARIZONA_DSP3RMIX_INPUT_4_SOURCE: + case ARIZONA_DSP3RMIX_INPUT_4_VOLUME: + case ARIZONA_DSP3AUX1MIX_INPUT_1_SOURCE: + case ARIZONA_DSP3AUX2MIX_INPUT_1_SOURCE: + case ARIZONA_DSP3AUX3MIX_INPUT_1_SOURCE: + case ARIZONA_DSP3AUX4MIX_INPUT_1_SOURCE: + case ARIZONA_DSP3AUX5MIX_INPUT_1_SOURCE: + case ARIZONA_DSP3AUX6MIX_INPUT_1_SOURCE: + case ARIZONA_ASRC1LMIX_INPUT_1_SOURCE: + case ARIZONA_ASRC1RMIX_INPUT_1_SOURCE: + case ARIZONA_ASRC2LMIX_INPUT_1_SOURCE: + case ARIZONA_ASRC2RMIX_INPUT_1_SOURCE: + case ARIZONA_ISRC1DEC1MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC1DEC2MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC1DEC3MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC1DEC4MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC1INT1MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC1INT2MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC1INT3MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC1INT4MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC2DEC1MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC2DEC2MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC2DEC3MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC2DEC4MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC2INT1MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC2INT2MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC2INT3MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC2INT4MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC3DEC1MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC3DEC2MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC3DEC3MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC3DEC4MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC3INT1MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC3INT2MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC3INT3MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC3INT4MIX_INPUT_1_SOURCE: + case ARIZONA_GPIO1_CTRL: + case ARIZONA_GPIO2_CTRL: + case ARIZONA_IRQ_CTRL_1: + case ARIZONA_GPIO_DEBOUNCE_CONFIG: + case ARIZONA_MISC_PAD_CTRL_1: + case ARIZONA_MISC_PAD_CTRL_2: + case ARIZONA_MISC_PAD_CTRL_3: + case ARIZONA_MISC_PAD_CTRL_4: + case ARIZONA_MISC_PAD_CTRL_5: + case ARIZONA_MISC_PAD_CTRL_6: + case ARIZONA_MISC_PAD_CTRL_7: + case ARIZONA_MISC_PAD_CTRL_9: + case ARIZONA_MISC_PAD_CTRL_10: + case ARIZONA_MISC_PAD_CTRL_11: + case ARIZONA_MISC_PAD_CTRL_12: + case ARIZONA_MISC_PAD_CTRL_13: + case ARIZONA_MISC_PAD_CTRL_14: + case ARIZONA_MISC_PAD_CTRL_16: + case ARIZONA_INTERRUPT_STATUS_1: + case ARIZONA_INTERRUPT_STATUS_2: + case ARIZONA_INTERRUPT_STATUS_3: + case ARIZONA_INTERRUPT_STATUS_4: + case ARIZONA_INTERRUPT_STATUS_5: + case ARIZONA_INTERRUPT_STATUS_6: + case ARIZONA_INTERRUPT_STATUS_1_MASK: + case ARIZONA_INTERRUPT_STATUS_2_MASK: + case ARIZONA_INTERRUPT_STATUS_3_MASK: + case ARIZONA_INTERRUPT_STATUS_4_MASK: + case ARIZONA_INTERRUPT_STATUS_5_MASK: + case ARIZONA_INTERRUPT_STATUS_6_MASK: + case ARIZONA_INTERRUPT_CONTROL: + case ARIZONA_IRQ2_STATUS_1: + case ARIZONA_IRQ2_STATUS_2: + case ARIZONA_IRQ2_STATUS_3: + case ARIZONA_IRQ2_STATUS_4: + case ARIZONA_IRQ2_STATUS_5: + case ARIZONA_IRQ2_STATUS_6: + case ARIZONA_IRQ2_STATUS_1_MASK: + case ARIZONA_IRQ2_STATUS_2_MASK: + case ARIZONA_IRQ2_STATUS_3_MASK: + case ARIZONA_IRQ2_STATUS_4_MASK: + case ARIZONA_IRQ2_STATUS_5_MASK: + case ARIZONA_IRQ2_STATUS_6_MASK: + case ARIZONA_IRQ2_CONTROL: + case ARIZONA_INTERRUPT_RAW_STATUS_2: + case ARIZONA_INTERRUPT_RAW_STATUS_3: + case ARIZONA_INTERRUPT_RAW_STATUS_4: + case ARIZONA_INTERRUPT_RAW_STATUS_5: + case ARIZONA_INTERRUPT_RAW_STATUS_6: + case ARIZONA_INTERRUPT_RAW_STATUS_7: + case ARIZONA_INTERRUPT_RAW_STATUS_8: + case ARIZONA_INTERRUPT_RAW_STATUS_9: + case ARIZONA_IRQ_PIN_STATUS: + case ARIZONA_FX_CTRL1: + case ARIZONA_FX_CTRL2: + case ARIZONA_EQ1_1: + case ARIZONA_EQ1_2: + case ARIZONA_EQ1_3: + case ARIZONA_EQ1_4: + case ARIZONA_EQ1_5: + case ARIZONA_EQ1_6: + case ARIZONA_EQ1_7: + case ARIZONA_EQ1_8: + case ARIZONA_EQ1_9: + case ARIZONA_EQ1_10: + case ARIZONA_EQ1_11: + case ARIZONA_EQ1_12: + case ARIZONA_EQ1_13: + case ARIZONA_EQ1_14: + case ARIZONA_EQ1_15: + case ARIZONA_EQ1_16: + case ARIZONA_EQ1_17: + case ARIZONA_EQ1_18: + case ARIZONA_EQ1_19: + case ARIZONA_EQ1_20: + case ARIZONA_EQ1_21: + case ARIZONA_EQ2_1: + case ARIZONA_EQ2_2: + case ARIZONA_EQ2_3: + case ARIZONA_EQ2_4: + case ARIZONA_EQ2_5: + case ARIZONA_EQ2_6: + case ARIZONA_EQ2_7: + case ARIZONA_EQ2_8: + case ARIZONA_EQ2_9: + case ARIZONA_EQ2_10: + case ARIZONA_EQ2_11: + case ARIZONA_EQ2_12: + case ARIZONA_EQ2_13: + case ARIZONA_EQ2_14: + case ARIZONA_EQ2_15: + case ARIZONA_EQ2_16: + case ARIZONA_EQ2_17: + case ARIZONA_EQ2_18: + case ARIZONA_EQ2_19: + case ARIZONA_EQ2_20: + case ARIZONA_EQ2_21: + case ARIZONA_DRC1_CTRL1: + case ARIZONA_DRC1_CTRL2: + case ARIZONA_DRC1_CTRL3: + case ARIZONA_DRC1_CTRL4: + case ARIZONA_DRC1_CTRL5: + case ARIZONA_DRC2_CTRL1: + case ARIZONA_DRC2_CTRL2: + case ARIZONA_DRC2_CTRL3: + case ARIZONA_DRC2_CTRL4: + case ARIZONA_DRC2_CTRL5: + case ARIZONA_HPLPF1_1: + case ARIZONA_HPLPF1_2: + case ARIZONA_HPLPF2_1: + case ARIZONA_HPLPF2_2: + case ARIZONA_HPLPF3_1: + case ARIZONA_HPLPF3_2: + case ARIZONA_HPLPF4_1: + case ARIZONA_HPLPF4_2: + case ARIZONA_ASRC_ENABLE: + case ARIZONA_ASRC_STATUS: + case ARIZONA_ASRC_RATE1: + case ARIZONA_ASRC_RATE2: + case ARIZONA_ISRC_1_CTRL_1: + case ARIZONA_ISRC_1_CTRL_2: + case ARIZONA_ISRC_1_CTRL_3: + case ARIZONA_ISRC_2_CTRL_1: + case ARIZONA_ISRC_2_CTRL_2: + case ARIZONA_ISRC_2_CTRL_3: + case ARIZONA_ISRC_3_CTRL_1: + case ARIZONA_ISRC_3_CTRL_2: + case ARIZONA_ISRC_3_CTRL_3: + case ARIZONA_DSP2_CONTROL_1: + case ARIZONA_DSP2_CLOCKING_1: + case ARIZONA_DSP2_STATUS_1: + case ARIZONA_DSP2_STATUS_2: + case ARIZONA_DSP2_STATUS_3: + case ARIZONA_DSP2_STATUS_4: + case ARIZONA_DSP2_WDMA_BUFFER_1: + case ARIZONA_DSP2_WDMA_BUFFER_2: + case ARIZONA_DSP2_WDMA_BUFFER_3: + case ARIZONA_DSP2_WDMA_BUFFER_4: + case ARIZONA_DSP2_WDMA_BUFFER_5: + case ARIZONA_DSP2_WDMA_BUFFER_6: + case ARIZONA_DSP2_WDMA_BUFFER_7: + case ARIZONA_DSP2_WDMA_BUFFER_8: + case ARIZONA_DSP2_RDMA_BUFFER_1: + case ARIZONA_DSP2_RDMA_BUFFER_2: + case ARIZONA_DSP2_RDMA_BUFFER_3: + case ARIZONA_DSP2_RDMA_BUFFER_4: + case ARIZONA_DSP2_RDMA_BUFFER_5: + case ARIZONA_DSP2_RDMA_BUFFER_6: + case ARIZONA_DSP2_WDMA_CONFIG_1: + case ARIZONA_DSP2_WDMA_CONFIG_2: + case ARIZONA_DSP2_WDMA_OFFSET_1: + case ARIZONA_DSP2_RDMA_CONFIG_1: + case ARIZONA_DSP2_RDMA_OFFSET_1: + case ARIZONA_DSP2_EXTERNAL_START_SELECT_1: + case ARIZONA_DSP2_SCRATCH_0: + case ARIZONA_DSP2_SCRATCH_1: + case ARIZONA_DSP2_SCRATCH_2: + case ARIZONA_DSP2_SCRATCH_3: + case ARIZONA_DSP3_CONTROL_1: + case ARIZONA_DSP3_CLOCKING_1: + case ARIZONA_DSP3_STATUS_1: + case ARIZONA_DSP3_STATUS_2: + case ARIZONA_DSP3_STATUS_3: + case ARIZONA_DSP3_STATUS_4: + case ARIZONA_DSP3_WDMA_BUFFER_1: + case ARIZONA_DSP3_WDMA_BUFFER_2: + case ARIZONA_DSP3_WDMA_BUFFER_3: + case ARIZONA_DSP3_WDMA_BUFFER_4: + case ARIZONA_DSP3_WDMA_BUFFER_5: + case ARIZONA_DSP3_WDMA_BUFFER_6: + case ARIZONA_DSP3_WDMA_BUFFER_7: + case ARIZONA_DSP3_WDMA_BUFFER_8: + case ARIZONA_DSP3_RDMA_BUFFER_1: + case ARIZONA_DSP3_RDMA_BUFFER_2: + case ARIZONA_DSP3_RDMA_BUFFER_3: + case ARIZONA_DSP3_RDMA_BUFFER_4: + case ARIZONA_DSP3_RDMA_BUFFER_5: + case ARIZONA_DSP3_RDMA_BUFFER_6: + case ARIZONA_DSP3_WDMA_CONFIG_1: + case ARIZONA_DSP3_WDMA_CONFIG_2: + case ARIZONA_DSP3_WDMA_OFFSET_1: + case ARIZONA_DSP3_RDMA_CONFIG_1: + case ARIZONA_DSP3_RDMA_OFFSET_1: + case ARIZONA_DSP3_EXTERNAL_START_SELECT_1: + case ARIZONA_DSP3_SCRATCH_0: + case ARIZONA_DSP3_SCRATCH_1: + case ARIZONA_DSP3_SCRATCH_2: + case ARIZONA_DSP3_SCRATCH_3: + return true; + default: + return cs47l24_is_adsp_memory(reg); + } +} + +static bool cs47l24_volatile_register(struct device *dev, unsigned int reg) +{ + switch (reg) { + case ARIZONA_SOFTWARE_RESET: + case ARIZONA_DEVICE_REVISION: + case ARIZONA_WRITE_SEQUENCER_CTRL_0: + case ARIZONA_WRITE_SEQUENCER_CTRL_1: + case ARIZONA_WRITE_SEQUENCER_CTRL_2: + case ARIZONA_HAPTICS_STATUS: + case ARIZONA_SAMPLE_RATE_1_STATUS: + case ARIZONA_SAMPLE_RATE_2_STATUS: + case ARIZONA_SAMPLE_RATE_3_STATUS: + case ARIZONA_ASYNC_SAMPLE_RATE_1_STATUS: + case ARIZONA_ASYNC_SAMPLE_RATE_2_STATUS: + case ARIZONA_HP_CTRL_1L: + case ARIZONA_HP_CTRL_1R: + case ARIZONA_INPUT_ENABLES_STATUS: + case ARIZONA_OUTPUT_STATUS_1: + case ARIZONA_RAW_OUTPUT_STATUS_1: + case ARIZONA_INTERRUPT_STATUS_1: + case ARIZONA_INTERRUPT_STATUS_2: + case ARIZONA_INTERRUPT_STATUS_3: + case ARIZONA_INTERRUPT_STATUS_4: + case ARIZONA_INTERRUPT_STATUS_5: + case ARIZONA_INTERRUPT_STATUS_6: + case ARIZONA_IRQ2_STATUS_1: + case ARIZONA_IRQ2_STATUS_2: + case ARIZONA_IRQ2_STATUS_3: + case ARIZONA_IRQ2_STATUS_4: + case ARIZONA_IRQ2_STATUS_5: + case ARIZONA_IRQ2_STATUS_6: + case ARIZONA_INTERRUPT_RAW_STATUS_2: + case ARIZONA_INTERRUPT_RAW_STATUS_3: + case ARIZONA_INTERRUPT_RAW_STATUS_4: + case ARIZONA_INTERRUPT_RAW_STATUS_5: + case ARIZONA_INTERRUPT_RAW_STATUS_6: + case ARIZONA_INTERRUPT_RAW_STATUS_7: + case ARIZONA_INTERRUPT_RAW_STATUS_8: + case ARIZONA_INTERRUPT_RAW_STATUS_9: + case ARIZONA_IRQ_PIN_STATUS: + case ARIZONA_FX_CTRL2: + case ARIZONA_ASRC_STATUS: + case ARIZONA_DSP2_STATUS_1: + case ARIZONA_DSP2_STATUS_2: + case ARIZONA_DSP2_STATUS_3: + case ARIZONA_DSP2_STATUS_4: + case ARIZONA_DSP2_WDMA_BUFFER_1: + case ARIZONA_DSP2_WDMA_BUFFER_2: + case ARIZONA_DSP2_WDMA_BUFFER_3: + case ARIZONA_DSP2_WDMA_BUFFER_4: + case ARIZONA_DSP2_WDMA_BUFFER_5: + case ARIZONA_DSP2_WDMA_BUFFER_6: + case ARIZONA_DSP2_WDMA_BUFFER_7: + case ARIZONA_DSP2_WDMA_BUFFER_8: + case ARIZONA_DSP2_RDMA_BUFFER_1: + case ARIZONA_DSP2_RDMA_BUFFER_2: + case ARIZONA_DSP2_RDMA_BUFFER_3: + case ARIZONA_DSP2_RDMA_BUFFER_4: + case ARIZONA_DSP2_RDMA_BUFFER_5: + case ARIZONA_DSP2_RDMA_BUFFER_6: + case ARIZONA_DSP2_WDMA_CONFIG_1: + case ARIZONA_DSP2_WDMA_CONFIG_2: + case ARIZONA_DSP2_WDMA_OFFSET_1: + case ARIZONA_DSP2_RDMA_CONFIG_1: + case ARIZONA_DSP2_RDMA_OFFSET_1: + case ARIZONA_DSP2_EXTERNAL_START_SELECT_1: + case ARIZONA_DSP2_SCRATCH_0: + case ARIZONA_DSP2_SCRATCH_1: + case ARIZONA_DSP2_SCRATCH_2: + case ARIZONA_DSP2_SCRATCH_3: + case ARIZONA_DSP2_CLOCKING_1: + case ARIZONA_DSP3_STATUS_1: + case ARIZONA_DSP3_STATUS_2: + case ARIZONA_DSP3_STATUS_3: + case ARIZONA_DSP3_STATUS_4: + case ARIZONA_DSP3_WDMA_BUFFER_1: + case ARIZONA_DSP3_WDMA_BUFFER_2: + case ARIZONA_DSP3_WDMA_BUFFER_3: + case ARIZONA_DSP3_WDMA_BUFFER_4: + case ARIZONA_DSP3_WDMA_BUFFER_5: + case ARIZONA_DSP3_WDMA_BUFFER_6: + case ARIZONA_DSP3_WDMA_BUFFER_7: + case ARIZONA_DSP3_WDMA_BUFFER_8: + case ARIZONA_DSP3_RDMA_BUFFER_1: + case ARIZONA_DSP3_RDMA_BUFFER_2: + case ARIZONA_DSP3_RDMA_BUFFER_3: + case ARIZONA_DSP3_RDMA_BUFFER_4: + case ARIZONA_DSP3_RDMA_BUFFER_5: + case ARIZONA_DSP3_RDMA_BUFFER_6: + case ARIZONA_DSP3_WDMA_CONFIG_1: + case ARIZONA_DSP3_WDMA_CONFIG_2: + case ARIZONA_DSP3_WDMA_OFFSET_1: + case ARIZONA_DSP3_RDMA_CONFIG_1: + case ARIZONA_DSP3_RDMA_OFFSET_1: + case ARIZONA_DSP3_EXTERNAL_START_SELECT_1: + case ARIZONA_DSP3_SCRATCH_0: + case ARIZONA_DSP3_SCRATCH_1: + case ARIZONA_DSP3_SCRATCH_2: + case ARIZONA_DSP3_SCRATCH_3: + case ARIZONA_DSP3_CLOCKING_1: + return true; + default: + return cs47l24_is_adsp_memory(reg); + } +} + +#define CS47L24_MAX_REGISTER 0x3b3fff + +const struct regmap_config cs47l24_spi_regmap = { + .reg_bits = 32, + .pad_bits = 16, + .val_bits = 16, + .reg_format_endian = REGMAP_ENDIAN_BIG, + .val_format_endian = REGMAP_ENDIAN_BIG, + + .max_register = CS47L24_MAX_REGISTER, + .readable_reg = cs47l24_readable_register, + .volatile_reg = cs47l24_volatile_register, + + .cache_type = REGCACHE_RBTREE, + .reg_defaults = cs47l24_reg_default, + .num_reg_defaults = ARRAY_SIZE(cs47l24_reg_default), +}; +EXPORT_SYMBOL_GPL(cs47l24_spi_regmap); + diff --git a/drivers/mfd/cs5535-mfd.c b/drivers/mfd/cs5535-mfd.c index be91cb5d6e78..f9d277ff4aaf 100644 --- a/drivers/mfd/cs5535-mfd.c +++ b/drivers/mfd/cs5535-mfd.c @@ -60,6 +60,7 @@ static int cs5535_mfd_res_enable(struct platform_device *pdev) static int cs5535_mfd_res_disable(struct platform_device *pdev) { struct resource *res; + res = platform_get_resource(pdev, IORESOURCE_IO, 0); if (!res) { dev_err(&pdev->dev, "can't fetch device resource info\n"); @@ -114,7 +115,10 @@ static struct mfd_cell cs5535_mfd_cells[] = { #ifdef CONFIG_OLPC static void cs5535_clone_olpc_cells(void) { - const char *acpi_clones[] = { "olpc-xo1-pm-acpi", "olpc-xo1-sci-acpi" }; + static const char *acpi_clones[] = { + "olpc-xo1-pm-acpi", + "olpc-xo1-sci-acpi" + }; if (!machine_is_olpc()) return; diff --git a/drivers/mfd/da903x.c b/drivers/mfd/da903x.c index 37e4426ef061..09f367571c58 100644 --- a/drivers/mfd/da903x.c +++ b/drivers/mfd/da903x.c @@ -2,10 +2,10 @@ * Base driver for Dialog Semiconductor DA9030/DA9034 * * Copyright (C) 2008 Compulab, Ltd. - * Mike Rapoport <mike@compulab.co.il> + * Mike Rapoport <mike@compulab.co.il> * * Copyright (C) 2006-2008 Marvell International Ltd. - * Eric Miao <eric.miao@marvell.com> + * Eric Miao <eric.miao@marvell.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 @@ -60,7 +60,7 @@ struct da903x_chip_ops { struct da903x_chip { struct i2c_client *client; struct device *dev; - struct da903x_chip_ops *ops; + const struct da903x_chip_ops *ops; int type; uint32_t events_mask; @@ -424,7 +424,7 @@ static irqreturn_t da903x_irq_handler(int irq, void *data) return IRQ_HANDLED; } -static struct da903x_chip_ops da903x_ops[] = { +static const struct da903x_chip_ops da903x_ops[] = { [0] = { .init_chip = da9030_init_chip, .unmask_events = da9030_unmask_events, @@ -565,6 +565,6 @@ static void __exit da903x_exit(void) module_exit(da903x_exit); MODULE_DESCRIPTION("PMIC Driver for Dialog Semiconductor DA9034"); -MODULE_AUTHOR("Eric Miao <eric.miao@marvell.com>" - "Mike Rapoport <mike@compulab.co.il>"); -MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Eric Miao <eric.miao@marvell.com>"); +MODULE_AUTHOR("Mike Rapoport <mike@compulab.co.il>"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/mfd/da9052-i2c.c b/drivers/mfd/da9052-i2c.c index 2697ffb08009..578e881067a5 100644 --- a/drivers/mfd/da9052-i2c.c +++ b/drivers/mfd/da9052-i2c.c @@ -70,7 +70,7 @@ static int da9052_i2c_fix(struct da9052 *da9052, unsigned char reg) case DA9053_BA: case DA9053_BB: /* A dummy read to a safe register address. */ - if (!i2c_safe_reg(reg)) + if (!i2c_safe_reg(reg)) return regmap_read(da9052->regmap, DA9052_PARK_REGISTER, &val); diff --git a/drivers/mfd/da9052-irq.c b/drivers/mfd/da9052-irq.c index f4cb4613140b..cd4ca849ca44 100644 --- a/drivers/mfd/da9052-irq.c +++ b/drivers/mfd/da9052-irq.c @@ -283,7 +283,7 @@ regmap_err: int da9052_irq_exit(struct da9052 *da9052) { - da9052_free_irq(da9052, DA9052_IRQ_ADC_EOM , da9052); + da9052_free_irq(da9052, DA9052_IRQ_ADC_EOM, da9052); regmap_del_irq_chip(da9052->chip_irq, da9052->irq_data); return 0; diff --git a/drivers/mfd/davinci_voicecodec.c b/drivers/mfd/davinci_voicecodec.c index 9bbc642a7b9d..dff2f19296b8 100644 --- a/drivers/mfd/davinci_voicecodec.c +++ b/drivers/mfd/davinci_voicecodec.c @@ -47,11 +47,8 @@ static int __init davinci_vc_probe(struct platform_device *pdev) davinci_vc = devm_kzalloc(&pdev->dev, sizeof(struct davinci_vc), GFP_KERNEL); - if (!davinci_vc) { - dev_dbg(&pdev->dev, - "could not allocate memory for private data\n"); + if (!davinci_vc) return -ENOMEM; - } davinci_vc->clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(davinci_vc->clk)) { diff --git a/drivers/mfd/dm355evm_msp.c b/drivers/mfd/dm355evm_msp.c index 4c826f78acd0..bf3e0b21b247 100644 --- a/drivers/mfd/dm355evm_msp.c +++ b/drivers/mfd/dm355evm_msp.c @@ -147,7 +147,7 @@ static int msp_gpio_get(struct gpio_chip *chip, unsigned offset) return status; if (reg == DM355EVM_MSP_LED) msp_led_cache = status; - return status & MSP_GPIO_MASK(offset); + return !!(status & MSP_GPIO_MASK(offset)); } static int msp_gpio_out(struct gpio_chip *chip, unsigned offset, int value) diff --git a/drivers/mfd/htc-egpio.c b/drivers/mfd/htc-egpio.c index 6ccaf90d98fd..e4f4a31b76d9 100644 --- a/drivers/mfd/htc-egpio.c +++ b/drivers/mfd/htc-egpio.c @@ -163,7 +163,7 @@ static int egpio_get(struct gpio_chip *chip, unsigned offset) value = egpio_readw(ei, reg); pr_debug("readw(%p + %x) = %x\n", ei->base_addr, reg << ei->bus_shift, value); - return value & bit; + return !!(value & bit); } static int egpio_direction_input(struct gpio_chip *chip, unsigned offset) diff --git a/drivers/mfd/lpc_ich.c b/drivers/mfd/lpc_ich.c index b514f3cf140d..bd3aa4578346 100644 --- a/drivers/mfd/lpc_ich.c +++ b/drivers/mfd/lpc_ich.c @@ -55,6 +55,7 @@ * document number TBD : Coleto Creek * document number TBD : Wildcat Point-LP * document number TBD : 9 Series + * document number TBD : Lewisburg */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -213,6 +214,7 @@ enum lpc_chipsets { LPC_COLETO, /* Coleto Creek */ LPC_WPT_LP, /* Wildcat Point-LP */ LPC_BRASWELL, /* Braswell SoC */ + LPC_LEWISBURG, /* Lewisburg */ LPC_9S, /* 9 Series */ }; @@ -521,6 +523,10 @@ static struct lpc_ich_info lpc_chipset_info[] = { .name = "Braswell SoC", .iTCO_version = 3, }, + [LPC_LEWISBURG] = { + .name = "Lewisburg", + .iTCO_version = 2, + }, [LPC_9S] = { .name = "9 Series", .iTCO_version = 2, @@ -757,6 +763,15 @@ static const struct pci_device_id lpc_ich_ids[] = { { PCI_VDEVICE(INTEL, 0x9cc6), LPC_WPT_LP}, { PCI_VDEVICE(INTEL, 0x9cc7), LPC_WPT_LP}, { PCI_VDEVICE(INTEL, 0x9cc9), LPC_WPT_LP}, + { PCI_VDEVICE(INTEL, 0xa1c1), LPC_LEWISBURG}, + { PCI_VDEVICE(INTEL, 0xa1c2), LPC_LEWISBURG}, + { PCI_VDEVICE(INTEL, 0xa1c3), LPC_LEWISBURG}, + { PCI_VDEVICE(INTEL, 0xa1c4), LPC_LEWISBURG}, + { PCI_VDEVICE(INTEL, 0xa1c5), LPC_LEWISBURG}, + { PCI_VDEVICE(INTEL, 0xa1c6), LPC_LEWISBURG}, + { PCI_VDEVICE(INTEL, 0xa1c7), LPC_LEWISBURG}, + { PCI_VDEVICE(INTEL, 0xa242), LPC_LEWISBURG}, + { PCI_VDEVICE(INTEL, 0xa243), LPC_LEWISBURG}, { 0, }, /* End of list */ }; MODULE_DEVICE_TABLE(pci, lpc_ich_ids); diff --git a/drivers/mfd/max14577.c b/drivers/mfd/max14577.c index 56e216dedc91..2280b3fdcf68 100644 --- a/drivers/mfd/max14577.c +++ b/drivers/mfd/max14577.c @@ -495,7 +495,7 @@ MODULE_DEVICE_TABLE(i2c, max14577_i2c_id); #ifdef CONFIG_PM_SLEEP static int max14577_suspend(struct device *dev) { - struct i2c_client *i2c = container_of(dev, struct i2c_client, dev); + struct i2c_client *i2c = to_i2c_client(dev); struct max14577 *max14577 = i2c_get_clientdata(i2c); if (device_may_wakeup(dev)) @@ -516,7 +516,7 @@ static int max14577_suspend(struct device *dev) static int max14577_resume(struct device *dev) { - struct i2c_client *i2c = container_of(dev, struct i2c_client, dev); + struct i2c_client *i2c = to_i2c_client(dev); struct max14577 *max14577 = i2c_get_clientdata(i2c); if (device_may_wakeup(dev)) diff --git a/drivers/mfd/max77686.c b/drivers/mfd/max77686.c index d19be64cd32b..d959ebbb2194 100644 --- a/drivers/mfd/max77686.c +++ b/drivers/mfd/max77686.c @@ -352,7 +352,7 @@ MODULE_DEVICE_TABLE(i2c, max77686_i2c_id); #ifdef CONFIG_PM_SLEEP static int max77686_suspend(struct device *dev) { - struct i2c_client *i2c = container_of(dev, struct i2c_client, dev); + struct i2c_client *i2c = to_i2c_client(dev); struct max77686_dev *max77686 = i2c_get_clientdata(i2c); if (device_may_wakeup(dev)) @@ -374,7 +374,7 @@ static int max77686_suspend(struct device *dev) static int max77686_resume(struct device *dev) { - struct i2c_client *i2c = container_of(dev, struct i2c_client, dev); + struct i2c_client *i2c = to_i2c_client(dev); struct max77686_dev *max77686 = i2c_get_clientdata(i2c); if (device_may_wakeup(dev)) diff --git a/drivers/mfd/max77693.c b/drivers/mfd/max77693.c index 007f729e150b..b83b7a7da1ae 100644 --- a/drivers/mfd/max77693.c +++ b/drivers/mfd/max77693.c @@ -334,7 +334,7 @@ MODULE_DEVICE_TABLE(i2c, max77693_i2c_id); static int max77693_suspend(struct device *dev) { - struct i2c_client *i2c = container_of(dev, struct i2c_client, dev); + struct i2c_client *i2c = to_i2c_client(dev); struct max77693_dev *max77693 = i2c_get_clientdata(i2c); if (device_may_wakeup(dev)) { @@ -347,7 +347,7 @@ static int max77693_suspend(struct device *dev) static int max77693_resume(struct device *dev) { - struct i2c_client *i2c = container_of(dev, struct i2c_client, dev); + struct i2c_client *i2c = to_i2c_client(dev); struct max77693_dev *max77693 = i2c_get_clientdata(i2c); if (device_may_wakeup(dev)) { diff --git a/drivers/mfd/max77843.c b/drivers/mfd/max77843.c index 586098f1b233..7cfc95b49c5d 100644 --- a/drivers/mfd/max77843.c +++ b/drivers/mfd/max77843.c @@ -197,7 +197,7 @@ MODULE_DEVICE_TABLE(i2c, max77843_id); static int __maybe_unused max77843_suspend(struct device *dev) { - struct i2c_client *i2c = container_of(dev, struct i2c_client, dev); + struct i2c_client *i2c = to_i2c_client(dev); struct max77693_dev *max77843 = i2c_get_clientdata(i2c); disable_irq(max77843->irq); @@ -209,7 +209,7 @@ static int __maybe_unused max77843_suspend(struct device *dev) static int __maybe_unused max77843_resume(struct device *dev) { - struct i2c_client *i2c = container_of(dev, struct i2c_client, dev); + struct i2c_client *i2c = to_i2c_client(dev); struct max77693_dev *max77843 = i2c_get_clientdata(i2c); if (device_may_wakeup(dev)) diff --git a/drivers/mfd/max8925-i2c.c b/drivers/mfd/max8925-i2c.c index b0fe8103e401..70443b161a5b 100644 --- a/drivers/mfd/max8925-i2c.c +++ b/drivers/mfd/max8925-i2c.c @@ -215,7 +215,7 @@ static int max8925_remove(struct i2c_client *client) #ifdef CONFIG_PM_SLEEP static int max8925_suspend(struct device *dev) { - struct i2c_client *client = container_of(dev, struct i2c_client, dev); + struct i2c_client *client = to_i2c_client(dev); struct max8925_chip *chip = i2c_get_clientdata(client); if (device_may_wakeup(dev) && chip->wakeup_flag) @@ -225,7 +225,7 @@ static int max8925_suspend(struct device *dev) static int max8925_resume(struct device *dev) { - struct i2c_client *client = container_of(dev, struct i2c_client, dev); + struct i2c_client *client = to_i2c_client(dev); struct max8925_chip *chip = i2c_get_clientdata(client); if (device_may_wakeup(dev) && chip->wakeup_flag) diff --git a/drivers/mfd/max8997.c b/drivers/mfd/max8997.c index 156ed6f92aa3..f316348e3d98 100644 --- a/drivers/mfd/max8997.c +++ b/drivers/mfd/max8997.c @@ -437,7 +437,7 @@ static u8 max8997_dumpaddr_haptic[] = { static int max8997_freeze(struct device *dev) { - struct i2c_client *i2c = container_of(dev, struct i2c_client, dev); + struct i2c_client *i2c = to_i2c_client(dev); struct max8997_dev *max8997 = i2c_get_clientdata(i2c); int i; @@ -459,7 +459,7 @@ static int max8997_freeze(struct device *dev) static int max8997_restore(struct device *dev) { - struct i2c_client *i2c = container_of(dev, struct i2c_client, dev); + struct i2c_client *i2c = to_i2c_client(dev); struct max8997_dev *max8997 = i2c_get_clientdata(i2c); int i; @@ -481,7 +481,7 @@ static int max8997_restore(struct device *dev) static int max8997_suspend(struct device *dev) { - struct i2c_client *i2c = container_of(dev, struct i2c_client, dev); + struct i2c_client *i2c = to_i2c_client(dev); struct max8997_dev *max8997 = i2c_get_clientdata(i2c); if (device_may_wakeup(dev)) @@ -491,7 +491,7 @@ static int max8997_suspend(struct device *dev) static int max8997_resume(struct device *dev) { - struct i2c_client *i2c = container_of(dev, struct i2c_client, dev); + struct i2c_client *i2c = to_i2c_client(dev); struct max8997_dev *max8997 = i2c_get_clientdata(i2c); if (device_may_wakeup(dev)) diff --git a/drivers/mfd/max8998.c b/drivers/mfd/max8998.c index a7afe3bf27fc..ab28b29400f6 100644 --- a/drivers/mfd/max8998.c +++ b/drivers/mfd/max8998.c @@ -274,7 +274,7 @@ MODULE_DEVICE_TABLE(i2c, max8998_i2c_id); static int max8998_suspend(struct device *dev) { - struct i2c_client *i2c = container_of(dev, struct i2c_client, dev); + struct i2c_client *i2c = to_i2c_client(dev); struct max8998_dev *max8998 = i2c_get_clientdata(i2c); if (device_may_wakeup(dev)) @@ -284,7 +284,7 @@ static int max8998_suspend(struct device *dev) static int max8998_resume(struct device *dev) { - struct i2c_client *i2c = container_of(dev, struct i2c_client, dev); + struct i2c_client *i2c = to_i2c_client(dev); struct max8998_dev *max8998 = i2c_get_clientdata(i2c); if (device_may_wakeup(dev)) @@ -344,7 +344,7 @@ static struct max8998_reg_dump max8998_dump[] = { /* Save registers before hibernation */ static int max8998_freeze(struct device *dev) { - struct i2c_client *i2c = container_of(dev, struct i2c_client, dev); + struct i2c_client *i2c = to_i2c_client(dev); int i; for (i = 0; i < ARRAY_SIZE(max8998_dump); i++) @@ -357,7 +357,7 @@ static int max8998_freeze(struct device *dev) /* Restore registers after hibernation */ static int max8998_restore(struct device *dev) { - struct i2c_client *i2c = container_of(dev, struct i2c_client, dev); + struct i2c_client *i2c = to_i2c_client(dev); int i; for (i = 0; i < ARRAY_SIZE(max8998_dump); i++) diff --git a/drivers/mfd/mc13xxx-core.c b/drivers/mfd/mc13xxx-core.c index 3f9f4c874d2a..d7f54e492aa6 100644 --- a/drivers/mfd/mc13xxx-core.c +++ b/drivers/mfd/mc13xxx-core.c @@ -383,16 +383,16 @@ static int mc13xxx_probe_flags_dt(struct mc13xxx *mc13xxx) if (!np) return -ENODEV; - if (of_get_property(np, "fsl,mc13xxx-uses-adc", NULL)) + if (of_property_read_bool(np, "fsl,mc13xxx-uses-adc")) mc13xxx->flags |= MC13XXX_USE_ADC; - if (of_get_property(np, "fsl,mc13xxx-uses-codec", NULL)) + if (of_property_read_bool(np, "fsl,mc13xxx-uses-codec")) mc13xxx->flags |= MC13XXX_USE_CODEC; - if (of_get_property(np, "fsl,mc13xxx-uses-rtc", NULL)) + if (of_property_read_bool(np, "fsl,mc13xxx-uses-rtc")) mc13xxx->flags |= MC13XXX_USE_RTC; - if (of_get_property(np, "fsl,mc13xxx-uses-touch", NULL)) + if (of_property_read_bool(np, "fsl,mc13xxx-uses-touch")) mc13xxx->flags |= MC13XXX_USE_TOUCHSCREEN; return 0; diff --git a/drivers/mfd/qcom-spmi-pmic.c b/drivers/mfd/qcom-spmi-pmic.c index af6ac1c4b45c..8653e8b9bb4f 100644 --- a/drivers/mfd/qcom-spmi-pmic.c +++ b/drivers/mfd/qcom-spmi-pmic.c @@ -127,7 +127,9 @@ static int pmic_spmi_probe(struct spmi_device *sdev) if (IS_ERR(regmap)) return PTR_ERR(regmap); - pmic_spmi_show_revid(regmap, &sdev->dev); + /* Only the first slave id for a PMIC contains this information */ + if (sdev->usid % 2 == 0) + pmic_spmi_show_revid(regmap, &sdev->dev); return of_platform_populate(root, NULL, NULL, &sdev->dev); } diff --git a/drivers/mfd/qcom_rpm.c b/drivers/mfd/qcom_rpm.c index 207a3bd68559..1be47ad6441b 100644 --- a/drivers/mfd/qcom_rpm.c +++ b/drivers/mfd/qcom_rpm.c @@ -495,6 +495,8 @@ static int qcom_rpm_probe(struct platform_device *pdev) } match = of_match_device(qcom_rpm_of_match, &pdev->dev); + if (!match) + return -ENODEV; rpm->data = match->data; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); diff --git a/drivers/mfd/sec-core.c b/drivers/mfd/sec-core.c index 989076d6cb83..400e1d7d8d08 100644 --- a/drivers/mfd/sec-core.c +++ b/drivers/mfd/sec-core.c @@ -29,6 +29,7 @@ #include <linux/mfd/samsung/s2mps11.h> #include <linux/mfd/samsung/s2mps13.h> #include <linux/mfd/samsung/s2mps14.h> +#include <linux/mfd/samsung/s2mps15.h> #include <linux/mfd/samsung/s2mpu02.h> #include <linux/mfd/samsung/s5m8763.h> #include <linux/mfd/samsung/s5m8767.h> @@ -67,7 +68,7 @@ static const struct mfd_cell s5m8767_devs[] = { static const struct mfd_cell s2mps11_devs[] = { { - .name = "s2mps11-pmic", + .name = "s2mps11-regulator", }, { .name = "s2mps14-rtc", }, { @@ -77,7 +78,7 @@ static const struct mfd_cell s2mps11_devs[] = { }; static const struct mfd_cell s2mps13_devs[] = { - { .name = "s2mps13-pmic", }, + { .name = "s2mps13-regulator", }, { .name = "s2mps13-rtc", }, { .name = "s2mps13-clk", @@ -87,7 +88,7 @@ static const struct mfd_cell s2mps13_devs[] = { static const struct mfd_cell s2mps14_devs[] = { { - .name = "s2mps14-pmic", + .name = "s2mps14-regulator", }, { .name = "s2mps14-rtc", }, { @@ -96,6 +97,17 @@ static const struct mfd_cell s2mps14_devs[] = { } }; +static const struct mfd_cell s2mps15_devs[] = { + { + .name = "s2mps15-regulator", + }, { + .name = "s2mps15-rtc", + }, { + .name = "s2mps13-clk", + .of_compatible = "samsung,s2mps13-clk", + }, +}; + static const struct mfd_cell s2mpa01_devs[] = { { .name = "s2mpa01-pmic", @@ -104,7 +116,7 @@ static const struct mfd_cell s2mpa01_devs[] = { static const struct mfd_cell s2mpu02_devs[] = { { - .name = "s2mpu02-pmic", + .name = "s2mpu02-regulator", }, }; @@ -122,6 +134,9 @@ static const struct of_device_id sec_dt_match[] = { .compatible = "samsung,s2mps14-pmic", .data = (void *)S2MPS14X, }, { + .compatible = "samsung,s2mps15-pmic", + .data = (void *)S2MPS15X, + }, { .compatible = "samsung,s2mpa01-pmic", .data = (void *)S2MPA01, }, { @@ -223,6 +238,15 @@ static const struct regmap_config s2mps14_regmap_config = { .cache_type = REGCACHE_FLAT, }; +static const struct regmap_config s2mps15_regmap_config = { + .reg_bits = 8, + .val_bits = 8, + + .max_register = S2MPS15_REG_LDODSCH4, + .volatile_reg = s2mps11_volatile, + .cache_type = REGCACHE_FLAT, +}; + static const struct regmap_config s2mpu02_regmap_config = { .reg_bits = 8, .val_bits = 8, @@ -384,6 +408,9 @@ static int sec_pmic_probe(struct i2c_client *i2c, case S2MPS14X: regmap = &s2mps14_regmap_config; break; + case S2MPS15X: + regmap = &s2mps15_regmap_config; + break; case S5M8763X: regmap = &s5m8763_regmap_config; break; @@ -442,6 +469,10 @@ static int sec_pmic_probe(struct i2c_client *i2c, sec_devs = s2mps14_devs; num_sec_devs = ARRAY_SIZE(s2mps14_devs); break; + case S2MPS15X: + sec_devs = s2mps15_devs; + num_sec_devs = ARRAY_SIZE(s2mps15_devs); + break; case S2MPU02: sec_devs = s2mpu02_devs; num_sec_devs = ARRAY_SIZE(s2mpu02_devs); @@ -505,7 +536,7 @@ static void sec_pmic_shutdown(struct i2c_client *i2c) #ifdef CONFIG_PM_SLEEP static int sec_pmic_suspend(struct device *dev) { - struct i2c_client *i2c = container_of(dev, struct i2c_client, dev); + struct i2c_client *i2c = to_i2c_client(dev); struct sec_pmic_dev *sec_pmic = i2c_get_clientdata(i2c); if (device_may_wakeup(dev)) @@ -526,7 +557,7 @@ static int sec_pmic_suspend(struct device *dev) static int sec_pmic_resume(struct device *dev) { - struct i2c_client *i2c = container_of(dev, struct i2c_client, dev); + struct i2c_client *i2c = to_i2c_client(dev); struct sec_pmic_dev *sec_pmic = i2c_get_clientdata(i2c); if (device_may_wakeup(dev)) diff --git a/drivers/mfd/sec-irq.c b/drivers/mfd/sec-irq.c index 806fa8dbb22d..d77de431cc50 100644 --- a/drivers/mfd/sec-irq.c +++ b/drivers/mfd/sec-irq.c @@ -407,6 +407,11 @@ static const struct regmap_irq_chip s2mps14_irq_chip = { S2MPS1X_IRQ_CHIP_COMMON_DATA, }; +static const struct regmap_irq_chip s2mps15_irq_chip = { + .name = "s2mps15", + S2MPS1X_IRQ_CHIP_COMMON_DATA, +}; + static const struct regmap_irq_chip s2mpu02_irq_chip = { .name = "s2mpu02", .irqs = s2mpu02_irqs, @@ -466,6 +471,9 @@ int sec_irq_init(struct sec_pmic_dev *sec_pmic) case S2MPS14X: sec_irq_chip = &s2mps14_irq_chip; break; + case S2MPS15X: + sec_irq_chip = &s2mps15_irq_chip; + break; case S2MPU02: sec_irq_chip = &s2mpu02_irq_chip; break; diff --git a/drivers/mfd/sta2x11-mfd.c b/drivers/mfd/sta2x11-mfd.c index b3e5c6f45105..9292202039ee 100644 --- a/drivers/mfd/sta2x11-mfd.c +++ b/drivers/mfd/sta2x11-mfd.c @@ -372,12 +372,6 @@ static struct platform_driver sta2x11_sctl_platform_driver = { .probe = sta2x11_sctl_probe, }; -static int __init sta2x11_sctl_init(void) -{ - pr_info("%s\n", __func__); - return platform_driver_register(&sta2x11_sctl_platform_driver); -} - static struct platform_driver sta2x11_platform_driver = { .driver = { .name = STA2X11_MFD_APBREG_NAME, @@ -385,12 +379,6 @@ static struct platform_driver sta2x11_platform_driver = { .probe = sta2x11_apbreg_probe, }; -static int __init sta2x11_apbreg_init(void) -{ - pr_info("%s\n", __func__); - return platform_driver_register(&sta2x11_platform_driver); -} - static struct platform_driver sta2x11_apb_soc_regs_platform_driver = { .driver = { .name = STA2X11_MFD_APB_SOC_REGS_NAME, @@ -398,12 +386,6 @@ static struct platform_driver sta2x11_apb_soc_regs_platform_driver = { .probe = sta2x11_apb_soc_regs_probe, }; -static int __init sta2x11_apb_soc_regs_init(void) -{ - pr_info("%s\n", __func__); - return platform_driver_register(&sta2x11_apb_soc_regs_platform_driver); -} - static struct platform_driver sta2x11_scr_platform_driver = { .driver = { .name = STA2X11_MFD_SCR_NAME, @@ -411,13 +393,18 @@ static struct platform_driver sta2x11_scr_platform_driver = { .probe = sta2x11_scr_probe, }; -static int __init sta2x11_scr_init(void) +static struct platform_driver * const drivers[] = { + &sta2x11_platform_driver, + &sta2x11_sctl_platform_driver, + &sta2x11_apb_soc_regs_platform_driver, + &sta2x11_scr_platform_driver, +}; + +static int __init sta2x11_drivers_init(void) { - pr_info("%s\n", __func__); - return platform_driver_register(&sta2x11_scr_platform_driver); + return platform_register_drivers(drivers, ARRAY_SIZE(drivers)); } - /* * What follows are the PCI devices that host the above pdevs. * Each logic block is 4kB and they are all consecutive: we use this info. @@ -664,10 +651,7 @@ static int __init sta2x11_mfd_init(void) * prepares platform drivers very early and probe the PCI device later, * but before other PCI devices. */ -subsys_initcall(sta2x11_apbreg_init); -subsys_initcall(sta2x11_sctl_init); -subsys_initcall(sta2x11_apb_soc_regs_init); -subsys_initcall(sta2x11_scr_init); +subsys_initcall(sta2x11_drivers_init); rootfs_initcall(sta2x11_mfd_init); MODULE_LICENSE("GPL v2"); diff --git a/drivers/mfd/syscon.c b/drivers/mfd/syscon.c index 176bf0fa2685..b7aabeefab07 100644 --- a/drivers/mfd/syscon.c +++ b/drivers/mfd/syscon.c @@ -47,6 +47,7 @@ static struct syscon *of_syscon_register(struct device_node *np) struct syscon *syscon; struct regmap *regmap; void __iomem *base; + u32 reg_io_width; int ret; struct regmap_config syscon_config = syscon_regmap_config; @@ -69,6 +70,18 @@ static struct syscon *of_syscon_register(struct device_node *np) else if (of_property_read_bool(np, "little-endian")) syscon_config.val_format_endian = REGMAP_ENDIAN_LITTLE; + /* + * search for reg-io-width property in DT. If it is not provided, + * default to 4 bytes. regmap_init_mmio will return an error if values + * are invalid so there is no need to check them here. + */ + ret = of_property_read_u32(np, "reg-io-width", ®_io_width); + if (ret) + reg_io_width = 4; + + syscon_config.reg_stride = reg_io_width; + syscon_config.val_bits = reg_io_width * 8; + regmap = regmap_init_mmio(NULL, base, &syscon_config); if (IS_ERR(regmap)) { pr_err("regmap init failed\n"); diff --git a/drivers/mfd/tc6393xb.c b/drivers/mfd/tc6393xb.c index 8c84a513016b..1ecbfa40d1b3 100644 --- a/drivers/mfd/tc6393xb.c +++ b/drivers/mfd/tc6393xb.c @@ -437,8 +437,8 @@ static int tc6393xb_gpio_get(struct gpio_chip *chip, struct tc6393xb *tc6393xb = container_of(chip, struct tc6393xb, gpio); /* XXX: does dsr also represent inputs? */ - return tmio_ioread8(tc6393xb->scr + SCR_GPO_DSR(offset / 8)) - & TC_GPIO_BIT(offset); + return !!(tmio_ioread8(tc6393xb->scr + SCR_GPO_DSR(offset / 8)) + & TC_GPIO_BIT(offset)); } static void __tc6393xb_gpio_set(struct gpio_chip *chip, diff --git a/drivers/mfd/tps65010.c b/drivers/mfd/tps65010.c index 448f0a182dc4..677a127619d4 100644 --- a/drivers/mfd/tps65010.c +++ b/drivers/mfd/tps65010.c @@ -499,11 +499,11 @@ static int tps65010_gpio_get(struct gpio_chip *chip, unsigned offset) if (offset < 4) { value = i2c_smbus_read_byte_data(tps->client, TPS_DEFGPIO); if (value < 0) - return 0; + return value; if (value & (1 << (offset + 4))) /* output */ return !(value & (1 << offset)); else /* input */ - return (value & (1 << offset)); + return !!(value & (1 << offset)); } /* REVISIT we *could* report LED1/nPG and LED2 state ... */ diff --git a/drivers/mfd/ucb1x00-core.c b/drivers/mfd/ucb1x00-core.c index f691d7ecad52..e0dd83fb95d3 100644 --- a/drivers/mfd/ucb1x00-core.c +++ b/drivers/mfd/ucb1x00-core.c @@ -133,7 +133,7 @@ static int ucb1x00_gpio_get(struct gpio_chip *chip, unsigned offset) val = ucb1x00_reg_read(ucb, UCB_IO_DATA); ucb1x00_disable(ucb); - return val & (1 << offset); + return !!(val & (1 << offset)); } static int ucb1x00_gpio_direction_input(struct gpio_chip *chip, unsigned offset) diff --git a/drivers/mfd/wm5110-tables.c b/drivers/mfd/wm5110-tables.c index 2bb2d0467a92..c18e11f42b3f 100644 --- a/drivers/mfd/wm5110-tables.c +++ b/drivers/mfd/wm5110-tables.c @@ -762,9 +762,9 @@ static const struct reg_default wm5110_reg_default[] = { { 0x00000200, 0x0006 }, /* R512 - Mic Charge Pump 1 */ { 0x00000210, 0x0184 }, /* R528 - LDO1 Control 1 */ { 0x00000213, 0x03E4 }, /* R531 - LDO2 Control 1 */ - { 0x00000218, 0x01A6 }, /* R536 - Mic Bias Ctrl 1 */ - { 0x00000219, 0x01A6 }, /* R537 - Mic Bias Ctrl 2 */ - { 0x0000021A, 0x01A6 }, /* R538 - Mic Bias Ctrl 3 */ + { 0x00000218, 0x00E6 }, /* R536 - Mic Bias Ctrl 1 */ + { 0x00000219, 0x00E6 }, /* R537 - Mic Bias Ctrl 2 */ + { 0x0000021A, 0x00E6 }, /* R538 - Mic Bias Ctrl 3 */ { 0x00000293, 0x0000 }, /* R659 - Accessory Detect Mode 1 */ { 0x0000029B, 0x0028 }, /* R667 - Headphone Detect 1 */ { 0x000002A2, 0x0000 }, /* R674 - Micd clamp control */ diff --git a/drivers/mfd/wm831x-otp.c b/drivers/mfd/wm831x-otp.c index b90f3e06b6c9..ebac0027f8e0 100644 --- a/drivers/mfd/wm831x-otp.c +++ b/drivers/mfd/wm831x-otp.c @@ -47,20 +47,14 @@ static ssize_t wm831x_unique_id_show(struct device *dev, struct device_attribute *attr, char *buf) { struct wm831x *wm831x = dev_get_drvdata(dev); - int i, rval; + int rval; char id[WM831X_UNIQUE_ID_LEN]; - ssize_t ret = 0; rval = wm831x_unique_id_read(wm831x, id); if (rval < 0) return 0; - for (i = 0; i < WM831X_UNIQUE_ID_LEN; i++) - ret += sprintf(&buf[ret], "%02x", buf[i]); - - ret += sprintf(&buf[ret], "\n"); - - return ret; + return sprintf(buf, "%*phN\n", WM831X_UNIQUE_ID_LEN, id); } static DEVICE_ATTR(unique_id, 0444, wm831x_unique_id_show, NULL); diff --git a/drivers/misc/cxl/Makefile b/drivers/misc/cxl/Makefile index 6982f603fadc..be2ac5ce349f 100644 --- a/drivers/misc/cxl/Makefile +++ b/drivers/misc/cxl/Makefile @@ -1,4 +1,5 @@ -ccflags-y := -Werror -Wno-unused-const-variable +ccflags-y := $(call cc-disable-warning, unused-const-variable) +ccflags-$(CONFIG_PPC_WERROR) += -Werror cxl-y += main.o file.o irq.o fault.o native.o cxl-y += context.o sysfs.o debugfs.o pci.o trace.o diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c index 103baf0e0c5b..ea3eeb7011e1 100644 --- a/drivers/misc/cxl/api.c +++ b/drivers/misc/cxl/api.c @@ -25,7 +25,6 @@ struct cxl_context *cxl_dev_context_init(struct pci_dev *dev) afu = cxl_pci_to_afu(dev); - get_device(&afu->dev); ctx = cxl_context_alloc(); if (IS_ERR(ctx)) { rc = PTR_ERR(ctx); @@ -61,7 +60,6 @@ err_mapping: err_ctx: kfree(ctx); err_dev: - put_device(&afu->dev); return ERR_PTR(rc); } EXPORT_SYMBOL_GPL(cxl_dev_context_init); @@ -87,8 +85,6 @@ int cxl_release_context(struct cxl_context *ctx) if (ctx->status >= STARTED) return -EBUSY; - put_device(&ctx->afu->dev); - cxl_context_free(ctx); return 0; @@ -176,7 +172,7 @@ int cxl_start_context(struct cxl_context *ctx, u64 wed, if (task) { ctx->pid = get_task_pid(task, PIDTYPE_PID); - get_pid(ctx->pid); + ctx->glpid = get_task_pid(task->group_leader, PIDTYPE_PID); kernel = false; } diff --git a/drivers/misc/cxl/context.c b/drivers/misc/cxl/context.c index 2faa1270d085..262b88eac414 100644 --- a/drivers/misc/cxl/context.c +++ b/drivers/misc/cxl/context.c @@ -42,7 +42,7 @@ int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master, spin_lock_init(&ctx->sste_lock); ctx->afu = afu; ctx->master = master; - ctx->pid = NULL; /* Set in start work ioctl */ + ctx->pid = ctx->glpid = NULL; /* Set in start work ioctl */ mutex_init(&ctx->mapping_lock); ctx->mapping = mapping; @@ -97,6 +97,12 @@ int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master, ctx->pe = i; ctx->elem = &ctx->afu->spa[i]; ctx->pe_inserted = false; + + /* + * take a ref on the afu so that it stays alive at-least till + * this context is reclaimed inside reclaim_ctx. + */ + cxl_afu_get(afu); return 0; } @@ -211,7 +217,11 @@ int __detach_context(struct cxl_context *ctx) WARN_ON(cxl_detach_process(ctx) && cxl_adapter_link_ok(ctx->afu->adapter)); flush_work(&ctx->fault_work); /* Only needed for dedicated process */ + + /* release the reference to the group leader and mm handling pid */ put_pid(ctx->pid); + put_pid(ctx->glpid); + cxl_ctx_put(); return 0; } @@ -278,6 +288,9 @@ static void reclaim_ctx(struct rcu_head *rcu) if (ctx->irq_bitmap) kfree(ctx->irq_bitmap); + /* Drop ref to the afu device taken during cxl_context_init */ + cxl_afu_put(ctx->afu); + kfree(ctx); } diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h index 0cfb9c129f27..a521bc72cec2 100644 --- a/drivers/misc/cxl/cxl.h +++ b/drivers/misc/cxl/cxl.h @@ -403,6 +403,18 @@ struct cxl_afu { bool enabled; }; +/* AFU refcount management */ +static inline struct cxl_afu *cxl_afu_get(struct cxl_afu *afu) +{ + + return (get_device(&afu->dev) == NULL) ? NULL : afu; +} + +static inline void cxl_afu_put(struct cxl_afu *afu) +{ + put_device(&afu->dev); +} + struct cxl_irq_name { struct list_head list; @@ -433,6 +445,9 @@ struct cxl_context { unsigned int sst_size, sst_lru; wait_queue_head_t wq; + /* pid of the group leader associated with the pid */ + struct pid *glpid; + /* use mm context associated with this pid for ds faults */ struct pid *pid; spinlock_t lock; /* Protects pending_irq_mask, pending_fault and fault_addr */ /* Only used in PR mode */ diff --git a/drivers/misc/cxl/fault.c b/drivers/misc/cxl/fault.c index 25a5418c55cb..81c3f75b7330 100644 --- a/drivers/misc/cxl/fault.c +++ b/drivers/misc/cxl/fault.c @@ -166,13 +166,92 @@ static void cxl_handle_page_fault(struct cxl_context *ctx, cxl_ack_irq(ctx, CXL_PSL_TFC_An_R, 0); } +/* + * Returns the mm_struct corresponding to the context ctx via ctx->pid + * In case the task has exited we use the task group leader accessible + * via ctx->glpid to find the next task in the thread group that has a + * valid mm_struct associated with it. If a task with valid mm_struct + * is found the ctx->pid is updated to use the task struct for subsequent + * translations. In case no valid mm_struct is found in the task group to + * service the fault a NULL is returned. + */ +static struct mm_struct *get_mem_context(struct cxl_context *ctx) +{ + struct task_struct *task = NULL; + struct mm_struct *mm = NULL; + struct pid *old_pid = ctx->pid; + + if (old_pid == NULL) { + pr_warn("%s: Invalid context for pe=%d\n", + __func__, ctx->pe); + return NULL; + } + + task = get_pid_task(old_pid, PIDTYPE_PID); + + /* + * pid_alive may look racy but this saves us from costly + * get_task_mm when the task is a zombie. In worst case + * we may think a task is alive, which is about to die + * but get_task_mm will return NULL. + */ + if (task != NULL && pid_alive(task)) + mm = get_task_mm(task); + + /* release the task struct that was taken earlier */ + if (task) + put_task_struct(task); + else + pr_devel("%s: Context owning pid=%i for pe=%i dead\n", + __func__, pid_nr(old_pid), ctx->pe); + + /* + * If we couldn't find the mm context then use the group + * leader to iterate over the task group and find a task + * that gives us mm_struct. + */ + if (unlikely(mm == NULL && ctx->glpid != NULL)) { + + rcu_read_lock(); + task = pid_task(ctx->glpid, PIDTYPE_PID); + if (task) + do { + mm = get_task_mm(task); + if (mm) { + ctx->pid = get_task_pid(task, + PIDTYPE_PID); + break; + } + task = next_thread(task); + } while (task && !thread_group_leader(task)); + rcu_read_unlock(); + + /* check if we switched pid */ + if (ctx->pid != old_pid) { + if (mm) + pr_devel("%s:pe=%i switch pid %i->%i\n", + __func__, ctx->pe, pid_nr(old_pid), + pid_nr(ctx->pid)); + else + pr_devel("%s:Cannot find mm for pid=%i\n", + __func__, pid_nr(old_pid)); + + /* drop the reference to older pid */ + put_pid(old_pid); + } + } + + return mm; +} + + + void cxl_handle_fault(struct work_struct *fault_work) { struct cxl_context *ctx = container_of(fault_work, struct cxl_context, fault_work); u64 dsisr = ctx->dsisr; u64 dar = ctx->dar; - struct task_struct *task = NULL; struct mm_struct *mm = NULL; if (cxl_p2n_read(ctx->afu, CXL_PSL_DSISR_An) != dsisr || @@ -195,17 +274,17 @@ void cxl_handle_fault(struct work_struct *fault_work) "DSISR: %#llx DAR: %#llx\n", ctx->pe, dsisr, dar); if (!ctx->kernel) { - if (!(task = get_pid_task(ctx->pid, PIDTYPE_PID))) { - pr_devel("cxl_handle_fault unable to get task %i\n", - pid_nr(ctx->pid)); + + mm = get_mem_context(ctx); + /* indicates all the thread in task group have exited */ + if (mm == NULL) { + pr_devel("%s: unable to get mm for pe=%d pid=%i\n", + __func__, ctx->pe, pid_nr(ctx->pid)); cxl_ack_ae(ctx); return; - } - if (!(mm = get_task_mm(task))) { - pr_devel("cxl_handle_fault unable to get mm %i\n", - pid_nr(ctx->pid)); - cxl_ack_ae(ctx); - goto out; + } else { + pr_devel("Handling page fault for pe=%d pid=%i\n", + ctx->pe, pid_nr(ctx->pid)); } } @@ -218,33 +297,22 @@ void cxl_handle_fault(struct work_struct *fault_work) if (mm) mmput(mm); -out: - if (task) - put_task_struct(task); } static void cxl_prefault_one(struct cxl_context *ctx, u64 ea) { - int rc; - struct task_struct *task; struct mm_struct *mm; - if (!(task = get_pid_task(ctx->pid, PIDTYPE_PID))) { - pr_devel("cxl_prefault_one unable to get task %i\n", - pid_nr(ctx->pid)); - return; - } - if (!(mm = get_task_mm(task))) { + mm = get_mem_context(ctx); + if (mm == NULL) { pr_devel("cxl_prefault_one unable to get mm %i\n", pid_nr(ctx->pid)); - put_task_struct(task); return; } - rc = cxl_fault_segment(ctx, mm, ea); + cxl_fault_segment(ctx, mm, ea); mmput(mm); - put_task_struct(task); } static u64 next_segment(u64 ea, u64 vsid) @@ -263,18 +331,13 @@ static void cxl_prefault_vma(struct cxl_context *ctx) struct copro_slb slb; struct vm_area_struct *vma; int rc; - struct task_struct *task; struct mm_struct *mm; - if (!(task = get_pid_task(ctx->pid, PIDTYPE_PID))) { - pr_devel("cxl_prefault_vma unable to get task %i\n", - pid_nr(ctx->pid)); - return; - } - if (!(mm = get_task_mm(task))) { + mm = get_mem_context(ctx); + if (mm == NULL) { pr_devel("cxl_prefault_vm unable to get mm %i\n", pid_nr(ctx->pid)); - goto out1; + return; } down_read(&mm->mmap_sem); @@ -295,8 +358,6 @@ static void cxl_prefault_vma(struct cxl_context *ctx) up_read(&mm->mmap_sem); mmput(mm); -out1: - put_task_struct(task); } void cxl_prefault(struct cxl_context *ctx, u64 wed) diff --git a/drivers/misc/cxl/file.c b/drivers/misc/cxl/file.c index 7ccd2998be92..783337d22f36 100644 --- a/drivers/misc/cxl/file.c +++ b/drivers/misc/cxl/file.c @@ -67,7 +67,13 @@ static int __afu_open(struct inode *inode, struct file *file, bool master) spin_unlock(&adapter->afu_list_lock); goto err_put_adapter; } - get_device(&afu->dev); + + /* + * taking a ref to the afu so that it doesn't go away + * for rest of the function. This ref is released before + * we return. + */ + cxl_afu_get(afu); spin_unlock(&adapter->afu_list_lock); if (!afu->current_mode) @@ -90,13 +96,12 @@ static int __afu_open(struct inode *inode, struct file *file, bool master) file->private_data = ctx; cxl_ctx_get(); - /* Our ref on the AFU will now hold the adapter */ - put_device(&adapter->dev); - - return 0; + /* indicate success */ + rc = 0; err_put_afu: - put_device(&afu->dev); + /* release the ref taken earlier */ + cxl_afu_put(afu); err_put_adapter: put_device(&adapter->dev); return rc; @@ -131,8 +136,6 @@ int afu_release(struct inode *inode, struct file *file) mutex_unlock(&ctx->mapping_lock); } - put_device(&ctx->afu->dev); - /* * At this this point all bottom halfs have finished and we should be * getting no more IRQs from the hardware for this context. Once it's @@ -198,8 +201,12 @@ static long afu_ioctl_start_work(struct cxl_context *ctx, * where a process (master, some daemon, etc) has opened the chardev on * behalf of another process, so the AFU's mm gets bound to the process * that performs this ioctl and not the process that opened the file. + * Also we grab the PID of the group leader so that if the task that + * has performed the attach operation exits the mm context of the + * process is still accessible. */ - ctx->pid = get_pid(get_task_pid(current, PIDTYPE_PID)); + ctx->pid = get_task_pid(current, PIDTYPE_PID); + ctx->glpid = get_task_pid(current->group_leader, PIDTYPE_PID); trace_cxl_attach(ctx, work.work_element_descriptor, work.num_interrupts, amr); diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c index 85761d7eb333..4c1903f781fc 100644 --- a/drivers/misc/cxl/pci.c +++ b/drivers/misc/cxl/pci.c @@ -138,6 +138,7 @@ static const struct pci_device_id cxl_pci_tbl[] = { { PCI_DEVICE(PCI_VENDOR_ID_IBM, 0x0477), }, { PCI_DEVICE(PCI_VENDOR_ID_IBM, 0x044b), }, { PCI_DEVICE(PCI_VENDOR_ID_IBM, 0x04cf), }, + { PCI_DEVICE(PCI_VENDOR_ID_IBM, 0x0601), }, { PCI_DEVICE_CLASS(0x120000, ~0), }, { } diff --git a/drivers/misc/cxl/vphb.c b/drivers/misc/cxl/vphb.c index c241e15cacb1..cbd4331fb45c 100644 --- a/drivers/misc/cxl/vphb.c +++ b/drivers/misc/cxl/vphb.c @@ -203,7 +203,7 @@ static int cxl_pcie_write_config(struct pci_bus *bus, unsigned int devfn, mask <<= shift; val <<= shift; - v = (in_le32(ioaddr) & ~mask) || (val & mask); + v = (in_le32(ioaddr) & ~mask) | (val & mask); out_le32(ioaddr, v); return PCIBIOS_SUCCESSFUL; diff --git a/drivers/net/ethernet/freescale/fsl_pq_mdio.c b/drivers/net/ethernet/freescale/fsl_pq_mdio.c index 622005abf859..f3c63dce1e30 100644 --- a/drivers/net/ethernet/freescale/fsl_pq_mdio.c +++ b/drivers/net/ethernet/freescale/fsl_pq_mdio.c @@ -29,7 +29,7 @@ #include <asm/io.h> #if IS_ENABLED(CONFIG_UCC_GETH) -#include <asm/ucc.h> /* for ucc_set_qe_mux_mii_mng() */ +#include <soc/fsl/qe/ucc.h> #endif #include "gianfar.h" diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c index cbddbe2d0429..5bf1ade28315 100644 --- a/drivers/net/ethernet/freescale/ucc_geth.c +++ b/drivers/net/ethernet/freescale/ucc_geth.c @@ -40,10 +40,10 @@ #include <asm/uaccess.h> #include <asm/irq.h> #include <asm/io.h> -#include <asm/immap_qe.h> -#include <asm/qe.h> -#include <asm/ucc.h> -#include <asm/ucc_fast.h> +#include <soc/fsl/qe/immap_qe.h> +#include <soc/fsl/qe/qe.h> +#include <soc/fsl/qe/ucc.h> +#include <soc/fsl/qe/ucc_fast.h> #include <asm/machdep.h> #include "ucc_geth.h" diff --git a/drivers/net/ethernet/freescale/ucc_geth.h b/drivers/net/ethernet/freescale/ucc_geth.h index 75f337163ce3..5da19b440a6a 100644 --- a/drivers/net/ethernet/freescale/ucc_geth.h +++ b/drivers/net/ethernet/freescale/ucc_geth.h @@ -22,11 +22,11 @@ #include <linux/list.h> #include <linux/if_ether.h> -#include <asm/immap_qe.h> -#include <asm/qe.h> +#include <soc/fsl/qe/immap_qe.h> +#include <soc/fsl/qe/qe.h> -#include <asm/ucc.h> -#include <asm/ucc_fast.h> +#include <soc/fsl/qe/ucc.h> +#include <soc/fsl/qe/ucc_fast.h> #define DRV_DESC "QE UCC Gigabit Ethernet Controller" #define DRV_NAME "ucc_geth" diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index a0bbb6b9f5aa..94da913b151d 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -1239,7 +1239,7 @@ static int i40evf_config_rss_aq(struct i40e_vsi *vsi, const u8 *seed, if (adapter->current_op != I40E_VIRTCHNL_OP_UNKNOWN) { /* bail because we already have a command pending */ - dev_err(&adapter->pdev->dev, "Cannot confiure RSS, command %d pending\n", + dev_err(&adapter->pdev->dev, "Cannot configure RSS, command %d pending\n", adapter->current_op); return -EBUSY; } diff --git a/drivers/of/address.c b/drivers/of/address.c index 9582c5703b3c..91a469d55b8f 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -597,7 +597,7 @@ static u64 __of_translate_address(struct device_node *dev, pbus = of_match_bus(parent); pbus->count_cells(dev, &pna, &pns); if (!OF_CHECK_COUNTS(pna, pns)) { - printk(KERN_ERR "prom_parse: Bad cell count for %s\n", + pr_err("prom_parse: Bad cell count for %s\n", of_node_full_name(dev)); break; } diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c index 53826b84e0ec..c647bd1b6903 100644 --- a/drivers/of/dynamic.c +++ b/drivers/of/dynamic.c @@ -646,6 +646,7 @@ void of_changeset_init(struct of_changeset *ocs) memset(ocs, 0, sizeof(*ocs)); INIT_LIST_HEAD(&ocs->entries); } +EXPORT_SYMBOL_GPL(of_changeset_init); /** * of_changeset_destroy - Destroy a changeset @@ -662,20 +663,9 @@ void of_changeset_destroy(struct of_changeset *ocs) list_for_each_entry_safe_reverse(ce, cen, &ocs->entries, node) __of_changeset_entry_destroy(ce); } +EXPORT_SYMBOL_GPL(of_changeset_destroy); -/** - * of_changeset_apply - Applies a changeset - * - * @ocs: changeset pointer - * - * Applies a changeset to the live tree. - * Any side-effects of live tree state changes are applied here on - * sucess, like creation/destruction of devices and side-effects - * like creation of sysfs properties and directories. - * Returns 0 on success, a negative error value in case of an error. - * On error the partially applied effects are reverted. - */ -int of_changeset_apply(struct of_changeset *ocs) +int __of_changeset_apply(struct of_changeset *ocs) { struct of_changeset_entry *ce; int ret; @@ -704,17 +694,30 @@ int of_changeset_apply(struct of_changeset *ocs) } /** - * of_changeset_revert - Reverts an applied changeset + * of_changeset_apply - Applies a changeset * * @ocs: changeset pointer * - * Reverts a changeset returning the state of the tree to what it - * was before the application. - * Any side-effects like creation/destruction of devices and - * removal of sysfs properties and directories are applied. + * Applies a changeset to the live tree. + * Any side-effects of live tree state changes are applied here on + * success, like creation/destruction of devices and side-effects + * like creation of sysfs properties and directories. * Returns 0 on success, a negative error value in case of an error. + * On error the partially applied effects are reverted. */ -int of_changeset_revert(struct of_changeset *ocs) +int of_changeset_apply(struct of_changeset *ocs) +{ + int ret; + + mutex_lock(&of_mutex); + ret = __of_changeset_apply(ocs); + mutex_unlock(&of_mutex); + + return ret; +} +EXPORT_SYMBOL_GPL(of_changeset_apply); + +int __of_changeset_revert(struct of_changeset *ocs) { struct of_changeset_entry *ce; int ret; @@ -742,6 +745,29 @@ int of_changeset_revert(struct of_changeset *ocs) } /** + * of_changeset_revert - Reverts an applied changeset + * + * @ocs: changeset pointer + * + * Reverts a changeset returning the state of the tree to what it + * was before the application. + * Any side-effects like creation/destruction of devices and + * removal of sysfs properties and directories are applied. + * Returns 0 on success, a negative error value in case of an error. + */ +int of_changeset_revert(struct of_changeset *ocs) +{ + int ret; + + mutex_lock(&of_mutex); + ret = __of_changeset_revert(ocs); + mutex_unlock(&of_mutex); + + return ret; +} +EXPORT_SYMBOL_GPL(of_changeset_revert); + +/** * of_changeset_action - Perform a changeset action * * @ocs: changeset pointer @@ -779,3 +805,4 @@ int of_changeset_action(struct of_changeset *ocs, unsigned long action, list_add_tail(&ce->node, &ocs->entries); return 0; } +EXPORT_SYMBOL_GPL(of_changeset_action); diff --git a/drivers/of/irq.c b/drivers/of/irq.c index 4fa916dffc91..706e3ff67f8b 100644 --- a/drivers/of/irq.c +++ b/drivers/of/irq.c @@ -473,6 +473,7 @@ EXPORT_SYMBOL_GPL(of_irq_to_resource_table); struct of_intc_desc { struct list_head list; + of_irq_init_cb_t irq_init_cb; struct device_node *dev; struct device_node *interrupt_parent; }; @@ -486,6 +487,7 @@ struct of_intc_desc { */ void __init of_irq_init(const struct of_device_id *matches) { + const struct of_device_id *match; struct device_node *np, *parent = NULL; struct of_intc_desc *desc, *temp_desc; struct list_head intc_desc_list, intc_parent_list; @@ -493,10 +495,15 @@ void __init of_irq_init(const struct of_device_id *matches) INIT_LIST_HEAD(&intc_desc_list); INIT_LIST_HEAD(&intc_parent_list); - for_each_matching_node(np, matches) { + for_each_matching_node_and_match(np, matches, &match) { if (!of_find_property(np, "interrupt-controller", NULL) || !of_device_is_available(np)) continue; + + if (WARN(!match->data, "of_irq_init: no init function for %s\n", + match->compatible)) + continue; + /* * Here, we allocate and populate an of_intc_desc with the node * pointer, interrupt-parent device_node etc. @@ -507,6 +514,7 @@ void __init of_irq_init(const struct of_device_id *matches) goto err; } + desc->irq_init_cb = match->data; desc->dev = of_node_get(np); desc->interrupt_parent = of_irq_find_parent(np); if (desc->interrupt_parent == np) @@ -526,27 +534,18 @@ void __init of_irq_init(const struct of_device_id *matches) * The assumption is that NULL parent means a root controller. */ list_for_each_entry_safe(desc, temp_desc, &intc_desc_list, list) { - const struct of_device_id *match; int ret; - of_irq_init_cb_t irq_init_cb; if (desc->interrupt_parent != parent) continue; list_del(&desc->list); - match = of_match_node(matches, desc->dev); - if (WARN(!match->data, - "of_irq_init: no init function for %s\n", - match->compatible)) { - kfree(desc); - continue; - } - pr_debug("of_irq_init: init %s @ %p, parent %p\n", - match->compatible, + pr_debug("of_irq_init: init %s (%p), parent %p\n", + desc->dev->full_name, desc->dev, desc->interrupt_parent); - irq_init_cb = (of_irq_init_cb_t)match->data; - ret = irq_init_cb(desc->dev, desc->interrupt_parent); + ret = desc->irq_init_cb(desc->dev, + desc->interrupt_parent); if (ret) { kfree(desc); continue; diff --git a/drivers/of/of_private.h b/drivers/of/of_private.h index 8e882e706cd8..829469faeb23 100644 --- a/drivers/of/of_private.h +++ b/drivers/of/of_private.h @@ -45,6 +45,8 @@ static inline struct device_node *kobj_to_device_node(struct kobject *kobj) extern int of_property_notify(int action, struct device_node *np, struct property *prop, struct property *old_prop); extern void of_node_release(struct kobject *kobj); +extern int __of_changeset_apply(struct of_changeset *ocs); +extern int __of_changeset_revert(struct of_changeset *ocs); #else /* CONFIG_OF_DYNAMIC */ static inline int of_property_notify(int action, struct device_node *np, struct property *prop, struct property *old_prop) diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c index 54e5af9d7377..82250815e9a5 100644 --- a/drivers/of/overlay.c +++ b/drivers/of/overlay.c @@ -379,9 +379,9 @@ int of_overlay_create(struct device_node *tree) } /* apply the changeset */ - err = of_changeset_apply(&ov->cset); + err = __of_changeset_apply(&ov->cset); if (err) { - pr_err("%s: of_changeset_apply() failed for tree@%s\n", + pr_err("%s: __of_changeset_apply() failed for tree@%s\n", __func__, tree->full_name); goto err_revert_overlay; } @@ -511,7 +511,7 @@ int of_overlay_destroy(int id) list_del(&ov->node); - of_changeset_revert(&ov->cset); + __of_changeset_revert(&ov->cset); of_free_overlay_info(ov); idr_remove(&ov_idr, id); of_changeset_destroy(&ov->cset); @@ -542,7 +542,7 @@ int of_overlay_destroy_all(void) /* the tail of list is guaranteed to be safe to remove */ list_for_each_entry_safe_reverse(ov, ovn, &ov_list, node) { list_del(&ov->node); - of_changeset_revert(&ov->cset); + __of_changeset_revert(&ov->cset); of_free_overlay_info(ov); idr_remove(&ov_idr, ov->id); kfree(ov); diff --git a/drivers/of/platform.c b/drivers/of/platform.c index af98343614d8..8d103e4968be 100644 --- a/drivers/of/platform.c +++ b/drivers/of/platform.c @@ -31,6 +31,7 @@ const struct of_device_id of_default_bus_match_table[] = { #endif /* CONFIG_ARM_AMBA */ {} /* Empty terminated list */ }; +EXPORT_SYMBOL(of_default_bus_match_table); static int of_dev_node_match(struct device *dev, void *data) { diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index e16ea5717b7f..979b6e415cea 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -530,18 +530,14 @@ static void __init of_unittest_changeset(void) unittest(!of_changeset_add_property(&chgset, parent, ppadd), "fail add prop\n"); unittest(!of_changeset_update_property(&chgset, parent, ppupdate), "fail update prop\n"); unittest(!of_changeset_remove_property(&chgset, parent, ppremove), "fail remove prop\n"); - mutex_lock(&of_mutex); unittest(!of_changeset_apply(&chgset), "apply failed\n"); - mutex_unlock(&of_mutex); /* Make sure node names are constructed correctly */ unittest((np = of_find_node_by_path("/testcase-data/changeset/n2/n21")), "'%s' not added\n", n21->full_name); of_node_put(np); - mutex_lock(&of_mutex); unittest(!of_changeset_revert(&chgset), "revert failed\n"); - mutex_unlock(&of_mutex); of_changeset_destroy(&chgset); #endif @@ -757,6 +753,11 @@ static void __init of_unittest_match_node(void) } } +static struct resource test_bus_res = { + .start = 0xfffffff8, + .end = 0xfffffff9, + .flags = IORESOURCE_MEM, +}; static const struct platform_device_info test_bus_info = { .name = "unittest-bus", }; @@ -800,6 +801,15 @@ static void __init of_unittest_platform_populate(void) return; test_bus->dev.of_node = np; + /* + * Add a dummy resource to the test bus node after it is + * registered to catch problems with un-inserted resources. The + * DT code doesn't insert the resources, and it has caused the + * kernel to oops in the past. This makes sure the same bug + * doesn't crop up again. + */ + platform_device_add_resources(test_bus, &test_bus_res, 1); + of_platform_populate(np, match, NULL, &test_bus->dev); for_each_child_of_node(np, child) { for_each_child_of_node(child, grandchild) diff --git a/drivers/power/Kconfig b/drivers/power/Kconfig index 237d7aa73e8c..1ddd13cc0c07 100644 --- a/drivers/power/Kconfig +++ b/drivers/power/Kconfig @@ -160,22 +160,16 @@ config BATTERY_SBS config BATTERY_BQ27XXX tristate "BQ27xxx battery driver" help - Say Y here to enable support for batteries with BQ27xxx (I2C/HDQ) chips. + Say Y here to enable support for batteries with BQ27xxx chips. config BATTERY_BQ27XXX_I2C - bool "BQ27xxx I2C support" + tristate "BQ27xxx I2C support" depends on BATTERY_BQ27XXX depends on I2C default y help - Say Y here to enable support for batteries with BQ27xxx (I2C) chips. - -config BATTERY_BQ27XXX_PLATFORM - bool "BQ27xxx HDQ support" - depends on BATTERY_BQ27XXX - default y - help - Say Y here to enable support for batteries with BQ27xxx (HDQ) chips. + Say Y here to enable support for batteries with BQ27xxx chips + connected over an I2C bus. config BATTERY_DA9030 tristate "DA9030 battery driver" @@ -508,8 +502,7 @@ config AXP20X_POWER This driver provides support for the power supply features of AXP20x PMIC. -source "drivers/power/reset/Kconfig" - endif # POWER_SUPPLY +source "drivers/power/reset/Kconfig" source "drivers/power/avs/Kconfig" diff --git a/drivers/power/Makefile b/drivers/power/Makefile index b656638f8b39..0e4eab55f8d7 100644 --- a/drivers/power/Makefile +++ b/drivers/power/Makefile @@ -31,6 +31,7 @@ obj-$(CONFIG_BATTERY_IPAQ_MICRO) += ipaq_micro_battery.o obj-$(CONFIG_BATTERY_WM97XX) += wm97xx_battery.o obj-$(CONFIG_BATTERY_SBS) += sbs-battery.o obj-$(CONFIG_BATTERY_BQ27XXX) += bq27xxx_battery.o +obj-$(CONFIG_BATTERY_BQ27XXX_I2C) += bq27xxx_battery_i2c.o obj-$(CONFIG_BATTERY_DA9030) += da9030_battery.o obj-$(CONFIG_BATTERY_DA9052) += da9052-battery.o obj-$(CONFIG_CHARGER_DA9150) += da9150-charger.o diff --git a/drivers/power/bq2415x_charger.c b/drivers/power/bq2415x_charger.c index 4afd76848bce..27e89536689a 100644 --- a/drivers/power/bq2415x_charger.c +++ b/drivers/power/bq2415x_charger.c @@ -1704,7 +1704,7 @@ error_4: error_3: bq2415x_power_supply_exit(bq); error_2: - if (bq && bq->notify_node) + if (bq) of_node_put(bq->notify_node); kfree(name); error_1: @@ -1724,9 +1724,7 @@ static int bq2415x_remove(struct i2c_client *client) if (bq->nb.notifier_call) power_supply_unreg_notifier(&bq->nb); - if (bq->notify_node) - of_node_put(bq->notify_node); - + of_node_put(bq->notify_node); bq2415x_sysfs_exit(bq); bq2415x_power_supply_exit(bq); diff --git a/drivers/power/bq27xxx_battery.c b/drivers/power/bq27xxx_battery.c index 880233ce9343..6b027a418943 100644 --- a/drivers/power/bq27xxx_battery.c +++ b/drivers/power/bq27xxx_battery.c @@ -45,11 +45,7 @@ #include <linux/delay.h> #include <linux/platform_device.h> #include <linux/power_supply.h> -#include <linux/idr.h> -#include <linux/i2c.h> #include <linux/slab.h> -#include <linux/interrupt.h> -#include <asm/unaligned.h> #include <linux/power/bq27xxx_battery.h> @@ -78,11 +74,6 @@ #define BQ27XXX_POWER_CONSTANT (29200) /* 29.2 µV^2 * 1000 */ #define BQ27XXX_CURRENT_CONSTANT (3570) /* 3.57 µV * 1000 */ -struct bq27xxx_device_info; -struct bq27xxx_access_methods { - int (*read)(struct bq27xxx_device_info *di, u8 reg, bool single); -}; - #define INVALID_REG_ADDR 0xff /* @@ -110,40 +101,6 @@ enum bq27xxx_reg_index { BQ27XXX_REG_AP, /* Average Power */ }; -struct bq27xxx_reg_cache { - int temperature; - int time_to_empty; - int time_to_empty_avg; - int time_to_full; - int charge_full; - int cycle_count; - int capacity; - int energy; - int flags; - int power_avg; - int health; -}; - -struct bq27xxx_device_info { - struct device *dev; - int id; - enum bq27xxx_chip chip; - - struct bq27xxx_reg_cache cache; - int charge_design_full; - - unsigned long last_update; - struct delayed_work work; - - struct power_supply *bat; - - struct bq27xxx_access_methods bus; - - struct mutex lock; - - u8 *regs; -}; - /* Register mappings */ static u8 bq27000_regs[] = { 0x00, /* CONTROL */ @@ -198,10 +155,10 @@ static u8 bq27500_regs[] = { INVALID_REG_ADDR, /* TTECP - NA */ 0x0c, /* NAC */ 0x12, /* LMD(FCC) */ - 0x1e, /* CYCT */ + 0x2a, /* CYCT */ INVALID_REG_ADDR, /* AE - NA */ - 0x20, /* SOC(RSOC) */ - 0x2e, /* DCAP(ILMD) */ + 0x2c, /* SOC(RSOC) */ + 0x3c, /* DCAP(ILMD) */ INVALID_REG_ADDR, /* AP - NA */ }; @@ -242,7 +199,7 @@ static u8 bq27541_regs[] = { INVALID_REG_ADDR, /* AE - NA */ 0x2c, /* SOC(RSOC) */ 0x3c, /* DCAP */ - 0x76, /* AP */ + 0x24, /* AP */ }; static u8 bq27545_regs[] = { @@ -471,7 +428,10 @@ static int bq27xxx_battery_read_soc(struct bq27xxx_device_info *di) { int soc; - soc = bq27xxx_read(di, BQ27XXX_REG_SOC, false); + if (di->chip == BQ27000 || di->chip == BQ27010) + soc = bq27xxx_read(di, BQ27XXX_REG_SOC, true); + else + soc = bq27xxx_read(di, BQ27XXX_REG_SOC, false); if (soc < 0) dev_dbg(di->dev, "error reading State-of-Charge\n"); @@ -536,7 +496,10 @@ static int bq27xxx_battery_read_dcap(struct bq27xxx_device_info *di) { int dcap; - dcap = bq27xxx_read(di, BQ27XXX_REG_DCAP, false); + if (di->chip == BQ27000 || di->chip == BQ27010) + dcap = bq27xxx_read(di, BQ27XXX_REG_DCAP, true); + else + dcap = bq27xxx_read(di, BQ27XXX_REG_DCAP, false); if (dcap < 0) { dev_dbg(di->dev, "error reading initial last measured discharge\n"); @@ -544,7 +507,7 @@ static int bq27xxx_battery_read_dcap(struct bq27xxx_device_info *di) } if (di->chip == BQ27000 || di->chip == BQ27010) - dcap *= BQ27XXX_CURRENT_CONSTANT / BQ27XXX_RS; + dcap = (dcap << 8) * BQ27XXX_CURRENT_CONSTANT / BQ27XXX_RS; else dcap *= 1000; @@ -710,7 +673,7 @@ static int bq27xxx_battery_read_health(struct bq27xxx_device_info *di) return POWER_SUPPLY_HEALTH_GOOD; } -static void bq27xxx_battery_update(struct bq27xxx_device_info *di) +void bq27xxx_battery_update(struct bq27xxx_device_info *di) { struct bq27xxx_reg_cache cache = {0, }; bool has_ci_flag = di->chip == BQ27000 || di->chip == BQ27010; @@ -722,7 +685,7 @@ static void bq27xxx_battery_update(struct bq27xxx_device_info *di) if (cache.flags >= 0) { cache.temperature = bq27xxx_battery_read_temperature(di); if (has_ci_flag && (cache.flags & BQ27000_FLAG_CI)) { - dev_info(di->dev, "battery is not calibrated! ignoring capacity values\n"); + dev_info_once(di->dev, "battery is not calibrated! ignoring capacity values\n"); cache.capacity = -ENODATA; cache.energy = -ENODATA; cache.time_to_empty = -ENODATA; @@ -761,6 +724,7 @@ static void bq27xxx_battery_update(struct bq27xxx_device_info *di) di->last_update = jiffies; } +EXPORT_SYMBOL_GPL(bq27xxx_battery_update); static void bq27xxx_battery_poll(struct work_struct *work) { @@ -991,32 +955,30 @@ static void bq27xxx_external_power_changed(struct power_supply *psy) schedule_delayed_work(&di->work, 0); } -static int bq27xxx_powersupply_init(struct bq27xxx_device_info *di, - const char *name) +int bq27xxx_battery_setup(struct bq27xxx_device_info *di) { - int ret; struct power_supply_desc *psy_desc; struct power_supply_config psy_cfg = { .drv_data = di, }; + INIT_DELAYED_WORK(&di->work, bq27xxx_battery_poll); + mutex_init(&di->lock); + di->regs = bq27xxx_regs[di->chip]; + psy_desc = devm_kzalloc(di->dev, sizeof(*psy_desc), GFP_KERNEL); if (!psy_desc) return -ENOMEM; - psy_desc->name = name; + psy_desc->name = di->name; psy_desc->type = POWER_SUPPLY_TYPE_BATTERY; psy_desc->properties = bq27xxx_battery_props[di->chip].props; psy_desc->num_properties = bq27xxx_battery_props[di->chip].size; psy_desc->get_property = bq27xxx_battery_get_property; psy_desc->external_power_changed = bq27xxx_external_power_changed; - INIT_DELAYED_WORK(&di->work, bq27xxx_battery_poll); - mutex_init(&di->lock); - di->bat = power_supply_register_no_ws(di->dev, psy_desc, &psy_cfg); if (IS_ERR(di->bat)) { - ret = PTR_ERR(di->bat); - dev_err(di->dev, "failed to register battery: %d\n", ret); - return ret; + dev_err(di->dev, "failed to register battery\n"); + return PTR_ERR(di->bat); } dev_info(di->dev, "support ver. %s enabled\n", DRIVER_VERSION); @@ -1025,8 +987,9 @@ static int bq27xxx_powersupply_init(struct bq27xxx_device_info *di, return 0; } +EXPORT_SYMBOL_GPL(bq27xxx_battery_setup); -static void bq27xxx_powersupply_unregister(struct bq27xxx_device_info *di) +void bq27xxx_battery_teardown(struct bq27xxx_device_info *di) { /* * power_supply_unregister call bq27xxx_battery_get_property which @@ -1042,192 +1005,7 @@ static void bq27xxx_powersupply_unregister(struct bq27xxx_device_info *di) mutex_destroy(&di->lock); } - -/* i2c specific code */ -#ifdef CONFIG_BATTERY_BQ27XXX_I2C - -/* If the system has several batteries we need a different name for each - * of them... - */ -static DEFINE_IDR(battery_id); -static DEFINE_MUTEX(battery_mutex); - -static irqreturn_t bq27xxx_battery_irq_handler_thread(int irq, void *data) -{ - struct bq27xxx_device_info *di = data; - - bq27xxx_battery_update(di); - - return IRQ_HANDLED; -} - -static int bq27xxx_battery_i2c_read(struct bq27xxx_device_info *di, u8 reg, - bool single) -{ - struct i2c_client *client = to_i2c_client(di->dev); - struct i2c_msg msg[2]; - unsigned char data[2]; - int ret; - - if (!client->adapter) - return -ENODEV; - - msg[0].addr = client->addr; - msg[0].flags = 0; - msg[0].buf = ® - msg[0].len = sizeof(reg); - msg[1].addr = client->addr; - msg[1].flags = I2C_M_RD; - msg[1].buf = data; - if (single) - msg[1].len = 1; - else - msg[1].len = 2; - - ret = i2c_transfer(client->adapter, msg, ARRAY_SIZE(msg)); - if (ret < 0) - return ret; - - if (!single) - ret = get_unaligned_le16(data); - else - ret = data[0]; - - return ret; -} - -static int bq27xxx_battery_i2c_probe(struct i2c_client *client, - const struct i2c_device_id *id) -{ - char *name; - struct bq27xxx_device_info *di; - int num; - int retval = 0; - - /* Get new ID for the new battery device */ - mutex_lock(&battery_mutex); - num = idr_alloc(&battery_id, client, 0, 0, GFP_KERNEL); - mutex_unlock(&battery_mutex); - if (num < 0) - return num; - - name = devm_kasprintf(&client->dev, GFP_KERNEL, "%s-%d", id->name, num); - if (!name) { - retval = -ENOMEM; - goto batt_failed; - } - - di = devm_kzalloc(&client->dev, sizeof(*di), GFP_KERNEL); - if (!di) { - retval = -ENOMEM; - goto batt_failed; - } - - di->id = num; - di->dev = &client->dev; - di->chip = id->driver_data; - di->bus.read = &bq27xxx_battery_i2c_read; - di->regs = bq27xxx_regs[di->chip]; - - retval = bq27xxx_powersupply_init(di, name); - if (retval) - goto batt_failed; - - /* Schedule a polling after about 1 min */ - schedule_delayed_work(&di->work, 60 * HZ); - - i2c_set_clientdata(client, di); - - if (client->irq) { - retval = devm_request_threaded_irq(&client->dev, client->irq, - NULL, bq27xxx_battery_irq_handler_thread, - IRQF_ONESHOT, - name, di); - if (retval) { - dev_err(&client->dev, - "Unable to register IRQ %d error %d\n", - client->irq, retval); - return retval; - } - } - - return 0; - -batt_failed: - mutex_lock(&battery_mutex); - idr_remove(&battery_id, num); - mutex_unlock(&battery_mutex); - - return retval; -} - -static int bq27xxx_battery_i2c_remove(struct i2c_client *client) -{ - struct bq27xxx_device_info *di = i2c_get_clientdata(client); - - bq27xxx_powersupply_unregister(di); - - mutex_lock(&battery_mutex); - idr_remove(&battery_id, di->id); - mutex_unlock(&battery_mutex); - - return 0; -} - -static const struct i2c_device_id bq27xxx_id[] = { - { "bq27200", BQ27000 }, - { "bq27210", BQ27010 }, - { "bq27500", BQ27500 }, - { "bq27510", BQ27500 }, - { "bq27520", BQ27500 }, - { "bq27530", BQ27530 }, - { "bq27531", BQ27530 }, - { "bq27541", BQ27541 }, - { "bq27542", BQ27541 }, - { "bq27546", BQ27541 }, - { "bq27742", BQ27541 }, - { "bq27545", BQ27545 }, - { "bq27421", BQ27421 }, - { "bq27425", BQ27421 }, - { "bq27441", BQ27421 }, - { "bq27621", BQ27421 }, - {}, -}; -MODULE_DEVICE_TABLE(i2c, bq27xxx_id); - -static struct i2c_driver bq27xxx_battery_i2c_driver = { - .driver = { - .name = "bq27xxx-battery", - }, - .probe = bq27xxx_battery_i2c_probe, - .remove = bq27xxx_battery_i2c_remove, - .id_table = bq27xxx_id, -}; - -static inline int bq27xxx_battery_i2c_init(void) -{ - int ret = i2c_add_driver(&bq27xxx_battery_i2c_driver); - - if (ret) - pr_err("Unable to register BQ27xxx i2c driver\n"); - - return ret; -} - -static inline void bq27xxx_battery_i2c_exit(void) -{ - i2c_del_driver(&bq27xxx_battery_i2c_driver); -} - -#else - -static inline int bq27xxx_battery_i2c_init(void) { return 0; } -static inline void bq27xxx_battery_i2c_exit(void) {}; - -#endif - -/* platform specific code */ -#ifdef CONFIG_BATTERY_BQ27XXX_PLATFORM +EXPORT_SYMBOL_GPL(bq27xxx_battery_teardown); static int bq27xxx_battery_platform_read(struct bq27xxx_device_info *di, u8 reg, bool single) @@ -1267,7 +1045,6 @@ static int bq27xxx_battery_platform_probe(struct platform_device *pdev) { struct bq27xxx_device_info *di; struct bq27xxx_platform_data *pdata = pdev->dev.platform_data; - const char *name; if (!pdata) { dev_err(&pdev->dev, "no platform_data supplied\n"); @@ -1292,83 +1069,36 @@ static int bq27xxx_battery_platform_probe(struct platform_device *pdev) di->dev = &pdev->dev; di->chip = pdata->chip; - di->regs = bq27xxx_regs[di->chip]; - - name = pdata->name ?: dev_name(&pdev->dev); - di->bus.read = &bq27xxx_battery_platform_read; + di->name = pdata->name ?: dev_name(&pdev->dev); + di->bus.read = bq27xxx_battery_platform_read; - return bq27xxx_powersupply_init(di, name); + return bq27xxx_battery_setup(di); } static int bq27xxx_battery_platform_remove(struct platform_device *pdev) { struct bq27xxx_device_info *di = platform_get_drvdata(pdev); - bq27xxx_powersupply_unregister(di); + bq27xxx_battery_teardown(di); return 0; } +static const struct platform_device_id bq27xxx_battery_platform_id_table[] = { + { "bq27000-battery", }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(platform, bq27xxx_battery_platform_id_table); + static struct platform_driver bq27xxx_battery_platform_driver = { .probe = bq27xxx_battery_platform_probe, .remove = bq27xxx_battery_platform_remove, .driver = { .name = "bq27000-battery", }, + .id_table = bq27xxx_battery_platform_id_table, }; - -static inline int bq27xxx_battery_platform_init(void) -{ - int ret = platform_driver_register(&bq27xxx_battery_platform_driver); - - if (ret) - pr_err("Unable to register BQ27xxx platform driver\n"); - - return ret; -} - -static inline void bq27xxx_battery_platform_exit(void) -{ - platform_driver_unregister(&bq27xxx_battery_platform_driver); -} - -#else - -static inline int bq27xxx_battery_platform_init(void) { return 0; } -static inline void bq27xxx_battery_platform_exit(void) {}; - -#endif - -/* - * Module stuff - */ - -static int __init bq27xxx_battery_init(void) -{ - int ret; - - ret = bq27xxx_battery_i2c_init(); - if (ret) - return ret; - - ret = bq27xxx_battery_platform_init(); - if (ret) - bq27xxx_battery_i2c_exit(); - - return ret; -} -module_init(bq27xxx_battery_init); - -static void __exit bq27xxx_battery_exit(void) -{ - bq27xxx_battery_platform_exit(); - bq27xxx_battery_i2c_exit(); -} -module_exit(bq27xxx_battery_exit); - -#ifdef CONFIG_BATTERY_BQ27XXX_PLATFORM -MODULE_ALIAS("platform:bq27000-battery"); -#endif +module_platform_driver(bq27xxx_battery_platform_driver); MODULE_AUTHOR("Rodolfo Giometti <giometti@linux.it>"); MODULE_DESCRIPTION("BQ27xxx battery monitor driver"); diff --git a/drivers/power/bq27xxx_battery_i2c.c b/drivers/power/bq27xxx_battery_i2c.c new file mode 100644 index 000000000000..9429e66be096 --- /dev/null +++ b/drivers/power/bq27xxx_battery_i2c.c @@ -0,0 +1,150 @@ +/* + * SCI Reset driver for Keystone based devices + * + * Copyright (C) 2015 Texas Instruments Incorporated - http://www.ti.com/ + * Andrew F. Davis <afd@ti.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 + * published by the Free Software Foundation. + * + * 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. + */ + +#include <linux/i2c.h> +#include <linux/interrupt.h> +#include <linux/module.h> +#include <asm/unaligned.h> + +#include <linux/power/bq27xxx_battery.h> + +static irqreturn_t bq27xxx_battery_irq_handler_thread(int irq, void *data) +{ + struct bq27xxx_device_info *di = data; + + bq27xxx_battery_update(di); + + return IRQ_HANDLED; +} + +static int bq27xxx_battery_i2c_read(struct bq27xxx_device_info *di, u8 reg, + bool single) +{ + struct i2c_client *client = to_i2c_client(di->dev); + struct i2c_msg msg[2]; + unsigned char data[2]; + int ret; + + if (!client->adapter) + return -ENODEV; + + msg[0].addr = client->addr; + msg[0].flags = 0; + msg[0].buf = ® + msg[0].len = sizeof(reg); + msg[1].addr = client->addr; + msg[1].flags = I2C_M_RD; + msg[1].buf = data; + if (single) + msg[1].len = 1; + else + msg[1].len = 2; + + ret = i2c_transfer(client->adapter, msg, ARRAY_SIZE(msg)); + if (ret < 0) + return ret; + + if (!single) + ret = get_unaligned_le16(data); + else + ret = data[0]; + + return ret; +} + +static int bq27xxx_battery_i2c_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + struct bq27xxx_device_info *di; + int ret; + + di = devm_kzalloc(&client->dev, sizeof(*di), GFP_KERNEL); + if (!di) + return -ENOMEM; + + di->dev = &client->dev; + di->chip = id->driver_data; + di->name = id->name; + di->bus.read = bq27xxx_battery_i2c_read; + + ret = bq27xxx_battery_setup(di); + if (ret) + return ret; + + /* Schedule a polling after about 1 min */ + schedule_delayed_work(&di->work, 60 * HZ); + + i2c_set_clientdata(client, di); + + if (client->irq) { + ret = devm_request_threaded_irq(&client->dev, client->irq, + NULL, bq27xxx_battery_irq_handler_thread, + IRQF_ONESHOT, + di->name, di); + if (ret) { + dev_err(&client->dev, + "Unable to register IRQ %d error %d\n", + client->irq, ret); + return ret; + } + } + + return 0; +} + +static int bq27xxx_battery_i2c_remove(struct i2c_client *client) +{ + struct bq27xxx_device_info *di = i2c_get_clientdata(client); + + bq27xxx_battery_teardown(di); + + return 0; +} + +static const struct i2c_device_id bq27xxx_i2c_id_table[] = { + { "bq27200", BQ27000 }, + { "bq27210", BQ27010 }, + { "bq27500", BQ27500 }, + { "bq27510", BQ27500 }, + { "bq27520", BQ27500 }, + { "bq27530", BQ27530 }, + { "bq27531", BQ27530 }, + { "bq27541", BQ27541 }, + { "bq27542", BQ27541 }, + { "bq27546", BQ27541 }, + { "bq27742", BQ27541 }, + { "bq27545", BQ27545 }, + { "bq27421", BQ27421 }, + { "bq27425", BQ27421 }, + { "bq27441", BQ27421 }, + { "bq27621", BQ27421 }, + {}, +}; +MODULE_DEVICE_TABLE(i2c, bq27xxx_i2c_id_table); + +static struct i2c_driver bq27xxx_battery_i2c_driver = { + .driver = { + .name = "bq27xxx-battery", + }, + .probe = bq27xxx_battery_i2c_probe, + .remove = bq27xxx_battery_i2c_remove, + .id_table = bq27xxx_i2c_id_table, +}; +module_i2c_driver(bq27xxx_battery_i2c_driver); + +MODULE_AUTHOR("Andrew F. Davis <afd@ti.com>"); +MODULE_DESCRIPTION("BQ27xxx battery monitor i2c driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/power/ds2782_battery.c b/drivers/power/ds2782_battery.c index ed4d756d21e4..a1b7e0592245 100644 --- a/drivers/power/ds2782_battery.c +++ b/drivers/power/ds2782_battery.c @@ -59,7 +59,7 @@ struct ds278x_info { struct i2c_client *client; struct power_supply *battery; struct power_supply_desc battery_desc; - struct ds278x_battery_ops *ops; + const struct ds278x_battery_ops *ops; struct delayed_work bat_work; int id; int rsns; @@ -361,7 +361,7 @@ enum ds278x_num_id { DS2786, }; -static struct ds278x_battery_ops ds278x_ops[] = { +static const struct ds278x_battery_ops ds278x_ops[] = { [DS2782] = { .get_battery_current = ds2782_get_current, .get_battery_voltage = ds2782_get_voltage, diff --git a/drivers/power/generic-adc-battery.c b/drivers/power/generic-adc-battery.c index fedc5818fab7..edb36bf781b0 100644 --- a/drivers/power/generic-adc-battery.c +++ b/drivers/power/generic-adc-battery.c @@ -206,7 +206,7 @@ static void gab_work(struct work_struct *work) bool is_plugged; int status; - delayed_work = container_of(work, struct delayed_work, work); + delayed_work = to_delayed_work(work); adc_bat = container_of(delayed_work, struct gab, bat_work); pdata = adc_bat->pdata; status = adc_bat->status; diff --git a/drivers/power/isp1704_charger.c b/drivers/power/isp1704_charger.c index f2a7d970388f..46a292aa182d 100644 --- a/drivers/power/isp1704_charger.c +++ b/drivers/power/isp1704_charger.c @@ -76,7 +76,7 @@ static inline int isp1704_read(struct isp1704_charger *isp, u32 reg) return usb_phy_io_read(isp->phy, reg); } -static inline int isp1704_write(struct isp1704_charger *isp, u32 val, u32 reg) +static inline int isp1704_write(struct isp1704_charger *isp, u32 reg, u32 val) { return usb_phy_io_write(isp->phy, val, reg); } diff --git a/drivers/power/max8903_charger.c b/drivers/power/max8903_charger.c index 6d39d52040d4..17876caf31e5 100644 --- a/drivers/power/max8903_charger.c +++ b/drivers/power/max8903_charger.c @@ -291,10 +291,10 @@ static int max8903_probe(struct platform_device *pdev) if (pdata->dc_valid) { ret = devm_request_threaded_irq(dev, gpio_to_irq(pdata->dok), - NULL, max8903_dcin, - IRQF_TRIGGER_FALLING | - IRQF_TRIGGER_RISING, - "MAX8903 DC IN", data); + NULL, max8903_dcin, + IRQF_TRIGGER_FALLING | + IRQF_TRIGGER_RISING | IRQF_ONESHOT, + "MAX8903 DC IN", data); if (ret) { dev_err(dev, "Cannot request irq %d for DC (%d)\n", gpio_to_irq(pdata->dok), ret); @@ -304,10 +304,10 @@ static int max8903_probe(struct platform_device *pdev) if (pdata->usb_valid) { ret = devm_request_threaded_irq(dev, gpio_to_irq(pdata->uok), - NULL, max8903_usbin, - IRQF_TRIGGER_FALLING | - IRQF_TRIGGER_RISING, - "MAX8903 USB IN", data); + NULL, max8903_usbin, + IRQF_TRIGGER_FALLING | + IRQF_TRIGGER_RISING | IRQF_ONESHOT, + "MAX8903 USB IN", data); if (ret) { dev_err(dev, "Cannot request irq %d for USB (%d)\n", gpio_to_irq(pdata->uok), ret); @@ -317,10 +317,10 @@ static int max8903_probe(struct platform_device *pdev) if (pdata->flt) { ret = devm_request_threaded_irq(dev, gpio_to_irq(pdata->flt), - NULL, max8903_fault, - IRQF_TRIGGER_FALLING | - IRQF_TRIGGER_RISING, - "MAX8903 Fault", data); + NULL, max8903_fault, + IRQF_TRIGGER_FALLING | + IRQF_TRIGGER_RISING | IRQF_ONESHOT, + "MAX8903 Fault", data); if (ret) { dev_err(dev, "Cannot request irq %d for Fault (%d)\n", gpio_to_irq(pdata->flt), ret); diff --git a/drivers/power/reset/at91-reset.c b/drivers/power/reset/at91-reset.c index 3f6b5dd7c3d4..1b5d450586d1 100644 --- a/drivers/power/reset/at91-reset.c +++ b/drivers/power/reset/at91-reset.c @@ -198,6 +198,7 @@ static int __init at91_reset_probe(struct platform_device *pdev) at91_ramc_base[idx] = of_iomap(np, 0); if (!at91_ramc_base[idx]) { dev_err(&pdev->dev, "Could not map ram controller address\n"); + of_node_put(np); return -ENODEV; } idx++; diff --git a/drivers/power/test_power.c b/drivers/power/test_power.c index 83c42ea88f2b..57246cdbd042 100644 --- a/drivers/power/test_power.c +++ b/drivers/power/test_power.c @@ -301,6 +301,8 @@ static int map_get_value(struct battery_property_map *map, const char *key, buf[MAX_KEYLENGTH-1] = '\0'; cr = strnlen(buf, MAX_KEYLENGTH) - 1; + if (cr < 0) + return def_val; if (buf[cr] == '\n') buf[cr] = '\0'; diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig index 8df0b0e62976..8155e80dd3f8 100644 --- a/drivers/regulator/Kconfig +++ b/drivers/regulator/Kconfig @@ -274,6 +274,15 @@ config REGULATOR_ISL6271A help This driver supports ISL6271A voltage regulator chip. +config REGULATOR_LM363X + tristate "TI LM363X voltage regulators" + depends on MFD_TI_LMU + help + This driver supports LM3631 and LM3632 voltage regulators for + the LCD bias. + One boost output voltage is configurable and always on. + Other LDOs are used for the display module. + config REGULATOR_LP3971 tristate "National Semiconductors LP3971 PMIC regulator driver" depends on I2C @@ -446,6 +455,7 @@ config REGULATOR_MC13892 config REGULATOR_MT6311 tristate "MediaTek MT6311 PMIC" depends on I2C + select REGMAP_I2C help Say y here to select this option to enable the power regulator of MediaTek MT6311 PMIC. @@ -504,6 +514,22 @@ config REGULATOR_PFUZE100 Say y here to support the regulators found on the Freescale PFUZE100/PFUZE200 PMIC. +config REGULATOR_PV88060 + tristate "Powerventure Semiconductor PV88060 regulator" + depends on I2C + select REGMAP_I2C + help + Say y here to support the voltage regulators and convertors + PV88060 + +config REGULATOR_PV88090 + tristate "Powerventure Semiconductor PV88090 regulator" + depends on I2C + select REGMAP_I2C + help + Say y here to support the voltage regulators and convertors + on PV88090 + config REGULATOR_PWM tristate "PWM voltage regulator" depends on PWM @@ -588,10 +614,10 @@ config REGULATOR_S2MPA01 via I2C bus. S2MPA01 has 10 Bucks and 26 LDO outputs. config REGULATOR_S2MPS11 - tristate "Samsung S2MPS11/S2MPS13/S2MPS14/S2MPU02 voltage regulator" + tristate "Samsung S2MPS11/13/14/15/S2MPU02 voltage regulator" depends on MFD_SEC_CORE help - This driver supports a Samsung S2MPS11/S2MPS13/S2MPS14/S2MPU02 voltage + This driver supports a Samsung S2MPS11/13/14/15/S2MPU02 voltage output regulator via I2C bus. The chip is comprised of high efficient Buck converters including Dual-Phase Buck converter, Buck-Boost converter, various LDOs. @@ -680,6 +706,13 @@ config REGULATOR_TPS6507X three step-down converters and two general-purpose LDO voltage regulators. It supports TI's software based Class-2 SmartReflex implementation. +config REGULATOR_TPS65086 + tristate "TI TPS65086 Power regulators" + depends on MFD_TPS65086 + help + This driver provides support for the voltage regulators on + TI TPS65086 PMICs. + config REGULATOR_TPS65090 tristate "TI TPS65090 Power regulator" depends on MFD_TPS65090 diff --git a/drivers/regulator/Makefile b/drivers/regulator/Makefile index 0f8174913c17..980b1943fa81 100644 --- a/drivers/regulator/Makefile +++ b/drivers/regulator/Makefile @@ -36,6 +36,7 @@ obj-$(CONFIG_REGULATOR_GPIO) += gpio-regulator.o obj-$(CONFIG_REGULATOR_HI6421) += hi6421-regulator.o obj-$(CONFIG_REGULATOR_ISL6271A) += isl6271a-regulator.o obj-$(CONFIG_REGULATOR_ISL9305) += isl9305.o +obj-$(CONFIG_REGULATOR_LM363X) += lm363x-regulator.o obj-$(CONFIG_REGULATOR_LP3971) += lp3971.o obj-$(CONFIG_REGULATOR_LP3972) += lp3972.o obj-$(CONFIG_REGULATOR_LP872X) += lp872x.o @@ -66,6 +67,8 @@ obj-$(CONFIG_REGULATOR_QCOM_SMD_RPM) += qcom_smd-regulator.o obj-$(CONFIG_REGULATOR_QCOM_SPMI) += qcom_spmi-regulator.o obj-$(CONFIG_REGULATOR_PALMAS) += palmas-regulator.o obj-$(CONFIG_REGULATOR_PFUZE100) += pfuze100-regulator.o +obj-$(CONFIG_REGULATOR_PV88060) += pv88060-regulator.o +obj-$(CONFIG_REGULATOR_PV88090) += pv88090-regulator.o obj-$(CONFIG_REGULATOR_PWM) += pwm-regulator.o obj-$(CONFIG_REGULATOR_TPS51632) += tps51632-regulator.o obj-$(CONFIG_REGULATOR_PBIAS) += pbias-regulator.o @@ -85,6 +88,7 @@ obj-$(CONFIG_REGULATOR_TPS6105X) += tps6105x-regulator.o obj-$(CONFIG_REGULATOR_TPS62360) += tps62360-regulator.o obj-$(CONFIG_REGULATOR_TPS65023) += tps65023-regulator.o obj-$(CONFIG_REGULATOR_TPS6507X) += tps6507x-regulator.o +obj-$(CONFIG_REGULATOR_TPS65086) += tps65086-regulator.o obj-$(CONFIG_REGULATOR_TPS65090) += tps65090-regulator.o obj-$(CONFIG_REGULATOR_TPS65217) += tps65217-regulator.o obj-$(CONFIG_REGULATOR_TPS65218) += tps65218-regulator.o diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c index 35de22fdb7a0..f2e1a39ce0f3 100644 --- a/drivers/regulator/axp20x-regulator.c +++ b/drivers/regulator/axp20x-regulator.c @@ -27,8 +27,8 @@ #define AXP20X_IO_ENABLED 0x03 #define AXP20X_IO_DISABLED 0x07 -#define AXP22X_IO_ENABLED 0x04 -#define AXP22X_IO_DISABLED 0x03 +#define AXP22X_IO_ENABLED 0x03 +#define AXP22X_IO_DISABLED 0x04 #define AXP20X_WORKMODE_DCDC2_MASK BIT(2) #define AXP20X_WORKMODE_DCDC3_MASK BIT(1) diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 73b7683355cd..744c9889f88d 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -132,24 +132,24 @@ static bool have_full_constraints(void) return has_full_constraints || of_have_populated_dt(); } +static inline struct regulator_dev *rdev_get_supply(struct regulator_dev *rdev) +{ + if (rdev && rdev->supply) + return rdev->supply->rdev; + + return NULL; +} + /** * regulator_lock_supply - lock a regulator and its supplies * @rdev: regulator source */ static void regulator_lock_supply(struct regulator_dev *rdev) { - struct regulator *supply; - int i = 0; - - while (1) { - mutex_lock_nested(&rdev->mutex, i++); - supply = rdev->supply; - - if (!rdev->supply) - return; + int i; - rdev = supply->rdev; - } + for (i = 0; rdev; rdev = rdev_get_supply(rdev), i++) + mutex_lock_nested(&rdev->mutex, i); } /** @@ -2368,7 +2368,6 @@ static void regulator_disable_work(struct work_struct *work) int regulator_disable_deferred(struct regulator *regulator, int ms) { struct regulator_dev *rdev = regulator->rdev; - int ret; if (regulator->always_on) return 0; @@ -2380,13 +2379,9 @@ int regulator_disable_deferred(struct regulator *regulator, int ms) rdev->deferred_disables++; mutex_unlock(&rdev->mutex); - ret = queue_delayed_work(system_power_efficient_wq, - &rdev->disable_work, - msecs_to_jiffies(ms)); - if (ret < 0) - return ret; - else - return 0; + queue_delayed_work(system_power_efficient_wq, &rdev->disable_work, + msecs_to_jiffies(ms)); + return 0; } EXPORT_SYMBOL_GPL(regulator_disable_deferred); @@ -3451,8 +3446,10 @@ int regulator_bulk_get(struct device *dev, int num_consumers, consumers[i].consumer = NULL; for (i = 0; i < num_consumers; i++) { - consumers[i].consumer = regulator_get(dev, - consumers[i].supply); + consumers[i].consumer = _regulator_get(dev, + consumers[i].supply, + false, + !consumers[i].optional); if (IS_ERR(consumers[i].consumer)) { ret = PTR_ERR(consumers[i].consumer); dev_err(dev, "Failed to get supply '%s': %d\n", @@ -3708,7 +3705,7 @@ static umode_t regulator_attr_is_visible(struct kobject *kobj, struct attribute *attr, int idx) { struct device *dev = kobj_to_dev(kobj); - struct regulator_dev *rdev = container_of(dev, struct regulator_dev, dev); + struct regulator_dev *rdev = dev_to_rdev(dev); const struct regulator_ops *ops = rdev->desc->ops; umode_t mode = attr->mode; diff --git a/drivers/regulator/da903x.c b/drivers/regulator/da903x.c index affa1b191314..33e8f3b8d2bd 100644 --- a/drivers/regulator/da903x.c +++ b/drivers/regulator/da903x.c @@ -257,7 +257,7 @@ static const struct regulator_linear_range da9034_ldo12_ranges[] = { REGULATOR_LINEAR_RANGE(2700000, 8, 15, 50000), }; -static struct regulator_ops da903x_regulator_ldo_ops = { +static const struct regulator_ops da903x_regulator_ldo_ops = { .set_voltage_sel = da903x_set_voltage_sel, .get_voltage_sel = da903x_get_voltage_sel, .list_voltage = regulator_list_voltage_linear, @@ -268,7 +268,7 @@ static struct regulator_ops da903x_regulator_ldo_ops = { }; /* NOTE: this is dedicated for the insane DA9030 LDO14 */ -static struct regulator_ops da9030_regulator_ldo14_ops = { +static const struct regulator_ops da9030_regulator_ldo14_ops = { .set_voltage_sel = da903x_set_voltage_sel, .get_voltage_sel = da903x_get_voltage_sel, .list_voltage = da9030_list_ldo14_voltage, @@ -279,7 +279,7 @@ static struct regulator_ops da9030_regulator_ldo14_ops = { }; /* NOTE: this is dedicated for the DA9030 LDO1 and LDO15 that have locks */ -static struct regulator_ops da9030_regulator_ldo1_15_ops = { +static const struct regulator_ops da9030_regulator_ldo1_15_ops = { .set_voltage_sel = da9030_set_ldo1_15_voltage_sel, .get_voltage_sel = da903x_get_voltage_sel, .list_voltage = regulator_list_voltage_linear, @@ -289,7 +289,7 @@ static struct regulator_ops da9030_regulator_ldo1_15_ops = { .is_enabled = da903x_is_enabled, }; -static struct regulator_ops da9034_regulator_dvc_ops = { +static const struct regulator_ops da9034_regulator_dvc_ops = { .set_voltage_sel = da9034_set_dvc_voltage_sel, .get_voltage_sel = da903x_get_voltage_sel, .list_voltage = regulator_list_voltage_linear, @@ -300,7 +300,7 @@ static struct regulator_ops da9034_regulator_dvc_ops = { }; /* NOTE: this is dedicated for the insane LDO12 */ -static struct regulator_ops da9034_regulator_ldo12_ops = { +static const struct regulator_ops da9034_regulator_ldo12_ops = { .set_voltage_sel = da903x_set_voltage_sel, .get_voltage_sel = da903x_get_voltage_sel, .list_voltage = regulator_list_voltage_linear_range, diff --git a/drivers/regulator/da9052-regulator.c b/drivers/regulator/da9052-regulator.c index 12a25b40e473..1050cb77561a 100644 --- a/drivers/regulator/da9052-regulator.c +++ b/drivers/regulator/da9052-regulator.c @@ -265,7 +265,7 @@ static int da9052_regulator_set_voltage_time_sel(struct regulator_dev *rdev, return ret; } -static struct regulator_ops da9052_dcdc_ops = { +static const struct regulator_ops da9052_dcdc_ops = { .get_current_limit = da9052_dcdc_get_current_limit, .set_current_limit = da9052_dcdc_set_current_limit, @@ -279,7 +279,7 @@ static struct regulator_ops da9052_dcdc_ops = { .disable = regulator_disable_regmap, }; -static struct regulator_ops da9052_ldo_ops = { +static const struct regulator_ops da9052_ldo_ops = { .list_voltage = da9052_list_voltage, .map_voltage = da9052_map_voltage, .get_voltage_sel = regulator_get_voltage_sel_regmap, diff --git a/drivers/regulator/da9055-regulator.c b/drivers/regulator/da9055-regulator.c index cafdafbffcaf..d029c941a1e1 100644 --- a/drivers/regulator/da9055-regulator.c +++ b/drivers/regulator/da9055-regulator.c @@ -324,7 +324,7 @@ static int da9055_suspend_disable(struct regulator_dev *rdev) return 0; } -static struct regulator_ops da9055_buck_ops = { +static const struct regulator_ops da9055_buck_ops = { .get_mode = da9055_buck_get_mode, .set_mode = da9055_buck_set_mode, @@ -345,7 +345,7 @@ static struct regulator_ops da9055_buck_ops = { .set_suspend_mode = da9055_buck_set_mode, }; -static struct regulator_ops da9055_ldo_ops = { +static const struct regulator_ops da9055_ldo_ops = { .get_mode = da9055_ldo_get_mode, .set_mode = da9055_ldo_set_mode, diff --git a/drivers/regulator/da9062-regulator.c b/drivers/regulator/da9062-regulator.c index 5638fe8d759d..0638c8b40521 100644 --- a/drivers/regulator/da9062-regulator.c +++ b/drivers/regulator/da9062-regulator.c @@ -371,7 +371,7 @@ static int da9062_ldo_set_suspend_mode(struct regulator_dev *rdev, return regmap_field_write(regl->suspend_sleep, val); } -static struct regulator_ops da9062_buck_ops = { +static const struct regulator_ops da9062_buck_ops = { .enable = regulator_enable_regmap, .disable = regulator_disable_regmap, .is_enabled = regulator_is_enabled_regmap, @@ -389,7 +389,7 @@ static struct regulator_ops da9062_buck_ops = { .set_suspend_mode = da9062_buck_set_suspend_mode, }; -static struct regulator_ops da9062_ldo_ops = { +static const struct regulator_ops da9062_ldo_ops = { .enable = regulator_enable_regmap, .disable = regulator_disable_regmap, .is_enabled = regulator_is_enabled_regmap, diff --git a/drivers/regulator/da9063-regulator.c b/drivers/regulator/da9063-regulator.c index 536e931eb921..ed9e7e96f877 100644 --- a/drivers/regulator/da9063-regulator.c +++ b/drivers/regulator/da9063-regulator.c @@ -427,7 +427,7 @@ static int da9063_ldo_set_suspend_mode(struct regulator_dev *rdev, unsigned mode return regmap_field_write(regl->suspend_sleep, val); } -static struct regulator_ops da9063_buck_ops = { +static const struct regulator_ops da9063_buck_ops = { .enable = regulator_enable_regmap, .disable = regulator_disable_regmap, .is_enabled = regulator_is_enabled_regmap, @@ -445,7 +445,7 @@ static struct regulator_ops da9063_buck_ops = { .set_suspend_mode = da9063_buck_set_suspend_mode, }; -static struct regulator_ops da9063_ldo_ops = { +static const struct regulator_ops da9063_ldo_ops = { .enable = regulator_enable_regmap, .disable = regulator_disable_regmap, .is_enabled = regulator_is_enabled_regmap, diff --git a/drivers/regulator/da9210-regulator.c b/drivers/regulator/da9210-regulator.c index b3517830edb6..8b3cc9f0cd64 100644 --- a/drivers/regulator/da9210-regulator.c +++ b/drivers/regulator/da9210-regulator.c @@ -46,7 +46,7 @@ static int da9210_set_current_limit(struct regulator_dev *rdev, int min_uA, int max_uA); static int da9210_get_current_limit(struct regulator_dev *rdev); -static struct regulator_ops da9210_buck_ops = { +static const struct regulator_ops da9210_buck_ops = { .enable = regulator_enable_regmap, .disable = regulator_disable_regmap, .is_enabled = regulator_is_enabled_regmap, diff --git a/drivers/regulator/da9211-regulator.c b/drivers/regulator/da9211-regulator.c index 04ef65b7eb3d..236abf473db5 100644 --- a/drivers/regulator/da9211-regulator.c +++ b/drivers/regulator/da9211-regulator.c @@ -219,7 +219,7 @@ static int da9211_get_current_limit(struct regulator_dev *rdev) return current_limits[data]; } -static struct regulator_ops da9211_buck_ops = { +static const struct regulator_ops da9211_buck_ops = { .get_mode = da9211_buck_get_mode, .set_mode = da9211_buck_set_mode, .enable = regulator_enable_regmap, diff --git a/drivers/regulator/devres.c b/drivers/regulator/devres.c index 6ec1d400adae..6ad8ab4c578d 100644 --- a/drivers/regulator/devres.c +++ b/drivers/regulator/devres.c @@ -164,8 +164,11 @@ int devm_regulator_bulk_get(struct device *dev, int num_consumers, consumers[i].consumer = NULL; for (i = 0; i < num_consumers; i++) { - consumers[i].consumer = devm_regulator_get(dev, - consumers[i].supply); + consumers[i].consumer = _devm_regulator_get(dev, + consumers[i].supply, + consumers[i].optional ? + OPTIONAL_GET : + NORMAL_GET); if (IS_ERR(consumers[i].consumer)) { ret = PTR_ERR(consumers[i].consumer); dev_err(dev, "Failed to get supply '%s': %d\n", diff --git a/drivers/regulator/lm363x-regulator.c b/drivers/regulator/lm363x-regulator.c new file mode 100644 index 000000000000..f53e63301a20 --- /dev/null +++ b/drivers/regulator/lm363x-regulator.c @@ -0,0 +1,291 @@ +/* + * TI LM363X Regulator Driver + * + * Copyright 2015 Texas Instruments + * + * Author: Milo Kim <milo.kim@ti.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 + * published by the Free Software Foundation. + */ + +#include <linux/err.h> +#include <linux/kernel.h> +#include <linux/mfd/ti-lmu.h> +#include <linux/mfd/ti-lmu-register.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_gpio.h> +#include <linux/platform_device.h> +#include <linux/regulator/driver.h> +#include <linux/regulator/of_regulator.h> +#include <linux/slab.h> + +/* LM3631 */ +#define LM3631_BOOST_VSEL_MAX 0x25 +#define LM3631_LDO_VSEL_MAX 0x28 +#define LM3631_CONT_VSEL_MAX 0x03 +#define LM3631_VBOOST_MIN 4500000 +#define LM3631_VCONT_MIN 1800000 +#define LM3631_VLDO_MIN 4000000 +#define ENABLE_TIME_USEC 1000 + +/* LM3632 */ +#define LM3632_BOOST_VSEL_MAX 0x26 +#define LM3632_LDO_VSEL_MAX 0x29 +#define LM3632_VBOOST_MIN 4500000 +#define LM3632_VLDO_MIN 4000000 + +/* Common */ +#define LM363X_STEP_50mV 50000 +#define LM363X_STEP_500mV 500000 + +static const int ldo_cont_enable_time[] = { + 0, 2000, 5000, 10000, 20000, 50000, 100000, 200000, +}; + +static int lm363x_regulator_enable_time(struct regulator_dev *rdev) +{ + enum lm363x_regulator_id id = rdev_get_id(rdev); + u8 val, addr, mask; + + switch (id) { + case LM3631_LDO_CONT: + addr = LM3631_REG_ENTIME_VCONT; + mask = LM3631_ENTIME_CONT_MASK; + break; + case LM3631_LDO_OREF: + addr = LM3631_REG_ENTIME_VOREF; + mask = LM3631_ENTIME_MASK; + break; + case LM3631_LDO_POS: + addr = LM3631_REG_ENTIME_VPOS; + mask = LM3631_ENTIME_MASK; + break; + case LM3631_LDO_NEG: + addr = LM3631_REG_ENTIME_VNEG; + mask = LM3631_ENTIME_MASK; + break; + default: + return 0; + } + + if (regmap_read(rdev->regmap, addr, (unsigned int *)&val)) + return -EINVAL; + + val = (val & mask) >> LM3631_ENTIME_SHIFT; + + if (id == LM3631_LDO_CONT) + return ldo_cont_enable_time[val]; + else + return ENABLE_TIME_USEC * val; +} + +static struct regulator_ops lm363x_boost_voltage_table_ops = { + .list_voltage = regulator_list_voltage_linear, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .get_voltage_sel = regulator_get_voltage_sel_regmap, +}; + +static struct regulator_ops lm363x_regulator_voltage_table_ops = { + .list_voltage = regulator_list_voltage_linear, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .is_enabled = regulator_is_enabled_regmap, + .enable_time = lm363x_regulator_enable_time, +}; + +static const struct regulator_desc lm363x_regulator_desc[] = { + /* LM3631 */ + { + .name = "vboost", + .of_match = "vboost", + .id = LM3631_BOOST, + .ops = &lm363x_boost_voltage_table_ops, + .n_voltages = LM3631_BOOST_VSEL_MAX + 1, + .min_uV = LM3631_VBOOST_MIN, + .uV_step = LM363X_STEP_50mV, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LM3631_REG_VOUT_BOOST, + .vsel_mask = LM3631_VOUT_MASK, + }, + { + .name = "ldo_cont", + .of_match = "vcont", + .id = LM3631_LDO_CONT, + .ops = &lm363x_regulator_voltage_table_ops, + .n_voltages = LM3631_CONT_VSEL_MAX + 1, + .min_uV = LM3631_VCONT_MIN, + .uV_step = LM363X_STEP_500mV, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LM3631_REG_VOUT_CONT, + .vsel_mask = LM3631_VOUT_CONT_MASK, + .enable_reg = LM3631_REG_LDO_CTRL2, + .enable_mask = LM3631_EN_CONT_MASK, + }, + { + .name = "ldo_oref", + .of_match = "voref", + .id = LM3631_LDO_OREF, + .ops = &lm363x_regulator_voltage_table_ops, + .n_voltages = LM3631_LDO_VSEL_MAX + 1, + .min_uV = LM3631_VLDO_MIN, + .uV_step = LM363X_STEP_50mV, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LM3631_REG_VOUT_OREF, + .vsel_mask = LM3631_VOUT_MASK, + .enable_reg = LM3631_REG_LDO_CTRL1, + .enable_mask = LM3631_EN_OREF_MASK, + }, + { + .name = "ldo_vpos", + .of_match = "vpos", + .id = LM3631_LDO_POS, + .ops = &lm363x_regulator_voltage_table_ops, + .n_voltages = LM3631_LDO_VSEL_MAX + 1, + .min_uV = LM3631_VLDO_MIN, + .uV_step = LM363X_STEP_50mV, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LM3631_REG_VOUT_POS, + .vsel_mask = LM3631_VOUT_MASK, + .enable_reg = LM3631_REG_LDO_CTRL1, + .enable_mask = LM3631_EN_VPOS_MASK, + }, + { + .name = "ldo_vneg", + .of_match = "vneg", + .id = LM3631_LDO_NEG, + .ops = &lm363x_regulator_voltage_table_ops, + .n_voltages = LM3631_LDO_VSEL_MAX + 1, + .min_uV = LM3631_VLDO_MIN, + .uV_step = LM363X_STEP_50mV, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LM3631_REG_VOUT_NEG, + .vsel_mask = LM3631_VOUT_MASK, + .enable_reg = LM3631_REG_LDO_CTRL1, + .enable_mask = LM3631_EN_VNEG_MASK, + }, + /* LM3632 */ + { + .name = "vboost", + .of_match = "vboost", + .id = LM3632_BOOST, + .ops = &lm363x_boost_voltage_table_ops, + .n_voltages = LM3632_BOOST_VSEL_MAX + 1, + .min_uV = LM3632_VBOOST_MIN, + .uV_step = LM363X_STEP_50mV, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LM3632_REG_VOUT_BOOST, + .vsel_mask = LM3632_VOUT_MASK, + }, + { + .name = "ldo_vpos", + .of_match = "vpos", + .id = LM3632_LDO_POS, + .ops = &lm363x_regulator_voltage_table_ops, + .n_voltages = LM3632_LDO_VSEL_MAX + 1, + .min_uV = LM3632_VLDO_MIN, + .uV_step = LM363X_STEP_50mV, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LM3632_REG_VOUT_POS, + .vsel_mask = LM3632_VOUT_MASK, + .enable_reg = LM3632_REG_BIAS_CONFIG, + .enable_mask = LM3632_EN_VPOS_MASK, + }, + { + .name = "ldo_vneg", + .of_match = "vneg", + .id = LM3632_LDO_NEG, + .ops = &lm363x_regulator_voltage_table_ops, + .n_voltages = LM3632_LDO_VSEL_MAX + 1, + .min_uV = LM3632_VLDO_MIN, + .uV_step = LM363X_STEP_50mV, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LM3632_REG_VOUT_NEG, + .vsel_mask = LM3632_VOUT_MASK, + .enable_reg = LM3632_REG_BIAS_CONFIG, + .enable_mask = LM3632_EN_VNEG_MASK, + }, +}; + +static int lm363x_regulator_of_get_enable_gpio(struct device_node *np, int id) +{ + /* + * Check LCM_EN1/2_GPIO is configured. + * Those pins are used for enabling VPOS/VNEG LDOs. + */ + switch (id) { + case LM3632_LDO_POS: + return of_get_named_gpio(np, "ti,lcm-en1-gpio", 0); + case LM3632_LDO_NEG: + return of_get_named_gpio(np, "ti,lcm-en2-gpio", 0); + default: + return -EINVAL; + } +} + +static int lm363x_regulator_probe(struct platform_device *pdev) +{ + struct ti_lmu *lmu = dev_get_drvdata(pdev->dev.parent); + struct regmap *regmap = lmu->regmap; + struct regulator_config cfg = { }; + struct regulator_dev *rdev; + struct device *dev = &pdev->dev; + int id = pdev->id; + int ret, ena_gpio; + + cfg.dev = dev; + cfg.regmap = regmap; + + /* + * LM3632 LDOs can be controlled by external pin. + * Register update is required if the pin is used. + */ + ena_gpio = lm363x_regulator_of_get_enable_gpio(dev->of_node, id); + if (gpio_is_valid(ena_gpio)) { + cfg.ena_gpio = ena_gpio; + cfg.ena_gpio_flags = GPIOF_OUT_INIT_LOW; + + ret = regmap_update_bits(regmap, LM3632_REG_BIAS_CONFIG, + LM3632_EXT_EN_MASK, + LM3632_EXT_EN_MASK); + if (ret) { + dev_err(dev, "External pin err: %d\n", ret); + return ret; + } + } + + rdev = devm_regulator_register(dev, &lm363x_regulator_desc[id], &cfg); + if (IS_ERR(rdev)) { + ret = PTR_ERR(rdev); + dev_err(dev, "[%d] regulator register err: %d\n", id, ret); + return ret; + } + + return 0; +} + +static struct platform_driver lm363x_regulator_driver = { + .probe = lm363x_regulator_probe, + .driver = { + .name = "lm363x-regulator", + }, +}; + +module_platform_driver(lm363x_regulator_driver); + +MODULE_DESCRIPTION("TI LM363X Regulator Driver"); +MODULE_AUTHOR("Milo Kim"); +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS("platform:lm363x-regulator"); diff --git a/drivers/regulator/lp872x.c b/drivers/regulator/lp872x.c index e5af07208f9d..19d758486553 100644 --- a/drivers/regulator/lp872x.c +++ b/drivers/regulator/lp872x.c @@ -108,7 +108,6 @@ struct lp872x { struct lp872x_platform_data *pdata; int num_regulators; enum lp872x_dvs_state dvs_pin; - int dvs_gpio; }; /* LP8720/LP8725 shared voltage table for LDOs */ @@ -520,6 +519,7 @@ static struct regulator_ops lp8725_buck_ops = { static struct regulator_desc lp8720_regulator_desc[] = { { .name = "ldo1", + .of_match = of_match_ptr("ldo1"), .id = LP8720_ID_LDO1, .ops = &lp872x_ldo_ops, .n_voltages = ARRAY_SIZE(lp872x_ldo_vtbl), @@ -533,6 +533,7 @@ static struct regulator_desc lp8720_regulator_desc[] = { }, { .name = "ldo2", + .of_match = of_match_ptr("ldo2"), .id = LP8720_ID_LDO2, .ops = &lp872x_ldo_ops, .n_voltages = ARRAY_SIZE(lp872x_ldo_vtbl), @@ -546,6 +547,7 @@ static struct regulator_desc lp8720_regulator_desc[] = { }, { .name = "ldo3", + .of_match = of_match_ptr("ldo3"), .id = LP8720_ID_LDO3, .ops = &lp872x_ldo_ops, .n_voltages = ARRAY_SIZE(lp872x_ldo_vtbl), @@ -559,6 +561,7 @@ static struct regulator_desc lp8720_regulator_desc[] = { }, { .name = "ldo4", + .of_match = of_match_ptr("ldo4"), .id = LP8720_ID_LDO4, .ops = &lp872x_ldo_ops, .n_voltages = ARRAY_SIZE(lp8720_ldo4_vtbl), @@ -572,6 +575,7 @@ static struct regulator_desc lp8720_regulator_desc[] = { }, { .name = "ldo5", + .of_match = of_match_ptr("ldo5"), .id = LP8720_ID_LDO5, .ops = &lp872x_ldo_ops, .n_voltages = ARRAY_SIZE(lp872x_ldo_vtbl), @@ -585,6 +589,7 @@ static struct regulator_desc lp8720_regulator_desc[] = { }, { .name = "buck", + .of_match = of_match_ptr("buck"), .id = LP8720_ID_BUCK, .ops = &lp8720_buck_ops, .n_voltages = ARRAY_SIZE(lp8720_buck_vtbl), @@ -599,6 +604,7 @@ static struct regulator_desc lp8720_regulator_desc[] = { static struct regulator_desc lp8725_regulator_desc[] = { { .name = "ldo1", + .of_match = of_match_ptr("ldo1"), .id = LP8725_ID_LDO1, .ops = &lp872x_ldo_ops, .n_voltages = ARRAY_SIZE(lp872x_ldo_vtbl), @@ -612,6 +618,7 @@ static struct regulator_desc lp8725_regulator_desc[] = { }, { .name = "ldo2", + .of_match = of_match_ptr("ldo2"), .id = LP8725_ID_LDO2, .ops = &lp872x_ldo_ops, .n_voltages = ARRAY_SIZE(lp872x_ldo_vtbl), @@ -625,6 +632,7 @@ static struct regulator_desc lp8725_regulator_desc[] = { }, { .name = "ldo3", + .of_match = of_match_ptr("ldo3"), .id = LP8725_ID_LDO3, .ops = &lp872x_ldo_ops, .n_voltages = ARRAY_SIZE(lp872x_ldo_vtbl), @@ -638,6 +646,7 @@ static struct regulator_desc lp8725_regulator_desc[] = { }, { .name = "ldo4", + .of_match = of_match_ptr("ldo4"), .id = LP8725_ID_LDO4, .ops = &lp872x_ldo_ops, .n_voltages = ARRAY_SIZE(lp872x_ldo_vtbl), @@ -651,6 +660,7 @@ static struct regulator_desc lp8725_regulator_desc[] = { }, { .name = "ldo5", + .of_match = of_match_ptr("ldo5"), .id = LP8725_ID_LDO5, .ops = &lp872x_ldo_ops, .n_voltages = ARRAY_SIZE(lp872x_ldo_vtbl), @@ -664,6 +674,7 @@ static struct regulator_desc lp8725_regulator_desc[] = { }, { .name = "lilo1", + .of_match = of_match_ptr("lilo1"), .id = LP8725_ID_LILO1, .ops = &lp872x_ldo_ops, .n_voltages = ARRAY_SIZE(lp8725_lilo_vtbl), @@ -677,6 +688,7 @@ static struct regulator_desc lp8725_regulator_desc[] = { }, { .name = "lilo2", + .of_match = of_match_ptr("lilo2"), .id = LP8725_ID_LILO2, .ops = &lp872x_ldo_ops, .n_voltages = ARRAY_SIZE(lp8725_lilo_vtbl), @@ -690,6 +702,7 @@ static struct regulator_desc lp8725_regulator_desc[] = { }, { .name = "buck1", + .of_match = of_match_ptr("buck1"), .id = LP8725_ID_BUCK1, .ops = &lp8725_buck_ops, .n_voltages = ARRAY_SIZE(lp8725_buck_vtbl), @@ -701,6 +714,7 @@ static struct regulator_desc lp8725_regulator_desc[] = { }, { .name = "buck2", + .of_match = of_match_ptr("buck2"), .id = LP8725_ID_BUCK2, .ops = &lp8725_buck_ops, .n_voltages = ARRAY_SIZE(lp8725_buck_vtbl), @@ -737,7 +751,6 @@ static int lp872x_init_dvs(struct lp872x *lp) } lp->dvs_pin = pinstate; - lp->dvs_gpio = gpio; return 0; diff --git a/drivers/regulator/lp8788-buck.c b/drivers/regulator/lp8788-buck.c index a97bed90d39b..ec46290b647e 100644 --- a/drivers/regulator/lp8788-buck.c +++ b/drivers/regulator/lp8788-buck.c @@ -344,7 +344,7 @@ static unsigned int lp8788_buck_get_mode(struct regulator_dev *rdev) REGULATOR_MODE_FAST : REGULATOR_MODE_NORMAL; } -static struct regulator_ops lp8788_buck12_ops = { +static const struct regulator_ops lp8788_buck12_ops = { .list_voltage = regulator_list_voltage_table, .map_voltage = regulator_map_voltage_ascend, .set_voltage_sel = lp8788_buck12_set_voltage_sel, @@ -357,7 +357,7 @@ static struct regulator_ops lp8788_buck12_ops = { .get_mode = lp8788_buck_get_mode, }; -static struct regulator_ops lp8788_buck34_ops = { +static const struct regulator_ops lp8788_buck34_ops = { .list_voltage = regulator_list_voltage_table, .map_voltage = regulator_map_voltage_ascend, .set_voltage_sel = regulator_set_voltage_sel_regmap, diff --git a/drivers/regulator/lp8788-ldo.c b/drivers/regulator/lp8788-ldo.c index 9f22d079c8cc..cbfd35873575 100644 --- a/drivers/regulator/lp8788-ldo.c +++ b/drivers/regulator/lp8788-ldo.c @@ -170,7 +170,7 @@ static int lp8788_ldo_enable_time(struct regulator_dev *rdev) return ENABLE_TIME_USEC * val; } -static struct regulator_ops lp8788_ldo_voltage_table_ops = { +static const struct regulator_ops lp8788_ldo_voltage_table_ops = { .list_voltage = regulator_list_voltage_table, .set_voltage_sel = regulator_set_voltage_sel_regmap, .get_voltage_sel = regulator_get_voltage_sel_regmap, @@ -180,7 +180,7 @@ static struct regulator_ops lp8788_ldo_voltage_table_ops = { .enable_time = lp8788_ldo_enable_time, }; -static struct regulator_ops lp8788_ldo_voltage_fixed_ops = { +static const struct regulator_ops lp8788_ldo_voltage_fixed_ops = { .list_voltage = regulator_list_voltage_linear, .enable = regulator_enable_regmap, .disable = regulator_disable_regmap, @@ -613,22 +613,20 @@ static struct platform_driver lp8788_aldo_driver = { }, }; +static struct platform_driver * const drivers[] = { + &lp8788_dldo_driver, + &lp8788_aldo_driver, +}; + static int __init lp8788_ldo_init(void) { - int ret; - - ret = platform_driver_register(&lp8788_dldo_driver); - if (ret) - return ret; - - return platform_driver_register(&lp8788_aldo_driver); + return platform_register_drivers(drivers, ARRAY_SIZE(drivers)); } subsys_initcall(lp8788_ldo_init); static void __exit lp8788_ldo_exit(void) { - platform_driver_unregister(&lp8788_aldo_driver); - platform_driver_unregister(&lp8788_dldo_driver); + platform_unregister_drivers(drivers, ARRAY_SIZE(drivers)); } module_exit(lp8788_ldo_exit); diff --git a/drivers/regulator/mt6311-regulator.c b/drivers/regulator/mt6311-regulator.c index 02c4e5feca8e..0495716fd35f 100644 --- a/drivers/regulator/mt6311-regulator.c +++ b/drivers/regulator/mt6311-regulator.c @@ -30,6 +30,7 @@ static const struct regmap_config mt6311_regmap_config = { .reg_bits = 8, .val_bits = 8, .max_register = MT6311_FQMTR_CON4, + .cache_type = REGCACHE_RBTREE, }; /* Default limits measured in millivolts and milliamps */ diff --git a/drivers/regulator/palmas-regulator.c b/drivers/regulator/palmas-regulator.c index 8217613807d3..6efc7ee8aea3 100644 --- a/drivers/regulator/palmas-regulator.c +++ b/drivers/regulator/palmas-regulator.c @@ -612,6 +612,18 @@ static struct regulator_ops palmas_ops_ldo = { .map_voltage = regulator_map_voltage_linear, }; +static struct regulator_ops palmas_ops_ldo9 = { + .is_enabled = palmas_is_enabled_ldo, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .list_voltage = regulator_list_voltage_linear, + .map_voltage = regulator_map_voltage_linear, + .set_bypass = regulator_set_bypass_regmap, + .get_bypass = regulator_get_bypass_regmap, +}; + static struct regulator_ops palmas_ops_ext_control_ldo = { .get_voltage_sel = regulator_get_voltage_sel_regmap, .set_voltage_sel = regulator_set_voltage_sel_regmap, @@ -639,6 +651,19 @@ static struct regulator_ops tps65917_ops_ldo = { .set_voltage_time_sel = regulator_set_voltage_time_sel, }; +static struct regulator_ops tps65917_ops_ldo_1_2 = { + .is_enabled = palmas_is_enabled_ldo, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .list_voltage = regulator_list_voltage_linear, + .map_voltage = regulator_map_voltage_linear, + .set_voltage_time_sel = regulator_set_voltage_time_sel, + .set_bypass = regulator_set_bypass_regmap, + .get_bypass = regulator_get_bypass_regmap, +}; + static int palmas_regulator_config_external(struct palmas *palmas, int id, struct palmas_reg_init *reg_init) { @@ -915,6 +940,13 @@ static int palmas_ldo_registration(struct palmas_pmic *pmic, if (pdata && pdata->ldo6_vibrator && (id == PALMAS_REG_LDO6)) desc->enable_time = 2000; + + if (id == PALMAS_REG_LDO9) { + desc->ops = &palmas_ops_ldo9; + desc->bypass_reg = desc->enable_reg; + desc->bypass_mask = + PALMAS_LDO9_CTRL_LDO_BYPASS_EN; + } } else { if (!ddata->has_regen3 && id == PALMAS_REG_REGEN3) continue; @@ -1019,6 +1051,13 @@ static int tps65917_ldo_registration(struct palmas_pmic *pmic, * It is of the order of ~60mV/uS. */ desc->ramp_delay = 2500; + if (id == TPS65917_REG_LDO1 || + id == TPS65917_REG_LDO2) { + desc->ops = &tps65917_ops_ldo_1_2; + desc->bypass_reg = desc->enable_reg; + desc->bypass_mask = + TPS65917_LDO1_CTRL_BYPASS_EN; + } } else { desc->n_voltages = 1; if (reg_init && reg_init->roof_floor) diff --git a/drivers/regulator/pv88060-regulator.c b/drivers/regulator/pv88060-regulator.c new file mode 100644 index 000000000000..094376c8de4b --- /dev/null +++ b/drivers/regulator/pv88060-regulator.c @@ -0,0 +1,437 @@ +/* + * pv88060-regulator.c - Regulator device driver for PV88060 + * Copyright (C) 2015 Powerventure Semiconductor Ltd. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/err.h> +#include <linux/gpio.h> +#include <linux/i2c.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/slab.h> +#include <linux/regulator/driver.h> +#include <linux/regulator/machine.h> +#include <linux/regmap.h> +#include <linux/irq.h> +#include <linux/interrupt.h> +#include <linux/regulator/of_regulator.h> +#include <linux/proc_fs.h> +#include <linux/uaccess.h> +#include "pv88060-regulator.h" + +#define PV88060_MAX_REGULATORS 14 + +/* PV88060 REGULATOR IDs */ +enum { + /* BUCKs */ + PV88060_ID_BUCK1, + + /* LDOs */ + PV88060_ID_LDO1, + PV88060_ID_LDO2, + PV88060_ID_LDO3, + PV88060_ID_LDO4, + PV88060_ID_LDO5, + PV88060_ID_LDO6, + PV88060_ID_LDO7, + + /* SWTs */ + PV88060_ID_SW1, + PV88060_ID_SW2, + PV88060_ID_SW3, + PV88060_ID_SW4, + PV88060_ID_SW5, + PV88060_ID_SW6, +}; + +struct pv88060_regulator { + struct regulator_desc desc; + /* Current limiting */ + unsigned n_current_limits; + const int *current_limits; + unsigned int limit_mask; + unsigned int conf; /* buck configuration register */ +}; + +struct pv88060 { + struct device *dev; + struct regmap *regmap; + struct regulator_dev *rdev[PV88060_MAX_REGULATORS]; +}; + +static const struct regmap_config pv88060_regmap_config = { + .reg_bits = 8, + .val_bits = 8, +}; + +/* Current limits array (in uA) for BUCK1 + * Entry indexes corresponds to register values. + */ + +static const int pv88060_buck1_limits[] = { + 1496000, 2393000, 3291000, 4189000 +}; + +static unsigned int pv88060_buck_get_mode(struct regulator_dev *rdev) +{ + struct pv88060_regulator *info = rdev_get_drvdata(rdev); + unsigned int data; + int ret, mode = 0; + + ret = regmap_read(rdev->regmap, info->conf, &data); + if (ret < 0) + return ret; + + switch (data & PV88060_BUCK_MODE_MASK) { + case PV88060_BUCK_MODE_SYNC: + mode = REGULATOR_MODE_FAST; + break; + case PV88060_BUCK_MODE_AUTO: + mode = REGULATOR_MODE_NORMAL; + break; + case PV88060_BUCK_MODE_SLEEP: + mode = REGULATOR_MODE_STANDBY; + break; + } + + return mode; +} + +static int pv88060_buck_set_mode(struct regulator_dev *rdev, + unsigned int mode) +{ + struct pv88060_regulator *info = rdev_get_drvdata(rdev); + int val = 0; + + switch (mode) { + case REGULATOR_MODE_FAST: + val = PV88060_BUCK_MODE_SYNC; + break; + case REGULATOR_MODE_NORMAL: + val = PV88060_BUCK_MODE_AUTO; + break; + case REGULATOR_MODE_STANDBY: + val = PV88060_BUCK_MODE_SLEEP; + break; + default: + return -EINVAL; + } + + return regmap_update_bits(rdev->regmap, info->conf, + PV88060_BUCK_MODE_MASK, val); +} + +static int pv88060_set_current_limit(struct regulator_dev *rdev, int min, + int max) +{ + struct pv88060_regulator *info = rdev_get_drvdata(rdev); + int i; + + /* search for closest to maximum */ + for (i = info->n_current_limits; i >= 0; i--) { + if (min <= info->current_limits[i] + && max >= info->current_limits[i]) { + return regmap_update_bits(rdev->regmap, + info->conf, + info->limit_mask, + i << PV88060_BUCK_ILIM_SHIFT); + } + } + + return -EINVAL; +} + +static int pv88060_get_current_limit(struct regulator_dev *rdev) +{ + struct pv88060_regulator *info = rdev_get_drvdata(rdev); + unsigned int data; + int ret; + + ret = regmap_read(rdev->regmap, info->conf, &data); + if (ret < 0) + return ret; + + data = (data & info->limit_mask) >> PV88060_BUCK_ILIM_SHIFT; + return info->current_limits[data]; +} + +static struct regulator_ops pv88060_buck_ops = { + .get_mode = pv88060_buck_get_mode, + .set_mode = pv88060_buck_set_mode, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .is_enabled = regulator_is_enabled_regmap, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .list_voltage = regulator_list_voltage_linear, + .set_current_limit = pv88060_set_current_limit, + .get_current_limit = pv88060_get_current_limit, +}; + +static struct regulator_ops pv88060_ldo_ops = { + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .is_enabled = regulator_is_enabled_regmap, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .list_voltage = regulator_list_voltage_linear, +}; + +#define PV88060_BUCK(chip, regl_name, min, step, max, limits_array) \ +{\ + .desc = {\ + .id = chip##_ID_##regl_name,\ + .name = __stringify(chip##_##regl_name),\ + .of_match = of_match_ptr(#regl_name),\ + .regulators_node = of_match_ptr("regulators"),\ + .type = REGULATOR_VOLTAGE,\ + .owner = THIS_MODULE,\ + .ops = &pv88060_buck_ops,\ + .min_uV = min,\ + .uV_step = step,\ + .n_voltages = ((max) - (min))/(step) + 1,\ + .enable_reg = PV88060_REG_##regl_name##_CONF0,\ + .enable_mask = PV88060_BUCK_EN, \ + .vsel_reg = PV88060_REG_##regl_name##_CONF0,\ + .vsel_mask = PV88060_VBUCK_MASK,\ + },\ + .current_limits = limits_array,\ + .n_current_limits = ARRAY_SIZE(limits_array),\ + .limit_mask = PV88060_BUCK_ILIM_MASK, \ + .conf = PV88060_REG_##regl_name##_CONF1,\ +} + +#define PV88060_LDO(chip, regl_name, min, step, max) \ +{\ + .desc = {\ + .id = chip##_ID_##regl_name,\ + .name = __stringify(chip##_##regl_name),\ + .of_match = of_match_ptr(#regl_name),\ + .regulators_node = of_match_ptr("regulators"),\ + .type = REGULATOR_VOLTAGE,\ + .owner = THIS_MODULE,\ + .ops = &pv88060_ldo_ops,\ + .min_uV = min, \ + .uV_step = step, \ + .n_voltages = (step) ? ((max - min) / step + 1) : 1, \ + .enable_reg = PV88060_REG_##regl_name##_CONF, \ + .enable_mask = PV88060_LDO_EN, \ + .vsel_reg = PV88060_REG_##regl_name##_CONF, \ + .vsel_mask = PV88060_VLDO_MASK, \ + },\ +} + +#define PV88060_SW(chip, regl_name, max) \ +{\ + .desc = {\ + .id = chip##_ID_##regl_name,\ + .name = __stringify(chip##_##regl_name),\ + .of_match = of_match_ptr(#regl_name),\ + .regulators_node = of_match_ptr("regulators"),\ + .type = REGULATOR_VOLTAGE,\ + .owner = THIS_MODULE,\ + .ops = &pv88060_ldo_ops,\ + .min_uV = max,\ + .uV_step = 0,\ + .n_voltages = 1,\ + .enable_reg = PV88060_REG_##regl_name##_CONF,\ + .enable_mask = PV88060_SW_EN,\ + },\ +} + +static const struct pv88060_regulator pv88060_regulator_info[] = { + PV88060_BUCK(PV88060, BUCK1, 2800000, 12500, 4387500, + pv88060_buck1_limits), + PV88060_LDO(PV88060, LDO1, 1200000, 50000, 3350000), + PV88060_LDO(PV88060, LDO2, 1200000, 50000, 3350000), + PV88060_LDO(PV88060, LDO3, 1200000, 50000, 3350000), + PV88060_LDO(PV88060, LDO4, 1200000, 50000, 3350000), + PV88060_LDO(PV88060, LDO5, 1200000, 50000, 3350000), + PV88060_LDO(PV88060, LDO6, 1200000, 50000, 3350000), + PV88060_LDO(PV88060, LDO7, 1200000, 50000, 3350000), + PV88060_SW(PV88060, SW1, 5000000), + PV88060_SW(PV88060, SW2, 5000000), + PV88060_SW(PV88060, SW3, 5000000), + PV88060_SW(PV88060, SW4, 5000000), + PV88060_SW(PV88060, SW5, 5000000), + PV88060_SW(PV88060, SW6, 5000000), +}; + +static irqreturn_t pv88060_irq_handler(int irq, void *data) +{ + struct pv88060 *chip = data; + int i, reg_val, err, ret = IRQ_NONE; + + err = regmap_read(chip->regmap, PV88060_REG_EVENT_A, ®_val); + if (err < 0) + goto error_i2c; + + if (reg_val & PV88060_E_VDD_FLT) { + for (i = 0; i < PV88060_MAX_REGULATORS; i++) { + if (chip->rdev[i] != NULL) { + regulator_notifier_call_chain(chip->rdev[i], + REGULATOR_EVENT_UNDER_VOLTAGE, + NULL); + } + } + + err = regmap_update_bits(chip->regmap, PV88060_REG_EVENT_A, + PV88060_E_VDD_FLT, PV88060_E_VDD_FLT); + if (err < 0) + goto error_i2c; + + ret = IRQ_HANDLED; + } + + if (reg_val & PV88060_E_OVER_TEMP) { + for (i = 0; i < PV88060_MAX_REGULATORS; i++) { + if (chip->rdev[i] != NULL) { + regulator_notifier_call_chain(chip->rdev[i], + REGULATOR_EVENT_OVER_TEMP, + NULL); + } + } + + err = regmap_update_bits(chip->regmap, PV88060_REG_EVENT_A, + PV88060_E_OVER_TEMP, PV88060_E_OVER_TEMP); + if (err < 0) + goto error_i2c; + + ret = IRQ_HANDLED; + } + + return ret; + +error_i2c: + dev_err(chip->dev, "I2C error : %d\n", err); + return IRQ_NONE; +} + +/* + * I2C driver interface functions + */ +static int pv88060_i2c_probe(struct i2c_client *i2c, + const struct i2c_device_id *id) +{ + struct regulator_init_data *init_data = dev_get_platdata(&i2c->dev); + struct pv88060 *chip; + struct regulator_config config = { }; + int error, i, ret = 0; + + chip = devm_kzalloc(&i2c->dev, sizeof(struct pv88060), GFP_KERNEL); + if (!chip) + return -ENOMEM; + + chip->dev = &i2c->dev; + chip->regmap = devm_regmap_init_i2c(i2c, &pv88060_regmap_config); + if (IS_ERR(chip->regmap)) { + error = PTR_ERR(chip->regmap); + dev_err(chip->dev, "Failed to allocate register map: %d\n", + error); + return error; + } + + i2c_set_clientdata(i2c, chip); + + if (i2c->irq != 0) { + ret = regmap_write(chip->regmap, PV88060_REG_MASK_A, 0xFF); + if (ret < 0) { + dev_err(chip->dev, + "Failed to mask A reg: %d\n", ret); + return ret; + } + + ret = regmap_write(chip->regmap, PV88060_REG_MASK_B, 0xFF); + if (ret < 0) { + dev_err(chip->dev, + "Failed to mask B reg: %d\n", ret); + return ret; + } + + ret = regmap_write(chip->regmap, PV88060_REG_MASK_C, 0xFF); + if (ret < 0) { + dev_err(chip->dev, + "Failed to mask C reg: %d\n", ret); + return ret; + } + + ret = devm_request_threaded_irq(&i2c->dev, i2c->irq, NULL, + pv88060_irq_handler, + IRQF_TRIGGER_LOW|IRQF_ONESHOT, + "pv88060", chip); + if (ret != 0) { + dev_err(chip->dev, "Failed to request IRQ: %d\n", + i2c->irq); + return ret; + } + + ret = regmap_update_bits(chip->regmap, PV88060_REG_MASK_A, + PV88060_M_VDD_FLT | PV88060_M_OVER_TEMP, 0); + if (ret < 0) { + dev_err(chip->dev, + "Failed to update mask reg: %d\n", ret); + return ret; + } + + } else { + dev_warn(chip->dev, "No IRQ configured\n"); + } + + config.dev = chip->dev; + config.regmap = chip->regmap; + + for (i = 0; i < PV88060_MAX_REGULATORS; i++) { + if (init_data) + config.init_data = &init_data[i]; + + config.driver_data = (void *)&pv88060_regulator_info[i]; + chip->rdev[i] = devm_regulator_register(chip->dev, + &pv88060_regulator_info[i].desc, &config); + if (IS_ERR(chip->rdev[i])) { + dev_err(chip->dev, + "Failed to register PV88060 regulator\n"); + return PTR_ERR(chip->rdev[i]); + } + } + + return 0; +} + +static const struct i2c_device_id pv88060_i2c_id[] = { + {"pv88060", 0}, + {}, +}; +MODULE_DEVICE_TABLE(i2c, pv88060_i2c_id); + +#ifdef CONFIG_OF +static const struct of_device_id pv88060_dt_ids[] = { + { .compatible = "pvs,pv88060", .data = &pv88060_i2c_id[0] }, + {}, +}; +MODULE_DEVICE_TABLE(of, pv88060_dt_ids); +#endif + +static struct i2c_driver pv88060_regulator_driver = { + .driver = { + .name = "pv88060", + .of_match_table = of_match_ptr(pv88060_dt_ids), + }, + .probe = pv88060_i2c_probe, + .id_table = pv88060_i2c_id, +}; + +module_i2c_driver(pv88060_regulator_driver); + +MODULE_AUTHOR("James Ban <James.Ban.opensource@diasemi.com>"); +MODULE_DESCRIPTION("Regulator device driver for Powerventure PV88060"); +MODULE_LICENSE("GPL"); diff --git a/drivers/regulator/pv88060-regulator.h b/drivers/regulator/pv88060-regulator.h new file mode 100644 index 000000000000..02ca9203a172 --- /dev/null +++ b/drivers/regulator/pv88060-regulator.h @@ -0,0 +1,69 @@ +/* + * pv88060-regulator.h - Regulator definitions for PV88060 + * Copyright (C) 2015 Powerventure Semiconductor Ltd. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __PV88060_REGISTERS_H__ +#define __PV88060_REGISTERS_H__ + +/* System Control and Event Registers */ +#define PV88060_REG_EVENT_A 0x04 +#define PV88060_REG_MASK_A 0x08 +#define PV88060_REG_MASK_B 0x09 +#define PV88060_REG_MASK_C 0x0A + +/* Regulator Registers */ +#define PV88060_REG_BUCK1_CONF0 0x1B +#define PV88060_REG_BUCK1_CONF1 0x1C +#define PV88060_REG_LDO1_CONF 0x1D +#define PV88060_REG_LDO2_CONF 0x1E +#define PV88060_REG_LDO3_CONF 0x1F +#define PV88060_REG_LDO4_CONF 0x20 +#define PV88060_REG_LDO5_CONF 0x21 +#define PV88060_REG_LDO6_CONF 0x22 +#define PV88060_REG_LDO7_CONF 0x23 + +#define PV88060_REG_SW1_CONF 0x3B +#define PV88060_REG_SW2_CONF 0x3C +#define PV88060_REG_SW3_CONF 0x3D +#define PV88060_REG_SW4_CONF 0x3E +#define PV88060_REG_SW5_CONF 0x3F +#define PV88060_REG_SW6_CONF 0x40 + +/* PV88060_REG_EVENT_A (addr=0x04) */ +#define PV88060_E_VDD_FLT 0x01 +#define PV88060_E_OVER_TEMP 0x02 + +/* PV88060_REG_MASK_A (addr=0x08) */ +#define PV88060_M_VDD_FLT 0x01 +#define PV88060_M_OVER_TEMP 0x02 + +/* PV88060_REG_BUCK1_CONF0 (addr=0x1B) */ +#define PV88060_BUCK_EN 0x80 +#define PV88060_VBUCK_MASK 0x7F +/* PV88060_REG_LDO1/2/3/4/5/6/7_CONT */ +#define PV88060_LDO_EN 0x40 +#define PV88060_VLDO_MASK 0x3F +/* PV88060_REG_SW1/2/3/4/5_CONF */ +#define PV88060_SW_EN 0x80 + +/* PV88060_REG_BUCK1_CONF1 (addr=0x1C) */ +#define PV88060_BUCK_ILIM_SHIFT 2 +#define PV88060_BUCK_ILIM_MASK 0x0C +#define PV88060_BUCK_MODE_SHIFT 0 +#define PV88060_BUCK_MODE_MASK 0x03 +#define PV88060_BUCK_MODE_SLEEP 0x00 +#define PV88060_BUCK_MODE_AUTO 0x01 +#define PV88060_BUCK_MODE_SYNC 0x02 + +#endif /* __PV88060_REGISTERS_H__ */ diff --git a/drivers/regulator/pv88090-regulator.c b/drivers/regulator/pv88090-regulator.c new file mode 100644 index 000000000000..ac15f31b5fe0 --- /dev/null +++ b/drivers/regulator/pv88090-regulator.c @@ -0,0 +1,458 @@ +/* + * pv88090-regulator.c - Regulator device driver for PV88090 + * Copyright (C) 2015 Powerventure Semiconductor Ltd. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/err.h> +#include <linux/gpio.h> +#include <linux/i2c.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/slab.h> +#include <linux/regulator/driver.h> +#include <linux/regulator/machine.h> +#include <linux/regmap.h> +#include <linux/irq.h> +#include <linux/interrupt.h> +#include <linux/regulator/of_regulator.h> +#include <linux/proc_fs.h> +#include <linux/uaccess.h> +#include "pv88090-regulator.h" + +#define PV88090_MAX_REGULATORS 5 + +/* PV88090 REGULATOR IDs */ +enum { + /* BUCKs */ + PV88090_ID_BUCK1, + PV88090_ID_BUCK2, + PV88090_ID_BUCK3, + + /* LDOs */ + PV88090_ID_LDO1, + PV88090_ID_LDO2, +}; + +struct pv88090_regulator { + struct regulator_desc desc; + /* Current limiting */ + unsigned n_current_limits; + const int *current_limits; + unsigned int limit_mask; + unsigned int conf; + unsigned int conf2; +}; + +struct pv88090 { + struct device *dev; + struct regmap *regmap; + struct regulator_dev *rdev[PV88090_MAX_REGULATORS]; +}; + +struct pv88090_buck_voltage { + int min_uV; + int max_uV; + int uV_step; +}; + +static const struct regmap_config pv88090_regmap_config = { + .reg_bits = 8, + .val_bits = 8, +}; + +/* Current limits array (in uA) for BUCK1, BUCK2, BUCK3. + * Entry indexes corresponds to register values. + */ + +static const int pv88090_buck1_limits[] = { + 220000, 440000, 660000, 880000, 1100000, 1320000, 1540000, 1760000, + 1980000, 2200000, 2420000, 2640000, 2860000, 3080000, 3300000, 3520000, + 3740000, 3960000, 4180000, 4400000, 4620000, 4840000, 5060000, 5280000, + 5500000, 5720000, 5940000, 6160000, 6380000, 6600000, 6820000, 7040000 +}; + +static const int pv88090_buck23_limits[] = { + 1496000, 2393000, 3291000, 4189000 +}; + +static const struct pv88090_buck_voltage pv88090_buck_vol[3] = { + { + .min_uV = 600000, + .max_uV = 1393750, + .uV_step = 6250, + }, + + { + .min_uV = 1400000, + .max_uV = 2193750, + .uV_step = 6250, + }, + { + .min_uV = 1250000, + .max_uV = 2837500, + .uV_step = 12500, + }, +}; + +static unsigned int pv88090_buck_get_mode(struct regulator_dev *rdev) +{ + struct pv88090_regulator *info = rdev_get_drvdata(rdev); + unsigned int data; + int ret, mode = 0; + + ret = regmap_read(rdev->regmap, info->conf, &data); + if (ret < 0) + return ret; + + switch (data & PV88090_BUCK1_MODE_MASK) { + case PV88090_BUCK_MODE_SYNC: + mode = REGULATOR_MODE_FAST; + break; + case PV88090_BUCK_MODE_AUTO: + mode = REGULATOR_MODE_NORMAL; + break; + case PV88090_BUCK_MODE_SLEEP: + mode = REGULATOR_MODE_STANDBY; + break; + } + + return mode; +} + +static int pv88090_buck_set_mode(struct regulator_dev *rdev, + unsigned int mode) +{ + struct pv88090_regulator *info = rdev_get_drvdata(rdev); + int val = 0; + + switch (mode) { + case REGULATOR_MODE_FAST: + val = PV88090_BUCK_MODE_SYNC; + break; + case REGULATOR_MODE_NORMAL: + val = PV88090_BUCK_MODE_AUTO; + break; + case REGULATOR_MODE_STANDBY: + val = PV88090_BUCK_MODE_SLEEP; + break; + default: + return -EINVAL; + } + + return regmap_update_bits(rdev->regmap, info->conf, + PV88090_BUCK1_MODE_MASK, val); +} + +static int pv88090_set_current_limit(struct regulator_dev *rdev, int min, + int max) +{ + struct pv88090_regulator *info = rdev_get_drvdata(rdev); + int i; + + /* search for closest to maximum */ + for (i = info->n_current_limits; i >= 0; i--) { + if (min <= info->current_limits[i] + && max >= info->current_limits[i]) { + return regmap_update_bits(rdev->regmap, + info->conf, + info->limit_mask, + i << PV88090_BUCK1_ILIM_SHIFT); + } + } + + return -EINVAL; +} + +static int pv88090_get_current_limit(struct regulator_dev *rdev) +{ + struct pv88090_regulator *info = rdev_get_drvdata(rdev); + unsigned int data; + int ret; + + ret = regmap_read(rdev->regmap, info->conf, &data); + if (ret < 0) + return ret; + + data = (data & info->limit_mask) >> PV88090_BUCK1_ILIM_SHIFT; + return info->current_limits[data]; +} + +static struct regulator_ops pv88090_buck_ops = { + .get_mode = pv88090_buck_get_mode, + .set_mode = pv88090_buck_set_mode, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .is_enabled = regulator_is_enabled_regmap, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .list_voltage = regulator_list_voltage_linear, + .set_current_limit = pv88090_set_current_limit, + .get_current_limit = pv88090_get_current_limit, +}; + +static struct regulator_ops pv88090_ldo_ops = { + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .is_enabled = regulator_is_enabled_regmap, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .list_voltage = regulator_list_voltage_linear, +}; + +#define PV88090_BUCK(chip, regl_name, min, step, max, limits_array) \ +{\ + .desc = {\ + .id = chip##_ID_##regl_name,\ + .name = __stringify(chip##_##regl_name),\ + .of_match = of_match_ptr(#regl_name),\ + .regulators_node = of_match_ptr("regulators"),\ + .type = REGULATOR_VOLTAGE,\ + .owner = THIS_MODULE,\ + .ops = &pv88090_buck_ops,\ + .min_uV = min, \ + .uV_step = step, \ + .n_voltages = ((max) - (min))/(step) + 1, \ + .enable_reg = PV88090_REG_##regl_name##_CONF0, \ + .enable_mask = PV88090_##regl_name##_EN, \ + .vsel_reg = PV88090_REG_##regl_name##_CONF0, \ + .vsel_mask = PV88090_V##regl_name##_MASK, \ + },\ + .current_limits = limits_array, \ + .n_current_limits = ARRAY_SIZE(limits_array), \ + .limit_mask = PV88090_##regl_name##_ILIM_MASK, \ + .conf = PV88090_REG_##regl_name##_CONF1, \ + .conf2 = PV88090_REG_##regl_name##_CONF2, \ +} + +#define PV88090_LDO(chip, regl_name, min, step, max) \ +{\ + .desc = {\ + .id = chip##_ID_##regl_name,\ + .name = __stringify(chip##_##regl_name),\ + .of_match = of_match_ptr(#regl_name),\ + .regulators_node = of_match_ptr("regulators"),\ + .type = REGULATOR_VOLTAGE,\ + .owner = THIS_MODULE,\ + .ops = &pv88090_ldo_ops,\ + .min_uV = min, \ + .uV_step = step, \ + .n_voltages = ((max) - (min))/(step) + 1, \ + .enable_reg = PV88090_REG_##regl_name##_CONT, \ + .enable_mask = PV88090_##regl_name##_EN, \ + .vsel_reg = PV88090_REG_##regl_name##_CONT, \ + .vsel_mask = PV88090_V##regl_name##_MASK, \ + },\ +} + +static struct pv88090_regulator pv88090_regulator_info[] = { + PV88090_BUCK(PV88090, BUCK1, 600000, 6250, 1393750, + pv88090_buck1_limits), + PV88090_BUCK(PV88090, BUCK2, 600000, 6250, 1393750, + pv88090_buck23_limits), + PV88090_BUCK(PV88090, BUCK3, 600000, 6250, 1393750, + pv88090_buck23_limits), + PV88090_LDO(PV88090, LDO1, 1200000, 50000, 4350000), + PV88090_LDO(PV88090, LDO2, 650000, 25000, 2225000), +}; + +static irqreturn_t pv88090_irq_handler(int irq, void *data) +{ + struct pv88090 *chip = data; + int i, reg_val, err, ret = IRQ_NONE; + + err = regmap_read(chip->regmap, PV88090_REG_EVENT_A, ®_val); + if (err < 0) + goto error_i2c; + + if (reg_val & PV88090_E_VDD_FLT) { + for (i = 0; i < PV88090_MAX_REGULATORS; i++) { + if (chip->rdev[i] != NULL) { + regulator_notifier_call_chain(chip->rdev[i], + REGULATOR_EVENT_UNDER_VOLTAGE, + NULL); + } + } + + err = regmap_update_bits(chip->regmap, PV88090_REG_EVENT_A, + PV88090_E_VDD_FLT, PV88090_E_VDD_FLT); + if (err < 0) + goto error_i2c; + + ret = IRQ_HANDLED; + } + + if (reg_val & PV88090_E_OVER_TEMP) { + for (i = 0; i < PV88090_MAX_REGULATORS; i++) { + if (chip->rdev[i] != NULL) { + regulator_notifier_call_chain(chip->rdev[i], + REGULATOR_EVENT_OVER_TEMP, + NULL); + } + } + + err = regmap_update_bits(chip->regmap, PV88090_REG_EVENT_A, + PV88090_E_OVER_TEMP, PV88090_E_OVER_TEMP); + if (err < 0) + goto error_i2c; + + ret = IRQ_HANDLED; + } + + return ret; + +error_i2c: + dev_err(chip->dev, "I2C error : %d\n", err); + return IRQ_NONE; +} + +/* + * I2C driver interface functions + */ +static int pv88090_i2c_probe(struct i2c_client *i2c, + const struct i2c_device_id *id) +{ + struct regulator_init_data *init_data = dev_get_platdata(&i2c->dev); + struct pv88090 *chip; + struct regulator_config config = { }; + int error, i, ret = 0; + unsigned int conf2, range, index; + + chip = devm_kzalloc(&i2c->dev, sizeof(struct pv88090), GFP_KERNEL); + if (!chip) + return -ENOMEM; + + chip->dev = &i2c->dev; + chip->regmap = devm_regmap_init_i2c(i2c, &pv88090_regmap_config); + if (IS_ERR(chip->regmap)) { + error = PTR_ERR(chip->regmap); + dev_err(chip->dev, "Failed to allocate register map: %d\n", + error); + return error; + } + + i2c_set_clientdata(i2c, chip); + + if (i2c->irq != 0) { + ret = regmap_write(chip->regmap, PV88090_REG_MASK_A, 0xFF); + if (ret < 0) { + dev_err(chip->dev, + "Failed to mask A reg: %d\n", ret); + return ret; + } + + ret = regmap_write(chip->regmap, PV88090_REG_MASK_B, 0xFF); + if (ret < 0) { + dev_err(chip->dev, + "Failed to mask B reg: %d\n", ret); + return ret; + } + + ret = devm_request_threaded_irq(&i2c->dev, i2c->irq, NULL, + pv88090_irq_handler, + IRQF_TRIGGER_LOW|IRQF_ONESHOT, + "pv88090", chip); + if (ret != 0) { + dev_err(chip->dev, "Failed to request IRQ: %d\n", + i2c->irq); + return ret; + } + + ret = regmap_update_bits(chip->regmap, PV88090_REG_MASK_A, + PV88090_M_VDD_FLT | PV88090_M_OVER_TEMP, 0); + if (ret < 0) { + dev_err(chip->dev, + "Failed to update mask reg: %d\n", ret); + return ret; + } + + } else { + dev_warn(chip->dev, "No IRQ configured\n"); + } + + config.dev = chip->dev; + config.regmap = chip->regmap; + + for (i = 0; i < PV88090_MAX_REGULATORS; i++) { + if (init_data) + config.init_data = &init_data[i]; + + if (i == PV88090_ID_BUCK2 || i == PV88090_ID_BUCK3) { + ret = regmap_read(chip->regmap, + pv88090_regulator_info[i].conf2, &conf2); + if (ret < 0) + return ret; + + conf2 = (conf2 >> PV88090_BUCK_VDAC_RANGE_SHIFT) & + PV88090_BUCK_VDAC_RANGE_MASK; + + ret = regmap_read(chip->regmap, + PV88090_REG_BUCK_FOLD_RANGE, &range); + if (ret < 0) + return ret; + + range = (range >> + (PV88080_BUCK_VRANGE_GAIN_SHIFT + i - 1)) & + PV88080_BUCK_VRANGE_GAIN_MASK; + index = ((range << 1) | conf2); + + pv88090_regulator_info[i].desc.min_uV + = pv88090_buck_vol[index].min_uV; + pv88090_regulator_info[i].desc.uV_step + = pv88090_buck_vol[index].uV_step; + pv88090_regulator_info[i].desc.n_voltages + = ((pv88090_buck_vol[index].max_uV) + - (pv88090_buck_vol[index].min_uV)) + /(pv88090_buck_vol[index].uV_step) + 1; + } + + config.driver_data = (void *)&pv88090_regulator_info[i]; + chip->rdev[i] = devm_regulator_register(chip->dev, + &pv88090_regulator_info[i].desc, &config); + if (IS_ERR(chip->rdev[i])) { + dev_err(chip->dev, + "Failed to register PV88090 regulator\n"); + return PTR_ERR(chip->rdev[i]); + } + } + + return 0; +} + +static const struct i2c_device_id pv88090_i2c_id[] = { + {"pv88090", 0}, + {}, +}; +MODULE_DEVICE_TABLE(i2c, pv88090_i2c_id); + +#ifdef CONFIG_OF +static const struct of_device_id pv88090_dt_ids[] = { + { .compatible = "pvs,pv88090", .data = &pv88090_i2c_id[0] }, + {}, +}; +MODULE_DEVICE_TABLE(of, pv88090_dt_ids); +#endif + +static struct i2c_driver pv88090_regulator_driver = { + .driver = { + .name = "pv88090", + .of_match_table = of_match_ptr(pv88090_dt_ids), + }, + .probe = pv88090_i2c_probe, + .id_table = pv88090_i2c_id, +}; + +module_i2c_driver(pv88090_regulator_driver); + +MODULE_AUTHOR("James Ban <James.Ban.opensource@diasemi.com>"); +MODULE_DESCRIPTION("Regulator device driver for Powerventure PV88090"); +MODULE_LICENSE("GPL"); diff --git a/drivers/regulator/pv88090-regulator.h b/drivers/regulator/pv88090-regulator.h new file mode 100644 index 000000000000..d7aca8d8266d --- /dev/null +++ b/drivers/regulator/pv88090-regulator.h @@ -0,0 +1,98 @@ +/* + * pv88090-regulator.h - Regulator definitions for PV88090 + * Copyright (C) 2015 Powerventure Semiconductor Ltd. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __PV88090_REGISTERS_H__ +#define __PV88090_REGISTERS_H__ + +/* System Control and Event Registers */ +#define PV88090_REG_EVENT_A 0x03 +#define PV88090_REG_MASK_A 0x06 +#define PV88090_REG_MASK_B 0x07 + +/* Regulator Registers */ +#define PV88090_REG_BUCK1_CONF0 0x18 +#define PV88090_REG_BUCK1_CONF1 0x19 +#define PV88090_REG_BUCK1_CONF2 0x1a +#define PV88090_REG_BUCK2_CONF0 0x1b +#define PV88090_REG_BUCK2_CONF1 0x1c +#define PV88090_REG_BUCK2_CONF2 0x58 +#define PV88090_REG_BUCK3_CONF0 0x1d +#define PV88090_REG_BUCK3_CONF1 0x1e +#define PV88090_REG_BUCK3_CONF2 0x5c + +#define PV88090_REG_LDO1_CONT 0x1f +#define PV88090_REG_LDO2_CONT 0x20 +#define PV88090_REG_LDO3_CONT 0x21 +#define PV88090_REG_BUCK_FOLD_RANGE 0x61 + +/* PV88090_REG_EVENT_A (addr=0x03) */ +#define PV88090_E_VDD_FLT 0x01 +#define PV88090_E_OVER_TEMP 0x02 + +/* PV88090_REG_MASK_A (addr=0x06) */ +#define PV88090_M_VDD_FLT 0x01 +#define PV88090_M_OVER_TEMP 0x02 + +/* PV88090_REG_BUCK1_CONF0 (addr=0x18) */ +#define PV88090_BUCK1_EN 0x80 +#define PV88090_VBUCK1_MASK 0x7F +/* PV88090_REG_BUCK2_CONF0 (addr=0x1b) */ +#define PV88090_BUCK2_EN 0x80 +#define PV88090_VBUCK2_MASK 0x7F +/* PV88090_REG_BUCK3_CONF0 (addr=0x1d) */ +#define PV88090_BUCK3_EN 0x80 +#define PV88090_VBUCK3_MASK 0x7F +/* PV88090_REG_LDO1_CONT (addr=0x1f) */ +#define PV88090_LDO1_EN 0x40 +#define PV88090_VLDO1_MASK 0x3F +/* PV88090_REG_LDO2_CONT (addr=0x20) */ +#define PV88090_LDO2_EN 0x40 +#define PV88090_VLDO2_MASK 0x3F + +/* PV88090_REG_BUCK1_CONF1 (addr=0x19) */ +#define PV88090_BUCK1_ILIM_SHIFT 2 +#define PV88090_BUCK1_ILIM_MASK 0x7C +#define PV88090_BUCK1_MODE_MASK 0x03 + +/* PV88090_REG_BUCK2_CONF1 (addr=0x1c) */ +#define PV88090_BUCK2_ILIM_SHIFT 2 +#define PV88090_BUCK2_ILIM_MASK 0x0C +#define PV88090_BUCK2_MODE_MASK 0x03 + +/* PV88090_REG_BUCK3_CONF1 (addr=0x1e) */ +#define PV88090_BUCK3_ILIM_SHIFT 2 +#define PV88090_BUCK3_ILIM_MASK 0x0C +#define PV88090_BUCK3_MODE_MASK 0x03 + +#define PV88090_BUCK_MODE_SLEEP 0x00 +#define PV88090_BUCK_MODE_AUTO 0x01 +#define PV88090_BUCK_MODE_SYNC 0x02 + +/* PV88090_REG_BUCK2_CONF2 (addr=0x58) */ +/* PV88090_REG_BUCK3_CONF2 (addr=0x5c) */ +#define PV88090_BUCK_VDAC_RANGE_SHIFT 7 +#define PV88090_BUCK_VDAC_RANGE_MASK 0x01 + +#define PV88090_BUCK_VDAC_RANGE_1 0x00 +#define PV88090_BUCK_VDAC_RANGE_2 0x01 + +/* PV88090_REG_BUCK_FOLD_RANGE (addr=0x61) */ +#define PV88080_BUCK_VRANGE_GAIN_SHIFT 3 +#define PV88080_BUCK_VRANGE_GAIN_MASK 0x01 + +#define PV88080_BUCK_VRANGE_GAIN_1 0x00 +#define PV88080_BUCK_VRANGE_GAIN_2 0x01 + +#endif /* __PV88090_REGISTERS_H__ */ diff --git a/drivers/regulator/qcom_smd-regulator.c b/drivers/regulator/qcom_smd-regulator.c index 6fa0c7d13290..56a17ec5b5ef 100644 --- a/drivers/regulator/qcom_smd-regulator.c +++ b/drivers/regulator/qcom_smd-regulator.c @@ -153,6 +153,49 @@ static const struct regulator_ops rpm_switch_ops = { .is_enabled = rpm_reg_is_enabled, }; +static const struct regulator_desc pma8084_hfsmps = { + .linear_ranges = (struct regulator_linear_range[]) { + REGULATOR_LINEAR_RANGE(375000, 0, 95, 12500), + REGULATOR_LINEAR_RANGE(1550000, 96, 158, 25000), + }, + .n_linear_ranges = 2, + .n_voltages = 159, + .ops = &rpm_smps_ldo_ops, +}; + +static const struct regulator_desc pma8084_ftsmps = { + .linear_ranges = (struct regulator_linear_range[]) { + REGULATOR_LINEAR_RANGE(350000, 0, 184, 5000), + REGULATOR_LINEAR_RANGE(700000, 185, 339, 10000), + }, + .n_linear_ranges = 2, + .n_voltages = 340, + .ops = &rpm_smps_ldo_ops, +}; + +static const struct regulator_desc pma8084_pldo = { + .linear_ranges = (struct regulator_linear_range[]) { + REGULATOR_LINEAR_RANGE(750000, 0, 30, 25000), + REGULATOR_LINEAR_RANGE(1500000, 31, 99, 50000), + }, + .n_linear_ranges = 2, + .n_voltages = 100, + .ops = &rpm_smps_ldo_ops, +}; + +static const struct regulator_desc pma8084_nldo = { + .linear_ranges = (struct regulator_linear_range[]) { + REGULATOR_LINEAR_RANGE(750000, 0, 63, 12500), + }, + .n_linear_ranges = 1, + .n_voltages = 64, + .ops = &rpm_smps_ldo_ops, +}; + +static const struct regulator_desc pma8084_switch = { + .ops = &rpm_switch_ops, +}; + static const struct regulator_desc pm8x41_hfsmps = { .linear_ranges = (struct regulator_linear_range[]) { REGULATOR_LINEAR_RANGE( 375000, 0, 95, 12500), @@ -211,6 +254,43 @@ static const struct regulator_desc pm8941_switch = { .ops = &rpm_switch_ops, }; +static const struct regulator_desc pm8916_pldo = { + .linear_ranges = (struct regulator_linear_range[]) { + REGULATOR_LINEAR_RANGE(750000, 0, 208, 12500), + }, + .n_linear_ranges = 1, + .n_voltages = 209, + .ops = &rpm_smps_ldo_ops, +}; + +static const struct regulator_desc pm8916_nldo = { + .linear_ranges = (struct regulator_linear_range[]) { + REGULATOR_LINEAR_RANGE(375000, 0, 93, 12500), + }, + .n_linear_ranges = 1, + .n_voltages = 94, + .ops = &rpm_smps_ldo_ops, +}; + +static const struct regulator_desc pm8916_buck_lvo_smps = { + .linear_ranges = (struct regulator_linear_range[]) { + REGULATOR_LINEAR_RANGE(375000, 0, 95, 12500), + REGULATOR_LINEAR_RANGE(750000, 96, 127, 25000), + }, + .n_linear_ranges = 2, + .n_voltages = 128, + .ops = &rpm_smps_ldo_ops, +}; + +static const struct regulator_desc pm8916_buck_hvo_smps = { + .linear_ranges = (struct regulator_linear_range[]) { + REGULATOR_LINEAR_RANGE(1550000, 0, 31, 25000), + }, + .n_linear_ranges = 1, + .n_voltages = 32, + .ops = &rpm_smps_ldo_ops, +}; + struct rpm_regulator_data { const char *name; u32 type; @@ -231,6 +311,32 @@ static const struct rpm_regulator_data rpm_pm8841_regulators[] = { {} }; +static const struct rpm_regulator_data rpm_pm8916_regulators[] = { + { "s1", QCOM_SMD_RPM_SMPA, 1, &pm8916_buck_lvo_smps, "vdd_s1" }, + { "s2", QCOM_SMD_RPM_SMPA, 2, &pm8916_buck_lvo_smps, "vdd_s2" }, + { "s3", QCOM_SMD_RPM_SMPA, 3, &pm8916_buck_lvo_smps, "vdd_s3" }, + { "s4", QCOM_SMD_RPM_SMPA, 4, &pm8916_buck_hvo_smps, "vdd_s4" }, + { "l1", QCOM_SMD_RPM_LDOA, 1, &pm8916_nldo, "vdd_l1_l2_l3" }, + { "l2", QCOM_SMD_RPM_LDOA, 2, &pm8916_nldo, "vdd_l1_l2_l3" }, + { "l3", QCOM_SMD_RPM_LDOA, 3, &pm8916_nldo, "vdd_l1_l2_l3" }, + { "l4", QCOM_SMD_RPM_LDOA, 4, &pm8916_pldo, "vdd_l4_l5_l6" }, + { "l5", QCOM_SMD_RPM_LDOA, 5, &pm8916_pldo, "vdd_l4_l5_l6" }, + { "l6", QCOM_SMD_RPM_LDOA, 6, &pm8916_pldo, "vdd_l4_l5_l6" }, + { "l7", QCOM_SMD_RPM_LDOA, 7, &pm8916_pldo, "vdd_l7" }, + { "l8", QCOM_SMD_RPM_LDOA, 8, &pm8916_pldo, "vdd_l8_l9_l10_l11_l12_l13_l14_l15_l16_l17_l18" }, + { "l9", QCOM_SMD_RPM_LDOA, 9, &pm8916_pldo, "vdd_l8_l9_l10_l11_l12_l13_l14_l15_l16_l17_l18" }, + { "l10", QCOM_SMD_RPM_LDOA, 10, &pm8916_pldo, "vdd_l8_l9_l10_l11_l12_l13_l14_l15_l16_l17_l18"}, + { "l11", QCOM_SMD_RPM_LDOA, 11, &pm8916_pldo, "vdd_l8_l9_l10_l11_l12_l13_l14_l15_l16_l17_l18"}, + { "l12", QCOM_SMD_RPM_LDOA, 12, &pm8916_pldo, "vdd_l8_l9_l10_l11_l12_l13_l14_l15_l16_l17_l18"}, + { "l13", QCOM_SMD_RPM_LDOA, 13, &pm8916_pldo, "vdd_l8_l9_l10_l11_l12_l13_l14_l15_l16_l17_l18"}, + { "l14", QCOM_SMD_RPM_LDOA, 14, &pm8916_pldo, "vdd_l8_l9_l10_l11_l12_l13_l14_l15_l16_l17_l18"}, + { "l15", QCOM_SMD_RPM_LDOA, 15, &pm8916_pldo, "vdd_l8_l9_l10_l11_l12_l13_l14_l15_l16_l17_l18"}, + { "l16", QCOM_SMD_RPM_LDOA, 16, &pm8916_pldo, "vdd_l8_l9_l10_l11_l12_l13_l14_l15_l16_l17_l18"}, + { "l17", QCOM_SMD_RPM_LDOA, 17, &pm8916_pldo, "vdd_l8_l9_l10_l11_l12_l13_l14_l15_l16_l17_l18"}, + { "l18", QCOM_SMD_RPM_LDOA, 18, &pm8916_pldo, "vdd_l8_l9_l10_l11_l12_l13_l14_l15_l16_l17_l18"}, + {} +}; + static const struct rpm_regulator_data rpm_pm8941_regulators[] = { { "s1", QCOM_SMD_RPM_SMPA, 1, &pm8x41_hfsmps, "vdd_s1" }, { "s2", QCOM_SMD_RPM_SMPA, 2, &pm8x41_hfsmps, "vdd_s2" }, @@ -272,9 +378,62 @@ static const struct rpm_regulator_data rpm_pm8941_regulators[] = { {} }; +static const struct rpm_regulator_data rpm_pma8084_regulators[] = { + { "s1", QCOM_SMD_RPM_SMPA, 1, &pma8084_ftsmps, "vdd_s1" }, + { "s2", QCOM_SMD_RPM_SMPA, 2, &pma8084_ftsmps, "vdd_s2" }, + { "s3", QCOM_SMD_RPM_SMPA, 3, &pma8084_hfsmps, "vdd_s3" }, + { "s4", QCOM_SMD_RPM_SMPA, 4, &pma8084_hfsmps, "vdd_s4" }, + { "s5", QCOM_SMD_RPM_SMPA, 5, &pma8084_hfsmps, "vdd_s5" }, + { "s6", QCOM_SMD_RPM_SMPA, 6, &pma8084_ftsmps, "vdd_s6" }, + { "s7", QCOM_SMD_RPM_SMPA, 7, &pma8084_ftsmps, "vdd_s7" }, + { "s8", QCOM_SMD_RPM_SMPA, 8, &pma8084_ftsmps, "vdd_s8" }, + { "s9", QCOM_SMD_RPM_SMPA, 9, &pma8084_ftsmps, "vdd_s9" }, + { "s10", QCOM_SMD_RPM_SMPA, 10, &pma8084_ftsmps, "vdd_s10" }, + { "s11", QCOM_SMD_RPM_SMPA, 11, &pma8084_ftsmps, "vdd_s11" }, + { "s12", QCOM_SMD_RPM_SMPA, 12, &pma8084_ftsmps, "vdd_s12" }, + + { "l1", QCOM_SMD_RPM_LDOA, 1, &pma8084_nldo, "vdd_l1_l11" }, + { "l2", QCOM_SMD_RPM_LDOA, 2, &pma8084_nldo, "vdd_l2_l3_l4_l27" }, + { "l3", QCOM_SMD_RPM_LDOA, 3, &pma8084_nldo, "vdd_l2_l3_l4_l27" }, + { "l4", QCOM_SMD_RPM_LDOA, 4, &pma8084_nldo, "vdd_l2_l3_l4_l27" }, + { "l5", QCOM_SMD_RPM_LDOA, 5, &pma8084_pldo, "vdd_l5_l7" }, + { "l6", QCOM_SMD_RPM_LDOA, 6, &pma8084_pldo, "vdd_l6_l12_l14_l15_l26" }, + { "l7", QCOM_SMD_RPM_LDOA, 7, &pma8084_pldo, "vdd_l5_l7" }, + { "l8", QCOM_SMD_RPM_LDOA, 8, &pma8084_pldo, "vdd_l8" }, + { "l9", QCOM_SMD_RPM_LDOA, 9, &pma8084_pldo, "vdd_l9_l10_l13_l20_l23_l24" }, + { "l10", QCOM_SMD_RPM_LDOA, 10, &pma8084_pldo, "vdd_l9_l10_l13_l20_l23_l24" }, + { "l11", QCOM_SMD_RPM_LDOA, 11, &pma8084_nldo, "vdd_l1_l11" }, + { "l12", QCOM_SMD_RPM_LDOA, 12, &pma8084_pldo, "vdd_l6_l12_l14_l15_l26" }, + { "l13", QCOM_SMD_RPM_LDOA, 13, &pma8084_pldo, "vdd_l9_l10_l13_l20_l23_l24" }, + { "l14", QCOM_SMD_RPM_LDOA, 14, &pma8084_pldo, "vdd_l6_l12_l14_l15_l26" }, + { "l15", QCOM_SMD_RPM_LDOA, 15, &pma8084_pldo, "vdd_l6_l12_l14_l15_l26" }, + { "l16", QCOM_SMD_RPM_LDOA, 16, &pma8084_pldo, "vdd_l16_l25" }, + { "l17", QCOM_SMD_RPM_LDOA, 17, &pma8084_pldo, "vdd_l17" }, + { "l18", QCOM_SMD_RPM_LDOA, 18, &pma8084_pldo, "vdd_l18" }, + { "l19", QCOM_SMD_RPM_LDOA, 19, &pma8084_pldo, "vdd_l19" }, + { "l20", QCOM_SMD_RPM_LDOA, 20, &pma8084_pldo, "vdd_l9_l10_l13_l20_l23_l24" }, + { "l21", QCOM_SMD_RPM_LDOA, 21, &pma8084_pldo, "vdd_l21" }, + { "l22", QCOM_SMD_RPM_LDOA, 22, &pma8084_pldo, "vdd_l22" }, + { "l23", QCOM_SMD_RPM_LDOA, 23, &pma8084_pldo, "vdd_l9_l10_l13_l20_l23_l24" }, + { "l24", QCOM_SMD_RPM_LDOA, 24, &pma8084_pldo, "vdd_l9_l10_l13_l20_l23_l24" }, + { "l25", QCOM_SMD_RPM_LDOA, 25, &pma8084_pldo, "vdd_l16_l25" }, + { "l26", QCOM_SMD_RPM_LDOA, 26, &pma8084_pldo, "vdd_l6_l12_l14_l15_l26" }, + { "l27", QCOM_SMD_RPM_LDOA, 27, &pma8084_nldo, "vdd_l2_l3_l4_l27" }, + + { "lvs1", QCOM_SMD_RPM_VSA, 1, &pma8084_switch }, + { "lvs2", QCOM_SMD_RPM_VSA, 2, &pma8084_switch }, + { "lvs3", QCOM_SMD_RPM_VSA, 3, &pma8084_switch }, + { "lvs4", QCOM_SMD_RPM_VSA, 4, &pma8084_switch }, + { "5vs1", QCOM_SMD_RPM_VSA, 5, &pma8084_switch }, + + {} +}; + static const struct of_device_id rpm_of_match[] = { { .compatible = "qcom,rpm-pm8841-regulators", .data = &rpm_pm8841_regulators }, + { .compatible = "qcom,rpm-pm8916-regulators", .data = &rpm_pm8916_regulators }, { .compatible = "qcom,rpm-pm8941-regulators", .data = &rpm_pm8941_regulators }, + { .compatible = "qcom,rpm-pma8084-regulators", .data = &rpm_pma8084_regulators }, {} }; MODULE_DEVICE_TABLE(of, rpm_of_match); diff --git a/drivers/regulator/s2mps11.c b/drivers/regulator/s2mps11.c index 72fc3c32db49..3242ffc0cb25 100644 --- a/drivers/regulator/s2mps11.c +++ b/drivers/regulator/s2mps11.c @@ -32,6 +32,7 @@ #include <linux/mfd/samsung/s2mps11.h> #include <linux/mfd/samsung/s2mps13.h> #include <linux/mfd/samsung/s2mps14.h> +#include <linux/mfd/samsung/s2mps15.h> #include <linux/mfd/samsung/s2mpu02.h> /* The highest number of possible regulators for supported devices. */ @@ -661,6 +662,133 @@ static const struct regulator_desc s2mps14_regulators[] = { S2MPS14_BUCK1235_START_SEL), }; +static struct regulator_ops s2mps15_reg_ldo_ops = { + .list_voltage = regulator_list_voltage_linear_range, + .map_voltage = regulator_map_voltage_linear_range, + .is_enabled = regulator_is_enabled_regmap, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .set_voltage_sel = regulator_set_voltage_sel_regmap, +}; + +static struct regulator_ops s2mps15_reg_buck_ops = { + .list_voltage = regulator_list_voltage_linear_range, + .map_voltage = regulator_map_voltage_linear_range, + .is_enabled = regulator_is_enabled_regmap, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .set_voltage_time_sel = regulator_set_voltage_time_sel, +}; + +#define regulator_desc_s2mps15_ldo(num, range) { \ + .name = "LDO"#num, \ + .id = S2MPS15_LDO##num, \ + .ops = &s2mps15_reg_ldo_ops, \ + .type = REGULATOR_VOLTAGE, \ + .owner = THIS_MODULE, \ + .linear_ranges = range, \ + .n_linear_ranges = ARRAY_SIZE(range), \ + .n_voltages = S2MPS15_LDO_N_VOLTAGES, \ + .vsel_reg = S2MPS15_REG_L1CTRL + num - 1, \ + .vsel_mask = S2MPS15_LDO_VSEL_MASK, \ + .enable_reg = S2MPS15_REG_L1CTRL + num - 1, \ + .enable_mask = S2MPS15_ENABLE_MASK \ +} + +#define regulator_desc_s2mps15_buck(num, range) { \ + .name = "BUCK"#num, \ + .id = S2MPS15_BUCK##num, \ + .ops = &s2mps15_reg_buck_ops, \ + .type = REGULATOR_VOLTAGE, \ + .owner = THIS_MODULE, \ + .linear_ranges = range, \ + .n_linear_ranges = ARRAY_SIZE(range), \ + .ramp_delay = 12500, \ + .n_voltages = S2MPS15_BUCK_N_VOLTAGES, \ + .vsel_reg = S2MPS15_REG_B1CTRL2 + ((num - 1) * 2), \ + .vsel_mask = S2MPS15_BUCK_VSEL_MASK, \ + .enable_reg = S2MPS15_REG_B1CTRL1 + ((num - 1) * 2), \ + .enable_mask = S2MPS15_ENABLE_MASK \ +} + +/* voltage range for s2mps15 LDO 3, 5, 15, 16, 18, 20, 23 and 27 */ +static const struct regulator_linear_range s2mps15_ldo_voltage_ranges1[] = { + REGULATOR_LINEAR_RANGE(1000000, 0xc, 0x38, 25000), +}; + +/* voltage range for s2mps15 LDO 2, 6, 14, 17, 19, 21, 24 and 25 */ +static const struct regulator_linear_range s2mps15_ldo_voltage_ranges2[] = { + REGULATOR_LINEAR_RANGE(1800000, 0x0, 0x3f, 25000), +}; + +/* voltage range for s2mps15 LDO 4, 11, 12, 13, 22 and 26 */ +static const struct regulator_linear_range s2mps15_ldo_voltage_ranges3[] = { + REGULATOR_LINEAR_RANGE(700000, 0x0, 0x34, 12500), +}; + +/* voltage range for s2mps15 LDO 7, 8, 9 and 10 */ +static const struct regulator_linear_range s2mps15_ldo_voltage_ranges4[] = { + REGULATOR_LINEAR_RANGE(700000, 0xc, 0x18, 25000), +}; + +/* voltage range for s2mps15 LDO 1 */ +static const struct regulator_linear_range s2mps15_ldo_voltage_ranges5[] = { + REGULATOR_LINEAR_RANGE(500000, 0x0, 0x20, 12500), +}; + +/* voltage range for s2mps15 BUCK 1, 2, 3, 4, 5, 6 and 7 */ +static const struct regulator_linear_range s2mps15_buck_voltage_ranges1[] = { + REGULATOR_LINEAR_RANGE(500000, 0x20, 0xb0, 6250), +}; + +/* voltage range for s2mps15 BUCK 8, 9 and 10 */ +static const struct regulator_linear_range s2mps15_buck_voltage_ranges2[] = { + REGULATOR_LINEAR_RANGE(1000000, 0x20, 0xc0, 12500), +}; + +static const struct regulator_desc s2mps15_regulators[] = { + regulator_desc_s2mps15_ldo(1, s2mps15_ldo_voltage_ranges5), + regulator_desc_s2mps15_ldo(2, s2mps15_ldo_voltage_ranges2), + regulator_desc_s2mps15_ldo(3, s2mps15_ldo_voltage_ranges1), + regulator_desc_s2mps15_ldo(4, s2mps15_ldo_voltage_ranges3), + regulator_desc_s2mps15_ldo(5, s2mps15_ldo_voltage_ranges1), + regulator_desc_s2mps15_ldo(6, s2mps15_ldo_voltage_ranges2), + regulator_desc_s2mps15_ldo(7, s2mps15_ldo_voltage_ranges4), + regulator_desc_s2mps15_ldo(8, s2mps15_ldo_voltage_ranges4), + regulator_desc_s2mps15_ldo(9, s2mps15_ldo_voltage_ranges4), + regulator_desc_s2mps15_ldo(10, s2mps15_ldo_voltage_ranges4), + regulator_desc_s2mps15_ldo(11, s2mps15_ldo_voltage_ranges3), + regulator_desc_s2mps15_ldo(12, s2mps15_ldo_voltage_ranges3), + regulator_desc_s2mps15_ldo(13, s2mps15_ldo_voltage_ranges3), + regulator_desc_s2mps15_ldo(14, s2mps15_ldo_voltage_ranges2), + regulator_desc_s2mps15_ldo(15, s2mps15_ldo_voltage_ranges1), + regulator_desc_s2mps15_ldo(16, s2mps15_ldo_voltage_ranges1), + regulator_desc_s2mps15_ldo(17, s2mps15_ldo_voltage_ranges2), + regulator_desc_s2mps15_ldo(18, s2mps15_ldo_voltage_ranges1), + regulator_desc_s2mps15_ldo(19, s2mps15_ldo_voltage_ranges2), + regulator_desc_s2mps15_ldo(20, s2mps15_ldo_voltage_ranges1), + regulator_desc_s2mps15_ldo(21, s2mps15_ldo_voltage_ranges2), + regulator_desc_s2mps15_ldo(22, s2mps15_ldo_voltage_ranges3), + regulator_desc_s2mps15_ldo(23, s2mps15_ldo_voltage_ranges1), + regulator_desc_s2mps15_ldo(24, s2mps15_ldo_voltage_ranges2), + regulator_desc_s2mps15_ldo(25, s2mps15_ldo_voltage_ranges2), + regulator_desc_s2mps15_ldo(26, s2mps15_ldo_voltage_ranges3), + regulator_desc_s2mps15_ldo(27, s2mps15_ldo_voltage_ranges1), + regulator_desc_s2mps15_buck(1, s2mps15_buck_voltage_ranges1), + regulator_desc_s2mps15_buck(2, s2mps15_buck_voltage_ranges1), + regulator_desc_s2mps15_buck(3, s2mps15_buck_voltage_ranges1), + regulator_desc_s2mps15_buck(4, s2mps15_buck_voltage_ranges1), + regulator_desc_s2mps15_buck(5, s2mps15_buck_voltage_ranges1), + regulator_desc_s2mps15_buck(6, s2mps15_buck_voltage_ranges1), + regulator_desc_s2mps15_buck(7, s2mps15_buck_voltage_ranges1), + regulator_desc_s2mps15_buck(8, s2mps15_buck_voltage_ranges2), + regulator_desc_s2mps15_buck(9, s2mps15_buck_voltage_ranges2), + regulator_desc_s2mps15_buck(10, s2mps15_buck_voltage_ranges2), +}; + static int s2mps14_pmic_enable_ext_control(struct s2mps11_info *s2mps11, struct regulator_dev *rdev) { @@ -974,6 +1102,10 @@ static int s2mps11_pmic_probe(struct platform_device *pdev) regulators = s2mps14_regulators; BUILD_BUG_ON(S2MPS_REGULATOR_MAX < s2mps11->rdev_num); break; + case S2MPS15X: + s2mps11->rdev_num = ARRAY_SIZE(s2mps15_regulators); + regulators = s2mps15_regulators; + break; case S2MPU02: s2mps11->rdev_num = ARRAY_SIZE(s2mpu02_regulators); regulators = s2mpu02_regulators; @@ -1067,10 +1199,11 @@ out: } static const struct platform_device_id s2mps11_pmic_id[] = { - { "s2mps11-pmic", S2MPS11X}, - { "s2mps13-pmic", S2MPS13X}, - { "s2mps14-pmic", S2MPS14X}, - { "s2mpu02-pmic", S2MPU02}, + { "s2mps11-regulator", S2MPS11X}, + { "s2mps13-regulator", S2MPS13X}, + { "s2mps14-regulator", S2MPS14X}, + { "s2mps15-regulator", S2MPS15X}, + { "s2mpu02-regulator", S2MPU02}, { }, }; MODULE_DEVICE_TABLE(platform, s2mps11_pmic_id); @@ -1097,5 +1230,5 @@ module_exit(s2mps11_pmic_exit); /* Module information */ MODULE_AUTHOR("Sangbeom Kim <sbkim73@samsung.com>"); -MODULE_DESCRIPTION("SAMSUNG S2MPS11/S2MPS14/S2MPU02 Regulator Driver"); +MODULE_DESCRIPTION("SAMSUNG S2MPS11/S2MPS14/S2MPS15/S2MPU02 Regulator Driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/regulator/tps6105x-regulator.c b/drivers/regulator/tps6105x-regulator.c index ddc4f10e268a..584ef3dedca6 100644 --- a/drivers/regulator/tps6105x-regulator.c +++ b/drivers/regulator/tps6105x-regulator.c @@ -27,90 +27,12 @@ static const unsigned int tps6105x_voltages[] = { 5000000, /* There is an additional 5V */ }; -static int tps6105x_regulator_enable(struct regulator_dev *rdev) -{ - struct tps6105x *tps6105x = rdev_get_drvdata(rdev); - int ret; - - /* Activate voltage mode */ - ret = regmap_update_bits(tps6105x->regmap, TPS6105X_REG_0, - TPS6105X_REG0_MODE_MASK, - TPS6105X_REG0_MODE_VOLTAGE << TPS6105X_REG0_MODE_SHIFT); - if (ret) - return ret; - - return 0; -} - -static int tps6105x_regulator_disable(struct regulator_dev *rdev) -{ - struct tps6105x *tps6105x = rdev_get_drvdata(rdev); - int ret; - - /* Set into shutdown mode */ - ret = regmap_update_bits(tps6105x->regmap, TPS6105X_REG_0, - TPS6105X_REG0_MODE_MASK, - TPS6105X_REG0_MODE_SHUTDOWN << TPS6105X_REG0_MODE_SHIFT); - if (ret) - return ret; - - return 0; -} - -static int tps6105x_regulator_is_enabled(struct regulator_dev *rdev) -{ - struct tps6105x *tps6105x = rdev_get_drvdata(rdev); - unsigned int regval; - int ret; - - ret = regmap_read(tps6105x->regmap, TPS6105X_REG_0, ®val); - if (ret) - return ret; - regval &= TPS6105X_REG0_MODE_MASK; - regval >>= TPS6105X_REG0_MODE_SHIFT; - - if (regval == TPS6105X_REG0_MODE_VOLTAGE) - return 1; - - return 0; -} - -static int tps6105x_regulator_get_voltage_sel(struct regulator_dev *rdev) -{ - struct tps6105x *tps6105x = rdev_get_drvdata(rdev); - unsigned int regval; - int ret; - - ret = regmap_read(tps6105x->regmap, TPS6105X_REG_0, ®val); - if (ret) - return ret; - - regval &= TPS6105X_REG0_VOLTAGE_MASK; - regval >>= TPS6105X_REG0_VOLTAGE_SHIFT; - return (int) regval; -} - -static int tps6105x_regulator_set_voltage_sel(struct regulator_dev *rdev, - unsigned selector) -{ - struct tps6105x *tps6105x = rdev_get_drvdata(rdev); - int ret; - - ret = regmap_update_bits(tps6105x->regmap, TPS6105X_REG_0, - TPS6105X_REG0_VOLTAGE_MASK, - selector << TPS6105X_REG0_VOLTAGE_SHIFT); - if (ret) - return ret; - - return 0; -} - static struct regulator_ops tps6105x_regulator_ops = { - .enable = tps6105x_regulator_enable, - .disable = tps6105x_regulator_disable, - .is_enabled = tps6105x_regulator_is_enabled, - .get_voltage_sel = tps6105x_regulator_get_voltage_sel, - .set_voltage_sel = tps6105x_regulator_set_voltage_sel, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .is_enabled = regulator_is_enabled_regmap, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .set_voltage_sel = regulator_set_voltage_sel_regmap, .list_voltage = regulator_list_voltage_table, }; @@ -122,6 +44,12 @@ static const struct regulator_desc tps6105x_regulator_desc = { .owner = THIS_MODULE, .n_voltages = ARRAY_SIZE(tps6105x_voltages), .volt_table = tps6105x_voltages, + .vsel_reg = TPS6105X_REG_0, + .vsel_mask = TPS6105X_REG0_VOLTAGE_MASK, + .enable_reg = TPS6105X_REG_0, + .enable_mask = TPS6105X_REG0_MODE_MASK, + .enable_val = TPS6105X_REG0_MODE_VOLTAGE << + TPS6105X_REG0_MODE_SHIFT, }; /* @@ -144,6 +72,7 @@ static int tps6105x_regulator_probe(struct platform_device *pdev) config.dev = &tps6105x->client->dev; config.init_data = pdata->regulator_data; config.driver_data = tps6105x; + config.regmap = tps6105x->regmap; /* Register regulator with framework */ tps6105x->regulator = devm_regulator_register(&pdev->dev, diff --git a/drivers/regulator/tps65086-regulator.c b/drivers/regulator/tps65086-regulator.c new file mode 100644 index 000000000000..33f389d583ef --- /dev/null +++ b/drivers/regulator/tps65086-regulator.c @@ -0,0 +1,251 @@ +/* + * Copyright (C) 2015 Texas Instruments Incorporated - http://www.ti.com/ + * + * Author: Andrew F. Davis <afd@ti.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 + * published by the Free Software Foundation. + * + * This program is distributed "as is" WITHOUT ANY WARRANTY of any + * kind, whether expressed or implied; without even the implied warranty + * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License version 2 for more details. + * + * Based on the TPS65912 driver + */ + +#include <linux/module.h> +#include <linux/of.h> +#include <linux/platform_device.h> +#include <linux/regulator/driver.h> + +#include <linux/mfd/tps65086.h> + +enum tps65086_regulators { BUCK1, BUCK2, BUCK3, BUCK4, BUCK5, BUCK6, LDOA1, + LDOA2, LDOA3, SWA1, SWB1, SWB2, VTT }; + +#define TPS65086_REGULATOR(_name, _of, _id, _nv, _vr, _vm, _er, _em, _lr, _dr, _dm) \ + [_id] = { \ + .desc = { \ + .name = _name, \ + .of_match = of_match_ptr(_of), \ + .regulators_node = "regulators", \ + .of_parse_cb = tps65086_of_parse_cb, \ + .id = _id, \ + .ops = ®_ops, \ + .n_voltages = _nv, \ + .type = REGULATOR_VOLTAGE, \ + .owner = THIS_MODULE, \ + .vsel_reg = _vr, \ + .vsel_mask = _vm, \ + .enable_reg = _er, \ + .enable_mask = _em, \ + .volt_table = NULL, \ + .linear_ranges = _lr, \ + .n_linear_ranges = ARRAY_SIZE(_lr), \ + }, \ + .decay_reg = _dr, \ + .decay_mask = _dm, \ + } + +#define TPS65086_SWITCH(_name, _of, _id, _er, _em) \ + [_id] = { \ + .desc = { \ + .name = _name, \ + .of_match = of_match_ptr(_of), \ + .regulators_node = "regulators", \ + .of_parse_cb = tps65086_of_parse_cb, \ + .id = _id, \ + .ops = &switch_ops, \ + .type = REGULATOR_VOLTAGE, \ + .owner = THIS_MODULE, \ + .enable_reg = _er, \ + .enable_mask = _em, \ + }, \ + } + +struct tps65086_regulator { + struct regulator_desc desc; + unsigned int decay_reg; + unsigned int decay_mask; +}; + +static const struct regulator_linear_range tps65086_buck126_10mv_ranges[] = { + REGULATOR_LINEAR_RANGE(0, 0x0, 0x0, 0), + REGULATOR_LINEAR_RANGE(410000, 0x1, 0x7F, 10000), +}; + +static const struct regulator_linear_range tps65086_buck126_25mv_ranges[] = { + REGULATOR_LINEAR_RANGE(0, 0x0, 0x0, 0), + REGULATOR_LINEAR_RANGE(1000000, 0x1, 0x18, 0), + REGULATOR_LINEAR_RANGE(1025000, 0x19, 0x7F, 25000), +}; + +static const struct regulator_linear_range tps65086_buck345_ranges[] = { + REGULATOR_LINEAR_RANGE(0, 0x0, 0x0, 0), + REGULATOR_LINEAR_RANGE(425000, 0x1, 0x7F, 25000), +}; + +static const struct regulator_linear_range tps65086_ldoa1_ranges[] = { + REGULATOR_LINEAR_RANGE(1350000, 0x0, 0x0, 0), + REGULATOR_LINEAR_RANGE(1500000, 0x1, 0x7, 100000), + REGULATOR_LINEAR_RANGE(2300000, 0x8, 0xA, 100000), + REGULATOR_LINEAR_RANGE(2700000, 0xB, 0xD, 150000), + REGULATOR_LINEAR_RANGE(3300000, 0xE, 0xE, 0), +}; + +static const struct regulator_linear_range tps65086_ldoa23_ranges[] = { + REGULATOR_LINEAR_RANGE(700000, 0x0, 0xD, 50000), + REGULATOR_LINEAR_RANGE(1400000, 0xE, 0xF, 100000), +}; + +/* Operations permitted on regulators */ +static struct regulator_ops reg_ops = { + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .is_enabled = regulator_is_enabled_regmap, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .map_voltage = regulator_map_voltage_linear_range, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .list_voltage = regulator_list_voltage_linear_range, +}; + +/* Operations permitted on load switches */ +static struct regulator_ops switch_ops = { + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .is_enabled = regulator_is_enabled_regmap, +}; + +static int tps65086_of_parse_cb(struct device_node *dev, + const struct regulator_desc *desc, + struct regulator_config *config); + +static struct tps65086_regulator regulators[] = { + TPS65086_REGULATOR("BUCK1", "buck1", BUCK1, 0x80, TPS65086_BUCK1CTRL, + BUCK_VID_MASK, TPS65086_BUCK123CTRL, BIT(0), + tps65086_buck126_10mv_ranges, TPS65086_BUCK1CTRL, + BIT(0)), + TPS65086_REGULATOR("BUCK2", "buck2", BUCK2, 0x80, TPS65086_BUCK2CTRL, + BUCK_VID_MASK, TPS65086_BUCK123CTRL, BIT(1), + tps65086_buck126_10mv_ranges, TPS65086_BUCK2CTRL, + BIT(0)), + TPS65086_REGULATOR("BUCK3", "buck3", BUCK3, 0x80, TPS65086_BUCK3VID, + BUCK_VID_MASK, TPS65086_BUCK123CTRL, BIT(2), + tps65086_buck345_ranges, TPS65086_BUCK3DECAY, + BIT(0)), + TPS65086_REGULATOR("BUCK4", "buck4", BUCK4, 0x80, TPS65086_BUCK4VID, + BUCK_VID_MASK, TPS65086_BUCK4CTRL, BIT(0), + tps65086_buck345_ranges, TPS65086_BUCK4VID, + BIT(0)), + TPS65086_REGULATOR("BUCK5", "buck5", BUCK5, 0x80, TPS65086_BUCK5VID, + BUCK_VID_MASK, TPS65086_BUCK5CTRL, BIT(0), + tps65086_buck345_ranges, TPS65086_BUCK5CTRL, + BIT(0)), + TPS65086_REGULATOR("BUCK6", "buck6", BUCK6, 0x80, TPS65086_BUCK6VID, + BUCK_VID_MASK, TPS65086_BUCK6CTRL, BIT(0), + tps65086_buck126_10mv_ranges, TPS65086_BUCK6CTRL, + BIT(0)), + TPS65086_REGULATOR("LDOA1", "ldoa1", LDOA1, 0xF, TPS65086_LDOA1CTRL, + VDOA1_VID_MASK, TPS65086_LDOA1CTRL, BIT(0), + tps65086_ldoa1_ranges, 0, 0), + TPS65086_REGULATOR("LDOA2", "ldoa2", LDOA2, 0x10, TPS65086_LDOA2VID, + VDOA23_VID_MASK, TPS65086_LDOA2CTRL, BIT(0), + tps65086_ldoa23_ranges, 0, 0), + TPS65086_REGULATOR("LDOA3", "ldoa3", LDOA3, 0x10, TPS65086_LDOA3VID, + VDOA23_VID_MASK, TPS65086_LDOA3CTRL, BIT(0), + tps65086_ldoa23_ranges, 0, 0), + TPS65086_SWITCH("SWA1", "swa1", SWA1, TPS65086_SWVTT_EN, BIT(5)), + TPS65086_SWITCH("SWB1", "swa2", SWB1, TPS65086_SWVTT_EN, BIT(6)), + TPS65086_SWITCH("SWB2", "swa3", SWB2, TPS65086_SWVTT_EN, BIT(7)), + TPS65086_SWITCH("VTT", "vtt", VTT, TPS65086_SWVTT_EN, BIT(4)), +}; + +static inline bool has_25mv_mode(int id) +{ + switch (id) { + case BUCK1: + case BUCK2: + case BUCK6: + return true; + default: + return false; + } +} + +static int tps65086_of_parse_cb(struct device_node *dev, + const struct regulator_desc *desc, + struct regulator_config *config) +{ + int ret; + + /* Check for 25mV step mode */ + if (has_25mv_mode(desc->id) && + of_property_read_bool(config->of_node, "ti,regulator-step-size-25mv")) { + regulators[desc->id].desc.linear_ranges = + tps65086_buck126_25mv_ranges; + regulators[desc->id].desc.n_linear_ranges = + ARRAY_SIZE(tps65086_buck126_25mv_ranges); + } + + /* Check for decay mode */ + if (desc->id <= BUCK6 && of_property_read_bool(config->of_node, "ti,regulator-decay")) { + ret = regmap_write_bits(config->regmap, + regulators[desc->id].decay_reg, + regulators[desc->id].decay_mask, + regulators[desc->id].decay_mask); + if (ret) { + dev_err(config->dev, "Error setting decay\n"); + return ret; + } + } + + return 0; +} + +static int tps65086_regulator_probe(struct platform_device *pdev) +{ + struct tps65086 *tps = dev_get_drvdata(pdev->dev.parent); + struct regulator_config config = { }; + struct regulator_dev *rdev; + int i; + + platform_set_drvdata(pdev, tps); + + config.dev = &pdev->dev; + config.dev->of_node = tps->dev->of_node; + config.driver_data = tps; + config.regmap = tps->regmap; + + for (i = 0; i < ARRAY_SIZE(regulators); i++) { + rdev = devm_regulator_register(&pdev->dev, ®ulators[i].desc, + &config); + if (IS_ERR(rdev)) { + dev_err(tps->dev, "failed to register %s regulator\n", + pdev->name); + return PTR_ERR(rdev); + } + } + + return 0; +} + +static const struct platform_device_id tps65086_regulator_id_table[] = { + { "tps65086-regulator", }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(platform, tps65086_regulator_id_table); + +static struct platform_driver tps65086_regulator_driver = { + .driver = { + .name = "tps65086-regulator", + }, + .probe = tps65086_regulator_probe, + .id_table = tps65086_regulator_id_table, +}; +module_platform_driver(tps65086_regulator_driver); + +MODULE_AUTHOR("Andrew F. Davis <afd@ti.com>"); +MODULE_DESCRIPTION("TPS65086 Regulator driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/regulator/tps65218-regulator.c b/drivers/regulator/tps65218-regulator.c index a02c1b961039..a5e5634eeb9e 100644 --- a/drivers/regulator/tps65218-regulator.c +++ b/drivers/regulator/tps65218-regulator.c @@ -27,19 +27,22 @@ #include <linux/regulator/machine.h> #include <linux/mfd/tps65218.h> -enum tps65218_regulators { DCDC1, DCDC2, DCDC3, DCDC4, DCDC5, DCDC6, LDO1 }; +enum tps65218_regulators { DCDC1, DCDC2, DCDC3, DCDC4, + DCDC5, DCDC6, LDO1, LS3 }; -#define TPS65218_REGULATOR(_name, _id, _ops, _n, _vr, _vm, _er, _em, \ - _lr, _nlr, _delay, _fuv) \ +#define TPS65218_REGULATOR(_name, _id, _type, _ops, _n, _vr, _vm, _er, _em, \ + _cr, _cm, _lr, _nlr, _delay, _fuv) \ { \ .name = _name, \ .id = _id, \ .ops = &_ops, \ .n_voltages = _n, \ - .type = REGULATOR_VOLTAGE, \ + .type = _type, \ .owner = THIS_MODULE, \ .vsel_reg = _vr, \ .vsel_mask = _vm, \ + .csel_reg = _cr, \ + .csel_mask = _cm, \ .enable_reg = _er, \ .enable_mask = _em, \ .volt_table = NULL, \ @@ -80,6 +83,7 @@ static struct tps_info tps65218_pmic_regs[] = { TPS65218_INFO(DCDC5, "DCDC5", 1000000, 1000000), TPS65218_INFO(DCDC6, "DCDC6", 1800000, 1800000), TPS65218_INFO(LDO1, "LDO1", 900000, 3400000), + TPS65218_INFO(LS3, "LS3", -1, -1), }; #define TPS65218_OF_MATCH(comp, label) \ @@ -96,6 +100,7 @@ static const struct of_device_id tps65218_of_match[] = { TPS65218_OF_MATCH("ti,tps65218-dcdc5", tps65218_pmic_regs[DCDC5]), TPS65218_OF_MATCH("ti,tps65218-dcdc6", tps65218_pmic_regs[DCDC6]), TPS65218_OF_MATCH("ti,tps65218-ldo1", tps65218_pmic_regs[LDO1]), + TPS65218_OF_MATCH("ti,tps65218-ls3", tps65218_pmic_regs[LS3]), { } }; MODULE_DEVICE_TABLE(of, tps65218_of_match); @@ -175,6 +180,68 @@ static struct regulator_ops tps65218_ldo1_dcdc34_ops = { .map_voltage = regulator_map_voltage_linear_range, }; +static const int ls3_currents[] = { 100, 200, 500, 1000 }; + +static int tps65218_pmic_set_input_current_lim(struct regulator_dev *dev, + int lim_uA) +{ + unsigned int index = 0; + unsigned int num_currents = ARRAY_SIZE(ls3_currents); + struct tps65218 *tps = rdev_get_drvdata(dev); + + while (index < num_currents && ls3_currents[index] != lim_uA) + index++; + + if (index == num_currents) + return -EINVAL; + + return tps65218_set_bits(tps, dev->desc->csel_reg, dev->desc->csel_mask, + index << 2, TPS65218_PROTECT_L1); +} + +static int tps65218_pmic_set_current_limit(struct regulator_dev *dev, + int min_uA, int max_uA) +{ + int index = 0; + unsigned int num_currents = ARRAY_SIZE(ls3_currents); + struct tps65218 *tps = rdev_get_drvdata(dev); + + while (index < num_currents && ls3_currents[index] < max_uA) + index++; + + index--; + + if (index < 0 || ls3_currents[index] < min_uA) + return -EINVAL; + + return tps65218_set_bits(tps, dev->desc->csel_reg, dev->desc->csel_mask, + index << 2, TPS65218_PROTECT_L1); +} + +static int tps65218_pmic_get_current_limit(struct regulator_dev *dev) +{ + int retval; + unsigned int index; + struct tps65218 *tps = rdev_get_drvdata(dev); + + retval = tps65218_reg_read(tps, dev->desc->csel_reg, &index); + if (retval < 0) + return retval; + + index = (index & dev->desc->csel_mask) >> 2; + + return ls3_currents[index]; +} + +static struct regulator_ops tps65218_ls3_ops = { + .is_enabled = regulator_is_enabled_regmap, + .enable = tps65218_pmic_enable, + .disable = tps65218_pmic_disable, + .set_input_current_limit = tps65218_pmic_set_input_current_lim, + .set_current_limit = tps65218_pmic_set_current_limit, + .get_current_limit = tps65218_pmic_get_current_limit, +}; + /* Operations permitted on DCDC5, DCDC6 */ static struct regulator_ops tps65218_dcdc56_pmic_ops = { .is_enabled = regulator_is_enabled_regmap, @@ -183,36 +250,46 @@ static struct regulator_ops tps65218_dcdc56_pmic_ops = { }; static const struct regulator_desc regulators[] = { - TPS65218_REGULATOR("DCDC1", TPS65218_DCDC_1, tps65218_dcdc12_ops, 64, - TPS65218_REG_CONTROL_DCDC1, - TPS65218_CONTROL_DCDC1_MASK, - TPS65218_REG_ENABLE1, TPS65218_ENABLE1_DC1_EN, - dcdc1_dcdc2_ranges, 2, 4000, 0), - TPS65218_REGULATOR("DCDC2", TPS65218_DCDC_2, tps65218_dcdc12_ops, 64, - TPS65218_REG_CONTROL_DCDC2, - TPS65218_CONTROL_DCDC2_MASK, - TPS65218_REG_ENABLE1, TPS65218_ENABLE1_DC2_EN, - dcdc1_dcdc2_ranges, 2, 4000, 0), - TPS65218_REGULATOR("DCDC3", TPS65218_DCDC_3, tps65218_ldo1_dcdc34_ops, - 64, TPS65218_REG_CONTROL_DCDC3, + TPS65218_REGULATOR("DCDC1", TPS65218_DCDC_1, REGULATOR_VOLTAGE, + tps65218_dcdc12_ops, 64, TPS65218_REG_CONTROL_DCDC1, + TPS65218_CONTROL_DCDC1_MASK, TPS65218_REG_ENABLE1, + TPS65218_ENABLE1_DC1_EN, 0, 0, dcdc1_dcdc2_ranges, + 2, 4000, 0), + TPS65218_REGULATOR("DCDC2", TPS65218_DCDC_2, REGULATOR_VOLTAGE, + tps65218_dcdc12_ops, 64, TPS65218_REG_CONTROL_DCDC2, + TPS65218_CONTROL_DCDC2_MASK, TPS65218_REG_ENABLE1, + TPS65218_ENABLE1_DC2_EN, 0, 0, dcdc1_dcdc2_ranges, + 2, 4000, 0), + TPS65218_REGULATOR("DCDC3", TPS65218_DCDC_3, REGULATOR_VOLTAGE, + tps65218_ldo1_dcdc34_ops, 64, + TPS65218_REG_CONTROL_DCDC3, TPS65218_CONTROL_DCDC3_MASK, TPS65218_REG_ENABLE1, - TPS65218_ENABLE1_DC3_EN, ldo1_dcdc3_ranges, 2, 0, 0), - TPS65218_REGULATOR("DCDC4", TPS65218_DCDC_4, tps65218_ldo1_dcdc34_ops, - 53, TPS65218_REG_CONTROL_DCDC4, - TPS65218_CONTROL_DCDC4_MASK, - TPS65218_REG_ENABLE1, TPS65218_ENABLE1_DC4_EN, - dcdc4_ranges, 2, 0, 0), - TPS65218_REGULATOR("DCDC5", TPS65218_DCDC_5, tps65218_dcdc56_pmic_ops, - 1, -1, -1, TPS65218_REG_ENABLE1, - TPS65218_ENABLE1_DC5_EN, NULL, 0, 0, 1000000), - TPS65218_REGULATOR("DCDC6", TPS65218_DCDC_6, tps65218_dcdc56_pmic_ops, - 1, -1, -1, TPS65218_REG_ENABLE1, - TPS65218_ENABLE1_DC6_EN, NULL, 0, 0, 1800000), - TPS65218_REGULATOR("LDO1", TPS65218_LDO_1, tps65218_ldo1_dcdc34_ops, 64, + TPS65218_ENABLE1_DC3_EN, 0, 0, ldo1_dcdc3_ranges, 2, + 0, 0), + TPS65218_REGULATOR("DCDC4", TPS65218_DCDC_4, REGULATOR_VOLTAGE, + tps65218_ldo1_dcdc34_ops, 53, + TPS65218_REG_CONTROL_DCDC4, + TPS65218_CONTROL_DCDC4_MASK, TPS65218_REG_ENABLE1, + TPS65218_ENABLE1_DC4_EN, 0, 0, dcdc4_ranges, 2, + 0, 0), + TPS65218_REGULATOR("DCDC5", TPS65218_DCDC_5, REGULATOR_VOLTAGE, + tps65218_dcdc56_pmic_ops, 1, -1, -1, + TPS65218_REG_ENABLE1, TPS65218_ENABLE1_DC5_EN, 0, 0, + NULL, 0, 0, 1000000), + TPS65218_REGULATOR("DCDC6", TPS65218_DCDC_6, REGULATOR_VOLTAGE, + tps65218_dcdc56_pmic_ops, 1, -1, -1, + TPS65218_REG_ENABLE1, TPS65218_ENABLE1_DC6_EN, 0, 0, + NULL, 0, 0, 1800000), + TPS65218_REGULATOR("LDO1", TPS65218_LDO_1, REGULATOR_VOLTAGE, + tps65218_ldo1_dcdc34_ops, 64, TPS65218_REG_CONTROL_LDO1, TPS65218_CONTROL_LDO1_MASK, TPS65218_REG_ENABLE2, - TPS65218_ENABLE2_LDO1_EN, ldo1_dcdc3_ranges, + TPS65218_ENABLE2_LDO1_EN, 0, 0, ldo1_dcdc3_ranges, 2, 0, 0), + TPS65218_REGULATOR("LS3", TPS65218_LS_3, REGULATOR_CURRENT, + tps65218_ls3_ops, 0, 0, 0, TPS65218_REG_ENABLE2, + TPS65218_ENABLE2_LS3_EN, TPS65218_REG_CONFIG2, + TPS65218_CONFIG2_LS3ILIM_MASK, NULL, 0, 0, 0), }; static int tps65218_regulator_probe(struct platform_device *pdev) diff --git a/drivers/regulator/wm831x-dcdc.c b/drivers/regulator/wm831x-dcdc.c index 8cbb82ceec40..5a5bc4bb08d2 100644 --- a/drivers/regulator/wm831x-dcdc.c +++ b/drivers/regulator/wm831x-dcdc.c @@ -365,7 +365,7 @@ static int wm831x_buckv_get_current_limit(struct regulator_dev *rdev) return wm831x_dcdc_ilim[val]; } -static struct regulator_ops wm831x_buckv_ops = { +static const struct regulator_ops wm831x_buckv_ops = { .set_voltage_sel = wm831x_buckv_set_voltage_sel, .get_voltage_sel = wm831x_buckv_get_voltage_sel, .list_voltage = wm831x_buckv_list_voltage, @@ -585,7 +585,7 @@ static int wm831x_buckp_set_suspend_voltage(struct regulator_dev *rdev, int uV) return wm831x_set_bits(wm831x, reg, WM831X_DC3_ON_VSEL_MASK, sel); } -static struct regulator_ops wm831x_buckp_ops = { +static const struct regulator_ops wm831x_buckp_ops = { .set_voltage_sel = regulator_set_voltage_sel_regmap, .get_voltage_sel = regulator_get_voltage_sel_regmap, .list_voltage = regulator_list_voltage_linear, @@ -725,7 +725,7 @@ static int wm831x_boostp_get_status(struct regulator_dev *rdev) return REGULATOR_STATUS_OFF; } -static struct regulator_ops wm831x_boostp_ops = { +static const struct regulator_ops wm831x_boostp_ops = { .get_status = wm831x_boostp_get_status, .is_enabled = regulator_is_enabled_regmap, @@ -818,7 +818,7 @@ static struct platform_driver wm831x_boostp_driver = { #define WM831X_EPE_BASE 6 -static struct regulator_ops wm831x_epe_ops = { +static const struct regulator_ops wm831x_epe_ops = { .is_enabled = regulator_is_enabled_regmap, .enable = regulator_enable_regmap, .disable = regulator_disable_regmap, @@ -884,35 +884,22 @@ static struct platform_driver wm831x_epe_driver = { }, }; +static struct platform_driver * const drivers[] = { + &wm831x_buckv_driver, + &wm831x_buckp_driver, + &wm831x_boostp_driver, + &wm831x_epe_driver, +}; + static int __init wm831x_dcdc_init(void) { - int ret; - ret = platform_driver_register(&wm831x_buckv_driver); - if (ret != 0) - pr_err("Failed to register WM831x BUCKV driver: %d\n", ret); - - ret = platform_driver_register(&wm831x_buckp_driver); - if (ret != 0) - pr_err("Failed to register WM831x BUCKP driver: %d\n", ret); - - ret = platform_driver_register(&wm831x_boostp_driver); - if (ret != 0) - pr_err("Failed to register WM831x BOOST driver: %d\n", ret); - - ret = platform_driver_register(&wm831x_epe_driver); - if (ret != 0) - pr_err("Failed to register WM831x EPE driver: %d\n", ret); - - return 0; + return platform_register_drivers(drivers, ARRAY_SIZE(drivers)); } subsys_initcall(wm831x_dcdc_init); static void __exit wm831x_dcdc_exit(void) { - platform_driver_unregister(&wm831x_epe_driver); - platform_driver_unregister(&wm831x_boostp_driver); - platform_driver_unregister(&wm831x_buckp_driver); - platform_driver_unregister(&wm831x_buckv_driver); + platform_unregister_drivers(drivers, ARRAY_SIZE(drivers)); } module_exit(wm831x_dcdc_exit); diff --git a/drivers/regulator/wm831x-isink.c b/drivers/regulator/wm831x-isink.c index 1442828fcd9a..6dd891d7eee3 100644 --- a/drivers/regulator/wm831x-isink.c +++ b/drivers/regulator/wm831x-isink.c @@ -128,7 +128,7 @@ static int wm831x_isink_get_current(struct regulator_dev *rdev) return wm831x_isinkv_values[ret]; } -static struct regulator_ops wm831x_isink_ops = { +static const struct regulator_ops wm831x_isink_ops = { .is_enabled = wm831x_isink_is_enabled, .enable = wm831x_isink_enable, .disable = wm831x_isink_disable, diff --git a/drivers/regulator/wm831x-ldo.c b/drivers/regulator/wm831x-ldo.c index 5a7b65e8a529..e4a6f888484e 100644 --- a/drivers/regulator/wm831x-ldo.c +++ b/drivers/regulator/wm831x-ldo.c @@ -198,7 +198,7 @@ static unsigned int wm831x_gp_ldo_get_optimum_mode(struct regulator_dev *rdev, } -static struct regulator_ops wm831x_gp_ldo_ops = { +static const struct regulator_ops wm831x_gp_ldo_ops = { .list_voltage = regulator_list_voltage_linear_range, .map_voltage = regulator_map_voltage_linear_range, .get_voltage_sel = regulator_get_voltage_sel_regmap, @@ -409,7 +409,7 @@ static int wm831x_aldo_get_status(struct regulator_dev *rdev) return regulator_mode_to_status(ret); } -static struct regulator_ops wm831x_aldo_ops = { +static const struct regulator_ops wm831x_aldo_ops = { .list_voltage = regulator_list_voltage_linear_range, .map_voltage = regulator_map_voltage_linear_range, .get_voltage_sel = regulator_get_voltage_sel_regmap, @@ -557,7 +557,7 @@ static int wm831x_alive_ldo_get_status(struct regulator_dev *rdev) return REGULATOR_STATUS_OFF; } -static struct regulator_ops wm831x_alive_ldo_ops = { +static const struct regulator_ops wm831x_alive_ldo_ops = { .list_voltage = regulator_list_voltage_linear, .map_voltage = regulator_map_voltage_linear, .get_voltage_sel = regulator_get_voltage_sel_regmap, @@ -653,32 +653,21 @@ static struct platform_driver wm831x_alive_ldo_driver = { }, }; +static struct platform_driver * const drivers[] = { + &wm831x_gp_ldo_driver, + &wm831x_aldo_driver, + &wm831x_alive_ldo_driver, +}; + static int __init wm831x_ldo_init(void) { - int ret; - - ret = platform_driver_register(&wm831x_gp_ldo_driver); - if (ret != 0) - pr_err("Failed to register WM831x GP LDO driver: %d\n", ret); - - ret = platform_driver_register(&wm831x_aldo_driver); - if (ret != 0) - pr_err("Failed to register WM831x ALDO driver: %d\n", ret); - - ret = platform_driver_register(&wm831x_alive_ldo_driver); - if (ret != 0) - pr_err("Failed to register WM831x alive LDO driver: %d\n", - ret); - - return 0; + return platform_register_drivers(drivers, ARRAY_SIZE(drivers)); } subsys_initcall(wm831x_ldo_init); static void __exit wm831x_ldo_exit(void) { - platform_driver_unregister(&wm831x_alive_ldo_driver); - platform_driver_unregister(&wm831x_aldo_driver); - platform_driver_unregister(&wm831x_gp_ldo_driver); + platform_unregister_drivers(drivers, ARRAY_SIZE(drivers)); } module_exit(wm831x_ldo_exit); diff --git a/drivers/regulator/wm8350-regulator.c b/drivers/regulator/wm8350-regulator.c index 95f6b040186e..da9106bd2109 100644 --- a/drivers/regulator/wm8350-regulator.c +++ b/drivers/regulator/wm8350-regulator.c @@ -941,7 +941,7 @@ static unsigned int wm8350_dcdc_get_optimum_mode(struct regulator_dev *rdev, return mode; } -static struct regulator_ops wm8350_dcdc_ops = { +static const struct regulator_ops wm8350_dcdc_ops = { .set_voltage_sel = regulator_set_voltage_sel_regmap, .get_voltage_sel = regulator_get_voltage_sel_regmap, .list_voltage = regulator_list_voltage_linear, @@ -958,7 +958,7 @@ static struct regulator_ops wm8350_dcdc_ops = { .set_suspend_mode = wm8350_dcdc_set_suspend_mode, }; -static struct regulator_ops wm8350_dcdc2_5_ops = { +static const struct regulator_ops wm8350_dcdc2_5_ops = { .enable = regulator_enable_regmap, .disable = regulator_disable_regmap, .is_enabled = regulator_is_enabled_regmap, @@ -966,7 +966,7 @@ static struct regulator_ops wm8350_dcdc2_5_ops = { .set_suspend_disable = wm8350_dcdc25_set_suspend_disable, }; -static struct regulator_ops wm8350_ldo_ops = { +static const struct regulator_ops wm8350_ldo_ops = { .map_voltage = regulator_map_voltage_linear_range, .set_voltage_sel = regulator_set_voltage_sel_regmap, .get_voltage_sel = regulator_get_voltage_sel_regmap, @@ -980,7 +980,7 @@ static struct regulator_ops wm8350_ldo_ops = { .set_suspend_disable = wm8350_ldo_set_suspend_disable, }; -static struct regulator_ops wm8350_isink_ops = { +static const struct regulator_ops wm8350_isink_ops = { .set_current_limit = wm8350_isink_set_current, .get_current_limit = wm8350_isink_get_current, .enable = wm8350_isink_enable, diff --git a/drivers/regulator/wm8400-regulator.c b/drivers/regulator/wm8400-regulator.c index 82d829000851..fb1837657b64 100644 --- a/drivers/regulator/wm8400-regulator.c +++ b/drivers/regulator/wm8400-regulator.c @@ -24,7 +24,7 @@ static const struct regulator_linear_range wm8400_ldo_ranges[] = { REGULATOR_LINEAR_RANGE(1700000, 15, 31, 100000), }; -static struct regulator_ops wm8400_ldo_ops = { +static const struct regulator_ops wm8400_ldo_ops = { .is_enabled = regulator_is_enabled_regmap, .enable = regulator_enable_regmap, .disable = regulator_disable_regmap, @@ -106,7 +106,7 @@ static unsigned int wm8400_dcdc_get_optimum_mode(struct regulator_dev *dev, return REGULATOR_MODE_NORMAL; } -static struct regulator_ops wm8400_dcdc_ops = { +static const struct regulator_ops wm8400_dcdc_ops = { .is_enabled = regulator_is_enabled_regmap, .enable = regulator_enable_regmap, .disable = regulator_disable_regmap, diff --git a/drivers/regulator/wm8994-regulator.c b/drivers/regulator/wm8994-regulator.c index 750e0bd61f9f..7a4ce6df4f22 100644 --- a/drivers/regulator/wm8994-regulator.c +++ b/drivers/regulator/wm8994-regulator.c @@ -36,7 +36,7 @@ struct wm8994_ldo { #define WM8994_LDO1_MAX_SELECTOR 0x7 #define WM8994_LDO2_MAX_SELECTOR 0x3 -static struct regulator_ops wm8994_ldo1_ops = { +static const struct regulator_ops wm8994_ldo1_ops = { .list_voltage = regulator_list_voltage_linear, .map_voltage = regulator_map_voltage_linear, .get_voltage_sel = regulator_get_voltage_sel_regmap, @@ -69,7 +69,7 @@ static int wm8994_ldo2_list_voltage(struct regulator_dev *rdev, } } -static struct regulator_ops wm8994_ldo2_ops = { +static const struct regulator_ops wm8994_ldo2_ops = { .list_voltage = wm8994_ldo2_list_voltage, .get_voltage_sel = regulator_get_voltage_sel_regmap, .set_voltage_sel = regulator_set_voltage_sel_regmap, diff --git a/drivers/rtc/rtc-opal.c b/drivers/rtc/rtc-opal.c index df39ce02a99d..9c18d6fd8107 100644 --- a/drivers/rtc/rtc-opal.c +++ b/drivers/rtc/rtc-opal.c @@ -40,7 +40,7 @@ static void opal_to_tm(u32 y_m_d, u64 h_m_s_ms, struct rtc_time *tm) tm->tm_min = bcd2bin((h_m_s_ms >> 48) & 0xff); tm->tm_sec = bcd2bin((h_m_s_ms >> 40) & 0xff); - GregorianDay(tm); + tm->tm_wday = -1; } static void tm_to_opal(struct rtc_time *tm, u32 *y_m_d, u64 *h_m_s_ms) diff --git a/drivers/rtc/rtc-s5m.c b/drivers/rtc/rtc-s5m.c index f2504b4eef34..0d68a85dd429 100644 --- a/drivers/rtc/rtc-s5m.c +++ b/drivers/rtc/rtc-s5m.c @@ -188,6 +188,7 @@ static inline int s5m_check_peding_alarm_interrupt(struct s5m_rtc_info *info, ret = regmap_read(info->regmap, S5M_RTC_STATUS, &val); val &= S5M_ALARM0_STATUS; break; + case S2MPS15X: case S2MPS14X: case S2MPS13X: ret = regmap_read(info->s5m87xx->regmap_pmic, S2MPS14_REG_ST2, @@ -219,9 +220,22 @@ static inline int s5m8767_rtc_set_time_reg(struct s5m_rtc_info *info) return ret; } - data |= info->regs->rtc_udr_mask; - if (info->device_type == S5M8763X || info->device_type == S5M8767X) - data |= S5M_RTC_TIME_EN_MASK; + switch (info->device_type) { + case S5M8763X: + case S5M8767X: + data |= info->regs->rtc_udr_mask | S5M_RTC_TIME_EN_MASK; + case S2MPS15X: + /* As per UM, for write time register, set WUDR bit to high */ + data |= S2MPS15_RTC_WUDR_MASK; + break; + case S2MPS14X: + case S2MPS13X: + data |= info->regs->rtc_udr_mask; + break; + default: + return -EINVAL; + } + ret = regmap_write(info->regmap, info->regs->rtc_udr_update, data); if (ret < 0) { @@ -252,6 +266,11 @@ static inline int s5m8767_rtc_set_alarm_reg(struct s5m_rtc_info *info) case S5M8767X: data &= ~S5M_RTC_TIME_EN_MASK; break; + case S2MPS15X: + /* As per UM, for write alarm, set A_UDR(bit[4]) to high + * rtc_udr_mask above sets bit[4] + */ + break; case S2MPS14X: data |= S2MPS_RTC_RUDR_MASK; break; @@ -317,7 +336,8 @@ static int s5m_rtc_read_time(struct device *dev, struct rtc_time *tm) u8 data[info->regs->regs_count]; int ret; - if (info->device_type == S2MPS14X || info->device_type == S2MPS13X) { + if (info->device_type == S2MPS15X || info->device_type == S2MPS14X || + info->device_type == S2MPS13X) { ret = regmap_update_bits(info->regmap, info->regs->rtc_udr_update, S2MPS_RTC_RUDR_MASK, S2MPS_RTC_RUDR_MASK); @@ -339,6 +359,7 @@ static int s5m_rtc_read_time(struct device *dev, struct rtc_time *tm) break; case S5M8767X: + case S2MPS15X: case S2MPS14X: case S2MPS13X: s5m8767_data_to_tm(data, tm, info->rtc_24hr_mode); @@ -366,6 +387,7 @@ static int s5m_rtc_set_time(struct device *dev, struct rtc_time *tm) s5m8763_tm_to_data(tm, data); break; case S5M8767X: + case S2MPS15X: case S2MPS14X: case S2MPS13X: ret = s5m8767_tm_to_data(tm, data); @@ -414,6 +436,7 @@ static int s5m_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm) break; case S5M8767X: + case S2MPS15X: case S2MPS14X: case S2MPS13X: s5m8767_data_to_tm(data, &alrm->time, info->rtc_24hr_mode); @@ -463,6 +486,7 @@ static int s5m_rtc_stop_alarm(struct s5m_rtc_info *info) break; case S5M8767X: + case S2MPS15X: case S2MPS14X: case S2MPS13X: for (i = 0; i < info->regs->regs_count; i++) @@ -508,6 +532,7 @@ static int s5m_rtc_start_alarm(struct s5m_rtc_info *info) break; case S5M8767X: + case S2MPS15X: case S2MPS14X: case S2MPS13X: data[RTC_SEC] |= ALARM_ENABLE_MASK; @@ -548,6 +573,7 @@ static int s5m_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm) break; case S5M8767X: + case S2MPS15X: case S2MPS14X: case S2MPS13X: s5m8767_tm_to_data(&alrm->time, data); @@ -631,6 +657,7 @@ static int s5m8767_rtc_init_reg(struct s5m_rtc_info *info) ret = regmap_raw_write(info->regmap, S5M_ALARM0_CONF, data, 2); break; + case S2MPS15X: case S2MPS14X: case S2MPS13X: data[0] = (0 << BCD_EN_SHIFT) | (1 << MODEL24_SHIFT); @@ -679,6 +706,7 @@ static int s5m_rtc_probe(struct platform_device *pdev) return -ENOMEM; switch (platform_get_device_id(pdev)->driver_data) { + case S2MPS15X: case S2MPS14X: case S2MPS13X: regmap_cfg = &s2mps14_rtc_regmap_config; @@ -805,6 +833,7 @@ static const struct platform_device_id s5m_rtc_id[] = { { "s5m-rtc", S5M8767X }, { "s2mps13-rtc", S2MPS13X }, { "s2mps14-rtc", S2MPS14X }, + { "s2mps15-rtc", S2MPS15X }, { }, }; MODULE_DEVICE_TABLE(platform, s5m_rtc_id); diff --git a/drivers/soc/Kconfig b/drivers/soc/Kconfig index 4e853ed2c82b..ad0df75fab6e 100644 --- a/drivers/soc/Kconfig +++ b/drivers/soc/Kconfig @@ -1,6 +1,7 @@ menu "SOC (System On Chip) specific Drivers" source "drivers/soc/brcmstb/Kconfig" +source "drivers/soc/fsl/qe/Kconfig" source "drivers/soc/mediatek/Kconfig" source "drivers/soc/qcom/Kconfig" source "drivers/soc/rockchip/Kconfig" diff --git a/drivers/soc/Makefile b/drivers/soc/Makefile index f2ba2e932ae1..9536b804424a 100644 --- a/drivers/soc/Makefile +++ b/drivers/soc/Makefile @@ -4,6 +4,7 @@ obj-$(CONFIG_SOC_BRCMSTB) += brcmstb/ obj-$(CONFIG_MACH_DOVE) += dove/ +obj-y += fsl/ obj-$(CONFIG_ARCH_MEDIATEK) += mediatek/ obj-$(CONFIG_ARCH_QCOM) += qcom/ obj-$(CONFIG_ARCH_ROCKCHIP) += rockchip/ diff --git a/drivers/soc/fsl/Makefile b/drivers/soc/fsl/Makefile new file mode 100644 index 000000000000..203307fd92c1 --- /dev/null +++ b/drivers/soc/fsl/Makefile @@ -0,0 +1,6 @@ +# +# Makefile for the Linux Kernel SOC fsl specific device drivers +# + +obj-$(CONFIG_QUICC_ENGINE) += qe/ +obj-$(CONFIG_CPM) += qe/ diff --git a/arch/powerpc/sysdev/qe_lib/Kconfig b/drivers/soc/fsl/qe/Kconfig index 3c251993bacd..20978f2058a6 100644 --- a/arch/powerpc/sysdev/qe_lib/Kconfig +++ b/drivers/soc/fsl/qe/Kconfig @@ -2,6 +2,17 @@ # QE Communication options # +config QUICC_ENGINE + bool "Freescale QUICC Engine (QE) Support" + depends on FSL_SOC && PPC32 + select GENERIC_ALLOCATOR + select CRC32 + help + The QUICC Engine (QE) is a new generation of communications + coprocessors on Freescale embedded CPUs (akin to CPM in older chips). + Selecting this option means that you wish to build a kernel + for a machine with a QE coprocessor. + config UCC_SLOW bool default y if SERIAL_QE diff --git a/arch/powerpc/sysdev/qe_lib/Makefile b/drivers/soc/fsl/qe/Makefile index f1855c185291..ffac5410c5c7 100644 --- a/arch/powerpc/sysdev/qe_lib/Makefile +++ b/drivers/soc/fsl/qe/Makefile @@ -1,8 +1,8 @@ # # Makefile for the linux ppc-specific parts of QE # -obj-$(CONFIG_QUICC_ENGINE)+= qe.o qe_ic.o qe_io.o - +obj-$(CONFIG_QUICC_ENGINE)+= qe.o qe_common.o qe_ic.o qe_io.o +obj-$(CONFIG_CPM) += qe_common.o obj-$(CONFIG_UCC) += ucc.o obj-$(CONFIG_UCC_SLOW) += ucc_slow.o obj-$(CONFIG_UCC_FAST) += ucc_fast.o diff --git a/arch/powerpc/sysdev/qe_lib/gpio.c b/drivers/soc/fsl/qe/gpio.c index 521e67a49dc4..aa5c11acf212 100644 --- a/arch/powerpc/sysdev/qe_lib/gpio.c +++ b/drivers/soc/fsl/qe/gpio.c @@ -21,7 +21,7 @@ #include <linux/gpio.h> #include <linux/slab.h> #include <linux/export.h> -#include <asm/qe.h> +#include <soc/fsl/qe/qe.h> struct qe_gpio_chip { struct of_mm_gpio_chip mm_gc; diff --git a/arch/powerpc/sysdev/qe_lib/qe.c b/drivers/soc/fsl/qe/qe.c index c2518cdb7ddb..709fc63809e5 100644 --- a/arch/powerpc/sysdev/qe_lib/qe.c +++ b/drivers/soc/fsl/qe/qe.c @@ -31,8 +31,8 @@ #include <asm/irq.h> #include <asm/page.h> #include <asm/pgtable.h> -#include <asm/immap_qe.h> -#include <asm/qe.h> +#include <soc/fsl/qe/immap_qe.h> +#include <soc/fsl/qe/qe.h> #include <asm/prom.h> #include <asm/rheap.h> @@ -671,6 +671,19 @@ unsigned int qe_get_num_of_snums(void) } EXPORT_SYMBOL(qe_get_num_of_snums); +static int __init qe_init(void) +{ + struct device_node *np; + + np = of_find_compatible_node(NULL, NULL, "fsl,qe"); + if (!np) + return -ENODEV; + qe_reset(); + of_node_put(np); + return 0; +} +subsys_initcall(qe_init); + #if defined(CONFIG_SUSPEND) && defined(CONFIG_PPC_85xx) static int qe_resume(struct platform_device *ofdev) { diff --git a/drivers/soc/fsl/qe/qe_common.c b/drivers/soc/fsl/qe/qe_common.c new file mode 100644 index 000000000000..419fa5b7be4d --- /dev/null +++ b/drivers/soc/fsl/qe/qe_common.c @@ -0,0 +1,235 @@ +/* + * Common CPM code + * + * Author: Scott Wood <scottwood@freescale.com> + * + * Copyright 2007-2008,2010 Freescale Semiconductor, Inc. + * + * Some parts derived from commproc.c/cpm2_common.c, which is: + * Copyright (c) 1997 Dan error_act (dmalek@jlc.net) + * Copyright (c) 1999-2001 Dan Malek <dan@embeddedalley.com> + * Copyright (c) 2000 MontaVista Software, Inc (source@mvista.com) + * 2006 (c) MontaVista Software, Inc. + * Vitaly Bordug <vbordug@ru.mvista.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + */ +#include <linux/genalloc.h> +#include <linux/init.h> +#include <linux/list.h> +#include <linux/of_device.h> +#include <linux/spinlock.h> +#include <linux/export.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/slab.h> +#include <linux/io.h> +#include <soc/fsl/qe/qe.h> + +static struct gen_pool *muram_pool; +static spinlock_t cpm_muram_lock; +static u8 __iomem *muram_vbase; +static phys_addr_t muram_pbase; + +struct muram_block { + struct list_head head; + unsigned long start; + int size; +}; + +static LIST_HEAD(muram_block_list); + +/* max address size we deal with */ +#define OF_MAX_ADDR_CELLS 4 +#define GENPOOL_OFFSET (4096 * 8) + +int cpm_muram_init(void) +{ + struct device_node *np; + struct resource r; + u32 zero[OF_MAX_ADDR_CELLS] = {}; + resource_size_t max = 0; + int i = 0; + int ret = 0; + + if (muram_pbase) + return 0; + + spin_lock_init(&cpm_muram_lock); + np = of_find_compatible_node(NULL, NULL, "fsl,cpm-muram-data"); + if (!np) { + /* try legacy bindings */ + np = of_find_node_by_name(NULL, "data-only"); + if (!np) { + pr_err("Cannot find CPM muram data node"); + ret = -ENODEV; + goto out_muram; + } + } + + muram_pool = gen_pool_create(0, -1); + muram_pbase = of_translate_address(np, zero); + if (muram_pbase == (phys_addr_t)OF_BAD_ADDR) { + pr_err("Cannot translate zero through CPM muram node"); + ret = -ENODEV; + goto out_pool; + } + + while (of_address_to_resource(np, i++, &r) == 0) { + if (r.end > max) + max = r.end; + ret = gen_pool_add(muram_pool, r.start - muram_pbase + + GENPOOL_OFFSET, resource_size(&r), -1); + if (ret) { + pr_err("QE: couldn't add muram to pool!\n"); + goto out_pool; + } + } + + muram_vbase = ioremap(muram_pbase, max - muram_pbase + 1); + if (!muram_vbase) { + pr_err("Cannot map QE muram"); + ret = -ENOMEM; + goto out_pool; + } + goto out_muram; +out_pool: + gen_pool_destroy(muram_pool); +out_muram: + of_node_put(np); + return ret; +} + +/* + * cpm_muram_alloc - allocate the requested size worth of multi-user ram + * @size: number of bytes to allocate + * @align: requested alignment, in bytes + * + * This function returns an offset into the muram area. + * Use cpm_dpram_addr() to get the virtual address of the area. + * Use cpm_muram_free() to free the allocation. + */ +unsigned long cpm_muram_alloc(unsigned long size, unsigned long align) +{ + unsigned long start; + unsigned long flags; + struct genpool_data_align muram_pool_data; + + spin_lock_irqsave(&cpm_muram_lock, flags); + muram_pool_data.align = align; + start = cpm_muram_alloc_common(size, gen_pool_first_fit_align, + &muram_pool_data); + spin_unlock_irqrestore(&cpm_muram_lock, flags); + return start; +} +EXPORT_SYMBOL(cpm_muram_alloc); + +/** + * cpm_muram_free - free a chunk of multi-user ram + * @offset: The beginning of the chunk as returned by cpm_muram_alloc(). + */ +int cpm_muram_free(unsigned long offset) +{ + unsigned long flags; + int size; + struct muram_block *tmp; + + size = 0; + spin_lock_irqsave(&cpm_muram_lock, flags); + list_for_each_entry(tmp, &muram_block_list, head) { + if (tmp->start == offset) { + size = tmp->size; + list_del(&tmp->head); + kfree(tmp); + break; + } + } + gen_pool_free(muram_pool, offset + GENPOOL_OFFSET, size); + spin_unlock_irqrestore(&cpm_muram_lock, flags); + return size; +} +EXPORT_SYMBOL(cpm_muram_free); + +/* + * cpm_muram_alloc_fixed - reserve a specific region of multi-user ram + * @offset: offset of allocation start address + * @size: number of bytes to allocate + * This function returns an offset into the muram area + * Use cpm_dpram_addr() to get the virtual address of the area. + * Use cpm_muram_free() to free the allocation. + */ +unsigned long cpm_muram_alloc_fixed(unsigned long offset, unsigned long size) +{ + unsigned long start; + unsigned long flags; + struct genpool_data_fixed muram_pool_data_fixed; + + spin_lock_irqsave(&cpm_muram_lock, flags); + muram_pool_data_fixed.offset = offset + GENPOOL_OFFSET; + start = cpm_muram_alloc_common(size, gen_pool_fixed_alloc, + &muram_pool_data_fixed); + spin_unlock_irqrestore(&cpm_muram_lock, flags); + return start; +} +EXPORT_SYMBOL(cpm_muram_alloc_fixed); + +/* + * cpm_muram_alloc_common - cpm_muram_alloc common code + * @size: number of bytes to allocate + * @algo: algorithm for alloc. + * @data: data for genalloc's algorithm. + * + * This function returns an offset into the muram area. + */ +unsigned long cpm_muram_alloc_common(unsigned long size, genpool_algo_t algo, + void *data) +{ + struct muram_block *entry; + unsigned long start; + + start = gen_pool_alloc_algo(muram_pool, size, algo, data); + if (!start) + goto out2; + start = start - GENPOOL_OFFSET; + memset_io(cpm_muram_addr(start), 0, size); + entry = kmalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) + goto out1; + entry->start = start; + entry->size = size; + list_add(&entry->head, &muram_block_list); + + return start; +out1: + gen_pool_free(muram_pool, start, size); +out2: + return (unsigned long)-ENOMEM; +} + +/** + * cpm_muram_addr - turn a muram offset into a virtual address + * @offset: muram offset to convert + */ +void __iomem *cpm_muram_addr(unsigned long offset) +{ + return muram_vbase + offset; +} +EXPORT_SYMBOL(cpm_muram_addr); + +unsigned long cpm_muram_offset(void __iomem *addr) +{ + return addr - (void __iomem *)muram_vbase; +} +EXPORT_SYMBOL(cpm_muram_offset); + +/** + * cpm_muram_dma - turn a muram virtual address into a DMA address + * @offset: virtual address from cpm_muram_addr() to convert + */ +dma_addr_t cpm_muram_dma(void __iomem *addr) +{ + return muram_pbase + ((u8 __iomem *)addr - muram_vbase); +} +EXPORT_SYMBOL(cpm_muram_dma); diff --git a/arch/powerpc/sysdev/qe_lib/qe_ic.c b/drivers/soc/fsl/qe/qe_ic.c index ef36f16f9f6f..b77d01ff8330 100644 --- a/arch/powerpc/sysdev/qe_lib/qe_ic.c +++ b/drivers/soc/fsl/qe/qe_ic.c @@ -14,6 +14,8 @@ * option) any later version. */ +#include <linux/of_irq.h> +#include <linux/of_address.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/errno.h> @@ -26,8 +28,7 @@ #include <linux/spinlock.h> #include <asm/irq.h> #include <asm/io.h> -#include <asm/prom.h> -#include <asm/qe_ic.h> +#include <soc/fsl/qe/qe_ic.h> #include "qe_ic.h" diff --git a/arch/powerpc/sysdev/qe_lib/qe_ic.h b/drivers/soc/fsl/qe/qe_ic.h index efef7ab9b753..926a2ed42319 100644 --- a/arch/powerpc/sysdev/qe_lib/qe_ic.h +++ b/drivers/soc/fsl/qe/qe_ic.h @@ -1,5 +1,5 @@ /* - * arch/powerpc/sysdev/qe_lib/qe_ic.h + * drivers/soc/fsl/qe/qe_ic.h * * QUICC ENGINE Interrupt Controller Header * @@ -16,7 +16,7 @@ #ifndef _POWERPC_SYSDEV_QE_IC_H #define _POWERPC_SYSDEV_QE_IC_H -#include <asm/qe_ic.h> +#include <soc/fsl/qe/qe_ic.h> #define NR_QE_IC_INTS 64 diff --git a/arch/powerpc/sysdev/qe_lib/qe_io.c b/drivers/soc/fsl/qe/qe_io.c index 7ea0174f6d3d..7ae59abc7863 100644 --- a/arch/powerpc/sysdev/qe_lib/qe_io.c +++ b/drivers/soc/fsl/qe/qe_io.c @@ -21,7 +21,7 @@ #include <linux/ioport.h> #include <asm/io.h> -#include <asm/qe.h> +#include <soc/fsl/qe/qe.h> #include <asm/prom.h> #include <sysdev/fsl_soc.h> diff --git a/arch/powerpc/sysdev/qe_lib/ucc.c b/drivers/soc/fsl/qe/ucc.c index 621575b7e84a..b59d3358f9bd 100644 --- a/arch/powerpc/sysdev/qe_lib/ucc.c +++ b/drivers/soc/fsl/qe/ucc.c @@ -21,9 +21,9 @@ #include <asm/irq.h> #include <asm/io.h> -#include <asm/immap_qe.h> -#include <asm/qe.h> -#include <asm/ucc.h> +#include <soc/fsl/qe/immap_qe.h> +#include <soc/fsl/qe/qe.h> +#include <soc/fsl/qe/ucc.h> int ucc_set_qe_mux_mii_mng(unsigned int ucc_num) { diff --git a/arch/powerpc/sysdev/qe_lib/ucc_fast.c b/drivers/soc/fsl/qe/ucc_fast.c index 65aaf15032ae..a7689310fe40 100644 --- a/arch/powerpc/sysdev/qe_lib/ucc_fast.c +++ b/drivers/soc/fsl/qe/ucc_fast.c @@ -21,11 +21,11 @@ #include <linux/export.h> #include <asm/io.h> -#include <asm/immap_qe.h> -#include <asm/qe.h> +#include <soc/fsl/qe/immap_qe.h> +#include <soc/fsl/qe/qe.h> -#include <asm/ucc.h> -#include <asm/ucc_fast.h> +#include <soc/fsl/qe/ucc.h> +#include <soc/fsl/qe/ucc_fast.h> void ucc_fast_dump_regs(struct ucc_fast_private * uccf) { diff --git a/arch/powerpc/sysdev/qe_lib/ucc_slow.c b/drivers/soc/fsl/qe/ucc_slow.c index 5f91628209eb..9334bdbd9b30 100644 --- a/arch/powerpc/sysdev/qe_lib/ucc_slow.c +++ b/drivers/soc/fsl/qe/ucc_slow.c @@ -21,11 +21,11 @@ #include <linux/export.h> #include <asm/io.h> -#include <asm/immap_qe.h> -#include <asm/qe.h> +#include <soc/fsl/qe/immap_qe.h> +#include <soc/fsl/qe/qe.h> -#include <asm/ucc.h> -#include <asm/ucc_slow.h> +#include <soc/fsl/qe/ucc.h> +#include <soc/fsl/qe/ucc_slow.h> u32 ucc_slow_get_qe_cr_subblock(int uccs_num) { diff --git a/arch/powerpc/sysdev/qe_lib/usb.c b/drivers/soc/fsl/qe/usb.c index 27f23bd15eb6..111f7ab80f04 100644 --- a/arch/powerpc/sysdev/qe_lib/usb.c +++ b/drivers/soc/fsl/qe/usb.c @@ -17,8 +17,8 @@ #include <linux/errno.h> #include <linux/export.h> #include <linux/io.h> -#include <asm/immap_qe.h> -#include <asm/qe.h> +#include <soc/fsl/qe/immap_qe.h> +#include <soc/fsl/qe/qe.h> int qe_usb_clock_set(enum qe_clock clk, int rate) { diff --git a/drivers/soc/ti/knav_dma.c b/drivers/soc/ti/knav_dma.c index bc1b80ec6afe..1a7b5caa127b 100644 --- a/drivers/soc/ti/knav_dma.c +++ b/drivers/soc/ti/knav_dma.c @@ -389,7 +389,7 @@ static int of_channel_match_helper(struct device_node *np, const char *name, *dma_instance = dma_node->name; index = of_property_match_string(np, "ti,navigator-dma-names", name); if (index < 0) { - dev_err(kdev->dev, "No 'ti,navigator-dma-names' propery\n"); + dev_err(kdev->dev, "No 'ti,navigator-dma-names' property\n"); return -ENODEV; } diff --git a/drivers/spi/spi-fsl-cpm.c b/drivers/spi/spi-fsl-cpm.c index 896add8cfd3b..8f7b26ec181e 100644 --- a/drivers/spi/spi-fsl-cpm.c +++ b/drivers/spi/spi-fsl-cpm.c @@ -16,7 +16,7 @@ * option) any later version. */ #include <asm/cpm.h> -#include <asm/qe.h> +#include <soc/fsl/qe/qe.h> #include <linux/dma-mapping.h> #include <linux/fsl_devices.h> #include <linux/kernel.h> diff --git a/drivers/staging/lustre/lustre/llite/super25.c b/drivers/staging/lustre/lustre/llite/super25.c index 7a9fafc67693..86c371ef71ea 100644 --- a/drivers/staging/lustre/lustre/llite/super25.c +++ b/drivers/staging/lustre/lustre/llite/super25.c @@ -106,7 +106,8 @@ static int __init init_lustre_lite(void) rc = -ENOMEM; ll_inode_cachep = kmem_cache_create("lustre_inode_cache", sizeof(struct ll_inode_info), - 0, SLAB_HWCACHE_ALIGN, NULL); + 0, SLAB_HWCACHE_ALIGN|SLAB_ACCOUNT, + NULL); if (ll_inode_cachep == NULL) goto out_cache; diff --git a/drivers/tty/serial/ucc_uart.c b/drivers/tty/serial/ucc_uart.c index 73190f5d2832..1a7dc3c590b1 100644 --- a/drivers/tty/serial/ucc_uart.c +++ b/drivers/tty/serial/ucc_uart.c @@ -31,7 +31,7 @@ #include <linux/dma-mapping.h> #include <linux/fs_uart_pd.h> -#include <asm/ucc_slow.h> +#include <soc/fsl/qe/ucc_slow.h> #include <linux/firmware.h> #include <asm/reg.h> diff --git a/drivers/usb/gadget/udc/fsl_qe_udc.c b/drivers/usb/gadget/udc/fsl_qe_udc.c index 5fb6f8b4f0b4..53c0692f1b09 100644 --- a/drivers/usb/gadget/udc/fsl_qe_udc.c +++ b/drivers/usb/gadget/udc/fsl_qe_udc.c @@ -38,7 +38,7 @@ #include <linux/usb/ch9.h> #include <linux/usb/gadget.h> #include <linux/usb/otg.h> -#include <asm/qe.h> +#include <soc/fsl/qe/qe.h> #include <asm/cpm.h> #include <asm/dma.h> #include <asm/reg.h> diff --git a/drivers/usb/host/fhci-hcd.c b/drivers/usb/host/fhci-hcd.c index c6cebb96fd21..0960f41f945a 100644 --- a/drivers/usb/host/fhci-hcd.c +++ b/drivers/usb/host/fhci-hcd.c @@ -31,7 +31,7 @@ #include <linux/of_platform.h> #include <linux/of_gpio.h> #include <linux/slab.h> -#include <asm/qe.h> +#include <soc/fsl/qe/qe.h> #include <asm/fsl_gtm.h> #include "fhci.h" diff --git a/drivers/usb/host/fhci-hub.c b/drivers/usb/host/fhci-hub.c index 3bacdd7befe9..60d55eb3de0d 100644 --- a/drivers/usb/host/fhci-hub.c +++ b/drivers/usb/host/fhci-hub.c @@ -24,7 +24,7 @@ #include <linux/usb.h> #include <linux/usb/hcd.h> #include <linux/gpio.h> -#include <asm/qe.h> +#include <soc/fsl/qe/qe.h> #include "fhci.h" /* virtual root hub specific descriptor */ diff --git a/drivers/usb/host/fhci-sched.c b/drivers/usb/host/fhci-sched.c index 95ca5986e672..a9609a336efe 100644 --- a/drivers/usb/host/fhci-sched.c +++ b/drivers/usb/host/fhci-sched.c @@ -25,7 +25,7 @@ #include <linux/io.h> #include <linux/usb.h> #include <linux/usb/hcd.h> -#include <asm/qe.h> +#include <soc/fsl/qe/qe.h> #include <asm/fsl_gtm.h> #include "fhci.h" diff --git a/drivers/usb/host/fhci.h b/drivers/usb/host/fhci.h index 154e6a007727..3fc82c1c3c73 100644 --- a/drivers/usb/host/fhci.h +++ b/drivers/usb/host/fhci.h @@ -27,8 +27,8 @@ #include <linux/io.h> #include <linux/usb.h> #include <linux/usb/hcd.h> -#include <asm/qe.h> -#include <asm/immap_qe.h> +#include <soc/fsl/qe/qe.h> +#include <soc/fsl/qe/immap_qe.h> #define USB_CLOCK 48000000 diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig index 850d86ca685b..da6e2ce77495 100644 --- a/drivers/vfio/Kconfig +++ b/drivers/vfio/Kconfig @@ -31,6 +31,21 @@ menuconfig VFIO If you don't know what to do here, say N. +menuconfig VFIO_NOIOMMU + bool "VFIO No-IOMMU support" + depends on VFIO + help + VFIO is built on the ability to isolate devices using the IOMMU. + Only with an IOMMU can userspace access to DMA capable devices be + considered secure. VFIO No-IOMMU mode enables IOMMU groups for + devices without IOMMU backing for the purpose of re-using the VFIO + infrastructure in a non-secure mode. Use of this mode will result + in an unsupportable kernel and will therefore taint the kernel. + Device assignment to virtual machines is also not possible with + this mode since there is no IOMMU to provide DMA translation. + + If you don't know what to do here, say N. + source "drivers/vfio/pci/Kconfig" source "drivers/vfio/platform/Kconfig" source "virt/lib/Kconfig" diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 56bf6dbb93db..2760a7ba3f30 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -940,13 +940,13 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (pdev->hdr_type != PCI_HEADER_TYPE_NORMAL) return -EINVAL; - group = iommu_group_get(&pdev->dev); + group = vfio_iommu_group_get(&pdev->dev); if (!group) return -EINVAL; vdev = kzalloc(sizeof(*vdev), GFP_KERNEL); if (!vdev) { - iommu_group_put(group); + vfio_iommu_group_put(group, &pdev->dev); return -ENOMEM; } @@ -957,7 +957,7 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) ret = vfio_add_group_dev(&pdev->dev, &vfio_pci_ops, vdev); if (ret) { - iommu_group_put(group); + vfio_iommu_group_put(group, &pdev->dev); kfree(vdev); return ret; } @@ -993,7 +993,7 @@ static void vfio_pci_remove(struct pci_dev *pdev) if (!vdev) return; - iommu_group_put(pdev->dev.iommu_group); + vfio_iommu_group_put(pdev->dev.iommu_group, &pdev->dev); kfree(vdev); if (vfio_pci_is_vga(pdev)) { diff --git a/drivers/vfio/platform/reset/vfio_platform_amdxgbe.c b/drivers/vfio/platform/reset/vfio_platform_amdxgbe.c index da5356f48d0b..d4030d0c38e9 100644 --- a/drivers/vfio/platform/reset/vfio_platform_amdxgbe.c +++ b/drivers/vfio/platform/reset/vfio_platform_amdxgbe.c @@ -110,7 +110,7 @@ int vfio_platform_amdxgbe_reset(struct vfio_platform_device *vdev) usleep_range(10, 15); count = 2000; - while (count-- && (ioread32(xgmac_regs->ioaddr + DMA_MR) & 1)) + while (--count && (ioread32(xgmac_regs->ioaddr + DMA_MR) & 1)) usleep_range(500, 600); if (!count) diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 6070b793cbcb..82f25cc1c460 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -62,6 +62,7 @@ struct vfio_container { struct rw_semaphore group_lock; struct vfio_iommu_driver *iommu_driver; void *iommu_data; + bool noiommu; }; struct vfio_unbound_dev { @@ -84,6 +85,7 @@ struct vfio_group { struct list_head unbound_list; struct mutex unbound_lock; atomic_t opened; + bool noiommu; }; struct vfio_device { @@ -95,6 +97,128 @@ struct vfio_device { void *device_data; }; +#ifdef CONFIG_VFIO_NOIOMMU +static bool noiommu __read_mostly; +module_param_named(enable_unsafe_noiommu_mode, + noiommu, bool, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(enable_unsafe_noiommu_mode, "Enable UNSAFE, no-IOMMU mode. This mode provides no device isolation, no DMA translation, no host kernel protection, cannot be used for device assignment to virtual machines, requires RAWIO permissions, and will taint the kernel. If you do not know what this is for, step away. (default: false)"); +#endif + +/* + * vfio_iommu_group_{get,put} are only intended for VFIO bus driver probe + * and remove functions, any use cases other than acquiring the first + * reference for the purpose of calling vfio_add_group_dev() or removing + * that symmetric reference after vfio_del_group_dev() should use the raw + * iommu_group_{get,put} functions. In particular, vfio_iommu_group_put() + * removes the device from the dummy group and cannot be nested. + */ +struct iommu_group *vfio_iommu_group_get(struct device *dev) +{ + struct iommu_group *group; + int __maybe_unused ret; + + group = iommu_group_get(dev); + +#ifdef CONFIG_VFIO_NOIOMMU + /* + * With noiommu enabled, an IOMMU group will be created for a device + * that doesn't already have one and doesn't have an iommu_ops on their + * bus. We use iommu_present() again in the main code to detect these + * fake groups. + */ + if (group || !noiommu || iommu_present(dev->bus)) + return group; + + group = iommu_group_alloc(); + if (IS_ERR(group)) + return NULL; + + iommu_group_set_name(group, "vfio-noiommu"); + ret = iommu_group_add_device(group, dev); + iommu_group_put(group); + if (ret) + return NULL; + + /* + * Where to taint? At this point we've added an IOMMU group for a + * device that is not backed by iommu_ops, therefore any iommu_ + * callback using iommu_ops can legitimately Oops. So, while we may + * be about to give a DMA capable device to a user without IOMMU + * protection, which is clearly taint-worthy, let's go ahead and do + * it here. + */ + add_taint(TAINT_USER, LOCKDEP_STILL_OK); + dev_warn(dev, "Adding kernel taint for vfio-noiommu group on device\n"); +#endif + + return group; +} +EXPORT_SYMBOL_GPL(vfio_iommu_group_get); + +void vfio_iommu_group_put(struct iommu_group *group, struct device *dev) +{ +#ifdef CONFIG_VFIO_NOIOMMU + if (!iommu_present(dev->bus)) + iommu_group_remove_device(dev); +#endif + + iommu_group_put(group); +} +EXPORT_SYMBOL_GPL(vfio_iommu_group_put); + +#ifdef CONFIG_VFIO_NOIOMMU +static void *vfio_noiommu_open(unsigned long arg) +{ + if (arg != VFIO_NOIOMMU_IOMMU) + return ERR_PTR(-EINVAL); + if (!capable(CAP_SYS_RAWIO)) + return ERR_PTR(-EPERM); + + return NULL; +} + +static void vfio_noiommu_release(void *iommu_data) +{ +} + +static long vfio_noiommu_ioctl(void *iommu_data, + unsigned int cmd, unsigned long arg) +{ + if (cmd == VFIO_CHECK_EXTENSION) + return noiommu && (arg == VFIO_NOIOMMU_IOMMU) ? 1 : 0; + + return -ENOTTY; +} + +static int vfio_iommu_present(struct device *dev, void *unused) +{ + return iommu_present(dev->bus) ? 1 : 0; +} + +static int vfio_noiommu_attach_group(void *iommu_data, + struct iommu_group *iommu_group) +{ + return iommu_group_for_each_dev(iommu_group, NULL, + vfio_iommu_present) ? -EINVAL : 0; +} + +static void vfio_noiommu_detach_group(void *iommu_data, + struct iommu_group *iommu_group) +{ +} + +static const struct vfio_iommu_driver_ops vfio_noiommu_ops = { + .name = "vfio-noiommu", + .owner = THIS_MODULE, + .open = vfio_noiommu_open, + .release = vfio_noiommu_release, + .ioctl = vfio_noiommu_ioctl, + .attach_group = vfio_noiommu_attach_group, + .detach_group = vfio_noiommu_detach_group, +}; +#endif + + /** * IOMMU driver registration */ @@ -199,7 +323,8 @@ static void vfio_group_unlock_and_free(struct vfio_group *group) /** * Group objects - create, release, get, put, search */ -static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group) +static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group, + bool iommu_present) { struct vfio_group *group, *tmp; struct device *dev; @@ -217,6 +342,7 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group) atomic_set(&group->container_users, 0); atomic_set(&group->opened, 0); group->iommu_group = iommu_group; + group->noiommu = !iommu_present; group->nb.notifier_call = vfio_iommu_group_notifier; @@ -252,7 +378,8 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group) dev = device_create(vfio.class, NULL, MKDEV(MAJOR(vfio.group_devt), minor), - group, "%d", iommu_group_id(iommu_group)); + group, "%s%d", group->noiommu ? "noiommu-" : "", + iommu_group_id(iommu_group)); if (IS_ERR(dev)) { vfio_free_group_minor(minor); vfio_group_unlock_and_free(group); @@ -640,7 +767,7 @@ int vfio_add_group_dev(struct device *dev, group = vfio_group_get_from_iommu(iommu_group); if (!group) { - group = vfio_create_group(iommu_group); + group = vfio_create_group(iommu_group, iommu_present(dev->bus)); if (IS_ERR(group)) { iommu_group_put(iommu_group); return PTR_ERR(group); @@ -854,6 +981,14 @@ static long vfio_ioctl_check_extension(struct vfio_container *container, mutex_lock(&vfio.iommu_drivers_lock); list_for_each_entry(driver, &vfio.iommu_drivers_list, vfio_next) { + +#ifdef CONFIG_VFIO_NOIOMMU + if (!list_empty(&container->group_list) && + (container->noiommu != + (driver->ops == &vfio_noiommu_ops))) + continue; +#endif + if (!try_module_get(driver->ops->owner)) continue; @@ -925,6 +1060,15 @@ static long vfio_ioctl_set_iommu(struct vfio_container *container, list_for_each_entry(driver, &vfio.iommu_drivers_list, vfio_next) { void *data; +#ifdef CONFIG_VFIO_NOIOMMU + /* + * Only noiommu containers can use vfio-noiommu and noiommu + * containers can only use vfio-noiommu. + */ + if (container->noiommu != (driver->ops == &vfio_noiommu_ops)) + continue; +#endif + if (!try_module_get(driver->ops->owner)) continue; @@ -1187,6 +1331,9 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd) if (atomic_read(&group->container_users)) return -EINVAL; + if (group->noiommu && !capable(CAP_SYS_RAWIO)) + return -EPERM; + f = fdget(container_fd); if (!f.file) return -EBADF; @@ -1202,6 +1349,13 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd) down_write(&container->group_lock); + /* Real groups and fake groups cannot mix */ + if (!list_empty(&container->group_list) && + container->noiommu != group->noiommu) { + ret = -EPERM; + goto unlock_out; + } + driver = container->iommu_driver; if (driver) { ret = driver->ops->attach_group(container->iommu_data, @@ -1211,6 +1365,7 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd) } group->container = container; + container->noiommu = group->noiommu; list_add(&group->container_next, &container->group_list); /* Get a reference on the container and mark a user within the group */ @@ -1241,6 +1396,9 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf) !group->container->iommu_driver || !vfio_group_viable(group)) return -EINVAL; + if (group->noiommu && !capable(CAP_SYS_RAWIO)) + return -EPERM; + device = vfio_device_get_from_name(group, buf); if (!device) return -ENODEV; @@ -1283,6 +1441,10 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf) fd_install(ret, filep); + if (group->noiommu) + dev_warn(device->dev, "vfio-noiommu device opened by user " + "(%s:%d)\n", current->comm, task_pid_nr(current)); + return ret; } @@ -1371,6 +1533,11 @@ static int vfio_group_fops_open(struct inode *inode, struct file *filep) if (!group) return -ENODEV; + if (group->noiommu && !capable(CAP_SYS_RAWIO)) { + vfio_group_put(group); + return -EPERM; + } + /* Do we need multiple instances of the group open? Seems not. */ opened = atomic_cmpxchg(&group->opened, 0, 1); if (opened) { @@ -1533,6 +1700,11 @@ struct vfio_group *vfio_group_get_external_user(struct file *filep) if (!atomic_inc_not_zero(&group->container_users)) return ERR_PTR(-EINVAL); + if (group->noiommu) { + atomic_dec(&group->container_users); + return ERR_PTR(-EPERM); + } + if (!group->container->iommu_driver || !vfio_group_viable(group)) { atomic_dec(&group->container_users); @@ -1625,6 +1797,9 @@ static int __init vfio_init(void) request_module_nowait("vfio_iommu_type1"); request_module_nowait("vfio_iommu_spapr_tce"); +#ifdef CONFIG_VFIO_NOIOMMU + vfio_register_iommu_driver(&vfio_noiommu_ops); +#endif return 0; err_cdev_add: @@ -1641,6 +1816,9 @@ static void __exit vfio_cleanup(void) { WARN_ON(!list_empty(&vfio.group_list)); +#ifdef CONFIG_VFIO_NOIOMMU + vfio_unregister_iommu_driver(&vfio_noiommu_ops); +#endif idr_destroy(&vfio.group_idr); cdev_del(&vfio.group_cdev); unregister_chrdev_region(vfio.group_devt, MINORMASK); diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 59d47cb638d5..6f1ea3dddbad 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -995,7 +995,7 @@ static long vfio_iommu_type1_ioctl(void *iommu_data, if (info.argsz < minsz) return -EINVAL; - info.flags = 0; + info.flags = VFIO_IOMMU_INFO_PGSIZES; info.iova_pgsizes = vfio_pgsize_bitmap(iommu); diff --git a/drivers/video/backlight/adp8860_bl.c b/drivers/video/backlight/adp8860_bl.c index 98ffe71e8af2..510e559c060e 100644 --- a/drivers/video/backlight/adp8860_bl.c +++ b/drivers/video/backlight/adp8860_bl.c @@ -566,11 +566,13 @@ static ssize_t adp8860_bl_ambient_light_level_show(struct device *dev, mutex_lock(&data->lock); error = adp8860_read(data->client, ADP8860_PH1LEVL, ®_val); - ret_val = reg_val; - error |= adp8860_read(data->client, ADP8860_PH1LEVH, ®_val); + if (!error) { + ret_val = reg_val; + error = adp8860_read(data->client, ADP8860_PH1LEVH, ®_val); + } mutex_unlock(&data->lock); - if (error < 0) + if (error) return error; /* Return 13-bit conversion value for the first light sensor */ @@ -621,10 +623,12 @@ static ssize_t adp8860_bl_ambient_light_zone_store(struct device *dev, /* Set user supplied ambient light zone */ mutex_lock(&data->lock); - adp8860_read(data->client, ADP8860_CFGR, ®_val); - reg_val &= ~(CFGR_BLV_MASK << CFGR_BLV_SHIFT); - reg_val |= (val - 1) << CFGR_BLV_SHIFT; - adp8860_write(data->client, ADP8860_CFGR, reg_val); + ret = adp8860_read(data->client, ADP8860_CFGR, ®_val); + if (!ret) { + reg_val &= ~(CFGR_BLV_MASK << CFGR_BLV_SHIFT); + reg_val |= (val - 1) << CFGR_BLV_SHIFT; + adp8860_write(data->client, ADP8860_CFGR, reg_val); + } mutex_unlock(&data->lock); } diff --git a/drivers/video/backlight/adp8870_bl.c b/drivers/video/backlight/adp8870_bl.c index 9d738352d7d4..21acac90fd77 100644 --- a/drivers/video/backlight/adp8870_bl.c +++ b/drivers/video/backlight/adp8870_bl.c @@ -807,10 +807,12 @@ static ssize_t adp8870_bl_ambient_light_zone_store(struct device *dev, /* Set user supplied ambient light zone */ mutex_lock(&data->lock); - adp8870_read(data->client, ADP8870_CFGR, ®_val); - reg_val &= ~(CFGR_BLV_MASK << CFGR_BLV_SHIFT); - reg_val |= (val - 1) << CFGR_BLV_SHIFT; - adp8870_write(data->client, ADP8870_CFGR, reg_val); + ret = adp8870_read(data->client, ADP8870_CFGR, ®_val); + if (!ret) { + reg_val &= ~(CFGR_BLV_MASK << CFGR_BLV_SHIFT); + reg_val |= (val - 1) << CFGR_BLV_SHIFT; + adp8870_write(data->client, ADP8870_CFGR, reg_val); + } mutex_unlock(&data->lock); } diff --git a/drivers/video/backlight/gpio_backlight.c b/drivers/video/backlight/gpio_backlight.c index 5fbbc2ebdf93..18134416b154 100644 --- a/drivers/video/backlight/gpio_backlight.c +++ b/drivers/video/backlight/gpio_backlight.c @@ -89,6 +89,7 @@ static int gpio_backlight_probe(struct platform_device *pdev) struct backlight_device *bl; struct gpio_backlight *gbl; struct device_node *np = pdev->dev.of_node; + unsigned long flags = GPIOF_DIR_OUT; int ret; if (!pdata && !np) { @@ -114,9 +115,12 @@ static int gpio_backlight_probe(struct platform_device *pdev) gbl->def_value = pdata->def_value; } - ret = devm_gpio_request_one(gbl->dev, gbl->gpio, GPIOF_DIR_OUT | - (gbl->active ? GPIOF_INIT_LOW - : GPIOF_INIT_HIGH), + if (gbl->active) + flags |= gbl->def_value ? GPIOF_INIT_HIGH : GPIOF_INIT_LOW; + else + flags |= gbl->def_value ? GPIOF_INIT_LOW : GPIOF_INIT_HIGH; + + ret = devm_gpio_request_one(gbl->dev, gbl->gpio, flags, pdata ? pdata->name : "backlight"); if (ret < 0) { dev_err(&pdev->dev, "unable to request GPIO\n"); diff --git a/drivers/video/backlight/pwm_bl.c b/drivers/video/backlight/pwm_bl.c index ae3c6b6fd5db..64f9e1b8655f 100644 --- a/drivers/video/backlight/pwm_bl.c +++ b/drivers/video/backlight/pwm_bl.c @@ -198,7 +198,9 @@ static int pwm_backlight_probe(struct platform_device *pdev) struct platform_pwm_backlight_data defdata; struct backlight_properties props; struct backlight_device *bl; + struct device_node *node = pdev->dev.of_node; struct pwm_bl_data *pb; + int initial_blank = FB_BLANK_UNBLANK; int ret; if (!data) { @@ -242,7 +244,7 @@ static int pwm_backlight_probe(struct platform_device *pdev) pb->enabled = false; pb->enable_gpio = devm_gpiod_get_optional(&pdev->dev, "enable", - GPIOD_OUT_HIGH); + GPIOD_ASIS); if (IS_ERR(pb->enable_gpio)) { ret = PTR_ERR(pb->enable_gpio); goto err_alloc; @@ -264,15 +266,32 @@ static int pwm_backlight_probe(struct platform_device *pdev) pb->enable_gpio = gpio_to_desc(data->enable_gpio); } + if (pb->enable_gpio) { + /* + * If the driver is probed from the device tree and there is a + * phandle link pointing to the backlight node, it is safe to + * assume that another driver will enable the backlight at the + * appropriate time. Therefore, if it is disabled, keep it so. + */ + if (node && node->phandle && + gpiod_get_direction(pb->enable_gpio) == GPIOF_DIR_OUT && + gpiod_get_value(pb->enable_gpio) == 0) + initial_blank = FB_BLANK_POWERDOWN; + else + gpiod_direction_output(pb->enable_gpio, 1); + } + pb->power_supply = devm_regulator_get(&pdev->dev, "power"); if (IS_ERR(pb->power_supply)) { ret = PTR_ERR(pb->power_supply); goto err_alloc; } + if (node && node->phandle && !regulator_is_enabled(pb->power_supply)) + initial_blank = FB_BLANK_POWERDOWN; + pb->pwm = devm_pwm_get(&pdev->dev, NULL); - if (IS_ERR(pb->pwm) && PTR_ERR(pb->pwm) != -EPROBE_DEFER - && !pdev->dev.of_node) { + if (IS_ERR(pb->pwm) && PTR_ERR(pb->pwm) != -EPROBE_DEFER && !node) { dev_err(&pdev->dev, "unable to request PWM, trying legacy API\n"); pb->legacy = true; pb->pwm = pwm_request(data->pwm_id, "pwm-backlight"); @@ -309,6 +328,8 @@ static int pwm_backlight_probe(struct platform_device *pdev) if (IS_ERR(bl)) { dev_err(&pdev->dev, "failed to register backlight\n"); ret = PTR_ERR(bl); + if (pb->legacy) + pwm_free(pb->pwm); goto err_alloc; } @@ -320,6 +341,7 @@ static int pwm_backlight_probe(struct platform_device *pdev) } bl->props.brightness = data->dft_brightness; + bl->props.power = initial_blank; backlight_update_status(bl); platform_set_drvdata(pdev, bl); diff --git a/drivers/video/backlight/tps65217_bl.c b/drivers/video/backlight/tps65217_bl.c index 61d72bffd402..fd524ad860a5 100644 --- a/drivers/video/backlight/tps65217_bl.c +++ b/drivers/video/backlight/tps65217_bl.c @@ -320,10 +320,19 @@ static int tps65217_bl_probe(struct platform_device *pdev) return 0; } +#ifdef CONFIG_OF +static const struct of_device_id tps65217_bl_of_match[] = { + { .compatible = "ti,tps65217-bl", }, + { /* sentinel */ }, +}; +MODULE_DEVICE_TABLE(of, tps65217_bl_of_match); +#endif + static struct platform_driver tps65217_bl_driver = { .probe = tps65217_bl_probe, .driver = { .name = "tps65217-bl", + .of_match_table = of_match_ptr(tps65217_bl_of_match), }, }; diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index 6caca025019d..072e7599583a 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -575,7 +575,7 @@ static int v9fs_init_inode_cache(void) v9fs_inode_cache = kmem_cache_create("v9fs_inode_cache", sizeof(struct v9fs_inode), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), v9fs_inode_init_once); if (!v9fs_inode_cache) return -ENOMEM; diff --git a/fs/adfs/super.c b/fs/adfs/super.c index 4d4a0df8344f..c9fdfb112933 100644 --- a/fs/adfs/super.c +++ b/fs/adfs/super.c @@ -271,7 +271,7 @@ static int __init init_inodecache(void) adfs_inode_cachep = kmem_cache_create("adfs_inode_cache", sizeof(struct adfs_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (adfs_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/affs/super.c b/fs/affs/super.c index 8836df5f1e11..2a6713b6b9f4 100644 --- a/fs/affs/super.c +++ b/fs/affs/super.c @@ -132,7 +132,7 @@ static int __init init_inodecache(void) affs_inode_cachep = kmem_cache_create("affs_inode_cache", sizeof(struct affs_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (affs_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/afs/super.c b/fs/afs/super.c index 1fb4a5129f7d..81afefe7d8a6 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -91,7 +91,7 @@ int __init afs_fs_init(void) afs_inode_cachep = kmem_cache_create("afs_inode_cache", sizeof(struct afs_vnode), 0, - SLAB_HWCACHE_ALIGN, + SLAB_HWCACHE_ALIGN|SLAB_ACCOUNT, afs_i_init_once); if (!afs_inode_cachep) { printk(KERN_NOTICE "kAFS: Failed to allocate inode cache\n"); diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index 25250fa87086..cc0e08252913 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -434,7 +434,7 @@ befs_init_inodecache(void) befs_inode_cachep = kmem_cache_create("befs_inode_cache", sizeof (struct befs_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (befs_inode_cachep == NULL) { pr_err("%s: Couldn't initialize inode slabcache\n", __func__); diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c index fdcb4d69f430..1e5c896f6b79 100644 --- a/fs/bfs/inode.c +++ b/fs/bfs/inode.c @@ -270,7 +270,7 @@ static int __init init_inodecache(void) bfs_inode_cachep = kmem_cache_create("bfs_inode_cache", sizeof(struct bfs_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (bfs_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/block_dev.c b/fs/block_dev.c index d878e4860fb7..81c0705558be 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -437,7 +437,7 @@ int bdev_write_page(struct block_device *bdev, sector_t sector, if (!ops->rw_page || bdev_get_integrity(bdev)) return -EOPNOTSUPP; - result = blk_queue_enter(bdev->bd_queue, GFP_KERNEL); + result = blk_queue_enter(bdev->bd_queue, GFP_NOIO); if (result) return result; @@ -595,7 +595,7 @@ void __init bdev_cache_init(void) bdev_cachep = kmem_cache_create("bdev_cache", sizeof(struct bdev_inode), 0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD|SLAB_PANIC), + SLAB_MEM_SPREAD|SLAB_ACCOUNT|SLAB_PANIC), init_once); err = register_filesystem(&bd_type); if (err) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 3b8856e182ae..394017831692 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9161,7 +9161,8 @@ int btrfs_init_cachep(void) { btrfs_inode_cachep = kmem_cache_create("btrfs_inode", sizeof(struct btrfs_inode), 0, - SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, init_once); + SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD | SLAB_ACCOUNT, + init_once); if (!btrfs_inode_cachep) goto fail; diff --git a/fs/ceph/super.c b/fs/ceph/super.c index f446afada328..ca4d5e8457f1 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -639,8 +639,8 @@ static int __init init_caches(void) ceph_inode_cachep = kmem_cache_create("ceph_inode_info", sizeof(struct ceph_inode_info), __alignof__(struct ceph_inode_info), - (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD), - ceph_inode_init_once); + SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD| + SLAB_ACCOUNT, ceph_inode_init_once); if (ceph_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index b7fcb3151103..c4c1169814b2 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -1092,7 +1092,7 @@ cifs_init_inodecache(void) cifs_inode_cachep = kmem_cache_create("cifs_inode_cache", sizeof(struct cifsInodeInfo), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), cifs_init_once); if (cifs_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/coda/inode.c b/fs/coda/inode.c index cac1390b87a3..57e81cbba0fa 100644 --- a/fs/coda/inode.c +++ b/fs/coda/inode.c @@ -74,9 +74,9 @@ static void init_once(void *foo) int __init coda_init_inodecache(void) { coda_inode_cachep = kmem_cache_create("coda_inode_cache", - sizeof(struct coda_inode_info), - 0, SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, - init_once); + sizeof(struct coda_inode_info), 0, + SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD| + SLAB_ACCOUNT, init_once); if (coda_inode_cachep == NULL) return -ENOMEM; return 0; diff --git a/fs/dcache.c b/fs/dcache.c index 8d38cd07b207..b4539e84e577 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1571,7 +1571,8 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) dentry->d_iname[DNAME_INLINE_LEN-1] = 0; if (name->len > DNAME_INLINE_LEN-1) { size_t size = offsetof(struct external_name, name[1]); - struct external_name *p = kmalloc(size + name->len, GFP_KERNEL); + struct external_name *p = kmalloc(size + name->len, + GFP_KERNEL_ACCOUNT); if (!p) { kmem_cache_free(dentry_cache, dentry); return NULL; @@ -3415,7 +3416,7 @@ static void __init dcache_init(void) * of the dcache. */ dentry_cache = KMEM_CACHE(dentry, - SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_MEM_SPREAD); + SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_MEM_SPREAD|SLAB_ACCOUNT); /* Hash may have been set up in dcache_init_early */ if (!hashdist) diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index 4f4d0474bee9..e25b6b06bacf 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -663,6 +663,7 @@ static struct ecryptfs_cache_info { struct kmem_cache **cache; const char *name; size_t size; + unsigned long flags; void (*ctor)(void *obj); } ecryptfs_cache_infos[] = { { @@ -684,6 +685,7 @@ static struct ecryptfs_cache_info { .cache = &ecryptfs_inode_info_cache, .name = "ecryptfs_inode_cache", .size = sizeof(struct ecryptfs_inode_info), + .flags = SLAB_ACCOUNT, .ctor = inode_info_init_once, }, { @@ -755,8 +757,8 @@ static int ecryptfs_init_kmem_caches(void) struct ecryptfs_cache_info *info; info = &ecryptfs_cache_infos[i]; - *(info->cache) = kmem_cache_create(info->name, info->size, - 0, SLAB_HWCACHE_ALIGN, info->ctor); + *(info->cache) = kmem_cache_create(info->name, info->size, 0, + SLAB_HWCACHE_ALIGN | info->flags, info->ctor); if (!*(info->cache)) { ecryptfs_free_kmem_caches(); ecryptfs_printk(KERN_WARNING, "%s: " diff --git a/fs/efs/super.c b/fs/efs/super.c index c8411a30f7da..cb68dac4f9d3 100644 --- a/fs/efs/super.c +++ b/fs/efs/super.c @@ -94,9 +94,9 @@ static void init_once(void *foo) static int __init init_inodecache(void) { efs_inode_cachep = kmem_cache_create("efs_inode_cache", - sizeof(struct efs_inode_info), - 0, SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, - init_once); + sizeof(struct efs_inode_info), 0, + SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD| + SLAB_ACCOUNT, init_once); if (efs_inode_cachep == NULL) return -ENOMEM; return 0; diff --git a/fs/eventfd.c b/fs/eventfd.c index 8d0c0df01854..ed70cf9fdc7b 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -45,10 +45,10 @@ struct eventfd_ctx { * * This function is supposed to be called by the kernel in paths that do not * allow sleeping. In this function we allow the counter to reach the ULLONG_MAX - * value, and we signal this as overflow condition by returining a POLLERR + * value, and we signal this as overflow condition by returning a POLLERR * to poll(2). * - * Returns the amount by which the counter was incrememnted. This will be less + * Returns the amount by which the counter was incremented. This will be less * than @n if the counter has overflowed. */ __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n) diff --git a/fs/exofs/super.c b/fs/exofs/super.c index b795c567b5e1..6658a50530a0 100644 --- a/fs/exofs/super.c +++ b/fs/exofs/super.c @@ -194,8 +194,8 @@ static int init_inodecache(void) { exofs_inode_cachep = kmem_cache_create("exofs_inode_cache", sizeof(struct exofs_i_info), 0, - SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, - exofs_init_once); + SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD | + SLAB_ACCOUNT, exofs_init_once); if (exofs_inode_cachep == NULL) return -ENOMEM; return 0; diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 748d35afc902..2a188413a2b0 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -203,7 +203,7 @@ static int __init init_inodecache(void) ext2_inode_cachep = kmem_cache_create("ext2_inode_cache", sizeof(struct ext2_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (ext2_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index c9ab67da6e5a..f1b56ff01208 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -966,7 +966,7 @@ static int __init init_inodecache(void) ext4_inode_cachep = kmem_cache_create("ext4_inode_cache", sizeof(struct ext4_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (ext4_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 3bf990b80026..6134832baaaf 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1541,8 +1541,9 @@ MODULE_ALIAS_FS("f2fs"); static int __init init_inodecache(void) { - f2fs_inode_cachep = f2fs_kmem_cache_create("f2fs_inode_cache", - sizeof(struct f2fs_inode_info)); + f2fs_inode_cachep = kmem_cache_create("f2fs_inode_cache", + sizeof(struct f2fs_inode_info), 0, + SLAB_RECLAIM_ACCOUNT|SLAB_ACCOUNT, NULL); if (!f2fs_inode_cachep) return -ENOMEM; return 0; diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 509411dd3698..6aece96df19f 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -677,7 +677,7 @@ static int __init fat_init_inodecache(void) fat_inode_cachep = kmem_cache_create("fat_inode_cache", sizeof(struct msdos_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (fat_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/file.c b/fs/file.c index 1aed0add16a2..1fbc5c0555a9 100644 --- a/fs/file.c +++ b/fs/file.c @@ -37,11 +37,12 @@ static void *alloc_fdmem(size_t size) * vmalloc() if the allocation size will be considered "large" by the VM. */ if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { - void *data = kmalloc(size, GFP_KERNEL|__GFP_NOWARN|__GFP_NORETRY); + void *data = kmalloc(size, GFP_KERNEL_ACCOUNT | + __GFP_NOWARN | __GFP_NORETRY); if (data != NULL) return data; } - return vmalloc(size); + return __vmalloc(size, GFP_KERNEL_ACCOUNT | __GFP_HIGHMEM, PAGE_KERNEL); } static void __free_fdtable(struct fdtable *fdt) @@ -126,7 +127,7 @@ static struct fdtable * alloc_fdtable(unsigned int nr) if (unlikely(nr > sysctl_nr_open)) nr = ((sysctl_nr_open - 1) | (BITS_PER_LONG - 1)) + 1; - fdt = kmalloc(sizeof(struct fdtable), GFP_KERNEL); + fdt = kmalloc(sizeof(struct fdtable), GFP_KERNEL_ACCOUNT); if (!fdt) goto out; fdt->max_fds = nr; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 2913db2a5b99..4d69d5c0bedc 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -1255,8 +1255,8 @@ static int __init fuse_fs_init(void) int err; fuse_inode_cachep = kmem_cache_create("fuse_inode", - sizeof(struct fuse_inode), - 0, SLAB_HWCACHE_ALIGN, + sizeof(struct fuse_inode), 0, + SLAB_HWCACHE_ALIGN|SLAB_ACCOUNT, fuse_inode_init_once); err = -ENOMEM; if (!fuse_inode_cachep) diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index 1d709d496364..f99f8e94de3f 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -114,7 +114,8 @@ static int __init init_gfs2_fs(void) gfs2_inode_cachep = kmem_cache_create("gfs2_inode", sizeof(struct gfs2_inode), 0, SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD, + SLAB_MEM_SPREAD| + SLAB_ACCOUNT, gfs2_init_inode_once); if (!gfs2_inode_cachep) goto fail; diff --git a/fs/hfs/super.c b/fs/hfs/super.c index 4574fdd3d421..1ca95c232bb5 100644 --- a/fs/hfs/super.c +++ b/fs/hfs/super.c @@ -483,8 +483,8 @@ static int __init init_hfs_fs(void) int err; hfs_inode_cachep = kmem_cache_create("hfs_inode_cache", - sizeof(struct hfs_inode_info), 0, SLAB_HWCACHE_ALIGN, - hfs_init_once); + sizeof(struct hfs_inode_info), 0, + SLAB_HWCACHE_ALIGN|SLAB_ACCOUNT, hfs_init_once); if (!hfs_inode_cachep) return -ENOMEM; err = register_filesystem(&hfs_fs_type); diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index 7302d96ae8bf..5d54490a136d 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -663,7 +663,7 @@ static int __init init_hfsplus_fs(void) int err; hfsplus_inode_cachep = kmem_cache_create("hfsplus_icache", - HFSPLUS_INODE_SIZE, 0, SLAB_HWCACHE_ALIGN, + HFSPLUS_INODE_SIZE, 0, SLAB_HWCACHE_ALIGN|SLAB_ACCOUNT, hfsplus_init_once); if (!hfsplus_inode_cachep) return -ENOMEM; diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index f49be23e78aa..cfaa18c7a337 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -223,7 +223,7 @@ static struct inode *hostfs_alloc_inode(struct super_block *sb) { struct hostfs_inode_info *hi; - hi = kmalloc(sizeof(*hi), GFP_KERNEL); + hi = kmalloc(sizeof(*hi), GFP_KERNEL_ACCOUNT); if (hi == NULL) return NULL; hi->fd = -1; diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c index a561591896bd..458cf463047b 100644 --- a/fs/hpfs/super.c +++ b/fs/hpfs/super.c @@ -261,7 +261,7 @@ static int init_inodecache(void) hpfs_inode_cachep = kmem_cache_create("hpfs_inode_cache", sizeof(struct hpfs_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (hpfs_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index d8f51ee8126b..47789292a582 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -4,11 +4,11 @@ * Nadia Yvette Chambers, 2002 * * Copyright (C) 2002 Linus Torvalds. + * License: GPL */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/module.h> #include <linux/thread_info.h> #include <asm/current.h> #include <linux/sched.h> /* remove ASAP */ @@ -738,7 +738,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, /* * The policy is initialized here even if we are creating a * private inode because initialization simply creates an - * an empty rb tree and calls spin_lock_init(), later when we + * an empty rb tree and calls rwlock_init(), later when we * call mpol_free_shared_policy() it will just return because * the rb tree will still be empty. */ @@ -1202,7 +1202,6 @@ static struct file_system_type hugetlbfs_fs_type = { .mount = hugetlbfs_mount, .kill_sb = kill_litter_super, }; -MODULE_ALIAS_FS("hugetlbfs"); static struct vfsmount *hugetlbfs_vfsmount[HUGE_MAX_HSTATE]; @@ -1322,7 +1321,7 @@ static int __init init_hugetlbfs_fs(void) error = -ENOMEM; hugetlbfs_inode_cachep = kmem_cache_create("hugetlbfs_inode_cache", sizeof(struct hugetlbfs_inode_info), - 0, 0, init_once); + 0, SLAB_ACCOUNT, init_once); if (hugetlbfs_inode_cachep == NULL) goto out2; @@ -1356,26 +1355,4 @@ static int __init init_hugetlbfs_fs(void) out2: return error; } - -static void __exit exit_hugetlbfs_fs(void) -{ - struct hstate *h; - int i; - - - /* - * Make sure all delayed rcu free inodes are flushed before we - * destroy cache. - */ - rcu_barrier(); - kmem_cache_destroy(hugetlbfs_inode_cachep); - i = 0; - for_each_hstate(h) - kern_unmount(hugetlbfs_vfsmount[i++]); - unregister_filesystem(&hugetlbfs_fs_type); -} - -module_init(init_hugetlbfs_fs) -module_exit(exit_hugetlbfs_fs) - -MODULE_LICENSE("GPL"); +fs_initcall(init_hugetlbfs_fs) diff --git a/fs/inode.c b/fs/inode.c index 4230f66b7410..e491e54d2430 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1883,7 +1883,7 @@ void __init inode_init(void) sizeof(struct inode), 0, (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); /* Hash may have been set up in inode_init_early */ diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index 61abdc4920da..bcd2d41b318a 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -94,7 +94,7 @@ static int __init init_inodecache(void) isofs_inode_cachep = kmem_cache_create("isofs_inode_cache", sizeof(struct iso_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (isofs_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c index d86c5e3176a1..bb080c272149 100644 --- a/fs/jffs2/super.c +++ b/fs/jffs2/super.c @@ -387,7 +387,7 @@ static int __init init_jffs2_fs(void) jffs2_inode_cachep = kmem_cache_create("jffs2_i", sizeof(struct jffs2_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), jffs2_i_init_once); if (!jffs2_inode_cachep) { pr_err("error: Failed to initialise inode cache\n"); diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 8f9176caf098..900925b5eb8c 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -898,7 +898,7 @@ static int __init init_jfs_fs(void) jfs_inode_cachep = kmem_cache_create("jfs_ip", sizeof(struct jfs_inode_info), 0, - SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, + SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|SLAB_ACCOUNT, init_once); if (jfs_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 742bf4a230e8..821973853340 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -541,14 +541,7 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, if (!kn) goto err_out1; - /* - * If the ino of the sysfs entry created for a kmem cache gets - * allocated from an ida layer, which is accounted to the memcg that - * owns the cache, the memcg will get pinned forever. So do not account - * ino ida allocations. - */ - ret = ida_simple_get(&root->ino_ida, 1, 0, - GFP_KERNEL | __GFP_NOACCOUNT); + ret = ida_simple_get(&root->ino_ida, 1, 0, GFP_KERNEL); if (ret < 0) goto err_out2; kn->ino = ret; diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 5f31ebd96c06..154a107cd376 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -25,13 +25,17 @@ #include <linux/mutex.h> #include <linux/kthread.h> #include <linux/freezer.h> +#include <linux/inetdevice.h> #include <linux/sunrpc/types.h> #include <linux/sunrpc/stats.h> #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/svc.h> #include <linux/sunrpc/svcsock.h> +#include <linux/sunrpc/svc_xprt.h> #include <net/ip.h> +#include <net/addrconf.h> +#include <net/ipv6.h> #include <linux/lockd/lockd.h> #include <linux/nfs.h> @@ -44,7 +48,7 @@ static struct svc_program nlmsvc_program; -struct nlmsvc_binding * nlmsvc_ops; +const struct nlmsvc_binding *nlmsvc_ops; EXPORT_SYMBOL_GPL(nlmsvc_ops); static DEFINE_MUTEX(nlmsvc_mutex); @@ -90,8 +94,7 @@ static unsigned long get_lockd_grace_period(void) static void grace_ender(struct work_struct *grace) { - struct delayed_work *dwork = container_of(grace, struct delayed_work, - work); + struct delayed_work *dwork = to_delayed_work(grace); struct lockd_net *ln = container_of(dwork, struct lockd_net, grace_period_end); @@ -279,6 +282,68 @@ static void lockd_down_net(struct svc_serv *serv, struct net *net) } } +static int lockd_inetaddr_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + struct in_ifaddr *ifa = (struct in_ifaddr *)ptr; + struct sockaddr_in sin; + + if (event != NETDEV_DOWN) + goto out; + + if (nlmsvc_rqst) { + dprintk("lockd_inetaddr_event: removed %pI4\n", + &ifa->ifa_local); + sin.sin_family = AF_INET; + sin.sin_addr.s_addr = ifa->ifa_local; + svc_age_temp_xprts_now(nlmsvc_rqst->rq_server, + (struct sockaddr *)&sin); + } + +out: + return NOTIFY_DONE; +} + +static struct notifier_block lockd_inetaddr_notifier = { + .notifier_call = lockd_inetaddr_event, +}; + +#if IS_ENABLED(CONFIG_IPV6) +static int lockd_inet6addr_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + struct inet6_ifaddr *ifa = (struct inet6_ifaddr *)ptr; + struct sockaddr_in6 sin6; + + if (event != NETDEV_DOWN) + goto out; + + if (nlmsvc_rqst) { + dprintk("lockd_inet6addr_event: removed %pI6\n", &ifa->addr); + sin6.sin6_family = AF_INET6; + sin6.sin6_addr = ifa->addr; + svc_age_temp_xprts_now(nlmsvc_rqst->rq_server, + (struct sockaddr *)&sin6); + } + +out: + return NOTIFY_DONE; +} + +static struct notifier_block lockd_inet6addr_notifier = { + .notifier_call = lockd_inet6addr_event, +}; +#endif + +static void lockd_svc_exit_thread(void) +{ + unregister_inetaddr_notifier(&lockd_inetaddr_notifier); +#if IS_ENABLED(CONFIG_IPV6) + unregister_inet6addr_notifier(&lockd_inet6addr_notifier); +#endif + svc_exit_thread(nlmsvc_rqst); +} + static int lockd_start_svc(struct svc_serv *serv) { int error; @@ -315,7 +380,7 @@ static int lockd_start_svc(struct svc_serv *serv) return 0; out_task: - svc_exit_thread(nlmsvc_rqst); + lockd_svc_exit_thread(); nlmsvc_task = NULL; out_rqst: nlmsvc_rqst = NULL; @@ -360,6 +425,10 @@ static struct svc_serv *lockd_create_svc(void) printk(KERN_WARNING "lockd_up: create service failed\n"); return ERR_PTR(-ENOMEM); } + register_inetaddr_notifier(&lockd_inetaddr_notifier); +#if IS_ENABLED(CONFIG_IPV6) + register_inet6addr_notifier(&lockd_inet6addr_notifier); +#endif dprintk("lockd_up: service created\n"); return serv; } @@ -428,7 +497,7 @@ lockd_down(struct net *net) } kthread_stop(nlmsvc_task); dprintk("lockd_down: service stopped\n"); - svc_exit_thread(nlmsvc_rqst); + lockd_svc_exit_thread(); dprintk("lockd_down: service destroyed\n"); nlmsvc_task = NULL; nlmsvc_rqst = NULL; diff --git a/fs/logfs/Kconfig b/fs/logfs/Kconfig index 09ed066c0221..2b4503163930 100644 --- a/fs/logfs/Kconfig +++ b/fs/logfs/Kconfig @@ -1,6 +1,6 @@ config LOGFS tristate "LogFS file system" - depends on (MTD || BLOCK) + depends on MTD || (!MTD && BLOCK) select ZLIB_INFLATE select ZLIB_DEFLATE select CRC32 diff --git a/fs/logfs/inode.c b/fs/logfs/inode.c index 0fce46d62b9c..db9cfc598883 100644 --- a/fs/logfs/inode.c +++ b/fs/logfs/inode.c @@ -409,7 +409,8 @@ const struct super_operations logfs_super_operations = { int logfs_init_inode_cache(void) { logfs_inode_cache = kmem_cache_create("logfs_inode_cache", - sizeof(struct logfs_inode), 0, SLAB_RECLAIM_ACCOUNT, + sizeof(struct logfs_inode), 0, + SLAB_RECLAIM_ACCOUNT|SLAB_ACCOUNT, logfs_init_once); if (!logfs_inode_cache) return -ENOMEM; diff --git a/fs/minix/inode.c b/fs/minix/inode.c index cb1789ca1ee6..f975d667c539 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -91,7 +91,7 @@ static int __init init_inodecache(void) minix_inode_cachep = kmem_cache_create("minix_inode_cache", sizeof(struct minix_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (minix_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c index ce1eb3f9dfe8..1af15fcbe57b 100644 --- a/fs/ncpfs/inode.c +++ b/fs/ncpfs/inode.c @@ -82,7 +82,7 @@ static int init_inodecache(void) ncp_inode_cachep = kmem_cache_create("ncp_inode_cache", sizeof(struct ncp_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (ncp_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index 807eb6ef4f91..f0939d097406 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -83,8 +83,11 @@ __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy, res = htonl(NFS4ERR_BADHANDLE); inode = nfs_delegation_find_inode(cps->clp, &args->fh); - if (inode == NULL) + if (inode == NULL) { + trace_nfs4_cb_recall(cps->clp, &args->fh, NULL, + &args->stateid, -ntohl(res)); goto out; + } /* Set up a helper thread to actually return the delegation */ switch (nfs_async_inode_return_delegation(inode, &args->stateid)) { case 0: @@ -96,7 +99,8 @@ __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy, default: res = htonl(NFS4ERR_RESOURCE); } - trace_nfs4_recall_delegation(inode, -ntohl(res)); + trace_nfs4_cb_recall(cps->clp, &args->fh, inode, + &args->stateid, -ntohl(res)); iput(inode); out: dprintk("%s: exit with status = %d\n", __func__, ntohl(res)); @@ -160,6 +164,22 @@ static struct pnfs_layout_hdr * get_layout_by_fh(struct nfs_client *clp, return lo; } +/* + * Enforce RFC5661 section 12.5.5.2.1. (Layout Recall and Return Sequencing) + */ +static bool pnfs_check_stateid_sequence(struct pnfs_layout_hdr *lo, + const nfs4_stateid *new) +{ + u32 oldseq, newseq; + + oldseq = be32_to_cpu(lo->plh_stateid.seqid); + newseq = be32_to_cpu(new->seqid); + + if (newseq > oldseq + 1) + return false; + return true; +} + static u32 initiate_file_draining(struct nfs_client *clp, struct cb_layoutrecallargs *args) { @@ -169,34 +189,52 @@ static u32 initiate_file_draining(struct nfs_client *clp, LIST_HEAD(free_me_list); lo = get_layout_by_fh(clp, &args->cbl_fh, &args->cbl_stateid); - if (!lo) + if (!lo) { + trace_nfs4_cb_layoutrecall_file(clp, &args->cbl_fh, NULL, + &args->cbl_stateid, -rv); goto out; + } ino = lo->plh_inode; spin_lock(&ino->i_lock); + if (!pnfs_check_stateid_sequence(lo, &args->cbl_stateid)) { + rv = NFS4ERR_DELAY; + goto unlock; + } pnfs_set_layout_stateid(lo, &args->cbl_stateid, true); spin_unlock(&ino->i_lock); pnfs_layoutcommit_inode(ino, false); spin_lock(&ino->i_lock); - if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags) || - pnfs_mark_matching_lsegs_invalid(lo, &free_me_list, - &args->cbl_range)) { + /* + * Enforce RFC5661 Section 12.5.5.2.1.5 (Bulk Recall and Return) + */ + if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags)) { rv = NFS4ERR_DELAY; goto unlock; } + if (pnfs_mark_matching_lsegs_return(lo, &free_me_list, + &args->cbl_range)) { + rv = NFS4_OK; + goto unlock; + } + if (NFS_SERVER(ino)->pnfs_curr_ld->return_range) { NFS_SERVER(ino)->pnfs_curr_ld->return_range(lo, &args->cbl_range); } + pnfs_mark_layout_returned_if_empty(lo); unlock: spin_unlock(&ino->i_lock); pnfs_free_lseg_list(&free_me_list); + /* Free all lsegs that are attached to commit buckets */ + nfs_commit_inode(ino, 0); pnfs_put_layout_hdr(lo); - trace_nfs4_cb_layoutrecall_inode(clp, &args->cbl_fh, ino, -rv); + trace_nfs4_cb_layoutrecall_file(clp, &args->cbl_fh, ino, + &args->cbl_stateid, -rv); iput(ino); out: return rv; diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index ce5a21861074..c82a21228a34 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1894,15 +1894,14 @@ int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) attr.ia_mode = S_IFLNK | S_IRWXUGO; attr.ia_valid = ATTR_MODE; - page = alloc_page(GFP_HIGHUSER); + page = alloc_page(GFP_USER); if (!page) return -ENOMEM; - kaddr = kmap_atomic(page); + kaddr = page_address(page); memcpy(kaddr, symname, pathlen); if (pathlen < PAGE_SIZE) memset(kaddr + pathlen, 0, PAGE_SIZE - pathlen); - kunmap_atomic(kaddr); trace_nfs_symlink_enter(dir, dentry); error = NFS_PROTO(dir)->symlink(dir, dentry, page, pathlen, &attr); @@ -2432,6 +2431,20 @@ int nfs_may_open(struct inode *inode, struct rpc_cred *cred, int openflags) } EXPORT_SYMBOL_GPL(nfs_may_open); +static int nfs_execute_ok(struct inode *inode, int mask) +{ + struct nfs_server *server = NFS_SERVER(inode); + int ret; + + if (mask & MAY_NOT_BLOCK) + ret = nfs_revalidate_inode_rcu(server, inode); + else + ret = nfs_revalidate_inode(server, inode); + if (ret == 0 && !execute_ok(inode)) + ret = -EACCES; + return ret; +} + int nfs_permission(struct inode *inode, int mask) { struct rpc_cred *cred; @@ -2449,6 +2462,9 @@ int nfs_permission(struct inode *inode, int mask) case S_IFLNK: goto out; case S_IFREG: + if ((mask & MAY_OPEN) && + nfs_server_capable(inode, NFS_CAP_ATOMIC_OPEN)) + return 0; break; case S_IFDIR: /* @@ -2481,8 +2497,8 @@ force_lookup: res = PTR_ERR(cred); } out: - if (!res && (mask & MAY_EXEC) && !execute_ok(inode)) - res = -EACCES; + if (!res && (mask & MAY_EXEC)) + res = nfs_execute_ok(inode, mask); dfprintk(VFS, "NFS: permission(%s/%lu), mask=0x%x, res=%d\n", inode->i_sb->s_id, inode->i_ino, mask, res); diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 4b1d08f56aba..7ab7ec9f4eed 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -117,12 +117,6 @@ static inline int put_dreq(struct nfs_direct_req *dreq) return atomic_dec_and_test(&dreq->io_count); } -void nfs_direct_set_resched_writes(struct nfs_direct_req *dreq) -{ - dreq->flags = NFS_ODIRECT_RESCHED_WRITES; -} -EXPORT_SYMBOL_GPL(nfs_direct_set_resched_writes); - static void nfs_direct_good_bytes(struct nfs_direct_req *dreq, struct nfs_pgio_header *hdr) { @@ -670,6 +664,10 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) req = nfs_list_entry(reqs.next); nfs_direct_setup_mirroring(dreq, &desc, req); + if (desc.pg_error < 0) { + list_splice_init(&reqs, &failed); + goto out_failed; + } list_for_each_entry_safe(req, tmp, &reqs, wb_list) { if (!nfs_pageio_add_request(&desc, req)) { @@ -677,13 +675,17 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) nfs_list_add_request(req, &failed); spin_lock(cinfo.lock); dreq->flags = 0; - dreq->error = -EIO; + if (desc.pg_error < 0) + dreq->error = desc.pg_error; + else + dreq->error = -EIO; spin_unlock(cinfo.lock); } nfs_release_request(req); } nfs_pageio_complete(&desc); +out_failed: while (!list_empty(&failed)) { req = nfs_list_entry(failed.next); nfs_list_remove_request(req); @@ -727,14 +729,20 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data) nfs_direct_write_complete(dreq, data->inode); } -static void nfs_direct_error_cleanup(struct nfs_inode *nfsi) +static void nfs_direct_resched_write(struct nfs_commit_info *cinfo, + struct nfs_page *req) { - /* There is no lock to clear */ + struct nfs_direct_req *dreq = cinfo->dreq; + + spin_lock(&dreq->lock); + dreq->flags = NFS_ODIRECT_RESCHED_WRITES; + spin_unlock(&dreq->lock); + nfs_mark_request_commit(req, NULL, cinfo, 0); } static const struct nfs_commit_completion_ops nfs_direct_commit_completion_ops = { .completion = nfs_direct_commit_complete, - .error_cleanup = nfs_direct_error_cleanup, + .resched_write = nfs_direct_resched_write, }; static void nfs_direct_commit_schedule(struct nfs_direct_req *dreq) @@ -839,10 +847,25 @@ static void nfs_write_sync_pgio_error(struct list_head *head) } } +static void nfs_direct_write_reschedule_io(struct nfs_pgio_header *hdr) +{ + struct nfs_direct_req *dreq = hdr->dreq; + + spin_lock(&dreq->lock); + if (dreq->error == 0) { + dreq->flags = NFS_ODIRECT_RESCHED_WRITES; + /* fake unstable write to let common nfs resend pages */ + hdr->verf.committed = NFS_UNSTABLE; + hdr->good_bytes = hdr->args.count; + } + spin_unlock(&dreq->lock); +} + static const struct nfs_pgio_completion_ops nfs_direct_write_completion_ops = { .error_cleanup = nfs_write_sync_pgio_error, .init_hdr = nfs_direct_pgio_init, .completion = nfs_direct_write_completion, + .reschedule_io = nfs_direct_write_reschedule_io, }; @@ -900,6 +923,11 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, } nfs_direct_setup_mirroring(dreq, &desc, req); + if (desc.pg_error < 0) { + nfs_free_request(req); + result = desc.pg_error; + break; + } nfs_lock_request(req); req->wb_index = pos >> PAGE_SHIFT; diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 93e236429c5d..4ef8f5addcad 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -514,7 +514,7 @@ static void nfs_check_dirty_writeback(struct page *page, * so it will not block due to pages that will shortly be freeable. */ nfsi = NFS_I(mapping->host); - if (test_bit(NFS_INO_COMMIT, &nfsi->flags)) { + if (atomic_read(&nfsi->commit_info.rpcs_out)) { *writeback = true; return; } @@ -545,7 +545,7 @@ static int nfs_launder_page(struct page *page) inode->i_ino, (long long)page_offset(page)); nfs_fscache_wait_on_page_write(nfsi, page); - return nfs_wb_page(inode, page); + return nfs_wb_launder_page(inode, page); } static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file, @@ -756,7 +756,7 @@ do_unlk(struct file *filp, int cmd, struct file_lock *fl, int is_local) l_ctx = nfs_get_lock_context(nfs_file_open_context(filp)); if (!IS_ERR(l_ctx)) { - status = nfs_iocounter_wait(&l_ctx->io_count); + status = nfs_iocounter_wait(l_ctx); nfs_put_lock_context(l_ctx); if (status < 0) return status; diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index 02ec07973bc4..bb1f4e7a3270 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -202,6 +202,7 @@ static int filelayout_async_handle_error(struct rpc_task *task, task->tk_status); nfs4_mark_deviceid_unavailable(devid); pnfs_error_mark_layout_for_return(inode, lseg); + pnfs_set_lo_fail(lseg); rpc_wake_up(&tbl->slot_tbl_waitq); /* fall through */ default: @@ -883,13 +884,19 @@ static void filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) { - if (!pgio->pg_lseg) + if (!pgio->pg_lseg) { pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, req->wb_context, 0, NFS4_MAX_UINT64, IOMODE_READ, GFP_KERNEL); + if (IS_ERR(pgio->pg_lseg)) { + pgio->pg_error = PTR_ERR(pgio->pg_lseg); + pgio->pg_lseg = NULL; + return; + } + } /* If no lseg, fall back to read through mds */ if (pgio->pg_lseg == NULL) nfs_pageio_reset_read_mds(pgio); @@ -902,13 +909,20 @@ filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_commit_info cinfo; int status; - if (!pgio->pg_lseg) + if (!pgio->pg_lseg) { pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, req->wb_context, 0, NFS4_MAX_UINT64, IOMODE_RW, GFP_NOFS); + if (IS_ERR(pgio->pg_lseg)) { + pgio->pg_error = PTR_ERR(pgio->pg_lseg); + pgio->pg_lseg = NULL; + return; + } + } + /* If no lseg, fall back to write through mds */ if (pgio->pg_lseg == NULL) goto out_mds; diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 03516c80855a..6594e9f903a0 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -145,7 +145,7 @@ static bool ff_mirror_match_fh(const struct nfs4_ff_layout_mirror *m1, return false; for (i = 0; i < m1->fh_versions_cnt; i++) { bool found_fh = false; - for (j = 0; j < m2->fh_versions_cnt; i++) { + for (j = 0; j < m2->fh_versions_cnt; j++) { if (nfs_compare_fh(&m1->fh_versions[i], &m2->fh_versions[j]) == 0) { found_fh = true; @@ -505,9 +505,17 @@ ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh, } p = xdr_inline_decode(&stream, 4); - if (p) - fls->flags = be32_to_cpup(p); + if (!p) + goto out_sort_mirrors; + fls->flags = be32_to_cpup(p); + + p = xdr_inline_decode(&stream, 4); + if (!p) + goto out_sort_mirrors; + for (i=0; i < fls->mirror_array_cnt; i++) + fls->mirror_array[i]->report_interval = be32_to_cpup(p); +out_sort_mirrors: ff_layout_sort_mirrors(fls); rc = ff_layout_check_layout(lgr); if (rc) @@ -603,7 +611,9 @@ nfs4_ff_layoutstat_start_io(struct nfs4_ff_layout_mirror *mirror, mirror->start_time = now; if (ktime_equal(mirror->last_report_time, notime)) mirror->last_report_time = now; - if (layoutstats_timer != 0) + if (mirror->report_interval != 0) + report_interval = (s64)mirror->report_interval * 1000LL; + else if (layoutstats_timer != 0) report_interval = (s64)layoutstats_timer * 1000LL; if (ktime_to_ms(ktime_sub(now, mirror->last_report_time)) >= report_interval) { @@ -785,13 +795,19 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio, int ds_idx; /* Use full layout for now */ - if (!pgio->pg_lseg) + if (!pgio->pg_lseg) { pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, req->wb_context, 0, NFS4_MAX_UINT64, IOMODE_READ, GFP_KERNEL); + if (IS_ERR(pgio->pg_lseg)) { + pgio->pg_error = PTR_ERR(pgio->pg_lseg); + pgio->pg_lseg = NULL; + return; + } + } /* If no lseg, fall back to read through mds */ if (pgio->pg_lseg == NULL) goto out_mds; @@ -825,13 +841,19 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio, int i; int status; - if (!pgio->pg_lseg) + if (!pgio->pg_lseg) { pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, req->wb_context, 0, NFS4_MAX_UINT64, IOMODE_RW, GFP_NOFS); + if (IS_ERR(pgio->pg_lseg)) { + pgio->pg_error = PTR_ERR(pgio->pg_lseg); + pgio->pg_lseg = NULL; + return; + } + } /* If no lseg, fall back to write through mds */ if (pgio->pg_lseg == NULL) goto out_mds; @@ -867,18 +889,25 @@ static unsigned int ff_layout_pg_get_mirror_count_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) { - if (!pgio->pg_lseg) + if (!pgio->pg_lseg) { pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, req->wb_context, 0, NFS4_MAX_UINT64, IOMODE_RW, GFP_NOFS); + if (IS_ERR(pgio->pg_lseg)) { + pgio->pg_error = PTR_ERR(pgio->pg_lseg); + pgio->pg_lseg = NULL; + goto out; + } + } if (pgio->pg_lseg) return FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg); /* no lseg means that pnfs is not in use, so no mirroring here */ nfs_pageio_reset_write_mds(pgio); +out: return 1; } @@ -912,18 +941,7 @@ static void ff_layout_reset_write(struct nfs_pgio_header *hdr, bool retry_pnfs) hdr->args.count, (unsigned long long)hdr->args.offset); - if (!hdr->dreq) { - struct nfs_open_context *ctx; - - ctx = nfs_list_entry(hdr->pages.next)->wb_context; - set_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags); - hdr->completion_ops->error_cleanup(&hdr->pages); - } else { - nfs_direct_set_resched_writes(hdr->dreq); - /* fake unstable write to let common nfs resend pages */ - hdr->verf.committed = NFS_UNSTABLE; - hdr->good_bytes = hdr->args.count; - } + hdr->completion_ops->reschedule_io(hdr); return; } @@ -1101,7 +1119,7 @@ static int ff_layout_async_handle_error_v3(struct rpc_task *task, return -NFS4ERR_RESET_TO_PNFS; out_retry: task->tk_status = 0; - rpc_restart_call(task); + rpc_restart_call_prepare(task); rpc_delay(task, NFS_JUKEBOX_RETRY_TIME); return -EAGAIN; } @@ -1159,6 +1177,14 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg, } } + switch (status) { + case NFS4ERR_DELAY: + case NFS4ERR_GRACE: + return; + default: + break; + } + mirror = FF_LAYOUT_COMP(lseg, idx); err = ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout), mirror, offset, length, status, opnum, @@ -1242,14 +1268,31 @@ ff_layout_reset_to_mds(struct pnfs_layout_segment *lseg, int idx) return ff_layout_test_devid_unavailable(node); } -static int ff_layout_read_prepare_common(struct rpc_task *task, - struct nfs_pgio_header *hdr) +static void ff_layout_read_record_layoutstats_start(struct rpc_task *task, + struct nfs_pgio_header *hdr) { + if (test_and_set_bit(NFS_IOHDR_STAT, &hdr->flags)) + return; nfs4_ff_layout_stat_io_start_read(hdr->inode, FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx), hdr->args.count, task->tk_start); +} + +static void ff_layout_read_record_layoutstats_done(struct rpc_task *task, + struct nfs_pgio_header *hdr) +{ + if (!test_and_clear_bit(NFS_IOHDR_STAT, &hdr->flags)) + return; + nfs4_ff_layout_stat_io_end_read(task, + FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx), + hdr->args.count, + hdr->res.count); +} +static int ff_layout_read_prepare_common(struct rpc_task *task, + struct nfs_pgio_header *hdr) +{ if (unlikely(test_bit(NFS_CONTEXT_BAD, &hdr->args.context->flags))) { rpc_exit(task, -EIO); return -EIO; @@ -1265,6 +1308,7 @@ static int ff_layout_read_prepare_common(struct rpc_task *task, } hdr->pgio_done_cb = ff_layout_read_done_cb; + ff_layout_read_record_layoutstats_start(task, hdr); return 0; } @@ -1323,10 +1367,6 @@ static void ff_layout_read_call_done(struct rpc_task *task, void *data) dprintk("--> %s task->tk_status %d\n", __func__, task->tk_status); - nfs4_ff_layout_stat_io_end_read(task, - FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx), - hdr->args.count, hdr->res.count); - if (test_bit(NFS_IOHDR_REDO, &hdr->flags) && task->tk_status == 0) { nfs4_sequence_done(task, &hdr->res.seq_res); @@ -1341,10 +1381,20 @@ static void ff_layout_read_count_stats(struct rpc_task *task, void *data) { struct nfs_pgio_header *hdr = data; + ff_layout_read_record_layoutstats_done(task, hdr); rpc_count_iostats_metrics(task, &NFS_CLIENT(hdr->inode)->cl_metrics[NFSPROC4_CLNT_READ]); } +static void ff_layout_read_release(void *data) +{ + struct nfs_pgio_header *hdr = data; + + ff_layout_read_record_layoutstats_done(&hdr->task, hdr); + pnfs_generic_rw_release(data); +} + + static int ff_layout_write_done_cb(struct rpc_task *task, struct nfs_pgio_header *hdr) { @@ -1362,15 +1412,12 @@ static int ff_layout_write_done_cb(struct rpc_task *task, switch (err) { case -NFS4ERR_RESET_TO_PNFS: - pnfs_set_retry_layoutget(hdr->lseg->pls_layout); ff_layout_reset_write(hdr, true); return task->tk_status; case -NFS4ERR_RESET_TO_MDS: - pnfs_clear_retry_layoutget(hdr->lseg->pls_layout); ff_layout_reset_write(hdr, false); return task->tk_status; case -EAGAIN: - rpc_restart_call_prepare(task); return -EAGAIN; } @@ -1402,11 +1449,9 @@ static int ff_layout_commit_done_cb(struct rpc_task *task, switch (err) { case -NFS4ERR_RESET_TO_PNFS: - pnfs_set_retry_layoutget(data->lseg->pls_layout); pnfs_generic_prepare_to_resend_writes(data); return -EAGAIN; case -NFS4ERR_RESET_TO_MDS: - pnfs_clear_retry_layoutget(data->lseg->pls_layout); pnfs_generic_prepare_to_resend_writes(data); return -EAGAIN; case -EAGAIN: @@ -1421,14 +1466,31 @@ static int ff_layout_commit_done_cb(struct rpc_task *task, return 0; } -static int ff_layout_write_prepare_common(struct rpc_task *task, - struct nfs_pgio_header *hdr) +static void ff_layout_write_record_layoutstats_start(struct rpc_task *task, + struct nfs_pgio_header *hdr) { + if (test_and_set_bit(NFS_IOHDR_STAT, &hdr->flags)) + return; nfs4_ff_layout_stat_io_start_write(hdr->inode, FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx), hdr->args.count, task->tk_start); +} + +static void ff_layout_write_record_layoutstats_done(struct rpc_task *task, + struct nfs_pgio_header *hdr) +{ + if (!test_and_clear_bit(NFS_IOHDR_STAT, &hdr->flags)) + return; + nfs4_ff_layout_stat_io_end_write(task, + FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx), + hdr->args.count, hdr->res.count, + hdr->res.verf->committed); +} +static int ff_layout_write_prepare_common(struct rpc_task *task, + struct nfs_pgio_header *hdr) +{ if (unlikely(test_bit(NFS_CONTEXT_BAD, &hdr->args.context->flags))) { rpc_exit(task, -EIO); return -EIO; @@ -1445,6 +1507,7 @@ static int ff_layout_write_prepare_common(struct rpc_task *task, return -EAGAIN; } + ff_layout_write_record_layoutstats_start(task, hdr); return 0; } @@ -1480,11 +1543,6 @@ static void ff_layout_write_call_done(struct rpc_task *task, void *data) { struct nfs_pgio_header *hdr = data; - nfs4_ff_layout_stat_io_end_write(task, - FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx), - hdr->args.count, hdr->res.count, - hdr->res.verf->committed); - if (test_bit(NFS_IOHDR_REDO, &hdr->flags) && task->tk_status == 0) { nfs4_sequence_done(task, &hdr->res.seq_res); @@ -1499,18 +1557,53 @@ static void ff_layout_write_count_stats(struct rpc_task *task, void *data) { struct nfs_pgio_header *hdr = data; + ff_layout_write_record_layoutstats_done(task, hdr); rpc_count_iostats_metrics(task, &NFS_CLIENT(hdr->inode)->cl_metrics[NFSPROC4_CLNT_WRITE]); } -static void ff_layout_commit_prepare_common(struct rpc_task *task, +static void ff_layout_write_release(void *data) +{ + struct nfs_pgio_header *hdr = data; + + ff_layout_write_record_layoutstats_done(&hdr->task, hdr); + pnfs_generic_rw_release(data); +} + +static void ff_layout_commit_record_layoutstats_start(struct rpc_task *task, struct nfs_commit_data *cdata) { + if (test_and_set_bit(NFS_IOHDR_STAT, &cdata->flags)) + return; nfs4_ff_layout_stat_io_start_write(cdata->inode, FF_LAYOUT_COMP(cdata->lseg, cdata->ds_commit_index), 0, task->tk_start); } +static void ff_layout_commit_record_layoutstats_done(struct rpc_task *task, + struct nfs_commit_data *cdata) +{ + struct nfs_page *req; + __u64 count = 0; + + if (!test_and_clear_bit(NFS_IOHDR_STAT, &cdata->flags)) + return; + + if (task->tk_status == 0) { + list_for_each_entry(req, &cdata->pages, wb_list) + count += req->wb_bytes; + } + nfs4_ff_layout_stat_io_end_write(task, + FF_LAYOUT_COMP(cdata->lseg, cdata->ds_commit_index), + count, count, NFS_FILE_SYNC); +} + +static void ff_layout_commit_prepare_common(struct rpc_task *task, + struct nfs_commit_data *cdata) +{ + ff_layout_commit_record_layoutstats_start(task, cdata); +} + static void ff_layout_commit_prepare_v3(struct rpc_task *task, void *data) { ff_layout_commit_prepare_common(task, data); @@ -1531,19 +1624,6 @@ static void ff_layout_commit_prepare_v4(struct rpc_task *task, void *data) static void ff_layout_commit_done(struct rpc_task *task, void *data) { - struct nfs_commit_data *cdata = data; - struct nfs_page *req; - __u64 count = 0; - - if (task->tk_status == 0) { - list_for_each_entry(req, &cdata->pages, wb_list) - count += req->wb_bytes; - } - - nfs4_ff_layout_stat_io_end_write(task, - FF_LAYOUT_COMP(cdata->lseg, cdata->ds_commit_index), - count, count, NFS_FILE_SYNC); - pnfs_generic_write_commit_done(task, data); } @@ -1551,50 +1631,59 @@ static void ff_layout_commit_count_stats(struct rpc_task *task, void *data) { struct nfs_commit_data *cdata = data; + ff_layout_commit_record_layoutstats_done(task, cdata); rpc_count_iostats_metrics(task, &NFS_CLIENT(cdata->inode)->cl_metrics[NFSPROC4_CLNT_COMMIT]); } +static void ff_layout_commit_release(void *data) +{ + struct nfs_commit_data *cdata = data; + + ff_layout_commit_record_layoutstats_done(&cdata->task, cdata); + pnfs_generic_commit_release(data); +} + static const struct rpc_call_ops ff_layout_read_call_ops_v3 = { .rpc_call_prepare = ff_layout_read_prepare_v3, .rpc_call_done = ff_layout_read_call_done, .rpc_count_stats = ff_layout_read_count_stats, - .rpc_release = pnfs_generic_rw_release, + .rpc_release = ff_layout_read_release, }; static const struct rpc_call_ops ff_layout_read_call_ops_v4 = { .rpc_call_prepare = ff_layout_read_prepare_v4, .rpc_call_done = ff_layout_read_call_done, .rpc_count_stats = ff_layout_read_count_stats, - .rpc_release = pnfs_generic_rw_release, + .rpc_release = ff_layout_read_release, }; static const struct rpc_call_ops ff_layout_write_call_ops_v3 = { .rpc_call_prepare = ff_layout_write_prepare_v3, .rpc_call_done = ff_layout_write_call_done, .rpc_count_stats = ff_layout_write_count_stats, - .rpc_release = pnfs_generic_rw_release, + .rpc_release = ff_layout_write_release, }; static const struct rpc_call_ops ff_layout_write_call_ops_v4 = { .rpc_call_prepare = ff_layout_write_prepare_v4, .rpc_call_done = ff_layout_write_call_done, .rpc_count_stats = ff_layout_write_count_stats, - .rpc_release = pnfs_generic_rw_release, + .rpc_release = ff_layout_write_release, }; static const struct rpc_call_ops ff_layout_commit_call_ops_v3 = { .rpc_call_prepare = ff_layout_commit_prepare_v3, .rpc_call_done = ff_layout_commit_done, .rpc_count_stats = ff_layout_commit_count_stats, - .rpc_release = pnfs_generic_commit_release, + .rpc_release = ff_layout_commit_release, }; static const struct rpc_call_ops ff_layout_commit_call_ops_v4 = { .rpc_call_prepare = ff_layout_commit_prepare_v4, .rpc_call_done = ff_layout_commit_done, .rpc_count_stats = ff_layout_commit_count_stats, - .rpc_release = pnfs_generic_commit_release, + .rpc_release = ff_layout_commit_release, }; static enum pnfs_try_status diff --git a/fs/nfs/flexfilelayout/flexfilelayout.h b/fs/nfs/flexfilelayout/flexfilelayout.h index 2bb08bc6aaf0..dd353bb7dc0a 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.h +++ b/fs/nfs/flexfilelayout/flexfilelayout.h @@ -85,6 +85,7 @@ struct nfs4_ff_layout_mirror { struct nfs4_ff_layoutstat write_stat; ktime_t start_time; ktime_t last_report_time; + u32 report_interval; }; struct nfs4_ff_layout_segment { diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index e125e55de86d..bd0327541366 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -429,22 +429,14 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx, mirror, lseg->pls_range.offset, lseg->pls_range.length, NFS4ERR_NXIO, OP_ILLEGAL, GFP_NOIO); - if (fail_return) { - pnfs_error_mark_layout_for_return(ino, lseg); - if (ff_layout_has_available_ds(lseg)) - pnfs_set_retry_layoutget(lseg->pls_layout); - else - pnfs_clear_retry_layoutget(lseg->pls_layout); - - } else { + if (!fail_return) { if (ff_layout_has_available_ds(lseg)) set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &lseg->pls_layout->plh_flags); - else { + else pnfs_error_mark_layout_for_return(ino, lseg); - pnfs_clear_retry_layoutget(lseg->pls_layout); - } - } + } else + pnfs_error_mark_layout_for_return(ino, lseg); } out_update_creds: if (ff_layout_update_mirror_cred(mirror, ds)) diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index bdb4dc7b4ecd..8e24d886d2c5 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -71,19 +71,25 @@ nfs_fattr_to_ino_t(struct nfs_fattr *fattr) return nfs_fileid_to_ino_t(fattr->fileid); } -/** - * nfs_wait_bit_killable - helper for functions that are sleeping on bit locks - * @word: long word containing the bit lock - */ -int nfs_wait_bit_killable(struct wait_bit_key *key, int mode) +static int nfs_wait_killable(int mode) { freezable_schedule_unsafe(); if (signal_pending_state(mode, current)) return -ERESTARTSYS; return 0; } + +int nfs_wait_bit_killable(struct wait_bit_key *key, int mode) +{ + return nfs_wait_killable(mode); +} EXPORT_SYMBOL_GPL(nfs_wait_bit_killable); +int nfs_wait_atomic_killable(atomic_t *p) +{ + return nfs_wait_killable(TASK_KILLABLE); +} + /** * nfs_compat_user_ino64 - returns the user-visible inode number * @fileid: 64-bit fileid @@ -700,7 +706,7 @@ static void nfs_init_lock_context(struct nfs_lock_context *l_ctx) l_ctx->lockowner.l_owner = current->files; l_ctx->lockowner.l_pid = current->tgid; INIT_LIST_HEAD(&l_ctx->list); - nfs_iocounter_init(&l_ctx->io_count); + atomic_set(&l_ctx->io_count, 0); } static struct nfs_lock_context *__nfs_find_lock_context(struct nfs_open_context *ctx) @@ -913,6 +919,12 @@ void nfs_file_clear_open_context(struct file *filp) if (ctx) { struct inode *inode = d_inode(ctx->dentry); + /* + * We fatal error on write before. Try to writeback + * every page again. + */ + if (ctx->error < 0) + invalidate_inode_pages2(inode->i_mapping); filp->private_data = NULL; spin_lock(&inode->i_lock); list_move_tail(&ctx->list, &NFS_I(inode)->open_files); @@ -1663,6 +1675,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) unsigned long invalid = 0; unsigned long now = jiffies; unsigned long save_cache_validity; + bool cache_revalidated = true; dfprintk(VFS, "NFS: %s(%s/%lu fh_crc=0x%08x ct=%d info=0x%x)\n", __func__, inode->i_sb->s_id, inode->i_ino, @@ -1724,22 +1737,28 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) nfs_force_lookup_revalidate(inode); inode->i_version = fattr->change_attr; } - } else + } else { nfsi->cache_validity |= save_cache_validity; + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_MTIME) { memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime)); - } else if (server->caps & NFS_CAP_MTIME) + } else if (server->caps & NFS_CAP_MTIME) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_CTIME) { memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime)); - } else if (server->caps & NFS_CAP_CTIME) + } else if (server->caps & NFS_CAP_CTIME) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } /* Check if our cached file size is stale */ if (fattr->valid & NFS_ATTR_FATTR_SIZE) { @@ -1759,19 +1778,23 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) (long long)cur_isize, (long long)new_isize); } - } else + } else { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_REVAL_PAGECACHE | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_ATIME) memcpy(&inode->i_atime, &fattr->atime, sizeof(inode->i_atime)); - else if (server->caps & NFS_CAP_ATIME) + else if (server->caps & NFS_CAP_ATIME) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATIME | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_MODE) { if ((inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)) { @@ -1780,36 +1803,42 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) inode->i_mode = newmode; invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; } - } else if (server->caps & NFS_CAP_MODE) + } else if (server->caps & NFS_CAP_MODE) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_OWNER) { if (!uid_eq(inode->i_uid, fattr->uid)) { invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; inode->i_uid = fattr->uid; } - } else if (server->caps & NFS_CAP_OWNER) + } else if (server->caps & NFS_CAP_OWNER) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_GROUP) { if (!gid_eq(inode->i_gid, fattr->gid)) { invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; inode->i_gid = fattr->gid; } - } else if (server->caps & NFS_CAP_OWNER_GROUP) + } else if (server->caps & NFS_CAP_OWNER_GROUP) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_NLINK) { if (inode->i_nlink != fattr->nlink) { @@ -1818,19 +1847,22 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) invalid |= NFS_INO_INVALID_DATA; set_nlink(inode, fattr->nlink); } - } else if (server->caps & NFS_CAP_NLINK) + } else if (server->caps & NFS_CAP_NLINK) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) { /* * report the blocks in 512byte units */ inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used); - } - if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) + } else if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) inode->i_blocks = fattr->du.nfs2.blocks; + else + cache_revalidated = false; /* Update attrtimeo value if we're out of the unstable period */ if (invalid & NFS_INO_INVALID_ATTR) { @@ -1840,9 +1872,13 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) /* Set barrier to be more recent than all outstanding updates */ nfsi->attr_gencount = nfs_inc_attr_generation_counter(); } else { - if (!time_in_range_open(now, nfsi->attrtimeo_timestamp, nfsi->attrtimeo_timestamp + nfsi->attrtimeo)) { - if ((nfsi->attrtimeo <<= 1) > NFS_MAXATTRTIMEO(inode)) - nfsi->attrtimeo = NFS_MAXATTRTIMEO(inode); + if (cache_revalidated) { + if (!time_in_range_open(now, nfsi->attrtimeo_timestamp, + nfsi->attrtimeo_timestamp + nfsi->attrtimeo)) { + nfsi->attrtimeo <<= 1; + if (nfsi->attrtimeo > NFS_MAXATTRTIMEO(inode)) + nfsi->attrtimeo = NFS_MAXATTRTIMEO(inode); + } nfsi->attrtimeo_timestamp = now; } /* Set the barrier to be more recent than this fattr */ @@ -1851,7 +1887,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) } /* Don't declare attrcache up to date if there were no attrs! */ - if (fattr->valid != 0) + if (cache_revalidated) invalid &= ~NFS_INO_INVALID_ATTR; /* Don't invalidate the data if we were to blame */ @@ -1933,7 +1969,7 @@ static int __init nfs_init_inodecache(void) nfs_inode_cachep = kmem_cache_create("nfs_inode_cache", sizeof(struct nfs_inode), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (nfs_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 9dea85f7f918..4e8cc942336c 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -238,7 +238,7 @@ extern void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr, void (*release)(struct nfs_pgio_header *hdr)); void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos); -int nfs_iocounter_wait(struct nfs_io_counter *c); +int nfs_iocounter_wait(struct nfs_lock_context *l_ctx); extern const struct nfs_pageio_ops nfs_pgio_rw_ops; struct nfs_pgio_header *nfs_pgio_header_alloc(const struct nfs_rw_ops *); @@ -252,18 +252,18 @@ void nfs_free_request(struct nfs_page *req); struct nfs_pgio_mirror * nfs_pgio_current_mirror(struct nfs_pageio_descriptor *desc); -static inline void nfs_iocounter_init(struct nfs_io_counter *c) -{ - c->flags = 0; - atomic_set(&c->io_count, 0); -} - static inline bool nfs_pgio_has_mirroring(struct nfs_pageio_descriptor *desc) { WARN_ON_ONCE(desc->pg_mirror_count < 1); return desc->pg_mirror_count > 1; } +static inline bool nfs_match_open_context(const struct nfs_open_context *ctx1, + const struct nfs_open_context *ctx2) +{ + return ctx1->cred == ctx2->cred && ctx1->state == ctx2->state; +} + /* nfs2xdr.c */ extern struct rpc_procinfo nfs_procedures[]; extern int nfs2_decode_dirent(struct xdr_stream *, @@ -380,6 +380,7 @@ extern void nfs_clear_inode(struct inode *); extern void nfs_evict_inode(struct inode *); void nfs_zap_acl_cache(struct inode *inode); extern int nfs_wait_bit_killable(struct wait_bit_key *key, int mode); +extern int nfs_wait_atomic_killable(atomic_t *p); /* super.c */ extern const struct super_operations nfs_sops; @@ -519,7 +520,6 @@ static inline void nfs_inode_dio_wait(struct inode *inode) inode_dio_wait(inode); } extern ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq); -extern void nfs_direct_set_resched_writes(struct nfs_direct_req *dreq); /* nfs4proc.c */ extern void __nfs4_read_done_cb(struct nfs_pgio_header *); @@ -696,9 +696,32 @@ static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh) { return ~crc32_le(0xFFFFFFFF, &fh->data[0], fh->size); } +static inline u32 nfs_stateid_hash(const nfs4_stateid *stateid) +{ + return ~crc32_le(0xFFFFFFFF, &stateid->other[0], + NFS4_STATEID_OTHER_SIZE); +} #else static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh) { return 0; } +static inline u32 nfs_stateid_hash(nfs4_stateid *stateid) +{ + return 0; +} #endif + +static inline bool nfs_error_is_fatal(int err) +{ + switch (err) { + case -ERESTARTSYS: + case -EIO: + case -ENOSPC: + case -EROFS: + case -E2BIG: + return true; + default: + return false; + } +} diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 6b1ce9825430..6e8174930a48 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -204,6 +204,8 @@ static void nfs42_layoutstat_done(struct rpc_task *task, void *calldata) { struct nfs42_layoutstat_data *data = calldata; + struct inode *inode = data->inode; + struct pnfs_layout_hdr *lo; if (!nfs4_sequence_done(task, &data->res.seq_res)) return; @@ -211,12 +213,35 @@ nfs42_layoutstat_done(struct rpc_task *task, void *calldata) switch (task->tk_status) { case 0: break; + case -NFS4ERR_EXPIRED: + case -NFS4ERR_STALE_STATEID: + case -NFS4ERR_OLD_STATEID: + case -NFS4ERR_BAD_STATEID: + spin_lock(&inode->i_lock); + lo = NFS_I(inode)->layout; + if (lo && nfs4_stateid_match(&data->args.stateid, + &lo->plh_stateid)) { + LIST_HEAD(head); + + /* + * Mark the bad layout state as invalid, then retry + * with the current stateid. + */ + set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags); + pnfs_mark_matching_lsegs_invalid(lo, &head, NULL); + spin_unlock(&inode->i_lock); + pnfs_free_lseg_list(&head); + } else + spin_unlock(&inode->i_lock); + break; case -ENOTSUPP: case -EOPNOTSUPP: - NFS_SERVER(data->inode)->caps &= ~NFS_CAP_LAYOUTSTATS; + NFS_SERVER(inode)->caps &= ~NFS_CAP_LAYOUTSTATS; default: - dprintk("%s server returns %d\n", __func__, task->tk_status); + break; } + + dprintk("%s server returns %d\n", __func__, task->tk_status); } static void diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index c57d1332c1c8..4bfc33ad0563 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -208,6 +208,9 @@ static const u32 nfs4_pnfs_open_bitmap[3] = { | FATTR4_WORD1_TIME_METADATA | FATTR4_WORD1_TIME_MODIFY, FATTR4_WORD2_MDSTHRESHOLD +#ifdef CONFIG_NFS_V4_SECURITY_LABEL + | FATTR4_WORD2_SECURITY_LABEL +#endif }; static const u32 nfs4_open_noattr_bitmap[3] = { @@ -1385,6 +1388,7 @@ static void __update_open_stateid(struct nfs4_state *state, nfs4_stateid *open_s * Protect the call to nfs4_state_set_mode_locked and * serialise the stateid update */ + spin_lock(&state->owner->so_lock); write_seqlock(&state->seqlock); if (deleg_stateid != NULL) { nfs4_stateid_copy(&state->stateid, deleg_stateid); @@ -1393,7 +1397,6 @@ static void __update_open_stateid(struct nfs4_state *state, nfs4_stateid *open_s if (open_stateid != NULL) nfs_set_open_stateid_locked(state, open_stateid, fmode); write_sequnlock(&state->seqlock); - spin_lock(&state->owner->so_lock); update_open_stateflags(state, fmode); spin_unlock(&state->owner->so_lock); } @@ -1598,6 +1601,7 @@ _nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data) if (!data->rpc_done) { state = nfs4_try_open_cached(data); + trace_nfs4_cached_open(data->state); goto out; } @@ -2015,6 +2019,7 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata) } return; unlock_no_action: + trace_nfs4_cached_open(data->state); rcu_read_unlock(); out_no_action: task->tk_action = NULL; @@ -2703,6 +2708,7 @@ static int _nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred, status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1); if (status == 0 && state != NULL) renew_lease(server, timestamp); + trace_nfs4_setattr(inode, &arg.stateid, status); return status; } @@ -2719,7 +2725,6 @@ static int nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred, int err; do { err = _nfs4_do_setattr(inode, cred, fattr, sattr, state, ilabel, olabel); - trace_nfs4_setattr(inode, err); switch (err) { case -NFS4ERR_OPENMODE: if (!(sattr->ia_valid & ATTR_SIZE)) { @@ -5048,7 +5053,6 @@ static void nfs4_init_boot_verifier(const struct nfs_client *clp, static int nfs4_init_nonuniform_client_string(struct nfs_client *clp) { - int result; size_t len; char *str; @@ -5076,7 +5080,7 @@ nfs4_init_nonuniform_client_string(struct nfs_client *clp) return -ENOMEM; rcu_read_lock(); - result = scnprintf(str, len, "Linux NFSv4.0 %s/%s %s", + scnprintf(str, len, "Linux NFSv4.0 %s/%s %s", clp->cl_ipaddr, rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_ADDR), rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_PROTO)); @@ -5089,7 +5093,6 @@ nfs4_init_nonuniform_client_string(struct nfs_client *clp) static int nfs4_init_uniquifier_client_string(struct nfs_client *clp) { - int result; size_t len; char *str; @@ -5109,7 +5112,7 @@ nfs4_init_uniquifier_client_string(struct nfs_client *clp) if (!str) return -ENOMEM; - result = scnprintf(str, len, "Linux NFSv%u.%u %s/%s", + scnprintf(str, len, "Linux NFSv%u.%u %s/%s", clp->rpc_ops->version, clp->cl_minorversion, nfs4_client_id_uniquifier, clp->cl_rpcclient->cl_nodename); @@ -5120,7 +5123,6 @@ nfs4_init_uniquifier_client_string(struct nfs_client *clp) static int nfs4_init_uniform_client_string(struct nfs_client *clp) { - int result; size_t len; char *str; @@ -5145,7 +5147,7 @@ nfs4_init_uniform_client_string(struct nfs_client *clp) if (!str) return -ENOMEM; - result = scnprintf(str, len, "Linux NFSv%u.%u %s", + scnprintf(str, len, "Linux NFSv%u.%u %s", clp->rpc_ops->version, clp->cl_minorversion, clp->cl_rpcclient->cl_nodename); clp->cl_owner_id = str; @@ -5384,6 +5386,11 @@ static int _nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, co if (data == NULL) return -ENOMEM; nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1); + + nfs4_state_protect(server->nfs_client, + NFS_SP4_MACH_CRED_CLEANUP, + &task_setup_data.rpc_client, &msg); + data->args.fhandle = &data->fh; data->args.stateid = &data->stateid; data->args.bitmask = server->cache_consistency_bitmask; @@ -5426,7 +5433,7 @@ int nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4 int err; do { err = _nfs4_proc_delegreturn(inode, cred, stateid, issync); - trace_nfs4_delegreturn(inode, err); + trace_nfs4_delegreturn(inode, stateid, err); switch (err) { case -NFS4ERR_STALE_STATEID: case -NFS4ERR_EXPIRED: @@ -5936,6 +5943,7 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f data->cancelled = 1; rpc_put_task(task); dprintk("%s: done, ret = %d!\n", __func__, ret); + trace_nfs4_set_lock(fl, state, &data->res.stateid, cmd, ret); return ret; } @@ -5952,7 +5960,6 @@ static int nfs4_lock_reclaim(struct nfs4_state *state, struct file_lock *request if (test_bit(NFS_DELEGATED_STATE, &state->flags) != 0) return 0; err = _nfs4_do_setlk(state, F_SETLK, request, NFS_LOCK_RECLAIM); - trace_nfs4_lock_reclaim(request, state, F_SETLK, err); if (err != -NFS4ERR_DELAY) break; nfs4_handle_exception(server, err, &exception); @@ -5979,7 +5986,6 @@ static int nfs4_lock_expired(struct nfs4_state *state, struct file_lock *request if (test_bit(NFS_DELEGATED_STATE, &state->flags) != 0) return 0; err = _nfs4_do_setlk(state, F_SETLK, request, NFS_LOCK_EXPIRED); - trace_nfs4_lock_expired(request, state, F_SETLK, err); switch (err) { default: goto out; @@ -6087,7 +6093,6 @@ static int nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock * do { err = _nfs4_proc_setlk(state, cmd, request); - trace_nfs4_set_lock(request, state, cmd, err); if (err == -NFS4ERR_DENIED) err = -EAGAIN; err = nfs4_handle_exception(NFS_SERVER(state->inode), @@ -6847,10 +6852,13 @@ static const struct nfs41_state_protection nfs4_sp4_mach_cred_request = { }, .allow.u.words = { [0] = 1 << (OP_CLOSE) | + 1 << (OP_OPEN_DOWNGRADE) | 1 << (OP_LOCKU) | + 1 << (OP_DELEGRETURN) | 1 << (OP_COMMIT), [1] = 1 << (OP_SECINFO - 32) | 1 << (OP_SECINFO_NO_NAME - 32) | + 1 << (OP_LAYOUTRETURN - 32) | 1 << (OP_TEST_STATEID - 32) | 1 << (OP_FREE_STATEID - 32) | 1 << (OP_WRITE - 32) @@ -6915,11 +6923,19 @@ static int nfs4_sp4_select_mode(struct nfs_client *clp, } if (test_bit(OP_CLOSE, sp->allow.u.longs) && + test_bit(OP_OPEN_DOWNGRADE, sp->allow.u.longs) && + test_bit(OP_DELEGRETURN, sp->allow.u.longs) && test_bit(OP_LOCKU, sp->allow.u.longs)) { dfprintk(MOUNT, " cleanup mode enabled\n"); set_bit(NFS_SP4_MACH_CRED_CLEANUP, &clp->cl_sp4_flags); } + if (test_bit(OP_LAYOUTRETURN, sp->allow.u.longs)) { + dfprintk(MOUNT, " pnfs cleanup mode enabled\n"); + set_bit(NFS_SP4_MACH_CRED_PNFS_CLEANUP, + &clp->cl_sp4_flags); + } + if (test_bit(OP_SECINFO, sp->allow.u.longs) && test_bit(OP_SECINFO_NO_NAME, sp->allow.u.longs)) { dfprintk(MOUNT, " secinfo mode enabled\n"); @@ -7748,6 +7764,7 @@ nfs4_layoutget_prepare(struct rpc_task *task, void *calldata) struct nfs4_layoutget *lgp = calldata; struct nfs_server *server = NFS_SERVER(lgp->args.inode); struct nfs4_session *session = nfs4_get_session(server); + int ret; dprintk("--> %s\n", __func__); /* Note the is a race here, where a CB_LAYOUTRECALL can come in @@ -7758,12 +7775,12 @@ nfs4_layoutget_prepare(struct rpc_task *task, void *calldata) if (nfs41_setup_sequence(session, &lgp->args.seq_args, &lgp->res.seq_res, task)) return; - if (pnfs_choose_layoutget_stateid(&lgp->args.stateid, + ret = pnfs_choose_layoutget_stateid(&lgp->args.stateid, NFS_I(lgp->args.inode)->layout, &lgp->args.range, - lgp->args.ctx->state)) { - rpc_exit(task, NFS4_OK); - } + lgp->args.ctx->state); + if (ret < 0) + rpc_exit(task, ret); } static void nfs4_layoutget_done(struct rpc_task *task, void *calldata) @@ -7783,6 +7800,15 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata) switch (task->tk_status) { case 0: goto out; + + /* + * NFS4ERR_LAYOUTUNAVAILABLE means we are not supposed to use pnfs + * on the file. set tk_status to -ENODATA to tell upper layer to + * retry go inband. + */ + case -NFS4ERR_LAYOUTUNAVAILABLE: + task->tk_status = -ENODATA; + goto out; /* * NFS4ERR_BADLAYOUT means the MDS cannot return a layout of * length lgp->args.minlength != 0 (see RFC5661 section 18.43.3). @@ -7979,6 +8005,7 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags) trace_nfs4_layoutget(lgp->args.ctx, &lgp->args.range, &lgp->res.range, + &lgp->res.stateid, status); /* if layoutp->len is 0, nfs4_layoutget_prepare called rpc_exit */ if (status == 0 && lgp->res.layoutp->len) @@ -8035,11 +8062,11 @@ static void nfs4_layoutreturn_release(void *calldata) dprintk("--> %s\n", __func__); spin_lock(&lo->plh_inode->i_lock); + pnfs_mark_matching_lsegs_invalid(lo, &freeme, &lrp->args.range); + pnfs_mark_layout_returned_if_empty(lo); if (lrp->res.lrs_present) pnfs_set_layout_stateid(lo, &lrp->res.stateid, true); - pnfs_mark_matching_lsegs_invalid(lo, &freeme, &lrp->args.range); pnfs_clear_layoutreturn_waitbit(lo); - lo->plh_block_lgets--; spin_unlock(&lo->plh_inode->i_lock); pnfs_free_lseg_list(&freeme); pnfs_put_layout_hdr(lrp->args.layout); @@ -8071,6 +8098,10 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync) }; int status = 0; + nfs4_state_protect(NFS_SERVER(lrp->args.inode)->nfs_client, + NFS_SP4_MACH_CRED_PNFS_CLEANUP, + &task_setup_data.rpc_client, &msg); + dprintk("--> %s\n", __func__); if (!sync) { lrp->inode = nfs_igrab_and_active(lrp->args.inode); @@ -8086,7 +8117,7 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync) return PTR_ERR(task); if (sync) status = task->tk_status; - trace_nfs4_layoutreturn(lrp->args.inode, status); + trace_nfs4_layoutreturn(lrp->args.inode, &lrp->args.stateid, status); dprintk("<-- %s status=%d\n", __func__, status); rpc_put_task(task); return status; @@ -8234,7 +8265,7 @@ nfs4_proc_layoutcommit(struct nfs4_layoutcommit_data *data, bool sync) return PTR_ERR(task); if (sync) status = task->tk_status; - trace_nfs4_layoutcommit(data->args.inode, status); + trace_nfs4_layoutcommit(data->args.inode, &data->args.stateid, status); dprintk("%s: status %d\n", __func__, status); rpc_put_task(task); return status; diff --git a/fs/nfs/nfs4sysctl.c b/fs/nfs/nfs4sysctl.c index 0fbd3ab1be22..8693d77c45ea 100644 --- a/fs/nfs/nfs4sysctl.c +++ b/fs/nfs/nfs4sysctl.c @@ -12,7 +12,7 @@ #include "nfs4idmap.h" #include "callback.h" -static const int nfs_set_port_min = 0; +static const int nfs_set_port_min; static const int nfs_set_port_max = 65535; static struct ctl_table_header *nfs4_callback_sysctl_table; diff --git a/fs/nfs/nfs4trace.c b/fs/nfs/nfs4trace.c index d774335cc8bc..2850bce19244 100644 --- a/fs/nfs/nfs4trace.c +++ b/fs/nfs/nfs4trace.c @@ -6,6 +6,7 @@ #include "internal.h" #include "nfs4session.h" #include "callback.h" +#include "pnfs.h" #define CREATE_TRACE_POINTS #include "nfs4trace.h" diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h index 671cf68fe56b..2c8d05dae5b1 100644 --- a/fs/nfs/nfs4trace.h +++ b/fs/nfs/nfs4trace.h @@ -321,6 +321,7 @@ TRACE_EVENT(nfs4_sequence_done, __entry->highest_slotid = res->sr_highest_slotid; __entry->target_highest_slotid = res->sr_target_highest_slotid; + __entry->status_flags = res->sr_status_flags; __entry->error = res->sr_status; ), TP_printk( @@ -399,6 +400,10 @@ DECLARE_EVENT_CLASS(nfs4_open_event, __field(u64, fileid) __field(u64, dir) __string(name, ctx->dentry->d_name.name) + __field(int, stateid_seq) + __field(u32, stateid_hash) + __field(int, openstateid_seq) + __field(u32, openstateid_hash) ), TP_fast_assign( @@ -409,8 +414,22 @@ DECLARE_EVENT_CLASS(nfs4_open_event, __entry->flags = flags; __entry->fmode = (__force unsigned int)ctx->mode; __entry->dev = ctx->dentry->d_sb->s_dev; - if (!IS_ERR_OR_NULL(state)) + if (!IS_ERR_OR_NULL(state)) { inode = state->inode; + __entry->stateid_seq = + be32_to_cpu(state->stateid.seqid); + __entry->stateid_hash = + nfs_stateid_hash(&state->stateid); + __entry->openstateid_seq = + be32_to_cpu(state->open_stateid.seqid); + __entry->openstateid_hash = + nfs_stateid_hash(&state->open_stateid); + } else { + __entry->stateid_seq = 0; + __entry->stateid_hash = 0; + __entry->openstateid_seq = 0; + __entry->openstateid_hash = 0; + } if (inode != NULL) { __entry->fileid = NFS_FILEID(inode); __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); @@ -425,7 +444,8 @@ DECLARE_EVENT_CLASS(nfs4_open_event, TP_printk( "error=%d (%s) flags=%d (%s) fmode=%s " "fileid=%02x:%02x:%llu fhandle=0x%08x " - "name=%02x:%02x:%llu/%s", + "name=%02x:%02x:%llu/%s stateid=%d:0x%08x " + "openstateid=%d:0x%08x", __entry->error, show_nfsv4_errors(__entry->error), __entry->flags, @@ -436,7 +456,9 @@ DECLARE_EVENT_CLASS(nfs4_open_event, __entry->fhandle, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, - __get_str(name) + __get_str(name), + __entry->stateid_seq, __entry->stateid_hash, + __entry->openstateid_seq, __entry->openstateid_hash ) ); @@ -452,6 +474,45 @@ DEFINE_NFS4_OPEN_EVENT(nfs4_open_reclaim); DEFINE_NFS4_OPEN_EVENT(nfs4_open_expired); DEFINE_NFS4_OPEN_EVENT(nfs4_open_file); +TRACE_EVENT(nfs4_cached_open, + TP_PROTO( + const struct nfs4_state *state + ), + TP_ARGS(state), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(unsigned int, fmode) + __field(int, stateid_seq) + __field(u32, stateid_hash) + ), + + TP_fast_assign( + const struct inode *inode = state->inode; + + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = NFS_FILEID(inode); + __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + __entry->fmode = (__force unsigned int)state->state; + __entry->stateid_seq = + be32_to_cpu(state->stateid.seqid); + __entry->stateid_hash = + nfs_stateid_hash(&state->stateid); + ), + + TP_printk( + "fmode=%s fileid=%02x:%02x:%llu " + "fhandle=0x%08x stateid=%d:0x%08x", + __entry->fmode ? show_fmode_flags(__entry->fmode) : + "closed", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + __entry->stateid_seq, __entry->stateid_hash + ) +); + TRACE_EVENT(nfs4_close, TP_PROTO( const struct nfs4_state *state, @@ -468,6 +529,8 @@ TRACE_EVENT(nfs4_close, __field(u64, fileid) __field(unsigned int, fmode) __field(int, error) + __field(int, stateid_seq) + __field(u32, stateid_hash) ), TP_fast_assign( @@ -478,18 +541,23 @@ TRACE_EVENT(nfs4_close, __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); __entry->fmode = (__force unsigned int)state->state; __entry->error = error; + __entry->stateid_seq = + be32_to_cpu(args->stateid.seqid); + __entry->stateid_hash = + nfs_stateid_hash(&args->stateid); ), TP_printk( "error=%d (%s) fmode=%s fileid=%02x:%02x:%llu " - "fhandle=0x%08x", + "fhandle=0x%08x openstateid=%d:0x%08x", __entry->error, show_nfsv4_errors(__entry->error), __entry->fmode ? show_fmode_flags(__entry->fmode) : "closed", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, - __entry->fhandle + __entry->fhandle, + __entry->stateid_seq, __entry->stateid_hash ) ); @@ -523,6 +591,8 @@ DECLARE_EVENT_CLASS(nfs4_lock_event, __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) + __field(int, stateid_seq) + __field(u32, stateid_hash) ), TP_fast_assign( @@ -536,11 +606,16 @@ DECLARE_EVENT_CLASS(nfs4_lock_event, __entry->dev = inode->i_sb->s_dev; __entry->fileid = NFS_FILEID(inode); __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + __entry->stateid_seq = + be32_to_cpu(state->stateid.seqid); + __entry->stateid_hash = + nfs_stateid_hash(&state->stateid); ), TP_printk( "error=%d (%s) cmd=%s:%s range=%lld:%lld " - "fileid=%02x:%02x:%llu fhandle=0x%08x", + "fileid=%02x:%02x:%llu fhandle=0x%08x " + "stateid=%d:0x%08x", __entry->error, show_nfsv4_errors(__entry->error), show_lock_cmd(__entry->cmd), @@ -549,7 +624,8 @@ DECLARE_EVENT_CLASS(nfs4_lock_event, (long long)__entry->end, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, - __entry->fhandle + __entry->fhandle, + __entry->stateid_seq, __entry->stateid_hash ) ); @@ -563,11 +639,73 @@ DECLARE_EVENT_CLASS(nfs4_lock_event, ), \ TP_ARGS(request, state, cmd, error)) DEFINE_NFS4_LOCK_EVENT(nfs4_get_lock); -DEFINE_NFS4_LOCK_EVENT(nfs4_set_lock); -DEFINE_NFS4_LOCK_EVENT(nfs4_lock_reclaim); -DEFINE_NFS4_LOCK_EVENT(nfs4_lock_expired); DEFINE_NFS4_LOCK_EVENT(nfs4_unlock); +TRACE_EVENT(nfs4_set_lock, + TP_PROTO( + const struct file_lock *request, + const struct nfs4_state *state, + const nfs4_stateid *lockstateid, + int cmd, + int error + ), + + TP_ARGS(request, state, lockstateid, cmd, error), + + TP_STRUCT__entry( + __field(int, error) + __field(int, cmd) + __field(char, type) + __field(loff_t, start) + __field(loff_t, end) + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(int, stateid_seq) + __field(u32, stateid_hash) + __field(int, lockstateid_seq) + __field(u32, lockstateid_hash) + ), + + TP_fast_assign( + const struct inode *inode = state->inode; + + __entry->error = error; + __entry->cmd = cmd; + __entry->type = request->fl_type; + __entry->start = request->fl_start; + __entry->end = request->fl_end; + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = NFS_FILEID(inode); + __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + __entry->stateid_seq = + be32_to_cpu(state->stateid.seqid); + __entry->stateid_hash = + nfs_stateid_hash(&state->stateid); + __entry->lockstateid_seq = + be32_to_cpu(lockstateid->seqid); + __entry->lockstateid_hash = + nfs_stateid_hash(lockstateid); + ), + + TP_printk( + "error=%d (%s) cmd=%s:%s range=%lld:%lld " + "fileid=%02x:%02x:%llu fhandle=0x%08x " + "stateid=%d:0x%08x lockstateid=%d:0x%08x", + __entry->error, + show_nfsv4_errors(__entry->error), + show_lock_cmd(__entry->cmd), + show_lock_type(__entry->type), + (long long)__entry->start, + (long long)__entry->end, + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + __entry->stateid_seq, __entry->stateid_hash, + __entry->lockstateid_seq, __entry->lockstateid_hash + ) +); + DECLARE_EVENT_CLASS(nfs4_set_delegation_event, TP_PROTO( const struct inode *inode, @@ -621,20 +759,28 @@ TRACE_EVENT(nfs4_delegreturn_exit, __field(dev_t, dev) __field(u32, fhandle) __field(int, error) + __field(int, stateid_seq) + __field(u32, stateid_hash) ), TP_fast_assign( __entry->dev = res->server->s_dev; __entry->fhandle = nfs_fhandle_hash(args->fhandle); __entry->error = error; + __entry->stateid_seq = + be32_to_cpu(args->stateid->seqid); + __entry->stateid_hash = + nfs_stateid_hash(args->stateid); ), TP_printk( - "error=%d (%s) dev=%02x:%02x fhandle=0x%08x", + "error=%d (%s) dev=%02x:%02x fhandle=0x%08x " + "stateid=%d:0x%08x", __entry->error, show_nfsv4_errors(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), - __entry->fhandle + __entry->fhandle, + __entry->stateid_seq, __entry->stateid_hash ) ); @@ -653,6 +799,8 @@ DECLARE_EVENT_CLASS(nfs4_test_stateid_event, __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) + __field(int, stateid_seq) + __field(u32, stateid_hash) ), TP_fast_assign( @@ -662,15 +810,21 @@ DECLARE_EVENT_CLASS(nfs4_test_stateid_event, __entry->dev = inode->i_sb->s_dev; __entry->fileid = NFS_FILEID(inode); __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + __entry->stateid_seq = + be32_to_cpu(state->stateid.seqid); + __entry->stateid_hash = + nfs_stateid_hash(&state->stateid); ), TP_printk( - "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x", + "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " + "stateid=%d:0x%08x", __entry->error, show_nfsv4_errors(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, - __entry->fhandle + __entry->fhandle, + __entry->stateid_seq, __entry->stateid_hash ) ); @@ -820,7 +974,6 @@ DECLARE_EVENT_CLASS(nfs4_inode_event, ), \ TP_ARGS(inode, error)) -DEFINE_NFS4_INODE_EVENT(nfs4_setattr); DEFINE_NFS4_INODE_EVENT(nfs4_access); DEFINE_NFS4_INODE_EVENT(nfs4_readlink); DEFINE_NFS4_INODE_EVENT(nfs4_readdir); @@ -830,8 +983,59 @@ DEFINE_NFS4_INODE_EVENT(nfs4_set_acl); DEFINE_NFS4_INODE_EVENT(nfs4_get_security_label); DEFINE_NFS4_INODE_EVENT(nfs4_set_security_label); #endif /* CONFIG_NFS_V4_SECURITY_LABEL */ -DEFINE_NFS4_INODE_EVENT(nfs4_recall_delegation); -DEFINE_NFS4_INODE_EVENT(nfs4_delegreturn); + +DECLARE_EVENT_CLASS(nfs4_inode_stateid_event, + TP_PROTO( + const struct inode *inode, + const nfs4_stateid *stateid, + int error + ), + + TP_ARGS(inode, stateid, error), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(int, error) + __field(int, stateid_seq) + __field(u32, stateid_hash) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = NFS_FILEID(inode); + __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + __entry->error = error; + __entry->stateid_seq = + be32_to_cpu(stateid->seqid); + __entry->stateid_hash = + nfs_stateid_hash(stateid); + ), + + TP_printk( + "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " + "stateid=%d:0x%08x", + __entry->error, + show_nfsv4_errors(__entry->error), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + __entry->stateid_seq, __entry->stateid_hash + ) +); + +#define DEFINE_NFS4_INODE_STATEID_EVENT(name) \ + DEFINE_EVENT(nfs4_inode_stateid_event, name, \ + TP_PROTO( \ + const struct inode *inode, \ + const nfs4_stateid *stateid, \ + int error \ + ), \ + TP_ARGS(inode, stateid, error)) + +DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_setattr); +DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_delegreturn); DECLARE_EVENT_CLASS(nfs4_getattr_event, TP_PROTO( @@ -941,8 +1145,74 @@ DECLARE_EVENT_CLASS(nfs4_inode_callback_event, ), \ TP_ARGS(clp, fhandle, inode, error)) DEFINE_NFS4_INODE_CALLBACK_EVENT(nfs4_cb_getattr); -DEFINE_NFS4_INODE_CALLBACK_EVENT(nfs4_cb_layoutrecall_inode); +DECLARE_EVENT_CLASS(nfs4_inode_stateid_callback_event, + TP_PROTO( + const struct nfs_client *clp, + const struct nfs_fh *fhandle, + const struct inode *inode, + const nfs4_stateid *stateid, + int error + ), + + TP_ARGS(clp, fhandle, inode, stateid, error), + + TP_STRUCT__entry( + __field(int, error) + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __string(dstaddr, clp ? + rpc_peeraddr2str(clp->cl_rpcclient, + RPC_DISPLAY_ADDR) : "unknown") + __field(int, stateid_seq) + __field(u32, stateid_hash) + ), + + TP_fast_assign( + __entry->error = error; + __entry->fhandle = nfs_fhandle_hash(fhandle); + if (inode != NULL) { + __entry->fileid = NFS_FILEID(inode); + __entry->dev = inode->i_sb->s_dev; + } else { + __entry->fileid = 0; + __entry->dev = 0; + } + __assign_str(dstaddr, clp ? + rpc_peeraddr2str(clp->cl_rpcclient, + RPC_DISPLAY_ADDR) : "unknown") + __entry->stateid_seq = + be32_to_cpu(stateid->seqid); + __entry->stateid_hash = + nfs_stateid_hash(stateid); + ), + + TP_printk( + "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " + "stateid=%d:0x%08x dstaddr=%s", + __entry->error, + show_nfsv4_errors(__entry->error), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + __entry->stateid_seq, __entry->stateid_hash, + __get_str(dstaddr) + ) +); + +#define DEFINE_NFS4_INODE_STATEID_CALLBACK_EVENT(name) \ + DEFINE_EVENT(nfs4_inode_stateid_callback_event, name, \ + TP_PROTO( \ + const struct nfs_client *clp, \ + const struct nfs_fh *fhandle, \ + const struct inode *inode, \ + const nfs4_stateid *stateid, \ + int error \ + ), \ + TP_ARGS(clp, fhandle, inode, stateid, error)) +DEFINE_NFS4_INODE_STATEID_CALLBACK_EVENT(nfs4_cb_recall); +DEFINE_NFS4_INODE_STATEID_CALLBACK_EVENT(nfs4_cb_layoutrecall_file); DECLARE_EVENT_CLASS(nfs4_idmap_event, TP_PROTO( @@ -1005,28 +1275,37 @@ DECLARE_EVENT_CLASS(nfs4_read_event, __field(loff_t, offset) __field(size_t, count) __field(int, error) + __field(int, stateid_seq) + __field(u32, stateid_hash) ), TP_fast_assign( const struct inode *inode = hdr->inode; + const struct nfs4_state *state = + hdr->args.context->state; __entry->dev = inode->i_sb->s_dev; __entry->fileid = NFS_FILEID(inode); __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); __entry->offset = hdr->args.offset; __entry->count = hdr->args.count; __entry->error = error; + __entry->stateid_seq = + be32_to_cpu(state->stateid.seqid); + __entry->stateid_hash = + nfs_stateid_hash(&state->stateid); ), TP_printk( "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " - "offset=%lld count=%zu", + "offset=%lld count=%zu stateid=%d:0x%08x", __entry->error, show_nfsv4_errors(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, - __entry->count + __entry->count, + __entry->stateid_seq, __entry->stateid_hash ) ); #define DEFINE_NFS4_READ_EVENT(name) \ @@ -1056,28 +1335,37 @@ DECLARE_EVENT_CLASS(nfs4_write_event, __field(loff_t, offset) __field(size_t, count) __field(int, error) + __field(int, stateid_seq) + __field(u32, stateid_hash) ), TP_fast_assign( const struct inode *inode = hdr->inode; + const struct nfs4_state *state = + hdr->args.context->state; __entry->dev = inode->i_sb->s_dev; __entry->fileid = NFS_FILEID(inode); __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); __entry->offset = hdr->args.offset; __entry->count = hdr->args.count; __entry->error = error; + __entry->stateid_seq = + be32_to_cpu(state->stateid.seqid); + __entry->stateid_hash = + nfs_stateid_hash(&state->stateid); ), TP_printk( "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " - "offset=%lld count=%zu", + "offset=%lld count=%zu stateid=%d:0x%08x", __entry->error, show_nfsv4_errors(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, - __entry->count + __entry->count, + __entry->stateid_seq, __entry->stateid_hash ) ); @@ -1154,10 +1442,11 @@ TRACE_EVENT(nfs4_layoutget, const struct nfs_open_context *ctx, const struct pnfs_layout_range *args, const struct pnfs_layout_range *res, + const nfs4_stateid *layout_stateid, int error ), - TP_ARGS(ctx, args, res, error), + TP_ARGS(ctx, args, res, layout_stateid, error), TP_STRUCT__entry( __field(dev_t, dev) @@ -1167,10 +1456,15 @@ TRACE_EVENT(nfs4_layoutget, __field(u64, offset) __field(u64, count) __field(int, error) + __field(int, stateid_seq) + __field(u32, stateid_hash) + __field(int, layoutstateid_seq) + __field(u32, layoutstateid_hash) ), TP_fast_assign( const struct inode *inode = d_inode(ctx->dentry); + const struct nfs4_state *state = ctx->state; __entry->dev = inode->i_sb->s_dev; __entry->fileid = NFS_FILEID(inode); __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); @@ -1178,11 +1472,25 @@ TRACE_EVENT(nfs4_layoutget, __entry->offset = args->offset; __entry->count = args->length; __entry->error = error; + __entry->stateid_seq = + be32_to_cpu(state->stateid.seqid); + __entry->stateid_hash = + nfs_stateid_hash(&state->stateid); + if (!error) { + __entry->layoutstateid_seq = + be32_to_cpu(layout_stateid->seqid); + __entry->layoutstateid_hash = + nfs_stateid_hash(layout_stateid); + } else { + __entry->layoutstateid_seq = 0; + __entry->layoutstateid_hash = 0; + } ), TP_printk( "error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " - "iomode=%s offset=%llu count=%llu", + "iomode=%s offset=%llu count=%llu stateid=%d:0x%08x " + "layoutstateid=%d:0x%08x", __entry->error, show_nfsv4_errors(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), @@ -1190,14 +1498,83 @@ TRACE_EVENT(nfs4_layoutget, __entry->fhandle, show_pnfs_iomode(__entry->iomode), (unsigned long long)__entry->offset, - (unsigned long long)__entry->count + (unsigned long long)__entry->count, + __entry->stateid_seq, __entry->stateid_hash, + __entry->layoutstateid_seq, __entry->layoutstateid_hash ) ); -DEFINE_NFS4_INODE_EVENT(nfs4_layoutcommit); -DEFINE_NFS4_INODE_EVENT(nfs4_layoutreturn); +DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_layoutcommit); +DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_layoutreturn); DEFINE_NFS4_INODE_EVENT(nfs4_layoutreturn_on_close); +#define show_pnfs_update_layout_reason(reason) \ + __print_symbolic(reason, \ + { PNFS_UPDATE_LAYOUT_UNKNOWN, "unknown" }, \ + { PNFS_UPDATE_LAYOUT_NO_PNFS, "no pnfs" }, \ + { PNFS_UPDATE_LAYOUT_RD_ZEROLEN, "read+zerolen" }, \ + { PNFS_UPDATE_LAYOUT_MDSTHRESH, "mdsthresh" }, \ + { PNFS_UPDATE_LAYOUT_NOMEM, "nomem" }, \ + { PNFS_UPDATE_LAYOUT_BULK_RECALL, "bulk recall" }, \ + { PNFS_UPDATE_LAYOUT_IO_TEST_FAIL, "io test fail" }, \ + { PNFS_UPDATE_LAYOUT_FOUND_CACHED, "found cached" }, \ + { PNFS_UPDATE_LAYOUT_RETURN, "layoutreturn" }, \ + { PNFS_UPDATE_LAYOUT_BLOCKED, "layouts blocked" }, \ + { PNFS_UPDATE_LAYOUT_SEND_LAYOUTGET, "sent layoutget" }) + +TRACE_EVENT(pnfs_update_layout, + TP_PROTO(struct inode *inode, + loff_t pos, + u64 count, + enum pnfs_iomode iomode, + struct pnfs_layout_hdr *lo, + enum pnfs_update_layout_reason reason + ), + TP_ARGS(inode, pos, count, iomode, lo, reason), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u64, fileid) + __field(u32, fhandle) + __field(loff_t, pos) + __field(u64, count) + __field(enum pnfs_iomode, iomode) + __field(int, layoutstateid_seq) + __field(u32, layoutstateid_hash) + __field(enum pnfs_update_layout_reason, reason) + ), + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = NFS_FILEID(inode); + __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + __entry->pos = pos; + __entry->count = count; + __entry->iomode = iomode; + __entry->reason = reason; + if (lo != NULL) { + __entry->layoutstateid_seq = + be32_to_cpu(lo->plh_stateid.seqid); + __entry->layoutstateid_hash = + nfs_stateid_hash(&lo->plh_stateid); + } else { + __entry->layoutstateid_seq = 0; + __entry->layoutstateid_hash = 0; + } + ), + TP_printk( + "fileid=%02x:%02x:%llu fhandle=0x%08x " + "iomode=%s pos=%llu count=%llu " + "layoutstateid=%d:0x%08x (%s)", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + show_pnfs_iomode(__entry->iomode), + (unsigned long long)__entry->pos, + (unsigned long long)__entry->count, + __entry->layoutstateid_seq, __entry->layoutstateid_hash, + show_pnfs_update_layout_reason(__entry->reason) + ) +); + #endif /* CONFIG_NFS_V4_1 */ #endif /* _TRACE_NFS4_H */ diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 59f838cdc009..9f80a086b612 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -39,7 +39,6 @@ { 1 << NFS_INO_INVALIDATING, "INVALIDATING" }, \ { 1 << NFS_INO_FLUSHING, "FLUSHING" }, \ { 1 << NFS_INO_FSCACHE, "FSCACHE" }, \ - { 1 << NFS_INO_COMMIT, "COMMIT" }, \ { 1 << NFS_INO_LAYOUTCOMMIT, "NEED_LAYOUTCOMMIT" }, \ { 1 << NFS_INO_LAYOUTCOMMITTING, "LAYOUTCOMMIT" }) diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 452a011ba0d8..8ce4f61cbaa5 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -101,53 +101,18 @@ nfs_page_free(struct nfs_page *p) kmem_cache_free(nfs_page_cachep, p); } -static void -nfs_iocounter_inc(struct nfs_io_counter *c) -{ - atomic_inc(&c->io_count); -} - -static void -nfs_iocounter_dec(struct nfs_io_counter *c) -{ - if (atomic_dec_and_test(&c->io_count)) { - clear_bit(NFS_IO_INPROGRESS, &c->flags); - smp_mb__after_atomic(); - wake_up_bit(&c->flags, NFS_IO_INPROGRESS); - } -} - -static int -__nfs_iocounter_wait(struct nfs_io_counter *c) -{ - wait_queue_head_t *wq = bit_waitqueue(&c->flags, NFS_IO_INPROGRESS); - DEFINE_WAIT_BIT(q, &c->flags, NFS_IO_INPROGRESS); - int ret = 0; - - do { - prepare_to_wait(wq, &q.wait, TASK_KILLABLE); - set_bit(NFS_IO_INPROGRESS, &c->flags); - if (atomic_read(&c->io_count) == 0) - break; - ret = nfs_wait_bit_killable(&q.key, TASK_KILLABLE); - } while (atomic_read(&c->io_count) != 0 && !ret); - finish_wait(wq, &q.wait); - return ret; -} - /** * nfs_iocounter_wait - wait for i/o to complete - * @c: nfs_io_counter to use + * @l_ctx: nfs_lock_context with io_counter to use * * returns -ERESTARTSYS if interrupted by a fatal signal. * Otherwise returns 0 once the io_count hits 0. */ int -nfs_iocounter_wait(struct nfs_io_counter *c) +nfs_iocounter_wait(struct nfs_lock_context *l_ctx) { - if (atomic_read(&c->io_count) == 0) - return 0; - return __nfs_iocounter_wait(c); + return wait_on_atomic_t(&l_ctx->io_count, nfs_wait_atomic_killable, + TASK_KILLABLE); } /* @@ -370,7 +335,7 @@ nfs_create_request(struct nfs_open_context *ctx, struct page *page, return ERR_CAST(l_ctx); } req->wb_lock_context = l_ctx; - nfs_iocounter_inc(&l_ctx->io_count); + atomic_inc(&l_ctx->io_count); /* Initialize the request struct. Initially, we assume a * long write-back delay. This will be adjusted in @@ -431,7 +396,8 @@ static void nfs_clear_request(struct nfs_page *req) req->wb_page = NULL; } if (l_ctx != NULL) { - nfs_iocounter_dec(&l_ctx->io_count); + if (atomic_dec_and_test(&l_ctx->io_count)) + wake_up_atomic_t(&l_ctx->io_count); nfs_put_lock_context(l_ctx); req->wb_lock_context = NULL; } @@ -664,22 +630,11 @@ EXPORT_SYMBOL_GPL(nfs_initiate_pgio); * @desc: IO descriptor * @hdr: pageio header */ -static int nfs_pgio_error(struct nfs_pageio_descriptor *desc, - struct nfs_pgio_header *hdr) +static void nfs_pgio_error(struct nfs_pgio_header *hdr) { - struct nfs_pgio_mirror *mirror; - u32 midx; - set_bit(NFS_IOHDR_REDO, &hdr->flags); nfs_pgio_data_destroy(hdr); hdr->completion_ops->completion(hdr); - /* TODO: Make sure it's right to clean up all mirrors here - * and not just hdr->pgio_mirror_idx */ - for (midx = 0; midx < desc->pg_mirror_count; midx++) { - mirror = &desc->pg_mirrors[midx]; - desc->pg_completion_ops->error_cleanup(&mirror->pg_list); - } - return -ENOMEM; } /** @@ -800,8 +755,11 @@ int nfs_generic_pgio(struct nfs_pageio_descriptor *desc, unsigned int pagecount, pageused; pagecount = nfs_page_array_len(mirror->pg_base, mirror->pg_count); - if (!nfs_pgarray_set(&hdr->page_array, pagecount)) - return nfs_pgio_error(desc, hdr); + if (!nfs_pgarray_set(&hdr->page_array, pagecount)) { + nfs_pgio_error(hdr); + desc->pg_error = -ENOMEM; + return desc->pg_error; + } nfs_init_cinfo(&cinfo, desc->pg_inode, desc->pg_dreq); pages = hdr->page_array.pagevec; @@ -819,8 +777,11 @@ int nfs_generic_pgio(struct nfs_pageio_descriptor *desc, *pages++ = last_page = req->wb_page; } } - if (WARN_ON_ONCE(pageused != pagecount)) - return nfs_pgio_error(desc, hdr); + if (WARN_ON_ONCE(pageused != pagecount)) { + nfs_pgio_error(hdr); + desc->pg_error = -EINVAL; + return desc->pg_error; + } if ((desc->pg_ioflags & FLUSH_COND_STABLE) && (desc->pg_moreio || nfs_reqs_to_commit(&cinfo))) @@ -835,18 +796,13 @@ EXPORT_SYMBOL_GPL(nfs_generic_pgio); static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc) { - struct nfs_pgio_mirror *mirror; struct nfs_pgio_header *hdr; int ret; - mirror = nfs_pgio_current_mirror(desc); - hdr = nfs_pgio_header_alloc(desc->pg_rw_ops); if (!hdr) { - /* TODO: make sure this is right with mirroring - or - * should it back out all mirrors? */ - desc->pg_completion_ops->error_cleanup(&mirror->pg_list); - return -ENOMEM; + desc->pg_error = -ENOMEM; + return desc->pg_error; } nfs_pgheader_init(desc, hdr, nfs_pgio_header_free); ret = nfs_generic_pgio(desc, hdr); @@ -874,6 +830,9 @@ static int nfs_pageio_setup_mirroring(struct nfs_pageio_descriptor *pgio, mirror_count = pgio->pg_ops->pg_get_mirror_count(pgio, req); + if (pgio->pg_error < 0) + return pgio->pg_error; + if (!mirror_count || mirror_count > NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX) return -EINVAL; @@ -903,12 +862,6 @@ static void nfs_pageio_cleanup_mirroring(struct nfs_pageio_descriptor *pgio) pgio->pg_mirrors_dynamic = NULL; } -static bool nfs_match_open_context(const struct nfs_open_context *ctx1, - const struct nfs_open_context *ctx2) -{ - return ctx1->cred == ctx2->cred && ctx1->state == ctx2->state; -} - static bool nfs_match_lock_context(const struct nfs_lock_context *l1, const struct nfs_lock_context *l2) { @@ -982,6 +935,8 @@ static int nfs_pageio_do_add_request(struct nfs_pageio_descriptor *desc, } else { if (desc->pg_ops->pg_init) desc->pg_ops->pg_init(desc, req); + if (desc->pg_error < 0) + return 0; mirror->pg_base = req->wb_pgbase; } if (!nfs_can_coalesce_requests(prev, req, desc)) @@ -1147,6 +1102,8 @@ int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, bytes = req->wb_bytes; nfs_pageio_setup_mirroring(desc, req); + if (desc->pg_error < 0) + goto out_failed; for (midx = 0; midx < desc->pg_mirror_count; midx++) { if (midx) { @@ -1163,7 +1120,8 @@ int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, if (IS_ERR(dupreq)) { nfs_page_group_unlock(req); - return 0; + desc->pg_error = PTR_ERR(dupreq); + goto out_failed; } nfs_lock_request(dupreq); @@ -1176,10 +1134,32 @@ int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, if (nfs_pgio_has_mirroring(desc)) desc->pg_mirror_idx = midx; if (!nfs_pageio_add_request_mirror(desc, dupreq)) - return 0; + goto out_failed; } return 1; + +out_failed: + /* + * We might have failed before sending any reqs over wire. + * Clean up rest of the reqs in mirror pg_list. + */ + if (desc->pg_error) { + struct nfs_pgio_mirror *mirror; + void (*func)(struct list_head *); + + /* remember fatal errors */ + if (nfs_error_is_fatal(desc->pg_error)) + mapping_set_error(desc->pg_inode->i_mapping, + desc->pg_error); + + func = desc->pg_completion_ops->error_cleanup; + for (midx = 0; midx < desc->pg_mirror_count; midx++) { + mirror = &desc->pg_mirrors[midx]; + func(&mirror->pg_list); + } + } + return 0; } /* @@ -1232,7 +1212,7 @@ int nfs_pageio_resend(struct nfs_pageio_descriptor *desc, nfs_pageio_complete(desc); if (!list_empty(&failed)) { list_move(&failed, &hdr->pages); - return -EIO; + return desc->pg_error < 0 ? desc->pg_error : -EIO; } return 0; } diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index bec0384499f7..a3592cc34a20 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -53,7 +53,7 @@ static DEFINE_SPINLOCK(pnfs_spinlock); static LIST_HEAD(pnfs_modules_tbl); static int -pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid, +pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, const nfs4_stateid *stateid, enum pnfs_iomode iomode, bool sync); /* Return the registered pnfs layout driver module matching given id */ @@ -385,13 +385,13 @@ static void pnfs_layoutreturn_before_put_lseg(struct pnfs_layout_segment *lseg, enum pnfs_iomode iomode; bool send; - stateid = lo->plh_stateid; + nfs4_stateid_copy(&stateid, &lo->plh_stateid); iomode = lo->plh_return_iomode; send = pnfs_prepare_layoutreturn(lo); spin_unlock(&inode->i_lock); if (send) { /* Send an async layoutreturn so we dont deadlock */ - pnfs_send_layoutreturn(lo, stateid, iomode, false); + pnfs_send_layoutreturn(lo, &stateid, iomode, false); } } else spin_unlock(&inode->i_lock); @@ -566,10 +566,10 @@ static int mark_lseg_invalid(struct pnfs_layout_segment *lseg, int pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo, struct list_head *tmp_list, - struct pnfs_layout_range *recall_range) + const struct pnfs_layout_range *recall_range) { struct pnfs_layout_segment *lseg, *next; - int invalid = 0, removed = 0; + int remaining = 0; dprintk("%s:Begin lo %p\n", __func__, lo); @@ -582,11 +582,11 @@ pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo, "offset %llu length %llu\n", __func__, lseg, lseg->pls_range.iomode, lseg->pls_range.offset, lseg->pls_range.length); - invalid++; - removed += mark_lseg_invalid(lseg, tmp_list); + if (!mark_lseg_invalid(lseg, tmp_list)) + remaining++; } - dprintk("%s:Return %i\n", __func__, invalid - removed); - return invalid - removed; + dprintk("%s:Return %i\n", __func__, remaining); + return remaining; } /* note free_me must contain lsegs from a single layout_hdr */ @@ -618,7 +618,6 @@ pnfs_destroy_layout(struct nfs_inode *nfsi) pnfs_get_layout_hdr(lo); pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RO_FAILED); pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RW_FAILED); - pnfs_clear_retry_layoutget(lo); spin_unlock(&nfsi->vfs_inode.i_lock); pnfs_free_lseg_list(&tmp_list); pnfs_put_layout_hdr(lo); @@ -703,6 +702,8 @@ pnfs_layout_free_bulk_destroy_list(struct list_head *layout_list, ret = -EAGAIN; spin_unlock(&inode->i_lock); pnfs_free_lseg_list(&lseg_list); + /* Free all lsegs that are attached to commit buckets */ + nfs_commit_inode(inode, 0); pnfs_put_layout_hdr(lo); iput(inode); } @@ -826,7 +827,7 @@ pnfs_layoutgets_blocked(const struct pnfs_layout_hdr *lo) int pnfs_choose_layoutget_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo, - struct pnfs_layout_range *range, + const struct pnfs_layout_range *range, struct nfs4_state *open_state) { int status = 0; @@ -861,7 +862,7 @@ pnfs_choose_layoutget_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo, static struct pnfs_layout_segment * send_layoutget(struct pnfs_layout_hdr *lo, struct nfs_open_context *ctx, - struct pnfs_layout_range *range, + const struct pnfs_layout_range *range, gfp_t gfp_flags) { struct inode *ino = lo->plh_inode; @@ -894,7 +895,7 @@ send_layoutget(struct pnfs_layout_hdr *lo, lgp->args.minlength = i_size - range->offset; } lgp->args.maxcount = PNFS_LAYOUT_MAXSIZE; - lgp->args.range = *range; + pnfs_copy_range(&lgp->args.range, range); lgp->args.type = server->pnfs_curr_ld->id; lgp->args.inode = ino; lgp->args.ctx = get_nfs_open_context(ctx); @@ -904,17 +905,9 @@ send_layoutget(struct pnfs_layout_hdr *lo, lseg = nfs4_proc_layoutget(lgp, gfp_flags); } while (lseg == ERR_PTR(-EAGAIN)); - if (IS_ERR(lseg)) { - switch (PTR_ERR(lseg)) { - case -ENOMEM: - case -ERESTARTSYS: - break; - default: - /* remember that LAYOUTGET failed and suspend trying */ - pnfs_layout_io_set_failed(lo, range->iomode); - } - return NULL; - } else + if (IS_ERR(lseg) && !nfs_error_is_fatal(PTR_ERR(lseg))) + lseg = NULL; + else pnfs_layout_clear_fail_bit(lo, pnfs_iomode_to_fail_bit(range->iomode)); @@ -945,7 +938,7 @@ void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo) } static int -pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid, +pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, const nfs4_stateid *stateid, enum pnfs_iomode iomode, bool sync) { struct inode *ino = lo->plh_inode; @@ -962,7 +955,7 @@ pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid, goto out; } - lrp->args.stateid = stateid; + nfs4_stateid_copy(&lrp->args.stateid, stateid); lrp->args.layout_type = NFS_SERVER(ino)->pnfs_curr_ld->id; lrp->args.inode = ino; lrp->args.range.iomode = iomode; @@ -1005,7 +998,7 @@ _pnfs_return_layout(struct inode *ino) dprintk("NFS: %s no layout to return\n", __func__); goto out; } - stateid = nfsi->layout->plh_stateid; + nfs4_stateid_copy(&stateid, &nfsi->layout->plh_stateid); /* Reference matched in nfs4_layoutreturn_release */ pnfs_get_layout_hdr(lo); empty = list_empty(&lo->plh_segs); @@ -1033,7 +1026,7 @@ _pnfs_return_layout(struct inode *ino) spin_unlock(&ino->i_lock); pnfs_free_lseg_list(&tmp_list); if (send) - status = pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, true); + status = pnfs_send_layoutreturn(lo, &stateid, IOMODE_ANY, true); out_put_layout_hdr: pnfs_put_layout_hdr(lo); out: @@ -1096,13 +1089,12 @@ bool pnfs_roc(struct inode *ino) goto out_noroc; } - stateid = lo->plh_stateid; + nfs4_stateid_copy(&stateid, &lo->plh_stateid); /* always send layoutreturn if being marked so */ if (test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &lo->plh_flags)) layoutreturn = pnfs_prepare_layoutreturn(lo); - pnfs_clear_retry_layoutget(lo); list_for_each_entry_safe(lseg, tmp, &lo->plh_segs, pls_list) /* If we are sending layoutreturn, invalidate all valid lsegs */ if (layoutreturn || test_bit(NFS_LSEG_ROC, &lseg->pls_flags)) { @@ -1124,7 +1116,7 @@ out_noroc: pnfs_free_lseg_list(&tmp_list); pnfs_layoutcommit_inode(ino, true); if (layoutreturn) - pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, true); + pnfs_send_layoutreturn(lo, &stateid, IOMODE_ANY, true); return roc; } @@ -1149,6 +1141,7 @@ void pnfs_roc_set_barrier(struct inode *ino, u32 barrier) spin_lock(&ino->i_lock); lo = NFS_I(ino)->layout; + pnfs_mark_layout_returned_if_empty(lo); if (pnfs_seqid_is_newer(barrier, lo->plh_barrier)) lo->plh_barrier = barrier; spin_unlock(&ino->i_lock); @@ -1465,25 +1458,15 @@ static bool pnfs_within_mdsthreshold(struct nfs_open_context *ctx, return ret; } -/* stop waiting if someone clears NFS_LAYOUT_RETRY_LAYOUTGET bit. */ -static int pnfs_layoutget_retry_bit_wait(struct wait_bit_key *key, int mode) -{ - if (!test_bit(NFS_LAYOUT_RETRY_LAYOUTGET, key->flags)) - return 1; - return nfs_wait_bit_killable(key, mode); -} - static bool pnfs_prepare_to_retry_layoutget(struct pnfs_layout_hdr *lo) { - if (!pnfs_should_retry_layoutget(lo)) - return false; /* * send layoutcommit as it can hold up layoutreturn due to lseg * reference */ pnfs_layoutcommit_inode(lo->plh_inode, false); return !wait_on_bit_action(&lo->plh_flags, NFS_LAYOUT_RETURN, - pnfs_layoutget_retry_bit_wait, + nfs_wait_bit_killable, TASK_UNINTERRUPTIBLE); } @@ -1520,14 +1503,23 @@ pnfs_update_layout(struct inode *ino, struct pnfs_layout_segment *lseg = NULL; bool first; - if (!pnfs_enabled_sb(NFS_SERVER(ino))) + if (!pnfs_enabled_sb(NFS_SERVER(ino))) { + trace_pnfs_update_layout(ino, pos, count, iomode, NULL, + PNFS_UPDATE_LAYOUT_NO_PNFS); goto out; + } - if (iomode == IOMODE_READ && i_size_read(ino) == 0) + if (iomode == IOMODE_READ && i_size_read(ino) == 0) { + trace_pnfs_update_layout(ino, pos, count, iomode, NULL, + PNFS_UPDATE_LAYOUT_RD_ZEROLEN); goto out; + } - if (pnfs_within_mdsthreshold(ctx, ino, iomode)) + if (pnfs_within_mdsthreshold(ctx, ino, iomode)) { + trace_pnfs_update_layout(ino, pos, count, iomode, NULL, + PNFS_UPDATE_LAYOUT_MDSTHRESH); goto out; + } lookup_again: first = false; @@ -1535,19 +1527,25 @@ lookup_again: lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags); if (lo == NULL) { spin_unlock(&ino->i_lock); + trace_pnfs_update_layout(ino, pos, count, iomode, NULL, + PNFS_UPDATE_LAYOUT_NOMEM); goto out; } /* Do we even need to bother with this? */ if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags)) { + trace_pnfs_update_layout(ino, pos, count, iomode, lo, + PNFS_UPDATE_LAYOUT_BULK_RECALL); dprintk("%s matches recall, use MDS\n", __func__); goto out_unlock; } /* if LAYOUTGET already failed once we don't try again */ - if (pnfs_layout_io_test_failed(lo, iomode) && - !pnfs_should_retry_layoutget(lo)) + if (pnfs_layout_io_test_failed(lo, iomode)) { + trace_pnfs_update_layout(ino, pos, count, iomode, lo, + PNFS_UPDATE_LAYOUT_IO_TEST_FAIL); goto out_unlock; + } first = list_empty(&lo->plh_segs); if (first) { @@ -1567,8 +1565,11 @@ lookup_again: * already exists */ lseg = pnfs_find_lseg(lo, &arg); - if (lseg) + if (lseg) { + trace_pnfs_update_layout(ino, pos, count, iomode, lo, + PNFS_UPDATE_LAYOUT_FOUND_CACHED); goto out_unlock; + } } /* @@ -1585,11 +1586,16 @@ lookup_again: dprintk("%s retrying\n", __func__); goto lookup_again; } + trace_pnfs_update_layout(ino, pos, count, iomode, lo, + PNFS_UPDATE_LAYOUT_RETURN); goto out_put_layout_hdr; } - if (pnfs_layoutgets_blocked(lo)) + if (pnfs_layoutgets_blocked(lo)) { + trace_pnfs_update_layout(ino, pos, count, iomode, lo, + PNFS_UPDATE_LAYOUT_BLOCKED); goto out_unlock; + } atomic_inc(&lo->plh_outstanding); spin_unlock(&ino->i_lock); @@ -1612,8 +1618,9 @@ lookup_again: arg.length = PAGE_CACHE_ALIGN(arg.length); lseg = send_layoutget(lo, ctx, &arg, gfp_flags); - pnfs_clear_retry_layoutget(lo); atomic_dec(&lo->plh_outstanding); + trace_pnfs_update_layout(ino, pos, count, iomode, lo, + PNFS_UPDATE_LAYOUT_SEND_LAYOUTGET); out_put_layout_hdr: if (first) pnfs_clear_first_layoutget(lo); @@ -1623,7 +1630,7 @@ out: "(%s, offset: %llu, length: %llu)\n", __func__, ino->i_sb->s_id, (unsigned long long)NFS_FILEID(ino), - lseg == NULL ? "not found" : "found", + IS_ERR_OR_NULL(lseg) ? "not found" : "found", iomode==IOMODE_RW ? "read/write" : "read-only", (unsigned long long)pos, (unsigned long long)count); @@ -1730,16 +1737,29 @@ out_forget_reply: } static void +pnfs_set_plh_return_iomode(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode) +{ + if (lo->plh_return_iomode == iomode) + return; + if (lo->plh_return_iomode != 0) + iomode = IOMODE_ANY; + lo->plh_return_iomode = iomode; +} + +int pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, struct list_head *tmp_list, - struct pnfs_layout_range *return_range) + const struct pnfs_layout_range *return_range) { struct pnfs_layout_segment *lseg, *next; + int remaining = 0; dprintk("%s:Begin lo %p\n", __func__, lo); if (list_empty(&lo->plh_segs)) - return; + return 0; + + assert_spin_locked(&lo->plh_inode->i_lock); list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list) if (should_free_lseg(&lseg->pls_range, return_range)) { @@ -1749,38 +1769,47 @@ pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, lseg->pls_range.offset, lseg->pls_range.length); set_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags); - mark_lseg_invalid(lseg, tmp_list); + pnfs_set_plh_return_iomode(lo, return_range->iomode); + if (!mark_lseg_invalid(lseg, tmp_list)) + remaining++; set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &lo->plh_flags); } + return remaining; } void pnfs_error_mark_layout_for_return(struct inode *inode, struct pnfs_layout_segment *lseg) { struct pnfs_layout_hdr *lo = NFS_I(inode)->layout; - int iomode = pnfs_iomode_to_fail_bit(lseg->pls_range.iomode); struct pnfs_layout_range range = { .iomode = lseg->pls_range.iomode, .offset = 0, .length = NFS4_MAX_UINT64, }; LIST_HEAD(free_me); + bool return_now = false; spin_lock(&inode->i_lock); - /* set failure bit so that pnfs path will be retried later */ - pnfs_layout_set_fail_bit(lo, iomode); - if (lo->plh_return_iomode == 0) - lo->plh_return_iomode = range.iomode; - else if (lo->plh_return_iomode != range.iomode) - lo->plh_return_iomode = IOMODE_ANY; + pnfs_set_plh_return_iomode(lo, range.iomode); /* * mark all matching lsegs so that we are sure to have no live * segments at hand when sending layoutreturn. See pnfs_put_lseg() * for how it works. */ - pnfs_mark_matching_lsegs_return(lo, &free_me, &range); - spin_unlock(&inode->i_lock); + if (!pnfs_mark_matching_lsegs_return(lo, &free_me, &range)) { + nfs4_stateid stateid; + enum pnfs_iomode iomode = lo->plh_return_iomode; + + nfs4_stateid_copy(&stateid, &lo->plh_stateid); + return_now = pnfs_prepare_layoutreturn(lo); + spin_unlock(&inode->i_lock); + if (return_now) + pnfs_send_layoutreturn(lo, &stateid, iomode, false); + } else { + spin_unlock(&inode->i_lock); + nfs_commit_inode(inode, 0); + } pnfs_free_lseg_list(&free_me); } EXPORT_SYMBOL_GPL(pnfs_error_mark_layout_for_return); @@ -1802,6 +1831,11 @@ pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *r rd_size, IOMODE_READ, GFP_KERNEL); + if (IS_ERR(pgio->pg_lseg)) { + pgio->pg_error = PTR_ERR(pgio->pg_lseg); + pgio->pg_lseg = NULL; + return; + } } /* If no lseg, fall back to read through mds */ if (pgio->pg_lseg == NULL) @@ -1814,13 +1848,19 @@ void pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req, u64 wb_size) { - if (pgio->pg_lseg == NULL) + if (pgio->pg_lseg == NULL) { pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, req->wb_context, req_offset(req), wb_size, IOMODE_RW, GFP_NOFS); + if (IS_ERR(pgio->pg_lseg)) { + pgio->pg_error = PTR_ERR(pgio->pg_lseg); + pgio->pg_lseg = NULL; + return; + } + } /* If no lseg, fall back to write through mds */ if (pgio->pg_lseg == NULL) nfs_pageio_reset_write_mds(pgio); @@ -1988,15 +2028,13 @@ static void pnfs_writehdr_free(struct nfs_pgio_header *hdr) int pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc) { - struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc); - struct nfs_pgio_header *hdr; int ret; hdr = nfs_pgio_header_alloc(desc->pg_rw_ops); if (!hdr) { - desc->pg_completion_ops->error_cleanup(&mirror->pg_list); - return -ENOMEM; + desc->pg_error = -ENOMEM; + return desc->pg_error; } nfs_pgheader_init(desc, hdr, pnfs_writehdr_free); @@ -2119,15 +2157,13 @@ static void pnfs_readhdr_free(struct nfs_pgio_header *hdr) int pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc) { - struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc); - struct nfs_pgio_header *hdr; int ret; hdr = nfs_pgio_header_alloc(desc->pg_rw_ops); if (!hdr) { - desc->pg_completion_ops->error_cleanup(&mirror->pg_list); - return -ENOMEM; + desc->pg_error = -ENOMEM; + return desc->pg_error; } nfs_pgheader_init(desc, hdr, pnfs_readhdr_free); hdr->lseg = pnfs_get_lseg(desc->pg_lseg); diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index d1990e90e7a0..9f4e2a47f4aa 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -98,7 +98,6 @@ enum { NFS_LAYOUT_RETURN_BEFORE_CLOSE, /* Return this layout before close */ NFS_LAYOUT_INVALID_STID, /* layout stateid id is invalid */ NFS_LAYOUT_FIRST_LAYOUTGET, /* Serialize first layoutget */ - NFS_LAYOUT_RETRY_LAYOUTGET, /* Retry layoutget */ }; enum layoutdriver_policy_flags { @@ -261,11 +260,14 @@ void pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo, bool update_barrier); int pnfs_choose_layoutget_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo, - struct pnfs_layout_range *range, + const struct pnfs_layout_range *range, struct nfs4_state *open_state); int pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo, struct list_head *tmp_list, - struct pnfs_layout_range *recall_range); + const struct pnfs_layout_range *recall_range); +int pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, + struct list_head *tmp_list, + const struct pnfs_layout_range *recall_range); bool pnfs_roc(struct inode *ino); void pnfs_roc_release(struct inode *ino); void pnfs_roc_set_barrier(struct inode *ino, u32 barrier); @@ -379,26 +381,6 @@ nfs4_get_deviceid(struct nfs4_deviceid_node *d) return d; } -static inline void pnfs_set_retry_layoutget(struct pnfs_layout_hdr *lo) -{ - if (!test_and_set_bit(NFS_LAYOUT_RETRY_LAYOUTGET, &lo->plh_flags)) - atomic_inc(&lo->plh_refcount); -} - -static inline void pnfs_clear_retry_layoutget(struct pnfs_layout_hdr *lo) -{ - if (test_and_clear_bit(NFS_LAYOUT_RETRY_LAYOUTGET, &lo->plh_flags)) { - atomic_dec(&lo->plh_refcount); - /* wake up waiters for LAYOUTRETURN as that is not needed */ - wake_up_bit(&lo->plh_flags, NFS_LAYOUT_RETURN); - } -} - -static inline bool pnfs_should_retry_layoutget(struct pnfs_layout_hdr *lo) -{ - return test_bit(NFS_LAYOUT_RETRY_LAYOUTGET, &lo->plh_flags); -} - static inline struct pnfs_layout_segment * pnfs_get_lseg(struct pnfs_layout_segment *lseg) { @@ -409,6 +391,12 @@ pnfs_get_lseg(struct pnfs_layout_segment *lseg) return lseg; } +static inline bool +pnfs_is_valid_lseg(struct pnfs_layout_segment *lseg) +{ + return test_bit(NFS_LSEG_VALID, &lseg->pls_flags) != 0; +} + /* Return true if a layout driver is being used for this mountpoint */ static inline int pnfs_enabled_sb(struct nfs_server *nfss) { @@ -556,6 +544,26 @@ pnfs_calc_offset_length(u64 offset, u64 end) return 1 + end - offset; } +/** + * pnfs_mark_layout_returned_if_empty - marks the layout as returned + * @lo: layout header + * + * Note: Caller must hold inode->i_lock + */ +static inline void +pnfs_mark_layout_returned_if_empty(struct pnfs_layout_hdr *lo) +{ + if (list_empty(&lo->plh_segs)) + set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags); +} + +static inline void +pnfs_copy_range(struct pnfs_layout_range *dst, + const struct pnfs_layout_range *src) +{ + memcpy(dst, src, sizeof(*dst)); +} + extern unsigned int layoutstats_timer; #ifdef NFS_DEBUG diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 24655b807d44..81ac6480f9e7 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -266,17 +266,14 @@ pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages, } else { nfs_retry_commit(mds_pages, NULL, cinfo, 0); pnfs_generic_retry_commit(cinfo, 0); - cinfo->completion_ops->error_cleanup(NFS_I(inode)); return -ENOMEM; } } nreq += pnfs_generic_alloc_ds_commits(cinfo, &list); - if (nreq == 0) { - cinfo->completion_ops->error_cleanup(NFS_I(inode)); + if (nreq == 0) goto out; - } atomic_add(nreq, &cinfo->mds->rpcs_out); @@ -871,6 +868,11 @@ pnfs_layout_mark_request_commit(struct nfs_page *req, buckets = cinfo->ds->buckets; list = &buckets[ds_commit_idx].written; if (list_empty(list)) { + if (!pnfs_is_valid_lseg(lseg)) { + spin_unlock(cinfo->lock); + cinfo->completion_ops->resched_write(cinfo, req); + return; + } /* Non-empty buckets hold a reference on the lseg. That ref * is normally transferred to the COMMIT call and released * there. It could also be released if the last req is pulled diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 0a5e33f33b5c..eb31e23e7def 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -85,6 +85,23 @@ void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio) } EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds); +static void nfs_readpage_release(struct nfs_page *req) +{ + struct inode *inode = d_inode(req->wb_context->dentry); + + dprintk("NFS: read done (%s/%llu %d@%lld)\n", inode->i_sb->s_id, + (unsigned long long)NFS_FILEID(inode), req->wb_bytes, + (long long)req_offset(req)); + + if (nfs_page_group_sync_on_bit(req, PG_UNLOCKPAGE)) { + if (PageUptodate(req->wb_page)) + nfs_readpage_to_fscache(inode, req->wb_page, 0); + + unlock_page(req->wb_page); + } + nfs_release_request(req); +} + int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, struct page *page) { @@ -106,7 +123,10 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, nfs_pageio_init_read(&pgio, inode, false, &nfs_async_read_completion_ops); - nfs_pageio_add_request(&pgio, new); + if (!nfs_pageio_add_request(&pgio, new)) { + nfs_list_remove_request(new); + nfs_readpage_release(new); + } nfs_pageio_complete(&pgio); /* It doesn't make sense to do mirrored reads! */ @@ -115,24 +135,7 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, pgm = &pgio.pg_mirrors[0]; NFS_I(inode)->read_io += pgm->pg_bytes_written; - return 0; -} - -static void nfs_readpage_release(struct nfs_page *req) -{ - struct inode *inode = d_inode(req->wb_context->dentry); - - dprintk("NFS: read done (%s/%llu %d@%lld)\n", inode->i_sb->s_id, - (unsigned long long)NFS_FILEID(inode), req->wb_bytes, - (long long)req_offset(req)); - - if (nfs_page_group_sync_on_bit(req, PG_UNLOCKPAGE)) { - if (PageUptodate(req->wb_page)) - nfs_readpage_to_fscache(inode, req->wb_page, 0); - - unlock_page(req->wb_page); - } - nfs_release_request(req); + return pgio.pg_error < 0 ? pgio.pg_error : 0; } static void nfs_page_group_set_uptodate(struct nfs_page *req) @@ -361,6 +364,8 @@ readpage_async_filler(void *data, struct page *page) if (len < PAGE_CACHE_SIZE) zero_user_segment(page, len, PAGE_CACHE_SIZE); if (!nfs_pageio_add_request(desc->pgio, new)) { + nfs_list_remove_request(new); + nfs_readpage_release(new); error = desc->pgio->pg_error; goto out_unlock; } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 7b9316406930..ce43cd6d88c6 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -21,6 +21,8 @@ #include <linux/nfs_page.h> #include <linux/backing-dev.h> #include <linux/export.h> +#include <linux/freezer.h> +#include <linux/wait.h> #include <asm/uaccess.h> @@ -244,11 +246,9 @@ static int wb_priority(struct writeback_control *wbc) { int ret = 0; if (wbc->for_reclaim) - return FLUSH_HIGHPRI | FLUSH_STABLE; + return FLUSH_HIGHPRI | FLUSH_COND_STABLE; if (wbc->sync_mode == WB_SYNC_ALL) ret = FLUSH_COND_STABLE; - if (wbc->for_kupdate || wbc->for_background) - ret |= FLUSH_LOWPRI; return ret; } @@ -545,12 +545,22 @@ try_again: return head; } +static void nfs_write_error_remove_page(struct nfs_page *req) +{ + nfs_unlock_request(req); + nfs_end_page_writeback(req); + nfs_release_request(req); + generic_error_remove_page(page_file_mapping(req->wb_page), + req->wb_page); +} + /* * Find an associated nfs write request, and prepare to flush it out * May return an error if the user signalled nfs_wait_on_request(). */ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, - struct page *page, bool nonblock) + struct page *page, bool nonblock, + bool launder) { struct nfs_page *req; int ret = 0; @@ -567,8 +577,21 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, ret = 0; if (!nfs_pageio_add_request(pgio, req)) { - nfs_redirty_request(req); ret = pgio->pg_error; + /* + * Remove the problematic req upon fatal errors + * in launder case, while other dirty pages can + * still be around until they get flushed. + */ + if (nfs_error_is_fatal(ret)) { + nfs_context_set_write_error(req->wb_context, ret); + if (launder) { + nfs_write_error_remove_page(req); + goto out; + } + } + nfs_redirty_request(req); + ret = -EAGAIN; } else nfs_add_stats(page_file_mapping(page)->host, NFSIOS_WRITEPAGES, 1); @@ -576,12 +599,14 @@ out: return ret; } -static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, struct nfs_pageio_descriptor *pgio) +static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, + struct nfs_pageio_descriptor *pgio, bool launder) { int ret; nfs_pageio_cond_complete(pgio, page_file_index(page)); - ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE); + ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE, + launder); if (ret == -EAGAIN) { redirty_page_for_writepage(wbc, page); ret = 0; @@ -592,7 +617,9 @@ static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, st /* * Write an mmapped page to the server. */ -static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc) +static int nfs_writepage_locked(struct page *page, + struct writeback_control *wbc, + bool launder) { struct nfs_pageio_descriptor pgio; struct inode *inode = page_file_mapping(page)->host; @@ -601,7 +628,7 @@ static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE); nfs_pageio_init_write(&pgio, inode, wb_priority(wbc), false, &nfs_async_write_completion_ops); - err = nfs_do_writepage(page, wbc, &pgio); + err = nfs_do_writepage(page, wbc, &pgio, launder); nfs_pageio_complete(&pgio); if (err < 0) return err; @@ -614,7 +641,7 @@ int nfs_writepage(struct page *page, struct writeback_control *wbc) { int ret; - ret = nfs_writepage_locked(page, wbc); + ret = nfs_writepage_locked(page, wbc, false); unlock_page(page); return ret; } @@ -623,7 +650,7 @@ static int nfs_writepages_callback(struct page *page, struct writeback_control * { int ret; - ret = nfs_do_writepage(page, wbc, data); + ret = nfs_do_writepage(page, wbc, data, false); unlock_page(page); return ret; } @@ -1128,7 +1155,8 @@ int nfs_flush_incompatible(struct file *file, struct page *page) if (req == NULL) return 0; l_ctx = req->wb_lock_context; - do_flush = req->wb_page != page || req->wb_context != ctx; + do_flush = req->wb_page != page || + !nfs_match_open_context(req->wb_context, ctx); /* for now, flush if more than 1 request in page_group */ do_flush |= req->wb_this_page != req; if (l_ctx && flctx && @@ -1326,9 +1354,15 @@ static void nfs_async_write_error(struct list_head *head) } } +static void nfs_async_write_reschedule_io(struct nfs_pgio_header *hdr) +{ + nfs_async_write_error(&hdr->pages); +} + static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops = { .error_cleanup = nfs_async_write_error, .completion = nfs_write_completion, + .reschedule_io = nfs_async_write_reschedule_io, }; void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, @@ -1529,27 +1563,21 @@ static void nfs_writeback_result(struct rpc_task *task, } } - -static int nfs_commit_set_lock(struct nfs_inode *nfsi, int may_wait) +static int wait_on_commit(struct nfs_mds_commit_info *cinfo) { - int ret; + return wait_on_atomic_t(&cinfo->rpcs_out, + nfs_wait_atomic_killable, TASK_KILLABLE); +} - if (!test_and_set_bit(NFS_INO_COMMIT, &nfsi->flags)) - return 1; - if (!may_wait) - return 0; - ret = out_of_line_wait_on_bit_lock(&nfsi->flags, - NFS_INO_COMMIT, - nfs_wait_bit_killable, - TASK_KILLABLE); - return (ret < 0) ? ret : 1; +static void nfs_commit_begin(struct nfs_mds_commit_info *cinfo) +{ + atomic_inc(&cinfo->rpcs_out); } -static void nfs_commit_clear_lock(struct nfs_inode *nfsi) +static void nfs_commit_end(struct nfs_mds_commit_info *cinfo) { - clear_bit(NFS_INO_COMMIT, &nfsi->flags); - smp_mb__after_atomic(); - wake_up_bit(&nfsi->flags, NFS_INO_COMMIT); + if (atomic_dec_and_test(&cinfo->rpcs_out)) + wake_up_atomic_t(&cinfo->rpcs_out); } void nfs_commitdata_release(struct nfs_commit_data *data) @@ -1666,6 +1694,13 @@ void nfs_retry_commit(struct list_head *page_list, } EXPORT_SYMBOL_GPL(nfs_retry_commit); +static void +nfs_commit_resched_write(struct nfs_commit_info *cinfo, + struct nfs_page *req) +{ + __set_page_dirty_nobuffers(req->wb_page); +} + /* * Commit dirty pages */ @@ -1687,7 +1722,6 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how, data->mds_ops, how, 0); out_bad: nfs_retry_commit(head, NULL, cinfo, 0); - cinfo->completion_ops->error_cleanup(NFS_I(inode)); return -ENOMEM; } @@ -1749,8 +1783,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data) clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC); nfs_init_cinfo(&cinfo, data->inode, data->dreq); - if (atomic_dec_and_test(&cinfo.mds->rpcs_out)) - nfs_commit_clear_lock(NFS_I(data->inode)); + nfs_commit_end(cinfo.mds); } static void nfs_commit_release(void *calldata) @@ -1769,7 +1802,7 @@ static const struct rpc_call_ops nfs_commit_ops = { static const struct nfs_commit_completion_ops nfs_commit_completion_ops = { .completion = nfs_commit_release_pages, - .error_cleanup = nfs_commit_clear_lock, + .resched_write = nfs_commit_resched_write, }; int nfs_generic_commit_list(struct inode *inode, struct list_head *head, @@ -1788,30 +1821,25 @@ int nfs_commit_inode(struct inode *inode, int how) LIST_HEAD(head); struct nfs_commit_info cinfo; int may_wait = how & FLUSH_SYNC; + int error = 0; int res; - res = nfs_commit_set_lock(NFS_I(inode), may_wait); - if (res <= 0) - goto out_mark_dirty; nfs_init_cinfo_from_inode(&cinfo, inode); + nfs_commit_begin(cinfo.mds); res = nfs_scan_commit(inode, &head, &cinfo); - if (res) { - int error; - + if (res) error = nfs_generic_commit_list(inode, &head, how, &cinfo); - if (error < 0) - return error; - if (!may_wait) - goto out_mark_dirty; - error = wait_on_bit_action(&NFS_I(inode)->flags, - NFS_INO_COMMIT, - nfs_wait_bit_killable, - TASK_KILLABLE); - if (error < 0) - return error; - } else - nfs_commit_clear_lock(NFS_I(inode)); + nfs_commit_end(cinfo.mds); + if (error < 0) + goto out_error; + if (!may_wait) + goto out_mark_dirty; + error = wait_on_commit(cinfo.mds); + if (error < 0) + return error; return res; +out_error: + res = error; /* Note: If we exit without ensuring that the commit is complete, * we must mark the inode as dirty. Otherwise, future calls to * sync_inode() with the WB_SYNC_ALL flag set will fail to ensure @@ -1821,6 +1849,7 @@ out_mark_dirty: __mark_inode_dirty(inode, I_DIRTY_DATASYNC); return res; } +EXPORT_SYMBOL_GPL(nfs_commit_inode); int nfs_write_inode(struct inode *inode, struct writeback_control *wbc) { @@ -1911,7 +1940,7 @@ int nfs_wb_page_cancel(struct inode *inode, struct page *page) /* * Write back all requests on one page - we do this before reading it. */ -int nfs_wb_page(struct inode *inode, struct page *page) +int nfs_wb_single_page(struct inode *inode, struct page *page, bool launder) { loff_t range_start = page_file_offset(page); loff_t range_end = range_start + (loff_t)(PAGE_CACHE_SIZE - 1); @@ -1928,7 +1957,7 @@ int nfs_wb_page(struct inode *inode, struct page *page) for (;;) { wait_on_page_writeback(page); if (clear_page_dirty_for_io(page)) { - ret = nfs_writepage_locked(page, &wbc); + ret = nfs_writepage_locked(page, &wbc, launder); if (ret < 0) goto out_error; continue; diff --git a/fs/nfsd/lockd.c b/fs/nfsd/lockd.c index 77e7a5cca888..1a03bc3059e8 100644 --- a/fs/nfsd/lockd.c +++ b/fs/nfsd/lockd.c @@ -58,7 +58,7 @@ nlm_fclose(struct file *filp) fput(filp); } -static struct nlmsvc_binding nfsd_nlm_ops = { +static const struct nlmsvc_binding nfsd_nlm_ops = { .fopen = nlm_fopen, /* open file for locking */ .fclose = nlm_fclose, /* close file */ }; diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index d8b16c2568f3..5fbf3bbd00d0 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -92,7 +92,7 @@ struct nfsd_net { struct file *rec_file; bool in_grace; - struct nfsd4_client_tracking_ops *client_tracking_ops; + const struct nfsd4_client_tracking_ops *client_tracking_ops; time_t nfsd4_lease; time_t nfsd4_grace; diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index e7f50c4081d6..7389cb1d7409 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -792,12 +792,16 @@ static void warn_no_callback_path(struct nfs4_client *clp, int reason) static void nfsd4_mark_cb_down(struct nfs4_client *clp, int reason) { + if (test_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags)) + return; clp->cl_cb_state = NFSD4_CB_DOWN; warn_no_callback_path(clp, reason); } static void nfsd4_mark_cb_fault(struct nfs4_client *clp, int reason) { + if (test_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags)) + return; clp->cl_cb_state = NFSD4_CB_FAULT; warn_no_callback_path(clp, reason); } @@ -1143,7 +1147,7 @@ nfsd4_run_cb_work(struct work_struct *work) } void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp, - struct nfsd4_callback_ops *ops, enum nfsd4_cb_op op) + const struct nfsd4_callback_ops *ops, enum nfsd4_cb_op op) { cb->cb_clp = clp; cb->cb_msg.rpc_proc = &nfs4_cb_procedures[op]; diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index c9d6c715c0fb..ce2d010d3b17 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -22,7 +22,7 @@ struct nfs4_layout { static struct kmem_cache *nfs4_layout_cache; static struct kmem_cache *nfs4_layout_stateid_cache; -static struct nfsd4_callback_ops nfsd4_cb_layout_ops; +static const struct nfsd4_callback_ops nfsd4_cb_layout_ops; static const struct lock_manager_operations nfsd4_layouts_lm_ops; const struct nfsd4_layout_ops *nfsd4_layout_ops[LAYOUT_TYPE_MAX] = { @@ -624,24 +624,39 @@ nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task) { struct nfs4_layout_stateid *ls = container_of(cb, struct nfs4_layout_stateid, ls_recall); + struct nfsd_net *nn; + ktime_t now, cutoff; LIST_HEAD(reaplist); + switch (task->tk_status) { case 0: - return 1; + case -NFS4ERR_DELAY: + /* + * Anything left? If not, then call it done. Note that we don't + * take the spinlock since this is an optimization and nothing + * should get added until the cb counter goes to zero. + */ + if (list_empty(&ls->ls_layouts)) + return 1; + + /* Poll the client until it's done with the layout */ + now = ktime_get(); + nn = net_generic(ls->ls_stid.sc_client->net, nfsd_net_id); + + /* Client gets 2 lease periods to return it */ + cutoff = ktime_add_ns(task->tk_start, + nn->nfsd4_lease * NSEC_PER_SEC * 2); + + if (ktime_before(now, cutoff)) { + rpc_delay(task, HZ/100); /* 10 mili-seconds */ + return 0; + } + /* Fallthrough */ case -NFS4ERR_NOMATCHING_LAYOUT: trace_layout_recall_done(&ls->ls_stid.sc_stateid); task->tk_status = 0; return 1; - case -NFS4ERR_DELAY: - /* Poll the client until it's done with the layout */ - /* FIXME: cap number of retries. - * The pnfs standard states that we need to only expire - * the client after at-least "lease time" .eg lease-time * 2 - * when failing to communicate a recall - */ - rpc_delay(task, HZ/100); /* 10 mili-seconds */ - return 0; default: /* * Unknown error or non-responding client, we'll need to fence. @@ -665,7 +680,7 @@ nfsd4_cb_layout_release(struct nfsd4_callback *cb) nfs4_put_stid(&ls->ls_stid); } -static struct nfsd4_callback_ops nfsd4_cb_layout_ops = { +static const struct nfsd4_callback_ops nfsd4_cb_layout_ops = { .prepare = nfsd4_cb_layout_prepare, .done = nfsd4_cb_layout_done, .release = nfsd4_cb_layout_release, diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index e3d47091b191..79f0307a5ec8 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -631,7 +631,7 @@ nfsd4_check_legacy_client(struct nfs4_client *clp) return -ENOENT; } -static struct nfsd4_client_tracking_ops nfsd4_legacy_tracking_ops = { +static const struct nfsd4_client_tracking_ops nfsd4_legacy_tracking_ops = { .init = nfsd4_legacy_tracking_init, .exit = nfsd4_legacy_tracking_exit, .create = nfsd4_create_clid_dir, @@ -1050,7 +1050,7 @@ out_err: printk(KERN_ERR "NFSD: Unable to end grace period: %d\n", ret); } -static struct nfsd4_client_tracking_ops nfsd4_cld_tracking_ops = { +static const struct nfsd4_client_tracking_ops nfsd4_cld_tracking_ops = { .init = nfsd4_init_cld_pipe, .exit = nfsd4_remove_cld_pipe, .create = nfsd4_cld_create, @@ -1394,7 +1394,7 @@ nfsd4_umh_cltrack_grace_done(struct nfsd_net *nn) kfree(legacy); } -static struct nfsd4_client_tracking_ops nfsd4_umh_tracking_ops = { +static const struct nfsd4_client_tracking_ops nfsd4_umh_tracking_ops = { .init = nfsd4_umh_cltrack_init, .exit = NULL, .create = nfsd4_umh_cltrack_create, diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index df5dba687265..c484a2b6cd10 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -98,7 +98,7 @@ static struct kmem_cache *odstate_slab; static void free_session(struct nfsd4_session *); -static struct nfsd4_callback_ops nfsd4_cb_recall_ops; +static const struct nfsd4_callback_ops nfsd4_cb_recall_ops; static bool is_session_dead(struct nfsd4_session *ses) { @@ -1857,15 +1857,28 @@ static void copy_clid(struct nfs4_client *target, struct nfs4_client *source) target->cl_clientid.cl_id = source->cl_clientid.cl_id; } -static int copy_cred(struct svc_cred *target, struct svc_cred *source) +int strdup_if_nonnull(char **target, char *source) { - if (source->cr_principal) { - target->cr_principal = - kstrdup(source->cr_principal, GFP_KERNEL); - if (target->cr_principal == NULL) + if (source) { + *target = kstrdup(source, GFP_KERNEL); + if (!*target) return -ENOMEM; } else - target->cr_principal = NULL; + *target = NULL; + return 0; +} + +static int copy_cred(struct svc_cred *target, struct svc_cred *source) +{ + int ret; + + ret = strdup_if_nonnull(&target->cr_principal, source->cr_principal); + if (ret) + return ret; + ret = strdup_if_nonnull(&target->cr_raw_principal, + source->cr_raw_principal); + if (ret) + return ret; target->cr_flavor = source->cr_flavor; target->cr_uid = source->cr_uid; target->cr_gid = source->cr_gid; @@ -1969,6 +1982,9 @@ static bool mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp) return false; if (!svc_rqst_integrity_protected(rqstp)) return false; + if (cl->cl_cred.cr_raw_principal) + return 0 == strcmp(cl->cl_cred.cr_raw_principal, + cr->cr_raw_principal); if (!cr->cr_principal) return false; return 0 == strcmp(cl->cl_cred.cr_principal, cr->cr_principal); @@ -2240,7 +2256,8 @@ nfsd4_store_cache_entry(struct nfsd4_compoundres *resp) base = resp->cstate.data_offset; slot->sl_datalen = buf->len - base; if (read_bytes_from_xdr_buf(buf, base, slot->sl_data, slot->sl_datalen)) - WARN("%s: sessions DRC could not cache compound\n", __func__); + WARN(1, "%s: sessions DRC could not cache compound\n", + __func__); return; } @@ -2365,10 +2382,27 @@ nfsd4_exchange_id(struct svc_rqst *rqstp, if (exid->flags & ~EXCHGID4_FLAG_MASK_A) return nfserr_inval; + new = create_client(exid->clname, rqstp, &verf); + if (new == NULL) + return nfserr_jukebox; + switch (exid->spa_how) { case SP4_MACH_CRED: - if (!svc_rqst_integrity_protected(rqstp)) - return nfserr_inval; + if (!svc_rqst_integrity_protected(rqstp)) { + status = nfserr_inval; + goto out_nolock; + } + /* + * Sometimes userspace doesn't give us a principal. + * Which is a bug, really. Anyway, we can't enforce + * MACH_CRED in that case, better to give up now: + */ + if (!new->cl_cred.cr_principal && + !new->cl_cred.cr_raw_principal) { + status = nfserr_serverfault; + goto out_nolock; + } + new->cl_mach_cred = true; case SP4_NONE: break; default: /* checked by xdr code */ @@ -2377,10 +2411,6 @@ nfsd4_exchange_id(struct svc_rqst *rqstp, return nfserr_encr_alg_unsupp; } - new = create_client(exid->clname, rqstp, &verf); - if (new == NULL) - return nfserr_jukebox; - /* Cases below refer to rfc 5661 section 18.35.4: */ spin_lock(&nn->client_lock); conf = find_confirmed_client_by_name(&exid->clname, nn); @@ -2442,7 +2472,6 @@ out_new: goto out; } new->cl_minorversion = cstate->minorversion; - new->cl_mach_cred = (exid->spa_how == SP4_MACH_CRED); gen_clid(new, nn); add_to_unconfirmed(new); @@ -2460,6 +2489,7 @@ out_copy: out: spin_unlock(&nn->client_lock); +out_nolock: if (new) expire_client(new); if (unconf) @@ -3648,7 +3678,7 @@ static void nfsd4_cb_recall_release(struct nfsd4_callback *cb) nfs4_put_stid(&dp->dl_stid); } -static struct nfsd4_callback_ops nfsd4_cb_recall_ops = { +static const struct nfsd4_callback_ops nfsd4_cb_recall_ops = { .prepare = nfsd4_cb_recall_prepare, .done = nfsd4_cb_recall_done, .release = nfsd4_cb_recall_release, @@ -4541,8 +4571,7 @@ static void laundromat_main(struct work_struct *laundry) { time_t t; - struct delayed_work *dwork = container_of(laundry, struct delayed_work, - work); + struct delayed_work *dwork = to_delayed_work(laundry); struct nfsd_net *nn = container_of(dwork, struct nfsd_net, laundromat_work); diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h index 2087bae17582..0770bcb543c8 100644 --- a/fs/nfsd/nfsfh.h +++ b/fs/nfsd/nfsfh.h @@ -7,6 +7,7 @@ #ifndef _LINUX_NFSD_NFSFH_H #define _LINUX_NFSD_NFSFH_H +#include <linux/crc32.h> #include <linux/sunrpc/svc.h> #include <uapi/linux/nfsd/nfsfh.h> @@ -205,6 +206,28 @@ static inline bool fh_fsid_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2) return true; } +#ifdef CONFIG_CRC32 +/** + * knfsd_fh_hash - calculate the crc32 hash for the filehandle + * @fh - pointer to filehandle + * + * returns a crc32 hash for the filehandle that is compatible with + * the one displayed by "wireshark". + */ + +static inline u32 +knfsd_fh_hash(struct knfsd_fh *fh) +{ + return ~crc32_le(0xFFFFFFFF, (unsigned char *)&fh->fh_base, fh->fh_size); +} +#else +static inline u32 +knfsd_fh_hash(struct knfsd_fh *fh) +{ + return 0; +} +#endif + #ifdef CONFIG_NFSD_V3 /* * The wcc data stored in current_fh should be cleared diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index ad4e2377dd63..45007acaf364 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -14,9 +14,13 @@ #include <linux/sunrpc/stats.h> #include <linux/sunrpc/svcsock.h> +#include <linux/sunrpc/svc_xprt.h> #include <linux/lockd/bind.h> #include <linux/nfsacl.h> #include <linux/seq_file.h> +#include <linux/inetdevice.h> +#include <net/addrconf.h> +#include <net/ipv6.h> #include <net/net_namespace.h> #include "nfsd.h" #include "cache.h" @@ -306,22 +310,81 @@ static void nfsd_shutdown_net(struct net *net) nfsd_shutdown_generic(); } +static int nfsd_inetaddr_event(struct notifier_block *this, unsigned long event, + void *ptr) +{ + struct in_ifaddr *ifa = (struct in_ifaddr *)ptr; + struct net_device *dev = ifa->ifa_dev->dev; + struct net *net = dev_net(dev); + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct sockaddr_in sin; + + if (event != NETDEV_DOWN) + goto out; + + if (nn->nfsd_serv) { + dprintk("nfsd_inetaddr_event: removed %pI4\n", &ifa->ifa_local); + sin.sin_family = AF_INET; + sin.sin_addr.s_addr = ifa->ifa_local; + svc_age_temp_xprts_now(nn->nfsd_serv, (struct sockaddr *)&sin); + } + +out: + return NOTIFY_DONE; +} + +static struct notifier_block nfsd_inetaddr_notifier = { + .notifier_call = nfsd_inetaddr_event, +}; + +#if IS_ENABLED(CONFIG_IPV6) +static int nfsd_inet6addr_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + struct inet6_ifaddr *ifa = (struct inet6_ifaddr *)ptr; + struct net_device *dev = ifa->idev->dev; + struct net *net = dev_net(dev); + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct sockaddr_in6 sin6; + + if (event != NETDEV_DOWN) + goto out; + + if (nn->nfsd_serv) { + dprintk("nfsd_inet6addr_event: removed %pI6\n", &ifa->addr); + sin6.sin6_family = AF_INET6; + sin6.sin6_addr = ifa->addr; + svc_age_temp_xprts_now(nn->nfsd_serv, (struct sockaddr *)&sin6); + } + +out: + return NOTIFY_DONE; +} + +static struct notifier_block nfsd_inet6addr_notifier = { + .notifier_call = nfsd_inet6addr_event, +}; +#endif + static void nfsd_last_thread(struct svc_serv *serv, struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); + unregister_inetaddr_notifier(&nfsd_inetaddr_notifier); +#if IS_ENABLED(CONFIG_IPV6) + unregister_inet6addr_notifier(&nfsd_inet6addr_notifier); +#endif /* * write_ports can create the server without actually starting * any threads--if we get shut down before any threads are * started, then nfsd_last_thread will be run before any of this - * other initialization has been done. + * other initialization has been done except the rpcb information. */ + svc_rpcb_cleanup(serv, net); if (!nn->nfsd_net_up) return; - nfsd_shutdown_net(net); - - svc_rpcb_cleanup(serv, net); + nfsd_shutdown_net(net); printk(KERN_WARNING "nfsd: last server has exited, flushing export " "cache\n"); nfsd_export_flush(net); @@ -425,6 +488,10 @@ int nfsd_create_serv(struct net *net) } set_max_drc(); + register_inetaddr_notifier(&nfsd_inetaddr_notifier); +#if IS_ENABLED(CONFIG_IPV6) + register_inet6addr_notifier(&nfsd_inet6addr_notifier); +#endif do_gettimeofday(&nn->nfssvc_boot); /* record boot time */ return 0; } diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 99432b7ecb9c..c050c53036a6 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -65,7 +65,7 @@ struct nfsd4_callback { struct nfs4_client *cb_clp; u32 cb_minorversion; struct rpc_message cb_msg; - struct nfsd4_callback_ops *cb_ops; + const struct nfsd4_callback_ops *cb_ops; struct work_struct cb_work; int cb_seq_status; int cb_status; @@ -599,7 +599,7 @@ extern void nfsd4_probe_callback(struct nfs4_client *clp); extern void nfsd4_probe_callback_sync(struct nfs4_client *clp); extern void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *); extern void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp, - struct nfsd4_callback_ops *ops, enum nfsd4_cb_op op); + const struct nfsd4_callback_ops *ops, enum nfsd4_cb_op op); extern void nfsd4_run_cb(struct nfsd4_callback *cb); extern int nfsd4_create_callback_queue(void); extern void nfsd4_destroy_callback_queue(void); diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index 0befe762762b..3287041905da 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -8,6 +8,47 @@ #define _NFSD_TRACE_H #include <linux/tracepoint.h> +#include "nfsfh.h" + +DECLARE_EVENT_CLASS(nfsd_io_class, + TP_PROTO(struct svc_rqst *rqstp, + struct svc_fh *fhp, + loff_t offset, + int len), + TP_ARGS(rqstp, fhp, offset, len), + TP_STRUCT__entry( + __field(__be32, xid) + __field_struct(struct knfsd_fh, fh) + __field(loff_t, offset) + __field(int, len) + ), + TP_fast_assign( + __entry->xid = rqstp->rq_xid, + fh_copy_shallow(&__entry->fh, &fhp->fh_handle); + __entry->offset = offset; + __entry->len = len; + ), + TP_printk("xid=0x%x fh=0x%x offset=%lld len=%d", + __be32_to_cpu(__entry->xid), knfsd_fh_hash(&__entry->fh), + __entry->offset, __entry->len) +) + +#define DEFINE_NFSD_IO_EVENT(name) \ +DEFINE_EVENT(nfsd_io_class, name, \ + TP_PROTO(struct svc_rqst *rqstp, \ + struct svc_fh *fhp, \ + loff_t offset, \ + int len), \ + TP_ARGS(rqstp, fhp, offset, len)) + +DEFINE_NFSD_IO_EVENT(read_start); +DEFINE_NFSD_IO_EVENT(read_opened); +DEFINE_NFSD_IO_EVENT(read_io_done); +DEFINE_NFSD_IO_EVENT(read_done); +DEFINE_NFSD_IO_EVENT(write_start); +DEFINE_NFSD_IO_EVENT(write_opened); +DEFINE_NFSD_IO_EVENT(write_io_done); +DEFINE_NFSD_IO_EVENT(write_done); #include "state.h" diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index d41c149fae75..6739077f17fe 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -43,6 +43,7 @@ #include "nfsd.h" #include "vfs.h" +#include "trace.h" #define NFSDDBG_FACILITY NFSDDBG_FILEOP @@ -997,16 +998,23 @@ __be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct raparms *ra; __be32 err; + trace_read_start(rqstp, fhp, offset, vlen); err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_READ, &file); if (err) return err; ra = nfsd_init_raparms(file); + + trace_read_opened(rqstp, fhp, offset, vlen); err = nfsd_vfs_read(rqstp, file, offset, vec, vlen, count); + trace_read_io_done(rqstp, fhp, offset, vlen); + if (ra) nfsd_put_raparams(file, ra); fput(file); + trace_read_done(rqstp, fhp, offset, vlen); + return err; } @@ -1022,24 +1030,31 @@ nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, { __be32 err = 0; + trace_write_start(rqstp, fhp, offset, vlen); + if (file) { err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry, NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE); if (err) goto out; + trace_write_opened(rqstp, fhp, offset, vlen); err = nfsd_vfs_write(rqstp, fhp, file, offset, vec, vlen, cnt, stablep); + trace_write_io_done(rqstp, fhp, offset, vlen); } else { err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_WRITE, &file); if (err) goto out; + trace_write_opened(rqstp, fhp, offset, vlen); if (cnt) err = nfsd_vfs_write(rqstp, fhp, file, offset, vec, vlen, cnt, stablep); + trace_write_io_done(rqstp, fhp, offset, vlen); fput(file); } out: + trace_write_done(rqstp, fhp, offset, vlen); return err; } diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index c7343844e6b6..7f5d3d9f1c37 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -1416,7 +1416,8 @@ static int __init nilfs_init_cachep(void) { nilfs_inode_cachep = kmem_cache_create("nilfs2_inode_cache", sizeof(struct nilfs_inode_info), 0, - SLAB_RECLAIM_ACCOUNT, nilfs_inode_init_once); + SLAB_RECLAIM_ACCOUNT|SLAB_ACCOUNT, + nilfs_inode_init_once); if (!nilfs_inode_cachep) goto fail; diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c index e785fd954c30..741077deef3b 100644 --- a/fs/notify/inode_mark.c +++ b/fs/notify/inode_mark.c @@ -199,8 +199,7 @@ void fsnotify_unmount_inodes(struct super_block *sb) break; } spin_unlock(&next_i->i_lock); - next_i = list_entry(next_i->i_sb_list.next, - struct inode, i_sb_list); + next_i = list_next_entry(next_i, i_sb_list); } /* diff --git a/fs/notify/mark.c b/fs/notify/mark.c index fc0df4442f7b..cfcbf114676e 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -92,9 +92,6 @@ #include "fsnotify.h" struct srcu_struct fsnotify_mark_srcu; -static DEFINE_SPINLOCK(destroy_lock); -static LIST_HEAD(destroy_list); -static DECLARE_WAIT_QUEUE_HEAD(destroy_waitq); void fsnotify_get_mark(struct fsnotify_mark *mark) { @@ -168,10 +165,19 @@ void fsnotify_detach_mark(struct fsnotify_mark *mark) atomic_dec(&group->num_marks); } +static void +fsnotify_mark_free_rcu(struct rcu_head *rcu) +{ + struct fsnotify_mark *mark; + + mark = container_of(rcu, struct fsnotify_mark, g_rcu); + fsnotify_put_mark(mark); +} + /* - * Free fsnotify mark. The freeing is actually happening from a kthread which - * first waits for srcu period end. Caller must have a reference to the mark - * or be protected by fsnotify_mark_srcu. + * Free fsnotify mark. The freeing is actually happening from a call_srcu + * callback. Caller must have a reference to the mark or be protected by + * fsnotify_mark_srcu. */ void fsnotify_free_mark(struct fsnotify_mark *mark) { @@ -186,10 +192,7 @@ void fsnotify_free_mark(struct fsnotify_mark *mark) mark->flags &= ~FSNOTIFY_MARK_FLAG_ALIVE; spin_unlock(&mark->lock); - spin_lock(&destroy_lock); - list_add(&mark->g_list, &destroy_list); - spin_unlock(&destroy_lock); - wake_up(&destroy_waitq); + call_srcu(&fsnotify_mark_srcu, &mark->g_rcu, fsnotify_mark_free_rcu); /* * Some groups like to know that marks are being freed. This is a @@ -385,11 +388,7 @@ err: spin_unlock(&mark->lock); - spin_lock(&destroy_lock); - list_add(&mark->g_list, &destroy_list); - spin_unlock(&destroy_lock); - wake_up(&destroy_waitq); - + call_srcu(&fsnotify_mark_srcu, &mark->g_rcu, fsnotify_mark_free_rcu); return ret; } @@ -492,40 +491,3 @@ void fsnotify_init_mark(struct fsnotify_mark *mark, atomic_set(&mark->refcnt, 1); mark->free_mark = free_mark; } - -static int fsnotify_mark_destroy(void *ignored) -{ - struct fsnotify_mark *mark, *next; - struct list_head private_destroy_list; - - for (;;) { - spin_lock(&destroy_lock); - /* exchange the list head */ - list_replace_init(&destroy_list, &private_destroy_list); - spin_unlock(&destroy_lock); - - synchronize_srcu(&fsnotify_mark_srcu); - - list_for_each_entry_safe(mark, next, &private_destroy_list, g_list) { - list_del_init(&mark->g_list); - fsnotify_put_mark(mark); - } - - wait_event_interruptible(destroy_waitq, !list_empty(&destroy_list)); - } - - return 0; -} - -static int __init fsnotify_mark_init(void) -{ - struct task_struct *thread; - - thread = kthread_run(fsnotify_mark_destroy, NULL, - "fsnotify_mark"); - if (IS_ERR(thread)) - panic("unable to start fsnotify mark destruction thread."); - - return 0; -} -device_initcall(fsnotify_mark_init); diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index d1a853585b53..2f77f8dfb861 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -3139,8 +3139,8 @@ static int __init init_ntfs_fs(void) ntfs_big_inode_cache = kmem_cache_create(ntfs_big_inode_cache_name, sizeof(big_ntfs_inode), 0, - SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, - ntfs_big_inode_init_once); + SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD| + SLAB_ACCOUNT, ntfs_big_inode_init_once); if (!ntfs_big_inode_cache) { pr_crit("Failed to create %s!\n", ntfs_big_inode_cache_name); goto big_inode_err_out; diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index 86181d6526dc..a3ded88718c9 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -164,7 +164,7 @@ static int ocfs2_dinode_insert_check(struct ocfs2_extent_tree *et, struct ocfs2_extent_rec *rec); static int ocfs2_dinode_sanity_check(struct ocfs2_extent_tree *et); static void ocfs2_dinode_fill_root_el(struct ocfs2_extent_tree *et); -static struct ocfs2_extent_tree_operations ocfs2_dinode_et_ops = { +static const struct ocfs2_extent_tree_operations ocfs2_dinode_et_ops = { .eo_set_last_eb_blk = ocfs2_dinode_set_last_eb_blk, .eo_get_last_eb_blk = ocfs2_dinode_get_last_eb_blk, .eo_update_clusters = ocfs2_dinode_update_clusters, @@ -286,7 +286,7 @@ static void ocfs2_xattr_value_update_clusters(struct ocfs2_extent_tree *et, le32_add_cpu(&vb->vb_xv->xr_clusters, clusters); } -static struct ocfs2_extent_tree_operations ocfs2_xattr_value_et_ops = { +static const struct ocfs2_extent_tree_operations ocfs2_xattr_value_et_ops = { .eo_set_last_eb_blk = ocfs2_xattr_value_set_last_eb_blk, .eo_get_last_eb_blk = ocfs2_xattr_value_get_last_eb_blk, .eo_update_clusters = ocfs2_xattr_value_update_clusters, @@ -332,7 +332,7 @@ static void ocfs2_xattr_tree_update_clusters(struct ocfs2_extent_tree *et, le32_add_cpu(&xb->xb_attrs.xb_root.xt_clusters, clusters); } -static struct ocfs2_extent_tree_operations ocfs2_xattr_tree_et_ops = { +static const struct ocfs2_extent_tree_operations ocfs2_xattr_tree_et_ops = { .eo_set_last_eb_blk = ocfs2_xattr_tree_set_last_eb_blk, .eo_get_last_eb_blk = ocfs2_xattr_tree_get_last_eb_blk, .eo_update_clusters = ocfs2_xattr_tree_update_clusters, @@ -379,7 +379,7 @@ static void ocfs2_dx_root_fill_root_el(struct ocfs2_extent_tree *et) et->et_root_el = &dx_root->dr_list; } -static struct ocfs2_extent_tree_operations ocfs2_dx_root_et_ops = { +static const struct ocfs2_extent_tree_operations ocfs2_dx_root_et_ops = { .eo_set_last_eb_blk = ocfs2_dx_root_set_last_eb_blk, .eo_get_last_eb_blk = ocfs2_dx_root_get_last_eb_blk, .eo_update_clusters = ocfs2_dx_root_update_clusters, @@ -425,7 +425,7 @@ ocfs2_refcount_tree_extent_contig(struct ocfs2_extent_tree *et, return CONTIG_NONE; } -static struct ocfs2_extent_tree_operations ocfs2_refcount_tree_et_ops = { +static const struct ocfs2_extent_tree_operations ocfs2_refcount_tree_et_ops = { .eo_set_last_eb_blk = ocfs2_refcount_tree_set_last_eb_blk, .eo_get_last_eb_blk = ocfs2_refcount_tree_get_last_eb_blk, .eo_update_clusters = ocfs2_refcount_tree_update_clusters, @@ -438,7 +438,7 @@ static void __ocfs2_init_extent_tree(struct ocfs2_extent_tree *et, struct buffer_head *bh, ocfs2_journal_access_func access, void *obj, - struct ocfs2_extent_tree_operations *ops) + const struct ocfs2_extent_tree_operations *ops) { et->et_ops = ops; et->et_root_bh = bh; @@ -6174,8 +6174,7 @@ int ocfs2_begin_truncate_log_recovery(struct ocfs2_super *osb, } bail: - if (tl_inode) - iput(tl_inode); + iput(tl_inode); brelse(tl_bh); if (status < 0) { diff --git a/fs/ocfs2/alloc.h b/fs/ocfs2/alloc.h index fb09b97db162..f3dc1b0dfffc 100644 --- a/fs/ocfs2/alloc.h +++ b/fs/ocfs2/alloc.h @@ -54,7 +54,7 @@ */ struct ocfs2_extent_tree_operations; struct ocfs2_extent_tree { - struct ocfs2_extent_tree_operations *et_ops; + const struct ocfs2_extent_tree_operations *et_ops; struct buffer_head *et_root_bh; struct ocfs2_extent_list *et_root_el; struct ocfs2_caching_info *et_ci; diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index 709fbbd44c65..a3cc6d2fc896 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -1780,8 +1780,8 @@ static ssize_t o2hb_region_dev_store(struct config_item *item, } ++live_threshold; atomic_set(®->hr_steady_iterations, live_threshold); - /* unsteady_iterations is double the steady_iterations */ - atomic_set(®->hr_unsteady_iterations, (live_threshold << 1)); + /* unsteady_iterations is triple the steady_iterations */ + atomic_set(®->hr_unsteady_iterations, (live_threshold * 3)); hb_task = kthread_run(o2hb_thread, reg, "o2hb-%s", reg->hr_item.ci_name); diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h index e88ccf8c83ff..68c607e63ff6 100644 --- a/fs/ocfs2/dlm/dlmcommon.h +++ b/fs/ocfs2/dlm/dlmcommon.h @@ -376,17 +376,6 @@ struct dlm_lock lksb_kernel_allocated:1; }; - -#define DLM_LKSB_UNUSED1 0x01 -#define DLM_LKSB_PUT_LVB 0x02 -#define DLM_LKSB_GET_LVB 0x04 -#define DLM_LKSB_UNUSED2 0x08 -#define DLM_LKSB_UNUSED3 0x10 -#define DLM_LKSB_UNUSED4 0x20 -#define DLM_LKSB_UNUSED5 0x40 -#define DLM_LKSB_UNUSED6 0x80 - - enum dlm_lockres_list { DLM_GRANTED_LIST = 0, DLM_CONVERTING_LIST = 1, diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 84f2f8079466..9477d6e1de37 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -2388,8 +2388,8 @@ static void dlm_deref_lockres_worker(struct dlm_work_item *item, void *data) spin_lock(&res->spinlock); BUG_ON(res->state & DLM_LOCK_RES_DROPPING_REF); + __dlm_wait_on_lockres_flags(res, DLM_LOCK_RES_SETREF_INPROG); if (test_bit(node, res->refmap)) { - __dlm_wait_on_lockres_flags(res, DLM_LOCK_RES_SETREF_INPROG); dlm_lockres_clear_refmap_bit(dlm, res, node); cleared = 1; } @@ -2519,6 +2519,11 @@ static int dlm_migrate_lockres(struct dlm_ctxt *dlm, spin_lock(&dlm->master_lock); ret = dlm_add_migration_mle(dlm, res, mle, &oldmle, name, namelen, target, dlm->node_num); + /* get an extra reference on the mle. + * otherwise the assert_master from the new + * master will destroy this. + */ + dlm_get_mle_inuse(mle); spin_unlock(&dlm->master_lock); spin_unlock(&dlm->spinlock); @@ -2544,7 +2549,7 @@ static int dlm_migrate_lockres(struct dlm_ctxt *dlm, } fail: - if (oldmle) { + if (ret != -EEXIST && oldmle) { /* master is known, detach if not already detached */ dlm_mle_detach_hb_events(dlm, oldmle); dlm_put_mle(oldmle); @@ -2554,6 +2559,7 @@ fail: if (mle_added) { dlm_mle_detach_hb_events(dlm, mle); dlm_put_mle(mle); + dlm_put_mle_inuse(mle); } else if (mle) { kmem_cache_free(dlm_mle_cache, mle); mle = NULL; @@ -2571,17 +2577,6 @@ fail: * ensure that all assert_master work is flushed. */ flush_workqueue(dlm->dlm_worker); - /* get an extra reference on the mle. - * otherwise the assert_master from the new - * master will destroy this. - * also, make sure that all callers of dlm_get_mle - * take both dlm->spinlock and dlm->master_lock */ - spin_lock(&dlm->spinlock); - spin_lock(&dlm->master_lock); - dlm_get_mle_inuse(mle); - spin_unlock(&dlm->master_lock); - spin_unlock(&dlm->spinlock); - /* notify new node and send all lock state */ /* call send_one_lockres with migration flag. * this serves as notice to the target node that a @@ -3050,7 +3045,7 @@ int dlm_migrate_request_handler(struct o2net_msg *msg, u32 len, void *data, int ret = 0; if (!dlm_grab(dlm)) - return -EINVAL; + return 0; name = migrate->name; namelen = migrate->namelen; @@ -3141,7 +3136,8 @@ static int dlm_add_migration_mle(struct dlm_ctxt *dlm, mlog(0, "tried to migrate %.*s, but some " "process beat me to it\n", namelen, name); - ret = -EEXIST; + spin_unlock(&tmp->spinlock); + return -EEXIST; } else { /* bad. 2 NODES are trying to migrate! */ mlog(ML_ERROR, "migration error mle: " @@ -3312,6 +3308,15 @@ top: mle->new_master != dead_node) continue; + if (mle->new_master == dead_node && mle->inuse) { + mlog(ML_NOTICE, "%s: target %u died during " + "migration from %u, the MLE is " + "still keep used, ignore it!\n", + dlm->name, dead_node, + mle->master); + continue; + } + /* If we have reached this point, this mle needs to be * removed from the list and freed. */ dlm_clean_migration_mle(dlm, mle); diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index 9e4f862d20fe..c5bdf02c213b 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -1373,6 +1373,7 @@ int dlm_mig_lockres_handler(struct o2net_msg *msg, u32 len, void *data, char *buf = NULL; struct dlm_work_item *item = NULL; struct dlm_lock_resource *res = NULL; + unsigned int hash; if (!dlm_grab(dlm)) return -EINVAL; @@ -1400,7 +1401,10 @@ int dlm_mig_lockres_handler(struct o2net_msg *msg, u32 len, void *data, /* lookup the lock to see if we have a secondary queue for this * already... just add the locks in and this will have its owner * and RECOVERY flag changed when it completes. */ - res = dlm_lookup_lockres(dlm, mres->lockname, mres->lockname_len); + hash = dlm_lockid_hash(mres->lockname, mres->lockname_len); + spin_lock(&dlm->spinlock); + res = __dlm_lookup_lockres(dlm, mres->lockname, mres->lockname_len, + hash); if (res) { /* this will get a ref on res */ /* mark it as recovering/migrating and hash it */ @@ -1421,13 +1425,16 @@ int dlm_mig_lockres_handler(struct o2net_msg *msg, u32 len, void *data, mres->lockname_len, mres->lockname); ret = -EFAULT; spin_unlock(&res->spinlock); + spin_unlock(&dlm->spinlock); dlm_lockres_put(res); goto leave; } res->state |= DLM_LOCK_RES_MIGRATING; } spin_unlock(&res->spinlock); + spin_unlock(&dlm->spinlock); } else { + spin_unlock(&dlm->spinlock); /* need to allocate, just like if it was * mastered here normally */ res = dlm_new_lockres(dlm, mres->lockname, mres->lockname_len); @@ -2450,11 +2457,7 @@ static void __dlm_hb_node_down(struct dlm_ctxt *dlm, int idx) * perhaps later we can genericize this for other waiters. */ wake_up(&dlm->migration_wq); - if (test_bit(idx, dlm->recovery_map)) - mlog(0, "domain %s, node %u already added " - "to recovery map!\n", dlm->name, idx); - else - set_bit(idx, dlm->recovery_map); + set_bit(idx, dlm->recovery_map); } void dlm_hb_node_down_cb(struct o2nm_node *node, int idx, void *data) diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c index 2e3c9dbab68c..1082b2c3014b 100644 --- a/fs/ocfs2/dlm/dlmunlock.c +++ b/fs/ocfs2/dlm/dlmunlock.c @@ -421,7 +421,7 @@ int dlm_unlock_lock_handler(struct o2net_msg *msg, u32 len, void *data, } if (!dlm_grab(dlm)) - return DLM_REJECTED; + return DLM_FORWARD; mlog_bug_on_msg(!dlm_domain_fully_joined(dlm), "Domain %s not fully joined!\n", dlm->name); diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c index b5cf27dcb18a..03768bb3aab1 100644 --- a/fs/ocfs2/dlmfs/dlmfs.c +++ b/fs/ocfs2/dlmfs/dlmfs.c @@ -638,7 +638,7 @@ static int __init init_dlmfs_fs(void) dlmfs_inode_cache = kmem_cache_create("dlmfs_inode_cache", sizeof(struct dlmfs_inode_private), 0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), dlmfs_init_once); if (!dlmfs_inode_cache) { status = -ENOMEM; diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 20276e340339..f92612e4b9d6 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -2432,12 +2432,6 @@ bail: * done this we have to return AOP_TRUNCATED_PAGE so the aop method * that called us can bubble that back up into the VFS who will then * immediately retry the aop call. - * - * We do a blocking lock and immediate unlock before returning, though, so that - * the lock has a great chance of being cached on this node by the time the VFS - * calls back to retry the aop. This has a potential to livelock as nodes - * ping locks back and forth, but that's a risk we're willing to take to avoid - * the lock inversion simply. */ int ocfs2_inode_lock_with_page(struct inode *inode, struct buffer_head **ret_bh, @@ -2449,8 +2443,6 @@ int ocfs2_inode_lock_with_page(struct inode *inode, ret = ocfs2_inode_lock_full(inode, ret_bh, ex, OCFS2_LOCK_NONBLOCK); if (ret == -EAGAIN) { unlock_page(page); - if (ocfs2_inode_lock(inode, ret_bh, ex) == 0) - ocfs2_inode_unlock(inode, ex); ret = AOP_TRUNCATED_PAGE; } diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 0e5b4515f92e..d63127932509 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1302,6 +1302,14 @@ int ocfs2_getattr(struct vfsmount *mnt, } generic_fillattr(inode, stat); + /* + * If there is inline data in the inode, the inode will normally not + * have data blocks allocated (it may have an external xattr block). + * Report at least one sector for such files, so tools like tar, rsync, + * others don't incorrectly think the file is completely sparse. + */ + if (unlikely(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)) + stat->blocks += (stat->size + 511)>>9; /* We set the blksize from the cluster size for performance */ stat->blksize = osb->s_clustersize; diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c index 3cb097ccce60..16b0bb482ea7 100644 --- a/fs/ocfs2/ioctl.c +++ b/fs/ocfs2/ioctl.c @@ -606,9 +606,7 @@ bail: if (gb_inode) mutex_unlock(&gb_inode->i_mutex); - if (gb_inode) - iput(gb_inode); - + iput(gb_inode); brelse(bh); return status; diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 13534f4fe5b5..3772a2dbb980 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -1042,8 +1042,7 @@ void ocfs2_journal_shutdown(struct ocfs2_super *osb) // up_write(&journal->j_trans_barrier); done: - if (inode) - iput(inode); + iput(inode); } static void ocfs2_clear_journal_error(struct super_block *sb, @@ -1687,9 +1686,7 @@ done: if (got_lock) ocfs2_inode_unlock(inode, 1); - if (inode) - iput(inode); - + iput(inode); brelse(bh); return status; @@ -1796,8 +1793,7 @@ static int ocfs2_trylock_journal(struct ocfs2_super *osb, ocfs2_inode_unlock(inode, 1); bail: - if (inode) - iput(inode); + iput(inode); return status; } diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c index 0a4457fb0711..e9c99e35f5ea 100644 --- a/fs/ocfs2/localalloc.c +++ b/fs/ocfs2/localalloc.c @@ -358,8 +358,7 @@ int ocfs2_load_local_alloc(struct ocfs2_super *osb) bail: if (status < 0) brelse(alloc_bh); - if (inode) - iput(inode); + iput(inode); trace_ocfs2_load_local_alloc(osb->local_alloc_bits); @@ -473,8 +472,7 @@ out_mutex: iput(main_bm_inode); out: - if (local_alloc_inode) - iput(local_alloc_inode); + iput(local_alloc_inode); kfree(alloc_copy); } @@ -1327,9 +1325,7 @@ bail: brelse(main_bm_bh); - if (main_bm_inode) - iput(main_bm_inode); - + iput(main_bm_inode); kfree(alloc_copy); if (ac) diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index afb81eae2c18..ab42c38031b1 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -1683,8 +1683,7 @@ bail: if (new_inode) sync_mapping_buffers(old_inode->i_mapping); - if (new_inode) - iput(new_inode); + iput(new_inode); ocfs2_free_dir_lookup_result(&target_lookup_res); ocfs2_free_dir_lookup_result(&old_entry_lookup); @@ -2373,6 +2372,15 @@ int ocfs2_orphan_del(struct ocfs2_super *osb, (unsigned long long)OCFS2_I(orphan_dir_inode)->ip_blkno, name, strlen(name)); + status = ocfs2_journal_access_di(handle, + INODE_CACHE(orphan_dir_inode), + orphan_dir_bh, + OCFS2_JOURNAL_ACCESS_WRITE); + if (status < 0) { + mlog_errno(status); + goto leave; + } + /* find it's spot in the orphan directory */ status = ocfs2_find_entry(name, strlen(name), orphan_dir_inode, &lookup); @@ -2388,15 +2396,6 @@ int ocfs2_orphan_del(struct ocfs2_super *osb, goto leave; } - status = ocfs2_journal_access_di(handle, - INODE_CACHE(orphan_dir_inode), - orphan_dir_bh, - OCFS2_JOURNAL_ACCESS_WRITE); - if (status < 0) { - mlog_errno(status); - goto leave; - } - /* do the i_nlink dance! :) */ orphan_fe = (struct ocfs2_dinode *) orphan_dir_bh->b_data; if (S_ISDIR(inode->i_mode)) diff --git a/fs/ocfs2/quota.h b/fs/ocfs2/quota.h index b6d51333ad02..d153e6e31529 100644 --- a/fs/ocfs2/quota.h +++ b/fs/ocfs2/quota.h @@ -82,7 +82,7 @@ struct ocfs2_quota_chunk { extern struct kmem_cache *ocfs2_dquot_cachep; extern struct kmem_cache *ocfs2_qf_chunk_cachep; -extern struct qtree_fmt_operations ocfs2_global_ops; +extern const struct qtree_fmt_operations ocfs2_global_ops; struct ocfs2_quota_recovery *ocfs2_begin_quota_recovery( struct ocfs2_super *osb, int slot_num); diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c index c93d67220887..fde9ef18cff3 100644 --- a/fs/ocfs2/quota_global.c +++ b/fs/ocfs2/quota_global.c @@ -123,7 +123,7 @@ static int ocfs2_global_is_id(void *dp, struct dquot *dquot) dquot->dq_id); } -struct qtree_fmt_operations ocfs2_global_ops = { +const struct qtree_fmt_operations ocfs2_global_ops = { .mem2disk_dqblk = ocfs2_global_mem2diskdqb, .disk2mem_dqblk = ocfs2_global_disk2memdqb, .is_id = ocfs2_global_is_id, diff --git a/fs/ocfs2/slot_map.c b/fs/ocfs2/slot_map.c index e78a203d44c8..1e09592148ad 100644 --- a/fs/ocfs2/slot_map.c +++ b/fs/ocfs2/slot_map.c @@ -322,8 +322,7 @@ static void __ocfs2_free_slot_info(struct ocfs2_slot_info *si) if (si == NULL) return; - if (si->si_inode) - iput(si->si_inode); + iput(si->si_inode); if (si->si_bh) { for (i = 0; i < si->si_blocks; i++) { if (si->si_bh[i]) { @@ -503,8 +502,17 @@ int ocfs2_find_slot(struct ocfs2_super *osb) trace_ocfs2_find_slot(osb->slot_num); status = ocfs2_update_disk_slot(osb, si, osb->slot_num); - if (status < 0) + if (status < 0) { mlog_errno(status); + /* + * if write block failed, invalidate slot to avoid overwrite + * slot during dismount in case another node rightly has mounted + */ + spin_lock(&osb->osb_lock); + ocfs2_invalidate_slot(si, osb->slot_num); + osb->slot_num = OCFS2_INVALID_SLOT; + spin_unlock(&osb->osb_lock); + } bail: return status; diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 2de4c8a9340c..faa1365097bc 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1280,6 +1280,8 @@ static int ocfs2_parse_options(struct super_block *sb, int status, user_stack = 0; char *p; u32 tmp; + int token, option; + substring_t args[MAX_OPT_ARGS]; trace_ocfs2_parse_options(is_remount, options ? options : "(none)"); @@ -1298,9 +1300,6 @@ static int ocfs2_parse_options(struct super_block *sb, } while ((p = strsep(&options, ",")) != NULL) { - int token, option; - substring_t args[MAX_OPT_ARGS]; - if (!*p) continue; @@ -1367,7 +1366,6 @@ static int ocfs2_parse_options(struct super_block *sb, mopt->atime_quantum = option; break; case Opt_slot: - option = 0; if (match_int(&args[0], &option)) { status = 0; goto bail; @@ -1376,7 +1374,6 @@ static int ocfs2_parse_options(struct super_block *sb, mopt->slot = (s16)option; break; case Opt_commit: - option = 0; if (match_int(&args[0], &option)) { status = 0; goto bail; @@ -1388,7 +1385,6 @@ static int ocfs2_parse_options(struct super_block *sb, mopt->commit_interval = HZ * option; break; case Opt_localalloc: - option = 0; if (match_int(&args[0], &option)) { status = 0; goto bail; @@ -1726,8 +1722,7 @@ static int ocfs2_statfs(struct dentry *dentry, struct kstatfs *buf) ocfs2_inode_unlock(inode, 0); status = 0; bail: - if (inode) - iput(inode); + iput(inode); if (status) mlog_errno(status); @@ -1771,7 +1766,7 @@ static int ocfs2_initialize_mem_caches(void) sizeof(struct ocfs2_inode_info), 0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), ocfs2_inode_init_once); ocfs2_dquot_cachep = kmem_cache_create("ocfs2_dquot_cache", sizeof(struct ocfs2_dquot), diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c index 15e4500cda3e..b61b883c8ff8 100644 --- a/fs/openpromfs/inode.c +++ b/fs/openpromfs/inode.c @@ -443,7 +443,7 @@ static int __init init_openprom_fs(void) sizeof(struct op_inode_info), 0, (SLAB_RECLAIM_ACCOUNT | - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD | SLAB_ACCOUNT), op_inode_init_once); if (!op_inode_cachep) return -ENOMEM; diff --git a/fs/proc/inode.c b/fs/proc/inode.c index d0e9b9b6223e..42305ddcbaa0 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -95,7 +95,8 @@ void __init proc_init_inodecache(void) proc_inode_cachep = kmem_cache_create("proc_inode_cache", sizeof(struct proc_inode), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD|SLAB_PANIC), + SLAB_MEM_SPREAD|SLAB_ACCOUNT| + SLAB_PANIC), init_once); } diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 9155a5a0d3b9..df4661abadc4 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -57,11 +57,8 @@ static int meminfo_proc_show(struct seq_file *m, void *v) /* * Estimate the amount of memory available for userspace allocations, * without causing swapping. - * - * Free memory cannot be taken below the low watermark, before the - * system starts swapping. */ - available = i.freeram - wmark_low; + available = i.freeram - totalreserve_pages; /* * Not all the page cache can be freed, otherwise the system will diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 187b3b5f242e..a353b4c6e86e 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -14,6 +14,7 @@ #include <linux/swapops.h> #include <linux/mmu_notifier.h> #include <linux/page_idle.h> +#include <linux/shmem_fs.h> #include <asm/elf.h> #include <asm/uaccess.h> @@ -22,9 +23,13 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) { - unsigned long data, text, lib, swap, ptes, pmds; + unsigned long text, lib, swap, ptes, pmds, anon, file, shmem; unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss; + anon = get_mm_counter(mm, MM_ANONPAGES); + file = get_mm_counter(mm, MM_FILEPAGES); + shmem = get_mm_counter(mm, MM_SHMEMPAGES); + /* * Note: to minimize their overhead, mm maintains hiwater_vm and * hiwater_rss only when about to *lower* total_vm or rss. Any @@ -35,11 +40,10 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) hiwater_vm = total_vm = mm->total_vm; if (hiwater_vm < mm->hiwater_vm) hiwater_vm = mm->hiwater_vm; - hiwater_rss = total_rss = get_mm_rss(mm); + hiwater_rss = total_rss = anon + file + shmem; if (hiwater_rss < mm->hiwater_rss) hiwater_rss = mm->hiwater_rss; - data = mm->total_vm - mm->shared_vm - mm->stack_vm; text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> 10; lib = (mm->exec_vm << (PAGE_SHIFT-10)) - text; swap = get_mm_counter(mm, MM_SWAPENTS); @@ -52,6 +56,9 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) "VmPin:\t%8lu kB\n" "VmHWM:\t%8lu kB\n" "VmRSS:\t%8lu kB\n" + "RssAnon:\t%8lu kB\n" + "RssFile:\t%8lu kB\n" + "RssShmem:\t%8lu kB\n" "VmData:\t%8lu kB\n" "VmStk:\t%8lu kB\n" "VmExe:\t%8lu kB\n" @@ -65,7 +72,10 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) mm->pinned_vm << (PAGE_SHIFT-10), hiwater_rss << (PAGE_SHIFT-10), total_rss << (PAGE_SHIFT-10), - data << (PAGE_SHIFT-10), + anon << (PAGE_SHIFT-10), + file << (PAGE_SHIFT-10), + shmem << (PAGE_SHIFT-10), + mm->data_vm << (PAGE_SHIFT-10), mm->stack_vm << (PAGE_SHIFT-10), text, lib, ptes >> 10, pmds >> 10, @@ -82,10 +92,11 @@ unsigned long task_statm(struct mm_struct *mm, unsigned long *shared, unsigned long *text, unsigned long *data, unsigned long *resident) { - *shared = get_mm_counter(mm, MM_FILEPAGES); + *shared = get_mm_counter(mm, MM_FILEPAGES) + + get_mm_counter(mm, MM_SHMEMPAGES); *text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> PAGE_SHIFT; - *data = mm->total_vm - mm->shared_vm; + *data = mm->data_vm + mm->stack_vm; *resident = *shared + get_mm_counter(mm, MM_ANONPAGES); return mm->total_vm; } @@ -451,6 +462,7 @@ struct mem_size_stats { unsigned long private_hugetlb; u64 pss; u64 swap_pss; + bool check_shmem_swap; }; static void smaps_account(struct mem_size_stats *mss, struct page *page, @@ -485,6 +497,19 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page, } } +#ifdef CONFIG_SHMEM +static int smaps_pte_hole(unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + struct mem_size_stats *mss = walk->private; + + mss->swap += shmem_partial_swap_usage( + walk->vma->vm_file->f_mapping, addr, end); + + return 0; +} +#endif + static void smaps_pte_entry(pte_t *pte, unsigned long addr, struct mm_walk *walk) { @@ -512,6 +537,19 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, } } else if (is_migration_entry(swpent)) page = migration_entry_to_page(swpent); + } else if (unlikely(IS_ENABLED(CONFIG_SHMEM) && mss->check_shmem_swap + && pte_none(*pte))) { + page = find_get_entry(vma->vm_file->f_mapping, + linear_page_index(vma, addr)); + if (!page) + return; + + if (radix_tree_exceptional_entry(page)) + mss->swap += PAGE_SIZE; + else + page_cache_release(page); + + return; } if (!page) @@ -671,6 +709,31 @@ static int show_smap(struct seq_file *m, void *v, int is_pid) }; memset(&mss, 0, sizeof mss); + +#ifdef CONFIG_SHMEM + if (vma->vm_file && shmem_mapping(vma->vm_file->f_mapping)) { + /* + * For shared or readonly shmem mappings we know that all + * swapped out pages belong to the shmem object, and we can + * obtain the swap value much more efficiently. For private + * writable mappings, we might have COW pages that are + * not affected by the parent swapped out pages of the shmem + * object, so we have to distinguish them during the page walk. + * Unless we know that the shmem object (or the part mapped by + * our VMA) has no swapped out pages at all. + */ + unsigned long shmem_swapped = shmem_swap_usage(vma); + + if (!shmem_swapped || (vma->vm_flags & VM_SHARED) || + !(vma->vm_flags & VM_WRITE)) { + mss.swap = shmem_swapped; + } else { + mss.check_shmem_swap = true; + smaps_walk.pte_hole = smaps_pte_hole; + } + } +#endif + /* mmap_sem is held in m_start */ walk_page_vma(vma, &smaps_walk); @@ -817,9 +880,6 @@ static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma, pmd = pmd_wrprotect(pmd); pmd = pmd_clear_soft_dirty(pmd); - if (vma->vm_flags & VM_SOFTDIRTY) - vma->vm_flags &= ~VM_SOFTDIRTY; - set_pmd_at(vma->vm_mm, addr, pmdp, pmd); } #else diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c index f37b3deb01b4..3a67cfb142d8 100644 --- a/fs/qnx4/inode.c +++ b/fs/qnx4/inode.c @@ -365,7 +365,7 @@ static int init_inodecache(void) qnx4_inode_cachep = kmem_cache_create("qnx4_inode_cache", sizeof(struct qnx4_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (qnx4_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c index 9728b5499e1d..47bb1de07155 100644 --- a/fs/qnx6/inode.c +++ b/fs/qnx6/inode.c @@ -625,7 +625,7 @@ static int init_inodecache(void) qnx6_inode_cachep = kmem_cache_create("qnx6_inode_cache", sizeof(struct qnx6_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (!qnx6_inode_cachep) return -ENOMEM; diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index ef0d64b2a6d9..fbd70af98820 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -2924,4 +2924,4 @@ static int __init dquot_init(void) return 0; } -module_init(dquot_init); +fs_initcall(dquot_init); diff --git a/fs/quota/netlink.c b/fs/quota/netlink.c index bb2869f5dfd8..d07a2f91d858 100644 --- a/fs/quota/netlink.c +++ b/fs/quota/netlink.c @@ -1,7 +1,5 @@ - #include <linux/cred.h> #include <linux/init.h> -#include <linux/module.h> #include <linux/kernel.h> #include <linux/quotaops.h> #include <linux/sched.h> @@ -105,5 +103,4 @@ static int __init quota_init(void) "VFS: Failed to create quota netlink interface.\n"); return 0; }; - -module_init(quota_init); +fs_initcall(quota_init); diff --git a/fs/quota/quota_v2.c b/fs/quota/quota_v2.c index 2aa012a68e90..ed85d4f35c04 100644 --- a/fs/quota/quota_v2.c +++ b/fs/quota/quota_v2.c @@ -30,13 +30,13 @@ static void v2r1_mem2diskdqb(void *dp, struct dquot *dquot); static void v2r1_disk2memdqb(struct dquot *dquot, void *dp); static int v2r1_is_id(void *dp, struct dquot *dquot); -static struct qtree_fmt_operations v2r0_qtree_ops = { +static const struct qtree_fmt_operations v2r0_qtree_ops = { .mem2disk_dqblk = v2r0_mem2diskdqb, .disk2mem_dqblk = v2r0_disk2memdqb, .is_id = v2r0_is_id, }; -static struct qtree_fmt_operations v2r1_qtree_ops = { +static const struct qtree_fmt_operations v2r1_qtree_ops = { .mem2disk_dqblk = v2r1_mem2diskdqb, .disk2mem_dqblk = v2r1_disk2memdqb, .is_id = v2r1_is_id, diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 4a62fe8cc3bf..05db7473bcb5 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -626,7 +626,8 @@ static int __init init_inodecache(void) sizeof(struct reiserfs_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD| + SLAB_ACCOUNT), init_once); if (reiserfs_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/romfs/super.c b/fs/romfs/super.c index bb894e78a821..6b00ca357c58 100644 --- a/fs/romfs/super.c +++ b/fs/romfs/super.c @@ -619,8 +619,8 @@ static int __init init_romfs_fs(void) romfs_inode_cachep = kmem_cache_create("romfs_i", sizeof(struct romfs_inode_info), 0, - SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, - romfs_i_init_once); + SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD | + SLAB_ACCOUNT, romfs_i_init_once); if (!romfs_inode_cachep) { pr_err("Failed to initialise inode cache\n"); diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c index dded920cbc8f..5e79bfa4f260 100644 --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -419,7 +419,8 @@ static int __init init_inodecache(void) { squashfs_inode_cachep = kmem_cache_create("squashfs_inode_cache", sizeof(struct squashfs_inode_info), 0, - SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT, init_once); + SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|SLAB_ACCOUNT, + init_once); return squashfs_inode_cachep ? 0 : -ENOMEM; } diff --git a/fs/super.c b/fs/super.c index cc658a20a29e..1182af8fd5ff 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1197,7 +1197,7 @@ int __sb_start_write(struct super_block *sb, int level, bool wait) else ret = percpu_down_read_trylock(sb->s_writers.rw_sem + level-1); - WARN_ON(force_trylock & !ret); + WARN_ON(force_trylock && !ret); return ret; } EXPORT_SYMBOL(__sb_start_write); diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c index 07ac18c355e7..d62c423a5a2d 100644 --- a/fs/sysv/inode.c +++ b/fs/sysv/inode.c @@ -346,7 +346,7 @@ int __init sysv_init_icache(void) { sysv_inode_cachep = kmem_cache_create("sysv_inode_cache", sizeof(struct sysv_inode_info), 0, - SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, + SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|SLAB_ACCOUNT, init_once); if (!sysv_inode_cachep) return -ENOMEM; diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 1fd90c079537..a233ba913be4 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -2248,8 +2248,8 @@ static int __init ubifs_init(void) ubifs_inode_slab = kmem_cache_create("ubifs_inode_slab", sizeof(struct ubifs_inode), 0, - SLAB_MEM_SPREAD | SLAB_RECLAIM_ACCOUNT, - &inode_slab_ctor); + SLAB_MEM_SPREAD | SLAB_RECLAIM_ACCOUNT | + SLAB_ACCOUNT, &inode_slab_ctor); if (!ubifs_inode_slab) return -ENOMEM; diff --git a/fs/udf/balloc.c b/fs/udf/balloc.c index 6d6a96b4e73f..e0fd65fe73e8 100644 --- a/fs/udf/balloc.c +++ b/fs/udf/balloc.c @@ -447,9 +447,6 @@ static void udf_table_free_blocks(struct super_block *sb, */ int adsize; - struct short_ad *sad = NULL; - struct long_ad *lad = NULL; - struct allocExtDesc *aed; eloc.logicalBlockNum = start; elen = EXT_RECORDED_ALLOCATED | @@ -466,102 +463,17 @@ static void udf_table_free_blocks(struct super_block *sb, } if (epos.offset + (2 * adsize) > sb->s_blocksize) { - unsigned char *sptr, *dptr; - int loffset; - - brelse(oepos.bh); - oepos = epos; - /* Steal a block from the extent being free'd */ - epos.block.logicalBlockNum = eloc.logicalBlockNum; + udf_setup_indirect_aext(table, eloc.logicalBlockNum, + &epos); + eloc.logicalBlockNum++; elen -= sb->s_blocksize; - - epos.bh = udf_tread(sb, - udf_get_lb_pblock(sb, &epos.block, 0)); - if (!epos.bh) { - brelse(oepos.bh); - goto error_return; - } - aed = (struct allocExtDesc *)(epos.bh->b_data); - aed->previousAllocExtLocation = - cpu_to_le32(oepos.block.logicalBlockNum); - if (epos.offset + adsize > sb->s_blocksize) { - loffset = epos.offset; - aed->lengthAllocDescs = cpu_to_le32(adsize); - sptr = iinfo->i_ext.i_data + epos.offset - - adsize; - dptr = epos.bh->b_data + - sizeof(struct allocExtDesc); - memcpy(dptr, sptr, adsize); - epos.offset = sizeof(struct allocExtDesc) + - adsize; - } else { - loffset = epos.offset + adsize; - aed->lengthAllocDescs = cpu_to_le32(0); - if (oepos.bh) { - sptr = oepos.bh->b_data + epos.offset; - aed = (struct allocExtDesc *) - oepos.bh->b_data; - le32_add_cpu(&aed->lengthAllocDescs, - adsize); - } else { - sptr = iinfo->i_ext.i_data + - epos.offset; - iinfo->i_lenAlloc += adsize; - mark_inode_dirty(table); - } - epos.offset = sizeof(struct allocExtDesc); - } - if (sbi->s_udfrev >= 0x0200) - udf_new_tag(epos.bh->b_data, TAG_IDENT_AED, - 3, 1, epos.block.logicalBlockNum, - sizeof(struct tag)); - else - udf_new_tag(epos.bh->b_data, TAG_IDENT_AED, - 2, 1, epos.block.logicalBlockNum, - sizeof(struct tag)); - - switch (iinfo->i_alloc_type) { - case ICBTAG_FLAG_AD_SHORT: - sad = (struct short_ad *)sptr; - sad->extLength = cpu_to_le32( - EXT_NEXT_EXTENT_ALLOCDECS | - sb->s_blocksize); - sad->extPosition = - cpu_to_le32(epos.block.logicalBlockNum); - break; - case ICBTAG_FLAG_AD_LONG: - lad = (struct long_ad *)sptr; - lad->extLength = cpu_to_le32( - EXT_NEXT_EXTENT_ALLOCDECS | - sb->s_blocksize); - lad->extLocation = - cpu_to_lelb(epos.block); - break; - } - if (oepos.bh) { - udf_update_tag(oepos.bh->b_data, loffset); - mark_buffer_dirty(oepos.bh); - } else { - mark_inode_dirty(table); - } } /* It's possible that stealing the block emptied the extent */ - if (elen) { - udf_write_aext(table, &epos, &eloc, elen, 1); - - if (!epos.bh) { - iinfo->i_lenAlloc += adsize; - mark_inode_dirty(table); - } else { - aed = (struct allocExtDesc *)epos.bh->b_data; - le32_add_cpu(&aed->lengthAllocDescs, adsize); - udf_update_tag(epos.bh->b_data, epos.offset); - mark_buffer_dirty(epos.bh); - } - } + if (elen) + __udf_add_aext(table, &epos, &eloc, elen, 1); } brelse(epos.bh); diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 055746350d16..87dc16d15572 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -539,9 +539,18 @@ static int udf_do_extend_file(struct inode *inode, udf_add_aext(inode, last_pos, &last_ext->extLocation, last_ext->extLength, 1); count++; - } else + } else { + struct kernel_lb_addr tmploc; + uint32_t tmplen; + udf_write_aext(inode, last_pos, &last_ext->extLocation, last_ext->extLength, 1); + /* + * We've rewritten the last extent but there may be empty + * indirect extent after it - enter it. + */ + udf_next_aext(inode, last_pos, &tmploc, &tmplen, 0); + } /* Managed to do everything necessary? */ if (!blocks) @@ -1867,22 +1876,90 @@ struct inode *__udf_iget(struct super_block *sb, struct kernel_lb_addr *ino, return inode; } -int udf_add_aext(struct inode *inode, struct extent_position *epos, - struct kernel_lb_addr *eloc, uint32_t elen, int inc) +int udf_setup_indirect_aext(struct inode *inode, int block, + struct extent_position *epos) { - int adsize; - struct short_ad *sad = NULL; - struct long_ad *lad = NULL; + struct super_block *sb = inode->i_sb; + struct buffer_head *bh; struct allocExtDesc *aed; - uint8_t *ptr; - struct udf_inode_info *iinfo = UDF_I(inode); + struct extent_position nepos; + struct kernel_lb_addr neloc; + int ver, adsize; - if (!epos->bh) - ptr = iinfo->i_ext.i_data + epos->offset - - udf_file_entry_alloc_offset(inode) + - iinfo->i_lenEAttr; + if (UDF_I(inode)->i_alloc_type == ICBTAG_FLAG_AD_SHORT) + adsize = sizeof(struct short_ad); + else if (UDF_I(inode)->i_alloc_type == ICBTAG_FLAG_AD_LONG) + adsize = sizeof(struct long_ad); else - ptr = epos->bh->b_data + epos->offset; + return -EIO; + + neloc.logicalBlockNum = block; + neloc.partitionReferenceNum = epos->block.partitionReferenceNum; + + bh = udf_tgetblk(sb, udf_get_lb_pblock(sb, &neloc, 0)); + if (!bh) + return -EIO; + lock_buffer(bh); + memset(bh->b_data, 0x00, sb->s_blocksize); + set_buffer_uptodate(bh); + unlock_buffer(bh); + mark_buffer_dirty_inode(bh, inode); + + aed = (struct allocExtDesc *)(bh->b_data); + if (!UDF_QUERY_FLAG(sb, UDF_FLAG_STRICT)) { + aed->previousAllocExtLocation = + cpu_to_le32(epos->block.logicalBlockNum); + } + aed->lengthAllocDescs = cpu_to_le32(0); + if (UDF_SB(sb)->s_udfrev >= 0x0200) + ver = 3; + else + ver = 2; + udf_new_tag(bh->b_data, TAG_IDENT_AED, ver, 1, block, + sizeof(struct tag)); + + nepos.block = neloc; + nepos.offset = sizeof(struct allocExtDesc); + nepos.bh = bh; + + /* + * Do we have to copy current last extent to make space for indirect + * one? + */ + if (epos->offset + adsize > sb->s_blocksize) { + struct kernel_lb_addr cp_loc; + uint32_t cp_len; + int cp_type; + + epos->offset -= adsize; + cp_type = udf_current_aext(inode, epos, &cp_loc, &cp_len, 0); + cp_len |= ((uint32_t)cp_type) << 30; + + __udf_add_aext(inode, &nepos, &cp_loc, cp_len, 1); + udf_write_aext(inode, epos, &nepos.block, + sb->s_blocksize | EXT_NEXT_EXTENT_ALLOCDECS, 0); + } else { + __udf_add_aext(inode, epos, &nepos.block, + sb->s_blocksize | EXT_NEXT_EXTENT_ALLOCDECS, 0); + } + + brelse(epos->bh); + *epos = nepos; + + return 0; +} + +/* + * Append extent at the given position - should be the first free one in inode + * / indirect extent. This function assumes there is enough space in the inode + * or indirect extent. Use udf_add_aext() if you didn't check for this before. + */ +int __udf_add_aext(struct inode *inode, struct extent_position *epos, + struct kernel_lb_addr *eloc, uint32_t elen, int inc) +{ + struct udf_inode_info *iinfo = UDF_I(inode); + struct allocExtDesc *aed; + int adsize; if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT) adsize = sizeof(struct short_ad); @@ -1891,88 +1968,14 @@ int udf_add_aext(struct inode *inode, struct extent_position *epos, else return -EIO; - if (epos->offset + (2 * adsize) > inode->i_sb->s_blocksize) { - unsigned char *sptr, *dptr; - struct buffer_head *nbh; - int err, loffset; - struct kernel_lb_addr obloc = epos->block; - - epos->block.logicalBlockNum = udf_new_block(inode->i_sb, NULL, - obloc.partitionReferenceNum, - obloc.logicalBlockNum, &err); - if (!epos->block.logicalBlockNum) - return -ENOSPC; - nbh = udf_tgetblk(inode->i_sb, udf_get_lb_pblock(inode->i_sb, - &epos->block, - 0)); - if (!nbh) - return -EIO; - lock_buffer(nbh); - memset(nbh->b_data, 0x00, inode->i_sb->s_blocksize); - set_buffer_uptodate(nbh); - unlock_buffer(nbh); - mark_buffer_dirty_inode(nbh, inode); - - aed = (struct allocExtDesc *)(nbh->b_data); - if (!UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_STRICT)) - aed->previousAllocExtLocation = - cpu_to_le32(obloc.logicalBlockNum); - if (epos->offset + adsize > inode->i_sb->s_blocksize) { - loffset = epos->offset; - aed->lengthAllocDescs = cpu_to_le32(adsize); - sptr = ptr - adsize; - dptr = nbh->b_data + sizeof(struct allocExtDesc); - memcpy(dptr, sptr, adsize); - epos->offset = sizeof(struct allocExtDesc) + adsize; - } else { - loffset = epos->offset + adsize; - aed->lengthAllocDescs = cpu_to_le32(0); - sptr = ptr; - epos->offset = sizeof(struct allocExtDesc); - - if (epos->bh) { - aed = (struct allocExtDesc *)epos->bh->b_data; - le32_add_cpu(&aed->lengthAllocDescs, adsize); - } else { - iinfo->i_lenAlloc += adsize; - mark_inode_dirty(inode); - } - } - if (UDF_SB(inode->i_sb)->s_udfrev >= 0x0200) - udf_new_tag(nbh->b_data, TAG_IDENT_AED, 3, 1, - epos->block.logicalBlockNum, sizeof(struct tag)); - else - udf_new_tag(nbh->b_data, TAG_IDENT_AED, 2, 1, - epos->block.logicalBlockNum, sizeof(struct tag)); - switch (iinfo->i_alloc_type) { - case ICBTAG_FLAG_AD_SHORT: - sad = (struct short_ad *)sptr; - sad->extLength = cpu_to_le32(EXT_NEXT_EXTENT_ALLOCDECS | - inode->i_sb->s_blocksize); - sad->extPosition = - cpu_to_le32(epos->block.logicalBlockNum); - break; - case ICBTAG_FLAG_AD_LONG: - lad = (struct long_ad *)sptr; - lad->extLength = cpu_to_le32(EXT_NEXT_EXTENT_ALLOCDECS | - inode->i_sb->s_blocksize); - lad->extLocation = cpu_to_lelb(epos->block); - memset(lad->impUse, 0x00, sizeof(lad->impUse)); - break; - } - if (epos->bh) { - if (!UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_STRICT) || - UDF_SB(inode->i_sb)->s_udfrev >= 0x0201) - udf_update_tag(epos->bh->b_data, loffset); - else - udf_update_tag(epos->bh->b_data, - sizeof(struct allocExtDesc)); - mark_buffer_dirty_inode(epos->bh, inode); - brelse(epos->bh); - } else { - mark_inode_dirty(inode); - } - epos->bh = nbh; + if (!epos->bh) { + WARN_ON(iinfo->i_lenAlloc != + epos->offset - udf_file_entry_alloc_offset(inode)); + } else { + aed = (struct allocExtDesc *)epos->bh->b_data; + WARN_ON(le32_to_cpu(aed->lengthAllocDescs) != + epos->offset - sizeof(struct allocExtDesc)); + WARN_ON(epos->offset + adsize > inode->i_sb->s_blocksize); } udf_write_aext(inode, epos, eloc, elen, inc); @@ -1996,6 +1999,41 @@ int udf_add_aext(struct inode *inode, struct extent_position *epos, return 0; } +/* + * Append extent at given position - should be the first free one in inode + * / indirect extent. Takes care of allocating and linking indirect blocks. + */ +int udf_add_aext(struct inode *inode, struct extent_position *epos, + struct kernel_lb_addr *eloc, uint32_t elen, int inc) +{ + int adsize; + struct super_block *sb = inode->i_sb; + + if (UDF_I(inode)->i_alloc_type == ICBTAG_FLAG_AD_SHORT) + adsize = sizeof(struct short_ad); + else if (UDF_I(inode)->i_alloc_type == ICBTAG_FLAG_AD_LONG) + adsize = sizeof(struct long_ad); + else + return -EIO; + + if (epos->offset + (2 * adsize) > sb->s_blocksize) { + int err; + int new_block; + + new_block = udf_new_block(sb, NULL, + epos->block.partitionReferenceNum, + epos->block.logicalBlockNum, &err); + if (!new_block) + return -ENOSPC; + + err = udf_setup_indirect_aext(inode, new_block, epos); + if (err) + return err; + } + + return __udf_add_aext(inode, epos, eloc, elen, inc); +} + void udf_write_aext(struct inode *inode, struct extent_position *epos, struct kernel_lb_addr *eloc, uint32_t elen, int inc) { @@ -2048,14 +2086,29 @@ void udf_write_aext(struct inode *inode, struct extent_position *epos, epos->offset += adsize; } +/* + * Only 1 indirect extent in a row really makes sense but allow upto 16 in case + * someone does some weird stuff. + */ +#define UDF_MAX_INDIR_EXTS 16 + int8_t udf_next_aext(struct inode *inode, struct extent_position *epos, struct kernel_lb_addr *eloc, uint32_t *elen, int inc) { int8_t etype; + unsigned int indirections = 0; while ((etype = udf_current_aext(inode, epos, eloc, elen, inc)) == (EXT_NEXT_EXTENT_ALLOCDECS >> 30)) { int block; + + if (++indirections > UDF_MAX_INDIR_EXTS) { + udf_err(inode->i_sb, + "too many indirect extents in inode %lu\n", + inode->i_ino); + return -1; + } + epos->block = *eloc; epos->offset = sizeof(struct allocExtDesc); brelse(epos->bh); diff --git a/fs/udf/super.c b/fs/udf/super.c index 81155b9b445b..0fbb4c7c72e8 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -179,7 +179,8 @@ static int __init init_inodecache(void) udf_inode_cachep = kmem_cache_create("udf_inode_cache", sizeof(struct udf_inode_info), 0, (SLAB_RECLAIM_ACCOUNT | - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD | + SLAB_ACCOUNT), init_once); if (!udf_inode_cachep) return -ENOMEM; @@ -1586,6 +1587,13 @@ static void udf_load_logicalvolint(struct super_block *sb, struct kernel_extent_ } /* + * Maximum number of Terminating Descriptor redirections. The chosen number is + * arbitrary - just that we hopefully don't limit any real use of rewritten + * inode on write-once media but avoid looping for too long on corrupted media. + */ +#define UDF_MAX_TD_NESTING 64 + +/* * Process a main/reserve volume descriptor sequence. * @block First block of first extent of the sequence. * @lastblock Lastblock of first extent of the sequence. @@ -1609,6 +1617,7 @@ static noinline int udf_process_sequence( uint16_t ident; long next_s = 0, next_e = 0; int ret; + unsigned int indirections = 0; memset(vds, 0, sizeof(struct udf_vds_record) * VDS_POS_LENGTH); @@ -1679,6 +1688,12 @@ static noinline int udf_process_sequence( } break; case TAG_IDENT_TD: /* ISO 13346 3/10.9 */ + if (++indirections > UDF_MAX_TD_NESTING) { + udf_err(sb, "too many TDs (max %u supported)\n", UDF_MAX_TD_NESTING); + brelse(bh); + return -EIO; + } + vds[VDS_POS_TERMINATING_DESC].block = block; if (next_e) { block = next_s; diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h index ce169b49429d..fa0044b6b81d 100644 --- a/fs/udf/udfdecl.h +++ b/fs/udf/udfdecl.h @@ -158,6 +158,10 @@ extern int udf_write_inode(struct inode *, struct writeback_control *wbc); extern long udf_block_map(struct inode *, sector_t); extern int8_t inode_bmap(struct inode *, sector_t, struct extent_position *, struct kernel_lb_addr *, uint32_t *, sector_t *); +extern int udf_setup_indirect_aext(struct inode *inode, int block, + struct extent_position *epos); +extern int __udf_add_aext(struct inode *inode, struct extent_position *epos, + struct kernel_lb_addr *eloc, uint32_t elen, int inc); extern int udf_add_aext(struct inode *, struct extent_position *, struct kernel_lb_addr *, uint32_t, int); extern void udf_write_aext(struct inode *, struct extent_position *, diff --git a/fs/udf/unicode.c b/fs/udf/unicode.c index ab478e62baae..e788a05aab83 100644 --- a/fs/udf/unicode.c +++ b/fs/udf/unicode.c @@ -128,11 +128,15 @@ int udf_CS0toUTF8(struct ustr *utf_o, const struct ustr *ocu_i) if (c < 0x80U) utf_o->u_name[utf_o->u_len++] = (uint8_t)c; else if (c < 0x800U) { + if (utf_o->u_len > (UDF_NAME_LEN - 4)) + break; utf_o->u_name[utf_o->u_len++] = (uint8_t)(0xc0 | (c >> 6)); utf_o->u_name[utf_o->u_len++] = (uint8_t)(0x80 | (c & 0x3f)); } else { + if (utf_o->u_len > (UDF_NAME_LEN - 5)) + break; utf_o->u_name[utf_o->u_len++] = (uint8_t)(0xe0 | (c >> 12)); utf_o->u_name[utf_o->u_len++] = @@ -173,17 +177,22 @@ int udf_CS0toUTF8(struct ustr *utf_o, const struct ustr *ocu_i) static int udf_UTF8toCS0(dstring *ocu, struct ustr *utf, int length) { unsigned c, i, max_val, utf_char; - int utf_cnt, u_len; + int utf_cnt, u_len, u_ch; memset(ocu, 0, sizeof(dstring) * length); ocu[0] = 8; max_val = 0xffU; + u_ch = 1; try_again: u_len = 0U; utf_char = 0U; utf_cnt = 0U; for (i = 0U; i < utf->u_len; i++) { + /* Name didn't fit? */ + if (u_len + 1 + u_ch >= length) + return 0; + c = (uint8_t)utf->u_name[i]; /* Complete a multi-byte UTF-8 character */ @@ -225,6 +234,7 @@ try_again: if (max_val == 0xffU) { max_val = 0xffffU; ocu[0] = (uint8_t)0x10U; + u_ch = 2; goto try_again; } goto error_out; @@ -277,7 +287,7 @@ static int udf_CS0toNLS(struct nls_table *nls, struct ustr *utf_o, c = (c << 8) | ocu[i++]; len = nls->uni2char(c, &utf_o->u_name[utf_o->u_len], - UDF_NAME_LEN - utf_o->u_len); + UDF_NAME_LEN - 2 - utf_o->u_len); /* Valid character? */ if (len >= 0) utf_o->u_len += len; @@ -295,15 +305,19 @@ static int udf_NLStoCS0(struct nls_table *nls, dstring *ocu, struct ustr *uni, int len; unsigned i, max_val; uint16_t uni_char; - int u_len; + int u_len, u_ch; memset(ocu, 0, sizeof(dstring) * length); ocu[0] = 8; max_val = 0xffU; + u_ch = 1; try_again: u_len = 0U; for (i = 0U; i < uni->u_len; i++) { + /* Name didn't fit? */ + if (u_len + 1 + u_ch >= length) + return 0; len = nls->char2uni(&uni->u_name[i], uni->u_len - i, &uni_char); if (!len) continue; @@ -316,6 +330,7 @@ try_again: if (uni_char > max_val) { max_val = 0xffffU; ocu[0] = (uint8_t)0x10U; + u_ch = 2; goto try_again; } diff --git a/fs/ufs/super.c b/fs/ufs/super.c index f6390eec02ca..442fd52ebffe 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -1427,7 +1427,7 @@ static int __init init_inodecache(void) ufs_inode_cachep = kmem_cache_create("ufs_inode_cache", sizeof(struct ufs_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (ufs_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/xfs/kmem.h b/fs/xfs/kmem.h index cc6b768fc068..d1c66e465ca5 100644 --- a/fs/xfs/kmem.h +++ b/fs/xfs/kmem.h @@ -84,6 +84,7 @@ kmem_zalloc(size_t size, xfs_km_flags_t flags) #define KM_ZONE_HWALIGN SLAB_HWCACHE_ALIGN #define KM_ZONE_RECLAIM SLAB_RECLAIM_ACCOUNT #define KM_ZONE_SPREAD SLAB_MEM_SPREAD +#define KM_ZONE_ACCOUNT SLAB_ACCOUNT #define kmem_zone kmem_cache #define kmem_zone_t struct kmem_cache diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index b35775752b74..59c9b7bd958d 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1714,8 +1714,8 @@ xfs_init_zones(void) xfs_inode_zone = kmem_zone_init_flags(sizeof(xfs_inode_t), "xfs_inode", - KM_ZONE_HWALIGN | KM_ZONE_RECLAIM | KM_ZONE_SPREAD, - xfs_fs_inode_init_once); + KM_ZONE_HWALIGN | KM_ZONE_RECLAIM | KM_ZONE_SPREAD | + KM_ZONE_ACCOUNT, xfs_fs_inode_init_once); if (!xfs_inode_zone) goto out_destroy_efi_zone; diff --git a/include/asm-generic/memory_model.h b/include/asm-generic/memory_model.h index 4b4b056a6eb0..5148150cc80b 100644 --- a/include/asm-generic/memory_model.h +++ b/include/asm-generic/memory_model.h @@ -1,6 +1,8 @@ #ifndef __ASM_MEMORY_MODEL_H #define __ASM_MEMORY_MODEL_H +#include <linux/pfn.h> + #ifndef __ASSEMBLY__ #if defined(CONFIG_FLATMEM) @@ -72,7 +74,7 @@ /* * Convert a physical address to a Page Frame Number and back */ -#define __phys_to_pfn(paddr) ((unsigned long)((paddr) >> PAGE_SHIFT)) +#define __phys_to_pfn(paddr) PHYS_PFN(paddr) #define __pfn_to_phys(pfn) PFN_PHYS(pfn) #define page_to_pfn __page_to_pfn diff --git a/include/dt-bindings/leds/common.h b/include/dt-bindings/leds/common.h index 79fcef72ef57..7958bec7de8c 100644 --- a/include/dt-bindings/leds/common.h +++ b/include/dt-bindings/leds/common.h @@ -6,7 +6,7 @@ * Author: Jacek Anaszewski <j.anaszewski@samsung.com> */ -#ifndef __DT_BINDINGS_LEDS_H__ +#ifndef __DT_BINDINGS_LEDS_H #define __DT_BINDINGS_LEDS_H /* External trigger type */ diff --git a/include/dt-bindings/mfd/palmas.h b/include/dt-bindings/mfd/palmas.h index 2c8ac4841385..cdb075aae4e1 100644 --- a/include/dt-bindings/mfd/palmas.h +++ b/include/dt-bindings/mfd/palmas.h @@ -7,7 +7,7 @@ * */ -#ifndef __DT_BINDINGS_PALMAS_H__ +#ifndef __DT_BINDINGS_PALMAS_H #define __DT_BINDINGS_PALMAS_H /* External control pins */ diff --git a/include/linux/dcache.h b/include/linux/dcache.h index d67ae119cf4e..7781ce110503 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -27,10 +27,10 @@ struct vfsmount; /* The hash is always the low bits of hash_len */ #ifdef __LITTLE_ENDIAN - #define HASH_LEN_DECLARE u32 hash; u32 len; + #define HASH_LEN_DECLARE u32 hash; u32 len #define bytemask_from_count(cnt) (~(~0ul << (cnt)*8)) #else - #define HASH_LEN_DECLARE u32 len; u32 hash; + #define HASH_LEN_DECLARE u32 len; u32 hash #define bytemask_from_count(cnt) (~(~0ul >> (cnt)*8)) #endif diff --git a/include/linux/dqblk_qtree.h b/include/linux/dqblk_qtree.h index 82a16527b367..ff8b55359648 100644 --- a/include/linux/dqblk_qtree.h +++ b/include/linux/dqblk_qtree.h @@ -34,7 +34,7 @@ struct qtree_mem_dqinfo { unsigned int dqi_entry_size; /* Size of quota entry in quota file */ unsigned int dqi_usable_bs; /* Space usable in block for quota data */ unsigned int dqi_qtree_depth; /* Precomputed depth of quota tree */ - struct qtree_fmt_operations *dqi_ops; /* Operations for entry manipulation */ + const struct qtree_fmt_operations *dqi_ops; /* Operations for entry manipulation */ }; int qtree_write_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot); diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 533c4408529a..6b7e89f45aa4 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -220,7 +220,10 @@ struct fsnotify_mark { /* List of marks by group->i_fsnotify_marks. Also reused for queueing * mark into destroy_list when it's waiting for the end of SRCU period * before it can be freed. [group->mark_mutex] */ - struct list_head g_list; + union { + struct list_head g_list; + struct rcu_head g_rcu; + }; /* Protects inode / mnt pointers, flags, masks */ spinlock_t lock; /* List of marks for inode / vfsmount [obj_lock] */ diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h index 7ff168d06967..29d4385903d4 100644 --- a/include/linux/genalloc.h +++ b/include/linux/genalloc.h @@ -30,10 +30,12 @@ #ifndef __GENALLOC_H__ #define __GENALLOC_H__ +#include <linux/types.h> #include <linux/spinlock_types.h> struct device; struct device_node; +struct gen_pool; /** * Allocation callback function type definition @@ -47,7 +49,7 @@ typedef unsigned long (*genpool_algo_t)(unsigned long *map, unsigned long size, unsigned long start, unsigned int nr, - void *data); + void *data, struct gen_pool *pool); /* * General purpose special memory pool descriptor. @@ -75,6 +77,20 @@ struct gen_pool_chunk { unsigned long bits[0]; /* bitmap for allocating memory chunk */ }; +/* + * gen_pool data descriptor for gen_pool_first_fit_align. + */ +struct genpool_data_align { + int align; /* alignment by bytes for starting address */ +}; + +/* + * gen_pool data descriptor for gen_pool_fixed_alloc. + */ +struct genpool_data_fixed { + unsigned long offset; /* The offset of the specific region */ +}; + extern struct gen_pool *gen_pool_create(int, int); extern phys_addr_t gen_pool_virt_to_phys(struct gen_pool *pool, unsigned long); extern int gen_pool_add_virt(struct gen_pool *, unsigned long, phys_addr_t, @@ -98,6 +114,8 @@ static inline int gen_pool_add(struct gen_pool *pool, unsigned long addr, } extern void gen_pool_destroy(struct gen_pool *); extern unsigned long gen_pool_alloc(struct gen_pool *, size_t); +extern unsigned long gen_pool_alloc_algo(struct gen_pool *, size_t, + genpool_algo_t algo, void *data); extern void *gen_pool_dma_alloc(struct gen_pool *pool, size_t size, dma_addr_t *dma); extern void gen_pool_free(struct gen_pool *, unsigned long, size_t); @@ -110,14 +128,26 @@ extern void gen_pool_set_algo(struct gen_pool *pool, genpool_algo_t algo, void *data); extern unsigned long gen_pool_first_fit(unsigned long *map, unsigned long size, - unsigned long start, unsigned int nr, void *data); + unsigned long start, unsigned int nr, void *data, + struct gen_pool *pool); + +extern unsigned long gen_pool_fixed_alloc(unsigned long *map, + unsigned long size, unsigned long start, unsigned int nr, + void *data, struct gen_pool *pool); + +extern unsigned long gen_pool_first_fit_align(unsigned long *map, + unsigned long size, unsigned long start, unsigned int nr, + void *data, struct gen_pool *pool); + extern unsigned long gen_pool_first_fit_order_align(unsigned long *map, unsigned long size, unsigned long start, unsigned int nr, - void *data); + void *data, struct gen_pool *pool); extern unsigned long gen_pool_best_fit(unsigned long *map, unsigned long size, - unsigned long start, unsigned int nr, void *data); + unsigned long start, unsigned int nr, void *data, + struct gen_pool *pool); + extern struct gen_pool *devm_gen_pool_create(struct device *dev, int min_alloc_order, int nid, const char *name); diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 8942af0813e3..28ad5f6494b0 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -30,7 +30,7 @@ struct vm_area_struct; #define ___GFP_HARDWALL 0x20000u #define ___GFP_THISNODE 0x40000u #define ___GFP_ATOMIC 0x80000u -#define ___GFP_NOACCOUNT 0x100000u +#define ___GFP_ACCOUNT 0x100000u #define ___GFP_NOTRACK 0x200000u #define ___GFP_DIRECT_RECLAIM 0x400000u #define ___GFP_OTHER_NODE 0x800000u @@ -73,11 +73,15 @@ struct vm_area_struct; * * __GFP_THISNODE forces the allocation to be satisified from the requested * node with no fallbacks or placement policy enforcements. + * + * __GFP_ACCOUNT causes the allocation to be accounted to kmemcg (only relevant + * to kmem allocations). */ #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) #define __GFP_WRITE ((__force gfp_t)___GFP_WRITE) #define __GFP_HARDWALL ((__force gfp_t)___GFP_HARDWALL) #define __GFP_THISNODE ((__force gfp_t)___GFP_THISNODE) +#define __GFP_ACCOUNT ((__force gfp_t)___GFP_ACCOUNT) /* * Watermark modifiers -- controls access to emergency reserves @@ -104,7 +108,6 @@ struct vm_area_struct; #define __GFP_HIGH ((__force gfp_t)___GFP_HIGH) #define __GFP_MEMALLOC ((__force gfp_t)___GFP_MEMALLOC) #define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC) -#define __GFP_NOACCOUNT ((__force gfp_t)___GFP_NOACCOUNT) /* * Reclaim modifiers @@ -197,6 +200,9 @@ struct vm_area_struct; * GFP_KERNEL is typical for kernel-internal allocations. The caller requires * ZONE_NORMAL or a lower zone for direct access but can direct reclaim. * + * GFP_KERNEL_ACCOUNT is the same as GFP_KERNEL, except the allocation is + * accounted to kmemcg. + * * GFP_NOWAIT is for kernel allocations that should not stall for direct * reclaim, start physical IO or use any filesystem callback. * @@ -236,6 +242,7 @@ struct vm_area_struct; */ #define GFP_ATOMIC (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM) #define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS) +#define GFP_KERNEL_ACCOUNT (GFP_KERNEL | __GFP_ACCOUNT) #define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM) #define GFP_NOIO (__GFP_RECLAIM) #define GFP_NOFS (__GFP_RECLAIM | __GFP_IO) @@ -271,7 +278,7 @@ static inline int gfpflags_to_migratetype(const gfp_t gfp_flags) static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags) { - return (bool __force)(gfp_flags & __GFP_DIRECT_RECLAIM); + return !!(gfp_flags & __GFP_DIRECT_RECLAIM); } #ifdef CONFIG_HIGHMEM @@ -377,10 +384,11 @@ static inline enum zone_type gfp_zone(gfp_t flags) static inline int gfp_zonelist(gfp_t flags) { - if (IS_ENABLED(CONFIG_NUMA) && unlikely(flags & __GFP_THISNODE)) - return 1; - - return 0; +#ifdef CONFIG_NUMA + if (unlikely(flags & __GFP_THISNODE)) + return ZONELIST_NOFALLBACK; +#endif + return ZONELIST_FALLBACK; } /* diff --git a/include/linux/hid.h b/include/linux/hid.h index 251a1d382e23..75b66eccc692 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -168,6 +168,8 @@ struct hid_item { #define HID_UP_MSVENDOR 0xff000000 #define HID_UP_CUSTOM 0x00ff0000 #define HID_UP_LOGIVENDOR 0xffbc0000 +#define HID_UP_LOGIVENDOR2 0xff090000 +#define HID_UP_LOGIVENDOR3 0xff430000 #define HID_UP_LNVENDOR 0xffa00000 #define HID_UP_SENSOR 0x00200000 @@ -563,6 +565,9 @@ struct hid_device { /* device report descriptor */ wait_queue_head_t debug_wait; }; +#define to_hid_device(pdev) \ + container_of(pdev, struct hid_device, dev) + static inline void *hid_get_drvdata(struct hid_device *hdev) { return dev_get_drvdata(&hdev->dev); @@ -712,6 +717,9 @@ struct hid_driver { struct device_driver driver; }; +#define to_hid_driver(pdrv) \ + container_of(pdrv, struct hid_driver, driver) + /** * hid_ll_driver - low level driver callbacks * @start: called on probe to start the device diff --git a/include/linux/hsi/hsi.h b/include/linux/hsi/hsi.h index 5dd60c2e120f..2790591c77cf 100644 --- a/include/linux/hsi/hsi.h +++ b/include/linux/hsi/hsi.h @@ -135,9 +135,6 @@ static inline int hsi_register_board_info(struct hsi_board_info const *info, * @device: Driver model representation of the device * @tx_cfg: HSI TX configuration * @rx_cfg: HSI RX configuration - * @e_handler: Callback for handling port events (RX Wake High/Low) - * @pclaimed: Keeps tracks if the clients claimed its associated HSI port - * @nb: Notifier block for port events */ struct hsi_client { struct device device; diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index b0eb06423d5e..e76574d8f9b5 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -263,20 +263,18 @@ struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct, struct user_struct **user, int creat_flags, int page_size_log); -static inline int is_file_hugepages(struct file *file) +static inline bool is_file_hugepages(struct file *file) { if (file->f_op == &hugetlbfs_file_operations) - return 1; - if (is_file_shm_hugepages(file)) - return 1; + return true; - return 0; + return is_file_shm_hugepages(file); } #else /* !CONFIG_HUGETLBFS */ -#define is_file_hugepages(file) 0 +#define is_file_hugepages(file) false static inline struct file * hugetlb_file_setup(const char *name, size_t size, vm_flags_t acctflag, struct user_struct **user, int creat_flags, diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 768063baafbf..200cf13b00f6 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -414,6 +414,22 @@ struct i2c_algorithm { }; /** + * struct i2c_timings - I2C timing information + * @bus_freq_hz: the bus frequency in Hz + * @scl_rise_ns: time SCL signal takes to rise in ns; t(r) in the I2C specification + * @scl_fall_ns: time SCL signal takes to fall in ns; t(f) in the I2C specification + * @scl_int_delay_ns: time IP core additionally needs to setup SCL in ns + * @sda_fall_ns: time SDA signal takes to fall in ns; t(f) in the I2C specification + */ +struct i2c_timings { + u32 bus_freq_hz; + u32 scl_rise_ns; + u32 scl_fall_ns; + u32 scl_int_delay_ns; + u32 sda_fall_ns; +}; + +/** * struct i2c_bus_recovery_info - I2C bus recovery information * @recover_bus: Recover routine. Either pass driver's recover_bus() routine, or * i2c_generic_scl_recovery() or i2c_generic_gpio_recovery(). @@ -493,6 +509,8 @@ struct i2c_adapter_quirks { /* convenience macro for typical write-then read case */ #define I2C_AQ_COMB_WRITE_THEN_READ (I2C_AQ_COMB | I2C_AQ_COMB_WRITE_FIRST | \ I2C_AQ_COMB_READ_SECOND | I2C_AQ_COMB_SAME_ADDR) +/* clock stretching is not supported */ +#define I2C_AQ_NO_CLK_STRETCH BIT(4) /* * i2c_adapter is the structure used to identify a physical i2c bus along @@ -602,6 +620,7 @@ extern void i2c_clients_command(struct i2c_adapter *adap, extern struct i2c_adapter *i2c_get_adapter(int nr); extern void i2c_put_adapter(struct i2c_adapter *adap); +void i2c_parse_fw_timings(struct device *dev, struct i2c_timings *t, bool use_defaults); /* Return the functionality mask */ static inline u32 i2c_get_functionality(struct i2c_adapter *adap) @@ -615,6 +634,20 @@ static inline int i2c_check_functionality(struct i2c_adapter *adap, u32 func) return (func & i2c_get_functionality(adap)) == func; } +/** + * i2c_check_quirks() - Function for checking the quirk flags in an i2c adapter + * @adap: i2c adapter + * @quirks: quirk flags + * + * Return: true if the adapter has all the specified quirk flags, false if not + */ +static inline bool i2c_check_quirks(struct i2c_adapter *adap, u64 quirks) +{ + if (!adap->quirks) + return false; + return (adap->quirks->flags & quirks) == quirks; +} + /* Return the adapter number for a specific adapter */ static inline int i2c_adapter_id(struct i2c_adapter *adap) { @@ -622,7 +655,7 @@ static inline int i2c_adapter_id(struct i2c_adapter *adap) } /** - * module_i2c_driver() - Helper macro for registering a I2C driver + * module_i2c_driver() - Helper macro for registering a modular I2C driver * @__i2c_driver: i2c_driver struct * * Helper macro for I2C drivers which do not do anything special in module @@ -633,6 +666,17 @@ static inline int i2c_adapter_id(struct i2c_adapter *adap) module_driver(__i2c_driver, i2c_add_driver, \ i2c_del_driver) +/** + * builtin_i2c_driver() - Helper macro for registering a builtin I2C driver + * @__i2c_driver: i2c_driver struct + * + * Helper macro for I2C drivers which do not do anything special in their + * init. This eliminates a lot of boilerplate. Each driver may only + * use this macro once, and calling it replaces device_initcall(). + */ +#define builtin_i2c_driver(__i2c_driver) \ + builtin_driver(__i2c_driver, i2c_add_driver) + #endif /* I2C */ #if IS_ENABLED(CONFIG_OF) @@ -644,6 +688,7 @@ extern struct i2c_adapter *of_find_i2c_adapter_by_node(struct device_node *node) /* must call i2c_put_adapter() when done with returned i2c_adapter device */ struct i2c_adapter *of_get_i2c_adapter_by_node(struct device_node *node); + #else static inline struct i2c_client *of_find_i2c_device_by_node(struct device_node *node) diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index 31db7a05dd36..a8828652f794 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -37,8 +37,9 @@ enum klp_state { * struct klp_func - function structure for live patching * @old_name: name of the function to be patched * @new_func: pointer to the patched function code - * @old_addr: a hint conveying at what address the old function - * can be found (optional, vmlinux patches only) + * @old_sympos: a hint indicating which symbol position the old function + * can be found (optional) + * @old_addr: the address of the function being patched * @kobj: kobject for sysfs resources * @state: tracks function-level patch application state * @stack_node: list node for klp_ops func_stack list @@ -48,16 +49,16 @@ struct klp_func { const char *old_name; void *new_func; /* - * The old_addr field is optional and can be used to resolve - * duplicate symbol names in the vmlinux object. If this - * information is not present, the symbol is located by name - * with kallsyms. If the name is not unique and old_addr is - * not provided, the patch application fails as there is no - * way to resolve the ambiguity. + * The old_sympos field is optional and can be used to resolve + * duplicate symbol names in livepatch objects. If this field is zero, + * it is expected the symbol is unique, otherwise patching fails. If + * this value is greater than zero then that occurrence of the symbol + * in kallsyms for the given object is used. */ - unsigned long old_addr; + unsigned long old_sympos; /* internal */ + unsigned long old_addr; struct kobject kobj; enum klp_state state; struct list_head stack_node; @@ -66,8 +67,7 @@ struct klp_func { /** * struct klp_reloc - relocation structure for live patching * @loc: address where the relocation will be written - * @val: address of the referenced symbol (optional, - * vmlinux patches only) + * @sympos: position in kallsyms to disambiguate symbols (optional) * @type: ELF relocation type * @name: name of the referenced symbol (for lookup/verification) * @addend: offset from the referenced symbol @@ -75,7 +75,7 @@ struct klp_func { */ struct klp_reloc { unsigned long loc; - unsigned long val; + unsigned long sympos; unsigned long type; const char *name; int addend; diff --git a/include/linux/lockd/bind.h b/include/linux/lockd/bind.h index 4d24d64578c4..140edab64446 100644 --- a/include/linux/lockd/bind.h +++ b/include/linux/lockd/bind.h @@ -29,7 +29,7 @@ struct nlmsvc_binding { void (*fclose)(struct file *); }; -extern struct nlmsvc_binding * nlmsvc_ops; +extern const struct nlmsvc_binding *nlmsvc_ops; /* * Similar to nfs_client_initdata, but without the NFS-specific diff --git a/include/linux/memblock.h b/include/linux/memblock.h index fec66f86eeff..173fb44e22f1 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -216,10 +216,10 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, * for_each_free_mem_range - iterate through free memblock areas * @i: u64 used as loop variable * @nid: node selector, %NUMA_NO_NODE for all nodes + * @flags: pick from blocks based on memory attributes * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL * @p_nid: ptr to int for nid of the range, can be %NULL - * @flags: pick from blocks based on memory attributes * * Walks over free (memory && !reserved) areas of memblock. Available as * soon as memblock is initialized. @@ -232,10 +232,10 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, * for_each_free_mem_range_reverse - rev-iterate through free memblock areas * @i: u64 used as loop variable * @nid: node selector, %NUMA_NO_NODE for all nodes + * @flags: pick from blocks based on memory attributes * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL * @p_nid: ptr to int for nid of the range, can be %NULL - * @flags: pick from blocks based on memory attributes * * Walks over free (memory && !reserved) areas of memblock in reverse * order. Available as soon as memblock is initialized. @@ -325,10 +325,10 @@ phys_addr_t memblock_mem_size(unsigned long limit_pfn); phys_addr_t memblock_start_of_DRAM(void); phys_addr_t memblock_end_of_DRAM(void); void memblock_enforce_memory_limit(phys_addr_t memory_limit); -int memblock_is_memory(phys_addr_t addr); +bool memblock_is_memory(phys_addr_t addr); int memblock_is_map_memory(phys_addr_t addr); int memblock_is_region_memory(phys_addr_t base, phys_addr_t size); -int memblock_is_reserved(phys_addr_t addr); +bool memblock_is_reserved(phys_addr_t addr); bool memblock_is_region_reserved(phys_addr_t base, phys_addr_t size); extern void __memblock_dump_all(void); @@ -399,6 +399,11 @@ static inline unsigned long memblock_region_reserved_end_pfn(const struct memblo region < (memblock.memblock_type.regions + memblock.memblock_type.cnt); \ region++) +#define for_each_memblock_type(memblock_type, rgn) \ + idx = 0; \ + rgn = &memblock_type->regions[idx]; \ + for (idx = 0; idx < memblock_type->cnt; \ + idx++,rgn = &memblock_type->regions[idx]) #ifdef CONFIG_ARCH_DISCARD_MEMBLOCK #define __init_memblock __meminit diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index cd0e2413c358..2292468f2a30 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -85,32 +85,10 @@ enum mem_cgroup_events_target { MEM_CGROUP_NTARGETS, }; -/* - * Bits in struct cg_proto.flags - */ -enum cg_proto_flags { - /* Currently active and new sockets should be assigned to cgroups */ - MEMCG_SOCK_ACTIVE, - /* It was ever activated; we must disarm static keys on destruction */ - MEMCG_SOCK_ACTIVATED, -}; - struct cg_proto { struct page_counter memory_allocated; /* Current allocated memory. */ - struct percpu_counter sockets_allocated; /* Current number of sockets. */ int memory_pressure; - long sysctl_mem[3]; - unsigned long flags; - /* - * memcg field is used to find which memcg we belong directly - * Each memcg struct can hold more than one cg_proto, so container_of - * won't really cut. - * - * The elegant solution would be having an inverse function to - * proto_cgroup in struct proto, but that means polluting the structure - * for everybody, instead of just for memcg users. - */ - struct mem_cgroup *memcg; + bool active; }; #ifdef CONFIG_MEMCG @@ -192,6 +170,9 @@ struct mem_cgroup { unsigned long low; unsigned long high; + /* Range enforcement for interrupt charges */ + struct work_struct high_work; + unsigned long soft_limit; /* vmpressure notifications */ @@ -268,6 +249,10 @@ struct mem_cgroup { struct wb_domain cgwb_domain; #endif +#ifdef CONFIG_INET + unsigned long socket_pressure; +#endif + /* List of events which userspace want to receive */ struct list_head event_list; spinlock_t event_list_lock; @@ -275,7 +260,8 @@ struct mem_cgroup { struct mem_cgroup_per_node *nodeinfo[0]; /* WARNING: nodeinfo must be the last member here */ }; -extern struct cgroup_subsys_state *mem_cgroup_root_css; + +extern struct mem_cgroup *root_mem_cgroup; /** * mem_cgroup_events - count memory events against a cgroup @@ -308,18 +294,34 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *); bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg); struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); -struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg); static inline struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){ return css ? container_of(css, struct mem_cgroup, css) : NULL; } +#define mem_cgroup_from_counter(counter, member) \ + container_of(counter, struct mem_cgroup, member) + struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *, struct mem_cgroup *, struct mem_cgroup_reclaim_cookie *); void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); +/** + * parent_mem_cgroup - find the accounting parent of a memcg + * @memcg: memcg whose parent to find + * + * Returns the parent memcg, or NULL if this is the root or the memory + * controller is in legacy no-hierarchy mode. + */ +static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) +{ + if (!memcg->memory.parent) + return NULL; + return mem_cgroup_from_counter(memcg->memory.parent, memory); +} + static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg, struct mem_cgroup *root) { @@ -671,12 +673,6 @@ void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx) } #endif /* CONFIG_MEMCG */ -enum { - UNDER_LIMIT, - SOFT_LIMIT, - OVER_LIMIT, -}; - #ifdef CONFIG_CGROUP_WRITEBACK struct list_head *mem_cgroup_cgwb_list(struct mem_cgroup *memcg); @@ -703,20 +699,35 @@ static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb, #endif /* CONFIG_CGROUP_WRITEBACK */ struct sock; -#if defined(CONFIG_INET) && defined(CONFIG_MEMCG_KMEM) void sock_update_memcg(struct sock *sk); void sock_release_memcg(struct sock *sk); -#else -static inline void sock_update_memcg(struct sock *sk) +bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages); +void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages); +#if defined(CONFIG_MEMCG) && defined(CONFIG_INET) +extern struct static_key_false memcg_sockets_enabled_key; +#define mem_cgroup_sockets_enabled static_branch_unlikely(&memcg_sockets_enabled_key) +static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) { +#ifdef CONFIG_MEMCG_KMEM + if (memcg->tcp_mem.memory_pressure) + return true; +#endif + do { + if (time_before(jiffies, memcg->socket_pressure)) + return true; + } while ((memcg = parent_mem_cgroup(memcg))); + return false; } -static inline void sock_release_memcg(struct sock *sk) +#else +#define mem_cgroup_sockets_enabled 0 +static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) { + return false; } -#endif /* CONFIG_INET && CONFIG_MEMCG_KMEM */ +#endif #ifdef CONFIG_MEMCG_KMEM -extern struct static_key memcg_kmem_enabled_key; +extern struct static_key_false memcg_kmem_enabled_key; extern int memcg_nr_cache_ids; void memcg_get_cache_ids(void); @@ -732,7 +743,7 @@ void memcg_put_cache_ids(void); static inline bool memcg_kmem_enabled(void) { - return static_key_false(&memcg_kmem_enabled_key); + return static_branch_unlikely(&memcg_kmem_enabled_key); } static inline bool memcg_kmem_is_active(struct mem_cgroup *memcg) @@ -766,15 +777,13 @@ static inline int memcg_cache_id(struct mem_cgroup *memcg) return memcg ? memcg->kmemcg_id : -1; } -struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep); +struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp); void __memcg_kmem_put_cache(struct kmem_cache *cachep); -static inline bool __memcg_kmem_bypass(gfp_t gfp) +static inline bool __memcg_kmem_bypass(void) { if (!memcg_kmem_enabled()) return true; - if (gfp & __GFP_NOACCOUNT) - return true; if (in_interrupt() || (!current->mm) || (current->flags & PF_KTHREAD)) return true; return false; @@ -791,7 +800,9 @@ static inline bool __memcg_kmem_bypass(gfp_t gfp) static __always_inline int memcg_kmem_charge(struct page *page, gfp_t gfp, int order) { - if (__memcg_kmem_bypass(gfp)) + if (__memcg_kmem_bypass()) + return 0; + if (!(gfp & __GFP_ACCOUNT)) return 0; return __memcg_kmem_charge(page, gfp, order); } @@ -810,16 +821,15 @@ static __always_inline void memcg_kmem_uncharge(struct page *page, int order) /** * memcg_kmem_get_cache: selects the correct per-memcg cache for allocation * @cachep: the original global kmem cache - * @gfp: allocation flags. * * All memory allocated from a per-memcg cache is charged to the owner memcg. */ static __always_inline struct kmem_cache * memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp) { - if (__memcg_kmem_bypass(gfp)) + if (__memcg_kmem_bypass()) return cachep; - return __memcg_kmem_get_cache(cachep); + return __memcg_kmem_get_cache(cachep, gfp); } static __always_inline void memcg_kmem_put_cache(struct kmem_cache *cachep) diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 3d385c81c153..2696c1f05ed1 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -122,7 +122,7 @@ struct sp_node { struct shared_policy { struct rb_root root; - spinlock_t lock; + rwlock_t lock; }; int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst); diff --git a/include/linux/mfd/arizona/core.h b/include/linux/mfd/arizona/core.h index 79e607e2f081..d55a42297d49 100644 --- a/include/linux/mfd/arizona/core.h +++ b/include/linux/mfd/arizona/core.h @@ -27,6 +27,8 @@ enum arizona_type { WM8280 = 4, WM8998 = 5, WM1814 = 6, + WM1831 = 7, + CS47L24 = 8, }; #define ARIZONA_IRQ_GP1 0 @@ -166,6 +168,7 @@ static inline int wm5102_patch(struct arizona *arizona) #endif int wm5110_patch(struct arizona *arizona); +int cs47l24_patch(struct arizona *arizona); int wm8997_patch(struct arizona *arizona); int wm8998_patch(struct arizona *arizona); diff --git a/include/linux/mfd/arizona/pdata.h b/include/linux/mfd/arizona/pdata.h index 57b45caaea80..64faeeff698c 100644 --- a/include/linux/mfd/arizona/pdata.h +++ b/include/linux/mfd/arizona/pdata.h @@ -171,7 +171,7 @@ struct arizona_pdata { int inmode[ARIZONA_MAX_INPUT]; /** Mode for outputs */ - bool out_mono[ARIZONA_MAX_OUTPUT]; + int out_mono[ARIZONA_MAX_OUTPUT]; /** PDM speaker mute setting */ unsigned int spk_mute[ARIZONA_MAX_PDM_SPK]; diff --git a/include/linux/mfd/samsung/core.h b/include/linux/mfd/samsung/core.h index a06098639399..6bc4bcd488ac 100644 --- a/include/linux/mfd/samsung/core.h +++ b/include/linux/mfd/samsung/core.h @@ -44,6 +44,7 @@ enum sec_device_type { S2MPS11X, S2MPS13X, S2MPS14X, + S2MPS15X, S2MPU02, }; diff --git a/include/linux/mfd/samsung/rtc.h b/include/linux/mfd/samsung/rtc.h index 29c30ac36020..a65e4655d470 100644 --- a/include/linux/mfd/samsung/rtc.h +++ b/include/linux/mfd/samsung/rtc.h @@ -107,6 +107,8 @@ enum s2mps_rtc_reg { #define S2MPS_RTC_WUDR_MASK (1 << S2MPS_RTC_WUDR_SHIFT) #define S2MPS13_RTC_AUDR_SHIFT 1 #define S2MPS13_RTC_AUDR_MASK (1 << S2MPS13_RTC_AUDR_SHIFT) +#define S2MPS15_RTC_WUDR_SHIFT 1 +#define S2MPS15_RTC_WUDR_MASK (1 << S2MPS15_RTC_WUDR_SHIFT) #define S2MPS_RTC_RUDR_SHIFT 0 #define S2MPS_RTC_RUDR_MASK (1 << S2MPS_RTC_RUDR_SHIFT) #define RTC_TCON_SHIFT 1 diff --git a/include/linux/mfd/samsung/s2mps15.h b/include/linux/mfd/samsung/s2mps15.h new file mode 100644 index 000000000000..36d35287c3c0 --- /dev/null +++ b/include/linux/mfd/samsung/s2mps15.h @@ -0,0 +1,158 @@ +/* + * Copyright (c) 2015 Samsung Electronics Co., Ltd + * http://www.samsung.com + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __LINUX_MFD_S2MPS15_H +#define __LINUX_MFD_S2MPS15_H + +/* S2MPS15 registers */ +enum s2mps15_reg { + S2MPS15_REG_ID, + S2MPS15_REG_INT1, + S2MPS15_REG_INT2, + S2MPS15_REG_INT3, + S2MPS15_REG_INT1M, + S2MPS15_REG_INT2M, + S2MPS15_REG_INT3M, + S2MPS15_REG_ST1, + S2MPS15_REG_ST2, + S2MPS15_REG_PWRONSRC, + S2MPS15_REG_OFFSRC, + S2MPS15_REG_BU_CHG, + S2MPS15_REG_RTC_BUF, + S2MPS15_REG_CTRL1, + S2MPS15_REG_CTRL2, + S2MPS15_REG_RSVD1, + S2MPS15_REG_RSVD2, + S2MPS15_REG_RSVD3, + S2MPS15_REG_RSVD4, + S2MPS15_REG_RSVD5, + S2MPS15_REG_RSVD6, + S2MPS15_REG_CTRL3, + S2MPS15_REG_RSVD7, + S2MPS15_REG_RSVD8, + S2MPS15_REG_RSVD9, + S2MPS15_REG_B1CTRL1, + S2MPS15_REG_B1CTRL2, + S2MPS15_REG_B2CTRL1, + S2MPS15_REG_B2CTRL2, + S2MPS15_REG_B3CTRL1, + S2MPS15_REG_B3CTRL2, + S2MPS15_REG_B4CTRL1, + S2MPS15_REG_B4CTRL2, + S2MPS15_REG_B5CTRL1, + S2MPS15_REG_B5CTRL2, + S2MPS15_REG_B6CTRL1, + S2MPS15_REG_B6CTRL2, + S2MPS15_REG_B7CTRL1, + S2MPS15_REG_B7CTRL2, + S2MPS15_REG_B8CTRL1, + S2MPS15_REG_B8CTRL2, + S2MPS15_REG_B9CTRL1, + S2MPS15_REG_B9CTRL2, + S2MPS15_REG_B10CTRL1, + S2MPS15_REG_B10CTRL2, + S2MPS15_REG_BBCTRL1, + S2MPS15_REG_BBCTRL2, + S2MPS15_REG_BRAMP, + S2MPS15_REG_LDODVS1, + S2MPS15_REG_LDODVS2, + S2MPS15_REG_LDODVS3, + S2MPS15_REG_LDODVS4, + S2MPS15_REG_L1CTRL, + S2MPS15_REG_L2CTRL, + S2MPS15_REG_L3CTRL, + S2MPS15_REG_L4CTRL, + S2MPS15_REG_L5CTRL, + S2MPS15_REG_L6CTRL, + S2MPS15_REG_L7CTRL, + S2MPS15_REG_L8CTRL, + S2MPS15_REG_L9CTRL, + S2MPS15_REG_L10CTRL, + S2MPS15_REG_L11CTRL, + S2MPS15_REG_L12CTRL, + S2MPS15_REG_L13CTRL, + S2MPS15_REG_L14CTRL, + S2MPS15_REG_L15CTRL, + S2MPS15_REG_L16CTRL, + S2MPS15_REG_L17CTRL, + S2MPS15_REG_L18CTRL, + S2MPS15_REG_L19CTRL, + S2MPS15_REG_L20CTRL, + S2MPS15_REG_L21CTRL, + S2MPS15_REG_L22CTRL, + S2MPS15_REG_L23CTRL, + S2MPS15_REG_L24CTRL, + S2MPS15_REG_L25CTRL, + S2MPS15_REG_L26CTRL, + S2MPS15_REG_L27CTRL, + S2MPS15_REG_LDODSCH1, + S2MPS15_REG_LDODSCH2, + S2MPS15_REG_LDODSCH3, + S2MPS15_REG_LDODSCH4, +}; + +/* S2MPS15 regulator ids */ +enum s2mps15_regulators { + S2MPS15_LDO1, + S2MPS15_LDO2, + S2MPS15_LDO3, + S2MPS15_LDO4, + S2MPS15_LDO5, + S2MPS15_LDO6, + S2MPS15_LDO7, + S2MPS15_LDO8, + S2MPS15_LDO9, + S2MPS15_LDO10, + S2MPS15_LDO11, + S2MPS15_LDO12, + S2MPS15_LDO13, + S2MPS15_LDO14, + S2MPS15_LDO15, + S2MPS15_LDO16, + S2MPS15_LDO17, + S2MPS15_LDO18, + S2MPS15_LDO19, + S2MPS15_LDO20, + S2MPS15_LDO21, + S2MPS15_LDO22, + S2MPS15_LDO23, + S2MPS15_LDO24, + S2MPS15_LDO25, + S2MPS15_LDO26, + S2MPS15_LDO27, + S2MPS15_BUCK1, + S2MPS15_BUCK2, + S2MPS15_BUCK3, + S2MPS15_BUCK4, + S2MPS15_BUCK5, + S2MPS15_BUCK6, + S2MPS15_BUCK7, + S2MPS15_BUCK8, + S2MPS15_BUCK9, + S2MPS15_BUCK10, + S2MPS15_BUCK11, + S2MPS15_REGULATOR_MAX, +}; + +#define S2MPS15_LDO_VSEL_MASK (0x3F) +#define S2MPS15_BUCK_VSEL_MASK (0xFF) + +#define S2MPS15_ENABLE_SHIFT (0x06) +#define S2MPS15_ENABLE_MASK (0x03 << S2MPS15_ENABLE_SHIFT) + +#define S2MPS15_LDO_N_VOLTAGES (S2MPS15_LDO_VSEL_MASK + 1) +#define S2MPS15_BUCK_N_VOLTAGES (S2MPS15_BUCK_VSEL_MASK + 1) + +#endif /* __LINUX_MFD_S2MPS15_H */ diff --git a/include/linux/mfd/tps65218.h b/include/linux/mfd/tps65218.h index 2f9b593246ee..d58f3b5f585a 100644 --- a/include/linux/mfd/tps65218.h +++ b/include/linux/mfd/tps65218.h @@ -200,6 +200,8 @@ enum tps65218_regulator_id { TPS65218_DCDC_4, TPS65218_DCDC_5, TPS65218_DCDC_6, + /* LS's */ + TPS65218_LS_3, /* LDOs */ TPS65218_LDO_1, }; @@ -210,8 +212,11 @@ enum tps65218_regulator_id { #define TPS65218_NUM_DCDC 6 /* Number of LDO voltage regulators available */ #define TPS65218_NUM_LDO 1 +/* Number of total LS current regulators available */ +#define TPS65218_NUM_LS 1 /* Number of total regulators available */ -#define TPS65218_NUM_REGULATOR (TPS65218_NUM_DCDC + TPS65218_NUM_LDO) +#define TPS65218_NUM_REGULATOR (TPS65218_NUM_DCDC + TPS65218_NUM_LDO \ + + TPS65218_NUM_LS) /* Define the TPS65218 IRQ numbers */ enum tps65218_irqs { diff --git a/include/linux/mm.h b/include/linux/mm.h index 00bad7793788..839d9e9a1c38 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -51,6 +51,17 @@ extern int sysctl_legacy_va_layout; #define sysctl_legacy_va_layout 0 #endif +#ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS +extern const int mmap_rnd_bits_min; +extern const int mmap_rnd_bits_max; +extern int mmap_rnd_bits __read_mostly; +#endif +#ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS +extern const int mmap_rnd_compat_bits_min; +extern const int mmap_rnd_compat_bits_max; +extern int mmap_rnd_compat_bits __read_mostly; +#endif + #include <asm/page.h> #include <asm/pgtable.h> #include <asm/processor.h> @@ -225,10 +236,14 @@ extern pgprot_t protection_map[16]; * ->fault function. The vma's ->fault is responsible for returning a bitmask * of VM_FAULT_xxx flags that give details about how the fault was handled. * + * MM layer fills up gfp_mask for page allocations but fault handler might + * alter it if its implementation requires a different allocation context. + * * pgoff should be used in favour of virtual_address, if possible. */ struct vm_fault { unsigned int flags; /* FAULT_FLAG_xxx flags */ + gfp_t gfp_mask; /* gfp mask to be used for allocations */ pgoff_t pgoff; /* Logical page offset based on vma */ void __user *virtual_address; /* Faulting virtual address */ @@ -1361,10 +1376,26 @@ static inline void dec_mm_counter(struct mm_struct *mm, int member) atomic_long_dec(&mm->rss_stat.count[member]); } +/* Optimized variant when page is already known not to be PageAnon */ +static inline int mm_counter_file(struct page *page) +{ + if (PageSwapBacked(page)) + return MM_SHMEMPAGES; + return MM_FILEPAGES; +} + +static inline int mm_counter(struct page *page) +{ + if (PageAnon(page)) + return MM_ANONPAGES; + return mm_counter_file(page); +} + static inline unsigned long get_mm_rss(struct mm_struct *mm) { return get_mm_counter(mm, MM_FILEPAGES) + - get_mm_counter(mm, MM_ANONPAGES); + get_mm_counter(mm, MM_ANONPAGES) + + get_mm_counter(mm, MM_SHMEMPAGES); } static inline unsigned long get_mm_hiwater_rss(struct mm_struct *mm) @@ -1898,7 +1929,9 @@ extern void mm_drop_all_locks(struct mm_struct *mm); extern void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file); extern struct file *get_mm_exe_file(struct mm_struct *mm); -extern int may_expand_vm(struct mm_struct *mm, unsigned long npages); +extern bool may_expand_vm(struct mm_struct *, vm_flags_t, unsigned long npages); +extern void vm_stat_account(struct mm_struct *, vm_flags_t, long npages); + extern struct vm_area_struct *_install_special_mapping(struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long flags, @@ -2116,15 +2149,6 @@ typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr, extern int apply_to_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); -#ifdef CONFIG_PROC_FS -void vm_stat_account(struct mm_struct *, unsigned long, struct file *, long); -#else -static inline void vm_stat_account(struct mm_struct *mm, - unsigned long flags, struct file *file, long pages) -{ - mm->total_vm += pages; -} -#endif /* CONFIG_PROC_FS */ #ifdef CONFIG_DEBUG_PAGEALLOC extern bool _debug_pagealloc_enabled; diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index cf55945c83fb..712e8c37a200 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -100,4 +100,6 @@ static __always_inline enum lru_list page_lru(struct page *page) return lru; } +#define lru_to_page(head) (list_entry((head)->prev, struct page, lru)) + #endif diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index f8d1492a114f..6bc9a0ce2253 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -369,9 +369,10 @@ struct core_state { }; enum { - MM_FILEPAGES, - MM_ANONPAGES, - MM_SWAPENTS, + MM_FILEPAGES, /* Resident file mapping pages */ + MM_ANONPAGES, /* Resident anonymous pages */ + MM_SWAPENTS, /* Anonymous swap entries */ + MM_SHMEMPAGES, /* Resident shared memory pages */ NR_MM_COUNTERS }; @@ -426,7 +427,7 @@ struct mm_struct { unsigned long total_vm; /* Total pages mapped */ unsigned long locked_vm; /* Pages that have PG_mlocked set */ unsigned long pinned_vm; /* Refcount permanently increased */ - unsigned long shared_vm; /* Shared pages (files) */ + unsigned long data_vm; /* VM_WRITE & ~VM_SHARED/GROWSDOWN */ unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE */ unsigned long stack_vm; /* VM_GROWSUP/DOWN */ unsigned long def_flags; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index e23a9e704536..33bb1b19273e 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -195,11 +195,6 @@ static inline int is_active_lru(enum lru_list lru) return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE); } -static inline int is_unevictable_lru(enum lru_list lru) -{ - return (lru == LRU_UNEVICTABLE); -} - struct zone_reclaim_stat { /* * The pageout code in vmscan.c keeps track of how many of the @@ -361,10 +356,10 @@ struct zone { struct per_cpu_pageset __percpu *pageset; /* - * This is a per-zone reserve of pages that should not be - * considered dirtyable memory. + * This is a per-zone reserve of pages that are not available + * to userspace allocations. */ - unsigned long dirty_balance_reserve; + unsigned long totalreserve_pages; #ifndef CONFIG_SPARSEMEM /* @@ -576,19 +571,17 @@ static inline bool zone_is_empty(struct zone *zone) /* Maximum number of zones on a zonelist */ #define MAX_ZONES_PER_ZONELIST (MAX_NUMNODES * MAX_NR_ZONES) +enum { + ZONELIST_FALLBACK, /* zonelist with fallback */ #ifdef CONFIG_NUMA - -/* - * The NUMA zonelists are doubled because we need zonelists that restrict the - * allocations to a single node for __GFP_THISNODE. - * - * [0] : Zonelist with fallback - * [1] : No fallback (__GFP_THISNODE) - */ -#define MAX_ZONELISTS 2 -#else -#define MAX_ZONELISTS 1 + /* + * The NUMA zonelists are doubled because we need zonelists that + * restrict the allocations to a single node for __GFP_THISNODE. + */ + ZONELIST_NOFALLBACK, /* zonelist without fallback (__GFP_THISNODE) */ #endif + MAX_ZONELISTS +}; /* * This struct contains information about a zone in a zonelist. It is stored @@ -1207,13 +1200,13 @@ unsigned long __init node_memmap_size_bytes(int, unsigned long, unsigned long); * the zone and PFN linkages are still valid. This is expensive, but walkers * of the full memmap are extremely rare. */ -int memmap_valid_within(unsigned long pfn, +bool memmap_valid_within(unsigned long pfn, struct page *page, struct zone *zone); #else -static inline int memmap_valid_within(unsigned long pfn, +static inline bool memmap_valid_within(unsigned long pfn, struct page *page, struct zone *zone) { - return 1; + return true; } #endif /* CONFIG_ARCH_HAS_HOLES_MEMORYMODEL */ diff --git a/include/linux/module.h b/include/linux/module.h index 3a19c79918e0..4560d8f1545d 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -302,6 +302,28 @@ struct mod_tree_node { struct latch_tree_node node; }; +struct module_layout { + /* The actual code + data. */ + void *base; + /* Total size. */ + unsigned int size; + /* The size of the executable code. */ + unsigned int text_size; + /* Size of RO section of the module (text+rodata) */ + unsigned int ro_size; + +#ifdef CONFIG_MODULES_TREE_LOOKUP + struct mod_tree_node mtn; +#endif +}; + +#ifdef CONFIG_MODULES_TREE_LOOKUP +/* Only touch one cacheline for common rbtree-for-core-layout case. */ +#define __module_layout_align ____cacheline_aligned +#else +#define __module_layout_align +#endif + struct module { enum module_state state; @@ -366,37 +388,9 @@ struct module { /* Startup function. */ int (*init)(void); - /* - * If this is non-NULL, vfree() after init() returns. - * - * Cacheline align here, such that: - * module_init, module_core, init_size, core_size, - * init_text_size, core_text_size and mtn_core::{mod,node[0]} - * are on the same cacheline. - */ - void *module_init ____cacheline_aligned; - - /* Here is the actual code + data, vfree'd on unload. */ - void *module_core; - - /* Here are the sizes of the init and core sections */ - unsigned int init_size, core_size; - - /* The size of the executable code in each section. */ - unsigned int init_text_size, core_text_size; - -#ifdef CONFIG_MODULES_TREE_LOOKUP - /* - * We want mtn_core::{mod,node[0]} to be in the same cacheline as the - * above entries such that a regular lookup will only touch one - * cacheline. - */ - struct mod_tree_node mtn_core; - struct mod_tree_node mtn_init; -#endif - - /* Size of RO sections of the module (text+rodata) */ - unsigned int init_ro_size, core_ro_size; + /* Core layout: rbtree is accessed frequently, so keep together. */ + struct module_layout core_layout __module_layout_align; + struct module_layout init_layout; /* Arch-specific module values */ struct mod_arch_specific arch; @@ -505,15 +499,15 @@ bool is_module_text_address(unsigned long addr); static inline bool within_module_core(unsigned long addr, const struct module *mod) { - return (unsigned long)mod->module_core <= addr && - addr < (unsigned long)mod->module_core + mod->core_size; + return (unsigned long)mod->core_layout.base <= addr && + addr < (unsigned long)mod->core_layout.base + mod->core_layout.size; } static inline bool within_module_init(unsigned long addr, const struct module *mod) { - return (unsigned long)mod->module_init <= addr && - addr < (unsigned long)mod->module_init + mod->init_size; + return (unsigned long)mod->init_layout.base <= addr && + addr < (unsigned long)mod->init_layout.base + mod->init_layout.size; } static inline bool within_module(unsigned long addr, const struct module *mod) @@ -768,9 +762,13 @@ extern int module_sysfs_initialized; #ifdef CONFIG_DEBUG_SET_MODULE_RONX extern void set_all_modules_text_rw(void); extern void set_all_modules_text_ro(void); +extern void module_enable_ro(const struct module *mod); +extern void module_disable_ro(const struct module *mod); #else static inline void set_all_modules_text_rw(void) { } static inline void set_all_modules_text_ro(void) { } +static inline void module_enable_ro(const struct module *mod) { } +static inline void module_disable_ro(const struct module *mod) { } #endif #ifdef CONFIG_GENERIC_BUG diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 43aeabd4b968..d6f9b4e6006d 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -592,4 +592,18 @@ enum data_content4 { NFS4_CONTENT_HOLE = 1, }; +enum pnfs_update_layout_reason { + PNFS_UPDATE_LAYOUT_UNKNOWN = 0, + PNFS_UPDATE_LAYOUT_NO_PNFS, + PNFS_UPDATE_LAYOUT_RD_ZEROLEN, + PNFS_UPDATE_LAYOUT_MDSTHRESH, + PNFS_UPDATE_LAYOUT_NOMEM, + PNFS_UPDATE_LAYOUT_BULK_RECALL, + PNFS_UPDATE_LAYOUT_IO_TEST_FAIL, + PNFS_UPDATE_LAYOUT_FOUND_CACHED, + PNFS_UPDATE_LAYOUT_RETURN, + PNFS_UPDATE_LAYOUT_BLOCKED, + PNFS_UPDATE_LAYOUT_SEND_LAYOUTGET, +}; + #endif diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 37a3d2981352..48e0320cd643 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -60,18 +60,12 @@ struct nfs_lockowner { pid_t l_pid; }; -#define NFS_IO_INPROGRESS 0 -struct nfs_io_counter { - unsigned long flags; - atomic_t io_count; -}; - struct nfs_lock_context { atomic_t count; struct list_head list; struct nfs_open_context *open_context; struct nfs_lockowner lockowner; - struct nfs_io_counter io_count; + atomic_t io_count; }; struct nfs4_state; @@ -216,7 +210,6 @@ struct nfs_inode { #define NFS_INO_FLUSHING (4) /* inode is flushing out data */ #define NFS_INO_FSCACHE (5) /* inode can be cached by FS-Cache */ #define NFS_INO_FSCACHE_LOCK (6) /* FS-Cache cookie management lock */ -#define NFS_INO_COMMIT (7) /* inode is committing unstable writes */ #define NFS_INO_LAYOUTCOMMIT (9) /* layoutcommit required */ #define NFS_INO_LAYOUTCOMMITTING (10) /* layoutcommit inflight */ #define NFS_INO_LAYOUTSTATS (11) /* layoutstats inflight */ @@ -518,13 +511,25 @@ extern int nfs_updatepage(struct file *, struct page *, unsigned int, unsigned */ extern int nfs_sync_inode(struct inode *inode); extern int nfs_wb_all(struct inode *inode); -extern int nfs_wb_page(struct inode *inode, struct page* page); +extern int nfs_wb_single_page(struct inode *inode, struct page *page, bool launder); extern int nfs_wb_page_cancel(struct inode *inode, struct page* page); extern int nfs_commit_inode(struct inode *, int); extern struct nfs_commit_data *nfs_commitdata_alloc(void); extern void nfs_commit_free(struct nfs_commit_data *data); static inline int +nfs_wb_launder_page(struct inode *inode, struct page *page) +{ + return nfs_wb_single_page(inode, page, true); +} + +static inline int +nfs_wb_page(struct inode *inode, struct page *page) +{ + return nfs_wb_single_page(inode, page, false); +} + +static inline int nfs_have_writebacks(struct inode *inode) { return NFS_I(inode)->nrequests != 0; diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 2469ab0bb3a1..7fcc13c8cf1f 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -102,6 +102,7 @@ struct nfs_client { #define NFS_SP4_MACH_CRED_STATEID 4 /* TEST_STATEID and FREE_STATEID */ #define NFS_SP4_MACH_CRED_WRITE 5 /* WRITE */ #define NFS_SP4_MACH_CRED_COMMIT 6 /* COMMIT */ +#define NFS_SP4_MACH_CRED_PNFS_CLEANUP 7 /* LAYOUTRETURN */ #endif /* CONFIG_NFS_V4 */ /* Our own IP address, as a null-terminated string. diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 11bbae44f4cb..791098a08a87 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1375,6 +1375,7 @@ enum { NFS_IOHDR_ERROR = 0, NFS_IOHDR_EOF, NFS_IOHDR_REDO, + NFS_IOHDR_STAT, }; struct nfs_pgio_header { @@ -1420,11 +1421,12 @@ struct nfs_mds_commit_info { struct list_head list; }; +struct nfs_commit_info; struct nfs_commit_data; struct nfs_inode; struct nfs_commit_completion_ops { - void (*error_cleanup) (struct nfs_inode *nfsi); void (*completion) (struct nfs_commit_data *data); + void (*resched_write) (struct nfs_commit_info *, struct nfs_page *); }; struct nfs_commit_info { @@ -1454,12 +1456,14 @@ struct nfs_commit_data { const struct rpc_call_ops *mds_ops; const struct nfs_commit_completion_ops *completion_ops; int (*commit_done_cb) (struct rpc_task *task, struct nfs_commit_data *data); + unsigned long flags; }; struct nfs_pgio_completion_ops { void (*error_cleanup)(struct list_head *head); void (*init_hdr)(struct nfs_pgio_header *hdr); void (*completion)(struct nfs_pgio_header *hdr); + void (*reschedule_io)(struct nfs_pgio_header *hdr); }; struct nfs_unlinkdata { diff --git a/include/linux/of_address.h b/include/linux/of_address.h index 507daad0bc8d..01c0a556448b 100644 --- a/include/linux/of_address.h +++ b/include/linux/of_address.h @@ -3,6 +3,7 @@ #include <linux/ioport.h> #include <linux/errno.h> #include <linux/of.h> +#include <linux/io.h> struct of_pci_range_parser { struct device_node *node; @@ -36,6 +37,8 @@ extern struct device_node *of_find_matching_node_by_address( const struct of_device_id *matches, u64 base_address); extern void __iomem *of_iomap(struct device_node *device, int index); +void __iomem *of_io_request_and_map(struct device_node *device, + int index, const char *name); /* Extract an address from a device, returns the region size and * the address space flags too. The PCI version uses a BAR number @@ -57,6 +60,11 @@ extern int of_dma_get_range(struct device_node *np, u64 *dma_addr, u64 *paddr, u64 *size); extern bool of_dma_is_coherent(struct device_node *np); #else /* CONFIG_OF_ADDRESS */ +static inline void __iomem *of_io_request_and_map(struct device_node *device, + int index, const char *name) +{ + return IOMEM_ERR_PTR(-EINVAL); +} static inline u64 of_translate_address(struct device_node *np, const __be32 *addr) @@ -112,12 +120,7 @@ static inline bool of_dma_is_coherent(struct device_node *np) extern int of_address_to_resource(struct device_node *dev, int index, struct resource *r); void __iomem *of_iomap(struct device_node *node, int index); -void __iomem *of_io_request_and_map(struct device_node *device, - int index, const char *name); #else - -#include <linux/io.h> - static inline int of_address_to_resource(struct device_node *dev, int index, struct resource *r) { @@ -128,12 +131,6 @@ static inline void __iomem *of_iomap(struct device_node *device, int index) { return NULL; } - -static inline void __iomem *of_io_request_and_map(struct device_node *device, - int index, const char *name) -{ - return IOMEM_ERR_PTR(-EINVAL); -} #endif #if defined(CONFIG_OF_ADDRESS) && defined(CONFIG_PCI) diff --git a/include/linux/pfn.h b/include/linux/pfn.h index 7646637221f3..97f3e88aead4 100644 --- a/include/linux/pfn.h +++ b/include/linux/pfn.h @@ -9,5 +9,6 @@ #define PFN_UP(x) (((x) + PAGE_SIZE-1) >> PAGE_SHIFT) #define PFN_DOWN(x) ((x) >> PAGE_SHIFT) #define PFN_PHYS(x) ((phys_addr_t)(x) << PAGE_SHIFT) +#define PHYS_PFN(x) ((unsigned long)((x) >> PAGE_SHIFT)) #endif diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index 45f6a7b5b3cb..998d8f1c3c91 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -1,6 +1,16 @@ #ifndef __LINUX_BQ27X00_BATTERY_H__ #define __LINUX_BQ27X00_BATTERY_H__ +enum bq27xxx_chip { + BQ27000 = 1, /* bq27000, bq27200 */ + BQ27010, /* bq27010, bq27210 */ + BQ27500, /* bq27500, bq27510, bq27520 */ + BQ27530, /* bq27530, bq27531 */ + BQ27541, /* bq27541, bq27542, bq27546, bq27742 */ + BQ27545, /* bq27545 */ + BQ27421, /* bq27421, bq27425, bq27441, bq27621 */ +}; + /** * struct bq27xxx_plaform_data - Platform data for bq27xxx devices * @name: Name of the battery. @@ -12,20 +22,47 @@ * register to be read. The return value should either be the content of * the passed register or an error value. */ -enum bq27xxx_chip { - BQ27000 = 1, /* bq27000, bq27200 */ - BQ27010, /* bq27010, bq27210 */ - BQ27500, /* bq27500, bq27510, bq27520 */ - BQ27530, /* bq27530, bq27531 */ - BQ27541, /* bq27541, bq27542, bq27546, bq27742 */ - BQ27545, /* bq27545 */ - BQ27421, /* bq27421, bq27425, bq27441, bq27621 */ -}; - struct bq27xxx_platform_data { const char *name; enum bq27xxx_chip chip; int (*read)(struct device *dev, unsigned int); }; +struct bq27xxx_device_info; +struct bq27xxx_access_methods { + int (*read)(struct bq27xxx_device_info *di, u8 reg, bool single); +}; + +struct bq27xxx_reg_cache { + int temperature; + int time_to_empty; + int time_to_empty_avg; + int time_to_full; + int charge_full; + int cycle_count; + int capacity; + int energy; + int flags; + int power_avg; + int health; +}; + +struct bq27xxx_device_info { + struct device *dev; + enum bq27xxx_chip chip; + const char *name; + struct bq27xxx_access_methods bus; + struct bq27xxx_reg_cache cache; + int charge_design_full; + unsigned long last_update; + struct delayed_work work; + struct power_supply *bat; + struct mutex lock; + u8 *regs; +}; + +void bq27xxx_battery_update(struct bq27xxx_device_info *di); +int bq27xxx_battery_setup(struct bq27xxx_device_info *di); +void bq27xxx_battery_teardown(struct bq27xxx_device_info *di); + #endif diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 9e0e76992be0..48603506f8de 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -140,6 +140,8 @@ struct regulator; * * @supply: The name of the supply. Initialised by the user before * using the bulk regulator APIs. + * @optional: The supply should be considered optional. Initialised by the user + * before using the bulk regulator APIs. * @consumer: The regulator consumer for the supply. This will be managed * by the bulk API. * @@ -149,6 +151,7 @@ struct regulator; */ struct regulator_bulk_data { const char *supply; + bool optional; struct regulator *consumer; /* private: Internal use */ diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 9c2903e58adb..16ac9e108806 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -302,6 +302,8 @@ struct regulator_desc { unsigned int vsel_reg; unsigned int vsel_mask; + unsigned int csel_reg; + unsigned int csel_mask; unsigned int apply_reg; unsigned int apply_bit; unsigned int enable_reg; diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 50777b5b1e4c..a43f41cb3c43 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -60,6 +60,10 @@ extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end); extern int shmem_unuse(swp_entry_t entry, struct page *page); +extern unsigned long shmem_swap_usage(struct vm_area_struct *vma); +extern unsigned long shmem_partial_swap_usage(struct address_space *mapping, + pgoff_t start, pgoff_t end); + static inline struct page *shmem_read_mapping_page( struct address_space *mapping, pgoff_t index) { diff --git a/include/linux/slab.h b/include/linux/slab.h index 2037a861e367..3ffee7422012 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -86,6 +86,11 @@ #else # define SLAB_FAILSLAB 0x00000000UL #endif +#ifdef CONFIG_MEMCG_KMEM +# define SLAB_ACCOUNT 0x04000000UL /* Account to memcg */ +#else +# define SLAB_ACCOUNT 0x00000000UL +#endif /* The following flags affect the page allocator grouping pages by mobility */ #define SLAB_RECLAIM_ACCOUNT 0x00020000UL /* Objects are reclaimable */ diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 78512cfe1fe6..b7dabc4baafd 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -128,6 +128,7 @@ struct svc_xprt *svc_find_xprt(struct svc_serv *serv, const char *xcl_name, const unsigned short port); int svc_xprt_names(struct svc_serv *serv, char *buf, const int buflen); void svc_add_new_perm_xprt(struct svc_serv *serv, struct svc_xprt *xprt); +void svc_age_temp_xprts_now(struct svc_serv *, struct sockaddr *); static inline void svc_xprt_get(struct svc_xprt *xprt) { diff --git a/include/linux/sunrpc/svcauth.h b/include/linux/sunrpc/svcauth.h index 8d71d6577459..c00f53a4ccdd 100644 --- a/include/linux/sunrpc/svcauth.h +++ b/include/linux/sunrpc/svcauth.h @@ -23,13 +23,19 @@ struct svc_cred { kgid_t cr_gid; struct group_info *cr_group_info; u32 cr_flavor; /* pseudoflavor */ - char *cr_principal; /* for gss */ + /* name of form servicetype/hostname@REALM, passed down by + * gss-proxy: */ + char *cr_raw_principal; + /* name of form servicetype@hostname, passed down by + * rpc.svcgssd, or computed from the above: */ + char *cr_principal; struct gss_api_mech *cr_gss_mech; }; static inline void init_svc_cred(struct svc_cred *cred) { cred->cr_group_info = NULL; + cred->cr_raw_principal = NULL; cred->cr_principal = NULL; cred->cr_gss_mech = NULL; } @@ -38,6 +44,7 @@ static inline void free_svc_cred(struct svc_cred *cred) { if (cred->cr_group_info) put_group_info(cred->cr_group_info); + kfree(cred->cr_raw_principal); kfree(cred->cr_principal); gss_mech_put(cred->cr_gss_mech); init_svc_cred(cred); diff --git a/include/linux/swap.h b/include/linux/swap.h index 7ba7dccaf0e7..066bd21765ad 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -287,7 +287,6 @@ static inline void workingset_node_shadows_dec(struct radix_tree_node *node) /* linux/mm/page_alloc.c */ extern unsigned long totalram_pages; extern unsigned long totalreserve_pages; -extern unsigned long dirty_balance_reserve; extern unsigned long nr_free_buffer_pages(void); extern unsigned long nr_free_pagecache_pages(void); diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index ff307b548ed3..b4c2a485b28a 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -56,9 +56,10 @@ extern long do_no_restart_syscall(struct restart_block *parm); #ifdef __KERNEL__ #ifdef CONFIG_DEBUG_STACK_USAGE -# define THREADINFO_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO) +# define THREADINFO_GFP (GFP_KERNEL_ACCOUNT | __GFP_NOTRACK | \ + __GFP_ZERO) #else -# define THREADINFO_GFP (GFP_KERNEL | __GFP_NOTRACK) +# define THREADINFO_GFP (GFP_KERNEL_ACCOUNT | __GFP_NOTRACK) #endif /* diff --git a/include/linux/vfio.h b/include/linux/vfio.h index ddb440975382..610a86a892b8 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -44,6 +44,9 @@ struct vfio_device_ops { void (*request)(void *device_data, unsigned int count); }; +extern struct iommu_group *vfio_iommu_group_get(struct device *dev); +extern void vfio_iommu_group_put(struct iommu_group *group, struct device *dev); + extern int vfio_add_group_dev(struct device *dev, const struct vfio_device_ops *ops, void *device_data); diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 3bff87a25a42..d1f1d338af20 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -14,7 +14,6 @@ struct vm_area_struct; /* vma defining user mapping in mm_types.h */ #define VM_ALLOC 0x00000002 /* vmalloc() */ #define VM_MAP 0x00000004 /* vmap()ed pages */ #define VM_USERMAP 0x00000008 /* suitable for remap_vmalloc_range */ -#define VM_VPAGES 0x00000010 /* buffer for pages was vmalloc'ed */ #define VM_UNINITIALIZED 0x00000020 /* vm_struct is not fully initialized */ #define VM_NO_GUARD 0x00000040 /* don't add guard page */ #define VM_KASAN 0x00000080 /* has allocated kasan shadow memory */ diff --git a/include/linux/vmpressure.h b/include/linux/vmpressure.h index 3e4535876d37..3347cc3ec0ab 100644 --- a/include/linux/vmpressure.h +++ b/include/linux/vmpressure.h @@ -12,6 +12,9 @@ struct vmpressure { unsigned long scanned; unsigned long reclaimed; + + unsigned long tree_scanned; + unsigned long tree_reclaimed; /* The lock is used to keep the scanned/reclaimed above in sync. */ struct spinlock sr_lock; @@ -26,7 +29,7 @@ struct vmpressure { struct mem_cgroup; #ifdef CONFIG_MEMCG -extern void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, +extern void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, bool tree, unsigned long scanned, unsigned long reclaimed); extern void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio); @@ -40,7 +43,7 @@ extern int vmpressure_register_event(struct mem_cgroup *memcg, extern void vmpressure_unregister_event(struct mem_cgroup *memcg, struct eventfd_ctx *eventfd); #else -static inline void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, +static inline void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, bool tree, unsigned long scanned, unsigned long reclaimed) {} static inline void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio) {} diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 3e5d9075960f..73fae8c4a5fb 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -189,6 +189,7 @@ extern void __inc_zone_state(struct zone *, enum zone_stat_item); extern void dec_zone_state(struct zone *, enum zone_stat_item); extern void __dec_zone_state(struct zone *, enum zone_stat_item); +void quiet_vmstat(void); void cpu_vm_stats_fold(int cpu); void refresh_zone_stat_thresholds(void); @@ -249,6 +250,7 @@ static inline void __dec_zone_page_state(struct page *page, static inline void refresh_zone_stat_thresholds(void) { } static inline void cpu_vm_stats_fold(int cpu) { } +static inline void quiet_vmstat(void) { } static inline void drain_zonestat(struct zone *zone, struct per_cpu_pageset *pset) { } diff --git a/include/net/sock.h b/include/net/sock.h index e830c1006935..b9e7b3d863a0 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -71,22 +71,6 @@ #include <net/tcp_states.h> #include <linux/net_tstamp.h> -struct cgroup; -struct cgroup_subsys; -#ifdef CONFIG_NET -int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss); -void mem_cgroup_sockets_destroy(struct mem_cgroup *memcg); -#else -static inline -int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss) -{ - return 0; -} -static inline -void mem_cgroup_sockets_destroy(struct mem_cgroup *memcg) -{ -} -#endif /* * This structure really needs to be cleaned up. * Most of it is for TCP, and not used by any of @@ -245,7 +229,6 @@ struct sock_common { /* public: */ }; -struct cg_proto; /** * struct sock - network layer representation of sockets * @__sk_common: shared layout with inet_timewait_sock @@ -310,7 +293,7 @@ struct cg_proto; * @sk_security: used by security modules * @sk_mark: generic packet mark * @sk_cgrp_data: cgroup data for this cgroup - * @sk_cgrp: this socket's cgroup-specific proto data + * @sk_memcg: this socket's memory cgroup association * @sk_write_pending: a write to stream socket waits to start * @sk_state_change: callback to indicate change in the state of the sock * @sk_data_ready: callback to indicate there is data to be processed @@ -446,7 +429,7 @@ struct sock { void *sk_security; #endif struct sock_cgroup_data sk_cgrp_data; - struct cg_proto *sk_cgrp; + struct mem_cgroup *sk_memcg; void (*sk_state_change)(struct sock *sk); void (*sk_data_ready)(struct sock *sk); void (*sk_write_space)(struct sock *sk); @@ -1096,23 +1079,6 @@ static inline void sk_refcnt_debug_release(const struct sock *sk) #define sk_refcnt_debug_release(sk) do { } while (0) #endif /* SOCK_REFCNT_DEBUG */ -#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_NET) -extern struct static_key memcg_socket_limit_enabled; -static inline struct cg_proto *parent_cg_proto(struct proto *proto, - struct cg_proto *cg_proto) -{ - return proto->proto_cgroup(parent_mem_cgroup(cg_proto->memcg)); -} -#define mem_cgroup_sockets_enabled static_key_false(&memcg_socket_limit_enabled) -#else -#define mem_cgroup_sockets_enabled 0 -static inline struct cg_proto *parent_cg_proto(struct proto *proto, - struct cg_proto *cg_proto) -{ - return NULL; -} -#endif - static inline bool sk_stream_memory_free(const struct sock *sk) { if (sk->sk_wmem_queued >= sk->sk_sndbuf) @@ -1139,8 +1105,9 @@ static inline bool sk_under_memory_pressure(const struct sock *sk) if (!sk->sk_prot->memory_pressure) return false; - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) - return !!sk->sk_cgrp->memory_pressure; + if (mem_cgroup_sockets_enabled && sk->sk_memcg && + mem_cgroup_under_socket_pressure(sk->sk_memcg)) + return true; return !!*sk->sk_prot->memory_pressure; } @@ -1154,15 +1121,6 @@ static inline void sk_leave_memory_pressure(struct sock *sk) if (*memory_pressure) *memory_pressure = 0; - - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) { - struct cg_proto *cg_proto = sk->sk_cgrp; - struct proto *prot = sk->sk_prot; - - for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto)) - cg_proto->memory_pressure = 0; - } - } static inline void sk_enter_memory_pressure(struct sock *sk) @@ -1170,116 +1128,46 @@ static inline void sk_enter_memory_pressure(struct sock *sk) if (!sk->sk_prot->enter_memory_pressure) return; - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) { - struct cg_proto *cg_proto = sk->sk_cgrp; - struct proto *prot = sk->sk_prot; - - for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto)) - cg_proto->memory_pressure = 1; - } - sk->sk_prot->enter_memory_pressure(sk); } static inline long sk_prot_mem_limits(const struct sock *sk, int index) { - long *prot = sk->sk_prot->sysctl_mem; - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) - prot = sk->sk_cgrp->sysctl_mem; - return prot[index]; -} - -static inline void memcg_memory_allocated_add(struct cg_proto *prot, - unsigned long amt, - int *parent_status) -{ - page_counter_charge(&prot->memory_allocated, amt); - - if (page_counter_read(&prot->memory_allocated) > - prot->memory_allocated.limit) - *parent_status = OVER_LIMIT; -} - -static inline void memcg_memory_allocated_sub(struct cg_proto *prot, - unsigned long amt) -{ - page_counter_uncharge(&prot->memory_allocated, amt); + return sk->sk_prot->sysctl_mem[index]; } static inline long sk_memory_allocated(const struct sock *sk) { - struct proto *prot = sk->sk_prot; - - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) - return page_counter_read(&sk->sk_cgrp->memory_allocated); - - return atomic_long_read(prot->memory_allocated); + return atomic_long_read(sk->sk_prot->memory_allocated); } static inline long -sk_memory_allocated_add(struct sock *sk, int amt, int *parent_status) +sk_memory_allocated_add(struct sock *sk, int amt) { - struct proto *prot = sk->sk_prot; - - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) { - memcg_memory_allocated_add(sk->sk_cgrp, amt, parent_status); - /* update the root cgroup regardless */ - atomic_long_add_return(amt, prot->memory_allocated); - return page_counter_read(&sk->sk_cgrp->memory_allocated); - } - - return atomic_long_add_return(amt, prot->memory_allocated); + return atomic_long_add_return(amt, sk->sk_prot->memory_allocated); } static inline void sk_memory_allocated_sub(struct sock *sk, int amt) { - struct proto *prot = sk->sk_prot; - - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) - memcg_memory_allocated_sub(sk->sk_cgrp, amt); - - atomic_long_sub(amt, prot->memory_allocated); + atomic_long_sub(amt, sk->sk_prot->memory_allocated); } static inline void sk_sockets_allocated_dec(struct sock *sk) { - struct proto *prot = sk->sk_prot; - - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) { - struct cg_proto *cg_proto = sk->sk_cgrp; - - for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto)) - percpu_counter_dec(&cg_proto->sockets_allocated); - } - - percpu_counter_dec(prot->sockets_allocated); + percpu_counter_dec(sk->sk_prot->sockets_allocated); } static inline void sk_sockets_allocated_inc(struct sock *sk) { - struct proto *prot = sk->sk_prot; - - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) { - struct cg_proto *cg_proto = sk->sk_cgrp; - - for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto)) - percpu_counter_inc(&cg_proto->sockets_allocated); - } - - percpu_counter_inc(prot->sockets_allocated); + percpu_counter_inc(sk->sk_prot->sockets_allocated); } static inline int sk_sockets_allocated_read_positive(struct sock *sk) { - struct proto *prot = sk->sk_prot; - - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) - return percpu_counter_read_positive(&sk->sk_cgrp->sockets_allocated); - - return percpu_counter_read_positive(prot->sockets_allocated); + return percpu_counter_read_positive(sk->sk_prot->sockets_allocated); } static inline int diff --git a/include/net/tcp.h b/include/net/tcp.h index a80255f4ca33..8ea19977ea53 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -289,8 +289,9 @@ extern int tcp_memory_pressure; /* optimized version of sk_under_memory_pressure() for TCP sockets */ static inline bool tcp_under_memory_pressure(const struct sock *sk) { - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) - return !!sk->sk_cgrp->memory_pressure; + if (mem_cgroup_sockets_enabled && sk->sk_memcg && + mem_cgroup_under_socket_pressure(sk->sk_memcg)) + return true; return tcp_memory_pressure; } diff --git a/include/net/tcp_memcontrol.h b/include/net/tcp_memcontrol.h index 05b94d9453de..3a17b16ae8aa 100644 --- a/include/net/tcp_memcontrol.h +++ b/include/net/tcp_memcontrol.h @@ -1,7 +1,6 @@ #ifndef _TCP_MEMCG_H #define _TCP_MEMCG_H -struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg); int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss); void tcp_destroy_cgroup(struct mem_cgroup *memcg); #endif /* _TCP_MEMCG_H */ diff --git a/arch/powerpc/include/asm/immap_qe.h b/include/soc/fsl/qe/immap_qe.h index bedbff891423..bedbff891423 100644 --- a/arch/powerpc/include/asm/immap_qe.h +++ b/include/soc/fsl/qe/immap_qe.h diff --git a/arch/powerpc/include/asm/qe.h b/include/soc/fsl/qe/qe.h index 32b9bfa0c9bd..c7fa36c335c9 100644 --- a/arch/powerpc/include/asm/qe.h +++ b/include/soc/fsl/qe/qe.h @@ -16,11 +16,16 @@ #define _ASM_POWERPC_QE_H #ifdef __KERNEL__ +#include <linux/compiler.h> +#include <linux/genalloc.h> #include <linux/spinlock.h> #include <linux/errno.h> #include <linux/err.h> #include <asm/cpm.h> -#include <asm/immap_qe.h> +#include <soc/fsl/qe/immap_qe.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/types.h> #define QE_NUM_OF_SNUM 256 /* There are 256 serial number in QE */ #define QE_NUM_OF_BRGS 16 @@ -92,6 +97,51 @@ extern void qe_reset(void); static inline void qe_reset(void) {} #endif +int cpm_muram_init(void); + +#if defined(CONFIG_CPM) || defined(CONFIG_QUICC_ENGINE) +unsigned long cpm_muram_alloc(unsigned long size, unsigned long align); +int cpm_muram_free(unsigned long offset); +unsigned long cpm_muram_alloc_fixed(unsigned long offset, unsigned long size); +unsigned long cpm_muram_alloc_common(unsigned long size, genpool_algo_t algo, + void *data); +void __iomem *cpm_muram_addr(unsigned long offset); +unsigned long cpm_muram_offset(void __iomem *addr); +dma_addr_t cpm_muram_dma(void __iomem *addr); +#else +static inline unsigned long cpm_muram_alloc(unsigned long size, + unsigned long align) +{ + return -ENOSYS; +} + +static inline int cpm_muram_free(unsigned long offset) +{ + return -ENOSYS; +} + +static inline unsigned long cpm_muram_alloc_fixed(unsigned long offset, + unsigned long size) +{ + return -ENOSYS; +} + +static inline void __iomem *cpm_muram_addr(unsigned long offset) +{ + return NULL; +} + +static inline unsigned long cpm_muram_offset(void __iomem *addr) +{ + return -ENOSYS; +} + +static inline dma_addr_t cpm_muram_dma(void __iomem *addr) +{ + return 0; +} +#endif /* defined(CONFIG_CPM) || defined(CONFIG_QUICC_ENGINE) */ + /* QE PIO */ #define QE_PIO_PINS 32 diff --git a/arch/powerpc/include/asm/qe_ic.h b/include/soc/fsl/qe/qe_ic.h index 1e155ca6d33c..1e155ca6d33c 100644 --- a/arch/powerpc/include/asm/qe_ic.h +++ b/include/soc/fsl/qe/qe_ic.h diff --git a/arch/powerpc/include/asm/ucc.h b/include/soc/fsl/qe/ucc.h index 6927ac26516e..894f14cbb044 100644 --- a/arch/powerpc/include/asm/ucc.h +++ b/include/soc/fsl/qe/ucc.h @@ -15,8 +15,8 @@ #ifndef __UCC_H__ #define __UCC_H__ -#include <asm/immap_qe.h> -#include <asm/qe.h> +#include <soc/fsl/qe/immap_qe.h> +#include <soc/fsl/qe/qe.h> #define STATISTICS diff --git a/arch/powerpc/include/asm/ucc_fast.h b/include/soc/fsl/qe/ucc_fast.h index 72ea9bab07df..df8ea7958c63 100644 --- a/arch/powerpc/include/asm/ucc_fast.h +++ b/include/soc/fsl/qe/ucc_fast.h @@ -16,10 +16,10 @@ #include <linux/kernel.h> -#include <asm/immap_qe.h> -#include <asm/qe.h> +#include <soc/fsl/qe/immap_qe.h> +#include <soc/fsl/qe/qe.h> -#include <asm/ucc.h> +#include <soc/fsl/qe/ucc.h> /* Receive BD's status */ #define R_E 0x80000000 /* buffer empty */ diff --git a/arch/powerpc/include/asm/ucc_slow.h b/include/soc/fsl/qe/ucc_slow.h index 233ef5fe5fde..6c0573a0825c 100644 --- a/arch/powerpc/include/asm/ucc_slow.h +++ b/include/soc/fsl/qe/ucc_slow.h @@ -17,10 +17,10 @@ #include <linux/kernel.h> -#include <asm/immap_qe.h> -#include <asm/qe.h> +#include <soc/fsl/qe/immap_qe.h> +#include <soc/fsl/qe/qe.h> -#include <asm/ucc.h> +#include <soc/fsl/qe/ucc.h> /* transmit BD's status */ #define T_R 0x80000000 /* ready bit */ diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h new file mode 100644 index 000000000000..97d635cabac8 --- /dev/null +++ b/include/trace/events/huge_memory.h @@ -0,0 +1,136 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM huge_memory + +#if !defined(__HUGE_MEMORY_H) || defined(TRACE_HEADER_MULTI_READ) +#define __HUGE_MEMORY_H + +#include <linux/tracepoint.h> + +#include <trace/events/gfpflags.h> + +#define SCAN_STATUS \ + EM( SCAN_FAIL, "failed") \ + EM( SCAN_SUCCEED, "succeeded") \ + EM( SCAN_PMD_NULL, "pmd_null") \ + EM( SCAN_EXCEED_NONE_PTE, "exceed_none_pte") \ + EM( SCAN_PTE_NON_PRESENT, "pte_non_present") \ + EM( SCAN_PAGE_RO, "no_writable_page") \ + EM( SCAN_NO_REFERENCED_PAGE, "no_referenced_page") \ + EM( SCAN_PAGE_NULL, "page_null") \ + EM( SCAN_SCAN_ABORT, "scan_aborted") \ + EM( SCAN_PAGE_COUNT, "not_suitable_page_count") \ + EM( SCAN_PAGE_LRU, "page_not_in_lru") \ + EM( SCAN_PAGE_LOCK, "page_locked") \ + EM( SCAN_PAGE_ANON, "page_not_anon") \ + EM( SCAN_ANY_PROCESS, "no_process_for_page") \ + EM( SCAN_VMA_NULL, "vma_null") \ + EM( SCAN_VMA_CHECK, "vma_check_failed") \ + EM( SCAN_ADDRESS_RANGE, "not_suitable_address_range") \ + EM( SCAN_SWAP_CACHE_PAGE, "page_swap_cache") \ + EM( SCAN_DEL_PAGE_LRU, "could_not_delete_page_from_lru")\ + EM( SCAN_ALLOC_HUGE_PAGE_FAIL, "alloc_huge_page_failed") \ + EMe( SCAN_CGROUP_CHARGE_FAIL, "ccgroup_charge_failed") + +#undef EM +#undef EMe +#define EM(a, b) TRACE_DEFINE_ENUM(a); +#define EMe(a, b) TRACE_DEFINE_ENUM(a); + +SCAN_STATUS + +#undef EM +#undef EMe +#define EM(a, b) {a, b}, +#define EMe(a, b) {a, b} + +TRACE_EVENT(mm_khugepaged_scan_pmd, + + TP_PROTO(struct mm_struct *mm, unsigned long pfn, bool writable, + bool referenced, int none_or_zero, int status), + + TP_ARGS(mm, pfn, writable, referenced, none_or_zero, status), + + TP_STRUCT__entry( + __field(struct mm_struct *, mm) + __field(unsigned long, pfn) + __field(bool, writable) + __field(bool, referenced) + __field(int, none_or_zero) + __field(int, status) + ), + + TP_fast_assign( + __entry->mm = mm; + __entry->pfn = pfn; + __entry->writable = writable; + __entry->referenced = referenced; + __entry->none_or_zero = none_or_zero; + __entry->status = status; + ), + + TP_printk("mm=%p, scan_pfn=0x%lx, writable=%d, referenced=%d, none_or_zero=%d, status=%s", + __entry->mm, + __entry->pfn, + __entry->writable, + __entry->referenced, + __entry->none_or_zero, + __print_symbolic(__entry->status, SCAN_STATUS)) +); + +TRACE_EVENT(mm_collapse_huge_page, + + TP_PROTO(struct mm_struct *mm, int isolated, int status), + + TP_ARGS(mm, isolated, status), + + TP_STRUCT__entry( + __field(struct mm_struct *, mm) + __field(int, isolated) + __field(int, status) + ), + + TP_fast_assign( + __entry->mm = mm; + __entry->isolated = isolated; + __entry->status = status; + ), + + TP_printk("mm=%p, isolated=%d, status=%s", + __entry->mm, + __entry->isolated, + __print_symbolic(__entry->status, SCAN_STATUS)) +); + +TRACE_EVENT(mm_collapse_huge_page_isolate, + + TP_PROTO(unsigned long pfn, int none_or_zero, + bool referenced, bool writable, int status), + + TP_ARGS(pfn, none_or_zero, referenced, writable, status), + + TP_STRUCT__entry( + __field(unsigned long, pfn) + __field(int, none_or_zero) + __field(bool, referenced) + __field(bool, writable) + __field(int, status) + ), + + TP_fast_assign( + __entry->pfn = pfn; + __entry->none_or_zero = none_or_zero; + __entry->referenced = referenced; + __entry->writable = writable; + __entry->status = status; + ), + + TP_printk("scan_pfn=0x%lx, none_or_zero=%d, referenced=%d, writable=%d, status=%s", + __entry->pfn, + __entry->none_or_zero, + __entry->referenced, + __entry->writable, + __print_symbolic(__entry->status, SCAN_STATUS)) +); + +#endif /* __HUGE_MEMORY_H */ +#include <trace/define_trace.h> diff --git a/include/trace/events/page_isolation.h b/include/trace/events/page_isolation.h new file mode 100644 index 000000000000..6fb644029c80 --- /dev/null +++ b/include/trace/events/page_isolation.h @@ -0,0 +1,38 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM page_isolation + +#if !defined(_TRACE_PAGE_ISOLATION_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_PAGE_ISOLATION_H + +#include <linux/tracepoint.h> + +TRACE_EVENT(test_pages_isolated, + + TP_PROTO( + unsigned long start_pfn, + unsigned long end_pfn, + unsigned long fin_pfn), + + TP_ARGS(start_pfn, end_pfn, fin_pfn), + + TP_STRUCT__entry( + __field(unsigned long, start_pfn) + __field(unsigned long, end_pfn) + __field(unsigned long, fin_pfn) + ), + + TP_fast_assign( + __entry->start_pfn = start_pfn; + __entry->end_pfn = end_pfn; + __entry->fin_pfn = fin_pfn; + ), + + TP_printk("start_pfn=0x%lx end_pfn=0x%lx fin_pfn=0x%lx ret=%s", + __entry->start_pfn, __entry->end_pfn, __entry->fin_pfn, + __entry->end_pfn == __entry->fin_pfn ? "success" : "fail") +); + +#endif /* _TRACE_PAGE_ISOLATION_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index f66476b96264..31763dd8db1c 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -330,10 +330,9 @@ DEFINE_EVENT(mm_vmscan_lru_isolate_template, mm_vmscan_memcg_isolate, TRACE_EVENT(mm_vmscan_writepage, - TP_PROTO(struct page *page, - int reclaim_flags), + TP_PROTO(struct page *page), - TP_ARGS(page, reclaim_flags), + TP_ARGS(page), TP_STRUCT__entry( __field(unsigned long, pfn) @@ -342,7 +341,7 @@ TRACE_EVENT(mm_vmscan_writepage, TP_fast_assign( __entry->pfn = page_to_pfn(page); - __entry->reclaim_flags = reclaim_flags; + __entry->reclaim_flags = trace_reclaim_flags(page); ), TP_printk("page=%p pfn=%lu flags=%s", @@ -353,11 +352,11 @@ TRACE_EVENT(mm_vmscan_writepage, TRACE_EVENT(mm_vmscan_lru_shrink_inactive, - TP_PROTO(int nid, int zid, - unsigned long nr_scanned, unsigned long nr_reclaimed, - int priority, int reclaim_flags), + TP_PROTO(struct zone *zone, + unsigned long nr_scanned, unsigned long nr_reclaimed, + int priority, int file), - TP_ARGS(nid, zid, nr_scanned, nr_reclaimed, priority, reclaim_flags), + TP_ARGS(zone, nr_scanned, nr_reclaimed, priority, file), TP_STRUCT__entry( __field(int, nid) @@ -369,12 +368,12 @@ TRACE_EVENT(mm_vmscan_lru_shrink_inactive, ), TP_fast_assign( - __entry->nid = nid; - __entry->zid = zid; + __entry->nid = zone_to_nid(zone); + __entry->zid = zone_idx(zone); __entry->nr_scanned = nr_scanned; __entry->nr_reclaimed = nr_reclaimed; __entry->priority = priority; - __entry->reclaim_flags = reclaim_flags; + __entry->reclaim_flags = trace_shrink_flags(file); ), TP_printk("nid=%d zid=%d nr_scanned=%ld nr_reclaimed=%ld priority=%d flags=%s", diff --git a/include/uapi/linux/raid/md_u.h b/include/uapi/linux/raid/md_u.h index 1cb8aa6850b5..36cd8210a5d1 100644 --- a/include/uapi/linux/raid/md_u.h +++ b/include/uapi/linux/raid/md_u.h @@ -80,7 +80,7 @@ typedef struct mdu_array_info_s { int major_version; int minor_version; int patch_version; - int ctime; + unsigned int ctime; int level; int size; int nr_disks; @@ -91,7 +91,7 @@ typedef struct mdu_array_info_s { /* * Generic state information */ - int utime; /* 0 Superblock update time */ + unsigned int utime; /* 0 Superblock update time */ int state; /* 1 State bits (clean, ...) */ int active_disks; /* 2 Number of currently active disks */ int working_disks; /* 3 Number of working disks */ diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 9fd7b5d8df2f..7d7a4c6f2090 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -39,6 +39,13 @@ #define VFIO_SPAPR_TCE_v2_IOMMU 7 /* + * The No-IOMMU IOMMU offers no translation or isolation for devices and + * supports no ioctls outside of VFIO_CHECK_EXTENSION. Use of VFIO's No-IOMMU + * code will taint the host kernel and should be used with extreme caution. + */ +#define VFIO_NOIOMMU_IOMMU 8 + +/* * The IOCTL interface is designed for extensibility by embedding the * structure length (argsz) and flags into structures passed between * kernel and userspace. We therefore use the _IO() macro for these @@ -568,8 +575,10 @@ struct vfio_iommu_spapr_tce_create { __u32 flags; /* in */ __u32 page_shift; + __u32 __resv1; __u64 window_size; __u32 levels; + __u32 __resv2; /* out */ __u64 start_addr; }; diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 161a1807e6ef..f4617cf07069 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -1438,7 +1438,7 @@ static int __init init_mqueue_fs(void) mqueue_inode_cachep = kmem_cache_create("mqueue_inode_cache", sizeof(struct mqueue_inode_info), 0, - SLAB_HWCACHE_ALIGN, init_once); + SLAB_HWCACHE_ALIGN|SLAB_ACCOUNT, init_once); if (mqueue_inode_cachep == NULL) return -ENOMEM; diff --git a/kernel/cred.c b/kernel/cred.c index 71179a09c1d6..0c0cd8a62285 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -569,8 +569,8 @@ EXPORT_SYMBOL(revert_creds); void __init cred_init(void) { /* allocate a slab in which we can store credentials */ - cred_jar = kmem_cache_create("cred_jar", sizeof(struct cred), - 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); + cred_jar = kmem_cache_create("cred_jar", sizeof(struct cred), 0, + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); } /** diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 4121345498e0..2a20c0dfdafc 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -2021,7 +2021,7 @@ static int kdb_lsmod(int argc, const char **argv) continue; kdb_printf("%-20s%8u 0x%p ", mod->name, - mod->core_size, (void *)mod); + mod->core_layout.size, (void *)mod); #ifdef CONFIG_MODULE_UNLOAD kdb_printf("%4d ", module_refcount(mod)); #endif @@ -2031,7 +2031,7 @@ static int kdb_lsmod(int argc, const char **argv) kdb_printf(" (Loading)"); else kdb_printf(" (Live)"); - kdb_printf(" 0x%p", mod->module_core); + kdb_printf(" 0x%p", mod->core_layout.base); #ifdef CONFIG_MODULE_UNLOAD { diff --git a/kernel/delayacct.c b/kernel/delayacct.c index ef90b04d783f..435c14a45118 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -34,7 +34,7 @@ __setup("nodelayacct", delayacct_setup_disable); void delayacct_init(void) { - delayacct_cache = KMEM_CACHE(task_delay_info, SLAB_PANIC); + delayacct_cache = KMEM_CACHE(task_delay_info, SLAB_PANIC|SLAB_ACCOUNT); delayacct_tsk_init(&init_task); } diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 7dad84913abf..bb0669169716 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -180,7 +180,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, lru_cache_add_active_or_unevictable(kpage, vma); if (!PageAnon(page)) { - dec_mm_counter(mm, MM_FILEPAGES); + dec_mm_counter(mm, mm_counter_file(page)); inc_mm_counter(mm, MM_ANONPAGES); } diff --git a/kernel/fork.c b/kernel/fork.c index 6774e6b2e96d..2e391c754ae7 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -300,9 +300,9 @@ void __init fork_init(void) #define ARCH_MIN_TASKALIGN L1_CACHE_BYTES #endif /* create a slab on which task_structs can be allocated */ - task_struct_cachep = - kmem_cache_create("task_struct", arch_task_struct_size, - ARCH_MIN_TASKALIGN, SLAB_PANIC | SLAB_NOTRACK, NULL); + task_struct_cachep = kmem_cache_create("task_struct", + arch_task_struct_size, ARCH_MIN_TASKALIGN, + SLAB_PANIC|SLAB_NOTRACK|SLAB_ACCOUNT, NULL); #endif /* do the arch specific task caches init */ @@ -414,7 +414,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm)); mm->total_vm = oldmm->total_vm; - mm->shared_vm = oldmm->shared_vm; + mm->data_vm = oldmm->data_vm; mm->exec_vm = oldmm->exec_vm; mm->stack_vm = oldmm->stack_vm; @@ -433,8 +433,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) struct file *file; if (mpnt->vm_flags & VM_DONTCOPY) { - vm_stat_account(mm, mpnt->vm_flags, mpnt->vm_file, - -vma_pages(mpnt)); + vm_stat_account(mm, mpnt->vm_flags, -vma_pages(mpnt)); continue; } charge = 0; @@ -1848,16 +1847,19 @@ void __init proc_caches_init(void) sighand_cachep = kmem_cache_create("sighand_cache", sizeof(struct sighand_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_DESTROY_BY_RCU| - SLAB_NOTRACK, sighand_ctor); + SLAB_NOTRACK|SLAB_ACCOUNT, sighand_ctor); signal_cachep = kmem_cache_create("signal_cache", sizeof(struct signal_struct), 0, - SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK|SLAB_ACCOUNT, + NULL); files_cachep = kmem_cache_create("files_cache", sizeof(struct files_struct), 0, - SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK|SLAB_ACCOUNT, + NULL); fs_cachep = kmem_cache_create("fs_cache", sizeof(struct fs_struct), 0, - SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK|SLAB_ACCOUNT, + NULL); /* * FIXME! The "sizeof(struct mm_struct)" currently includes the * whole struct cpumask for the OFFSTACK case. We could change @@ -1867,8 +1869,9 @@ void __init proc_caches_init(void) */ mm_cachep = kmem_cache_create("mm_struct", sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN, - SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); - vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC); + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK|SLAB_ACCOUNT, + NULL); + vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC|SLAB_ACCOUNT); mmap_init(); nsproxy_cache_init(); } diff --git a/kernel/gcov/base.c b/kernel/gcov/base.c index 7080ae1eb6c1..2f9df37940a0 100644 --- a/kernel/gcov/base.c +++ b/kernel/gcov/base.c @@ -123,11 +123,6 @@ void gcov_enable_events(void) } #ifdef CONFIG_MODULES -static inline int within(void *addr, void *start, unsigned long size) -{ - return ((addr >= start) && (addr < start + size)); -} - /* Update list and generate events when modules are unloaded. */ static int gcov_module_notifier(struct notifier_block *nb, unsigned long event, void *data) @@ -142,7 +137,7 @@ static int gcov_module_notifier(struct notifier_block *nb, unsigned long event, /* Remove entries located in module from linked list. */ while ((info = gcov_info_next(info))) { - if (within(info, mod->module_core, mod->core_size)) { + if (within_module((unsigned long)info, mod)) { gcov_info_unlink(prev, info); if (gcov_events_enabled) gcov_event(GCOV_REMOVE, info); diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index db545cbcdb89..bc2c85c064c1 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -28,6 +28,7 @@ #include <linux/list.h> #include <linux/kallsyms.h> #include <linux/livepatch.h> +#include <asm/cacheflush.h> /** * struct klp_ops - structure for tracking registered ftrace ops structs @@ -135,13 +136,8 @@ struct klp_find_arg { const char *objname; const char *name; unsigned long addr; - /* - * If count == 0, the symbol was not found. If count == 1, a unique - * match was found and addr is set. If count > 1, there is - * unresolvable ambiguity among "count" number of symbols with the same - * name in the same object. - */ unsigned long count; + unsigned long pos; }; static int klp_find_callback(void *data, const char *name, @@ -158,37 +154,48 @@ static int klp_find_callback(void *data, const char *name, if (args->objname && strcmp(args->objname, mod->name)) return 0; - /* - * args->addr might be overwritten if another match is found - * but klp_find_object_symbol() handles this and only returns the - * addr if count == 1. - */ args->addr = addr; args->count++; + /* + * Finish the search when the symbol is found for the desired position + * or the position is not defined for a non-unique symbol. + */ + if ((args->pos && (args->count == args->pos)) || + (!args->pos && (args->count > 1))) + return 1; + return 0; } static int klp_find_object_symbol(const char *objname, const char *name, - unsigned long *addr) + unsigned long sympos, unsigned long *addr) { struct klp_find_arg args = { .objname = objname, .name = name, .addr = 0, - .count = 0 + .count = 0, + .pos = sympos, }; mutex_lock(&module_mutex); kallsyms_on_each_symbol(klp_find_callback, &args); mutex_unlock(&module_mutex); - if (args.count == 0) + /* + * Ensure an address was found. If sympos is 0, ensure symbol is unique; + * otherwise ensure the symbol position count matches sympos. + */ + if (args.addr == 0) pr_err("symbol '%s' not found in symbol table\n", name); - else if (args.count > 1) + else if (args.count > 1 && sympos == 0) { pr_err("unresolvable ambiguity (%lu matches) on symbol '%s' in object '%s'\n", args.count, name, objname); - else { + } else if (sympos != args.count && sympos > 0) { + pr_err("symbol position %lu for symbol '%s' in object '%s' not found\n", + sympos, name, objname ? objname : "vmlinux"); + } else { *addr = args.addr; return 0; } @@ -197,66 +204,6 @@ static int klp_find_object_symbol(const char *objname, const char *name, return -EINVAL; } -struct klp_verify_args { - const char *name; - const unsigned long addr; -}; - -static int klp_verify_callback(void *data, const char *name, - struct module *mod, unsigned long addr) -{ - struct klp_verify_args *args = data; - - if (!mod && - !strcmp(args->name, name) && - args->addr == addr) - return 1; - - return 0; -} - -static int klp_verify_vmlinux_symbol(const char *name, unsigned long addr) -{ - struct klp_verify_args args = { - .name = name, - .addr = addr, - }; - int ret; - - mutex_lock(&module_mutex); - ret = kallsyms_on_each_symbol(klp_verify_callback, &args); - mutex_unlock(&module_mutex); - - if (!ret) { - pr_err("symbol '%s' not found at specified address 0x%016lx, kernel mismatch?\n", - name, addr); - return -EINVAL; - } - - return 0; -} - -static int klp_find_verify_func_addr(struct klp_object *obj, - struct klp_func *func) -{ - int ret; - -#if defined(CONFIG_RANDOMIZE_BASE) - /* If KASLR has been enabled, adjust old_addr accordingly */ - if (kaslr_enabled() && func->old_addr) - func->old_addr += kaslr_offset(); -#endif - - if (!func->old_addr || klp_is_module(obj)) - ret = klp_find_object_symbol(obj->name, func->old_name, - &func->old_addr); - else - ret = klp_verify_vmlinux_symbol(func->old_name, - func->old_addr); - - return ret; -} - /* * external symbols are located outside the parent object (where the parent * object is either vmlinux or the kmod being patched). @@ -276,14 +223,18 @@ static int klp_find_external_symbol(struct module *pmod, const char *name, } preempt_enable(); - /* otherwise check if it's in another .o within the patch module */ - return klp_find_object_symbol(pmod->name, name, addr); + /* + * Check if it's in another .o within the patch module. This also + * checks that the external symbol is unique. + */ + return klp_find_object_symbol(pmod->name, name, 0, addr); } static int klp_write_object_relocations(struct module *pmod, struct klp_object *obj) { - int ret; + int ret = 0; + unsigned long val; struct klp_reloc *reloc; if (WARN_ON(!klp_is_object_loaded(obj))) @@ -292,41 +243,38 @@ static int klp_write_object_relocations(struct module *pmod, if (WARN_ON(!obj->relocs)) return -EINVAL; + module_disable_ro(pmod); + for (reloc = obj->relocs; reloc->name; reloc++) { - if (!klp_is_module(obj)) { - -#if defined(CONFIG_RANDOMIZE_BASE) - /* If KASLR has been enabled, adjust old value accordingly */ - if (kaslr_enabled()) - reloc->val += kaslr_offset(); -#endif - ret = klp_verify_vmlinux_symbol(reloc->name, - reloc->val); - if (ret) - return ret; - } else { - /* module, reloc->val needs to be discovered */ - if (reloc->external) - ret = klp_find_external_symbol(pmod, - reloc->name, - &reloc->val); - else - ret = klp_find_object_symbol(obj->mod->name, - reloc->name, - &reloc->val); - if (ret) - return ret; - } + /* discover the address of the referenced symbol */ + if (reloc->external) { + if (reloc->sympos > 0) { + pr_err("non-zero sympos for external reloc symbol '%s' is not supported\n", + reloc->name); + ret = -EINVAL; + goto out; + } + ret = klp_find_external_symbol(pmod, reloc->name, &val); + } else + ret = klp_find_object_symbol(obj->name, + reloc->name, + reloc->sympos, + &val); + if (ret) + goto out; + ret = klp_write_module_reloc(pmod, reloc->type, reloc->loc, - reloc->val + reloc->addend); + val + reloc->addend); if (ret) { pr_err("relocation failed for symbol '%s' at 0x%016lx (%d)\n", - reloc->name, reloc->val, ret); - return ret; + reloc->name, val, ret); + goto out; } } - return 0; +out: + module_enable_ro(pmod); + return ret; } static void notrace klp_ftrace_handler(unsigned long ip, @@ -593,7 +541,7 @@ EXPORT_SYMBOL_GPL(klp_enable_patch); * /sys/kernel/livepatch/<patch> * /sys/kernel/livepatch/<patch>/enabled * /sys/kernel/livepatch/<patch>/<object> - * /sys/kernel/livepatch/<patch>/<object>/<func> + * /sys/kernel/livepatch/<patch>/<object>/<function,sympos> */ static ssize_t enabled_store(struct kobject *kobj, struct kobj_attribute *attr, @@ -738,8 +686,14 @@ static int klp_init_func(struct klp_object *obj, struct klp_func *func) INIT_LIST_HEAD(&func->stack_node); func->state = KLP_DISABLED; + /* The format for the sysfs directory is <function,sympos> where sympos + * is the nth occurrence of this symbol in kallsyms for the patched + * object. If the user selects 0 for old_sympos, then 1 will be used + * since a unique symbol will be the first occurrence. + */ return kobject_init_and_add(&func->kobj, &klp_ktype_func, - &obj->kobj, "%s", func->old_name); + &obj->kobj, "%s,%lu", func->old_name, + func->old_sympos ? func->old_sympos : 1); } /* parts of the initialization that is done only when the object is loaded */ @@ -756,7 +710,9 @@ static int klp_init_object_loaded(struct klp_patch *patch, } klp_for_each_func(obj, func) { - ret = klp_find_verify_func_addr(obj, func); + ret = klp_find_object_symbol(obj->name, func->old_name, + func->old_sympos, + &func->old_addr); if (ret) return ret; } diff --git a/kernel/module.c b/kernel/module.c index 38c7bd5583ff..8358f4697c0c 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -80,15 +80,6 @@ # define debug_align(X) (X) #endif -/* - * Given BASE and SIZE this macro calculates the number of pages the - * memory regions occupies - */ -#define MOD_NUMBER_OF_PAGES(BASE, SIZE) (((SIZE) > 0) ? \ - (PFN_DOWN((unsigned long)(BASE) + (SIZE) - 1) - \ - PFN_DOWN((unsigned long)BASE) + 1) \ - : (0UL)) - /* If this is set, the section belongs in the init part of the module */ #define INIT_OFFSET_MASK (1UL << (BITS_PER_LONG-1)) @@ -108,13 +99,6 @@ static LIST_HEAD(modules); * Use a latched RB-tree for __module_address(); this allows us to use * RCU-sched lookups of the address from any context. * - * Because modules have two address ranges: init and core, we need two - * latch_tree_nodes entries. Therefore we need the back-pointer from - * mod_tree_node. - * - * Because init ranges are short lived we mark them unlikely and have placed - * them outside the critical cacheline in struct module. - * * This is conditional on PERF_EVENTS || TRACING because those can really hit * __module_address() hard by doing a lot of stack unwinding; potentially from * NMI context. @@ -122,24 +106,16 @@ static LIST_HEAD(modules); static __always_inline unsigned long __mod_tree_val(struct latch_tree_node *n) { - struct mod_tree_node *mtn = container_of(n, struct mod_tree_node, node); - struct module *mod = mtn->mod; + struct module_layout *layout = container_of(n, struct module_layout, mtn.node); - if (unlikely(mtn == &mod->mtn_init)) - return (unsigned long)mod->module_init; - - return (unsigned long)mod->module_core; + return (unsigned long)layout->base; } static __always_inline unsigned long __mod_tree_size(struct latch_tree_node *n) { - struct mod_tree_node *mtn = container_of(n, struct mod_tree_node, node); - struct module *mod = mtn->mod; - - if (unlikely(mtn == &mod->mtn_init)) - return (unsigned long)mod->init_size; + struct module_layout *layout = container_of(n, struct module_layout, mtn.node); - return (unsigned long)mod->core_size; + return (unsigned long)layout->size; } static __always_inline bool @@ -197,23 +173,23 @@ static void __mod_tree_remove(struct mod_tree_node *node) */ static void mod_tree_insert(struct module *mod) { - mod->mtn_core.mod = mod; - mod->mtn_init.mod = mod; + mod->core_layout.mtn.mod = mod; + mod->init_layout.mtn.mod = mod; - __mod_tree_insert(&mod->mtn_core); - if (mod->init_size) - __mod_tree_insert(&mod->mtn_init); + __mod_tree_insert(&mod->core_layout.mtn); + if (mod->init_layout.size) + __mod_tree_insert(&mod->init_layout.mtn); } static void mod_tree_remove_init(struct module *mod) { - if (mod->init_size) - __mod_tree_remove(&mod->mtn_init); + if (mod->init_layout.size) + __mod_tree_remove(&mod->init_layout.mtn); } static void mod_tree_remove(struct module *mod) { - __mod_tree_remove(&mod->mtn_core); + __mod_tree_remove(&mod->core_layout.mtn); mod_tree_remove_init(mod); } @@ -267,9 +243,9 @@ static void __mod_update_bounds(void *base, unsigned int size) static void mod_update_bounds(struct module *mod) { - __mod_update_bounds(mod->module_core, mod->core_size); - if (mod->init_size) - __mod_update_bounds(mod->module_init, mod->init_size); + __mod_update_bounds(mod->core_layout.base, mod->core_layout.size); + if (mod->init_layout.size) + __mod_update_bounds(mod->init_layout.base, mod->init_layout.size); } #ifdef CONFIG_KGDB_KDB @@ -1214,7 +1190,7 @@ struct module_attribute module_uevent = static ssize_t show_coresize(struct module_attribute *mattr, struct module_kobject *mk, char *buffer) { - return sprintf(buffer, "%u\n", mk->mod->core_size); + return sprintf(buffer, "%u\n", mk->mod->core_layout.size); } static struct module_attribute modinfo_coresize = @@ -1223,7 +1199,7 @@ static struct module_attribute modinfo_coresize = static ssize_t show_initsize(struct module_attribute *mattr, struct module_kobject *mk, char *buffer) { - return sprintf(buffer, "%u\n", mk->mod->init_size); + return sprintf(buffer, "%u\n", mk->mod->init_layout.size); } static struct module_attribute modinfo_initsize = @@ -1873,64 +1849,75 @@ static void mod_sysfs_teardown(struct module *mod) /* * LKM RO/NX protection: protect module's text/ro-data * from modification and any data from execution. + * + * General layout of module is: + * [text] [read-only-data] [writable data] + * text_size -----^ ^ ^ + * ro_size ------------------------| | + * size -------------------------------------------| + * + * These values are always page-aligned (as is base) */ -void set_page_attributes(void *start, void *end, int (*set)(unsigned long start, int num_pages)) +static void frob_text(const struct module_layout *layout, + int (*set_memory)(unsigned long start, int num_pages)) { - unsigned long begin_pfn = PFN_DOWN((unsigned long)start); - unsigned long end_pfn = PFN_DOWN((unsigned long)end); + BUG_ON((unsigned long)layout->base & (PAGE_SIZE-1)); + BUG_ON((unsigned long)layout->text_size & (PAGE_SIZE-1)); + set_memory((unsigned long)layout->base, + layout->text_size >> PAGE_SHIFT); +} - if (end_pfn > begin_pfn) - set(begin_pfn << PAGE_SHIFT, end_pfn - begin_pfn); +static void frob_rodata(const struct module_layout *layout, + int (*set_memory)(unsigned long start, int num_pages)) +{ + BUG_ON((unsigned long)layout->base & (PAGE_SIZE-1)); + BUG_ON((unsigned long)layout->text_size & (PAGE_SIZE-1)); + BUG_ON((unsigned long)layout->ro_size & (PAGE_SIZE-1)); + set_memory((unsigned long)layout->base + layout->text_size, + (layout->ro_size - layout->text_size) >> PAGE_SHIFT); } -static void set_section_ro_nx(void *base, - unsigned long text_size, - unsigned long ro_size, - unsigned long total_size) +static void frob_writable_data(const struct module_layout *layout, + int (*set_memory)(unsigned long start, int num_pages)) { - /* begin and end PFNs of the current subsection */ - unsigned long begin_pfn; - unsigned long end_pfn; + BUG_ON((unsigned long)layout->base & (PAGE_SIZE-1)); + BUG_ON((unsigned long)layout->ro_size & (PAGE_SIZE-1)); + BUG_ON((unsigned long)layout->size & (PAGE_SIZE-1)); + set_memory((unsigned long)layout->base + layout->ro_size, + (layout->size - layout->ro_size) >> PAGE_SHIFT); +} - /* - * Set RO for module text and RO-data: - * - Always protect first page. - * - Do not protect last partial page. - */ - if (ro_size > 0) - set_page_attributes(base, base + ro_size, set_memory_ro); +/* livepatching wants to disable read-only so it can frob module. */ +void module_disable_ro(const struct module *mod) +{ + frob_text(&mod->core_layout, set_memory_rw); + frob_rodata(&mod->core_layout, set_memory_rw); + frob_text(&mod->init_layout, set_memory_rw); + frob_rodata(&mod->init_layout, set_memory_rw); +} - /* - * Set NX permissions for module data: - * - Do not protect first partial page. - * - Always protect last page. - */ - if (total_size > text_size) { - begin_pfn = PFN_UP((unsigned long)base + text_size); - end_pfn = PFN_UP((unsigned long)base + total_size); - if (end_pfn > begin_pfn) - set_memory_nx(begin_pfn << PAGE_SHIFT, end_pfn - begin_pfn); - } +void module_enable_ro(const struct module *mod) +{ + frob_text(&mod->core_layout, set_memory_ro); + frob_rodata(&mod->core_layout, set_memory_ro); + frob_text(&mod->init_layout, set_memory_ro); + frob_rodata(&mod->init_layout, set_memory_ro); } -static void unset_module_core_ro_nx(struct module *mod) +static void module_enable_nx(const struct module *mod) { - set_page_attributes(mod->module_core + mod->core_text_size, - mod->module_core + mod->core_size, - set_memory_x); - set_page_attributes(mod->module_core, - mod->module_core + mod->core_ro_size, - set_memory_rw); + frob_rodata(&mod->core_layout, set_memory_nx); + frob_writable_data(&mod->core_layout, set_memory_nx); + frob_rodata(&mod->init_layout, set_memory_nx); + frob_writable_data(&mod->init_layout, set_memory_nx); } -static void unset_module_init_ro_nx(struct module *mod) +static void module_disable_nx(const struct module *mod) { - set_page_attributes(mod->module_init + mod->init_text_size, - mod->module_init + mod->init_size, - set_memory_x); - set_page_attributes(mod->module_init, - mod->module_init + mod->init_ro_size, - set_memory_rw); + frob_rodata(&mod->core_layout, set_memory_x); + frob_writable_data(&mod->core_layout, set_memory_x); + frob_rodata(&mod->init_layout, set_memory_x); + frob_writable_data(&mod->init_layout, set_memory_x); } /* Iterate through all modules and set each module's text as RW */ @@ -1942,16 +1929,9 @@ void set_all_modules_text_rw(void) list_for_each_entry_rcu(mod, &modules, list) { if (mod->state == MODULE_STATE_UNFORMED) continue; - if ((mod->module_core) && (mod->core_text_size)) { - set_page_attributes(mod->module_core, - mod->module_core + mod->core_text_size, - set_memory_rw); - } - if ((mod->module_init) && (mod->init_text_size)) { - set_page_attributes(mod->module_init, - mod->module_init + mod->init_text_size, - set_memory_rw); - } + + frob_text(&mod->core_layout, set_memory_rw); + frob_text(&mod->init_layout, set_memory_rw); } mutex_unlock(&module_mutex); } @@ -1965,23 +1945,25 @@ void set_all_modules_text_ro(void) list_for_each_entry_rcu(mod, &modules, list) { if (mod->state == MODULE_STATE_UNFORMED) continue; - if ((mod->module_core) && (mod->core_text_size)) { - set_page_attributes(mod->module_core, - mod->module_core + mod->core_text_size, - set_memory_ro); - } - if ((mod->module_init) && (mod->init_text_size)) { - set_page_attributes(mod->module_init, - mod->module_init + mod->init_text_size, - set_memory_ro); - } + + frob_text(&mod->core_layout, set_memory_ro); + frob_text(&mod->init_layout, set_memory_ro); } mutex_unlock(&module_mutex); } + +static void disable_ro_nx(const struct module_layout *layout) +{ + frob_text(layout, set_memory_rw); + frob_rodata(layout, set_memory_rw); + frob_rodata(layout, set_memory_x); + frob_writable_data(layout, set_memory_x); +} + #else -static inline void set_section_ro_nx(void *base, unsigned long text_size, unsigned long ro_size, unsigned long total_size) { } -static void unset_module_core_ro_nx(struct module *mod) { } -static void unset_module_init_ro_nx(struct module *mod) { } +static void disable_ro_nx(const struct module_layout *layout) { } +static void module_enable_nx(const struct module *mod) { } +static void module_disable_nx(const struct module *mod) { } #endif void __weak module_memfree(void *module_region) @@ -2033,19 +2015,19 @@ static void free_module(struct module *mod) synchronize_sched(); mutex_unlock(&module_mutex); - /* This may be NULL, but that's OK */ - unset_module_init_ro_nx(mod); + /* This may be empty, but that's OK */ + disable_ro_nx(&mod->init_layout); module_arch_freeing_init(mod); - module_memfree(mod->module_init); + module_memfree(mod->init_layout.base); kfree(mod->args); percpu_modfree(mod); /* Free lock-classes; relies on the preceding sync_rcu(). */ - lockdep_free_key_range(mod->module_core, mod->core_size); + lockdep_free_key_range(mod->core_layout.base, mod->core_layout.size); /* Finally, free the core (containing the module structure) */ - unset_module_core_ro_nx(mod); - module_memfree(mod->module_core); + disable_ro_nx(&mod->core_layout); + module_memfree(mod->core_layout.base); #ifdef CONFIG_MPU update_protections(current->mm); @@ -2248,20 +2230,20 @@ static void layout_sections(struct module *mod, struct load_info *info) || s->sh_entsize != ~0UL || strstarts(sname, ".init")) continue; - s->sh_entsize = get_offset(mod, &mod->core_size, s, i); + s->sh_entsize = get_offset(mod, &mod->core_layout.size, s, i); pr_debug("\t%s\n", sname); } switch (m) { case 0: /* executable */ - mod->core_size = debug_align(mod->core_size); - mod->core_text_size = mod->core_size; + mod->core_layout.size = debug_align(mod->core_layout.size); + mod->core_layout.text_size = mod->core_layout.size; break; case 1: /* RO: text and ro-data */ - mod->core_size = debug_align(mod->core_size); - mod->core_ro_size = mod->core_size; + mod->core_layout.size = debug_align(mod->core_layout.size); + mod->core_layout.ro_size = mod->core_layout.size; break; case 3: /* whole core */ - mod->core_size = debug_align(mod->core_size); + mod->core_layout.size = debug_align(mod->core_layout.size); break; } } @@ -2277,21 +2259,21 @@ static void layout_sections(struct module *mod, struct load_info *info) || s->sh_entsize != ~0UL || !strstarts(sname, ".init")) continue; - s->sh_entsize = (get_offset(mod, &mod->init_size, s, i) + s->sh_entsize = (get_offset(mod, &mod->init_layout.size, s, i) | INIT_OFFSET_MASK); pr_debug("\t%s\n", sname); } switch (m) { case 0: /* executable */ - mod->init_size = debug_align(mod->init_size); - mod->init_text_size = mod->init_size; + mod->init_layout.size = debug_align(mod->init_layout.size); + mod->init_layout.text_size = mod->init_layout.size; break; case 1: /* RO: text and ro-data */ - mod->init_size = debug_align(mod->init_size); - mod->init_ro_size = mod->init_size; + mod->init_layout.size = debug_align(mod->init_layout.size); + mod->init_layout.ro_size = mod->init_layout.size; break; case 3: /* whole init */ - mod->init_size = debug_align(mod->init_size); + mod->init_layout.size = debug_align(mod->init_layout.size); break; } } @@ -2401,7 +2383,7 @@ static char elf_type(const Elf_Sym *sym, const struct load_info *info) } if (sym->st_shndx == SHN_UNDEF) return 'U'; - if (sym->st_shndx == SHN_ABS) + if (sym->st_shndx == SHN_ABS || sym->st_shndx == info->index.pcpu) return 'a'; if (sym->st_shndx >= SHN_LORESERVE) return '?'; @@ -2430,7 +2412,7 @@ static char elf_type(const Elf_Sym *sym, const struct load_info *info) } static bool is_core_symbol(const Elf_Sym *src, const Elf_Shdr *sechdrs, - unsigned int shnum) + unsigned int shnum, unsigned int pcpundx) { const Elf_Shdr *sec; @@ -2439,6 +2421,11 @@ static bool is_core_symbol(const Elf_Sym *src, const Elf_Shdr *sechdrs, || !src->st_name) return false; +#ifdef CONFIG_KALLSYMS_ALL + if (src->st_shndx == pcpundx) + return true; +#endif + sec = sechdrs + src->st_shndx; if (!(sec->sh_flags & SHF_ALLOC) #ifndef CONFIG_KALLSYMS_ALL @@ -2466,7 +2453,7 @@ static void layout_symtab(struct module *mod, struct load_info *info) /* Put symbol section at end of init part of module. */ symsect->sh_flags |= SHF_ALLOC; - symsect->sh_entsize = get_offset(mod, &mod->init_size, symsect, + symsect->sh_entsize = get_offset(mod, &mod->init_layout.size, symsect, info->index.sym) | INIT_OFFSET_MASK; pr_debug("\t%s\n", info->secstrings + symsect->sh_name); @@ -2476,23 +2463,24 @@ static void layout_symtab(struct module *mod, struct load_info *info) /* Compute total space required for the core symbols' strtab. */ for (ndst = i = 0; i < nsrc; i++) { if (i == 0 || - is_core_symbol(src+i, info->sechdrs, info->hdr->e_shnum)) { + is_core_symbol(src+i, info->sechdrs, info->hdr->e_shnum, + info->index.pcpu)) { strtab_size += strlen(&info->strtab[src[i].st_name])+1; ndst++; } } /* Append room for core symbols at end of core part. */ - info->symoffs = ALIGN(mod->core_size, symsect->sh_addralign ?: 1); - info->stroffs = mod->core_size = info->symoffs + ndst * sizeof(Elf_Sym); - mod->core_size += strtab_size; - mod->core_size = debug_align(mod->core_size); + info->symoffs = ALIGN(mod->core_layout.size, symsect->sh_addralign ?: 1); + info->stroffs = mod->core_layout.size = info->symoffs + ndst * sizeof(Elf_Sym); + mod->core_layout.size += strtab_size; + mod->core_layout.size = debug_align(mod->core_layout.size); /* Put string table section at end of init part of module. */ strsect->sh_flags |= SHF_ALLOC; - strsect->sh_entsize = get_offset(mod, &mod->init_size, strsect, + strsect->sh_entsize = get_offset(mod, &mod->init_layout.size, strsect, info->index.str) | INIT_OFFSET_MASK; - mod->init_size = debug_align(mod->init_size); + mod->init_layout.size = debug_align(mod->init_layout.size); pr_debug("\t%s\n", info->secstrings + strsect->sh_name); } @@ -2513,12 +2501,13 @@ static void add_kallsyms(struct module *mod, const struct load_info *info) for (i = 0; i < mod->num_symtab; i++) mod->symtab[i].st_info = elf_type(&mod->symtab[i], info); - mod->core_symtab = dst = mod->module_core + info->symoffs; - mod->core_strtab = s = mod->module_core + info->stroffs; + mod->core_symtab = dst = mod->core_layout.base + info->symoffs; + mod->core_strtab = s = mod->core_layout.base + info->stroffs; src = mod->symtab; for (ndst = i = 0; i < mod->num_symtab; i++) { if (i == 0 || - is_core_symbol(src+i, info->sechdrs, info->hdr->e_shnum)) { + is_core_symbol(src+i, info->sechdrs, info->hdr->e_shnum, + info->index.pcpu)) { dst[ndst] = src[i]; dst[ndst++].st_name = s - mod->core_strtab; s += strlcpy(s, &mod->strtab[src[i].st_name], @@ -2964,7 +2953,7 @@ static int move_module(struct module *mod, struct load_info *info) void *ptr; /* Do the allocs. */ - ptr = module_alloc(mod->core_size); + ptr = module_alloc(mod->core_layout.size); /* * The pointer to this block is stored in the module structure * which is inside the block. Just mark it as not being a @@ -2974,11 +2963,11 @@ static int move_module(struct module *mod, struct load_info *info) if (!ptr) return -ENOMEM; - memset(ptr, 0, mod->core_size); - mod->module_core = ptr; + memset(ptr, 0, mod->core_layout.size); + mod->core_layout.base = ptr; - if (mod->init_size) { - ptr = module_alloc(mod->init_size); + if (mod->init_layout.size) { + ptr = module_alloc(mod->init_layout.size); /* * The pointer to this block is stored in the module structure * which is inside the block. This block doesn't need to be @@ -2987,13 +2976,13 @@ static int move_module(struct module *mod, struct load_info *info) */ kmemleak_ignore(ptr); if (!ptr) { - module_memfree(mod->module_core); + module_memfree(mod->core_layout.base); return -ENOMEM; } - memset(ptr, 0, mod->init_size); - mod->module_init = ptr; + memset(ptr, 0, mod->init_layout.size); + mod->init_layout.base = ptr; } else - mod->module_init = NULL; + mod->init_layout.base = NULL; /* Transfer each section which specifies SHF_ALLOC */ pr_debug("final section addresses:\n"); @@ -3005,10 +2994,10 @@ static int move_module(struct module *mod, struct load_info *info) continue; if (shdr->sh_entsize & INIT_OFFSET_MASK) - dest = mod->module_init + dest = mod->init_layout.base + (shdr->sh_entsize & ~INIT_OFFSET_MASK); else - dest = mod->module_core + shdr->sh_entsize; + dest = mod->core_layout.base + shdr->sh_entsize; if (shdr->sh_type != SHT_NOBITS) memcpy(dest, (void *)shdr->sh_addr, shdr->sh_size); @@ -3070,12 +3059,12 @@ static void flush_module_icache(const struct module *mod) * Do it before processing of module parameters, so the module * can provide parameter accessor functions of its own. */ - if (mod->module_init) - flush_icache_range((unsigned long)mod->module_init, - (unsigned long)mod->module_init - + mod->init_size); - flush_icache_range((unsigned long)mod->module_core, - (unsigned long)mod->module_core + mod->core_size); + if (mod->init_layout.base) + flush_icache_range((unsigned long)mod->init_layout.base, + (unsigned long)mod->init_layout.base + + mod->init_layout.size); + flush_icache_range((unsigned long)mod->core_layout.base, + (unsigned long)mod->core_layout.base + mod->core_layout.size); set_fs(old_fs); } @@ -3133,8 +3122,8 @@ static void module_deallocate(struct module *mod, struct load_info *info) { percpu_modfree(mod); module_arch_freeing_init(mod); - module_memfree(mod->module_init); - module_memfree(mod->module_core); + module_memfree(mod->init_layout.base); + module_memfree(mod->core_layout.base); } int __weak module_finalize(const Elf_Ehdr *hdr, @@ -3221,7 +3210,7 @@ static noinline int do_init_module(struct module *mod) ret = -ENOMEM; goto fail; } - freeinit->module_init = mod->module_init; + freeinit->module_init = mod->init_layout.base; /* * We want to find out whether @mod uses async during init. Clear @@ -3279,12 +3268,12 @@ static noinline int do_init_module(struct module *mod) mod->strtab = mod->core_strtab; #endif mod_tree_remove_init(mod); - unset_module_init_ro_nx(mod); + disable_ro_nx(&mod->init_layout); module_arch_freeing_init(mod); - mod->module_init = NULL; - mod->init_size = 0; - mod->init_ro_size = 0; - mod->init_text_size = 0; + mod->init_layout.base = NULL; + mod->init_layout.size = 0; + mod->init_layout.ro_size = 0; + mod->init_layout.text_size = 0; /* * We want to free module_init, but be aware that kallsyms may be * walking this with preempt disabled. In all the failure paths, we @@ -3373,17 +3362,9 @@ static int complete_formation(struct module *mod, struct load_info *info) /* This relies on module_mutex for list integrity. */ module_bug_finalize(info->hdr, info->sechdrs, mod); - /* Set RO and NX regions for core */ - set_section_ro_nx(mod->module_core, - mod->core_text_size, - mod->core_ro_size, - mod->core_size); - - /* Set RO and NX regions for init */ - set_section_ro_nx(mod->module_init, - mod->init_text_size, - mod->init_ro_size, - mod->init_size); + /* Set RO and NX regions */ + module_enable_ro(mod); + module_enable_nx(mod); /* Mark state as coming so strong_try_module_get() ignores us, * but kallsyms etc. can see us. */ @@ -3548,8 +3529,8 @@ static int load_module(struct load_info *info, const char __user *uargs, MODULE_STATE_GOING, mod); /* we can't deallocate the module until we clear memory protection */ - unset_module_init_ro_nx(mod); - unset_module_core_ro_nx(mod); + module_disable_ro(mod); + module_disable_nx(mod); ddebug_cleanup: dynamic_debug_remove(info->debug); @@ -3578,7 +3559,7 @@ static int load_module(struct load_info *info, const char __user *uargs, */ ftrace_release_mod(mod); /* Free lock-classes; relies on the preceding sync_rcu() */ - lockdep_free_key_range(mod->module_core, mod->core_size); + lockdep_free_key_range(mod->core_layout.base, mod->core_layout.size); module_deallocate(mod, info); free_copy: @@ -3656,9 +3637,9 @@ static const char *get_ksymbol(struct module *mod, /* At worse, next value is at end of module */ if (within_module_init(addr, mod)) - nextval = (unsigned long)mod->module_init+mod->init_text_size; + nextval = (unsigned long)mod->init_layout.base+mod->init_layout.text_size; else - nextval = (unsigned long)mod->module_core+mod->core_text_size; + nextval = (unsigned long)mod->core_layout.base+mod->core_layout.text_size; /* Scan for closest preceding symbol, and next symbol. (ELF starts real symbols at 1). */ @@ -3905,7 +3886,7 @@ static int m_show(struct seq_file *m, void *p) return 0; seq_printf(m, "%s %u", - mod->name, mod->init_size + mod->core_size); + mod->name, mod->init_layout.size + mod->core_layout.size); print_unload_info(m, mod); /* Informative for users. */ @@ -3914,7 +3895,7 @@ static int m_show(struct seq_file *m, void *p) mod->state == MODULE_STATE_COMING ? "Loading" : "Live"); /* Used by oprofile and other similar tools. */ - seq_printf(m, " 0x%pK", mod->module_core); + seq_printf(m, " 0x%pK", mod->core_layout.base); /* Taints info */ if (mod->taints) @@ -4057,8 +4038,8 @@ struct module *__module_text_address(unsigned long addr) struct module *mod = __module_address(addr); if (mod) { /* Make sure it's within the text section. */ - if (!within(addr, mod->module_init, mod->init_text_size) - && !within(addr, mod->module_core, mod->core_text_size)) + if (!within(addr, mod->init_layout.base, mod->init_layout.text_size) + && !within(addr, mod->core_layout.base, mod->core_layout.text_size)) mod = NULL; } return mod; diff --git a/kernel/pid.c b/kernel/pid.c index 78b3d9f80d44..f4ad91b746f1 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -604,5 +604,5 @@ void __init pidmap_init(void) atomic_dec(&init_pid_ns.pidmap[0].nr_free); init_pid_ns.pid_cachep = KMEM_CACHE(pid, - SLAB_HWCACHE_ALIGN | SLAB_PANIC); + SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT); } diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 4a2ef5a02fd3..2489140a7c51 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -219,6 +219,7 @@ static void cpu_idle_loop(void) */ __current_set_polling(); + quiet_vmstat(); tick_nohz_idle_enter(); while (!need_resched()) { diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 5faf89ac9ec0..c810f8afdb7f 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1568,6 +1568,28 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, +#ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS + { + .procname = "mmap_rnd_bits", + .data = &mmap_rnd_bits, + .maxlen = sizeof(mmap_rnd_bits), + .mode = 0600, + .proc_handler = proc_dointvec_minmax, + .extra1 = (void *)&mmap_rnd_bits_min, + .extra2 = (void *)&mmap_rnd_bits_max, + }, +#endif +#ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS + { + .procname = "mmap_rnd_compat_bits", + .data = &mmap_rnd_compat_bits, + .maxlen = sizeof(mmap_rnd_compat_bits), + .mode = 0600, + .proc_handler = proc_dointvec_minmax, + .extra1 = (void *)&mmap_rnd_compat_bits_min, + .extra2 = (void *)&mmap_rnd_compat_bits_max, + }, +#endif { } }; diff --git a/lib/Kconfig b/lib/Kconfig index f0df318104e7..5a0c1c83cdf0 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -512,9 +512,9 @@ source "lib/fonts/Kconfig" config SG_SPLIT def_bool n help - Provides a heler to split scatterlists into chunks, each chunk being a - scatterlist. This should be selected by a driver or an API which - whishes to split a scatterlist amongst multiple DMA channel. + Provides a helper to split scatterlists into chunks, each chunk being + a scatterlist. This should be selected by a driver or an API which + whishes to split a scatterlist amongst multiple DMA channels. # # sg chaining option diff --git a/lib/dma-debug.c b/lib/dma-debug.c index d34bd24c2c84..4a1515f4b452 100644 --- a/lib/dma-debug.c +++ b/lib/dma-debug.c @@ -1181,7 +1181,7 @@ static inline bool overlap(void *addr, unsigned long len, void *start, void *end static void check_for_illegal_area(struct device *dev, void *addr, unsigned long len) { - if (overlap(addr, len, _text, _etext) || + if (overlap(addr, len, _stext, _etext) || overlap(addr, len, __start_rodata, __end_rodata)) err_printk(dev, NULL, "DMA-API: device driver maps memory from kernel text or rodata [addr=%p] [len=%lu]\n", addr, len); } diff --git a/lib/genalloc.c b/lib/genalloc.c index 116a166b096f..0a1139644d32 100644 --- a/lib/genalloc.c +++ b/lib/genalloc.c @@ -270,6 +270,25 @@ EXPORT_SYMBOL(gen_pool_destroy); */ unsigned long gen_pool_alloc(struct gen_pool *pool, size_t size) { + return gen_pool_alloc_algo(pool, size, pool->algo, pool->data); +} +EXPORT_SYMBOL(gen_pool_alloc); + +/** + * gen_pool_alloc_algo - allocate special memory from the pool + * @pool: pool to allocate from + * @size: number of bytes to allocate from the pool + * @algo: algorithm passed from caller + * @data: data passed to algorithm + * + * Allocate the requested number of bytes from the specified pool. + * Uses the pool allocation function (with first-fit algorithm by default). + * Can not be used in NMI handler on architectures without + * NMI-safe cmpxchg implementation. + */ +unsigned long gen_pool_alloc_algo(struct gen_pool *pool, size_t size, + genpool_algo_t algo, void *data) +{ struct gen_pool_chunk *chunk; unsigned long addr = 0; int order = pool->min_alloc_order; @@ -290,8 +309,8 @@ unsigned long gen_pool_alloc(struct gen_pool *pool, size_t size) end_bit = chunk_size(chunk) >> order; retry: - start_bit = pool->algo(chunk->bits, end_bit, start_bit, nbits, - pool->data); + start_bit = algo(chunk->bits, end_bit, start_bit, + nbits, data, pool); if (start_bit >= end_bit) continue; remain = bitmap_set_ll(chunk->bits, start_bit, nbits); @@ -310,7 +329,7 @@ retry: rcu_read_unlock(); return addr; } -EXPORT_SYMBOL(gen_pool_alloc); +EXPORT_SYMBOL(gen_pool_alloc_algo); /** * gen_pool_dma_alloc - allocate special memory from the pool for DMA usage @@ -501,15 +520,74 @@ EXPORT_SYMBOL(gen_pool_set_algo); * @start: The bitnumber to start searching at * @nr: The number of zeroed bits we're looking for * @data: additional data - unused + * @pool: pool to find the fit region memory from */ unsigned long gen_pool_first_fit(unsigned long *map, unsigned long size, - unsigned long start, unsigned int nr, void *data) + unsigned long start, unsigned int nr, void *data, + struct gen_pool *pool) { return bitmap_find_next_zero_area(map, size, start, nr, 0); } EXPORT_SYMBOL(gen_pool_first_fit); /** + * gen_pool_first_fit_align - find the first available region + * of memory matching the size requirement (alignment constraint) + * @map: The address to base the search on + * @size: The bitmap size in bits + * @start: The bitnumber to start searching at + * @nr: The number of zeroed bits we're looking for + * @data: data for alignment + * @pool: pool to get order from + */ +unsigned long gen_pool_first_fit_align(unsigned long *map, unsigned long size, + unsigned long start, unsigned int nr, void *data, + struct gen_pool *pool) +{ + struct genpool_data_align *alignment; + unsigned long align_mask; + int order; + + alignment = data; + order = pool->min_alloc_order; + align_mask = ((alignment->align + (1UL << order) - 1) >> order) - 1; + return bitmap_find_next_zero_area(map, size, start, nr, align_mask); +} +EXPORT_SYMBOL(gen_pool_first_fit_align); + +/** + * gen_pool_fixed_alloc - reserve a specific region + * @map: The address to base the search on + * @size: The bitmap size in bits + * @start: The bitnumber to start searching at + * @nr: The number of zeroed bits we're looking for + * @data: data for alignment + * @pool: pool to get order from + */ +unsigned long gen_pool_fixed_alloc(unsigned long *map, unsigned long size, + unsigned long start, unsigned int nr, void *data, + struct gen_pool *pool) +{ + struct genpool_data_fixed *fixed_data; + int order; + unsigned long offset_bit; + unsigned long start_bit; + + fixed_data = data; + order = pool->min_alloc_order; + offset_bit = fixed_data->offset >> order; + if (WARN_ON(fixed_data->offset & ((1UL << order) - 1))) + return size; + + start_bit = bitmap_find_next_zero_area(map, size, + start + offset_bit, nr, 0); + if (start_bit != offset_bit) + start_bit = size; + return start_bit; +} +EXPORT_SYMBOL(gen_pool_fixed_alloc); + +/** * gen_pool_first_fit_order_align - find the first available region * of memory matching the size requirement. The region will be aligned * to the order of the size specified. @@ -518,10 +596,11 @@ EXPORT_SYMBOL(gen_pool_first_fit); * @start: The bitnumber to start searching at * @nr: The number of zeroed bits we're looking for * @data: additional data - unused + * @pool: pool to find the fit region memory from */ unsigned long gen_pool_first_fit_order_align(unsigned long *map, unsigned long size, unsigned long start, - unsigned int nr, void *data) + unsigned int nr, void *data, struct gen_pool *pool) { unsigned long align_mask = roundup_pow_of_two(nr) - 1; @@ -537,12 +616,14 @@ EXPORT_SYMBOL(gen_pool_first_fit_order_align); * @start: The bitnumber to start searching at * @nr: The number of zeroed bits we're looking for * @data: additional data - unused + * @pool: pool to find the fit region memory from * * Iterate over the bitmap to find the smallest free region * which we can allocate the memory. */ unsigned long gen_pool_best_fit(unsigned long *map, unsigned long size, - unsigned long start, unsigned int nr, void *data) + unsigned long start, unsigned int nr, void *data, + struct gen_pool *pool) { unsigned long start_bit = size; unsigned long len = size + 1; diff --git a/lib/raid6/altivec.uc b/lib/raid6/altivec.uc index bec27fce7501..682aae8a1fef 100644 --- a/lib/raid6/altivec.uc +++ b/lib/raid6/altivec.uc @@ -101,6 +101,7 @@ static void raid6_altivec$#_gen_syndrome(int disks, size_t bytes, void **ptrs) raid6_altivec$#_gen_syndrome_real(disks, bytes, ptrs); + disable_kernel_altivec(); preempt_enable(); } diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 7340353f8aea..cc5d29d2da9b 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -672,7 +672,7 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi) ret = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL); if (!ret) { - bdi->wb.memcg_css = mem_cgroup_root_css; + bdi->wb.memcg_css = &root_mem_cgroup->css; bdi->wb.blkcg_css = blkcg_root_css; } return ret; diff --git a/mm/compaction.c b/mm/compaction.c index de3e1e71cd9f..585de54dbe8c 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1658,14 +1658,15 @@ static void __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc) !compaction_deferred(zone, cc->order)) compact_zone(zone, cc); - if (cc->order > 0) { - if (zone_watermark_ok(zone, cc->order, - low_wmark_pages(zone), 0, 0)) - compaction_defer_reset(zone, cc->order, false); - } - VM_BUG_ON(!list_empty(&cc->freepages)); VM_BUG_ON(!list_empty(&cc->migratepages)); + + if (is_via_compact_memory(cc->order)) + continue; + + if (zone_watermark_ok(zone, cc->order, + low_wmark_pages(zone), 0, 0)) + compaction_defer_reset(zone, cc->order, false); } } @@ -1708,7 +1709,10 @@ static void compact_nodes(void) /* The written value is actually unused, all memory is compacted */ int sysctl_compact_memory; -/* This is the entry point for compacting all nodes via /proc/sys/vm */ +/* + * This is the entry point for compacting all nodes via + * /proc/sys/vm/compact_memory + */ int sysctl_compaction_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { diff --git a/mm/debug.c b/mm/debug.c index 668aa35191ca..5d2072ed8d5e 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -175,7 +175,7 @@ void dump_mm(const struct mm_struct *mm) "mmap_base %lu mmap_legacy_base %lu highest_vm_end %lu\n" "pgd %p mm_users %d mm_count %d nr_ptes %lu nr_pmds %lu map_count %d\n" "hiwater_rss %lx hiwater_vm %lx total_vm %lx locked_vm %lx\n" - "pinned_vm %lx shared_vm %lx exec_vm %lx stack_vm %lx\n" + "pinned_vm %lx data_vm %lx exec_vm %lx stack_vm %lx\n" "start_code %lx end_code %lx start_data %lx end_data %lx\n" "start_brk %lx brk %lx start_stack %lx\n" "arg_start %lx arg_end %lx env_start %lx env_end %lx\n" @@ -209,7 +209,7 @@ void dump_mm(const struct mm_struct *mm) mm_nr_pmds((struct mm_struct *)mm), mm->map_count, mm->hiwater_rss, mm->hiwater_vm, mm->total_vm, mm->locked_vm, - mm->pinned_vm, mm->shared_vm, mm->exec_vm, mm->stack_vm, + mm->pinned_vm, mm->data_vm, mm->exec_vm, mm->stack_vm, mm->start_code, mm->end_code, mm->start_data, mm->end_data, mm->start_brk, mm->brk, mm->start_stack, mm->arg_start, mm->arg_end, mm->env_start, mm->env_end, diff --git a/mm/filemap.c b/mm/filemap.c index 1bb007624b53..ff42d31c891a 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1812,19 +1812,18 @@ EXPORT_SYMBOL(generic_file_read_iter); * This adds the requested page to the page cache if it isn't already there, * and schedules an I/O to read in its contents from disk. */ -static int page_cache_read(struct file *file, pgoff_t offset) +static int page_cache_read(struct file *file, pgoff_t offset, gfp_t gfp_mask) { struct address_space *mapping = file->f_mapping; struct page *page; int ret; do { - page = page_cache_alloc_cold(mapping); + page = __page_cache_alloc(gfp_mask|__GFP_COLD); if (!page) return -ENOMEM; - ret = add_to_page_cache_lru(page, mapping, offset, - mapping_gfp_constraint(mapping, GFP_KERNEL)); + ret = add_to_page_cache_lru(page, mapping, offset, gfp_mask & GFP_KERNEL); if (ret == 0) ret = mapping->a_ops->readpage(file, page); else if (ret == -EEXIST) @@ -2005,7 +2004,7 @@ no_cached_page: * We're only likely to ever get here if MADV_RANDOM is in * effect. */ - error = page_cache_read(file, offset); + error = page_cache_read(file, offset, vmf->gfp_mask); /* * The page we want has now been added to the page cache. diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 62fe06bb7d04..f952f055fdcf 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -31,6 +31,33 @@ #include <asm/pgalloc.h> #include "internal.h" +enum scan_result { + SCAN_FAIL, + SCAN_SUCCEED, + SCAN_PMD_NULL, + SCAN_EXCEED_NONE_PTE, + SCAN_PTE_NON_PRESENT, + SCAN_PAGE_RO, + SCAN_NO_REFERENCED_PAGE, + SCAN_PAGE_NULL, + SCAN_SCAN_ABORT, + SCAN_PAGE_COUNT, + SCAN_PAGE_LRU, + SCAN_PAGE_LOCK, + SCAN_PAGE_ANON, + SCAN_ANY_PROCESS, + SCAN_VMA_NULL, + SCAN_VMA_CHECK, + SCAN_ADDRESS_RANGE, + SCAN_SWAP_CACHE_PAGE, + SCAN_DEL_PAGE_LRU, + SCAN_ALLOC_HUGE_PAGE_FAIL, + SCAN_CGROUP_CHARGE_FAIL +}; + +#define CREATE_TRACE_POINTS +#include <trace/events/huge_memory.h> + /* * By default transparent hugepage support is disabled in order that avoid * to risk increase the memory footprint of applications without a guaranteed @@ -2198,26 +2225,33 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, unsigned long address, pte_t *pte) { - struct page *page; + struct page *page = NULL; pte_t *_pte; - int none_or_zero = 0; + int none_or_zero = 0, result = 0; bool referenced = false, writable = false; + for (_pte = pte; _pte < pte+HPAGE_PMD_NR; _pte++, address += PAGE_SIZE) { pte_t pteval = *_pte; if (pte_none(pteval) || (pte_present(pteval) && is_zero_pfn(pte_pfn(pteval)))) { if (!userfaultfd_armed(vma) && - ++none_or_zero <= khugepaged_max_ptes_none) + ++none_or_zero <= khugepaged_max_ptes_none) { continue; - else + } else { + result = SCAN_EXCEED_NONE_PTE; goto out; + } } - if (!pte_present(pteval)) + if (!pte_present(pteval)) { + result = SCAN_PTE_NON_PRESENT; goto out; + } page = vm_normal_page(vma, address, pteval); - if (unlikely(!page)) + if (unlikely(!page)) { + result = SCAN_PAGE_NULL; goto out; + } VM_BUG_ON_PAGE(PageCompound(page), page); VM_BUG_ON_PAGE(!PageAnon(page), page); @@ -2229,8 +2263,10 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, * is needed to serialize against split_huge_page * when invoked from the VM. */ - if (!trylock_page(page)) + if (!trylock_page(page)) { + result = SCAN_PAGE_LOCK; goto out; + } /* * cannot use mapcount: can't collapse if there's a gup pin. @@ -2239,6 +2275,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, */ if (page_count(page) != 1 + !!PageSwapCache(page)) { unlock_page(page); + result = SCAN_PAGE_COUNT; goto out; } if (pte_write(pteval)) { @@ -2246,6 +2283,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, } else { if (PageSwapCache(page) && !reuse_swap_page(page)) { unlock_page(page); + result = SCAN_SWAP_CACHE_PAGE; goto out; } /* @@ -2260,6 +2298,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, */ if (isolate_lru_page(page)) { unlock_page(page); + result = SCAN_DEL_PAGE_LRU; goto out; } /* 0 stands for page_is_file_cache(page) == false */ @@ -2273,10 +2312,21 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, mmu_notifier_test_young(vma->vm_mm, address)) referenced = true; } - if (likely(referenced && writable)) - return 1; + if (likely(writable)) { + if (likely(referenced)) { + result = SCAN_SUCCEED; + trace_mm_collapse_huge_page_isolate(page_to_pfn(page), none_or_zero, + referenced, writable, result); + return 1; + } + } else { + result = SCAN_PAGE_RO; + } + out: release_pte_pages(pte, _pte); + trace_mm_collapse_huge_page_isolate(page_to_pfn(page), none_or_zero, + referenced, writable, result); return 0; } @@ -2513,7 +2563,7 @@ static void collapse_huge_page(struct mm_struct *mm, pgtable_t pgtable; struct page *new_page; spinlock_t *pmd_ptl, *pte_ptl; - int isolated; + int isolated, result = 0; unsigned long hstart, hend; struct mem_cgroup *memcg; unsigned long mmun_start; /* For mmu_notifiers */ @@ -2528,12 +2578,15 @@ static void collapse_huge_page(struct mm_struct *mm, /* release the mmap_sem read lock. */ new_page = khugepaged_alloc_page(hpage, gfp, mm, address, node); - if (!new_page) - return; + if (!new_page) { + result = SCAN_ALLOC_HUGE_PAGE_FAIL; + goto out_nolock; + } - if (unlikely(mem_cgroup_try_charge(new_page, mm, - gfp, &memcg))) - return; + if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg))) { + result = SCAN_CGROUP_CHARGE_FAIL; + goto out_nolock; + } /* * Prevent all access to pagetables with the exception of @@ -2541,21 +2594,31 @@ static void collapse_huge_page(struct mm_struct *mm, * handled by the anon_vma lock + PG_lock. */ down_write(&mm->mmap_sem); - if (unlikely(khugepaged_test_exit(mm))) + if (unlikely(khugepaged_test_exit(mm))) { + result = SCAN_ANY_PROCESS; goto out; + } vma = find_vma(mm, address); - if (!vma) + if (!vma) { + result = SCAN_VMA_NULL; goto out; + } hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; hend = vma->vm_end & HPAGE_PMD_MASK; - if (address < hstart || address + HPAGE_PMD_SIZE > hend) + if (address < hstart || address + HPAGE_PMD_SIZE > hend) { + result = SCAN_ADDRESS_RANGE; goto out; - if (!hugepage_vma_check(vma)) + } + if (!hugepage_vma_check(vma)) { + result = SCAN_VMA_CHECK; goto out; + } pmd = mm_find_pmd(mm, address); - if (!pmd) + if (!pmd) { + result = SCAN_PMD_NULL; goto out; + } anon_vma_lock_write(vma->anon_vma); @@ -2592,6 +2655,7 @@ static void collapse_huge_page(struct mm_struct *mm, pmd_populate(mm, pmd, pmd_pgtable(_pmd)); spin_unlock(pmd_ptl); anon_vma_unlock_write(vma->anon_vma); + result = SCAN_FAIL; goto out; } @@ -2629,10 +2693,15 @@ static void collapse_huge_page(struct mm_struct *mm, *hpage = NULL; khugepaged_pages_collapsed++; + result = SCAN_SUCCEED; out_up_write: up_write(&mm->mmap_sem); + trace_mm_collapse_huge_page(mm, isolated, result); return; +out_nolock: + trace_mm_collapse_huge_page(mm, isolated, result); + return; out: mem_cgroup_cancel_charge(new_page, memcg); goto out_up_write; @@ -2645,8 +2714,8 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, { pmd_t *pmd; pte_t *pte, *_pte; - int ret = 0, none_or_zero = 0; - struct page *page; + int ret = 0, none_or_zero = 0, result = 0; + struct page *page = NULL; unsigned long _address; spinlock_t *ptl; int node = NUMA_NO_NODE; @@ -2655,8 +2724,10 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, VM_BUG_ON(address & ~HPAGE_PMD_MASK); pmd = mm_find_pmd(mm, address); - if (!pmd) + if (!pmd) { + result = SCAN_PMD_NULL; goto out; + } memset(khugepaged_node_load, 0, sizeof(khugepaged_node_load)); pte = pte_offset_map_lock(mm, pmd, address, &ptl); @@ -2665,19 +2736,25 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, pte_t pteval = *_pte; if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { if (!userfaultfd_armed(vma) && - ++none_or_zero <= khugepaged_max_ptes_none) + ++none_or_zero <= khugepaged_max_ptes_none) { continue; - else + } else { + result = SCAN_EXCEED_NONE_PTE; goto out_unmap; + } } - if (!pte_present(pteval)) + if (!pte_present(pteval)) { + result = SCAN_PTE_NON_PRESENT; goto out_unmap; + } if (pte_write(pteval)) writable = true; page = vm_normal_page(vma, _address, pteval); - if (unlikely(!page)) + if (unlikely(!page)) { + result = SCAN_PAGE_NULL; goto out_unmap; + } /* * Record which node the original page is from and save this * information to khugepaged_node_load[]. @@ -2685,26 +2762,49 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, * hit record. */ node = page_to_nid(page); - if (khugepaged_scan_abort(node)) + if (khugepaged_scan_abort(node)) { + result = SCAN_SCAN_ABORT; goto out_unmap; + } khugepaged_node_load[node]++; VM_BUG_ON_PAGE(PageCompound(page), page); - if (!PageLRU(page) || PageLocked(page) || !PageAnon(page)) + if (!PageLRU(page)) { + result = SCAN_SCAN_ABORT; + goto out_unmap; + } + if (PageLocked(page)) { + result = SCAN_PAGE_LOCK; + goto out_unmap; + } + if (!PageAnon(page)) { + result = SCAN_PAGE_ANON; goto out_unmap; + } + /* * cannot use mapcount: can't collapse if there's a gup pin. * The page must only be referenced by the scanned process * and page swap cache. */ - if (page_count(page) != 1 + !!PageSwapCache(page)) + if (page_count(page) != 1 + !!PageSwapCache(page)) { + result = SCAN_PAGE_COUNT; goto out_unmap; + } if (pte_young(pteval) || page_is_young(page) || PageReferenced(page) || mmu_notifier_test_young(vma->vm_mm, address)) referenced = true; } - if (referenced && writable) - ret = 1; + if (writable) { + if (referenced) { + result = SCAN_SUCCEED; + ret = 1; + } else { + result = SCAN_NO_REFERENCED_PAGE; + } + } else { + result = SCAN_PAGE_RO; + } out_unmap: pte_unmap_unlock(pte, ptl); if (ret) { @@ -2713,6 +2813,8 @@ out_unmap: collapse_huge_page(mm, address, hpage, vma, node); } out: + trace_mm_khugepaged_scan_pmd(mm, page_to_pfn(page), writable, referenced, + none_or_zero, result); return ret; } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index ef6963b577fd..be934df69b85 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4,7 +4,6 @@ */ #include <linux/list.h> #include <linux/init.h> -#include <linux/module.h> #include <linux/mm.h> #include <linux/seq_file.h> #include <linux/sysctl.h> @@ -2549,25 +2548,6 @@ static void hugetlb_unregister_node(struct node *node) nhs->hugepages_kobj = NULL; } -/* - * hugetlb module exit: unregister hstate attributes from node devices - * that have them. - */ -static void hugetlb_unregister_all_nodes(void) -{ - int nid; - - /* - * disable node device registrations. - */ - register_hugetlbfs_with_node(NULL, NULL); - - /* - * remove hstate attributes from any nodes that have them. - */ - for (nid = 0; nid < nr_node_ids; nid++) - hugetlb_unregister_node(node_devices[nid]); -} /* * Register hstate attributes for a single node device. @@ -2632,27 +2612,10 @@ static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp) return NULL; } -static void hugetlb_unregister_all_nodes(void) { } - static void hugetlb_register_all_nodes(void) { } #endif -static void __exit hugetlb_exit(void) -{ - struct hstate *h; - - hugetlb_unregister_all_nodes(); - - for_each_hstate(h) { - kobject_put(hstate_kobjs[hstate_index(h)]); - } - - kobject_put(hugepages_kobj); - kfree(hugetlb_fault_mutex_table); -} -module_exit(hugetlb_exit); - static int __init hugetlb_init(void) { int i; @@ -2690,7 +2653,7 @@ static int __init hugetlb_init(void) mutex_init(&hugetlb_fault_mutex_table[i]); return 0; } -module_init(hugetlb_init); +subsys_initcall(hugetlb_init); /* Should be called on processing a hugepagesz=... option */ void __init hugetlb_add_hstate(unsigned int order) diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 19423a45d7d7..25c0ad36fe38 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -122,8 +122,7 @@ #define BYTES_PER_POINTER sizeof(void *) /* GFP bitmask for kmemleak internal allocations */ -#define gfp_kmemleak_mask(gfp) (((gfp) & (GFP_KERNEL | GFP_ATOMIC | \ - __GFP_NOACCOUNT)) | \ +#define gfp_kmemleak_mask(gfp) (((gfp) & (GFP_KERNEL | GFP_ATOMIC)) | \ __GFP_NORETRY | __GFP_NOMEMALLOC | \ __GFP_NOWARN) @@ -740,8 +740,7 @@ static int remove_stable_node(struct stable_node *stable_node) static int remove_all_stable_nodes(void) { - struct stable_node *stable_node; - struct list_head *this, *next; + struct stable_node *stable_node, *next; int nid; int err = 0; @@ -756,8 +755,7 @@ static int remove_all_stable_nodes(void) cond_resched(); } } - list_for_each_safe(this, next, &migrate_nodes) { - stable_node = list_entry(this, struct stable_node, list); + list_for_each_entry_safe(stable_node, next, &migrate_nodes, list) { if (remove_stable_node(stable_node)) err = -EBUSY; cond_resched(); @@ -1583,13 +1581,11 @@ static struct rmap_item *scan_get_next_rmap_item(struct page **page) * so prune them once before each full scan. */ if (!ksm_merge_across_nodes) { - struct stable_node *stable_node; - struct list_head *this, *next; + struct stable_node *stable_node, *next; struct page *page; - list_for_each_safe(this, next, &migrate_nodes) { - stable_node = list_entry(this, - struct stable_node, list); + list_for_each_entry_safe(stable_node, next, + &migrate_nodes, list) { page = get_ksm_page(stable_node, false); if (page) put_page(page); @@ -2012,8 +2008,7 @@ static void wait_while_offlining(void) static void ksm_check_stable_tree(unsigned long start_pfn, unsigned long end_pfn) { - struct stable_node *stable_node; - struct list_head *this, *next; + struct stable_node *stable_node, *next; struct rb_node *node; int nid; @@ -2034,8 +2029,7 @@ static void ksm_check_stable_tree(unsigned long start_pfn, cond_resched(); } } - list_for_each_safe(this, next, &migrate_nodes) { - stable_node = list_entry(this, struct stable_node, list); + list_for_each_entry_safe(stable_node, next, &migrate_nodes, list) { if (stable_node->kpfn >= start_pfn && stable_node->kpfn < end_pfn) remove_node_from_stable_tree(stable_node); diff --git a/mm/memblock.c b/mm/memblock.c index 07ff069fef25..d2ed81e59a94 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -96,13 +96,10 @@ bool __init_memblock memblock_overlaps_region(struct memblock_type *type, { unsigned long i; - for (i = 0; i < type->cnt; i++) { - phys_addr_t rgnbase = type->regions[i].base; - phys_addr_t rgnsize = type->regions[i].size; - if (memblock_addrs_overlap(base, size, rgnbase, rgnsize)) + for (i = 0; i < type->cnt; i++) + if (memblock_addrs_overlap(base, size, type->regions[i].base, + type->regions[i].size)) break; - } - return i < type->cnt; } @@ -528,7 +525,8 @@ int __init_memblock memblock_add_range(struct memblock_type *type, bool insert = false; phys_addr_t obase = base; phys_addr_t end = base + memblock_cap_size(base, &size); - int i, nr_new; + int idx, nr_new; + struct memblock_region *rgn; if (!size) return 0; @@ -552,8 +550,7 @@ repeat: base = obase; nr_new = 0; - for (i = 0; i < type->cnt; i++) { - struct memblock_region *rgn = &type->regions[i]; + for_each_memblock_type(type, rgn) { phys_addr_t rbase = rgn->base; phys_addr_t rend = rbase + rgn->size; @@ -572,7 +569,7 @@ repeat: WARN_ON(flags != rgn->flags); nr_new++; if (insert) - memblock_insert_region(type, i++, base, + memblock_insert_region(type, idx++, base, rbase - base, nid, flags); } @@ -584,7 +581,7 @@ repeat: if (base < end) { nr_new++; if (insert) - memblock_insert_region(type, i, base, end - base, + memblock_insert_region(type, idx, base, end - base, nid, flags); } @@ -651,7 +648,8 @@ static int __init_memblock memblock_isolate_range(struct memblock_type *type, int *start_rgn, int *end_rgn) { phys_addr_t end = base + memblock_cap_size(base, &size); - int i; + int idx; + struct memblock_region *rgn; *start_rgn = *end_rgn = 0; @@ -663,8 +661,7 @@ static int __init_memblock memblock_isolate_range(struct memblock_type *type, if (memblock_double_array(type, base, size) < 0) return -ENOMEM; - for (i = 0; i < type->cnt; i++) { - struct memblock_region *rgn = &type->regions[i]; + for_each_memblock_type(type, rgn) { phys_addr_t rbase = rgn->base; phys_addr_t rend = rbase + rgn->size; @@ -681,7 +678,7 @@ static int __init_memblock memblock_isolate_range(struct memblock_type *type, rgn->base = base; rgn->size -= base - rbase; type->total_size -= base - rbase; - memblock_insert_region(type, i, rbase, base - rbase, + memblock_insert_region(type, idx, rbase, base - rbase, memblock_get_region_node(rgn), rgn->flags); } else if (rend > end) { @@ -692,14 +689,14 @@ static int __init_memblock memblock_isolate_range(struct memblock_type *type, rgn->base = end; rgn->size -= end - rbase; type->total_size -= end - rbase; - memblock_insert_region(type, i--, rbase, end - rbase, + memblock_insert_region(type, idx--, rbase, end - rbase, memblock_get_region_node(rgn), rgn->flags); } else { /* @rgn is fully contained, record it */ if (!*end_rgn) - *start_rgn = i; - *end_rgn = i + 1; + *start_rgn = idx; + *end_rgn = idx + 1; } } @@ -1528,12 +1525,12 @@ static int __init_memblock memblock_search(struct memblock_type *type, phys_addr return -1; } -int __init memblock_is_reserved(phys_addr_t addr) +bool __init memblock_is_reserved(phys_addr_t addr) { return memblock_search(&memblock.reserved, addr) != -1; } -int __init_memblock memblock_is_memory(phys_addr_t addr) +bool __init_memblock memblock_is_memory(phys_addr_t addr) { return memblock_search(&memblock.memory, addr) != -1; } @@ -1641,12 +1638,12 @@ static void __init_memblock memblock_dump(struct memblock_type *type, char *name { unsigned long long base, size; unsigned long flags; - int i; + int idx; + struct memblock_region *rgn; pr_info(" %s.cnt = 0x%lx\n", name, type->cnt); - for (i = 0; i < type->cnt; i++) { - struct memblock_region *rgn = &type->regions[i]; + for_each_memblock_type(type, rgn) { char nid_buf[32] = ""; base = rgn->base; @@ -1658,7 +1655,7 @@ static void __init_memblock memblock_dump(struct memblock_type *type, char *name memblock_get_region_node(rgn)); #endif pr_info(" %s[%#x]\t[%#016llx-%#016llx], %#llx bytes%s flags: %#lx\n", - name, i, base, base + size - 1, size, nid_buf, flags); + name, idx, base, base + size - 1, size, nid_buf, flags); } } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 14cb1db4c52b..54eae4f19d80 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -76,9 +76,12 @@ struct cgroup_subsys memory_cgrp_subsys __read_mostly; EXPORT_SYMBOL(memory_cgrp_subsys); +struct mem_cgroup *root_mem_cgroup __read_mostly; + #define MEM_CGROUP_RECLAIM_RETRIES 5 -static struct mem_cgroup *root_mem_cgroup __read_mostly; -struct cgroup_subsys_state *mem_cgroup_root_css __read_mostly; + +/* Socket memory accounting disabled? */ +static bool cgroup_memory_nosocket; /* Whether the swap controller is active */ #ifdef CONFIG_MEMCG_SWAP @@ -87,6 +90,12 @@ int do_swap_account __read_mostly; #define do_swap_account 0 #endif +/* Whether legacy memory+swap accounting is active */ +static bool do_memsw_account(void) +{ + return !cgroup_subsys_on_dfl(memory_cgrp_subsys) && do_swap_account; +} + static const char * const mem_cgroup_stat_names[] = { "cache", "rss", @@ -288,64 +297,6 @@ static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id) return mem_cgroup_from_css(css); } -/* Writing them here to avoid exposing memcg's inner layout */ -#if defined(CONFIG_INET) && defined(CONFIG_MEMCG_KMEM) - -void sock_update_memcg(struct sock *sk) -{ - if (mem_cgroup_sockets_enabled) { - struct mem_cgroup *memcg; - struct cg_proto *cg_proto; - - BUG_ON(!sk->sk_prot->proto_cgroup); - - /* Socket cloning can throw us here with sk_cgrp already - * filled. It won't however, necessarily happen from - * process context. So the test for root memcg given - * the current task's memcg won't help us in this case. - * - * Respecting the original socket's memcg is a better - * decision in this case. - */ - if (sk->sk_cgrp) { - BUG_ON(mem_cgroup_is_root(sk->sk_cgrp->memcg)); - css_get(&sk->sk_cgrp->memcg->css); - return; - } - - rcu_read_lock(); - memcg = mem_cgroup_from_task(current); - cg_proto = sk->sk_prot->proto_cgroup(memcg); - if (cg_proto && test_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags) && - css_tryget_online(&memcg->css)) { - sk->sk_cgrp = cg_proto; - } - rcu_read_unlock(); - } -} -EXPORT_SYMBOL(sock_update_memcg); - -void sock_release_memcg(struct sock *sk) -{ - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) { - struct mem_cgroup *memcg; - WARN_ON(!sk->sk_cgrp->memcg); - memcg = sk->sk_cgrp->memcg; - css_put(&sk->sk_cgrp->memcg->css); - } -} - -struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg) -{ - if (!memcg || mem_cgroup_is_root(memcg)) - return NULL; - - return &memcg->tcp_mem; -} -EXPORT_SYMBOL(tcp_proto_cgroup); - -#endif - #ifdef CONFIG_MEMCG_KMEM /* * This will be the memcg's index in each cache's ->memcg_params.memcg_caches. @@ -395,7 +346,7 @@ void memcg_put_cache_ids(void) * conditional to this static branch, we'll have to allow modules that does * kmem_cache_alloc and the such to see this symbol as well */ -struct static_key memcg_kmem_enabled_key; +DEFINE_STATIC_KEY_FALSE(memcg_kmem_enabled_key); EXPORT_SYMBOL(memcg_kmem_enabled_key); #endif /* CONFIG_MEMCG_KMEM */ @@ -1162,9 +1113,6 @@ bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg) return ret; } -#define mem_cgroup_from_counter(counter, member) \ - container_of(counter, struct mem_cgroup, member) - /** * mem_cgroup_margin - calculate chargeable space of a memory cgroup * @memcg: the memory cgroup @@ -1183,7 +1131,7 @@ static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg) if (count < limit) margin = limit - count; - if (do_swap_account) { + if (do_memsw_account()) { count = page_counter_read(&memcg->memsw); limit = READ_ONCE(memcg->memsw.limit); if (count <= limit) @@ -1286,7 +1234,7 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) pr_cont(":"); for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) { - if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account) + if (i == MEM_CGROUP_STAT_SWAP && !do_memsw_account()) continue; pr_cont(" %s:%luKB", mem_cgroup_stat_names[i], K(mem_cgroup_read_stat(iter, i))); @@ -1909,7 +1857,7 @@ static void drain_stock(struct memcg_stock_pcp *stock) if (stock->nr_pages) { page_counter_uncharge(&old->memory, stock->nr_pages); - if (do_swap_account) + if (do_memsw_account()) page_counter_uncharge(&old->memsw, stock->nr_pages); css_put_many(&old->css, stock->nr_pages); stock->nr_pages = 0; @@ -1997,6 +1945,26 @@ static int memcg_cpu_hotplug_callback(struct notifier_block *nb, return NOTIFY_OK; } +static void reclaim_high(struct mem_cgroup *memcg, + unsigned int nr_pages, + gfp_t gfp_mask) +{ + do { + if (page_counter_read(&memcg->memory) <= memcg->high) + continue; + mem_cgroup_events(memcg, MEMCG_HIGH, 1); + try_to_free_mem_cgroup_pages(memcg, nr_pages, gfp_mask, true); + } while ((memcg = parent_mem_cgroup(memcg))); +} + +static void high_work_func(struct work_struct *work) +{ + struct mem_cgroup *memcg; + + memcg = container_of(work, struct mem_cgroup, high_work); + reclaim_high(memcg, CHARGE_BATCH, GFP_KERNEL); +} + /* * Scheduled by try_charge() to be executed from the userland return path * and reclaims memory over the high limit. @@ -2004,20 +1972,13 @@ static int memcg_cpu_hotplug_callback(struct notifier_block *nb, void mem_cgroup_handle_over_high(void) { unsigned int nr_pages = current->memcg_nr_pages_over_high; - struct mem_cgroup *memcg, *pos; + struct mem_cgroup *memcg; if (likely(!nr_pages)) return; - pos = memcg = get_mem_cgroup_from_mm(current->mm); - - do { - if (page_counter_read(&pos->memory) <= pos->high) - continue; - mem_cgroup_events(pos, MEMCG_HIGH, 1); - try_to_free_mem_cgroup_pages(pos, nr_pages, GFP_KERNEL, true); - } while ((pos = parent_mem_cgroup(pos))); - + memcg = get_mem_cgroup_from_mm(current->mm); + reclaim_high(memcg, nr_pages, GFP_KERNEL); css_put(&memcg->css); current->memcg_nr_pages_over_high = 0; } @@ -2039,11 +2000,11 @@ retry: if (consume_stock(memcg, nr_pages)) return 0; - if (!do_swap_account || + if (!do_memsw_account() || page_counter_try_charge(&memcg->memsw, batch, &counter)) { if (page_counter_try_charge(&memcg->memory, batch, &counter)) goto done_restock; - if (do_swap_account) + if (do_memsw_account()) page_counter_uncharge(&memcg->memsw, batch); mem_over_limit = mem_cgroup_from_counter(counter, memory); } else { @@ -2130,7 +2091,7 @@ force: * temporarily by force charging it. */ page_counter_charge(&memcg->memory, nr_pages); - if (do_swap_account) + if (do_memsw_account()) page_counter_charge(&memcg->memsw, nr_pages); css_get_many(&memcg->css, nr_pages); @@ -2152,6 +2113,11 @@ done_restock: */ do { if (page_counter_read(&memcg->memory) > memcg->high) { + /* Don't bother a random interrupted task */ + if (in_interrupt()) { + schedule_work(&memcg->high_work); + break; + } current->memcg_nr_pages_over_high += batch; set_notify_resume(current); break; @@ -2167,7 +2133,7 @@ static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages) return; page_counter_uncharge(&memcg->memory, nr_pages); - if (do_swap_account) + if (do_memsw_account()) page_counter_uncharge(&memcg->memsw, nr_pages); css_put_many(&memcg->css, nr_pages); @@ -2356,7 +2322,7 @@ static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg, * Can't be called in interrupt context or from kernel threads. * This function needs to be called with rcu_read_lock() held. */ -struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep) +struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp) { struct mem_cgroup *memcg; struct kmem_cache *memcg_cachep; @@ -2364,6 +2330,12 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep) VM_BUG_ON(!is_root_cache(cachep)); + if (cachep->flags & SLAB_ACCOUNT) + gfp |= __GFP_ACCOUNT; + + if (!(gfp & __GFP_ACCOUNT)) + return cachep; + if (current->memcg_kmem_skip_account) return cachep; @@ -2447,7 +2419,7 @@ void __memcg_kmem_uncharge(struct page *page, int order) page_counter_uncharge(&memcg->kmem, nr_pages); page_counter_uncharge(&memcg->memory, nr_pages); - if (do_swap_account) + if (do_memsw_account()) page_counter_uncharge(&memcg->memsw, nr_pages); page->mem_cgroup = NULL; @@ -2935,7 +2907,7 @@ static int memcg_activate_kmem(struct mem_cgroup *memcg, err = page_counter_limit(&memcg->kmem, nr_pages); VM_BUG_ON(err); - static_key_slow_inc(&memcg_kmem_enabled_key); + static_branch_inc(&memcg_kmem_enabled_key); /* * A memory cgroup is considered kmem-active as soon as it gets * kmemcg_id. Setting the id after enabling static branching will @@ -3162,7 +3134,7 @@ static int memcg_stat_show(struct seq_file *m, void *v) BUILD_BUG_ON(ARRAY_SIZE(mem_cgroup_lru_names) != NR_LRU_LISTS); for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) { - if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account) + if (i == MEM_CGROUP_STAT_SWAP && !do_memsw_account()) continue; seq_printf(m, "%s %lu\n", mem_cgroup_stat_names[i], mem_cgroup_read_stat(memcg, i) * PAGE_SIZE); @@ -3184,14 +3156,14 @@ static int memcg_stat_show(struct seq_file *m, void *v) } seq_printf(m, "hierarchical_memory_limit %llu\n", (u64)memory * PAGE_SIZE); - if (do_swap_account) + if (do_memsw_account()) seq_printf(m, "hierarchical_memsw_limit %llu\n", (u64)memsw * PAGE_SIZE); for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) { unsigned long long val = 0; - if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account) + if (i == MEM_CGROUP_STAT_SWAP && !do_memsw_account()) continue; for_each_mem_cgroup_tree(mi, memcg) val += mem_cgroup_read_stat(mi, i) * PAGE_SIZE; @@ -3322,7 +3294,7 @@ static void mem_cgroup_threshold(struct mem_cgroup *memcg) { while (memcg) { __mem_cgroup_threshold(memcg, false); - if (do_swap_account) + if (do_memsw_account()) __mem_cgroup_threshold(memcg, true); memcg = parent_mem_cgroup(memcg); @@ -3621,7 +3593,7 @@ static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss) if (ret) return ret; - return mem_cgroup_sockets_init(memcg, ss); + return tcp_init_cgroup(memcg, ss); } static void memcg_deactivate_kmem(struct mem_cgroup *memcg) @@ -3674,10 +3646,10 @@ static void memcg_destroy_kmem(struct mem_cgroup *memcg) { if (memcg->kmem_acct_activated) { memcg_destroy_kmem_caches(memcg); - static_key_slow_dec(&memcg_kmem_enabled_key); + static_branch_dec(&memcg_kmem_enabled_key); WARN_ON(page_counter_read(&memcg->kmem)); } - mem_cgroup_sockets_destroy(memcg); + tcp_destroy_cgroup(memcg); } #else static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss) @@ -4196,6 +4168,8 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg) { int node; + cancel_work_sync(&memcg->high_work); + mem_cgroup_remove_from_trees(memcg); for_each_node(node) @@ -4206,17 +4180,6 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg) kfree(memcg); } -/* - * Returns the parent mem_cgroup in memcgroup hierarchy with hierarchy enabled. - */ -struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) -{ - if (!memcg->memory.parent) - return NULL; - return mem_cgroup_from_counter(memcg->memory.parent, memory); -} -EXPORT_SYMBOL(parent_mem_cgroup); - static struct cgroup_subsys_state * __ref mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) { @@ -4235,7 +4198,6 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) /* root ? */ if (parent_css == NULL) { root_mem_cgroup = memcg; - mem_cgroup_root_css = &memcg->css; page_counter_init(&memcg->memory, NULL); memcg->high = PAGE_COUNTER_MAX; memcg->soft_limit = PAGE_COUNTER_MAX; @@ -4243,6 +4205,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) page_counter_init(&memcg->kmem, NULL); } + INIT_WORK(&memcg->high_work, high_work_func); memcg->last_scanned_node = MAX_NUMNODES; INIT_LIST_HEAD(&memcg->oom_notify); memcg->move_charge_at_immigrate = 0; @@ -4257,6 +4220,9 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) #ifdef CONFIG_CGROUP_WRITEBACK INIT_LIST_HEAD(&memcg->cgwb_list); #endif +#ifdef CONFIG_INET + memcg->socket_pressure = jiffies; +#endif return &memcg->css; free_out: @@ -4314,6 +4280,11 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css) if (ret) return ret; +#ifdef CONFIG_INET + if (cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_nosocket) + static_branch_inc(&memcg_sockets_enabled_key); +#endif + /* * Make sure the memcg is initialized: mem_cgroup_iter() * orders reading memcg->initialized against its callers @@ -4360,6 +4331,10 @@ static void mem_cgroup_css_free(struct cgroup_subsys_state *css) struct mem_cgroup *memcg = mem_cgroup_from_css(css); memcg_destroy_kmem(memcg); +#ifdef CONFIG_INET + if (cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_nosocket) + static_branch_dec(&memcg_sockets_enabled_key); +#endif __mem_cgroup_free(memcg); } @@ -4476,7 +4451,7 @@ static struct page *mc_handle_swap_pte(struct vm_area_struct *vma, * we call find_get_page() with swapper_space directly. */ page = find_get_page(swap_address_space(ent), ent.val); - if (do_swap_account) + if (do_memsw_account()) entry->val = ent.val; return page; @@ -4511,7 +4486,7 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma, page = find_get_entry(mapping, pgoff); if (radix_tree_exceptional_entry(page)) { swp_entry_t swp = radix_to_swp_entry(page); - if (do_swap_account) + if (do_memsw_account()) *entry = swp; page = find_get_page(swap_address_space(swp), swp.val); } @@ -5304,7 +5279,7 @@ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, if (page->mem_cgroup) goto out; - if (do_swap_account) { + if (do_memsw_account()) { swp_entry_t ent = { .val = page_private(page), }; unsigned short id = lookup_swap_cgroup_id(ent); @@ -5378,7 +5353,7 @@ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, memcg_check_events(memcg, page); local_irq_enable(); - if (do_swap_account && PageSwapCache(page)) { + if (do_memsw_account() && PageSwapCache(page)) { swp_entry_t entry = { .val = page_private(page) }; /* * The swap entry might not get freed for a long time, @@ -5427,7 +5402,7 @@ static void uncharge_batch(struct mem_cgroup *memcg, unsigned long pgpgout, if (!mem_cgroup_is_root(memcg)) { page_counter_uncharge(&memcg->memory, nr_pages); - if (do_swap_account) + if (do_memsw_account()) page_counter_uncharge(&memcg->memsw, nr_pages); memcg_oom_recover(memcg); } @@ -5580,6 +5555,121 @@ void mem_cgroup_replace_page(struct page *oldpage, struct page *newpage) commit_charge(newpage, memcg, true); } +#ifdef CONFIG_INET + +DEFINE_STATIC_KEY_FALSE(memcg_sockets_enabled_key); +EXPORT_SYMBOL(memcg_sockets_enabled_key); + +void sock_update_memcg(struct sock *sk) +{ + struct mem_cgroup *memcg; + + /* Socket cloning can throw us here with sk_cgrp already + * filled. It won't however, necessarily happen from + * process context. So the test for root memcg given + * the current task's memcg won't help us in this case. + * + * Respecting the original socket's memcg is a better + * decision in this case. + */ + if (sk->sk_memcg) { + BUG_ON(mem_cgroup_is_root(sk->sk_memcg)); + css_get(&sk->sk_memcg->css); + return; + } + + rcu_read_lock(); + memcg = mem_cgroup_from_task(current); + if (memcg == root_mem_cgroup) + goto out; +#ifdef CONFIG_MEMCG_KMEM + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && !memcg->tcp_mem.active) + goto out; +#endif + if (css_tryget_online(&memcg->css)) + sk->sk_memcg = memcg; +out: + rcu_read_unlock(); +} +EXPORT_SYMBOL(sock_update_memcg); + +void sock_release_memcg(struct sock *sk) +{ + WARN_ON(!sk->sk_memcg); + css_put(&sk->sk_memcg->css); +} + +/** + * mem_cgroup_charge_skmem - charge socket memory + * @memcg: memcg to charge + * @nr_pages: number of pages to charge + * + * Charges @nr_pages to @memcg. Returns %true if the charge fit within + * @memcg's configured limit, %false if the charge had to be forced. + */ +bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages) +{ + gfp_t gfp_mask = GFP_KERNEL; + +#ifdef CONFIG_MEMCG_KMEM + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) { + struct page_counter *counter; + + if (page_counter_try_charge(&memcg->tcp_mem.memory_allocated, + nr_pages, &counter)) { + memcg->tcp_mem.memory_pressure = 0; + return true; + } + page_counter_charge(&memcg->tcp_mem.memory_allocated, nr_pages); + memcg->tcp_mem.memory_pressure = 1; + return false; + } +#endif + /* Don't block in the packet receive path */ + if (in_softirq()) + gfp_mask = GFP_NOWAIT; + + if (try_charge(memcg, gfp_mask, nr_pages) == 0) + return true; + + try_charge(memcg, gfp_mask|__GFP_NOFAIL, nr_pages); + return false; +} + +/** + * mem_cgroup_uncharge_skmem - uncharge socket memory + * @memcg - memcg to uncharge + * @nr_pages - number of pages to uncharge + */ +void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages) +{ +#ifdef CONFIG_MEMCG_KMEM + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) { + page_counter_uncharge(&memcg->tcp_mem.memory_allocated, + nr_pages); + return; + } +#endif + page_counter_uncharge(&memcg->memory, nr_pages); + css_put_many(&memcg->css, nr_pages); +} + +#endif /* CONFIG_INET */ + +static int __init cgroup_memory(char *s) +{ + char *token; + + while ((token = strsep(&s, ",")) != NULL) { + if (!*token) + continue; + if (!strcmp(token, "nosocket")) + cgroup_memory_nosocket = true; + } + return 0; +} +__setup("cgroup.memory=", cgroup_memory); + /* * subsys_initcall() for memory controller. * @@ -5635,7 +5725,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) VM_BUG_ON_PAGE(PageLRU(page), page); VM_BUG_ON_PAGE(page_count(page), page); - if (!do_swap_account) + if (!do_memsw_account()) return; memcg = page->mem_cgroup; @@ -5675,7 +5765,7 @@ void mem_cgroup_uncharge_swap(swp_entry_t entry) struct mem_cgroup *memcg; unsigned short id; - if (!do_swap_account) + if (!do_memsw_account()) return; id = swap_cgroup_record(entry, 0); diff --git a/mm/memory.c b/mm/memory.c index c387430f06c3..d4e4d37c1989 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -832,10 +832,7 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, } else if (is_migration_entry(entry)) { page = migration_entry_to_page(entry); - if (PageAnon(page)) - rss[MM_ANONPAGES]++; - else - rss[MM_FILEPAGES]++; + rss[mm_counter(page)]++; if (is_write_migration_entry(entry) && is_cow_mapping(vm_flags)) { @@ -874,10 +871,7 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, if (page) { get_page(page); page_dup_rmap(page); - if (PageAnon(page)) - rss[MM_ANONPAGES]++; - else - rss[MM_FILEPAGES]++; + rss[mm_counter(page)]++; } out_set_pte: @@ -1113,9 +1107,8 @@ again: tlb_remove_tlb_entry(tlb, pte, addr); if (unlikely(!page)) continue; - if (PageAnon(page)) - rss[MM_ANONPAGES]--; - else { + + if (!PageAnon(page)) { if (pte_dirty(ptent)) { force_flush = 1; set_page_dirty(page); @@ -1123,8 +1116,8 @@ again: if (pte_young(ptent) && likely(!(vma->vm_flags & VM_SEQ_READ))) mark_page_accessed(page); - rss[MM_FILEPAGES]--; } + rss[mm_counter(page)]--; page_remove_rmap(page); if (unlikely(page_mapcount(page) < 0)) print_bad_pte(vma, addr, ptent, page); @@ -1146,11 +1139,7 @@ again: struct page *page; page = migration_entry_to_page(entry); - - if (PageAnon(page)) - rss[MM_ANONPAGES]--; - else - rss[MM_FILEPAGES]--; + rss[mm_counter(page)]--; } if (unlikely(!free_swap_and_cache(entry))) print_bad_pte(vma, addr, ptent, NULL); @@ -1460,7 +1449,7 @@ static int insert_page(struct vm_area_struct *vma, unsigned long addr, /* Ok, finally just insert the thing.. */ get_page(page); - inc_mm_counter_fast(mm, MM_FILEPAGES); + inc_mm_counter_fast(mm, mm_counter_file(page)); page_add_file_rmap(page); set_pte_at(mm, addr, pte, mk_pte(page, prot)); @@ -1949,6 +1938,20 @@ static inline void cow_user_page(struct page *dst, struct page *src, unsigned lo copy_user_highpage(dst, src, va, vma); } +static gfp_t __get_fault_gfp_mask(struct vm_area_struct *vma) +{ + struct file *vm_file = vma->vm_file; + + if (vm_file) + return mapping_gfp_mask(vm_file->f_mapping) | __GFP_FS | __GFP_IO; + + /* + * Special mappings (e.g. VDSO) do not have any file so fake + * a default GFP_KERNEL for them. + */ + return GFP_KERNEL; +} + /* * Notify the address space that the page is about to become writable so that * it can prohibit this or wait for the page to get into an appropriate state. @@ -1964,6 +1967,7 @@ static int do_page_mkwrite(struct vm_area_struct *vma, struct page *page, vmf.virtual_address = (void __user *)(address & PAGE_MASK); vmf.pgoff = page->index; vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE; + vmf.gfp_mask = __get_fault_gfp_mask(vma); vmf.page = page; vmf.cow_page = NULL; @@ -2097,7 +2101,8 @@ static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma, if (likely(pte_same(*page_table, orig_pte))) { if (old_page) { if (!PageAnon(old_page)) { - dec_mm_counter_fast(mm, MM_FILEPAGES); + dec_mm_counter_fast(mm, + mm_counter_file(old_page)); inc_mm_counter_fast(mm, MM_ANONPAGES); } } else { @@ -2767,6 +2772,7 @@ static int __do_fault(struct vm_area_struct *vma, unsigned long address, vmf.pgoff = pgoff; vmf.flags = flags; vmf.page = NULL; + vmf.gfp_mask = __get_fault_gfp_mask(vma); vmf.cow_page = cow_page; ret = vma->vm_ops->fault(vma, &vmf); @@ -2820,7 +2826,7 @@ void do_set_pte(struct vm_area_struct *vma, unsigned long address, inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, address); } else { - inc_mm_counter_fast(vma->vm_mm, MM_FILEPAGES); + inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page)); page_add_file_rmap(page); } set_pte_at(vma->vm_mm, address, pte, entry); @@ -2933,6 +2939,7 @@ static void do_fault_around(struct vm_area_struct *vma, unsigned long address, vmf.pgoff = pgoff; vmf.max_pgoff = max_pgoff; vmf.flags = flags; + vmf.gfp_mask = __get_fault_gfp_mask(vma); vma->vm_ops->map_pages(vma, &vmf); } diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index a042a9d537bb..92f95952692b 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -131,7 +131,8 @@ static struct resource *register_memory_resource(u64 start, u64 size) { struct resource *res; res = kzalloc(sizeof(struct resource), GFP_KERNEL); - BUG_ON(!res); + if (!res) + return ERR_PTR(-ENOMEM); res->name = "System RAM"; res->start = start; @@ -140,7 +141,7 @@ static struct resource *register_memory_resource(u64 start, u64 size) if (request_resource(&iomem_resource, res) < 0) { pr_debug("System RAM resource %pR cannot be added\n", res); kfree(res); - res = NULL; + return ERR_PTR(-EEXIST); } return res; } @@ -1312,8 +1313,8 @@ int __ref add_memory(int nid, u64 start, u64 size) int ret; res = register_memory_resource(start, size); - if (!res) - return -EEXIST; + if (IS_ERR(res)) + return PTR_ERR(res); ret = add_memory_resource(nid, res); if (ret < 0) diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 87a177917cb2..d8caff071a30 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2142,12 +2142,14 @@ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b) * * Remember policies even when nobody has shared memory mapped. * The policies are kept in Red-Black tree linked from the inode. - * They are protected by the sp->lock spinlock, which should be held + * They are protected by the sp->lock rwlock, which should be held * for any accesses to the tree. */ -/* lookup first element intersecting start-end */ -/* Caller holds sp->lock */ +/* + * lookup first element intersecting start-end. Caller holds sp->lock for + * reading or for writing + */ static struct sp_node * sp_lookup(struct shared_policy *sp, unsigned long start, unsigned long end) { @@ -2178,8 +2180,10 @@ sp_lookup(struct shared_policy *sp, unsigned long start, unsigned long end) return rb_entry(n, struct sp_node, nd); } -/* Insert a new shared policy into the list. */ -/* Caller holds sp->lock */ +/* + * Insert a new shared policy into the list. Caller holds sp->lock for + * writing. + */ static void sp_insert(struct shared_policy *sp, struct sp_node *new) { struct rb_node **p = &sp->root.rb_node; @@ -2211,13 +2215,13 @@ mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx) if (!sp->root.rb_node) return NULL; - spin_lock(&sp->lock); + read_lock(&sp->lock); sn = sp_lookup(sp, idx, idx+1); if (sn) { mpol_get(sn->policy); pol = sn->policy; } - spin_unlock(&sp->lock); + read_unlock(&sp->lock); return pol; } @@ -2360,7 +2364,7 @@ static int shared_policy_replace(struct shared_policy *sp, unsigned long start, int ret = 0; restart: - spin_lock(&sp->lock); + write_lock(&sp->lock); n = sp_lookup(sp, start, end); /* Take care of old policies in the same range. */ while (n && n->start < end) { @@ -2393,7 +2397,7 @@ restart: } if (new) sp_insert(sp, new); - spin_unlock(&sp->lock); + write_unlock(&sp->lock); ret = 0; err_out: @@ -2405,7 +2409,7 @@ err_out: return ret; alloc_new: - spin_unlock(&sp->lock); + write_unlock(&sp->lock); ret = -ENOMEM; n_new = kmem_cache_alloc(sn_cache, GFP_KERNEL); if (!n_new) @@ -2431,7 +2435,7 @@ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) int ret; sp->root = RB_ROOT; /* empty tree == default mempolicy */ - spin_lock_init(&sp->lock); + rwlock_init(&sp->lock); if (mpol) { struct vm_area_struct pvma; @@ -2497,14 +2501,14 @@ void mpol_free_shared_policy(struct shared_policy *p) if (!p->root.rb_node) return; - spin_lock(&p->lock); + write_lock(&p->lock); next = rb_first(&p->root); while (next) { n = rb_entry(next, struct sp_node, nd); next = rb_next(&n->nd); sp_delete(p, n); } - spin_unlock(&p->lock); + write_unlock(&p->lock); } #ifdef CONFIG_NUMA_BALANCING diff --git a/mm/mlock.c b/mm/mlock.c index 339d9e0949b6..9cb87cbc4071 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -425,7 +425,7 @@ void munlock_vma_pages_range(struct vm_area_struct *vma, vma->vm_flags &= VM_LOCKED_CLEAR_MASK; while (start < end) { - struct page *page = NULL; + struct page *page; unsigned int page_mask; unsigned long page_increm; struct pagevec pvec; diff --git a/mm/mmap.c b/mm/mmap.c index 2ce04a649f6b..b3f00b616b81 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -58,6 +58,18 @@ #define arch_rebalance_pgtables(addr, len) (addr) #endif +#ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS +const int mmap_rnd_bits_min = CONFIG_ARCH_MMAP_RND_BITS_MIN; +const int mmap_rnd_bits_max = CONFIG_ARCH_MMAP_RND_BITS_MAX; +int mmap_rnd_bits __read_mostly = CONFIG_ARCH_MMAP_RND_BITS; +#endif +#ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS +const int mmap_rnd_compat_bits_min = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MIN; +const int mmap_rnd_compat_bits_max = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MAX; +int mmap_rnd_compat_bits __read_mostly = CONFIG_ARCH_MMAP_RND_COMPAT_BITS; +#endif + + static void unmap_region(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, unsigned long start, unsigned long end); @@ -1208,24 +1220,6 @@ none: return NULL; } -#ifdef CONFIG_PROC_FS -void vm_stat_account(struct mm_struct *mm, unsigned long flags, - struct file *file, long pages) -{ - const unsigned long stack_flags - = VM_STACK_FLAGS & (VM_GROWSUP|VM_GROWSDOWN); - - mm->total_vm += pages; - - if (file) { - mm->shared_vm += pages; - if ((flags & (VM_EXEC|VM_WRITE)) == VM_EXEC) - mm->exec_vm += pages; - } else if (flags & stack_flags) - mm->stack_vm += pages; -} -#endif /* CONFIG_PROC_FS */ - /* * If a hint addr is less than mmap_min_addr change hint to be as * low as possible but still greater than mmap_min_addr @@ -1544,19 +1538,17 @@ unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long charged = 0; /* Check against address space limit. */ - if (!may_expand_vm(mm, len >> PAGE_SHIFT)) { + if (!may_expand_vm(mm, vm_flags, len >> PAGE_SHIFT)) { unsigned long nr_pages; /* * MAP_FIXED may remove pages of mappings that intersects with * requested mapping. Account for the pages it would unmap. */ - if (!(vm_flags & MAP_FIXED)) - return -ENOMEM; - nr_pages = count_vma_pages_range(mm, addr, addr + len); - if (!may_expand_vm(mm, (len >> PAGE_SHIFT) - nr_pages)) + if (!may_expand_vm(mm, vm_flags, + (len >> PAGE_SHIFT) - nr_pages)) return -ENOMEM; } @@ -1655,7 +1647,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, out: perf_event_mmap(vma); - vm_stat_account(mm, vm_flags, file, len >> PAGE_SHIFT); + vm_stat_account(mm, vm_flags, len >> PAGE_SHIFT); if (vm_flags & VM_LOCKED) { if (!((vm_flags & VM_SPECIAL) || is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm))) @@ -2102,7 +2094,7 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns unsigned long new_start, actual_size; /* address space limit tests */ - if (!may_expand_vm(mm, grow)) + if (!may_expand_vm(mm, vma->vm_flags, grow)) return -ENOMEM; /* Stack limit test */ @@ -2199,8 +2191,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address) spin_lock(&mm->page_table_lock); if (vma->vm_flags & VM_LOCKED) mm->locked_vm += grow; - vm_stat_account(mm, vma->vm_flags, - vma->vm_file, grow); + vm_stat_account(mm, vma->vm_flags, grow); anon_vma_interval_tree_pre_update_vma(vma); vma->vm_end = address; anon_vma_interval_tree_post_update_vma(vma); @@ -2275,8 +2266,7 @@ int expand_downwards(struct vm_area_struct *vma, spin_lock(&mm->page_table_lock); if (vma->vm_flags & VM_LOCKED) mm->locked_vm += grow; - vm_stat_account(mm, vma->vm_flags, - vma->vm_file, grow); + vm_stat_account(mm, vma->vm_flags, grow); anon_vma_interval_tree_pre_update_vma(vma); vma->vm_start = address; vma->vm_pgoff -= grow; @@ -2390,7 +2380,7 @@ static void remove_vma_list(struct mm_struct *mm, struct vm_area_struct *vma) if (vma->vm_flags & VM_ACCOUNT) nr_accounted += nrpages; - vm_stat_account(mm, vma->vm_flags, vma->vm_file, -nrpages); + vm_stat_account(mm, vma->vm_flags, -nrpages); vma = remove_vma(vma); } while (vma); vm_unacct_memory(nr_accounted); @@ -2760,7 +2750,7 @@ static unsigned long do_brk(unsigned long addr, unsigned long len) } /* Check against address space limits *after* clearing old maps... */ - if (!may_expand_vm(mm, len >> PAGE_SHIFT)) + if (!may_expand_vm(mm, flags, len >> PAGE_SHIFT)) return -ENOMEM; if (mm->map_count > sysctl_max_map_count) @@ -2795,6 +2785,7 @@ static unsigned long do_brk(unsigned long addr, unsigned long len) out: perf_event_mmap(vma); mm->total_vm += len >> PAGE_SHIFT; + mm->data_vm += len >> PAGE_SHIFT; if (flags & VM_LOCKED) mm->locked_vm += (len >> PAGE_SHIFT); vma->vm_flags |= VM_SOFTDIRTY; @@ -2986,16 +2977,28 @@ out: * Return true if the calling process may expand its vm space by the passed * number of pages */ -int may_expand_vm(struct mm_struct *mm, unsigned long npages) +bool may_expand_vm(struct mm_struct *mm, vm_flags_t flags, unsigned long npages) { - unsigned long cur = mm->total_vm; /* pages */ - unsigned long lim; + if (mm->total_vm + npages > rlimit(RLIMIT_AS) >> PAGE_SHIFT) + return false; - lim = rlimit(RLIMIT_AS) >> PAGE_SHIFT; + if ((flags & (VM_WRITE | VM_SHARED | (VM_STACK_FLAGS & + (VM_GROWSUP | VM_GROWSDOWN)))) == VM_WRITE) + return mm->data_vm + npages <= rlimit(RLIMIT_DATA); - if (cur + npages > lim) - return 0; - return 1; + return true; +} + +void vm_stat_account(struct mm_struct *mm, vm_flags_t flags, long npages) +{ + mm->total_vm += npages; + + if ((flags & (VM_EXEC | VM_WRITE)) == VM_EXEC) + mm->exec_vm += npages; + else if (flags & (VM_STACK_FLAGS & (VM_GROWSUP | VM_GROWSDOWN))) + mm->stack_vm += npages; + else if ((flags & (VM_WRITE | VM_SHARED)) == VM_WRITE) + mm->data_vm += npages; } static int special_mapping_fault(struct vm_area_struct *vma, @@ -3077,7 +3080,7 @@ static struct vm_area_struct *__install_special_mapping( if (ret) goto out; - mm->total_vm += len >> PAGE_SHIFT; + vm_stat_account(mm, vma->vm_flags, len >> PAGE_SHIFT); perf_event_mmap(vma); diff --git a/mm/mmzone.c b/mm/mmzone.c index 7d87ebb0d632..52687fb4de6f 100644 --- a/mm/mmzone.c +++ b/mm/mmzone.c @@ -72,16 +72,16 @@ struct zoneref *next_zones_zonelist(struct zoneref *z, } #ifdef CONFIG_ARCH_HAS_HOLES_MEMORYMODEL -int memmap_valid_within(unsigned long pfn, +bool memmap_valid_within(unsigned long pfn, struct page *page, struct zone *zone) { if (page_to_pfn(page) != pfn) - return 0; + return false; if (page_zone(page) != zone) - return 0; + return false; - return 1; + return true; } #endif /* CONFIG_ARCH_HAS_HOLES_MEMORYMODEL */ diff --git a/mm/mprotect.c b/mm/mprotect.c index ef5be8eaab00..c764402c464f 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -278,6 +278,10 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, * even if read-only so there is no need to account for them here */ if (newflags & VM_WRITE) { + /* Check space limits when area turns into data. */ + if (!may_expand_vm(mm, newflags, nrpages) && + may_expand_vm(mm, oldflags, nrpages)) + return -ENOMEM; if (!(oldflags & (VM_ACCOUNT|VM_WRITE|VM_HUGETLB| VM_SHARED|VM_NORESERVE))) { charged = nrpages; @@ -334,8 +338,8 @@ success: populate_vma_page_range(vma, start, end, NULL); } - vm_stat_account(mm, oldflags, vma->vm_file, -nrpages); - vm_stat_account(mm, newflags, vma->vm_file, nrpages); + vm_stat_account(mm, oldflags, -nrpages); + vm_stat_account(mm, newflags, nrpages); perf_event_mmap(vma); return 0; diff --git a/mm/mremap.c b/mm/mremap.c index de824e72c3e8..e55b157865d5 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -317,7 +317,7 @@ static unsigned long move_vma(struct vm_area_struct *vma, * If this were a serious issue, we'd add a flag to do_munmap(). */ hiwater_vm = mm->hiwater_vm; - vm_stat_account(mm, vma->vm_flags, vma->vm_file, new_len>>PAGE_SHIFT); + vm_stat_account(mm, vma->vm_flags, new_len >> PAGE_SHIFT); /* Tell pfnmap has moved from this vma */ if (unlikely(vma->vm_flags & VM_PFNMAP)) @@ -383,7 +383,8 @@ static struct vm_area_struct *vma_to_resize(unsigned long addr, return ERR_PTR(-EAGAIN); } - if (!may_expand_vm(mm, (new_len - old_len) >> PAGE_SHIFT)) + if (!may_expand_vm(mm, vma->vm_flags, + (new_len - old_len) >> PAGE_SHIFT)) return ERR_PTR(-ENOMEM); if (vma->vm_flags & VM_ACCOUNT) { @@ -545,7 +546,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, goto out; } - vm_stat_account(mm, vma->vm_flags, vma->vm_file, pages); + vm_stat_account(mm, vma->vm_flags, pages); if (vma->vm_flags & VM_LOCKED) { mm->locked_vm += pages; locked = true; diff --git a/mm/nommu.c b/mm/nommu.c index 92be862c859b..fbf6f0f1d6c9 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -560,7 +560,7 @@ void __init mmap_init(void) ret = percpu_counter_init(&vm_committed_as, 0, GFP_KERNEL); VM_BUG_ON(ret); - vm_region_jar = KMEM_CACHE(vm_region, SLAB_PANIC); + vm_region_jar = KMEM_CACHE(vm_region, SLAB_PANIC|SLAB_ACCOUNT); } /* diff --git a/mm/oom_kill.c b/mm/oom_kill.c index c12680993ff3..dc490c06941b 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -585,10 +585,11 @@ void oom_kill_process(struct oom_control *oc, struct task_struct *p, */ do_send_sig_info(SIGKILL, SEND_SIG_FORCED, victim, true); mark_oom_victim(victim); - pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB\n", + pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n", task_pid_nr(victim), victim->comm, K(victim->mm->total_vm), K(get_mm_counter(victim->mm, MM_ANONPAGES)), - K(get_mm_counter(victim->mm, MM_FILEPAGES))); + K(get_mm_counter(victim->mm, MM_FILEPAGES)), + K(get_mm_counter(victim->mm, MM_SHMEMPAGES))); task_unlock(victim); /* diff --git a/mm/page-writeback.c b/mm/page-writeback.c index d15d88c8efa1..6fe7d15bd1f7 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -278,7 +278,12 @@ static unsigned long zone_dirtyable_memory(struct zone *zone) unsigned long nr_pages; nr_pages = zone_page_state(zone, NR_FREE_PAGES); - nr_pages -= min(nr_pages, zone->dirty_balance_reserve); + /* + * Pages reserved for the kernel should not be considered + * dirtyable, to prevent a situation where reclaim has to + * clean pages in order to balance the zones. + */ + nr_pages -= min(nr_pages, zone->totalreserve_pages); nr_pages += zone_page_state(zone, NR_INACTIVE_FILE); nr_pages += zone_page_state(zone, NR_ACTIVE_FILE); @@ -332,7 +337,12 @@ static unsigned long global_dirtyable_memory(void) unsigned long x; x = global_page_state(NR_FREE_PAGES); - x -= min(x, dirty_balance_reserve); + /* + * Pages reserved for the kernel should not be considered + * dirtyable, to prevent a situation where reclaim has to + * clean pages in order to balance the zones. + */ + x -= min(x, totalreserve_pages); x += global_page_state(NR_INACTIVE_FILE); x += global_page_state(NR_ACTIVE_FILE); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 9d666df5ef95..ce63d603820f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -114,13 +114,6 @@ static DEFINE_SPINLOCK(managed_page_count_lock); unsigned long totalram_pages __read_mostly; unsigned long totalreserve_pages __read_mostly; unsigned long totalcma_pages __read_mostly; -/* - * When calculating the number of globally allowed dirty pages, there - * is a certain number of per-zone reserves that should not be - * considered dirtyable memory. This is the sum of those reserves - * over all existing zones that contribute dirtyable memory. - */ -unsigned long dirty_balance_reserve __read_mostly; int percpu_pagelist_fraction; gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK; @@ -812,7 +805,7 @@ static void free_pcppages_bulk(struct zone *zone, int count, do { int mt; /* migratetype of the to-be-freed page */ - page = list_entry(list->prev, struct page, lru); + page = list_last_entry(list, struct page, lru); /* must delete as __free_one_page list manipulates */ list_del(&page->lru); @@ -1417,11 +1410,10 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, /* Find a page of the appropriate size in the preferred list */ for (current_order = order; current_order < MAX_ORDER; ++current_order) { area = &(zone->free_area[current_order]); - if (list_empty(&area->free_list[migratetype])) - continue; - - page = list_entry(area->free_list[migratetype].next, + page = list_first_entry_or_null(&area->free_list[migratetype], struct page, lru); + if (!page) + continue; list_del(&page->lru); rmv_page_order(page); area->nr_free--; @@ -1700,12 +1692,12 @@ static void unreserve_highatomic_pageblock(const struct alloc_context *ac) for (order = 0; order < MAX_ORDER; order++) { struct free_area *area = &(zone->free_area[order]); - if (list_empty(&area->free_list[MIGRATE_HIGHATOMIC])) + page = list_first_entry_or_null( + &area->free_list[MIGRATE_HIGHATOMIC], + struct page, lru); + if (!page) continue; - page = list_entry(area->free_list[MIGRATE_HIGHATOMIC].next, - struct page, lru); - /* * It should never happen but changes to locking could * inadvertently allow a per-cpu drain to add pages @@ -1753,7 +1745,7 @@ __rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype) if (fallback_mt == -1) continue; - page = list_entry(area->free_list[fallback_mt].next, + page = list_first_entry(&area->free_list[fallback_mt], struct page, lru); if (can_steal) steal_suitable_fallback(zone, page, start_migratetype); @@ -1788,7 +1780,7 @@ __rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype) * Call me with the zone->lock already held. */ static struct page *__rmqueue(struct zone *zone, unsigned int order, - int migratetype, gfp_t gfp_flags) + int migratetype) { struct page *page; @@ -1818,7 +1810,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, spin_lock(&zone->lock); for (i = 0; i < count; ++i) { - struct page *page = __rmqueue(zone, order, migratetype, 0); + struct page *page = __rmqueue(zone, order, migratetype); if (unlikely(page == NULL)) break; @@ -1988,7 +1980,7 @@ void mark_free_pages(struct zone *zone) unsigned long pfn, max_zone_pfn; unsigned long flags; unsigned int order, t; - struct list_head *curr; + struct page *page; if (zone_is_empty(zone)) return; @@ -1998,17 +1990,17 @@ void mark_free_pages(struct zone *zone) max_zone_pfn = zone_end_pfn(zone); for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) if (pfn_valid(pfn)) { - struct page *page = pfn_to_page(pfn); - + page = pfn_to_page(pfn); if (!swsusp_page_is_forbidden(page)) swsusp_unset_page_free(page); } for_each_migratetype_order(order, t) { - list_for_each(curr, &zone->free_area[order].free_list[t]) { + list_for_each_entry(page, + &zone->free_area[order].free_list[t], lru) { unsigned long i; - pfn = page_to_pfn(list_entry(curr, struct page, lru)); + pfn = page_to_pfn(page); for (i = 0; i < (1UL << order); i++) swsusp_set_page_free(pfn_to_page(pfn + i)); } @@ -2212,9 +2204,9 @@ struct page *buffered_rmqueue(struct zone *preferred_zone, } if (cold) - page = list_entry(list->prev, struct page, lru); + page = list_last_entry(list, struct page, lru); else - page = list_entry(list->next, struct page, lru); + page = list_first_entry(list, struct page, lru); list_del(&page->lru); pcp->count--; @@ -2241,7 +2233,7 @@ struct page *buffered_rmqueue(struct zone *preferred_zone, trace_mm_page_alloc_zone_locked(page, order, migratetype); } if (!page) - page = __rmqueue(zone, order, migratetype, gfp_flags); + page = __rmqueue(zone, order, migratetype); spin_unlock(&zone->lock); if (!page) goto failed; @@ -2740,8 +2732,21 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, goto out; } /* Exhausted what can be done so it's blamo time */ - if (out_of_memory(&oc) || WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL)) + if (out_of_memory(&oc) || WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL)) { *did_some_progress = 1; + + if (gfp_mask & __GFP_NOFAIL) { + page = get_page_from_freelist(gfp_mask, order, + ALLOC_NO_WATERMARKS|ALLOC_CPUSET, ac); + /* + * fallback to ignore cpuset restriction if our nodes + * are depleted + */ + if (!page) + page = get_page_from_freelist(gfp_mask, order, + ALLOC_NO_WATERMARKS, ac); + } + } out: mutex_unlock(&oom_lock); return page; @@ -2876,28 +2881,6 @@ retry: return page; } -/* - * This is called in the allocator slow-path if the allocation request is of - * sufficient urgency to ignore watermarks and take other desperate measures - */ -static inline struct page * -__alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order, - const struct alloc_context *ac) -{ - struct page *page; - - do { - page = get_page_from_freelist(gfp_mask, order, - ALLOC_NO_WATERMARKS, ac); - - if (!page && gfp_mask & __GFP_NOFAIL) - wait_iff_congested(ac->preferred_zone, BLK_RW_ASYNC, - HZ/50); - } while (!page && (gfp_mask & __GFP_NOFAIL)); - - return page; -} - static void wake_all_kswapds(unsigned int order, const struct alloc_context *ac) { struct zoneref *z; @@ -3042,28 +3025,36 @@ retry: * allocations are system rather than user orientated */ ac->zonelist = node_zonelist(numa_node_id(), gfp_mask); - - page = __alloc_pages_high_priority(gfp_mask, order, ac); - - if (page) { + page = get_page_from_freelist(gfp_mask, order, + ALLOC_NO_WATERMARKS, ac); + if (page) goto got_pg; - } } /* Caller is not willing to reclaim, we can't balance anything */ if (!can_direct_reclaim) { /* - * All existing users of the deprecated __GFP_NOFAIL are - * blockable, so warn of any new users that actually allow this - * type of allocation to fail. + * All existing users of the __GFP_NOFAIL are blockable, so warn + * of any new users that actually allow this type of allocation + * to fail. */ WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL); goto nopage; } /* Avoid recursion of direct reclaim */ - if (current->flags & PF_MEMALLOC) + if (current->flags & PF_MEMALLOC) { + /* + * __GFP_NOFAIL request from this context is rather bizarre + * because we cannot reclaim anything and only can loop waiting + * for somebody to do a work for us. + */ + if (WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL)) { + cond_resched(); + goto retry; + } goto nopage; + } /* Avoid allocations with no watermarks from looping endlessly */ if (test_thread_flag(TIF_MEMDIE) && !(gfp_mask & __GFP_NOFAIL)) @@ -3402,7 +3393,8 @@ EXPORT_SYMBOL(__free_page_frag); /* * alloc_kmem_pages charges newly allocated pages to the kmem resource counter - * of the current memory cgroup. + * of the current memory cgroup if __GFP_ACCOUNT is set, other than that it is + * equivalent to alloc_pages. * * It should be used when the caller would like to use kmalloc, but since the * allocation is large, it has to fall back to the page allocator. @@ -4147,8 +4139,7 @@ static void set_zonelist_order(void) static void build_zonelists(pg_data_t *pgdat) { - int j, node, load; - enum zone_type i; + int i, node, load; nodemask_t used_mask; int local_node, prev_node; struct zonelist *zonelist; @@ -4168,7 +4159,7 @@ static void build_zonelists(pg_data_t *pgdat) nodes_clear(used_mask); memset(node_order, 0, sizeof(node_order)); - j = 0; + i = 0; while ((node = find_next_best_node(local_node, &used_mask)) >= 0) { /* @@ -4185,12 +4176,12 @@ static void build_zonelists(pg_data_t *pgdat) if (order == ZONELIST_ORDER_NODE) build_zonelists_in_node_order(pgdat, node); else - node_order[j++] = node; /* remember order */ + node_order[i++] = node; /* remember order */ } if (order == ZONELIST_ORDER_ZONE) { /* calculate node order -- i.e., DMA last! */ - build_zonelists_in_zone_order(pgdat, j); + build_zonelists_in_zone_order(pgdat, i); } build_thisnode_zonelists(pgdat); @@ -5956,20 +5947,12 @@ static void calculate_totalreserve_pages(void) if (max > zone->managed_pages) max = zone->managed_pages; + + zone->totalreserve_pages = max; + reserve_pages += max; - /* - * Lowmem reserves are not available to - * GFP_HIGHUSER page cache allocations and - * kswapd tries to balance zones to their high - * watermark. As a result, neither should be - * regarded as dirtyable memory, to prevent a - * situation where reclaim has to clean pages - * in order to balance the zones. - */ - zone->dirty_balance_reserve = max; } } - dirty_balance_reserve = reserve_pages; totalreserve_pages = reserve_pages; } @@ -6724,8 +6707,12 @@ int alloc_contig_range(unsigned long start, unsigned long end, if (ret) return ret; + /* + * In case of -EBUSY, we'd like to know which page causes problem. + * So, just fall through. We will check it in test_pages_isolated(). + */ ret = __alloc_contig_migrate_range(&cc, start, end); - if (ret) + if (ret && ret != -EBUSY) goto done; /* @@ -6752,12 +6739,25 @@ int alloc_contig_range(unsigned long start, unsigned long end, outer_start = start; while (!PageBuddy(pfn_to_page(outer_start))) { if (++order >= MAX_ORDER) { - ret = -EBUSY; - goto done; + outer_start = start; + break; } outer_start &= ~0UL << order; } + if (outer_start != start) { + order = page_order(pfn_to_page(outer_start)); + + /* + * outer_start page could be small order buddy page and + * it doesn't include start page. Adjust outer_start + * in this case to report failed page properly + * on tracepoint in test_pages_isolated() + */ + if (outer_start + (1UL << order) <= start) + outer_start = start; + } + /* Make sure the range is really isolated. */ if (test_pages_isolated(outer_start, end, false)) { pr_info("%s: [%lx, %lx) PFNs busy\n", diff --git a/mm/page_isolation.c b/mm/page_isolation.c index 4568fd58f70a..5e139fec6c6c 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -9,6 +9,9 @@ #include <linux/hugetlb.h> #include "internal.h" +#define CREATE_TRACE_POINTS +#include <trace/events/page_isolation.h> + static int set_migratetype_isolate(struct page *page, bool skip_hwpoisoned_pages) { @@ -162,8 +165,8 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, unsigned long undo_pfn; struct page *page; - BUG_ON((start_pfn) & (pageblock_nr_pages - 1)); - BUG_ON((end_pfn) & (pageblock_nr_pages - 1)); + BUG_ON(!IS_ALIGNED(start_pfn, pageblock_nr_pages)); + BUG_ON(!IS_ALIGNED(end_pfn, pageblock_nr_pages)); for (pfn = start_pfn; pfn < end_pfn; @@ -212,7 +215,7 @@ int undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, * * Returns 1 if all pages in the range are isolated. */ -static int +static unsigned long __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn, bool skip_hwpoisoned_pages) { @@ -237,9 +240,8 @@ __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn, else break; } - if (pfn < end_pfn) - return 0; - return 1; + + return pfn; } int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn, @@ -248,7 +250,6 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn, unsigned long pfn, flags; struct page *page; struct zone *zone; - int ret; /* * Note: pageblock_nr_pages != MAX_ORDER. Then, chunks of free pages @@ -266,10 +267,13 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn, /* Check all pages are free or marked as ISOLATED */ zone = page_zone(page); spin_lock_irqsave(&zone->lock, flags); - ret = __test_page_isolated_in_pageblock(start_pfn, end_pfn, + pfn = __test_page_isolated_in_pageblock(start_pfn, end_pfn, skip_hwpoisoned_pages); spin_unlock_irqrestore(&zone->lock, flags); - return ret ? 0 : -EBUSY; + + trace_test_pages_isolated(start_pfn, end_pfn, pfn); + + return pfn < end_pfn ? -EBUSY : 0; } struct page *alloc_migrate_target(struct page *page, unsigned long private, diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index 7d3db0247983..4c681baff363 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -176,13 +176,10 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp) /* FIFO */ pgtable = pmd_huge_pte(mm, pmdp); - if (list_empty(&pgtable->lru)) - pmd_huge_pte(mm, pmdp) = NULL; - else { - pmd_huge_pte(mm, pmdp) = list_entry(pgtable->lru.next, - struct page, lru); + pmd_huge_pte(mm, pmdp) = list_first_entry_or_null(&pgtable->lru, + struct page, lru); + if (pmd_huge_pte(mm, pmdp)) list_del(&pgtable->lru); - } return pgtable; } #endif diff --git a/mm/readahead.c b/mm/readahead.c index ba22d7fe0afb..20e58e820e44 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -17,6 +17,7 @@ #include <linux/pagemap.h> #include <linux/syscalls.h> #include <linux/file.h> +#include <linux/mm_inline.h> #include "internal.h" @@ -32,8 +33,6 @@ file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping) } EXPORT_SYMBOL_GPL(file_ra_state_init); -#define list_to_page(head) (list_entry((head)->prev, struct page, lru)) - /* * see if a page needs releasing upon read_cache_pages() failure * - the caller of read_cache_pages() may have set PG_private or PG_fscache @@ -64,7 +63,7 @@ static void read_cache_pages_invalidate_pages(struct address_space *mapping, struct page *victim; while (!list_empty(pages)) { - victim = list_to_page(pages); + victim = lru_to_page(pages); list_del(&victim->lru); read_cache_pages_invalidate_page(mapping, victim); } @@ -87,7 +86,7 @@ int read_cache_pages(struct address_space *mapping, struct list_head *pages, int ret = 0; while (!list_empty(pages)) { - page = list_to_page(pages); + page = lru_to_page(pages); list_del(&page->lru); if (add_to_page_cache_lru(page, mapping, page->index, mapping_gfp_constraint(mapping, GFP_KERNEL))) { @@ -125,7 +124,7 @@ static int read_pages(struct address_space *mapping, struct file *filp, } for (page_idx = 0; page_idx < nr_pages; page_idx++) { - struct page *page = list_to_page(pages); + struct page *page = lru_to_page(pages); list_del(&page->lru); if (!add_to_page_cache_lru(page, mapping, page->index, mapping_gfp_constraint(mapping, GFP_KERNEL))) { diff --git a/mm/rmap.c b/mm/rmap.c index b577fbb98d4b..622756c16ac8 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -428,8 +428,10 @@ static void anon_vma_ctor(void *data) void __init anon_vma_init(void) { anon_vma_cachep = kmem_cache_create("anon_vma", sizeof(struct anon_vma), - 0, SLAB_DESTROY_BY_RCU|SLAB_PANIC, anon_vma_ctor); - anon_vma_chain_cachep = KMEM_CACHE(anon_vma_chain, SLAB_PANIC); + 0, SLAB_DESTROY_BY_RCU|SLAB_PANIC|SLAB_ACCOUNT, + anon_vma_ctor); + anon_vma_chain_cachep = KMEM_CACHE(anon_vma_chain, + SLAB_PANIC|SLAB_ACCOUNT); } /* @@ -1362,10 +1364,7 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, if (PageHuge(page)) { hugetlb_count_sub(1 << compound_order(page), mm); } else { - if (PageAnon(page)) - dec_mm_counter(mm, MM_ANONPAGES); - else - dec_mm_counter(mm, MM_FILEPAGES); + dec_mm_counter(mm, mm_counter(page)); } set_pte_at(mm, address, pte, swp_entry_to_pte(make_hwpoison_entry(page))); @@ -1375,10 +1374,7 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, * interest anymore. Simply discard the pte, vmscan * will take care of the rest. */ - if (PageAnon(page)) - dec_mm_counter(mm, MM_ANONPAGES); - else - dec_mm_counter(mm, MM_FILEPAGES); + dec_mm_counter(mm, mm_counter(page)); } else if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION)) { swp_entry_t entry; pte_t swp_pte; @@ -1418,7 +1414,7 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, swp_pte = pte_swp_mksoft_dirty(swp_pte); set_pte_at(mm, address, pte, swp_pte); } else - dec_mm_counter(mm, MM_FILEPAGES); + dec_mm_counter(mm, mm_counter_file(page)); page_remove_rmap(page); page_cache_release(page); diff --git a/mm/shmem.c b/mm/shmem.c index 5813b7fa85b6..970ff5b80853 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -360,6 +360,87 @@ static int shmem_free_swap(struct address_space *mapping, } /* + * Determine (in bytes) how many of the shmem object's pages mapped by the + * given offsets are swapped out. + * + * This is safe to call without i_mutex or mapping->tree_lock thanks to RCU, + * as long as the inode doesn't go away and racy results are not a problem. + */ +unsigned long shmem_partial_swap_usage(struct address_space *mapping, + pgoff_t start, pgoff_t end) +{ + struct radix_tree_iter iter; + void **slot; + struct page *page; + unsigned long swapped = 0; + + rcu_read_lock(); + +restart: + radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) { + if (iter.index >= end) + break; + + page = radix_tree_deref_slot(slot); + + /* + * This should only be possible to happen at index 0, so we + * don't need to reset the counter, nor do we risk infinite + * restarts. + */ + if (radix_tree_deref_retry(page)) + goto restart; + + if (radix_tree_exceptional_entry(page)) + swapped++; + + if (need_resched()) { + cond_resched_rcu(); + start = iter.index + 1; + goto restart; + } + } + + rcu_read_unlock(); + + return swapped << PAGE_SHIFT; +} + +/* + * Determine (in bytes) how many of the shmem object's pages mapped by the + * given vma is swapped out. + * + * This is safe to call without i_mutex or mapping->tree_lock thanks to RCU, + * as long as the inode doesn't go away and racy results are not a problem. + */ +unsigned long shmem_swap_usage(struct vm_area_struct *vma) +{ + struct inode *inode = file_inode(vma->vm_file); + struct shmem_inode_info *info = SHMEM_I(inode); + struct address_space *mapping = inode->i_mapping; + unsigned long swapped; + + /* Be careful as we don't hold info->lock */ + swapped = READ_ONCE(info->swapped); + + /* + * The easier cases are when the shmem object has nothing in swap, or + * the vma maps it whole. Then we can simply use the stats that we + * already track. + */ + if (!swapped) + return 0; + + if (!vma->vm_pgoff && vma->vm_end - vma->vm_start >= inode->i_size) + return swapped << PAGE_SHIFT; + + /* Here comes the more involved part */ + return shmem_partial_swap_usage(mapping, + linear_page_index(vma, vma->vm_start), + linear_page_index(vma, vma->vm_end)); +} + +/* * SysV IPC SHM_UNLOCK restore Unevictable pages to their evictable lists. */ void shmem_unlock_mapping(struct address_space *mapping) @@ -2469,6 +2550,7 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s inode->i_op = &shmem_short_symlink_operations; inode->i_link = info->symlink; } else { + inode_nohighmem(inode); error = shmem_getpage(inode, 0, &page, SGP_WRITE, NULL); if (error) { iput(inode); @@ -2476,7 +2558,6 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s } inode->i_mapping->a_ops = &shmem_aops; inode->i_op = &shmem_symlink_inode_operations; - inode_nohighmem(inode); memcpy(page_address(page), symname, len); SetPageUptodate(page); set_page_dirty(page); @@ -3064,7 +3145,7 @@ static int shmem_init_inodecache(void) { shmem_inode_cachep = kmem_cache_create("shmem_inode_cache", sizeof(struct shmem_inode_info), - 0, SLAB_PANIC, shmem_init_inode); + 0, SLAB_PANIC|SLAB_ACCOUNT, shmem_init_inode); return 0; } diff --git a/mm/slab.c b/mm/slab.c index 4765c97ce690..6ecc697a8bc4 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -2756,6 +2756,21 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp, #define cache_free_debugcheck(x,objp,z) (objp) #endif +static struct page *get_first_slab(struct kmem_cache_node *n) +{ + struct page *page; + + page = list_first_entry_or_null(&n->slabs_partial, + struct page, lru); + if (!page) { + n->free_touched = 1; + page = list_first_entry_or_null(&n->slabs_free, + struct page, lru); + } + + return page; +} + static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags, bool force_refill) { @@ -2791,18 +2806,12 @@ retry: } while (batchcount > 0) { - struct list_head *entry; struct page *page; /* Get slab alloc is to come from. */ - entry = n->slabs_partial.next; - if (entry == &n->slabs_partial) { - n->free_touched = 1; - entry = n->slabs_free.next; - if (entry == &n->slabs_free) - goto must_grow; - } + page = get_first_slab(n); + if (!page) + goto must_grow; - page = list_entry(entry, struct page, lru); check_spinlock_acquired(cachep); /* @@ -3085,7 +3094,6 @@ retry: static void *____cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid) { - struct list_head *entry; struct page *page; struct kmem_cache_node *n; void *obj; @@ -3098,15 +3106,10 @@ static void *____cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, retry: check_irq_off(); spin_lock(&n->list_lock); - entry = n->slabs_partial.next; - if (entry == &n->slabs_partial) { - n->free_touched = 1; - entry = n->slabs_free.next; - if (entry == &n->slabs_free) - goto must_grow; - } + page = get_first_slab(n); + if (!page) + goto must_grow; - page = list_entry(entry, struct page, lru); check_spinlock_acquired_node(cachep, nodeid); STATS_INC_NODEALLOCS(cachep); @@ -3338,17 +3341,12 @@ free_done: #if STATS { int i = 0; - struct list_head *p; - - p = n->slabs_free.next; - while (p != &(n->slabs_free)) { - struct page *page; + struct page *page; - page = list_entry(p, struct page, lru); + list_for_each_entry(page, &n->slabs_free, lru) { BUG_ON(page->active); i++; - p = p->next; } STATS_SET_FREEABLE(cachep, i); } diff --git a/mm/slab.h b/mm/slab.h index 7b6087197997..c63b8699cfa3 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -128,10 +128,11 @@ static inline unsigned long kmem_cache_flags(unsigned long object_size, #if defined(CONFIG_SLAB) #define SLAB_CACHE_FLAGS (SLAB_MEM_SPREAD | SLAB_NOLEAKTRACE | \ - SLAB_RECLAIM_ACCOUNT | SLAB_TEMPORARY | SLAB_NOTRACK) + SLAB_RECLAIM_ACCOUNT | SLAB_TEMPORARY | \ + SLAB_NOTRACK | SLAB_ACCOUNT) #elif defined(CONFIG_SLUB) #define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE | SLAB_RECLAIM_ACCOUNT | \ - SLAB_TEMPORARY | SLAB_NOTRACK) + SLAB_TEMPORARY | SLAB_NOTRACK | SLAB_ACCOUNT) #else #define SLAB_CACHE_FLAGS (0) #endif diff --git a/mm/slab_common.c b/mm/slab_common.c index 3c6a86b4ec25..e016178063e1 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -37,7 +37,8 @@ struct kmem_cache *kmem_cache; SLAB_TRACE | SLAB_DESTROY_BY_RCU | SLAB_NOLEAKTRACE | \ SLAB_FAILSLAB) -#define SLAB_MERGE_SAME (SLAB_RECLAIM_ACCOUNT | SLAB_CACHE_DMA | SLAB_NOTRACK) +#define SLAB_MERGE_SAME (SLAB_RECLAIM_ACCOUNT | SLAB_CACHE_DMA | \ + SLAB_NOTRACK | SLAB_ACCOUNT) /* * Merge control. If this is set then no merging of slab caches will occur. diff --git a/mm/slub.c b/mm/slub.c index 46997517406e..2d0e610d195a 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -5362,6 +5362,8 @@ static char *create_unique_id(struct kmem_cache *s) *p++ = 'F'; if (!(s->flags & SLAB_NOTRACK)) *p++ = 't'; + if (s->flags & SLAB_ACCOUNT) + *p++ = 'A'; if (p != name + 1) *p++ = '-'; p += sprintf(p, "%07d", s->size); diff --git a/mm/swapfile.c b/mm/swapfile.c index 58877312cf6b..e6b8591a3ed2 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -165,8 +165,6 @@ static void discard_swap_cluster(struct swap_info_struct *si, int found_extent = 0; while (nr_pages) { - struct list_head *lh; - if (se->start_page <= start_page && start_page < se->start_page + se->nr_pages) { pgoff_t offset = start_page - se->start_page; @@ -188,8 +186,7 @@ static void discard_swap_cluster(struct swap_info_struct *si, break; } - lh = se->list.next; - se = list_entry(lh, struct swap_extent, list); + se = list_next_entry(se, list); } } @@ -903,7 +900,7 @@ int swp_swapcount(swp_entry_t entry) VM_BUG_ON(page_private(page) != SWP_CONTINUED); do { - page = list_entry(page->lru.next, struct page, lru); + page = list_next_entry(page, lru); map = kmap_atomic(page); tmp_count = map[offset]; kunmap_atomic(map); @@ -1633,14 +1630,11 @@ static sector_t map_swap_entry(swp_entry_t entry, struct block_device **bdev) se = start_se; for ( ; ; ) { - struct list_head *lh; - if (se->start_page <= offset && offset < (se->start_page + se->nr_pages)) { return se->start_block + (offset - se->start_page); } - lh = se->list.next; - se = list_entry(lh, struct swap_extent, list); + se = list_next_entry(se, list); sis->curr_swap_extent = se; BUG_ON(se == start_se); /* It *must* be present */ } @@ -1664,7 +1658,7 @@ static void destroy_swap_extents(struct swap_info_struct *sis) while (!list_empty(&sis->first_swap_extent.list)) { struct swap_extent *se; - se = list_entry(sis->first_swap_extent.list.next, + se = list_first_entry(&sis->first_swap_extent.list, struct swap_extent, list); list_del(&se->list); kfree(se); @@ -2959,11 +2953,10 @@ static void free_swap_count_continuations(struct swap_info_struct *si) struct page *head; head = vmalloc_to_page(si->swap_map + offset); if (page_private(head)) { - struct list_head *this, *next; - list_for_each_safe(this, next, &head->lru) { - struct page *page; - page = list_entry(this, struct page, lru); - list_del(this); + struct page *page, *next; + + list_for_each_entry_safe(page, next, &head->lru, lru) { + list_del(&page->lru); __free_page(page); } } diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 8e3c9c5a3042..58ceeb107960 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -441,8 +441,7 @@ nocache: if (list_is_last(&first->list, &vmap_area_list)) goto found; - first = list_entry(first->list.next, - struct vmap_area, list); + first = list_next_entry(first, list); } found: @@ -1477,13 +1476,10 @@ static void __vunmap(const void *addr, int deallocate_pages) struct page *page = area->pages[i]; BUG_ON(!page); - __free_page(page); + __free_kmem_pages(page, 0); } - if (area->flags & VM_VPAGES) - vfree(area->pages); - else - kfree(area->pages); + kvfree(area->pages); } kfree(area); @@ -1593,7 +1589,6 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, if (array_size > PAGE_SIZE) { pages = __vmalloc_node(array_size, 1, nested_gfp|__GFP_HIGHMEM, PAGE_KERNEL, node, area->caller); - area->flags |= VM_VPAGES; } else { pages = kmalloc_node(array_size, nested_gfp, node); } @@ -1608,9 +1603,9 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, struct page *page; if (node == NUMA_NO_NODE) - page = alloc_page(alloc_mask); + page = alloc_kmem_pages(alloc_mask, order); else - page = alloc_pages_node(node, alloc_mask, order); + page = alloc_kmem_pages_node(node, alloc_mask, order); if (unlikely(!page)) { /* Successfully allocated i pages, free them in __vunmap() */ @@ -2559,10 +2554,10 @@ static void *s_start(struct seq_file *m, loff_t *pos) struct vmap_area *va; spin_lock(&vmap_area_lock); - va = list_entry((&vmap_area_list)->next, typeof(*va), list); + va = list_first_entry(&vmap_area_list, typeof(*va), list); while (n > 0 && &va->list != &vmap_area_list) { n--; - va = list_entry(va->list.next, typeof(*va), list); + va = list_next_entry(va, list); } if (!n && &va->list != &vmap_area_list) return va; @@ -2576,7 +2571,7 @@ static void *s_next(struct seq_file *m, void *p, loff_t *pos) struct vmap_area *va = p, *next; ++*pos; - next = list_entry(va->list.next, typeof(*va), list); + next = list_next_entry(va, list); if (&next->list != &vmap_area_list) return next; @@ -2651,7 +2646,7 @@ static int s_show(struct seq_file *m, void *p) if (v->flags & VM_USERMAP) seq_puts(m, " user"); - if (v->flags & VM_VPAGES) + if (is_vmalloc_addr(v->pages)) seq_puts(m, " vpages"); show_numa_info(m, v); diff --git a/mm/vmpressure.c b/mm/vmpressure.c index c5afd573d7da..9a6c0704211c 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -137,14 +137,11 @@ struct vmpressure_event { }; static bool vmpressure_event(struct vmpressure *vmpr, - unsigned long scanned, unsigned long reclaimed) + enum vmpressure_levels level) { struct vmpressure_event *ev; - enum vmpressure_levels level; bool signalled = false; - level = vmpressure_calc_level(scanned, reclaimed); - mutex_lock(&vmpr->events_lock); list_for_each_entry(ev, &vmpr->events, node) { @@ -164,6 +161,7 @@ static void vmpressure_work_fn(struct work_struct *work) struct vmpressure *vmpr = work_to_vmpressure(work); unsigned long scanned; unsigned long reclaimed; + enum vmpressure_levels level; spin_lock(&vmpr->sr_lock); /* @@ -174,19 +172,21 @@ static void vmpressure_work_fn(struct work_struct *work) * here. No need for any locks here since we don't care if * vmpr->reclaimed is in sync. */ - scanned = vmpr->scanned; + scanned = vmpr->tree_scanned; if (!scanned) { spin_unlock(&vmpr->sr_lock); return; } - reclaimed = vmpr->reclaimed; - vmpr->scanned = 0; - vmpr->reclaimed = 0; + reclaimed = vmpr->tree_reclaimed; + vmpr->tree_scanned = 0; + vmpr->tree_reclaimed = 0; spin_unlock(&vmpr->sr_lock); + level = vmpressure_calc_level(scanned, reclaimed); + do { - if (vmpressure_event(vmpr, scanned, reclaimed)) + if (vmpressure_event(vmpr, level)) break; /* * If not handled, propagate the event upward into the @@ -199,6 +199,7 @@ static void vmpressure_work_fn(struct work_struct *work) * vmpressure() - Account memory pressure through scanned/reclaimed ratio * @gfp: reclaimer's gfp mask * @memcg: cgroup memory controller handle + * @tree: legacy subtree mode * @scanned: number of pages scanned * @reclaimed: number of pages reclaimed * @@ -206,9 +207,16 @@ static void vmpressure_work_fn(struct work_struct *work) * "instantaneous" memory pressure (scanned/reclaimed ratio). The raw * pressure index is then further refined and averaged over time. * + * If @tree is set, vmpressure is in traditional userspace reporting + * mode: @memcg is considered the pressure root and userspace is + * notified of the entire subtree's reclaim efficiency. + * + * If @tree is not set, reclaim efficiency is recorded for @memcg, and + * only in-kernel users are notified. + * * This function does not return any value. */ -void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, +void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, bool tree, unsigned long scanned, unsigned long reclaimed) { struct vmpressure *vmpr = memcg_to_vmpressure(memcg); @@ -238,15 +246,47 @@ void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, if (!scanned) return; - spin_lock(&vmpr->sr_lock); - vmpr->scanned += scanned; - vmpr->reclaimed += reclaimed; - scanned = vmpr->scanned; - spin_unlock(&vmpr->sr_lock); + if (tree) { + spin_lock(&vmpr->sr_lock); + vmpr->tree_scanned += scanned; + vmpr->tree_reclaimed += reclaimed; + scanned = vmpr->scanned; + spin_unlock(&vmpr->sr_lock); - if (scanned < vmpressure_win) - return; - schedule_work(&vmpr->work); + if (scanned < vmpressure_win) + return; + schedule_work(&vmpr->work); + } else { + enum vmpressure_levels level; + + /* For now, no users for root-level efficiency */ + if (!memcg || memcg == root_mem_cgroup) + return; + + spin_lock(&vmpr->sr_lock); + scanned = vmpr->scanned += scanned; + reclaimed = vmpr->reclaimed += reclaimed; + if (scanned < vmpressure_win) { + spin_unlock(&vmpr->sr_lock); + return; + } + vmpr->scanned = vmpr->reclaimed = 0; + spin_unlock(&vmpr->sr_lock); + + level = vmpressure_calc_level(scanned, reclaimed); + + if (level > VMPRESSURE_LOW) { + /* + * Let the socket buffer allocator know that + * we are having trouble reclaiming LRU pages. + * + * For hysteresis keep the pressure state + * asserted for a second in which subsequent + * pressure events can occur. + */ + memcg->socket_pressure = jiffies + HZ; + } + } } /** @@ -276,7 +316,7 @@ void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio) * to the vmpressure() basically means that we signal 'critical' * level. */ - vmpressure(gfp, memcg, vmpressure_win, 0); + vmpressure(gfp, memcg, true, vmpressure_win, 0); } /** diff --git a/mm/vmscan.c b/mm/vmscan.c index 2aec4241b42a..108bd119f2f6 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -106,8 +106,6 @@ struct scan_control { unsigned long nr_reclaimed; }; -#define lru_to_page(_head) (list_entry((_head)->prev, struct page, lru)) - #ifdef ARCH_HAS_PREFETCH #define prefetch_prev_lru_page(_page, _base, _field) \ do { \ @@ -197,11 +195,13 @@ static unsigned long zone_reclaimable_pages(struct zone *zone) unsigned long nr; nr = zone_page_state(zone, NR_ACTIVE_FILE) + - zone_page_state(zone, NR_INACTIVE_FILE); + zone_page_state(zone, NR_INACTIVE_FILE) + + zone_page_state(zone, NR_ISOLATED_FILE); if (get_nr_swap_pages() > 0) nr += zone_page_state(zone, NR_ACTIVE_ANON) + - zone_page_state(zone, NR_INACTIVE_ANON); + zone_page_state(zone, NR_INACTIVE_ANON) + + zone_page_state(zone, NR_ISOLATED_ANON); return nr; } @@ -594,7 +594,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping, /* synchronous write or broken a_ops? */ ClearPageReclaim(page); } - trace_mm_vmscan_writepage(page, trace_reclaim_flags(page)); + trace_mm_vmscan_writepage(page); inc_zone_page_state(page, NR_VMSCAN_WRITE); return PAGE_SUCCESS; } @@ -1426,6 +1426,7 @@ int isolate_lru_page(struct page *page) int ret = -EBUSY; VM_BUG_ON_PAGE(!page_count(page), page); + VM_BUG_ON_PAGE(PageTail(page), page); if (PageLRU(page)) { struct zone *zone = page_zone(page); @@ -1691,11 +1692,8 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, current_may_throttle()) wait_iff_congested(zone, BLK_RW_ASYNC, HZ/10); - trace_mm_vmscan_lru_shrink_inactive(zone->zone_pgdat->node_id, - zone_idx(zone), - nr_scanned, nr_reclaimed, - sc->priority, - trace_shrink_flags(file)); + trace_mm_vmscan_lru_shrink_inactive(zone, nr_scanned, nr_reclaimed, + sc->priority, file); return nr_reclaimed; } @@ -2046,10 +2044,16 @@ static void get_scan_count(struct lruvec *lruvec, int swappiness, } /* - * There is enough inactive page cache, do not reclaim - * anything from the anonymous working set right now. + * If there is enough inactive page cache, i.e. if the size of the + * inactive list is greater than that of the active list *and* the + * inactive list actually has some pages to scan on this priority, we + * do not reclaim anything from the anonymous working set right now. + * Without the second condition we could end up never scanning an + * lruvec even if it has plenty of old anonymous pages unless the + * system is under heavy pressure. */ - if (!inactive_file_is_low(lruvec)) { + if (!inactive_file_is_low(lruvec) && + get_lru_size(lruvec, LRU_INACTIVE_FILE) >> sc->priority) { scan_balance = SCAN_FILE; goto out; } @@ -2393,6 +2397,7 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc, memcg = mem_cgroup_iter(root, NULL, &reclaim); do { unsigned long lru_pages; + unsigned long reclaimed; unsigned long scanned; struct lruvec *lruvec; int swappiness; @@ -2405,6 +2410,7 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc, lruvec = mem_cgroup_zone_lruvec(zone, memcg); swappiness = mem_cgroup_swappiness(memcg); + reclaimed = sc->nr_reclaimed; scanned = sc->nr_scanned; shrink_lruvec(lruvec, swappiness, sc, &lru_pages); @@ -2415,6 +2421,11 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc, memcg, sc->nr_scanned - scanned, lru_pages); + /* Record the group's reclaim efficiency */ + vmpressure(sc->gfp_mask, memcg, false, + sc->nr_scanned - scanned, + sc->nr_reclaimed - reclaimed); + /* * Direct reclaim and kswapd have to scan all memory * cgroups to fulfill the overall scan target for the @@ -2446,7 +2457,8 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc, reclaim_state->reclaimed_slab = 0; } - vmpressure(sc->gfp_mask, sc->target_mem_cgroup, + /* Record the subtree's reclaim efficiency */ + vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true, sc->nr_scanned - nr_scanned, sc->nr_reclaimed - nr_reclaimed); diff --git a/mm/vmstat.c b/mm/vmstat.c index c54fd2924f25..83a003bc3cae 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -460,7 +460,7 @@ static int fold_diff(int *diff) * * The function returns the number of global counters updated. */ -static int refresh_cpu_vm_stats(void) +static int refresh_cpu_vm_stats(bool do_pagesets) { struct zone *zone; int i; @@ -484,33 +484,35 @@ static int refresh_cpu_vm_stats(void) #endif } } - cond_resched(); #ifdef CONFIG_NUMA - /* - * Deal with draining the remote pageset of this - * processor - * - * Check if there are pages remaining in this pageset - * if not then there is nothing to expire. - */ - if (!__this_cpu_read(p->expire) || + if (do_pagesets) { + cond_resched(); + /* + * Deal with draining the remote pageset of this + * processor + * + * Check if there are pages remaining in this pageset + * if not then there is nothing to expire. + */ + if (!__this_cpu_read(p->expire) || !__this_cpu_read(p->pcp.count)) - continue; + continue; - /* - * We never drain zones local to this processor. - */ - if (zone_to_nid(zone) == numa_node_id()) { - __this_cpu_write(p->expire, 0); - continue; - } + /* + * We never drain zones local to this processor. + */ + if (zone_to_nid(zone) == numa_node_id()) { + __this_cpu_write(p->expire, 0); + continue; + } - if (__this_cpu_dec_return(p->expire)) - continue; + if (__this_cpu_dec_return(p->expire)) + continue; - if (__this_cpu_read(p->pcp.count)) { - drain_zone_pages(zone, this_cpu_ptr(&p->pcp)); - changes++; + if (__this_cpu_read(p->pcp.count)) { + drain_zone_pages(zone, this_cpu_ptr(&p->pcp)); + changes++; + } } #endif } @@ -1386,7 +1388,7 @@ static cpumask_var_t cpu_stat_off; static void vmstat_update(struct work_struct *w) { - if (refresh_cpu_vm_stats()) { + if (refresh_cpu_vm_stats(true)) { /* * Counters were updated so we expect more updates * to occur in the future. Keep on running the @@ -1418,6 +1420,23 @@ static void vmstat_update(struct work_struct *w) } /* + * Switch off vmstat processing and then fold all the remaining differentials + * until the diffs stay at zero. The function is used by NOHZ and can only be + * invoked when tick processing is not active. + */ +void quiet_vmstat(void) +{ + if (system_state != SYSTEM_RUNNING) + return; + + do { + if (!cpumask_test_and_set_cpu(smp_processor_id(), cpu_stat_off)) + cancel_delayed_work(this_cpu_ptr(&vmstat_work)); + + } while (refresh_cpu_vm_stats(false)); +} + +/* * Check if the diffs for a certain cpu indicate that * an update is needed. */ @@ -1449,7 +1468,7 @@ static bool need_update(int cpu) */ static void vmstat_shepherd(struct work_struct *w); -static DECLARE_DELAYED_WORK(shepherd, vmstat_shepherd); +static DECLARE_DEFERRABLE_WORK(shepherd, vmstat_shepherd); static void vmstat_shepherd(struct work_struct *w) { diff --git a/mm/zbud.c b/mm/zbud.c index d8a181fd779b..b42322e50f63 100644 --- a/mm/zbud.c +++ b/mm/zbud.c @@ -463,9 +463,6 @@ void zbud_free(struct zbud_pool *pool, unsigned long handle) spin_unlock(&pool->lock); } -#define list_tail_entry(ptr, type, member) \ - list_entry((ptr)->prev, type, member) - /** * zbud_reclaim_page() - evicts allocations from a pool page and frees it * @pool: pool from which a page will attempt to be evicted @@ -514,7 +511,7 @@ int zbud_reclaim_page(struct zbud_pool *pool, unsigned int retries) return -EINVAL; } for (i = 0; i < retries; i++) { - zhdr = list_tail_entry(&pool->lru, struct zbud_header, lru); + zhdr = list_last_entry(&pool->lru, struct zbud_header, lru); list_del(&zhdr->lru); list_del(&zhdr->buddy); /* Protect zbud page against free */ diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 9f15bdd9163c..e7414cec220b 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -213,10 +213,10 @@ struct size_class { int size; unsigned int index; - /* Number of PAGE_SIZE sized pages to combine to form a 'zspage' */ - int pages_per_zspage; struct zs_size_stat stats; + /* Number of PAGE_SIZE sized pages to combine to form a 'zspage' */ + int pages_per_zspage; /* huge object: pages_per_zspage == 1 && maxobj_per_zspage == 1 */ bool huge; }; diff --git a/net/core/sock.c b/net/core/sock.c index 51270238e269..6c1c8bc93412 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -195,44 +195,6 @@ bool sk_net_capable(const struct sock *sk, int cap) } EXPORT_SYMBOL(sk_net_capable); - -#ifdef CONFIG_MEMCG_KMEM -int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss) -{ - struct proto *proto; - int ret = 0; - - mutex_lock(&proto_list_mutex); - list_for_each_entry(proto, &proto_list, node) { - if (proto->init_cgroup) { - ret = proto->init_cgroup(memcg, ss); - if (ret) - goto out; - } - } - - mutex_unlock(&proto_list_mutex); - return ret; -out: - list_for_each_entry_continue_reverse(proto, &proto_list, node) - if (proto->destroy_cgroup) - proto->destroy_cgroup(memcg); - mutex_unlock(&proto_list_mutex); - return ret; -} - -void mem_cgroup_sockets_destroy(struct mem_cgroup *memcg) -{ - struct proto *proto; - - mutex_lock(&proto_list_mutex); - list_for_each_entry_reverse(proto, &proto_list, node) - if (proto->destroy_cgroup) - proto->destroy_cgroup(memcg); - mutex_unlock(&proto_list_mutex); -} -#endif - /* * Each address family might have different locking rules, so we have * one slock key per address family: @@ -240,11 +202,6 @@ void mem_cgroup_sockets_destroy(struct mem_cgroup *memcg) static struct lock_class_key af_family_keys[AF_MAX]; static struct lock_class_key af_family_slock_keys[AF_MAX]; -#if defined(CONFIG_MEMCG_KMEM) -struct static_key memcg_socket_limit_enabled; -EXPORT_SYMBOL(memcg_socket_limit_enabled); -#endif - /* * Make lock validator output more readable. (we pre-construct these * strings build-time, so that runtime initialization of socket @@ -1507,12 +1464,6 @@ void sk_free(struct sock *sk) } EXPORT_SYMBOL(sk_free); -static void sk_update_clone(const struct sock *sk, struct sock *newsk) -{ - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) - sock_update_memcg(newsk); -} - /** * sk_clone_lock - clone a socket, and lock its clone * @sk: the socket to clone @@ -1607,7 +1558,8 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) sk_set_socket(newsk, NULL); newsk->sk_wq = NULL; - sk_update_clone(sk, newsk); + if (mem_cgroup_sockets_enabled && sk->sk_memcg) + sock_update_memcg(newsk); if (newsk->sk_prot->sockets_allocated) sk_sockets_allocated_inc(newsk); @@ -2089,27 +2041,27 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind) struct proto *prot = sk->sk_prot; int amt = sk_mem_pages(size); long allocated; - int parent_status = UNDER_LIMIT; sk->sk_forward_alloc += amt * SK_MEM_QUANTUM; - allocated = sk_memory_allocated_add(sk, amt, &parent_status); + allocated = sk_memory_allocated_add(sk, amt); + + if (mem_cgroup_sockets_enabled && sk->sk_memcg && + !mem_cgroup_charge_skmem(sk->sk_memcg, amt)) + goto suppress_allocation; /* Under limit. */ - if (parent_status == UNDER_LIMIT && - allocated <= sk_prot_mem_limits(sk, 0)) { + if (allocated <= sk_prot_mem_limits(sk, 0)) { sk_leave_memory_pressure(sk); return 1; } - /* Under pressure. (we or our parents) */ - if ((parent_status > SOFT_LIMIT) || - allocated > sk_prot_mem_limits(sk, 1)) + /* Under pressure. */ + if (allocated > sk_prot_mem_limits(sk, 1)) sk_enter_memory_pressure(sk); - /* Over hard limit (we or our parents) */ - if ((parent_status == OVER_LIMIT) || - (allocated > sk_prot_mem_limits(sk, 2))) + /* Over hard limit. */ + if (allocated > sk_prot_mem_limits(sk, 2)) goto suppress_allocation; /* guarantee minimum buffer size under pressure */ @@ -2158,6 +2110,9 @@ suppress_allocation: sk_memory_allocated_sub(sk, amt); + if (mem_cgroup_sockets_enabled && sk->sk_memcg) + mem_cgroup_uncharge_skmem(sk->sk_memcg, amt); + return 0; } EXPORT_SYMBOL(__sk_mem_schedule); @@ -2173,6 +2128,9 @@ void __sk_mem_reclaim(struct sock *sk, int amount) sk_memory_allocated_sub(sk, amount); sk->sk_forward_alloc -= amount << SK_MEM_QUANTUM_SHIFT; + if (mem_cgroup_sockets_enabled && sk->sk_memcg) + mem_cgroup_uncharge_skmem(sk->sk_memcg, amount); + if (sk_under_memory_pressure(sk) && (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0))) sk_leave_memory_pressure(sk); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 7bb1b091efd1..fd17eec93525 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -422,7 +422,8 @@ void tcp_init_sock(struct sock *sk) sk->sk_rcvbuf = sysctl_tcp_rmem[1]; local_bh_disable(); - sock_update_memcg(sk); + if (mem_cgroup_sockets_enabled) + sock_update_memcg(sk); sk_sockets_allocated_inc(sk); local_bh_enable(); } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 65947c1f4733..c7d1fb50f381 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1818,7 +1818,9 @@ void tcp_v4_destroy_sock(struct sock *sk) tcp_saved_syn_free(tp); sk_sockets_allocated_dec(sk); - sock_release_memcg(sk); + + if (mem_cgroup_sockets_enabled && sk->sk_memcg) + sock_release_memcg(sk); } EXPORT_SYMBOL(tcp_v4_destroy_sock); @@ -2342,11 +2344,6 @@ struct proto tcp_prot = { .compat_setsockopt = compat_tcp_setsockopt, .compat_getsockopt = compat_tcp_getsockopt, #endif -#ifdef CONFIG_MEMCG_KMEM - .init_cgroup = tcp_init_cgroup, - .destroy_cgroup = tcp_destroy_cgroup, - .proto_cgroup = tcp_proto_cgroup, -#endif .diag_destroy = tcp_abort, }; EXPORT_SYMBOL(tcp_prot); diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c index 2379c1b4efb2..18bc7f745e9c 100644 --- a/net/ipv4/tcp_memcontrol.c +++ b/net/ipv4/tcp_memcontrol.c @@ -8,75 +8,49 @@ int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss) { + struct mem_cgroup *parent = parent_mem_cgroup(memcg); + struct page_counter *counter_parent = NULL; /* * The root cgroup does not use page_counters, but rather, * rely on the data already collected by the network * subsystem */ - struct mem_cgroup *parent = parent_mem_cgroup(memcg); - struct page_counter *counter_parent = NULL; - struct cg_proto *cg_proto, *parent_cg; - - cg_proto = tcp_prot.proto_cgroup(memcg); - if (!cg_proto) + if (memcg == root_mem_cgroup) return 0; - cg_proto->sysctl_mem[0] = sysctl_tcp_mem[0]; - cg_proto->sysctl_mem[1] = sysctl_tcp_mem[1]; - cg_proto->sysctl_mem[2] = sysctl_tcp_mem[2]; - cg_proto->memory_pressure = 0; - cg_proto->memcg = memcg; + memcg->tcp_mem.memory_pressure = 0; - parent_cg = tcp_prot.proto_cgroup(parent); - if (parent_cg) - counter_parent = &parent_cg->memory_allocated; + if (parent) + counter_parent = &parent->tcp_mem.memory_allocated; - page_counter_init(&cg_proto->memory_allocated, counter_parent); - percpu_counter_init(&cg_proto->sockets_allocated, 0, GFP_KERNEL); + page_counter_init(&memcg->tcp_mem.memory_allocated, counter_parent); return 0; } -EXPORT_SYMBOL(tcp_init_cgroup); void tcp_destroy_cgroup(struct mem_cgroup *memcg) { - struct cg_proto *cg_proto; - - cg_proto = tcp_prot.proto_cgroup(memcg); - if (!cg_proto) + if (memcg == root_mem_cgroup) return; - percpu_counter_destroy(&cg_proto->sockets_allocated); - - if (test_bit(MEMCG_SOCK_ACTIVATED, &cg_proto->flags)) - static_key_slow_dec(&memcg_socket_limit_enabled); - + if (memcg->tcp_mem.active) + static_branch_dec(&memcg_sockets_enabled_key); } -EXPORT_SYMBOL(tcp_destroy_cgroup); static int tcp_update_limit(struct mem_cgroup *memcg, unsigned long nr_pages) { - struct cg_proto *cg_proto; - int i; int ret; - cg_proto = tcp_prot.proto_cgroup(memcg); - if (!cg_proto) + if (memcg == root_mem_cgroup) return -EINVAL; - ret = page_counter_limit(&cg_proto->memory_allocated, nr_pages); + ret = page_counter_limit(&memcg->tcp_mem.memory_allocated, nr_pages); if (ret) return ret; - for (i = 0; i < 3; i++) - cg_proto->sysctl_mem[i] = min_t(long, nr_pages, - sysctl_tcp_mem[i]); - - if (nr_pages == PAGE_COUNTER_MAX) - clear_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags); - else { + if (!memcg->tcp_mem.active) { /* - * The active bit needs to be written after the static_key + * The active flag needs to be written after the static_key * update. This is what guarantees that the socket activation * function is the last one to run. See sock_update_memcg() for * details, and note that we don't mark any socket as belonging @@ -90,14 +64,9 @@ static int tcp_update_limit(struct mem_cgroup *memcg, unsigned long nr_pages) * We never race with the readers in sock_update_memcg(), * because when this value change, the code to process it is not * patched in yet. - * - * The activated bit is used to guarantee that no two writers - * will do the update in the same memcg. Without that, we can't - * properly shutdown the static key. */ - if (!test_and_set_bit(MEMCG_SOCK_ACTIVATED, &cg_proto->flags)) - static_key_slow_inc(&memcg_socket_limit_enabled); - set_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags); + static_branch_inc(&memcg_sockets_enabled_key); + memcg->tcp_mem.active = true; } return 0; @@ -141,32 +110,32 @@ static ssize_t tcp_cgroup_write(struct kernfs_open_file *of, static u64 tcp_cgroup_read(struct cgroup_subsys_state *css, struct cftype *cft) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); - struct cg_proto *cg_proto = tcp_prot.proto_cgroup(memcg); u64 val; switch (cft->private) { case RES_LIMIT: - if (!cg_proto) - return PAGE_COUNTER_MAX; - val = cg_proto->memory_allocated.limit; + if (memcg == root_mem_cgroup) + val = PAGE_COUNTER_MAX; + else + val = memcg->tcp_mem.memory_allocated.limit; val *= PAGE_SIZE; break; case RES_USAGE: - if (!cg_proto) + if (memcg == root_mem_cgroup) val = atomic_long_read(&tcp_memory_allocated); else - val = page_counter_read(&cg_proto->memory_allocated); + val = page_counter_read(&memcg->tcp_mem.memory_allocated); val *= PAGE_SIZE; break; case RES_FAILCNT: - if (!cg_proto) + if (memcg == root_mem_cgroup) return 0; - val = cg_proto->memory_allocated.failcnt; + val = memcg->tcp_mem.memory_allocated.failcnt; break; case RES_MAX_USAGE: - if (!cg_proto) + if (memcg == root_mem_cgroup) return 0; - val = cg_proto->memory_allocated.watermark; + val = memcg->tcp_mem.memory_allocated.watermark; val *= PAGE_SIZE; break; default: @@ -179,19 +148,17 @@ static ssize_t tcp_cgroup_reset(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct mem_cgroup *memcg; - struct cg_proto *cg_proto; memcg = mem_cgroup_from_css(of_css(of)); - cg_proto = tcp_prot.proto_cgroup(memcg); - if (!cg_proto) + if (memcg == root_mem_cgroup) return nbytes; switch (of_cft(of)->private) { case RES_MAX_USAGE: - page_counter_reset_watermark(&cg_proto->memory_allocated); + page_counter_reset_watermark(&memcg->tcp_mem.memory_allocated); break; case RES_FAILCNT: - cg_proto->memory_allocated.failcnt = 0; + memcg->tcp_mem.memory_allocated.failcnt = 0; break; } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 412a920fe0ec..fda379cd600d 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2813,13 +2813,16 @@ begin_fwd: */ void sk_forced_mem_schedule(struct sock *sk, int size) { - int amt, status; + int amt; if (size <= sk->sk_forward_alloc) return; amt = sk_mem_pages(size); sk->sk_forward_alloc += amt * SK_MEM_QUANTUM; - sk_memory_allocated_add(sk, amt, &status); + sk_memory_allocated_add(sk, amt); + + if (mem_cgroup_sockets_enabled && sk->sk_memcg) + mem_cgroup_charge_skmem(sk->sk_memcg, amt); } /* Send a FIN. The caller locks the socket for us. diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index db9f1c318afc..4ad8edb46f7c 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1889,9 +1889,6 @@ struct proto tcpv6_prot = { .compat_setsockopt = compat_tcp_setsockopt, .compat_getsockopt = compat_tcp_getsockopt, #endif -#ifdef CONFIG_MEMCG_KMEM - .proto_cgroup = tcp_proto_cgroup, -#endif .clear_sk = tcp_v6_clear_sk, .diag_destroy = tcp_abort, }; diff --git a/net/socket.c b/net/socket.c index 91c2de6f5020..c044d1e8508c 100644 --- a/net/socket.c +++ b/net/socket.c @@ -294,7 +294,7 @@ static int init_inodecache(void) 0, (SLAB_HWCACHE_ALIGN | SLAB_RECLAIM_ACCOUNT | - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD | SLAB_ACCOUNT), init_once); if (sock_inode_cachep == NULL) return -ENOMEM; diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c index 59eeed43eda2..f0c6a8c78a56 100644 --- a/net/sunrpc/auth_gss/gss_rpc_upcall.c +++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c @@ -326,6 +326,9 @@ int gssp_accept_sec_context_upcall(struct net *net, if (data->found_creds && client_name.data != NULL) { char *c; + data->creds.cr_raw_principal = kstrndup(client_name.data, + client_name.len, GFP_KERNEL); + data->creds.cr_principal = kstrndup(client_name.data, client_name.len, GFP_KERNEL); if (data->creds.cr_principal) { diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 23608eb0ded2..b7f21044f4d8 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1217,6 +1217,7 @@ static int rpc_anyaddr(int family, struct sockaddr *buf, size_t buflen) return -EINVAL; memcpy(buf, &rpc_in6addr_loopback, sizeof(rpc_in6addr_loopback)); + break; default: dprintk("RPC: %s: address family not supported\n", __func__); diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index d81186d34558..14f45bf0410c 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -1500,7 +1500,7 @@ int register_rpc_pipefs(void) rpc_inode_cachep = kmem_cache_create("rpc_inode_cache", sizeof(struct rpc_inode), 0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (!rpc_inode_cachep) return -ENOMEM; diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index a6cbb2104667..7422f28818b2 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -10,11 +10,13 @@ #include <linux/kthread.h> #include <linux/slab.h> #include <net/sock.h> +#include <linux/sunrpc/addr.h> #include <linux/sunrpc/stats.h> #include <linux/sunrpc/svc_xprt.h> #include <linux/sunrpc/svcsock.h> #include <linux/sunrpc/xprt.h> #include <linux/module.h> +#include <linux/netdevice.h> #include <trace/events/sunrpc.h> #define RPCDBG_FACILITY RPCDBG_SVCXPRT @@ -938,6 +940,49 @@ static void svc_age_temp_xprts(unsigned long closure) mod_timer(&serv->sv_temptimer, jiffies + svc_conn_age_period * HZ); } +/* Close temporary transports whose xpt_local matches server_addr immediately + * instead of waiting for them to be picked up by the timer. + * + * This is meant to be called from a notifier_block that runs when an ip + * address is deleted. + */ +void svc_age_temp_xprts_now(struct svc_serv *serv, struct sockaddr *server_addr) +{ + struct svc_xprt *xprt; + struct svc_sock *svsk; + struct socket *sock; + struct list_head *le, *next; + LIST_HEAD(to_be_closed); + struct linger no_linger = { + .l_onoff = 1, + .l_linger = 0, + }; + + spin_lock_bh(&serv->sv_lock); + list_for_each_safe(le, next, &serv->sv_tempsocks) { + xprt = list_entry(le, struct svc_xprt, xpt_list); + if (rpc_cmp_addr(server_addr, (struct sockaddr *) + &xprt->xpt_local)) { + dprintk("svc_age_temp_xprts_now: found %p\n", xprt); + list_move(le, &to_be_closed); + } + } + spin_unlock_bh(&serv->sv_lock); + + while (!list_empty(&to_be_closed)) { + le = to_be_closed.next; + list_del_init(le); + xprt = list_entry(le, struct svc_xprt, xpt_list); + dprintk("svc_age_temp_xprts_now: closing %p\n", xprt); + svsk = container_of(xprt, struct svc_sock, sk_xprt); + sock = svsk->sk_sock; + kernel_setsockopt(sock, SOL_SOCKET, SO_LINGER, + (char *)&no_linger, sizeof(no_linger)); + svc_close_xprt(xprt); + } +} +EXPORT_SYMBOL_GPL(svc_age_temp_xprts_now); + static void call_xpt_users(struct svc_xprt *xprt) { struct svc_xpt_user *u; diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c index 79c0f3459b5c..69841db1f533 100644 --- a/net/sunrpc/svcauth.c +++ b/net/sunrpc/svcauth.c @@ -55,6 +55,7 @@ svc_authenticate(struct svc_rqst *rqstp, __be32 *authp) spin_unlock(&authtab_lock); rqstp->rq_auth_slack = 0; + init_svc_cred(&rqstp->rq_cred); rqstp->rq_authop = aops; return aops->accept(rqstp, authp); @@ -63,6 +64,7 @@ EXPORT_SYMBOL_GPL(svc_authenticate); int svc_set_client(struct svc_rqst *rqstp) { + rqstp->rq_client = NULL; return rqstp->rq_authop->set_client(rqstp); } EXPORT_SYMBOL_GPL(svc_set_client); diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 621ca7b4a155..dfacdc95b3f5 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -728,10 +728,6 @@ svcauth_null_accept(struct svc_rqst *rqstp, __be32 *authp) struct kvec *resv = &rqstp->rq_res.head[0]; struct svc_cred *cred = &rqstp->rq_cred; - cred->cr_group_info = NULL; - cred->cr_principal = NULL; - rqstp->rq_client = NULL; - if (argv->iov_len < 3*4) return SVC_GARBAGE; @@ -794,10 +790,6 @@ svcauth_unix_accept(struct svc_rqst *rqstp, __be32 *authp) u32 slen, i; int len = argv->iov_len; - cred->cr_group_info = NULL; - cred->cr_principal = NULL; - rqstp->rq_client = NULL; - if ((len -= 3*4) < 0) return SVC_GARBAGE; diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c index 2dcb44f69e53..cc1251d07297 100644 --- a/net/sunrpc/xprtrdma/backchannel.c +++ b/net/sunrpc/xprtrdma/backchannel.c @@ -15,7 +15,7 @@ # define RPCDBG_FACILITY RPCDBG_TRANS #endif -#define RPCRDMA_BACKCHANNEL_DEBUG +#undef RPCRDMA_BACKCHANNEL_DEBUG static void rpcrdma_bc_free_rqst(struct rpcrdma_xprt *r_xprt, struct rpc_rqst *rqst) @@ -42,8 +42,8 @@ static int rpcrdma_bc_setup_rqst(struct rpcrdma_xprt *r_xprt, size_t size; req = rpcrdma_create_req(r_xprt); - if (!req) - return -ENOMEM; + if (IS_ERR(req)) + return PTR_ERR(req); req->rl_backchannel = true; size = RPCRDMA_INLINE_WRITE_THRESHOLD(rqst); @@ -84,9 +84,7 @@ out_fail: static int rpcrdma_bc_setup_reps(struct rpcrdma_xprt *r_xprt, unsigned int count) { - struct rpcrdma_buffer *buffers = &r_xprt->rx_buf; struct rpcrdma_rep *rep; - unsigned long flags; int rc = 0; while (count--) { @@ -98,9 +96,7 @@ static int rpcrdma_bc_setup_reps(struct rpcrdma_xprt *r_xprt, break; } - spin_lock_irqsave(&buffers->rb_lock, flags); - list_add(&rep->rr_list, &buffers->rb_recv_bufs); - spin_unlock_irqrestore(&buffers->rb_lock, flags); + rpcrdma_recv_buffer_put(rep); } return rc; @@ -140,6 +136,7 @@ int xprt_rdma_bc_setup(struct rpc_xprt *xprt, unsigned int reqs) __func__); goto out_free; } + dprintk("RPC: %s: new rqst %p\n", __func__, rqst); rqst->rq_xprt = &r_xprt->rx_xprt; INIT_LIST_HEAD(&rqst->rq_list); @@ -220,12 +217,14 @@ int rpcrdma_bc_marshal_reply(struct rpc_rqst *rqst) rpclen = rqst->rq_svec[0].iov_len; +#ifdef RPCRDMA_BACKCHANNEL_DEBUG pr_info("RPC: %s: rpclen %zd headerp 0x%p lkey 0x%x\n", __func__, rpclen, headerp, rdmab_lkey(req->rl_rdmabuf)); pr_info("RPC: %s: RPC/RDMA: %*ph\n", __func__, (int)RPCRDMA_HDRLEN_MIN, headerp); pr_info("RPC: %s: RPC: %*ph\n", __func__, (int)rpclen, rqst->rq_svec[0].iov_base); +#endif req->rl_send_iov[0].addr = rdmab_addr(req->rl_rdmabuf); req->rl_send_iov[0].length = RPCRDMA_HDRLEN_MIN; @@ -269,6 +268,9 @@ void xprt_rdma_bc_free_rqst(struct rpc_rqst *rqst) { struct rpc_xprt *xprt = rqst->rq_xprt; + dprintk("RPC: %s: freeing rqst %p (req %p)\n", + __func__, rqst, rpcr_to_rdmar(rqst)); + smp_mb__before_atomic(); WARN_ON_ONCE(!test_bit(RPC_BC_PA_IN_USE, &rqst->rq_bc_pa_state)); clear_bit(RPC_BC_PA_IN_USE, &rqst->rq_bc_pa_state); @@ -333,9 +335,7 @@ void rpcrdma_bc_receive_call(struct rpcrdma_xprt *r_xprt, struct rpc_rqst, rq_bc_pa_list); list_del(&rqst->rq_bc_pa_list); spin_unlock(&xprt->bc_pa_lock); -#ifdef RPCRDMA_BACKCHANNEL_DEBUG - pr_info("RPC: %s: using rqst %p\n", __func__, rqst); -#endif + dprintk("RPC: %s: using rqst %p\n", __func__, rqst); /* Prepare rqst */ rqst->rq_reply_bytes_recvd = 0; @@ -355,10 +355,8 @@ void rpcrdma_bc_receive_call(struct rpcrdma_xprt *r_xprt, * direction reply. */ req = rpcr_to_rdmar(rqst); -#ifdef RPCRDMA_BACKCHANNEL_DEBUG - pr_info("RPC: %s: attaching rep %p to req %p\n", + dprintk("RPC: %s: attaching rep %p to req %p\n", __func__, rep, req); -#endif req->rl_reply = rep; /* Defeat the retransmit detection logic in send_request */ diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c index f1e8dafbd507..c14f3a4bff68 100644 --- a/net/sunrpc/xprtrdma/fmr_ops.c +++ b/net/sunrpc/xprtrdma/fmr_ops.c @@ -179,6 +179,69 @@ out_maperr: return rc; } +static void +__fmr_dma_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg) +{ + struct ib_device *device = r_xprt->rx_ia.ri_device; + struct rpcrdma_mw *mw = seg->rl_mw; + int nsegs = seg->mr_nsegs; + + seg->rl_mw = NULL; + + while (nsegs--) + rpcrdma_unmap_one(device, seg++); + + rpcrdma_put_mw(r_xprt, mw); +} + +/* Invalidate all memory regions that were registered for "req". + * + * Sleeps until it is safe for the host CPU to access the + * previously mapped memory regions. + */ +static void +fmr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) +{ + struct rpcrdma_mr_seg *seg; + unsigned int i, nchunks; + struct rpcrdma_mw *mw; + LIST_HEAD(unmap_list); + int rc; + + dprintk("RPC: %s: req %p\n", __func__, req); + + /* ORDER: Invalidate all of the req's MRs first + * + * ib_unmap_fmr() is slow, so use a single call instead + * of one call per mapped MR. + */ + for (i = 0, nchunks = req->rl_nchunks; nchunks; nchunks--) { + seg = &req->rl_segments[i]; + mw = seg->rl_mw; + + list_add(&mw->r.fmr.fmr->list, &unmap_list); + + i += seg->mr_nsegs; + } + rc = ib_unmap_fmr(&unmap_list); + if (rc) + pr_warn("%s: ib_unmap_fmr failed (%i)\n", __func__, rc); + + /* ORDER: Now DMA unmap all of the req's MRs, and return + * them to the free MW list. + */ + for (i = 0, nchunks = req->rl_nchunks; nchunks; nchunks--) { + seg = &req->rl_segments[i]; + + __fmr_dma_unmap(r_xprt, seg); + + i += seg->mr_nsegs; + seg->mr_nsegs = 0; + } + + req->rl_nchunks = 0; +} + /* Use the ib_unmap_fmr() verb to prevent further remote * access via RDMA READ or RDMA WRITE. */ @@ -231,6 +294,7 @@ fmr_op_destroy(struct rpcrdma_buffer *buf) const struct rpcrdma_memreg_ops rpcrdma_fmr_memreg_ops = { .ro_map = fmr_op_map, + .ro_unmap_sync = fmr_op_unmap_sync, .ro_unmap = fmr_op_unmap, .ro_open = fmr_op_open, .ro_maxpages = fmr_op_maxpages, diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index 88cf9e7269c2..c6836844bd0e 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -245,12 +245,14 @@ frwr_op_maxpages(struct rpcrdma_xprt *r_xprt) rpcrdma_max_segments(r_xprt) * ia->ri_max_frmr_depth); } -/* If FAST_REG or LOCAL_INV failed, indicate the frmr needs to be reset. */ +/* If FAST_REG or LOCAL_INV failed, indicate the frmr needs + * to be reset. + * + * WARNING: Only wr_id and status are reliable at this point + */ static void -frwr_sendcompletion(struct ib_wc *wc) +__frwr_sendcompletion_flush(struct ib_wc *wc, struct rpcrdma_mw *r) { - struct rpcrdma_mw *r; - if (likely(wc->status == IB_WC_SUCCESS)) return; @@ -261,9 +263,23 @@ frwr_sendcompletion(struct ib_wc *wc) else pr_warn("RPC: %s: frmr %p error, status %s (%d)\n", __func__, r, ib_wc_status_msg(wc->status), wc->status); + r->r.frmr.fr_state = FRMR_IS_STALE; } +static void +frwr_sendcompletion(struct ib_wc *wc) +{ + struct rpcrdma_mw *r = (struct rpcrdma_mw *)(unsigned long)wc->wr_id; + struct rpcrdma_frmr *f = &r->r.frmr; + + if (unlikely(wc->status != IB_WC_SUCCESS)) + __frwr_sendcompletion_flush(wc, r); + + if (f->fr_waiter) + complete(&f->fr_linv_done); +} + static int frwr_op_init(struct rpcrdma_xprt *r_xprt) { @@ -319,7 +335,7 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, struct rpcrdma_mw *mw; struct rpcrdma_frmr *frmr; struct ib_mr *mr; - struct ib_reg_wr reg_wr; + struct ib_reg_wr *reg_wr; struct ib_send_wr *bad_wr; int rc, i, n, dma_nents; u8 key; @@ -335,7 +351,9 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, } while (mw->r.frmr.fr_state != FRMR_IS_INVALID); frmr = &mw->r.frmr; frmr->fr_state = FRMR_IS_VALID; + frmr->fr_waiter = false; mr = frmr->fr_mr; + reg_wr = &frmr->fr_regwr; if (nsegs > ia->ri_max_frmr_depth) nsegs = ia->ri_max_frmr_depth; @@ -381,19 +399,19 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, key = (u8)(mr->rkey & 0x000000FF); ib_update_fast_reg_key(mr, ++key); - reg_wr.wr.next = NULL; - reg_wr.wr.opcode = IB_WR_REG_MR; - reg_wr.wr.wr_id = (uintptr_t)mw; - reg_wr.wr.num_sge = 0; - reg_wr.wr.send_flags = 0; - reg_wr.mr = mr; - reg_wr.key = mr->rkey; - reg_wr.access = writing ? - IB_ACCESS_REMOTE_WRITE | IB_ACCESS_LOCAL_WRITE : - IB_ACCESS_REMOTE_READ; + reg_wr->wr.next = NULL; + reg_wr->wr.opcode = IB_WR_REG_MR; + reg_wr->wr.wr_id = (uintptr_t)mw; + reg_wr->wr.num_sge = 0; + reg_wr->wr.send_flags = 0; + reg_wr->mr = mr; + reg_wr->key = mr->rkey; + reg_wr->access = writing ? + IB_ACCESS_REMOTE_WRITE | IB_ACCESS_LOCAL_WRITE : + IB_ACCESS_REMOTE_READ; DECR_CQCOUNT(&r_xprt->rx_ep); - rc = ib_post_send(ia->ri_id->qp, ®_wr.wr, &bad_wr); + rc = ib_post_send(ia->ri_id->qp, ®_wr->wr, &bad_wr); if (rc) goto out_senderr; @@ -413,6 +431,116 @@ out_senderr: return rc; } +static struct ib_send_wr * +__frwr_prepare_linv_wr(struct rpcrdma_mr_seg *seg) +{ + struct rpcrdma_mw *mw = seg->rl_mw; + struct rpcrdma_frmr *f = &mw->r.frmr; + struct ib_send_wr *invalidate_wr; + + f->fr_waiter = false; + f->fr_state = FRMR_IS_INVALID; + invalidate_wr = &f->fr_invwr; + + memset(invalidate_wr, 0, sizeof(*invalidate_wr)); + invalidate_wr->wr_id = (unsigned long)(void *)mw; + invalidate_wr->opcode = IB_WR_LOCAL_INV; + invalidate_wr->ex.invalidate_rkey = f->fr_mr->rkey; + + return invalidate_wr; +} + +static void +__frwr_dma_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, + int rc) +{ + struct ib_device *device = r_xprt->rx_ia.ri_device; + struct rpcrdma_mw *mw = seg->rl_mw; + struct rpcrdma_frmr *f = &mw->r.frmr; + + seg->rl_mw = NULL; + + ib_dma_unmap_sg(device, f->sg, f->sg_nents, seg->mr_dir); + + if (!rc) + rpcrdma_put_mw(r_xprt, mw); + else + __frwr_queue_recovery(mw); +} + +/* Invalidate all memory regions that were registered for "req". + * + * Sleeps until it is safe for the host CPU to access the + * previously mapped memory regions. + */ +static void +frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) +{ + struct ib_send_wr *invalidate_wrs, *pos, *prev, *bad_wr; + struct rpcrdma_ia *ia = &r_xprt->rx_ia; + struct rpcrdma_mr_seg *seg; + unsigned int i, nchunks; + struct rpcrdma_frmr *f; + int rc; + + dprintk("RPC: %s: req %p\n", __func__, req); + + /* ORDER: Invalidate all of the req's MRs first + * + * Chain the LOCAL_INV Work Requests and post them with + * a single ib_post_send() call. + */ + invalidate_wrs = pos = prev = NULL; + seg = NULL; + for (i = 0, nchunks = req->rl_nchunks; nchunks; nchunks--) { + seg = &req->rl_segments[i]; + + pos = __frwr_prepare_linv_wr(seg); + + if (!invalidate_wrs) + invalidate_wrs = pos; + else + prev->next = pos; + prev = pos; + + i += seg->mr_nsegs; + } + f = &seg->rl_mw->r.frmr; + + /* Strong send queue ordering guarantees that when the + * last WR in the chain completes, all WRs in the chain + * are complete. + */ + f->fr_invwr.send_flags = IB_SEND_SIGNALED; + f->fr_waiter = true; + init_completion(&f->fr_linv_done); + INIT_CQCOUNT(&r_xprt->rx_ep); + + /* Transport disconnect drains the receive CQ before it + * replaces the QP. The RPC reply handler won't call us + * unless ri_id->qp is a valid pointer. + */ + rc = ib_post_send(ia->ri_id->qp, invalidate_wrs, &bad_wr); + if (rc) + pr_warn("%s: ib_post_send failed %i\n", __func__, rc); + + wait_for_completion(&f->fr_linv_done); + + /* ORDER: Now DMA unmap all of the req's MRs, and return + * them to the free MW list. + */ + for (i = 0, nchunks = req->rl_nchunks; nchunks; nchunks--) { + seg = &req->rl_segments[i]; + + __frwr_dma_unmap(r_xprt, seg, rc); + + i += seg->mr_nsegs; + seg->mr_nsegs = 0; + } + + req->rl_nchunks = 0; +} + /* Post a LOCAL_INV Work Request to prevent further remote access * via RDMA READ or RDMA WRITE. */ @@ -423,23 +551,24 @@ frwr_op_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg) struct rpcrdma_ia *ia = &r_xprt->rx_ia; struct rpcrdma_mw *mw = seg1->rl_mw; struct rpcrdma_frmr *frmr = &mw->r.frmr; - struct ib_send_wr invalidate_wr, *bad_wr; + struct ib_send_wr *invalidate_wr, *bad_wr; int rc, nsegs = seg->mr_nsegs; dprintk("RPC: %s: FRMR %p\n", __func__, mw); seg1->rl_mw = NULL; frmr->fr_state = FRMR_IS_INVALID; + invalidate_wr = &mw->r.frmr.fr_invwr; - memset(&invalidate_wr, 0, sizeof(invalidate_wr)); - invalidate_wr.wr_id = (unsigned long)(void *)mw; - invalidate_wr.opcode = IB_WR_LOCAL_INV; - invalidate_wr.ex.invalidate_rkey = frmr->fr_mr->rkey; + memset(invalidate_wr, 0, sizeof(*invalidate_wr)); + invalidate_wr->wr_id = (uintptr_t)mw; + invalidate_wr->opcode = IB_WR_LOCAL_INV; + invalidate_wr->ex.invalidate_rkey = frmr->fr_mr->rkey; DECR_CQCOUNT(&r_xprt->rx_ep); ib_dma_unmap_sg(ia->ri_device, frmr->sg, frmr->sg_nents, seg1->mr_dir); read_lock(&ia->ri_qplock); - rc = ib_post_send(ia->ri_id->qp, &invalidate_wr, &bad_wr); + rc = ib_post_send(ia->ri_id->qp, invalidate_wr, &bad_wr); read_unlock(&ia->ri_qplock); if (rc) goto out_err; @@ -471,6 +600,7 @@ frwr_op_destroy(struct rpcrdma_buffer *buf) const struct rpcrdma_memreg_ops rpcrdma_frwr_memreg_ops = { .ro_map = frwr_op_map, + .ro_unmap_sync = frwr_op_unmap_sync, .ro_unmap = frwr_op_unmap, .ro_open = frwr_op_open, .ro_maxpages = frwr_op_maxpages, diff --git a/net/sunrpc/xprtrdma/physical_ops.c b/net/sunrpc/xprtrdma/physical_ops.c index 617b76f22154..dbb302ecf590 100644 --- a/net/sunrpc/xprtrdma/physical_ops.c +++ b/net/sunrpc/xprtrdma/physical_ops.c @@ -83,6 +83,18 @@ physical_op_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg) return 1; } +/* DMA unmap all memory regions that were mapped for "req". + */ +static void +physical_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) +{ + struct ib_device *device = r_xprt->rx_ia.ri_device; + unsigned int i; + + for (i = 0; req->rl_nchunks; --req->rl_nchunks) + rpcrdma_unmap_one(device, &req->rl_segments[i++]); +} + static void physical_op_destroy(struct rpcrdma_buffer *buf) { @@ -90,6 +102,7 @@ physical_op_destroy(struct rpcrdma_buffer *buf) const struct rpcrdma_memreg_ops rpcrdma_physical_memreg_ops = { .ro_map = physical_op_map, + .ro_unmap_sync = physical_op_unmap_sync, .ro_unmap = physical_op_unmap, .ro_open = physical_op_open, .ro_maxpages = physical_op_maxpages, diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index c10d9699441c..0f28f2d743ed 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -804,6 +804,11 @@ rpcrdma_reply_handler(struct rpcrdma_rep *rep) if (req->rl_reply) goto out_duplicate; + /* Sanity checking has passed. We are now committed + * to complete this transaction. + */ + list_del_init(&rqst->rq_list); + spin_unlock_bh(&xprt->transport_lock); dprintk("RPC: %s: reply 0x%p completes request 0x%p\n" " RPC request 0x%p xid 0x%08x\n", __func__, rep, req, rqst, @@ -888,12 +893,23 @@ badheader: break; } + /* Invalidate and flush the data payloads before waking the + * waiting application. This guarantees the memory region is + * properly fenced from the server before the application + * accesses the data. It also ensures proper send flow + * control: waking the next RPC waits until this RPC has + * relinquished all its Send Queue entries. + */ + if (req->rl_nchunks) + r_xprt->rx_ia.ri_ops->ro_unmap_sync(r_xprt, req); + credits = be32_to_cpu(headerp->rm_credit); if (credits == 0) credits = 1; /* don't deadlock */ else if (credits > r_xprt->rx_buf.rb_max_requests) credits = r_xprt->rx_buf.rb_max_requests; + spin_lock_bh(&xprt->transport_lock); cwnd = xprt->cwnd; xprt->cwnd = credits << RPC_CWNDSHIFT; if (xprt->cwnd > cwnd) diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 8c545f7d7525..740bddcf3488 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -576,6 +576,9 @@ xprt_rdma_free(void *buffer) rb = container_of(buffer, struct rpcrdma_regbuf, rg_base[0]); req = rb->rg_owner; + if (req->rl_backchannel) + return; + r_xprt = container_of(req->rl_buffer, struct rpcrdma_xprt, rx_buf); dprintk("RPC: %s: called on 0x%p\n", __func__, req->rl_reply); diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index eadd1655145a..732c71ce5dca 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -616,10 +616,8 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, /* set trigger for requesting send completion */ ep->rep_cqinit = ep->rep_attr.cap.max_send_wr/2 - 1; - if (ep->rep_cqinit > RPCRDMA_MAX_UNSIGNALED_SENDS) - ep->rep_cqinit = RPCRDMA_MAX_UNSIGNALED_SENDS; - else if (ep->rep_cqinit <= 2) - ep->rep_cqinit = 0; + if (ep->rep_cqinit <= 2) + ep->rep_cqinit = 0; /* always signal? */ INIT_CQCOUNT(ep); init_waitqueue_head(&ep->rep_connect_wait); INIT_DELAYED_WORK(&ep->rep_connect_worker, rpcrdma_connect_worker); @@ -852,10 +850,11 @@ retry: if (extras) { rc = rpcrdma_ep_post_extra_recv(r_xprt, extras); - if (rc) + if (rc) { pr_warn("%s: rpcrdma_ep_post_extra_recv: %i\n", __func__, rc); rc = 0; + } } } @@ -1337,15 +1336,14 @@ rpcrdma_ep_post_extra_recv(struct rpcrdma_xprt *r_xprt, unsigned int count) struct rpcrdma_ia *ia = &r_xprt->rx_ia; struct rpcrdma_ep *ep = &r_xprt->rx_ep; struct rpcrdma_rep *rep; - unsigned long flags; int rc; while (count--) { - spin_lock_irqsave(&buffers->rb_lock, flags); + spin_lock(&buffers->rb_lock); if (list_empty(&buffers->rb_recv_bufs)) goto out_reqbuf; rep = rpcrdma_buffer_get_rep_locked(buffers); - spin_unlock_irqrestore(&buffers->rb_lock, flags); + spin_unlock(&buffers->rb_lock); rc = rpcrdma_ep_post_recv(ia, ep, rep); if (rc) @@ -1355,7 +1353,7 @@ rpcrdma_ep_post_extra_recv(struct rpcrdma_xprt *r_xprt, unsigned int count) return 0; out_reqbuf: - spin_unlock_irqrestore(&buffers->rb_lock, flags); + spin_unlock(&buffers->rb_lock); pr_warn("%s: no extra receive buffers\n", __func__); return -ENOMEM; diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index ac7f8d4f632a..728101ddc44b 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -88,12 +88,6 @@ struct rpcrdma_ep { struct delayed_work rep_connect_worker; }; -/* - * Force a signaled SEND Work Request every so often, - * in case the provider needs to do some housekeeping. - */ -#define RPCRDMA_MAX_UNSIGNALED_SENDS (32) - #define INIT_CQCOUNT(ep) atomic_set(&(ep)->rep_cqcount, (ep)->rep_cqinit) #define DECR_CQCOUNT(ep) atomic_sub_return(1, &(ep)->rep_cqcount) @@ -207,6 +201,12 @@ struct rpcrdma_frmr { enum rpcrdma_frmr_state fr_state; struct work_struct fr_work; struct rpcrdma_xprt *fr_xprt; + bool fr_waiter; + struct completion fr_linv_done;; + union { + struct ib_reg_wr fr_regwr; + struct ib_send_wr fr_invwr; + }; }; struct rpcrdma_fmr { @@ -364,6 +364,8 @@ struct rpcrdma_xprt; struct rpcrdma_memreg_ops { int (*ro_map)(struct rpcrdma_xprt *, struct rpcrdma_mr_seg *, int, bool); + void (*ro_unmap_sync)(struct rpcrdma_xprt *, + struct rpcrdma_req *); int (*ro_unmap)(struct rpcrdma_xprt *, struct rpcrdma_mr_seg *); int (*ro_open)(struct rpcrdma_ia *, diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 2ffaf6a79499..fde2138b81e7 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -398,7 +398,6 @@ static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, if (unlikely(!sock)) return -ENOTSOCK; - clear_bit(SOCKWQ_ASYNC_NOSPACE, &sock->flags); if (base != 0) { addr = NULL; addrlen = 0; @@ -442,7 +441,6 @@ static void xs_nospace_callback(struct rpc_task *task) struct sock_xprt *transport = container_of(task->tk_rqstp->rq_xprt, struct sock_xprt, xprt); transport->inet->sk_write_pending--; - clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags); } /** @@ -467,20 +465,11 @@ static int xs_nospace(struct rpc_task *task) /* Don't race with disconnect */ if (xprt_connected(xprt)) { - if (test_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags)) { - /* - * Notify TCP that we're limited by the application - * window size - */ - set_bit(SOCK_NOSPACE, &transport->sock->flags); - sk->sk_write_pending++; - /* ...and wait for more buffer space */ - xprt_wait_for_buffer_space(task, xs_nospace_callback); - } - } else { - clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags); + /* wait for more buffer space */ + sk->sk_write_pending++; + xprt_wait_for_buffer_space(task, xs_nospace_callback); + } else ret = -ENOTCONN; - } spin_unlock_bh(&xprt->transport_lock); @@ -616,9 +605,6 @@ process_status: case -EAGAIN: status = xs_nospace(task); break; - default: - dprintk("RPC: sendmsg returned unrecognized error %d\n", - -status); case -ENETUNREACH: case -ENOBUFS: case -EPIPE: @@ -626,7 +612,10 @@ process_status: case -EPERM: /* When the server has died, an ICMP port unreachable message * prompts ECONNREFUSED. */ - clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags); + break; + default: + dprintk("RPC: sendmsg returned unrecognized error %d\n", + -status); } return status; @@ -706,16 +695,16 @@ static int xs_tcp_send_request(struct rpc_task *task) case -EAGAIN: status = xs_nospace(task); break; - default: - dprintk("RPC: sendmsg returned unrecognized error %d\n", - -status); case -ECONNRESET: case -ECONNREFUSED: case -ENOTCONN: case -EADDRINUSE: case -ENOBUFS: case -EPIPE: - clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags); + break; + default: + dprintk("RPC: sendmsg returned unrecognized error %d\n", + -status); } return status; @@ -1609,19 +1598,23 @@ static void xs_tcp_state_change(struct sock *sk) static void xs_write_space(struct sock *sk) { - struct socket *sock; + struct socket_wq *wq; struct rpc_xprt *xprt; - if (unlikely(!(sock = sk->sk_socket))) + if (!sk->sk_socket) return; - clear_bit(SOCK_NOSPACE, &sock->flags); + clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags); if (unlikely(!(xprt = xprt_from_sock(sk)))) return; - if (test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &sock->flags) == 0) - return; + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (!wq || test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &wq->flags) == 0) + goto out; xprt_write_space(xprt); +out: + rcu_read_unlock(); } /** @@ -1907,18 +1900,6 @@ static inline void xs_reclassify_socket(int family, struct socket *sock) } } #else -static inline void xs_reclassify_socketu(struct socket *sock) -{ -} - -static inline void xs_reclassify_socket4(struct socket *sock) -{ -} - -static inline void xs_reclassify_socket6(struct socket *sock) -{ -} - static inline void xs_reclassify_socket(int family, struct socket *sock) { } @@ -2008,7 +1989,7 @@ static int xs_local_setup_socket(struct sock_xprt *transport) "transport socket (%d).\n", -status); goto out; } - xs_reclassify_socketu(sock); + xs_reclassify_socket(AF_LOCAL, sock); dprintk("RPC: worker connecting xprt %p via AF_LOCAL to %s\n", xprt, xprt->address_strings[RPC_DISPLAY_ADDR]); diff --git a/scripts/bloat-o-meter b/scripts/bloat-o-meter index 23e78dcd12bf..38b64f487315 100755 --- a/scripts/bloat-o-meter +++ b/scripts/bloat-o-meter @@ -58,8 +58,8 @@ for name in common: delta.sort() delta.reverse() -print "add/remove: %s/%s grow/shrink: %s/%s up/down: %s/%s (%s)" % \ - (add, remove, grow, shrink, up, -down, up-down) -print "%-40s %7s %7s %+7s" % ("function", "old", "new", "delta") +print("add/remove: %s/%s grow/shrink: %s/%s up/down: %s/%s (%s)" % \ + (add, remove, grow, shrink, up, -down, up-down)) +print("%-40s %7s %7s %+7s" % ("function", "old", "new", "delta")) for d, n in delta: - if d: print "%-40s %7s %7s %+7d" % (n, old.get(n,"-"), new.get(n,"-"), d) + if d: print("%-40s %7s %7s %+7d" % (n, old.get(n,"-"), new.get(n,"-"), d)) diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index 8adca4406198..161dd0d67da8 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -125,7 +125,7 @@ do { \ sprintf(str + strlen(str), "*"); \ } while(0) -/* Always end in a wildcard, for future extension */ +/* End in a wildcard, for future extension */ static inline void add_wildcard(char *str) { int len = strlen(str); @@ -704,7 +704,6 @@ static int do_of_entry (const char *filename, void *symval, char *alias) if (isspace (*tmp)) *tmp = '_'; - add_wildcard(alias); return 1; } ADD_TO_DEVTABLE("of", of_device_id, do_of_entry); diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl index 826470d7f000..96e2486a6fc4 100755 --- a/scripts/recordmcount.pl +++ b/scripts/recordmcount.pl @@ -263,7 +263,8 @@ if ($arch eq "x86_64") { } elsif ($arch eq "powerpc") { $local_regex = "^[0-9a-fA-F]+\\s+t\\s+(\\.?\\S+)"; - $function_regex = "^([0-9a-fA-F]+)\\s+<(\\.?.*?)>:"; + # See comment in the sparc64 section for why we use '\w'. + $function_regex = "^([0-9a-fA-F]+)\\s+<(\\.?\\w*?)>:"; $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\s\\.?_mcount\$"; if ($bits == 64) { diff --git a/sound/drivers/pcm-indirect2.c b/sound/drivers/pcm-indirect2.c index e73fafd761b3..d16bc14a0f0e 100644 --- a/sound/drivers/pcm-indirect2.c +++ b/sound/drivers/pcm-indirect2.c @@ -47,7 +47,7 @@ void snd_pcm_indirect2_stat(struct snd_pcm_substream *substream, int seconds = (rec->lastbytetime - rec->firstbytetime) / HZ; snd_printk(KERN_DEBUG "STAT: mul_elapsed: %u, mul_elapsed_real: %d, " - "irq_occured: %d\n", + "irq_occurred: %d\n", rec->mul_elapsed, rec->mul_elapsed_real, rec->irq_occured); snd_printk(KERN_DEBUG "STAT: min_multiple: %d (irqs/period)\n", rec->min_multiple); diff --git a/sound/usb/6fire/firmware.c b/sound/usb/6fire/firmware.c index 62c25e74f0e5..9520b4cd7038 100644 --- a/sound/usb/6fire/firmware.c +++ b/sound/usb/6fire/firmware.c @@ -350,7 +350,7 @@ static int usb6fire_fw_check(struct usb_interface *intf, const u8 *version) if (!memcmp(version, known_fw_versions + i, 2)) return 0; - dev_err(&intf->dev, "invalid fimware version in device: %4ph. " + dev_err(&intf->dev, "invalid firmware version in device: %4ph. " "please reconnect to power. if this failure " "still happens, check your firmware installation.", version); diff --git a/tools/Makefile b/tools/Makefile index 1dc6900468ed..6339f6ac3ccb 100644 --- a/tools/Makefile +++ b/tools/Makefile @@ -8,24 +8,24 @@ include scripts/Makefile.include help: @echo 'Possible targets:' @echo '' - @echo ' acpi - ACPI tools' - @echo ' cgroup - cgroup tools' - @echo ' cpupower - a tool for all things x86 CPU power' - @echo ' firewire - the userspace part of nosy, an IEEE-1394 traffic sniffer' - @echo ' hv - tools used when in Hyper-V clients' - @echo ' iio - IIO tools' - @echo ' lguest - a minimal 32-bit x86 hypervisor' - @echo ' perf - Linux performance measurement and analysis tool' - @echo ' selftests - various kernel selftests' - @echo ' spi - spi tools' - @echo ' turbostat - Intel CPU idle stats and freq reporting tool' - @echo ' usb - USB testing tools' - @echo ' virtio - vhost test module' - @echo ' net - misc networking tools' - @echo ' vm - misc vm tools' + @echo ' acpi - ACPI tools' + @echo ' cgroup - cgroup tools' + @echo ' cpupower - a tool for all things x86 CPU power' + @echo ' firewire - the userspace part of nosy, an IEEE-1394 traffic sniffer' + @echo ' freefall - laptop accelerometer program for disk protection' + @echo ' hv - tools used when in Hyper-V clients' + @echo ' iio - IIO tools' + @echo ' lguest - a minimal 32-bit x86 hypervisor' + @echo ' net - misc networking tools' + @echo ' perf - Linux performance measurement and analysis tool' + @echo ' selftests - various kernel selftests' + @echo ' spi - spi tools' + @echo ' tmon - thermal monitoring and tuning tool' + @echo ' turbostat - Intel CPU idle stats and freq reporting tool' + @echo ' usb - USB testing tools' + @echo ' virtio - vhost test module' + @echo ' vm - misc vm tools' @echo ' x86_energy_perf_policy - Intel energy policy tool' - @echo ' tmon - thermal monitoring and tuning tool' - @echo ' freefall - laptop accelerometer program for disk protection' @echo '' @echo 'You can do:' @echo ' $$ make -C tools/ <tool>_install' @@ -128,6 +128,12 @@ liblockdep_clean: libapi_clean: $(call descend,lib/api,clean) +libbpf_clean: + $(call descend,lib/bpf,clean) + +libsubcmd_clean: + $(call descend,lib/subcmd,clean) + perf_clean: $(call descend,$(@:_clean=),clean) @@ -143,9 +149,12 @@ tmon_clean: freefall_clean: $(call descend,laptop/freefall,clean) +build_clean: + $(call descend,build,clean) + clean: acpi_clean cgroup_clean cpupower_clean hv_clean firewire_clean lguest_clean \ perf_clean selftests_clean turbostat_clean spi_clean usb_clean virtio_clean \ vm_clean net_clean iio_clean x86_energy_perf_policy_clean tmon_clean \ - freefall_clean + freefall_clean build_clean libbpf_clean libsubcmd_clean liblockdep_clean .PHONY: FORCE diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c index 33cf6f20bd4e..81025cade45f 100644 --- a/tools/build/feature/test-all.c +++ b/tools/build/feature/test-all.c @@ -125,6 +125,10 @@ # include "test-get_cpuid.c" #undef main +#define main main_test_bpf +# include "test-bpf.c" +#undef main + int main(int argc, char *argv[]) { main_test_libpython(); @@ -153,6 +157,7 @@ int main(int argc, char *argv[]) main_test_pthread_attr_setaffinity_np(); main_test_lzma(); main_test_get_cpuid(); + main_test_bpf(); return 0; } diff --git a/tools/build/feature/test-bpf.c b/tools/build/feature/test-bpf.c index 062bac811af9..b389026839b9 100644 --- a/tools/build/feature/test-bpf.c +++ b/tools/build/feature/test-bpf.c @@ -1,9 +1,23 @@ +#include <asm/unistd.h> #include <linux/bpf.h> +#include <unistd.h> + +#ifndef __NR_bpf +# if defined(__i386__) +# define __NR_bpf 357 +# elif defined(__x86_64__) +# define __NR_bpf 321 +# elif defined(__aarch64__) +# define __NR_bpf 280 +# error __NR_bpf not defined. libbpf does not support your arch. +# endif +#endif int main(void) { union bpf_attr attr; + /* Check fields in attr */ attr.prog_type = BPF_PROG_TYPE_KPROBE; attr.insn_cnt = 0; attr.insns = 0; @@ -14,5 +28,9 @@ int main(void) attr.kern_version = 0; attr = attr; - return 0; + /* + * Test existence of __NR_bpf and BPF_PROG_LOAD. + * This call should fail if we run the testcase. + */ + return syscall(__NR_bpf, BPF_PROG_LOAD, attr, sizeof(attr)); } diff --git a/tools/include/linux/list.h b/tools/include/linux/list.h index a017f1595676..1da423820ad4 100644 --- a/tools/include/linux/list.h +++ b/tools/include/linux/list.h @@ -1,11 +1,751 @@ -#include <linux/compiler.h> -#include <linux/kernel.h> +#ifndef __TOOLS_LINUX_LIST_H +#define __TOOLS_LINUX_LIST_H + #include <linux/types.h> +#include <linux/poison.h> +#include <linux/kernel.h> +#include <linux/compiler.h> + +/* + * Simple doubly linked list implementation. + * + * Some of the internal functions ("__xxx") are useful when + * manipulating whole lists rather than single entries, as + * sometimes we already know the next/prev entries and we can + * generate better code by using them directly rather than + * using the generic single-entry routines. + */ + +#define LIST_HEAD_INIT(name) { &(name), &(name) } + +#define LIST_HEAD(name) \ + struct list_head name = LIST_HEAD_INIT(name) + +static inline void INIT_LIST_HEAD(struct list_head *list) +{ + list->next = list; + list->prev = list; +} + +/* + * Insert a new entry between two known consecutive entries. + * + * This is only for internal list manipulation where we know + * the prev/next entries already! + */ +#ifndef CONFIG_DEBUG_LIST +static inline void __list_add(struct list_head *new, + struct list_head *prev, + struct list_head *next) +{ + next->prev = new; + new->next = next; + new->prev = prev; + prev->next = new; +} +#else +extern void __list_add(struct list_head *new, + struct list_head *prev, + struct list_head *next); +#endif + +/** + * list_add - add a new entry + * @new: new entry to be added + * @head: list head to add it after + * + * Insert a new entry after the specified head. + * This is good for implementing stacks. + */ +static inline void list_add(struct list_head *new, struct list_head *head) +{ + __list_add(new, head, head->next); +} + + +/** + * list_add_tail - add a new entry + * @new: new entry to be added + * @head: list head to add it before + * + * Insert a new entry before the specified head. + * This is useful for implementing queues. + */ +static inline void list_add_tail(struct list_head *new, struct list_head *head) +{ + __list_add(new, head->prev, head); +} + +/* + * Delete a list entry by making the prev/next entries + * point to each other. + * + * This is only for internal list manipulation where we know + * the prev/next entries already! + */ +static inline void __list_del(struct list_head * prev, struct list_head * next) +{ + next->prev = prev; + WRITE_ONCE(prev->next, next); +} + +/** + * list_del - deletes entry from list. + * @entry: the element to delete from the list. + * Note: list_empty() on entry does not return true after this, the entry is + * in an undefined state. + */ +#ifndef CONFIG_DEBUG_LIST +static inline void __list_del_entry(struct list_head *entry) +{ + __list_del(entry->prev, entry->next); +} + +static inline void list_del(struct list_head *entry) +{ + __list_del(entry->prev, entry->next); + entry->next = LIST_POISON1; + entry->prev = LIST_POISON2; +} +#else +extern void __list_del_entry(struct list_head *entry); +extern void list_del(struct list_head *entry); +#endif + +/** + * list_replace - replace old entry by new one + * @old : the element to be replaced + * @new : the new element to insert + * + * If @old was empty, it will be overwritten. + */ +static inline void list_replace(struct list_head *old, + struct list_head *new) +{ + new->next = old->next; + new->next->prev = new; + new->prev = old->prev; + new->prev->next = new; +} + +static inline void list_replace_init(struct list_head *old, + struct list_head *new) +{ + list_replace(old, new); + INIT_LIST_HEAD(old); +} + +/** + * list_del_init - deletes entry from list and reinitialize it. + * @entry: the element to delete from the list. + */ +static inline void list_del_init(struct list_head *entry) +{ + __list_del_entry(entry); + INIT_LIST_HEAD(entry); +} + +/** + * list_move - delete from one list and add as another's head + * @list: the entry to move + * @head: the head that will precede our entry + */ +static inline void list_move(struct list_head *list, struct list_head *head) +{ + __list_del_entry(list); + list_add(list, head); +} + +/** + * list_move_tail - delete from one list and add as another's tail + * @list: the entry to move + * @head: the head that will follow our entry + */ +static inline void list_move_tail(struct list_head *list, + struct list_head *head) +{ + __list_del_entry(list); + list_add_tail(list, head); +} + +/** + * list_is_last - tests whether @list is the last entry in list @head + * @list: the entry to test + * @head: the head of the list + */ +static inline int list_is_last(const struct list_head *list, + const struct list_head *head) +{ + return list->next == head; +} + +/** + * list_empty - tests whether a list is empty + * @head: the list to test. + */ +static inline int list_empty(const struct list_head *head) +{ + return head->next == head; +} + +/** + * list_empty_careful - tests whether a list is empty and not being modified + * @head: the list to test + * + * Description: + * tests whether a list is empty _and_ checks that no other CPU might be + * in the process of modifying either member (next or prev) + * + * NOTE: using list_empty_careful() without synchronization + * can only be safe if the only activity that can happen + * to the list entry is list_del_init(). Eg. it cannot be used + * if another CPU could re-list_add() it. + */ +static inline int list_empty_careful(const struct list_head *head) +{ + struct list_head *next = head->next; + return (next == head) && (next == head->prev); +} + +/** + * list_rotate_left - rotate the list to the left + * @head: the head of the list + */ +static inline void list_rotate_left(struct list_head *head) +{ + struct list_head *first; + + if (!list_empty(head)) { + first = head->next; + list_move_tail(first, head); + } +} + +/** + * list_is_singular - tests whether a list has just one entry. + * @head: the list to test. + */ +static inline int list_is_singular(const struct list_head *head) +{ + return !list_empty(head) && (head->next == head->prev); +} + +static inline void __list_cut_position(struct list_head *list, + struct list_head *head, struct list_head *entry) +{ + struct list_head *new_first = entry->next; + list->next = head->next; + list->next->prev = list; + list->prev = entry; + entry->next = list; + head->next = new_first; + new_first->prev = head; +} + +/** + * list_cut_position - cut a list into two + * @list: a new list to add all removed entries + * @head: a list with entries + * @entry: an entry within head, could be the head itself + * and if so we won't cut the list + * + * This helper moves the initial part of @head, up to and + * including @entry, from @head to @list. You should + * pass on @entry an element you know is on @head. @list + * should be an empty list or a list you do not care about + * losing its data. + * + */ +static inline void list_cut_position(struct list_head *list, + struct list_head *head, struct list_head *entry) +{ + if (list_empty(head)) + return; + if (list_is_singular(head) && + (head->next != entry && head != entry)) + return; + if (entry == head) + INIT_LIST_HEAD(list); + else + __list_cut_position(list, head, entry); +} + +static inline void __list_splice(const struct list_head *list, + struct list_head *prev, + struct list_head *next) +{ + struct list_head *first = list->next; + struct list_head *last = list->prev; + + first->prev = prev; + prev->next = first; + + last->next = next; + next->prev = last; +} + +/** + * list_splice - join two lists, this is designed for stacks + * @list: the new list to add. + * @head: the place to add it in the first list. + */ +static inline void list_splice(const struct list_head *list, + struct list_head *head) +{ + if (!list_empty(list)) + __list_splice(list, head, head->next); +} + +/** + * list_splice_tail - join two lists, each list being a queue + * @list: the new list to add. + * @head: the place to add it in the first list. + */ +static inline void list_splice_tail(struct list_head *list, + struct list_head *head) +{ + if (!list_empty(list)) + __list_splice(list, head->prev, head); +} + +/** + * list_splice_init - join two lists and reinitialise the emptied list. + * @list: the new list to add. + * @head: the place to add it in the first list. + * + * The list at @list is reinitialised + */ +static inline void list_splice_init(struct list_head *list, + struct list_head *head) +{ + if (!list_empty(list)) { + __list_splice(list, head, head->next); + INIT_LIST_HEAD(list); + } +} + +/** + * list_splice_tail_init - join two lists and reinitialise the emptied list + * @list: the new list to add. + * @head: the place to add it in the first list. + * + * Each of the lists is a queue. + * The list at @list is reinitialised + */ +static inline void list_splice_tail_init(struct list_head *list, + struct list_head *head) +{ + if (!list_empty(list)) { + __list_splice(list, head->prev, head); + INIT_LIST_HEAD(list); + } +} + +/** + * list_entry - get the struct for this entry + * @ptr: the &struct list_head pointer. + * @type: the type of the struct this is embedded in. + * @member: the name of the list_head within the struct. + */ +#define list_entry(ptr, type, member) \ + container_of(ptr, type, member) + +/** + * list_first_entry - get the first element from a list + * @ptr: the list head to take the element from. + * @type: the type of the struct this is embedded in. + * @member: the name of the list_head within the struct. + * + * Note, that list is expected to be not empty. + */ +#define list_first_entry(ptr, type, member) \ + list_entry((ptr)->next, type, member) + +/** + * list_last_entry - get the last element from a list + * @ptr: the list head to take the element from. + * @type: the type of the struct this is embedded in. + * @member: the name of the list_head within the struct. + * + * Note, that list is expected to be not empty. + */ +#define list_last_entry(ptr, type, member) \ + list_entry((ptr)->prev, type, member) + +/** + * list_first_entry_or_null - get the first element from a list + * @ptr: the list head to take the element from. + * @type: the type of the struct this is embedded in. + * @member: the name of the list_head within the struct. + * + * Note that if the list is empty, it returns NULL. + */ +#define list_first_entry_or_null(ptr, type, member) \ + (!list_empty(ptr) ? list_first_entry(ptr, type, member) : NULL) + +/** + * list_next_entry - get the next element in list + * @pos: the type * to cursor + * @member: the name of the list_head within the struct. + */ +#define list_next_entry(pos, member) \ + list_entry((pos)->member.next, typeof(*(pos)), member) + +/** + * list_prev_entry - get the prev element in list + * @pos: the type * to cursor + * @member: the name of the list_head within the struct. + */ +#define list_prev_entry(pos, member) \ + list_entry((pos)->member.prev, typeof(*(pos)), member) + +/** + * list_for_each - iterate over a list + * @pos: the &struct list_head to use as a loop cursor. + * @head: the head for your list. + */ +#define list_for_each(pos, head) \ + for (pos = (head)->next; pos != (head); pos = pos->next) + +/** + * list_for_each_prev - iterate over a list backwards + * @pos: the &struct list_head to use as a loop cursor. + * @head: the head for your list. + */ +#define list_for_each_prev(pos, head) \ + for (pos = (head)->prev; pos != (head); pos = pos->prev) + +/** + * list_for_each_safe - iterate over a list safe against removal of list entry + * @pos: the &struct list_head to use as a loop cursor. + * @n: another &struct list_head to use as temporary storage + * @head: the head for your list. + */ +#define list_for_each_safe(pos, n, head) \ + for (pos = (head)->next, n = pos->next; pos != (head); \ + pos = n, n = pos->next) + +/** + * list_for_each_prev_safe - iterate over a list backwards safe against removal of list entry + * @pos: the &struct list_head to use as a loop cursor. + * @n: another &struct list_head to use as temporary storage + * @head: the head for your list. + */ +#define list_for_each_prev_safe(pos, n, head) \ + for (pos = (head)->prev, n = pos->prev; \ + pos != (head); \ + pos = n, n = pos->prev) + +/** + * list_for_each_entry - iterate over list of given type + * @pos: the type * to use as a loop cursor. + * @head: the head for your list. + * @member: the name of the list_head within the struct. + */ +#define list_for_each_entry(pos, head, member) \ + for (pos = list_first_entry(head, typeof(*pos), member); \ + &pos->member != (head); \ + pos = list_next_entry(pos, member)) + +/** + * list_for_each_entry_reverse - iterate backwards over list of given type. + * @pos: the type * to use as a loop cursor. + * @head: the head for your list. + * @member: the name of the list_head within the struct. + */ +#define list_for_each_entry_reverse(pos, head, member) \ + for (pos = list_last_entry(head, typeof(*pos), member); \ + &pos->member != (head); \ + pos = list_prev_entry(pos, member)) + +/** + * list_prepare_entry - prepare a pos entry for use in list_for_each_entry_continue() + * @pos: the type * to use as a start point + * @head: the head of the list + * @member: the name of the list_head within the struct. + * + * Prepares a pos entry for use as a start point in list_for_each_entry_continue(). + */ +#define list_prepare_entry(pos, head, member) \ + ((pos) ? : list_entry(head, typeof(*pos), member)) + +/** + * list_for_each_entry_continue - continue iteration over list of given type + * @pos: the type * to use as a loop cursor. + * @head: the head for your list. + * @member: the name of the list_head within the struct. + * + * Continue to iterate over list of given type, continuing after + * the current position. + */ +#define list_for_each_entry_continue(pos, head, member) \ + for (pos = list_next_entry(pos, member); \ + &pos->member != (head); \ + pos = list_next_entry(pos, member)) + +/** + * list_for_each_entry_continue_reverse - iterate backwards from the given point + * @pos: the type * to use as a loop cursor. + * @head: the head for your list. + * @member: the name of the list_head within the struct. + * + * Start to iterate over list of given type backwards, continuing after + * the current position. + */ +#define list_for_each_entry_continue_reverse(pos, head, member) \ + for (pos = list_prev_entry(pos, member); \ + &pos->member != (head); \ + pos = list_prev_entry(pos, member)) + +/** + * list_for_each_entry_from - iterate over list of given type from the current point + * @pos: the type * to use as a loop cursor. + * @head: the head for your list. + * @member: the name of the list_head within the struct. + * + * Iterate over list of given type, continuing from current position. + */ +#define list_for_each_entry_from(pos, head, member) \ + for (; &pos->member != (head); \ + pos = list_next_entry(pos, member)) + +/** + * list_for_each_entry_safe - iterate over list of given type safe against removal of list entry + * @pos: the type * to use as a loop cursor. + * @n: another type * to use as temporary storage + * @head: the head for your list. + * @member: the name of the list_head within the struct. + */ +#define list_for_each_entry_safe(pos, n, head, member) \ + for (pos = list_first_entry(head, typeof(*pos), member), \ + n = list_next_entry(pos, member); \ + &pos->member != (head); \ + pos = n, n = list_next_entry(n, member)) + +/** + * list_for_each_entry_safe_continue - continue list iteration safe against removal + * @pos: the type * to use as a loop cursor. + * @n: another type * to use as temporary storage + * @head: the head for your list. + * @member: the name of the list_head within the struct. + * + * Iterate over list of given type, continuing after current point, + * safe against removal of list entry. + */ +#define list_for_each_entry_safe_continue(pos, n, head, member) \ + for (pos = list_next_entry(pos, member), \ + n = list_next_entry(pos, member); \ + &pos->member != (head); \ + pos = n, n = list_next_entry(n, member)) + +/** + * list_for_each_entry_safe_from - iterate over list from current point safe against removal + * @pos: the type * to use as a loop cursor. + * @n: another type * to use as temporary storage + * @head: the head for your list. + * @member: the name of the list_head within the struct. + * + * Iterate over list of given type from current point, safe against + * removal of list entry. + */ +#define list_for_each_entry_safe_from(pos, n, head, member) \ + for (n = list_next_entry(pos, member); \ + &pos->member != (head); \ + pos = n, n = list_next_entry(n, member)) + +/** + * list_for_each_entry_safe_reverse - iterate backwards over list safe against removal + * @pos: the type * to use as a loop cursor. + * @n: another type * to use as temporary storage + * @head: the head for your list. + * @member: the name of the list_head within the struct. + * + * Iterate backwards over list of given type, safe against removal + * of list entry. + */ +#define list_for_each_entry_safe_reverse(pos, n, head, member) \ + for (pos = list_last_entry(head, typeof(*pos), member), \ + n = list_prev_entry(pos, member); \ + &pos->member != (head); \ + pos = n, n = list_prev_entry(n, member)) -#include "../../../include/linux/list.h" +/** + * list_safe_reset_next - reset a stale list_for_each_entry_safe loop + * @pos: the loop cursor used in the list_for_each_entry_safe loop + * @n: temporary storage used in list_for_each_entry_safe + * @member: the name of the list_head within the struct. + * + * list_safe_reset_next is not safe to use in general if the list may be + * modified concurrently (eg. the lock is dropped in the loop body). An + * exception to this is if the cursor element (pos) is pinned in the list, + * and list_safe_reset_next is called after re-taking the lock and before + * completing the current iteration of the loop body. + */ +#define list_safe_reset_next(pos, n, member) \ + n = list_next_entry(pos, member) + +/* + * Double linked lists with a single pointer list head. + * Mostly useful for hash tables where the two pointer list head is + * too wasteful. + * You lose the ability to access the tail in O(1). + */ + +#define HLIST_HEAD_INIT { .first = NULL } +#define HLIST_HEAD(name) struct hlist_head name = { .first = NULL } +#define INIT_HLIST_HEAD(ptr) ((ptr)->first = NULL) +static inline void INIT_HLIST_NODE(struct hlist_node *h) +{ + h->next = NULL; + h->pprev = NULL; +} + +static inline int hlist_unhashed(const struct hlist_node *h) +{ + return !h->pprev; +} + +static inline int hlist_empty(const struct hlist_head *h) +{ + return !h->first; +} + +static inline void __hlist_del(struct hlist_node *n) +{ + struct hlist_node *next = n->next; + struct hlist_node **pprev = n->pprev; + + WRITE_ONCE(*pprev, next); + if (next) + next->pprev = pprev; +} + +static inline void hlist_del(struct hlist_node *n) +{ + __hlist_del(n); + n->next = LIST_POISON1; + n->pprev = LIST_POISON2; +} + +static inline void hlist_del_init(struct hlist_node *n) +{ + if (!hlist_unhashed(n)) { + __hlist_del(n); + INIT_HLIST_NODE(n); + } +} + +static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h) +{ + struct hlist_node *first = h->first; + n->next = first; + if (first) + first->pprev = &n->next; + h->first = n; + n->pprev = &h->first; +} + +/* next must be != NULL */ +static inline void hlist_add_before(struct hlist_node *n, + struct hlist_node *next) +{ + n->pprev = next->pprev; + n->next = next; + next->pprev = &n->next; + *(n->pprev) = n; +} + +static inline void hlist_add_behind(struct hlist_node *n, + struct hlist_node *prev) +{ + n->next = prev->next; + prev->next = n; + n->pprev = &prev->next; + + if (n->next) + n->next->pprev = &n->next; +} + +/* after that we'll appear to be on some hlist and hlist_del will work */ +static inline void hlist_add_fake(struct hlist_node *n) +{ + n->pprev = &n->next; +} + +static inline bool hlist_fake(struct hlist_node *h) +{ + return h->pprev == &h->next; +} + +/* + * Move a list from one list head to another. Fixup the pprev + * reference of the first entry if it exists. + */ +static inline void hlist_move_list(struct hlist_head *old, + struct hlist_head *new) +{ + new->first = old->first; + if (new->first) + new->first->pprev = &new->first; + old->first = NULL; +} + +#define hlist_entry(ptr, type, member) container_of(ptr,type,member) + +#define hlist_for_each(pos, head) \ + for (pos = (head)->first; pos ; pos = pos->next) + +#define hlist_for_each_safe(pos, n, head) \ + for (pos = (head)->first; pos && ({ n = pos->next; 1; }); \ + pos = n) + +#define hlist_entry_safe(ptr, type, member) \ + ({ typeof(ptr) ____ptr = (ptr); \ + ____ptr ? hlist_entry(____ptr, type, member) : NULL; \ + }) + +/** + * hlist_for_each_entry - iterate over list of given type + * @pos: the type * to use as a loop cursor. + * @head: the head for your list. + * @member: the name of the hlist_node within the struct. + */ +#define hlist_for_each_entry(pos, head, member) \ + for (pos = hlist_entry_safe((head)->first, typeof(*(pos)), member);\ + pos; \ + pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) + +/** + * hlist_for_each_entry_continue - iterate over a hlist continuing after current point + * @pos: the type * to use as a loop cursor. + * @member: the name of the hlist_node within the struct. + */ +#define hlist_for_each_entry_continue(pos, member) \ + for (pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member);\ + pos; \ + pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) + +/** + * hlist_for_each_entry_from - iterate over a hlist continuing from current point + * @pos: the type * to use as a loop cursor. + * @member: the name of the hlist_node within the struct. + */ +#define hlist_for_each_entry_from(pos, member) \ + for (; pos; \ + pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) + +/** + * hlist_for_each_entry_safe - iterate over list of given type safe against removal of list entry + * @pos: the type * to use as a loop cursor. + * @n: another &struct hlist_node to use as temporary storage + * @head: the head for your list. + * @member: the name of the hlist_node within the struct. + */ +#define hlist_for_each_entry_safe(pos, n, head, member) \ + for (pos = hlist_entry_safe((head)->first, typeof(*pos), member);\ + pos && ({ n = pos->member.next; 1; }); \ + pos = hlist_entry_safe(n, typeof(*pos), member)) -#ifndef TOOLS_LIST_H -#define TOOLS_LIST_H /** * list_del_range - deletes range of entries from list. * @begin: first element in the range to delete from the list. @@ -27,4 +767,5 @@ static inline void list_del_range(struct list_head *begin, */ #define list_for_each_from(pos, head) \ for (; pos != (head); pos = pos->next) -#endif + +#endif /* __TOOLS_LINUX_LIST_H */ diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index 919b71780710..fc1bc75ae56d 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -6,6 +6,12 @@ BPF_EXTRAVERSION = 1 MAKEFLAGS += --no-print-directory +ifeq ($(srctree),) +srctree := $(patsubst %/,%,$(dir $(shell pwd))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +#$(info Determined 'srctree' to be $(srctree)) +endif # Makefiles suck: This macro sets a default value of $(2) for the # variable named by $(1), unless the variable has been set by @@ -31,7 +37,8 @@ INSTALL = install DESTDIR ?= DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))' -LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1) +include $(srctree)/tools/scripts/Makefile.arch + ifeq ($(LP64), 1) libdir_relative = lib64 else @@ -57,13 +64,6 @@ ifndef VERBOSE VERBOSE = 0 endif -ifeq ($(srctree),) -srctree := $(patsubst %/,%,$(dir $(shell pwd))) -srctree := $(patsubst %/,%,$(dir $(srctree))) -srctree := $(patsubst %/,%,$(dir $(srctree))) -#$(info Determined 'srctree' to be $(srctree)) -endif - FEATURE_USER = .libbpf FEATURE_TESTS = libelf libelf-getphdrnum libelf-mmap bpf FEATURE_DISPLAY = libelf bpf @@ -192,7 +192,7 @@ config-clean: $(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null clean: - $(call QUIET_CLEAN, libbpf) $(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d \ + $(call QUIET_CLEAN, libbpf) $(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d .*.cmd \ $(RM) LIBBPF-CFLAGS $(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 5bdc6eab6852..1f91cc941b7c 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -14,8 +14,8 @@ #include "bpf.h" /* - * When building perf, unistd.h is override. Define __NR_bpf is - * required to be defined. + * When building perf, unistd.h is overrided. __NR_bpf is + * required to be defined explicitly. */ #ifndef __NR_bpf # if defined(__i386__) diff --git a/tools/lib/lockdep/Makefile b/tools/lib/lockdep/Makefile index 7e319afac78a..90d2baeb621a 100644 --- a/tools/lib/lockdep/Makefile +++ b/tools/lib/lockdep/Makefile @@ -149,7 +149,7 @@ install_lib: all_cmd install: install_lib clean: - $(RM) *.o *~ $(TARGETS) *.a *liblockdep*.so* $(VERSION_FILES) .*.d + $(RM) *.o *~ $(TARGETS) *.a *liblockdep*.so* $(VERSION_FILES) .*.d .*.cmd $(RM) tags TAGS PHONY += force diff --git a/tools/lib/subcmd/parse-options.h b/tools/lib/subcmd/parse-options.h index 13a2cc1d6140..d60cab2726da 100644 --- a/tools/lib/subcmd/parse-options.h +++ b/tools/lib/subcmd/parse-options.h @@ -4,6 +4,10 @@ #include <stdbool.h> #include <stdint.h> +#ifndef NORETURN +#define NORETURN __attribute__((__noreturn__)) +#endif + enum parse_opt_type { /* special types */ OPTION_END, diff --git a/tools/perf/Build b/tools/perf/Build index 6b67e6f4179f..a43fae7f439a 100644 --- a/tools/perf/Build +++ b/tools/perf/Build @@ -42,6 +42,7 @@ CFLAGS_perf.o += -DPERF_HTML_PATH="BUILD_STR($(htmldir_SQ))" \ -include $(OUTPUT)PERF-VERSION-FILE CFLAGS_builtin-trace.o += -DSTRACE_GROUPS_DIR="BUILD_STR($(STRACE_GROUPS_DIR_SQ))" CFLAGS_builtin-report.o += -DTIPDIR="BUILD_STR($(tipdir_SQ))" +CFLAGS_builtin-report.o += -DDOCDIR="BUILD_STR($(srcdir_SQ)/Documentation)" libperf-y += util/ libperf-y += arch/ diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 3a1a32f5479f..fbceb631387c 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -338,6 +338,9 @@ Options passed to clang when compiling BPF scriptlets. Specify vmlinux path which has debuginfo. (enabled when BPF prologue is on) +--buildid-all:: +Record build-id of all DSOs regardless whether it's actually hit or not. + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-list[1] diff --git a/tools/perf/Documentation/tips.txt b/tools/perf/Documentation/tips.txt index a1c10e360db5..e0ce9573b79b 100644 --- a/tools/perf/Documentation/tips.txt +++ b/tools/perf/Documentation/tips.txt @@ -12,3 +12,18 @@ List events using substring match: perf list <keyword> To see list of saved events and attributes: perf evlist -v Use --symfs <dir> if your symbol files are in non-standard locations To see callchains in a more compact form: perf report -g folded +Show individual samples with: perf script +Limit to show entries above 5% only: perf report --percent-limit 5 +Profiling branch (mis)predictions with: perf record -b / perf report +Treat branches as callchains: perf report --branch-history +To count events in every 1000 msec: perf stat -I 1000 +Print event counts in CSV format with: perf stat -x, +If you have debuginfo enabled, try: perf report -s sym,srcline +For memory address profiling, try: perf mem record / perf mem report +For tracepoint events, try: perf report -s trace_fields +To record callchains for each sample: perf record -g +To record every process run by an user: perf record -u <user> +Skip collecing build-id when recording: perf record -B +To change sampling frequency to 100 Hz: perf record -F 100 +See assembly instructions with percentage: perf annotate <symbol> +If you prefer Intel style assembly, try: perf annotate -M intel diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index ddf922f93aa1..2e1fa2357528 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -28,6 +28,7 @@ tools/lib/string.c tools/lib/symbol/kallsyms.c tools/lib/symbol/kallsyms.h tools/lib/find_bit.c +tools/lib/bitmap.c tools/include/asm/atomic.h tools/include/asm/barrier.h tools/include/asm/bug.h @@ -57,6 +58,7 @@ tools/include/linux/rbtree_augmented.h tools/include/linux/string.h tools/include/linux/types.h tools/include/linux/err.h +tools/include/linux/bitmap.h include/asm-generic/bitops/arch_hweight.h include/asm-generic/bitops/const_hweight.h include/asm-generic/bitops/fls64.h diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index dc4e0adf5c5b..319712a4e02b 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -50,6 +50,7 @@ struct record { int realtime_prio; bool no_buildid; bool no_buildid_cache; + bool buildid_all; unsigned long long samples; }; @@ -362,6 +363,13 @@ static int process_buildids(struct record *rec) */ symbol_conf.ignore_vmlinux_buildid = true; + /* + * If --buildid-all is given, it marks all DSO regardless of hits, + * so no need to process samples. + */ + if (rec->buildid_all) + rec->tool.sample = NULL; + return perf_session__process_events(session); } @@ -756,12 +764,8 @@ out_child: if (!rec->no_buildid) { process_buildids(rec); - /* - * We take all buildids when the file contains - * AUX area tracing data because we do not decode the - * trace because it would take too long. - */ - if (rec->opts.full_auxtrace) + + if (rec->buildid_all) dsos__hit_all(rec->session); } perf_session__write_header(rec->session, rec->evlist, fd, true); @@ -1138,6 +1142,8 @@ struct option __record_options[] = { "options passed to clang when compiling BPF scriptlets"), OPT_STRING(0, "vmlinux", &symbol_conf.vmlinux_name, "file", "vmlinux pathname"), + OPT_BOOLEAN(0, "buildid-all", &record.buildid_all, + "Record build-id of all DSOs regardless of hits"), OPT_END() }; @@ -1255,6 +1261,14 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) if (err) goto out_symbol_exit; + /* + * We take all buildids when the file contains + * AUX area tracing data because we do not decode the + * trace because it would take too long. + */ + if (rec->opts.full_auxtrace) + rec->buildid_all = true; + if (record_opts__config(&rec->opts)) { err = -EINVAL; goto out_symbol_exit; diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index d5a42ee12529..2bf537f190a0 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -28,6 +28,7 @@ #include "util/tool.h" #include <subcmd/parse-options.h> +#include <subcmd/exec-cmd.h> #include "util/parse-events.h" #include "util/thread.h" @@ -433,7 +434,14 @@ static int report__browse_hists(struct report *rep) int ret; struct perf_session *session = rep->session; struct perf_evlist *evlist = session->evlist; - const char *help = perf_tip(TIPDIR); + const char *help = perf_tip(system_path(TIPDIR)); + + if (help == NULL) { + /* fallback for people who don't install perf ;-) */ + help = perf_tip(DOCDIR); + if (help == NULL) + help = "Cannot load tips.txt file, please install perf!"; + } switch (use_browser) { case 1: diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 7f568244662b..038e877081b6 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -1588,7 +1588,7 @@ static int add_default_attributes(void) return perf_evlist__add_default_attrs(evsel_list, very_very_detailed_attrs); } -static const char * const recort_usage[] = { +static const char * const stat_record_usage[] = { "perf stat record [<options>]", NULL, }; @@ -1611,7 +1611,7 @@ static int __cmd_record(int argc, const char **argv) struct perf_session *session; struct perf_data_file *file = &perf_stat.file; - argc = parse_options(argc, argv, stat_options, record_usage, + argc = parse_options(argc, argv, stat_options, stat_record_usage, PARSE_OPT_STOP_AT_NON_OPTION); if (output_name) @@ -1745,7 +1745,7 @@ int process_cpu_map_event(struct perf_tool *tool __maybe_unused, return set_maps(st); } -static const char * const report_usage[] = { +static const char * const stat_report_usage[] = { "perf stat report [<options>]", NULL, }; @@ -1779,7 +1779,7 @@ static int __cmd_report(int argc, const char **argv) struct stat st; int ret; - argc = parse_options(argc, argv, options, report_usage, 0); + argc = parse_options(argc, argv, options, stat_report_usage, 0); if (!input_name || !strlen(input_name)) { if (!fstat(STDIN_FILENO, &st) && S_ISFIFO(st.st_mode)) diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index 254d06e39bea..e5959c136a19 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -17,7 +17,7 @@ detected_var = $(shell echo "$(1)=$($(1))" >> $(OUTPUT).config-detected) CFLAGS := $(EXTRA_CFLAGS) $(EXTRA_WARNINGS) -include $(src-perf)/config/Makefile.arch +include $(srctree)/tools/scripts/Makefile.arch $(call detected_var,ARCH) @@ -493,7 +493,7 @@ else PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null) PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS)) - PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) + PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null) FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS) @@ -692,6 +692,7 @@ template_dir = share/perf-core/templates STRACE_GROUPS_DIR = share/perf-core/strace/groups htmldir = share/doc/perf-doc tipdir = share/doc/perf-tip +srcdir = $(srctree)/tools/perf ifeq ($(prefix),/usr) sysconfdir = /etc ETC_PERFCONFIG = $(sysconfdir)/perfconfig @@ -722,6 +723,7 @@ tipdir_SQ = $(subst ','\'',$(tipdir)) prefix_SQ = $(subst ','\'',$(prefix)) sysconfdir_SQ = $(subst ','\'',$(sysconfdir)) libdir_SQ = $(subst ','\'',$(libdir)) +srcdir_SQ = $(subst ','\'',$(srcdir)) ifneq ($(filter /%,$(firstword $(perfexecdir))),) perfexec_instdir = $(perfexecdir) @@ -776,6 +778,7 @@ $(call detected_var,STRACE_GROUPS_DIR_SQ) $(call detected_var,prefix_SQ) $(call detected_var,perfexecdir_SQ) $(call detected_var,tipdir_SQ) +$(call detected_var,srcdir_SQ) $(call detected_var,LIBDIR) $(call detected_var,GTK_CFLAGS) $(call detected_var,PERL_EMBED_CCOPTS) diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c index bcfd081ee1d2..071a8b5f5232 100644 --- a/tools/perf/tests/hists_common.c +++ b/tools/perf/tests/hists_common.c @@ -87,11 +87,6 @@ struct machine *setup_fake_machine(struct machines *machines) return NULL; } - if (machine__create_kernel_maps(machine)) { - pr_debug("Cannot create kernel maps\n"); - return NULL; - } - for (i = 0; i < ARRAY_SIZE(fake_threads); i++) { struct thread *thread; diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c index e36089212061..5e6a86e50fb9 100644 --- a/tools/perf/tests/hists_cumulate.c +++ b/tools/perf/tests/hists_cumulate.c @@ -706,6 +706,7 @@ int test__hists_cumulate(int subtest __maybe_unused) err = parse_events(evlist, "cpu-clock", NULL); if (err) goto out; + err = TEST_FAIL; machines__init(&machines); diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c index 2a784befd9ce..351a42463444 100644 --- a/tools/perf/tests/hists_filter.c +++ b/tools/perf/tests/hists_filter.c @@ -120,6 +120,7 @@ int test__hists_filter(int subtest __maybe_unused) err = parse_events(evlist, "task-clock", NULL); if (err) goto out; + err = TEST_FAIL; /* default sort order (comm,dso,sym) will be used */ if (setup_sorting(NULL) < 0) diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c index c764d69ac6ef..64b257d8d557 100644 --- a/tools/perf/tests/hists_link.c +++ b/tools/perf/tests/hists_link.c @@ -293,6 +293,7 @@ int test__hists_link(int subtest __maybe_unused) if (err) goto out; + err = TEST_FAIL; /* default sort order (comm,dso,sym) will be used */ if (setup_sorting(NULL) < 0) goto out; diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c index ebe6cd485b5d..b231265148d8 100644 --- a/tools/perf/tests/hists_output.c +++ b/tools/perf/tests/hists_output.c @@ -597,6 +597,7 @@ int test__hists_output(int subtest __maybe_unused) err = parse_events(evlist, "cpu-clock", NULL); if (err) goto out; + err = TEST_FAIL; machines__init(&machines); diff --git a/tools/perf/tests/make b/tools/perf/tests/make index c1fbb8e884c0..df38decc48c3 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -1,3 +1,5 @@ +include ../scripts/Makefile.include + ifndef MK ifeq ($(MAKECMDGOALS),) # no target specified, trigger the whole suite @@ -12,7 +14,19 @@ endif else PERF := . -include config/Makefile.arch +# As per kernel Makefile, avoid funny character set dependencies +unexport LC_ALL +LC_COLLATE=C +LC_NUMERIC=C +export LC_COLLATE LC_NUMERIC + +ifeq ($(srctree),) +srctree := $(patsubst %/,%,$(dir $(shell pwd))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +#$(info Determined 'srctree' to be $(srctree)) +endif + +include $(srctree)/tools/scripts/Makefile.arch # FIXME looks like x86 is the only arch running tests ;-) # we need some IS_(32/64) flag to make this generic @@ -280,5 +294,5 @@ all: $(run) $(run_O) tarpkg make_kernelsrc make_kernelsrc_tools out: $(run_O) @echo OK -.PHONY: all $(run) $(run_O) tarpkg clean +.PHONY: all $(run) $(run_O) tarpkg clean make_kernelsrc make_kernelsrc_tools endif # ifndef MK diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 901d481e6cea..08c09ad755d2 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -480,7 +480,7 @@ static int hist_browser__run(struct hist_browser *browser, const char *help) hists__browser_title(browser->hists, hbt, title, sizeof(title)); - if (ui_browser__show(&browser->b, title, help) < 0) + if (ui_browser__show(&browser->b, title, "%s", help) < 0) return -1; while (1) { diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index cd61bb1f3917..85155e91b61b 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -503,7 +503,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, if (comm_event == NULL) goto out; - mmap_event = malloc(sizeof(mmap_event->mmap) + machine->id_hdr_size); + mmap_event = malloc(sizeof(mmap_event->mmap2) + machine->id_hdr_size); if (mmap_event == NULL) goto out_free_comm; @@ -577,7 +577,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool, if (comm_event == NULL) goto out; - mmap_event = malloc(sizeof(mmap_event->mmap) + machine->id_hdr_size); + mmap_event = malloc(sizeof(mmap_event->mmap2) + machine->id_hdr_size); if (mmap_event == NULL) goto out_free_comm; diff --git a/tools/perf/util/strlist.c b/tools/perf/util/strlist.c index bdf98f6f27bb..0d3dfcb919b4 100644 --- a/tools/perf/util/strlist.c +++ b/tools/perf/util/strlist.c @@ -126,6 +126,11 @@ static int strlist__parse_list_entry(struct strlist *slist, const char *s, err = strlist__load(slist, subst); goto out; } + + if (slist->file_only) { + err = -ENOENT; + goto out; + } } err = strlist__add(slist, s); @@ -157,11 +162,13 @@ struct strlist *strlist__new(const char *list, const struct strlist_config *conf if (slist != NULL) { bool dupstr = true; + bool file_only = false; const char *dirname = NULL; if (config) { dupstr = !config->dont_dupstr; dirname = config->dirname; + file_only = config->file_only; } rblist__init(&slist->rblist); @@ -170,6 +177,7 @@ struct strlist *strlist__new(const char *list, const struct strlist_config *conf slist->rblist.node_delete = strlist__node_delete; slist->dupstr = dupstr; + slist->file_only = file_only; if (list && strlist__parse_list(slist, list, dirname) != 0) goto out_error; diff --git a/tools/perf/util/strlist.h b/tools/perf/util/strlist.h index 297565aa7535..ca990029e243 100644 --- a/tools/perf/util/strlist.h +++ b/tools/perf/util/strlist.h @@ -13,11 +13,18 @@ struct str_node { struct strlist { struct rblist rblist; - bool dupstr; + bool dupstr; + bool file_only; }; +/* + * @file_only: When dirname is present, only consider entries as filenames, + * that should not be added to the list if dirname/entry is not + * found + */ struct strlist_config { bool dont_dupstr; + bool file_only; const char *dirname; }; diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 88b8f8d21f58..ead9509835d2 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -17,7 +17,6 @@ #include <unistd.h> #include "callchain.h" #include "strlist.h" -#include <subcmd/exec-cmd.h> struct callchain_param callchain_param = { .mode = CHAIN_GRAPH_ABS, @@ -672,14 +671,16 @@ const char *perf_tip(const char *dirpath) struct str_node *node; char *tip = NULL; struct strlist_config conf = { - .dirname = system_path(dirpath) , + .dirname = dirpath, + .file_only = true, }; tips = strlist__new("tips.txt", &conf); - if (tips == NULL || strlist__nr_entries(tips) == 1) { - tip = (char *)"Cannot find tips.txt file"; + if (tips == NULL) + return errno == ENOENT ? NULL : "Tip: get more memory! ;-p"; + + if (strlist__nr_entries(tips) == 0) goto out; - } node = strlist__entry(tips, random() % strlist__nr_entries(tips)); if (asprintf(&tip, "Tip: %s", node->s) < 0) diff --git a/tools/perf/config/Makefile.arch b/tools/scripts/Makefile.arch index e11fbd6fae78..e11fbd6fae78 100644 --- a/tools/perf/config/Makefile.arch +++ b/tools/scripts/Makefile.arch diff --git a/tools/testing/selftests/powerpc/benchmarks/.gitignore b/tools/testing/selftests/powerpc/benchmarks/.gitignore index b4709ea588c1..6fa673316ac2 100644 --- a/tools/testing/selftests/powerpc/benchmarks/.gitignore +++ b/tools/testing/selftests/powerpc/benchmarks/.gitignore @@ -1 +1,2 @@ gettimeofday +context_switch diff --git a/tools/testing/selftests/powerpc/benchmarks/Makefile b/tools/testing/selftests/powerpc/benchmarks/Makefile index 5fa48702070d..912445ff7ce7 100644 --- a/tools/testing/selftests/powerpc/benchmarks/Makefile +++ b/tools/testing/selftests/powerpc/benchmarks/Makefile @@ -1,4 +1,4 @@ -TEST_PROGS := gettimeofday +TEST_PROGS := gettimeofday context_switch CFLAGS += -O2 @@ -6,6 +6,9 @@ all: $(TEST_PROGS) $(TEST_PROGS): ../harness.c +context_switch: ../utils.c +context_switch: LDLIBS += -lpthread + include ../../lib.mk clean: diff --git a/tools/testing/selftests/powerpc/benchmarks/context_switch.c b/tools/testing/selftests/powerpc/benchmarks/context_switch.c new file mode 100644 index 000000000000..7b785941adec --- /dev/null +++ b/tools/testing/selftests/powerpc/benchmarks/context_switch.c @@ -0,0 +1,466 @@ +/* + * Context switch microbenchmark. + * + * Copyright (C) 2015 Anton Blanchard <anton@au.ibm.com>, IBM + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#define _GNU_SOURCE +#include <sched.h> +#include <string.h> +#include <stdio.h> +#include <unistd.h> +#include <stdlib.h> +#include <getopt.h> +#include <signal.h> +#include <assert.h> +#include <pthread.h> +#include <limits.h> +#include <sys/time.h> +#include <sys/syscall.h> +#include <sys/types.h> +#include <sys/shm.h> +#include <linux/futex.h> + +#include "../utils.h" + +static unsigned int timeout = 30; + +static int touch_vdso; +struct timeval tv; + +static int touch_fp = 1; +double fp; + +static int touch_vector = 1; +typedef int v4si __attribute__ ((vector_size (16))); +v4si a, b, c; + +#ifdef __powerpc__ +static int touch_altivec = 1; + +static void __attribute__((__target__("no-vsx"))) altivec_touch_fn(void) +{ + c = a + b; +} +#endif + +static void touch(void) +{ + if (touch_vdso) + gettimeofday(&tv, NULL); + + if (touch_fp) + fp += 0.1; + +#ifdef __powerpc__ + if (touch_altivec) + altivec_touch_fn(); +#endif + + if (touch_vector) + c = a + b; + + asm volatile("# %0 %1 %2": : "r"(&tv), "r"(&fp), "r"(&c)); +} + +static void start_thread_on(void *(*fn)(void *), void *arg, unsigned long cpu) +{ + pthread_t tid; + cpu_set_t cpuset; + pthread_attr_t attr; + + CPU_ZERO(&cpuset); + CPU_SET(cpu, &cpuset); + + pthread_attr_init(&attr); + + if (pthread_attr_setaffinity_np(&attr, sizeof(cpu_set_t), &cpuset)) { + perror("pthread_attr_setaffinity_np"); + exit(1); + } + + if (pthread_create(&tid, &attr, fn, arg)) { + perror("pthread_create"); + exit(1); + } +} + +static void start_process_on(void *(*fn)(void *), void *arg, unsigned long cpu) +{ + int pid; + cpu_set_t cpuset; + + pid = fork(); + if (pid == -1) { + perror("fork"); + exit(1); + } + + if (pid) + return; + + CPU_ZERO(&cpuset); + CPU_SET(cpu, &cpuset); + + if (sched_setaffinity(0, sizeof(cpuset), &cpuset)) { + perror("sched_setaffinity"); + exit(1); + } + + fn(arg); + + exit(0); +} + +static unsigned long iterations; +static unsigned long iterations_prev; + +static void sigalrm_handler(int junk) +{ + unsigned long i = iterations; + + printf("%ld\n", i - iterations_prev); + iterations_prev = i; + + if (--timeout == 0) + kill(0, SIGUSR1); + + alarm(1); +} + +static void sigusr1_handler(int junk) +{ + exit(0); +} + +struct actions { + void (*setup)(int, int); + void *(*thread1)(void *); + void *(*thread2)(void *); +}; + +#define READ 0 +#define WRITE 1 + +static int pipe_fd1[2]; +static int pipe_fd2[2]; + +static void pipe_setup(int cpu1, int cpu2) +{ + if (pipe(pipe_fd1) || pipe(pipe_fd2)) + exit(1); +} + +static void *pipe_thread1(void *arg) +{ + signal(SIGALRM, sigalrm_handler); + alarm(1); + + while (1) { + assert(read(pipe_fd1[READ], &c, 1) == 1); + touch(); + + assert(write(pipe_fd2[WRITE], &c, 1) == 1); + touch(); + + iterations += 2; + } + + return NULL; +} + +static void *pipe_thread2(void *arg) +{ + while (1) { + assert(write(pipe_fd1[WRITE], &c, 1) == 1); + touch(); + + assert(read(pipe_fd2[READ], &c, 1) == 1); + touch(); + } + + return NULL; +} + +static struct actions pipe_actions = { + .setup = pipe_setup, + .thread1 = pipe_thread1, + .thread2 = pipe_thread2, +}; + +static void yield_setup(int cpu1, int cpu2) +{ + if (cpu1 != cpu2) { + fprintf(stderr, "Both threads must be on the same CPU for yield test\n"); + exit(1); + } +} + +static void *yield_thread1(void *arg) +{ + signal(SIGALRM, sigalrm_handler); + alarm(1); + + while (1) { + sched_yield(); + touch(); + + iterations += 2; + } + + return NULL; +} + +static void *yield_thread2(void *arg) +{ + while (1) { + sched_yield(); + touch(); + } + + return NULL; +} + +static struct actions yield_actions = { + .setup = yield_setup, + .thread1 = yield_thread1, + .thread2 = yield_thread2, +}; + +static long sys_futex(void *addr1, int op, int val1, struct timespec *timeout, + void *addr2, int val3) +{ + return syscall(SYS_futex, addr1, op, val1, timeout, addr2, val3); +} + +static unsigned long cmpxchg(unsigned long *p, unsigned long expected, + unsigned long desired) +{ + unsigned long exp = expected; + + __atomic_compare_exchange_n(p, &exp, desired, 0, + __ATOMIC_SEQ_CST, __ATOMIC_SEQ_CST); + return exp; +} + +static unsigned long xchg(unsigned long *p, unsigned long val) +{ + return __atomic_exchange_n(p, val, __ATOMIC_SEQ_CST); +} + +static int mutex_lock(unsigned long *m) +{ + int c; + + c = cmpxchg(m, 0, 1); + if (!c) + return 0; + + if (c == 1) + c = xchg(m, 2); + + while (c) { + sys_futex(m, FUTEX_WAIT, 2, NULL, NULL, 0); + c = xchg(m, 2); + } + + return 0; +} + +static int mutex_unlock(unsigned long *m) +{ + if (*m == 2) + *m = 0; + else if (xchg(m, 0) == 1) + return 0; + + sys_futex(m, FUTEX_WAKE, 1, NULL, NULL, 0); + + return 0; +} + +static unsigned long *m1, *m2; + +static void futex_setup(int cpu1, int cpu2) +{ + int shmid; + void *shmaddr; + + shmid = shmget(IPC_PRIVATE, getpagesize(), SHM_R | SHM_W); + if (shmid < 0) { + perror("shmget"); + exit(1); + } + + shmaddr = shmat(shmid, NULL, 0); + if (shmaddr == (char *)-1) { + perror("shmat"); + shmctl(shmid, IPC_RMID, NULL); + exit(1); + } + + shmctl(shmid, IPC_RMID, NULL); + + m1 = shmaddr; + m2 = shmaddr + sizeof(*m1); + + *m1 = 0; + *m2 = 0; + + mutex_lock(m1); + mutex_lock(m2); +} + +static void *futex_thread1(void *arg) +{ + signal(SIGALRM, sigalrm_handler); + alarm(1); + + while (1) { + mutex_lock(m2); + mutex_unlock(m1); + + iterations += 2; + } + + return NULL; +} + +static void *futex_thread2(void *arg) +{ + while (1) { + mutex_unlock(m2); + mutex_lock(m1); + } + + return NULL; +} + +static struct actions futex_actions = { + .setup = futex_setup, + .thread1 = futex_thread1, + .thread2 = futex_thread2, +}; + +static int processes; + +static struct option options[] = { + { "test", required_argument, 0, 't' }, + { "process", no_argument, &processes, 1 }, + { "timeout", required_argument, 0, 's' }, + { "vdso", no_argument, &touch_vdso, 1 }, + { "no-fp", no_argument, &touch_fp, 0 }, +#ifdef __powerpc__ + { "no-altivec", no_argument, &touch_altivec, 0 }, +#endif + { "no-vector", no_argument, &touch_vector, 0 }, + { 0, }, +}; + +static void usage(void) +{ + fprintf(stderr, "Usage: context_switch2 <options> CPU1 CPU2\n\n"); + fprintf(stderr, "\t\t--test=X\tpipe, futex or yield (default)\n"); + fprintf(stderr, "\t\t--process\tUse processes (default threads)\n"); + fprintf(stderr, "\t\t--timeout=X\tDuration in seconds to run (default 30)\n"); + fprintf(stderr, "\t\t--vdso\t\ttouch VDSO\n"); + fprintf(stderr, "\t\t--fp\t\ttouch FP\n"); +#ifdef __powerpc__ + fprintf(stderr, "\t\t--altivec\ttouch altivec\n"); +#endif + fprintf(stderr, "\t\t--vector\ttouch vector\n"); +} + +int main(int argc, char *argv[]) +{ + signed char c; + struct actions *actions = &yield_actions; + int cpu1; + int cpu2; + static void (*start_fn)(void *(*fn)(void *), void *arg, unsigned long cpu); + + while (1) { + int option_index = 0; + + c = getopt_long(argc, argv, "", options, &option_index); + + if (c == -1) + break; + + switch (c) { + case 0: + if (options[option_index].flag != 0) + break; + + usage(); + exit(1); + break; + + case 't': + if (!strcmp(optarg, "pipe")) { + actions = &pipe_actions; + } else if (!strcmp(optarg, "yield")) { + actions = &yield_actions; + } else if (!strcmp(optarg, "futex")) { + actions = &futex_actions; + } else { + usage(); + exit(1); + } + break; + + case 's': + timeout = atoi(optarg); + break; + + default: + usage(); + exit(1); + } + } + + if (processes) + start_fn = start_process_on; + else + start_fn = start_thread_on; + + if (((argc - optind) != 2)) { + cpu1 = cpu2 = pick_online_cpu(); + } else { + cpu1 = atoi(argv[optind++]); + cpu2 = atoi(argv[optind++]); + } + + printf("Using %s with ", processes ? "processes" : "threads"); + + if (actions == &pipe_actions) + printf("pipe"); + else if (actions == &yield_actions) + printf("yield"); + else + printf("futex"); + + printf(" on cpus %d/%d touching FP:%s altivec:%s vector:%s vdso:%s\n", + cpu1, cpu2, touch_fp ? "yes" : "no", touch_altivec ? "yes" : "no", + touch_vector ? "yes" : "no", touch_vdso ? "yes" : "no"); + + /* Create a new process group so we can signal everyone for exit */ + setpgid(getpid(), getpid()); + + signal(SIGUSR1, sigusr1_handler); + + actions->setup(cpu1, cpu2); + + start_fn(actions->thread1, NULL, cpu1); + start_fn(actions->thread2, NULL, cpu2); + + while (1) + sleep(3600); + + return 0; +} diff --git a/tools/testing/selftests/powerpc/dscr/dscr_inherit_exec_test.c b/tools/testing/selftests/powerpc/dscr/dscr_inherit_exec_test.c index 8265504de571..08a8b95e3bc1 100644 --- a/tools/testing/selftests/powerpc/dscr/dscr_inherit_exec_test.c +++ b/tools/testing/selftests/powerpc/dscr/dscr_inherit_exec_test.c @@ -60,14 +60,6 @@ int dscr_inherit_exec(void) else set_dscr(dscr); - /* - * XXX: Force a context switch out so that DSCR - * current value is copied into the thread struct - * which is required for the child to inherit the - * changed value. - */ - sleep(1); - pid = fork(); if (pid == -1) { perror("fork() failed"); diff --git a/tools/testing/selftests/powerpc/dscr/dscr_inherit_test.c b/tools/testing/selftests/powerpc/dscr/dscr_inherit_test.c index 4e414caf7f40..3e5a6d195e9a 100644 --- a/tools/testing/selftests/powerpc/dscr/dscr_inherit_test.c +++ b/tools/testing/selftests/powerpc/dscr/dscr_inherit_test.c @@ -40,14 +40,6 @@ int dscr_inherit(void) else set_dscr(dscr); - /* - * XXX: Force a context switch out so that DSCR - * current value is copied into the thread struct - * which is required for the child to inherit the - * changed value. - */ - sleep(1); - pid = fork(); if (pid == -1) { perror("fork() failed"); diff --git a/tools/testing/selftests/powerpc/harness.c b/tools/testing/selftests/powerpc/harness.c index f7997affd143..52f9be7f61f0 100644 --- a/tools/testing/selftests/powerpc/harness.c +++ b/tools/testing/selftests/powerpc/harness.c @@ -116,46 +116,3 @@ int test_harness(int (test_function)(void), char *name) return rc; } - -static char auxv[4096]; - -void *get_auxv_entry(int type) -{ - ElfW(auxv_t) *p; - void *result; - ssize_t num; - int fd; - - fd = open("/proc/self/auxv", O_RDONLY); - if (fd == -1) { - perror("open"); - return NULL; - } - - result = NULL; - - num = read(fd, auxv, sizeof(auxv)); - if (num < 0) { - perror("read"); - goto out; - } - - if (num > sizeof(auxv)) { - printf("Overflowed auxv buffer\n"); - goto out; - } - - p = (ElfW(auxv_t) *)auxv; - - while (p->a_type != AT_NULL) { - if (p->a_type == type) { - result = (void *)p->a_un.a_val; - break; - } - - p++; - } -out: - close(fd); - return result; -} diff --git a/tools/testing/selftests/powerpc/pmu/Makefile b/tools/testing/selftests/powerpc/pmu/Makefile index a9099d9f8f39..ac41a7177f2e 100644 --- a/tools/testing/selftests/powerpc/pmu/Makefile +++ b/tools/testing/selftests/powerpc/pmu/Makefile @@ -2,7 +2,7 @@ noarg: $(MAKE) -C ../ TEST_PROGS := count_instructions l3_bank_test per_event_excludes -EXTRA_SOURCES := ../harness.c event.c lib.c +EXTRA_SOURCES := ../harness.c event.c lib.c ../utils.c all: $(TEST_PROGS) ebb @@ -12,6 +12,8 @@ $(TEST_PROGS): $(EXTRA_SOURCES) count_instructions: loop.S count_instructions.c $(EXTRA_SOURCES) $(CC) $(CFLAGS) -m64 -o $@ $^ +per_event_excludes: ../utils.c + include ../../lib.mk DEFAULT_RUN_TESTS := $(RUN_TESTS) diff --git a/tools/testing/selftests/powerpc/pmu/ebb/Makefile b/tools/testing/selftests/powerpc/pmu/ebb/Makefile index 5cdc9dbf2b27..8d2279c4bb4b 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/Makefile +++ b/tools/testing/selftests/powerpc/pmu/ebb/Makefile @@ -18,7 +18,8 @@ TEST_PROGS := reg_access_test event_attributes_test cycles_test \ all: $(TEST_PROGS) -$(TEST_PROGS): ../../harness.c ../event.c ../lib.c ebb.c ebb_handler.S trace.c busy_loop.S +$(TEST_PROGS): ../../harness.c ../../utils.c ../event.c ../lib.c \ + ebb.c ebb_handler.S trace.c busy_loop.S instruction_count_test: ../loop.S diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c index 9729d9f90218..e67452f1bcff 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c +++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c @@ -13,7 +13,6 @@ #include <stdlib.h> #include <string.h> #include <sys/ioctl.h> -#include <linux/auxvec.h> #include "trace.h" #include "reg.h" @@ -324,7 +323,7 @@ bool ebb_is_supported(void) { #ifdef PPC_FEATURE2_EBB /* EBB requires at least POWER8 */ - return ((long)get_auxv_entry(AT_HWCAP2) & PPC_FEATURE2_EBB); + return have_hwcap2(PPC_FEATURE2_EBB); #else return false; #endif diff --git a/tools/testing/selftests/powerpc/pmu/lib.c b/tools/testing/selftests/powerpc/pmu/lib.c index a07104c2afe6..a361ad3334ce 100644 --- a/tools/testing/selftests/powerpc/pmu/lib.c +++ b/tools/testing/selftests/powerpc/pmu/lib.c @@ -15,32 +15,6 @@ #include "lib.h" -int pick_online_cpu(void) -{ - cpu_set_t mask; - int cpu; - - CPU_ZERO(&mask); - - if (sched_getaffinity(0, sizeof(mask), &mask)) { - perror("sched_getaffinity"); - return -1; - } - - /* We prefer a primary thread, but skip 0 */ - for (cpu = 8; cpu < CPU_SETSIZE; cpu += 8) - if (CPU_ISSET(cpu, &mask)) - return cpu; - - /* Search for anything, but in reverse */ - for (cpu = CPU_SETSIZE - 1; cpu >= 0; cpu--) - if (CPU_ISSET(cpu, &mask)) - return cpu; - - printf("No cpus in affinity mask?!\n"); - return -1; -} - int bind_to_cpu(int cpu) { cpu_set_t mask; diff --git a/tools/testing/selftests/powerpc/pmu/lib.h b/tools/testing/selftests/powerpc/pmu/lib.h index ca5d72ae3be6..0213af4ff332 100644 --- a/tools/testing/selftests/powerpc/pmu/lib.h +++ b/tools/testing/selftests/powerpc/pmu/lib.h @@ -19,7 +19,6 @@ union pipe { int fds[2]; }; -extern int pick_online_cpu(void); extern int bind_to_cpu(int cpu); extern int kill_child_and_wait(pid_t child_pid); extern int wait_for_child(pid_t child_pid); diff --git a/tools/testing/selftests/powerpc/scripts/hmi.sh b/tools/testing/selftests/powerpc/scripts/hmi.sh new file mode 100755 index 000000000000..83fb253ae3bd --- /dev/null +++ b/tools/testing/selftests/powerpc/scripts/hmi.sh @@ -0,0 +1,89 @@ +#!/bin/sh +# +# Copyright 2015, Daniel Axtens, IBM Corporation +# +# 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 of the License. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. + + +# do we have ./getscom, ./putscom? +if [ -x ./getscom ] && [ -x ./putscom ]; then + GETSCOM=./getscom + PUTSCOM=./putscom +elif which getscom > /dev/null; then + GETSCOM=$(which getscom) + PUTSCOM=$(which putscom) +else + cat <<EOF +Can't find getscom/putscom in . or \$PATH. +See https://github.com/open-power/skiboot. +The tool is in external/xscom-utils +EOF + exit 1 +fi + +# We will get 8 HMI events per injection +# todo: deal with things being offline +expected_hmis=8 +COUNT_HMIS() { + dmesg | grep -c 'Harmless Hypervisor Maintenance interrupt' +} + +# massively expand snooze delay, allowing injection on all cores +ppc64_cpu --smt-snooze-delay=1000000000 + +# when we exit, restore it +trap "ppc64_cpu --smt-snooze-delay=100" 0 1 + +# for each chip+core combination +# todo - less fragile parsing +egrep -o 'OCC: Chip [0-9a-f]+ Core [0-9a-f]' < /sys/firmware/opal/msglog | +while read chipcore; do + chip=$(echo "$chipcore"|awk '{print $3}') + core=$(echo "$chipcore"|awk '{print $5}') + fir="0x1${core}013100" + + # verify that Core FIR is zero as expected + if [ "$($GETSCOM -c 0x${chip} $fir)" != 0 ]; then + echo "FIR was not zero before injection for chip $chip, core $core. Aborting!" + echo "Result of $GETSCOM -c 0x${chip} $fir:" + $GETSCOM -c 0x${chip} $fir + echo "If you get a -5 error, the core may be in idle state. Try stress-ng." + echo "Otherwise, try $PUTSCOM -c 0x${chip} $fir 0" + exit 1 + fi + + # keep track of the number of HMIs handled + old_hmis=$(COUNT_HMIS) + + # do injection, adding a marker to dmesg for clarity + echo "Injecting HMI on core $core, chip $chip" | tee /dev/kmsg + # inject a RegFile recoverable error + if ! $PUTSCOM -c 0x${chip} $fir 2000000000000000 > /dev/null; then + echo "Error injecting. Aborting!" + exit 1 + fi + + # now we want to wait for all the HMIs to be processed + # we expect one per thread on the core + i=0; + new_hmis=$(COUNT_HMIS) + while [ $new_hmis -lt $((old_hmis + expected_hmis)) ] && [ $i -lt 12 ]; do + echo "Seen $((new_hmis - old_hmis)) HMI(s) out of $expected_hmis expected, sleeping" + sleep 5; + i=$((i + 1)) + new_hmis=$(COUNT_HMIS) + done + if [ $i = 12 ]; then + echo "Haven't seen expected $expected_hmis recoveries after 1 min. Aborting." + exit 1 + fi + echo "Processed $expected_hmis events; presumed success. Check dmesg." + echo "" +done diff --git a/tools/testing/selftests/powerpc/tm/.gitignore b/tools/testing/selftests/powerpc/tm/.gitignore index 2699635d2cd9..7d0f14b8cb2e 100644 --- a/tools/testing/selftests/powerpc/tm/.gitignore +++ b/tools/testing/selftests/powerpc/tm/.gitignore @@ -1,2 +1,5 @@ tm-resched-dscr tm-syscall +tm-signal-msr-resv +tm-signal-stack +tm-vmxcopy diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile index 4bea62a319dc..737f72c964e6 100644 --- a/tools/testing/selftests/powerpc/tm/Makefile +++ b/tools/testing/selftests/powerpc/tm/Makefile @@ -1,8 +1,8 @@ -TEST_PROGS := tm-resched-dscr tm-syscall +TEST_PROGS := tm-resched-dscr tm-syscall tm-signal-msr-resv tm-signal-stack tm-vmxcopy all: $(TEST_PROGS) -$(TEST_PROGS): ../harness.c +$(TEST_PROGS): ../harness.c ../utils.c tm-syscall: tm-syscall-asm.S tm-syscall: CFLAGS += -mhtm -I../../../../../usr/include diff --git a/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c b/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c index 42d4c8caad81..8fde93d6021f 100644 --- a/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c +++ b/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c @@ -29,6 +29,7 @@ #include <asm/tm.h> #include "utils.h" +#include "tm.h" #define TBEGIN ".long 0x7C00051D ;" #define TEND ".long 0x7C00055D ;" @@ -42,6 +43,8 @@ int test_body(void) { uint64_t rv, dscr1 = 1, dscr2, texasr; + SKIP_IF(!have_htm()); + printf("Check DSCR TM context switch: "); fflush(stdout); for (;;) { diff --git a/tools/testing/selftests/powerpc/tm/tm-signal-msr-resv.c b/tools/testing/selftests/powerpc/tm/tm-signal-msr-resv.c new file mode 100644 index 000000000000..d86653f282b1 --- /dev/null +++ b/tools/testing/selftests/powerpc/tm/tm-signal-msr-resv.c @@ -0,0 +1,74 @@ +/* + * Copyright 2015, Michael Neuling, IBM Corp. + * Licensed under GPLv2. + * + * Test the kernel's signal return code to ensure that it doesn't + * crash when both the transactional and suspend MSR bits are set in + * the signal context. + * + * For this test, we send ourselves a SIGUSR1. In the SIGUSR1 handler + * we modify the signal context to set both MSR TM S and T bits (which + * is "reserved" by the PowerISA). When we return from the signal + * handler (implicit sigreturn), the kernel should detect reserved MSR + * value and send us with a SIGSEGV. + */ + +#include <stdlib.h> +#include <stdio.h> +#include <signal.h> +#include <unistd.h> + +#include "utils.h" +#include "tm.h" + +int segv_expected = 0; + +void signal_segv(int signum) +{ + if (segv_expected && (signum == SIGSEGV)) + _exit(0); + _exit(1); +} + +void signal_usr1(int signum, siginfo_t *info, void *uc) +{ + ucontext_t *ucp = uc; + + /* Link tm checkpointed context to normal context */ + ucp->uc_link = ucp; + /* Set all TM bits so that the context is now invalid */ +#ifdef __powerpc64__ + ucp->uc_mcontext.gp_regs[PT_MSR] |= (7ULL << 32); +#else + ucp->uc_mcontext.regs->gpr[PT_MSR] |= (7ULL); +#endif + /* Should segv on return becuase of invalid context */ + segv_expected = 1; +} + +int tm_signal_msr_resv() +{ + struct sigaction act; + + SKIP_IF(!have_htm()); + + act.sa_sigaction = signal_usr1; + sigemptyset(&act.sa_mask); + act.sa_flags = SA_SIGINFO; + if (sigaction(SIGUSR1, &act, NULL) < 0) { + perror("sigaction sigusr1"); + exit(1); + } + if (signal(SIGSEGV, signal_segv) == SIG_ERR) + exit(1); + + raise(SIGUSR1); + + /* We shouldn't get here as we exit in the segv handler */ + return 1; +} + +int main(void) +{ + return test_harness(tm_signal_msr_resv, "tm_signal_msr_resv"); +} diff --git a/tools/testing/selftests/powerpc/tm/tm-signal-stack.c b/tools/testing/selftests/powerpc/tm/tm-signal-stack.c new file mode 100644 index 000000000000..e44a238c1d77 --- /dev/null +++ b/tools/testing/selftests/powerpc/tm/tm-signal-stack.c @@ -0,0 +1,76 @@ +/* + * Copyright 2015, Michael Neuling, IBM Corp. + * Licensed under GPLv2. + * + * Test the kernel's signal delievery code to ensure that we don't + * trelaim twice in the kernel signal delivery code. This can happen + * if we trigger a signal when in a transaction and the stack pointer + * is bogus. + * + * This test case registers a SEGV handler, sets the stack pointer + * (r1) to NULL, starts a transaction and then generates a SEGV. The + * SEGV should be handled but we exit here as the stack pointer is + * invalid and hance we can't sigreturn. We only need to check that + * this flow doesn't crash the kernel. + */ + +#include <unistd.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <stdlib.h> +#include <stdio.h> +#include <signal.h> + +#include "utils.h" +#include "tm.h" + +void signal_segv(int signum) +{ + /* This should never actually run since stack is foobar */ + exit(1); +} + +int tm_signal_stack() +{ + int pid; + + SKIP_IF(!have_htm()); + + pid = fork(); + if (pid < 0) + exit(1); + + if (pid) { /* Parent */ + /* + * It's likely the whole machine will crash here so if + * the child ever exits, we are good. + */ + wait(NULL); + return 0; + } + + /* + * The flow here is: + * 1) register a signal handler (so signal delievery occurs) + * 2) make stack pointer (r1) = NULL + * 3) start transaction + * 4) cause segv + */ + if (signal(SIGSEGV, signal_segv) == SIG_ERR) + exit(1); + asm volatile("li 1, 0 ;" /* stack ptr == NULL */ + "1:" + ".long 0x7C00051D ;" /* tbegin */ + "beq 1b ;" /* retry forever */ + ".long 0x7C0005DD ; ;" /* tsuspend */ + "ld 2, 0(1) ;" /* trigger segv" */ + : : : "memory"); + + /* This should never get here due to above segv */ + return 1; +} + +int main(void) +{ + return test_harness(tm_signal_stack, "tm_signal_stack"); +} diff --git a/tools/testing/selftests/powerpc/tm/tm-syscall.c b/tools/testing/selftests/powerpc/tm/tm-syscall.c index e835bf7ec7ae..60560cb20e38 100644 --- a/tools/testing/selftests/powerpc/tm/tm-syscall.c +++ b/tools/testing/selftests/powerpc/tm/tm-syscall.c @@ -13,12 +13,11 @@ #include <unistd.h> #include <sys/syscall.h> #include <asm/tm.h> -#include <asm/cputable.h> -#include <linux/auxvec.h> #include <sys/time.h> #include <stdlib.h> #include "utils.h" +#include "tm.h" extern int getppid_tm_active(void); extern int getppid_tm_suspended(void); @@ -77,16 +76,6 @@ pid_t getppid_tm(bool suspend) exit(-1); } -static inline bool have_htm_nosc(void) -{ -#ifdef PPC_FEATURE2_HTM_NOSC - return ((long)get_auxv_entry(AT_HWCAP2) & PPC_FEATURE2_HTM_NOSC); -#else - printf("PPC_FEATURE2_HTM_NOSC not defined, can't check AT_HWCAP2\n"); - return false; -#endif -} - int tm_syscall(void) { unsigned count = 0; diff --git a/tools/testing/selftests/powerpc/tm/tm-vmxcopy.c b/tools/testing/selftests/powerpc/tm/tm-vmxcopy.c new file mode 100644 index 000000000000..0274de7b11f3 --- /dev/null +++ b/tools/testing/selftests/powerpc/tm/tm-vmxcopy.c @@ -0,0 +1,103 @@ +/* + * Copyright 2015, Michael Neuling, IBM Corp. + * Licensed under GPLv2. + * + * Original: Michael Neuling 4/12/2013 + * Edited: Rashmica Gupta 4/12/2015 + * + * See if the altivec state is leaked out of an aborted transaction due to + * kernel vmx copy loops. + * + * When the transaction aborts, VSR values should rollback to the values + * they held before the transaction commenced. Using VSRs while transaction + * is suspended should not affect the checkpointed values. + * + * (1) write A to a VSR + * (2) start transaction + * (3) suspend transaction + * (4) change the VSR to B + * (5) trigger kernel vmx copy loop + * (6) abort transaction + * (7) check that the VSR value is A + */ + +#include <inttypes.h> +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <sys/mman.h> +#include <string.h> +#include <assert.h> + +#include "tm.h" +#include "utils.h" + +int test_vmxcopy() +{ + long double vecin = 1.3; + long double vecout; + unsigned long pgsize = getpagesize(); + int i; + int fd; + int size = pgsize*16; + char tmpfile[] = "/tmp/page_faultXXXXXX"; + char buf[pgsize]; + char *a; + uint64_t aborted = 0; + + SKIP_IF(!have_htm()); + + fd = mkstemp(tmpfile); + assert(fd >= 0); + + memset(buf, 0, pgsize); + for (i = 0; i < size; i += pgsize) + assert(write(fd, buf, pgsize) == pgsize); + + unlink(tmpfile); + + a = mmap(NULL, size, PROT_READ|PROT_WRITE, MAP_PRIVATE, fd, 0); + assert(a != MAP_FAILED); + + asm __volatile__( + "lxvd2x 40,0,%[vecinptr];" /* set 40 to initial value*/ + "tbegin.;" + "beq 3f;" + "tsuspend.;" + "xxlxor 40,40,40;" /* set 40 to 0 */ + "std 5, 0(%[map]);" /* cause kernel vmx copy page */ + "tabort. 0;" + "tresume.;" + "tend.;" + "li %[res], 0;" + "b 5f;" + + /* Abort handler */ + "3:;" + "li %[res], 1;" + + "5:;" + "stxvd2x 40,0,%[vecoutptr];" + : [res]"=r"(aborted) + : [vecinptr]"r"(&vecin), + [vecoutptr]"r"(&vecout), + [map]"r"(a) + : "memory", "r0", "r3", "r4", "r5", "r6", "r7"); + + if (aborted && (vecin != vecout)){ + printf("FAILED: vector state leaked on abort %f != %f\n", + (double)vecin, (double)vecout); + return 1; + } + + munmap(a, size); + + close(fd); + + return 0; +} + +int main(void) +{ + return test_harness(test_vmxcopy, "tm_vmxcopy"); +} diff --git a/tools/testing/selftests/powerpc/tm/tm.h b/tools/testing/selftests/powerpc/tm/tm.h new file mode 100644 index 000000000000..24144b25772c --- /dev/null +++ b/tools/testing/selftests/powerpc/tm/tm.h @@ -0,0 +1,34 @@ +/* + * Copyright 2015, Michael Ellerman, IBM Corp. + * Licensed under GPLv2. + */ + +#ifndef _SELFTESTS_POWERPC_TM_TM_H +#define _SELFTESTS_POWERPC_TM_TM_H + +#include <stdbool.h> +#include <asm/cputable.h> + +#include "../utils.h" + +static inline bool have_htm(void) +{ +#ifdef PPC_FEATURE2_HTM + return have_hwcap2(PPC_FEATURE2_HTM); +#else + printf("PPC_FEATURE2_HTM not defined, can't check AT_HWCAP2\n"); + return false; +#endif +} + +static inline bool have_htm_nosc(void) +{ +#ifdef PPC_FEATURE2_HTM_NOSC + return have_hwcap2(PPC_FEATURE2_HTM_NOSC); +#else + printf("PPC_FEATURE2_HTM_NOSC not defined, can't check AT_HWCAP2\n"); + return false; +#endif +} + +#endif /* _SELFTESTS_POWERPC_TM_TM_H */ diff --git a/tools/testing/selftests/powerpc/utils.c b/tools/testing/selftests/powerpc/utils.c new file mode 100644 index 000000000000..dcf74184bfd0 --- /dev/null +++ b/tools/testing/selftests/powerpc/utils.c @@ -0,0 +1,87 @@ +/* + * Copyright 2013-2015, Michael Ellerman, IBM Corp. + * Licensed under GPLv2. + */ + +#define _GNU_SOURCE /* For CPU_ZERO etc. */ + +#include <elf.h> +#include <errno.h> +#include <fcntl.h> +#include <link.h> +#include <sched.h> +#include <stdio.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <unistd.h> + +#include "utils.h" + +static char auxv[4096]; + +void *get_auxv_entry(int type) +{ + ElfW(auxv_t) *p; + void *result; + ssize_t num; + int fd; + + fd = open("/proc/self/auxv", O_RDONLY); + if (fd == -1) { + perror("open"); + return NULL; + } + + result = NULL; + + num = read(fd, auxv, sizeof(auxv)); + if (num < 0) { + perror("read"); + goto out; + } + + if (num > sizeof(auxv)) { + printf("Overflowed auxv buffer\n"); + goto out; + } + + p = (ElfW(auxv_t) *)auxv; + + while (p->a_type != AT_NULL) { + if (p->a_type == type) { + result = (void *)p->a_un.a_val; + break; + } + + p++; + } +out: + close(fd); + return result; +} + +int pick_online_cpu(void) +{ + cpu_set_t mask; + int cpu; + + CPU_ZERO(&mask); + + if (sched_getaffinity(0, sizeof(mask), &mask)) { + perror("sched_getaffinity"); + return -1; + } + + /* We prefer a primary thread, but skip 0 */ + for (cpu = 8; cpu < CPU_SETSIZE; cpu += 8) + if (CPU_ISSET(cpu, &mask)) + return cpu; + + /* Search for anything, but in reverse */ + for (cpu = CPU_SETSIZE - 1; cpu >= 0; cpu--) + if (CPU_ISSET(cpu, &mask)) + return cpu; + + printf("No cpus in affinity mask?!\n"); + return -1; +} diff --git a/tools/testing/selftests/powerpc/utils.h b/tools/testing/selftests/powerpc/utils.h index b7d41086bb0a..175ac6ad10dd 100644 --- a/tools/testing/selftests/powerpc/utils.h +++ b/tools/testing/selftests/powerpc/utils.h @@ -8,6 +8,7 @@ #include <stdint.h> #include <stdbool.h> +#include <linux/auxvec.h> /* Avoid headaches with PRI?64 - just use %ll? always */ typedef unsigned long long u64; @@ -21,6 +22,12 @@ typedef uint8_t u8; int test_harness(int (test_function)(void), char *name); extern void *get_auxv_entry(int type); +int pick_online_cpu(void); + +static inline bool have_hwcap2(unsigned long ftr2) +{ + return ((unsigned long)get_auxv_entry(AT_HWCAP2) & ftr2) == ftr2; +} /* Yes, this is evil */ #define FAIL_IF(x) \ diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index eabcff411984..d0c473f65850 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -4,9 +4,11 @@ include ../lib.mk .PHONY: all all_32 all_64 warn_32bit_failure clean -TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs ldt_gdt syscall_nt ptrace_syscall +TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_syscall TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault sigreturn test_syscall_vdso unwind_vdso \ - test_FCMOV test_FCOMI test_FISTTP + test_FCMOV test_FCOMI test_FISTTP \ + ldt_gdt \ + vdso_restorer TARGETS_C_32BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_32BIT_ONLY) BINARIES_32 := $(TARGETS_C_32BIT_ALL:%=%_32) diff --git a/tools/testing/selftests/x86/vdso_restorer.c b/tools/testing/selftests/x86/vdso_restorer.c new file mode 100644 index 000000000000..cb038424a403 --- /dev/null +++ b/tools/testing/selftests/x86/vdso_restorer.c @@ -0,0 +1,88 @@ +/* + * vdso_restorer.c - tests vDSO-based signal restore + * Copyright (c) 2015 Andrew Lutomirski + * + * This program is free software; you can redistribute it and/or modify + * it under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * This makes sure that sa_restorer == NULL keeps working on 32-bit + * configurations. Modern glibc doesn't use it under any circumstances, + * so it's easy to overlook breakage. + * + * 64-bit userspace has never supported sa_restorer == NULL, so this is + * 32-bit only. + */ + +#define _GNU_SOURCE + +#include <err.h> +#include <stdio.h> +#include <string.h> +#include <signal.h> +#include <unistd.h> +#include <syscall.h> +#include <sys/syscall.h> + +/* Open-code this -- the headers are too messy to easily use them. */ +struct real_sigaction { + void *handler; + unsigned long flags; + void *restorer; + unsigned int mask[2]; +}; + +static volatile sig_atomic_t handler_called; + +static void handler_with_siginfo(int sig, siginfo_t *info, void *ctx_void) +{ + handler_called = 1; +} + +static void handler_without_siginfo(int sig) +{ + handler_called = 1; +} + +int main() +{ + int nerrs = 0; + struct real_sigaction sa; + + memset(&sa, 0, sizeof(sa)); + sa.handler = handler_with_siginfo; + sa.flags = SA_SIGINFO; + sa.restorer = NULL; /* request kernel-provided restorer */ + + if (syscall(SYS_rt_sigaction, SIGUSR1, &sa, NULL, 8) != 0) + err(1, "raw rt_sigaction syscall"); + + raise(SIGUSR1); + + if (handler_called) { + printf("[OK]\tSA_SIGINFO handler returned successfully\n"); + } else { + printf("[FAIL]\tSA_SIGINFO handler was not called\n"); + nerrs++; + } + + sa.flags = 0; + sa.handler = handler_without_siginfo; + if (syscall(SYS_sigaction, SIGUSR1, &sa, 0) != 0) + err(1, "raw sigaction syscall"); + handler_called = 0; + + raise(SIGUSR1); + + if (handler_called) { + printf("[OK]\t!SA_SIGINFO handler returned successfully\n"); + } else { + printf("[FAIL]\t!SA_SIGINFO handler was not called\n"); + nerrs++; + } +} |