diff --git a/CREDITS b/CREDITS index d8f63e8329e8..b97256d5bc24 100644 --- a/CREDITS +++ b/CREDITS @@ -315,6 +315,11 @@ S: Via Delle Palme, 9 S: Terni 05100 S: Italy +N: Ohad Ben Cohen +E: ohad@wizery.com +D: Remote Processor (remoteproc) subsystem +D: Remote Processor Messaging (rpmsg) subsystem + N: Krzysztof Benedyczak E: golbi@mat.uni.torun.pl W: http://www.mat.uni.torun.pl/~golbi diff --git a/Documentation/ABI/stable/sysfs-driver-dma-idxd b/Documentation/ABI/stable/sysfs-driver-dma-idxd index df4afbccf037..0c2b613f2373 100644 --- a/Documentation/ABI/stable/sysfs-driver-dma-idxd +++ b/Documentation/ABI/stable/sysfs-driver-dma-idxd @@ -41,14 +41,14 @@ KernelVersion: 5.6.0 Contact: dmaengine@vger.kernel.org Description: The maximum number of groups can be created under this device. -What: /sys/bus/dsa/devices/dsa/max_tokens -Date: Oct 25, 2019 -KernelVersion: 5.6.0 +What: /sys/bus/dsa/devices/dsa/max_read_buffers +Date: Dec 10, 2021 +KernelVersion: 5.17.0 Contact: dmaengine@vger.kernel.org -Description: The total number of bandwidth tokens supported by this device. - The bandwidth tokens represent resources within the DSA +Description: The total number of read buffers supported by this device. + The read buffers represent resources within the DSA implementation, and these resources are allocated by engines to - support operations. + support operations. See DSA spec v1.2 9.2.4 Total Read Buffers. What: /sys/bus/dsa/devices/dsa/max_transfer_size Date: Oct 25, 2019 @@ -115,13 +115,13 @@ KernelVersion: 5.6.0 Contact: dmaengine@vger.kernel.org Description: To indicate if this device is configurable or not. -What: /sys/bus/dsa/devices/dsa/token_limit -Date: Oct 25, 2019 -KernelVersion: 5.6.0 +What: /sys/bus/dsa/devices/dsa/read_buffer_limit +Date: Dec 10, 2021 +KernelVersion: 5.17.0 Contact: dmaengine@vger.kernel.org -Description: The maximum number of bandwidth tokens that may be in use at +Description: The maximum number of read buffers that may be in use at one time by operations that access low bandwidth memory in the - device. + device. See DSA spec v1.2 9.2.8 GENCFG on Global Read Buffer Limit. What: /sys/bus/dsa/devices/dsa/cmd_status Date: Aug 28, 2020 @@ -220,8 +220,38 @@ Contact: dmaengine@vger.kernel.org Description: Show the current number of entries in this WQ if WQ Occupancy Support bit WQ capabilities is 1. +What: /sys/bus/dsa/devices/wq./enqcmds_retries +Date Oct 29, 2021 +KernelVersion: 5.17.0 +Contact: dmaengine@vger.kernel.org +Description: Indicate the number of retires for an enqcmds submission on a sharedwq. + A max value to set attribute is capped at 64. + What: /sys/bus/dsa/devices/engine./group_id Date: Oct 25, 2019 KernelVersion: 5.6.0 Contact: dmaengine@vger.kernel.org Description: The group that this engine belongs to. + +What: /sys/bus/dsa/devices/group./use_read_buffer_limit +Date: Dec 10, 2021 +KernelVersion: 5.17.0 +Contact: dmaengine@vger.kernel.org +Description: Enable the use of global read buffer limit for the group. See DSA + spec v1.2 9.2.18 GRPCFG Use Global Read Buffer Limit. + +What: /sys/bus/dsa/devices/group./read_buffers_allowed +Date: Dec 10, 2021 +KernelVersion: 5.17.0 +Contact: dmaengine@vger.kernel.org +Description: Indicates max number of read buffers that may be in use at one time + by all engines in the group. See DSA spec v1.2 9.2.18 GRPCFG Read + Buffers Allowed. + +What: /sys/bus/dsa/devices/group./read_buffers_reserved +Date: Dec 10, 2021 +KernelVersion: 5.17.0 +Contact: dmaengine@vger.kernel.org +Description: Indicates the number of Read Buffers reserved for the use of + engines in the group. See DSA spec v1.2 9.2.18 GRPCFG Read Buffers + Reserved. diff --git a/Documentation/ABI/testing/sysfs-bus-vdpa b/Documentation/ABI/testing/sysfs-bus-vdpa new file mode 100644 index 000000000000..28a6111202ba --- /dev/null +++ b/Documentation/ABI/testing/sysfs-bus-vdpa @@ -0,0 +1,57 @@ +What: /sys/bus/vdpa/driver_autoprobe +Date: March 2020 +Contact: virtualization@lists.linux-foundation.org +Description: + This file determines whether new devices are immediately bound + to a driver after the creation. It initially contains 1, which + means the kernel automatically binds devices to a compatible + driver immediately after they are created. + + Writing "0" to this file disable this feature, any other string + enable it. + +What: /sys/bus/vdpa/driver_probe +Date: March 2020 +Contact: virtualization@lists.linux-foundation.org +Description: + Writing a device name to this file will cause the kernel binds + devices to a compatible driver. + + This can be useful when /sys/bus/vdpa/driver_autoprobe is + disabled. + +What: /sys/bus/vdpa/drivers/.../bind +Date: March 2020 +Contact: virtualization@lists.linux-foundation.org +Description: + Writing a device name to this file will cause the driver to + attempt to bind to the device. This is useful for overriding + default bindings. + +What: /sys/bus/vdpa/drivers/.../unbind +Date: March 2020 +Contact: virtualization@lists.linux-foundation.org +Description: + Writing a device name to this file will cause the driver to + attempt to unbind from the device. This may be useful when + overriding default bindings. + +What: /sys/bus/vdpa/devices/.../driver_override +Date: November 2021 +Contact: virtualization@lists.linux-foundation.org +Description: + This file allows the driver for a device to be specified. + When specified, only a driver with a name matching the value + written to driver_override will have an opportunity to bind to + the device. The override is specified by writing a string to the + driver_override file (echo vhost-vdpa > driver_override) and may + be cleared with an empty string (echo > driver_override). + This returns the device to standard matching rules binding. + Writing to driver_override does not automatically unbind the + device from its current driver or make any attempt to + automatically load the specified driver. If no driver with a + matching name is currently loaded in the kernel, the device will + not bind to any driver. This also allows devices to opt-out of + driver binding using a driver_override name such as "none". + Only a single driver may be specified in the override, there is + no support for parsing delimiters. diff --git a/Documentation/devicetree/bindings/dma/arm,pl330.yaml b/Documentation/devicetree/bindings/dma/arm,pl330.yaml new file mode 100644 index 000000000000..decab185cf4d --- /dev/null +++ b/Documentation/devicetree/bindings/dma/arm,pl330.yaml @@ -0,0 +1,83 @@ +# SPDX-License-Identifier: GPL-2.0 +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/dma/arm,pl330.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: ARM PrimeCell PL330 DMA Controller + +maintainers: + - Vinod Koul + +description: + The ARM PrimeCell PL330 DMA controller can move blocks of memory contents + between memory and peripherals or memory to memory. + +# We need a select here so we don't match all nodes with 'arm,primecell' +select: + properties: + compatible: + contains: + const: arm,pl330 + required: + - compatible + +allOf: + - $ref: dma-controller.yaml# + - $ref: /schemas/arm/primecell.yaml# + +properties: + compatible: + items: + - enum: + - arm,pl330 + - const: arm,primecell + + reg: + maxItems: 1 + + interrupts: + minItems: 1 + maxItems: 32 + description: A single combined interrupt or an interrupt per event + + '#dma-cells': + const: 1 + description: Contains the DMA request number for the consumer + + arm,pl330-broken-no-flushp: + type: boolean + description: quirk for avoiding to execute DMAFLUSHP + + arm,pl330-periph-burst: + type: boolean + description: quirk for performing burst transfer only + + dma-coherent: true + + resets: + minItems: 1 + maxItems: 2 + + reset-names: + minItems: 1 + items: + - const: dma + - const: dma-ocp + +required: + - compatible + - reg + - interrupts + +unevaluatedProperties: false + +examples: + - | + dma-controller@12680000 { + compatible = "arm,pl330", "arm,primecell"; + reg = <0x12680000 0x1000>; + interrupts = <99>; + #dma-cells = <1>; + }; +... diff --git a/Documentation/devicetree/bindings/dma/arm-pl08x.yaml b/Documentation/devicetree/bindings/dma/arm-pl08x.yaml index 3bd9eea543ca..9193b18fb75f 100644 --- a/Documentation/devicetree/bindings/dma/arm-pl08x.yaml +++ b/Documentation/devicetree/bindings/dma/arm-pl08x.yaml @@ -10,6 +10,7 @@ maintainers: - Vinod Koul allOf: + - $ref: /schemas/arm/primecell.yaml# - $ref: "dma-controller.yaml#" # We need a select here so we don't match all nodes with 'arm,primecell' @@ -89,6 +90,9 @@ properties: - 64 description: bus width used for memcpy in bits. FTDMAC020 also accept 64 bits + resets: + maxItems: 1 + required: - reg - interrupts diff --git a/Documentation/devicetree/bindings/dma/arm-pl330.txt b/Documentation/devicetree/bindings/dma/arm-pl330.txt deleted file mode 100644 index 315e90122afa..000000000000 --- a/Documentation/devicetree/bindings/dma/arm-pl330.txt +++ /dev/null @@ -1,49 +0,0 @@ -* ARM PrimeCell PL330 DMA Controller - -The ARM PrimeCell PL330 DMA controller can move blocks of memory contents -between memory and peripherals or memory to memory. - -Required properties: - - compatible: should include both "arm,pl330" and "arm,primecell". - - reg: physical base address of the controller and length of memory mapped - region. - - interrupts: interrupt number to the cpu. - -Optional properties: - - dma-coherent : Present if dma operations are coherent - - #dma-cells: must be <1>. used to represent the number of integer - cells in the dmas property of client device. - - dma-channels: contains the total number of DMA channels supported by the DMAC - - dma-requests: contains the total number of DMA requests supported by the DMAC - - arm,pl330-broken-no-flushp: quirk for avoiding to execute DMAFLUSHP - - arm,pl330-periph-burst: quirk for performing burst transfer only - - resets: contains an entry for each entry in reset-names. - See ../reset/reset.txt for details. - - reset-names: must contain at least "dma", and optional is "dma-ocp". - -Example: - - pdma0: pdma@12680000 { - compatible = "arm,pl330", "arm,primecell"; - reg = <0x12680000 0x1000>; - interrupts = <99>; - #dma-cells = <1>; - #dma-channels = <8>; - #dma-requests = <32>; - }; - -Client drivers (device nodes requiring dma transfers from dev-to-mem or -mem-to-dev) should specify the DMA channel numbers and dma channel names -as shown below. - - [property name] = <[phandle of the dma controller] [dma request id]>; - [property name] = <[dma channel name]> - - where 'dma request id' is the dma request number which is connected - to the client controller. The 'property name' 'dmas' and 'dma-names' - as required by the generic dma device tree binding helpers. The dma - names correspond 1:1 with the dma request ids in the dmas property. - - Example: dmas = <&pdma0 12 - &pdma1 11>; - dma-names = "tx", "rx"; diff --git a/Documentation/devicetree/bindings/dma/dma-controller.yaml b/Documentation/devicetree/bindings/dma/dma-controller.yaml index 0043b91da95e..6d3727267fa8 100644 --- a/Documentation/devicetree/bindings/dma/dma-controller.yaml +++ b/Documentation/devicetree/bindings/dma/dma-controller.yaml @@ -24,10 +24,10 @@ examples: dma: dma-controller@48000000 { compatible = "ti,omap-sdma"; reg = <0x48000000 0x1000>; - interrupts = <0 12 0x4 - 0 13 0x4 - 0 14 0x4 - 0 15 0x4>; + interrupts = <0 12 0x4>, + <0 13 0x4>, + <0 14 0x4>, + <0 15 0x4>; #dma-cells = <1>; dma-channels = <32>; dma-requests = <127>; diff --git a/Documentation/devicetree/bindings/dma/ingenic,dma.yaml b/Documentation/devicetree/bindings/dma/ingenic,dma.yaml index dc059d6fd037..3b0b3b919af8 100644 --- a/Documentation/devicetree/bindings/dma/ingenic,dma.yaml +++ b/Documentation/devicetree/bindings/dma/ingenic,dma.yaml @@ -14,15 +14,23 @@ allOf: properties: compatible: - enum: - - ingenic,jz4740-dma - - ingenic,jz4725b-dma - - ingenic,jz4760-dma - - ingenic,jz4760b-dma - - ingenic,jz4770-dma - - ingenic,jz4780-dma - - ingenic,x1000-dma - - ingenic,x1830-dma + oneOf: + - enum: + - ingenic,jz4740-dma + - ingenic,jz4725b-dma + - ingenic,jz4760-dma + - ingenic,jz4760-bdma + - ingenic,jz4760-mdma + - ingenic,jz4760b-dma + - ingenic,jz4760b-bdma + - ingenic,jz4760b-mdma + - ingenic,jz4770-dma + - ingenic,jz4780-dma + - ingenic,x1000-dma + - ingenic,x1830-dma + - items: + - const: ingenic,jz4770-bdma + - const: ingenic,jz4760b-bdma reg: items: @@ -36,13 +44,19 @@ properties: maxItems: 1 "#dma-cells": - const: 2 + enum: [2, 3] description: > DMA clients must use the format described in dma.txt, giving a phandle - to the DMA controller plus the following 2 integer cells: + to the DMA controller plus the following integer cells: - - Request type: The DMA request type for transfers to/from the - device on the allocated channel, as defined in the SoC documentation. + - Request type: The DMA request type specifies the device endpoint that + will be the source or destination of the DMA transfer. + If "#dma-cells" is 2, the request type is a single cell, and the + direction will be unidirectional (either RX or TX but not both). + If "#dma-cells" is 3, the request type has two cells; the first + one corresponds to the host to device direction (TX), the second one + corresponds to the device to host direction (RX). The DMA channel is + then bidirectional. - Channel: If set to 0xffffffff, any available channel will be allocated for the client. Otherwise, the exact channel specified will be used. diff --git a/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.yaml b/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.yaml index d8142cbd13d3..7c6badf39921 100644 --- a/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.yaml +++ b/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.yaml @@ -44,6 +44,10 @@ properties: - items: - const: renesas,dmac-r8a779a0 # R-Car V3U + - items: + - const: renesas,dmac-r8a779f0 # R-Car S4-8 + - const: renesas,rcar-gen4-dmac + reg: true interrupts: @@ -118,6 +122,7 @@ if: contains: enum: - renesas,dmac-r8a779a0 + - renesas,rcar-gen4-dmac then: properties: reg: diff --git a/Documentation/devicetree/bindings/dma/snps,dw-axi-dmac.yaml b/Documentation/devicetree/bindings/dma/snps,dw-axi-dmac.yaml index 79e241498e25..4324a94b26b2 100644 --- a/Documentation/devicetree/bindings/dma/snps,dw-axi-dmac.yaml +++ b/Documentation/devicetree/bindings/dma/snps,dw-axi-dmac.yaml @@ -53,6 +53,9 @@ properties: minimum: 1 maximum: 8 + resets: + maxItems: 1 + snps,dma-masters: description: | Number of AXI masters supported by the hardware. diff --git a/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml b/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml index df29d59d13a8..08627d91e607 100644 --- a/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml +++ b/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml @@ -30,6 +30,7 @@ description: | allOf: - $ref: /schemas/dma/dma-controller.yaml# + - $ref: /schemas/arm/keystone/ti,k3-sci-common.yaml# properties: compatible: diff --git a/Documentation/devicetree/bindings/dma/ti/k3-pktdma.yaml b/Documentation/devicetree/bindings/dma/ti/k3-pktdma.yaml index ea19d12a9337..507d16d84ade 100644 --- a/Documentation/devicetree/bindings/dma/ti/k3-pktdma.yaml +++ b/Documentation/devicetree/bindings/dma/ti/k3-pktdma.yaml @@ -25,6 +25,7 @@ description: | allOf: - $ref: /schemas/dma/dma-controller.yaml# + - $ref: /schemas/arm/keystone/ti,k3-sci-common.yaml# properties: compatible: diff --git a/Documentation/devicetree/bindings/input/touchscreen/zinitix,bt400.yaml b/Documentation/devicetree/bindings/input/touchscreen/zinitix,bt400.yaml new file mode 100644 index 000000000000..b4e5ba7c0b49 --- /dev/null +++ b/Documentation/devicetree/bindings/input/touchscreen/zinitix,bt400.yaml @@ -0,0 +1,115 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/input/touchscreen/zinitix,bt400.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Zinitix BT4xx and BT5xx series touchscreen controller bindings + +description: The Zinitix BT4xx and BT5xx series of touchscreen controllers + are Korea-produced touchscreens with embedded microcontrollers. The + BT4xx series was produced 2010-2013 and the BT5xx series 2013-2014. + +maintainers: + - Michael Srba + - Linus Walleij + +allOf: + - $ref: touchscreen.yaml# + +properties: + $nodename: + pattern: "^touchscreen(@.*)?$" + + compatible: + enum: + - zinitix,bt402 + - zinitix,bt403 + - zinitix,bt404 + - zinitix,bt412 + - zinitix,bt413 + - zinitix,bt431 + - zinitix,bt432 + - zinitix,bt531 + - zinitix,bt532 + - zinitix,bt538 + - zinitix,bt541 + - zinitix,bt548 + - zinitix,bt554 + - zinitix,at100 + + reg: + description: I2C address on the I2C bus + + clock-frequency: + description: I2C client clock frequency, defined for host when using + the device on the I2C bus + minimum: 0 + maximum: 400000 + + interrupts: + description: Interrupt to host + maxItems: 1 + + vcca-supply: + description: Analog power supply regulator on the VCCA pin + + vdd-supply: + description: Digital power supply regulator on the VDD pin. + In older device trees this can be the accidental name for the analog + supply on the VCCA pin, and in that case the deprecated vddo-supply is + used for the digital power supply. + + vddo-supply: + description: Deprecated name for the digital power supply, use vdd-supply + as this reflects the real name of the pin. If this supply is present, + the vdd-supply represents VCCA instead of VDD. Implementers should first + check for this property, and if it is present assume that the vdd-supply + represents the analog supply. + deprecated: true + + reset-gpios: + description: Reset line for the touchscreen, should be tagged + as GPIO_ACTIVE_LOW + + zinitix,mode: + description: Mode of reporting touch points. Some modes may not work + with a particular ts firmware for unknown reasons. Available modes are + 1 and 2. Mode 2 is the default and preferred. + $ref: /schemas/types.yaml#/definitions/uint32 + enum: [1, 2] + + touchscreen-size-x: true + touchscreen-size-y: true + touchscreen-fuzz-x: true + touchscreen-fuzz-y: true + +additionalProperties: false + +required: + - compatible + - reg + - interrupts + - touchscreen-size-x + - touchscreen-size-y + +examples: + - | + #include + #include + i2c { + #address-cells = <1>; + #size-cells = <0>; + + touchscreen@20 { + compatible = "zinitix,bt541"; + reg = <0x20>; + interrupt-parent = <&gpio>; + interrupts = <13 IRQ_TYPE_EDGE_FALLING>; + vcca-supply = <®_vcca_tsp>; + vdd-supply = <®_vdd_tsp>; + touchscreen-size-x = <540>; + touchscreen-size-y = <960>; + zinitix,mode = <2>; + }; + }; diff --git a/Documentation/devicetree/bindings/input/touchscreen/zinitix.txt b/Documentation/devicetree/bindings/input/touchscreen/zinitix.txt deleted file mode 100644 index 446efb9f5f55..000000000000 --- a/Documentation/devicetree/bindings/input/touchscreen/zinitix.txt +++ /dev/null @@ -1,40 +0,0 @@ -Device tree bindings for Zinitx BT541 touchscreen controller - -Required properties: - - - compatible : Should be "zinitix,bt541" - - reg : I2C address of the chip. Should be 0x20 - - interrupts : Interrupt to which the chip is connected - -Optional properties: - - - vdd-supply : Analog power supply regulator on VCCA pin - - vddo-supply : Digital power supply regulator on VDD pin - - zinitix,mode : Mode of reporting touch points. Some modes may not work - with a particular ts firmware for unknown reasons. Available - modes are 1 and 2. Mode 2 is the default and preferred. - -The touchscreen-* properties are documented in touchscreen.txt in this -directory. - -Example: - - i2c@00000000 { - /* ... */ - - bt541@20 { - compatible = "zinitix,bt541"; - reg = <0x20>; - interrupt-parent = <&msmgpio>; - interrupts = <13 IRQ_TYPE_EDGE_FALLING>; - pinctrl-names = "default"; - pinctrl-0 = <&tsp_default>; - vdd-supply = <®_vdd_tsp>; - vddo-supply = <&pm8916_l6>; - touchscreen-size-x = <540>; - touchscreen-size-y = <960>; - zinitix,mode = <2>; - }; - - /* ... */ - }; diff --git a/Documentation/devicetree/bindings/remoteproc/qcom,adsp.yaml b/Documentation/devicetree/bindings/remoteproc/qcom,adsp.yaml index 63e06d93bca3..c635c181d2c2 100644 --- a/Documentation/devicetree/bindings/remoteproc/qcom,adsp.yaml +++ b/Documentation/devicetree/bindings/remoteproc/qcom,adsp.yaml @@ -33,6 +33,9 @@ properties: - qcom,sdm845-adsp-pas - qcom,sdm845-cdsp-pas - qcom,sdx55-mpss-pas + - qcom,sm6350-adsp-pas + - qcom,sm6350-cdsp-pas + - qcom,sm6350-mpss-pas - qcom,sm8150-adsp-pas - qcom,sm8150-cdsp-pas - qcom,sm8150-mpss-pas @@ -158,6 +161,9 @@ allOf: - qcom,sc8180x-mpss-pas - qcom,sdm845-adsp-pas - qcom,sdm845-cdsp-pas + - qcom,sm6350-adsp-pas + - qcom,sm6350-cdsp-pas + - qcom,sm6350-mpss-pas - qcom,sm8150-adsp-pas - qcom,sm8150-cdsp-pas - qcom,sm8150-mpss-pas @@ -266,6 +272,8 @@ allOf: - qcom,sc8180x-cdsp-pas - qcom,sdm845-adsp-pas - qcom,sdm845-cdsp-pas + - qcom,sm6350-adsp-pas + - qcom,sm6350-cdsp-pas - qcom,sm8150-adsp-pas - qcom,sm8150-cdsp-pas - qcom,sm8150-slpi-pas @@ -301,6 +309,7 @@ allOf: - qcom,sc7280-mpss-pas - qcom,sc8180x-mpss-pas - qcom,sdx55-mpss-pas + - qcom,sm6350-mpss-pas - qcom,sm8150-mpss-pas - qcom,sm8350-mpss-pas then: @@ -385,6 +394,23 @@ allOf: - const: mx - const: mss + - if: + properties: + compatible: + contains: + enum: + - qcom,sm6350-cdsp-pas + then: + properties: + power-domains: + items: + - description: CX power domain + - description: MX power domain + power-domain-names: + items: + - const: cx + - const: mx + - if: properties: compatible: @@ -405,6 +431,7 @@ allOf: enum: - qcom,sc7280-mpss-pas - qcom,sdx55-mpss-pas + - qcom,sm6350-mpss-pas - qcom,sm8150-mpss-pas - qcom,sm8350-mpss-pas then: @@ -425,6 +452,7 @@ allOf: enum: - qcom,sc8180x-adsp-pas - qcom,sc8180x-cdsp-pas + - qcom,sm6350-adsp-pas - qcom,sm8150-slpi-pas - qcom,sm8250-adsp-pas - qcom,sm8250-slpi-pas diff --git a/Documentation/devicetree/bindings/remoteproc/renesas,rcar-rproc.yaml b/Documentation/devicetree/bindings/remoteproc/renesas,rcar-rproc.yaml new file mode 100644 index 000000000000..a7d25fa920e5 --- /dev/null +++ b/Documentation/devicetree/bindings/remoteproc/renesas,rcar-rproc.yaml @@ -0,0 +1,65 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: "http://devicetree.org/schemas/remoteproc/renesas,rcar-rproc.yaml#" +$schema: "http://devicetree.org/meta-schemas/core.yaml#" + +title: Renesas R-Car remote processor controller bindings + +maintainers: + - Julien Massot + +description: | + This document defines the bindings for the remoteproc component that loads and + boots firmwares on the Renesas R-Car family chipset. + R-Car gen3 family may have a realtime processor, this processor shares peripheral + and RAM with the host processor with the same address map. + +properties: + compatible: + const: renesas,rcar-cr7 + + resets: + maxItems: 1 + + power-domains: + maxItems: 1 + + memory-region: + description: + List of phandles to the reserved memory regions associated with the + remoteproc device. This is variable and describes the memories shared with + the remote processor (e.g. remoteproc firmware and carveouts, rpmsg + vrings, ...). + (see ../reserved-memory/reserved-memory.yaml) + +required: + - compatible + - resets + - memory-region + - power-domains + +additionalProperties: false + +examples: + - | + #include + #include + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + + cr7_ram: cr7_ram@40040000 { + no-map; + reg = <0x0 0x40040000 0x0 0x1fc0000>; + }; + }; + + cr7_rproc: cr7 { + compatible = "renesas,rcar-cr7"; + memory-region = <&cr7_ram>; + power-domains = <&sysc R8A7795_PD_CR7>; + resets = <&cpg 222>; + }; + +... diff --git a/Documentation/devicetree/bindings/remoteproc/ti,k3-dsp-rproc.yaml b/Documentation/devicetree/bindings/remoteproc/ti,k3-dsp-rproc.yaml index 5ec6505ac408..7b56497eec4d 100644 --- a/Documentation/devicetree/bindings/remoteproc/ti,k3-dsp-rproc.yaml +++ b/Documentation/devicetree/bindings/remoteproc/ti,k3-dsp-rproc.yaml @@ -33,9 +33,11 @@ properties: enum: - ti,j721e-c66-dsp - ti,j721e-c71-dsp + - ti,j721s2-c71-dsp description: Use "ti,j721e-c66-dsp" for C66x DSPs on K3 J721E SoCs Use "ti,j721e-c71-dsp" for C71x DSPs on K3 J721E SoCs + Use "ti,j721s2-c71-dsp" for C71x DSPs on K3 J721S2 SoCs resets: description: | @@ -106,6 +108,7 @@ else: compatible: enum: - ti,j721e-c71-dsp + - ti,j721s2-c71-dsp then: properties: reg: diff --git a/Documentation/devicetree/bindings/remoteproc/ti,k3-r5f-rproc.yaml b/Documentation/devicetree/bindings/remoteproc/ti,k3-r5f-rproc.yaml index eeef255c4045..d9c7e8c2b268 100644 --- a/Documentation/devicetree/bindings/remoteproc/ti,k3-r5f-rproc.yaml +++ b/Documentation/devicetree/bindings/remoteproc/ti,k3-r5f-rproc.yaml @@ -38,6 +38,7 @@ properties: - ti,j721e-r5fss - ti,j7200-r5fss - ti,am64-r5fss + - ti,j721s2-r5fss power-domains: description: | @@ -64,9 +65,9 @@ properties: description: | Configuration Mode for the Dual R5F cores within the R5F cluster. Should be either a value of 1 (LockStep mode) or 0 (Split mode) on - most SoCs (AM65x, J721E, J7200), default is LockStep mode if omitted; - and should be either a value of 0 (Split mode) or 2 (Single-CPU mode) - on AM64x SoCs, default is Split mode if omitted. + most SoCs (AM65x, J721E, J7200, J721s2), default is LockStep mode if + omitted; and should be either a value of 0 (Split mode) or 2 + (Single-CPU mode) on AM64x SoCs, default is Split mode if omitted. # R5F Processor Child Nodes: # ========================== @@ -104,6 +105,7 @@ patternProperties: - ti,j721e-r5f - ti,j7200-r5f - ti,am64-r5f + - ti,j721s2-r5f reg: items: diff --git a/Documentation/devicetree/bindings/watchdog/brcm,bcm7038-wdt.txt b/Documentation/devicetree/bindings/watchdog/brcm,bcm7038-wdt.txt deleted file mode 100644 index 84122270be8f..000000000000 --- a/Documentation/devicetree/bindings/watchdog/brcm,bcm7038-wdt.txt +++ /dev/null @@ -1,19 +0,0 @@ -BCM7038 Watchdog timer - -Required properties: - -- compatible : should be "brcm,bcm7038-wdt" -- reg : Specifies base physical address and size of the registers. - -Optional properties: - -- clocks: The clock running the watchdog. If no clock is found the - driver will default to 27000000 Hz. - -Example: - -watchdog@f040a7e8 { - compatible = "brcm,bcm7038-wdt"; - clocks = <&upg_fixed>; - reg = <0xf040a7e8 0x16>; -}; diff --git a/Documentation/devicetree/bindings/watchdog/brcm,bcm7038-wdt.yaml b/Documentation/devicetree/bindings/watchdog/brcm,bcm7038-wdt.yaml new file mode 100644 index 000000000000..a926809352b8 --- /dev/null +++ b/Documentation/devicetree/bindings/watchdog/brcm,bcm7038-wdt.yaml @@ -0,0 +1,43 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/watchdog/brcm,bcm7038-wdt.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: BCM63xx and BCM7038 watchdog timer + +allOf: + - $ref: "watchdog.yaml#" + +maintainers: + - Florian Fainelli + - Justin Chen + - Rafał Miłecki + +properties: + compatible: + enum: + - brcm,bcm6345-wdt + - brcm,bcm7038-wdt + + reg: + maxItems: 1 + + clocks: + maxItems: 1 + description: > + The clock running the watchdog. If no clock is found the driver will + default to 27000000 Hz. + +unevaluatedProperties: false + +required: + - reg + +examples: + - | + watchdog@f040a7e8 { + compatible = "brcm,bcm7038-wdt"; + reg = <0xf040a7e8 0x16>; + clocks = <&upg_fixed>; + }; diff --git a/Documentation/devicetree/bindings/watchdog/fsl-imx7ulp-wdt.yaml b/Documentation/devicetree/bindings/watchdog/fsl-imx7ulp-wdt.yaml index 51d6d482bbc2..fb603a20e396 100644 --- a/Documentation/devicetree/bindings/watchdog/fsl-imx7ulp-wdt.yaml +++ b/Documentation/devicetree/bindings/watchdog/fsl-imx7ulp-wdt.yaml @@ -14,8 +14,11 @@ allOf: properties: compatible: - enum: - - fsl,imx7ulp-wdt + oneOf: + - const: fsl,imx7ulp-wdt + - items: + - const: fsl,imx8ulp-wdt + - const: fsl,imx7ulp-wdt reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml b/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml index ba60bdf1fecc..16c6f82a13ca 100644 --- a/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml +++ b/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml @@ -20,7 +20,9 @@ properties: - qcom,apss-wdt-sc7280 - qcom,apss-wdt-sdm845 - qcom,apss-wdt-sdx55 + - qcom,apss-wdt-sm6350 - qcom,apss-wdt-sm8150 + - qcom,apss-wdt-sm8250 - qcom,kpss-timer - qcom,kpss-wdt - qcom,kpss-wdt-apq8064 diff --git a/Documentation/devicetree/bindings/watchdog/realtek,otto-wdt.yaml b/Documentation/devicetree/bindings/watchdog/realtek,otto-wdt.yaml new file mode 100644 index 000000000000..11b220a5e0f6 --- /dev/null +++ b/Documentation/devicetree/bindings/watchdog/realtek,otto-wdt.yaml @@ -0,0 +1,91 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/watchdog/realtek,otto-wdt.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Realtek Otto watchdog timer + +maintainers: + - Sander Vanheule + +description: | + The timer has two timeout phases. Both phases have a maximum duration of 32 + prescaled clock ticks, which is ca. 43s with a bus clock of 200MHz. The + minimum duration of each phase is one tick. Each phase can trigger an + interrupt, although the phase 2 interrupt will occur with the system reset. + - Phase 1: During this phase, the WDT can be pinged to reset the timeout. + - Phase 2: Starts after phase 1 has timed out, and only serves to give the + system some time to clean up, or notify others that it's going to reset. + During this phase, pinging the WDT has no effect, and a reset is + unavoidable, unless the WDT is disabled. + +allOf: + - $ref: watchdog.yaml# + +properties: + compatible: + enum: + - realtek,rtl8380-wdt + - realtek,rtl8390-wdt + - realtek,rtl9300-wdt + + reg: + maxItems: 1 + + clocks: + maxItems: 1 + + interrupts: + items: + - description: interrupt specifier for pretimeout + - description: interrupt specifier for timeout + + interrupt-names: + items: + - const: phase1 + - const: phase2 + + realtek,reset-mode: + $ref: /schemas/types.yaml#/definitions/string + description: | + Specify how the system is reset after a timeout. Defaults to "cpu" if + left unspecified. + oneOf: + - description: Reset the entire chip + const: soc + - description: | + Reset the CPU and IPsec engine, but leave other peripherals untouched + const: cpu + - description: | + Reset the execution pointer, but don't actually reset any hardware + const: software + +required: + - compatible + - reg + - clocks + - interrupts + +unevaluatedProperties: false + +dependencies: + interrupts: [ interrupt-names ] + +examples: + - | + watchdog: watchdog@3150 { + compatible = "realtek,rtl8380-wdt"; + reg = <0x3150 0xc>; + + realtek,reset-mode = "soc"; + + clocks = <&lxbus_clock>; + timeout-sec = <20>; + + interrupt-parent = <&rtlintc>; + interrupt-names = "phase1", "phase2"; + interrupts = <19>, <18>; + }; + +... diff --git a/Documentation/devicetree/bindings/watchdog/renesas,wdt.yaml b/Documentation/devicetree/bindings/watchdog/renesas,wdt.yaml index ab66d3f0c476..91a98ccd4226 100644 --- a/Documentation/devicetree/bindings/watchdog/renesas,wdt.yaml +++ b/Documentation/devicetree/bindings/watchdog/renesas,wdt.yaml @@ -10,9 +10,6 @@ maintainers: - Wolfram Sang - Geert Uytterhoeven -allOf: - - $ref: "watchdog.yaml#" - properties: compatible: oneOf: @@ -22,6 +19,11 @@ properties: - renesas,r7s9210-wdt # RZ/A2 - const: renesas,rza-wdt # RZ/A + - items: + - enum: + - renesas,r9a07g044-wdt # RZ/G2{L,LC} + - const: renesas,rzg2l-wdt # RZ/G2L + - items: - enum: - renesas,r8a7742-wdt # RZ/G1H @@ -56,11 +58,13 @@ properties: reg: maxItems: 1 - interrupts: - maxItems: 1 + interrupts: true - clocks: - maxItems: 1 + interrupt-names: true + + clocks: true + + clock-names: true power-domains: maxItems: 1 @@ -75,17 +79,52 @@ required: - reg - clocks -if: - not: - properties: - compatible: - contains: - enum: - - renesas,rza-wdt -then: - required: - - power-domains - - resets +allOf: + - $ref: "watchdog.yaml#" + + - if: + not: + properties: + compatible: + contains: + enum: + - renesas,rza-wdt + then: + required: + - power-domains + - resets + + - if: + properties: + compatible: + contains: + enum: + - renesas,rzg2l-wdt + then: + properties: + interrupts: + maxItems: 2 + interrupt-names: + items: + - const: wdt + - const: perrout + clocks: + items: + - description: Register access clock + - description: Main clock + clock-names: + items: + - const: pclk + - const: oscclk + required: + - clock-names + - interrupt-names + else: + properties: + interrupts: + maxItems: 1 + clocks: + maxItems: 1 additionalProperties: false diff --git a/Documentation/devicetree/bindings/watchdog/samsung-wdt.yaml b/Documentation/devicetree/bindings/watchdog/samsung-wdt.yaml index 76cb9586ee00..b08373336b16 100644 --- a/Documentation/devicetree/bindings/watchdog/samsung-wdt.yaml +++ b/Documentation/devicetree/bindings/watchdog/samsung-wdt.yaml @@ -22,25 +22,32 @@ properties: - samsung,exynos5250-wdt # for Exynos5250 - samsung,exynos5420-wdt # for Exynos5420 - samsung,exynos7-wdt # for Exynos7 + - samsung,exynos850-wdt # for Exynos850 reg: maxItems: 1 clocks: - maxItems: 1 + minItems: 1 + maxItems: 2 clock-names: - items: - - const: watchdog + minItems: 1 + maxItems: 2 interrupts: maxItems: 1 + samsung,cluster-index: + $ref: /schemas/types.yaml#/definitions/uint32 + description: + Index of CPU cluster on which watchdog is running (in case of Exynos850) + samsung,syscon-phandle: $ref: /schemas/types.yaml#/definitions/phandle description: - Phandle to the PMU system controller node (in case of Exynos5250 - and Exynos5420). + Phandle to the PMU system controller node (in case of Exynos5250, + Exynos5420, Exynos7 and Exynos850). required: - compatible @@ -58,9 +65,40 @@ allOf: enum: - samsung,exynos5250-wdt - samsung,exynos5420-wdt + - samsung,exynos7-wdt + - samsung,exynos850-wdt then: required: - samsung,syscon-phandle + - if: + properties: + compatible: + contains: + enum: + - samsung,exynos850-wdt + then: + properties: + clocks: + items: + - description: Bus clock, used for register interface + - description: Source clock (driving watchdog counter) + clock-names: + items: + - const: watchdog + - const: watchdog_src + samsung,cluster-index: + enum: [0, 1] + required: + - samsung,cluster-index + else: + properties: + clocks: + items: + - description: Bus clock, which is also a source clock + clock-names: + items: + - const: watchdog + samsung,cluster-index: false unevaluatedProperties: false diff --git a/Documentation/driver-api/dmaengine/dmatest.rst b/Documentation/driver-api/dmaengine/dmatest.rst index ee268d445d38..cf9859cd0b43 100644 --- a/Documentation/driver-api/dmaengine/dmatest.rst +++ b/Documentation/driver-api/dmaengine/dmatest.rst @@ -6,6 +6,16 @@ Andy Shevchenko This small document introduces how to test DMA drivers using dmatest module. +The dmatest module tests DMA memcpy, memset, XOR and RAID6 P+Q operations using +various lengths and various offsets into the source and destination buffers. It +will initialize both buffers with a repeatable pattern and verify that the DMA +engine copies the requested region and nothing more. It will also verify that +the bytes aren't swapped around, and that the source buffer isn't modified. + +The dmatest module can be configured to test a specific channel. It can also +test multiple channels at the same time, and it can start multiple threads +competing for the same channel. + .. note:: The test suite works only on the channels that have at least one capability of the following: DMA_MEMCPY (memory-to-memory), DMA_MEMSET @@ -143,13 +153,14 @@ Part 5 - Handling channel allocation Allocating Channels ------------------- -Channels are required to be configured prior to starting the test run. -Attempting to run the test without configuring the channels will fail. +Channels do not need to be configured prior to starting a test run. Attempting +to run the test without configuring the channels will result in testing any +channels that are available. Example:: % echo 1 > /sys/module/dmatest/parameters/run - dmatest: Could not start test, no channels configured + dmatest: No channels configured, continue with any Channels are registered using the "channel" parameter. Channels can be requested by their name, once requested, the channel is registered and a pending thread is added to the test list. diff --git a/Documentation/driver-api/dmaengine/provider.rst b/Documentation/driver-api/dmaengine/provider.rst index ddb0a81a796c..0072c9c7efd3 100644 --- a/Documentation/driver-api/dmaengine/provider.rst +++ b/Documentation/driver-api/dmaengine/provider.rst @@ -162,6 +162,29 @@ Currently, the types available are: - The device is able to do memory to memory copies +- - DMA_MEMCPY_SG + + - The device supports memory to memory scatter-gather transfers. + + - Even though a plain memcpy can look like a particular case of a + scatter-gather transfer, with a single chunk to copy, it's a distinct + transaction type in the mem2mem transfer case. This is because some very + simple devices might be able to do contiguous single-chunk memory copies, + but have no support for more complex SG transfers. + + - No matter what the overall size of the combined chunks for source and + destination is, only as many bytes as the smallest of the two will be + transmitted. That means the number and size of the scatter-gather buffers in + both lists need not be the same, and that the operation functionally is + equivalent to a ``strncpy`` where the ``count`` argument equals the smallest + total size of the two scatter-gather list buffers. + + - It's usually used for copying pixel data between host memory and + memory-mapped GPU device memory, such as found on modern PCI video graphics + cards. The most immediate example is the OpenGL API function + ``glReadPielx()``, which might require a verbatim copy of a huge framebuffer + from local device memory onto host memory. + - DMA_XOR - The device is able to perform XOR operations on memory areas diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index cfe6cccf0f44..687efcf245c1 100644 --- a/Documentation/userspace-api/ioctl/ioctl-number.rst +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst @@ -367,6 +367,7 @@ Code Seq# Include File Comments 0xE5 00-3F linux/fuse.h 0xEC 00-01 drivers/platform/chrome/cros_ec_dev.h ChromeOS EC driver +0xEE 00-09 uapi/linux/pfrut.h Platform Firmware Runtime Update and Telemetry 0xF3 00-3F drivers/usb/misc/sisusbvga/sisusb.h sisfb (in development) 0xF6 all LTTng Linux Trace Toolkit Next Generation diff --git a/MAINTAINERS b/MAINTAINERS index 3c44be0ab7b7..8437af79eec3 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4745,7 +4745,6 @@ F: drivers/media/pci/cobalt/ COCCINELLE/Semantic Patches (SmPL) M: Julia Lawall -M: Gilles Muller M: Nicolas Palix L: cocci@inria.fr (moderated for non-subscribers) S: Supported @@ -7583,11 +7582,12 @@ W: http://floatingpoint.sourceforge.net/emulator/index.html F: arch/x86/math-emu/ FRAMEBUFFER LAYER -L: dri-devel@lists.freedesktop.org +M: Helge Deller L: linux-fbdev@vger.kernel.org -S: Orphan +L: dri-devel@lists.freedesktop.org +S: Maintained Q: http://patchwork.kernel.org/project/linux-fbdev/list/ -T: git git://anongit.freedesktop.org/drm/drm-misc +T: git git://git.kernel.org/pub/scm/linux/kernel/git/deller/linux-fbdev.git F: Documentation/fb/ F: drivers/video/ F: include/linux/fb.h @@ -16351,6 +16351,13 @@ S: Maintained F: include/sound/rt*.h F: sound/soc/codecs/rt* +REALTEK OTTO WATCHDOG +M: Sander Vanheule +L: linux-watchdog@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/watchdog/realtek,otto-wdt.yaml +F: drivers/watchdog/realtek_otto_wdt.c + REALTEK RTL83xx SMI DSA ROUTER CHIPS M: Linus Walleij S: Maintained @@ -16400,7 +16407,6 @@ S: Supported F: fs/reiserfs/ REMOTE PROCESSOR (REMOTEPROC) SUBSYSTEM -M: Ohad Ben-Cohen M: Bjorn Andersson M: Mathieu Poirier L: linux-remoteproc@vger.kernel.org @@ -16414,7 +16420,6 @@ F: include/linux/remoteproc.h F: include/linux/remoteproc/ REMOTE PROCESSOR MESSAGING (RPMSG) SUBSYSTEM -M: Ohad Ben-Cohen M: Bjorn Andersson M: Mathieu Poirier L: linux-remoteproc@vger.kernel.org @@ -20379,6 +20384,7 @@ M: "Michael S. Tsirkin" M: Jason Wang L: virtualization@lists.linux-foundation.org S: Maintained +F: Documentation/ABI/testing/sysfs-bus-vdpa F: Documentation/devicetree/bindings/virtio/ F: drivers/block/virtio_blk.c F: drivers/crypto/virtio/ diff --git a/arch/arc/include/asm/irqflags-compact.h b/arch/arc/include/asm/irqflags-compact.h index 863d63ad18d6..0d63e568d64c 100644 --- a/arch/arc/include/asm/irqflags-compact.h +++ b/arch/arc/include/asm/irqflags-compact.h @@ -50,8 +50,12 @@ * are redone after IRQs are re-enabled (and gcc doesn't reuse stale register) * * Noted at the time of Abilis Timer List corruption - * Orig Bug + Rejected solution : https://lkml.org/lkml/2013/3/29/67 - * Reasoning : https://lkml.org/lkml/2013/4/8/15 + * + * Orig Bug + Rejected solution: + * https://lore.kernel.org/lkml/1364553218-31255-1-git-send-email-vgupta@synopsys.com + * + * Reasoning: + * https://lore.kernel.org/lkml/CA+55aFyFWjpSVQM6M266tKrG_ZXJzZ-nYejpmXYQXbrr42mGPQ@mail.gmail.com * ******************************************************************/ diff --git a/arch/arc/include/asm/perf_event.h b/arch/arc/include/asm/perf_event.h index e1971d34ef30..4c919c0f4b30 100644 --- a/arch/arc/include/asm/perf_event.h +++ b/arch/arc/include/asm/perf_event.h @@ -63,166 +63,4 @@ struct arc_reg_cc_build { #define PERF_COUNT_ARC_HW_MAX (PERF_COUNT_HW_MAX + 8) -/* - * Some ARC pct quirks: - * - * PERF_COUNT_HW_STALLED_CYCLES_BACKEND - * PERF_COUNT_HW_STALLED_CYCLES_FRONTEND - * The ARC 700 can either measure stalls per pipeline stage, or all stalls - * combined; for now we assign all stalls to STALLED_CYCLES_BACKEND - * and all pipeline flushes (e.g. caused by mispredicts, etc.) to - * STALLED_CYCLES_FRONTEND. - * - * We could start multiple performance counters and combine everything - * afterwards, but that makes it complicated. - * - * Note that I$ cache misses aren't counted by either of the two! - */ - -/* - * ARC PCT has hardware conditions with fixed "names" but variable "indexes" - * (based on a specific RTL build) - * Below is the static map between perf generic/arc specific event_id and - * h/w condition names. - * At the time of probe, we loop thru each index and find it's name to - * complete the mapping of perf event_id to h/w index as latter is needed - * to program the counter really - */ -static const char * const arc_pmu_ev_hw_map[] = { - /* count cycles */ - [PERF_COUNT_HW_CPU_CYCLES] = "crun", - [PERF_COUNT_HW_REF_CPU_CYCLES] = "crun", - [PERF_COUNT_HW_BUS_CYCLES] = "crun", - - [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = "bflush", - [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = "bstall", - - /* counts condition */ - [PERF_COUNT_HW_INSTRUCTIONS] = "iall", - /* All jump instructions that are taken */ - [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "ijmptak", -#ifdef CONFIG_ISA_ARCV2 - [PERF_COUNT_HW_BRANCH_MISSES] = "bpmp", -#else - [PERF_COUNT_ARC_BPOK] = "bpok", /* NP-NT, PT-T, PNT-NT */ - [PERF_COUNT_HW_BRANCH_MISSES] = "bpfail", /* NP-T, PT-NT, PNT-T */ -#endif - [PERF_COUNT_ARC_LDC] = "imemrdc", /* Instr: mem read cached */ - [PERF_COUNT_ARC_STC] = "imemwrc", /* Instr: mem write cached */ - - [PERF_COUNT_ARC_DCLM] = "dclm", /* D-cache Load Miss */ - [PERF_COUNT_ARC_DCSM] = "dcsm", /* D-cache Store Miss */ - [PERF_COUNT_ARC_ICM] = "icm", /* I-cache Miss */ - [PERF_COUNT_ARC_EDTLB] = "edtlb", /* D-TLB Miss */ - [PERF_COUNT_ARC_EITLB] = "eitlb", /* I-TLB Miss */ - - [PERF_COUNT_HW_CACHE_REFERENCES] = "imemrdc", /* Instr: mem read cached */ - [PERF_COUNT_HW_CACHE_MISSES] = "dclm", /* D-cache Load Miss */ -}; - -#define C(_x) PERF_COUNT_HW_CACHE_##_x -#define CACHE_OP_UNSUPPORTED 0xffff - -static const unsigned int arc_pmu_cache_map[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { - [C(L1D)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = PERF_COUNT_ARC_LDC, - [C(RESULT_MISS)] = PERF_COUNT_ARC_DCLM, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = PERF_COUNT_ARC_STC, - [C(RESULT_MISS)] = PERF_COUNT_ARC_DCSM, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(L1I)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = PERF_COUNT_HW_INSTRUCTIONS, - [C(RESULT_MISS)] = PERF_COUNT_ARC_ICM, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(LL)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(DTLB)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = PERF_COUNT_ARC_LDC, - [C(RESULT_MISS)] = PERF_COUNT_ARC_EDTLB, - }, - /* DTLB LD/ST Miss not segregated by h/w*/ - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(ITLB)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = PERF_COUNT_ARC_EITLB, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(BPU)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = PERF_COUNT_HW_BRANCH_INSTRUCTIONS, - [C(RESULT_MISS)] = PERF_COUNT_HW_BRANCH_MISSES, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(NODE)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, -}; - #endif /* __ASM_PERF_EVENT_H */ diff --git a/arch/arc/include/asm/thread_info.h b/arch/arc/include/asm/thread_info.h index c0942c24d401..d36863e34bfc 100644 --- a/arch/arc/include/asm/thread_info.h +++ b/arch/arc/include/asm/thread_info.h @@ -99,8 +99,8 @@ static inline __attribute_const__ struct thread_info *current_thread_info(void) /* * _TIF_ALLWORK_MASK includes SYSCALL_TRACE, but we don't need it. - * SYSCALL_TRACE is anyway seperately/unconditionally tested right after a - * syscall, so all that reamins to be tested is _TIF_WORK_MASK + * SYSCALL_TRACE is anyway separately/unconditionally tested right after a + * syscall, so all that remains to be tested is _TIF_WORK_MASK */ #endif /* _ASM_THREAD_INFO_H */ diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c index 145722f80c9b..adff957962da 100644 --- a/arch/arc/kernel/perf_event.c +++ b/arch/arc/kernel/perf_event.c @@ -17,6 +17,168 @@ /* HW holds 8 symbols + one for null terminator */ #define ARCPMU_EVENT_NAME_LEN 9 +/* + * Some ARC pct quirks: + * + * PERF_COUNT_HW_STALLED_CYCLES_BACKEND + * PERF_COUNT_HW_STALLED_CYCLES_FRONTEND + * The ARC 700 can either measure stalls per pipeline stage, or all stalls + * combined; for now we assign all stalls to STALLED_CYCLES_BACKEND + * and all pipeline flushes (e.g. caused by mispredicts, etc.) to + * STALLED_CYCLES_FRONTEND. + * + * We could start multiple performance counters and combine everything + * afterwards, but that makes it complicated. + * + * Note that I$ cache misses aren't counted by either of the two! + */ + +/* + * ARC PCT has hardware conditions with fixed "names" but variable "indexes" + * (based on a specific RTL build) + * Below is the static map between perf generic/arc specific event_id and + * h/w condition names. + * At the time of probe, we loop thru each index and find it's name to + * complete the mapping of perf event_id to h/w index as latter is needed + * to program the counter really + */ +static const char * const arc_pmu_ev_hw_map[] = { + /* count cycles */ + [PERF_COUNT_HW_CPU_CYCLES] = "crun", + [PERF_COUNT_HW_REF_CPU_CYCLES] = "crun", + [PERF_COUNT_HW_BUS_CYCLES] = "crun", + + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = "bflush", + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = "bstall", + + /* counts condition */ + [PERF_COUNT_HW_INSTRUCTIONS] = "iall", + /* All jump instructions that are taken */ + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "ijmptak", +#ifdef CONFIG_ISA_ARCV2 + [PERF_COUNT_HW_BRANCH_MISSES] = "bpmp", +#else + [PERF_COUNT_ARC_BPOK] = "bpok", /* NP-NT, PT-T, PNT-NT */ + [PERF_COUNT_HW_BRANCH_MISSES] = "bpfail", /* NP-T, PT-NT, PNT-T */ +#endif + [PERF_COUNT_ARC_LDC] = "imemrdc", /* Instr: mem read cached */ + [PERF_COUNT_ARC_STC] = "imemwrc", /* Instr: mem write cached */ + + [PERF_COUNT_ARC_DCLM] = "dclm", /* D-cache Load Miss */ + [PERF_COUNT_ARC_DCSM] = "dcsm", /* D-cache Store Miss */ + [PERF_COUNT_ARC_ICM] = "icm", /* I-cache Miss */ + [PERF_COUNT_ARC_EDTLB] = "edtlb", /* D-TLB Miss */ + [PERF_COUNT_ARC_EITLB] = "eitlb", /* I-TLB Miss */ + + [PERF_COUNT_HW_CACHE_REFERENCES] = "imemrdc", /* Instr: mem read cached */ + [PERF_COUNT_HW_CACHE_MISSES] = "dclm", /* D-cache Load Miss */ +}; + +#define C(_x) PERF_COUNT_HW_CACHE_##_x +#define CACHE_OP_UNSUPPORTED 0xffff + +static const unsigned int arc_pmu_cache_map[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { + [C(L1D)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = PERF_COUNT_ARC_LDC, + [C(RESULT_MISS)] = PERF_COUNT_ARC_DCLM, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = PERF_COUNT_ARC_STC, + [C(RESULT_MISS)] = PERF_COUNT_ARC_DCSM, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(L1I)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = PERF_COUNT_HW_INSTRUCTIONS, + [C(RESULT_MISS)] = PERF_COUNT_ARC_ICM, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(LL)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(DTLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = PERF_COUNT_ARC_LDC, + [C(RESULT_MISS)] = PERF_COUNT_ARC_EDTLB, + }, + /* DTLB LD/ST Miss not segregated by h/w*/ + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(ITLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = PERF_COUNT_ARC_EITLB, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(BPU)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = PERF_COUNT_HW_BRANCH_INSTRUCTIONS, + [C(RESULT_MISS)] = PERF_COUNT_HW_BRANCH_MISSES, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(NODE)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, +}; + enum arc_pmu_attr_groups { ARCPMU_ATTR_GR_EVENTS, ARCPMU_ATTR_GR_FORMATS, @@ -328,7 +490,7 @@ static void arc_pmu_stop(struct perf_event *event, int flags) } if (!(event->hw.state & PERF_HES_STOPPED)) { - /* stop ARC pmu here */ + /* stop hw counter here */ write_aux_reg(ARC_REG_PCT_INDEX, idx); /* condition code #0 is always "never" */ @@ -361,7 +523,7 @@ static int arc_pmu_add(struct perf_event *event, int flags) { struct arc_pmu_cpu *pmu_cpu = this_cpu_ptr(&arc_pmu_cpu); struct hw_perf_event *hwc = &event->hw; - int idx = hwc->idx; + int idx; idx = ffz(pmu_cpu->used_mask[0]); if (idx == arc_pmu->n_counters) diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c index 9e28058cdba8..200270a94558 100644 --- a/arch/arc/kernel/unwind.c +++ b/arch/arc/kernel/unwind.c @@ -245,14 +245,9 @@ static void swap_eh_frame_hdr_table_entries(void *p1, void *p2, int size) { struct eh_frame_hdr_table_entry *e1 = p1; struct eh_frame_hdr_table_entry *e2 = p2; - unsigned long v; - v = e1->start; - e1->start = e2->start; - e2->start = v; - v = e1->fde; - e1->fde = e2->fde; - e2->fde = v; + swap(e1->start, e2->start); + swap(e1->fde, e2->fde); } static void init_unwind_hdr(struct unwind_table *table, diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c index 517988e60cfc..2a7fbbb83b70 100644 --- a/arch/arc/mm/dma.c +++ b/arch/arc/mm/dma.c @@ -32,7 +32,7 @@ void arch_dma_prep_coherent(struct page *page, size_t size) /* * Cache operations depending on function and direction argument, inspired by - * https://lkml.org/lkml/2018/5/18/979 + * https://lore.kernel.org/lkml/20180518175004.GF17671@n2100.armlinux.org.uk * "dma_sync_*_for_cpu and direction=TO_DEVICE (was Re: [PATCH 02/20] * dma-mapping: provide a generic dma-noncoherent implementation)" * diff --git a/arch/arc/plat-axs10x/axs10x.c b/arch/arc/plat-axs10x/axs10x.c index 63ea5a606ecd..b821df7b0089 100644 --- a/arch/arc/plat-axs10x/axs10x.c +++ b/arch/arc/plat-axs10x/axs10x.c @@ -50,7 +50,7 @@ static void __init axs10x_enable_gpio_intc_wire(void) * Current implementation of "irq-dw-apb-ictl" driver doesn't work well * with stacked INTCs. In particular problem happens if its master INTC * not yet instantiated. See discussion here - - * https://lkml.org/lkml/2015/3/4/755 + * https://lore.kernel.org/lkml/54F6FE2C.7020309@synopsys.com * * So setup the first gpio block as a passive pass thru and hide it from * DT hardware topology - connect MB intc directly to cpu intc diff --git a/arch/arc/plat-hsdk/platform.c b/arch/arc/plat-hsdk/platform.c index b3ea1fa11f87..c4a875b22352 100644 --- a/arch/arc/plat-hsdk/platform.c +++ b/arch/arc/plat-hsdk/platform.c @@ -52,7 +52,7 @@ static void __init hsdk_enable_gpio_intc_wire(void) * Current implementation of "irq-dw-apb-ictl" driver doesn't work well * with stacked INTCs. In particular problem happens if its master INTC * not yet instantiated. See discussion here - - * https://lkml.org/lkml/2015/3/4/755 + * https://lore.kernel.org/lkml/54F6FE2C.7020309@synopsys.com * * So setup the first gpio block as a passive pass thru and hide it from * DT hardware topology - connect intc directly to cpu intc diff --git a/arch/mips/bcm63xx/dev-wdt.c b/arch/mips/bcm63xx/dev-wdt.c index 2a2346a99bcb..42130914a3c2 100644 --- a/arch/mips/bcm63xx/dev-wdt.c +++ b/arch/mips/bcm63xx/dev-wdt.c @@ -9,6 +9,7 @@ #include #include #include +#include #include static struct resource wdt_resources[] = { @@ -19,11 +20,18 @@ static struct resource wdt_resources[] = { }, }; +static struct bcm7038_wdt_platform_data bcm63xx_wdt_pdata = { + .clk_name = "periph", +}; + static struct platform_device bcm63xx_wdt_device = { .name = "bcm63xx-wdt", .id = -1, .num_resources = ARRAY_SIZE(wdt_resources), .resource = wdt_resources, + .dev = { + .platform_data = &bcm63xx_wdt_pdata, + }, }; int __init bcm63xx_wdt_register(void) diff --git a/arch/um/drivers/virt-pci.c b/arch/um/drivers/virt-pci.c index 0ab58016db22..5c092a9153ea 100644 --- a/arch/um/drivers/virt-pci.c +++ b/arch/um/drivers/virt-pci.c @@ -616,7 +616,7 @@ static void um_pci_virtio_remove(struct virtio_device *vdev) int i; /* Stop all virtqueues */ - vdev->config->reset(vdev); + virtio_reset_device(vdev); vdev->config->del_vqs(vdev); device_set_wakeup_enable(&vdev->dev, false); diff --git a/arch/x86/kernel/resource.c b/arch/x86/kernel/resource.c index 9b9fb7882c20..9ae64f9af956 100644 --- a/arch/x86/kernel/resource.c +++ b/arch/x86/kernel/resource.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include #include #include @@ -23,11 +24,31 @@ static void resource_clip(struct resource *res, resource_size_t start, res->start = end + 1; } +/* + * Some BIOS-es contain a bug where they add addresses which map to + * system RAM in the PCI host bridge window returned by the ACPI _CRS + * method, see commit 4dc2287c1805 ("x86: avoid E820 regions when + * allocating address space"). To avoid this Linux by default excludes + * E820 reservations when allocating addresses since 2010. + * In 2019 some systems have shown-up with E820 reservations which cover + * the entire _CRS returned PCI host bridge window, causing all attempts + * to assign memory to PCI BARs to fail if Linux uses E820 reservations. + * + * Ideally Linux would fully stop using E820 reservations, but then + * the old systems this was added for will regress. + * Instead keep the old behavior for old systems, while ignoring the + * E820 reservations for any systems from now on. + */ static void remove_e820_regions(struct resource *avail) { - int i; + int i, year = dmi_get_bios_year(); struct e820_entry *entry; + if (year >= 2018) + return; + + pr_info_once("PCI: Removing E820 reservations from host bridge windows\n"); + for (i = 0; i < e820_table->nr_entries; i++) { entry = &e820_table->entries[i]; diff --git a/crypto/Kconfig b/crypto/Kconfig index 94bfa32cc6a1..442765219c37 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -1928,5 +1928,3 @@ source "crypto/asymmetric_keys/Kconfig" source "certs/Kconfig" endif # if CRYPTO - -source "lib/crypto/Kconfig" diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index 705331e3d87a..ba45541b1f1f 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -520,6 +520,28 @@ config ACPI_CONFIGFS userspace. The configurable ACPI groups will be visible under /config/acpi, assuming configfs is mounted under /config. +config ACPI_PFRUT + tristate "ACPI Platform Firmware Runtime Update and Telemetry" + depends on 64BIT + help + This mechanism allows certain pieces of the platform firmware + to be updated on the fly while the system is running (runtime) + without the need to restart it, which is key in the cases when + the system needs to be available 100% of the time and it cannot + afford the downtime related to restarting it, or when the work + carried out by the system is particularly important, so it cannot + be interrupted, and it is not practical to wait until it is complete. + + The existing firmware code can be modified (driver update) or + extended by adding new code to the firmware (code injection). + + Besides, the telemetry driver allows user space to fetch telemetry + data from the firmware with the help of the Platform Firmware Runtime + Telemetry interface. + + To compile the drivers as modules, choose M here: + the modules will be called pfr_update and pfr_telemetry. + if ARM64 source "drivers/acpi/arm64/Kconfig" diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile index 08c2d985c57c..f47032769f69 100644 --- a/drivers/acpi/Makefile +++ b/drivers/acpi/Makefile @@ -103,6 +103,7 @@ obj-$(CONFIG_ACPI_CPPC_LIB) += cppc_acpi.o obj-$(CONFIG_ACPI_SPCR_TABLE) += spcr.o obj-$(CONFIG_ACPI_DEBUGGER_USER) += acpi_dbg.o obj-$(CONFIG_ACPI_PPTT) += pptt.o +obj-$(CONFIG_ACPI_PFRUT) += pfr_update.o pfr_telemetry.o # processor has its own "processor." module_param namespace processor-y := processor_driver.o diff --git a/drivers/acpi/acpi_apd.c b/drivers/acpi/acpi_apd.c index 2b958b426b03..e7934ba79b02 100644 --- a/drivers/acpi/acpi_apd.c +++ b/drivers/acpi/acpi_apd.c @@ -102,6 +102,8 @@ static int fch_misc_setup(struct apd_private_data *pdata) resource_size(rentry->res)); break; } + if (!clk_data->base) + return -ENOMEM; acpi_dev_free_resource_list(&resource_list); diff --git a/drivers/acpi/acpi_pcc.c b/drivers/acpi/acpi_pcc.c index 41e3ebd204ff..a12b55d81209 100644 --- a/drivers/acpi/acpi_pcc.c +++ b/drivers/acpi/acpi_pcc.c @@ -31,7 +31,7 @@ struct pcc_data { struct acpi_pcc_info ctx; }; -struct acpi_pcc_info pcc_ctx; +static struct acpi_pcc_info pcc_ctx; static void pcc_rx_callback(struct mbox_client *cl, void *m) { diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index 1db3a2f81763..457e11d851b8 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -14,7 +14,7 @@ int early_acpi_osi_init(void); int acpi_osi_init(void); acpi_status acpi_os_initialize1(void); -int acpi_scan_init(void); +void acpi_scan_init(void); #ifdef CONFIG_PCI void acpi_pci_root_init(void); void acpi_pci_link_init(void); diff --git a/drivers/acpi/pfr_telemetry.c b/drivers/acpi/pfr_telemetry.c new file mode 100644 index 000000000000..9abf350bd7a5 --- /dev/null +++ b/drivers/acpi/pfr_telemetry.c @@ -0,0 +1,435 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ACPI Platform Firmware Runtime Telemetry driver + * + * Copyright (C) 2021 Intel Corporation + * Author: Chen Yu + * + * This driver allows user space to fetch telemetry data from the + * firmware with the help of the Platform Firmware Runtime Telemetry + * interface. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#define PFRT_LOG_EXEC_IDX 0 +#define PFRT_LOG_HISTORY_IDX 1 + +#define PFRT_LOG_ERR 0 +#define PFRT_LOG_WARN 1 +#define PFRT_LOG_INFO 2 +#define PFRT_LOG_VERB 4 + +#define PFRT_FUNC_SET_LEV 1 +#define PFRT_FUNC_GET_LEV 2 +#define PFRT_FUNC_GET_DATA 3 + +#define PFRT_REVID_1 1 +#define PFRT_REVID_2 2 +#define PFRT_DEFAULT_REV_ID PFRT_REVID_1 + +enum log_index { + LOG_STATUS_IDX = 0, + LOG_EXT_STATUS_IDX = 1, + LOG_MAX_SZ_IDX = 2, + LOG_CHUNK1_LO_IDX = 3, + LOG_CHUNK1_HI_IDX = 4, + LOG_CHUNK1_SZ_IDX = 5, + LOG_CHUNK2_LO_IDX = 6, + LOG_CHUNK2_HI_IDX = 7, + LOG_CHUNK2_SZ_IDX = 8, + LOG_ROLLOVER_CNT_IDX = 9, + LOG_RESET_CNT_IDX = 10, + LOG_NR_IDX +}; + +struct pfrt_log_device { + int index; + struct pfrt_log_info info; + struct device *parent_dev; + struct miscdevice miscdev; +}; + +/* pfrt_guid is the parameter for _DSM method */ +static const guid_t pfrt_log_guid = + GUID_INIT(0x75191659, 0x8178, 0x4D9D, 0xB8, 0x8F, 0xAC, 0x5E, + 0x5E, 0x93, 0xE8, 0xBF); + +static DEFINE_IDA(pfrt_log_ida); + +static inline struct pfrt_log_device *to_pfrt_log_dev(struct file *file) +{ + return container_of(file->private_data, struct pfrt_log_device, miscdev); +} + +static int get_pfrt_log_data_info(struct pfrt_log_data_info *data_info, + struct pfrt_log_device *pfrt_log_dev) +{ + acpi_handle handle = ACPI_HANDLE(pfrt_log_dev->parent_dev); + union acpi_object *out_obj, in_obj, in_buf; + int ret = -EBUSY; + + memset(data_info, 0, sizeof(*data_info)); + memset(&in_obj, 0, sizeof(in_obj)); + memset(&in_buf, 0, sizeof(in_buf)); + in_obj.type = ACPI_TYPE_PACKAGE; + in_obj.package.count = 1; + in_obj.package.elements = &in_buf; + in_buf.type = ACPI_TYPE_INTEGER; + in_buf.integer.value = pfrt_log_dev->info.log_type; + + out_obj = acpi_evaluate_dsm_typed(handle, &pfrt_log_guid, + pfrt_log_dev->info.log_revid, PFRT_FUNC_GET_DATA, + &in_obj, ACPI_TYPE_PACKAGE); + if (!out_obj) + return -EINVAL; + + if (out_obj->package.count < LOG_NR_IDX || + out_obj->package.elements[LOG_STATUS_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[LOG_EXT_STATUS_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[LOG_MAX_SZ_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[LOG_CHUNK1_LO_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[LOG_CHUNK1_HI_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[LOG_CHUNK1_SZ_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[LOG_CHUNK2_LO_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[LOG_CHUNK2_HI_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[LOG_CHUNK2_SZ_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[LOG_ROLLOVER_CNT_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[LOG_RESET_CNT_IDX].type != ACPI_TYPE_INTEGER) + goto free_acpi_buffer; + + data_info->status = out_obj->package.elements[LOG_STATUS_IDX].integer.value; + data_info->ext_status = + out_obj->package.elements[LOG_EXT_STATUS_IDX].integer.value; + if (data_info->status != DSM_SUCCEED) { + dev_dbg(pfrt_log_dev->parent_dev, "Error Status:%d\n", data_info->status); + dev_dbg(pfrt_log_dev->parent_dev, "Error Extend Status:%d\n", + data_info->ext_status); + goto free_acpi_buffer; + } + + data_info->max_data_size = + out_obj->package.elements[LOG_MAX_SZ_IDX].integer.value; + data_info->chunk1_addr_lo = + out_obj->package.elements[LOG_CHUNK1_LO_IDX].integer.value; + data_info->chunk1_addr_hi = + out_obj->package.elements[LOG_CHUNK1_HI_IDX].integer.value; + data_info->chunk1_size = + out_obj->package.elements[LOG_CHUNK1_SZ_IDX].integer.value; + data_info->chunk2_addr_lo = + out_obj->package.elements[LOG_CHUNK2_LO_IDX].integer.value; + data_info->chunk2_addr_hi = + out_obj->package.elements[LOG_CHUNK2_HI_IDX].integer.value; + data_info->chunk2_size = + out_obj->package.elements[LOG_CHUNK2_SZ_IDX].integer.value; + data_info->rollover_cnt = + out_obj->package.elements[LOG_ROLLOVER_CNT_IDX].integer.value; + data_info->reset_cnt = + out_obj->package.elements[LOG_RESET_CNT_IDX].integer.value; + + ret = 0; + +free_acpi_buffer: + kfree(out_obj); + + return ret; +} + +static int set_pfrt_log_level(int level, struct pfrt_log_device *pfrt_log_dev) +{ + acpi_handle handle = ACPI_HANDLE(pfrt_log_dev->parent_dev); + union acpi_object *out_obj, *obj, in_obj, in_buf; + enum pfru_dsm_status status, ext_status; + int ret = 0; + + memset(&in_obj, 0, sizeof(in_obj)); + memset(&in_buf, 0, sizeof(in_buf)); + in_obj.type = ACPI_TYPE_PACKAGE; + in_obj.package.count = 1; + in_obj.package.elements = &in_buf; + in_buf.type = ACPI_TYPE_INTEGER; + in_buf.integer.value = level; + + out_obj = acpi_evaluate_dsm_typed(handle, &pfrt_log_guid, + pfrt_log_dev->info.log_revid, PFRT_FUNC_SET_LEV, + &in_obj, ACPI_TYPE_PACKAGE); + if (!out_obj) + return -EINVAL; + + obj = &out_obj->package.elements[0]; + status = obj->integer.value; + if (status != DSM_SUCCEED) { + obj = &out_obj->package.elements[1]; + ext_status = obj->integer.value; + dev_dbg(pfrt_log_dev->parent_dev, "Error Status:%d\n", status); + dev_dbg(pfrt_log_dev->parent_dev, "Error Extend Status:%d\n", ext_status); + ret = -EBUSY; + } + + kfree(out_obj); + + return ret; +} + +static int get_pfrt_log_level(struct pfrt_log_device *pfrt_log_dev) +{ + acpi_handle handle = ACPI_HANDLE(pfrt_log_dev->parent_dev); + union acpi_object *out_obj, *obj; + enum pfru_dsm_status status, ext_status; + int ret = -EBUSY; + + out_obj = acpi_evaluate_dsm_typed(handle, &pfrt_log_guid, + pfrt_log_dev->info.log_revid, PFRT_FUNC_GET_LEV, + NULL, ACPI_TYPE_PACKAGE); + if (!out_obj) + return -EINVAL; + + obj = &out_obj->package.elements[0]; + if (obj->type != ACPI_TYPE_INTEGER) + goto free_acpi_buffer; + + status = obj->integer.value; + if (status != DSM_SUCCEED) { + obj = &out_obj->package.elements[1]; + ext_status = obj->integer.value; + dev_dbg(pfrt_log_dev->parent_dev, "Error Status:%d\n", status); + dev_dbg(pfrt_log_dev->parent_dev, "Error Extend Status:%d\n", ext_status); + goto free_acpi_buffer; + } + + obj = &out_obj->package.elements[2]; + if (obj->type != ACPI_TYPE_INTEGER) + goto free_acpi_buffer; + + ret = obj->integer.value; + +free_acpi_buffer: + kfree(out_obj); + + return ret; +} + +static int valid_log_level(u32 level) +{ + return level == PFRT_LOG_ERR || level == PFRT_LOG_WARN || + level == PFRT_LOG_INFO || level == PFRT_LOG_VERB; +} + +static int valid_log_type(u32 type) +{ + return type == PFRT_LOG_EXEC_IDX || type == PFRT_LOG_HISTORY_IDX; +} + +static inline int valid_log_revid(u32 id) +{ + return id == PFRT_REVID_1 || id == PFRT_REVID_2; +} + +static long pfrt_log_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct pfrt_log_device *pfrt_log_dev = to_pfrt_log_dev(file); + struct pfrt_log_data_info data_info; + struct pfrt_log_info info; + void __user *p; + int ret = 0; + + p = (void __user *)arg; + + switch (cmd) { + case PFRT_LOG_IOC_SET_INFO: + if (copy_from_user(&info, p, sizeof(info))) + return -EFAULT; + + if (valid_log_revid(info.log_revid)) + pfrt_log_dev->info.log_revid = info.log_revid; + + if (valid_log_level(info.log_level)) { + ret = set_pfrt_log_level(info.log_level, pfrt_log_dev); + if (ret < 0) + return ret; + + pfrt_log_dev->info.log_level = info.log_level; + } + + if (valid_log_type(info.log_type)) + pfrt_log_dev->info.log_type = info.log_type; + + return 0; + + case PFRT_LOG_IOC_GET_INFO: + info.log_level = get_pfrt_log_level(pfrt_log_dev); + if (ret < 0) + return ret; + + info.log_type = pfrt_log_dev->info.log_type; + info.log_revid = pfrt_log_dev->info.log_revid; + if (copy_to_user(p, &info, sizeof(info))) + return -EFAULT; + + return 0; + + case PFRT_LOG_IOC_GET_DATA_INFO: + ret = get_pfrt_log_data_info(&data_info, pfrt_log_dev); + if (ret) + return ret; + + if (copy_to_user(p, &data_info, sizeof(struct pfrt_log_data_info))) + return -EFAULT; + + return 0; + + default: + return -ENOTTY; + } +} + +static int +pfrt_log_mmap(struct file *file, struct vm_area_struct *vma) +{ + struct pfrt_log_device *pfrt_log_dev; + struct pfrt_log_data_info info; + unsigned long psize, vsize; + phys_addr_t base_addr; + int ret; + + if (vma->vm_flags & VM_WRITE) + return -EROFS; + + /* changing from read to write with mprotect is not allowed */ + vma->vm_flags &= ~VM_MAYWRITE; + + pfrt_log_dev = to_pfrt_log_dev(file); + + ret = get_pfrt_log_data_info(&info, pfrt_log_dev); + if (ret) + return ret; + + base_addr = (phys_addr_t)((info.chunk2_addr_hi << 32) | info.chunk2_addr_lo); + /* pfrt update has not been launched yet */ + if (!base_addr) + return -ENODEV; + + psize = info.max_data_size; + /* base address and total buffer size must be page aligned */ + if (!PAGE_ALIGNED(base_addr) || !PAGE_ALIGNED(psize)) + return -ENODEV; + + vsize = vma->vm_end - vma->vm_start; + if (vsize > psize) + return -EINVAL; + + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); + if (io_remap_pfn_range(vma, vma->vm_start, PFN_DOWN(base_addr), + vsize, vma->vm_page_prot)) + return -EAGAIN; + + return 0; +} + +static const struct file_operations acpi_pfrt_log_fops = { + .owner = THIS_MODULE, + .mmap = pfrt_log_mmap, + .unlocked_ioctl = pfrt_log_ioctl, + .llseek = noop_llseek, +}; + +static int acpi_pfrt_log_remove(struct platform_device *pdev) +{ + struct pfrt_log_device *pfrt_log_dev = platform_get_drvdata(pdev); + + misc_deregister(&pfrt_log_dev->miscdev); + + return 0; +} + +static void pfrt_log_put_idx(void *data) +{ + struct pfrt_log_device *pfrt_log_dev = data; + + ida_free(&pfrt_log_ida, pfrt_log_dev->index); +} + +static int acpi_pfrt_log_probe(struct platform_device *pdev) +{ + acpi_handle handle = ACPI_HANDLE(&pdev->dev); + struct pfrt_log_device *pfrt_log_dev; + int ret; + + if (!acpi_has_method(handle, "_DSM")) { + dev_dbg(&pdev->dev, "Missing _DSM\n"); + return -ENODEV; + } + + pfrt_log_dev = devm_kzalloc(&pdev->dev, sizeof(*pfrt_log_dev), GFP_KERNEL); + if (!pfrt_log_dev) + return -ENOMEM; + + ret = ida_alloc(&pfrt_log_ida, GFP_KERNEL); + if (ret < 0) + return ret; + + pfrt_log_dev->index = ret; + ret = devm_add_action_or_reset(&pdev->dev, pfrt_log_put_idx, pfrt_log_dev); + if (ret) + return ret; + + pfrt_log_dev->info.log_revid = PFRT_DEFAULT_REV_ID; + pfrt_log_dev->parent_dev = &pdev->dev; + + pfrt_log_dev->miscdev.minor = MISC_DYNAMIC_MINOR; + pfrt_log_dev->miscdev.name = devm_kasprintf(&pdev->dev, GFP_KERNEL, + "pfrt%d", + pfrt_log_dev->index); + if (!pfrt_log_dev->miscdev.name) + return -ENOMEM; + + pfrt_log_dev->miscdev.nodename = devm_kasprintf(&pdev->dev, GFP_KERNEL, + "acpi_pfr_telemetry%d", + pfrt_log_dev->index); + if (!pfrt_log_dev->miscdev.nodename) + return -ENOMEM; + + pfrt_log_dev->miscdev.fops = &acpi_pfrt_log_fops; + pfrt_log_dev->miscdev.parent = &pdev->dev; + + ret = misc_register(&pfrt_log_dev->miscdev); + if (ret) + return ret; + + platform_set_drvdata(pdev, pfrt_log_dev); + + return 0; +} + +static const struct acpi_device_id acpi_pfrt_log_ids[] = { + {"INTC1081"}, + {} +}; +MODULE_DEVICE_TABLE(acpi, acpi_pfrt_log_ids); + +static struct platform_driver acpi_pfrt_log_driver = { + .driver = { + .name = "pfr_telemetry", + .acpi_match_table = acpi_pfrt_log_ids, + }, + .probe = acpi_pfrt_log_probe, + .remove = acpi_pfrt_log_remove, +}; +module_platform_driver(acpi_pfrt_log_driver); + +MODULE_DESCRIPTION("Platform Firmware Runtime Update Telemetry driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/acpi/pfr_update.c b/drivers/acpi/pfr_update.c new file mode 100644 index 000000000000..6bb0b778b5da --- /dev/null +++ b/drivers/acpi/pfr_update.c @@ -0,0 +1,575 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ACPI Platform Firmware Runtime Update Device driver + * + * Copyright (C) 2021 Intel Corporation + * Author: Chen Yu + * + * pfr_update driver is used for Platform Firmware Runtime + * Update, which includes the code injection and driver update. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#define PFRU_FUNC_STANDARD_QUERY 0 +#define PFRU_FUNC_QUERY_UPDATE_CAP 1 +#define PFRU_FUNC_QUERY_BUF 2 +#define PFRU_FUNC_START 3 + +#define PFRU_CODE_INJECT_TYPE 1 +#define PFRU_DRIVER_UPDATE_TYPE 2 + +#define PFRU_REVID_1 1 +#define PFRU_REVID_2 2 +#define PFRU_DEFAULT_REV_ID PFRU_REVID_1 + +enum cap_index { + CAP_STATUS_IDX = 0, + CAP_UPDATE_IDX = 1, + CAP_CODE_TYPE_IDX = 2, + CAP_FW_VER_IDX = 3, + CAP_CODE_RT_VER_IDX = 4, + CAP_DRV_TYPE_IDX = 5, + CAP_DRV_RT_VER_IDX = 6, + CAP_DRV_SVN_IDX = 7, + CAP_PLAT_ID_IDX = 8, + CAP_OEM_ID_IDX = 9, + CAP_OEM_INFO_IDX = 10, + CAP_NR_IDX +}; + +enum buf_index { + BUF_STATUS_IDX = 0, + BUF_EXT_STATUS_IDX = 1, + BUF_ADDR_LOW_IDX = 2, + BUF_ADDR_HI_IDX = 3, + BUF_SIZE_IDX = 4, + BUF_NR_IDX +}; + +enum update_index { + UPDATE_STATUS_IDX = 0, + UPDATE_EXT_STATUS_IDX = 1, + UPDATE_AUTH_TIME_LOW_IDX = 2, + UPDATE_AUTH_TIME_HI_IDX = 3, + UPDATE_EXEC_TIME_LOW_IDX = 4, + UPDATE_EXEC_TIME_HI_IDX = 5, + UPDATE_NR_IDX +}; + +enum pfru_start_action { + START_STAGE = 0, + START_ACTIVATE = 1, + START_STAGE_ACTIVATE = 2, +}; + +struct pfru_device { + u32 rev_id, index; + struct device *parent_dev; + struct miscdevice miscdev; +}; + +static DEFINE_IDA(pfru_ida); + +/* + * Manual reference: + * https://uefi.org/sites/default/files/resources/Intel_MM_OS_Interface_Spec_Rev100.pdf + * + * pfru_guid is the parameter for _DSM method + */ +static const guid_t pfru_guid = + GUID_INIT(0xECF9533B, 0x4A3C, 0x4E89, 0x93, 0x9E, 0xC7, 0x71, + 0x12, 0x60, 0x1C, 0x6D); + +/* pfru_code_inj_guid is the UUID to identify code injection EFI capsule file */ +static const guid_t pfru_code_inj_guid = + GUID_INIT(0xB2F84B79, 0x7B6E, 0x4E45, 0x88, 0x5F, 0x3F, 0xB9, + 0xBB, 0x18, 0x54, 0x02); + +/* pfru_drv_update_guid is the UUID to identify driver update EFI capsule file */ +static const guid_t pfru_drv_update_guid = + GUID_INIT(0x4569DD8C, 0x75F1, 0x429A, 0xA3, 0xD6, 0x24, 0xDE, + 0x80, 0x97, 0xA0, 0xDF); + +static inline int pfru_valid_revid(u32 id) +{ + return id == PFRU_REVID_1 || id == PFRU_REVID_2; +} + +static inline struct pfru_device *to_pfru_dev(struct file *file) +{ + return container_of(file->private_data, struct pfru_device, miscdev); +} + +static int query_capability(struct pfru_update_cap_info *cap_hdr, + struct pfru_device *pfru_dev) +{ + acpi_handle handle = ACPI_HANDLE(pfru_dev->parent_dev); + union acpi_object *out_obj; + int ret = -EINVAL; + + out_obj = acpi_evaluate_dsm_typed(handle, &pfru_guid, + pfru_dev->rev_id, + PFRU_FUNC_QUERY_UPDATE_CAP, + NULL, ACPI_TYPE_PACKAGE); + if (!out_obj) + return ret; + + if (out_obj->package.count < CAP_NR_IDX || + out_obj->package.elements[CAP_STATUS_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[CAP_UPDATE_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[CAP_CODE_TYPE_IDX].type != ACPI_TYPE_BUFFER || + out_obj->package.elements[CAP_FW_VER_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[CAP_CODE_RT_VER_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[CAP_DRV_TYPE_IDX].type != ACPI_TYPE_BUFFER || + out_obj->package.elements[CAP_DRV_RT_VER_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[CAP_DRV_SVN_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[CAP_PLAT_ID_IDX].type != ACPI_TYPE_BUFFER || + out_obj->package.elements[CAP_OEM_ID_IDX].type != ACPI_TYPE_BUFFER || + out_obj->package.elements[CAP_OEM_INFO_IDX].type != ACPI_TYPE_BUFFER) + goto free_acpi_buffer; + + cap_hdr->status = out_obj->package.elements[CAP_STATUS_IDX].integer.value; + if (cap_hdr->status != DSM_SUCCEED) { + ret = -EBUSY; + dev_dbg(pfru_dev->parent_dev, "Error Status:%d\n", cap_hdr->status); + goto free_acpi_buffer; + } + + cap_hdr->update_cap = out_obj->package.elements[CAP_UPDATE_IDX].integer.value; + memcpy(&cap_hdr->code_type, + out_obj->package.elements[CAP_CODE_TYPE_IDX].buffer.pointer, + out_obj->package.elements[CAP_CODE_TYPE_IDX].buffer.length); + cap_hdr->fw_version = + out_obj->package.elements[CAP_FW_VER_IDX].integer.value; + cap_hdr->code_rt_version = + out_obj->package.elements[CAP_CODE_RT_VER_IDX].integer.value; + memcpy(&cap_hdr->drv_type, + out_obj->package.elements[CAP_DRV_TYPE_IDX].buffer.pointer, + out_obj->package.elements[CAP_DRV_TYPE_IDX].buffer.length); + cap_hdr->drv_rt_version = + out_obj->package.elements[CAP_DRV_RT_VER_IDX].integer.value; + cap_hdr->drv_svn = + out_obj->package.elements[CAP_DRV_SVN_IDX].integer.value; + memcpy(&cap_hdr->platform_id, + out_obj->package.elements[CAP_PLAT_ID_IDX].buffer.pointer, + out_obj->package.elements[CAP_PLAT_ID_IDX].buffer.length); + memcpy(&cap_hdr->oem_id, + out_obj->package.elements[CAP_OEM_ID_IDX].buffer.pointer, + out_obj->package.elements[CAP_OEM_ID_IDX].buffer.length); + cap_hdr->oem_info_len = + out_obj->package.elements[CAP_OEM_INFO_IDX].buffer.length; + + ret = 0; + +free_acpi_buffer: + kfree(out_obj); + + return ret; +} + +static int query_buffer(struct pfru_com_buf_info *info, + struct pfru_device *pfru_dev) +{ + acpi_handle handle = ACPI_HANDLE(pfru_dev->parent_dev); + union acpi_object *out_obj; + int ret = -EINVAL; + + out_obj = acpi_evaluate_dsm_typed(handle, &pfru_guid, + pfru_dev->rev_id, PFRU_FUNC_QUERY_BUF, + NULL, ACPI_TYPE_PACKAGE); + if (!out_obj) + return ret; + + if (out_obj->package.count < BUF_NR_IDX || + out_obj->package.elements[BUF_STATUS_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[BUF_EXT_STATUS_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[BUF_ADDR_LOW_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[BUF_ADDR_HI_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[BUF_SIZE_IDX].type != ACPI_TYPE_INTEGER) + goto free_acpi_buffer; + + info->status = out_obj->package.elements[BUF_STATUS_IDX].integer.value; + info->ext_status = + out_obj->package.elements[BUF_EXT_STATUS_IDX].integer.value; + if (info->status != DSM_SUCCEED) { + ret = -EBUSY; + dev_dbg(pfru_dev->parent_dev, "Error Status:%d\n", info->status); + dev_dbg(pfru_dev->parent_dev, "Error Extended Status:%d\n", info->ext_status); + + goto free_acpi_buffer; + } + + info->addr_lo = + out_obj->package.elements[BUF_ADDR_LOW_IDX].integer.value; + info->addr_hi = + out_obj->package.elements[BUF_ADDR_HI_IDX].integer.value; + info->buf_size = out_obj->package.elements[BUF_SIZE_IDX].integer.value; + + ret = 0; + +free_acpi_buffer: + kfree(out_obj); + + return ret; +} + +static int get_image_type(const struct efi_manage_capsule_image_header *img_hdr, + struct pfru_device *pfru_dev) +{ + const efi_guid_t *image_type_id = &img_hdr->image_type_id; + + /* check whether this is a code injection or driver update */ + if (guid_equal(image_type_id, &pfru_code_inj_guid)) + return PFRU_CODE_INJECT_TYPE; + + if (guid_equal(image_type_id, &pfru_drv_update_guid)) + return PFRU_DRIVER_UPDATE_TYPE; + + return -EINVAL; +} + +static int adjust_efi_size(const struct efi_manage_capsule_image_header *img_hdr, + int size) +{ + /* + * The (u64 hw_ins) was introduced in UEFI spec version 2, + * and (u64 capsule_support) was introduced in version 3. + * The size needs to be adjusted accordingly. That is to + * say, version 1 should subtract the size of hw_ins+capsule_support, + * and version 2 should sbstract the size of capsule_support. + */ + size += sizeof(struct efi_manage_capsule_image_header); + switch (img_hdr->ver) { + case 1: + return size - 2 * sizeof(u64); + + case 2: + return size - sizeof(u64); + + default: + /* only support version 1 and 2 */ + return -EINVAL; + } +} + +static bool applicable_image(const void *data, struct pfru_update_cap_info *cap, + struct pfru_device *pfru_dev) +{ + struct pfru_payload_hdr *payload_hdr; + const efi_capsule_header_t *cap_hdr = data; + const struct efi_manage_capsule_header *m_hdr; + const struct efi_manage_capsule_image_header *m_img_hdr; + const struct efi_image_auth *auth; + int type, size; + + /* + * If the code in the capsule is older than the current + * firmware code, the update will be rejected by the firmware, + * so check the version of it upfront without engaging the + * Management Mode update mechanism which may be costly. + */ + size = cap_hdr->headersize; + m_hdr = data + size; + /* + * Current data structure size plus variable array indicated + * by number of (emb_drv_cnt + payload_cnt) + */ + size += offsetof(struct efi_manage_capsule_header, offset_list) + + (m_hdr->emb_drv_cnt + m_hdr->payload_cnt) * sizeof(u64); + m_img_hdr = data + size; + + type = get_image_type(m_img_hdr, pfru_dev); + if (type < 0) + return false; + + size = adjust_efi_size(m_img_hdr, size); + if (size < 0) + return false; + + auth = data + size; + size += sizeof(u64) + auth->auth_info.hdr.len; + payload_hdr = (struct pfru_payload_hdr *)(data + size); + + /* finally compare the version */ + if (type == PFRU_CODE_INJECT_TYPE) + return payload_hdr->rt_ver >= cap->code_rt_version; + + return payload_hdr->rt_ver >= cap->drv_rt_version; +} + +static void print_update_debug_info(struct pfru_updated_result *result, + struct pfru_device *pfru_dev) +{ + dev_dbg(pfru_dev->parent_dev, "Update result:\n"); + dev_dbg(pfru_dev->parent_dev, "Authentication Time Low:%lld\n", + result->low_auth_time); + dev_dbg(pfru_dev->parent_dev, "Authentication Time High:%lld\n", + result->high_auth_time); + dev_dbg(pfru_dev->parent_dev, "Execution Time Low:%lld\n", + result->low_exec_time); + dev_dbg(pfru_dev->parent_dev, "Execution Time High:%lld\n", + result->high_exec_time); +} + +static int start_update(int action, struct pfru_device *pfru_dev) +{ + union acpi_object *out_obj, in_obj, in_buf; + struct pfru_updated_result update_result; + acpi_handle handle; + int ret = -EINVAL; + + memset(&in_obj, 0, sizeof(in_obj)); + memset(&in_buf, 0, sizeof(in_buf)); + in_obj.type = ACPI_TYPE_PACKAGE; + in_obj.package.count = 1; + in_obj.package.elements = &in_buf; + in_buf.type = ACPI_TYPE_INTEGER; + in_buf.integer.value = action; + + handle = ACPI_HANDLE(pfru_dev->parent_dev); + out_obj = acpi_evaluate_dsm_typed(handle, &pfru_guid, + pfru_dev->rev_id, PFRU_FUNC_START, + &in_obj, ACPI_TYPE_PACKAGE); + if (!out_obj) + return ret; + + if (out_obj->package.count < UPDATE_NR_IDX || + out_obj->package.elements[UPDATE_STATUS_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[UPDATE_EXT_STATUS_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[UPDATE_AUTH_TIME_LOW_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[UPDATE_AUTH_TIME_HI_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[UPDATE_EXEC_TIME_LOW_IDX].type != ACPI_TYPE_INTEGER || + out_obj->package.elements[UPDATE_EXEC_TIME_HI_IDX].type != ACPI_TYPE_INTEGER) + goto free_acpi_buffer; + + update_result.status = + out_obj->package.elements[UPDATE_STATUS_IDX].integer.value; + update_result.ext_status = + out_obj->package.elements[UPDATE_EXT_STATUS_IDX].integer.value; + + if (update_result.status != DSM_SUCCEED) { + ret = -EBUSY; + dev_dbg(pfru_dev->parent_dev, "Error Status:%d\n", update_result.status); + dev_dbg(pfru_dev->parent_dev, "Error Extended Status:%d\n", + update_result.ext_status); + + goto free_acpi_buffer; + } + + update_result.low_auth_time = + out_obj->package.elements[UPDATE_AUTH_TIME_LOW_IDX].integer.value; + update_result.high_auth_time = + out_obj->package.elements[UPDATE_AUTH_TIME_HI_IDX].integer.value; + update_result.low_exec_time = + out_obj->package.elements[UPDATE_EXEC_TIME_LOW_IDX].integer.value; + update_result.high_exec_time = + out_obj->package.elements[UPDATE_EXEC_TIME_HI_IDX].integer.value; + + print_update_debug_info(&update_result, pfru_dev); + ret = 0; + +free_acpi_buffer: + kfree(out_obj); + + return ret; +} + +static long pfru_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct pfru_update_cap_info cap_hdr; + struct pfru_device *pfru_dev = to_pfru_dev(file); + void __user *p = (void __user *)arg; + u32 rev; + int ret; + + switch (cmd) { + case PFRU_IOC_QUERY_CAP: + ret = query_capability(&cap_hdr, pfru_dev); + if (ret) + return ret; + + if (copy_to_user(p, &cap_hdr, sizeof(cap_hdr))) + return -EFAULT; + + return 0; + + case PFRU_IOC_SET_REV: + if (copy_from_user(&rev, p, sizeof(rev))) + return -EFAULT; + + if (!pfru_valid_revid(rev)) + return -EINVAL; + + pfru_dev->rev_id = rev; + + return 0; + + case PFRU_IOC_STAGE: + return start_update(START_STAGE, pfru_dev); + + case PFRU_IOC_ACTIVATE: + return start_update(START_ACTIVATE, pfru_dev); + + case PFRU_IOC_STAGE_ACTIVATE: + return start_update(START_STAGE_ACTIVATE, pfru_dev); + + default: + return -ENOTTY; + } +} + +static ssize_t pfru_write(struct file *file, const char __user *buf, + size_t len, loff_t *ppos) +{ + struct pfru_device *pfru_dev = to_pfru_dev(file); + struct pfru_update_cap_info cap; + struct pfru_com_buf_info buf_info; + phys_addr_t phy_addr; + struct iov_iter iter; + struct iovec iov; + char *buf_ptr; + int ret; + + ret = query_buffer(&buf_info, pfru_dev); + if (ret) + return ret; + + if (len > buf_info.buf_size) + return -EINVAL; + + iov.iov_base = (void __user *)buf; + iov.iov_len = len; + iov_iter_init(&iter, WRITE, &iov, 1, len); + + /* map the communication buffer */ + phy_addr = (phys_addr_t)((buf_info.addr_hi << 32) | buf_info.addr_lo); + buf_ptr = memremap(phy_addr, buf_info.buf_size, MEMREMAP_WB); + if (!buf_ptr) + return -ENOMEM; + + if (!copy_from_iter_full(buf_ptr, len, &iter)) { + ret = -EINVAL; + goto unmap; + } + + /* check if the capsule header has a valid version number */ + ret = query_capability(&cap, pfru_dev); + if (ret) + goto unmap; + + if (!applicable_image(buf_ptr, &cap, pfru_dev)) + ret = -EINVAL; + +unmap: + memunmap(buf_ptr); + + return ret ?: len; +} + +static const struct file_operations acpi_pfru_fops = { + .owner = THIS_MODULE, + .write = pfru_write, + .unlocked_ioctl = pfru_ioctl, + .llseek = noop_llseek, +}; + +static int acpi_pfru_remove(struct platform_device *pdev) +{ + struct pfru_device *pfru_dev = platform_get_drvdata(pdev); + + misc_deregister(&pfru_dev->miscdev); + + return 0; +} + +static void pfru_put_idx(void *data) +{ + struct pfru_device *pfru_dev = data; + + ida_free(&pfru_ida, pfru_dev->index); +} + +static int acpi_pfru_probe(struct platform_device *pdev) +{ + acpi_handle handle = ACPI_HANDLE(&pdev->dev); + struct pfru_device *pfru_dev; + int ret; + + if (!acpi_has_method(handle, "_DSM")) { + dev_dbg(&pdev->dev, "Missing _DSM\n"); + return -ENODEV; + } + + pfru_dev = devm_kzalloc(&pdev->dev, sizeof(*pfru_dev), GFP_KERNEL); + if (!pfru_dev) + return -ENOMEM; + + ret = ida_alloc(&pfru_ida, GFP_KERNEL); + if (ret < 0) + return ret; + + pfru_dev->index = ret; + ret = devm_add_action_or_reset(&pdev->dev, pfru_put_idx, pfru_dev); + if (ret) + return ret; + + pfru_dev->rev_id = PFRU_DEFAULT_REV_ID; + pfru_dev->parent_dev = &pdev->dev; + + pfru_dev->miscdev.minor = MISC_DYNAMIC_MINOR; + pfru_dev->miscdev.name = devm_kasprintf(&pdev->dev, GFP_KERNEL, + "pfru%d", pfru_dev->index); + if (!pfru_dev->miscdev.name) + return -ENOMEM; + + pfru_dev->miscdev.nodename = devm_kasprintf(&pdev->dev, GFP_KERNEL, + "acpi_pfr_update%d", pfru_dev->index); + if (!pfru_dev->miscdev.nodename) + return -ENOMEM; + + pfru_dev->miscdev.fops = &acpi_pfru_fops; + pfru_dev->miscdev.parent = &pdev->dev; + + ret = misc_register(&pfru_dev->miscdev); + if (ret) + return ret; + + platform_set_drvdata(pdev, pfru_dev); + + return 0; +} + +static const struct acpi_device_id acpi_pfru_ids[] = { + {"INTC1080"}, + {} +}; +MODULE_DEVICE_TABLE(acpi, acpi_pfru_ids); + +static struct platform_driver acpi_pfru_driver = { + .driver = { + .name = "pfr_update", + .acpi_match_table = acpi_pfru_ids, + }, + .probe = acpi_pfru_probe, + .remove = acpi_pfru_remove, +}; +module_platform_driver(acpi_pfru_driver); + +MODULE_DESCRIPTION("Platform Firmware Runtime Update device driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index c215bc8723d0..1331756d4cfc 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -2502,42 +2502,33 @@ int acpi_bus_register_early_device(int type) } EXPORT_SYMBOL_GPL(acpi_bus_register_early_device); -static int acpi_bus_scan_fixed(void) +static void acpi_bus_scan_fixed(void) { - int result = 0; - - /* - * Enumerate all fixed-feature devices. - */ if (!(acpi_gbl_FADT.flags & ACPI_FADT_POWER_BUTTON)) { - struct acpi_device *device = NULL; + struct acpi_device *adev = NULL; - result = acpi_add_single_object(&device, NULL, - ACPI_BUS_TYPE_POWER_BUTTON, false); - if (result) - return result; - - device->flags.match_driver = true; - result = device_attach(&device->dev); - if (result < 0) - return result; - - device_init_wakeup(&device->dev, true); + acpi_add_single_object(&adev, NULL, ACPI_BUS_TYPE_POWER_BUTTON, + false); + if (adev) { + adev->flags.match_driver = true; + if (device_attach(&adev->dev) >= 0) + device_init_wakeup(&adev->dev, true); + else + dev_dbg(&adev->dev, "No driver\n"); + } } if (!(acpi_gbl_FADT.flags & ACPI_FADT_SLEEP_BUTTON)) { - struct acpi_device *device = NULL; + struct acpi_device *adev = NULL; - result = acpi_add_single_object(&device, NULL, - ACPI_BUS_TYPE_SLEEP_BUTTON, false); - if (result) - return result; - - device->flags.match_driver = true; - result = device_attach(&device->dev); + acpi_add_single_object(&adev, NULL, ACPI_BUS_TYPE_SLEEP_BUTTON, + false); + if (adev) { + adev->flags.match_driver = true; + if (device_attach(&adev->dev) < 0) + dev_dbg(&adev->dev, "No driver\n"); + } } - - return result < 0 ? result : 0; } static void __init acpi_get_spcr_uart_addr(void) @@ -2558,9 +2549,8 @@ static void __init acpi_get_spcr_uart_addr(void) static bool acpi_scan_initialized; -int __init acpi_scan_init(void) +void __init acpi_scan_init(void) { - int result; acpi_status status; struct acpi_table_stao *stao_ptr; @@ -2610,33 +2600,23 @@ int __init acpi_scan_init(void) /* * Enumerate devices in the ACPI namespace. */ - result = acpi_bus_scan(ACPI_ROOT_OBJECT); - if (result) - goto out; + if (acpi_bus_scan(ACPI_ROOT_OBJECT)) + goto unlock; acpi_root = acpi_fetch_acpi_dev(ACPI_ROOT_OBJECT); if (!acpi_root) - goto out; + goto unlock; /* Fixed feature devices do not exist on HW-reduced platform */ - if (!acpi_gbl_reduced_hardware) { - result = acpi_bus_scan_fixed(); - if (result) { - acpi_detach_data(acpi_root->handle, - acpi_scan_drop_device); - acpi_device_del(acpi_root); - acpi_bus_put_acpi_device(acpi_root); - goto out; - } - } + if (!acpi_gbl_reduced_hardware) + acpi_bus_scan_fixed(); acpi_turn_off_unused_power_resources(); acpi_scan_initialized = true; - out: +unlock: mutex_unlock(&acpi_scan_lock); - return result; } static struct acpi_probe_entry *ape; diff --git a/drivers/acpi/spcr.c b/drivers/acpi/spcr.c index 25c2d0be953e..d589543875b8 100644 --- a/drivers/acpi/spcr.c +++ b/drivers/acpi/spcr.c @@ -107,8 +107,13 @@ int __init acpi_parse_spcr(bool enable_earlycon, bool enable_console) pr_info("SPCR table version %d\n", table->header.revision); if (table->serial_port.space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) { - switch (ACPI_ACCESS_BIT_WIDTH(( - table->serial_port.access_width))) { + u32 bit_width = table->serial_port.access_width; + + if (bit_width > ACPI_ACCESS_BIT_MAX) { + pr_err("Unacceptable wide SPCR Access Width. Defaulting to byte size\n"); + bit_width = ACPI_ACCESS_BIT_DEFAULT; + } + switch (ACPI_ACCESS_BIT_WIDTH((bit_width))) { default: pr_err("Unexpected SPCR Access Width. Defaulting to byte size\n"); fallthrough; diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig index a7da8ea7b3ed..cb54631fd950 100644 --- a/drivers/ata/Kconfig +++ b/drivers/ata/Kconfig @@ -146,7 +146,7 @@ config SATA_AHCI_PLATFORM config AHCI_BRCM tristate "Broadcom AHCI SATA support" depends on ARCH_BRCMSTB || BMIPS_GENERIC || ARCH_BCM_NSP || \ - ARCH_BCM_63XX + ARCH_BCM_63XX || COMPILE_TEST select SATA_HOST help This option enables support for the AHCI SATA3 controller found on @@ -156,7 +156,7 @@ config AHCI_BRCM config AHCI_DA850 tristate "DaVinci DA850 AHCI SATA support" - depends on ARCH_DAVINCI_DA850 + depends on ARCH_DAVINCI_DA850 || COMPILE_TEST select SATA_HOST help This option enables support for the DaVinci DA850 SoC's @@ -166,7 +166,7 @@ config AHCI_DA850 config AHCI_DM816 tristate "DaVinci DM816 AHCI SATA support" - depends on ARCH_OMAP2PLUS + depends on ARCH_OMAP2PLUS || COMPILE_TEST select SATA_HOST help This option enables support for the DaVinci DM816 SoC's @@ -206,7 +206,7 @@ config AHCI_CEVA config AHCI_MTK tristate "MediaTek AHCI SATA support" - depends on ARCH_MEDIATEK + depends on ARCH_MEDIATEK || COMPILE_TEST select MFD_SYSCON select SATA_HOST help @@ -217,7 +217,7 @@ config AHCI_MTK config AHCI_MVEBU tristate "Marvell EBU AHCI SATA support" - depends on ARCH_MVEBU + depends on ARCH_MVEBU || COMPILE_TEST select SATA_HOST help This option enables support for the Marvebu EBU SoC's @@ -236,7 +236,7 @@ config AHCI_OCTEON config AHCI_SUNXI tristate "Allwinner sunxi AHCI SATA support" - depends on ARCH_SUNXI + depends on ARCH_SUNXI || COMPILE_TEST select SATA_HOST help This option enables support for the Allwinner sunxi SoC's @@ -246,7 +246,7 @@ config AHCI_SUNXI config AHCI_TEGRA tristate "NVIDIA Tegra AHCI SATA support" - depends on ARCH_TEGRA + depends on ARCH_TEGRA || COMPILE_TEST select SATA_HOST help This option enables support for the NVIDIA Tegra SoC's @@ -256,7 +256,7 @@ config AHCI_TEGRA config AHCI_XGENE tristate "APM X-Gene 6.0Gbps AHCI SATA host controller support" - depends on PHY_XGENE + depends on PHY_XGENE || COMPILE_TEST select SATA_HOST help This option enables support for APM X-Gene SoC SATA host controller. @@ -273,7 +273,7 @@ config AHCI_QORIQ config SATA_FSL tristate "Freescale 3.0Gbps SATA support" - depends on FSL_SOC + depends on FSL_SOC || COMPILE_TEST select SATA_HOST help This option enables support for Freescale 3.0Gbps SATA controller. @@ -294,7 +294,7 @@ config SATA_GEMINI config SATA_AHCI_SEATTLE tristate "AMD Seattle 6.0Gbps AHCI SATA host controller support" - depends on ARCH_SEATTLE + depends on ARCH_SEATTLE || COMPILE_TEST select SATA_HOST help This option enables support for AMD Seattle SATA host controller. @@ -432,18 +432,6 @@ config SATA_DWC_OLD_DMA This option enables support for old device trees without the "dmas" property. -config SATA_DWC_DEBUG - bool "Debugging driver version" - depends on SATA_DWC - help - This option enables debugging output in the driver. - -config SATA_DWC_VDEBUG - bool "Verbose debug output" - depends on SATA_DWC_DEBUG - help - This option enables the taskfile dumping and NCQ debugging. - config SATA_HIGHBANK tristate "Calxeda Highbank SATA support" depends on ARCH_HIGHBANK || COMPILE_TEST @@ -611,7 +599,7 @@ config PATA_ATP867X config PATA_BK3710 tristate "Palmchip BK3710 PATA support" - depends on ARCH_DAVINCI + depends on ARCH_DAVINCI || COMPILE_TEST select PATA_TIMINGS help This option enables support for the integrated IDE controller on @@ -649,7 +637,7 @@ config PATA_CS5530 config PATA_CS5535 tristate "CS5535 PATA support (Experimental)" - depends on PCI && X86_32 + depends on PCI && (X86_32 || (X86_64 && COMPILE_TEST)) help This option enables support for the NatSemi/AMD CS5535 companion chip used with the Geode processor family. @@ -697,7 +685,7 @@ config PATA_EP93XX config PATA_FTIDE010 tristate "Faraday Technology FTIDE010 PATA support" depends on OF - depends on ARM + depends on ARM || COMPILE_TEST depends on SATA_GEMINI help This option enables support for the Faraday FTIDE010 @@ -760,7 +748,7 @@ config PATA_ICSIDE config PATA_IMX tristate "PATA support for Freescale iMX" - depends on ARCH_MXC + depends on ARCH_MXC || COMPILE_TEST select PATA_TIMINGS help This option enables support for the PATA host available on Freescale @@ -981,7 +969,7 @@ config PATA_VIA config PATA_PXA tristate "PXA DMA-capable PATA support" - depends on ARCH_PXA + depends on ARCH_PXA || COMPILE_TEST help This option enables support for harddrive attached to PXA CPU's bus. @@ -1157,7 +1145,7 @@ config PATA_RZ1000 config PATA_SAMSUNG_CF tristate "Samsung SoC PATA support" - depends on SAMSUNG_DEV_IDE + depends on SAMSUNG_DEV_IDE || COMPILE_TEST select PATA_TIMINGS help This option enables basic support for Samsung's S3C/S5P board diff --git a/drivers/ata/acard-ahci.c b/drivers/ata/acard-ahci.c index 2a04e8abd397..536d4cb8f08b 100644 --- a/drivers/ata/acard-ahci.c +++ b/drivers/ata/acard-ahci.c @@ -185,8 +185,6 @@ static unsigned int acard_ahci_fill_sg(struct ata_queued_cmd *qc, void *cmd_tbl) struct acard_sg *acard_sg = cmd_tbl + AHCI_CMD_TBL_HDR_SZ; unsigned int si, last_si = 0; - VPRINTK("ENTER\n"); - /* * Next, the S/G list. */ @@ -362,8 +360,6 @@ static int acard_ahci_init_one(struct pci_dev *pdev, const struct pci_device_id struct ata_host *host; int n_ports, i, rc; - VPRINTK("ENTER\n"); - WARN_ON((int)ATA_MAX_QUEUE > AHCI_MAX_CMDS); ata_print_version_once(&pdev->dev, DRV_VERSION); diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 1e1167e725a4..ab5811ef5a53 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -51,6 +51,7 @@ enum board_ids { board_ahci, board_ahci_ign_iferr, board_ahci_mobile, + board_ahci_no_debounce_delay, board_ahci_nomsi, board_ahci_noncq, board_ahci_nosntf, @@ -141,6 +142,13 @@ static const struct ata_port_info ahci_port_info[] = { .udma_mask = ATA_UDMA6, .port_ops = &ahci_ops, }, + [board_ahci_no_debounce_delay] = { + .flags = AHCI_FLAG_COMMON, + .link_flags = ATA_LFLAG_NO_DEBOUNCE_DELAY, + .pio_mask = ATA_PIO4, + .udma_mask = ATA_UDMA6, + .port_ops = &ahci_ops, + }, [board_ahci_nomsi] = { AHCI_HFLAGS (AHCI_HFLAG_NO_MSI), .flags = AHCI_FLAG_COMMON, @@ -437,6 +445,7 @@ static const struct pci_device_id ahci_pci_tbl[] = { board_ahci_al }, /* AMD */ { PCI_VDEVICE(AMD, 0x7800), board_ahci }, /* AMD Hudson-2 */ + { PCI_VDEVICE(AMD, 0x7801), board_ahci_no_debounce_delay }, /* AMD Hudson-2 (AHCI mode) */ { PCI_VDEVICE(AMD, 0x7900), board_ahci }, /* AMD CZ */ { PCI_VDEVICE(AMD, 0x7901), board_ahci_mobile }, /* AMD Green Sardine */ /* AMD is using RAID class only for ahci controllers */ @@ -684,7 +693,7 @@ static void ahci_pci_init_controller(struct ata_host *host) /* clear port IRQ */ tmp = readl(port_mmio + PORT_IRQ_STAT); - VPRINTK("PORT_IRQ_STAT 0x%x\n", tmp); + dev_dbg(&pdev->dev, "PORT_IRQ_STAT 0x%x\n", tmp); if (tmp) writel(tmp, port_mmio + PORT_IRQ_STAT); } @@ -700,8 +709,6 @@ static int ahci_vt8251_hardreset(struct ata_link *link, unsigned int *class, bool online; int rc; - DPRINTK("ENTER\n"); - hpriv->stop_engine(ap); rc = sata_link_hardreset(link, sata_ehc_deb_timing(&link->eh_context), @@ -709,8 +716,6 @@ static int ahci_vt8251_hardreset(struct ata_link *link, unsigned int *class, hpriv->start_engine(ap); - DPRINTK("EXIT, rc=%d, class=%u\n", rc, *class); - /* vt8251 doesn't clear BSY on signature FIS reception, * request follow-up softreset. */ @@ -790,8 +795,6 @@ static int ahci_avn_hardreset(struct ata_link *link, unsigned int *class, bool online; int rc, i; - DPRINTK("ENTER\n"); - hpriv->stop_engine(ap); for (i = 0; i < 2; i++) { @@ -829,7 +832,6 @@ static int ahci_avn_hardreset(struct ata_link *link, unsigned int *class, if (online) *class = ahci_dev_classify(ap); - DPRINTK("EXIT, rc=%d, class=%u\n", rc, *class); return rc; } @@ -1476,7 +1478,6 @@ static irqreturn_t ahci_thunderx_irq_handler(int irq, void *dev_instance) u32 irq_stat, irq_masked; unsigned int handled = 1; - VPRINTK("ENTER\n"); hpriv = host->private_data; mmio = hpriv->mmio; irq_stat = readl(mmio + HOST_IRQ_STAT); @@ -1493,7 +1494,6 @@ static irqreturn_t ahci_thunderx_irq_handler(int irq, void *dev_instance) irq_stat = readl(mmio + HOST_IRQ_STAT); spin_unlock(&host->lock); } while (irq_stat); - VPRINTK("EXIT\n"); return IRQ_RETVAL(handled); } @@ -1657,7 +1657,7 @@ static ssize_t remapped_nvme_show(struct device *dev, struct ata_host *host = dev_get_drvdata(dev); struct ahci_host_priv *hpriv = host->private_data; - return sprintf(buf, "%u\n", hpriv->remapped_nvme); + return sysfs_emit(buf, "%u\n", hpriv->remapped_nvme); } static DEVICE_ATTR_RO(remapped_nvme); @@ -1673,8 +1673,6 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) int n_ports, i, rc; int ahci_pci_bar = AHCI_PCI_BAR_STANDARD; - VPRINTK("ENTER\n"); - WARN_ON((int)ATA_MAX_QUEUE > AHCI_MAX_CMDS); ata_print_version_once(&pdev->dev, DRV_VERSION); diff --git a/drivers/ata/ahci_brcm.c b/drivers/ata/ahci_brcm.c index 6e9c5ade4c2e..64dd8aa397d5 100644 --- a/drivers/ata/ahci_brcm.c +++ b/drivers/ata/ahci_brcm.c @@ -246,7 +246,7 @@ static void brcm_sata_init(struct brcm_ahci_priv *priv) } static unsigned int brcm_ahci_read_id(struct ata_device *dev, - struct ata_taskfile *tf, u16 *id) + struct ata_taskfile *tf, __le16 *id) { struct ata_port *ap = dev->link->ap; struct ata_host *host = ap->host; @@ -333,7 +333,7 @@ static struct ata_port_operations ahci_brcm_platform_ops = { static const struct ata_port_info ahci_brcm_port_info = { .flags = AHCI_FLAG_COMMON | ATA_FLAG_NO_DIPM, - .link_flags = ATA_LFLAG_NO_DB_DELAY, + .link_flags = ATA_LFLAG_NO_DEBOUNCE_DELAY, .pio_mask = ATA_PIO4, .udma_mask = ATA_UDMA6, .port_ops = &ahci_brcm_platform_ops, diff --git a/drivers/ata/ahci_ceva.c b/drivers/ata/ahci_ceva.c index e9c7c07fd84c..acf59f51b356 100644 --- a/drivers/ata/ahci_ceva.c +++ b/drivers/ata/ahci_ceva.c @@ -92,9 +92,8 @@ struct ceva_ahci_priv { }; static unsigned int ceva_ahci_read_id(struct ata_device *dev, - struct ata_taskfile *tf, u16 *id) + struct ata_taskfile *tf, __le16 *id) { - __le16 *__id = (__le16 *)id; u32 err_mask; err_mask = ata_do_dev_read_id(dev, tf, id); @@ -104,7 +103,7 @@ static unsigned int ceva_ahci_read_id(struct ata_device *dev, * Since CEVA controller does not support device sleep feature, we * need to clear DEVSLP (bit 8) in word78 of the IDENTIFY DEVICE data. */ - __id[ATA_ID_FEATURE_SUPP] &= cpu_to_le16(~(1 << 8)); + id[ATA_ID_FEATURE_SUPP] &= cpu_to_le16(~(1 << 8)); return 0; } diff --git a/drivers/ata/ahci_qoriq.c b/drivers/ata/ahci_qoriq.c index 5b46fc9aeb4a..bf5b388bd4e0 100644 --- a/drivers/ata/ahci_qoriq.c +++ b/drivers/ata/ahci_qoriq.c @@ -103,8 +103,6 @@ static int ahci_qoriq_hardreset(struct ata_link *link, unsigned int *class, int rc; bool ls1021a_workaround = (qoriq_priv->type == AHCI_LS1021A); - DPRINTK("ENTER\n"); - hpriv->stop_engine(ap); /* @@ -146,8 +144,6 @@ static int ahci_qoriq_hardreset(struct ata_link *link, unsigned int *class, if (online) *class = ahci_dev_classify(ap); - - DPRINTK("EXIT, rc=%d, class=%u\n", rc, *class); return rc; } diff --git a/drivers/ata/ahci_xgene.c b/drivers/ata/ahci_xgene.c index dffc432b9d54..8e206379d699 100644 --- a/drivers/ata/ahci_xgene.c +++ b/drivers/ata/ahci_xgene.c @@ -193,7 +193,7 @@ static unsigned int xgene_ahci_qc_issue(struct ata_queued_cmd *qc) struct xgene_ahci_context *ctx = hpriv->plat_data; int rc = 0; u32 port_fbs; - void *port_mmio = ahci_port_base(ap); + void __iomem *port_mmio = ahci_port_base(ap); /* * Write the pmp value to PxFBS.DEV @@ -237,7 +237,7 @@ static bool xgene_ahci_is_memram_inited(struct xgene_ahci_context *ctx) * does not support DEVSLP. */ static unsigned int xgene_ahci_read_id(struct ata_device *dev, - struct ata_taskfile *tf, u16 *id) + struct ata_taskfile *tf, __le16 *id) { u32 err_mask; @@ -454,7 +454,7 @@ static int xgene_ahci_pmp_softreset(struct ata_link *link, unsigned int *class, int pmp = sata_srst_pmp(link); struct ata_port *ap = link->ap; u32 rc; - void *port_mmio = ahci_port_base(ap); + void __iomem *port_mmio = ahci_port_base(ap); u32 port_fbs; /* @@ -499,7 +499,7 @@ static int xgene_ahci_softreset(struct ata_link *link, unsigned int *class, struct ata_port *ap = link->ap; struct ahci_host_priv *hpriv = ap->host->private_data; struct xgene_ahci_context *ctx = hpriv->plat_data; - void *port_mmio = ahci_port_base(ap); + void __iomem *port_mmio = ahci_port_base(ap); u32 port_fbs; u32 port_fbs_save; u32 retry = 1; @@ -588,8 +588,6 @@ static irqreturn_t xgene_ahci_irq_intr(int irq, void *dev_instance) void __iomem *mmio; u32 irq_stat, irq_masked; - VPRINTK("ENTER\n"); - hpriv = host->private_data; mmio = hpriv->mmio; @@ -612,8 +610,6 @@ static irqreturn_t xgene_ahci_irq_intr(int irq, void *dev_instance) spin_unlock(&host->lock); - VPRINTK("EXIT\n"); - return IRQ_RETVAL(rc); } diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c index 0b2fcf0d1d6c..27b0d903f91f 100644 --- a/drivers/ata/ata_piix.c +++ b/drivers/ata/ata_piix.c @@ -77,6 +77,7 @@ #include #include #include +#include #define DRV_NAME "ata_piix" #define DRV_VERSION "2.13" @@ -816,10 +817,15 @@ static int piix_sidpr_set_lpm(struct ata_link *link, enum ata_lpm_policy policy, static bool piix_irq_check(struct ata_port *ap) { + unsigned char host_stat; + if (unlikely(!ap->ioaddr.bmdma_addr)) return false; - return ap->ops->bmdma_status(ap) & ATA_DMA_INTR; + host_stat = ap->ops->bmdma_status(ap); + trace_ata_bmdma_status(ap, host_stat); + + return host_stat & ATA_DMA_INTR; } #ifdef CONFIG_PM_SLEEP @@ -1345,7 +1351,6 @@ static void piix_init_pcs(struct ata_host *host, new_pcs = pcs | map_db->port_enable; if (new_pcs != pcs) { - DPRINTK("updating PCS from 0x%x to 0x%x\n", pcs, new_pcs); pci_write_config_word(pdev, ICH5_PCS, new_pcs); msleep(150); } @@ -1769,14 +1774,12 @@ static int __init piix_init(void) { int rc; - DPRINTK("pci_register_driver\n"); rc = pci_register_driver(&piix_pci_driver); if (rc) return rc; in_module_init = 0; - DPRINTK("done\n"); return 0; } diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index f76b8418e6fb..0ed484e04fd6 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -1234,12 +1234,12 @@ static void ahci_port_init(struct device *dev, struct ata_port *ap, /* clear SError */ tmp = readl(port_mmio + PORT_SCR_ERR); - VPRINTK("PORT_SCR_ERR 0x%x\n", tmp); + dev_dbg(dev, "PORT_SCR_ERR 0x%x\n", tmp); writel(tmp, port_mmio + PORT_SCR_ERR); /* clear port IRQ */ tmp = readl(port_mmio + PORT_IRQ_STAT); - VPRINTK("PORT_IRQ_STAT 0x%x\n", tmp); + dev_dbg(dev, "PORT_IRQ_STAT 0x%x\n", tmp); if (tmp) writel(tmp, port_mmio + PORT_IRQ_STAT); @@ -1270,10 +1270,10 @@ void ahci_init_controller(struct ata_host *host) } tmp = readl(mmio + HOST_CTL); - VPRINTK("HOST_CTL 0x%x\n", tmp); + dev_dbg(host->dev, "HOST_CTL 0x%x\n", tmp); writel(tmp | HOST_IRQ_EN, mmio + HOST_CTL); tmp = readl(mmio + HOST_CTL); - VPRINTK("HOST_CTL 0x%x\n", tmp); + dev_dbg(host->dev, "HOST_CTL 0x%x\n", tmp); } EXPORT_SYMBOL_GPL(ahci_init_controller); @@ -1300,7 +1300,7 @@ unsigned int ahci_dev_classify(struct ata_port *ap) tf.lbal = (tmp >> 8) & 0xff; tf.nsect = (tmp) & 0xff; - return ata_dev_classify(&tf); + return ata_port_classify(ap, &tf); } EXPORT_SYMBOL_GPL(ahci_dev_classify); @@ -1415,8 +1415,6 @@ int ahci_do_softreset(struct ata_link *link, unsigned int *class, bool fbs_disabled = false; int rc; - DPRINTK("ENTER\n"); - /* prepare for SRST (AHCI-1.1 10.4.1) */ rc = ahci_kick_engine(ap); if (rc && rc != -EOPNOTSUPP) @@ -1476,7 +1474,6 @@ int ahci_do_softreset(struct ata_link *link, unsigned int *class, if (fbs_disabled) ahci_enable_fbs(ap); - DPRINTK("EXIT, class=%u\n", *class); return 0; fail: @@ -1498,8 +1495,6 @@ static int ahci_softreset(struct ata_link *link, unsigned int *class, { int pmp = sata_srst_pmp(link); - DPRINTK("ENTER\n"); - return ahci_do_softreset(link, class, pmp, deadline, ahci_check_ready); } EXPORT_SYMBOL_GPL(ahci_do_softreset); @@ -1529,8 +1524,6 @@ static int ahci_pmp_retry_softreset(struct ata_link *link, unsigned int *class, int rc; u32 irq_sts; - DPRINTK("ENTER\n"); - rc = ahci_do_softreset(link, class, pmp, deadline, ahci_bad_pmp_check_ready); @@ -1564,8 +1557,6 @@ int ahci_do_hardreset(struct ata_link *link, unsigned int *class, struct ata_taskfile tf; int rc; - DPRINTK("ENTER\n"); - hpriv->stop_engine(ap); /* clear D2H reception area to properly wait for D2H FIS */ @@ -1581,7 +1572,6 @@ int ahci_do_hardreset(struct ata_link *link, unsigned int *class, if (*online) *class = ahci_dev_classify(ap); - DPRINTK("EXIT, rc=%d, class=%u\n", rc, *class); return rc; } EXPORT_SYMBOL_GPL(ahci_do_hardreset); @@ -1620,8 +1610,6 @@ static unsigned int ahci_fill_sg(struct ata_queued_cmd *qc, void *cmd_tbl) struct ahci_sg *ahci_sg = cmd_tbl + AHCI_CMD_TBL_HDR_SZ; unsigned int si; - VPRINTK("ENTER\n"); - /* * Next, the S/G list. */ @@ -1695,7 +1683,6 @@ static void ahci_fbs_dec_intr(struct ata_port *ap) u32 fbs = readl(port_mmio + PORT_FBS); int retries = 3; - DPRINTK("ENTER\n"); BUG_ON(!pp->fbs_enabled); /* time to wait for DEC is not specified by AHCI spec, @@ -1924,8 +1911,6 @@ static irqreturn_t ahci_multi_irqs_intr_hard(int irq, void *dev_instance) void __iomem *port_mmio = ahci_port_base(ap); u32 status; - VPRINTK("ENTER\n"); - status = readl(port_mmio + PORT_IRQ_STAT); writel(status, port_mmio + PORT_IRQ_STAT); @@ -1933,8 +1918,6 @@ static irqreturn_t ahci_multi_irqs_intr_hard(int irq, void *dev_instance) ahci_handle_port_interrupt(ap, port_mmio, status); spin_unlock(ap->lock); - VPRINTK("EXIT\n"); - return IRQ_HANDLED; } @@ -1951,9 +1934,7 @@ u32 ahci_handle_port_intr(struct ata_host *host, u32 irq_masked) ap = host->ports[i]; if (ap) { ahci_port_intr(ap); - VPRINTK("port %u\n", i); } else { - VPRINTK("port %u (no irq)\n", i); if (ata_ratelimit()) dev_warn(host->dev, "interrupt on disabled port %u\n", i); @@ -1974,8 +1955,6 @@ static irqreturn_t ahci_single_level_irq_intr(int irq, void *dev_instance) void __iomem *mmio; u32 irq_stat, irq_masked; - VPRINTK("ENTER\n"); - hpriv = host->private_data; mmio = hpriv->mmio; @@ -2003,8 +1982,6 @@ static irqreturn_t ahci_single_level_irq_intr(int irq, void *dev_instance) spin_unlock(&host->lock); - VPRINTK("EXIT\n"); - return IRQ_RETVAL(rc); } diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c index 0910441321f7..18296443ccba 100644 --- a/drivers/ata/libahci_platform.c +++ b/drivers/ata/libahci_platform.c @@ -579,11 +579,8 @@ int ahci_platform_init_host(struct platform_device *pdev, int i, irq, n_ports, rc; irq = platform_get_irq(pdev, 0); - if (irq < 0) { - if (irq != -EPROBE_DEFER) - dev_err(dev, "no irq\n"); + if (irq < 0) return irq; - } if (!irq) return -EINVAL; @@ -642,13 +639,8 @@ int ahci_platform_init_host(struct platform_device *pdev, if (hpriv->cap & HOST_CAP_64) { rc = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(64)); if (rc) { - rc = dma_coerce_mask_and_coherent(dev, - DMA_BIT_MASK(32)); - if (rc) { - dev_err(dev, "Failed to enable 64-bit DMA.\n"); - return rc; - } - dev_warn(dev, "Enable 32-bit DMA instead of 64-bit.\n"); + dev_err(dev, "Failed to enable 64-bit DMA.\n"); + return rc; } } diff --git a/drivers/ata/libata-acpi.c b/drivers/ata/libata-acpi.c index 7a7d6642edcc..8cfa8c96bb13 100644 --- a/drivers/ata/libata-acpi.c +++ b/drivers/ata/libata-acpi.c @@ -402,7 +402,6 @@ EXPORT_SYMBOL_GPL(ata_acpi_stm); */ static int ata_dev_get_GTF(struct ata_device *dev, struct ata_acpi_gtf **gtf) { - struct ata_port *ap = dev->link->ap; acpi_status status; struct acpi_buffer output; union acpi_object *out_obj; @@ -418,10 +417,6 @@ static int ata_dev_get_GTF(struct ata_device *dev, struct ata_acpi_gtf **gtf) output.length = ACPI_ALLOCATE_BUFFER; output.pointer = NULL; /* ACPI-CA sets this; save/free it later */ - if (ata_msg_probe(ap)) - ata_dev_dbg(dev, "%s: ENTER: port#: %d\n", - __func__, ap->port_no); - /* _GTF has no input parameters */ status = acpi_evaluate_object(ata_dev_acpi_handle(dev), "_GTF", NULL, &output); @@ -437,11 +432,9 @@ static int ata_dev_get_GTF(struct ata_device *dev, struct ata_acpi_gtf **gtf) } if (!output.length || !output.pointer) { - if (ata_msg_probe(ap)) - ata_dev_dbg(dev, "%s: Run _GTF: length or ptr is NULL (0x%llx, 0x%p)\n", - __func__, - (unsigned long long)output.length, - output.pointer); + ata_dev_dbg(dev, "Run _GTF: length or ptr is NULL (0x%llx, 0x%p)\n", + (unsigned long long)output.length, + output.pointer); rc = -EINVAL; goto out_free; } @@ -464,9 +457,8 @@ static int ata_dev_get_GTF(struct ata_device *dev, struct ata_acpi_gtf **gtf) rc = out_obj->buffer.length / REGS_PER_GTF; if (gtf) { *gtf = (void *)out_obj->buffer.pointer; - if (ata_msg_probe(ap)) - ata_dev_dbg(dev, "%s: returning gtf=%p, gtf_count=%d\n", - __func__, *gtf, rc); + ata_dev_dbg(dev, "returning gtf=%p, gtf_count=%d\n", + *gtf, rc); } return rc; @@ -650,9 +642,7 @@ static int ata_acpi_run_tf(struct ata_device *dev, struct ata_taskfile *pptf = NULL; struct ata_taskfile tf, ptf, rtf; unsigned int err_mask; - const char *level; const char *descr; - char msg[60]; int rc; if ((gtf->tf[0] == 0) && (gtf->tf[1] == 0) && (gtf->tf[2] == 0) @@ -666,6 +656,8 @@ static int ata_acpi_run_tf(struct ata_device *dev, pptf = &ptf; } + descr = ata_get_cmd_name(tf.command); + if (!ata_acpi_filter_tf(dev, &tf, pptf)) { rtf = tf; err_mask = ata_exec_internal(dev, &rtf, NULL, @@ -673,40 +665,42 @@ static int ata_acpi_run_tf(struct ata_device *dev, switch (err_mask) { case 0: - level = KERN_DEBUG; - snprintf(msg, sizeof(msg), "succeeded"); + ata_dev_dbg(dev, + "ACPI cmd %02x/%02x:%02x:%02x:%02x:%02x:%02x" + "(%s) succeeded\n", + tf.command, tf.feature, tf.nsect, tf.lbal, + tf.lbam, tf.lbah, tf.device, descr); rc = 1; break; case AC_ERR_DEV: - level = KERN_INFO; - snprintf(msg, sizeof(msg), - "rejected by device (Stat=0x%02x Err=0x%02x)", - rtf.command, rtf.feature); + ata_dev_info(dev, + "ACPI cmd %02x/%02x:%02x:%02x:%02x:%02x:%02x" + "(%s) rejected by device (Stat=0x%02x Err=0x%02x)", + tf.command, tf.feature, tf.nsect, tf.lbal, + tf.lbam, tf.lbah, tf.device, descr, + rtf.command, rtf.feature); rc = 0; break; default: - level = KERN_ERR; - snprintf(msg, sizeof(msg), - "failed (Emask=0x%x Stat=0x%02x Err=0x%02x)", - err_mask, rtf.command, rtf.feature); + ata_dev_err(dev, + "ACPI cmd %02x/%02x:%02x:%02x:%02x:%02x:%02x" + "(%s) failed (Emask=0x%x Stat=0x%02x Err=0x%02x)", + tf.command, tf.feature, tf.nsect, tf.lbal, + tf.lbam, tf.lbah, tf.device, descr, + err_mask, rtf.command, rtf.feature); rc = -EIO; break; } } else { - level = KERN_INFO; - snprintf(msg, sizeof(msg), "filtered out"); + ata_dev_info(dev, + "ACPI cmd %02x/%02x:%02x:%02x:%02x:%02x:%02x" + "(%s) filtered out\n", + tf.command, tf.feature, tf.nsect, tf.lbal, + tf.lbam, tf.lbah, tf.device, descr); rc = 0; } - descr = ata_get_cmd_descript(tf.command); - - ata_dev_printk(dev, level, - "ACPI cmd %02x/%02x:%02x:%02x:%02x:%02x:%02x (%s) %s\n", - tf.command, tf.feature, tf.nsect, tf.lbal, - tf.lbam, tf.lbah, tf.device, - (descr ? descr : "unknown"), msg); - return rc; } @@ -776,9 +770,8 @@ static int ata_acpi_push_id(struct ata_device *dev) struct acpi_object_list input; union acpi_object in_params[1]; - if (ata_msg_probe(ap)) - ata_dev_dbg(dev, "%s: ix = %d, port#: %d\n", - __func__, dev->devno, ap->port_no); + ata_dev_dbg(dev, "%s: ix = %d, port#: %d\n", + __func__, dev->devno, ap->port_no); /* Give the drive Identify data to the drive via the _SDD method */ /* _SDD: set up input parameters */ diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index aba0c67d1bd6..67f88027680a 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -764,9 +764,6 @@ int ata_build_rw_tf(struct ata_taskfile *tf, struct ata_device *dev, head = track % dev->heads; sect = (u32)block % dev->sectors + 1; - DPRINTK("block %u track %u cyl %u head %u sect %u\n", - (u32)block, track, cyl, head, sect); - /* Check whether the converted CHS can fit. Cylinder: 0-65535 Head: 0-15 @@ -1010,32 +1007,21 @@ unsigned int ata_dev_classify(const struct ata_taskfile *tf) * SEMB signature. This is worked around in * ata_dev_read_id(). */ - if ((tf->lbam == 0) && (tf->lbah == 0)) { - DPRINTK("found ATA device by sig\n"); + if (tf->lbam == 0 && tf->lbah == 0) return ATA_DEV_ATA; - } - if ((tf->lbam == 0x14) && (tf->lbah == 0xeb)) { - DPRINTK("found ATAPI device by sig\n"); + if (tf->lbam == 0x14 && tf->lbah == 0xeb) return ATA_DEV_ATAPI; - } - if ((tf->lbam == 0x69) && (tf->lbah == 0x96)) { - DPRINTK("found PMP device by sig\n"); + if (tf->lbam == 0x69 && tf->lbah == 0x96) return ATA_DEV_PMP; - } - if ((tf->lbam == 0x3c) && (tf->lbah == 0xc3)) { - DPRINTK("found SEMB device by sig (could be ATA device)\n"); + if (tf->lbam == 0x3c && tf->lbah == 0xc3) return ATA_DEV_SEMB; - } - if ((tf->lbam == 0xcd) && (tf->lbah == 0xab)) { - DPRINTK("found ZAC device by sig\n"); + if (tf->lbam == 0xcd && tf->lbah == 0xab) return ATA_DEV_ZAC; - } - DPRINTK("unknown device\n"); return ATA_DEV_UNKNOWN; } EXPORT_SYMBOL_GPL(ata_dev_classify); @@ -1355,6 +1341,7 @@ static int ata_hpa_resize(struct ata_device *dev) /** * ata_dump_id - IDENTIFY DEVICE info debugging output + * @dev: device from which the information is fetched * @id: IDENTIFY DEVICE page to dump * * Dump selected 16-bit words from the given IDENTIFY DEVICE @@ -1364,32 +1351,14 @@ static int ata_hpa_resize(struct ata_device *dev) * caller. */ -static inline void ata_dump_id(const u16 *id) +static inline void ata_dump_id(struct ata_device *dev, const u16 *id) { - DPRINTK("49==0x%04x " - "53==0x%04x " - "63==0x%04x " - "64==0x%04x " - "75==0x%04x \n", - id[49], - id[53], - id[63], - id[64], - id[75]); - DPRINTK("80==0x%04x " - "81==0x%04x " - "82==0x%04x " - "83==0x%04x " - "84==0x%04x \n", - id[80], - id[81], - id[82], - id[83], - id[84]); - DPRINTK("88==0x%04x " - "93==0x%04x\n", - id[88], - id[93]); + ata_dev_dbg(dev, + "49==0x%04x 53==0x%04x 63==0x%04x 64==0x%04x 75==0x%04x\n" + "80==0x%04x 81==0x%04x 82==0x%04x 83==0x%04x 84==0x%04x\n" + "88==0x%04x 93==0x%04x\n", + id[49], id[53], id[63], id[64], id[75], id[80], + id[81], id[82], id[83], id[84], id[88], id[93]); } /** @@ -1602,9 +1571,8 @@ unsigned ata_exec_internal_sg(struct ata_device *dev, else ata_qc_complete(qc); - if (ata_msg_warn(ap)) - ata_dev_warn(dev, "qc timeout (cmd 0x%x)\n", - command); + ata_dev_warn(dev, "qc timeout (cmd 0x%x)\n", + command); } spin_unlock_irqrestore(ap->lock, flags); @@ -1754,7 +1722,7 @@ static u32 ata_pio_mask_no_iordy(const struct ata_device *adev) * this function is wrapped or replaced by the driver */ unsigned int ata_do_dev_read_id(struct ata_device *dev, - struct ata_taskfile *tf, u16 *id) + struct ata_taskfile *tf, __le16 *id) { return ata_exec_internal(dev, tf, NULL, DMA_FROM_DEVICE, id, sizeof(id[0]) * ATA_ID_WORDS, 0); @@ -1794,9 +1762,6 @@ int ata_dev_read_id(struct ata_device *dev, unsigned int *p_class, int may_fallback = 1, tried_spinup = 0; int rc; - if (ata_msg_ctl(ap)) - ata_dev_dbg(dev, "%s: ENTER\n", __func__); - retry: ata_tf_init(dev, &tf); @@ -1830,9 +1795,9 @@ retry: tf.flags |= ATA_TFLAG_POLLING; if (ap->ops->read_id) - err_mask = ap->ops->read_id(dev, &tf, id); + err_mask = ap->ops->read_id(dev, &tf, (__le16 *)id); else - err_mask = ata_do_dev_read_id(dev, &tf, id); + err_mask = ata_do_dev_read_id(dev, &tf, (__le16 *)id); if (err_mask) { if (err_mask & AC_ERR_NODEV_HINT) { @@ -1879,10 +1844,10 @@ retry: } if (dev->horkage & ATA_HORKAGE_DUMP_ID) { - ata_dev_dbg(dev, "dumping IDENTIFY data, " + ata_dev_info(dev, "dumping IDENTIFY data, " "class=%d may_fallback=%d tried_spinup=%d\n", class, may_fallback, tried_spinup); - print_hex_dump(KERN_DEBUG, "", DUMP_PREFIX_OFFSET, + print_hex_dump(KERN_INFO, "", DUMP_PREFIX_OFFSET, 16, 2, id, ATA_ID_WORDS * sizeof(*id), true); } @@ -1966,9 +1931,8 @@ retry: return 0; err_out: - if (ata_msg_warn(ap)) - ata_dev_warn(dev, "failed to IDENTIFY (%s, err_mask=0x%x)\n", - reason, err_mask); + ata_dev_warn(dev, "failed to IDENTIFY (%s, err_mask=0x%x)\n", + reason, err_mask); return rc; } @@ -1996,7 +1960,7 @@ unsigned int ata_read_log_page(struct ata_device *dev, u8 log, unsigned int err_mask; bool dma = false; - DPRINTK("read log page - log 0x%x, page 0x%x\n", log, page); + ata_dev_dbg(dev, "read log page - log 0x%x, page 0x%x\n", log, page); /* * Return error without actually issuing the command on controllers @@ -2390,7 +2354,6 @@ static void ata_dev_config_trusted(struct ata_device *dev) static int ata_dev_config_lba(struct ata_device *dev) { - struct ata_port *ap = dev->link->ap; const u16 *id = dev->id; const char *lba_desc; char ncq_desc[24]; @@ -2412,7 +2375,7 @@ static int ata_dev_config_lba(struct ata_device *dev) ret = ata_dev_config_ncq(dev, ncq_desc, sizeof(ncq_desc)); /* print device info to dmesg */ - if (ata_msg_drv(ap) && ata_dev_print_info(dev)) + if (ata_dev_print_info(dev)) ata_dev_info(dev, "%llu sectors, multi %u: %s %s\n", (unsigned long long)dev->n_sectors, @@ -2423,7 +2386,6 @@ static int ata_dev_config_lba(struct ata_device *dev) static void ata_dev_config_chs(struct ata_device *dev) { - struct ata_port *ap = dev->link->ap; const u16 *id = dev->id; if (ata_id_current_chs_valid(id)) { @@ -2439,7 +2401,7 @@ static void ata_dev_config_chs(struct ata_device *dev) } /* print device info to dmesg */ - if (ata_msg_drv(ap) && ata_dev_print_info(dev)) + if (ata_dev_print_info(dev)) ata_dev_info(dev, "%llu sectors, multi %u, CHS %u/%u/%u\n", (unsigned long long)dev->n_sectors, @@ -2566,14 +2528,11 @@ int ata_dev_configure(struct ata_device *dev) char modelbuf[ATA_ID_PROD_LEN+1]; int rc; - if (!ata_dev_enabled(dev) && ata_msg_info(ap)) { - ata_dev_info(dev, "%s: ENTER/EXIT -- nodev\n", __func__); + if (!ata_dev_enabled(dev)) { + ata_dev_dbg(dev, "no device\n"); return 0; } - if (ata_msg_probe(ap)) - ata_dev_dbg(dev, "%s: ENTER\n", __func__); - /* set horkage */ dev->horkage |= ata_dev_blacklisted(dev); ata_force_horkage(dev); @@ -2621,13 +2580,12 @@ int ata_dev_configure(struct ata_device *dev) return rc; /* print device capabilities */ - if (ata_msg_probe(ap)) - ata_dev_dbg(dev, - "%s: cfg 49:%04x 82:%04x 83:%04x 84:%04x " - "85:%04x 86:%04x 87:%04x 88:%04x\n", - __func__, - id[49], id[82], id[83], id[84], - id[85], id[86], id[87], id[88]); + ata_dev_dbg(dev, + "%s: cfg 49:%04x 82:%04x 83:%04x 84:%04x " + "85:%04x 86:%04x 87:%04x 88:%04x\n", + __func__, + id[49], id[82], id[83], id[84], + id[85], id[86], id[87], id[88]); /* initialize to-be-configured parameters */ dev->flags &= ~ATA_DFLAG_CFG_MASK; @@ -2646,8 +2604,7 @@ int ata_dev_configure(struct ata_device *dev) /* find max transfer mode; for printk only */ xfer_mask = ata_id_xfermask(id); - if (ata_msg_probe(ap)) - ata_dump_id(id); + ata_dump_id(dev, id); /* SCSI only uses 4-char revisions, dump full 8 chars from ATA */ ata_id_c_string(dev->id, fwrevbuf, ATA_ID_FW_REV, @@ -2685,7 +2642,7 @@ int ata_dev_configure(struct ata_device *dev) } /* print device info to dmesg */ - if (ata_msg_drv(ap) && print_info) + if (print_info) ata_dev_info(dev, "%s: %s, %s, max %s\n", revbuf, modelbuf, fwrevbuf, ata_mode_string(xfer_mask)); @@ -2705,7 +2662,7 @@ int ata_dev_configure(struct ata_device *dev) ata_dev_config_cpr(dev); dev->cdb_len = 32; - if (ata_msg_drv(ap) && print_info) + if (print_info) ata_dev_print_features(dev); } @@ -2718,8 +2675,7 @@ int ata_dev_configure(struct ata_device *dev) rc = atapi_cdb_len(id); if ((rc < 12) || (rc > ATAPI_CDB_LEN)) { - if (ata_msg_warn(ap)) - ata_dev_warn(dev, "unsupported CDB len\n"); + ata_dev_warn(dev, "unsupported CDB len %d\n", rc); rc = -EINVAL; goto err_out_nosup; } @@ -2763,7 +2719,7 @@ int ata_dev_configure(struct ata_device *dev) } /* print device info to dmesg */ - if (ata_msg_drv(ap) && print_info) + if (print_info) ata_dev_info(dev, "ATAPI: %s, %s, max %s%s%s%s\n", modelbuf, fwrevbuf, @@ -2780,7 +2736,7 @@ int ata_dev_configure(struct ata_device *dev) /* Limit PATA drive on SATA cable bridge transfers to udma5, 200 sectors */ if (ata_dev_knobble(dev)) { - if (ata_msg_drv(ap) && print_info) + if (print_info) ata_dev_info(dev, "applying bridge limits\n"); dev->udma_mask &= ATA_UDMA5; dev->max_sectors = ATA_MAX_SECTORS; @@ -2829,8 +2785,6 @@ int ata_dev_configure(struct ata_device *dev) return 0; err_out_nosup: - if (ata_msg_probe(ap)) - ata_dev_dbg(dev, "%s: EXIT, err\n", __func__); return rc; } @@ -3373,8 +3327,8 @@ static int ata_dev_set_mode(struct ata_device *dev) dev_err_whine = " (device error ignored)"; } - DPRINTK("xfer_shift=%u, xfer_mode=0x%x\n", - dev->xfer_shift, (int)dev->xfer_mode); + ata_dev_dbg(dev, "xfer_shift=%u, xfer_mode=0x%x\n", + dev->xfer_shift, (int)dev->xfer_mode); if (!(ehc->i.flags & ATA_EHI_QUIET) || ehc->i.flags & ATA_EHI_DID_HARDRESET) @@ -3688,16 +3642,12 @@ void ata_std_postreset(struct ata_link *link, unsigned int *classes) { u32 serror; - DPRINTK("ENTER\n"); - /* reset complete, clear SError */ if (!sata_scr_read(link, SCR_ERROR, &serror)) sata_scr_write(link, SCR_ERROR, serror); /* print link status */ sata_print_link_status(link); - - DPRINTK("EXIT\n"); } EXPORT_SYMBOL_GPL(ata_std_postreset); @@ -4324,7 +4274,7 @@ static unsigned int ata_dev_set_xfermode(struct ata_device *dev) unsigned int err_mask; /* set up set-features taskfile */ - DPRINTK("set features - xfer mode\n"); + ata_dev_dbg(dev, "set features - xfer mode\n"); /* Some controllers and ATAPI devices show flaky interrupt * behavior after setting xfer mode. Use polling instead. @@ -4346,7 +4296,6 @@ static unsigned int ata_dev_set_xfermode(struct ata_device *dev) /* On some disks, this command causes spin-up, so we need longer timeout */ err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 15000); - DPRINTK("EXIT, err_mask=%x\n", err_mask); return err_mask; } @@ -4372,7 +4321,7 @@ unsigned int ata_dev_set_feature(struct ata_device *dev, u8 enable, u8 feature) unsigned long timeout = 0; /* set up set-features taskfile */ - DPRINTK("set features - SATA features\n"); + ata_dev_dbg(dev, "set features - SATA features\n"); ata_tf_init(dev, &tf); tf.command = ATA_CMD_SET_FEATURES; @@ -4386,7 +4335,6 @@ unsigned int ata_dev_set_feature(struct ata_device *dev, u8 enable, u8 feature) ata_probe_timeout * 1000 : SETFEATURES_SPINUP_TIMEOUT; err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, timeout); - DPRINTK("EXIT, err_mask=%x\n", err_mask); return err_mask; } EXPORT_SYMBOL_GPL(ata_dev_set_feature); @@ -4414,7 +4362,7 @@ static unsigned int ata_dev_init_params(struct ata_device *dev, return AC_ERR_INVALID; /* set up init dev params taskfile */ - DPRINTK("init dev params \n"); + ata_dev_dbg(dev, "init dev params \n"); ata_tf_init(dev, &tf); tf.command = ATA_CMD_INIT_DEV_PARAMS; @@ -4430,7 +4378,6 @@ static unsigned int ata_dev_init_params(struct ata_device *dev, if (err_mask == AC_ERR_DEV && (tf.feature & ATA_ABORTED)) err_mask = 0; - DPRINTK("EXIT, err_mask=%x\n", err_mask); return err_mask; } @@ -4542,8 +4489,6 @@ static void ata_sg_clean(struct ata_queued_cmd *qc) WARN_ON_ONCE(sg == NULL); - VPRINTK("unmapping %u sg elements\n", qc->n_elem); - if (qc->n_elem) dma_unmap_sg(ap->dev, sg, qc->orig_n_elem, dir); @@ -4569,13 +4514,10 @@ static int ata_sg_setup(struct ata_queued_cmd *qc) struct ata_port *ap = qc->ap; unsigned int n_elem; - VPRINTK("ENTER, ata%u\n", ap->print_id); - n_elem = dma_map_sg(ap->dev, qc->sg, qc->n_elem, qc->dma_dir); if (n_elem < 1) return -1; - VPRINTK("%d sg elements mapped\n", n_elem); qc->orig_n_elem = qc->n_elem; qc->n_elem = n_elem; qc->flags |= ATA_QCFLAG_DMAMAP; @@ -4930,6 +4872,7 @@ void ata_qc_issue(struct ata_queued_cmd *qc) return; } + trace_ata_qc_prep(qc); qc->err_mask |= ap->ops->qc_prep(qc); if (unlikely(qc->err_mask)) goto err; @@ -5375,8 +5318,6 @@ struct ata_port *ata_port_alloc(struct ata_host *host) { struct ata_port *ap; - DPRINTK("ENTER\n"); - ap = kzalloc(sizeof(*ap), GFP_KERNEL); if (!ap) return NULL; @@ -5388,15 +5329,6 @@ struct ata_port *ata_port_alloc(struct ata_host *host) ap->host = host; ap->dev = host->dev; -#if defined(ATA_VERBOSE_DEBUG) - /* turn on all debugging levels */ - ap->msg_enable = 0x00FF; -#elif defined(ATA_DEBUG) - ap->msg_enable = ATA_MSG_DRV | ATA_MSG_INFO | ATA_MSG_CTL | ATA_MSG_WARN | ATA_MSG_ERR; -#else - ap->msg_enable = ATA_MSG_DRV | ATA_MSG_ERR | ATA_MSG_WARN; -#endif - mutex_init(&ap->scsi_scan_mutex); INIT_DELAYED_WORK(&ap->hotplug_task, ata_scsi_hotplug); INIT_WORK(&ap->scsi_rescan_task, ata_scsi_dev_rescan); @@ -5493,8 +5425,6 @@ struct ata_host *ata_host_alloc(struct device *dev, int max_ports) int i; void *dr; - DPRINTK("ENTER\n"); - /* alloc a container for our list of ATA ports (buses) */ sz = sizeof(struct ata_host) + (max_ports + 1) * sizeof(void *); host = kzalloc(sz, GFP_KERNEL); @@ -5784,9 +5714,7 @@ int ata_port_probe(struct ata_port *ap) __ata_port_probe(ap); ata_port_wait_eh(ap); } else { - DPRINTK("ata%u: bus probe begin\n", ap->print_id); rc = ata_bus_probe(ap); - DPRINTK("ata%u: bus probe end\n", ap->print_id); } return rc; } @@ -6553,69 +6481,14 @@ const struct ata_port_info ata_dummy_port_info = { }; EXPORT_SYMBOL_GPL(ata_dummy_port_info); -/* - * Utility print functions - */ -void ata_port_printk(const struct ata_port *ap, const char *level, - const char *fmt, ...) -{ - struct va_format vaf; - va_list args; - - va_start(args, fmt); - - vaf.fmt = fmt; - vaf.va = &args; - - printk("%sata%u: %pV", level, ap->print_id, &vaf); - - va_end(args); -} -EXPORT_SYMBOL(ata_port_printk); - -void ata_link_printk(const struct ata_link *link, const char *level, - const char *fmt, ...) -{ - struct va_format vaf; - va_list args; - - va_start(args, fmt); - - vaf.fmt = fmt; - vaf.va = &args; - - if (sata_pmp_attached(link->ap) || link->ap->slave_link) - printk("%sata%u.%02u: %pV", - level, link->ap->print_id, link->pmp, &vaf); - else - printk("%sata%u: %pV", - level, link->ap->print_id, &vaf); - - va_end(args); -} -EXPORT_SYMBOL(ata_link_printk); - -void ata_dev_printk(const struct ata_device *dev, const char *level, - const char *fmt, ...) -{ - struct va_format vaf; - va_list args; - - va_start(args, fmt); - - vaf.fmt = fmt; - vaf.va = &args; - - printk("%sata%u.%02u: %pV", - level, dev->link->ap->print_id, dev->link->pmp + dev->devno, - &vaf); - - va_end(args); -} -EXPORT_SYMBOL(ata_dev_printk); - void ata_print_version(const struct device *dev, const char *version) { dev_printk(KERN_DEBUG, dev, "version %s\n", version); } EXPORT_SYMBOL(ata_print_version); + +EXPORT_TRACEPOINT_SYMBOL_GPL(ata_tf_load); +EXPORT_TRACEPOINT_SYMBOL_GPL(ata_exec_command); +EXPORT_TRACEPOINT_SYMBOL_GPL(ata_bmdma_setup); +EXPORT_TRACEPOINT_SYMBOL_GPL(ata_bmdma_start); +EXPORT_TRACEPOINT_SYMBOL_GPL(ata_bmdma_status); diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index 1d4a6f1e88cd..7951fd946bf9 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -533,8 +533,6 @@ void ata_scsi_error(struct Scsi_Host *host) unsigned long flags; LIST_HEAD(eh_work_q); - DPRINTK("ENTER\n"); - spin_lock_irqsave(host->host_lock, flags); list_splice_init(&host->eh_cmd_q, &eh_work_q); spin_unlock_irqrestore(host->host_lock, flags); @@ -548,7 +546,6 @@ void ata_scsi_error(struct Scsi_Host *host) /* finish or retry handled scmd's and clean up */ WARN_ON(!list_empty(&eh_work_q)); - DPRINTK("EXIT\n"); } /** @@ -940,7 +937,7 @@ void ata_std_sched_eh(struct ata_port *ap) ata_eh_set_pending(ap, 1); scsi_schedule_eh(ap->scsi_host); - DPRINTK("port EH scheduled\n"); + trace_ata_std_sched_eh(ap); } EXPORT_SYMBOL_GPL(ata_std_sched_eh); @@ -1070,7 +1067,7 @@ static void __ata_port_freeze(struct ata_port *ap) ap->pflags |= ATA_PFLAG_FROZEN; - DPRINTK("ata%u port frozen\n", ap->print_id); + trace_ata_port_freeze(ap); } /** @@ -1147,7 +1144,7 @@ void ata_eh_thaw_port(struct ata_port *ap) spin_unlock_irqrestore(ap->lock, flags); - DPRINTK("ata%u port thawed\n", ap->print_id); + trace_ata_port_thaw(ap); } static void ata_eh_scsidone(struct scsi_cmnd *scmd) @@ -1217,8 +1214,7 @@ void ata_dev_disable(struct ata_device *dev) if (!ata_dev_enabled(dev)) return; - if (ata_msg_drv(dev->link->ap)) - ata_dev_warn(dev, "disabled\n"); + ata_dev_warn(dev, "disable device\n"); ata_acpi_on_disable(dev); ata_down_xfermask_limit(dev, ATA_DNXFER_FORCE_PIO0 | ATA_DNXFER_QUIET); dev->class++; @@ -1287,6 +1283,8 @@ void ata_eh_about_to_do(struct ata_link *link, struct ata_device *dev, struct ata_eh_context *ehc = &link->eh_context; unsigned long flags; + trace_ata_eh_about_to_do(link, dev ? dev->devno : 0, action); + spin_lock_irqsave(ap->lock, flags); ata_eh_clear_action(link, dev, ehi, action); @@ -1317,6 +1315,8 @@ void ata_eh_done(struct ata_link *link, struct ata_device *dev, { struct ata_eh_context *ehc = &link->eh_context; + trace_ata_eh_done(link, dev ? dev->devno : 0, action); + ata_eh_clear_action(link, dev, &ehc->i, action); } @@ -1421,8 +1421,6 @@ static void ata_eh_request_sense(struct ata_queued_cmd *qc, return; } - DPRINTK("ATA request sense\n"); - ata_tf_init(dev, &tf); tf.flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE; tf.flags |= ATA_TFLAG_LBA | ATA_TFLAG_LBA48; @@ -1463,8 +1461,6 @@ unsigned int atapi_eh_request_sense(struct ata_device *dev, struct ata_port *ap = dev->link->ap; struct ata_taskfile tf; - DPRINTK("ATAPI request sense\n"); - memset(sense_buf, 0, SCSI_SENSE_BUFFERSIZE); /* initialize sense_buf with the error register, @@ -1928,8 +1924,6 @@ static void ata_eh_link_autopsy(struct ata_link *link) u32 serror; int rc; - DPRINTK("ENTER\n"); - if (ehc->i.flags & ATA_EHI_NO_AUTOPSY) return; @@ -2036,7 +2030,6 @@ static void ata_eh_link_autopsy(struct ata_link *link) ehc->i.action |= ata_eh_speed_down(dev, eflags, all_err_mask); trace_ata_eh_link_autopsy(dev, ehc->i.action, all_err_mask); } - DPRINTK("EXIT\n"); } /** @@ -2086,16 +2079,15 @@ void ata_eh_autopsy(struct ata_port *ap) } /** - * ata_get_cmd_descript - get description for ATA command - * @command: ATA command code to get description for + * ata_get_cmd_name - get name for ATA command + * @command: ATA command code to get name for * - * Return a textual description of the given command, or NULL if the - * command is not known. + * Return a textual name of the given command or "unknown" * * LOCKING: * None */ -const char *ata_get_cmd_descript(u8 command) +const char *ata_get_cmd_name(u8 command) { #ifdef CONFIG_ATA_VERBOSE_ERROR static const struct @@ -2203,9 +2195,9 @@ const char *ata_get_cmd_descript(u8 command) return cmd_descr[i].text; #endif - return NULL; + return "unknown"; } -EXPORT_SYMBOL_GPL(ata_get_cmd_descript); +EXPORT_SYMBOL_GPL(ata_get_cmd_name); /** * ata_eh_link_report - report error handling to user @@ -2354,12 +2346,9 @@ static void ata_eh_link_report(struct ata_link *link) } __scsi_format_command(cdb_buf, sizeof(cdb_buf), cdb, cdb_len); - } else { - const char *descr = ata_get_cmd_descript(cmd->command); - if (descr) - ata_dev_err(qc->dev, "failed command: %s\n", - descr); - } + } else + ata_dev_err(qc->dev, "failed command: %s\n", + ata_get_cmd_name(cmd->command)); ata_dev_err(qc->dev, "cmd %02x/%02x:%02x:%02x:%02x:%02x/%02x:%02x:%02x:%02x:%02x/%02x " @@ -2596,12 +2585,19 @@ int ata_eh_reset(struct ata_link *link, int classify, /* mark that this EH session started with reset */ ehc->last_reset = jiffies; - if (reset == hardreset) + if (reset == hardreset) { ehc->i.flags |= ATA_EHI_DID_HARDRESET; - else + trace_ata_link_hardreset_begin(link, classes, deadline); + } else { ehc->i.flags |= ATA_EHI_DID_SOFTRESET; + trace_ata_link_softreset_begin(link, classes, deadline); + } rc = ata_do_reset(link, reset, classes, deadline, true); + if (reset == hardreset) + trace_ata_link_hardreset_end(link, classes, rc); + else + trace_ata_link_softreset_end(link, classes, rc); if (rc && rc != -EAGAIN) { failed_link = link; goto fail; @@ -2615,8 +2611,11 @@ int ata_eh_reset(struct ata_link *link, int classify, ata_link_info(slave, "hard resetting link\n"); ata_eh_about_to_do(slave, NULL, ATA_EH_RESET); + trace_ata_slave_hardreset_begin(slave, classes, + deadline); tmp = ata_do_reset(slave, reset, classes, deadline, false); + trace_ata_slave_hardreset_end(slave, classes, tmp); switch (tmp) { case -EAGAIN: rc = -EAGAIN; @@ -2644,7 +2643,9 @@ int ata_eh_reset(struct ata_link *link, int classify, } ata_eh_about_to_do(link, NULL, ATA_EH_RESET); + trace_ata_link_softreset_begin(link, classes, deadline); rc = ata_do_reset(link, reset, classes, deadline, true); + trace_ata_link_softreset_end(link, classes, rc); if (rc) { failed_link = link; goto fail; @@ -2698,8 +2699,11 @@ int ata_eh_reset(struct ata_link *link, int classify, */ if (postreset) { postreset(link, classes); - if (slave) + trace_ata_link_postreset(link, classes, rc); + if (slave) { postreset(slave, classes); + trace_ata_slave_postreset(slave, classes, rc); + } } /* @@ -2921,8 +2925,6 @@ static int ata_eh_revalidate_and_attach(struct ata_link *link, unsigned long flags; int rc = 0; - DPRINTK("ENTER\n"); - /* For PATA drive side cable detection to work, IDENTIFY must * be done backwards such that PDIAG- is released by the slave * device before the master device is identified. @@ -3036,7 +3038,6 @@ static int ata_eh_revalidate_and_attach(struct ata_link *link, err: *r_failed_dev = dev; - DPRINTK("EXIT rc=%d\n", rc); return rc; } @@ -3551,8 +3552,6 @@ int ata_eh_recover(struct ata_port *ap, ata_prereset_fn_t prereset, int rc, nr_fails; unsigned long flags, deadline; - DPRINTK("ENTER\n"); - /* prep for recovery */ ata_for_each_link(link, ap, EDGE) { struct ata_eh_context *ehc = &link->eh_context; @@ -3760,7 +3759,6 @@ int ata_eh_recover(struct ata_port *ap, ata_prereset_fn_t prereset, if (rc && r_failed_link) *r_failed_link = link; - DPRINTK("EXIT, rc=%d\n", rc); return rc; } diff --git a/drivers/ata/libata-pmp.c b/drivers/ata/libata-pmp.c index ba7be3f38617..e2e9cbd405fa 100644 --- a/drivers/ata/libata-pmp.c +++ b/drivers/ata/libata-pmp.c @@ -652,8 +652,6 @@ static int sata_pmp_revalidate(struct ata_device *dev, unsigned int new_class) u32 *gscr = (void *)ap->sector_buf; int rc; - DPRINTK("ENTER\n"); - ata_eh_about_to_do(link, NULL, ATA_EH_REVALIDATE); if (!ata_dev_enabled(dev)) { @@ -686,12 +684,10 @@ static int sata_pmp_revalidate(struct ata_device *dev, unsigned int new_class) ata_eh_done(link, NULL, ATA_EH_REVALIDATE); - DPRINTK("EXIT, rc=0\n"); return 0; fail: ata_dev_err(dev, "PMP revalidation failed (errno=%d)\n", rc); - DPRINTK("EXIT, rc=%d\n", rc); return rc; } @@ -759,8 +755,6 @@ static int sata_pmp_eh_recover_pmp(struct ata_port *ap, int detach = 0, rc = 0; int reval_failed = 0; - DPRINTK("ENTER\n"); - if (dev->flags & ATA_DFLAG_DETACH) { detach = 1; rc = -ENODEV; @@ -828,7 +822,6 @@ static int sata_pmp_eh_recover_pmp(struct ata_port *ap, /* okay, PMP resurrected */ ehc->i.flags = 0; - DPRINTK("EXIT, rc=0\n"); return 0; fail: @@ -838,7 +831,6 @@ static int sata_pmp_eh_recover_pmp(struct ata_port *ap, else ata_dev_disable(dev); - DPRINTK("EXIT, rc=%d\n", rc); return rc; } diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c index b9c77885b872..071158c0c44c 100644 --- a/drivers/ata/libata-sata.c +++ b/drivers/ata/libata-sata.c @@ -317,7 +317,7 @@ int sata_link_resume(struct ata_link *link, const unsigned long *params, * immediately after resuming. Delay 200ms before * debouncing. */ - if (!(link->flags & ATA_LFLAG_NO_DB_DELAY)) + if (!(link->flags & ATA_LFLAG_NO_DEBOUNCE_DELAY)) ata_msleep(link->ap, 200); /* is SControl restored correctly? */ @@ -533,8 +533,6 @@ int sata_link_hardreset(struct ata_link *link, const unsigned long *timing, u32 scontrol; int rc; - DPRINTK("ENTER\n"); - if (online) *online = false; @@ -610,7 +608,6 @@ int sata_link_hardreset(struct ata_link *link, const unsigned long *timing, *online = false; ata_link_err(link, "COMRESET failed (errno=%d)\n", rc); } - DPRINTK("EXIT, rc=%d\n", rc); return rc; } EXPORT_SYMBOL_GPL(sata_link_hardreset); @@ -876,7 +873,7 @@ static ssize_t ata_ncq_prio_enable_show(struct device *device, ncq_prio_enable = dev->flags & ATA_DFLAG_NCQ_PRIO_ENABLE; spin_unlock_irq(ap->lock); - return rc ? rc : snprintf(buf, 20, "%u\n", ncq_prio_enable); + return rc ? rc : sysfs_emit(buf, "%u\n", ncq_prio_enable); } static ssize_t ata_ncq_prio_enable_store(struct device *device, @@ -972,7 +969,7 @@ ata_scsi_em_message_type_show(struct device *dev, struct device_attribute *attr, struct Scsi_Host *shost = class_to_shost(dev); struct ata_port *ap = ata_shost_to_port(shost); - return snprintf(buf, 23, "%d\n", ap->em_message_type); + return sysfs_emit(buf, "%d\n", ap->em_message_type); } DEVICE_ATTR(em_message_type, S_IRUGO, ata_scsi_em_message_type_show, NULL); @@ -1261,8 +1258,6 @@ int ata_sas_queuecmd(struct scsi_cmnd *cmd, struct ata_port *ap) { int rc = 0; - ata_scsi_dump_cdb(ap, cmd); - if (likely(ata_dev_enabled(ap->link.device))) rc = __ata_scsi_queuecmd(cmd, ap->link.device); else { diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 313e9475507b..ed8be585a98f 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -121,7 +121,7 @@ static ssize_t ata_scsi_park_show(struct device *device, unlock: spin_unlock_irq(ap->lock); - return rc ? rc : snprintf(buf, 20, "%u\n", msecs); + return rc ? rc : sysfs_emit(buf, "%u\n", msecs); } static ssize_t ata_scsi_park_store(struct device *device, @@ -668,7 +668,7 @@ static void ata_qc_set_pc_nbytes(struct ata_queued_cmd *qc) /** * ata_dump_status - user friendly display of error info - * @id: id of the port in question + * @ap: the port in question * @tf: ptr to filled out taskfile * * Decode and dump the ATA error/status registers for the user so @@ -678,37 +678,32 @@ static void ata_qc_set_pc_nbytes(struct ata_queued_cmd *qc) * LOCKING: * inherited from caller */ -static void ata_dump_status(unsigned id, struct ata_taskfile *tf) +static void ata_dump_status(struct ata_port *ap, struct ata_taskfile *tf) { u8 stat = tf->command, err = tf->feature; - pr_warn("ata%u: status=0x%02x { ", id, stat); if (stat & ATA_BUSY) { - pr_cont("Busy }\n"); /* Data is not valid in this case */ + ata_port_warn(ap, "status=0x%02x {Busy} ", stat); } else { - if (stat & ATA_DRDY) pr_cont("DriveReady "); - if (stat & ATA_DF) pr_cont("DeviceFault "); - if (stat & ATA_DSC) pr_cont("SeekComplete "); - if (stat & ATA_DRQ) pr_cont("DataRequest "); - if (stat & ATA_CORR) pr_cont("CorrectedError "); - if (stat & ATA_SENSE) pr_cont("Sense "); - if (stat & ATA_ERR) pr_cont("Error "); - pr_cont("}\n"); - - if (err) { - pr_warn("ata%u: error=0x%02x { ", id, err); - if (err & ATA_ABORTED) pr_cont("DriveStatusError "); - if (err & ATA_ICRC) { - if (err & ATA_ABORTED) - pr_cont("BadCRC "); - else pr_cont("Sector "); - } - if (err & ATA_UNC) pr_cont("UncorrectableError "); - if (err & ATA_IDNF) pr_cont("SectorIdNotFound "); - if (err & ATA_TRK0NF) pr_cont("TrackZeroNotFound "); - if (err & ATA_AMNF) pr_cont("AddrMarkNotFound "); - pr_cont("}\n"); - } + ata_port_warn(ap, "status=0x%02x { %s%s%s%s%s%s%s} ", stat, + stat & ATA_DRDY ? "DriveReady " : "", + stat & ATA_DF ? "DeviceFault " : "", + stat & ATA_DSC ? "SeekComplete " : "", + stat & ATA_DRQ ? "DataRequest " : "", + stat & ATA_CORR ? "CorrectedError " : "", + stat & ATA_SENSE ? "Sense " : "", + stat & ATA_ERR ? "Error " : ""); + if (err) + ata_port_warn(ap, "error=0x%02x {%s%s%s%s%s%s", err, + err & ATA_ABORTED ? + "DriveStatusError " : "", + err & ATA_ICRC ? + (err & ATA_ABORTED ? + "BadCRC " : "Sector ") : "", + err & ATA_UNC ? "UncorrectableError " : "", + err & ATA_IDNF ? "SectorIdNotFound " : "", + err & ATA_TRK0NF ? "TrackZeroNotFound " : "", + err & ATA_AMNF ? "AddrMarkNotFound " : ""); } } @@ -1299,8 +1294,6 @@ static void scsi_6_lba_len(const u8 *cdb, u64 *plba, u32 *plen) u64 lba = 0; u32 len; - VPRINTK("six-byte command\n"); - lba |= ((u64)(cdb[1] & 0x1f)) << 16; lba |= ((u64)cdb[2]) << 8; lba |= ((u64)cdb[3]); @@ -1326,8 +1319,6 @@ static void scsi_10_lba_len(const u8 *cdb, u64 *plba, u32 *plen) u64 lba = 0; u32 len = 0; - VPRINTK("ten-byte command\n"); - lba |= ((u64)cdb[2]) << 24; lba |= ((u64)cdb[3]) << 16; lba |= ((u64)cdb[4]) << 8; @@ -1355,8 +1346,6 @@ static void scsi_16_lba_len(const u8 *cdb, u64 *plba, u32 *plen) u64 lba = 0; u32 len = 0; - VPRINTK("sixteen-byte command\n"); - lba |= ((u64)cdb[2]) << 56; lba |= ((u64)cdb[3]) << 48; lba |= ((u64)cdb[4]) << 40; @@ -1469,9 +1458,6 @@ static unsigned int ata_scsi_verify_xlat(struct ata_queued_cmd *qc) head = track % dev->heads; sect = (u32)block % dev->sectors + 1; - DPRINTK("block %u track %u cyl %u head %u sect %u\n", - (u32)block, track, cyl, head, sect); - /* Check whether the converted CHS can fit. Cylinder: 0-65535 Head: 0-15 @@ -1594,7 +1580,6 @@ static unsigned int ata_scsi_rw_xlat(struct ata_queued_cmd *qc) goto invalid_fld; break; default: - DPRINTK("no-byte command\n"); fp = 0; goto invalid_fld; } @@ -1672,7 +1657,7 @@ static void ata_scsi_qc_complete(struct ata_queued_cmd *qc) cmd->result = SAM_STAT_GOOD; if (need_sense && !ap->ops->error_handler) - ata_dump_status(ap->print_id, &qc->result_tf); + ata_dump_status(ap, &qc->result_tf); ata_qc_done(qc); } @@ -1710,8 +1695,6 @@ static int ata_scsi_translate(struct ata_device *dev, struct scsi_cmnd *cmd, struct ata_queued_cmd *qc; int rc; - VPRINTK("ENTER\n"); - qc = ata_scsi_qc_new(dev, cmd); if (!qc) goto err_mem; @@ -1742,13 +1725,11 @@ static int ata_scsi_translate(struct ata_device *dev, struct scsi_cmnd *cmd, /* select device, send command to hardware */ ata_qc_issue(qc); - VPRINTK("EXIT\n"); return 0; early_finish: ata_qc_free(qc); scsi_done(cmd); - DPRINTK("EXIT - early finish (good or error)\n"); return 0; err_did: @@ -1756,12 +1737,10 @@ err_did: cmd->result = (DID_ERROR << 16); scsi_done(cmd); err_mem: - DPRINTK("EXIT - internal\n"); return 0; defer: ata_qc_free(qc); - DPRINTK("EXIT - defer\n"); if (rc == ATA_DEFER_LINK) return SCSI_MLQUEUE_DEVICE_BUSY; else @@ -1858,8 +1837,6 @@ static unsigned int ata_scsiop_inq_std(struct ata_scsi_args *args, u8 *rbuf) 2 }; - VPRINTK("ENTER\n"); - /* set scsi removable (RMB) bit per ata bit, or if the * AHCI port says it's external (Hotplug-capable, eSATA). */ @@ -2294,8 +2271,6 @@ static unsigned int ata_scsiop_mode_sense(struct ata_scsi_args *args, u8 *rbuf) u8 dpofua, bp = 0xff; u16 fp; - VPRINTK("ENTER\n"); - six_byte = (scsicmd[0] == MODE_SENSE); ebd = !(scsicmd[1] & 0x8); /* dbd bit inverted == edb */ /* @@ -2413,8 +2388,6 @@ static unsigned int ata_scsiop_read_cap(struct ata_scsi_args *args, u8 *rbuf) log2_per_phys = ata_id_log2_per_physical_sector(dev->id); lowest_aligned = ata_id_logical_sector_offset(dev->id, log2_per_phys); - VPRINTK("ENTER\n"); - if (args->cmd->cmnd[0] == READ_CAPACITY) { if (last_lba >= 0xffffffffULL) last_lba = 0xffffffff; @@ -2481,7 +2454,6 @@ static unsigned int ata_scsiop_read_cap(struct ata_scsi_args *args, u8 *rbuf) */ static unsigned int ata_scsiop_report_luns(struct ata_scsi_args *args, u8 *rbuf) { - VPRINTK("ENTER\n"); rbuf[3] = 8; /* just one lun, LUN 0, size 8 bytes */ return 0; @@ -2512,8 +2484,6 @@ static void atapi_request_sense(struct ata_queued_cmd *qc) struct ata_port *ap = qc->ap; struct scsi_cmnd *cmd = qc->scsicmd; - DPRINTK("ATAPI request sense\n"); - memset(cmd->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE); #ifdef CONFIG_ATA_SFF @@ -2552,8 +2522,6 @@ static void atapi_request_sense(struct ata_queued_cmd *qc) qc->complete_fn = atapi_sense_complete; ata_qc_issue(qc); - - DPRINTK("EXIT\n"); } /* @@ -2581,8 +2549,6 @@ static void atapi_qc_complete(struct ata_queued_cmd *qc) struct scsi_cmnd *cmd = qc->scsicmd; unsigned int err_mask = qc->err_mask; - VPRINTK("ENTER, err_mask 0x%X\n", err_mask); - /* handle completion from new EH */ if (unlikely(qc->ap->ops->error_handler && (err_mask || qc->flags & ATA_QCFLAG_SENSE_VALID))) { @@ -2663,7 +2629,6 @@ static unsigned int atapi_xlat(struct ata_queued_cmd *qc) qc->tf.flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE; if (scmd->sc_data_direction == DMA_TO_DEVICE) { qc->tf.flags |= ATA_TFLAG_WRITE; - DPRINTK("direction: write\n"); } qc->tf.command = ATA_CMD_PACKET; @@ -3591,10 +3556,7 @@ static int ata_mselect_caching(struct ata_queued_cmd *qc, */ if (len != CACHE_MPAGE_LEN - 2) { - if (len < CACHE_MPAGE_LEN - 2) - *fp = len; - else - *fp = CACHE_MPAGE_LEN - 2; + *fp = min(len, CACHE_MPAGE_LEN - 2); return -EINVAL; } @@ -3647,10 +3609,7 @@ static int ata_mselect_control(struct ata_queued_cmd *qc, */ if (len != CONTROL_MPAGE_LEN - 2) { - if (len < CONTROL_MPAGE_LEN - 2) - *fp = len; - else - *fp = CONTROL_MPAGE_LEN - 2; + *fp = min(len, CONTROL_MPAGE_LEN - 2); return -EINVAL; } @@ -3698,8 +3657,6 @@ static unsigned int ata_scsi_mode_select_xlat(struct ata_queued_cmd *qc) u8 buffer[64]; const u8 *p = buffer; - VPRINTK("ENTER\n"); - six_byte = (cdb[0] == MODE_SELECT); if (six_byte) { if (scmd->cmd_len < 5) { @@ -3997,70 +3954,45 @@ static inline ata_xlat_func_t ata_get_xlat_func(struct ata_device *dev, u8 cmd) return NULL; } -/** - * ata_scsi_dump_cdb - dump SCSI command contents to dmesg - * @ap: ATA port to which the command was being sent - * @cmd: SCSI command to dump - * - * Prints the contents of a SCSI command via printk(). - */ - -void ata_scsi_dump_cdb(struct ata_port *ap, struct scsi_cmnd *cmd) -{ -#ifdef ATA_VERBOSE_DEBUG - struct scsi_device *scsidev = cmd->device; - - VPRINTK("CDB (%u:%d,%d,%lld) %9ph\n", - ap->print_id, - scsidev->channel, scsidev->id, scsidev->lun, - cmd->cmnd); -#endif -} - int __ata_scsi_queuecmd(struct scsi_cmnd *scmd, struct ata_device *dev) { u8 scsi_op = scmd->cmnd[0]; ata_xlat_func_t xlat_func; - int rc = 0; + + if (unlikely(!scmd->cmd_len)) + goto bad_cdb_len; if (dev->class == ATA_DEV_ATA || dev->class == ATA_DEV_ZAC) { - if (unlikely(!scmd->cmd_len || scmd->cmd_len > dev->cdb_len)) + if (unlikely(scmd->cmd_len > dev->cdb_len)) goto bad_cdb_len; xlat_func = ata_get_xlat_func(dev, scsi_op); - } else { - if (unlikely(!scmd->cmd_len)) + } else if (likely((scsi_op != ATA_16) || !atapi_passthru16)) { + /* relay SCSI command to ATAPI device */ + int len = COMMAND_SIZE(scsi_op); + + if (unlikely(len > scmd->cmd_len || + len > dev->cdb_len || + scmd->cmd_len > ATAPI_CDB_LEN)) goto bad_cdb_len; - xlat_func = NULL; - if (likely((scsi_op != ATA_16) || !atapi_passthru16)) { - /* relay SCSI command to ATAPI device */ - int len = COMMAND_SIZE(scsi_op); - if (unlikely(len > scmd->cmd_len || - len > dev->cdb_len || - scmd->cmd_len > ATAPI_CDB_LEN)) - goto bad_cdb_len; + xlat_func = atapi_xlat; + } else { + /* ATA_16 passthru, treat as an ATA command */ + if (unlikely(scmd->cmd_len > 16)) + goto bad_cdb_len; - xlat_func = atapi_xlat; - } else { - /* ATA_16 passthru, treat as an ATA command */ - if (unlikely(scmd->cmd_len > 16)) - goto bad_cdb_len; - - xlat_func = ata_get_xlat_func(dev, scsi_op); - } + xlat_func = ata_get_xlat_func(dev, scsi_op); } if (xlat_func) - rc = ata_scsi_translate(dev, scmd, xlat_func); - else - ata_scsi_simulate(dev, scmd); + return ata_scsi_translate(dev, scmd, xlat_func); - return rc; + ata_scsi_simulate(dev, scmd); + + return 0; bad_cdb_len: - DPRINTK("bad CDB len=%u, scsi_op=0x%02x, max=%u\n", - scmd->cmd_len, scsi_op, dev->cdb_len); scmd->result = DID_ERROR << 16; scsi_done(scmd); return 0; @@ -4097,8 +4029,6 @@ int ata_scsi_queuecmd(struct Scsi_Host *shost, struct scsi_cmnd *cmd) spin_lock_irqsave(ap->lock, irq_flags); - ata_scsi_dump_cdb(ap, cmd); - dev = ata_scsi_find_dev(ap, scsidev); if (likely(dev)) rc = __ata_scsi_queuecmd(cmd, dev); @@ -4531,12 +4461,9 @@ void ata_scsi_hotplug(struct work_struct *work) container_of(work, struct ata_port, hotplug_task.work); int i; - if (ap->pflags & ATA_PFLAG_UNLOADING) { - DPRINTK("ENTER/EXIT - unloading\n"); + if (ap->pflags & ATA_PFLAG_UNLOADING) return; - } - DPRINTK("ENTER\n"); mutex_lock(&ap->scsi_scan_mutex); /* Unplug detached devices. We cannot use link iterator here @@ -4552,7 +4479,6 @@ void ata_scsi_hotplug(struct work_struct *work) ata_scsi_scan_host(ap, 0); mutex_unlock(&ap->scsi_scan_mutex); - DPRINTK("EXIT\n"); } /** diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index b71ea4a680b0..75217828dfe3 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -18,7 +18,7 @@ #include #include #include - +#include #include "libata.h" static struct workqueue_struct *ata_sff_wq; @@ -330,10 +330,6 @@ EXPORT_SYMBOL_GPL(ata_sff_dev_select); static void ata_dev_select(struct ata_port *ap, unsigned int device, unsigned int wait, unsigned int can_sleep) { - if (ata_msg_probe(ap)) - ata_port_info(ap, "ata_dev_select: ENTER, device %u, wait %u\n", - device, wait); - if (wait) ata_wait_idle(ap); @@ -409,12 +405,6 @@ void ata_sff_tf_load(struct ata_port *ap, const struct ata_taskfile *tf) iowrite8(tf->hob_lbal, ioaddr->lbal_addr); iowrite8(tf->hob_lbam, ioaddr->lbam_addr); iowrite8(tf->hob_lbah, ioaddr->lbah_addr); - VPRINTK("hob: feat 0x%X nsect 0x%X, lba 0x%X 0x%X 0x%X\n", - tf->hob_feature, - tf->hob_nsect, - tf->hob_lbal, - tf->hob_lbam, - tf->hob_lbah); } if (is_addr) { @@ -423,18 +413,10 @@ void ata_sff_tf_load(struct ata_port *ap, const struct ata_taskfile *tf) iowrite8(tf->lbal, ioaddr->lbal_addr); iowrite8(tf->lbam, ioaddr->lbam_addr); iowrite8(tf->lbah, ioaddr->lbah_addr); - VPRINTK("feat 0x%X nsect 0x%X lba 0x%X 0x%X 0x%X\n", - tf->feature, - tf->nsect, - tf->lbal, - tf->lbam, - tf->lbah); } - if (tf->flags & ATA_TFLAG_DEVICE) { + if (tf->flags & ATA_TFLAG_DEVICE) iowrite8(tf->device, ioaddr->device_addr); - VPRINTK("device 0x%X\n", tf->device); - } ata_wait_idle(ap); } @@ -494,8 +476,6 @@ EXPORT_SYMBOL_GPL(ata_sff_tf_read); */ void ata_sff_exec_command(struct ata_port *ap, const struct ata_taskfile *tf) { - DPRINTK("ata%u: cmd 0x%X\n", ap->print_id, tf->command); - iowrite8(tf->command, ap->ioaddr.command_addr); ata_sff_pause(ap); } @@ -505,6 +485,7 @@ EXPORT_SYMBOL_GPL(ata_sff_exec_command); * ata_tf_to_host - issue ATA taskfile to host controller * @ap: port to which command is being issued * @tf: ATA taskfile register set + * @tag: tag of the associated command * * Issues ATA taskfile register set to ATA host controller, * with proper synchronization with interrupt handler and @@ -514,9 +495,12 @@ EXPORT_SYMBOL_GPL(ata_sff_exec_command); * spin_lock_irqsave(host lock) */ static inline void ata_tf_to_host(struct ata_port *ap, - const struct ata_taskfile *tf) + const struct ata_taskfile *tf, + unsigned int tag) { + trace_ata_tf_load(ap, tf); ap->ops->sff_tf_load(ap, tf); + trace_ata_exec_command(ap, tf, tag); ap->ops->sff_exec_command(ap, tf); } @@ -680,7 +664,7 @@ static void ata_pio_sector(struct ata_queued_cmd *qc) page = nth_page(page, (offset >> PAGE_SHIFT)); offset %= PAGE_SIZE; - DPRINTK("data %s\n", qc->tf.flags & ATA_TFLAG_WRITE ? "write" : "read"); + trace_ata_sff_pio_transfer_data(qc, offset, qc->sect_size); /* * Split the transfer when it splits a page boundary. Note that the @@ -750,7 +734,7 @@ static void ata_pio_sectors(struct ata_queued_cmd *qc) static void atapi_send_cdb(struct ata_port *ap, struct ata_queued_cmd *qc) { /* send SCSI cdb */ - DPRINTK("send cdb\n"); + trace_atapi_send_cdb(qc, 0, qc->dev->cdb_len); WARN_ON_ONCE(qc->dev->cdb_len < 12); ap->ops->sff_data_xfer(qc, qc->cdb, qc->dev->cdb_len, 1); @@ -768,6 +752,7 @@ static void atapi_send_cdb(struct ata_port *ap, struct ata_queued_cmd *qc) case ATAPI_PROT_DMA: ap->hsm_task_state = HSM_ST_LAST; /* initiate bmdma */ + trace_ata_bmdma_start(ap, &qc->tf, qc->tag); ap->ops->bmdma_start(qc); break; #endif /* CONFIG_ATA_BMDMA */ @@ -820,7 +805,7 @@ next_sg: /* don't cross page boundaries */ count = min(count, (unsigned int)PAGE_SIZE - offset); - DPRINTK("data %s\n", qc->tf.flags & ATA_TFLAG_WRITE ? "write" : "read"); + trace_atapi_pio_transfer_data(qc, offset, count); /* do the actual data transfer */ buf = kmap_atomic(page); @@ -888,8 +873,6 @@ static void atapi_pio_bytes(struct ata_queued_cmd *qc) if (unlikely(!bytes)) goto atapi_check; - VPRINTK("ata%u: xfering %d bytes\n", ap->print_id, bytes); - if (unlikely(__atapi_pio_bytes(qc, bytes))) goto err_out; ata_sff_sync(ap); /* flush */ @@ -1002,8 +985,7 @@ int ata_sff_hsm_move(struct ata_port *ap, struct ata_queued_cmd *qc, WARN_ON_ONCE(in_wq != ata_hsm_ok_in_wq(ap, qc)); fsm_start: - DPRINTK("ata%u: protocol %d task_state %d (dev_stat 0x%X)\n", - ap->print_id, qc->tf.protocol, ap->hsm_task_state, status); + trace_ata_sff_hsm_state(qc, status); switch (ap->hsm_task_state) { case HSM_ST_FIRST: @@ -1204,8 +1186,7 @@ fsm_start: } /* no more data to transfer */ - DPRINTK("ata%u: dev %u command complete, drv_stat 0x%x\n", - ap->print_id, qc->dev->devno, status); + trace_ata_sff_hsm_command_complete(qc, status); WARN_ON_ONCE(qc->err_mask & (AC_ERR_DEV | AC_ERR_HSM)); @@ -1262,7 +1243,7 @@ EXPORT_SYMBOL_GPL(ata_sff_queue_pio_task); void ata_sff_flush_pio_task(struct ata_port *ap) { - DPRINTK("ENTER\n"); + trace_ata_sff_flush_pio_task(ap); cancel_delayed_work_sync(&ap->sff_pio_task); @@ -1279,9 +1260,6 @@ void ata_sff_flush_pio_task(struct ata_port *ap) spin_unlock_irq(ap->lock); ap->sff_pio_task_link = NULL; - - if (ata_msg_ctl(ap)) - ata_port_dbg(ap, "%s: EXIT\n", __func__); } static void ata_sff_pio_task(struct work_struct *work) @@ -1376,7 +1354,7 @@ unsigned int ata_sff_qc_issue(struct ata_queued_cmd *qc) if (qc->tf.flags & ATA_TFLAG_POLLING) ata_qc_set_polling(qc); - ata_tf_to_host(ap, &qc->tf); + ata_tf_to_host(ap, &qc->tf, qc->tag); ap->hsm_task_state = HSM_ST_LAST; if (qc->tf.flags & ATA_TFLAG_POLLING) @@ -1388,7 +1366,7 @@ unsigned int ata_sff_qc_issue(struct ata_queued_cmd *qc) if (qc->tf.flags & ATA_TFLAG_POLLING) ata_qc_set_polling(qc); - ata_tf_to_host(ap, &qc->tf); + ata_tf_to_host(ap, &qc->tf, qc->tag); if (qc->tf.flags & ATA_TFLAG_WRITE) { /* PIO data out protocol */ @@ -1418,7 +1396,7 @@ unsigned int ata_sff_qc_issue(struct ata_queued_cmd *qc) if (qc->tf.flags & ATA_TFLAG_POLLING) ata_qc_set_polling(qc); - ata_tf_to_host(ap, &qc->tf); + ata_tf_to_host(ap, &qc->tf, qc->tag); ap->hsm_task_state = HSM_ST_FIRST; @@ -1478,8 +1456,7 @@ static unsigned int __ata_sff_port_intr(struct ata_port *ap, { u8 status; - VPRINTK("ata%u: protocol %d task_state %d\n", - ap->print_id, qc->tf.protocol, ap->hsm_task_state); + trace_ata_sff_port_intr(qc, hsmv_on_idle); /* Check whether we are expecting interrupt in this state */ switch (ap->hsm_task_state) { @@ -1853,7 +1830,7 @@ unsigned int ata_sff_dev_classify(struct ata_device *dev, int present, return ATA_DEV_NONE; /* determine if device is ATA or ATAPI */ - class = ata_dev_classify(&tf); + class = ata_port_classify(ap, &tf); if (class == ATA_DEV_UNKNOWN) { /* If the device failed diagnostic, it's likely to @@ -1956,8 +1933,6 @@ static int ata_bus_softreset(struct ata_port *ap, unsigned int devmask, { struct ata_ioports *ioaddr = &ap->ioaddr; - DPRINTK("ata%u: bus reset via SRST\n", ap->print_id); - if (ap->ioaddr.ctl_addr) { /* software reset. causes dev0 to be selected */ iowrite8(ap->ctl, ioaddr->ctl_addr); @@ -1995,8 +1970,6 @@ int ata_sff_softreset(struct ata_link *link, unsigned int *classes, int rc; u8 err; - DPRINTK("ENTER\n"); - /* determine if device 0/1 are present */ if (ata_devchk(ap, 0)) devmask |= (1 << 0); @@ -2007,7 +1980,6 @@ int ata_sff_softreset(struct ata_link *link, unsigned int *classes, ap->ops->sff_dev_select(ap, 0); /* issue bus reset */ - DPRINTK("about to softreset, devmask=%x\n", devmask); rc = ata_bus_softreset(ap, devmask, deadline); /* if link is occupied, -ENODEV too is an error */ if (rc && (rc != -ENODEV || sata_scr_valid(link))) { @@ -2022,7 +1994,6 @@ int ata_sff_softreset(struct ata_link *link, unsigned int *classes, classes[1] = ata_sff_dev_classify(&link->device[1], devmask & (1 << 1), &err); - DPRINTK("EXIT, classes[0]=%u [1]=%u\n", classes[0], classes[1]); return 0; } EXPORT_SYMBOL_GPL(ata_sff_softreset); @@ -2055,7 +2026,6 @@ int sata_sff_hardreset(struct ata_link *link, unsigned int *class, if (online) *class = ata_sff_dev_classify(link->device, 1, NULL); - DPRINTK("EXIT, class=%u\n", *class); return rc; } EXPORT_SYMBOL_GPL(sata_sff_hardreset); @@ -2085,10 +2055,8 @@ void ata_sff_postreset(struct ata_link *link, unsigned int *classes) ap->ops->sff_dev_select(ap, 0); /* bail out if no device is present */ - if (classes[0] == ATA_DEV_NONE && classes[1] == ATA_DEV_NONE) { - DPRINTK("EXIT, no device\n"); + if (classes[0] == ATA_DEV_NONE && classes[1] == ATA_DEV_NONE) return; - } /* set up device control */ if (ap->ops->sff_set_devctl || ap->ioaddr.ctl_addr) { @@ -2123,7 +2091,6 @@ void ata_sff_drain_fifo(struct ata_queued_cmd *qc) && count < 65536; count += 2) ioread16(ap->ioaddr.data_addr); - /* Can become DEBUG later */ if (count) ata_port_dbg(ap, "drained %d bytes to clear DRQ\n", count); @@ -2467,8 +2434,6 @@ static int ata_pci_init_one(struct pci_dev *pdev, struct ata_host *host = NULL; int rc; - DPRINTK("ENTER\n"); - pi = ata_sff_find_valid_pi(ppi); if (!pi) { dev_err(&pdev->dev, "no valid port_info specified\n"); @@ -2614,7 +2579,6 @@ static void ata_bmdma_fill_sg(struct ata_queued_cmd *qc) prd[pi].addr = cpu_to_le32(addr); prd[pi].flags_len = cpu_to_le32(len & 0xffff); - VPRINTK("PRD[%u] = (0x%X, 0x%X)\n", pi, addr, len); pi++; sg_len -= len; @@ -2674,7 +2638,6 @@ static void ata_bmdma_fill_sg_dumb(struct ata_queued_cmd *qc) prd[++pi].addr = cpu_to_le32(addr + 0x8000); } prd[pi].flags_len = cpu_to_le32(blen); - VPRINTK("PRD[%u] = (0x%X, 0x%X)\n", pi, addr, len); pi++; sg_len -= len; @@ -2756,8 +2719,11 @@ unsigned int ata_bmdma_qc_issue(struct ata_queued_cmd *qc) case ATA_PROT_DMA: WARN_ON_ONCE(qc->tf.flags & ATA_TFLAG_POLLING); + trace_ata_tf_load(ap, &qc->tf); ap->ops->sff_tf_load(ap, &qc->tf); /* load tf registers */ + trace_ata_bmdma_setup(ap, &qc->tf, qc->tag); ap->ops->bmdma_setup(qc); /* set up bmdma */ + trace_ata_bmdma_start(ap, &qc->tf, qc->tag); ap->ops->bmdma_start(qc); /* initiate bmdma */ ap->hsm_task_state = HSM_ST_LAST; break; @@ -2765,7 +2731,9 @@ unsigned int ata_bmdma_qc_issue(struct ata_queued_cmd *qc) case ATAPI_PROT_DMA: WARN_ON_ONCE(qc->tf.flags & ATA_TFLAG_POLLING); + trace_ata_tf_load(ap, &qc->tf); ap->ops->sff_tf_load(ap, &qc->tf); /* load tf registers */ + trace_ata_bmdma_setup(ap, &qc->tf, qc->tag); ap->ops->bmdma_setup(qc); /* set up bmdma */ ap->hsm_task_state = HSM_ST_FIRST; @@ -2806,13 +2774,14 @@ unsigned int ata_bmdma_port_intr(struct ata_port *ap, struct ata_queued_cmd *qc) if (ap->hsm_task_state == HSM_ST_LAST && ata_is_dma(qc->tf.protocol)) { /* check status of DMA engine */ host_stat = ap->ops->bmdma_status(ap); - VPRINTK("ata%u: host_stat 0x%X\n", ap->print_id, host_stat); + trace_ata_bmdma_status(ap, host_stat); /* if it's not our irq... */ if (!(host_stat & ATA_DMA_INTR)) return ata_sff_idle_irq(ap); /* before we do anything else, clear DMA-Start bit */ + trace_ata_bmdma_stop(ap, &qc->tf, qc->tag); ap->ops->bmdma_stop(qc); bmdma_stopped = true; @@ -2881,6 +2850,7 @@ void ata_bmdma_error_handler(struct ata_port *ap) u8 host_stat; host_stat = ap->ops->bmdma_status(ap); + trace_ata_bmdma_status(ap, host_stat); /* BMDMA controllers indicate host bus error by * setting DMA_ERR bit and timing out. As it wasn't @@ -2892,6 +2862,7 @@ void ata_bmdma_error_handler(struct ata_port *ap) thaw = true; } + trace_ata_bmdma_stop(ap, &qc->tf, qc->tag); ap->ops->bmdma_stop(qc); /* if we're gonna thaw, make sure IRQ is clear */ @@ -2925,6 +2896,7 @@ void ata_bmdma_post_internal_cmd(struct ata_queued_cmd *qc) if (ata_is_dma(qc->tf.protocol)) { spin_lock_irqsave(ap->lock, flags); + trace_ata_bmdma_stop(ap, &qc->tf, qc->tag); ap->ops->bmdma_stop(qc); spin_unlock_irqrestore(ap->lock, flags); } diff --git a/drivers/ata/libata-trace.c b/drivers/ata/libata-trace.c index 08e001303a82..e0e4d0d5a100 100644 --- a/drivers/ata/libata-trace.c +++ b/drivers/ata/libata-trace.c @@ -38,6 +38,24 @@ libata_trace_parse_status(struct trace_seq *p, unsigned char status) return ret; } +const char * +libata_trace_parse_host_stat(struct trace_seq *p, unsigned char host_stat) +{ + const char *ret = trace_seq_buffer_ptr(p); + + trace_seq_printf(p, "{ "); + if (host_stat & ATA_DMA_INTR) + trace_seq_printf(p, "INTR "); + if (host_stat & ATA_DMA_ERR) + trace_seq_printf(p, "ERR "); + if (host_stat & ATA_DMA_ACTIVE) + trace_seq_printf(p, "ACTIVE "); + trace_seq_putc(p, '}'); + trace_seq_putc(p, 0); + + return ret; +} + const char * libata_trace_parse_eh_action(struct trace_seq *p, unsigned int eh_action) { @@ -137,6 +155,35 @@ libata_trace_parse_qc_flags(struct trace_seq *p, unsigned int qc_flags) return ret; } +const char * +libata_trace_parse_tf_flags(struct trace_seq *p, unsigned int tf_flags) +{ + const char *ret = trace_seq_buffer_ptr(p); + + trace_seq_printf(p, "%x", tf_flags); + if (tf_flags) { + trace_seq_printf(p, "{ "); + if (tf_flags & ATA_TFLAG_LBA48) + trace_seq_printf(p, "LBA48 "); + if (tf_flags & ATA_TFLAG_ISADDR) + trace_seq_printf(p, "ISADDR "); + if (tf_flags & ATA_TFLAG_DEVICE) + trace_seq_printf(p, "DEV "); + if (tf_flags & ATA_TFLAG_WRITE) + trace_seq_printf(p, "WRITE "); + if (tf_flags & ATA_TFLAG_LBA) + trace_seq_printf(p, "LBA "); + if (tf_flags & ATA_TFLAG_FUA) + trace_seq_printf(p, "FUA "); + if (tf_flags & ATA_TFLAG_POLLING) + trace_seq_printf(p, "POLL "); + trace_seq_putc(p, '}'); + } + trace_seq_putc(p, 0); + + return ret; +} + const char * libata_trace_parse_subcmd(struct trace_seq *p, unsigned char cmd, unsigned char feature, unsigned char hob_nsect) diff --git a/drivers/ata/libata-transport.c b/drivers/ata/libata-transport.c index 34bb4608bdc6..ca129854a88c 100644 --- a/drivers/ata/libata-transport.c +++ b/drivers/ata/libata-transport.c @@ -163,7 +163,7 @@ static struct { { AC_ERR_INVALID, "InvalidArg" }, { AC_ERR_OTHER, "Unknown" }, { AC_ERR_NODEV_HINT, "NoDeviceHint" }, - { AC_ERR_NCQ, "NCQError" } + { AC_ERR_NCQ, "NCQError" } }; ata_bitfield_name_match(err, ata_err_names) @@ -321,13 +321,43 @@ int ata_tport_add(struct device *parent, return error; } +/** + * ata_port_classify - determine device type based on ATA-spec signature + * @ap: ATA port device on which the classification should be run + * @tf: ATA taskfile register set for device to be identified + * + * A wrapper around ata_dev_classify() to provide additional logging + * + * RETURNS: + * Device type, %ATA_DEV_ATA, %ATA_DEV_ATAPI, %ATA_DEV_PMP, + * %ATA_DEV_ZAC, or %ATA_DEV_UNKNOWN the event of failure. + */ +unsigned int ata_port_classify(struct ata_port *ap, + const struct ata_taskfile *tf) +{ + int i; + unsigned int class = ata_dev_classify(tf); + + /* Start with index '1' to skip the 'unknown' entry */ + for (i = 1; i < ARRAY_SIZE(ata_class_names); i++) { + if (ata_class_names[i].value == class) { + ata_port_dbg(ap, "found %s device by sig\n", + ata_class_names[i].name); + return class; + } + } + + ata_port_info(ap, "found unknown device (class %u)\n", class); + return class; +} +EXPORT_SYMBOL_GPL(ata_port_classify); /* * ATA link attributes */ static int noop(int x) { return x; } -#define ata_link_show_linkspeed(field, format) \ +#define ata_link_show_linkspeed(field, format) \ static ssize_t \ show_ata_link_##field(struct device *dev, \ struct device_attribute *attr, char *buf) \ @@ -416,7 +446,7 @@ int ata_tlink_add(struct ata_link *link) dev->release = ata_tlink_release; if (ata_is_host_link(link)) dev_set_name(dev, "link%d", ap->print_id); - else + else dev_set_name(dev, "link%d.%d", ap->print_id, link->pmp); transport_setup_device(dev); @@ -472,7 +502,7 @@ ata_dev_attr(xfer, dma_mode); ata_dev_attr(xfer, xfer_mode); -#define ata_dev_show_simple(field, format_string, cast) \ +#define ata_dev_show_simple(field, format_string, cast) \ static ssize_t \ show_ata_dev_##field(struct device *dev, \ struct device_attribute *attr, char *buf) \ @@ -482,9 +512,9 @@ show_ata_dev_##field(struct device *dev, \ return scnprintf(buf, 20, format_string, cast ata_dev->field); \ } -#define ata_dev_simple_attr(field, format_string, type) \ +#define ata_dev_simple_attr(field, format_string, type) \ ata_dev_show_simple(field, format_string, (type)) \ -static DEVICE_ATTR(field, S_IRUGO, \ + static DEVICE_ATTR(field, S_IRUGO, \ show_ata_dev_##field, NULL) ata_dev_simple_attr(spdn_cnt, "%d\n", int); @@ -502,7 +532,7 @@ static int ata_show_ering(struct ata_ering_entry *ent, void *void_arg) seconds = div_u64_rem(ent->timestamp, HZ, &rem); arg->written += sprintf(arg->buf + arg->written, - "[%5llu.%09lu]", seconds, + "[%5llu.%09lu]", seconds, rem * NSEC_PER_SEC / HZ); arg->written += get_ata_err_names(ent->err_mask, arg->buf + arg->written); @@ -667,7 +697,7 @@ static int ata_tdev_add(struct ata_device *ata_dev) dev->release = ata_tdev_release; if (ata_is_host_link(link)) dev_set_name(dev, "dev%d.%d", ap->print_id,ata_dev->devno); - else + else dev_set_name(dev, "dev%d.%d.0", ap->print_id, link->pmp); transport_setup_device(dev); @@ -689,7 +719,7 @@ static int ata_tdev_add(struct ata_device *ata_dev) */ #define SETUP_TEMPLATE(attrb, field, perm, test) \ - i->private_##attrb[count] = dev_attr_##field; \ + i->private_##attrb[count] = dev_attr_##field; \ i->private_##attrb[count].attr.mode = perm; \ i->attrb[count] = &i->private_##attrb[count]; \ if (test) \ diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h index 68cdd81d747c..51e01acdd241 100644 --- a/drivers/ata/libata.h +++ b/drivers/ata/libata.h @@ -148,7 +148,6 @@ extern int ata_scsi_user_scan(struct Scsi_Host *shost, unsigned int channel, unsigned int id, u64 lun); void ata_scsi_sdev_config(struct scsi_device *sdev); int ata_scsi_dev_config(struct scsi_device *sdev, struct ata_device *dev); -void ata_scsi_dump_cdb(struct ata_port *ap, struct scsi_cmnd *cmd); int __ata_scsi_queuecmd(struct scsi_cmnd *scmd, struct ata_device *dev); /* libata-eh.c */ @@ -166,7 +165,7 @@ extern void ata_eh_about_to_do(struct ata_link *link, struct ata_device *dev, extern void ata_eh_done(struct ata_link *link, struct ata_device *dev, unsigned int action); extern void ata_eh_autopsy(struct ata_port *ap); -const char *ata_get_cmd_descript(u8 command); +const char *ata_get_cmd_name(u8 command); extern void ata_eh_report(struct ata_port *ap); extern int ata_eh_reset(struct ata_link *link, int classify, ata_prereset_fn_t prereset, ata_reset_fn_t softreset, @@ -179,7 +178,7 @@ extern int ata_eh_recover(struct ata_port *ap, ata_prereset_fn_t prereset, extern void ata_eh_finish(struct ata_port *ap); extern int ata_ering_map(struct ata_ering *ering, int (*map_fn)(struct ata_ering_entry *, void *), - void *arg); + void *arg); extern unsigned int atapi_eh_tur(struct ata_device *dev, u8 *r_sense_key); extern unsigned int atapi_eh_request_sense(struct ata_device *dev, u8 *sense_buf, u8 dfl_sense_key); diff --git a/drivers/ata/pata_ali.c b/drivers/ata/pata_ali.c index b7ff63ed3bbb..1b90cda27246 100644 --- a/drivers/ata/pata_ali.c +++ b/drivers/ata/pata_ali.c @@ -37,7 +37,7 @@ #define DRV_NAME "pata_ali" #define DRV_VERSION "0.7.8" -static int ali_atapi_dma = 0; +static int ali_atapi_dma; module_param_named(atapi_dma, ali_atapi_dma, int, 0644); MODULE_PARM_DESC(atapi_dma, "Enable ATAPI DMA (0=disable, 1=enable)"); @@ -123,7 +123,7 @@ static unsigned long ali_20_filter(struct ata_device *adev, unsigned long mask) mask &= ~(ATA_MASK_MWDMA | ATA_MASK_UDMA); ata_id_c_string(adev->id, model_num, ATA_ID_PROD, sizeof(model_num)); if (strstr(model_num, "WDC")) - return mask &= ~ATA_MASK_UDMA; + mask &= ~ATA_MASK_UDMA; return mask; } diff --git a/drivers/ata/pata_arasan_cf.c b/drivers/ata/pata_arasan_cf.c index 63f39440a9b4..24c3d5e1fca3 100644 --- a/drivers/ata/pata_arasan_cf.c +++ b/drivers/ata/pata_arasan_cf.c @@ -39,6 +39,7 @@ #include #include #include +#include #define DRIVER_NAME "arasan_cf" #define TIMEOUT msecs_to_jiffies(3000) @@ -703,9 +704,11 @@ static unsigned int arasan_cf_qc_issue(struct ata_queued_cmd *qc) case ATA_PROT_DMA: WARN_ON_ONCE(qc->tf.flags & ATA_TFLAG_POLLING); + trace_ata_tf_load(ap, &qc->tf); ap->ops->sff_tf_load(ap, &qc->tf); acdev->dma_status = 0; acdev->qc = qc; + trace_ata_bmdma_start(ap, &qc->tf, qc->tag); arasan_cf_dma_start(acdev); ap->hsm_task_state = HSM_ST_LAST; break; diff --git a/drivers/ata/pata_atp867x.c b/drivers/ata/pata_atp867x.c index 2bc5fc81efe3..779d660415c8 100644 --- a/drivers/ata/pata_atp867x.c +++ b/drivers/ata/pata_atp867x.c @@ -155,7 +155,7 @@ static int atp867x_get_active_clocks_shifted(struct ata_port *ap, case 1 ... 6: break; default: - printk(KERN_WARNING "ATP867X: active %dclk is invalid. " + ata_port_warn(ap, "ATP867X: active %dclk is invalid. " "Using 12clk.\n", clk); fallthrough; case 9 ... 12: @@ -171,7 +171,8 @@ active_clock_shift_done: return clocks << ATP867X_IO_PIOSPD_ACTIVE_SHIFT; } -static int atp867x_get_recover_clocks_shifted(unsigned int clk) +static int atp867x_get_recover_clocks_shifted(struct ata_port *ap, + unsigned int clk) { unsigned char clocks = clk; @@ -188,7 +189,7 @@ static int atp867x_get_recover_clocks_shifted(unsigned int clk) case 15: break; default: - printk(KERN_WARNING "ATP867X: recover %dclk is invalid. " + ata_port_warn(ap, "ATP867X: recover %dclk is invalid. " "Using default 12clk.\n", clk); fallthrough; case 12: /* default 12 clk */ @@ -225,7 +226,7 @@ static void atp867x_set_piomode(struct ata_port *ap, struct ata_device *adev) iowrite8(b, dp->dma_mode); b = atp867x_get_active_clocks_shifted(ap, t.active) | - atp867x_get_recover_clocks_shifted(t.recover); + atp867x_get_recover_clocks_shifted(ap, t.recover); if (adev->devno & 1) iowrite8(b, dp->slave_piospd); @@ -233,7 +234,7 @@ static void atp867x_set_piomode(struct ata_port *ap, struct ata_device *adev) iowrite8(b, dp->mstr_piospd); b = atp867x_get_active_clocks_shifted(ap, t.act8b) | - atp867x_get_recover_clocks_shifted(t.rec8b); + atp867x_get_recover_clocks_shifted(ap, t.rec8b); iowrite8(b, dp->eightb_piospd); } @@ -270,7 +271,6 @@ static struct ata_port_operations atp867x_ops = { }; -#ifdef ATP867X_DEBUG static void atp867x_check_res(struct pci_dev *pdev) { int i; @@ -280,7 +280,7 @@ static void atp867x_check_res(struct pci_dev *pdev) for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) { start = pci_resource_start(pdev, i); len = pci_resource_len(pdev, i); - printk(KERN_DEBUG "ATP867X: resource start:len=%lx:%lx\n", + dev_dbg(&pdev->dev, "ATP867X: resource start:len=%lx:%lx\n", start, len); } } @@ -290,49 +290,48 @@ static void atp867x_check_ports(struct ata_port *ap, int port) struct ata_ioports *ioaddr = &ap->ioaddr; struct atp867x_priv *dp = ap->private_data; - printk(KERN_DEBUG "ATP867X: port[%d] addresses\n" - " cmd_addr =0x%llx, 0x%llx\n" - " ctl_addr =0x%llx, 0x%llx\n" - " bmdma_addr =0x%llx, 0x%llx\n" - " data_addr =0x%llx\n" - " error_addr =0x%llx\n" - " feature_addr =0x%llx\n" - " nsect_addr =0x%llx\n" - " lbal_addr =0x%llx\n" - " lbam_addr =0x%llx\n" - " lbah_addr =0x%llx\n" - " device_addr =0x%llx\n" - " status_addr =0x%llx\n" - " command_addr =0x%llx\n" - " dp->dma_mode =0x%llx\n" - " dp->mstr_piospd =0x%llx\n" - " dp->slave_piospd =0x%llx\n" - " dp->eightb_piospd =0x%llx\n" + ata_port_dbg(ap, "ATP867X: port[%d] addresses\n" + " cmd_addr =0x%lx, 0x%lx\n" + " ctl_addr =0x%lx, 0x%lx\n" + " bmdma_addr =0x%lx, 0x%lx\n" + " data_addr =0x%lx\n" + " error_addr =0x%lx\n" + " feature_addr =0x%lx\n" + " nsect_addr =0x%lx\n" + " lbal_addr =0x%lx\n" + " lbam_addr =0x%lx\n" + " lbah_addr =0x%lx\n" + " device_addr =0x%lx\n" + " status_addr =0x%lx\n" + " command_addr =0x%lx\n" + " dp->dma_mode =0x%lx\n" + " dp->mstr_piospd =0x%lx\n" + " dp->slave_piospd =0x%lx\n" + " dp->eightb_piospd =0x%lx\n" " dp->pci66mhz =0x%lx\n", port, - (unsigned long long)ioaddr->cmd_addr, - (unsigned long long)ATP867X_IO_PORTBASE(ap, port), - (unsigned long long)ioaddr->ctl_addr, - (unsigned long long)ATP867X_IO_ALTSTATUS(ap, port), - (unsigned long long)ioaddr->bmdma_addr, - (unsigned long long)ATP867X_IO_DMABASE(ap, port), - (unsigned long long)ioaddr->data_addr, - (unsigned long long)ioaddr->error_addr, - (unsigned long long)ioaddr->feature_addr, - (unsigned long long)ioaddr->nsect_addr, - (unsigned long long)ioaddr->lbal_addr, - (unsigned long long)ioaddr->lbam_addr, - (unsigned long long)ioaddr->lbah_addr, - (unsigned long long)ioaddr->device_addr, - (unsigned long long)ioaddr->status_addr, - (unsigned long long)ioaddr->command_addr, - (unsigned long long)dp->dma_mode, - (unsigned long long)dp->mstr_piospd, - (unsigned long long)dp->slave_piospd, - (unsigned long long)dp->eightb_piospd, + (unsigned long)ioaddr->cmd_addr, + (unsigned long)ATP867X_IO_PORTBASE(ap, port), + (unsigned long)ioaddr->ctl_addr, + (unsigned long)ATP867X_IO_ALTSTATUS(ap, port), + (unsigned long)ioaddr->bmdma_addr, + (unsigned long)ATP867X_IO_DMABASE(ap, port), + (unsigned long)ioaddr->data_addr, + (unsigned long)ioaddr->error_addr, + (unsigned long)ioaddr->feature_addr, + (unsigned long)ioaddr->nsect_addr, + (unsigned long)ioaddr->lbal_addr, + (unsigned long)ioaddr->lbam_addr, + (unsigned long)ioaddr->lbah_addr, + (unsigned long)ioaddr->device_addr, + (unsigned long)ioaddr->status_addr, + (unsigned long)ioaddr->command_addr, + (unsigned long)dp->dma_mode, + (unsigned long)dp->mstr_piospd, + (unsigned long)dp->slave_piospd, + (unsigned long)dp->eightb_piospd, (unsigned long)dp->pci66mhz); } -#endif static int atp867x_set_priv(struct ata_port *ap) { @@ -370,8 +369,7 @@ static void atp867x_fixup(struct ata_host *host) if (v < 0x80) { v = 0x80; pci_write_config_byte(pdev, PCI_LATENCY_TIMER, v); - printk(KERN_DEBUG "ATP867X: set latency timer of device %s" - " to %d\n", pci_name(pdev), v); + dev_dbg(&pdev->dev, "ATP867X: set latency timer to %d\n", v); } /* @@ -419,13 +417,11 @@ static int atp867x_ata_pci_sff_init_host(struct ata_host *host) return rc; host->iomap = pcim_iomap_table(pdev); -#ifdef ATP867X_DEBUG atp867x_check_res(pdev); for (i = 0; i < PCI_STD_NUM_BARS; i++) - printk(KERN_DEBUG "ATP867X: iomap[%d]=0x%llx\n", i, - (unsigned long long)(host->iomap[i])); -#endif + dev_dbg(gdev, "ATP867X: iomap[%d]=0x%p\n", i, + host->iomap[i]); /* * request, iomap BARs and init port addresses accordingly @@ -444,9 +440,8 @@ static int atp867x_ata_pci_sff_init_host(struct ata_host *host) if (rc) return rc; -#ifdef ATP867X_DEBUG atp867x_check_ports(ap, i); -#endif + ata_port_desc(ap, "cmd 0x%lx ctl 0x%lx", (unsigned long)ioaddr->cmd_addr, (unsigned long)ioaddr->ctl_addr); @@ -486,7 +481,7 @@ static int atp867x_init_one(struct pci_dev *pdev, if (rc) return rc; - printk(KERN_INFO "ATP867X: ATP867 ATA UDMA133 controller (rev %02X)", + dev_info(&pdev->dev, "ATP867X: ATP867 ATA UDMA133 controller (rev %02X)", pdev->device); host = ata_host_alloc_pinfo(&pdev->dev, ppi, ATP867X_NUM_PORTS); diff --git a/drivers/ata/pata_cmd640.c b/drivers/ata/pata_cmd640.c index d0bcabb58b44..1a3372a72213 100644 --- a/drivers/ata/pata_cmd640.c +++ b/drivers/ata/pata_cmd640.c @@ -61,7 +61,7 @@ static void cmd640_set_piomode(struct ata_port *ap, struct ata_device *adev) struct ata_device *pair = ata_dev_pair(adev); if (ata_timing_compute(adev, adev->pio_mode, &t, T, 0) < 0) { - printk(KERN_ERR DRV_NAME ": mode computation failed.\n"); + ata_dev_err(adev, DRV_NAME ": mode computation failed.\n"); return; } diff --git a/drivers/ata/pata_cmd64x.c b/drivers/ata/pata_cmd64x.c index 1d74d89b5bed..5baa4a7819c1 100644 --- a/drivers/ata/pata_cmd64x.c +++ b/drivers/ata/pata_cmd64x.c @@ -116,7 +116,7 @@ static void cmd64x_set_timing(struct ata_port *ap, struct ata_device *adev, u8 m /* ata_timing_compute is smart and will produce timings for MWDMA that don't violate the drives PIO capabilities. */ if (ata_timing_compute(adev, mode, &t, T, 0) < 0) { - printk(KERN_ERR DRV_NAME ": mode computation failed.\n"); + ata_dev_err(adev, DRV_NAME ": mode computation failed.\n"); return; } if (ap->port_no) { @@ -130,7 +130,7 @@ static void cmd64x_set_timing(struct ata_port *ap, struct ata_device *adev, u8 m } } - printk(KERN_DEBUG DRV_NAME ": active %d recovery %d setup %d.\n", + ata_dev_dbg(adev, DRV_NAME ": active %d recovery %d setup %d.\n", t.active, t.recover, t.setup); if (t.recover > 16) { t.active += t.recover - 16; diff --git a/drivers/ata/pata_cs5520.c b/drivers/ata/pata_cs5520.c index 247c14702624..24ce8665b1f9 100644 --- a/drivers/ata/pata_cs5520.c +++ b/drivers/ata/pata_cs5520.c @@ -153,12 +153,12 @@ static int cs5520_init_one(struct pci_dev *pdev, const struct pci_device_id *id) /* Perform set up for DMA */ if (pci_enable_device_io(pdev)) { - printk(KERN_ERR DRV_NAME ": unable to configure BAR2.\n"); + dev_err(&pdev->dev, "unable to configure BAR2.\n"); return -ENODEV; } if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32))) { - printk(KERN_ERR DRV_NAME ": unable to configure DMA mask.\n"); + dev_err(&pdev->dev, "unable to configure DMA mask.\n"); return -ENODEV; } diff --git a/drivers/ata/pata_cs5536.c b/drivers/ata/pata_cs5536.c index 760ac6e65216..ab47aeb5587f 100644 --- a/drivers/ata/pata_cs5536.c +++ b/drivers/ata/pata_cs5536.c @@ -263,12 +263,12 @@ static int cs5536_init_one(struct pci_dev *dev, const struct pci_device_id *id) ppi[1] = &ata_dummy_port_info; if (use_msr) - printk(KERN_ERR DRV_NAME ": Using MSR regs instead of PCI\n"); + dev_err(&dev->dev, DRV_NAME ": Using MSR regs instead of PCI\n"); cs5536_read(dev, CFG, &cfg); if ((cfg & IDE_CFG_CHANEN) == 0) { - printk(KERN_ERR DRV_NAME ": disabled by BIOS\n"); + dev_err(&dev->dev, DRV_NAME ": disabled by BIOS\n"); return -ENODEV; } diff --git a/drivers/ata/pata_cypress.c b/drivers/ata/pata_cypress.c index 5b3a7a8ebef6..3be5d52a777b 100644 --- a/drivers/ata/pata_cypress.c +++ b/drivers/ata/pata_cypress.c @@ -62,7 +62,7 @@ static void cy82c693_set_piomode(struct ata_port *ap, struct ata_device *adev) u32 addr; if (ata_timing_compute(adev, adev->pio_mode, &t, T, 1) < 0) { - printk(KERN_ERR DRV_NAME ": mome computation failed.\n"); + ata_dev_err(adev, DRV_NAME ": mome computation failed.\n"); return; } diff --git a/drivers/ata/pata_ep93xx.c b/drivers/ata/pata_ep93xx.c index 46208ececbb6..b78f71c70f27 100644 --- a/drivers/ata/pata_ep93xx.c +++ b/drivers/ata/pata_ep93xx.c @@ -855,7 +855,6 @@ static void ep93xx_pata_drain_fifo(struct ata_queued_cmd *qc) && count < 65536; count += 2) ep93xx_pata_read_reg(drv_data, IDECTRL_ADDR_DATA); - /* Can become DEBUG later */ if (count) ata_port_dbg(ap, "drained %d bytes to clear DRQ.\n", count); diff --git a/drivers/ata/pata_hpt366.c b/drivers/ata/pata_hpt366.c index 06b7c4a9ec95..778c893f276b 100644 --- a/drivers/ata/pata_hpt366.c +++ b/drivers/ata/pata_hpt366.c @@ -14,9 +14,6 @@ * TODO * Look into engine reset on timeout errors. Should not be required. */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - #include #include #include @@ -183,7 +180,7 @@ static int hpt_dma_blacklisted(const struct ata_device *dev, char *modestr, i = match_string(list, -1, model_num); if (i >= 0) { - pr_warn("%s is not supported for %s\n", modestr, list[i]); + ata_dev_warn(dev, "%s is not supported for %s\n", modestr, list[i]); return 1; } return 0; diff --git a/drivers/ata/pata_hpt37x.c b/drivers/ata/pata_hpt37x.c index f242157bc81b..7abc7e04f656 100644 --- a/drivers/ata/pata_hpt37x.c +++ b/drivers/ata/pata_hpt37x.c @@ -14,9 +14,6 @@ * TODO * Look into engine reset on timeout errors. Should not be required. */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - #include #include #include @@ -231,7 +228,8 @@ static int hpt_dma_blacklisted(const struct ata_device *dev, char *modestr, i = match_string(list, -1, model_num); if (i >= 0) { - pr_warn("%s is not supported for %s\n", modestr, list[i]); + ata_dev_warn(dev, "%s is not supported for %s\n", + modestr, list[i]); return 1; } return 0; @@ -864,7 +862,8 @@ static int hpt37x_init_one(struct pci_dev *dev, const struct pci_device_id *id) chip_table = &hpt372; break; default: - pr_err("Unknown HPT366 subtype, please report (%d)\n", + dev_err(&dev->dev, + "Unknown HPT366 subtype, please report (%d)\n", rev); return -ENODEV; } @@ -905,7 +904,8 @@ static int hpt37x_init_one(struct pci_dev *dev, const struct pci_device_id *id) *ppi = &info_hpt374_fn1; break; default: - pr_err("PCI table is bogus, please report (%d)\n", dev->device); + dev_err(&dev->dev, "PCI table is bogus, please report (%d)\n", + dev->device); return -ENODEV; } /* Ok so this is a chip we support */ @@ -953,7 +953,7 @@ static int hpt37x_init_one(struct pci_dev *dev, const struct pci_device_id *id) u8 sr; u32 total = 0; - pr_warn("BIOS has not set timing clocks\n"); + dev_warn(&dev->dev, "BIOS has not set timing clocks\n"); /* This is the process the HPT371 BIOS is reported to use */ for (i = 0; i < 128; i++) { @@ -1009,7 +1009,7 @@ static int hpt37x_init_one(struct pci_dev *dev, const struct pci_device_id *id) (f_high << 16) | f_low | 0x100); } if (adjust == 8) { - pr_err("DPLL did not stabilize!\n"); + dev_err(&dev->dev, "DPLL did not stabilize!\n"); return -ENODEV; } if (dpll == 3) @@ -1017,7 +1017,7 @@ static int hpt37x_init_one(struct pci_dev *dev, const struct pci_device_id *id) else private_data = (void *)hpt37x_timings_50; - pr_info("bus clock %dMHz, using %dMHz DPLL\n", + dev_info(&dev->dev, "bus clock %dMHz, using %dMHz DPLL\n", MHz[clock_slot], MHz[dpll]); } else { private_data = (void *)chip_table->clocks[clock_slot]; @@ -1032,7 +1032,7 @@ static int hpt37x_init_one(struct pci_dev *dev, const struct pci_device_id *id) if (clock_slot < 2 && ppi[0] == &info_hpt370a) ppi[0] = &info_hpt370a_33; - pr_info("%s using %dMHz bus clock\n", + dev_info(&dev->dev, "%s using %dMHz bus clock\n", chip_table->name, MHz[clock_slot]); } diff --git a/drivers/ata/pata_hpt3x2n.c b/drivers/ata/pata_hpt3x2n.c index 48eef338e050..1d9d4eec5b8a 100644 --- a/drivers/ata/pata_hpt3x2n.c +++ b/drivers/ata/pata_hpt3x2n.c @@ -15,9 +15,6 @@ * TODO * Work out best PLL policy */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - #include #include #include @@ -420,7 +417,7 @@ static int hpt3x2n_pci_clock(struct pci_dev *pdev) u16 sr; u32 total = 0; - pr_warn("BIOS clock data not set\n"); + dev_warn(&pdev->dev, "BIOS clock data not set\n"); /* This is the process the HPT371 BIOS is reported to use */ for (i = 0; i < 128; i++) { @@ -530,7 +527,8 @@ hpt372n: ppi[0] = &info_hpt372n; break; default: - pr_err("PCI table is bogus, please report (%d)\n", dev->device); + dev_err(&dev->dev,"PCI table is bogus, please report (%d)\n", + dev->device); return -ENODEV; } @@ -579,11 +577,11 @@ hpt372n: pci_write_config_dword(dev, 0x5C, (f_high << 16) | f_low); } if (adjust == 8) { - pr_err("DPLL did not stabilize!\n"); + dev_err(&dev->dev, "DPLL did not stabilize!\n"); return -ENODEV; } - pr_info("bus clock %dMHz, using 66MHz DPLL\n", pci_mhz); + dev_info(&dev->dev, "bus clock %dMHz, using 66MHz DPLL\n", pci_mhz); /* * Set our private data up. We only need a few flags diff --git a/drivers/ata/pata_it821x.c b/drivers/ata/pata_it821x.c index 0e2265978a34..8a5b4e0079ab 100644 --- a/drivers/ata/pata_it821x.c +++ b/drivers/ata/pata_it821x.c @@ -431,7 +431,8 @@ static unsigned int it821x_smart_qc_issue(struct ata_queued_cmd *qc) case ATA_CMD_SET_FEATURES: return ata_bmdma_qc_issue(qc); } - printk(KERN_DEBUG "it821x: can't process command 0x%02X\n", qc->tf.command); + ata_dev_dbg(qc->dev, "it821x: can't process command 0x%02X\n", + qc->tf.command); return AC_ERR_DEV; } @@ -507,12 +508,14 @@ static void it821x_dev_config(struct ata_device *adev) if (strstr(model_num, "Integrated Technology Express")) { /* RAID mode */ - ata_dev_info(adev, "%sRAID%d volume", - adev->id[147] ? "Bootable " : "", - adev->id[129]); - if (adev->id[129] != 1) - pr_cont("(%dK stripe)", adev->id[146]); - pr_cont("\n"); + if (adev->id[129] == 1) + ata_dev_info(adev, "%sRAID%d volume\n", + adev->id[147] ? "Bootable " : "", + adev->id[129]); + else + ata_dev_info(adev, "%sRAID%d volume (%dK stripe)\n", + adev->id[147] ? "Bootable " : "", + adev->id[129], adev->id[146]); } /* This is a controller firmware triggered funny, don't report the drive faulty! */ @@ -534,7 +537,7 @@ static void it821x_dev_config(struct ata_device *adev) */ static unsigned int it821x_read_id(struct ata_device *adev, - struct ata_taskfile *tf, u16 *id) + struct ata_taskfile *tf, __le16 *id) { unsigned int err_mask; unsigned char model_num[ATA_ID_PROD_LEN + 1]; @@ -542,21 +545,20 @@ static unsigned int it821x_read_id(struct ata_device *adev, err_mask = ata_do_dev_read_id(adev, tf, id); if (err_mask) return err_mask; - ata_id_c_string(id, model_num, ATA_ID_PROD, sizeof(model_num)); + ata_id_c_string((u16 *)id, model_num, ATA_ID_PROD, sizeof(model_num)); - id[83] &= ~(1 << 12); /* Cache flush is firmware handled */ - id[83] &= ~(1 << 13); /* Ditto for LBA48 flushes */ - id[84] &= ~(1 << 6); /* No FUA */ - id[85] &= ~(1 << 10); /* No HPA */ - id[76] = 0; /* No NCQ/AN etc */ + id[83] &= cpu_to_le16(~(1 << 12)); /* Cache flush is firmware handled */ + id[84] &= cpu_to_le16(~(1 << 6)); /* No FUA */ + id[85] &= cpu_to_le16(~(1 << 10)); /* No HPA */ + id[76] = 0; /* No NCQ/AN etc */ if (strstr(model_num, "Integrated Technology Express")) { /* Set feature bits the firmware neglects */ - id[49] |= 0x0300; /* LBA, DMA */ - id[83] &= 0x7FFF; - id[83] |= 0x4400; /* Word 83 is valid and LBA48 */ - id[86] |= 0x0400; /* LBA48 on */ - id[ATA_ID_MAJOR_VER] |= 0x1F; + id[49] |= cpu_to_le16(0x0300); /* LBA, DMA */ + id[83] &= cpu_to_le16(0x7FFF); + id[83] |= cpu_to_le16(0x4400); /* Word 83 is valid and LBA48 */ + id[86] |= cpu_to_le16(0x0400); /* LBA48 on */ + id[ATA_ID_MAJOR_VER] |= cpu_to_le16(0x1F); /* Clear the serial number because it's different each boot which breaks validation on resume */ memset(&id[ATA_ID_SERNO], 0x20, ATA_ID_SERNO_LEN); @@ -593,6 +595,7 @@ static int it821x_check_atapi_dma(struct ata_queued_cmd *qc) /** * it821x_display_disk - display disk setup + * @ap: ATA port * @n: Device number * @buf: Buffer block from firmware * @@ -600,7 +603,7 @@ static int it821x_check_atapi_dma(struct ata_queued_cmd *qc) * by the firmware. */ -static void it821x_display_disk(int n, u8 *buf) +static void it821x_display_disk(struct ata_port *ap, int n, u8 *buf) { unsigned char id[41]; int mode = 0; @@ -633,13 +636,13 @@ static void it821x_display_disk(int n, u8 *buf) else strcpy(mbuf, "PIO"); if (buf[52] == 4) - printk(KERN_INFO "%d: %-6s %-8s %s %s\n", + ata_port_info(ap, "%d: %-6s %-8s %s %s\n", n, mbuf, types[buf[52]], id, cbl); else - printk(KERN_INFO "%d: %-6s %-8s Volume: %1d %s %s\n", + ata_port_info(ap, "%d: %-6s %-8s Volume: %1d %s %s\n", n, mbuf, types[buf[52]], buf[53], id, cbl); if (buf[125] < 100) - printk(KERN_INFO "%d: Rebuilding: %d%%\n", n, buf[125]); + ata_port_info(ap, "%d: Rebuilding: %d%%\n", n, buf[125]); } /** @@ -676,7 +679,7 @@ static u8 *it821x_firmware_command(struct ata_port *ap, u8 cmd, int len) status = ioread8(ap->ioaddr.status_addr); if (status & ATA_ERR) { kfree(buf); - printk(KERN_ERR "it821x_firmware_command: rejected\n"); + ata_port_err(ap, "%s: rejected\n", __func__); return NULL; } if (status & ATA_DRQ) { @@ -686,7 +689,7 @@ static u8 *it821x_firmware_command(struct ata_port *ap, u8 cmd, int len) usleep_range(500, 1000); } kfree(buf); - printk(KERN_ERR "it821x_firmware_command: timeout\n"); + ata_port_err(ap, "%s: timeout\n", __func__); return NULL; } @@ -709,13 +712,13 @@ static void it821x_probe_firmware(struct ata_port *ap) buf = it821x_firmware_command(ap, 0xFA, 512); if (buf != NULL) { - printk(KERN_INFO "pata_it821x: Firmware %02X/%02X/%02X%02X\n", + ata_port_info(ap, "pata_it821x: Firmware %02X/%02X/%02X%02X\n", buf[505], buf[506], buf[507], buf[508]); for (i = 0; i < 4; i++) - it821x_display_disk(i, buf + 128 * i); + it821x_display_disk(ap, i, buf + 128 * i); kfree(buf); } } @@ -771,7 +774,8 @@ static int it821x_port_start(struct ata_port *ap) itdev->timing10 = 1; /* Need to disable ATAPI DMA for this case */ if (!itdev->smart) - printk(KERN_WARNING DRV_NAME": Revision 0x10, workarounds activated.\n"); + dev_warn(&pdev->dev, + "Revision 0x10, workarounds activated.\n"); } return 0; @@ -919,14 +923,14 @@ static int it821x_init_one(struct pci_dev *pdev, const struct pci_device_id *id) } else { /* Force the card into bypass mode if so requested */ if (it8212_noraid) { - printk(KERN_INFO DRV_NAME ": forcing bypass mode.\n"); + dev_info(&pdev->dev, "forcing bypass mode.\n"); it821x_disable_raid(pdev); } pci_read_config_byte(pdev, 0x50, &conf); conf &= 1; - printk(KERN_INFO DRV_NAME": controller in %s mode.\n", - mode[conf]); + dev_info(&pdev->dev, "controller in %s mode.\n", mode[conf]); + if (conf == 0) ppi[0] = &info_passthru; else diff --git a/drivers/ata/pata_ixp4xx_cf.c b/drivers/ata/pata_ixp4xx_cf.c index 99c63087c8ae..17b557c91e1c 100644 --- a/drivers/ata/pata_ixp4xx_cf.c +++ b/drivers/ata/pata_ixp4xx_cf.c @@ -114,7 +114,7 @@ static void ixp4xx_set_piomode(struct ata_port *ap, struct ata_device *adev) { struct ixp4xx_pata *ixpp = ap->host->private_data; - ata_dev_printk(adev, KERN_INFO, "configured for PIO%d 8bit\n", + ata_dev_info(adev, "configured for PIO%d 8bit\n", adev->pio_mode - XFER_PIO_0); ixp4xx_set_8bit_timing(ixpp, adev->pio_mode); } @@ -132,8 +132,8 @@ static unsigned int ixp4xx_mmio_data_xfer(struct ata_queued_cmd *qc, struct ixp4xx_pata *ixpp = ap->host->private_data; unsigned long flags; - ata_dev_printk(adev, KERN_DEBUG, "%s %d bytes\n", (rw == READ) ? "READ" : "WRITE", - buflen); + ata_dev_dbg(adev, "%s %d bytes\n", (rw == READ) ? "READ" : "WRITE", + buflen); spin_lock_irqsave(ap->lock, flags); /* set the expansion bus in 16bit mode and restore diff --git a/drivers/ata/pata_marvell.c b/drivers/ata/pata_marvell.c index 361597d14c56..0c5a51970fbf 100644 --- a/drivers/ata/pata_marvell.c +++ b/drivers/ata/pata_marvell.c @@ -32,7 +32,6 @@ static int marvell_pata_active(struct pci_dev *pdev) { - int i; u32 devices; void __iomem *barp; @@ -44,11 +43,6 @@ static int marvell_pata_active(struct pci_dev *pdev) if (barp == NULL) return -ENOMEM; - printk("BAR5:"); - for(i = 0; i <= 0x0F; i++) - printk("%02X:%02X ", i, ioread8(barp + i)); - printk("\n"); - devices = ioread32(barp + 0x0C); pci_iounmap(pdev, barp); @@ -149,7 +143,8 @@ static int marvell_init_one (struct pci_dev *pdev, const struct pci_device_id *i #if IS_ENABLED(CONFIG_SATA_AHCI) if (!marvell_pata_active(pdev)) { - printk(KERN_INFO DRV_NAME ": PATA port not active, deferring to AHCI driver.\n"); + dev_info(&pdev->dev, + "PATA port not active, deferring to AHCI driver.\n"); return -ENODEV; } #endif diff --git a/drivers/ata/pata_netcell.c b/drivers/ata/pata_netcell.c index a7ecc1a204b5..06929e77c491 100644 --- a/drivers/ata/pata_netcell.c +++ b/drivers/ata/pata_netcell.c @@ -21,12 +21,13 @@ /* No PIO or DMA methods needed for this device */ static unsigned int netcell_read_id(struct ata_device *adev, - struct ata_taskfile *tf, u16 *id) + struct ata_taskfile *tf, __le16 *id) { unsigned int err_mask = ata_do_dev_read_id(adev, tf, id); + /* Firmware forgets to mark words 85-87 valid */ if (err_mask == 0) - id[ATA_ID_CSF_DEFAULT] |= 0x4000; + id[ATA_ID_CSF_DEFAULT] |= cpu_to_le16(0x4000); return err_mask; } diff --git a/drivers/ata/pata_octeon_cf.c b/drivers/ata/pata_octeon_cf.c index b5a3f710d76d..0912846bc1b0 100644 --- a/drivers/ata/pata_octeon_cf.c +++ b/drivers/ata/pata_octeon_cf.c @@ -19,7 +19,7 @@ #include #include #include - +#include #include #include @@ -73,16 +73,12 @@ MODULE_PARM_DESC(enable_dma, */ static unsigned int ns_to_tim_reg(unsigned int tim_mult, unsigned int nsecs) { - unsigned int val; - /* * Compute # of eclock periods to get desired duration in * nanoseconds. */ - val = DIV_ROUND_UP(nsecs * (octeon_get_io_clock_rate() / 1000000), + return DIV_ROUND_UP(nsecs * (octeon_get_io_clock_rate() / 1000000), 1000 * tim_mult); - - return val; } static void octeon_cf_set_boot_reg_cfg(int cs, unsigned int multiplier) @@ -273,9 +269,9 @@ static void octeon_cf_set_dmamode(struct ata_port *ap, struct ata_device *dev) dma_tim.s.we_n = ns_to_tim_reg(tim_mult, oe_n); dma_tim.s.we_a = ns_to_tim_reg(tim_mult, oe_a); - pr_debug("ns to ticks (mult %d) of %d is: %d\n", tim_mult, 60, + ata_dev_dbg(dev, "ns to ticks (mult %d) of %d is: %d\n", tim_mult, 60, ns_to_tim_reg(tim_mult, 60)); - pr_debug("oe_n: %d, oe_a: %d, dmack_s: %d, dmack_h: %d, dmarq: %d, pause: %d\n", + ata_dev_dbg(dev, "oe_n: %d, oe_a: %d, dmack_s: %d, dmack_h: %d, dmarq: %d, pause: %d\n", dma_tim.s.oe_n, dma_tim.s.oe_a, dma_tim.s.dmack_s, dma_tim.s.dmack_h, dma_tim.s.dmarq, dma_tim.s.pause); @@ -440,7 +436,6 @@ static int octeon_cf_softreset16(struct ata_link *link, unsigned int *classes, int rc; u8 err; - DPRINTK("about to softreset\n"); __raw_writew(ap->ctl, base + 0xe); udelay(20); __raw_writew(ap->ctl | ATA_SRST, base + 0xe); @@ -455,7 +450,6 @@ static int octeon_cf_softreset16(struct ata_link *link, unsigned int *classes, /* determine by signature whether we have ATA or ATAPI devices */ classes[0] = ata_sff_dev_classify(&link->device[0], 1, &err); - DPRINTK("EXIT, classes[0]=%u [1]=%u\n", classes[0], classes[1]); return 0; } @@ -479,23 +473,11 @@ static void octeon_cf_tf_load16(struct ata_port *ap, __raw_writew(tf->hob_feature << 8, base + 0xc); __raw_writew(tf->hob_nsect | tf->hob_lbal << 8, base + 2); __raw_writew(tf->hob_lbam | tf->hob_lbah << 8, base + 4); - VPRINTK("hob: feat 0x%X nsect 0x%X, lba 0x%X 0x%X 0x%X\n", - tf->hob_feature, - tf->hob_nsect, - tf->hob_lbal, - tf->hob_lbam, - tf->hob_lbah); } if (is_addr) { __raw_writew(tf->feature << 8, base + 0xc); __raw_writew(tf->nsect | tf->lbal << 8, base + 2); __raw_writew(tf->lbam | tf->lbah << 8, base + 4); - VPRINTK("feat 0x%X nsect 0x%X, lba 0x%X 0x%X 0x%X\n", - tf->feature, - tf->nsect, - tf->lbal, - tf->lbam, - tf->lbah); } ata_wait_idle(ap); } @@ -516,20 +498,14 @@ static void octeon_cf_exec_command16(struct ata_port *ap, { /* The base of the registers is at ioaddr.data_addr. */ void __iomem *base = ap->ioaddr.data_addr; - u16 blob; + u16 blob = 0; - if (tf->flags & ATA_TFLAG_DEVICE) { - VPRINTK("device 0x%X\n", tf->device); + if (tf->flags & ATA_TFLAG_DEVICE) blob = tf->device; - } else { - blob = 0; - } - DPRINTK("ata%u: cmd 0x%X\n", ap->print_id, tf->command); blob |= (tf->command << 8); __raw_writew(blob, base + 6); - ata_wait_idle(ap); } @@ -543,12 +519,10 @@ static void octeon_cf_dma_setup(struct ata_queued_cmd *qc) struct octeon_cf_port *cf_port; cf_port = ap->private_data; - DPRINTK("ENTER\n"); /* issue r/w command */ qc->cursg = qc->sg; cf_port->dma_finished = 0; ap->ops->sff_exec_command(ap, &qc->tf); - DPRINTK("EXIT\n"); } /** @@ -563,8 +537,6 @@ static void octeon_cf_dma_start(struct ata_queued_cmd *qc) union cvmx_mio_boot_dma_intx mio_boot_dma_int; struct scatterlist *sg; - VPRINTK("%d scatterlists\n", qc->n_elem); - /* Get the scatter list entry we need to DMA into */ sg = qc->cursg; BUG_ON(!sg); @@ -605,10 +577,6 @@ static void octeon_cf_dma_start(struct ata_queued_cmd *qc) mio_boot_dma_cfg.s.adr = sg_dma_address(sg); - VPRINTK("%s %d bytes address=%p\n", - (mio_boot_dma_cfg.s.rw) ? "write" : "read", sg->length, - (void *)(unsigned long)mio_boot_dma_cfg.s.adr); - cvmx_write_csr(cf_port->dma_base + DMA_CFG, mio_boot_dma_cfg.u64); } @@ -627,9 +595,7 @@ static unsigned int octeon_cf_dma_finished(struct ata_port *ap, union cvmx_mio_boot_dma_intx dma_int; u8 status; - VPRINTK("ata%u: protocol %d task_state %d\n", - ap->print_id, qc->tf.protocol, ap->hsm_task_state); - + trace_ata_bmdma_stop(qc, &qc->tf, qc->tag); if (ap->hsm_task_state != HSM_ST_LAST) return 0; @@ -678,7 +644,6 @@ static irqreturn_t octeon_cf_interrupt(int irq, void *dev_instance) spin_lock_irqsave(&host->lock, flags); - DPRINTK("ENTER\n"); for (i = 0; i < host->n_ports; i++) { u8 status; struct ata_port *ap; @@ -701,6 +666,7 @@ static irqreturn_t octeon_cf_interrupt(int irq, void *dev_instance) if (!sg_is_last(qc->cursg)) { qc->cursg = sg_next(qc->cursg); handled = 1; + trace_ata_bmdma_start(ap, &qc->tf, qc->tag); octeon_cf_dma_start(qc); continue; } else { @@ -732,7 +698,6 @@ static irqreturn_t octeon_cf_interrupt(int irq, void *dev_instance) } } spin_unlock_irqrestore(&host->lock, flags); - DPRINTK("EXIT\n"); return IRQ_RETVAL(handled); } @@ -800,8 +765,11 @@ static unsigned int octeon_cf_qc_issue(struct ata_queued_cmd *qc) case ATA_PROT_DMA: WARN_ON(qc->tf.flags & ATA_TFLAG_POLLING); + trace_ata_tf_load(ap, &qc->tf); ap->ops->sff_tf_load(ap, &qc->tf); /* load tf registers */ + trace_ata_bmdma_setup(ap, &qc->tf, qc->tag); octeon_cf_dma_setup(qc); /* set up dma */ + trace_ata_bmdma_start(ap, &qc->tf, qc->tag); octeon_cf_dma_start(qc); /* initiate dma */ ap->hsm_task_state = HSM_ST_LAST; break; diff --git a/drivers/ata/pata_of_platform.c b/drivers/ata/pata_of_platform.c index 35aa158fc976..c3a40b717dcd 100644 --- a/drivers/ata/pata_of_platform.c +++ b/drivers/ata/pata_of_platform.c @@ -25,11 +25,12 @@ static int pata_of_platform_probe(struct platform_device *ofdev) struct device_node *dn = ofdev->dev.of_node; struct resource io_res; struct resource ctl_res; - struct resource *irq_res; + struct resource irq_res; unsigned int reg_shift = 0; int pio_mode = 0; int pio_mask; bool use16bit; + int irq; ret = of_address_to_resource(dn, 0, &io_res); if (ret) { @@ -45,7 +46,15 @@ static int pata_of_platform_probe(struct platform_device *ofdev) return -EINVAL; } - irq_res = platform_get_resource(ofdev, IORESOURCE_IRQ, 0); + memset(&irq_res, 0, sizeof(irq_res)); + + irq = platform_get_irq_optional(ofdev, 0); + if (irq < 0 && irq != -ENXIO) + return irq; + if (irq > 0) { + irq_res.start = irq; + irq_res.end = irq; + } of_property_read_u32(dn, "reg-shift", ®_shift); @@ -63,7 +72,7 @@ static int pata_of_platform_probe(struct platform_device *ofdev) pio_mask = 1 << pio_mode; pio_mask |= (1 << pio_mode) - 1; - return __pata_platform_probe(&ofdev->dev, &io_res, &ctl_res, irq_res, + return __pata_platform_probe(&ofdev->dev, &io_res, &ctl_res, irq > 0 ? &irq_res : NULL, reg_shift, pio_mask, &pata_platform_sht, use16bit); } diff --git a/drivers/ata/pata_pdc2027x.c b/drivers/ata/pata_pdc2027x.c index effc1a09444d..4fbb3eed8b0b 100644 --- a/drivers/ata/pata_pdc2027x.c +++ b/drivers/ata/pata_pdc2027x.c @@ -30,13 +30,6 @@ #define DRV_NAME "pata_pdc2027x" #define DRV_VERSION "1.0" -#undef PDC_DEBUG - -#ifdef PDC_DEBUG -#define PDPRINTK(fmt, args...) printk(KERN_ERR "%s: " fmt, __func__, ## args) -#else -#define PDPRINTK(fmt, args...) -#endif enum { PDC_MMIO_BAR = 5, @@ -214,11 +207,11 @@ static int pdc2027x_cable_detect(struct ata_port *ap) if (cgcr & (1 << 26)) goto cbl40; - PDPRINTK("No cable or 80-conductor cable on port %d\n", ap->port_no); + ata_port_dbg(ap, "No cable or 80-conductor cable\n"); return ATA_CBL_PATA80; cbl40: - printk(KERN_INFO DRV_NAME ": 40-conductor cable detected on port %d\n", ap->port_no); + ata_port_info(ap, DRV_NAME ":40-conductor cable detected\n"); return ATA_CBL_PATA40; } @@ -292,17 +285,17 @@ static void pdc2027x_set_piomode(struct ata_port *ap, struct ata_device *adev) unsigned int pio = adev->pio_mode - XFER_PIO_0; u32 ctcr0, ctcr1; - PDPRINTK("adev->pio_mode[%X]\n", adev->pio_mode); + ata_port_dbg(ap, "adev->pio_mode[%X]\n", adev->pio_mode); /* Sanity check */ if (pio > 4) { - printk(KERN_ERR DRV_NAME ": Unknown pio mode [%d] ignored\n", pio); + ata_port_err(ap, "Unknown pio mode [%d] ignored\n", pio); return; } /* Set the PIO timing registers using value table for 133MHz */ - PDPRINTK("Set pio regs... \n"); + ata_port_dbg(ap, "Set pio regs... \n"); ctcr0 = ioread32(dev_mmio(ap, adev, PDC_CTCR0)); ctcr0 &= 0xffff0000; @@ -315,9 +308,7 @@ static void pdc2027x_set_piomode(struct ata_port *ap, struct ata_device *adev) ctcr1 |= (pdc2027x_pio_timing_tbl[pio].value2 << 24); iowrite32(ctcr1, dev_mmio(ap, adev, PDC_CTCR1)); - PDPRINTK("Set pio regs done\n"); - - PDPRINTK("Set to pio mode[%u] \n", pio); + ata_port_dbg(ap, "Set to pio mode[%u] \n", pio); } /** @@ -350,7 +341,7 @@ static void pdc2027x_set_dmamode(struct ata_port *ap, struct ata_device *adev) iowrite32(ctcr1 & ~(1 << 7), dev_mmio(ap, adev, PDC_CTCR1)); } - PDPRINTK("Set udma regs... \n"); + ata_port_dbg(ap, "Set udma regs... \n"); ctcr1 = ioread32(dev_mmio(ap, adev, PDC_CTCR1)); ctcr1 &= 0xff000000; @@ -359,16 +350,14 @@ static void pdc2027x_set_dmamode(struct ata_port *ap, struct ata_device *adev) (pdc2027x_udma_timing_tbl[udma_mode].value2 << 16); iowrite32(ctcr1, dev_mmio(ap, adev, PDC_CTCR1)); - PDPRINTK("Set udma regs done\n"); - - PDPRINTK("Set to udma mode[%u] \n", udma_mode); + ata_port_dbg(ap, "Set to udma mode[%u] \n", udma_mode); } else if ((dma_mode >= XFER_MW_DMA_0) && (dma_mode <= XFER_MW_DMA_2)) { /* Set the MDMA timing registers with value table for 133MHz */ unsigned int mdma_mode = dma_mode & 0x07; - PDPRINTK("Set mdma regs... \n"); + ata_port_dbg(ap, "Set mdma regs... \n"); ctcr0 = ioread32(dev_mmio(ap, adev, PDC_CTCR0)); ctcr0 &= 0x0000ffff; @@ -376,11 +365,10 @@ static void pdc2027x_set_dmamode(struct ata_port *ap, struct ata_device *adev) (pdc2027x_mdma_timing_tbl[mdma_mode].value1 << 24); iowrite32(ctcr0, dev_mmio(ap, adev, PDC_CTCR0)); - PDPRINTK("Set mdma regs done\n"); - PDPRINTK("Set to mdma mode[%u] \n", mdma_mode); + ata_port_dbg(ap, "Set to mdma mode[%u] \n", mdma_mode); } else { - printk(KERN_ERR DRV_NAME ": Unknown dma mode [%u] ignored\n", dma_mode); + ata_port_err(ap, "Unknown dma mode [%u] ignored\n", dma_mode); } } @@ -414,7 +402,7 @@ static int pdc2027x_set_mode(struct ata_link *link, struct ata_device **r_failed ctcr1 |= (1 << 25); iowrite32(ctcr1, dev_mmio(ap, dev, PDC_CTCR1)); - PDPRINTK("Turn on prefetch\n"); + ata_dev_dbg(dev, "Turn on prefetch\n"); } else { pdc2027x_set_dmamode(ap, dev); } @@ -485,8 +473,8 @@ retry: counter = (bccrh << 15) | bccrl; - PDPRINTK("bccrh [%X] bccrl [%X]\n", bccrh, bccrl); - PDPRINTK("bccrhv[%X] bccrlv[%X]\n", bccrhv, bccrlv); + dev_dbg(host->dev, "bccrh [%X] bccrl [%X]\n", bccrh, bccrl); + dev_dbg(host->dev, "bccrhv[%X] bccrlv[%X]\n", bccrhv, bccrlv); /* * The 30-bit decreasing counter are read by 2 pieces. @@ -495,7 +483,7 @@ retry: */ if (retry && !(bccrh == bccrhv && bccrl >= bccrlv)) { retry--; - PDPRINTK("rereading counter\n"); + dev_dbg(host->dev, "rereading counter\n"); goto retry; } @@ -520,20 +508,19 @@ static void pdc_adjust_pll(struct ata_host *host, long pll_clock, unsigned int b /* Sanity check */ if (unlikely(pll_clock_khz < 5000L || pll_clock_khz > 70000L)) { - printk(KERN_ERR DRV_NAME ": Invalid PLL input clock %ldkHz, give up!\n", pll_clock_khz); + dev_err(host->dev, "Invalid PLL input clock %ldkHz, give up!\n", + pll_clock_khz); return; } -#ifdef PDC_DEBUG - PDPRINTK("pout_required is %ld\n", pout_required); + dev_dbg(host->dev, "pout_required is %ld\n", pout_required); /* Show the current clock value of PLL control register * (maybe already configured by the firmware) */ pll_ctl = ioread16(mmio_base + PDC_PLL_CTL); - PDPRINTK("pll_ctl[%X]\n", pll_ctl); -#endif + dev_dbg(host->dev, "pll_ctl[%X]\n", pll_ctl); /* * Calculate the ratio of F, R and OD @@ -552,7 +539,7 @@ static void pdc_adjust_pll(struct ata_host *host, long pll_clock, unsigned int b R = 0x00; } else { /* Invalid ratio */ - printk(KERN_ERR DRV_NAME ": Invalid ratio %ld, give up!\n", ratio); + dev_err(host->dev, "Invalid ratio %ld, give up!\n", ratio); return; } @@ -560,15 +547,15 @@ static void pdc_adjust_pll(struct ata_host *host, long pll_clock, unsigned int b if (unlikely(F < 0 || F > 127)) { /* Invalid F */ - printk(KERN_ERR DRV_NAME ": F[%d] invalid!\n", F); + dev_err(host->dev, "F[%d] invalid!\n", F); return; } - PDPRINTK("F[%d] R[%d] ratio*1000[%ld]\n", F, R, ratio); + dev_dbg(host->dev, "F[%d] R[%d] ratio*1000[%ld]\n", F, R, ratio); pll_ctl = (R << 8) | F; - PDPRINTK("Writing pll_ctl[%X]\n", pll_ctl); + dev_dbg(host->dev, "Writing pll_ctl[%X]\n", pll_ctl); iowrite16(pll_ctl, mmio_base + PDC_PLL_CTL); ioread16(mmio_base + PDC_PLL_CTL); /* flush */ @@ -576,15 +563,13 @@ static void pdc_adjust_pll(struct ata_host *host, long pll_clock, unsigned int b /* Wait the PLL circuit to be stable */ msleep(30); -#ifdef PDC_DEBUG /* * Show the current clock value of PLL control register * (maybe configured by the firmware) */ pll_ctl = ioread16(mmio_base + PDC_PLL_CTL); - PDPRINTK("pll_ctl[%X]\n", pll_ctl); -#endif + dev_dbg(host->dev, "pll_ctl[%X]\n", pll_ctl); return; } @@ -605,7 +590,7 @@ static long pdc_detect_pll_input_clock(struct ata_host *host) /* Start the test mode */ scr = ioread32(mmio_base + PDC_SYS_CTL); - PDPRINTK("scr[%X]\n", scr); + dev_dbg(host->dev, "scr[%X]\n", scr); iowrite32(scr | (0x01 << 14), mmio_base + PDC_SYS_CTL); ioread32(mmio_base + PDC_SYS_CTL); /* flush */ @@ -622,7 +607,7 @@ static long pdc_detect_pll_input_clock(struct ata_host *host) /* Stop the test mode */ scr = ioread32(mmio_base + PDC_SYS_CTL); - PDPRINTK("scr[%X]\n", scr); + dev_dbg(host->dev, "scr[%X]\n", scr); iowrite32(scr & ~(0x01 << 14), mmio_base + PDC_SYS_CTL); ioread32(mmio_base + PDC_SYS_CTL); /* flush */ @@ -632,8 +617,8 @@ static long pdc_detect_pll_input_clock(struct ata_host *host) pll_clock = ((start_count - end_count) & 0x3fffffff) / 100 * (100000000 / usec_elapsed); - PDPRINTK("start[%ld] end[%ld] \n", start_count, end_count); - PDPRINTK("PLL input clock[%ld]Hz\n", pll_clock); + dev_dbg(host->dev, "start[%ld] end[%ld] PLL input clock[%ld]HZ\n", + start_count, end_count, pll_clock); return pll_clock; } diff --git a/drivers/ata/pata_pdc202xx_old.c b/drivers/ata/pata_pdc202xx_old.c index 0c5cbcd28d0d..b99849095853 100644 --- a/drivers/ata/pata_pdc202xx_old.c +++ b/drivers/ata/pata_pdc202xx_old.c @@ -38,8 +38,6 @@ static int pdc2026x_cable_detect(struct ata_port *ap) static void pdc202xx_exec_command(struct ata_port *ap, const struct ata_taskfile *tf) { - DPRINTK("ata%u: cmd 0x%X\n", ap->print_id, tf->command); - iowrite8(tf->command, ap->ioaddr.command_addr); ndelay(400); } diff --git a/drivers/ata/pata_rz1000.c b/drivers/ata/pata_rz1000.c index 3722a67083fd..fb00c3e5fd19 100644 --- a/drivers/ata/pata_rz1000.c +++ b/drivers/ata/pata_rz1000.c @@ -69,7 +69,7 @@ static int rz1000_fifo_disable(struct pci_dev *pdev) reg &= 0xDFFF; if (pci_write_config_word(pdev, 0x40, reg) != 0) return -1; - printk(KERN_INFO DRV_NAME ": disabled chipset readahead.\n"); + dev_info(&pdev->dev, "disabled chipset readahead.\n"); return 0; } @@ -97,7 +97,7 @@ static int rz1000_init_one (struct pci_dev *pdev, const struct pci_device_id *en if (rz1000_fifo_disable(pdev) == 0) return ata_pci_sff_init_one(pdev, ppi, &rz1000_sht, NULL, 0); - printk(KERN_ERR DRV_NAME ": failed to disable read-ahead on chipset..\n"); + dev_err(&pdev->dev, "failed to disable read-ahead on chipset.\n"); /* Not safe to use so skip */ return -ENODEV; } diff --git a/drivers/ata/pata_serverworks.c b/drivers/ata/pata_serverworks.c index b602e303fb54..e410fe44177f 100644 --- a/drivers/ata/pata_serverworks.c +++ b/drivers/ata/pata_serverworks.c @@ -286,13 +286,13 @@ static int serverworks_fixup_osb4(struct pci_dev *pdev) pci_read_config_dword(isa_dev, 0x64, ®); reg &= ~0x00002000; /* disable 600ns interrupt mask */ if (!(reg & 0x00004000)) - printk(KERN_DEBUG DRV_NAME ": UDMA not BIOS enabled.\n"); + dev_info(&pdev->dev, "UDMA not BIOS enabled.\n"); reg |= 0x00004000; /* enable UDMA/33 support */ pci_write_config_dword(isa_dev, 0x64, reg); pci_dev_put(isa_dev); return 0; } - printk(KERN_WARNING DRV_NAME ": Unable to find bridge.\n"); + dev_warn(&pdev->dev, "Unable to find bridge.\n"); return -ENODEV; } diff --git a/drivers/ata/pata_sil680.c b/drivers/ata/pata_sil680.c index 43215a664b96..0da58ce20d82 100644 --- a/drivers/ata/pata_sil680.c +++ b/drivers/ata/pata_sil680.c @@ -212,7 +212,6 @@ static void sil680_set_dmamode(struct ata_port *ap, struct ata_device *adev) static void sil680_sff_exec_command(struct ata_port *ap, const struct ata_taskfile *tf) { - DPRINTK("ata%u: cmd 0x%X\n", ap->print_id, tf->command); iowrite8(tf->command, ap->ioaddr.command_addr); ioread8(ap->ioaddr.bmdma_addr + ATA_DMA_CMD); } @@ -309,17 +308,17 @@ static u8 sil680_init_chip(struct pci_dev *pdev, int *try_mmio) switch (tmpbyte & 0x30) { case 0x00: - printk(KERN_INFO "sil680: 100MHz clock.\n"); + dev_info(&pdev->dev, "sil680: 100MHz clock.\n"); break; case 0x10: - printk(KERN_INFO "sil680: 133MHz clock.\n"); + dev_info(&pdev->dev, "sil680: 133MHz clock.\n"); break; case 0x20: - printk(KERN_INFO "sil680: Using PCI clock.\n"); + dev_info(&pdev->dev, "sil680: Using PCI clock.\n"); break; /* This last case is _NOT_ ok */ case 0x30: - printk(KERN_ERR "sil680: Clock disabled ?\n"); + dev_err(&pdev->dev, "sil680: Clock disabled ?\n"); } return tmpbyte & 0x30; } diff --git a/drivers/ata/pata_via.c b/drivers/ata/pata_via.c index 475032048984..439ca882f73c 100644 --- a/drivers/ata/pata_via.c +++ b/drivers/ata/pata_via.c @@ -414,12 +414,6 @@ static void via_tf_load(struct ata_port *ap, const struct ata_taskfile *tf) iowrite8(tf->hob_lbal, ioaddr->lbal_addr); iowrite8(tf->hob_lbam, ioaddr->lbam_addr); iowrite8(tf->hob_lbah, ioaddr->lbah_addr); - VPRINTK("hob: feat 0x%X nsect 0x%X, lba 0x%X 0x%X 0x%X\n", - tf->hob_feature, - tf->hob_nsect, - tf->hob_lbal, - tf->hob_lbam, - tf->hob_lbah); } if (is_addr) { @@ -428,12 +422,6 @@ static void via_tf_load(struct ata_port *ap, const struct ata_taskfile *tf) iowrite8(tf->lbal, ioaddr->lbal_addr); iowrite8(tf->lbam, ioaddr->lbam_addr); iowrite8(tf->lbah, ioaddr->lbah_addr); - VPRINTK("feat 0x%X nsect 0x%X lba 0x%X 0x%X 0x%X\n", - tf->feature, - tf->nsect, - tf->lbal, - tf->lbam, - tf->lbah); } ata_wait_idle(ap); diff --git a/drivers/ata/pdc_adma.c b/drivers/ata/pdc_adma.c index 5db55e1e2a61..35b823ac20c9 100644 --- a/drivers/ata/pdc_adma.c +++ b/drivers/ata/pdc_adma.c @@ -284,9 +284,6 @@ static int adma_fill_sg(struct ata_queued_cmd *qc) *(__le32 *)(buf + i) = (pFLAGS & pEND) ? 0 : cpu_to_le32(pp->pkt_dma + i + 4); i += 4; - - VPRINTK("PRD[%u] = (0x%lX, 0x%X)\n", i/4, - (unsigned long)addr, len); } if (likely(last_buf)) @@ -302,8 +299,6 @@ static enum ata_completion_errors adma_qc_prep(struct ata_queued_cmd *qc) u32 pkt_dma = (u32)pp->pkt_dma; int i = 0; - VPRINTK("ENTER\n"); - adma_enter_reg_mode(qc->ap); if (qc->tf.protocol != ATA_PROT_DMA) return AC_ERR_OK; @@ -355,22 +350,6 @@ static enum ata_completion_errors adma_qc_prep(struct ata_queued_cmd *qc) i = adma_fill_sg(qc); wmb(); /* flush PRDs and pkt to memory */ -#if 0 - /* dump out CPB + PRDs for debug */ - { - int j, len = 0; - static char obuf[2048]; - for (j = 0; j < i; ++j) { - len += sprintf(obuf+len, "%02x ", buf[j]); - if ((j & 7) == 7) { - printk("%s\n", obuf); - len = 0; - } - } - if (len) - printk("%s\n", obuf); - } -#endif return AC_ERR_OK; } @@ -379,8 +358,6 @@ static inline void adma_packet_start(struct ata_queued_cmd *qc) struct ata_port *ap = qc->ap; void __iomem *chan = ADMA_PORT_REGS(ap); - VPRINTK("ENTER, ap %p\n", ap); - /* fire up the ADMA engine */ writew(aPIOMD4 | aGO, chan + ADMA_CONTROL); } @@ -475,8 +452,6 @@ static inline unsigned int adma_intr_mmio(struct ata_host *host) u8 status = ata_sff_check_status(ap); if ((status & ATA_BUSY)) continue; - DPRINTK("ata%u: protocol %d (dev_stat 0x%X)\n", - ap->print_id, qc->tf.protocol, status); /* complete taskfile transaction */ pp->state = adma_state_idle; @@ -504,14 +479,10 @@ static irqreturn_t adma_intr(int irq, void *dev_instance) struct ata_host *host = dev_instance; unsigned int handled = 0; - VPRINTK("ENTER\n"); - spin_lock(&host->lock); handled = adma_intr_pkt(host) | adma_intr_mmio(host); spin_unlock(&host->lock); - VPRINTK("EXIT\n"); - return IRQ_RETVAL(handled); } @@ -547,8 +518,8 @@ static int adma_port_start(struct ata_port *ap) return -ENOMEM; /* paranoia? */ if ((pp->pkt_dma & 7) != 0) { - printk(KERN_ERR "bad alignment for pp->pkt_dma: %08x\n", - (u32)pp->pkt_dma); + ata_port_err(ap, "bad alignment for pp->pkt_dma: %08x\n", + (u32)pp->pkt_dma); return -ENOMEM; } ap->private_data = pp; diff --git a/drivers/ata/sata_dwc_460ex.c b/drivers/ata/sata_dwc_460ex.c index 338c2e50f759..bec33d781ae0 100644 --- a/drivers/ata/sata_dwc_460ex.c +++ b/drivers/ata/sata_dwc_460ex.c @@ -14,15 +14,6 @@ * COPYRIGHT (C) 2005 SYNOPSYS, INC. ALL RIGHTS RESERVED */ -#ifdef CONFIG_SATA_DWC_DEBUG -#define DEBUG -#endif - -#ifdef CONFIG_SATA_DWC_VDEBUG -#define VERBOSE_DEBUG -#define DEBUG_NCQ -#endif - #include #include #include @@ -34,6 +25,7 @@ #include #include #include +#include #include "libata.h" @@ -182,10 +174,8 @@ enum { * Prototypes */ static void sata_dwc_bmdma_start_by_tag(struct ata_queued_cmd *qc, u8 tag); -static int sata_dwc_qc_complete(struct ata_port *ap, struct ata_queued_cmd *qc, - u32 check_status); -static void sata_dwc_dma_xfer_complete(struct ata_port *ap, u32 check_status); -static void sata_dwc_port_stop(struct ata_port *ap); +static int sata_dwc_qc_complete(struct ata_port *ap, struct ata_queued_cmd *qc); +static void sata_dwc_dma_xfer_complete(struct ata_port *ap); static void sata_dwc_clear_dmacr(struct sata_dwc_device_port *hsdevp, u8 tag); #ifdef CONFIG_SATA_DWC_OLD_DMA @@ -215,9 +205,10 @@ static int sata_dwc_dma_get_channel_old(struct sata_dwc_device_port *hsdevp) { struct sata_dwc_device *hsdev = hsdevp->hsdev; struct dw_dma_slave *dws = &sata_dwc_dma_dws; + struct device *dev = hsdev->dev; dma_cap_mask_t mask; - dws->dma_dev = hsdev->dev; + dws->dma_dev = dev; dma_cap_zero(mask); dma_cap_set(DMA_SLAVE, mask); @@ -225,8 +216,7 @@ static int sata_dwc_dma_get_channel_old(struct sata_dwc_device_port *hsdevp) /* Acquire DMA channel */ hsdevp->chan = dma_request_channel(mask, sata_dwc_dma_filter, hsdevp); if (!hsdevp->chan) { - dev_err(hsdev->dev, "%s: dma channel unavailable\n", - __func__); + dev_err(dev, "%s: dma channel unavailable\n", __func__); return -EAGAIN; } @@ -236,26 +226,25 @@ static int sata_dwc_dma_get_channel_old(struct sata_dwc_device_port *hsdevp) static int sata_dwc_dma_init_old(struct platform_device *pdev, struct sata_dwc_device *hsdev) { - struct device_node *np = pdev->dev.of_node; - struct resource *res; + struct device *dev = &pdev->dev; + struct device_node *np = dev->of_node; - hsdev->dma = devm_kzalloc(&pdev->dev, sizeof(*hsdev->dma), GFP_KERNEL); + hsdev->dma = devm_kzalloc(dev, sizeof(*hsdev->dma), GFP_KERNEL); if (!hsdev->dma) return -ENOMEM; - hsdev->dma->dev = &pdev->dev; + hsdev->dma->dev = dev; hsdev->dma->id = pdev->id; /* Get SATA DMA interrupt number */ hsdev->dma->irq = irq_of_parse_and_map(np, 1); if (hsdev->dma->irq == NO_IRQ) { - dev_err(&pdev->dev, "no SATA DMA irq\n"); + dev_err(dev, "no SATA DMA irq\n"); return -ENODEV; } /* Get physical SATA DMA register base address */ - res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - hsdev->dma->regs = devm_ioremap_resource(&pdev->dev, res); + hsdev->dma->regs = devm_platform_ioremap_resource(pdev, 1); if (IS_ERR(hsdev->dma->regs)) return PTR_ERR(hsdev->dma->regs); @@ -297,35 +286,6 @@ static const char *get_prot_descript(u8 protocol) } } -static const char *get_dma_dir_descript(int dma_dir) -{ - switch ((enum dma_data_direction)dma_dir) { - case DMA_BIDIRECTIONAL: - return "bidirectional"; - case DMA_TO_DEVICE: - return "to device"; - case DMA_FROM_DEVICE: - return "from device"; - default: - return "none"; - } -} - -static void sata_dwc_tf_dump(struct ata_port *ap, struct ata_taskfile *tf) -{ - dev_vdbg(ap->dev, - "taskfile cmd: 0x%02x protocol: %s flags: 0x%lx device: %x\n", - tf->command, get_prot_descript(tf->protocol), tf->flags, - tf->device); - dev_vdbg(ap->dev, - "feature: 0x%02x nsect: 0x%x lbal: 0x%x lbam: 0x%x lbah: 0x%x\n", - tf->feature, tf->nsect, tf->lbal, tf->lbam, tf->lbah); - dev_vdbg(ap->dev, - "hob_feature: 0x%02x hob_nsect: 0x%x hob_lbal: 0x%x hob_lbam: 0x%x hob_lbah: 0x%x\n", - tf->hob_feature, tf->hob_nsect, tf->hob_lbal, tf->hob_lbam, - tf->hob_lbah); -} - static void dma_dwc_xfer_done(void *hsdev_instance) { unsigned long flags; @@ -355,7 +315,7 @@ static void dma_dwc_xfer_done(void *hsdev_instance) } if ((hsdevp->dma_interrupt_count % 2) == 0) - sata_dwc_dma_xfer_complete(ap, 1); + sata_dwc_dma_xfer_complete(ap); spin_unlock_irqrestore(&host->lock, flags); } @@ -553,6 +513,7 @@ static irqreturn_t sata_dwc_isr(int irq, void *dev_instance) * active tag. It is the tag that matches the command about to * be completed. */ + trace_ata_bmdma_start(ap, &qc->tf, tag); qc->ap->link.active_tag = tag; sata_dwc_bmdma_start_by_tag(qc, tag); @@ -586,7 +547,7 @@ static irqreturn_t sata_dwc_isr(int irq, void *dev_instance) if (status & ATA_ERR) { dev_dbg(ap->dev, "interrupt ATA_ERR (0x%x)\n", status); - sata_dwc_qc_complete(ap, qc, 1); + sata_dwc_qc_complete(ap, qc); handled = 1; goto DONE; } @@ -611,13 +572,13 @@ DRVSTILLBUSY: } if ((hsdevp->dma_interrupt_count % 2) == 0) - sata_dwc_dma_xfer_complete(ap, 1); + sata_dwc_dma_xfer_complete(ap); } else if (ata_is_pio(qc->tf.protocol)) { ata_sff_hsm_move(ap, qc, status, 0); handled = 1; goto DONE; } else { - if (unlikely(sata_dwc_qc_complete(ap, qc, 1))) + if (unlikely(sata_dwc_qc_complete(ap, qc))) goto DRVSTILLBUSY; } @@ -677,7 +638,7 @@ DRVSTILLBUSY: if (status & ATA_ERR) { dev_dbg(ap->dev, "%s ATA_ERR (0x%x)\n", __func__, status); - sata_dwc_qc_complete(ap, qc, 1); + sata_dwc_qc_complete(ap, qc); handled = 1; goto DONE; } @@ -692,9 +653,9 @@ DRVSTILLBUSY: dev_warn(ap->dev, "%s: DMA not pending?\n", __func__); if ((hsdevp->dma_interrupt_count % 2) == 0) - sata_dwc_dma_xfer_complete(ap, 1); + sata_dwc_dma_xfer_complete(ap); } else { - if (unlikely(sata_dwc_qc_complete(ap, qc, 1))) + if (unlikely(sata_dwc_qc_complete(ap, qc))) goto STILLBUSY; } continue; @@ -749,7 +710,7 @@ static void sata_dwc_clear_dmacr(struct sata_dwc_device_port *hsdevp, u8 tag) } } -static void sata_dwc_dma_xfer_complete(struct ata_port *ap, u32 check_status) +static void sata_dwc_dma_xfer_complete(struct ata_port *ap) { struct ata_queued_cmd *qc; struct sata_dwc_device_port *hsdevp = HSDEVP_FROM_AP(ap); @@ -763,17 +724,6 @@ static void sata_dwc_dma_xfer_complete(struct ata_port *ap, u32 check_status) return; } -#ifdef DEBUG_NCQ - if (tag > 0) { - dev_info(ap->dev, - "%s tag=%u cmd=0x%02x dma dir=%s proto=%s dmacr=0x%08x\n", - __func__, qc->hw_tag, qc->tf.command, - get_dma_dir_descript(qc->dma_dir), - get_prot_descript(qc->tf.protocol), - sata_dwc_readl(&hsdev->sata_dwc_regs->dmacr)); - } -#endif - if (ata_is_dma(qc->tf.protocol)) { if (hsdevp->dma_pending[tag] == SATA_DWC_DMA_PENDING_NONE) { dev_err(ap->dev, @@ -783,15 +733,14 @@ static void sata_dwc_dma_xfer_complete(struct ata_port *ap, u32 check_status) } hsdevp->dma_pending[tag] = SATA_DWC_DMA_PENDING_NONE; - sata_dwc_qc_complete(ap, qc, check_status); + sata_dwc_qc_complete(ap, qc); ap->link.active_tag = ATA_TAG_POISON; } else { - sata_dwc_qc_complete(ap, qc, check_status); + sata_dwc_qc_complete(ap, qc); } } -static int sata_dwc_qc_complete(struct ata_port *ap, struct ata_queued_cmd *qc, - u32 check_status) +static int sata_dwc_qc_complete(struct ata_port *ap, struct ata_queued_cmd *qc) { u8 status = 0; u32 mask = 0x0; @@ -799,7 +748,6 @@ static int sata_dwc_qc_complete(struct ata_port *ap, struct ata_queued_cmd *qc, struct sata_dwc_device *hsdev = HSDEV_FROM_AP(ap); struct sata_dwc_device_port *hsdevp = HSDEVP_FROM_AP(ap); hsdev->sactive_queued = 0; - dev_dbg(ap->dev, "%s checkstatus? %x\n", __func__, check_status); if (hsdevp->dma_pending[tag] == SATA_DWC_DMA_PENDING_TX) dev_err(ap->dev, "TX DMA PENDING\n"); @@ -980,9 +928,6 @@ static void sata_dwc_exec_command_by_tag(struct ata_port *ap, { struct sata_dwc_device_port *hsdevp = HSDEVP_FROM_AP(ap); - dev_dbg(ap->dev, "%s cmd(0x%02x): %s tag=%d\n", __func__, tf->command, - ata_get_cmd_descript(tf->command), tag); - hsdevp->cmd_issued[tag] = cmd_issued; /* @@ -1005,12 +950,9 @@ static void sata_dwc_bmdma_setup(struct ata_queued_cmd *qc) { u8 tag = qc->hw_tag; - if (ata_is_ncq(qc->tf.protocol)) { - dev_dbg(qc->ap->dev, "%s: ap->link.sactive=0x%08x tag=%d\n", - __func__, qc->ap->link.sactive, tag); - } else { + if (!ata_is_ncq(qc->tf.protocol)) tag = 0; - } + sata_dwc_bmdma_setup_by_tag(qc, tag); } @@ -1037,12 +979,6 @@ static void sata_dwc_bmdma_start_by_tag(struct ata_queued_cmd *qc, u8 tag) start_dma = 0; } - dev_dbg(ap->dev, - "%s qc=%p tag: %x cmd: 0x%02x dma_dir: %s start_dma? %x\n", - __func__, qc, tag, qc->tf.command, - get_dma_dir_descript(qc->dma_dir), start_dma); - sata_dwc_tf_dump(ap, &qc->tf); - if (start_dma) { sata_dwc_scr_read(&ap->link, SCR_ERROR, ®); if (reg & SATA_DWC_SERROR_ERR_BITS) { @@ -1067,13 +1003,9 @@ static void sata_dwc_bmdma_start(struct ata_queued_cmd *qc) { u8 tag = qc->hw_tag; - if (ata_is_ncq(qc->tf.protocol)) { - dev_dbg(qc->ap->dev, "%s: ap->link.sactive=0x%08x tag=%d\n", - __func__, qc->ap->link.sactive, tag); - } else { + if (!ata_is_ncq(qc->tf.protocol)) tag = 0; - } - dev_dbg(qc->ap->dev, "%s\n", __func__); + sata_dwc_bmdma_start_by_tag(qc, tag); } @@ -1084,16 +1016,6 @@ static unsigned int sata_dwc_qc_issue(struct ata_queued_cmd *qc) struct ata_port *ap = qc->ap; struct sata_dwc_device_port *hsdevp = HSDEVP_FROM_AP(ap); -#ifdef DEBUG_NCQ - if (qc->hw_tag > 0 || ap->link.sactive > 1) - dev_info(ap->dev, - "%s ap id=%d cmd(0x%02x)=%s qc tag=%d prot=%s ap active_tag=0x%08x ap sactive=0x%08x\n", - __func__, ap->print_id, qc->tf.command, - ata_get_cmd_descript(qc->tf.command), - qc->hw_tag, get_prot_descript(qc->tf.protocol), - ap->link.active_tag, ap->link.sactive); -#endif - if (!ata_is_ncq(qc->tf.protocol)) tag = 0; @@ -1110,11 +1032,9 @@ static unsigned int sata_dwc_qc_issue(struct ata_queued_cmd *qc) sactive |= (0x00000001 << tag); sata_dwc_scr_write(&ap->link, SCR_ACTIVE, sactive); - dev_dbg(qc->ap->dev, - "%s: tag=%d ap->link.sactive = 0x%08x sactive=0x%08x\n", - __func__, tag, qc->ap->link.sactive, sactive); - + trace_ata_tf_load(ap, &qc->tf); ap->ops->sff_tf_load(ap, &qc->tf); + trace_ata_exec_command(ap, &qc->tf, tag); sata_dwc_exec_command_by_tag(ap, &qc->tf, tag, SATA_DWC_CMD_ISSUED_PEND); } else { @@ -1207,6 +1127,8 @@ static const struct ata_port_info sata_dwc_port_info[] = { static int sata_dwc_probe(struct platform_device *ofdev) { + struct device *dev = &ofdev->dev; + struct device_node *np = dev->of_node; struct sata_dwc_device *hsdev; u32 idr, versionr; char *ver = (char *)&versionr; @@ -1216,23 +1138,21 @@ static int sata_dwc_probe(struct platform_device *ofdev) struct ata_host *host; struct ata_port_info pi = sata_dwc_port_info[0]; const struct ata_port_info *ppi[] = { &pi, NULL }; - struct device_node *np = ofdev->dev.of_node; struct resource *res; /* Allocate DWC SATA device */ - host = ata_host_alloc_pinfo(&ofdev->dev, ppi, SATA_DWC_MAX_PORTS); - hsdev = devm_kzalloc(&ofdev->dev, sizeof(*hsdev), GFP_KERNEL); + host = ata_host_alloc_pinfo(dev, ppi, SATA_DWC_MAX_PORTS); + hsdev = devm_kzalloc(dev, sizeof(*hsdev), GFP_KERNEL); if (!host || !hsdev) return -ENOMEM; host->private_data = hsdev; /* Ioremap SATA registers */ - res = platform_get_resource(ofdev, IORESOURCE_MEM, 0); - base = devm_ioremap_resource(&ofdev->dev, res); + base = devm_platform_get_and_ioremap_resource(ofdev, 0, &res); if (IS_ERR(base)) return PTR_ERR(base); - dev_dbg(&ofdev->dev, "ioremap done for SATA register address\n"); + dev_dbg(dev, "ioremap done for SATA register address\n"); /* Synopsys DWC SATA specific Registers */ hsdev->sata_dwc_regs = base + SATA_DWC_REG_OFFSET; @@ -1246,11 +1166,10 @@ static int sata_dwc_probe(struct platform_device *ofdev) /* Read the ID and Version Registers */ idr = sata_dwc_readl(&hsdev->sata_dwc_regs->idr); versionr = sata_dwc_readl(&hsdev->sata_dwc_regs->versionr); - dev_notice(&ofdev->dev, "id %d, controller version %c.%c%c\n", - idr, ver[0], ver[1], ver[2]); + dev_notice(dev, "id %d, controller version %c.%c%c\n", idr, ver[0], ver[1], ver[2]); /* Save dev for later use in dev_xxx() routines */ - hsdev->dev = &ofdev->dev; + hsdev->dev = dev; /* Enable SATA Interrupts */ sata_dwc_enable_interrupts(hsdev); @@ -1258,7 +1177,7 @@ static int sata_dwc_probe(struct platform_device *ofdev) /* Get SATA interrupt number */ irq = irq_of_parse_and_map(np, 0); if (irq == NO_IRQ) { - dev_err(&ofdev->dev, "no SATA DMA irq\n"); + dev_err(dev, "no SATA DMA irq\n"); return -ENODEV; } @@ -1270,7 +1189,7 @@ static int sata_dwc_probe(struct platform_device *ofdev) } #endif - hsdev->phy = devm_phy_optional_get(hsdev->dev, "sata-phy"); + hsdev->phy = devm_phy_optional_get(dev, "sata-phy"); if (IS_ERR(hsdev->phy)) return PTR_ERR(hsdev->phy); @@ -1285,7 +1204,7 @@ static int sata_dwc_probe(struct platform_device *ofdev) */ err = ata_host_activate(host, irq, sata_dwc_isr, 0, &sata_dwc_sht); if (err) - dev_err(&ofdev->dev, "failed to activate host"); + dev_err(dev, "failed to activate host"); return 0; @@ -1309,7 +1228,7 @@ static int sata_dwc_remove(struct platform_device *ofdev) sata_dwc_dma_exit_old(hsdev); #endif - dev_dbg(&ofdev->dev, "done\n"); + dev_dbg(dev, "done\n"); return 0; } diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c index 3b31a4f596d8..da0152116d9f 100644 --- a/drivers/ata/sata_fsl.c +++ b/drivers/ata/sata_fsl.c @@ -221,10 +221,10 @@ enum { * 4 Dwords per command slot, command header size == 64 Dwords. */ struct cmdhdr_tbl_entry { - u32 cda; - u32 prde_fis_len; - u32 ttl; - u32 desc_info; + __le32 cda; + __le32 prde_fis_len; + __le32 ttl; + __le32 desc_info; }; /* @@ -246,8 +246,10 @@ enum { struct command_desc { u8 cfis[8 * 4]; u8 sfis[8 * 4]; - u8 acmd[4 * 4]; - u8 fill[4 * 4]; + struct_group(cdb, + u8 acmd[4 * 4]; + u8 fill[4 * 4]; + ); u32 prdt[SATA_FSL_MAX_PRD_DIRECT * 4]; u32 prdt_indirect[(SATA_FSL_MAX_PRD - SATA_FSL_MAX_PRD_DIRECT) * 4]; }; @@ -257,9 +259,9 @@ struct command_desc { */ struct prde { - u32 dba; + __le32 dba; u8 fill[2 * 4]; - u32 ddc_and_ext; + __le32 ddc_and_ext; }; /* @@ -311,16 +313,16 @@ static void fsl_sata_set_irq_coalescing(struct ata_host *host, intr_coalescing_ticks = ticks; spin_unlock_irqrestore(&host->lock, flags); - DPRINTK("interrupt coalescing, count = 0x%x, ticks = %x\n", - intr_coalescing_count, intr_coalescing_ticks); - DPRINTK("ICC register status: (hcr base: %p) = 0x%x\n", - hcr_base, ioread32(hcr_base + ICC)); + dev_dbg(host->dev, "interrupt coalescing, count = 0x%x, ticks = %x\n", + intr_coalescing_count, intr_coalescing_ticks); + dev_dbg(host->dev, "ICC register status: (hcr base: 0x%p) = 0x%x\n", + hcr_base, ioread32(hcr_base + ICC)); } static ssize_t fsl_sata_intr_coalescing_show(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "%d %d\n", + return sysfs_emit(buf, "%d %d\n", intr_coalescing_count, intr_coalescing_ticks); } @@ -355,9 +357,9 @@ static ssize_t fsl_sata_rx_watermark_show(struct device *dev, spin_lock_irqsave(&host->lock, flags); rx_watermark = ioread32(csr_base + TRANSCFG); rx_watermark &= 0x1f; - spin_unlock_irqrestore(&host->lock, flags); - return sprintf(buf, "%d\n", rx_watermark); + + return sysfs_emit(buf, "%d\n", rx_watermark); } static ssize_t fsl_sata_rx_watermark_store(struct device *dev, @@ -385,25 +387,27 @@ static ssize_t fsl_sata_rx_watermark_store(struct device *dev, return strlen(buf); } -static inline unsigned int sata_fsl_tag(unsigned int tag, +static inline unsigned int sata_fsl_tag(struct ata_port *ap, + unsigned int tag, void __iomem *hcr_base) { /* We let libATA core do actual (queue) tag allocation */ if (unlikely(tag >= SATA_FSL_QUEUE_DEPTH)) { - DPRINTK("tag %d invalid : out of range\n", tag); + ata_port_dbg(ap, "tag %d invalid : out of range\n", tag); return 0; } if (unlikely((ioread32(hcr_base + CQ)) & (1 << tag))) { - DPRINTK("tag %d invalid : in use!!\n", tag); + ata_port_dbg(ap, "tag %d invalid : in use!!\n", tag); return 0; } return tag; } -static void sata_fsl_setup_cmd_hdr_entry(struct sata_fsl_port_priv *pp, +static void sata_fsl_setup_cmd_hdr_entry(struct ata_port *ap, + struct sata_fsl_port_priv *pp, unsigned int tag, u32 desc_info, u32 data_xfer_len, u8 num_prde, u8 fis_len) @@ -421,11 +425,11 @@ static void sata_fsl_setup_cmd_hdr_entry(struct sata_fsl_port_priv *pp, pp->cmdslot[tag].ttl = cpu_to_le32(data_xfer_len & ~0x03); pp->cmdslot[tag].desc_info = cpu_to_le32(desc_info | (tag & 0x1F)); - VPRINTK("cda=0x%x, prde_fis_len=0x%x, ttl=0x%x, di=0x%x\n", - pp->cmdslot[tag].cda, - pp->cmdslot[tag].prde_fis_len, - pp->cmdslot[tag].ttl, pp->cmdslot[tag].desc_info); - + ata_port_dbg(ap, "cda=0x%x, prde_fis_len=0x%x, ttl=0x%x, di=0x%x\n", + le32_to_cpu(pp->cmdslot[tag].cda), + le32_to_cpu(pp->cmdslot[tag].prde_fis_len), + le32_to_cpu(pp->cmdslot[tag].ttl), + le32_to_cpu(pp->cmdslot[tag].desc_info)); } static unsigned int sata_fsl_fill_sg(struct ata_queued_cmd *qc, void *cmd_desc, @@ -447,8 +451,6 @@ static unsigned int sata_fsl_fill_sg(struct ata_queued_cmd *qc, void *cmd_desc, dma_addr_t indirect_ext_segment_paddr; unsigned int si; - VPRINTK("SATA FSL : cd = 0x%p, prd = 0x%p\n", cmd_desc, prd); - indirect_ext_segment_paddr = cmd_desc_paddr + SATA_FSL_CMD_DESC_OFFSET_TO_PRDT + SATA_FSL_MAX_PRD_DIRECT * 16; @@ -456,9 +458,6 @@ static unsigned int sata_fsl_fill_sg(struct ata_queued_cmd *qc, void *cmd_desc, dma_addr_t sg_addr = sg_dma_address(sg); u32 sg_len = sg_dma_len(sg); - VPRINTK("SATA FSL : fill_sg, sg_addr = 0x%llx, sg_len = %d\n", - (unsigned long long)sg_addr, sg_len); - /* warn if each s/g element is not dword aligned */ if (unlikely(sg_addr & 0x03)) ata_port_err(qc->ap, "s/g addr unaligned : 0x%llx\n", @@ -469,7 +468,6 @@ static unsigned int sata_fsl_fill_sg(struct ata_queued_cmd *qc, void *cmd_desc, if (num_prde == (SATA_FSL_MAX_PRD_DIRECT - 1) && sg_next(sg) != NULL) { - VPRINTK("setting indirect prde\n"); prd_ptr_to_indirect_ext = prd; prd->dba = cpu_to_le32(indirect_ext_segment_paddr); indirect_ext_segment_sz = 0; @@ -481,9 +479,6 @@ static unsigned int sata_fsl_fill_sg(struct ata_queued_cmd *qc, void *cmd_desc, prd->dba = cpu_to_le32(sg_addr); prd->ddc_and_ext = cpu_to_le32(data_snoop | (sg_len & ~0x03)); - VPRINTK("sg_fill, ttl=%d, dba=0x%x, ddc=0x%x\n", - ttl_dwords, prd->dba, prd->ddc_and_ext); - ++num_prde; ++prd; if (prd_ptr_to_indirect_ext) @@ -508,7 +503,7 @@ static enum ata_completion_errors sata_fsl_qc_prep(struct ata_queued_cmd *qc) struct sata_fsl_port_priv *pp = ap->private_data; struct sata_fsl_host_priv *host_priv = ap->host->private_data; void __iomem *hcr_base = host_priv->hcr_base; - unsigned int tag = sata_fsl_tag(qc->hw_tag, hcr_base); + unsigned int tag = sata_fsl_tag(ap, qc->hw_tag, hcr_base); struct command_desc *cd; u32 desc_info = CMD_DESC_RES | CMD_DESC_SNOOP_ENABLE; u32 num_prde = 0; @@ -520,19 +515,11 @@ static enum ata_completion_errors sata_fsl_qc_prep(struct ata_queued_cmd *qc) ata_tf_to_fis(&qc->tf, qc->dev->link->pmp, 1, (u8 *) &cd->cfis); - VPRINTK("Dumping cfis : 0x%x, 0x%x, 0x%x\n", - cd->cfis[0], cd->cfis[1], cd->cfis[2]); - - if (qc->tf.protocol == ATA_PROT_NCQ) { - VPRINTK("FPDMA xfer,Sctor cnt[0:7],[8:15] = %d,%d\n", - cd->cfis[3], cd->cfis[11]); - } - /* setup "ACMD - atapi command" in cmd. desc. if this is ATAPI cmd */ if (ata_is_atapi(qc->tf.protocol)) { desc_info |= ATAPI_CMD; - memset((void *)&cd->acmd, 0, 32); - memcpy((void *)&cd->acmd, qc->cdb, qc->dev->cdb_len); + memset(&cd->cdb, 0, sizeof(cd->cdb)); + memcpy(&cd->cdb, qc->cdb, qc->dev->cdb_len); } if (qc->flags & ATA_QCFLAG_DMAMAP) @@ -543,10 +530,10 @@ static enum ata_completion_errors sata_fsl_qc_prep(struct ata_queued_cmd *qc) if (qc->tf.protocol == ATA_PROT_NCQ) desc_info |= FPDMA_QUEUED_CMD; - sata_fsl_setup_cmd_hdr_entry(pp, tag, desc_info, ttl_dwords, + sata_fsl_setup_cmd_hdr_entry(ap, pp, tag, desc_info, ttl_dwords, num_prde, 5); - VPRINTK("SATA FSL : xx_qc_prep, di = 0x%x, ttl = %d, num_prde = %d\n", + ata_port_dbg(ap, "SATA FSL : di = 0x%x, ttl = %d, num_prde = %d\n", desc_info, ttl_dwords, num_prde); return AC_ERR_OK; @@ -557,9 +544,9 @@ static unsigned int sata_fsl_qc_issue(struct ata_queued_cmd *qc) struct ata_port *ap = qc->ap; struct sata_fsl_host_priv *host_priv = ap->host->private_data; void __iomem *hcr_base = host_priv->hcr_base; - unsigned int tag = sata_fsl_tag(qc->hw_tag, hcr_base); + unsigned int tag = sata_fsl_tag(ap, qc->hw_tag, hcr_base); - VPRINTK("xx_qc_issue called,CQ=0x%x,CA=0x%x,CE=0x%x,CC=0x%x\n", + ata_port_dbg(ap, "CQ=0x%x,CA=0x%x,CE=0x%x,CC=0x%x\n", ioread32(CQ + hcr_base), ioread32(CA + hcr_base), ioread32(CE + hcr_base), ioread32(CC + hcr_base)); @@ -569,10 +556,10 @@ static unsigned int sata_fsl_qc_issue(struct ata_queued_cmd *qc) /* Simply queue command to the controller/device */ iowrite32(1 << tag, CQ + hcr_base); - VPRINTK("xx_qc_issue called, tag=%d, CQ=0x%x, CA=0x%x\n", + ata_port_dbg(ap, "tag=%d, CQ=0x%x, CA=0x%x\n", tag, ioread32(CQ + hcr_base), ioread32(CA + hcr_base)); - VPRINTK("CE=0x%x, DE=0x%x, CC=0x%x, CmdStat = 0x%x\n", + ata_port_dbg(ap, "CE=0x%x, DE=0x%x, CC=0x%x, CmdStat = 0x%x\n", ioread32(CE + hcr_base), ioread32(DE + hcr_base), ioread32(CC + hcr_base), @@ -586,7 +573,7 @@ static bool sata_fsl_qc_fill_rtf(struct ata_queued_cmd *qc) struct sata_fsl_port_priv *pp = qc->ap->private_data; struct sata_fsl_host_priv *host_priv = qc->ap->host->private_data; void __iomem *hcr_base = host_priv->hcr_base; - unsigned int tag = sata_fsl_tag(qc->hw_tag, hcr_base); + unsigned int tag = sata_fsl_tag(qc->ap, qc->hw_tag, hcr_base); struct command_desc *cd; cd = pp->cmdentry + tag; @@ -613,7 +600,7 @@ static int sata_fsl_scr_write(struct ata_link *link, return -EINVAL; } - VPRINTK("xx_scr_write, reg_in = %d\n", sc_reg); + ata_link_dbg(link, "reg_in = %d\n", sc_reg); iowrite32(val, ssr_base + (sc_reg * 4)); return 0; @@ -637,7 +624,7 @@ static int sata_fsl_scr_read(struct ata_link *link, return -EINVAL; } - VPRINTK("xx_scr_read, reg_in = %d\n", sc_reg); + ata_link_dbg(link, "reg_in = %d\n", sc_reg); *val = ioread32(ssr_base + (sc_reg * 4)); return 0; @@ -649,18 +636,18 @@ static void sata_fsl_freeze(struct ata_port *ap) void __iomem *hcr_base = host_priv->hcr_base; u32 temp; - VPRINTK("xx_freeze, CQ=0x%x, CA=0x%x, CE=0x%x, DE=0x%x\n", + ata_port_dbg(ap, "CQ=0x%x, CA=0x%x, CE=0x%x, DE=0x%x\n", ioread32(CQ + hcr_base), ioread32(CA + hcr_base), ioread32(CE + hcr_base), ioread32(DE + hcr_base)); - VPRINTK("CmdStat = 0x%x\n", + ata_port_dbg(ap, "CmdStat = 0x%x\n", ioread32(host_priv->csr_base + COMMANDSTAT)); /* disable interrupts on the controller/port */ temp = ioread32(hcr_base + HCONTROL); iowrite32((temp & ~0x3F), hcr_base + HCONTROL); - VPRINTK("in xx_freeze : HControl = 0x%x, HStatus = 0x%x\n", + ata_port_dbg(ap, "HControl = 0x%x, HStatus = 0x%x\n", ioread32(hcr_base + HCONTROL), ioread32(hcr_base + HSTATUS)); } @@ -673,7 +660,7 @@ static void sata_fsl_thaw(struct ata_port *ap) /* ack. any pending IRQs for this controller/port */ temp = ioread32(hcr_base + HSTATUS); - VPRINTK("xx_thaw, pending IRQs = 0x%x\n", (temp & 0x3F)); + ata_port_dbg(ap, "pending IRQs = 0x%x\n", (temp & 0x3F)); if (temp & 0x3F) iowrite32((temp & 0x3F), hcr_base + HSTATUS); @@ -682,7 +669,7 @@ static void sata_fsl_thaw(struct ata_port *ap) temp = ioread32(hcr_base + HCONTROL); iowrite32((temp | DEFAULT_PORT_IRQ_ENABLE_MASK), hcr_base + HCONTROL); - VPRINTK("xx_thaw : HControl = 0x%x, HStatus = 0x%x\n", + ata_port_dbg(ap, "HControl = 0x%x, HStatus = 0x%x\n", ioread32(hcr_base + HCONTROL), ioread32(hcr_base + HSTATUS)); } @@ -744,8 +731,9 @@ static int sata_fsl_port_start(struct ata_port *ap) ap->private_data = pp; - VPRINTK("CHBA = 0x%x, cmdentry_phys = 0x%x\n", - pp->cmdslot_paddr, pp->cmdentry_paddr); + ata_port_dbg(ap, "CHBA = 0x%lx, cmdentry_phys = 0x%lx\n", + (unsigned long)pp->cmdslot_paddr, + (unsigned long)pp->cmdentry_paddr); /* Now, update the CHBA register in host controller cmd register set */ iowrite32(pp->cmdslot_paddr & 0xffffffff, hcr_base + CHBA); @@ -761,9 +749,9 @@ static int sata_fsl_port_start(struct ata_port *ap) temp = ioread32(hcr_base + HCONTROL); iowrite32((temp | HCONTROL_ONLINE_PHY_RST), hcr_base + HCONTROL); - VPRINTK("HStatus = 0x%x\n", ioread32(hcr_base + HSTATUS)); - VPRINTK("HControl = 0x%x\n", ioread32(hcr_base + HCONTROL)); - VPRINTK("CHBA = 0x%x\n", ioread32(hcr_base + CHBA)); + ata_port_dbg(ap, "HStatus = 0x%x\n", ioread32(hcr_base + HSTATUS)); + ata_port_dbg(ap, "HControl = 0x%x\n", ioread32(hcr_base + HCONTROL)); + ata_port_dbg(ap, "CHBA = 0x%x\n", ioread32(hcr_base + CHBA)); return 0; } @@ -803,16 +791,15 @@ static unsigned int sata_fsl_dev_classify(struct ata_port *ap) temp = ioread32(hcr_base + SIGNATURE); - VPRINTK("raw sig = 0x%x\n", temp); - VPRINTK("HStatus = 0x%x\n", ioread32(hcr_base + HSTATUS)); - VPRINTK("HControl = 0x%x\n", ioread32(hcr_base + HCONTROL)); + ata_port_dbg(ap, "HStatus = 0x%x\n", ioread32(hcr_base + HSTATUS)); + ata_port_dbg(ap, "HControl = 0x%x\n", ioread32(hcr_base + HCONTROL)); tf.lbah = (temp >> 24) & 0xff; tf.lbam = (temp >> 16) & 0xff; tf.lbal = (temp >> 8) & 0xff; tf.nsect = temp & 0xff; - return ata_dev_classify(&tf); + return ata_port_classify(ap, &tf); } static int sata_fsl_hardreset(struct ata_link *link, unsigned int *class, @@ -825,8 +812,6 @@ static int sata_fsl_hardreset(struct ata_link *link, unsigned int *class, int i = 0; unsigned long start_jiffies; - DPRINTK("in xx_hardreset\n"); - try_offline_again: /* * Force host controller to go off-line, aborting current operations @@ -852,9 +837,10 @@ try_offline_again: goto try_offline_again; } - DPRINTK("hardreset, controller off-lined\n"); - VPRINTK("HStatus = 0x%x\n", ioread32(hcr_base + HSTATUS)); - VPRINTK("HControl = 0x%x\n", ioread32(hcr_base + HCONTROL)); + ata_port_dbg(ap, "hardreset, controller off-lined\n" + "HStatus = 0x%x HControl = 0x%x\n", + ioread32(hcr_base + HSTATUS), + ioread32(hcr_base + HCONTROL)); /* * PHY reset should remain asserted for atleast 1ms @@ -882,9 +868,10 @@ try_offline_again: goto err; } - DPRINTK("hardreset, controller off-lined & on-lined\n"); - VPRINTK("HStatus = 0x%x\n", ioread32(hcr_base + HSTATUS)); - VPRINTK("HControl = 0x%x\n", ioread32(hcr_base + HCONTROL)); + ata_port_dbg(ap, "controller off-lined & on-lined\n" + "HStatus = 0x%x HControl = 0x%x\n", + ioread32(hcr_base + HSTATUS), + ioread32(hcr_base + HCONTROL)); /* * First, wait for the PHYRDY change to occur before waiting for @@ -941,10 +928,7 @@ static int sata_fsl_softreset(struct ata_link *link, unsigned int *class, u8 *cfis; u32 Serror; - DPRINTK("in xx_softreset\n"); - if (ata_link_offline(link)) { - DPRINTK("PHY reports no device\n"); *class = ATA_DEV_NONE; return 0; } @@ -957,19 +941,17 @@ static int sata_fsl_softreset(struct ata_link *link, unsigned int *class, * reached here, we can send a command to the target device */ - DPRINTK("Sending SRST/device reset\n"); - ata_tf_init(link->device, &tf); cfis = (u8 *) &pp->cmdentry->cfis; /* device reset/SRST is a control register update FIS, uses tag0 */ - sata_fsl_setup_cmd_hdr_entry(pp, 0, + sata_fsl_setup_cmd_hdr_entry(ap, pp, 0, SRST_CMD | CMD_DESC_RES | CMD_DESC_SNOOP_ENABLE, 0, 0, 5); tf.ctl |= ATA_SRST; /* setup SRST bit in taskfile control reg */ ata_tf_to_fis(&tf, pmp, 0, cfis); - DPRINTK("Dumping cfis : 0x%x, 0x%x, 0x%x, 0x%x\n", + ata_port_dbg(ap, "Dumping cfis : 0x%x, 0x%x, 0x%x, 0x%x\n", cfis[0], cfis[1], cfis[2], cfis[3]); /* @@ -977,7 +959,7 @@ static int sata_fsl_softreset(struct ata_link *link, unsigned int *class, * other commands are active on the controller/device */ - DPRINTK("@Softreset, CQ = 0x%x, CA = 0x%x, CC = 0x%x\n", + ata_port_dbg(ap, "CQ = 0x%x, CA = 0x%x, CC = 0x%x\n", ioread32(CQ + hcr_base), ioread32(CA + hcr_base), ioread32(CC + hcr_base)); @@ -990,15 +972,16 @@ static int sata_fsl_softreset(struct ata_link *link, unsigned int *class, if (temp & 0x1) { ata_port_warn(ap, "ATA_SRST issue failed\n"); - DPRINTK("Softreset@5000,CQ=0x%x,CA=0x%x,CC=0x%x\n", + ata_port_dbg(ap, "Softreset@5000,CQ=0x%x,CA=0x%x,CC=0x%x\n", ioread32(CQ + hcr_base), ioread32(CA + hcr_base), ioread32(CC + hcr_base)); sata_fsl_scr_read(&ap->link, SCR_ERROR, &Serror); - DPRINTK("HStatus = 0x%x\n", ioread32(hcr_base + HSTATUS)); - DPRINTK("HControl = 0x%x\n", ioread32(hcr_base + HCONTROL)); - DPRINTK("Serror = 0x%x\n", Serror); + ata_port_dbg(ap, "HStatus = 0x%x HControl = 0x%x Serror = 0x%x\n", + ioread32(hcr_base + HSTATUS), + ioread32(hcr_base + HCONTROL), + Serror); goto err; } @@ -1012,8 +995,9 @@ static int sata_fsl_softreset(struct ata_link *link, unsigned int *class, * using ATA signature D2H register FIS to the host controller. */ - sata_fsl_setup_cmd_hdr_entry(pp, 0, CMD_DESC_RES | CMD_DESC_SNOOP_ENABLE, - 0, 0, 5); + sata_fsl_setup_cmd_hdr_entry(ap, pp, 0, + CMD_DESC_RES | CMD_DESC_SNOOP_ENABLE, + 0, 0, 5); tf.ctl &= ~ATA_SRST; /* 2nd H2D Ctl. register FIS */ ata_tf_to_fis(&tf, pmp, 0, cfis); @@ -1030,8 +1014,6 @@ static int sata_fsl_softreset(struct ata_link *link, unsigned int *class, */ iowrite32(0x01, CC + hcr_base); /* We know it will be cmd#0 always */ - DPRINTK("SATA FSL : Now checking device signature\n"); - *class = ATA_DEV_NONE; /* Verify if SStatus indicates device presence */ @@ -1045,9 +1027,8 @@ static int sata_fsl_softreset(struct ata_link *link, unsigned int *class, *class = sata_fsl_dev_classify(ap); - DPRINTK("class = %d\n", *class); - VPRINTK("ccreg = 0x%x\n", ioread32(hcr_base + CC)); - VPRINTK("cereg = 0x%x\n", ioread32(hcr_base + CE)); + ata_port_dbg(ap, "ccreg = 0x%x\n", ioread32(hcr_base + CC)); + ata_port_dbg(ap, "cereg = 0x%x\n", ioread32(hcr_base + CE)); } return 0; @@ -1058,10 +1039,7 @@ err: static void sata_fsl_error_handler(struct ata_port *ap) { - - DPRINTK("in xx_error_handler\n"); sata_pmp_error_handler(ap); - } static void sata_fsl_post_internal_cmd(struct ata_queued_cmd *qc) @@ -1102,7 +1080,7 @@ static void sata_fsl_error_intr(struct ata_port *ap) if (unlikely(SError & 0xFFFF0000)) sata_fsl_scr_write(&ap->link, SCR_ERROR, SError); - DPRINTK("error_intr,hStat=0x%x,CE=0x%x,DE =0x%x,SErr=0x%x\n", + ata_port_dbg(ap, "hStat=0x%x,CE=0x%x,DE =0x%x,SErr=0x%x\n", hstatus, cereg, ioread32(hcr_base + DE), SError); /* handle fatal errors */ @@ -1119,7 +1097,7 @@ static void sata_fsl_error_intr(struct ata_port *ap) /* Handle PHYRDY change notification */ if (hstatus & INT_ON_PHYRDY_CHG) { - DPRINTK("SATA FSL: PHYRDY change indication\n"); + ata_port_dbg(ap, "PHYRDY change indication\n"); /* Setup a soft-reset EH action */ ata_ehi_hotplugged(ehi); @@ -1140,7 +1118,7 @@ static void sata_fsl_error_intr(struct ata_port *ap) */ abort = 1; - DPRINTK("single device error, CE=0x%x, DE=0x%x\n", + ata_port_dbg(ap, "single device error, CE=0x%x, DE=0x%x\n", ioread32(hcr_base + CE), ioread32(hcr_base + DE)); /* find out the offending link and qc */ @@ -1245,18 +1223,18 @@ static void sata_fsl_host_intr(struct ata_port *ap) } if (unlikely(SError & 0xFFFF0000)) { - DPRINTK("serror @host_intr : 0x%x\n", SError); + ata_port_dbg(ap, "serror @host_intr : 0x%x\n", SError); sata_fsl_error_intr(ap); } if (unlikely(hstatus & status_mask)) { - DPRINTK("error interrupt!!\n"); + ata_port_dbg(ap, "error interrupt!!\n"); sata_fsl_error_intr(ap); return; } - VPRINTK("Status of all queues :\n"); - VPRINTK("done_mask/CC = 0x%x, CA = 0x%x, CE=0x%x,CQ=0x%x,apqa=0x%llx\n", + ata_port_dbg(ap, "Status of all queues :\n"); + ata_port_dbg(ap, "done_mask/CC = 0x%x, CA = 0x%x, CE=0x%x,CQ=0x%x,apqa=0x%llx\n", done_mask, ioread32(hcr_base + CA), ioread32(hcr_base + CE), @@ -1268,15 +1246,13 @@ static void sata_fsl_host_intr(struct ata_port *ap) /* clear CC bit, this will also complete the interrupt */ iowrite32(done_mask, hcr_base + CC); - DPRINTK("Status of all queues :\n"); - DPRINTK("done_mask/CC = 0x%x, CA = 0x%x, CE=0x%x\n", + ata_port_dbg(ap, "Status of all queues: done_mask/CC = 0x%x, CA = 0x%x, CE=0x%x\n", done_mask, ioread32(hcr_base + CA), ioread32(hcr_base + CE)); for (i = 0; i < SATA_FSL_QUEUE_DEPTH; i++) { if (done_mask & (1 << i)) - DPRINTK - ("completing ncq cmd,tag=%d,CC=0x%x,CA=0x%x\n", + ata_port_dbg(ap, "completing ncq cmd,tag=%d,CC=0x%x,CA=0x%x\n", i, ioread32(hcr_base + CC), ioread32(hcr_base + CA)); } @@ -1287,7 +1263,7 @@ static void sata_fsl_host_intr(struct ata_port *ap) iowrite32(1, hcr_base + CC); qc = ata_qc_from_tag(ap, ATA_TAG_INTERNAL); - DPRINTK("completing non-ncq cmd, CC=0x%x\n", + ata_port_dbg(ap, "completing non-ncq cmd, CC=0x%x\n", ioread32(hcr_base + CC)); if (qc) { @@ -1295,7 +1271,7 @@ static void sata_fsl_host_intr(struct ata_port *ap) } } else { /* Spurious Interrupt!! */ - DPRINTK("spurious interrupt!!, CC = 0x%x\n", + ata_port_dbg(ap, "spurious interrupt!!, CC = 0x%x\n", ioread32(hcr_base + CC)); iowrite32(done_mask, hcr_base + CC); return; @@ -1315,8 +1291,6 @@ static irqreturn_t sata_fsl_interrupt(int irq, void *dev_instance) interrupt_enables = ioread32(hcr_base + HSTATUS); interrupt_enables &= 0x3F; - DPRINTK("interrupt status 0x%x\n", interrupt_enables); - if (!interrupt_enables) return IRQ_NONE; @@ -1369,7 +1343,7 @@ static int sata_fsl_init_controller(struct ata_host *host) iowrite32((temp & ~0x3F), hcr_base + HCONTROL); /* Disable interrupt coalescing control(icc), for the moment */ - DPRINTK("icc = 0x%x\n", ioread32(hcr_base + ICC)); + dev_dbg(host->dev, "icc = 0x%x\n", ioread32(hcr_base + ICC)); iowrite32(0x01000000, hcr_base + ICC); /* clear error registers, SError is cleared by libATA */ @@ -1388,8 +1362,8 @@ static int sata_fsl_init_controller(struct ata_host *host) * callback, that should also initiate the OOB, COMINIT sequence */ - DPRINTK("HStatus = 0x%x\n", ioread32(hcr_base + HSTATUS)); - DPRINTK("HControl = 0x%x\n", ioread32(hcr_base + HCONTROL)); + dev_dbg(host->dev, "HStatus = 0x%x HControl = 0x%x\n", + ioread32(hcr_base + HSTATUS), ioread32(hcr_base + HCONTROL)); return 0; } @@ -1406,8 +1380,7 @@ static void sata_fsl_host_stop(struct ata_host *host) * scsi mid-layer and libata interface structures */ static struct scsi_host_template sata_fsl_sht = { - ATA_NCQ_SHT("sata_fsl"), - .can_queue = SATA_FSL_QUEUE_DEPTH, + ATA_NCQ_SHT_QD("sata_fsl", SATA_FSL_QUEUE_DEPTH), .sg_tablesize = SATA_FSL_MAX_PRD_USABLE, .dma_boundary = ATA_DMA_BOUNDARY, }; @@ -1478,9 +1451,8 @@ static int sata_fsl_probe(struct platform_device *ofdev) iowrite32(temp | TRANSCFG_RX_WATER_MARK, csr_base + TRANSCFG); } - DPRINTK("@reset i/o = 0x%x\n", ioread32(csr_base + TRANSCFG)); - DPRINTK("sizeof(cmd_desc) = %d\n", sizeof(struct command_desc)); - DPRINTK("sizeof(#define cmd_desc) = %d\n", SATA_FSL_CMD_DESC_SIZE); + dev_dbg(&ofdev->dev, "@reset i/o = 0x%x\n", + ioread32(csr_base + TRANSCFG)); host_priv = kzalloc(sizeof(struct sata_fsl_host_priv), GFP_KERNEL); if (!host_priv) diff --git a/drivers/ata/sata_gemini.c b/drivers/ata/sata_gemini.c index f793564f3d78..440a63de20d0 100644 --- a/drivers/ata/sata_gemini.c +++ b/drivers/ata/sata_gemini.c @@ -253,12 +253,12 @@ static int gemini_sata_bridge_init(struct sata_gemini *sg) ret = clk_prepare_enable(sg->sata0_pclk); if (ret) { - pr_err("failed to enable SATA0 PCLK\n"); + dev_err(dev, "failed to enable SATA0 PCLK\n"); return ret; } ret = clk_prepare_enable(sg->sata1_pclk); if (ret) { - pr_err("failed to enable SATA1 PCLK\n"); + dev_err(dev, "failed to enable SATA1 PCLK\n"); clk_disable_unprepare(sg->sata0_pclk); return ret; } diff --git a/drivers/ata/sata_inic162x.c b/drivers/ata/sata_inic162x.c index e517bd8822a5..781901151d82 100644 --- a/drivers/ata/sata_inic162x.c +++ b/drivers/ata/sata_inic162x.c @@ -488,8 +488,6 @@ static enum ata_completion_errors inic_qc_prep(struct ata_queued_cmd *qc) bool is_data = ata_is_data(qc->tf.protocol); unsigned int cdb_len = 0; - VPRINTK("ENTER\n"); - if (is_atapi) cdb_len = qc->dev->cdb_len; @@ -657,7 +655,7 @@ static int inic_hardreset(struct ata_link *link, unsigned int *class, } inic_tf_read(ap, &tf); - *class = ata_dev_classify(&tf); + *class = ata_port_classify(ap, &tf); } return 0; diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c index cae4c1eab102..53446b997740 100644 --- a/drivers/ata/sata_mv.c +++ b/drivers/ata/sata_mv.c @@ -579,7 +579,7 @@ struct mv_hw_ops { void (*enable_leds)(struct mv_host_priv *hpriv, void __iomem *mmio); void (*read_preamp)(struct mv_host_priv *hpriv, int idx, void __iomem *mmio); - int (*reset_hc)(struct mv_host_priv *hpriv, void __iomem *mmio, + int (*reset_hc)(struct ata_host *host, void __iomem *mmio, unsigned int n_hc); void (*reset_flash)(struct mv_host_priv *hpriv, void __iomem *mmio); void (*reset_bus)(struct ata_host *host, void __iomem *mmio); @@ -606,7 +606,7 @@ static void mv5_phy_errata(struct mv_host_priv *hpriv, void __iomem *mmio, static void mv5_enable_leds(struct mv_host_priv *hpriv, void __iomem *mmio); static void mv5_read_preamp(struct mv_host_priv *hpriv, int idx, void __iomem *mmio); -static int mv5_reset_hc(struct mv_host_priv *hpriv, void __iomem *mmio, +static int mv5_reset_hc(struct ata_host *host, void __iomem *mmio, unsigned int n_hc); static void mv5_reset_flash(struct mv_host_priv *hpriv, void __iomem *mmio); static void mv5_reset_bus(struct ata_host *host, void __iomem *mmio); @@ -616,14 +616,14 @@ static void mv6_phy_errata(struct mv_host_priv *hpriv, void __iomem *mmio, static void mv6_enable_leds(struct mv_host_priv *hpriv, void __iomem *mmio); static void mv6_read_preamp(struct mv_host_priv *hpriv, int idx, void __iomem *mmio); -static int mv6_reset_hc(struct mv_host_priv *hpriv, void __iomem *mmio, +static int mv6_reset_hc(struct ata_host *host, void __iomem *mmio, unsigned int n_hc); static void mv6_reset_flash(struct mv_host_priv *hpriv, void __iomem *mmio); static void mv_soc_enable_leds(struct mv_host_priv *hpriv, void __iomem *mmio); static void mv_soc_read_preamp(struct mv_host_priv *hpriv, int idx, void __iomem *mmio); -static int mv_soc_reset_hc(struct mv_host_priv *hpriv, +static int mv_soc_reset_hc(struct ata_host *host, void __iomem *mmio, unsigned int n_hc); static void mv_soc_reset_flash(struct mv_host_priv *hpriv, void __iomem *mmio); @@ -1248,81 +1248,74 @@ static int mv_stop_edma(struct ata_port *ap) return err; } -#ifdef ATA_DEBUG -static void mv_dump_mem(void __iomem *start, unsigned bytes) +static void mv_dump_mem(struct device *dev, void __iomem *start, unsigned bytes) { - int b, w; + int b, w, o; + unsigned char linebuf[38]; + for (b = 0; b < bytes; ) { - DPRINTK("%p: ", start + b); - for (w = 0; b < bytes && w < 4; w++) { - printk("%08x ", readl(start + b)); + for (w = 0, o = 0; b < bytes && w < 4; w++) { + o += snprintf(linebuf + o, sizeof(linebuf) - o, + "%08x ", readl(start + b)); b += sizeof(u32); } - printk("\n"); + dev_dbg(dev, "%s: %p: %s\n", + __func__, start + b, linebuf); } } -#endif -#if defined(ATA_DEBUG) || defined(CONFIG_PCI) + static void mv_dump_pci_cfg(struct pci_dev *pdev, unsigned bytes) { -#ifdef ATA_DEBUG - int b, w; - u32 dw; + int b, w, o; + u32 dw = 0; + unsigned char linebuf[38]; + for (b = 0; b < bytes; ) { - DPRINTK("%02x: ", b); - for (w = 0; b < bytes && w < 4; w++) { + for (w = 0, o = 0; b < bytes && w < 4; w++) { (void) pci_read_config_dword(pdev, b, &dw); - printk("%08x ", dw); + o += snprintf(linebuf + o, sizeof(linebuf) - o, + "%08x ", dw); b += sizeof(u32); } - printk("\n"); + dev_dbg(&pdev->dev, "%s: %02x: %s\n", + __func__, b, linebuf); } -#endif } -#endif -static void mv_dump_all_regs(void __iomem *mmio_base, int port, + +static void mv_dump_all_regs(void __iomem *mmio_base, struct pci_dev *pdev) { -#ifdef ATA_DEBUG - void __iomem *hc_base = mv_hc_base(mmio_base, - port >> MV_PORT_HC_SHIFT); + void __iomem *hc_base; void __iomem *port_base; int start_port, num_ports, p, start_hc, num_hcs, hc; - if (0 > port) { - start_hc = start_port = 0; - num_ports = 8; /* shld be benign for 4 port devs */ - num_hcs = 2; - } else { - start_hc = port >> MV_PORT_HC_SHIFT; - start_port = port; - num_ports = num_hcs = 1; - } - DPRINTK("All registers for port(s) %u-%u:\n", start_port, - num_ports > 1 ? num_ports - 1 : start_port); + start_hc = start_port = 0; + num_ports = 8; /* should be benign for 4 port devs */ + num_hcs = 2; + dev_dbg(&pdev->dev, + "%s: All registers for port(s) %u-%u:\n", __func__, + start_port, num_ports > 1 ? num_ports - 1 : start_port); - if (NULL != pdev) { - DPRINTK("PCI config space regs:\n"); - mv_dump_pci_cfg(pdev, 0x68); - } - DPRINTK("PCI regs:\n"); - mv_dump_mem(mmio_base+0xc00, 0x3c); - mv_dump_mem(mmio_base+0xd00, 0x34); - mv_dump_mem(mmio_base+0xf00, 0x4); - mv_dump_mem(mmio_base+0x1d00, 0x6c); + dev_dbg(&pdev->dev, "%s: PCI config space regs:\n", __func__); + mv_dump_pci_cfg(pdev, 0x68); + + dev_dbg(&pdev->dev, "%s: PCI regs:\n", __func__); + mv_dump_mem(&pdev->dev, mmio_base+0xc00, 0x3c); + mv_dump_mem(&pdev->dev, mmio_base+0xd00, 0x34); + mv_dump_mem(&pdev->dev, mmio_base+0xf00, 0x4); + mv_dump_mem(&pdev->dev, mmio_base+0x1d00, 0x6c); for (hc = start_hc; hc < start_hc + num_hcs; hc++) { hc_base = mv_hc_base(mmio_base, hc); - DPRINTK("HC regs (HC %i):\n", hc); - mv_dump_mem(hc_base, 0x1c); + dev_dbg(&pdev->dev, "%s: HC regs (HC %i):\n", __func__, hc); + mv_dump_mem(&pdev->dev, hc_base, 0x1c); } for (p = start_port; p < start_port + num_ports; p++) { port_base = mv_port_base(mmio_base, p); - DPRINTK("EDMA regs (port %i):\n", p); - mv_dump_mem(port_base, 0x54); - DPRINTK("SATA regs (port %i):\n", p); - mv_dump_mem(port_base+0x300, 0x60); + dev_dbg(&pdev->dev, "%s: EDMA regs (port %i):\n", __func__, p); + mv_dump_mem(&pdev->dev, port_base, 0x54); + dev_dbg(&pdev->dev, "%s: SATA regs (port %i):\n", __func__, p); + mv_dump_mem(&pdev->dev, port_base+0x300, 0x60); } -#endif } static unsigned int mv_scr_offset(unsigned int sc_reg_in) @@ -2962,8 +2955,8 @@ static int mv_pci_error(struct ata_host *host, void __iomem *mmio) dev_err(host->dev, "PCI ERROR; PCI IRQ cause=0x%08x\n", err_cause); - DPRINTK("All regs @ PCI error\n"); - mv_dump_all_regs(mmio, -1, to_pci_dev(host->dev)); + dev_dbg(host->dev, "%s: All regs @ PCI error\n", __func__); + mv_dump_all_regs(mmio, to_pci_dev(host->dev)); writelfl(0, mmio + hpriv->irq_cause_offset); @@ -3201,9 +3194,10 @@ static void mv5_reset_one_hc(struct mv_host_priv *hpriv, void __iomem *mmio, } #undef ZERO -static int mv5_reset_hc(struct mv_host_priv *hpriv, void __iomem *mmio, +static int mv5_reset_hc(struct ata_host *host, void __iomem *mmio, unsigned int n_hc) { + struct mv_host_priv *hpriv = host->private_data; unsigned int hc, port; for (hc = 0; hc < n_hc; hc++) { @@ -3262,7 +3256,7 @@ static void mv6_reset_flash(struct mv_host_priv *hpriv, void __iomem *mmio) * LOCKING: * Inherited from caller. */ -static int mv6_reset_hc(struct mv_host_priv *hpriv, void __iomem *mmio, +static int mv6_reset_hc(struct ata_host *host, void __iomem *mmio, unsigned int n_hc) { void __iomem *reg = mmio + PCI_MAIN_CMD_STS; @@ -3282,7 +3276,7 @@ static int mv6_reset_hc(struct mv_host_priv *hpriv, void __iomem *mmio, break; } if (!(PCI_MASTER_EMPTY & t)) { - printk(KERN_ERR DRV_NAME ": PCI master won't flush\n"); + dev_err(host->dev, "PCI master won't flush\n"); rc = 1; goto done; } @@ -3296,7 +3290,7 @@ static int mv6_reset_hc(struct mv_host_priv *hpriv, void __iomem *mmio, } while (!(GLOB_SFT_RST & t) && (i-- > 0)); if (!(GLOB_SFT_RST & t)) { - printk(KERN_ERR DRV_NAME ": can't set global reset\n"); + dev_err(host->dev, "can't set global reset\n"); rc = 1; goto done; } @@ -3310,7 +3304,7 @@ static int mv6_reset_hc(struct mv_host_priv *hpriv, void __iomem *mmio, } while ((GLOB_SFT_RST & t) && (i-- > 0)); if (GLOB_SFT_RST & t) { - printk(KERN_ERR DRV_NAME ": can't clear global reset\n"); + dev_err(host->dev, "can't clear global reset\n"); rc = 1; } done: @@ -3479,9 +3473,10 @@ static void mv_soc_reset_one_hc(struct mv_host_priv *hpriv, #undef ZERO -static int mv_soc_reset_hc(struct mv_host_priv *hpriv, +static int mv_soc_reset_hc(struct ata_host *host, void __iomem *mmio, unsigned int n_hc) { + struct mv_host_priv *hpriv = host->private_data; unsigned int port; for (port = 0; port < hpriv->n_ports; port++) @@ -3723,11 +3718,6 @@ static void mv_port_init(struct ata_ioports *port, void __iomem *port_mmio) /* unmask all non-transient EDMA error interrupts */ writelfl(~EDMA_ERR_IRQ_TRANSIENT, port_mmio + EDMA_ERR_IRQ_MASK); - - VPRINTK("EDMA cfg=0x%08x EDMA IRQ err cause/mask=0x%08x/0x%08x\n", - readl(port_mmio + EDMA_CFG), - readl(port_mmio + EDMA_ERR_IRQ_CAUSE), - readl(port_mmio + EDMA_ERR_IRQ_MASK)); } static unsigned int mv_in_pcix_mode(struct ata_host *host) @@ -3859,11 +3849,11 @@ static int mv_chip_id(struct ata_host *host, unsigned int board_idx) * * Warn the user, lest they think we're just buggy. */ - printk(KERN_WARNING DRV_NAME ": Highpoint RocketRAID" + dev_warn(&pdev->dev, "Highpoint RocketRAID" " BIOS CORRUPTS DATA on all attached drives," " regardless of if/how they are configured." " BEWARE!\n"); - printk(KERN_WARNING DRV_NAME ": For data safety, do not" + dev_warn(&pdev->dev, "For data safety, do not" " use sectors 8-9 on \"Legacy\" drives," " and avoid the final two gigabytes on" " all RocketRAID BIOS initialized drives.\n"); @@ -3954,7 +3944,7 @@ static int mv_init_host(struct ata_host *host) if (hpriv->ops->read_preamp) hpriv->ops->read_preamp(hpriv, port, mmio); - rc = hpriv->ops->reset_hc(hpriv, mmio, n_hc); + rc = hpriv->ops->reset_hc(host, mmio, n_hc); if (rc) goto done; @@ -3972,7 +3962,7 @@ static int mv_init_host(struct ata_host *host) for (hc = 0; hc < n_hc; hc++) { void __iomem *hc_mmio = mv_hc_base(mmio, hc); - VPRINTK("HC%i: HC config=0x%08x HC IRQ cause " + dev_dbg(host->dev, "HC%i: HC config=0x%08x HC IRQ cause " "(before clear)=0x%08x\n", hc, readl(hc_mmio + HC_CFG), readl(hc_mmio + HC_IRQ_CAUSE)); @@ -4270,7 +4260,7 @@ static int mv_platform_resume(struct platform_device *pdev) /* initialize adapter */ ret = mv_init_host(host); if (ret) { - printk(KERN_ERR DRV_NAME ": Error during HW init\n"); + dev_err(&pdev->dev, "Error during HW init\n"); return ret; } ata_host_resume(host); diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c index 16272c111208..7f14d0d31057 100644 --- a/drivers/ata/sata_nv.c +++ b/drivers/ata/sata_nv.c @@ -31,6 +31,7 @@ #include #include #include +#include #define DRV_NAME "sata_nv" #define DRV_VERSION "3.5" @@ -808,7 +809,7 @@ static int nv_adma_check_cpb(struct ata_port *ap, int cpb_num, int force_err) struct nv_adma_port_priv *pp = ap->private_data; u8 flags = pp->cpb[cpb_num].resp_flags; - VPRINTK("CPB %d, flags=0x%x\n", cpb_num, flags); + ata_port_dbg(ap, "CPB %d, flags=0x%x\n", cpb_num, flags); if (unlikely((force_err || flags & (NV_CPB_RESP_ATA_ERR | @@ -1100,8 +1101,6 @@ static int nv_adma_port_start(struct ata_port *ap) struct pci_dev *pdev = to_pci_dev(dev); u16 tmp; - VPRINTK("ENTER\n"); - /* * Ensure DMA mask is set to 32-bit before allocating legacy PRD and * pad buffers. @@ -1190,7 +1189,6 @@ static void nv_adma_port_stop(struct ata_port *ap) struct nv_adma_port_priv *pp = ap->private_data; void __iomem *mmio = pp->ctl_block; - VPRINTK("ENTER\n"); writew(0, mmio + NV_ADMA_CTL); } @@ -1252,8 +1250,6 @@ static void nv_adma_setup_port(struct ata_port *ap) void __iomem *mmio = ap->host->iomap[NV_MMIO_BAR]; struct ata_ioports *ioport = &ap->ioaddr; - VPRINTK("ENTER\n"); - mmio += NV_ADMA_PORT + ap->port_no * NV_ADMA_PORT_SIZE; ioport->cmd_addr = mmio; @@ -1277,8 +1273,6 @@ static int nv_adma_host_init(struct ata_host *host) unsigned int i; u32 tmp32; - VPRINTK("ENTER\n"); - /* enable ADMA on the ports */ pci_read_config_dword(pdev, NV_MCP_SATA_CFG_20, &tmp32); tmp32 |= NV_MCP_SATA_CFG_20_PORT0_EN | @@ -1320,8 +1314,6 @@ static void nv_adma_fill_sg(struct ata_queued_cmd *qc, struct nv_adma_cpb *cpb) struct scatterlist *sg; unsigned int si; - VPRINTK("ENTER\n"); - for_each_sg(qc->sg, sg, qc->n_elem, si) { aprd = (si < 5) ? &cpb->aprd[si] : &pp->aprd[NV_ADMA_SGTBL_LEN * qc->hw_tag + (si-5)]; @@ -1378,8 +1370,6 @@ static enum ata_completion_errors nv_adma_qc_prep(struct ata_queued_cmd *qc) if (qc->tf.protocol == ATA_PROT_NCQ) ctl_flags |= NV_CPB_CTL_QUEUE | NV_CPB_CTL_FPDMA; - VPRINTK("qc->flags = 0x%lx\n", qc->flags); - nv_adma_tf_to_cpb(&qc->tf, cpb->tf); if (qc->flags & ATA_QCFLAG_DMAMAP) { @@ -1404,8 +1394,6 @@ static unsigned int nv_adma_qc_issue(struct ata_queued_cmd *qc) void __iomem *mmio = pp->ctl_block; int curr_ncq = (qc->tf.protocol == ATA_PROT_NCQ); - VPRINTK("ENTER\n"); - /* We can't handle result taskfile with NCQ commands, since retrieving the taskfile switches us out of ADMA mode and would abort existing commands. */ @@ -1417,7 +1405,6 @@ static unsigned int nv_adma_qc_issue(struct ata_queued_cmd *qc) if (nv_adma_use_reg_mode(qc)) { /* use ATA register mode */ - VPRINTK("using ATA register mode: 0x%lx\n", qc->flags); BUG_ON(!(pp->flags & NV_ADMA_ATAPI_SETUP_COMPLETE) && (qc->flags & ATA_QCFLAG_DMAMAP)); nv_adma_register_mode(qc->ap); @@ -1438,8 +1425,6 @@ static unsigned int nv_adma_qc_issue(struct ata_queued_cmd *qc) writew(qc->hw_tag, mmio + NV_ADMA_APPEND); - DPRINTK("Issued tag %u\n", qc->hw_tag); - return 0; } @@ -1871,12 +1856,12 @@ static void nv_swncq_host_init(struct ata_host *host) /* enable swncq */ tmp = readl(mmio + NV_CTL_MCP55); - VPRINTK("HOST_CTL:0x%X\n", tmp); + dev_dbg(&pdev->dev, "HOST_CTL:0x%X\n", tmp); writel(tmp | NV_CTL_PRI_SWNCQ | NV_CTL_SEC_SWNCQ, mmio + NV_CTL_MCP55); /* enable irq intr */ tmp = readl(mmio + NV_INT_ENABLE_MCP55); - VPRINTK("HOST_ENABLE:0x%X\n", tmp); + dev_dbg(&pdev->dev, "HOST_ENABLE:0x%X\n", tmp); writel(tmp | 0x00fd00fd, mmio + NV_INT_ENABLE_MCP55); /* clear port irq */ @@ -2017,19 +2002,17 @@ static unsigned int nv_swncq_issue_atacmd(struct ata_port *ap, if (qc == NULL) return 0; - DPRINTK("Enter\n"); - writel((1 << qc->hw_tag), pp->sactive_block); pp->last_issue_tag = qc->hw_tag; pp->dhfis_bits &= ~(1 << qc->hw_tag); pp->dmafis_bits &= ~(1 << qc->hw_tag); pp->qc_active |= (0x1 << qc->hw_tag); + trace_ata_tf_load(ap, &qc->tf); ap->ops->sff_tf_load(ap, &qc->tf); /* load tf registers */ + trace_ata_exec_command(ap, &qc->tf, qc->hw_tag); ap->ops->sff_exec_command(ap, &qc->tf); - DPRINTK("Issued tag %u\n", qc->hw_tag); - return 0; } @@ -2041,8 +2024,6 @@ static unsigned int nv_swncq_qc_issue(struct ata_queued_cmd *qc) if (qc->tf.protocol != ATA_PROT_NCQ) return ata_bmdma_qc_issue(qc); - DPRINTK("Enter\n"); - if (!pp->qc_active) nv_swncq_issue_atacmd(ap, qc); else @@ -2087,6 +2068,7 @@ static int nv_swncq_sdbfis(struct ata_port *ap) u8 lack_dhfis = 0; host_stat = ap->ops->bmdma_status(ap); + trace_ata_bmdma_status(ap, host_stat); if (unlikely(host_stat & ATA_DMA_ERR)) { /* error when transferring data to/from memory */ ata_ehi_clear_desc(ehi); @@ -2109,7 +2091,7 @@ static int nv_swncq_sdbfis(struct ata_port *ap) ata_qc_complete_multiple(ap, ata_qc_get_active(ap) ^ done_mask); if (!ap->qc_active) { - DPRINTK("over\n"); + ata_port_dbg(ap, "over\n"); nv_swncq_pp_reinit(ap); return 0; } @@ -2124,12 +2106,12 @@ static int nv_swncq_sdbfis(struct ata_port *ap) */ lack_dhfis = 1; - DPRINTK("id 0x%x QC: qc_active 0x%llx," - "SWNCQ:qc_active 0x%X defer_bits %X " - "dhfis 0x%X dmafis 0x%X last_issue_tag %x\n", - ap->print_id, ap->qc_active, pp->qc_active, - pp->defer_queue.defer_bits, pp->dhfis_bits, - pp->dmafis_bits, pp->last_issue_tag); + ata_port_dbg(ap, "QC: qc_active 0x%llx," + "SWNCQ:qc_active 0x%X defer_bits %X " + "dhfis 0x%X dmafis 0x%X last_issue_tag %x\n", + ap->qc_active, pp->qc_active, + pp->defer_queue.defer_bits, pp->dhfis_bits, + pp->dmafis_bits, pp->last_issue_tag); nv_swncq_fis_reinit(ap); @@ -2169,7 +2151,7 @@ static void nv_swncq_dmafis(struct ata_port *ap) __ata_bmdma_stop(ap); tag = nv_swncq_tag(ap); - DPRINTK("dma setup tag 0x%x\n", tag); + ata_port_dbg(ap, "dma setup tag 0x%x\n", tag); qc = ata_qc_from_tag(ap, tag); if (unlikely(!qc)) @@ -2237,9 +2219,9 @@ static void nv_swncq_host_interrupt(struct ata_port *ap, u16 fis) if (fis & NV_SWNCQ_IRQ_SDBFIS) { pp->ncq_flags |= ncq_saw_sdb; - DPRINTK("id 0x%x SWNCQ: qc_active 0x%X " + ata_port_dbg(ap, "SWNCQ: qc_active 0x%X " "dhfis 0x%X dmafis 0x%X sactive 0x%X\n", - ap->print_id, pp->qc_active, pp->dhfis_bits, + pp->qc_active, pp->dhfis_bits, pp->dmafis_bits, readl(pp->sactive_block)); if (nv_swncq_sdbfis(ap) < 0) goto irq_error; @@ -2265,7 +2247,7 @@ static void nv_swncq_host_interrupt(struct ata_port *ap, u16 fis) goto irq_exit; if (pp->defer_queue.defer_bits) { - DPRINTK("send next command\n"); + ata_port_dbg(ap, "send next command\n"); qc = nv_swncq_qc_from_dq(ap); nv_swncq_issue_atacmd(ap, qc); } diff --git a/drivers/ata/sata_promise.c b/drivers/ata/sata_promise.c index 7815da8ef9e5..b8465fef2ed2 100644 --- a/drivers/ata/sata_promise.c +++ b/drivers/ata/sata_promise.c @@ -596,7 +596,8 @@ static void pdc_fill_sg(struct ata_queued_cmd *qc) prd[idx].addr = cpu_to_le32(addr); prd[idx].flags_len = cpu_to_le32(len & 0xffff); - VPRINTK("PRD[%u] = (0x%X, 0x%X)\n", idx, addr, len); + ata_port_dbg(ap, "PRD[%u] = (0x%X, 0x%X)\n", + idx, addr, len); idx++; sg_len -= len; @@ -609,17 +610,16 @@ static void pdc_fill_sg(struct ata_queued_cmd *qc) if (len > SG_COUNT_ASIC_BUG) { u32 addr; - VPRINTK("Splitting last PRD.\n"); - addr = le32_to_cpu(prd[idx - 1].addr); prd[idx - 1].flags_len = cpu_to_le32(len - SG_COUNT_ASIC_BUG); - VPRINTK("PRD[%u] = (0x%X, 0x%X)\n", idx - 1, addr, SG_COUNT_ASIC_BUG); + ata_port_dbg(ap, "PRD[%u] = (0x%X, 0x%X)\n", + idx - 1, addr, SG_COUNT_ASIC_BUG); addr = addr + len - SG_COUNT_ASIC_BUG; len = SG_COUNT_ASIC_BUG; prd[idx].addr = cpu_to_le32(addr); prd[idx].flags_len = cpu_to_le32(len); - VPRINTK("PRD[%u] = (0x%X, 0x%X)\n", idx, addr, len); + ata_port_dbg(ap, "PRD[%u] = (0x%X, 0x%X)\n", idx, addr, len); idx++; } @@ -632,8 +632,6 @@ static enum ata_completion_errors pdc_qc_prep(struct ata_queued_cmd *qc) struct pdc_port_priv *pp = qc->ap->private_data; unsigned int i; - VPRINTK("ENTER\n"); - switch (qc->tf.protocol) { case ATA_PROT_DMA: pdc_fill_sg(qc); @@ -922,12 +920,8 @@ static irqreturn_t pdc_interrupt(int irq, void *dev_instance) u32 hotplug_status; int is_sataii_tx4; - VPRINTK("ENTER\n"); - - if (!host || !host->iomap[PDC_MMIO_BAR]) { - VPRINTK("QUICK EXIT\n"); + if (!host || !host->iomap[PDC_MMIO_BAR]) return IRQ_NONE; - } host_mmio = host->iomap[PDC_MMIO_BAR]; @@ -946,23 +940,18 @@ static irqreturn_t pdc_interrupt(int irq, void *dev_instance) /* reading should also clear interrupts */ mask = readl(host_mmio + PDC_INT_SEQMASK); - if (mask == 0xffffffff && hotplug_status == 0) { - VPRINTK("QUICK EXIT 2\n"); + if (mask == 0xffffffff && hotplug_status == 0) goto done_irq; - } mask &= 0xffff; /* only 16 SEQIDs possible */ - if (mask == 0 && hotplug_status == 0) { - VPRINTK("QUICK EXIT 3\n"); + if (mask == 0 && hotplug_status == 0) goto done_irq; - } writel(mask, host_mmio + PDC_INT_SEQMASK); is_sataii_tx4 = pdc_is_sataii_tx4(host->ports[0]->flags); for (i = 0; i < host->n_ports; i++) { - VPRINTK("port %u\n", i); ap = host->ports[i]; /* check for a plug or unplug event */ @@ -989,8 +978,6 @@ static irqreturn_t pdc_interrupt(int irq, void *dev_instance) } } - VPRINTK("EXIT\n"); - done_irq: spin_unlock(&host->lock); return IRQ_RETVAL(handled); @@ -1005,8 +992,6 @@ static void pdc_packet_start(struct ata_queued_cmd *qc) unsigned int port_no = ap->port_no; u8 seq = (u8) (port_no + 1); - VPRINTK("ENTER, ap %p\n", ap); - writel(0x00000001, host_mmio + (seq * 4)); readl(host_mmio + (seq * 4)); /* flush */ diff --git a/drivers/ata/sata_qstor.c b/drivers/ata/sata_qstor.c index ef00ab644afb..8ca0810aad26 100644 --- a/drivers/ata/sata_qstor.c +++ b/drivers/ata/sata_qstor.c @@ -252,9 +252,6 @@ static unsigned int qs_fill_sg(struct ata_queued_cmd *qc) len = sg_dma_len(sg); *(__le32 *)prd = cpu_to_le32(len); prd += sizeof(u64); - - VPRINTK("PRD[%u] = (0x%llX, 0x%X)\n", si, - (unsigned long long)addr, len); } return si; @@ -268,8 +265,6 @@ static enum ata_completion_errors qs_qc_prep(struct ata_queued_cmd *qc) u64 addr; unsigned int nelem; - VPRINTK("ENTER\n"); - qs_enter_reg_mode(qc->ap); if (qc->tf.protocol != ATA_PROT_DMA) return AC_ERR_OK; @@ -304,8 +299,6 @@ static inline void qs_packet_start(struct ata_queued_cmd *qc) struct ata_port *ap = qc->ap; u8 __iomem *chan = qs_mmio_base(ap->host) + (ap->port_no * 0x4000); - VPRINTK("ENTER, ap %p\n", ap); - writeb(QS_CTR0_CLER, chan + QS_CCT_CTR0); wmb(); /* flush PRDs and pkt to memory */ writel(QS_CCF_RUN_PKT, chan + QS_CCT_CFF); @@ -374,8 +367,8 @@ static inline unsigned int qs_intr_pkt(struct ata_host *host) struct qs_port_priv *pp = ap->private_data; struct ata_queued_cmd *qc; - DPRINTK("SFF=%08x%08x: sCHAN=%u sHST=%d sDST=%02x\n", - sff1, sff0, port_no, sHST, sDST); + dev_dbg(host->dev, "SFF=%08x%08x: sHST=%d sDST=%02x\n", + sff1, sff0, sHST, sDST); handled = 1; if (!pp || pp->state != qs_state_pkt) continue; @@ -435,14 +428,10 @@ static irqreturn_t qs_intr(int irq, void *dev_instance) unsigned int handled = 0; unsigned long flags; - VPRINTK("ENTER\n"); - spin_lock_irqsave(&host->lock, flags); handled = qs_intr_pkt(host) | qs_intr_mmio(host); spin_unlock_irqrestore(&host->lock, flags); - VPRINTK("EXIT\n"); - return IRQ_RETVAL(handled); } diff --git a/drivers/ata/sata_rcar.c b/drivers/ata/sata_rcar.c index 44b0ed8f6bb8..3d96b6faa3f0 100644 --- a/drivers/ata/sata_rcar.c +++ b/drivers/ata/sata_rcar.c @@ -323,8 +323,6 @@ static int sata_rcar_bus_softreset(struct ata_port *ap, unsigned long deadline) { struct ata_ioports *ioaddr = &ap->ioaddr; - DPRINTK("ata%u: bus reset via SRST\n", ap->print_id); - /* software reset. causes dev0 to be selected */ iowrite32(ap->ctl, ioaddr->ctl_addr); udelay(20); @@ -350,7 +348,6 @@ static int sata_rcar_softreset(struct ata_link *link, unsigned int *classes, devmask |= 1 << 0; /* issue bus reset */ - DPRINTK("about to softreset, devmask=%x\n", devmask); rc = sata_rcar_bus_softreset(ap, deadline); /* if link is occupied, -ENODEV too is an error */ if (rc && (rc != -ENODEV || sata_scr_valid(link))) { @@ -361,7 +358,6 @@ static int sata_rcar_softreset(struct ata_link *link, unsigned int *classes, /* determine by signature whether we have ATA or ATAPI devices */ classes[0] = ata_sff_dev_classify(&link->device[0], devmask, &err); - DPRINTK("classes[0]=%u\n", classes[0]); return 0; } @@ -383,12 +379,6 @@ static void sata_rcar_tf_load(struct ata_port *ap, iowrite32(tf->hob_lbal, ioaddr->lbal_addr); iowrite32(tf->hob_lbam, ioaddr->lbam_addr); iowrite32(tf->hob_lbah, ioaddr->lbah_addr); - VPRINTK("hob: feat 0x%X nsect 0x%X, lba 0x%X 0x%X 0x%X\n", - tf->hob_feature, - tf->hob_nsect, - tf->hob_lbal, - tf->hob_lbam, - tf->hob_lbah); } if (is_addr) { @@ -397,18 +387,10 @@ static void sata_rcar_tf_load(struct ata_port *ap, iowrite32(tf->lbal, ioaddr->lbal_addr); iowrite32(tf->lbam, ioaddr->lbam_addr); iowrite32(tf->lbah, ioaddr->lbah_addr); - VPRINTK("feat 0x%X nsect 0x%X lba 0x%X 0x%X 0x%X\n", - tf->feature, - tf->nsect, - tf->lbal, - tf->lbam, - tf->lbah); } - if (tf->flags & ATA_TFLAG_DEVICE) { + if (tf->flags & ATA_TFLAG_DEVICE) iowrite32(tf->device, ioaddr->device_addr); - VPRINTK("device 0x%X\n", tf->device); - } ata_wait_idle(ap); } @@ -440,8 +422,6 @@ static void sata_rcar_tf_read(struct ata_port *ap, struct ata_taskfile *tf) static void sata_rcar_exec_command(struct ata_port *ap, const struct ata_taskfile *tf) { - DPRINTK("ata%u: cmd 0x%X\n", ap->print_id, tf->command); - iowrite32(tf->command, ap->ioaddr.command_addr); ata_sff_pause(ap); } @@ -499,7 +479,6 @@ static void sata_rcar_drain_fifo(struct ata_queued_cmd *qc) count < 65536; count += 2) ioread32(ap->ioaddr.data_addr); - /* Can become DEBUG later */ if (count) ata_port_dbg(ap, "drained %d bytes to clear DRQ\n", count); } @@ -543,7 +522,6 @@ static void sata_rcar_bmdma_fill_sg(struct ata_queued_cmd *qc) prd[si].addr = cpu_to_le32(addr); prd[si].flags_len = cpu_to_le32(sg_len); - VPRINTK("PRD[%u] = (0x%X, 0x%X)\n", si, addr, sg_len); } /* end-of-table flag */ @@ -685,7 +663,7 @@ static void sata_rcar_serr_interrupt(struct ata_port *ap) if (!serror) return; - DPRINTK("SError @host_intr: 0x%x\n", serror); + ata_port_dbg(ap, "SError @host_intr: 0x%x\n", serror); /* first, analyze and record host port events */ ata_ehi_clear_desc(ehi); diff --git a/drivers/ata/sata_sil.c b/drivers/ata/sata_sil.c index 75321f1ceba5..3b989a52879d 100644 --- a/drivers/ata/sata_sil.c +++ b/drivers/ata/sata_sil.c @@ -307,7 +307,6 @@ static void sil_fill_sg(struct ata_queued_cmd *qc) prd->addr = cpu_to_le32(addr); prd->flags_len = cpu_to_le32(sg_len); - VPRINTK("PRD[%u] = (0x%X, 0x%X)\n", si, addr, sg_len); last_prd = prd; prd++; diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c index f99ec6f7d7c0..2fef6ce93f07 100644 --- a/drivers/ata/sata_sil24.c +++ b/drivers/ata/sata_sil24.c @@ -656,8 +656,6 @@ static int sil24_softreset(struct ata_link *link, unsigned int *class, const char *reason; int rc; - DPRINTK("ENTER\n"); - /* put the port into known state */ if (sil24_init_port(ap)) { reason = "port not ready"; @@ -680,9 +678,8 @@ static int sil24_softreset(struct ata_link *link, unsigned int *class, } sil24_read_tf(ap, 0, &tf); - *class = ata_dev_classify(&tf); + *class = ata_port_classify(ap, &tf); - DPRINTK("EXIT, class=%u\n", *class); return 0; err: diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c index 4c01190a5e37..6ceec59cb291 100644 --- a/drivers/ata/sata_sx4.c +++ b/drivers/ata/sata_sx4.c @@ -78,6 +78,9 @@ #define DRV_NAME "sata_sx4" #define DRV_VERSION "0.12" +static int dimm_test; +module_param(dimm_test, int, 0644); +MODULE_PARM_DESC(dimm_test, "Enable DIMM test during startup (1 = enabled)"); enum { PDC_MMIO_BAR = 3, @@ -211,10 +214,8 @@ static unsigned int pdc20621_i2c_read(struct ata_host *host, u32 device, u32 subaddr, u32 *pdata); static int pdc20621_prog_dimm0(struct ata_host *host); static unsigned int pdc20621_prog_dimm_global(struct ata_host *host); -#ifdef ATA_VERBOSE_DEBUG static void pdc20621_get_from_dimm(struct ata_host *host, void *psource, u32 offset, u32 size); -#endif static void pdc20621_put_to_dimm(struct ata_host *host, void *psource, u32 offset, u32 size); static void pdc20621_irq_clear(struct ata_port *ap); @@ -308,15 +309,9 @@ static inline void pdc20621_ata_sg(u8 *buf, unsigned int portno, /* output ATA packet S/G table */ addr = PDC_20621_DIMM_BASE + PDC_20621_DIMM_DATA + (PDC_DIMM_DATA_STEP * portno); - VPRINTK("ATA sg addr 0x%x, %d\n", addr, addr); + buf32[dw] = cpu_to_le32(addr); buf32[dw + 1] = cpu_to_le32(total_len | ATA_PRD_EOT); - - VPRINTK("ATA PSG @ %x == (0x%x, 0x%x)\n", - PDC_20621_DIMM_BASE + - (PDC_DIMM_WINDOW_STEP * portno) + - PDC_DIMM_APKT_PRD, - buf32[dw], buf32[dw + 1]); } static inline void pdc20621_host_sg(u8 *buf, unsigned int portno, @@ -332,12 +327,6 @@ static inline void pdc20621_host_sg(u8 *buf, unsigned int portno, buf32[dw] = cpu_to_le32(addr); buf32[dw + 1] = cpu_to_le32(total_len | ATA_PRD_EOT); - - VPRINTK("HOST PSG @ %x == (0x%x, 0x%x)\n", - PDC_20621_DIMM_BASE + - (PDC_DIMM_WINDOW_STEP * portno) + - PDC_DIMM_HPKT_PRD, - buf32[dw], buf32[dw + 1]); } static inline unsigned int pdc20621_ata_pkt(struct ata_taskfile *tf, @@ -351,7 +340,6 @@ static inline unsigned int pdc20621_ata_pkt(struct ata_taskfile *tf, unsigned int dimm_sg = PDC_20621_DIMM_BASE + (PDC_DIMM_WINDOW_STEP * portno) + PDC_DIMM_APKT_PRD; - VPRINTK("ENTER, dimm_sg == 0x%x, %d\n", dimm_sg, dimm_sg); i = PDC_DIMM_ATA_PKT; @@ -406,8 +394,6 @@ static inline void pdc20621_host_pkt(struct ata_taskfile *tf, u8 *buf, unsigned int dimm_sg = PDC_20621_DIMM_BASE + (PDC_DIMM_WINDOW_STEP * portno) + PDC_DIMM_HPKT_PRD; - VPRINTK("ENTER, dimm_sg == 0x%x, %d\n", dimm_sg, dimm_sg); - VPRINTK("host_sg == 0x%x, %d\n", host_sg, host_sg); dw = PDC_DIMM_HOST_PKT >> 2; @@ -424,14 +410,6 @@ static inline void pdc20621_host_pkt(struct ata_taskfile *tf, u8 *buf, buf32[dw + 1] = cpu_to_le32(host_sg); buf32[dw + 2] = cpu_to_le32(dimm_sg); buf32[dw + 3] = 0; - - VPRINTK("HOST PKT @ %x == (0x%x 0x%x 0x%x 0x%x)\n", - PDC_20621_DIMM_BASE + (PDC_DIMM_WINDOW_STEP * portno) + - PDC_DIMM_HOST_PKT, - buf32[dw + 0], - buf32[dw + 1], - buf32[dw + 2], - buf32[dw + 3]); } static void pdc20621_dma_prep(struct ata_queued_cmd *qc) @@ -447,8 +425,6 @@ static void pdc20621_dma_prep(struct ata_queued_cmd *qc) WARN_ON(!(qc->flags & ATA_QCFLAG_DMAMAP)); - VPRINTK("ata%u: ENTER\n", ap->print_id); - /* hard-code chip #0 */ mmio += PDC_CHIP0_OFS; @@ -492,7 +468,8 @@ static void pdc20621_dma_prep(struct ata_queued_cmd *qc) readl(dimm_mmio); /* MMIO PCI posting flush */ - VPRINTK("ata pkt buf ofs %u, prd size %u, mmio copied\n", i, sgt_len); + ata_port_dbg(ap, "ata pkt buf ofs %u, prd size %u, mmio copied\n", + i, sgt_len); } static void pdc20621_nodata_prep(struct ata_queued_cmd *qc) @@ -504,8 +481,6 @@ static void pdc20621_nodata_prep(struct ata_queued_cmd *qc) unsigned int portno = ap->port_no; unsigned int i; - VPRINTK("ata%u: ENTER\n", ap->print_id); - /* hard-code chip #0 */ mmio += PDC_CHIP0_OFS; @@ -527,7 +502,7 @@ static void pdc20621_nodata_prep(struct ata_queued_cmd *qc) readl(dimm_mmio); /* MMIO PCI posting flush */ - VPRINTK("ata pkt buf ofs %u, mmio copied\n", i); + ata_port_dbg(ap, "ata pkt buf ofs %u, mmio copied\n", i); } static enum ata_completion_errors pdc20621_qc_prep(struct ata_queued_cmd *qc) @@ -601,7 +576,6 @@ static void pdc20621_pop_hdma(struct ata_queued_cmd *qc) pp->hdma_cons++; } -#ifdef ATA_VERBOSE_DEBUG static void pdc20621_dump_hdma(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; @@ -611,14 +585,10 @@ static void pdc20621_dump_hdma(struct ata_queued_cmd *qc) dimm_mmio += (port_no * PDC_DIMM_WINDOW_STEP); dimm_mmio += PDC_DIMM_HOST_PKT; - printk(KERN_ERR "HDMA[0] == 0x%08X\n", readl(dimm_mmio)); - printk(KERN_ERR "HDMA[1] == 0x%08X\n", readl(dimm_mmio + 4)); - printk(KERN_ERR "HDMA[2] == 0x%08X\n", readl(dimm_mmio + 8)); - printk(KERN_ERR "HDMA[3] == 0x%08X\n", readl(dimm_mmio + 12)); + ata_port_dbg(ap, "HDMA 0x%08X 0x%08X 0x%08X 0x%08X\n", + readl(dimm_mmio), readl(dimm_mmio + 4), + readl(dimm_mmio + 8), readl(dimm_mmio + 12)); } -#else -static inline void pdc20621_dump_hdma(struct ata_queued_cmd *qc) { } -#endif /* ATA_VERBOSE_DEBUG */ static void pdc20621_packet_start(struct ata_queued_cmd *qc) { @@ -633,8 +603,6 @@ static void pdc20621_packet_start(struct ata_queued_cmd *qc) /* hard-code chip #0 */ mmio += PDC_CHIP0_OFS; - VPRINTK("ata%u: ENTER\n", ap->print_id); - wmb(); /* flush PRD, pkt writes */ port_ofs = PDC_20621_DIMM_BASE + (PDC_DIMM_WINDOW_STEP * port_no); @@ -645,7 +613,7 @@ static void pdc20621_packet_start(struct ata_queued_cmd *qc) pdc20621_dump_hdma(qc); pdc20621_push_hdma(qc, seq, port_ofs + PDC_DIMM_HOST_PKT); - VPRINTK("queued ofs 0x%x (%u), seq %u\n", + ata_port_dbg(ap, "queued ofs 0x%x (%u), seq %u\n", port_ofs + PDC_DIMM_HOST_PKT, port_ofs + PDC_DIMM_HOST_PKT, seq); @@ -656,7 +624,7 @@ static void pdc20621_packet_start(struct ata_queued_cmd *qc) writel(port_ofs + PDC_DIMM_ATA_PKT, ap->ioaddr.cmd_addr + PDC_PKT_SUBMIT); readl(ap->ioaddr.cmd_addr + PDC_PKT_SUBMIT); - VPRINTK("submitted ofs 0x%x (%u), seq %u\n", + ata_port_dbg(ap, "submitted ofs 0x%x (%u), seq %u\n", port_ofs + PDC_DIMM_ATA_PKT, port_ofs + PDC_DIMM_ATA_PKT, seq); @@ -696,14 +664,12 @@ static inline unsigned int pdc20621_host_intr(struct ata_port *ap, u8 status; unsigned int handled = 0; - VPRINTK("ENTER\n"); - if ((qc->tf.protocol == ATA_PROT_DMA) && /* read */ (!(qc->tf.flags & ATA_TFLAG_WRITE))) { /* step two - DMA from DIMM to host */ if (doing_hdma) { - VPRINTK("ata%u: read hdma, 0x%x 0x%x\n", ap->print_id, + ata_port_dbg(ap, "read hdma, 0x%x 0x%x\n", readl(mmio + 0x104), readl(mmio + PDC_HDMA_CTLSTAT)); /* get drive status; clear intr; complete txn */ qc->err_mask |= ac_err_mask(ata_wait_idle(ap)); @@ -714,7 +680,7 @@ static inline unsigned int pdc20621_host_intr(struct ata_port *ap, /* step one - exec ATA command */ else { u8 seq = (u8) (port_no + 1 + 4); - VPRINTK("ata%u: read ata, 0x%x 0x%x\n", ap->print_id, + ata_port_dbg(ap, "read ata, 0x%x 0x%x\n", readl(mmio + 0x104), readl(mmio + PDC_HDMA_CTLSTAT)); /* submit hdma pkt */ @@ -729,7 +695,7 @@ static inline unsigned int pdc20621_host_intr(struct ata_port *ap, /* step one - DMA from host to DIMM */ if (doing_hdma) { u8 seq = (u8) (port_no + 1); - VPRINTK("ata%u: write hdma, 0x%x 0x%x\n", ap->print_id, + ata_port_dbg(ap, "write hdma, 0x%x 0x%x\n", readl(mmio + 0x104), readl(mmio + PDC_HDMA_CTLSTAT)); /* submit ata pkt */ @@ -742,7 +708,7 @@ static inline unsigned int pdc20621_host_intr(struct ata_port *ap, /* step two - execute ATA command */ else { - VPRINTK("ata%u: write ata, 0x%x 0x%x\n", ap->print_id, + ata_port_dbg(ap, "write ata, 0x%x 0x%x\n", readl(mmio + 0x104), readl(mmio + PDC_HDMA_CTLSTAT)); /* get drive status; clear intr; complete txn */ qc->err_mask |= ac_err_mask(ata_wait_idle(ap)); @@ -755,7 +721,7 @@ static inline unsigned int pdc20621_host_intr(struct ata_port *ap, } else if (qc->tf.protocol == ATA_PROT_NODATA) { status = ata_sff_busy_wait(ap, ATA_BUSY | ATA_DRQ, 1000); - DPRINTK("BUS_NODATA (drv_stat 0x%X)\n", status); + ata_port_dbg(ap, "BUS_NODATA (drv_stat 0x%X)\n", status); qc->err_mask |= ac_err_mask(status); ata_qc_complete(qc); handled = 1; @@ -781,29 +747,21 @@ static irqreturn_t pdc20621_interrupt(int irq, void *dev_instance) unsigned int handled = 0; void __iomem *mmio_base; - VPRINTK("ENTER\n"); - - if (!host || !host->iomap[PDC_MMIO_BAR]) { - VPRINTK("QUICK EXIT\n"); + if (!host || !host->iomap[PDC_MMIO_BAR]) return IRQ_NONE; - } mmio_base = host->iomap[PDC_MMIO_BAR]; /* reading should also clear interrupts */ mmio_base += PDC_CHIP0_OFS; mask = readl(mmio_base + PDC_20621_SEQMASK); - VPRINTK("mask == 0x%x\n", mask); - if (mask == 0xffffffff) { - VPRINTK("QUICK EXIT 2\n"); + if (mask == 0xffffffff) return IRQ_NONE; - } + mask &= 0xffff; /* only 16 tags possible */ - if (!mask) { - VPRINTK("QUICK EXIT 3\n"); + if (!mask) return IRQ_NONE; - } spin_lock(&host->lock); @@ -816,7 +774,8 @@ static irqreturn_t pdc20621_interrupt(int irq, void *dev_instance) else ap = host->ports[port_no]; tmp = mask & (1 << i); - VPRINTK("seq %u, port_no %u, ap %p, tmp %x\n", i, port_no, ap, tmp); + if (ap) + ata_port_dbg(ap, "seq %u, tmp %x\n", i, tmp); if (tmp && ap) { struct ata_queued_cmd *qc; @@ -829,10 +788,6 @@ static irqreturn_t pdc20621_interrupt(int irq, void *dev_instance) spin_unlock(&host->lock); - VPRINTK("mask == 0x%x\n", mask); - - VPRINTK("EXIT\n"); - return IRQ_RETVAL(handled); } @@ -979,7 +934,6 @@ static void pdc_sata_setup_port(struct ata_ioports *port, void __iomem *base) } -#ifdef ATA_VERBOSE_DEBUG static void pdc20621_get_from_dimm(struct ata_host *host, void *psource, u32 offset, u32 size) { @@ -1029,7 +983,6 @@ static void pdc20621_get_from_dimm(struct ata_host *host, void *psource, memcpy_fromio(psource, dimm_mmio, size / 4); } } -#endif static void pdc20621_put_to_dimm(struct ata_host *host, void *psource, @@ -1226,15 +1179,16 @@ static unsigned int pdc20621_prog_dimm_global(struct ata_host *host) /* Turn on for ECC */ if (!pdc20621_i2c_read(host, PDC_DIMM0_SPD_DEV_ADDRESS, PDC_DIMM_SPD_TYPE, &spd0)) { - pr_err("Failed in i2c read: device=%#x, subaddr=%#x\n", - PDC_DIMM0_SPD_DEV_ADDRESS, PDC_DIMM_SPD_TYPE); + dev_err(host->dev, + "Failed in i2c read: device=%#x, subaddr=%#x\n", + PDC_DIMM0_SPD_DEV_ADDRESS, PDC_DIMM_SPD_TYPE); return 1; } if (spd0 == 0x02) { data |= (0x01 << 16); writel(data, mmio + PDC_SDRAM_CONTROL); readl(mmio + PDC_SDRAM_CONTROL); - printk(KERN_ERR "Local DIMM ECC Enabled\n"); + dev_err(host->dev, "Local DIMM ECC Enabled\n"); } /* DIMM Initialization Select/Enable (bit 18/19) */ @@ -1274,7 +1228,7 @@ static unsigned int pdc20621_dimm_init(struct ata_host *host) /* Initialize Time Period Register */ writel(0xffffffff, mmio + PDC_TIME_PERIOD); time_period = readl(mmio + PDC_TIME_PERIOD); - VPRINTK("Time Period Register (0x40): 0x%x\n", time_period); + dev_dbg(host->dev, "Time Period Register (0x40): 0x%x\n", time_period); /* Enable timer */ writel(PDC_TIMER_DEFAULT, mmio + PDC_TIME_CONTROL); @@ -1289,7 +1243,7 @@ static unsigned int pdc20621_dimm_init(struct ata_host *host) */ tcount = readl(mmio + PDC_TIME_COUNTER); - VPRINTK("Time Counter Register (0x44): 0x%x\n", tcount); + dev_dbg(host->dev, "Time Counter Register (0x44): 0x%x\n", tcount); /* If SX4 is on PCI-X bus, after 3 seconds, the timer counter @@ -1297,17 +1251,19 @@ static unsigned int pdc20621_dimm_init(struct ata_host *host) */ if (tcount >= PCI_X_TCOUNT) { ticks = (time_period - tcount); - VPRINTK("Num counters 0x%x (%d)\n", ticks, ticks); + dev_dbg(host->dev, "Num counters 0x%x (%d)\n", ticks, ticks); clock = (ticks / 300000); - VPRINTK("10 * Internal clk = 0x%x (%d)\n", clock, clock); + dev_dbg(host->dev, "10 * Internal clk = 0x%x (%d)\n", + clock, clock); clock = (clock * 33); - VPRINTK("10 * Internal clk * 33 = 0x%x (%d)\n", clock, clock); + dev_dbg(host->dev, "10 * Internal clk * 33 = 0x%x (%d)\n", + clock, clock); /* PLL F Param (bit 22:16) */ fparam = (1400000 / clock) - 2; - VPRINTK("PLL F Param: 0x%x (%d)\n", fparam, fparam); + dev_dbg(host->dev, "PLL F Param: 0x%x (%d)\n", fparam, fparam); /* OD param = 0x2 (bit 31:30), R param = 0x5 (bit 29:25) */ pci_status = (0x8a001824 | (fparam << 16)); @@ -1315,7 +1271,7 @@ static unsigned int pdc20621_dimm_init(struct ata_host *host) pci_status = PCI_PLL_INIT; /* Initialize PLL. */ - VPRINTK("pci_status: 0x%x\n", pci_status); + dev_dbg(host->dev, "pci_status: 0x%x\n", pci_status); writel(pci_status, mmio + PDC_CTL_STATUS); readl(mmio + PDC_CTL_STATUS); @@ -1324,23 +1280,23 @@ static unsigned int pdc20621_dimm_init(struct ata_host *host) and program the DIMM Module Controller. */ if (!(speed = pdc20621_detect_dimm(host))) { - printk(KERN_ERR "Detect Local DIMM Fail\n"); + dev_err(host->dev, "Detect Local DIMM Fail\n"); return 1; /* DIMM error */ } - VPRINTK("Local DIMM Speed = %d\n", speed); + dev_dbg(host->dev, "Local DIMM Speed = %d\n", speed); /* Programming DIMM0 Module Control Register (index_CID0:80h) */ size = pdc20621_prog_dimm0(host); - VPRINTK("Local DIMM Size = %dMB\n", size); + dev_dbg(host->dev, "Local DIMM Size = %dMB\n", size); /* Programming DIMM Module Global Control Register (index_CID0:88h) */ if (pdc20621_prog_dimm_global(host)) { - printk(KERN_ERR "Programming DIMM Module Global Control Register Fail\n"); + dev_err(host->dev, + "Programming DIMM Module Global Control Register Fail\n"); return 1; } -#ifdef ATA_VERBOSE_DEBUG - { + if (dimm_test) { u8 test_parttern1[40] = {0x55,0xAA,'P','r','o','m','i','s','e',' ', 'N','o','t',' ','Y','e','t',' ', @@ -1354,31 +1310,33 @@ static unsigned int pdc20621_dimm_init(struct ata_host *host) pdc20621_put_to_dimm(host, test_parttern1, 0x10040, 40); pdc20621_get_from_dimm(host, test_parttern2, 0x40, 40); - printk(KERN_ERR "%x, %x, %s\n", test_parttern2[0], + dev_info(host->dev, "DIMM test pattern 1: %x, %x, %s\n", test_parttern2[0], test_parttern2[1], &(test_parttern2[2])); pdc20621_get_from_dimm(host, test_parttern2, 0x10040, 40); - printk(KERN_ERR "%x, %x, %s\n", test_parttern2[0], - test_parttern2[1], &(test_parttern2[2])); + dev_info(host->dev, "DIMM test pattern 2: %x, %x, %s\n", + test_parttern2[0], + test_parttern2[1], &(test_parttern2[2])); pdc20621_put_to_dimm(host, test_parttern1, 0x40, 40); pdc20621_get_from_dimm(host, test_parttern2, 0x40, 40); - printk(KERN_ERR "%x, %x, %s\n", test_parttern2[0], - test_parttern2[1], &(test_parttern2[2])); + dev_info(host->dev, "DIMM test pattern 3: %x, %x, %s\n", + test_parttern2[0], + test_parttern2[1], &(test_parttern2[2])); } -#endif /* ECC initiliazation. */ if (!pdc20621_i2c_read(host, PDC_DIMM0_SPD_DEV_ADDRESS, PDC_DIMM_SPD_TYPE, &spd0)) { - pr_err("Failed in i2c read: device=%#x, subaddr=%#x\n", + dev_err(host->dev, + "Failed in i2c read: device=%#x, subaddr=%#x\n", PDC_DIMM0_SPD_DEV_ADDRESS, PDC_DIMM_SPD_TYPE); return 1; } if (spd0 == 0x02) { void *buf; - VPRINTK("Start ECC initialization\n"); + dev_dbg(host->dev, "Start ECC initialization\n"); addr = 0; length = size * 1024 * 1024; buf = kzalloc(ECC_ERASE_BUF_SZ, GFP_KERNEL); @@ -1390,7 +1348,7 @@ static unsigned int pdc20621_dimm_init(struct ata_host *host) addr += ECC_ERASE_BUF_SZ; } kfree(buf); - VPRINTK("Finish ECC initialization\n"); + dev_dbg(host->dev, "Finish ECC initialization\n"); } return 0; } diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c index 1e2c2d3882e2..f41063ac1aee 100644 --- a/drivers/base/devtmpfs.c +++ b/drivers/base/devtmpfs.c @@ -65,8 +65,15 @@ static struct dentry *public_dev_mount(struct file_system_type *fs_type, int fla const char *dev_name, void *data) { struct super_block *s = mnt->mnt_sb; + int err; + atomic_inc(&s->s_active); down_write(&s->s_umount); + err = reconfigure_single(s, flags, data); + if (err < 0) { + deactivate_locked_super(s); + return ERR_PTR(err); + } return dget(s->s_root); } diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index c3dc3cd7a779..c443cd64fc9b 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -976,7 +976,7 @@ static void virtblk_remove(struct virtio_device *vdev) mutex_lock(&vblk->vdev_mutex); /* Stop all the virtqueues. */ - vdev->config->reset(vdev); + virtio_reset_device(vdev); /* Virtqueues are stopped, nothing can use vblk->vdev anymore. */ vblk->vdev = NULL; @@ -995,7 +995,7 @@ static int virtblk_freeze(struct virtio_device *vdev) struct virtio_blk *vblk = vdev->priv; /* Ensure we don't receive any more interrupts */ - vdev->config->reset(vdev); + virtio_reset_device(vdev); /* Make sure no work handler is accessing the device. */ flush_work(&vblk->config_work); diff --git a/drivers/bluetooth/virtio_bt.c b/drivers/bluetooth/virtio_bt.c index 076e4942a3f0..67c21263f9e0 100644 --- a/drivers/bluetooth/virtio_bt.c +++ b/drivers/bluetooth/virtio_bt.c @@ -367,7 +367,7 @@ static void virtbt_remove(struct virtio_device *vdev) struct hci_dev *hdev = vbt->hdev; hci_unregister_dev(hdev); - vdev->config->reset(vdev); + virtio_reset_device(vdev); hci_free_dev(hdev); vbt->hdev = NULL; diff --git a/drivers/char/hw_random/virtio-rng.c b/drivers/char/hw_random/virtio-rng.c index 0a7dde135db1..e856df7e285c 100644 --- a/drivers/char/hw_random/virtio-rng.c +++ b/drivers/char/hw_random/virtio-rng.c @@ -179,9 +179,9 @@ static void remove_common(struct virtio_device *vdev) vi->data_avail = 0; vi->data_idx = 0; complete(&vi->have_data); - vdev->config->reset(vdev); if (vi->hwrng_register_done) hwrng_unregister(&vi->hwrng); + virtio_reset_device(vdev); vdev->config->del_vqs(vdev); ida_simple_remove(&rng_index_ida, vi->index); kfree(vi); diff --git a/drivers/char/random.c b/drivers/char/random.c index 227fb7802738..b411182df6f6 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -101,7 +101,7 @@ * =============================== * * There are four exported interfaces; two for use within the kernel, - * and two or use from userspace. + * and two for use from userspace. * * Exported interfaces ---- userspace output * ----------------------------------------- @@ -124,7 +124,7 @@ * * The primary kernel interface is * - * void get_random_bytes(void *buf, int nbytes); + * void get_random_bytes(void *buf, int nbytes); * * This interface will return the requested number of random bytes, * and place it in the requested buffer. This is equivalent to a @@ -132,10 +132,10 @@ * * For less critical applications, there are the functions: * - * u32 get_random_u32() - * u64 get_random_u64() - * unsigned int get_random_int() - * unsigned long get_random_long() + * u32 get_random_u32() + * u64 get_random_u64() + * unsigned int get_random_int() + * unsigned long get_random_long() * * These are produced by a cryptographic RNG seeded from get_random_bytes, * and so do not deplete the entropy pool as much. These are recommended @@ -197,10 +197,10 @@ * from the devices are: * * void add_device_randomness(const void *buf, unsigned int size); - * void add_input_randomness(unsigned int type, unsigned int code, + * void add_input_randomness(unsigned int type, unsigned int code, * unsigned int value); * void add_interrupt_randomness(int irq); - * void add_disk_randomness(struct gendisk *disk); + * void add_disk_randomness(struct gendisk *disk); * void add_hwgenerator_randomness(const char *buffer, size_t count, * size_t entropy); * void add_bootloader_randomness(const void *buf, unsigned int size); @@ -296,8 +296,8 @@ * /dev/random and /dev/urandom created already, they can be created * by using the commands: * - * mknod /dev/random c 1 8 - * mknod /dev/urandom c 1 9 + * mknod /dev/random c 1 8 + * mknod /dev/urandom c 1 9 * * Acknowledgements: * ================= @@ -337,7 +337,6 @@ #include #include #include -#include #include #include #include @@ -359,31 +358,12 @@ /* #define ADD_INTERRUPT_BENCH */ -/* - * Configuration information - */ -#define INPUT_POOL_SHIFT 12 -#define INPUT_POOL_WORDS (1 << (INPUT_POOL_SHIFT-5)) -#define OUTPUT_POOL_SHIFT 10 -#define OUTPUT_POOL_WORDS (1 << (OUTPUT_POOL_SHIFT-5)) -#define EXTRACT_SIZE (BLAKE2S_HASH_SIZE / 2) - -/* - * To allow fractional bits to be tracked, the entropy_count field is - * denominated in units of 1/8th bits. - * - * 2*(ENTROPY_SHIFT + poolbitshift) must <= 31, or the multiply in - * credit_entropy_bits() needs to be 64 bits wide. - */ -#define ENTROPY_SHIFT 3 -#define ENTROPY_BITS(r) ((r)->entropy_count >> ENTROPY_SHIFT) - /* * If the entropy count falls under this number of bits, then we * should wake up processes which are selecting or polling on write * access to /dev/random. */ -static int random_write_wakeup_bits = 28 * OUTPUT_POOL_WORDS; +static int random_write_wakeup_bits = 28 * (1 << 5); /* * Originally, we used a primitive polynomial of degree .poolwords @@ -430,14 +410,27 @@ static int random_write_wakeup_bits = 28 * OUTPUT_POOL_WORDS; * polynomial which improves the resulting TGFSR polynomial to be * irreducible, which we have made here. */ -static const struct poolinfo { - int poolbitshift, poolwords, poolbytes, poolfracbits; -#define S(x) ilog2(x)+5, (x), (x)*4, (x) << (ENTROPY_SHIFT+5) - int tap1, tap2, tap3, tap4, tap5; -} poolinfo_table[] = { - /* was: x^128 + x^103 + x^76 + x^51 +x^25 + x + 1 */ +enum poolinfo { + POOL_WORDS = 128, + POOL_WORDMASK = POOL_WORDS - 1, + POOL_BYTES = POOL_WORDS * sizeof(u32), + POOL_BITS = POOL_BYTES * 8, + POOL_BITSHIFT = ilog2(POOL_BITS), + + /* To allow fractional bits to be tracked, the entropy_count field is + * denominated in units of 1/8th bits. */ + POOL_ENTROPY_SHIFT = 3, +#define POOL_ENTROPY_BITS() (input_pool.entropy_count >> POOL_ENTROPY_SHIFT) + POOL_FRACBITS = POOL_BITS << POOL_ENTROPY_SHIFT, + /* x^128 + x^104 + x^76 + x^51 +x^25 + x + 1 */ - { S(128), 104, 76, 51, 25, 1 }, + POOL_TAP1 = 104, + POOL_TAP2 = 76, + POOL_TAP3 = 51, + POOL_TAP4 = 25, + POOL_TAP5 = 1, + + EXTRACT_SIZE = BLAKE2S_HASH_SIZE / 2 }; /* @@ -450,9 +443,9 @@ static DEFINE_SPINLOCK(random_ready_list_lock); static LIST_HEAD(random_ready_list); struct crng_state { - __u32 state[16]; - unsigned long init_time; - spinlock_t lock; + u32 state[16]; + unsigned long init_time; + spinlock_t lock; }; static struct crng_state primary_crng = { @@ -476,10 +469,10 @@ static bool crng_need_final_init = false; #define crng_ready() (likely(crng_init > 1)) static int crng_init_cnt = 0; static unsigned long crng_global_init_time = 0; -#define CRNG_INIT_CNT_THRESH (2*CHACHA_KEY_SIZE) -static void _extract_crng(struct crng_state *crng, __u8 out[CHACHA_BLOCK_SIZE]); +#define CRNG_INIT_CNT_THRESH (2 * CHACHA_KEY_SIZE) +static void _extract_crng(struct crng_state *crng, u8 out[CHACHA_BLOCK_SIZE]); static void _crng_backtrack_protect(struct crng_state *crng, - __u8 tmp[CHACHA_BLOCK_SIZE], int used); + u8 tmp[CHACHA_BLOCK_SIZE], int used); static void process_random_ready_list(void); static void _get_random_bytes(void *buf, int nbytes); @@ -500,38 +493,23 @@ MODULE_PARM_DESC(ratelimit_disable, "Disable random ratelimit suppression"); * **********************************************************************/ -struct entropy_store; -struct entropy_store { - /* read-only data: */ - const struct poolinfo *poolinfo; - __u32 *pool; - const char *name; +static u32 input_pool_data[POOL_WORDS] __latent_entropy; - /* read-write data: */ +static struct { spinlock_t lock; - unsigned short add_ptr; - unsigned short input_rotate; + u16 add_ptr; + u16 input_rotate; int entropy_count; - unsigned int last_data_init:1; - __u8 last_data[EXTRACT_SIZE]; -}; - -static ssize_t extract_entropy(struct entropy_store *r, void *buf, - size_t nbytes, int min, int rsvd); -static ssize_t _extract_entropy(struct entropy_store *r, void *buf, - size_t nbytes, int fips); - -static void crng_reseed(struct crng_state *crng, struct entropy_store *r); -static __u32 input_pool_data[INPUT_POOL_WORDS] __latent_entropy; - -static struct entropy_store input_pool = { - .poolinfo = &poolinfo_table[0], - .name = "input", +} input_pool = { .lock = __SPIN_LOCK_UNLOCKED(input_pool.lock), - .pool = input_pool_data }; -static __u32 const twist_table[8] = { +static ssize_t extract_entropy(void *buf, size_t nbytes, int min); +static ssize_t _extract_entropy(void *buf, size_t nbytes); + +static void crng_reseed(struct crng_state *crng, bool use_input_pool); + +static const u32 twist_table[8] = { 0x00000000, 0x3b6e20c8, 0x76dc4190, 0x4db26158, 0xedb88320, 0xd6d6a3e8, 0x9b64c2b0, 0xa00ae278 }; @@ -545,39 +523,31 @@ static __u32 const twist_table[8] = { * it's cheap to do so and helps slightly in the expected case where * the entropy is concentrated in the low-order bits. */ -static void _mix_pool_bytes(struct entropy_store *r, const void *in, - int nbytes) +static void _mix_pool_bytes(const void *in, int nbytes) { - unsigned long i, tap1, tap2, tap3, tap4, tap5; + unsigned long i; int input_rotate; - int wordmask = r->poolinfo->poolwords - 1; - const unsigned char *bytes = in; - __u32 w; + const u8 *bytes = in; + u32 w; - tap1 = r->poolinfo->tap1; - tap2 = r->poolinfo->tap2; - tap3 = r->poolinfo->tap3; - tap4 = r->poolinfo->tap4; - tap5 = r->poolinfo->tap5; - - input_rotate = r->input_rotate; - i = r->add_ptr; + input_rotate = input_pool.input_rotate; + i = input_pool.add_ptr; /* mix one byte at a time to simplify size handling and churn faster */ while (nbytes--) { w = rol32(*bytes++, input_rotate); - i = (i - 1) & wordmask; + i = (i - 1) & POOL_WORDMASK; /* XOR in the various taps */ - w ^= r->pool[i]; - w ^= r->pool[(i + tap1) & wordmask]; - w ^= r->pool[(i + tap2) & wordmask]; - w ^= r->pool[(i + tap3) & wordmask]; - w ^= r->pool[(i + tap4) & wordmask]; - w ^= r->pool[(i + tap5) & wordmask]; + w ^= input_pool_data[i]; + w ^= input_pool_data[(i + POOL_TAP1) & POOL_WORDMASK]; + w ^= input_pool_data[(i + POOL_TAP2) & POOL_WORDMASK]; + w ^= input_pool_data[(i + POOL_TAP3) & POOL_WORDMASK]; + w ^= input_pool_data[(i + POOL_TAP4) & POOL_WORDMASK]; + w ^= input_pool_data[(i + POOL_TAP5) & POOL_WORDMASK]; /* Mix the result back in with a twist */ - r->pool[i] = (w >> 3) ^ twist_table[w & 7]; + input_pool_data[i] = (w >> 3) ^ twist_table[w & 7]; /* * Normally, we add 7 bits of rotation to the pool. @@ -588,33 +558,31 @@ static void _mix_pool_bytes(struct entropy_store *r, const void *in, input_rotate = (input_rotate + (i ? 7 : 14)) & 31; } - r->input_rotate = input_rotate; - r->add_ptr = i; + input_pool.input_rotate = input_rotate; + input_pool.add_ptr = i; } -static void __mix_pool_bytes(struct entropy_store *r, const void *in, - int nbytes) +static void __mix_pool_bytes(const void *in, int nbytes) { - trace_mix_pool_bytes_nolock(r->name, nbytes, _RET_IP_); - _mix_pool_bytes(r, in, nbytes); + trace_mix_pool_bytes_nolock(nbytes, _RET_IP_); + _mix_pool_bytes(in, nbytes); } -static void mix_pool_bytes(struct entropy_store *r, const void *in, - int nbytes) +static void mix_pool_bytes(const void *in, int nbytes) { unsigned long flags; - trace_mix_pool_bytes(r->name, nbytes, _RET_IP_); - spin_lock_irqsave(&r->lock, flags); - _mix_pool_bytes(r, in, nbytes); - spin_unlock_irqrestore(&r->lock, flags); + trace_mix_pool_bytes(nbytes, _RET_IP_); + spin_lock_irqsave(&input_pool.lock, flags); + _mix_pool_bytes(in, nbytes); + spin_unlock_irqrestore(&input_pool.lock, flags); } struct fast_pool { - __u32 pool[4]; - unsigned long last; - unsigned short reg_idx; - unsigned char count; + u32 pool[4]; + unsigned long last; + u16 reg_idx; + u8 count; }; /* @@ -624,8 +592,8 @@ struct fast_pool { */ static void fast_mix(struct fast_pool *f) { - __u32 a = f->pool[0], b = f->pool[1]; - __u32 c = f->pool[2], d = f->pool[3]; + u32 a = f->pool[0], b = f->pool[1]; + u32 c = f->pool[2], d = f->pool[3]; a += b; c += d; b = rol32(b, 6); d = rol32(d, 27); @@ -669,17 +637,19 @@ static void process_random_ready_list(void) * Use credit_entropy_bits_safe() if the value comes from userspace * or otherwise should be checked for extreme values. */ -static void credit_entropy_bits(struct entropy_store *r, int nbits) +static void credit_entropy_bits(int nbits) { - int entropy_count, orig; - const int pool_size = r->poolinfo->poolfracbits; - int nfrac = nbits << ENTROPY_SHIFT; + int entropy_count, entropy_bits, orig; + int nfrac = nbits << POOL_ENTROPY_SHIFT; + + /* Ensure that the multiplication can avoid being 64 bits wide. */ + BUILD_BUG_ON(2 * (POOL_ENTROPY_SHIFT + POOL_BITSHIFT) > 31); if (!nbits) return; retry: - entropy_count = orig = READ_ONCE(r->entropy_count); + entropy_count = orig = READ_ONCE(input_pool.entropy_count); if (nfrac < 0) { /* Debit */ entropy_count += nfrac; @@ -706,50 +676,43 @@ retry: * turns no matter how large nbits is. */ int pnfrac = nfrac; - const int s = r->poolinfo->poolbitshift + ENTROPY_SHIFT + 2; + const int s = POOL_BITSHIFT + POOL_ENTROPY_SHIFT + 2; /* The +2 corresponds to the /4 in the denominator */ do { - unsigned int anfrac = min(pnfrac, pool_size/2); + unsigned int anfrac = min(pnfrac, POOL_FRACBITS / 2); unsigned int add = - ((pool_size - entropy_count)*anfrac*3) >> s; + ((POOL_FRACBITS - entropy_count) * anfrac * 3) >> s; entropy_count += add; pnfrac -= anfrac; - } while (unlikely(entropy_count < pool_size-2 && pnfrac)); + } while (unlikely(entropy_count < POOL_FRACBITS - 2 && pnfrac)); } if (WARN_ON(entropy_count < 0)) { - pr_warn("negative entropy/overflow: pool %s count %d\n", - r->name, entropy_count); + pr_warn("negative entropy/overflow: count %d\n", entropy_count); entropy_count = 0; - } else if (entropy_count > pool_size) - entropy_count = pool_size; - if (cmpxchg(&r->entropy_count, orig, entropy_count) != orig) + } else if (entropy_count > POOL_FRACBITS) + entropy_count = POOL_FRACBITS; + if (cmpxchg(&input_pool.entropy_count, orig, entropy_count) != orig) goto retry; - trace_credit_entropy_bits(r->name, nbits, - entropy_count >> ENTROPY_SHIFT, _RET_IP_); + trace_credit_entropy_bits(nbits, entropy_count >> POOL_ENTROPY_SHIFT, _RET_IP_); - if (r == &input_pool) { - int entropy_bits = entropy_count >> ENTROPY_SHIFT; - - if (crng_init < 2 && entropy_bits >= 128) - crng_reseed(&primary_crng, r); - } + entropy_bits = entropy_count >> POOL_ENTROPY_SHIFT; + if (crng_init < 2 && entropy_bits >= 128) + crng_reseed(&primary_crng, true); } -static int credit_entropy_bits_safe(struct entropy_store *r, int nbits) +static int credit_entropy_bits_safe(int nbits) { - const int nbits_max = r->poolinfo->poolwords * 32; - if (nbits < 0) return -EINVAL; /* Cap the value to avoid overflows */ - nbits = min(nbits, nbits_max); + nbits = min(nbits, POOL_BITS); - credit_entropy_bits(r, nbits); + credit_entropy_bits(nbits); return 0; } @@ -759,7 +722,7 @@ static int credit_entropy_bits_safe(struct entropy_store *r, int nbits) * *********************************************************************/ -#define CRNG_RESEED_INTERVAL (300*HZ) +#define CRNG_RESEED_INTERVAL (300 * HZ) static DECLARE_WAIT_QUEUE_HEAD(crng_init_wait); @@ -783,9 +746,9 @@ early_param("random.trust_cpu", parse_trust_cpu); static bool crng_init_try_arch(struct crng_state *crng) { - int i; - bool arch_init = true; - unsigned long rv; + int i; + bool arch_init = true; + unsigned long rv; for (i = 4; i < 16; i++) { if (!arch_get_random_seed_long(&rv) && @@ -801,9 +764,9 @@ static bool crng_init_try_arch(struct crng_state *crng) static bool __init crng_init_try_arch_early(struct crng_state *crng) { - int i; - bool arch_init = true; - unsigned long rv; + int i; + bool arch_init = true; + unsigned long rv; for (i = 4; i < 16; i++) { if (!arch_get_random_seed_long_early(&rv) && @@ -820,14 +783,14 @@ static bool __init crng_init_try_arch_early(struct crng_state *crng) static void crng_initialize_secondary(struct crng_state *crng) { chacha_init_consts(crng->state); - _get_random_bytes(&crng->state[4], sizeof(__u32) * 12); + _get_random_bytes(&crng->state[4], sizeof(u32) * 12); crng_init_try_arch(crng); crng->init_time = jiffies - CRNG_RESEED_INTERVAL - 1; } static void __init crng_initialize_primary(struct crng_state *crng) { - _extract_entropy(&input_pool, &crng->state[4], sizeof(__u32) * 12, 0); + _extract_entropy(&crng->state[4], sizeof(u32) * 12); if (crng_init_try_arch_early(crng) && trust_cpu && crng_init < 2) { invalidate_batched_entropy(); numa_crng_init(); @@ -873,7 +836,7 @@ static void do_numa_crng_init(struct work_struct *work) struct crng_state *crng; struct crng_state **pool; - pool = kcalloc(nr_node_ids, sizeof(*pool), GFP_KERNEL|__GFP_NOFAIL); + pool = kcalloc(nr_node_ids, sizeof(*pool), GFP_KERNEL | __GFP_NOFAIL); for_each_online_node(i) { crng = kmalloc_node(sizeof(struct crng_state), GFP_KERNEL | __GFP_NOFAIL, i); @@ -917,10 +880,10 @@ static struct crng_state *select_crng(void) * path. So we can't afford to dilly-dally. Returns the number of * bytes processed from cp. */ -static size_t crng_fast_load(const char *cp, size_t len) +static size_t crng_fast_load(const u8 *cp, size_t len) { unsigned long flags; - char *p; + u8 *p; size_t ret = 0; if (!spin_trylock_irqsave(&primary_crng.lock, flags)) @@ -929,7 +892,7 @@ static size_t crng_fast_load(const char *cp, size_t len) spin_unlock_irqrestore(&primary_crng.lock, flags); return 0; } - p = (unsigned char *) &primary_crng.state[4]; + p = (u8 *)&primary_crng.state[4]; while (len > 0 && crng_init_cnt < CRNG_INIT_CNT_THRESH) { p[crng_init_cnt % CHACHA_KEY_SIZE] ^= *cp; cp++; crng_init_cnt++; len--; ret++; @@ -957,14 +920,14 @@ static size_t crng_fast_load(const char *cp, size_t len) * like a fixed DMI table (for example), which might very well be * unique to the machine, but is otherwise unvarying. */ -static int crng_slow_load(const char *cp, size_t len) +static int crng_slow_load(const u8 *cp, size_t len) { - unsigned long flags; - static unsigned char lfsr = 1; - unsigned char tmp; - unsigned i, max = CHACHA_KEY_SIZE; - const char * src_buf = cp; - char * dest_buf = (char *) &primary_crng.state[4]; + unsigned long flags; + static u8 lfsr = 1; + u8 tmp; + unsigned int i, max = CHACHA_KEY_SIZE; + const u8 *src_buf = cp; + u8 *dest_buf = (u8 *)&primary_crng.state[4]; if (!spin_trylock_irqsave(&primary_crng.lock, flags)) return 0; @@ -975,7 +938,7 @@ static int crng_slow_load(const char *cp, size_t len) if (len > max) max = len; - for (i = 0; i < max ; i++) { + for (i = 0; i < max; i++) { tmp = lfsr; lfsr >>= 1; if (tmp & 1) @@ -988,17 +951,17 @@ static int crng_slow_load(const char *cp, size_t len) return 1; } -static void crng_reseed(struct crng_state *crng, struct entropy_store *r) +static void crng_reseed(struct crng_state *crng, bool use_input_pool) { - unsigned long flags; - int i, num; + unsigned long flags; + int i, num; union { - __u8 block[CHACHA_BLOCK_SIZE]; - __u32 key[8]; + u8 block[CHACHA_BLOCK_SIZE]; + u32 key[8]; } buf; - if (r) { - num = extract_entropy(r, &buf, 32, 16, 0); + if (use_input_pool) { + num = extract_entropy(&buf, 32, 16); if (num == 0) return; } else { @@ -1008,11 +971,11 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r) } spin_lock_irqsave(&crng->lock, flags); for (i = 0; i < 8; i++) { - unsigned long rv; + unsigned long rv; if (!arch_get_random_seed_long(&rv) && !arch_get_random_long(&rv)) rv = random_get_entropy(); - crng->state[i+4] ^= buf.key[i] ^ rv; + crng->state[i + 4] ^= buf.key[i] ^ rv; } memzero_explicit(&buf, sizeof(buf)); WRITE_ONCE(crng->init_time, jiffies); @@ -1020,8 +983,7 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r) crng_finalize_init(crng); } -static void _extract_crng(struct crng_state *crng, - __u8 out[CHACHA_BLOCK_SIZE]) +static void _extract_crng(struct crng_state *crng, u8 out[CHACHA_BLOCK_SIZE]) { unsigned long flags, init_time; @@ -1029,8 +991,7 @@ static void _extract_crng(struct crng_state *crng, init_time = READ_ONCE(crng->init_time); if (time_after(READ_ONCE(crng_global_init_time), init_time) || time_after(jiffies, init_time + CRNG_RESEED_INTERVAL)) - crng_reseed(crng, crng == &primary_crng ? - &input_pool : NULL); + crng_reseed(crng, crng == &primary_crng); } spin_lock_irqsave(&crng->lock, flags); chacha20_block(&crng->state[0], out); @@ -1039,7 +1000,7 @@ static void _extract_crng(struct crng_state *crng, spin_unlock_irqrestore(&crng->lock, flags); } -static void extract_crng(__u8 out[CHACHA_BLOCK_SIZE]) +static void extract_crng(u8 out[CHACHA_BLOCK_SIZE]) { _extract_crng(select_crng(), out); } @@ -1049,26 +1010,26 @@ static void extract_crng(__u8 out[CHACHA_BLOCK_SIZE]) * enough) to mutate the CRNG key to provide backtracking protection. */ static void _crng_backtrack_protect(struct crng_state *crng, - __u8 tmp[CHACHA_BLOCK_SIZE], int used) + u8 tmp[CHACHA_BLOCK_SIZE], int used) { - unsigned long flags; - __u32 *s, *d; - int i; + unsigned long flags; + u32 *s, *d; + int i; - used = round_up(used, sizeof(__u32)); + used = round_up(used, sizeof(u32)); if (used + CHACHA_KEY_SIZE > CHACHA_BLOCK_SIZE) { extract_crng(tmp); used = 0; } spin_lock_irqsave(&crng->lock, flags); - s = (__u32 *) &tmp[used]; + s = (u32 *)&tmp[used]; d = &crng->state[4]; - for (i=0; i < 8; i++) + for (i = 0; i < 8; i++) *d++ ^= *s++; spin_unlock_irqrestore(&crng->lock, flags); } -static void crng_backtrack_protect(__u8 tmp[CHACHA_BLOCK_SIZE], int used) +static void crng_backtrack_protect(u8 tmp[CHACHA_BLOCK_SIZE], int used) { _crng_backtrack_protect(select_crng(), tmp, used); } @@ -1076,7 +1037,7 @@ static void crng_backtrack_protect(__u8 tmp[CHACHA_BLOCK_SIZE], int used) static ssize_t extract_crng_user(void __user *buf, size_t nbytes) { ssize_t ret = 0, i = CHACHA_BLOCK_SIZE; - __u8 tmp[CHACHA_BLOCK_SIZE] __aligned(4); + u8 tmp[CHACHA_BLOCK_SIZE] __aligned(4); int large_request = (nbytes > 256); while (nbytes) { @@ -1108,7 +1069,6 @@ static ssize_t extract_crng_user(void __user *buf, size_t nbytes) return ret; } - /********************************************************************* * * Entropy input management @@ -1141,8 +1101,8 @@ void add_device_randomness(const void *buf, unsigned int size) trace_add_device_randomness(size, _RET_IP_); spin_lock_irqsave(&input_pool.lock, flags); - _mix_pool_bytes(&input_pool, buf, size); - _mix_pool_bytes(&input_pool, &time, sizeof(time)); + _mix_pool_bytes(buf, size); + _mix_pool_bytes(&time, sizeof(time)); spin_unlock_irqrestore(&input_pool.lock, flags); } EXPORT_SYMBOL(add_device_randomness); @@ -1161,19 +1121,17 @@ static struct timer_rand_state input_timer_state = INIT_TIMER_RAND_STATE; */ static void add_timer_randomness(struct timer_rand_state *state, unsigned num) { - struct entropy_store *r; struct { long jiffies; - unsigned cycles; - unsigned num; + unsigned int cycles; + unsigned int num; } sample; long delta, delta2, delta3; sample.jiffies = jiffies; sample.cycles = random_get_entropy(); sample.num = num; - r = &input_pool; - mix_pool_bytes(r, &sample, sizeof(sample)); + mix_pool_bytes(&sample, sizeof(sample)); /* * Calculate number of bits of randomness we probably added. @@ -1205,11 +1163,11 @@ static void add_timer_randomness(struct timer_rand_state *state, unsigned num) * Round down by 1 bit on general principles, * and limit entropy estimate to 12 bits. */ - credit_entropy_bits(r, min_t(int, fls(delta>>1), 11)); + credit_entropy_bits(min_t(int, fls(delta >> 1), 11)); } void add_input_randomness(unsigned int type, unsigned int code, - unsigned int value) + unsigned int value) { static unsigned char last_value; @@ -1220,7 +1178,7 @@ void add_input_randomness(unsigned int type, unsigned int code, last_value = value; add_timer_randomness(&input_timer_state, (type << 4) ^ code ^ (code >> 4) ^ value); - trace_add_input_randomness(ENTROPY_BITS(&input_pool)); + trace_add_input_randomness(POOL_ENTROPY_BITS()); } EXPORT_SYMBOL_GPL(add_input_randomness); @@ -1229,33 +1187,33 @@ static DEFINE_PER_CPU(struct fast_pool, irq_randomness); #ifdef ADD_INTERRUPT_BENCH static unsigned long avg_cycles, avg_deviation; -#define AVG_SHIFT 8 /* Exponential average factor k=1/256 */ -#define FIXED_1_2 (1 << (AVG_SHIFT-1)) +#define AVG_SHIFT 8 /* Exponential average factor k=1/256 */ +#define FIXED_1_2 (1 << (AVG_SHIFT - 1)) static void add_interrupt_bench(cycles_t start) { - long delta = random_get_entropy() - start; + long delta = random_get_entropy() - start; - /* Use a weighted moving average */ - delta = delta - ((avg_cycles + FIXED_1_2) >> AVG_SHIFT); - avg_cycles += delta; - /* And average deviation */ - delta = abs(delta) - ((avg_deviation + FIXED_1_2) >> AVG_SHIFT); - avg_deviation += delta; + /* Use a weighted moving average */ + delta = delta - ((avg_cycles + FIXED_1_2) >> AVG_SHIFT); + avg_cycles += delta; + /* And average deviation */ + delta = abs(delta) - ((avg_deviation + FIXED_1_2) >> AVG_SHIFT); + avg_deviation += delta; } #else #define add_interrupt_bench(x) #endif -static __u32 get_reg(struct fast_pool *f, struct pt_regs *regs) +static u32 get_reg(struct fast_pool *f, struct pt_regs *regs) { - __u32 *ptr = (__u32 *) regs; + u32 *ptr = (u32 *)regs; unsigned int idx; if (regs == NULL) return 0; idx = READ_ONCE(f->reg_idx); - if (idx >= sizeof(struct pt_regs) / sizeof(__u32)) + if (idx >= sizeof(struct pt_regs) / sizeof(u32)) idx = 0; ptr += idx++; WRITE_ONCE(f->reg_idx, idx); @@ -1264,13 +1222,12 @@ static __u32 get_reg(struct fast_pool *f, struct pt_regs *regs) void add_interrupt_randomness(int irq) { - struct entropy_store *r; - struct fast_pool *fast_pool = this_cpu_ptr(&irq_randomness); - struct pt_regs *regs = get_irq_regs(); - unsigned long now = jiffies; - cycles_t cycles = random_get_entropy(); - __u32 c_high, j_high; - __u64 ip; + struct fast_pool *fast_pool = this_cpu_ptr(&irq_randomness); + struct pt_regs *regs = get_irq_regs(); + unsigned long now = jiffies; + cycles_t cycles = random_get_entropy(); + u32 c_high, j_high; + u64 ip; if (cycles == 0) cycles = get_reg(fast_pool, regs); @@ -1280,38 +1237,35 @@ void add_interrupt_randomness(int irq) fast_pool->pool[1] ^= now ^ c_high; ip = regs ? instruction_pointer(regs) : _RET_IP_; fast_pool->pool[2] ^= ip; - fast_pool->pool[3] ^= (sizeof(ip) > 4) ? ip >> 32 : - get_reg(fast_pool, regs); + fast_pool->pool[3] ^= + (sizeof(ip) > 4) ? ip >> 32 : get_reg(fast_pool, regs); fast_mix(fast_pool); add_interrupt_bench(cycles); if (unlikely(crng_init == 0)) { if ((fast_pool->count >= 64) && - crng_fast_load((char *) fast_pool->pool, - sizeof(fast_pool->pool)) > 0) { + crng_fast_load((u8 *)fast_pool->pool, sizeof(fast_pool->pool)) > 0) { fast_pool->count = 0; fast_pool->last = now; } return; } - if ((fast_pool->count < 64) && - !time_after(now, fast_pool->last + HZ)) + if ((fast_pool->count < 64) && !time_after(now, fast_pool->last + HZ)) return; - r = &input_pool; - if (!spin_trylock(&r->lock)) + if (!spin_trylock(&input_pool.lock)) return; fast_pool->last = now; - __mix_pool_bytes(r, &fast_pool->pool, sizeof(fast_pool->pool)); - spin_unlock(&r->lock); + __mix_pool_bytes(&fast_pool->pool, sizeof(fast_pool->pool)); + spin_unlock(&input_pool.lock); fast_pool->count = 0; /* award one bit for the contents of the fast pool */ - credit_entropy_bits(r, 1); + credit_entropy_bits(1); } EXPORT_SYMBOL_GPL(add_interrupt_randomness); @@ -1322,7 +1276,7 @@ void add_disk_randomness(struct gendisk *disk) return; /* first major is 1, so we get >= 0x200 here */ add_timer_randomness(disk->random, 0x100 + disk_devt(disk)); - trace_add_disk_randomness(disk_devt(disk), ENTROPY_BITS(&input_pool)); + trace_add_disk_randomness(disk_devt(disk), POOL_ENTROPY_BITS()); } EXPORT_SYMBOL_GPL(add_disk_randomness); #endif @@ -1337,43 +1291,36 @@ EXPORT_SYMBOL_GPL(add_disk_randomness); * This function decides how many bytes to actually take from the * given pool, and also debits the entropy count accordingly. */ -static size_t account(struct entropy_store *r, size_t nbytes, int min, - int reserved) +static size_t account(size_t nbytes, int min) { - int entropy_count, orig, have_bytes; + int entropy_count, orig; size_t ibytes, nfrac; - BUG_ON(r->entropy_count > r->poolinfo->poolfracbits); + BUG_ON(input_pool.entropy_count > POOL_FRACBITS); /* Can we pull enough? */ retry: - entropy_count = orig = READ_ONCE(r->entropy_count); - ibytes = nbytes; - /* never pull more than available */ - have_bytes = entropy_count >> (ENTROPY_SHIFT + 3); - - if ((have_bytes -= reserved) < 0) - have_bytes = 0; - ibytes = min_t(size_t, ibytes, have_bytes); - if (ibytes < min) - ibytes = 0; - + entropy_count = orig = READ_ONCE(input_pool.entropy_count); if (WARN_ON(entropy_count < 0)) { - pr_warn("negative entropy count: pool %s count %d\n", - r->name, entropy_count); + pr_warn("negative entropy count: count %d\n", entropy_count); entropy_count = 0; } - nfrac = ibytes << (ENTROPY_SHIFT + 3); - if ((size_t) entropy_count > nfrac) + + /* never pull more than available */ + ibytes = min_t(size_t, nbytes, entropy_count >> (POOL_ENTROPY_SHIFT + 3)); + if (ibytes < min) + ibytes = 0; + nfrac = ibytes << (POOL_ENTROPY_SHIFT + 3); + if ((size_t)entropy_count > nfrac) entropy_count -= nfrac; else entropy_count = 0; - if (cmpxchg(&r->entropy_count, orig, entropy_count) != orig) + if (cmpxchg(&input_pool.entropy_count, orig, entropy_count) != orig) goto retry; - trace_debit_entropy(r->name, 8 * ibytes); - if (ibytes && ENTROPY_BITS(r) < random_write_wakeup_bits) { + trace_debit_entropy(8 * ibytes); + if (ibytes && POOL_ENTROPY_BITS() < random_write_wakeup_bits) { wake_up_interruptible(&random_write_wait); kill_fasync(&fasync, SIGIO, POLL_OUT); } @@ -1386,7 +1333,7 @@ retry: * * Note: we assume that .poolwords is a multiple of 16 words. */ -static void extract_buf(struct entropy_store *r, __u8 *out) +static void extract_buf(u8 *out) { struct blake2s_state state __aligned(__alignof__(unsigned long)); u8 hash[BLAKE2S_HASH_SIZE]; @@ -1408,9 +1355,8 @@ static void extract_buf(struct entropy_store *r, __u8 *out) } /* Generate a hash across the pool */ - spin_lock_irqsave(&r->lock, flags); - blake2s_update(&state, (const u8 *)r->pool, - r->poolinfo->poolwords * sizeof(*r->pool)); + spin_lock_irqsave(&input_pool.lock, flags); + blake2s_update(&state, (const u8 *)input_pool_data, POOL_BYTES); blake2s_final(&state, hash); /* final zeros out state */ /* @@ -1422,8 +1368,8 @@ static void extract_buf(struct entropy_store *r, __u8 *out) * brute-forcing the feedback as hard as brute-forcing the * hash. */ - __mix_pool_bytes(r, hash, sizeof(hash)); - spin_unlock_irqrestore(&r->lock, flags); + __mix_pool_bytes(hash, sizeof(hash)); + spin_unlock_irqrestore(&input_pool.lock, flags); /* Note that EXTRACT_SIZE is half of hash size here, because above * we've dumped the full length back into mixer. By reducing the @@ -1433,23 +1379,13 @@ static void extract_buf(struct entropy_store *r, __u8 *out) memzero_explicit(hash, sizeof(hash)); } -static ssize_t _extract_entropy(struct entropy_store *r, void *buf, - size_t nbytes, int fips) +static ssize_t _extract_entropy(void *buf, size_t nbytes) { ssize_t ret = 0, i; - __u8 tmp[EXTRACT_SIZE]; - unsigned long flags; + u8 tmp[EXTRACT_SIZE]; while (nbytes) { - extract_buf(r, tmp); - - if (fips) { - spin_lock_irqsave(&r->lock, flags); - if (!memcmp(tmp, r->last_data, EXTRACT_SIZE)) - panic("Hardware RNG duplicated output!\n"); - memcpy(r->last_data, tmp, EXTRACT_SIZE); - spin_unlock_irqrestore(&r->lock, flags); - } + extract_buf(tmp); i = min_t(int, nbytes, EXTRACT_SIZE); memcpy(buf, tmp, i); nbytes -= i; @@ -1468,42 +1404,19 @@ static ssize_t _extract_entropy(struct entropy_store *r, void *buf, * returns it in a buffer. * * The min parameter specifies the minimum amount we can pull before - * failing to avoid races that defeat catastrophic reseeding while the - * reserved parameter indicates how much entropy we must leave in the - * pool after each pull to avoid starving other readers. + * failing to avoid races that defeat catastrophic reseeding. */ -static ssize_t extract_entropy(struct entropy_store *r, void *buf, - size_t nbytes, int min, int reserved) +static ssize_t extract_entropy(void *buf, size_t nbytes, int min) { - __u8 tmp[EXTRACT_SIZE]; - unsigned long flags; - - /* if last_data isn't primed, we need EXTRACT_SIZE extra bytes */ - if (fips_enabled) { - spin_lock_irqsave(&r->lock, flags); - if (!r->last_data_init) { - r->last_data_init = 1; - spin_unlock_irqrestore(&r->lock, flags); - trace_extract_entropy(r->name, EXTRACT_SIZE, - ENTROPY_BITS(r), _RET_IP_); - extract_buf(r, tmp); - spin_lock_irqsave(&r->lock, flags); - memcpy(r->last_data, tmp, EXTRACT_SIZE); - } - spin_unlock_irqrestore(&r->lock, flags); - } - - trace_extract_entropy(r->name, nbytes, ENTROPY_BITS(r), _RET_IP_); - nbytes = account(r, nbytes, min, reserved); - - return _extract_entropy(r, buf, nbytes, fips_enabled); + trace_extract_entropy(nbytes, POOL_ENTROPY_BITS(), _RET_IP_); + nbytes = account(nbytes, min); + return _extract_entropy(buf, nbytes); } #define warn_unseeded_randomness(previous) \ - _warn_unseeded_randomness(__func__, (void *) _RET_IP_, (previous)) + _warn_unseeded_randomness(__func__, (void *)_RET_IP_, (previous)) -static void _warn_unseeded_randomness(const char *func_name, void *caller, - void **previous) +static void _warn_unseeded_randomness(const char *func_name, void *caller, void **previous) { #ifdef CONFIG_WARN_ALL_UNSEEDED_RANDOM const bool print_once = false; @@ -1511,8 +1424,7 @@ static void _warn_unseeded_randomness(const char *func_name, void *caller, static bool print_once __read_mostly; #endif - if (print_once || - crng_ready() || + if (print_once || crng_ready() || (previous && (caller == READ_ONCE(*previous)))) return; WRITE_ONCE(*previous, caller); @@ -1520,9 +1432,8 @@ static void _warn_unseeded_randomness(const char *func_name, void *caller, print_once = true; #endif if (__ratelimit(&unseeded_warning)) - printk_deferred(KERN_NOTICE "random: %s called from %pS " - "with crng_init=%d\n", func_name, caller, - crng_init); + printk_deferred(KERN_NOTICE "random: %s called from %pS with crng_init=%d\n", + func_name, caller, crng_init); } /* @@ -1537,7 +1448,7 @@ static void _warn_unseeded_randomness(const char *func_name, void *caller, */ static void _get_random_bytes(void *buf, int nbytes) { - __u8 tmp[CHACHA_BLOCK_SIZE] __aligned(4); + u8 tmp[CHACHA_BLOCK_SIZE] __aligned(4); trace_get_random_bytes(nbytes, _RET_IP_); @@ -1565,7 +1476,6 @@ void get_random_bytes(void *buf, int nbytes) } EXPORT_SYMBOL(get_random_bytes); - /* * Each time the timer fires, we expect that we got an unpredictable * jump in the cycle counter. Even if the timer is running on another @@ -1581,7 +1491,7 @@ EXPORT_SYMBOL(get_random_bytes); */ static void entropy_timer(struct timer_list *t) { - credit_entropy_bits(&input_pool, 1); + credit_entropy_bits(1); } /* @@ -1604,15 +1514,15 @@ static void try_to_generate_entropy(void) timer_setup_on_stack(&stack.timer, entropy_timer, 0); while (!crng_ready()) { if (!timer_pending(&stack.timer)) - mod_timer(&stack.timer, jiffies+1); - mix_pool_bytes(&input_pool, &stack.now, sizeof(stack.now)); + mod_timer(&stack.timer, jiffies + 1); + mix_pool_bytes(&stack.now, sizeof(stack.now)); schedule(); stack.now = random_get_entropy(); } del_timer_sync(&stack.timer); destroy_timer_on_stack(&stack.timer); - mix_pool_bytes(&input_pool, &stack.now, sizeof(stack.now)); + mix_pool_bytes(&stack.now, sizeof(stack.now)); } /* @@ -1731,7 +1641,7 @@ EXPORT_SYMBOL(del_random_ready_callback); int __must_check get_random_bytes_arch(void *buf, int nbytes) { int left = nbytes; - char *p = buf; + u8 *p = buf; trace_get_random_bytes_arch(left, _RET_IP_); while (left) { @@ -1753,26 +1663,24 @@ EXPORT_SYMBOL(get_random_bytes_arch); /* * init_std_data - initialize pool with system data * - * @r: pool to initialize - * * This function clears the pool's entropy count and mixes some system * data into the pool to prepare it for use. The pool is not cleared * as that can only decrease the entropy in the pool. */ -static void __init init_std_data(struct entropy_store *r) +static void __init init_std_data(void) { int i; ktime_t now = ktime_get_real(); unsigned long rv; - mix_pool_bytes(r, &now, sizeof(now)); - for (i = r->poolinfo->poolbytes; i > 0; i -= sizeof(rv)) { + mix_pool_bytes(&now, sizeof(now)); + for (i = POOL_BYTES; i > 0; i -= sizeof(rv)) { if (!arch_get_random_seed_long(&rv) && !arch_get_random_long(&rv)) rv = random_get_entropy(); - mix_pool_bytes(r, &rv, sizeof(rv)); + mix_pool_bytes(&rv, sizeof(rv)); } - mix_pool_bytes(r, utsname(), sizeof(*(utsname()))); + mix_pool_bytes(utsname(), sizeof(*(utsname()))); } /* @@ -1787,7 +1695,7 @@ static void __init init_std_data(struct entropy_store *r) */ int __init rand_initialize(void) { - init_std_data(&input_pool); + init_std_data(); if (crng_need_final_init) crng_finalize_init(&primary_crng); crng_initialize_primary(&primary_crng); @@ -1816,20 +1724,19 @@ void rand_initialize_disk(struct gendisk *disk) } #endif -static ssize_t -urandom_read_nowarn(struct file *file, char __user *buf, size_t nbytes, - loff_t *ppos) +static ssize_t urandom_read_nowarn(struct file *file, char __user *buf, + size_t nbytes, loff_t *ppos) { int ret; - nbytes = min_t(size_t, nbytes, INT_MAX >> (ENTROPY_SHIFT + 3)); + nbytes = min_t(size_t, nbytes, INT_MAX >> (POOL_ENTROPY_SHIFT + 3)); ret = extract_crng_user(buf, nbytes); - trace_urandom_read(8 * nbytes, 0, ENTROPY_BITS(&input_pool)); + trace_urandom_read(8 * nbytes, 0, POOL_ENTROPY_BITS()); return ret; } -static ssize_t -urandom_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos) +static ssize_t urandom_read(struct file *file, char __user *buf, size_t nbytes, + loff_t *ppos) { static int maxwarn = 10; @@ -1843,8 +1750,8 @@ urandom_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos) return urandom_read_nowarn(file, buf, nbytes, ppos); } -static ssize_t -random_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos) +static ssize_t random_read(struct file *file, char __user *buf, size_t nbytes, + loff_t *ppos) { int ret; @@ -1854,8 +1761,7 @@ random_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos) return urandom_read_nowarn(file, buf, nbytes, ppos); } -static __poll_t -random_poll(struct file *file, poll_table * wait) +static __poll_t random_poll(struct file *file, poll_table *wait) { __poll_t mask; @@ -1864,16 +1770,15 @@ random_poll(struct file *file, poll_table * wait) mask = 0; if (crng_ready()) mask |= EPOLLIN | EPOLLRDNORM; - if (ENTROPY_BITS(&input_pool) < random_write_wakeup_bits) + if (POOL_ENTROPY_BITS() < random_write_wakeup_bits) mask |= EPOLLOUT | EPOLLWRNORM; return mask; } -static int -write_pool(struct entropy_store *r, const char __user *buffer, size_t count) +static int write_pool(const char __user *buffer, size_t count) { size_t bytes; - __u32 t, buf[16]; + u32 t, buf[16]; const char __user *p = buffer; while (count > 0) { @@ -1883,7 +1788,7 @@ write_pool(struct entropy_store *r, const char __user *buffer, size_t count) if (copy_from_user(&buf, p, bytes)) return -EFAULT; - for (b = bytes ; b > 0 ; b -= sizeof(__u32), i++) { + for (b = bytes; b > 0; b -= sizeof(u32), i++) { if (!arch_get_random_int(&t)) break; buf[i] ^= t; @@ -1892,7 +1797,7 @@ write_pool(struct entropy_store *r, const char __user *buffer, size_t count) count -= bytes; p += bytes; - mix_pool_bytes(r, buf, bytes); + mix_pool_bytes(buf, bytes); cond_resched(); } @@ -1904,7 +1809,7 @@ static ssize_t random_write(struct file *file, const char __user *buffer, { size_t ret; - ret = write_pool(&input_pool, buffer, count); + ret = write_pool(buffer, count); if (ret) return ret; @@ -1920,7 +1825,7 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg) switch (cmd) { case RNDGETENTCNT: /* inherently racy, no point locking */ - ent_count = ENTROPY_BITS(&input_pool); + ent_count = POOL_ENTROPY_BITS(); if (put_user(ent_count, p)) return -EFAULT; return 0; @@ -1929,7 +1834,7 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg) return -EPERM; if (get_user(ent_count, p)) return -EFAULT; - return credit_entropy_bits_safe(&input_pool, ent_count); + return credit_entropy_bits_safe(ent_count); case RNDADDENTROPY: if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -1939,11 +1844,10 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg) return -EINVAL; if (get_user(size, p++)) return -EFAULT; - retval = write_pool(&input_pool, (const char __user *)p, - size); + retval = write_pool((const char __user *)p, size); if (retval < 0) return retval; - return credit_entropy_bits_safe(&input_pool, ent_count); + return credit_entropy_bits_safe(ent_count); case RNDZAPENTCNT: case RNDCLEARPOOL: /* @@ -1959,7 +1863,7 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg) return -EPERM; if (crng_init < 2) return -ENODATA; - crng_reseed(&primary_crng, &input_pool); + crng_reseed(&primary_crng, true); WRITE_ONCE(crng_global_init_time, jiffies - 1); return 0; default: @@ -1973,9 +1877,9 @@ static int random_fasync(int fd, struct file *filp, int on) } const struct file_operations random_fops = { - .read = random_read, + .read = random_read, .write = random_write, - .poll = random_poll, + .poll = random_poll, .unlocked_ioctl = random_ioctl, .compat_ioctl = compat_ptr_ioctl, .fasync = random_fasync, @@ -1983,7 +1887,7 @@ const struct file_operations random_fops = { }; const struct file_operations urandom_fops = { - .read = urandom_read, + .read = urandom_read, .write = random_write, .unlocked_ioctl = random_ioctl, .compat_ioctl = compat_ptr_ioctl, @@ -1991,19 +1895,19 @@ const struct file_operations urandom_fops = { .llseek = noop_llseek, }; -SYSCALL_DEFINE3(getrandom, char __user *, buf, size_t, count, - unsigned int, flags) +SYSCALL_DEFINE3(getrandom, char __user *, buf, size_t, count, unsigned int, + flags) { int ret; - if (flags & ~(GRND_NONBLOCK|GRND_RANDOM|GRND_INSECURE)) + if (flags & ~(GRND_NONBLOCK | GRND_RANDOM | GRND_INSECURE)) return -EINVAL; /* * Requesting insecure and blocking randomness at the same time makes * no sense. */ - if ((flags & (GRND_INSECURE|GRND_RANDOM)) == (GRND_INSECURE|GRND_RANDOM)) + if ((flags & (GRND_INSECURE | GRND_RANDOM)) == (GRND_INSECURE | GRND_RANDOM)) return -EINVAL; if (count > INT_MAX) @@ -2030,7 +1934,7 @@ SYSCALL_DEFINE3(getrandom, char __user *, buf, size_t, count, #include static int min_write_thresh; -static int max_write_thresh = INPUT_POOL_WORDS * 32; +static int max_write_thresh = POOL_BITS; static int random_min_urandom_seed = 60; static char sysctl_bootid[16]; @@ -2043,8 +1947,8 @@ static char sysctl_bootid[16]; * returned as an ASCII string in the standard UUID format; if via the * sysctl system call, as 16 bytes of binary data. */ -static int proc_do_uuid(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) +static int proc_do_uuid(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos) { struct ctl_table fake_table; unsigned char buf[64], tmp_uuid[16], *uuid; @@ -2073,13 +1977,13 @@ static int proc_do_uuid(struct ctl_table *table, int write, /* * Return entropy available scaled to integral bits */ -static int proc_do_entropy(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) +static int proc_do_entropy(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos) { struct ctl_table fake_table; int entropy_count; - entropy_count = *(int *)table->data >> ENTROPY_SHIFT; + entropy_count = *(int *)table->data >> POOL_ENTROPY_SHIFT; fake_table.data = &entropy_count; fake_table.maxlen = sizeof(entropy_count); @@ -2087,7 +1991,7 @@ static int proc_do_entropy(struct ctl_table *table, int write, return proc_dointvec(&fake_table, write, buffer, lenp, ppos); } -static int sysctl_poolsize = INPUT_POOL_WORDS * 32; +static int sysctl_poolsize = POOL_BITS; extern struct ctl_table random_table[]; struct ctl_table random_table[] = { { @@ -2151,7 +2055,7 @@ struct ctl_table random_table[] = { #endif { } }; -#endif /* CONFIG_SYSCTL */ +#endif /* CONFIG_SYSCTL */ struct batched_entropy { union { @@ -2171,7 +2075,7 @@ struct batched_entropy { * point prior. */ static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u64) = { - .batch_lock = __SPIN_LOCK_UNLOCKED(batched_entropy_u64.lock), + .batch_lock = __SPIN_LOCK_UNLOCKED(batched_entropy_u64.lock), }; u64 get_random_u64(void) @@ -2196,7 +2100,7 @@ u64 get_random_u64(void) EXPORT_SYMBOL(get_random_u64); static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u32) = { - .batch_lock = __SPIN_LOCK_UNLOCKED(batched_entropy_u32.lock), + .batch_lock = __SPIN_LOCK_UNLOCKED(batched_entropy_u32.lock), }; u32 get_random_u32(void) { @@ -2228,7 +2132,7 @@ static void invalidate_batched_entropy(void) int cpu; unsigned long flags; - for_each_possible_cpu (cpu) { + for_each_possible_cpu(cpu) { struct batched_entropy *batched_entropy; batched_entropy = per_cpu_ptr(&batched_entropy_u32, cpu); @@ -2257,8 +2161,7 @@ static void invalidate_batched_entropy(void) * Return: A page aligned address within [start, start + range). On error, * @start is returned. */ -unsigned long -randomize_page(unsigned long start, unsigned long range) +unsigned long randomize_page(unsigned long start, unsigned long range) { if (!PAGE_ALIGNED(start)) { range -= PAGE_ALIGN(start) - start; @@ -2283,11 +2186,9 @@ randomize_page(unsigned long start, unsigned long range) void add_hwgenerator_randomness(const char *buffer, size_t count, size_t entropy) { - struct entropy_store *poolp = &input_pool; - if (unlikely(crng_init == 0)) { size_t ret = crng_fast_load(buffer, count); - mix_pool_bytes(poolp, buffer, ret); + mix_pool_bytes(buffer, ret); count -= ret; buffer += ret; if (!count || crng_init == 0) @@ -2300,9 +2201,9 @@ void add_hwgenerator_randomness(const char *buffer, size_t count, */ wait_event_interruptible(random_write_wait, !system_wq || kthread_should_stop() || - ENTROPY_BITS(&input_pool) <= random_write_wakeup_bits); - mix_pool_bytes(poolp, buffer, count); - credit_entropy_bits(poolp, entropy); + POOL_ENTROPY_BITS() <= random_write_wakeup_bits); + mix_pool_bytes(buffer, count); + credit_entropy_bits(entropy); } EXPORT_SYMBOL_GPL(add_hwgenerator_randomness); diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index 660c5c388c29..2359889a35a0 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -1958,7 +1958,7 @@ static void virtcons_remove(struct virtio_device *vdev) spin_unlock_irq(&pdrvdata_lock); /* Disable interrupts for vqs */ - vdev->config->reset(vdev); + virtio_reset_device(vdev); /* Finish up work that's lined up */ if (use_multiport(portdev)) cancel_work_sync(&portdev->control_work); @@ -2148,7 +2148,7 @@ static int virtcons_freeze(struct virtio_device *vdev) portdev = vdev->priv; - vdev->config->reset(vdev); + virtio_reset_device(vdev); if (use_multiport(portdev)) virtqueue_disable_cb(portdev->c_ivq); diff --git a/drivers/crypto/virtio/virtio_crypto_core.c b/drivers/crypto/virtio/virtio_crypto_core.c index e2375d992308..8e977b7627cb 100644 --- a/drivers/crypto/virtio/virtio_crypto_core.c +++ b/drivers/crypto/virtio/virtio_crypto_core.c @@ -404,7 +404,7 @@ static int virtcrypto_probe(struct virtio_device *vdev) free_engines: virtcrypto_clear_crypto_engines(vcrypto); free_vqs: - vcrypto->vdev->config->reset(vdev); + virtio_reset_device(vdev); virtcrypto_del_vqs(vcrypto); free_dev: virtcrypto_devmgr_rm_dev(vcrypto); @@ -436,7 +436,7 @@ static void virtcrypto_remove(struct virtio_device *vdev) if (virtcrypto_dev_started(vcrypto)) virtcrypto_dev_stop(vcrypto); - vdev->config->reset(vdev); + virtio_reset_device(vdev); virtcrypto_free_unused_reqs(vcrypto); virtcrypto_clear_crypto_engines(vcrypto); virtcrypto_del_vqs(vcrypto); @@ -456,7 +456,7 @@ static int virtcrypto_freeze(struct virtio_device *vdev) { struct virtio_crypto *vcrypto = vdev->priv; - vdev->config->reset(vdev); + virtio_reset_device(vdev); virtcrypto_free_unused_reqs(vcrypto); if (virtcrypto_dev_started(vcrypto)) virtcrypto_dev_stop(vcrypto); @@ -492,7 +492,7 @@ static int virtcrypto_restore(struct virtio_device *vdev) free_engines: virtcrypto_clear_crypto_engines(vcrypto); free_vqs: - vcrypto->vdev->config->reset(vdev); + virtio_reset_device(vdev); virtcrypto_del_vqs(vcrypto); return err; } diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 275a76f188ae..a1da2b4b6d73 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -99,6 +99,7 @@ #define AT_XDMAC_CNDC_NDE (0x1 << 0) /* Channel x Next Descriptor Enable */ #define AT_XDMAC_CNDC_NDSUP (0x1 << 1) /* Channel x Next Descriptor Source Update */ #define AT_XDMAC_CNDC_NDDUP (0x1 << 2) /* Channel x Next Descriptor Destination Update */ +#define AT_XDMAC_CNDC_NDVIEW_MASK GENMASK(28, 27) #define AT_XDMAC_CNDC_NDVIEW_NDV0 (0x0 << 3) /* Channel x Next Descriptor View 0 */ #define AT_XDMAC_CNDC_NDVIEW_NDV1 (0x1 << 3) /* Channel x Next Descriptor View 1 */ #define AT_XDMAC_CNDC_NDVIEW_NDV2 (0x2 << 3) /* Channel x Next Descriptor View 2 */ @@ -252,15 +253,15 @@ struct at_xdmac { /* Linked List Descriptor */ struct at_xdmac_lld { - dma_addr_t mbr_nda; /* Next Descriptor Member */ - u32 mbr_ubc; /* Microblock Control Member */ - dma_addr_t mbr_sa; /* Source Address Member */ - dma_addr_t mbr_da; /* Destination Address Member */ - u32 mbr_cfg; /* Configuration Register */ - u32 mbr_bc; /* Block Control Register */ - u32 mbr_ds; /* Data Stride Register */ - u32 mbr_sus; /* Source Microblock Stride Register */ - u32 mbr_dus; /* Destination Microblock Stride Register */ + u32 mbr_nda; /* Next Descriptor Member */ + u32 mbr_ubc; /* Microblock Control Member */ + u32 mbr_sa; /* Source Address Member */ + u32 mbr_da; /* Destination Address Member */ + u32 mbr_cfg; /* Configuration Register */ + u32 mbr_bc; /* Block Control Register */ + u32 mbr_ds; /* Data Stride Register */ + u32 mbr_sus; /* Source Microblock Stride Register */ + u32 mbr_dus; /* Destination Microblock Stride Register */ }; /* 64-bit alignment needed to update CNDA and CUBC registers in an atomic way. */ @@ -385,9 +386,6 @@ static void at_xdmac_start_xfer(struct at_xdmac_chan *atchan, dev_vdbg(chan2dev(&atchan->chan), "%s: desc 0x%p\n", __func__, first); - if (at_xdmac_chan_is_enabled(atchan)) - return; - /* Set transfer as active to not try to start it again. */ first->active_xfer = true; @@ -405,7 +403,8 @@ static void at_xdmac_start_xfer(struct at_xdmac_chan *atchan, */ if (at_xdmac_chan_is_cyclic(atchan)) reg = AT_XDMAC_CNDC_NDVIEW_NDV1; - else if (first->lld.mbr_ubc & AT_XDMAC_MBR_UBC_NDV3) + else if ((first->lld.mbr_ubc & + AT_XDMAC_CNDC_NDVIEW_MASK) == AT_XDMAC_MBR_UBC_NDV3) reg = AT_XDMAC_CNDC_NDVIEW_NDV3; else reg = AT_XDMAC_CNDC_NDVIEW_NDV2; @@ -476,13 +475,12 @@ static dma_cookie_t at_xdmac_tx_submit(struct dma_async_tx_descriptor *tx) spin_lock_irqsave(&atchan->lock, irqflags); cookie = dma_cookie_assign(tx); + list_add_tail(&desc->xfer_node, &atchan->xfers_list); + spin_unlock_irqrestore(&atchan->lock, irqflags); + dev_vdbg(chan2dev(tx->chan), "%s: atchan 0x%p, add desc 0x%p to xfers_list\n", __func__, atchan, desc); - list_add_tail(&desc->xfer_node, &atchan->xfers_list); - if (list_is_singular(&atchan->xfers_list)) - at_xdmac_start_xfer(atchan, desc); - spin_unlock_irqrestore(&atchan->lock, irqflags); return cookie; } @@ -733,7 +731,8 @@ at_xdmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, if (!desc) { dev_err(chan2dev(chan), "can't get descriptor\n"); if (first) - list_splice_init(&first->descs_list, &atchan->free_descs_list); + list_splice_tail_init(&first->descs_list, + &atchan->free_descs_list); goto spin_unlock; } @@ -821,7 +820,8 @@ at_xdmac_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr, if (!desc) { dev_err(chan2dev(chan), "can't get descriptor\n"); if (first) - list_splice_init(&first->descs_list, &atchan->free_descs_list); + list_splice_tail_init(&first->descs_list, + &atchan->free_descs_list); spin_unlock_irqrestore(&atchan->lock, irqflags); return NULL; } @@ -1055,8 +1055,8 @@ at_xdmac_prep_interleaved(struct dma_chan *chan, src_addr, dst_addr, xt, chunk); if (!desc) { - list_splice_init(&first->descs_list, - &atchan->free_descs_list); + list_splice_tail_init(&first->descs_list, + &atchan->free_descs_list); return NULL; } @@ -1136,7 +1136,8 @@ at_xdmac_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src, if (!desc) { dev_err(chan2dev(chan), "can't get descriptor\n"); if (first) - list_splice_init(&first->descs_list, &atchan->free_descs_list); + list_splice_tail_init(&first->descs_list, + &atchan->free_descs_list); return NULL; } @@ -1312,8 +1313,8 @@ at_xdmac_prep_dma_memset_sg(struct dma_chan *chan, struct scatterlist *sgl, sg_dma_len(sg), value); if (!desc && first) - list_splice_init(&first->descs_list, - &atchan->free_descs_list); + list_splice_tail_init(&first->descs_list, + &atchan->free_descs_list); if (!first) first = desc; @@ -1586,20 +1587,6 @@ spin_unlock: return ret; } -/* Call must be protected by lock. */ -static void at_xdmac_remove_xfer(struct at_xdmac_chan *atchan, - struct at_xdmac_desc *desc) -{ - dev_dbg(chan2dev(&atchan->chan), "%s: desc 0x%p\n", __func__, desc); - - /* - * Remove the transfer from the transfer list then move the transfer - * descriptors into the free descriptors list. - */ - list_del(&desc->xfer_node); - list_splice_init(&desc->descs_list, &atchan->free_descs_list); -} - static void at_xdmac_advance_work(struct at_xdmac_chan *atchan) { struct at_xdmac_desc *desc; @@ -1608,14 +1595,14 @@ static void at_xdmac_advance_work(struct at_xdmac_chan *atchan) * If channel is enabled, do nothing, advance_work will be triggered * after the interruption. */ - if (!at_xdmac_chan_is_enabled(atchan) && !list_empty(&atchan->xfers_list)) { - desc = list_first_entry(&atchan->xfers_list, - struct at_xdmac_desc, - xfer_node); - dev_vdbg(chan2dev(&atchan->chan), "%s: desc 0x%p\n", __func__, desc); - if (!desc->active_xfer) - at_xdmac_start_xfer(atchan, desc); - } + if (at_xdmac_chan_is_enabled(atchan) || list_empty(&atchan->xfers_list)) + return; + + desc = list_first_entry(&atchan->xfers_list, struct at_xdmac_desc, + xfer_node); + dev_vdbg(chan2dev(&atchan->chan), "%s: desc 0x%p\n", __func__, desc); + if (!desc->active_xfer) + at_xdmac_start_xfer(atchan, desc); } static void at_xdmac_handle_cyclic(struct at_xdmac_chan *atchan) @@ -1623,16 +1610,22 @@ static void at_xdmac_handle_cyclic(struct at_xdmac_chan *atchan) struct at_xdmac_desc *desc; struct dma_async_tx_descriptor *txd; - if (!list_empty(&atchan->xfers_list)) { - desc = list_first_entry(&atchan->xfers_list, - struct at_xdmac_desc, xfer_node); - txd = &desc->tx_dma_desc; - - if (txd->flags & DMA_PREP_INTERRUPT) - dmaengine_desc_get_callback_invoke(txd, NULL); + spin_lock_irq(&atchan->lock); + dev_dbg(chan2dev(&atchan->chan), "%s: status=0x%08x\n", + __func__, atchan->irq_status); + if (list_empty(&atchan->xfers_list)) { + spin_unlock_irq(&atchan->lock); + return; } + desc = list_first_entry(&atchan->xfers_list, struct at_xdmac_desc, + xfer_node); + spin_unlock_irq(&atchan->lock); + txd = &desc->tx_dma_desc; + if (txd->flags & DMA_PREP_INTERRUPT) + dmaengine_desc_get_callback_invoke(txd, NULL); } +/* Called with atchan->lock held. */ static void at_xdmac_handle_error(struct at_xdmac_chan *atchan) { struct at_xdmac *atxdmac = to_at_xdmac(atchan->chan.device); @@ -1651,8 +1644,6 @@ static void at_xdmac_handle_error(struct at_xdmac_chan *atchan) if (atchan->irq_status & AT_XDMAC_CIS_ROIS) dev_err(chan2dev(&atchan->chan), "request overflow error!!!"); - spin_lock_irq(&atchan->lock); - /* Channel must be disabled first as it's not done automatically */ at_xdmac_write(atxdmac, AT_XDMAC_GD, atchan->mask); while (at_xdmac_read(atxdmac, AT_XDMAC_GS) & atchan->mask) @@ -1662,8 +1653,6 @@ static void at_xdmac_handle_error(struct at_xdmac_chan *atchan) struct at_xdmac_desc, xfer_node); - spin_unlock_irq(&atchan->lock); - /* Print bad descriptor's details if needed */ dev_dbg(chan2dev(&atchan->chan), "%s: lld: mbr_sa=%pad, mbr_da=%pad, mbr_ubc=0x%08x\n", @@ -1677,50 +1666,52 @@ static void at_xdmac_tasklet(struct tasklet_struct *t) { struct at_xdmac_chan *atchan = from_tasklet(atchan, t, tasklet); struct at_xdmac_desc *desc; + struct dma_async_tx_descriptor *txd; u32 error_mask; + if (at_xdmac_chan_is_cyclic(atchan)) + return at_xdmac_handle_cyclic(atchan); + + error_mask = AT_XDMAC_CIS_RBEIS | AT_XDMAC_CIS_WBEIS | + AT_XDMAC_CIS_ROIS; + + spin_lock_irq(&atchan->lock); + dev_dbg(chan2dev(&atchan->chan), "%s: status=0x%08x\n", __func__, atchan->irq_status); - error_mask = AT_XDMAC_CIS_RBEIS - | AT_XDMAC_CIS_WBEIS - | AT_XDMAC_CIS_ROIS; + if (!(atchan->irq_status & AT_XDMAC_CIS_LIS) && + !(atchan->irq_status & error_mask)) + return; - if (at_xdmac_chan_is_cyclic(atchan)) { - at_xdmac_handle_cyclic(atchan); - } else if ((atchan->irq_status & AT_XDMAC_CIS_LIS) - || (atchan->irq_status & error_mask)) { - struct dma_async_tx_descriptor *txd; + if (atchan->irq_status & error_mask) + at_xdmac_handle_error(atchan); - if (atchan->irq_status & error_mask) - at_xdmac_handle_error(atchan); - - spin_lock_irq(&atchan->lock); - desc = list_first_entry(&atchan->xfers_list, - struct at_xdmac_desc, - xfer_node); - dev_vdbg(chan2dev(&atchan->chan), "%s: desc 0x%p\n", __func__, desc); - if (!desc->active_xfer) { - dev_err(chan2dev(&atchan->chan), "Xfer not active: exiting"); - spin_unlock_irq(&atchan->lock); - return; - } - - txd = &desc->tx_dma_desc; - - at_xdmac_remove_xfer(atchan, desc); - spin_unlock_irq(&atchan->lock); - - dma_cookie_complete(txd); - if (txd->flags & DMA_PREP_INTERRUPT) - dmaengine_desc_get_callback_invoke(txd, NULL); - - dma_run_dependencies(txd); - - spin_lock_irq(&atchan->lock); - at_xdmac_advance_work(atchan); + desc = list_first_entry(&atchan->xfers_list, struct at_xdmac_desc, + xfer_node); + dev_vdbg(chan2dev(&atchan->chan), "%s: desc 0x%p\n", __func__, desc); + if (!desc->active_xfer) { + dev_err(chan2dev(&atchan->chan), "Xfer not active: exiting"); spin_unlock_irq(&atchan->lock); + return; } + + txd = &desc->tx_dma_desc; + dma_cookie_complete(txd); + /* Remove the transfer from the transfer list. */ + list_del(&desc->xfer_node); + spin_unlock_irq(&atchan->lock); + + if (txd->flags & DMA_PREP_INTERRUPT) + dmaengine_desc_get_callback_invoke(txd, NULL); + + dma_run_dependencies(txd); + + spin_lock_irq(&atchan->lock); + /* Move the xfer descriptors into the free descriptors list. */ + list_splice_tail_init(&desc->descs_list, &atchan->free_descs_list); + at_xdmac_advance_work(atchan); + spin_unlock_irq(&atchan->lock); } static irqreturn_t at_xdmac_interrupt(int irq, void *dev_id) @@ -1784,11 +1775,9 @@ static void at_xdmac_issue_pending(struct dma_chan *chan) dev_dbg(chan2dev(&atchan->chan), "%s\n", __func__); - if (!at_xdmac_chan_is_cyclic(atchan)) { - spin_lock_irqsave(&atchan->lock, flags); - at_xdmac_advance_work(atchan); - spin_unlock_irqrestore(&atchan->lock, flags); - } + spin_lock_irqsave(&atchan->lock, flags); + at_xdmac_advance_work(atchan); + spin_unlock_irqrestore(&atchan->lock, flags); return; } @@ -1866,8 +1855,11 @@ static int at_xdmac_device_terminate_all(struct dma_chan *chan) cpu_relax(); /* Cancel all pending transfers. */ - list_for_each_entry_safe(desc, _desc, &atchan->xfers_list, xfer_node) - at_xdmac_remove_xfer(atchan, desc); + list_for_each_entry_safe(desc, _desc, &atchan->xfers_list, xfer_node) { + list_del(&desc->xfer_node); + list_splice_tail_init(&desc->descs_list, + &atchan->free_descs_list); + } clear_bit(AT_XDMAC_CHAN_IS_PAUSED, &atchan->status); clear_bit(AT_XDMAC_CHAN_IS_CYCLIC, &atchan->status); @@ -2031,7 +2023,7 @@ static int __maybe_unused atmel_xdmac_resume(struct device *dev) static int at_xdmac_probe(struct platform_device *pdev) { struct at_xdmac *atxdmac; - int irq, size, nr_channels, i, ret; + int irq, nr_channels, i, ret; void __iomem *base; u32 reg; @@ -2056,9 +2048,9 @@ static int at_xdmac_probe(struct platform_device *pdev) return -EINVAL; } - size = sizeof(*atxdmac); - size += nr_channels * sizeof(struct at_xdmac_chan); - atxdmac = devm_kzalloc(&pdev->dev, size, GFP_KERNEL); + atxdmac = devm_kzalloc(&pdev->dev, + struct_size(atxdmac, chan, nr_channels), + GFP_KERNEL); if (!atxdmac) { dev_err(&pdev->dev, "can't allocate at_xdmac structure\n"); return -ENOMEM; diff --git a/drivers/dma/dma-jz4780.c b/drivers/dma/dma-jz4780.c index 96701dedcac8..fc513eb2b289 100644 --- a/drivers/dma/dma-jz4780.c +++ b/drivers/dma/dma-jz4780.c @@ -104,10 +104,10 @@ * descriptor base address in the upper 8 bits. */ struct jz4780_dma_hwdesc { - uint32_t dcm; - uint32_t dsa; - uint32_t dta; - uint32_t dtc; + u32 dcm; + u32 dsa; + u32 dta; + u32 dtc; }; /* Size of allocations for hardware descriptor blocks. */ @@ -122,7 +122,8 @@ struct jz4780_dma_desc { dma_addr_t desc_phys; unsigned int count; enum dma_transaction_type type; - uint32_t status; + u32 transfer_type; + u32 status; }; struct jz4780_dma_chan { @@ -130,8 +131,8 @@ struct jz4780_dma_chan { unsigned int id; struct dma_pool *desc_pool; - uint32_t transfer_type; - uint32_t transfer_shift; + u32 transfer_type_tx, transfer_type_rx; + u32 transfer_shift; struct dma_slave_config config; struct jz4780_dma_desc *desc; @@ -152,12 +153,12 @@ struct jz4780_dma_dev { unsigned int irq; const struct jz4780_dma_soc_data *soc_data; - uint32_t chan_reserved; + u32 chan_reserved; struct jz4780_dma_chan chan[]; }; struct jz4780_dma_filter_data { - uint32_t transfer_type; + u32 transfer_type_tx, transfer_type_rx; int channel; }; @@ -179,26 +180,26 @@ static inline struct jz4780_dma_dev *jz4780_dma_chan_parent( dma_device); } -static inline uint32_t jz4780_dma_chn_readl(struct jz4780_dma_dev *jzdma, +static inline u32 jz4780_dma_chn_readl(struct jz4780_dma_dev *jzdma, unsigned int chn, unsigned int reg) { return readl(jzdma->chn_base + reg + JZ_DMA_REG_CHAN(chn)); } static inline void jz4780_dma_chn_writel(struct jz4780_dma_dev *jzdma, - unsigned int chn, unsigned int reg, uint32_t val) + unsigned int chn, unsigned int reg, u32 val) { writel(val, jzdma->chn_base + reg + JZ_DMA_REG_CHAN(chn)); } -static inline uint32_t jz4780_dma_ctrl_readl(struct jz4780_dma_dev *jzdma, +static inline u32 jz4780_dma_ctrl_readl(struct jz4780_dma_dev *jzdma, unsigned int reg) { return readl(jzdma->ctrl_base + reg); } static inline void jz4780_dma_ctrl_writel(struct jz4780_dma_dev *jzdma, - unsigned int reg, uint32_t val) + unsigned int reg, u32 val) { writel(val, jzdma->ctrl_base + reg); } @@ -226,9 +227,10 @@ static inline void jz4780_dma_chan_disable(struct jz4780_dma_dev *jzdma, jz4780_dma_ctrl_writel(jzdma, JZ_DMA_REG_DCKEC, BIT(chn)); } -static struct jz4780_dma_desc *jz4780_dma_desc_alloc( - struct jz4780_dma_chan *jzchan, unsigned int count, - enum dma_transaction_type type) +static struct jz4780_dma_desc * +jz4780_dma_desc_alloc(struct jz4780_dma_chan *jzchan, unsigned int count, + enum dma_transaction_type type, + enum dma_transfer_direction direction) { struct jz4780_dma_desc *desc; @@ -248,6 +250,12 @@ static struct jz4780_dma_desc *jz4780_dma_desc_alloc( desc->count = count; desc->type = type; + + if (direction == DMA_DEV_TO_MEM) + desc->transfer_type = jzchan->transfer_type_rx; + else + desc->transfer_type = jzchan->transfer_type_tx; + return desc; } @@ -260,8 +268,8 @@ static void jz4780_dma_desc_free(struct virt_dma_desc *vdesc) kfree(desc); } -static uint32_t jz4780_dma_transfer_size(struct jz4780_dma_chan *jzchan, - unsigned long val, uint32_t *shift) +static u32 jz4780_dma_transfer_size(struct jz4780_dma_chan *jzchan, + unsigned long val, u32 *shift) { struct jz4780_dma_dev *jzdma = jz4780_dma_chan_parent(jzchan); int ord = ffs(val) - 1; @@ -303,7 +311,7 @@ static int jz4780_dma_setup_hwdesc(struct jz4780_dma_chan *jzchan, enum dma_transfer_direction direction) { struct dma_slave_config *config = &jzchan->config; - uint32_t width, maxburst, tsz; + u32 width, maxburst, tsz; if (direction == DMA_MEM_TO_DEV) { desc->dcm = JZ_DMA_DCM_SAI; @@ -361,7 +369,7 @@ static struct dma_async_tx_descriptor *jz4780_dma_prep_slave_sg( unsigned int i; int err; - desc = jz4780_dma_desc_alloc(jzchan, sg_len, DMA_SLAVE); + desc = jz4780_dma_desc_alloc(jzchan, sg_len, DMA_SLAVE, direction); if (!desc) return NULL; @@ -410,7 +418,7 @@ static struct dma_async_tx_descriptor *jz4780_dma_prep_dma_cyclic( periods = buf_len / period_len; - desc = jz4780_dma_desc_alloc(jzchan, periods, DMA_CYCLIC); + desc = jz4780_dma_desc_alloc(jzchan, periods, DMA_CYCLIC, direction); if (!desc) return NULL; @@ -453,16 +461,16 @@ static struct dma_async_tx_descriptor *jz4780_dma_prep_dma_memcpy( { struct jz4780_dma_chan *jzchan = to_jz4780_dma_chan(chan); struct jz4780_dma_desc *desc; - uint32_t tsz; + u32 tsz; - desc = jz4780_dma_desc_alloc(jzchan, 1, DMA_MEMCPY); + desc = jz4780_dma_desc_alloc(jzchan, 1, DMA_MEMCPY, 0); if (!desc) return NULL; tsz = jz4780_dma_transfer_size(jzchan, dest | src | len, &jzchan->transfer_shift); - jzchan->transfer_type = JZ_DMA_DRT_AUTO; + desc->transfer_type = JZ_DMA_DRT_AUTO; desc->desc[0].dsa = src; desc->desc[0].dta = dest; @@ -528,7 +536,7 @@ static void jz4780_dma_begin(struct jz4780_dma_chan *jzchan) /* Set transfer type. */ jz4780_dma_chn_writel(jzdma, jzchan->id, JZ_DMA_REG_DRT, - jzchan->transfer_type); + jzchan->desc->transfer_type); /* * Set the transfer count. This is redundant for a descriptor-driven @@ -670,7 +678,7 @@ static bool jz4780_dma_chan_irq(struct jz4780_dma_dev *jzdma, { const unsigned int soc_flags = jzdma->soc_data->flags; struct jz4780_dma_desc *desc = jzchan->desc; - uint32_t dcs; + u32 dcs; bool ack = true; spin_lock(&jzchan->vchan.lock); @@ -727,7 +735,7 @@ static irqreturn_t jz4780_dma_irq_handler(int irq, void *data) struct jz4780_dma_dev *jzdma = data; unsigned int nb_channels = jzdma->soc_data->nb_channels; unsigned long pending; - uint32_t dmac; + u32 dmac; int i; pending = jz4780_dma_ctrl_readl(jzdma, JZ_DMA_REG_DIRQP); @@ -788,7 +796,8 @@ static bool jz4780_dma_filter_fn(struct dma_chan *chan, void *param) return false; } - jzchan->transfer_type = data->transfer_type; + jzchan->transfer_type_tx = data->transfer_type_tx; + jzchan->transfer_type_rx = data->transfer_type_rx; return true; } @@ -800,11 +809,17 @@ static struct dma_chan *jz4780_of_dma_xlate(struct of_phandle_args *dma_spec, dma_cap_mask_t mask = jzdma->dma_device.cap_mask; struct jz4780_dma_filter_data data; - if (dma_spec->args_count != 2) + if (dma_spec->args_count == 2) { + data.transfer_type_tx = dma_spec->args[0]; + data.transfer_type_rx = dma_spec->args[0]; + data.channel = dma_spec->args[1]; + } else if (dma_spec->args_count == 3) { + data.transfer_type_tx = dma_spec->args[0]; + data.transfer_type_rx = dma_spec->args[1]; + data.channel = dma_spec->args[2]; + } else { return NULL; - - data.transfer_type = dma_spec->args[0]; - data.channel = dma_spec->args[1]; + } if (data.channel > -1) { if (data.channel >= jzdma->soc_data->nb_channels) { @@ -822,7 +837,8 @@ static struct dma_chan *jz4780_of_dma_xlate(struct of_phandle_args *dma_spec, return NULL; } - jzdma->chan[data.channel].transfer_type = data.transfer_type; + jzdma->chan[data.channel].transfer_type_tx = data.transfer_type_tx; + jzdma->chan[data.channel].transfer_type_rx = data.transfer_type_rx; return dma_get_slave_channel( &jzdma->chan[data.channel].vchan.chan); @@ -938,6 +954,14 @@ static int jz4780_dma_probe(struct platform_device *pdev) jzchan->vchan.desc_free = jz4780_dma_desc_free; } + /* + * On JZ4760, chan0 won't enable properly the first time. + * Enabling then disabling chan1 will magically make chan0 work + * correctly. + */ + jz4780_dma_chan_enable(jzdma, 1); + jz4780_dma_chan_disable(jzdma, 1); + ret = platform_get_irq(pdev, 0); if (ret < 0) goto err_disable_clk; @@ -1011,12 +1035,36 @@ static const struct jz4780_dma_soc_data jz4760_dma_soc_data = { .flags = JZ_SOC_DATA_PER_CHAN_PM | JZ_SOC_DATA_NO_DCKES_DCKEC, }; +static const struct jz4780_dma_soc_data jz4760_mdma_soc_data = { + .nb_channels = 2, + .transfer_ord_max = 6, + .flags = JZ_SOC_DATA_PER_CHAN_PM | JZ_SOC_DATA_NO_DCKES_DCKEC, +}; + +static const struct jz4780_dma_soc_data jz4760_bdma_soc_data = { + .nb_channels = 3, + .transfer_ord_max = 6, + .flags = JZ_SOC_DATA_PER_CHAN_PM | JZ_SOC_DATA_NO_DCKES_DCKEC, +}; + static const struct jz4780_dma_soc_data jz4760b_dma_soc_data = { .nb_channels = 5, .transfer_ord_max = 6, .flags = JZ_SOC_DATA_PER_CHAN_PM, }; +static const struct jz4780_dma_soc_data jz4760b_mdma_soc_data = { + .nb_channels = 2, + .transfer_ord_max = 6, + .flags = JZ_SOC_DATA_PER_CHAN_PM, +}; + +static const struct jz4780_dma_soc_data jz4760b_bdma_soc_data = { + .nb_channels = 3, + .transfer_ord_max = 6, + .flags = JZ_SOC_DATA_PER_CHAN_PM, +}; + static const struct jz4780_dma_soc_data jz4770_dma_soc_data = { .nb_channels = 6, .transfer_ord_max = 6, @@ -1045,7 +1093,11 @@ static const struct of_device_id jz4780_dma_dt_match[] = { { .compatible = "ingenic,jz4740-dma", .data = &jz4740_dma_soc_data }, { .compatible = "ingenic,jz4725b-dma", .data = &jz4725b_dma_soc_data }, { .compatible = "ingenic,jz4760-dma", .data = &jz4760_dma_soc_data }, + { .compatible = "ingenic,jz4760-mdma", .data = &jz4760_mdma_soc_data }, + { .compatible = "ingenic,jz4760-bdma", .data = &jz4760_bdma_soc_data }, { .compatible = "ingenic,jz4760b-dma", .data = &jz4760b_dma_soc_data }, + { .compatible = "ingenic,jz4760b-mdma", .data = &jz4760b_mdma_soc_data }, + { .compatible = "ingenic,jz4760b-bdma", .data = &jz4760b_bdma_soc_data }, { .compatible = "ingenic,jz4770-dma", .data = &jz4770_dma_soc_data }, { .compatible = "ingenic,jz4780-dma", .data = &jz4780_dma_soc_data }, { .compatible = "ingenic,x1000-dma", .data = &x1000_dma_soc_data }, diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index d9f7c097cfd6..2cfa8458b51b 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -1159,6 +1159,13 @@ int dma_async_device_register(struct dma_device *device) return -EIO; } + if (dma_has_cap(DMA_MEMCPY_SG, device->cap_mask) && !device->device_prep_dma_memcpy_sg) { + dev_err(device->dev, + "Device claims capability %s, but op is not defined\n", + "DMA_MEMCPY_SG"); + return -EIO; + } + if (dma_has_cap(DMA_XOR, device->cap_mask) && !device->device_prep_dma_xor) { dev_err(device->dev, "Device claims capability %s, but op is not defined\n", diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c index fab412349f7f..573ad8b86804 100644 --- a/drivers/dma/idxd/device.c +++ b/drivers/dma/idxd/device.c @@ -19,30 +19,6 @@ static void idxd_device_wqs_clear_state(struct idxd_device *idxd); static void idxd_wq_disable_cleanup(struct idxd_wq *wq); /* Interrupt control bits */ -void idxd_mask_msix_vector(struct idxd_device *idxd, int vec_id) -{ - struct irq_data *data = irq_get_irq_data(idxd->irq_entries[vec_id].vector); - - pci_msi_mask_irq(data); -} - -void idxd_mask_msix_vectors(struct idxd_device *idxd) -{ - struct pci_dev *pdev = idxd->pdev; - int msixcnt = pci_msix_vec_count(pdev); - int i; - - for (i = 0; i < msixcnt; i++) - idxd_mask_msix_vector(idxd, i); -} - -void idxd_unmask_msix_vector(struct idxd_device *idxd, int vec_id) -{ - struct irq_data *data = irq_get_irq_data(idxd->irq_entries[vec_id].vector); - - pci_msi_unmask_irq(data); -} - void idxd_unmask_error_interrupts(struct idxd_device *idxd) { union genctrl_reg genctrl; @@ -382,14 +358,24 @@ static void idxd_wq_disable_cleanup(struct idxd_wq *wq) lockdep_assert_held(&wq->wq_lock); memset(wq->wqcfg, 0, idxd->wqcfg_size); wq->type = IDXD_WQT_NONE; - wq->size = 0; - wq->group = NULL; wq->threshold = 0; wq->priority = 0; wq->ats_dis = 0; + wq->enqcmds_retries = IDXD_ENQCMDS_RETRIES; clear_bit(WQ_FLAG_DEDICATED, &wq->flags); clear_bit(WQ_FLAG_BLOCK_ON_FAULT, &wq->flags); memset(wq->name, 0, WQ_NAME_SIZE); + wq->max_xfer_bytes = WQ_DEFAULT_MAX_XFER; + wq->max_batch_size = WQ_DEFAULT_MAX_BATCH; +} + +static void idxd_wq_device_reset_cleanup(struct idxd_wq *wq) +{ + lockdep_assert_held(&wq->wq_lock); + + idxd_wq_disable_cleanup(wq); + wq->size = 0; + wq->group = NULL; } static void idxd_wq_ref_release(struct percpu_ref *ref) @@ -404,17 +390,29 @@ int idxd_wq_init_percpu_ref(struct idxd_wq *wq) int rc; memset(&wq->wq_active, 0, sizeof(wq->wq_active)); - rc = percpu_ref_init(&wq->wq_active, idxd_wq_ref_release, 0, GFP_KERNEL); + rc = percpu_ref_init(&wq->wq_active, idxd_wq_ref_release, + PERCPU_REF_ALLOW_REINIT, GFP_KERNEL); if (rc < 0) return rc; reinit_completion(&wq->wq_dead); + reinit_completion(&wq->wq_resurrect); return 0; } +void __idxd_wq_quiesce(struct idxd_wq *wq) +{ + lockdep_assert_held(&wq->wq_lock); + reinit_completion(&wq->wq_resurrect); + percpu_ref_kill(&wq->wq_active); + complete_all(&wq->wq_resurrect); + wait_for_completion(&wq->wq_dead); +} + void idxd_wq_quiesce(struct idxd_wq *wq) { - percpu_ref_kill(&wq->wq_active); - wait_for_completion(&wq->wq_dead); + mutex_lock(&wq->wq_lock); + __idxd_wq_quiesce(wq); + mutex_unlock(&wq->wq_lock); } /* Device control bits */ @@ -572,7 +570,6 @@ void idxd_device_reset(struct idxd_device *idxd) idxd_device_clear_state(idxd); idxd->state = IDXD_DEV_DISABLED; idxd_unmask_error_interrupts(idxd); - idxd_msix_perm_setup(idxd); spin_unlock(&idxd->dev_lock); } @@ -681,9 +678,9 @@ static void idxd_groups_clear_state(struct idxd_device *idxd) memset(&group->grpcfg, 0, sizeof(group->grpcfg)); group->num_engines = 0; group->num_wqs = 0; - group->use_token_limit = false; - group->tokens_allowed = 0; - group->tokens_reserved = 0; + group->use_rdbuf_limit = false; + group->rdbufs_allowed = 0; + group->rdbufs_reserved = 0; group->tc_a = -1; group->tc_b = -1; } @@ -699,6 +696,7 @@ static void idxd_device_wqs_clear_state(struct idxd_device *idxd) if (wq->state == IDXD_WQ_ENABLED) { idxd_wq_disable_cleanup(wq); + idxd_wq_device_reset_cleanup(wq); wq->state = IDXD_WQ_DISABLED; } } @@ -711,36 +709,6 @@ void idxd_device_clear_state(struct idxd_device *idxd) idxd_device_wqs_clear_state(idxd); } -void idxd_msix_perm_setup(struct idxd_device *idxd) -{ - union msix_perm mperm; - int i, msixcnt; - - msixcnt = pci_msix_vec_count(idxd->pdev); - if (msixcnt < 0) - return; - - mperm.bits = 0; - mperm.pasid = idxd->pasid; - mperm.pasid_en = device_pasid_enabled(idxd); - for (i = 1; i < msixcnt; i++) - iowrite32(mperm.bits, idxd->reg_base + idxd->msix_perm_offset + i * 8); -} - -void idxd_msix_perm_clear(struct idxd_device *idxd) -{ - union msix_perm mperm; - int i, msixcnt; - - msixcnt = pci_msix_vec_count(idxd->pdev); - if (msixcnt < 0) - return; - - mperm.bits = 0; - for (i = 1; i < msixcnt; i++) - iowrite32(mperm.bits, idxd->reg_base + idxd->msix_perm_offset + i * 8); -} - static void idxd_group_config_write(struct idxd_group *group) { struct idxd_device *idxd = group->idxd; @@ -780,10 +748,10 @@ static int idxd_groups_config_write(struct idxd_device *idxd) int i; struct device *dev = &idxd->pdev->dev; - /* Setup bandwidth token limit */ - if (idxd->hw.gen_cap.config_en && idxd->token_limit) { + /* Setup bandwidth rdbuf limit */ + if (idxd->hw.gen_cap.config_en && idxd->rdbuf_limit) { reg.bits = ioread32(idxd->reg_base + IDXD_GENCFG_OFFSET); - reg.token_limit = idxd->token_limit; + reg.rdbuf_limit = idxd->rdbuf_limit; iowrite32(reg.bits, idxd->reg_base + IDXD_GENCFG_OFFSET); } @@ -827,15 +795,12 @@ static int idxd_wq_config_write(struct idxd_wq *wq) wq->wqcfg->bits[i] = ioread32(idxd->reg_base + wq_offset); } + if (wq->size == 0 && wq->type != IDXD_WQT_NONE) + wq->size = WQ_DEFAULT_QUEUE_DEPTH; + /* byte 0-3 */ wq->wqcfg->wq_size = wq->size; - if (wq->size == 0) { - idxd->cmd_status = IDXD_SCMD_WQ_NO_SIZE; - dev_warn(dev, "Incorrect work queue size: 0\n"); - return -EINVAL; - } - /* bytes 4-7 */ wq->wqcfg->wq_thresh = wq->threshold; @@ -924,13 +889,12 @@ static void idxd_group_flags_setup(struct idxd_device *idxd) group->tc_b = group->grpcfg.flags.tc_b = 1; else group->grpcfg.flags.tc_b = group->tc_b; - group->grpcfg.flags.use_token_limit = group->use_token_limit; - group->grpcfg.flags.tokens_reserved = group->tokens_reserved; - if (group->tokens_allowed) - group->grpcfg.flags.tokens_allowed = - group->tokens_allowed; + group->grpcfg.flags.use_rdbuf_limit = group->use_rdbuf_limit; + group->grpcfg.flags.rdbufs_reserved = group->rdbufs_reserved; + if (group->rdbufs_allowed) + group->grpcfg.flags.rdbufs_allowed = group->rdbufs_allowed; else - group->grpcfg.flags.tokens_allowed = idxd->max_tokens; + group->grpcfg.flags.rdbufs_allowed = idxd->max_rdbufs; } } @@ -981,8 +945,6 @@ static int idxd_wqs_setup(struct idxd_device *idxd) if (!wq->group) continue; - if (!wq->size) - continue; if (wq_shared(wq) && !device_swq_supported(idxd)) { idxd->cmd_status = IDXD_SCMD_WQ_NO_SWQ_SUPPORT; @@ -1123,7 +1085,7 @@ int idxd_device_load_config(struct idxd_device *idxd) int i, rc; reg.bits = ioread32(idxd->reg_base + IDXD_GENCFG_OFFSET); - idxd->token_limit = reg.token_limit; + idxd->rdbuf_limit = reg.rdbuf_limit; for (i = 0; i < idxd->max_groups; i++) { struct idxd_group *group = idxd->groups[i]; @@ -1142,6 +1104,106 @@ int idxd_device_load_config(struct idxd_device *idxd) return 0; } +static void idxd_flush_pending_descs(struct idxd_irq_entry *ie) +{ + struct idxd_desc *desc, *itr; + struct llist_node *head; + LIST_HEAD(flist); + enum idxd_complete_type ctype; + + spin_lock(&ie->list_lock); + head = llist_del_all(&ie->pending_llist); + if (head) { + llist_for_each_entry_safe(desc, itr, head, llnode) + list_add_tail(&desc->list, &ie->work_list); + } + + list_for_each_entry_safe(desc, itr, &ie->work_list, list) + list_move_tail(&desc->list, &flist); + spin_unlock(&ie->list_lock); + + list_for_each_entry_safe(desc, itr, &flist, list) { + list_del(&desc->list); + ctype = desc->completion->status ? IDXD_COMPLETE_NORMAL : IDXD_COMPLETE_ABORT; + idxd_dma_complete_txd(desc, ctype, true); + } +} + +static void idxd_device_set_perm_entry(struct idxd_device *idxd, + struct idxd_irq_entry *ie) +{ + union msix_perm mperm; + + if (ie->pasid == INVALID_IOASID) + return; + + mperm.bits = 0; + mperm.pasid = ie->pasid; + mperm.pasid_en = 1; + iowrite32(mperm.bits, idxd->reg_base + idxd->msix_perm_offset + ie->id * 8); +} + +static void idxd_device_clear_perm_entry(struct idxd_device *idxd, + struct idxd_irq_entry *ie) +{ + iowrite32(0, idxd->reg_base + idxd->msix_perm_offset + ie->id * 8); +} + +void idxd_wq_free_irq(struct idxd_wq *wq) +{ + struct idxd_device *idxd = wq->idxd; + struct idxd_irq_entry *ie = &wq->ie; + + synchronize_irq(ie->vector); + free_irq(ie->vector, ie); + idxd_flush_pending_descs(ie); + if (idxd->request_int_handles) + idxd_device_release_int_handle(idxd, ie->int_handle, IDXD_IRQ_MSIX); + idxd_device_clear_perm_entry(idxd, ie); + ie->vector = -1; + ie->int_handle = INVALID_INT_HANDLE; + ie->pasid = INVALID_IOASID; +} + +int idxd_wq_request_irq(struct idxd_wq *wq) +{ + struct idxd_device *idxd = wq->idxd; + struct pci_dev *pdev = idxd->pdev; + struct device *dev = &pdev->dev; + struct idxd_irq_entry *ie; + int rc; + + ie = &wq->ie; + ie->vector = pci_irq_vector(pdev, ie->id); + ie->pasid = device_pasid_enabled(idxd) ? idxd->pasid : INVALID_IOASID; + idxd_device_set_perm_entry(idxd, ie); + + rc = request_threaded_irq(ie->vector, NULL, idxd_wq_thread, 0, "idxd-portal", ie); + if (rc < 0) { + dev_err(dev, "Failed to request irq %d.\n", ie->vector); + goto err_irq; + } + + if (idxd->request_int_handles) { + rc = idxd_device_request_int_handle(idxd, ie->id, &ie->int_handle, + IDXD_IRQ_MSIX); + if (rc < 0) + goto err_int_handle; + } else { + ie->int_handle = ie->id; + } + + return 0; + +err_int_handle: + ie->int_handle = INVALID_INT_HANDLE; + free_irq(ie->vector, ie); +err_irq: + idxd_device_clear_perm_entry(idxd, ie); + ie->pasid = INVALID_IOASID; + return rc; +} + int __drv_enable_wq(struct idxd_wq *wq) { struct idxd_device *idxd = wq->idxd; diff --git a/drivers/dma/idxd/dma.c b/drivers/dma/idxd/dma.c index c39e9483206a..bfff59617d04 100644 --- a/drivers/dma/idxd/dma.c +++ b/drivers/dma/idxd/dma.c @@ -21,20 +21,27 @@ static inline struct idxd_wq *to_idxd_wq(struct dma_chan *c) } void idxd_dma_complete_txd(struct idxd_desc *desc, - enum idxd_complete_type comp_type) + enum idxd_complete_type comp_type, + bool free_desc) { + struct idxd_device *idxd = desc->wq->idxd; struct dma_async_tx_descriptor *tx; struct dmaengine_result res; int complete = 1; - if (desc->completion->status == DSA_COMP_SUCCESS) + if (desc->completion->status == DSA_COMP_SUCCESS) { res.result = DMA_TRANS_NOERROR; - else if (desc->completion->status) + } else if (desc->completion->status) { + if (idxd->request_int_handles && comp_type != IDXD_COMPLETE_ABORT && + desc->completion->status == DSA_COMP_INT_HANDLE_INVAL && + idxd_queue_int_handle_resubmit(desc)) + return; res.result = DMA_TRANS_WRITE_FAILED; - else if (comp_type == IDXD_COMPLETE_ABORT) + } else if (comp_type == IDXD_COMPLETE_ABORT) { res.result = DMA_TRANS_ABORTED; - else + } else { complete = 0; + } tx = &desc->txd; if (complete && tx->cookie) { @@ -44,6 +51,9 @@ void idxd_dma_complete_txd(struct idxd_desc *desc, tx->callback = NULL; tx->callback_result = NULL; } + + if (free_desc) + idxd_free_desc(desc->wq, desc); } static void op_flag_setup(unsigned long flags, u32 *desc_flags) @@ -153,8 +163,10 @@ static dma_cookie_t idxd_dma_tx_submit(struct dma_async_tx_descriptor *tx) cookie = dma_cookie_assign(tx); rc = idxd_submit_desc(wq, desc); - if (rc < 0) + if (rc < 0) { + idxd_free_desc(wq, desc); return rc; + } return cookie; } @@ -277,6 +289,14 @@ static int idxd_dmaengine_drv_probe(struct idxd_dev *idxd_dev) mutex_lock(&wq->wq_lock); wq->type = IDXD_WQT_KERNEL; + + rc = idxd_wq_request_irq(wq); + if (rc < 0) { + idxd->cmd_status = IDXD_SCMD_WQ_IRQ_ERR; + dev_dbg(dev, "WQ %d irq setup failed: %d\n", wq->id, rc); + goto err_irq; + } + rc = __drv_enable_wq(wq); if (rc < 0) { dev_dbg(dev, "Enable wq %d failed: %d\n", wq->id, rc); @@ -310,13 +330,15 @@ static int idxd_dmaengine_drv_probe(struct idxd_dev *idxd_dev) return 0; err_dma: - idxd_wq_quiesce(wq); + __idxd_wq_quiesce(wq); percpu_ref_exit(&wq->wq_active); err_ref: idxd_wq_free_resources(wq); err_res_alloc: __drv_disable_wq(wq); err: + idxd_wq_free_irq(wq); +err_irq: wq->type = IDXD_WQT_NONE; mutex_unlock(&wq->wq_lock); return rc; @@ -327,11 +349,13 @@ static void idxd_dmaengine_drv_remove(struct idxd_dev *idxd_dev) struct idxd_wq *wq = idxd_dev_to_wq(idxd_dev); mutex_lock(&wq->wq_lock); - idxd_wq_quiesce(wq); + __idxd_wq_quiesce(wq); idxd_unregister_dma_channel(wq); idxd_wq_free_resources(wq); __drv_disable_wq(wq); percpu_ref_exit(&wq->wq_active); + idxd_wq_free_irq(wq); + wq->type = IDXD_WQT_NONE; mutex_unlock(&wq->wq_lock); } diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index 0cf8d3145870..da72eb15f610 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include "registers.h" @@ -51,6 +52,9 @@ enum idxd_type { #define IDXD_NAME_SIZE 128 #define IDXD_PMU_EVENT_MAX 64 +#define IDXD_ENQCMDS_RETRIES 32 +#define IDXD_ENQCMDS_MAX_RETRIES 64 + struct idxd_device_driver { const char *name; enum idxd_dev_type *type; @@ -64,8 +68,8 @@ extern struct idxd_device_driver idxd_drv; extern struct idxd_device_driver idxd_dmaengine_drv; extern struct idxd_device_driver idxd_user_drv; +#define INVALID_INT_HANDLE -1 struct idxd_irq_entry { - struct idxd_device *idxd; int id; int vector; struct llist_head pending_llist; @@ -75,6 +79,8 @@ struct idxd_irq_entry { * and irq thread processing error descriptor. */ spinlock_t list_lock; + int int_handle; + ioasid_t pasid; }; struct idxd_group { @@ -84,9 +90,9 @@ struct idxd_group { int id; int num_engines; int num_wqs; - bool use_token_limit; - u8 tokens_allowed; - u8 tokens_reserved; + bool use_rdbuf_limit; + u8 rdbufs_allowed; + u8 rdbufs_reserved; int tc_a; int tc_b; }; @@ -145,6 +151,10 @@ struct idxd_cdev { #define WQ_NAME_SIZE 1024 #define WQ_TYPE_SIZE 10 +#define WQ_DEFAULT_QUEUE_DEPTH 16 +#define WQ_DEFAULT_MAX_XFER SZ_2M +#define WQ_DEFAULT_MAX_BATCH 32 + enum idxd_op_type { IDXD_OP_BLOCK = 0, IDXD_OP_NONBLOCK = 1, @@ -164,13 +174,16 @@ struct idxd_dma_chan { struct idxd_wq { void __iomem *portal; u32 portal_offset; + unsigned int enqcmds_retries; struct percpu_ref wq_active; struct completion wq_dead; + struct completion wq_resurrect; struct idxd_dev idxd_dev; struct idxd_cdev *idxd_cdev; struct wait_queue_head err_queue; struct idxd_device *idxd; int id; + struct idxd_irq_entry ie; enum idxd_wq_type type; struct idxd_group *group; int client_count; @@ -251,6 +264,7 @@ struct idxd_device { int id; int major; u32 cmd_status; + struct idxd_irq_entry ie; /* misc irq, msix 0 */ struct pci_dev *pdev; void __iomem *reg_base; @@ -266,6 +280,8 @@ struct idxd_device { unsigned int pasid; int num_groups; + int irq_cnt; + bool request_int_handles; u32 msix_perm_offset; u32 wqcfg_offset; @@ -276,24 +292,20 @@ struct idxd_device { u32 max_batch_size; int max_groups; int max_engines; - int max_tokens; + int max_rdbufs; int max_wqs; int max_wq_size; - int token_limit; - int nr_tokens; /* non-reserved tokens */ + int rdbuf_limit; + int nr_rdbufs; /* non-reserved read buffers */ unsigned int wqcfg_size; union sw_err_reg sw_err; wait_queue_head_t cmd_waitq; - int num_wq_irqs; - struct idxd_irq_entry *irq_entries; struct idxd_dma_dev *idxd_dma; struct workqueue_struct *wq; struct work_struct work; - int *int_handles; - struct idxd_pmu *idxd_pmu; }; @@ -380,6 +392,21 @@ static inline void idxd_dev_set_type(struct idxd_dev *idev, int type) idev->type = type; } +static inline struct idxd_irq_entry *idxd_get_ie(struct idxd_device *idxd, int idx) +{ + return (idx == 0) ? &idxd->ie : &idxd->wqs[idx - 1]->ie; +} + +static inline struct idxd_wq *ie_to_wq(struct idxd_irq_entry *ie) +{ + return container_of(ie, struct idxd_wq, ie); +} + +static inline struct idxd_device *ie_to_idxd(struct idxd_irq_entry *ie) +{ + return container_of(ie, struct idxd_device, ie); +} + extern struct bus_type dsa_bus_type; extern bool support_enqcmd; @@ -518,17 +545,13 @@ void idxd_unregister_devices(struct idxd_device *idxd); int idxd_register_driver(void); void idxd_unregister_driver(void); void idxd_wqs_quiesce(struct idxd_device *idxd); +bool idxd_queue_int_handle_resubmit(struct idxd_desc *desc); /* device interrupt control */ -void idxd_msix_perm_setup(struct idxd_device *idxd); -void idxd_msix_perm_clear(struct idxd_device *idxd); irqreturn_t idxd_misc_thread(int vec, void *data); irqreturn_t idxd_wq_thread(int irq, void *data); void idxd_mask_error_interrupts(struct idxd_device *idxd); void idxd_unmask_error_interrupts(struct idxd_device *idxd); -void idxd_mask_msix_vectors(struct idxd_device *idxd); -void idxd_mask_msix_vector(struct idxd_device *idxd, int vec_id); -void idxd_unmask_msix_vector(struct idxd_device *idxd, int vec_id); /* device control */ int idxd_register_idxd_drv(void); @@ -564,13 +587,17 @@ int idxd_wq_map_portal(struct idxd_wq *wq); void idxd_wq_unmap_portal(struct idxd_wq *wq); int idxd_wq_set_pasid(struct idxd_wq *wq, int pasid); int idxd_wq_disable_pasid(struct idxd_wq *wq); +void __idxd_wq_quiesce(struct idxd_wq *wq); void idxd_wq_quiesce(struct idxd_wq *wq); int idxd_wq_init_percpu_ref(struct idxd_wq *wq); +void idxd_wq_free_irq(struct idxd_wq *wq); +int idxd_wq_request_irq(struct idxd_wq *wq); /* submission */ int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc); struct idxd_desc *idxd_alloc_desc(struct idxd_wq *wq, enum idxd_op_type optype); void idxd_free_desc(struct idxd_wq *wq, struct idxd_desc *desc); +int idxd_enqcmds(struct idxd_wq *wq, void __iomem *portal, const void *desc); /* dmaengine */ int idxd_register_dma_device(struct idxd_device *idxd); @@ -579,7 +606,7 @@ int idxd_register_dma_channel(struct idxd_wq *wq); void idxd_unregister_dma_channel(struct idxd_wq *wq); void idxd_parse_completion_status(u8 status, enum dmaengine_tx_result *res); void idxd_dma_complete_txd(struct idxd_desc *desc, - enum idxd_complete_type comp_type); + enum idxd_complete_type comp_type, bool free_desc); /* cdev */ int idxd_cdev_register(void); @@ -603,10 +630,4 @@ static inline void perfmon_init(void) {} static inline void perfmon_exit(void) {} #endif -static inline void complete_desc(struct idxd_desc *desc, enum idxd_complete_type reason) -{ - idxd_dma_complete_txd(desc, reason); - idxd_free_desc(desc->wq, desc); -} - #endif diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 7bf03f371ce1..08a5f4310188 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -72,7 +72,7 @@ static int idxd_setup_interrupts(struct idxd_device *idxd) { struct pci_dev *pdev = idxd->pdev; struct device *dev = &pdev->dev; - struct idxd_irq_entry *irq_entry; + struct idxd_irq_entry *ie; int i, msixcnt; int rc = 0; @@ -81,6 +81,7 @@ static int idxd_setup_interrupts(struct idxd_device *idxd) dev_err(dev, "Not MSI-X interrupt capable.\n"); return -ENOSPC; } + idxd->irq_cnt = msixcnt; rc = pci_alloc_irq_vectors(pdev, msixcnt, msixcnt, PCI_IRQ_MSIX); if (rc != msixcnt) { @@ -89,87 +90,34 @@ static int idxd_setup_interrupts(struct idxd_device *idxd) } dev_dbg(dev, "Enabled %d msix vectors\n", msixcnt); - /* - * We implement 1 completion list per MSI-X entry except for - * entry 0, which is for errors and others. - */ - idxd->irq_entries = kcalloc_node(msixcnt, sizeof(struct idxd_irq_entry), - GFP_KERNEL, dev_to_node(dev)); - if (!idxd->irq_entries) { - rc = -ENOMEM; - goto err_irq_entries; - } - for (i = 0; i < msixcnt; i++) { - idxd->irq_entries[i].id = i; - idxd->irq_entries[i].idxd = idxd; - idxd->irq_entries[i].vector = pci_irq_vector(pdev, i); - spin_lock_init(&idxd->irq_entries[i].list_lock); - } - - idxd_msix_perm_setup(idxd); - - irq_entry = &idxd->irq_entries[0]; - rc = request_threaded_irq(irq_entry->vector, NULL, idxd_misc_thread, - 0, "idxd-misc", irq_entry); + ie = idxd_get_ie(idxd, 0); + ie->vector = pci_irq_vector(pdev, 0); + rc = request_threaded_irq(ie->vector, NULL, idxd_misc_thread, 0, "idxd-misc", ie); if (rc < 0) { dev_err(dev, "Failed to allocate misc interrupt.\n"); goto err_misc_irq; } + dev_dbg(dev, "Requested idxd-misc handler on msix vector %d\n", ie->vector); - dev_dbg(dev, "Allocated idxd-misc handler on msix vector %d\n", irq_entry->vector); + for (i = 0; i < idxd->max_wqs; i++) { + int msix_idx = i + 1; - /* first MSI-X entry is not for wq interrupts */ - idxd->num_wq_irqs = msixcnt - 1; + ie = idxd_get_ie(idxd, msix_idx); + ie->id = msix_idx; + ie->int_handle = INVALID_INT_HANDLE; + ie->pasid = INVALID_IOASID; - for (i = 1; i < msixcnt; i++) { - irq_entry = &idxd->irq_entries[i]; - - init_llist_head(&idxd->irq_entries[i].pending_llist); - INIT_LIST_HEAD(&idxd->irq_entries[i].work_list); - rc = request_threaded_irq(irq_entry->vector, NULL, - idxd_wq_thread, 0, "idxd-portal", irq_entry); - if (rc < 0) { - dev_err(dev, "Failed to allocate irq %d.\n", irq_entry->vector); - goto err_wq_irqs; - } - - dev_dbg(dev, "Allocated idxd-msix %d for vector %d\n", i, irq_entry->vector); - if (idxd->hw.cmd_cap & BIT(IDXD_CMD_REQUEST_INT_HANDLE)) { - /* - * The MSIX vector enumeration starts at 1 with vector 0 being the - * misc interrupt that handles non I/O completion events. The - * interrupt handles are for IMS enumeration on guest. The misc - * interrupt vector does not require a handle and therefore we start - * the int_handles at index 0. Since 'i' starts at 1, the first - * int_handles index will be 0. - */ - rc = idxd_device_request_int_handle(idxd, i, &idxd->int_handles[i - 1], - IDXD_IRQ_MSIX); - if (rc < 0) { - free_irq(irq_entry->vector, irq_entry); - goto err_wq_irqs; - } - dev_dbg(dev, "int handle requested: %u\n", idxd->int_handles[i - 1]); - } + spin_lock_init(&ie->list_lock); + init_llist_head(&ie->pending_llist); + INIT_LIST_HEAD(&ie->work_list); } idxd_unmask_error_interrupts(idxd); return 0; - err_wq_irqs: - while (--i >= 0) { - irq_entry = &idxd->irq_entries[i]; - free_irq(irq_entry->vector, irq_entry); - if (i != 0) - idxd_device_release_int_handle(idxd, - idxd->int_handles[i], IDXD_IRQ_MSIX); - } err_misc_irq: - /* Disable error interrupt generation */ idxd_mask_error_interrupts(idxd); - idxd_msix_perm_clear(idxd); - err_irq_entries: pci_free_irq_vectors(pdev); dev_err(dev, "No usable interrupts\n"); return rc; @@ -178,26 +126,16 @@ static int idxd_setup_interrupts(struct idxd_device *idxd) static void idxd_cleanup_interrupts(struct idxd_device *idxd) { struct pci_dev *pdev = idxd->pdev; - struct idxd_irq_entry *irq_entry; - int i, msixcnt; + struct idxd_irq_entry *ie; + int msixcnt; msixcnt = pci_msix_vec_count(pdev); if (msixcnt <= 0) return; - irq_entry = &idxd->irq_entries[0]; - free_irq(irq_entry->vector, irq_entry); - - for (i = 1; i < msixcnt; i++) { - - irq_entry = &idxd->irq_entries[i]; - if (idxd->hw.cmd_cap & BIT(IDXD_CMD_RELEASE_INT_HANDLE)) - idxd_device_release_int_handle(idxd, idxd->int_handles[i], - IDXD_IRQ_MSIX); - free_irq(irq_entry->vector, irq_entry); - } - + ie = idxd_get_ie(idxd, 0); idxd_mask_error_interrupts(idxd); + free_irq(ie->vector, ie); pci_free_irq_vectors(pdev); } @@ -237,8 +175,10 @@ static int idxd_setup_wqs(struct idxd_device *idxd) mutex_init(&wq->wq_lock); init_waitqueue_head(&wq->err_queue); init_completion(&wq->wq_dead); - wq->max_xfer_bytes = idxd->max_xfer_bytes; - wq->max_batch_size = idxd->max_batch_size; + init_completion(&wq->wq_resurrect); + wq->max_xfer_bytes = WQ_DEFAULT_MAX_XFER; + wq->max_batch_size = WQ_DEFAULT_MAX_BATCH; + wq->enqcmds_retries = IDXD_ENQCMDS_RETRIES; wq->wqcfg = kzalloc_node(idxd->wqcfg_size, GFP_KERNEL, dev_to_node(dev)); if (!wq->wqcfg) { put_device(conf_dev); @@ -379,13 +319,6 @@ static int idxd_setup_internals(struct idxd_device *idxd) init_waitqueue_head(&idxd->cmd_waitq); - if (idxd->hw.cmd_cap & BIT(IDXD_CMD_REQUEST_INT_HANDLE)) { - idxd->int_handles = kcalloc_node(idxd->max_wqs, sizeof(int), GFP_KERNEL, - dev_to_node(dev)); - if (!idxd->int_handles) - return -ENOMEM; - } - rc = idxd_setup_wqs(idxd); if (rc < 0) goto err_wqs; @@ -416,7 +349,6 @@ static int idxd_setup_internals(struct idxd_device *idxd) for (i = 0; i < idxd->max_wqs; i++) put_device(wq_confdev(idxd->wqs[i])); err_wqs: - kfree(idxd->int_handles); return rc; } @@ -451,6 +383,10 @@ static void idxd_read_caps(struct idxd_device *idxd) dev_dbg(dev, "cmd_cap: %#x\n", idxd->hw.cmd_cap); } + /* reading command capabilities */ + if (idxd->hw.cmd_cap & BIT(IDXD_CMD_REQUEST_INT_HANDLE)) + idxd->request_int_handles = true; + idxd->max_xfer_bytes = 1ULL << idxd->hw.gen_cap.max_xfer_shift; dev_dbg(dev, "max xfer size: %llu bytes\n", idxd->max_xfer_bytes); idxd->max_batch_size = 1U << idxd->hw.gen_cap.max_batch_shift; @@ -464,9 +400,9 @@ static void idxd_read_caps(struct idxd_device *idxd) dev_dbg(dev, "group_cap: %#llx\n", idxd->hw.group_cap.bits); idxd->max_groups = idxd->hw.group_cap.num_groups; dev_dbg(dev, "max groups: %u\n", idxd->max_groups); - idxd->max_tokens = idxd->hw.group_cap.total_tokens; - dev_dbg(dev, "max tokens: %u\n", idxd->max_tokens); - idxd->nr_tokens = idxd->max_tokens; + idxd->max_rdbufs = idxd->hw.group_cap.total_rdbufs; + dev_dbg(dev, "max read buffers: %u\n", idxd->max_rdbufs); + idxd->nr_rdbufs = idxd->max_rdbufs; /* read engine capabilities */ idxd->hw.engine_cap.bits = @@ -611,8 +547,6 @@ static int idxd_probe(struct idxd_device *idxd) if (rc) goto err_config; - dev_dbg(dev, "IDXD interrupt setup complete.\n"); - idxd->major = idxd_cdev_get_major(idxd); rc = perfmon_pmu_init(idxd); @@ -708,32 +642,6 @@ static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) return rc; } -static void idxd_flush_pending_llist(struct idxd_irq_entry *ie) -{ - struct idxd_desc *desc, *itr; - struct llist_node *head; - - head = llist_del_all(&ie->pending_llist); - if (!head) - return; - - llist_for_each_entry_safe(desc, itr, head, llnode) { - idxd_dma_complete_txd(desc, IDXD_COMPLETE_ABORT); - idxd_free_desc(desc->wq, desc); - } -} - -static void idxd_flush_work_list(struct idxd_irq_entry *ie) -{ - struct idxd_desc *desc, *iter; - - list_for_each_entry_safe(desc, iter, &ie->work_list, list) { - list_del(&desc->list); - idxd_dma_complete_txd(desc, IDXD_COMPLETE_ABORT); - idxd_free_desc(desc->wq, desc); - } -} - void idxd_wqs_quiesce(struct idxd_device *idxd) { struct idxd_wq *wq; @@ -746,47 +654,19 @@ void idxd_wqs_quiesce(struct idxd_device *idxd) } } -static void idxd_release_int_handles(struct idxd_device *idxd) -{ - struct device *dev = &idxd->pdev->dev; - int i, rc; - - for (i = 0; i < idxd->num_wq_irqs; i++) { - if (idxd->hw.cmd_cap & BIT(IDXD_CMD_RELEASE_INT_HANDLE)) { - rc = idxd_device_release_int_handle(idxd, idxd->int_handles[i], - IDXD_IRQ_MSIX); - if (rc < 0) - dev_warn(dev, "irq handle %d release failed\n", - idxd->int_handles[i]); - else - dev_dbg(dev, "int handle requested: %u\n", idxd->int_handles[i]); - } - } -} - static void idxd_shutdown(struct pci_dev *pdev) { struct idxd_device *idxd = pci_get_drvdata(pdev); - int rc, i; struct idxd_irq_entry *irq_entry; - int msixcnt = pci_msix_vec_count(pdev); + int rc; rc = idxd_device_disable(idxd); if (rc) dev_err(&pdev->dev, "Disabling device failed\n"); - dev_dbg(&pdev->dev, "%s called\n", __func__); - idxd_mask_msix_vectors(idxd); + irq_entry = &idxd->ie; + synchronize_irq(irq_entry->vector); idxd_mask_error_interrupts(idxd); - - for (i = 0; i < msixcnt; i++) { - irq_entry = &idxd->irq_entries[i]; - synchronize_irq(irq_entry->vector); - if (i == 0) - continue; - idxd_flush_pending_llist(irq_entry); - idxd_flush_work_list(irq_entry); - } flush_workqueue(idxd->wq); } @@ -794,8 +674,6 @@ static void idxd_remove(struct pci_dev *pdev) { struct idxd_device *idxd = pci_get_drvdata(pdev); struct idxd_irq_entry *irq_entry; - int msixcnt = pci_msix_vec_count(pdev); - int i; idxd_unregister_devices(idxd); /* @@ -811,12 +689,8 @@ static void idxd_remove(struct pci_dev *pdev) if (device_pasid_enabled(idxd)) idxd_disable_system_pasid(idxd); - for (i = 0; i < msixcnt; i++) { - irq_entry = &idxd->irq_entries[i]; - free_irq(irq_entry->vector, irq_entry); - } - idxd_msix_perm_clear(idxd); - idxd_release_int_handles(idxd); + irq_entry = idxd_get_ie(idxd, 0); + free_irq(irq_entry->vector, irq_entry); pci_free_irq_vectors(pdev); pci_iounmap(pdev, idxd->reg_base); iommu_dev_disable_feature(&pdev->dev, IOMMU_DEV_FEAT_SVA); diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c index cf2c8bc4f147..743ead5ebc57 100644 --- a/drivers/dma/idxd/irq.c +++ b/drivers/dma/idxd/irq.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include "../dmaengine.h" #include "idxd.h" @@ -22,6 +23,16 @@ struct idxd_fault { struct idxd_device *idxd; }; +struct idxd_resubmit { + struct work_struct work; + struct idxd_desc *desc; +}; + +struct idxd_int_handle_revoke { + struct work_struct work; + struct idxd_device *idxd; +}; + static void idxd_device_reinit(struct work_struct *work) { struct idxd_device *idxd = container_of(work, struct idxd_device, work); @@ -55,6 +66,162 @@ static void idxd_device_reinit(struct work_struct *work) idxd_device_clear_state(idxd); } +/* + * The function sends a drain descriptor for the interrupt handle. The drain ensures + * all descriptors with this interrupt handle is flushed and the interrupt + * will allow the cleanup of the outstanding descriptors. + */ +static void idxd_int_handle_revoke_drain(struct idxd_irq_entry *ie) +{ + struct idxd_wq *wq = ie_to_wq(ie); + struct idxd_device *idxd = wq->idxd; + struct device *dev = &idxd->pdev->dev; + struct dsa_hw_desc desc = {}; + void __iomem *portal; + int rc; + + /* Issue a simple drain operation with interrupt but no completion record */ + desc.flags = IDXD_OP_FLAG_RCI; + desc.opcode = DSA_OPCODE_DRAIN; + desc.priv = 1; + + if (ie->pasid != INVALID_IOASID) + desc.pasid = ie->pasid; + desc.int_handle = ie->int_handle; + portal = idxd_wq_portal_addr(wq); + + /* + * The wmb() makes sure that the descriptor is all there before we + * issue. + */ + wmb(); + if (wq_dedicated(wq)) { + iosubmit_cmds512(portal, &desc, 1); + } else { + rc = idxd_enqcmds(wq, portal, &desc); + /* This should not fail unless hardware failed. */ + if (rc < 0) + dev_warn(dev, "Failed to submit drain desc on wq %d\n", wq->id); + } +} + +static void idxd_abort_invalid_int_handle_descs(struct idxd_irq_entry *ie) +{ + LIST_HEAD(flist); + struct idxd_desc *d, *t; + struct llist_node *head; + + spin_lock(&ie->list_lock); + head = llist_del_all(&ie->pending_llist); + if (head) { + llist_for_each_entry_safe(d, t, head, llnode) + list_add_tail(&d->list, &ie->work_list); + } + + list_for_each_entry_safe(d, t, &ie->work_list, list) { + if (d->completion->status == DSA_COMP_INT_HANDLE_INVAL) + list_move_tail(&d->list, &flist); + } + spin_unlock(&ie->list_lock); + + list_for_each_entry_safe(d, t, &flist, list) { + list_del(&d->list); + idxd_dma_complete_txd(d, IDXD_COMPLETE_ABORT, true); + } +} + +static void idxd_int_handle_revoke(struct work_struct *work) +{ + struct idxd_int_handle_revoke *revoke = + container_of(work, struct idxd_int_handle_revoke, work); + struct idxd_device *idxd = revoke->idxd; + struct pci_dev *pdev = idxd->pdev; + struct device *dev = &pdev->dev; + int i, new_handle, rc; + + if (!idxd->request_int_handles) { + kfree(revoke); + dev_warn(dev, "Unexpected int handle refresh interrupt.\n"); + return; + } + + /* + * The loop attempts to acquire new interrupt handle for all interrupt + * vectors that supports a handle. If a new interrupt handle is acquired and the + * wq is kernel type, the driver will kill the percpu_ref to pause all + * ongoing descriptor submissions. The interrupt handle is then changed. + * After change, the percpu_ref is revived and all the pending submissions + * are woken to try again. A drain is sent to for the interrupt handle + * at the end to make sure all invalid int handle descriptors are processed. + */ + for (i = 1; i < idxd->irq_cnt; i++) { + struct idxd_irq_entry *ie = idxd_get_ie(idxd, i); + struct idxd_wq *wq = ie_to_wq(ie); + + if (ie->int_handle == INVALID_INT_HANDLE) + continue; + + rc = idxd_device_request_int_handle(idxd, i, &new_handle, IDXD_IRQ_MSIX); + if (rc < 0) { + dev_warn(dev, "get int handle %d failed: %d\n", i, rc); + /* + * Failed to acquire new interrupt handle. Kill the WQ + * and release all the pending submitters. The submitters will + * get error return code and handle appropriately. + */ + ie->int_handle = INVALID_INT_HANDLE; + idxd_wq_quiesce(wq); + idxd_abort_invalid_int_handle_descs(ie); + continue; + } + + /* No change in interrupt handle, nothing needs to be done */ + if (ie->int_handle == new_handle) + continue; + + if (wq->state != IDXD_WQ_ENABLED || wq->type != IDXD_WQT_KERNEL) { + /* + * All the MSIX interrupts are allocated at once during probe. + * Therefore we need to update all interrupts even if the WQ + * isn't supporting interrupt operations. + */ + ie->int_handle = new_handle; + continue; + } + + mutex_lock(&wq->wq_lock); + reinit_completion(&wq->wq_resurrect); + + /* Kill percpu_ref to pause additional descriptor submissions */ + percpu_ref_kill(&wq->wq_active); + + /* Wait for all submitters quiesce before we change interrupt handle */ + wait_for_completion(&wq->wq_dead); + + ie->int_handle = new_handle; + + /* Revive percpu ref and wake up all the waiting submitters */ + percpu_ref_reinit(&wq->wq_active); + complete_all(&wq->wq_resurrect); + mutex_unlock(&wq->wq_lock); + + /* + * The delay here is to wait for all possible MOVDIR64B that + * are issued before percpu_ref_kill() has happened to have + * reached the PCIe domain before the drain is issued. The driver + * needs to ensure that the drain descriptor issued does not pass + * all the other issued descriptors that contain the invalid + * interrupt handle in order to ensure that the drain descriptor + * interrupt will allow the cleanup of all the descriptors with + * invalid interrupt handle. + */ + if (wq_dedicated(wq)) + udelay(100); + idxd_int_handle_revoke_drain(ie); + } + kfree(revoke); +} + static int process_misc_interrupts(struct idxd_device *idxd, u32 cause) { struct device *dev = &idxd->pdev->dev; @@ -101,6 +268,23 @@ static int process_misc_interrupts(struct idxd_device *idxd, u32 cause) err = true; } + if (cause & IDXD_INTC_INT_HANDLE_REVOKED) { + struct idxd_int_handle_revoke *revoke; + + val |= IDXD_INTC_INT_HANDLE_REVOKED; + + revoke = kzalloc(sizeof(*revoke), GFP_ATOMIC); + if (revoke) { + revoke->idxd = idxd; + INIT_WORK(&revoke->work, idxd_int_handle_revoke); + queue_work(idxd->wq, &revoke->work); + + } else { + dev_err(dev, "Failed to allocate work for int handle revoke\n"); + idxd_wqs_quiesce(idxd); + } + } + if (cause & IDXD_INTC_CMD) { val |= IDXD_INTC_CMD; complete(idxd->cmd_done); @@ -157,7 +341,7 @@ halt: irqreturn_t idxd_misc_thread(int vec, void *data) { struct idxd_irq_entry *irq_entry = data; - struct idxd_device *idxd = irq_entry->idxd; + struct idxd_device *idxd = ie_to_idxd(irq_entry); int rc; u32 cause; @@ -177,6 +361,51 @@ irqreturn_t idxd_misc_thread(int vec, void *data) return IRQ_HANDLED; } +static void idxd_int_handle_resubmit_work(struct work_struct *work) +{ + struct idxd_resubmit *irw = container_of(work, struct idxd_resubmit, work); + struct idxd_desc *desc = irw->desc; + struct idxd_wq *wq = desc->wq; + int rc; + + desc->completion->status = 0; + rc = idxd_submit_desc(wq, desc); + if (rc < 0) { + dev_dbg(&wq->idxd->pdev->dev, "Failed to resubmit desc %d to wq %d.\n", + desc->id, wq->id); + /* + * If the error is not -EAGAIN, it means the submission failed due to wq + * has been killed instead of ENQCMDS failure. Here the driver needs to + * notify the submitter of the failure by reporting abort status. + * + * -EAGAIN comes from ENQCMDS failure. idxd_submit_desc() will handle the + * abort. + */ + if (rc != -EAGAIN) { + desc->completion->status = IDXD_COMP_DESC_ABORT; + idxd_dma_complete_txd(desc, IDXD_COMPLETE_ABORT, false); + } + idxd_free_desc(wq, desc); + } + kfree(irw); +} + +bool idxd_queue_int_handle_resubmit(struct idxd_desc *desc) +{ + struct idxd_wq *wq = desc->wq; + struct idxd_device *idxd = wq->idxd; + struct idxd_resubmit *irw; + + irw = kzalloc(sizeof(*irw), GFP_KERNEL); + if (!irw) + return false; + + irw->desc = desc; + INIT_WORK(&irw->work, idxd_int_handle_resubmit_work); + queue_work(idxd->wq, &irw->work); + return true; +} + static void irq_process_pending_llist(struct idxd_irq_entry *irq_entry) { struct idxd_desc *desc, *t; @@ -195,11 +424,11 @@ static void irq_process_pending_llist(struct idxd_irq_entry *irq_entry) * and 0xff, which DSA_COMP_STATUS_MASK can mask out. */ if (unlikely(desc->completion->status == IDXD_COMP_DESC_ABORT)) { - complete_desc(desc, IDXD_COMPLETE_ABORT); + idxd_dma_complete_txd(desc, IDXD_COMPLETE_ABORT, true); continue; } - complete_desc(desc, IDXD_COMPLETE_NORMAL); + idxd_dma_complete_txd(desc, IDXD_COMPLETE_NORMAL, true); } else { spin_lock(&irq_entry->list_lock); list_add_tail(&desc->list, @@ -238,11 +467,11 @@ static void irq_process_work_list(struct idxd_irq_entry *irq_entry) * and 0xff, which DSA_COMP_STATUS_MASK can mask out. */ if (unlikely(desc->completion->status == IDXD_COMP_DESC_ABORT)) { - complete_desc(desc, IDXD_COMPLETE_ABORT); + idxd_dma_complete_txd(desc, IDXD_COMPLETE_ABORT, true); continue; } - complete_desc(desc, IDXD_COMPLETE_NORMAL); + idxd_dma_complete_txd(desc, IDXD_COMPLETE_NORMAL, true); } } diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h index 262c8220adbd..aa642aecdc0b 100644 --- a/drivers/dma/idxd/registers.h +++ b/drivers/dma/idxd/registers.h @@ -64,9 +64,9 @@ union wq_cap_reg { union group_cap_reg { struct { u64 num_groups:8; - u64 total_tokens:8; - u64 token_en:1; - u64 token_limit:1; + u64 total_rdbufs:8; /* formerly total_tokens */ + u64 rdbuf_ctrl:1; /* formerly token_en */ + u64 rdbuf_limit:1; /* formerly token_limit */ u64 rsvd:46; }; u64 bits; @@ -110,7 +110,7 @@ union offsets_reg { #define IDXD_GENCFG_OFFSET 0x80 union gencfg_reg { struct { - u32 token_limit:8; + u32 rdbuf_limit:8; u32 rsvd:4; u32 user_int_en:1; u32 rsvd2:19; @@ -158,6 +158,7 @@ enum idxd_device_reset_type { #define IDXD_INTC_OCCUPY 0x04 #define IDXD_INTC_PERFMON_OVFL 0x08 #define IDXD_INTC_HALT_STATE 0x10 +#define IDXD_INTC_INT_HANDLE_REVOKED 0x80000000 #define IDXD_CMD_OFFSET 0xa0 union idxd_command_reg { @@ -287,10 +288,10 @@ union group_flags { u32 tc_a:3; u32 tc_b:3; u32 rsvd:1; - u32 use_token_limit:1; - u32 tokens_reserved:8; + u32 use_rdbuf_limit:1; + u32 rdbufs_reserved:8; u32 rsvd2:4; - u32 tokens_allowed:8; + u32 rdbufs_allowed:8; u32 rsvd3:4; }; u32 bits; diff --git a/drivers/dma/idxd/submit.c b/drivers/dma/idxd/submit.c index 83452fbbb168..e289fd48711a 100644 --- a/drivers/dma/idxd/submit.c +++ b/drivers/dma/idxd/submit.c @@ -21,15 +21,6 @@ static struct idxd_desc *__get_desc(struct idxd_wq *wq, int idx, int cpu) if (device_pasid_enabled(idxd)) desc->hw->pasid = idxd->pasid; - /* - * On host, MSIX vecotr 0 is used for misc interrupt. Therefore when we match - * vector 1:1 to the WQ id, we need to add 1 - */ - if (!idxd->int_handles) - desc->hw->int_handle = wq->id + 1; - else - desc->hw->int_handle = idxd->int_handles[wq->id]; - return desc; } @@ -134,35 +125,58 @@ static void llist_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie, spin_unlock(&ie->list_lock); if (found) - complete_desc(found, IDXD_COMPLETE_ABORT); + idxd_dma_complete_txd(found, IDXD_COMPLETE_ABORT, false); /* - * complete_desc() will return desc to allocator and the desc can be - * acquired by a different process and the desc->list can be modified. - * Delete desc from list so the list trasversing does not get corrupted - * by the other process. + * completing the descriptor will return desc to allocator and + * the desc can be acquired by a different process and the + * desc->list can be modified. Delete desc from list so the + * list trasversing does not get corrupted by the other process. */ list_for_each_entry_safe(d, t, &flist, list) { list_del_init(&d->list); - complete_desc(d, IDXD_COMPLETE_NORMAL); + idxd_dma_complete_txd(found, IDXD_COMPLETE_ABORT, true); } } +/* + * ENQCMDS typically fail when the WQ is inactive or busy. On host submission, the driver + * has better control of number of descriptors being submitted to a shared wq by limiting + * the number of driver allocated descriptors to the wq size. However, when the swq is + * exported to a guest kernel, it may be shared with multiple guest kernels. This means + * the likelihood of getting busy returned on the swq when submitting goes significantly up. + * Having a tunable retry mechanism allows the driver to keep trying for a bit before giving + * up. The sysfs knob can be tuned by the system administrator. + */ +int idxd_enqcmds(struct idxd_wq *wq, void __iomem *portal, const void *desc) +{ + int rc, retries = 0; + + do { + rc = enqcmds(portal, desc); + if (rc == 0) + break; + cpu_relax(); + } while (retries++ < wq->enqcmds_retries); + + return rc; +} + int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc) { struct idxd_device *idxd = wq->idxd; struct idxd_irq_entry *ie = NULL; + u32 desc_flags = desc->hw->flags; void __iomem *portal; int rc; - if (idxd->state != IDXD_DEV_ENABLED) { - idxd_free_desc(wq, desc); + if (idxd->state != IDXD_DEV_ENABLED) return -EIO; - } if (!percpu_ref_tryget_live(&wq->wq_active)) { - idxd_free_desc(wq, desc); - return -ENXIO; + wait_for_completion(&wq->wq_resurrect); + if (!percpu_ref_tryget_live(&wq->wq_active)) + return -ENXIO; } portal = idxd_wq_portal_addr(wq); @@ -178,28 +192,21 @@ int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc) * Pending the descriptor to the lockless list for the irq_entry * that we designated the descriptor to. */ - if (desc->hw->flags & IDXD_OP_FLAG_RCI) { - ie = &idxd->irq_entries[wq->id + 1]; + if (desc_flags & IDXD_OP_FLAG_RCI) { + ie = &wq->ie; + desc->hw->int_handle = ie->int_handle; llist_add(&desc->llnode, &ie->pending_llist); } if (wq_dedicated(wq)) { iosubmit_cmds512(portal, desc->hw, 1); } else { - /* - * It's not likely that we would receive queue full rejection - * since the descriptor allocation gates at wq size. If we - * receive a -EAGAIN, that means something went wrong such as the - * device is not accepting descriptor at all. - */ - rc = enqcmds(portal, desc->hw); + rc = idxd_enqcmds(wq, portal, desc->hw); if (rc < 0) { percpu_ref_put(&wq->wq_active); /* abort operation frees the descriptor */ if (ie) llist_abort_desc(wq, ie, desc); - else - idxd_free_desc(wq, desc); return rc; } } diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c index a9025be940db..7e19ab92b61a 100644 --- a/drivers/dma/idxd/sysfs.c +++ b/drivers/dma/idxd/sysfs.c @@ -99,31 +99,39 @@ struct device_type idxd_engine_device_type = { /* Group attributes */ -static void idxd_set_free_tokens(struct idxd_device *idxd) +static void idxd_set_free_rdbufs(struct idxd_device *idxd) { - int i, tokens; + int i, rdbufs; - for (i = 0, tokens = 0; i < idxd->max_groups; i++) { + for (i = 0, rdbufs = 0; i < idxd->max_groups; i++) { struct idxd_group *g = idxd->groups[i]; - tokens += g->tokens_reserved; + rdbufs += g->rdbufs_reserved; } - idxd->nr_tokens = idxd->max_tokens - tokens; + idxd->nr_rdbufs = idxd->max_rdbufs - rdbufs; +} + +static ssize_t group_read_buffers_reserved_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct idxd_group *group = confdev_to_group(dev); + + return sysfs_emit(buf, "%u\n", group->rdbufs_reserved); } static ssize_t group_tokens_reserved_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct idxd_group *group = confdev_to_group(dev); - - return sysfs_emit(buf, "%u\n", group->tokens_reserved); + dev_warn_once(dev, "attribute deprecated, see read_buffers_reserved.\n"); + return group_read_buffers_reserved_show(dev, attr, buf); } -static ssize_t group_tokens_reserved_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t group_read_buffers_reserved_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct idxd_group *group = confdev_to_group(dev); struct idxd_device *idxd = group->idxd; @@ -143,33 +151,53 @@ static ssize_t group_tokens_reserved_store(struct device *dev, if (idxd->state == IDXD_DEV_ENABLED) return -EPERM; - if (val > idxd->max_tokens) + if (val > idxd->max_rdbufs) return -EINVAL; - if (val > idxd->nr_tokens + group->tokens_reserved) + if (val > idxd->nr_rdbufs + group->rdbufs_reserved) return -EINVAL; - group->tokens_reserved = val; - idxd_set_free_tokens(idxd); + group->rdbufs_reserved = val; + idxd_set_free_rdbufs(idxd); return count; } +static ssize_t group_tokens_reserved_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + dev_warn_once(dev, "attribute deprecated, see read_buffers_reserved.\n"); + return group_read_buffers_reserved_store(dev, attr, buf, count); +} + static struct device_attribute dev_attr_group_tokens_reserved = __ATTR(tokens_reserved, 0644, group_tokens_reserved_show, group_tokens_reserved_store); +static struct device_attribute dev_attr_group_read_buffers_reserved = + __ATTR(read_buffers_reserved, 0644, group_read_buffers_reserved_show, + group_read_buffers_reserved_store); + +static ssize_t group_read_buffers_allowed_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct idxd_group *group = confdev_to_group(dev); + + return sysfs_emit(buf, "%u\n", group->rdbufs_allowed); +} + static ssize_t group_tokens_allowed_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct idxd_group *group = confdev_to_group(dev); - - return sysfs_emit(buf, "%u\n", group->tokens_allowed); + dev_warn_once(dev, "attribute deprecated, see read_buffers_allowed.\n"); + return group_read_buffers_allowed_show(dev, attr, buf); } -static ssize_t group_tokens_allowed_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t group_read_buffers_allowed_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct idxd_group *group = confdev_to_group(dev); struct idxd_device *idxd = group->idxd; @@ -190,29 +218,49 @@ static ssize_t group_tokens_allowed_store(struct device *dev, return -EPERM; if (val < 4 * group->num_engines || - val > group->tokens_reserved + idxd->nr_tokens) + val > group->rdbufs_reserved + idxd->nr_rdbufs) return -EINVAL; - group->tokens_allowed = val; + group->rdbufs_allowed = val; return count; } +static ssize_t group_tokens_allowed_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + dev_warn_once(dev, "attribute deprecated, see read_buffers_allowed.\n"); + return group_read_buffers_allowed_store(dev, attr, buf, count); +} + static struct device_attribute dev_attr_group_tokens_allowed = __ATTR(tokens_allowed, 0644, group_tokens_allowed_show, group_tokens_allowed_store); +static struct device_attribute dev_attr_group_read_buffers_allowed = + __ATTR(read_buffers_allowed, 0644, group_read_buffers_allowed_show, + group_read_buffers_allowed_store); + +static ssize_t group_use_read_buffer_limit_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct idxd_group *group = confdev_to_group(dev); + + return sysfs_emit(buf, "%u\n", group->use_rdbuf_limit); +} + static ssize_t group_use_token_limit_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct idxd_group *group = confdev_to_group(dev); - - return sysfs_emit(buf, "%u\n", group->use_token_limit); + dev_warn_once(dev, "attribute deprecated, see use_read_buffer_limit.\n"); + return group_use_read_buffer_limit_show(dev, attr, buf); } -static ssize_t group_use_token_limit_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t group_use_read_buffer_limit_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct idxd_group *group = confdev_to_group(dev); struct idxd_device *idxd = group->idxd; @@ -232,17 +280,29 @@ static ssize_t group_use_token_limit_store(struct device *dev, if (idxd->state == IDXD_DEV_ENABLED) return -EPERM; - if (idxd->token_limit == 0) + if (idxd->rdbuf_limit == 0) return -EPERM; - group->use_token_limit = !!val; + group->use_rdbuf_limit = !!val; return count; } +static ssize_t group_use_token_limit_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + dev_warn_once(dev, "attribute deprecated, see use_read_buffer_limit.\n"); + return group_use_read_buffer_limit_store(dev, attr, buf, count); +} + static struct device_attribute dev_attr_group_use_token_limit = __ATTR(use_token_limit, 0644, group_use_token_limit_show, group_use_token_limit_store); +static struct device_attribute dev_attr_group_use_read_buffer_limit = + __ATTR(use_read_buffer_limit, 0644, group_use_read_buffer_limit_show, + group_use_read_buffer_limit_store); + static ssize_t group_engines_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -387,8 +447,11 @@ static struct attribute *idxd_group_attributes[] = { &dev_attr_group_work_queues.attr, &dev_attr_group_engines.attr, &dev_attr_group_use_token_limit.attr, + &dev_attr_group_use_read_buffer_limit.attr, &dev_attr_group_tokens_allowed.attr, + &dev_attr_group_read_buffers_allowed.attr, &dev_attr_group_tokens_reserved.attr, + &dev_attr_group_read_buffers_reserved.attr, &dev_attr_group_traffic_class_a.attr, &dev_attr_group_traffic_class_b.attr, NULL, @@ -945,6 +1008,41 @@ static ssize_t wq_occupancy_show(struct device *dev, struct device_attribute *at static struct device_attribute dev_attr_wq_occupancy = __ATTR(occupancy, 0444, wq_occupancy_show, NULL); +static ssize_t wq_enqcmds_retries_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct idxd_wq *wq = confdev_to_wq(dev); + + if (wq_dedicated(wq)) + return -EOPNOTSUPP; + + return sysfs_emit(buf, "%u\n", wq->enqcmds_retries); +} + +static ssize_t wq_enqcmds_retries_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct idxd_wq *wq = confdev_to_wq(dev); + int rc; + unsigned int retries; + + if (wq_dedicated(wq)) + return -EOPNOTSUPP; + + rc = kstrtouint(buf, 10, &retries); + if (rc < 0) + return rc; + + if (retries > IDXD_ENQCMDS_MAX_RETRIES) + retries = IDXD_ENQCMDS_MAX_RETRIES; + + wq->enqcmds_retries = retries; + return count; +} + +static struct device_attribute dev_attr_wq_enqcmds_retries = + __ATTR(enqcmds_retries, 0644, wq_enqcmds_retries_show, wq_enqcmds_retries_store); + static struct attribute *idxd_wq_attributes[] = { &dev_attr_wq_clients.attr, &dev_attr_wq_state.attr, @@ -961,6 +1059,7 @@ static struct attribute *idxd_wq_attributes[] = { &dev_attr_wq_max_batch_size.attr, &dev_attr_wq_ats_disable.attr, &dev_attr_wq_occupancy.attr, + &dev_attr_wq_enqcmds_retries.attr, NULL, }; @@ -1156,26 +1255,42 @@ static ssize_t errors_show(struct device *dev, } static DEVICE_ATTR_RO(errors); -static ssize_t max_tokens_show(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t max_read_buffers_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct idxd_device *idxd = confdev_to_idxd(dev); - return sysfs_emit(buf, "%u\n", idxd->max_tokens); + return sysfs_emit(buf, "%u\n", idxd->max_rdbufs); +} + +static ssize_t max_tokens_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + dev_warn_once(dev, "attribute deprecated, see max_read_buffers.\n"); + return max_read_buffers_show(dev, attr, buf); +} + +static DEVICE_ATTR_RO(max_tokens); /* deprecated */ +static DEVICE_ATTR_RO(max_read_buffers); + +static ssize_t read_buffer_limit_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct idxd_device *idxd = confdev_to_idxd(dev); + + return sysfs_emit(buf, "%u\n", idxd->rdbuf_limit); } -static DEVICE_ATTR_RO(max_tokens); static ssize_t token_limit_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct idxd_device *idxd = confdev_to_idxd(dev); - - return sysfs_emit(buf, "%u\n", idxd->token_limit); + dev_warn_once(dev, "attribute deprecated, see read_buffer_limit.\n"); + return read_buffer_limit_show(dev, attr, buf); } -static ssize_t token_limit_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t read_buffer_limit_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct idxd_device *idxd = confdev_to_idxd(dev); unsigned long val; @@ -1191,16 +1306,26 @@ static ssize_t token_limit_store(struct device *dev, if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) return -EPERM; - if (!idxd->hw.group_cap.token_limit) + if (!idxd->hw.group_cap.rdbuf_limit) return -EPERM; - if (val > idxd->hw.group_cap.total_tokens) + if (val > idxd->hw.group_cap.total_rdbufs) return -EINVAL; - idxd->token_limit = val; + idxd->rdbuf_limit = val; return count; } -static DEVICE_ATTR_RW(token_limit); + +static ssize_t token_limit_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + dev_warn_once(dev, "attribute deprecated, see read_buffer_limit\n"); + return read_buffer_limit_store(dev, attr, buf, count); +} + +static DEVICE_ATTR_RW(token_limit); /* deprecated */ +static DEVICE_ATTR_RW(read_buffer_limit); static ssize_t cdev_major_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -1246,7 +1371,9 @@ static struct attribute *idxd_device_attributes[] = { &dev_attr_state.attr, &dev_attr_errors.attr, &dev_attr_max_tokens.attr, + &dev_attr_max_read_buffers.attr, &dev_attr_token_limit.attr, + &dev_attr_read_buffer_limit.attr, &dev_attr_cdev_major.attr, &dev_attr_cmd_status.attr, NULL, @@ -1268,8 +1395,6 @@ static void idxd_conf_device_release(struct device *dev) kfree(idxd->groups); kfree(idxd->wqs); kfree(idxd->engines); - kfree(idxd->irq_entries); - kfree(idxd->int_handles); ida_free(&idxd_ida, idxd->id); kfree(idxd); } diff --git a/drivers/dma/ioat/sysfs.c b/drivers/dma/ioat/sysfs.c index aa44bcd6a356..168adf28c5b1 100644 --- a/drivers/dma/ioat/sysfs.c +++ b/drivers/dma/ioat/sysfs.c @@ -158,8 +158,9 @@ static struct attribute *ioat_attrs[] = { &intr_coalesce_attr.attr, NULL, }; +ATTRIBUTE_GROUPS(ioat); struct kobj_type ioat_ktype = { .sysfs_ops = &ioat_sysfs_ops, - .default_attrs = ioat_attrs, + .default_groups = ioat_groups, }; diff --git a/drivers/dma/pch_dma.c b/drivers/dma/pch_dma.c index 1da04112fcdb..c359decc07a3 100644 --- a/drivers/dma/pch_dma.c +++ b/drivers/dma/pch_dma.c @@ -835,7 +835,7 @@ static int pch_dma_probe(struct pci_dev *pdev, goto err_disable_pdev; } - err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); + err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); if (err) { dev_err(&pdev->dev, "Cannot set proper DMA config\n"); goto err_free_res; diff --git a/drivers/dma/ppc4xx/adma.c b/drivers/dma/ppc4xx/adma.c index e2b5129c5f84..5e46e347e28b 100644 --- a/drivers/dma/ppc4xx/adma.c +++ b/drivers/dma/ppc4xx/adma.c @@ -3240,7 +3240,6 @@ static int ppc440spe_adma_dma2rxor_prep_src( struct ppc440spe_rxor *cursor, int index, int src_cnt, u32 addr) { - int rval = 0; u32 sign; struct ppc440spe_adma_desc_slot *desc = hdesc; int i; @@ -3348,7 +3347,7 @@ static int ppc440spe_adma_dma2rxor_prep_src( break; } - return rval; + return 0; } /** diff --git a/drivers/dma/qcom/gpi.c b/drivers/dma/qcom/gpi.c index 1a1b7d8458c9..94f3648f7483 100644 --- a/drivers/dma/qcom/gpi.c +++ b/drivers/dma/qcom/gpi.c @@ -2206,10 +2206,8 @@ static int gpi_probe(struct platform_device *pdev) /* set up irq */ ret = platform_get_irq(pdev, i); - if (ret < 0) { - dev_err(gpi_dev->dev, "platform_get_irq failed for %d:%d\n", i, ret); + if (ret < 0) return ret; - } gpii->irq = ret; /* set up channel specific register info */ diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c index 5c7716fd6bc5..481f45c77ce1 100644 --- a/drivers/dma/sh/rcar-dmac.c +++ b/drivers/dma/sh/rcar-dmac.c @@ -236,7 +236,7 @@ struct rcar_dmac_of_data { #define RCAR_DMAOR_PRI_ROUND_ROBIN (3 << 8) #define RCAR_DMAOR_AE (1 << 2) #define RCAR_DMAOR_DME (1 << 0) -#define RCAR_DMACHCLR 0x0080 /* Not on R-Car V3U */ +#define RCAR_DMACHCLR 0x0080 /* Not on R-Car Gen4 */ #define RCAR_DMADPSEC 0x00a0 #define RCAR_DMASAR 0x0000 @@ -299,8 +299,8 @@ struct rcar_dmac_of_data { #define RCAR_DMAFIXDAR 0x0014 #define RCAR_DMAFIXDPBASE 0x0060 -/* For R-Car V3U */ -#define RCAR_V3U_DMACHCLR 0x0100 +/* For R-Car Gen4 */ +#define RCAR_GEN4_DMACHCLR 0x0100 /* Hardcode the MEMCPY transfer size to 4 bytes. */ #define RCAR_DMAC_MEMCPY_XFER_SIZE 4 @@ -345,7 +345,7 @@ static void rcar_dmac_chan_clear(struct rcar_dmac *dmac, struct rcar_dmac_chan *chan) { if (dmac->chan_base) - rcar_dmac_chan_write(chan, RCAR_V3U_DMACHCLR, 1); + rcar_dmac_chan_write(chan, RCAR_GEN4_DMACHCLR, 1); else rcar_dmac_write(dmac, RCAR_DMACHCLR, BIT(chan->index)); } @@ -357,7 +357,7 @@ static void rcar_dmac_chan_clear_all(struct rcar_dmac *dmac) if (dmac->chan_base) { for_each_rcar_dmac_chan(i, dmac, chan) - rcar_dmac_chan_write(chan, RCAR_V3U_DMACHCLR, 1); + rcar_dmac_chan_write(chan, RCAR_GEN4_DMACHCLR, 1); } else { rcar_dmac_write(dmac, RCAR_DMACHCLR, dmac->channels_mask); } @@ -2009,7 +2009,7 @@ static const struct rcar_dmac_of_data rcar_dmac_data = { .chan_offset_stride = 0x80, }; -static const struct rcar_dmac_of_data rcar_v3u_dmac_data = { +static const struct rcar_dmac_of_data rcar_gen4_dmac_data = { .chan_offset_base = 0x0, .chan_offset_stride = 0x1000, }; @@ -2018,9 +2018,12 @@ static const struct of_device_id rcar_dmac_of_ids[] = { { .compatible = "renesas,rcar-dmac", .data = &rcar_dmac_data, + }, { + .compatible = "renesas,rcar-gen4-dmac", + .data = &rcar_gen4_dmac_data, }, { .compatible = "renesas,dmac-r8a779a0", - .data = &rcar_v3u_dmac_data, + .data = &rcar_gen4_dmac_data, }, { /* Sentinel */ } }; diff --git a/drivers/dma/sh/shdma-base.c b/drivers/dma/sh/shdma-base.c index 41c6bc650fa3..158e5e7defae 100644 --- a/drivers/dma/sh/shdma-base.c +++ b/drivers/dma/sh/shdma-base.c @@ -1034,9 +1034,7 @@ EXPORT_SYMBOL(shdma_cleanup); static int __init shdma_enter(void) { - shdma_slave_used = kcalloc(DIV_ROUND_UP(slave_num, BITS_PER_LONG), - sizeof(long), - GFP_KERNEL); + shdma_slave_used = bitmap_zalloc(slave_num, GFP_KERNEL); if (!shdma_slave_used) return -ENOMEM; return 0; @@ -1045,7 +1043,7 @@ module_init(shdma_enter); static void __exit shdma_exit(void) { - kfree(shdma_slave_used); + bitmap_free(shdma_slave_used); } module_exit(shdma_exit); diff --git a/drivers/dma/stm32-mdma.c b/drivers/dma/stm32-mdma.c index d30a4a28d3bf..6f57ff0e7b37 100644 --- a/drivers/dma/stm32-mdma.c +++ b/drivers/dma/stm32-mdma.c @@ -10,6 +10,7 @@ * Inspired by stm32-dma.c and dma-jz4780.c */ +#include #include #include #include @@ -32,13 +33,6 @@ #include "virt-dma.h" -/* MDMA Generic getter/setter */ -#define STM32_MDMA_SHIFT(n) (ffs(n) - 1) -#define STM32_MDMA_SET(n, mask) (((n) << STM32_MDMA_SHIFT(mask)) & \ - (mask)) -#define STM32_MDMA_GET(n, mask) (((n) & (mask)) >> \ - STM32_MDMA_SHIFT(mask)) - #define STM32_MDMA_GISR0 0x0000 /* MDMA Int Status Reg 1 */ #define STM32_MDMA_GISR1 0x0004 /* MDMA Int Status Reg 2 */ @@ -80,8 +74,7 @@ #define STM32_MDMA_CCR_HEX BIT(13) #define STM32_MDMA_CCR_BEX BIT(12) #define STM32_MDMA_CCR_PL_MASK GENMASK(7, 6) -#define STM32_MDMA_CCR_PL(n) STM32_MDMA_SET(n, \ - STM32_MDMA_CCR_PL_MASK) +#define STM32_MDMA_CCR_PL(n) FIELD_PREP(STM32_MDMA_CCR_PL_MASK, (n)) #define STM32_MDMA_CCR_TCIE BIT(5) #define STM32_MDMA_CCR_BTIE BIT(4) #define STM32_MDMA_CCR_BRTIE BIT(3) @@ -99,48 +92,33 @@ #define STM32_MDMA_CTCR_BWM BIT(31) #define STM32_MDMA_CTCR_SWRM BIT(30) #define STM32_MDMA_CTCR_TRGM_MSK GENMASK(29, 28) -#define STM32_MDMA_CTCR_TRGM(n) STM32_MDMA_SET((n), \ - STM32_MDMA_CTCR_TRGM_MSK) -#define STM32_MDMA_CTCR_TRGM_GET(n) STM32_MDMA_GET((n), \ - STM32_MDMA_CTCR_TRGM_MSK) +#define STM32_MDMA_CTCR_TRGM(n) FIELD_PREP(STM32_MDMA_CTCR_TRGM_MSK, (n)) +#define STM32_MDMA_CTCR_TRGM_GET(n) FIELD_GET(STM32_MDMA_CTCR_TRGM_MSK, (n)) #define STM32_MDMA_CTCR_PAM_MASK GENMASK(27, 26) -#define STM32_MDMA_CTCR_PAM(n) STM32_MDMA_SET(n, \ - STM32_MDMA_CTCR_PAM_MASK) +#define STM32_MDMA_CTCR_PAM(n) FIELD_PREP(STM32_MDMA_CTCR_PAM_MASK, (n)) #define STM32_MDMA_CTCR_PKE BIT(25) #define STM32_MDMA_CTCR_TLEN_MSK GENMASK(24, 18) -#define STM32_MDMA_CTCR_TLEN(n) STM32_MDMA_SET((n), \ - STM32_MDMA_CTCR_TLEN_MSK) -#define STM32_MDMA_CTCR_TLEN_GET(n) STM32_MDMA_GET((n), \ - STM32_MDMA_CTCR_TLEN_MSK) +#define STM32_MDMA_CTCR_TLEN(n) FIELD_PREP(STM32_MDMA_CTCR_TLEN_MSK, (n)) +#define STM32_MDMA_CTCR_TLEN_GET(n) FIELD_GET(STM32_MDMA_CTCR_TLEN_MSK, (n)) #define STM32_MDMA_CTCR_LEN2_MSK GENMASK(25, 18) -#define STM32_MDMA_CTCR_LEN2(n) STM32_MDMA_SET((n), \ - STM32_MDMA_CTCR_LEN2_MSK) -#define STM32_MDMA_CTCR_LEN2_GET(n) STM32_MDMA_GET((n), \ - STM32_MDMA_CTCR_LEN2_MSK) +#define STM32_MDMA_CTCR_LEN2(n) FIELD_PREP(STM32_MDMA_CTCR_LEN2_MSK, (n)) +#define STM32_MDMA_CTCR_LEN2_GET(n) FIELD_GET(STM32_MDMA_CTCR_LEN2_MSK, (n)) #define STM32_MDMA_CTCR_DBURST_MASK GENMASK(17, 15) -#define STM32_MDMA_CTCR_DBURST(n) STM32_MDMA_SET(n, \ - STM32_MDMA_CTCR_DBURST_MASK) +#define STM32_MDMA_CTCR_DBURST(n) FIELD_PREP(STM32_MDMA_CTCR_DBURST_MASK, (n)) #define STM32_MDMA_CTCR_SBURST_MASK GENMASK(14, 12) -#define STM32_MDMA_CTCR_SBURST(n) STM32_MDMA_SET(n, \ - STM32_MDMA_CTCR_SBURST_MASK) +#define STM32_MDMA_CTCR_SBURST(n) FIELD_PREP(STM32_MDMA_CTCR_SBURST_MASK, (n)) #define STM32_MDMA_CTCR_DINCOS_MASK GENMASK(11, 10) -#define STM32_MDMA_CTCR_DINCOS(n) STM32_MDMA_SET((n), \ - STM32_MDMA_CTCR_DINCOS_MASK) +#define STM32_MDMA_CTCR_DINCOS(n) FIELD_PREP(STM32_MDMA_CTCR_DINCOS_MASK, (n)) #define STM32_MDMA_CTCR_SINCOS_MASK GENMASK(9, 8) -#define STM32_MDMA_CTCR_SINCOS(n) STM32_MDMA_SET((n), \ - STM32_MDMA_CTCR_SINCOS_MASK) +#define STM32_MDMA_CTCR_SINCOS(n) FIELD_PREP(STM32_MDMA_CTCR_SINCOS_MASK, (n)) #define STM32_MDMA_CTCR_DSIZE_MASK GENMASK(7, 6) -#define STM32_MDMA_CTCR_DSIZE(n) STM32_MDMA_SET(n, \ - STM32_MDMA_CTCR_DSIZE_MASK) +#define STM32_MDMA_CTCR_DSIZE(n) FIELD_PREP(STM32_MDMA_CTCR_DSIZE_MASK, (n)) #define STM32_MDMA_CTCR_SSIZE_MASK GENMASK(5, 4) -#define STM32_MDMA_CTCR_SSIZE(n) STM32_MDMA_SET(n, \ - STM32_MDMA_CTCR_SSIZE_MASK) +#define STM32_MDMA_CTCR_SSIZE(n) FIELD_PREP(STM32_MDMA_CTCR_SSIZE_MASK, (n)) #define STM32_MDMA_CTCR_DINC_MASK GENMASK(3, 2) -#define STM32_MDMA_CTCR_DINC(n) STM32_MDMA_SET((n), \ - STM32_MDMA_CTCR_DINC_MASK) +#define STM32_MDMA_CTCR_DINC(n) FIELD_PREP(STM32_MDMA_CTCR_DINC_MASK, (n)) #define STM32_MDMA_CTCR_SINC_MASK GENMASK(1, 0) -#define STM32_MDMA_CTCR_SINC(n) STM32_MDMA_SET((n), \ - STM32_MDMA_CTCR_SINC_MASK) +#define STM32_MDMA_CTCR_SINC(n) FIELD_PREP(STM32_MDMA_CTCR_SINC_MASK, (n)) #define STM32_MDMA_CTCR_CFG_MASK (STM32_MDMA_CTCR_SINC_MASK \ | STM32_MDMA_CTCR_DINC_MASK \ | STM32_MDMA_CTCR_SINCOS_MASK \ @@ -151,16 +129,13 @@ /* MDMA Channel x block number of data register */ #define STM32_MDMA_CBNDTR(x) (0x54 + 0x40 * (x)) #define STM32_MDMA_CBNDTR_BRC_MK GENMASK(31, 20) -#define STM32_MDMA_CBNDTR_BRC(n) STM32_MDMA_SET(n, \ - STM32_MDMA_CBNDTR_BRC_MK) -#define STM32_MDMA_CBNDTR_BRC_GET(n) STM32_MDMA_GET((n), \ - STM32_MDMA_CBNDTR_BRC_MK) +#define STM32_MDMA_CBNDTR_BRC(n) FIELD_PREP(STM32_MDMA_CBNDTR_BRC_MK, (n)) +#define STM32_MDMA_CBNDTR_BRC_GET(n) FIELD_GET(STM32_MDMA_CBNDTR_BRC_MK, (n)) #define STM32_MDMA_CBNDTR_BRDUM BIT(19) #define STM32_MDMA_CBNDTR_BRSUM BIT(18) #define STM32_MDMA_CBNDTR_BNDT_MASK GENMASK(16, 0) -#define STM32_MDMA_CBNDTR_BNDT(n) STM32_MDMA_SET(n, \ - STM32_MDMA_CBNDTR_BNDT_MASK) +#define STM32_MDMA_CBNDTR_BNDT(n) FIELD_PREP(STM32_MDMA_CBNDTR_BNDT_MASK, (n)) /* MDMA Channel x source address register */ #define STM32_MDMA_CSAR(x) (0x58 + 0x40 * (x)) @@ -171,11 +146,9 @@ /* MDMA Channel x block repeat address update register */ #define STM32_MDMA_CBRUR(x) (0x60 + 0x40 * (x)) #define STM32_MDMA_CBRUR_DUV_MASK GENMASK(31, 16) -#define STM32_MDMA_CBRUR_DUV(n) STM32_MDMA_SET(n, \ - STM32_MDMA_CBRUR_DUV_MASK) +#define STM32_MDMA_CBRUR_DUV(n) FIELD_PREP(STM32_MDMA_CBRUR_DUV_MASK, (n)) #define STM32_MDMA_CBRUR_SUV_MASK GENMASK(15, 0) -#define STM32_MDMA_CBRUR_SUV(n) STM32_MDMA_SET(n, \ - STM32_MDMA_CBRUR_SUV_MASK) +#define STM32_MDMA_CBRUR_SUV(n) FIELD_PREP(STM32_MDMA_CBRUR_SUV_MASK, (n)) /* MDMA Channel x link address register */ #define STM32_MDMA_CLAR(x) (0x64 + 0x40 * (x)) @@ -184,9 +157,8 @@ #define STM32_MDMA_CTBR(x) (0x68 + 0x40 * (x)) #define STM32_MDMA_CTBR_DBUS BIT(17) #define STM32_MDMA_CTBR_SBUS BIT(16) -#define STM32_MDMA_CTBR_TSEL_MASK GENMASK(7, 0) -#define STM32_MDMA_CTBR_TSEL(n) STM32_MDMA_SET(n, \ - STM32_MDMA_CTBR_TSEL_MASK) +#define STM32_MDMA_CTBR_TSEL_MASK GENMASK(5, 0) +#define STM32_MDMA_CTBR_TSEL(n) FIELD_PREP(STM32_MDMA_CTBR_TSEL_MASK, (n)) /* MDMA Channel x mask address register */ #define STM32_MDMA_CMAR(x) (0x70 + 0x40 * (x)) @@ -1279,7 +1251,7 @@ static size_t stm32_mdma_desc_residue(struct stm32_mdma_chan *chan, u32 curr_hwdesc) { struct stm32_mdma_device *dmadev = stm32_mdma_get_dev(chan); - struct stm32_mdma_hwdesc *hwdesc = desc->node[0].hwdesc; + struct stm32_mdma_hwdesc *hwdesc; u32 cbndtr, residue, modulo, burst_size; int i; diff --git a/drivers/dma/ti/Makefile b/drivers/dma/ti/Makefile index bd496efadff7..1d4081a049b7 100644 --- a/drivers/dma/ti/Makefile +++ b/drivers/dma/ti/Makefile @@ -8,5 +8,6 @@ obj-$(CONFIG_TI_K3_PSIL) += k3-psil.o \ k3-psil-am654.o \ k3-psil-j721e.o \ k3-psil-j7200.o \ - k3-psil-am64.o + k3-psil-am64.o \ + k3-psil-j721s2.o obj-$(CONFIG_TI_DMA_CROSSBAR) += dma-crossbar.o diff --git a/drivers/dma/ti/edma.c b/drivers/dma/ti/edma.c index 35d81bd857f1..08e47f44d325 100644 --- a/drivers/dma/ti/edma.c +++ b/drivers/dma/ti/edma.c @@ -1681,8 +1681,7 @@ static irqreturn_t dma_ccerr_handler(int irq, void *data) dev_dbg(ecc->dev, "EMR%d 0x%08x\n", j, val); emr = val; - for (i = find_next_bit(&emr, 32, 0); i < 32; - i = find_next_bit(&emr, 32, i + 1)) { + for_each_set_bit(i, &emr, 32) { int k = (j << 5) + i; /* Clear the corresponding EMR bits */ diff --git a/drivers/dma/ti/k3-psil-j721s2.c b/drivers/dma/ti/k3-psil-j721s2.c new file mode 100644 index 000000000000..4c4172a4d271 --- /dev/null +++ b/drivers/dma/ti/k3-psil-j721s2.c @@ -0,0 +1,167 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 Texas Instruments Incorporated - https://www.ti.com + */ + +#include + +#include "k3-psil-priv.h" + +#define PSIL_PDMA_XY_TR(x) \ + { \ + .thread_id = x, \ + .ep_config = { \ + .ep_type = PSIL_EP_PDMA_XY, \ + }, \ + } + +#define PSIL_PDMA_XY_PKT(x) \ + { \ + .thread_id = x, \ + .ep_config = { \ + .ep_type = PSIL_EP_PDMA_XY, \ + .pkt_mode = 1, \ + }, \ + } + +#define PSIL_PDMA_MCASP(x) \ + { \ + .thread_id = x, \ + .ep_config = { \ + .ep_type = PSIL_EP_PDMA_XY, \ + .pdma_acc32 = 1, \ + .pdma_burst = 1, \ + }, \ + } + +#define PSIL_ETHERNET(x) \ + { \ + .thread_id = x, \ + .ep_config = { \ + .ep_type = PSIL_EP_NATIVE, \ + .pkt_mode = 1, \ + .needs_epib = 1, \ + .psd_size = 16, \ + }, \ + } + +#define PSIL_SA2UL(x, tx) \ + { \ + .thread_id = x, \ + .ep_config = { \ + .ep_type = PSIL_EP_NATIVE, \ + .pkt_mode = 1, \ + .needs_epib = 1, \ + .psd_size = 64, \ + .notdpkt = tx, \ + }, \ + } + +/* PSI-L source thread IDs, used for RX (DMA_DEV_TO_MEM) */ +static struct psil_ep j721s2_src_ep_map[] = { + /* PDMA_MCASP - McASP0-4 */ + PSIL_PDMA_MCASP(0x4400), + PSIL_PDMA_MCASP(0x4401), + PSIL_PDMA_MCASP(0x4402), + PSIL_PDMA_MCASP(0x4403), + PSIL_PDMA_MCASP(0x4404), + /* PDMA_SPI_G0 - SPI0-3 */ + PSIL_PDMA_XY_PKT(0x4600), + PSIL_PDMA_XY_PKT(0x4601), + PSIL_PDMA_XY_PKT(0x4602), + PSIL_PDMA_XY_PKT(0x4603), + PSIL_PDMA_XY_PKT(0x4604), + PSIL_PDMA_XY_PKT(0x4605), + PSIL_PDMA_XY_PKT(0x4606), + PSIL_PDMA_XY_PKT(0x4607), + PSIL_PDMA_XY_PKT(0x4608), + PSIL_PDMA_XY_PKT(0x4609), + PSIL_PDMA_XY_PKT(0x460a), + PSIL_PDMA_XY_PKT(0x460b), + PSIL_PDMA_XY_PKT(0x460c), + PSIL_PDMA_XY_PKT(0x460d), + PSIL_PDMA_XY_PKT(0x460e), + PSIL_PDMA_XY_PKT(0x460f), + /* PDMA_SPI_G1 - SPI4-7 */ + PSIL_PDMA_XY_PKT(0x4610), + PSIL_PDMA_XY_PKT(0x4611), + PSIL_PDMA_XY_PKT(0x4612), + PSIL_PDMA_XY_PKT(0x4613), + PSIL_PDMA_XY_PKT(0x4614), + PSIL_PDMA_XY_PKT(0x4615), + PSIL_PDMA_XY_PKT(0x4616), + PSIL_PDMA_XY_PKT(0x4617), + PSIL_PDMA_XY_PKT(0x4618), + PSIL_PDMA_XY_PKT(0x4619), + PSIL_PDMA_XY_PKT(0x461a), + PSIL_PDMA_XY_PKT(0x461b), + PSIL_PDMA_XY_PKT(0x461c), + PSIL_PDMA_XY_PKT(0x461d), + PSIL_PDMA_XY_PKT(0x461e), + PSIL_PDMA_XY_PKT(0x461f), + /* PDMA_USART_G0 - UART0-1 */ + PSIL_PDMA_XY_PKT(0x4700), + PSIL_PDMA_XY_PKT(0x4701), + /* PDMA_USART_G1 - UART2-3 */ + PSIL_PDMA_XY_PKT(0x4702), + PSIL_PDMA_XY_PKT(0x4703), + /* PDMA_USART_G2 - UART4-9 */ + PSIL_PDMA_XY_PKT(0x4704), + PSIL_PDMA_XY_PKT(0x4705), + PSIL_PDMA_XY_PKT(0x4706), + PSIL_PDMA_XY_PKT(0x4707), + PSIL_PDMA_XY_PKT(0x4708), + PSIL_PDMA_XY_PKT(0x4709), + /* CPSW0 */ + PSIL_ETHERNET(0x7000), + /* MCU_PDMA0 (MCU_PDMA_MISC_G0) - SPI0 */ + PSIL_PDMA_XY_PKT(0x7100), + PSIL_PDMA_XY_PKT(0x7101), + PSIL_PDMA_XY_PKT(0x7102), + PSIL_PDMA_XY_PKT(0x7103), + /* MCU_PDMA1 (MCU_PDMA_MISC_G1) - SPI1-2 */ + PSIL_PDMA_XY_PKT(0x7200), + PSIL_PDMA_XY_PKT(0x7201), + PSIL_PDMA_XY_PKT(0x7202), + PSIL_PDMA_XY_PKT(0x7203), + PSIL_PDMA_XY_PKT(0x7204), + PSIL_PDMA_XY_PKT(0x7205), + PSIL_PDMA_XY_PKT(0x7206), + PSIL_PDMA_XY_PKT(0x7207), + /* MCU_PDMA2 (MCU_PDMA_MISC_G2) - UART0 */ + PSIL_PDMA_XY_PKT(0x7300), + /* MCU_PDMA_ADC - ADC0-1 */ + PSIL_PDMA_XY_TR(0x7400), + PSIL_PDMA_XY_TR(0x7401), + PSIL_PDMA_XY_TR(0x7402), + PSIL_PDMA_XY_TR(0x7403), + /* SA2UL */ + PSIL_SA2UL(0x7500, 0), + PSIL_SA2UL(0x7501, 0), + PSIL_SA2UL(0x7502, 0), + PSIL_SA2UL(0x7503, 0), +}; + +/* PSI-L destination thread IDs, used for TX (DMA_MEM_TO_DEV) */ +static struct psil_ep j721s2_dst_ep_map[] = { + /* CPSW0 */ + PSIL_ETHERNET(0xf000), + PSIL_ETHERNET(0xf001), + PSIL_ETHERNET(0xf002), + PSIL_ETHERNET(0xf003), + PSIL_ETHERNET(0xf004), + PSIL_ETHERNET(0xf005), + PSIL_ETHERNET(0xf006), + PSIL_ETHERNET(0xf007), + /* SA2UL */ + PSIL_SA2UL(0xf500, 1), + PSIL_SA2UL(0xf501, 1), +}; + +struct psil_ep_map j721s2_ep_map = { + .name = "j721s2", + .src = j721s2_src_ep_map, + .src_count = ARRAY_SIZE(j721s2_src_ep_map), + .dst = j721s2_dst_ep_map, + .dst_count = ARRAY_SIZE(j721s2_dst_ep_map), +}; diff --git a/drivers/dma/ti/k3-psil-priv.h b/drivers/dma/ti/k3-psil-priv.h index b74e192e3c2d..e51e179cdb56 100644 --- a/drivers/dma/ti/k3-psil-priv.h +++ b/drivers/dma/ti/k3-psil-priv.h @@ -41,5 +41,6 @@ extern struct psil_ep_map am654_ep_map; extern struct psil_ep_map j721e_ep_map; extern struct psil_ep_map j7200_ep_map; extern struct psil_ep_map am64_ep_map; +extern struct psil_ep_map j721s2_ep_map; #endif /* K3_PSIL_PRIV_H_ */ diff --git a/drivers/dma/ti/k3-psil.c b/drivers/dma/ti/k3-psil.c index 13ce7367d870..8867b4bd0c51 100644 --- a/drivers/dma/ti/k3-psil.c +++ b/drivers/dma/ti/k3-psil.c @@ -21,6 +21,7 @@ static const struct soc_device_attribute k3_soc_devices[] = { { .family = "J721E", .data = &j721e_ep_map }, { .family = "J7200", .data = &j7200_ep_map }, { .family = "AM64X", .data = &am64_ep_map }, + { .family = "J721S2", .data = &j721s2_ep_map }, { /* sentinel */ } }; diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c index c542ba5d383d..d2d4cbe63e44 100644 --- a/drivers/dma/ti/k3-udma.c +++ b/drivers/dma/ti/k3-udma.c @@ -4374,6 +4374,7 @@ static const struct soc_device_attribute k3_soc_devices[] = { { .family = "J721E", .data = &j721e_soc_data }, { .family = "J7200", .data = &j7200_soc_data }, { .family = "AM64X", .data = &am64_soc_data }, + { .family = "J721S2", .data = &j721e_soc_data}, { /* sentinel */ } }; diff --git a/drivers/dma/uniphier-xdmac.c b/drivers/dma/uniphier-xdmac.c index d6b8a202474f..290836b7e1be 100644 --- a/drivers/dma/uniphier-xdmac.c +++ b/drivers/dma/uniphier-xdmac.c @@ -131,8 +131,9 @@ uniphier_xdmac_next_desc(struct uniphier_xdmac_chan *xc) static void uniphier_xdmac_chan_start(struct uniphier_xdmac_chan *xc, struct uniphier_xdmac_desc *xd) { - u32 src_mode, src_addr, src_width; - u32 dst_mode, dst_addr, dst_width; + u32 src_mode, src_width; + u32 dst_mode, dst_width; + dma_addr_t src_addr, dst_addr; u32 val, its, tnum; enum dma_slave_buswidth buswidth; diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c index 4677ce08ed40..cd62bbb50e8b 100644 --- a/drivers/dma/xilinx/xilinx_dma.c +++ b/drivers/dma/xilinx/xilinx_dma.c @@ -2127,6 +2127,126 @@ error: return NULL; } +/** + * xilinx_cdma_prep_memcpy_sg - prepare descriptors for a memcpy_sg transaction + * @dchan: DMA channel + * @dst_sg: Destination scatter list + * @dst_sg_len: Number of entries in destination scatter list + * @src_sg: Source scatter list + * @src_sg_len: Number of entries in source scatter list + * @flags: transfer ack flags + * + * Return: Async transaction descriptor on success and NULL on failure + */ +static struct dma_async_tx_descriptor *xilinx_cdma_prep_memcpy_sg( + struct dma_chan *dchan, struct scatterlist *dst_sg, + unsigned int dst_sg_len, struct scatterlist *src_sg, + unsigned int src_sg_len, unsigned long flags) +{ + struct xilinx_dma_chan *chan = to_xilinx_chan(dchan); + struct xilinx_dma_tx_descriptor *desc; + struct xilinx_cdma_tx_segment *segment, *prev = NULL; + struct xilinx_cdma_desc_hw *hw; + size_t len, dst_avail, src_avail; + dma_addr_t dma_dst, dma_src; + + if (unlikely(dst_sg_len == 0 || src_sg_len == 0)) + return NULL; + + if (unlikely(!dst_sg || !src_sg)) + return NULL; + + desc = xilinx_dma_alloc_tx_descriptor(chan); + if (!desc) + return NULL; + + dma_async_tx_descriptor_init(&desc->async_tx, &chan->common); + desc->async_tx.tx_submit = xilinx_dma_tx_submit; + + dst_avail = sg_dma_len(dst_sg); + src_avail = sg_dma_len(src_sg); + /* + * loop until there is either no more source or no more destination + * scatterlist entry + */ + while (true) { + len = min_t(size_t, src_avail, dst_avail); + len = min_t(size_t, len, chan->xdev->max_buffer_len); + if (len == 0) + goto fetch; + + /* Allocate the link descriptor from DMA pool */ + segment = xilinx_cdma_alloc_tx_segment(chan); + if (!segment) + goto error; + + dma_dst = sg_dma_address(dst_sg) + sg_dma_len(dst_sg) - + dst_avail; + dma_src = sg_dma_address(src_sg) + sg_dma_len(src_sg) - + src_avail; + hw = &segment->hw; + hw->control = len; + hw->src_addr = dma_src; + hw->dest_addr = dma_dst; + if (chan->ext_addr) { + hw->src_addr_msb = upper_32_bits(dma_src); + hw->dest_addr_msb = upper_32_bits(dma_dst); + } + + if (prev) { + prev->hw.next_desc = segment->phys; + if (chan->ext_addr) + prev->hw.next_desc_msb = + upper_32_bits(segment->phys); + } + + prev = segment; + dst_avail -= len; + src_avail -= len; + list_add_tail(&segment->node, &desc->segments); + +fetch: + /* Fetch the next dst scatterlist entry */ + if (dst_avail == 0) { + if (dst_sg_len == 0) + break; + dst_sg = sg_next(dst_sg); + if (dst_sg == NULL) + break; + dst_sg_len--; + dst_avail = sg_dma_len(dst_sg); + } + /* Fetch the next src scatterlist entry */ + if (src_avail == 0) { + if (src_sg_len == 0) + break; + src_sg = sg_next(src_sg); + if (src_sg == NULL) + break; + src_sg_len--; + src_avail = sg_dma_len(src_sg); + } + } + + if (list_empty(&desc->segments)) { + dev_err(chan->xdev->dev, + "%s: Zero-size SG transfer requested\n", __func__); + goto error; + } + + /* Link the last hardware descriptor with the first. */ + segment = list_first_entry(&desc->segments, + struct xilinx_cdma_tx_segment, node); + desc->async_tx.phys = segment->phys; + prev->hw.next_desc = segment->phys; + + return &desc->async_tx; + +error: + xilinx_dma_free_tx_descriptor(chan, desc); + return NULL; +} + /** * xilinx_dma_prep_slave_sg - prepare descriptors for a DMA_SLAVE transaction * @dchan: DMA channel @@ -2860,7 +2980,9 @@ static int xilinx_dma_chan_probe(struct xilinx_dma_device *xdev, } /* Request the interrupt */ - chan->irq = irq_of_parse_and_map(node, chan->tdest); + chan->irq = of_irq_get(node, chan->tdest); + if (chan->irq < 0) + return dev_err_probe(xdev->dev, chan->irq, "failed to get irq\n"); err = request_irq(chan->irq, xdev->dma_config->irq_handler, IRQF_SHARED, "xilinx-dma-controller", chan); if (err) { @@ -2934,8 +3056,11 @@ static int xilinx_dma_child_probe(struct xilinx_dma_device *xdev, if (xdev->dma_config->dmatype == XDMA_TYPE_AXIMCDMA && ret < 0) dev_warn(xdev->dev, "missing dma-channels property\n"); - for (i = 0; i < nr_channels; i++) - xilinx_dma_chan_probe(xdev, node); + for (i = 0; i < nr_channels; i++) { + ret = xilinx_dma_chan_probe(xdev, node); + if (ret) + return ret; + } return 0; } @@ -3115,7 +3240,9 @@ static int xilinx_dma_probe(struct platform_device *pdev) DMA_RESIDUE_GRANULARITY_SEGMENT; } else if (xdev->dma_config->dmatype == XDMA_TYPE_CDMA) { dma_cap_set(DMA_MEMCPY, xdev->common.cap_mask); + dma_cap_set(DMA_MEMCPY_SG, xdev->common.cap_mask); xdev->common.device_prep_dma_memcpy = xilinx_cdma_prep_memcpy; + xdev->common.device_prep_dma_memcpy_sg = xilinx_cdma_prep_memcpy_sg; /* Residue calculation is supported by only AXI DMA and CDMA */ xdev->common.residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT; diff --git a/drivers/firmware/arm_scmi/virtio.c b/drivers/firmware/arm_scmi/virtio.c index 87039c5c03fd..eefcc4146749 100644 --- a/drivers/firmware/arm_scmi/virtio.c +++ b/drivers/firmware/arm_scmi/virtio.c @@ -452,7 +452,7 @@ static void scmi_vio_remove(struct virtio_device *vdev) * outstanding message on any vqueue to be ignored by complete_cb: now * we can just stop processing buffers and destroy the vqueues. */ - vdev->config->reset(vdev); + virtio_reset_device(vdev); vdev->config->del_vqs(vdev); /* Ensure scmi_vdev is visible as NULL */ smp_store_mb(scmi_vdev, NULL); diff --git a/drivers/gpio/gpio-virtio.c b/drivers/gpio/gpio-virtio.c index 9f4941bc5760..fcc5e8c08973 100644 --- a/drivers/gpio/gpio-virtio.c +++ b/drivers/gpio/gpio-virtio.c @@ -450,7 +450,7 @@ static void virtio_gpio_request_vq(struct virtqueue *vq) static void virtio_gpio_free_vqs(struct virtio_device *vdev) { - vdev->config->reset(vdev); + virtio_reset_device(vdev); vdev->config->del_vqs(vdev); } diff --git a/drivers/gpu/drm/virtio/virtgpu_kms.c b/drivers/gpu/drm/virtio/virtgpu_kms.c index 21f410901694..3313b92db531 100644 --- a/drivers/gpu/drm/virtio/virtgpu_kms.c +++ b/drivers/gpu/drm/virtio/virtgpu_kms.c @@ -279,7 +279,7 @@ void virtio_gpu_deinit(struct drm_device *dev) flush_work(&vgdev->ctrlq.dequeue_work); flush_work(&vgdev->cursorq.dequeue_work); flush_work(&vgdev->config_changed_work); - vgdev->vdev->config->reset(vgdev->vdev); + virtio_reset_device(vgdev->vdev); vgdev->vdev->config->del_vqs(vgdev->vdev); } diff --git a/drivers/hwspinlock/stm32_hwspinlock.c b/drivers/hwspinlock/stm32_hwspinlock.c index 3ad0ce0da4d9..5bd11a7fab65 100644 --- a/drivers/hwspinlock/stm32_hwspinlock.c +++ b/drivers/hwspinlock/stm32_hwspinlock.c @@ -54,8 +54,23 @@ static const struct hwspinlock_ops stm32_hwspinlock_ops = { .relax = stm32_hwspinlock_relax, }; +static void stm32_hwspinlock_disable_clk(void *data) +{ + struct platform_device *pdev = data; + struct stm32_hwspinlock *hw = platform_get_drvdata(pdev); + struct device *dev = &pdev->dev; + + pm_runtime_get_sync(dev); + pm_runtime_disable(dev); + pm_runtime_set_suspended(dev); + pm_runtime_put_noidle(dev); + + clk_disable_unprepare(hw->clk); +} + static int stm32_hwspinlock_probe(struct platform_device *pdev) { + struct device *dev = &pdev->dev; struct stm32_hwspinlock *hw; void __iomem *io_base; size_t array_size; @@ -66,43 +81,45 @@ static int stm32_hwspinlock_probe(struct platform_device *pdev) return PTR_ERR(io_base); array_size = STM32_MUTEX_NUM_LOCKS * sizeof(struct hwspinlock); - hw = devm_kzalloc(&pdev->dev, sizeof(*hw) + array_size, GFP_KERNEL); + hw = devm_kzalloc(dev, sizeof(*hw) + array_size, GFP_KERNEL); if (!hw) return -ENOMEM; - hw->clk = devm_clk_get(&pdev->dev, "hsem"); + hw->clk = devm_clk_get(dev, "hsem"); if (IS_ERR(hw->clk)) return PTR_ERR(hw->clk); + ret = clk_prepare_enable(hw->clk); + if (ret) { + dev_err(dev, "Failed to prepare_enable clock\n"); + return ret; + } + + platform_set_drvdata(pdev, hw); + + pm_runtime_get_noresume(dev); + pm_runtime_set_active(dev); + pm_runtime_enable(dev); + pm_runtime_put(dev); + + ret = devm_add_action_or_reset(dev, stm32_hwspinlock_disable_clk, pdev); + if (ret) { + dev_err(dev, "Failed to register action\n"); + return ret; + } + for (i = 0; i < STM32_MUTEX_NUM_LOCKS; i++) hw->bank.lock[i].priv = io_base + i * sizeof(u32); - platform_set_drvdata(pdev, hw); - pm_runtime_enable(&pdev->dev); - - ret = hwspin_lock_register(&hw->bank, &pdev->dev, &stm32_hwspinlock_ops, - 0, STM32_MUTEX_NUM_LOCKS); + ret = devm_hwspin_lock_register(dev, &hw->bank, &stm32_hwspinlock_ops, + 0, STM32_MUTEX_NUM_LOCKS); if (ret) - pm_runtime_disable(&pdev->dev); + dev_err(dev, "Failed to register hwspinlock\n"); return ret; } -static int stm32_hwspinlock_remove(struct platform_device *pdev) -{ - struct stm32_hwspinlock *hw = platform_get_drvdata(pdev); - int ret; - - ret = hwspin_lock_unregister(&hw->bank); - if (ret) - dev_err(&pdev->dev, "%s failed: %d\n", __func__, ret); - - pm_runtime_disable(&pdev->dev); - - return 0; -} - static int __maybe_unused stm32_hwspinlock_runtime_suspend(struct device *dev) { struct stm32_hwspinlock *hw = dev_get_drvdata(dev); @@ -135,7 +152,6 @@ MODULE_DEVICE_TABLE(of, stm32_hwpinlock_ids); static struct platform_driver stm32_hwspinlock_driver = { .probe = stm32_hwspinlock_probe, - .remove = stm32_hwspinlock_remove, .driver = { .name = "stm32_hwspinlock", .of_match_table = stm32_hwpinlock_ids, diff --git a/drivers/i2c/busses/i2c-virtio.c b/drivers/i2c/busses/i2c-virtio.c index 41eb0dcc3204..4b9536f50800 100644 --- a/drivers/i2c/busses/i2c-virtio.c +++ b/drivers/i2c/busses/i2c-virtio.c @@ -165,7 +165,7 @@ err_free: static void virtio_i2c_del_vqs(struct virtio_device *vdev) { - vdev->config->reset(vdev); + virtio_reset_device(vdev); vdev->config->del_vqs(vdev); } diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c index c3b4c677b442..dfe18dcd008d 100644 --- a/drivers/i3c/master.c +++ b/drivers/i3c/master.c @@ -343,7 +343,8 @@ struct bus_type i3c_bus_type = { static enum i3c_addr_slot_status i3c_bus_get_addr_slot_status(struct i3c_bus *bus, u16 addr) { - int status, bitpos = addr * 2; + unsigned long status; + int bitpos = addr * 2; if (addr > I2C_MAX_ADDR) return I3C_ADDR_SLOT_RSVD; diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c index 03a368da51b9..51a8608203de 100644 --- a/drivers/i3c/master/dw-i3c-master.c +++ b/drivers/i3c/master/dw-i3c-master.c @@ -793,6 +793,10 @@ static int dw_i3c_master_daa(struct i3c_master_controller *m) return -ENOMEM; pos = dw_i3c_master_get_free_pos(master); + if (pos < 0) { + dw_i3c_master_free_xfer(xfer); + return pos; + } cmd = &xfer->cmds[0]; cmd->cmd_hi = 0x1; cmd->cmd_lo = COMMAND_PORT_DEV_COUNT(master->maxdevs - pos) | diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c index 1b73647cc3b1..8c01123dc4ed 100644 --- a/drivers/i3c/master/mipi-i3c-hci/core.c +++ b/drivers/i3c/master/mipi-i3c-hci/core.c @@ -662,7 +662,7 @@ static int i3c_hci_init(struct i3c_hci *hci) /* Make sure our data ordering fits the host's */ regval = reg_read(HC_CONTROL); - if (IS_ENABLED(CONFIG_BIG_ENDIAN)) { + if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) { if (!(regval & HC_CONTROL_DATA_BIG_ENDIAN)) { regval |= HC_CONTROL_DATA_BIG_ENDIAN; reg_write(HC_CONTROL, regval); diff --git a/drivers/i3c/master/mipi-i3c-hci/dat_v1.c b/drivers/i3c/master/mipi-i3c-hci/dat_v1.c index 783e551a2c85..97bb49ff5b53 100644 --- a/drivers/i3c/master/mipi-i3c-hci/dat_v1.c +++ b/drivers/i3c/master/mipi-i3c-hci/dat_v1.c @@ -160,9 +160,7 @@ static int hci_dat_v1_get_index(struct i3c_hci *hci, u8 dev_addr) unsigned int dat_idx; u32 dat_w0; - for (dat_idx = find_first_bit(hci->DAT_data, hci->DAT_entries); - dat_idx < hci->DAT_entries; - dat_idx = find_next_bit(hci->DAT_data, hci->DAT_entries, dat_idx)) { + for_each_set_bit(dat_idx, hci->DAT_data, hci->DAT_entries) { dat_w0 = dat_w0_read(dat_idx); if (FIELD_GET(DAT_0_DYNAMIC_ADDRESS, dat_w0) == dev_addr) return dat_idx; diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c index af873a9be050..2990ac9eaade 100644 --- a/drivers/i3c/master/mipi-i3c-hci/dma.c +++ b/drivers/i3c/master/mipi-i3c-hci/dma.c @@ -223,7 +223,7 @@ static int hci_dma_init(struct i3c_hci *hci) } if (nr_rings > XFER_RINGS) nr_rings = XFER_RINGS; - rings = kzalloc(sizeof(*rings) + nr_rings * sizeof(*rh), GFP_KERNEL); + rings = kzalloc(struct_size(rings, headers, nr_rings), GFP_KERNEL); if (!rings) return -ENOMEM; hci->io_data = rings; diff --git a/drivers/i3c/master/mipi-i3c-hci/hci.h b/drivers/i3c/master/mipi-i3c-hci/hci.h index 80beb1d5be8f..f109923f6c3f 100644 --- a/drivers/i3c/master/mipi-i3c-hci/hci.h +++ b/drivers/i3c/master/mipi-i3c-hci/hci.h @@ -98,7 +98,7 @@ struct hci_xfer { static inline struct hci_xfer *hci_alloc_xfer(unsigned int n) { - return kzalloc(sizeof(struct hci_xfer) * n, GFP_KERNEL); + return kcalloc(n, sizeof(struct hci_xfer), GFP_KERNEL); } static inline void hci_free_xfer(struct hci_xfer *xfer, unsigned int n) diff --git a/drivers/i3c/master/svc-i3c-master.c b/drivers/i3c/master/svc-i3c-master.c index 879e5a64acaf..7550dad64ecf 100644 --- a/drivers/i3c/master/svc-i3c-master.c +++ b/drivers/i3c/master/svc-i3c-master.c @@ -17,7 +17,9 @@ #include #include #include +#include #include +#include /* Master Mode Registers */ #define SVC_I3C_MCONFIG 0x000 @@ -119,6 +121,7 @@ #define SVC_MDYNADDR_ADDR(x) FIELD_PREP(GENMASK(7, 1), (x)) #define SVC_I3C_MAX_DEVS 32 +#define SVC_I3C_PM_TIMEOUT_MS 1000 /* This parameter depends on the implementation and may be tuned */ #define SVC_I3C_FIFO_SIZE 16 @@ -236,6 +239,40 @@ static void svc_i3c_master_disable_interrupts(struct svc_i3c_master *master) writel(mask, master->regs + SVC_I3C_MINTCLR); } +static void svc_i3c_master_clear_merrwarn(struct svc_i3c_master *master) +{ + /* Clear pending warnings */ + writel(readl(master->regs + SVC_I3C_MERRWARN), + master->regs + SVC_I3C_MERRWARN); +} + +static void svc_i3c_master_flush_fifo(struct svc_i3c_master *master) +{ + /* Flush FIFOs */ + writel(SVC_I3C_MDATACTRL_FLUSHTB | SVC_I3C_MDATACTRL_FLUSHRB, + master->regs + SVC_I3C_MDATACTRL); +} + +static void svc_i3c_master_reset_fifo_trigger(struct svc_i3c_master *master) +{ + u32 reg; + + /* Set RX and TX tigger levels, flush FIFOs */ + reg = SVC_I3C_MDATACTRL_FLUSHTB | + SVC_I3C_MDATACTRL_FLUSHRB | + SVC_I3C_MDATACTRL_UNLOCK_TRIG | + SVC_I3C_MDATACTRL_TXTRIG_FIFO_NOT_FULL | + SVC_I3C_MDATACTRL_RXTRIG_FIFO_NOT_EMPTY; + writel(reg, master->regs + SVC_I3C_MDATACTRL); +} + +static void svc_i3c_master_reset(struct svc_i3c_master *master) +{ + svc_i3c_master_clear_merrwarn(master); + svc_i3c_master_reset_fifo_trigger(master); + svc_i3c_master_disable_interrupts(master); +} + static inline struct svc_i3c_master * to_svc_i3c_master(struct i3c_master_controller *master) { @@ -279,12 +316,6 @@ static void svc_i3c_master_emit_stop(struct svc_i3c_master *master) udelay(1); } -static void svc_i3c_master_clear_merrwarn(struct svc_i3c_master *master) -{ - writel(readl(master->regs + SVC_I3C_MERRWARN), - master->regs + SVC_I3C_MERRWARN); -} - static int svc_i3c_master_handle_ibi(struct svc_i3c_master *master, struct i3c_dev_desc *dev) { @@ -449,13 +480,23 @@ static int svc_i3c_master_bus_init(struct i3c_master_controller *m) struct i3c_device_info info = {}; unsigned long fclk_rate, fclk_period_ns; unsigned int high_period_ns, od_low_period_ns; - u32 ppbaud, pplow, odhpp, odbaud, i2cbaud, reg; + u32 ppbaud, pplow, odhpp, odbaud, odstop, i2cbaud, reg; int ret; + ret = pm_runtime_resume_and_get(master->dev); + if (ret < 0) { + dev_err(master->dev, + "<%s> cannot resume i3c bus master, err: %d\n", + __func__, ret); + return ret; + } + /* Timings derivation */ fclk_rate = clk_get_rate(master->fclk); - if (!fclk_rate) - return -EINVAL; + if (!fclk_rate) { + ret = -EINVAL; + goto rpm_out; + } fclk_period_ns = DIV_ROUND_UP(1000000000, fclk_rate); @@ -479,6 +520,7 @@ static int svc_i3c_master_bus_init(struct i3c_master_controller *m) switch (bus->mode) { case I3C_BUS_MODE_PURE: i2cbaud = 0; + odstop = 0; break; case I3C_BUS_MODE_MIXED_FAST: case I3C_BUS_MODE_MIXED_LIMITED: @@ -487,6 +529,7 @@ static int svc_i3c_master_bus_init(struct i3c_master_controller *m) * between the high and low period does not really matter. */ i2cbaud = DIV_ROUND_UP(1000, od_low_period_ns) - 2; + odstop = 1; break; case I3C_BUS_MODE_MIXED_SLOW: /* @@ -494,15 +537,16 @@ static int svc_i3c_master_bus_init(struct i3c_master_controller *m) * constraints as the FM+ mode. */ i2cbaud = DIV_ROUND_UP(2500, od_low_period_ns) - 2; + odstop = 1; break; default: - return -EINVAL; + goto rpm_out; } reg = SVC_I3C_MCONFIG_MASTER_EN | SVC_I3C_MCONFIG_DISTO(0) | SVC_I3C_MCONFIG_HKEEP(0) | - SVC_I3C_MCONFIG_ODSTOP(0) | + SVC_I3C_MCONFIG_ODSTOP(odstop) | SVC_I3C_MCONFIG_PPBAUD(ppbaud) | SVC_I3C_MCONFIG_PPLOW(pplow) | SVC_I3C_MCONFIG_ODBAUD(odbaud) | @@ -514,7 +558,7 @@ static int svc_i3c_master_bus_init(struct i3c_master_controller *m) /* Master core's registration */ ret = i3c_master_get_free_addr(m, 0); if (ret < 0) - return ret; + goto rpm_out; info.dyn_addr = ret; @@ -523,21 +567,33 @@ static int svc_i3c_master_bus_init(struct i3c_master_controller *m) ret = i3c_master_set_info(&master->base, &info); if (ret) - return ret; + goto rpm_out; - svc_i3c_master_enable_interrupts(master, SVC_I3C_MINT_SLVSTART); +rpm_out: + pm_runtime_mark_last_busy(master->dev); + pm_runtime_put_autosuspend(master->dev); - return 0; + return ret; } static void svc_i3c_master_bus_cleanup(struct i3c_master_controller *m) { struct svc_i3c_master *master = to_svc_i3c_master(m); + int ret; + + ret = pm_runtime_resume_and_get(master->dev); + if (ret < 0) { + dev_err(master->dev, "<%s> Cannot get runtime PM.\n", __func__); + return; + } svc_i3c_master_disable_interrupts(master); /* Disable master */ writel(0, master->regs + SVC_I3C_MCONFIG); + + pm_runtime_mark_last_busy(master->dev); + pm_runtime_put_autosuspend(master->dev); } static int svc_i3c_master_reserve_slot(struct svc_i3c_master *master) @@ -656,8 +712,10 @@ static int svc_i3c_master_readb(struct svc_i3c_master *master, u8 *dst, u32 reg; for (i = 0; i < len; i++) { - ret = readl_poll_timeout(master->regs + SVC_I3C_MSTATUS, reg, - SVC_I3C_MSTATUS_RXPEND(reg), 0, 1000); + ret = readl_poll_timeout_atomic(master->regs + SVC_I3C_MSTATUS, + reg, + SVC_I3C_MSTATUS_RXPEND(reg), + 0, 1000); if (ret) return ret; @@ -687,10 +745,11 @@ static int svc_i3c_master_do_daa_locked(struct svc_i3c_master *master, * Either one slave will send its ID, or the assignment process * is done. */ - ret = readl_poll_timeout(master->regs + SVC_I3C_MSTATUS, reg, - SVC_I3C_MSTATUS_RXPEND(reg) | - SVC_I3C_MSTATUS_MCTRLDONE(reg), - 1, 1000); + ret = readl_poll_timeout_atomic(master->regs + SVC_I3C_MSTATUS, + reg, + SVC_I3C_MSTATUS_RXPEND(reg) | + SVC_I3C_MSTATUS_MCTRLDONE(reg), + 1, 1000); if (ret) return ret; @@ -744,11 +803,12 @@ static int svc_i3c_master_do_daa_locked(struct svc_i3c_master *master, } /* Wait for the slave to be ready to receive its address */ - ret = readl_poll_timeout(master->regs + SVC_I3C_MSTATUS, reg, - SVC_I3C_MSTATUS_MCTRLDONE(reg) && - SVC_I3C_MSTATUS_STATE_DAA(reg) && - SVC_I3C_MSTATUS_BETWEEN(reg), - 0, 1000); + ret = readl_poll_timeout_atomic(master->regs + SVC_I3C_MSTATUS, + reg, + SVC_I3C_MSTATUS_MCTRLDONE(reg) && + SVC_I3C_MSTATUS_STATE_DAA(reg) && + SVC_I3C_MSTATUS_BETWEEN(reg), + 0, 1000); if (ret) return ret; @@ -832,31 +892,36 @@ static int svc_i3c_master_do_daa(struct i3c_master_controller *m) unsigned int dev_nb; int ret, i; + ret = pm_runtime_resume_and_get(master->dev); + if (ret < 0) { + dev_err(master->dev, "<%s> Cannot get runtime PM.\n", __func__); + return ret; + } + spin_lock_irqsave(&master->xferqueue.lock, flags); ret = svc_i3c_master_do_daa_locked(master, addrs, &dev_nb); spin_unlock_irqrestore(&master->xferqueue.lock, flags); - if (ret) - goto emit_stop; + if (ret) { + svc_i3c_master_emit_stop(master); + svc_i3c_master_clear_merrwarn(master); + goto rpm_out; + } /* Register all devices who participated to the core */ for (i = 0; i < dev_nb; i++) { ret = i3c_master_add_i3c_dev_locked(m, addrs[i]); if (ret) - return ret; + goto rpm_out; } /* Configure IBI auto-rules */ ret = svc_i3c_update_ibirules(master); - if (ret) { + if (ret) dev_err(master->dev, "Cannot handle such a list of devices"); - return ret; - } - return 0; - -emit_stop: - svc_i3c_master_emit_stop(master); - svc_i3c_master_clear_merrwarn(master); +rpm_out: + pm_runtime_mark_last_busy(master->dev); + pm_runtime_put_autosuspend(master->dev); return ret; } @@ -864,27 +929,35 @@ emit_stop: static int svc_i3c_master_read(struct svc_i3c_master *master, u8 *in, unsigned int len) { - int offset = 0, i, ret; - u32 mdctrl; + int offset = 0, i; + u32 mdctrl, mstatus; + bool completed = false; + unsigned int count; + unsigned long start = jiffies; - while (offset < len) { - unsigned int count; + while (!completed) { + mstatus = readl(master->regs + SVC_I3C_MSTATUS); + if (SVC_I3C_MSTATUS_COMPLETE(mstatus) != 0) + completed = true; - ret = readl_poll_timeout(master->regs + SVC_I3C_MDATACTRL, - mdctrl, - !(mdctrl & SVC_I3C_MDATACTRL_RXEMPTY), - 0, 1000); - if (ret) - return ret; + if (time_after(jiffies, start + msecs_to_jiffies(1000))) { + dev_dbg(master->dev, "I3C read timeout\n"); + return -ETIMEDOUT; + } + mdctrl = readl(master->regs + SVC_I3C_MDATACTRL); count = SVC_I3C_MDATACTRL_RXCOUNT(mdctrl); + if (offset + count > len) { + dev_err(master->dev, "I3C receive length too long!\n"); + return -EINVAL; + } for (i = 0; i < count; i++) in[offset + i] = readl(master->regs + SVC_I3C_MRDATAB); offset += count; } - return 0; + return offset; } static int svc_i3c_master_write(struct svc_i3c_master *master, @@ -917,7 +990,7 @@ static int svc_i3c_master_write(struct svc_i3c_master *master, static int svc_i3c_master_xfer(struct svc_i3c_master *master, bool rnw, unsigned int xfer_type, u8 addr, u8 *in, const u8 *out, unsigned int xfer_len, - unsigned int read_len, bool continued) + unsigned int *read_len, bool continued) { u32 reg; int ret; @@ -927,7 +1000,7 @@ static int svc_i3c_master_xfer(struct svc_i3c_master *master, SVC_I3C_MCTRL_IBIRESP_NACK | SVC_I3C_MCTRL_DIR(rnw) | SVC_I3C_MCTRL_ADDR(addr) | - SVC_I3C_MCTRL_RDTERM(read_len), + SVC_I3C_MCTRL_RDTERM(*read_len), master->regs + SVC_I3C_MCTRL); ret = readl_poll_timeout(master->regs + SVC_I3C_MSTATUS, reg, @@ -939,17 +1012,27 @@ static int svc_i3c_master_xfer(struct svc_i3c_master *master, ret = svc_i3c_master_read(master, in, xfer_len); else ret = svc_i3c_master_write(master, out, xfer_len); - if (ret) + if (ret < 0) goto emit_stop; + if (rnw) + *read_len = ret; + ret = readl_poll_timeout(master->regs + SVC_I3C_MSTATUS, reg, SVC_I3C_MSTATUS_COMPLETE(reg), 0, 1000); if (ret) goto emit_stop; - if (!continued) + writel(SVC_I3C_MINT_COMPLETE, master->regs + SVC_I3C_MSTATUS); + + if (!continued) { svc_i3c_master_emit_stop(master); + /* Wait idle if stop is sent. */ + readl_poll_timeout(master->regs + SVC_I3C_MSTATUS, reg, + SVC_I3C_MSTATUS_STATE_IDLE(reg), 0, 1000); + } + return 0; emit_stop: @@ -1007,17 +1090,29 @@ static void svc_i3c_master_start_xfer_locked(struct svc_i3c_master *master) if (!xfer) return; + ret = pm_runtime_resume_and_get(master->dev); + if (ret < 0) { + dev_err(master->dev, "<%s> Cannot get runtime PM.\n", __func__); + return; + } + + svc_i3c_master_clear_merrwarn(master); + svc_i3c_master_flush_fifo(master); + for (i = 0; i < xfer->ncmds; i++) { struct svc_i3c_cmd *cmd = &xfer->cmds[i]; ret = svc_i3c_master_xfer(master, cmd->rnw, xfer->type, cmd->addr, cmd->in, cmd->out, - cmd->len, cmd->read_len, + cmd->len, &cmd->read_len, cmd->continued); if (ret) break; } + pm_runtime_mark_last_busy(master->dev); + pm_runtime_put_autosuspend(master->dev); + xfer->ret = ret; complete(&xfer->comp); @@ -1141,6 +1236,9 @@ static int svc_i3c_master_send_direct_ccc_cmd(struct svc_i3c_master *master, if (!wait_for_completion_timeout(&xfer->comp, msecs_to_jiffies(1000))) svc_i3c_master_dequeue_xfer(master, xfer); + if (cmd->read_len != xfer_len) + ccc->dests[0].payload.len = cmd->read_len; + ret = xfer->ret; svc_i3c_master_free_xfer(xfer); @@ -1291,6 +1389,16 @@ static void svc_i3c_master_free_ibi(struct i3c_dev_desc *dev) static int svc_i3c_master_enable_ibi(struct i3c_dev_desc *dev) { struct i3c_master_controller *m = i3c_dev_get_master(dev); + struct svc_i3c_master *master = to_svc_i3c_master(m); + int ret; + + ret = pm_runtime_resume_and_get(master->dev); + if (ret < 0) { + dev_err(master->dev, "<%s> Cannot get runtime PM.\n", __func__); + return ret; + } + + svc_i3c_master_enable_interrupts(master, SVC_I3C_MINT_SLVSTART); return i3c_master_enec_locked(m, dev->info.dyn_addr, I3C_CCC_EVENT_SIR); } @@ -1298,8 +1406,17 @@ static int svc_i3c_master_enable_ibi(struct i3c_dev_desc *dev) static int svc_i3c_master_disable_ibi(struct i3c_dev_desc *dev) { struct i3c_master_controller *m = i3c_dev_get_master(dev); + struct svc_i3c_master *master = to_svc_i3c_master(m); + int ret; - return i3c_master_disec_locked(m, dev->info.dyn_addr, I3C_CCC_EVENT_SIR); + svc_i3c_master_disable_interrupts(master); + + ret = i3c_master_disec_locked(m, dev->info.dyn_addr, I3C_CCC_EVENT_SIR); + + pm_runtime_mark_last_busy(master->dev); + pm_runtime_put_autosuspend(master->dev); + + return ret; } static void svc_i3c_master_recycle_ibi_slot(struct i3c_dev_desc *dev, @@ -1330,23 +1447,35 @@ static const struct i3c_master_controller_ops svc_i3c_master_ops = { .disable_ibi = svc_i3c_master_disable_ibi, }; -static void svc_i3c_master_reset(struct svc_i3c_master *master) +static int svc_i3c_master_prepare_clks(struct svc_i3c_master *master) { - u32 reg; + int ret = 0; - /* Clear pending warnings */ - writel(readl(master->regs + SVC_I3C_MERRWARN), - master->regs + SVC_I3C_MERRWARN); + ret = clk_prepare_enable(master->pclk); + if (ret) + return ret; - /* Set RX and TX tigger levels, flush FIFOs */ - reg = SVC_I3C_MDATACTRL_FLUSHTB | - SVC_I3C_MDATACTRL_FLUSHRB | - SVC_I3C_MDATACTRL_UNLOCK_TRIG | - SVC_I3C_MDATACTRL_TXTRIG_FIFO_NOT_FULL | - SVC_I3C_MDATACTRL_RXTRIG_FIFO_NOT_EMPTY; - writel(reg, master->regs + SVC_I3C_MDATACTRL); + ret = clk_prepare_enable(master->fclk); + if (ret) { + clk_disable_unprepare(master->pclk); + return ret; + } - svc_i3c_master_disable_interrupts(master); + ret = clk_prepare_enable(master->sclk); + if (ret) { + clk_disable_unprepare(master->pclk); + clk_disable_unprepare(master->fclk); + return ret; + } + + return 0; +} + +static void svc_i3c_master_unprepare_clks(struct svc_i3c_master *master) +{ + clk_disable_unprepare(master->pclk); + clk_disable_unprepare(master->fclk); + clk_disable_unprepare(master->sclk); } static int svc_i3c_master_probe(struct platform_device *pdev) @@ -1381,26 +1510,16 @@ static int svc_i3c_master_probe(struct platform_device *pdev) master->dev = dev; - svc_i3c_master_reset(master); - - ret = clk_prepare_enable(master->pclk); + ret = svc_i3c_master_prepare_clks(master); if (ret) return ret; - ret = clk_prepare_enable(master->fclk); - if (ret) - goto err_disable_pclk; - - ret = clk_prepare_enable(master->sclk); - if (ret) - goto err_disable_fclk; - INIT_WORK(&master->hj_work, svc_i3c_master_hj_work); INIT_WORK(&master->ibi_work, svc_i3c_master_ibi_work); ret = devm_request_irq(dev, master->irq, svc_i3c_master_irq_handler, IRQF_NO_SUSPEND, "svc-i3c-irq", master); if (ret) - goto err_disable_sclk; + goto err_disable_clks; master->free_slots = GENMASK(SVC_I3C_MAX_DEVS - 1, 0); @@ -1414,27 +1533,38 @@ static int svc_i3c_master_probe(struct platform_device *pdev) GFP_KERNEL); if (!master->ibi.slots) { ret = -ENOMEM; - goto err_disable_sclk; + goto err_disable_clks; } platform_set_drvdata(pdev, master); + pm_runtime_set_autosuspend_delay(&pdev->dev, SVC_I3C_PM_TIMEOUT_MS); + pm_runtime_use_autosuspend(&pdev->dev); + pm_runtime_get_noresume(&pdev->dev); + pm_runtime_set_active(&pdev->dev); + pm_runtime_enable(&pdev->dev); + + svc_i3c_master_reset(master); + /* Register the master */ ret = i3c_master_register(&master->base, &pdev->dev, &svc_i3c_master_ops, false); if (ret) - goto err_disable_sclk; + goto rpm_disable; + + pm_runtime_mark_last_busy(&pdev->dev); + pm_runtime_put_autosuspend(&pdev->dev); return 0; -err_disable_sclk: - clk_disable_unprepare(master->sclk); +rpm_disable: + pm_runtime_dont_use_autosuspend(&pdev->dev); + pm_runtime_put_noidle(&pdev->dev); + pm_runtime_set_suspended(&pdev->dev); + pm_runtime_disable(&pdev->dev); -err_disable_fclk: - clk_disable_unprepare(master->fclk); - -err_disable_pclk: - clk_disable_unprepare(master->pclk); +err_disable_clks: + svc_i3c_master_unprepare_clks(master); return ret; } @@ -1448,17 +1578,45 @@ static int svc_i3c_master_remove(struct platform_device *pdev) if (ret) return ret; - clk_disable_unprepare(master->pclk); - clk_disable_unprepare(master->fclk); - clk_disable_unprepare(master->sclk); + pm_runtime_dont_use_autosuspend(&pdev->dev); + pm_runtime_disable(&pdev->dev); return 0; } +static int __maybe_unused svc_i3c_runtime_suspend(struct device *dev) +{ + struct svc_i3c_master *master = dev_get_drvdata(dev); + + svc_i3c_master_unprepare_clks(master); + pinctrl_pm_select_sleep_state(dev); + + return 0; +} + +static int __maybe_unused svc_i3c_runtime_resume(struct device *dev) +{ + struct svc_i3c_master *master = dev_get_drvdata(dev); + int ret = 0; + + pinctrl_pm_select_default_state(dev); + svc_i3c_master_prepare_clks(master); + + return ret; +} + +static const struct dev_pm_ops svc_i3c_pm_ops = { + SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, + pm_runtime_force_resume) + SET_RUNTIME_PM_OPS(svc_i3c_runtime_suspend, + svc_i3c_runtime_resume, NULL) +}; + static const struct of_device_id svc_i3c_master_of_match_tbl[] = { { .compatible = "silvaco,i3c-master" }, { /* sentinel */ }, }; +MODULE_DEVICE_TABLE(of, svc_i3c_master_of_match_tbl); static struct platform_driver svc_i3c_master = { .probe = svc_i3c_master_probe, @@ -1466,6 +1624,7 @@ static struct platform_driver svc_i3c_master = { .driver = { .name = "silvaco-i3c-master", .of_match_table = svc_i3c_master_of_match_tbl, + .pm = &svc_i3c_pm_ops, }, }; module_platform_driver(svc_i3c_master); diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c index 6b7da40f99c8..bf8167f43c56 100644 --- a/drivers/iio/pressure/bmp280-core.c +++ b/drivers/iio/pressure/bmp280-core.c @@ -1138,7 +1138,6 @@ int bmp280_common_probe(struct device *dev, } EXPORT_SYMBOL(bmp280_common_probe); -#ifdef CONFIG_PM static int bmp280_runtime_suspend(struct device *dev) { struct iio_dev *indio_dev = dev_get_drvdata(dev); @@ -1159,15 +1158,9 @@ static int bmp280_runtime_resume(struct device *dev) usleep_range(data->start_up_time, data->start_up_time + 100); return data->chip_info->chip_config(data); } -#endif /* CONFIG_PM */ -const struct dev_pm_ops bmp280_dev_pm_ops = { - SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, - pm_runtime_force_resume) - SET_RUNTIME_PM_OPS(bmp280_runtime_suspend, - bmp280_runtime_resume, NULL) -}; -EXPORT_SYMBOL(bmp280_dev_pm_ops); +EXPORT_RUNTIME_DEV_PM_OPS(bmp280_dev_pm_ops, bmp280_runtime_suspend, + bmp280_runtime_resume, NULL); MODULE_AUTHOR("Vlad Dogaru "); MODULE_DESCRIPTION("Driver for Bosch Sensortec BMP180/BMP280 pressure and temperature sensor"); diff --git a/drivers/iio/pressure/bmp280-i2c.c b/drivers/iio/pressure/bmp280-i2c.c index 8b03ea15c0d0..35045bd92846 100644 --- a/drivers/iio/pressure/bmp280-i2c.c +++ b/drivers/iio/pressure/bmp280-i2c.c @@ -58,7 +58,7 @@ static struct i2c_driver bmp280_i2c_driver = { .driver = { .name = "bmp280", .of_match_table = bmp280_of_i2c_match, - .pm = &bmp280_dev_pm_ops, + .pm = pm_ptr(&bmp280_dev_pm_ops), }, .probe = bmp280_i2c_probe, .id_table = bmp280_i2c_id, diff --git a/drivers/iio/pressure/bmp280-spi.c b/drivers/iio/pressure/bmp280-spi.c index 625b86878ad8..41f6cc56d229 100644 --- a/drivers/iio/pressure/bmp280-spi.c +++ b/drivers/iio/pressure/bmp280-spi.c @@ -109,7 +109,7 @@ static struct spi_driver bmp280_spi_driver = { .driver = { .name = "bmp280", .of_match_table = bmp280_of_spi_match, - .pm = &bmp280_dev_pm_ops, + .pm = pm_ptr(&bmp280_dev_pm_ops), }, .id_table = bmp280_spi_id, .probe = bmp280_spi_probe, diff --git a/drivers/input/ff-core.c b/drivers/input/ff-core.c index 1cf5deda06e1..fa8d1a466014 100644 --- a/drivers/input/ff-core.c +++ b/drivers/input/ff-core.c @@ -67,7 +67,7 @@ static int compat_effect(struct ff_device *ff, struct ff_effect *effect) effect->type = FF_PERIODIC; effect->u.periodic.waveform = FF_SINE; effect->u.periodic.period = 50; - effect->u.periodic.magnitude = max(magnitude, 0x7fff); + effect->u.periodic.magnitude = magnitude; effect->u.periodic.offset = 0; effect->u.periodic.phase = 0; effect->u.periodic.envelope.attack_length = 0; diff --git a/drivers/input/keyboard/gpio_keys.c b/drivers/input/keyboard/gpio_keys.c index 8dbf1e69c90a..d75a8b179a8a 100644 --- a/drivers/input/keyboard/gpio_keys.c +++ b/drivers/input/keyboard/gpio_keys.c @@ -247,7 +247,7 @@ static ssize_t gpio_keys_attr_store_helper(struct gpio_keys_drvdata *ddata, ssize_t error; int i; - bits = bitmap_zalloc(n_events, GFP_KERNEL); + bits = bitmap_alloc(n_events, GFP_KERNEL); if (!bits) return -ENOMEM; diff --git a/drivers/input/misc/axp20x-pek.c b/drivers/input/misc/axp20x-pek.c index e09b1fae42e1..04da7916eb70 100644 --- a/drivers/input/misc/axp20x-pek.c +++ b/drivers/input/misc/axp20x-pek.c @@ -206,11 +206,8 @@ ATTRIBUTE_GROUPS(axp20x); static irqreturn_t axp20x_pek_irq(int irq, void *pwr) { - struct axp20x_pek *axp20x_pek = pwr; - struct input_dev *idev = axp20x_pek->input; - - if (!idev) - return IRQ_HANDLED; + struct input_dev *idev = pwr; + struct axp20x_pek *axp20x_pek = input_get_drvdata(idev); /* * The power-button is connected to ground so a falling edge (dbf) @@ -229,9 +226,22 @@ static irqreturn_t axp20x_pek_irq(int irq, void *pwr) static int axp20x_pek_probe_input_device(struct axp20x_pek *axp20x_pek, struct platform_device *pdev) { + struct axp20x_dev *axp20x = axp20x_pek->axp20x; struct input_dev *idev; int error; + axp20x_pek->irq_dbr = platform_get_irq_byname(pdev, "PEK_DBR"); + if (axp20x_pek->irq_dbr < 0) + return axp20x_pek->irq_dbr; + axp20x_pek->irq_dbr = regmap_irq_get_virq(axp20x->regmap_irqc, + axp20x_pek->irq_dbr); + + axp20x_pek->irq_dbf = platform_get_irq_byname(pdev, "PEK_DBF"); + if (axp20x_pek->irq_dbf < 0) + return axp20x_pek->irq_dbf; + axp20x_pek->irq_dbf = regmap_irq_get_virq(axp20x->regmap_irqc, + axp20x_pek->irq_dbf); + axp20x_pek->input = devm_input_allocate_device(&pdev->dev); if (!axp20x_pek->input) return -ENOMEM; @@ -246,6 +256,24 @@ static int axp20x_pek_probe_input_device(struct axp20x_pek *axp20x_pek, input_set_drvdata(idev, axp20x_pek); + error = devm_request_any_context_irq(&pdev->dev, axp20x_pek->irq_dbr, + axp20x_pek_irq, 0, + "axp20x-pek-dbr", idev); + if (error < 0) { + dev_err(&pdev->dev, "Failed to request dbr IRQ#%d: %d\n", + axp20x_pek->irq_dbr, error); + return error; + } + + error = devm_request_any_context_irq(&pdev->dev, axp20x_pek->irq_dbf, + axp20x_pek_irq, 0, + "axp20x-pek-dbf", idev); + if (error < 0) { + dev_err(&pdev->dev, "Failed to request dbf IRQ#%d: %d\n", + axp20x_pek->irq_dbf, error); + return error; + } + error = input_register_device(idev); if (error) { dev_err(&pdev->dev, "Can't register input device: %d\n", @@ -253,6 +281,8 @@ static int axp20x_pek_probe_input_device(struct axp20x_pek *axp20x_pek, return error; } + device_init_wakeup(&pdev->dev, true); + return 0; } @@ -293,18 +323,6 @@ static int axp20x_pek_probe(struct platform_device *pdev) axp20x_pek->axp20x = dev_get_drvdata(pdev->dev.parent); - axp20x_pek->irq_dbr = platform_get_irq_byname(pdev, "PEK_DBR"); - if (axp20x_pek->irq_dbr < 0) - return axp20x_pek->irq_dbr; - axp20x_pek->irq_dbr = regmap_irq_get_virq( - axp20x_pek->axp20x->regmap_irqc, axp20x_pek->irq_dbr); - - axp20x_pek->irq_dbf = platform_get_irq_byname(pdev, "PEK_DBF"); - if (axp20x_pek->irq_dbf < 0) - return axp20x_pek->irq_dbf; - axp20x_pek->irq_dbf = regmap_irq_get_virq( - axp20x_pek->axp20x->regmap_irqc, axp20x_pek->irq_dbf); - if (axp20x_pek_should_register_input(axp20x_pek)) { error = axp20x_pek_probe_input_device(axp20x_pek, pdev); if (error) @@ -313,26 +331,6 @@ static int axp20x_pek_probe(struct platform_device *pdev) axp20x_pek->info = (struct axp20x_info *)match->driver_data; - error = devm_request_any_context_irq(&pdev->dev, axp20x_pek->irq_dbr, - axp20x_pek_irq, 0, - "axp20x-pek-dbr", axp20x_pek); - if (error < 0) { - dev_err(&pdev->dev, "Failed to request dbr IRQ#%d: %d\n", - axp20x_pek->irq_dbr, error); - return error; - } - - error = devm_request_any_context_irq(&pdev->dev, axp20x_pek->irq_dbf, - axp20x_pek_irq, 0, - "axp20x-pek-dbf", axp20x_pek); - if (error < 0) { - dev_err(&pdev->dev, "Failed to request dbf IRQ#%d: %d\n", - axp20x_pek->irq_dbf, error); - return error; - } - - device_init_wakeup(&pdev->dev, true); - platform_set_drvdata(pdev, axp20x_pek); return 0; diff --git a/drivers/input/misc/palmas-pwrbutton.c b/drivers/input/misc/palmas-pwrbutton.c index f9b05cf09ff5..2213e06b611d 100644 --- a/drivers/input/misc/palmas-pwrbutton.c +++ b/drivers/input/misc/palmas-pwrbutton.c @@ -15,6 +15,7 @@ * GNU General Public License for more details. */ +#include #include #include #include @@ -115,8 +116,8 @@ static void palmas_pwron_params_ofinit(struct device *dev, struct device_node *np; u32 val; int i, error; - u8 lpk_times[] = { 6, 8, 10, 12 }; - int pwr_on_deb_ms[] = { 15, 100, 500, 1000 }; + static const u8 lpk_times[] = { 6, 8, 10, 12 }; + static const int pwr_on_deb_ms[] = { 15, 100, 500, 1000 }; memset(config, 0, sizeof(*config)); @@ -192,8 +193,8 @@ static int palmas_pwron_probe(struct platform_device *pdev) * Setup default hardware shutdown option (long key press) * and debounce. */ - val = config.long_press_time_val << __ffs(PALMAS_LPK_TIME_MASK); - val |= config.pwron_debounce_val << __ffs(PALMAS_PWRON_DEBOUNCE_MASK); + val = FIELD_PREP(PALMAS_LPK_TIME_MASK, config.long_press_time_val) | + FIELD_PREP(PALMAS_PWRON_DEBOUNCE_MASK, config.pwron_debounce_val); error = palmas_update_bits(palmas, PALMAS_PMU_CONTROL_BASE, PALMAS_LONG_PRESS_KEY, PALMAS_LPK_TIME_MASK | diff --git a/drivers/input/mouse/byd.c b/drivers/input/mouse/byd.c index 6e0c5f5a2713..221a553f45cd 100644 --- a/drivers/input/mouse/byd.c +++ b/drivers/input/mouse/byd.c @@ -191,7 +191,7 @@ /* * The touchpad generates a mixture of absolute and relative packets, indicated - * by the the last byte of each packet being set to one of the following: + * by the last byte of each packet being set to one of the following: */ #define BYD_PACKET_ABSOLUTE 0xf8 #define BYD_PACKET_RELATIVE 0x00 diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c index aaa3c455e01e..a3bfc7a41679 100644 --- a/drivers/input/touchscreen/goodix.c +++ b/drivers/input/touchscreen/goodix.c @@ -297,6 +297,108 @@ static int goodix_ts_read_input_report(struct goodix_ts_data *ts, u8 *data) return -ENOMSG; } +static struct input_dev *goodix_create_pen_input(struct goodix_ts_data *ts) +{ + struct device *dev = &ts->client->dev; + struct input_dev *input; + + input = devm_input_allocate_device(dev); + if (!input) + return NULL; + + input_alloc_absinfo(input); + if (!input->absinfo) { + input_free_device(input); + return NULL; + } + + input->absinfo[ABS_X] = ts->input_dev->absinfo[ABS_MT_POSITION_X]; + input->absinfo[ABS_Y] = ts->input_dev->absinfo[ABS_MT_POSITION_Y]; + __set_bit(ABS_X, input->absbit); + __set_bit(ABS_Y, input->absbit); + input_set_abs_params(input, ABS_PRESSURE, 0, 255, 0, 0); + + input_set_capability(input, EV_KEY, BTN_TOUCH); + input_set_capability(input, EV_KEY, BTN_TOOL_PEN); + input_set_capability(input, EV_KEY, BTN_STYLUS); + input_set_capability(input, EV_KEY, BTN_STYLUS2); + __set_bit(INPUT_PROP_DIRECT, input->propbit); + /* + * The resolution of these touchscreens is about 10 units/mm, the actual + * resolution does not matter much since we set INPUT_PROP_DIRECT. + * Userspace wants something here though, so just set it to 10 units/mm. + */ + input_abs_set_res(input, ABS_X, 10); + input_abs_set_res(input, ABS_Y, 10); + + input->name = "Goodix Active Pen"; + input->phys = "input/pen"; + input->id.bustype = BUS_I2C; + input->id.vendor = 0x0416; + if (kstrtou16(ts->id, 10, &input->id.product)) + input->id.product = 0x1001; + input->id.version = ts->version; + + if (input_register_device(input) != 0) { + input_free_device(input); + return NULL; + } + + return input; +} + +static void goodix_ts_report_pen_down(struct goodix_ts_data *ts, u8 *data) +{ + int input_x, input_y, input_w; + u8 key_value; + + if (!ts->input_pen) { + ts->input_pen = goodix_create_pen_input(ts); + if (!ts->input_pen) + return; + } + + if (ts->contact_size == 9) { + input_x = get_unaligned_le16(&data[4]); + input_y = get_unaligned_le16(&data[6]); + input_w = get_unaligned_le16(&data[8]); + } else { + input_x = get_unaligned_le16(&data[2]); + input_y = get_unaligned_le16(&data[4]); + input_w = get_unaligned_le16(&data[6]); + } + + touchscreen_report_pos(ts->input_pen, &ts->prop, input_x, input_y, false); + input_report_abs(ts->input_pen, ABS_PRESSURE, input_w); + + input_report_key(ts->input_pen, BTN_TOUCH, 1); + input_report_key(ts->input_pen, BTN_TOOL_PEN, 1); + + if (data[0] & GOODIX_HAVE_KEY) { + key_value = data[1 + ts->contact_size]; + input_report_key(ts->input_pen, BTN_STYLUS, key_value & 0x10); + input_report_key(ts->input_pen, BTN_STYLUS2, key_value & 0x20); + } else { + input_report_key(ts->input_pen, BTN_STYLUS, 0); + input_report_key(ts->input_pen, BTN_STYLUS2, 0); + } + + input_sync(ts->input_pen); +} + +static void goodix_ts_report_pen_up(struct goodix_ts_data *ts) +{ + if (!ts->input_pen) + return; + + input_report_key(ts->input_pen, BTN_TOUCH, 0); + input_report_key(ts->input_pen, BTN_TOOL_PEN, 0); + input_report_key(ts->input_pen, BTN_STYLUS, 0); + input_report_key(ts->input_pen, BTN_STYLUS2, 0); + + input_sync(ts->input_pen); +} + static void goodix_ts_report_touch_8b(struct goodix_ts_data *ts, u8 *coor_data) { int id = coor_data[0] & 0x0F; @@ -327,6 +429,14 @@ static void goodix_ts_report_touch_9b(struct goodix_ts_data *ts, u8 *coor_data) input_report_abs(ts->input_dev, ABS_MT_WIDTH_MAJOR, input_w); } +static void goodix_ts_release_keys(struct goodix_ts_data *ts) +{ + int i; + + for (i = 0; i < GOODIX_MAX_KEYS; i++) + input_report_key(ts->input_dev, ts->keymap[i], 0); +} + static void goodix_ts_report_key(struct goodix_ts_data *ts, u8 *data) { int touch_num; @@ -341,8 +451,7 @@ static void goodix_ts_report_key(struct goodix_ts_data *ts, u8 *data) input_report_key(ts->input_dev, ts->keymap[i], 1); } else { - for (i = 0; i < GOODIX_MAX_KEYS; i++) - input_report_key(ts->input_dev, ts->keymap[i], 0); + goodix_ts_release_keys(ts); } } @@ -364,6 +473,15 @@ static void goodix_process_events(struct goodix_ts_data *ts) if (touch_num < 0) return; + /* The pen being down is always reported as a single touch */ + if (touch_num == 1 && (point_data[1] & 0x80)) { + goodix_ts_report_pen_down(ts, point_data); + goodix_ts_release_keys(ts); + goto sync; /* Release any previously registered touches */ + } else { + goodix_ts_report_pen_up(ts); + } + goodix_ts_report_key(ts, point_data); for (i = 0; i < touch_num; i++) @@ -374,6 +492,7 @@ static void goodix_process_events(struct goodix_ts_data *ts) goodix_ts_report_touch_8b(ts, &point_data[1 + ts->contact_size * i]); +sync: input_mt_sync_frame(ts->input_dev); input_sync(ts->input_dev); } @@ -857,7 +976,7 @@ retry_get_irq_gpio: if (IS_ERR(gpiod)) { error = PTR_ERR(gpiod); if (error != -EPROBE_DEFER) - dev_dbg(dev, "Failed to get %s GPIO: %d\n", + dev_err(dev, "Failed to get %s GPIO: %d\n", GOODIX_GPIO_INT_NAME, error); return error; } @@ -874,7 +993,7 @@ retry_get_irq_gpio: if (IS_ERR(gpiod)) { error = PTR_ERR(gpiod); if (error != -EPROBE_DEFER) - dev_dbg(dev, "Failed to get %s GPIO: %d\n", + dev_err(dev, "Failed to get %s GPIO: %d\n", GOODIX_GPIO_RST_NAME, error); return error; } diff --git a/drivers/input/touchscreen/goodix.h b/drivers/input/touchscreen/goodix.h index 02065d1c3263..fa8602e78a64 100644 --- a/drivers/input/touchscreen/goodix.h +++ b/drivers/input/touchscreen/goodix.h @@ -76,6 +76,7 @@ struct goodix_chip_data { struct goodix_ts_data { struct i2c_client *client; struct input_dev *input_dev; + struct input_dev *input_pen; const struct goodix_chip_data *chip; const char *firmware_name; struct touchscreen_properties prop; diff --git a/drivers/input/touchscreen/silead.c b/drivers/input/touchscreen/silead.c index 1ee760bac0cf..3eef8c01090f 100644 --- a/drivers/input/touchscreen/silead.c +++ b/drivers/input/touchscreen/silead.c @@ -67,6 +67,7 @@ struct silead_ts_data { struct i2c_client *client; struct gpio_desc *gpio_power; struct input_dev *input; + struct input_dev *pen_input; struct regulator_bulk_data regulators[2]; char fw_name[64]; struct touchscreen_properties prop; @@ -75,6 +76,13 @@ struct silead_ts_data { struct input_mt_pos pos[SILEAD_MAX_FINGERS]; int slots[SILEAD_MAX_FINGERS]; int id[SILEAD_MAX_FINGERS]; + u32 efi_fw_min_max[4]; + bool efi_fw_min_max_set; + bool pen_supported; + bool pen_down; + u32 pen_x_res; + u32 pen_y_res; + int pen_up_count; }; struct silead_fw_data { @@ -82,6 +90,35 @@ struct silead_fw_data { u32 val; }; +static void silead_apply_efi_fw_min_max(struct silead_ts_data *data) +{ + struct input_absinfo *absinfo_x = &data->input->absinfo[ABS_MT_POSITION_X]; + struct input_absinfo *absinfo_y = &data->input->absinfo[ABS_MT_POSITION_Y]; + + if (!data->efi_fw_min_max_set) + return; + + absinfo_x->minimum = data->efi_fw_min_max[0]; + absinfo_x->maximum = data->efi_fw_min_max[1]; + absinfo_y->minimum = data->efi_fw_min_max[2]; + absinfo_y->maximum = data->efi_fw_min_max[3]; + + if (data->prop.invert_x) { + absinfo_x->maximum -= absinfo_x->minimum; + absinfo_x->minimum = 0; + } + + if (data->prop.invert_y) { + absinfo_y->maximum -= absinfo_y->minimum; + absinfo_y->minimum = 0; + } + + if (data->prop.swap_x_y) { + swap(absinfo_x->minimum, absinfo_y->minimum); + swap(absinfo_x->maximum, absinfo_y->maximum); + } +} + static int silead_ts_request_input_dev(struct silead_ts_data *data) { struct device *dev = &data->client->dev; @@ -97,6 +134,7 @@ static int silead_ts_request_input_dev(struct silead_ts_data *data) input_set_abs_params(data->input, ABS_MT_POSITION_X, 0, 4095, 0, 0); input_set_abs_params(data->input, ABS_MT_POSITION_Y, 0, 4095, 0, 0); touchscreen_parse_properties(data->input, true, &data->prop); + silead_apply_efi_fw_min_max(data); input_mt_init_slots(data->input, data->max_fingers, INPUT_MT_DIRECT | INPUT_MT_DROP_UNUSED | @@ -112,6 +150,40 @@ static int silead_ts_request_input_dev(struct silead_ts_data *data) error = input_register_device(data->input); if (error) { dev_err(dev, "Failed to register input device: %d\n", error); + return error; + } + + return 0; +} + +static int silead_ts_request_pen_input_dev(struct silead_ts_data *data) +{ + struct device *dev = &data->client->dev; + int error; + + if (!data->pen_supported) + return 0; + + data->pen_input = devm_input_allocate_device(dev); + if (!data->pen_input) + return -ENOMEM; + + input_set_abs_params(data->pen_input, ABS_X, 0, 4095, 0, 0); + input_set_abs_params(data->pen_input, ABS_Y, 0, 4095, 0, 0); + input_set_capability(data->pen_input, EV_KEY, BTN_TOUCH); + input_set_capability(data->pen_input, EV_KEY, BTN_TOOL_PEN); + set_bit(INPUT_PROP_DIRECT, data->pen_input->propbit); + touchscreen_parse_properties(data->pen_input, false, &data->prop); + input_abs_set_res(data->pen_input, ABS_X, data->pen_x_res); + input_abs_set_res(data->pen_input, ABS_Y, data->pen_y_res); + + data->pen_input->name = SILEAD_TS_NAME " pen"; + data->pen_input->phys = "input/pen"; + data->input->id.bustype = BUS_I2C; + + error = input_register_device(data->pen_input); + if (error) { + dev_err(dev, "Failed to register pen input device: %d\n", error); return error; } @@ -129,6 +201,45 @@ static void silead_ts_set_power(struct i2c_client *client, } } +static bool silead_ts_handle_pen_data(struct silead_ts_data *data, u8 *buf) +{ + u8 *coord = buf + SILEAD_POINT_DATA_LEN; + struct input_mt_pos pos; + + if (!data->pen_supported || buf[2] != 0x00 || buf[3] != 0x00) + return false; + + if (buf[0] == 0x00 && buf[1] == 0x00 && data->pen_down) { + data->pen_up_count++; + if (data->pen_up_count == 6) { + data->pen_down = false; + goto sync; + } + return true; + } + + if (buf[0] == 0x01 && buf[1] == 0x08) { + touchscreen_set_mt_pos(&pos, &data->prop, + get_unaligned_le16(&coord[SILEAD_POINT_X_OFF]) & 0xfff, + get_unaligned_le16(&coord[SILEAD_POINT_Y_OFF]) & 0xfff); + + input_report_abs(data->pen_input, ABS_X, pos.x); + input_report_abs(data->pen_input, ABS_Y, pos.y); + + data->pen_up_count = 0; + data->pen_down = true; + goto sync; + } + + return false; + +sync: + input_report_key(data->pen_input, BTN_TOOL_PEN, data->pen_down); + input_report_key(data->pen_input, BTN_TOUCH, data->pen_down); + input_sync(data->pen_input); + return true; +} + static void silead_ts_read_data(struct i2c_client *client) { struct silead_ts_data *data = i2c_get_clientdata(client); @@ -151,6 +262,9 @@ static void silead_ts_read_data(struct i2c_client *client) buf[0] = data->max_fingers; } + if (silead_ts_handle_pen_data(data, buf)) + goto sync; /* Pen is down, release all previous touches */ + touch_nr = 0; bufp = buf + SILEAD_POINT_DATA_LEN; for (i = 0; i < buf[0]; i++, bufp += SILEAD_POINT_DATA_LEN) { @@ -193,6 +307,7 @@ static void silead_ts_read_data(struct i2c_client *client) data->pos[i].y, data->id[i], data->slots[i]); } +sync: input_mt_sync_frame(input); input_report_key(input, KEY_LEFTMETA, softbutton_pressed); input_sync(input); @@ -282,17 +397,56 @@ static int silead_ts_load_fw(struct i2c_client *client) { struct device *dev = &client->dev; struct silead_ts_data *data = i2c_get_clientdata(client); - unsigned int fw_size, i; - const struct firmware *fw; + const struct firmware *fw = NULL; struct silead_fw_data *fw_data; + unsigned int fw_size, i; int error; dev_dbg(dev, "Firmware file name: %s", data->fw_name); - error = firmware_request_platform(&fw, data->fw_name, dev); + /* + * Unfortunately, at the time of writing this comment, we have been unable to + * get permission from Silead, or from device OEMs, to distribute the necessary + * Silead firmware files in linux-firmware. + * + * On a whole bunch of devices the UEFI BIOS code contains a touchscreen driver, + * which contains an embedded copy of the firmware. The fw-loader code has a + * "platform" fallback mechanism, which together with info on the firmware + * from drivers/platform/x86/touchscreen_dmi.c will use the firmware from the + * UEFI driver when the firmware is missing from /lib/firmware. This makes the + * touchscreen work OOTB without users needing to manually download the firmware. + * + * The firmware bundled with the original Windows/Android is usually newer then + * the firmware in the UEFI driver and it is better calibrated. This better + * calibration can lead to significant differences in the reported min/max + * coordinates. + * + * To deal with this we first try to load the firmware without "platform" + * fallback. If that fails we retry with "platform" fallback and if that + * succeeds we apply an (optional) set of alternative min/max values from the + * "silead,efi-fw-min-max" property. + */ + error = firmware_request_nowarn(&fw, data->fw_name, dev); if (error) { - dev_err(dev, "Firmware request error %d\n", error); - return error; + error = firmware_request_platform(&fw, data->fw_name, dev); + if (error) { + dev_err(dev, "Firmware request error %d\n", error); + return error; + } + + error = device_property_read_u32_array(dev, "silead,efi-fw-min-max", + data->efi_fw_min_max, + ARRAY_SIZE(data->efi_fw_min_max)); + if (!error) + data->efi_fw_min_max_set = true; + + /* The EFI (platform) embedded fw does not have pen support */ + if (data->pen_supported) { + dev_warn(dev, "Warning loading '%s' from filesystem failed, using EFI embedded copy.\n", + data->fw_name); + dev_warn(dev, "Warning pen support is known to be broken in the EFI embedded fw version\n"); + data->pen_supported = false; + } } fw_size = fw->size / sizeof(*fw_data); @@ -450,6 +604,10 @@ static void silead_ts_read_props(struct i2c_client *client) "silead/%s", str); else dev_dbg(dev, "Firmware file name read error. Using default."); + + data->pen_supported = device_property_read_bool(dev, "silead,pen-supported"); + device_property_read_u32(dev, "silead,pen-resolution-x", &data->pen_x_res); + device_property_read_u32(dev, "silead,pen-resolution-y", &data->pen_y_res); } #ifdef CONFIG_ACPI @@ -562,6 +720,10 @@ static int silead_ts_probe(struct i2c_client *client, if (error) return error; + error = silead_ts_request_pen_input_dev(data); + if (error) + return error; + error = devm_request_threaded_irq(dev, client->irq, NULL, silead_ts_threaded_irq_handler, IRQF_ONESHOT, client->name, data); diff --git a/drivers/input/touchscreen/ti_am335x_tsc.c b/drivers/input/touchscreen/ti_am335x_tsc.c index 83e685557a19..f2fb6a9a1a57 100644 --- a/drivers/input/touchscreen/ti_am335x_tsc.c +++ b/drivers/input/touchscreen/ti_am335x_tsc.c @@ -126,12 +126,13 @@ static int titsc_config_wires(struct titsc *ts_dev) static void titsc_step_config(struct titsc *ts_dev) { unsigned int config; - int i; + int i, n; int end_step, first_step, tsc_steps; u32 stepenable; config = STEPCONFIG_MODE_HWSYNC | - STEPCONFIG_AVG_16 | ts_dev->bit_xp; + STEPCONFIG_AVG_16 | ts_dev->bit_xp | + STEPCONFIG_INM_ADCREFM; switch (ts_dev->wires) { case 4: config |= STEPCONFIG_INP(ts_dev->inp_yp) | ts_dev->bit_xn; @@ -150,9 +151,11 @@ static void titsc_step_config(struct titsc *ts_dev) first_step = TOTAL_STEPS - tsc_steps; /* Steps 16 to 16-coordinate_readouts is for X */ end_step = first_step + tsc_steps; + n = 0; for (i = end_step - ts_dev->coordinate_readouts; i < end_step; i++) { titsc_writel(ts_dev, REG_STEPCONFIG(i), config); - titsc_writel(ts_dev, REG_STEPDELAY(i), STEPCONFIG_OPENDLY); + titsc_writel(ts_dev, REG_STEPDELAY(i), + n++ == 0 ? STEPCONFIG_OPENDLY : 0); } config = 0; @@ -174,9 +177,11 @@ static void titsc_step_config(struct titsc *ts_dev) /* 1 ... coordinate_readouts is for Y */ end_step = first_step + ts_dev->coordinate_readouts; + n = 0; for (i = first_step; i < end_step; i++) { titsc_writel(ts_dev, REG_STEPCONFIG(i), config); - titsc_writel(ts_dev, REG_STEPDELAY(i), STEPCONFIG_OPENDLY); + titsc_writel(ts_dev, REG_STEPDELAY(i), + n++ == 0 ? STEPCONFIG_OPENDLY : 0); } /* Make CHARGECONFIG same as IDLECONFIG */ @@ -195,7 +200,10 @@ static void titsc_step_config(struct titsc *ts_dev) STEPCONFIG_OPENDLY); end_step++; - config |= STEPCONFIG_INP(ts_dev->inp_yn); + config = STEPCONFIG_MODE_HWSYNC | + STEPCONFIG_AVG_16 | ts_dev->bit_yp | + ts_dev->bit_xn | STEPCONFIG_INM_ADCREFM | + STEPCONFIG_INP(ts_dev->inp_yn); titsc_writel(ts_dev, REG_STEPCONFIG(end_step), config); titsc_writel(ts_dev, REG_STEPDELAY(end_step), STEPCONFIG_OPENDLY); @@ -310,7 +318,7 @@ static irqreturn_t titsc_irq(int irq, void *dev) /* * Calculate pressure using formula * Resistance(touch) = x plate resistance * - * x postion/4096 * ((z2 / z1) - 1) + * x position/4096 * ((z2 / z1) - 1) */ z = z1 - z2; z *= x; diff --git a/drivers/input/touchscreen/ucb1400_ts.c b/drivers/input/touchscreen/ucb1400_ts.c index e3f2c940ef3d..dfd3b35590c3 100644 --- a/drivers/input/touchscreen/ucb1400_ts.c +++ b/drivers/input/touchscreen/ucb1400_ts.c @@ -186,7 +186,6 @@ static irqreturn_t ucb1400_irq(int irqnr, void *devid) { struct ucb1400_ts *ucb = devid; unsigned int x, y, p; - bool penup; if (unlikely(irqnr != ucb->irq)) return IRQ_NONE; @@ -196,8 +195,7 @@ static irqreturn_t ucb1400_irq(int irqnr, void *devid) /* Start with a small delay before checking pendown state */ msleep(UCB1400_TS_POLL_PERIOD); - while (!ucb->stopped && !(penup = ucb1400_ts_pen_up(ucb))) { - + while (!ucb->stopped && !ucb1400_ts_pen_up(ucb)) { ucb1400_adc_enable(ucb->ac97); x = ucb1400_ts_read_xpos(ucb); y = ucb1400_ts_read_ypos(ucb); diff --git a/drivers/input/touchscreen/wacom_i2c.c b/drivers/input/touchscreen/wacom_i2c.c index fe4ea6204a4e..141754b2764c 100644 --- a/drivers/input/touchscreen/wacom_i2c.c +++ b/drivers/input/touchscreen/wacom_i2c.c @@ -24,12 +24,19 @@ #define WACOM_IN_PROXIMITY BIT(5) /* Registers */ -#define WACOM_CMD_QUERY0 0x04 -#define WACOM_CMD_QUERY1 0x00 -#define WACOM_CMD_QUERY2 0x33 -#define WACOM_CMD_QUERY3 0x02 -#define WACOM_CMD_THROW0 0x05 -#define WACOM_CMD_THROW1 0x00 +#define WACOM_COMMAND_LSB 0x04 +#define WACOM_COMMAND_MSB 0x00 + +#define WACOM_DATA_LSB 0x05 +#define WACOM_DATA_MSB 0x00 + +/* Report types */ +#define REPORT_FEATURE 0x30 + +/* Requests / operations */ +#define OPCODE_GET_REPORT 0x02 + +#define WACOM_QUERY_REPORT 3 #define WACOM_QUERY_SIZE 19 struct wacom_features { @@ -50,23 +57,24 @@ struct wacom_i2c { static int wacom_query_device(struct i2c_client *client, struct wacom_features *features) { - int ret; - u8 cmd1[] = { WACOM_CMD_QUERY0, WACOM_CMD_QUERY1, - WACOM_CMD_QUERY2, WACOM_CMD_QUERY3 }; - u8 cmd2[] = { WACOM_CMD_THROW0, WACOM_CMD_THROW1 }; + u8 get_query_data_cmd[] = { + WACOM_COMMAND_LSB, + WACOM_COMMAND_MSB, + REPORT_FEATURE | WACOM_QUERY_REPORT, + OPCODE_GET_REPORT, + WACOM_DATA_LSB, + WACOM_DATA_MSB, + }; u8 data[WACOM_QUERY_SIZE]; + int ret; + struct i2c_msg msgs[] = { + /* Request reading of feature ReportID: 3 (Pen Query Data) */ { .addr = client->addr, .flags = 0, - .len = sizeof(cmd1), - .buf = cmd1, - }, - { - .addr = client->addr, - .flags = 0, - .len = sizeof(cmd2), - .buf = cmd2, + .len = sizeof(get_query_data_cmd), + .buf = get_query_data_cmd, }, { .addr = client->addr, diff --git a/drivers/input/touchscreen/zinitix.c b/drivers/input/touchscreen/zinitix.c index 1e70b8d2a8d7..7c82c4f5fa6b 100644 --- a/drivers/input/touchscreen/zinitix.c +++ b/drivers/input/touchscreen/zinitix.c @@ -252,16 +252,27 @@ static int zinitix_init_touch(struct bt541_ts_data *bt541) static int zinitix_init_regulators(struct bt541_ts_data *bt541) { - struct i2c_client *client = bt541->client; + struct device *dev = &bt541->client->dev; int error; - bt541->supplies[0].supply = "vdd"; - bt541->supplies[1].supply = "vddo"; - error = devm_regulator_bulk_get(&client->dev, + /* + * Some older device trees have erroneous names for the regulators, + * so check if "vddo" is present and in that case use these names. + * Else use the proper supply names on the component. + */ + if (of_find_property(dev->of_node, "vddo-supply", NULL)) { + bt541->supplies[0].supply = "vdd"; + bt541->supplies[1].supply = "vddo"; + } else { + /* Else use the proper supply names */ + bt541->supplies[0].supply = "vcca"; + bt541->supplies[1].supply = "vdd"; + } + error = devm_regulator_bulk_get(dev, ARRAY_SIZE(bt541->supplies), bt541->supplies); if (error < 0) { - dev_err(&client->dev, "Failed to get regulators: %d\n", error); + dev_err(dev, "Failed to get regulators: %d\n", error); return error; } @@ -560,6 +571,7 @@ static SIMPLE_DEV_PM_OPS(zinitix_pm_ops, zinitix_suspend, zinitix_resume); #ifdef CONFIG_OF static const struct of_device_id zinitix_of_match[] = { + { .compatible = "zinitix,bt532" }, { .compatible = "zinitix,bt541" }, { } }; diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c index 1f793219cac6..f2aa34f57454 100644 --- a/drivers/iommu/virtio-iommu.c +++ b/drivers/iommu/virtio-iommu.c @@ -1189,7 +1189,7 @@ static void viommu_remove(struct virtio_device *vdev) iommu_device_unregister(&viommu->iommu); /* Stop all virtqueues */ - vdev->config->reset(vdev); + virtio_reset_device(vdev); vdev->config->del_vqs(vdev); dev_info(&vdev->dev, "device removed\n"); diff --git a/drivers/mmc/host/jz4740_mmc.c b/drivers/mmc/host/jz4740_mmc.c index 7693236c946f..7ab1b38a7be5 100644 --- a/drivers/mmc/host/jz4740_mmc.c +++ b/drivers/mmc/host/jz4740_mmc.c @@ -1128,8 +1128,8 @@ static int jz4740_mmc_resume(struct device *dev) return pinctrl_select_default_state(dev); } -DEFINE_SIMPLE_DEV_PM_OPS(jz4740_mmc_pm_ops, jz4740_mmc_suspend, - jz4740_mmc_resume); +static DEFINE_SIMPLE_DEV_PM_OPS(jz4740_mmc_pm_ops, jz4740_mmc_suspend, + jz4740_mmc_resume); static struct platform_driver jz4740_mmc_driver = { .probe = jz4740_mmc_probe, diff --git a/drivers/mmc/host/mxcmmc.c b/drivers/mmc/host/mxcmmc.c index 98c218bd6669..40b6878bea6c 100644 --- a/drivers/mmc/host/mxcmmc.c +++ b/drivers/mmc/host/mxcmmc.c @@ -1210,7 +1210,7 @@ static int mxcmci_resume(struct device *dev) return ret; } -DEFINE_SIMPLE_DEV_PM_OPS(mxcmci_pm_ops, mxcmci_suspend, mxcmci_resume); +static DEFINE_SIMPLE_DEV_PM_OPS(mxcmci_pm_ops, mxcmci_suspend, mxcmci_resume); static struct platform_driver mxcmci_driver = { .probe = mxcmci_probe, diff --git a/drivers/net/caif/caif_virtio.c b/drivers/net/caif/caif_virtio.c index 91230894692d..444ef6a342f6 100644 --- a/drivers/net/caif/caif_virtio.c +++ b/drivers/net/caif/caif_virtio.c @@ -754,7 +754,7 @@ static void cfv_remove(struct virtio_device *vdev) debugfs_remove_recursive(cfv->debugfs); vringh_kiov_cleanup(&cfv->ctx.riov); - vdev->config->reset(vdev); + virtio_reset_device(vdev); vdev->vringh_config->del_vrhs(cfv->vdev); cfv->vr_rx = NULL; vdev->config->del_vqs(cfv->vdev); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 569eecfbc2cd..3d97f158ec59 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -3312,7 +3312,7 @@ static int virtnet_probe(struct virtio_device *vdev) return 0; free_unregister_netdev: - vi->vdev->config->reset(vdev); + virtio_reset_device(vdev); unregister_netdev(dev); free_failover: @@ -3328,7 +3328,7 @@ free: static void remove_vq_common(struct virtnet_info *vi) { - vi->vdev->config->reset(vi->vdev); + virtio_reset_device(vi->vdev); /* Free unused buffers in both send and recv, if any. */ free_unused_bufs(vi); diff --git a/drivers/net/wireguard/noise.c b/drivers/net/wireguard/noise.c index c0cfd9b36c0b..720952b92e78 100644 --- a/drivers/net/wireguard/noise.c +++ b/drivers/net/wireguard/noise.c @@ -302,6 +302,41 @@ void wg_noise_set_static_identity_private_key( static_identity->static_public, private_key); } +static void hmac(u8 *out, const u8 *in, const u8 *key, const size_t inlen, const size_t keylen) +{ + struct blake2s_state state; + u8 x_key[BLAKE2S_BLOCK_SIZE] __aligned(__alignof__(u32)) = { 0 }; + u8 i_hash[BLAKE2S_HASH_SIZE] __aligned(__alignof__(u32)); + int i; + + if (keylen > BLAKE2S_BLOCK_SIZE) { + blake2s_init(&state, BLAKE2S_HASH_SIZE); + blake2s_update(&state, key, keylen); + blake2s_final(&state, x_key); + } else + memcpy(x_key, key, keylen); + + for (i = 0; i < BLAKE2S_BLOCK_SIZE; ++i) + x_key[i] ^= 0x36; + + blake2s_init(&state, BLAKE2S_HASH_SIZE); + blake2s_update(&state, x_key, BLAKE2S_BLOCK_SIZE); + blake2s_update(&state, in, inlen); + blake2s_final(&state, i_hash); + + for (i = 0; i < BLAKE2S_BLOCK_SIZE; ++i) + x_key[i] ^= 0x5c ^ 0x36; + + blake2s_init(&state, BLAKE2S_HASH_SIZE); + blake2s_update(&state, x_key, BLAKE2S_BLOCK_SIZE); + blake2s_update(&state, i_hash, BLAKE2S_HASH_SIZE); + blake2s_final(&state, i_hash); + + memcpy(out, i_hash, BLAKE2S_HASH_SIZE); + memzero_explicit(x_key, BLAKE2S_BLOCK_SIZE); + memzero_explicit(i_hash, BLAKE2S_HASH_SIZE); +} + /* This is Hugo Krawczyk's HKDF: * - https://eprint.iacr.org/2010/264.pdf * - https://tools.ietf.org/html/rfc5869 @@ -322,14 +357,14 @@ static void kdf(u8 *first_dst, u8 *second_dst, u8 *third_dst, const u8 *data, ((third_len || third_dst) && (!second_len || !second_dst)))); /* Extract entropy from data into secret */ - blake2s256_hmac(secret, data, chaining_key, data_len, NOISE_HASH_LEN); + hmac(secret, data, chaining_key, data_len, NOISE_HASH_LEN); if (!first_dst || !first_len) goto out; /* Expand first key: key = secret, data = 0x1 */ output[0] = 1; - blake2s256_hmac(output, output, secret, 1, BLAKE2S_HASH_SIZE); + hmac(output, output, secret, 1, BLAKE2S_HASH_SIZE); memcpy(first_dst, output, first_len); if (!second_dst || !second_len) @@ -337,8 +372,7 @@ static void kdf(u8 *first_dst, u8 *second_dst, u8 *third_dst, const u8 *data, /* Expand second key: key = secret, data = first-key || 0x2 */ output[BLAKE2S_HASH_SIZE] = 2; - blake2s256_hmac(output, output, secret, BLAKE2S_HASH_SIZE + 1, - BLAKE2S_HASH_SIZE); + hmac(output, output, secret, BLAKE2S_HASH_SIZE + 1, BLAKE2S_HASH_SIZE); memcpy(second_dst, output, second_len); if (!third_dst || !third_len) @@ -346,8 +380,7 @@ static void kdf(u8 *first_dst, u8 *second_dst, u8 *third_dst, const u8 *data, /* Expand third key: key = secret, data = second-key || 0x3 */ output[BLAKE2S_HASH_SIZE] = 3; - blake2s256_hmac(output, output, secret, BLAKE2S_HASH_SIZE + 1, - BLAKE2S_HASH_SIZE); + hmac(output, output, secret, BLAKE2S_HASH_SIZE + 1, BLAKE2S_HASH_SIZE); memcpy(third_dst, output, third_len); out: diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 0307a6677907..8d54f9face2f 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -4498,7 +4498,7 @@ static void remove_vqs(struct virtio_device *vdev) { int i; - vdev->config->reset(vdev); + virtio_reset_device(vdev); for (i = 0; i < ARRAY_SIZE(hwsim_vqs); i++) { struct virtqueue *vq = hwsim_vqs[i]; diff --git a/drivers/ntb/hw/amd/ntb_hw_amd.c b/drivers/ntb/hw/amd/ntb_hw_amd.c index 87847c380051..04550b1f984c 100644 --- a/drivers/ntb/hw/amd/ntb_hw_amd.c +++ b/drivers/ntb/hw/amd/ntb_hw_amd.c @@ -1321,6 +1321,8 @@ static const struct ntb_dev_data dev_data[] = { static const struct pci_device_id amd_ntb_pci_tbl[] = { { PCI_VDEVICE(AMD, 0x145b), (kernel_ulong_t)&dev_data[0] }, { PCI_VDEVICE(AMD, 0x148b), (kernel_ulong_t)&dev_data[1] }, + { PCI_VDEVICE(AMD, 0x14c0), (kernel_ulong_t)&dev_data[1] }, + { PCI_VDEVICE(AMD, 0x14c3), (kernel_ulong_t)&dev_data[1] }, { PCI_VDEVICE(HYGON, 0x145b), (kernel_ulong_t)&dev_data[0] }, { 0, } }; diff --git a/drivers/ntb/hw/mscc/ntb_hw_switchtec.c b/drivers/ntb/hw/mscc/ntb_hw_switchtec.c index 4c6eb61a6ac6..88ae18b0efa8 100644 --- a/drivers/ntb/hw/mscc/ntb_hw_switchtec.c +++ b/drivers/ntb/hw/mscc/ntb_hw_switchtec.c @@ -297,7 +297,7 @@ static int switchtec_ntb_mw_set_trans(struct ntb_dev *ntb, int pidx, int widx, * (see CMA_CONFIG_ALIGNMENT) */ dev_err(&sndev->stdev->dev, - "ERROR: Memory window address is not aligned to it's size!\n"); + "ERROR: Memory window address is not aligned to its size!\n"); return -EINVAL; } @@ -419,8 +419,10 @@ static void switchtec_ntb_part_link_speed(struct switchtec_ntb *sndev, enum ntb_width *width) { struct switchtec_dev *stdev = sndev->stdev; + struct part_cfg_regs __iomem *part_cfg = + &stdev->mmio_part_cfg_all[partition]; - u32 pff = ioread32(&stdev->mmio_part_cfg[partition].vep_pff_inst_id); + u32 pff = ioread32(&part_cfg->vep_pff_inst_id) & 0xFF; u32 linksta = ioread32(&stdev->mmio_pff_csr[pff].pci_cap_region[13]); if (speed) @@ -840,7 +842,6 @@ static int switchtec_ntb_init_sndev(struct switchtec_ntb *sndev) u64 tpart_vec; int self; u64 part_map; - int bit; sndev->ntb.pdev = sndev->stdev->pdev; sndev->ntb.topo = NTB_TOPO_SWITCH; @@ -859,31 +860,31 @@ static int switchtec_ntb_init_sndev(struct switchtec_ntb *sndev) tpart_vec |= ioread32(&sndev->mmio_ntb->ntp_info[self].target_part_low); part_map = ioread64(&sndev->mmio_ntb->ep_map); + tpart_vec &= part_map; part_map &= ~(1 << sndev->self_partition); - if (!ffs(tpart_vec)) { + if (!tpart_vec) { if (sndev->stdev->partition_count != 2) { dev_err(&sndev->stdev->dev, "ntb target partition not defined\n"); return -ENODEV; } - bit = ffs(part_map); - if (!bit) { + if (!part_map) { dev_err(&sndev->stdev->dev, "peer partition is not NT partition\n"); return -ENODEV; } - sndev->peer_partition = bit - 1; + sndev->peer_partition = __ffs64(part_map); } else { - if (ffs(tpart_vec) != fls(tpart_vec)) { + if (__ffs64(tpart_vec) != (fls64(tpart_vec) - 1)) { dev_err(&sndev->stdev->dev, "ntb driver only supports 1 pair of 1-1 ntb mapping\n"); return -ENODEV; } - sndev->peer_partition = ffs(tpart_vec) - 1; + sndev->peer_partition = __ffs64(tpart_vec); if (!(part_map & (1ULL << sndev->peer_partition))) { dev_err(&sndev->stdev->dev, "ntb target partition is not NT partition\n"); @@ -954,7 +955,7 @@ static int config_req_id_table(struct switchtec_ntb *sndev, u32 error; u32 proxy_id; - if (ioread32(&mmio_ctrl->req_id_table_size) < count) { + if (ioread16(&mmio_ctrl->req_id_table_size) < count) { dev_err(&sndev->stdev->dev, "Not enough requester IDs available.\n"); return -EFAULT; @@ -966,9 +967,6 @@ static int config_req_id_table(struct switchtec_ntb *sndev, if (rc) return rc; - iowrite32(NTB_PART_CTRL_ID_PROT_DIS, - &mmio_ctrl->partition_ctrl); - for (i = 0; i < count; i++) { iowrite32(req_ids[i] << 16 | NTB_CTRL_REQ_ID_EN, &mmio_ctrl->req_id_table[i]); @@ -1090,7 +1088,7 @@ static int crosslink_enum_partition(struct switchtec_ntb *sndev, { struct part_cfg_regs __iomem *part_cfg = &sndev->stdev->mmio_part_cfg_all[sndev->peer_partition]; - u32 pff = ioread32(&part_cfg->vep_pff_inst_id); + u32 pff = ioread32(&part_cfg->vep_pff_inst_id) & 0xFF; struct pff_csr_regs __iomem *mmio_pff = &sndev->stdev->mmio_pff_csr[pff]; const u64 bar_space = 0x1000000000LL; diff --git a/drivers/ntb/msi.c b/drivers/ntb/msi.c index 2818bfcf4031..dd683cb58d09 100644 --- a/drivers/ntb/msi.c +++ b/drivers/ntb/msi.c @@ -262,8 +262,9 @@ static int ntbm_msi_setup_callback(struct ntb_dev *ntb, struct msi_desc *entry, * @handler: Function to be called when the IRQ occurs * @thread_fn: Function to be called in a threaded interrupt context. NULL * for clients which handle everything in @handler - * @devname: An ascii name for the claiming device, dev_name(dev) if NULL + * @name: An ascii name for the claiming device, dev_name(dev) if NULL * @dev_id: A cookie passed back to the handler function + * @msi_desc: MSI descriptor data which triggers the interrupt * * This function assigns an interrupt handler to an unused * MSI interrupt and returns the descriptor used to trigger diff --git a/drivers/nvdimm/virtio_pmem.c b/drivers/nvdimm/virtio_pmem.c index 726c7354d465..995b6cdc67ed 100644 --- a/drivers/nvdimm/virtio_pmem.c +++ b/drivers/nvdimm/virtio_pmem.c @@ -105,7 +105,7 @@ static void virtio_pmem_remove(struct virtio_device *vdev) nvdimm_bus_unregister(nvdimm_bus); vdev->config->del_vqs(vdev); - vdev->config->reset(vdev); + virtio_reset_device(vdev); } static struct virtio_driver virtio_pmem_driver = { diff --git a/drivers/remoteproc/Kconfig b/drivers/remoteproc/Kconfig index f2e961f998ca..3ddd426fc969 100644 --- a/drivers/remoteproc/Kconfig +++ b/drivers/remoteproc/Kconfig @@ -283,6 +283,17 @@ config QCOM_WCNSS_PIL verified and booted with the help of the Peripheral Authentication System (PAS) in TrustZone. +config RCAR_REMOTEPROC + tristate "Renesas R-Car Gen3 remoteproc support" + depends on ARCH_RENESAS || COMPILE_TEST + help + Say y here to support R-Car realtime processor via the + remote processor framework. An ELF firmware can be loaded + thanks to sysfs remoteproc entries. The remote processor + can be started and stopped. + This can be either built-in or a loadable module. + If compiled as module (M), the module name is rcar_rproc. + config ST_REMOTEPROC tristate "ST remoteproc support" depends on ARCH_STI diff --git a/drivers/remoteproc/Makefile b/drivers/remoteproc/Makefile index 0ac256b6c977..5478c7cb9e07 100644 --- a/drivers/remoteproc/Makefile +++ b/drivers/remoteproc/Makefile @@ -32,6 +32,7 @@ obj-$(CONFIG_QCOM_SYSMON) += qcom_sysmon.o obj-$(CONFIG_QCOM_WCNSS_PIL) += qcom_wcnss_pil.o qcom_wcnss_pil-y += qcom_wcnss.o qcom_wcnss_pil-y += qcom_wcnss_iris.o +obj-$(CONFIG_RCAR_REMOTEPROC) += rcar_rproc.o obj-$(CONFIG_ST_REMOTEPROC) += st_remoteproc.o obj-$(CONFIG_ST_SLIM_REMOTEPROC) += st_slim_rproc.o obj-$(CONFIG_STM32_RPROC) += stm32_rproc.o diff --git a/drivers/remoteproc/imx_rproc.c b/drivers/remoteproc/imx_rproc.c index ff8170dbbc3c..7a096f1891e6 100644 --- a/drivers/remoteproc/imx_rproc.c +++ b/drivers/remoteproc/imx_rproc.c @@ -34,7 +34,8 @@ #define IMX7D_M4_START (IMX7D_ENABLE_M4 | IMX7D_SW_M4P_RST \ | IMX7D_SW_M4C_RST) -#define IMX7D_M4_STOP IMX7D_SW_M4C_NON_SCLR_RST +#define IMX7D_M4_STOP (IMX7D_ENABLE_M4 | IMX7D_SW_M4C_RST | \ + IMX7D_SW_M4C_NON_SCLR_RST) /* Address: 0x020D8000 */ #define IMX6SX_SRC_SCR 0x00 @@ -45,7 +46,8 @@ #define IMX6SX_M4_START (IMX6SX_ENABLE_M4 | IMX6SX_SW_M4P_RST \ | IMX6SX_SW_M4C_RST) -#define IMX6SX_M4_STOP IMX6SX_SW_M4C_NON_SCLR_RST +#define IMX6SX_M4_STOP (IMX6SX_ENABLE_M4 | IMX6SX_SW_M4C_RST | \ + IMX6SX_SW_M4C_NON_SCLR_RST) #define IMX6SX_M4_RST_MASK (IMX6SX_ENABLE_M4 | IMX6SX_SW_M4P_RST \ | IMX6SX_SW_M4C_NON_SCLR_RST \ | IMX6SX_SW_M4C_RST) @@ -684,7 +686,7 @@ static int imx_rproc_detect_mode(struct imx_rproc *priv) return ret; } - if (!(val & dcfg->src_stop)) + if ((val & dcfg->src_mask) != dcfg->src_stop) priv->rproc->state = RPROC_DETACHED; return 0; @@ -804,6 +806,7 @@ static int imx_rproc_remove(struct platform_device *pdev) clk_disable_unprepare(priv->clk); rproc_del(rproc); imx_rproc_free_mbox(rproc); + destroy_workqueue(priv->workqueue); rproc_free(rproc); return 0; diff --git a/drivers/remoteproc/ingenic_rproc.c b/drivers/remoteproc/ingenic_rproc.c index a356738160a4..9902cce28692 100644 --- a/drivers/remoteproc/ingenic_rproc.c +++ b/drivers/remoteproc/ingenic_rproc.c @@ -218,14 +218,13 @@ static int ingenic_rproc_probe(struct platform_device *pdev) if (vpu->irq < 0) return vpu->irq; - ret = devm_request_irq(dev, vpu->irq, vpu_interrupt, 0, "VPU", rproc); + ret = devm_request_irq(dev, vpu->irq, vpu_interrupt, IRQF_NO_AUTOEN, + "VPU", rproc); if (ret < 0) { dev_err(dev, "Failed to request IRQ\n"); return ret; } - disable_irq(vpu->irq); - ret = devm_rproc_add(dev, rproc); if (ret) { dev_err(dev, "Failed to register remote processor\n"); diff --git a/drivers/remoteproc/mtk_scp_ipi.c b/drivers/remoteproc/mtk_scp_ipi.c index 6dc955ecab80..00f041ebcde6 100644 --- a/drivers/remoteproc/mtk_scp_ipi.c +++ b/drivers/remoteproc/mtk_scp_ipi.c @@ -23,7 +23,7 @@ * * Register an ipi function to receive ipi interrupt from SCP. * - * Returns 0 if ipi registers successfully, -error on error. + * Return: 0 if ipi registers successfully, -error on error. */ int scp_ipi_register(struct mtk_scp *scp, u32 id, @@ -150,7 +150,7 @@ EXPORT_SYMBOL_GPL(scp_ipi_unlock); * When the processing completes, IPI handler registered * by scp_ipi_register will be called in interrupt context. * - * Returns 0 if sending data successfully, -error on error. + * Return: 0 if sending data successfully, -error on error. **/ int scp_ipi_send(struct mtk_scp *scp, u32 id, void *buf, unsigned int len, unsigned int wait) diff --git a/drivers/remoteproc/qcom_pil_info.c b/drivers/remoteproc/qcom_pil_info.c index 7c007dd7b200..aca21560e20b 100644 --- a/drivers/remoteproc/qcom_pil_info.c +++ b/drivers/remoteproc/qcom_pil_info.c @@ -104,7 +104,7 @@ int qcom_pil_info_store(const char *image, phys_addr_t base, size_t size) return -ENOMEM; found_unused: - memcpy_toio(entry, image, PIL_RELOC_NAME_LEN); + memcpy_toio(entry, image, strnlen(image, PIL_RELOC_NAME_LEN)); found_existing: /* Use two writel() as base is only aligned to 4 bytes on odd entries */ writel(base, entry + PIL_RELOC_NAME_LEN); diff --git a/drivers/remoteproc/qcom_q6v5_pas.c b/drivers/remoteproc/qcom_q6v5_pas.c index 03857dc9cdc1..184bb7cdf95a 100644 --- a/drivers/remoteproc/qcom_q6v5_pas.c +++ b/drivers/remoteproc/qcom_q6v5_pas.c @@ -524,6 +524,23 @@ static const struct adsp_data sdm845_adsp_resource_init = { .ssctl_id = 0x14, }; +static const struct adsp_data sm6350_adsp_resource = { + .crash_reason_smem = 423, + .firmware_name = "adsp.mdt", + .pas_id = 1, + .has_aggre2_clk = false, + .auto_boot = true, + .proxy_pd_names = (char*[]){ + "lcx", + "lmx", + NULL + }, + .load_state = "adsp", + .ssr_name = "lpass", + .sysmon_name = "adsp", + .ssctl_id = 0x14, +}; + static const struct adsp_data sm8150_adsp_resource = { .crash_reason_smem = 423, .firmware_name = "adsp.mdt", @@ -612,6 +629,23 @@ static const struct adsp_data sdm845_cdsp_resource_init = { .ssctl_id = 0x17, }; +static const struct adsp_data sm6350_cdsp_resource = { + .crash_reason_smem = 601, + .firmware_name = "cdsp.mdt", + .pas_id = 18, + .has_aggre2_clk = false, + .auto_boot = true, + .proxy_pd_names = (char*[]){ + "cx", + "mx", + NULL + }, + .load_state = "cdsp", + .ssr_name = "cdsp", + .sysmon_name = "cdsp", + .ssctl_id = 0x17, +}; + static const struct adsp_data sm8150_cdsp_resource = { .crash_reason_smem = 601, .firmware_name = "cdsp.mdt", @@ -652,6 +686,7 @@ static const struct adsp_data sm8350_cdsp_resource = { .auto_boot = true, .proxy_pd_names = (char*[]){ "cx", + "mxc", NULL }, .load_state = "cdsp", @@ -804,6 +839,9 @@ static const struct of_device_id adsp_of_match[] = { { .compatible = "qcom,sdm845-adsp-pas", .data = &sdm845_adsp_resource_init}, { .compatible = "qcom,sdm845-cdsp-pas", .data = &sdm845_cdsp_resource_init}, { .compatible = "qcom,sdx55-mpss-pas", .data = &sdx55_mpss_resource}, + { .compatible = "qcom,sm6350-adsp-pas", .data = &sm6350_adsp_resource}, + { .compatible = "qcom,sm6350-cdsp-pas", .data = &sm6350_cdsp_resource}, + { .compatible = "qcom,sm6350-mpss-pas", .data = &mpss_resource_init}, { .compatible = "qcom,sm8150-adsp-pas", .data = &sm8150_adsp_resource}, { .compatible = "qcom,sm8150-cdsp-pas", .data = &sm8150_cdsp_resource}, { .compatible = "qcom,sm8150-mpss-pas", .data = &mpss_resource_init}, diff --git a/drivers/remoteproc/rcar_rproc.c b/drivers/remoteproc/rcar_rproc.c new file mode 100644 index 000000000000..aa86154109c7 --- /dev/null +++ b/drivers/remoteproc/rcar_rproc.c @@ -0,0 +1,224 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) IoT.bzh 2021 + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "remoteproc_internal.h" + +struct rcar_rproc { + struct reset_control *rst; +}; + +static int rcar_rproc_mem_alloc(struct rproc *rproc, + struct rproc_mem_entry *mem) +{ + struct device *dev = &rproc->dev; + void *va; + + dev_dbg(dev, "map memory: %pa+%zx\n", &mem->dma, mem->len); + va = ioremap_wc(mem->dma, mem->len); + if (!va) { + dev_err(dev, "Unable to map memory region: %pa+%zx\n", + &mem->dma, mem->len); + return -ENOMEM; + } + + /* Update memory entry va */ + mem->va = va; + + return 0; +} + +static int rcar_rproc_mem_release(struct rproc *rproc, + struct rproc_mem_entry *mem) +{ + dev_dbg(&rproc->dev, "unmap memory: %pa\n", &mem->dma); + iounmap(mem->va); + + return 0; +} + +static int rcar_rproc_prepare(struct rproc *rproc) +{ + struct device *dev = rproc->dev.parent; + struct device_node *np = dev->of_node; + struct of_phandle_iterator it; + struct rproc_mem_entry *mem; + struct reserved_mem *rmem; + u32 da; + + /* Register associated reserved memory regions */ + of_phandle_iterator_init(&it, np, "memory-region", NULL, 0); + while (of_phandle_iterator_next(&it) == 0) { + + rmem = of_reserved_mem_lookup(it.node); + if (!rmem) { + dev_err(&rproc->dev, + "unable to acquire memory-region\n"); + return -EINVAL; + } + + if (rmem->base > U32_MAX) + return -EINVAL; + + /* No need to translate pa to da, R-Car use same map */ + da = rmem->base; + mem = rproc_mem_entry_init(dev, NULL, + rmem->base, + rmem->size, da, + rcar_rproc_mem_alloc, + rcar_rproc_mem_release, + it.node->name); + + if (!mem) + return -ENOMEM; + + rproc_add_carveout(rproc, mem); + } + + return 0; +} + +static int rcar_rproc_parse_fw(struct rproc *rproc, const struct firmware *fw) +{ + int ret; + + ret = rproc_elf_load_rsc_table(rproc, fw); + if (ret) + dev_info(&rproc->dev, "No resource table in elf\n"); + + return 0; +} + +static int rcar_rproc_start(struct rproc *rproc) +{ + struct rcar_rproc *priv = rproc->priv; + int err; + + if (!rproc->bootaddr) + return -EINVAL; + + err = rcar_rst_set_rproc_boot_addr(rproc->bootaddr); + if (err) { + dev_err(&rproc->dev, "failed to set rproc boot addr\n"); + return err; + } + + err = reset_control_deassert(priv->rst); + if (err) + dev_err(&rproc->dev, "failed to deassert reset\n"); + + return err; +} + +static int rcar_rproc_stop(struct rproc *rproc) +{ + struct rcar_rproc *priv = rproc->priv; + int err; + + err = reset_control_assert(priv->rst); + if (err) + dev_err(&rproc->dev, "failed to assert reset\n"); + + return err; +} + +static struct rproc_ops rcar_rproc_ops = { + .prepare = rcar_rproc_prepare, + .start = rcar_rproc_start, + .stop = rcar_rproc_stop, + .load = rproc_elf_load_segments, + .parse_fw = rcar_rproc_parse_fw, + .find_loaded_rsc_table = rproc_elf_find_loaded_rsc_table, + .sanity_check = rproc_elf_sanity_check, + .get_boot_addr = rproc_elf_get_boot_addr, + +}; + +static int rcar_rproc_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct device_node *np = dev->of_node; + struct rcar_rproc *priv; + struct rproc *rproc; + int ret; + + rproc = devm_rproc_alloc(dev, np->name, &rcar_rproc_ops, + NULL, sizeof(*priv)); + if (!rproc) + return -ENOMEM; + + priv = rproc->priv; + + priv->rst = devm_reset_control_get_exclusive(dev, NULL); + if (IS_ERR(priv->rst)) { + ret = PTR_ERR(priv->rst); + dev_err_probe(dev, ret, "fail to acquire rproc reset\n"); + return ret; + } + + pm_runtime_enable(dev); + ret = pm_runtime_resume_and_get(dev); + if (ret) { + dev_err(dev, "failed to power up\n"); + return ret; + } + + dev_set_drvdata(dev, rproc); + + /* Manually start the rproc */ + rproc->auto_boot = false; + + ret = devm_rproc_add(dev, rproc); + if (ret) { + dev_err(dev, "rproc_add failed\n"); + goto pm_disable; + } + + return 0; + +pm_disable: + pm_runtime_disable(dev); + + return ret; +} + +static int rcar_rproc_remove(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + + pm_runtime_disable(dev); + + return 0; +} + +static const struct of_device_id rcar_rproc_of_match[] = { + { .compatible = "renesas,rcar-cr7" }, + {}, +}; + +MODULE_DEVICE_TABLE(of, rcar_rproc_of_match); + +static struct platform_driver rcar_rproc_driver = { + .probe = rcar_rproc_probe, + .remove = rcar_rproc_remove, + .driver = { + .name = "rcar-rproc", + .of_match_table = rcar_rproc_of_match, + }, +}; + +module_platform_driver(rcar_rproc_driver); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("Renesas R-Car Gen3 remote processor control driver"); +MODULE_AUTHOR("Julien Massot "); diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index 775df165eb45..69f51acf235e 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -577,8 +577,8 @@ static int rproc_handle_vdev(struct rproc *rproc, void *ptr, dma_get_mask(rproc->dev.parent)); if (ret) { dev_warn(dev, - "Failed to set DMA mask %llx. Trying to continue... %x\n", - dma_get_mask(rproc->dev.parent), ret); + "Failed to set DMA mask %llx. Trying to continue... (%pe)\n", + dma_get_mask(rproc->dev.parent), ERR_PTR(ret)); } /* parse the vrings */ diff --git a/drivers/remoteproc/remoteproc_coredump.c b/drivers/remoteproc/remoteproc_coredump.c index c892f433a323..4b093420d98a 100644 --- a/drivers/remoteproc/remoteproc_coredump.c +++ b/drivers/remoteproc/remoteproc_coredump.c @@ -166,7 +166,7 @@ static void rproc_copy_segment(struct rproc *rproc, void *dest, memset(dest, 0xff, size); } else { if (is_iomem) - memcpy_fromio(dest, ptr, size); + memcpy_fromio(dest, (void const __iomem *)ptr, size); else memcpy(dest, ptr, size); } diff --git a/drivers/remoteproc/st_slim_rproc.c b/drivers/remoteproc/st_slim_rproc.c index 22096adc1ad3..4ed9467897e5 100644 --- a/drivers/remoteproc/st_slim_rproc.c +++ b/drivers/remoteproc/st_slim_rproc.c @@ -216,7 +216,7 @@ static const struct rproc_ops slim_rproc_ops = { * obtains and enables any clocks required by the SLIM core and also * ioremaps the various IO. * - * Returns st_slim_rproc pointer or PTR_ERR() on error. + * Return: st_slim_rproc pointer or PTR_ERR() on error. */ struct st_slim_rproc *st_slim_rproc_alloc(struct platform_device *pdev, diff --git a/drivers/remoteproc/stm32_rproc.c b/drivers/remoteproc/stm32_rproc.c index b643efcf995a..7d782ed9e589 100644 --- a/drivers/remoteproc/stm32_rproc.c +++ b/drivers/remoteproc/stm32_rproc.c @@ -494,7 +494,7 @@ static int stm32_rproc_stop(struct rproc *rproc) int err, idx; /* request shutdown of the remote processor */ - if (rproc->state != RPROC_OFFLINE) { + if (rproc->state != RPROC_OFFLINE && rproc->state != RPROC_CRASHED) { idx = stm32_rproc_mbox_idx(rproc, STM32_MBX_SHUTDOWN); if (idx >= 0 && ddata->mb[idx].chan) { err = mbox_send_message(ddata->mb[idx].chan, "detach"); diff --git a/drivers/remoteproc/ti_k3_dsp_remoteproc.c b/drivers/remoteproc/ti_k3_dsp_remoteproc.c index c352fa277c8d..939c5d90b562 100644 --- a/drivers/remoteproc/ti_k3_dsp_remoteproc.c +++ b/drivers/remoteproc/ti_k3_dsp_remoteproc.c @@ -767,6 +767,7 @@ static const struct k3_dsp_dev_data c71_data = { static const struct of_device_id k3_dsp_of_match[] = { { .compatible = "ti,j721e-c66-dsp", .data = &c66_data, }, { .compatible = "ti,j721e-c71-dsp", .data = &c71_data, }, + { .compatible = "ti,j721s2-c71-dsp", .data = &c71_data, }, { /* sentinel */ }, }; MODULE_DEVICE_TABLE(of, k3_dsp_of_match); diff --git a/drivers/remoteproc/ti_k3_r5_remoteproc.c b/drivers/remoteproc/ti_k3_r5_remoteproc.c index 6499302d00c3..969531c05b13 100644 --- a/drivers/remoteproc/ti_k3_r5_remoteproc.c +++ b/drivers/remoteproc/ti_k3_r5_remoteproc.c @@ -1535,7 +1535,7 @@ static const struct k3_r5_soc_data am65_j721e_soc_data = { .single_cpu_mode = false, }; -static const struct k3_r5_soc_data j7200_soc_data = { +static const struct k3_r5_soc_data j7200_j721s2_soc_data = { .tcm_is_double = true, .tcm_ecc_autoinit = true, .single_cpu_mode = false, @@ -1550,8 +1550,9 @@ static const struct k3_r5_soc_data am64_soc_data = { static const struct of_device_id k3_r5_of_match[] = { { .compatible = "ti,am654-r5fss", .data = &am65_j721e_soc_data, }, { .compatible = "ti,j721e-r5fss", .data = &am65_j721e_soc_data, }, - { .compatible = "ti,j7200-r5fss", .data = &j7200_soc_data, }, + { .compatible = "ti,j7200-r5fss", .data = &j7200_j721s2_soc_data, }, { .compatible = "ti,am64-r5fss", .data = &am64_soc_data, }, + { .compatible = "ti,j721s2-r5fss", .data = &j7200_j721s2_soc_data, }, { /* sentinel */ }, }; MODULE_DEVICE_TABLE(of, k3_r5_of_match); diff --git a/drivers/rpmsg/qcom_glink_native.c b/drivers/rpmsg/qcom_glink_native.c index 3f377a795b33..1030cfa80e04 100644 --- a/drivers/rpmsg/qcom_glink_native.c +++ b/drivers/rpmsg/qcom_glink_native.c @@ -427,7 +427,7 @@ static void qcom_glink_handle_intent_req_ack(struct qcom_glink *glink, * Allocates a local channel id and sends a RPM_CMD_OPEN message to the remote. * Will return with refcount held, regardless of outcome. * - * Returns 0 on success, negative errno otherwise. + * Return: 0 on success, negative errno otherwise. */ static int qcom_glink_send_open_req(struct qcom_glink *glink, struct glink_channel *channel) diff --git a/drivers/rpmsg/qcom_smd.c b/drivers/rpmsg/qcom_smd.c index 8da1b5cb31b3..540e027f08c4 100644 --- a/drivers/rpmsg/qcom_smd.c +++ b/drivers/rpmsg/qcom_smd.c @@ -1467,7 +1467,7 @@ ATTRIBUTE_GROUPS(qcom_smd_edge); * @parent: parent device for the edge * @node: device_node describing the edge * - * Returns an edge reference, or negative ERR_PTR() on failure. + * Return: an edge reference, or negative ERR_PTR() on failure. */ struct qcom_smd_edge *qcom_smd_register_edge(struct device *parent, struct device_node *node) diff --git a/drivers/rpmsg/rpmsg_char.c b/drivers/rpmsg/rpmsg_char.c index b5907b80727c..d6214cb66026 100644 --- a/drivers/rpmsg/rpmsg_char.c +++ b/drivers/rpmsg/rpmsg_char.c @@ -9,6 +9,9 @@ * Based on rpmsg performance statistics driver by Michal Simek, which in turn * was based on TI & Google OMX rpmsg driver. */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include #include #include @@ -550,7 +553,7 @@ static int rpmsg_chrdev_init(void) ret = alloc_chrdev_region(&rpmsg_major, 0, RPMSG_DEV_MAX, "rpmsg"); if (ret < 0) { - pr_err("rpmsg: failed to allocate char dev region\n"); + pr_err("failed to allocate char dev region\n"); return ret; } @@ -563,7 +566,7 @@ static int rpmsg_chrdev_init(void) ret = register_rpmsg_driver(&rpmsg_chrdev_driver); if (ret < 0) { - pr_err("rpmsgchr: failed to register rpmsg driver\n"); + pr_err("failed to register rpmsg driver\n"); class_destroy(rpmsg_class); unregister_chrdev_region(rpmsg_major, RPMSG_DEV_MAX); } diff --git a/drivers/rpmsg/rpmsg_core.c b/drivers/rpmsg/rpmsg_core.c index d3eb60059ef1..d9e612f4f0f2 100644 --- a/drivers/rpmsg/rpmsg_core.c +++ b/drivers/rpmsg/rpmsg_core.c @@ -26,7 +26,7 @@ * @rpdev: rpmsg device * @chinfo: channel_info to bind * - * Returns a pointer to the new rpmsg device on success, or NULL on error. + * Return: a pointer to the new rpmsg device on success, or NULL on error. */ struct rpmsg_device *rpmsg_create_channel(struct rpmsg_device *rpdev, struct rpmsg_channel_info *chinfo) @@ -48,7 +48,7 @@ EXPORT_SYMBOL(rpmsg_create_channel); * @rpdev: rpmsg device * @chinfo: channel_info to bind * - * Returns 0 on success or an appropriate error value. + * Return: 0 on success or an appropriate error value. */ int rpmsg_release_channel(struct rpmsg_device *rpdev, struct rpmsg_channel_info *chinfo) @@ -102,7 +102,7 @@ EXPORT_SYMBOL(rpmsg_release_channel); * dynamically assign them an available rpmsg address (drivers should have * a very good reason why not to always use RPMSG_ADDR_ANY here). * - * Returns a pointer to the endpoint on success, or NULL on error. + * Return: a pointer to the endpoint on success, or NULL on error. */ struct rpmsg_endpoint *rpmsg_create_ept(struct rpmsg_device *rpdev, rpmsg_rx_cb_t cb, void *priv, @@ -146,7 +146,7 @@ EXPORT_SYMBOL(rpmsg_destroy_ept); * * Can only be called from process context (for now). * - * Returns 0 on success and an appropriate error value on failure. + * Return: 0 on success and an appropriate error value on failure. */ int rpmsg_send(struct rpmsg_endpoint *ept, void *data, int len) { @@ -175,7 +175,7 @@ EXPORT_SYMBOL(rpmsg_send); * * Can only be called from process context (for now). * - * Returns 0 on success and an appropriate error value on failure. + * Return: 0 on success and an appropriate error value on failure. */ int rpmsg_sendto(struct rpmsg_endpoint *ept, void *data, int len, u32 dst) { @@ -206,7 +206,7 @@ EXPORT_SYMBOL(rpmsg_sendto); * * Can only be called from process context (for now). * - * Returns 0 on success and an appropriate error value on failure. + * Return: 0 on success and an appropriate error value on failure. */ int rpmsg_send_offchannel(struct rpmsg_endpoint *ept, u32 src, u32 dst, void *data, int len) @@ -235,7 +235,7 @@ EXPORT_SYMBOL(rpmsg_send_offchannel); * * Can only be called from process context (for now). * - * Returns 0 on success and an appropriate error value on failure. + * Return: 0 on success and an appropriate error value on failure. */ int rpmsg_trysend(struct rpmsg_endpoint *ept, void *data, int len) { @@ -263,7 +263,7 @@ EXPORT_SYMBOL(rpmsg_trysend); * * Can only be called from process context (for now). * - * Returns 0 on success and an appropriate error value on failure. + * Return: 0 on success and an appropriate error value on failure. */ int rpmsg_trysendto(struct rpmsg_endpoint *ept, void *data, int len, u32 dst) { @@ -282,7 +282,7 @@ EXPORT_SYMBOL(rpmsg_trysendto); * @filp: file for poll_wait() * @wait: poll_table for poll_wait() * - * Returns mask representing the current state of the endpoint's send buffers + * Return: mask representing the current state of the endpoint's send buffers */ __poll_t rpmsg_poll(struct rpmsg_endpoint *ept, struct file *filp, poll_table *wait) @@ -313,7 +313,7 @@ EXPORT_SYMBOL(rpmsg_poll); * * Can only be called from process context (for now). * - * Returns 0 on success and an appropriate error value on failure. + * Return: 0 on success and an appropriate error value on failure. */ int rpmsg_trysend_offchannel(struct rpmsg_endpoint *ept, u32 src, u32 dst, void *data, int len) @@ -540,13 +540,25 @@ static int rpmsg_dev_probe(struct device *dev) err = rpdrv->probe(rpdev); if (err) { dev_err(dev, "%s: failed: %d\n", __func__, err); - if (ept) - rpmsg_destroy_ept(ept); - goto out; + goto destroy_ept; } - if (ept && rpdev->ops->announce_create) + if (ept && rpdev->ops->announce_create) { err = rpdev->ops->announce_create(rpdev); + if (err) { + dev_err(dev, "failed to announce creation\n"); + goto remove_rpdev; + } + } + + return 0; + +remove_rpdev: + if (rpdrv->remove) + rpdrv->remove(rpdev); +destroy_ept: + if (ept) + rpmsg_destroy_ept(ept); out: return err; } @@ -623,7 +635,7 @@ EXPORT_SYMBOL(rpmsg_unregister_device); * @rpdrv: pointer to a struct rpmsg_driver * @owner: owning module/driver * - * Returns 0 on success, and an appropriate error value on failure. + * Return: 0 on success, and an appropriate error value on failure. */ int __register_rpmsg_driver(struct rpmsg_driver *rpdrv, struct module *owner) { @@ -637,7 +649,7 @@ EXPORT_SYMBOL(__register_rpmsg_driver); * unregister_rpmsg_driver() - unregister an rpmsg driver from the rpmsg bus * @rpdrv: pointer to a struct rpmsg_driver * - * Returns 0 on success, and an appropriate error value on failure. + * Return: 0 on success, and an appropriate error value on failure. */ void unregister_rpmsg_driver(struct rpmsg_driver *rpdrv) { diff --git a/drivers/rpmsg/virtio_rpmsg_bus.c b/drivers/rpmsg/virtio_rpmsg_bus.c index 9c112aa65040..ac764e04c898 100644 --- a/drivers/rpmsg/virtio_rpmsg_bus.c +++ b/drivers/rpmsg/virtio_rpmsg_bus.c @@ -547,7 +547,7 @@ static void rpmsg_downref_sleepers(struct virtproc_info *vrp) * should use the appropriate rpmsg_{try}send{to, _offchannel} API * (see include/linux/rpmsg.h). * - * Returns 0 on success and an appropriate error value on failure. + * Return: 0 on success and an appropriate error value on failure. */ static int rpmsg_send_offchannel_raw(struct rpmsg_device *rpdev, u32 src, u32 dst, @@ -1024,7 +1024,7 @@ static void rpmsg_remove(struct virtio_device *vdev) size_t total_buf_space = vrp->num_bufs * vrp->buf_size; int ret; - vdev->config->reset(vdev); + virtio_reset_device(vdev); ret = device_for_each_child(&vdev->dev, NULL, rpmsg_remove_device); if (ret) diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index 65c642b24ecf..0e6110da69e7 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -778,7 +778,7 @@ static void virtscsi_init_vq(struct virtio_scsi_vq *virtscsi_vq, static void virtscsi_remove_vqs(struct virtio_device *vdev) { /* Stop all the virtqueues. */ - vdev->config->reset(vdev); + virtio_reset_device(vdev); vdev->config->del_vqs(vdev); } diff --git a/drivers/vdpa/alibaba/eni_vdpa.c b/drivers/vdpa/alibaba/eni_vdpa.c index 3f788794571a..f480d54f308c 100644 --- a/drivers/vdpa/alibaba/eni_vdpa.c +++ b/drivers/vdpa/alibaba/eni_vdpa.c @@ -58,7 +58,7 @@ static struct virtio_pci_legacy_device *vdpa_to_ldev(struct vdpa_device *vdpa) return &eni_vdpa->ldev; } -static u64 eni_vdpa_get_features(struct vdpa_device *vdpa) +static u64 eni_vdpa_get_device_features(struct vdpa_device *vdpa) { struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa); u64 features = vp_legacy_get_features(ldev); @@ -69,7 +69,7 @@ static u64 eni_vdpa_get_features(struct vdpa_device *vdpa) return features; } -static int eni_vdpa_set_features(struct vdpa_device *vdpa, u64 features) +static int eni_vdpa_set_driver_features(struct vdpa_device *vdpa, u64 features) { struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa); @@ -84,6 +84,13 @@ static int eni_vdpa_set_features(struct vdpa_device *vdpa, u64 features) return 0; } +static u64 eni_vdpa_get_driver_features(struct vdpa_device *vdpa) +{ + struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa); + + return vp_legacy_get_driver_features(ldev); +} + static u8 eni_vdpa_get_status(struct vdpa_device *vdpa) { struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa); @@ -401,8 +408,9 @@ static void eni_vdpa_set_config_cb(struct vdpa_device *vdpa, } static const struct vdpa_config_ops eni_vdpa_ops = { - .get_features = eni_vdpa_get_features, - .set_features = eni_vdpa_set_features, + .get_device_features = eni_vdpa_get_device_features, + .set_driver_features = eni_vdpa_set_driver_features, + .get_driver_features = eni_vdpa_get_driver_features, .get_status = eni_vdpa_get_status, .set_status = eni_vdpa_set_status, .reset = eni_vdpa_reset, @@ -450,11 +458,6 @@ static u16 eni_vdpa_get_num_queues(struct eni_vdpa *eni_vdpa) return num; } -static void eni_vdpa_free_irq_vectors(void *data) -{ - pci_free_irq_vectors(data); -} - static int eni_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct device *dev = &pdev->dev; @@ -488,13 +491,6 @@ static int eni_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id) eni_vdpa->vdpa.dma_dev = &pdev->dev; eni_vdpa->queues = eni_vdpa_get_num_queues(eni_vdpa); - ret = devm_add_action_or_reset(dev, eni_vdpa_free_irq_vectors, pdev); - if (ret) { - ENI_ERR(pdev, - "failed for adding devres for freeing irq vectors\n"); - goto err; - } - eni_vdpa->vring = devm_kcalloc(&pdev->dev, eni_vdpa->queues, sizeof(*eni_vdpa->vring), GFP_KERNEL); diff --git a/drivers/vdpa/ifcvf/ifcvf_base.c b/drivers/vdpa/ifcvf/ifcvf_base.c index 2808f1ba9f7b..7d41dfe48ade 100644 --- a/drivers/vdpa/ifcvf/ifcvf_base.c +++ b/drivers/vdpa/ifcvf/ifcvf_base.c @@ -143,8 +143,8 @@ int ifcvf_init_hw(struct ifcvf_hw *hw, struct pci_dev *pdev) IFCVF_DBG(pdev, "hw->isr = %p\n", hw->isr); break; case VIRTIO_PCI_CAP_DEVICE_CFG: - hw->net_cfg = get_cap_addr(hw, &cap); - IFCVF_DBG(pdev, "hw->net_cfg = %p\n", hw->net_cfg); + hw->dev_cfg = get_cap_addr(hw, &cap); + IFCVF_DBG(pdev, "hw->dev_cfg = %p\n", hw->dev_cfg); break; } @@ -153,7 +153,7 @@ next: } if (hw->common_cfg == NULL || hw->notify_base == NULL || - hw->isr == NULL || hw->net_cfg == NULL) { + hw->isr == NULL || hw->dev_cfg == NULL) { IFCVF_ERR(pdev, "Incomplete PCI capabilities\n"); return -EIO; } @@ -174,7 +174,7 @@ next: IFCVF_DBG(pdev, "PCI capability mapping: common cfg: %p, notify base: %p\n, isr cfg: %p, device cfg: %p, multiplier: %u\n", hw->common_cfg, hw->notify_base, hw->isr, - hw->net_cfg, hw->notify_off_multiplier); + hw->dev_cfg, hw->notify_off_multiplier); return 0; } @@ -242,33 +242,54 @@ int ifcvf_verify_min_features(struct ifcvf_hw *hw, u64 features) return 0; } -void ifcvf_read_net_config(struct ifcvf_hw *hw, u64 offset, +u32 ifcvf_get_config_size(struct ifcvf_hw *hw) +{ + struct ifcvf_adapter *adapter; + u32 config_size; + + adapter = vf_to_adapter(hw); + switch (hw->dev_type) { + case VIRTIO_ID_NET: + config_size = sizeof(struct virtio_net_config); + break; + case VIRTIO_ID_BLOCK: + config_size = sizeof(struct virtio_blk_config); + break; + default: + config_size = 0; + IFCVF_ERR(adapter->pdev, "VIRTIO ID %u not supported\n", hw->dev_type); + } + + return config_size; +} + +void ifcvf_read_dev_config(struct ifcvf_hw *hw, u64 offset, void *dst, int length) { u8 old_gen, new_gen, *p; int i; - WARN_ON(offset + length > sizeof(struct virtio_net_config)); + WARN_ON(offset + length > hw->config_size); do { old_gen = ifc_ioread8(&hw->common_cfg->config_generation); p = dst; for (i = 0; i < length; i++) - *p++ = ifc_ioread8(hw->net_cfg + offset + i); + *p++ = ifc_ioread8(hw->dev_cfg + offset + i); new_gen = ifc_ioread8(&hw->common_cfg->config_generation); } while (old_gen != new_gen); } -void ifcvf_write_net_config(struct ifcvf_hw *hw, u64 offset, +void ifcvf_write_dev_config(struct ifcvf_hw *hw, u64 offset, const void *src, int length) { const u8 *p; int i; p = src; - WARN_ON(offset + length > sizeof(struct virtio_net_config)); + WARN_ON(offset + length > hw->config_size); for (i = 0; i < length; i++) - ifc_iowrite8(*p++, hw->net_cfg + offset + i); + ifc_iowrite8(*p++, hw->dev_cfg + offset + i); } static void ifcvf_set_features(struct ifcvf_hw *hw, u64 features) diff --git a/drivers/vdpa/ifcvf/ifcvf_base.h b/drivers/vdpa/ifcvf/ifcvf_base.h index 09918af3ecf8..c486873f370a 100644 --- a/drivers/vdpa/ifcvf/ifcvf_base.h +++ b/drivers/vdpa/ifcvf/ifcvf_base.h @@ -71,12 +71,14 @@ struct ifcvf_hw { u64 hw_features; u32 dev_type; struct virtio_pci_common_cfg __iomem *common_cfg; - void __iomem *net_cfg; + void __iomem *dev_cfg; struct vring_info vring[IFCVF_MAX_QUEUES]; void __iomem * const *base; char config_msix_name[256]; struct vdpa_callback config_cb; unsigned int config_irq; + /* virtio-net or virtio-blk device config size */ + u32 config_size; }; struct ifcvf_adapter { @@ -105,9 +107,9 @@ int ifcvf_init_hw(struct ifcvf_hw *hw, struct pci_dev *dev); int ifcvf_start_hw(struct ifcvf_hw *hw); void ifcvf_stop_hw(struct ifcvf_hw *hw); void ifcvf_notify_queue(struct ifcvf_hw *hw, u16 qid); -void ifcvf_read_net_config(struct ifcvf_hw *hw, u64 offset, +void ifcvf_read_dev_config(struct ifcvf_hw *hw, u64 offset, void *dst, int length); -void ifcvf_write_net_config(struct ifcvf_hw *hw, u64 offset, +void ifcvf_write_dev_config(struct ifcvf_hw *hw, u64 offset, const void *src, int length); u8 ifcvf_get_status(struct ifcvf_hw *hw); void ifcvf_set_status(struct ifcvf_hw *hw, u8 status); @@ -120,4 +122,5 @@ u16 ifcvf_get_vq_state(struct ifcvf_hw *hw, u16 qid); int ifcvf_set_vq_state(struct ifcvf_hw *hw, u16 qid, u16 num); struct ifcvf_adapter *vf_to_adapter(struct ifcvf_hw *hw); int ifcvf_probed_virtio_net(struct ifcvf_hw *hw); +u32 ifcvf_get_config_size(struct ifcvf_hw *hw); #endif /* _IFCVF_H_ */ diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c index 6dc75ca70b37..d1a6b5ab543c 100644 --- a/drivers/vdpa/ifcvf/ifcvf_main.c +++ b/drivers/vdpa/ifcvf/ifcvf_main.c @@ -169,7 +169,7 @@ static struct ifcvf_hw *vdpa_to_vf(struct vdpa_device *vdpa_dev) return &adapter->vf; } -static u64 ifcvf_vdpa_get_features(struct vdpa_device *vdpa_dev) +static u64 ifcvf_vdpa_get_device_features(struct vdpa_device *vdpa_dev) { struct ifcvf_adapter *adapter = vdpa_to_adapter(vdpa_dev); struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); @@ -187,7 +187,7 @@ static u64 ifcvf_vdpa_get_features(struct vdpa_device *vdpa_dev) return features; } -static int ifcvf_vdpa_set_features(struct vdpa_device *vdpa_dev, u64 features) +static int ifcvf_vdpa_set_driver_features(struct vdpa_device *vdpa_dev, u64 features) { struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); int ret; @@ -201,6 +201,13 @@ static int ifcvf_vdpa_set_features(struct vdpa_device *vdpa_dev, u64 features) return 0; } +static u64 ifcvf_vdpa_get_driver_features(struct vdpa_device *vdpa_dev) +{ + struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); + + return vf->req_features; +} + static u8 ifcvf_vdpa_get_status(struct vdpa_device *vdpa_dev) { struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); @@ -366,24 +373,9 @@ static u32 ifcvf_vdpa_get_vq_align(struct vdpa_device *vdpa_dev) static size_t ifcvf_vdpa_get_config_size(struct vdpa_device *vdpa_dev) { - struct ifcvf_adapter *adapter = vdpa_to_adapter(vdpa_dev); struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); - struct pci_dev *pdev = adapter->pdev; - size_t size; - switch (vf->dev_type) { - case VIRTIO_ID_NET: - size = sizeof(struct virtio_net_config); - break; - case VIRTIO_ID_BLOCK: - size = sizeof(struct virtio_blk_config); - break; - default: - size = 0; - IFCVF_ERR(pdev, "VIRTIO ID %u not supported\n", vf->dev_type); - } - - return size; + return vf->config_size; } static void ifcvf_vdpa_get_config(struct vdpa_device *vdpa_dev, @@ -392,8 +384,7 @@ static void ifcvf_vdpa_get_config(struct vdpa_device *vdpa_dev, { struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); - WARN_ON(offset + len > sizeof(struct virtio_net_config)); - ifcvf_read_net_config(vf, offset, buf, len); + ifcvf_read_dev_config(vf, offset, buf, len); } static void ifcvf_vdpa_set_config(struct vdpa_device *vdpa_dev, @@ -402,8 +393,7 @@ static void ifcvf_vdpa_set_config(struct vdpa_device *vdpa_dev, { struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); - WARN_ON(offset + len > sizeof(struct virtio_net_config)); - ifcvf_write_net_config(vf, offset, buf, len); + ifcvf_write_dev_config(vf, offset, buf, len); } static void ifcvf_vdpa_set_config_cb(struct vdpa_device *vdpa_dev, @@ -443,8 +433,9 @@ static struct vdpa_notification_area ifcvf_get_vq_notification(struct vdpa_devic * implemented set_map()/dma_map()/dma_unmap() */ static const struct vdpa_config_ops ifc_vdpa_ops = { - .get_features = ifcvf_vdpa_get_features, - .set_features = ifcvf_vdpa_set_features, + .get_device_features = ifcvf_vdpa_get_device_features, + .set_driver_features = ifcvf_vdpa_set_driver_features, + .get_driver_features = ifcvf_vdpa_get_driver_features, .get_status = ifcvf_vdpa_get_status, .set_status = ifcvf_vdpa_set_status, .reset = ifcvf_vdpa_reset, @@ -542,6 +533,7 @@ static int ifcvf_vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, vf->vring[i].irq = -EINVAL; vf->hw_features = ifcvf_get_hw_features(vf); + vf->config_size = ifcvf_get_config_size(vf); adapter->vdpa.mdev = &ifcvf_mgmt_dev->mdev; ret = _vdpa_register_device(&adapter->vdpa, vf->nr_vring); diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index cf59f7e17c6d..f648f1c54a0f 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -131,25 +131,24 @@ struct mlx5_vdpa_virtqueue { struct mlx5_vq_restore_info ri; }; -/* We will remove this limitation once mlx5_vdpa_alloc_resources() - * provides for driver space allocation - */ -#define MLX5_MAX_SUPPORTED_VQS 16 - static bool is_index_valid(struct mlx5_vdpa_dev *mvdev, u16 idx) { - if (unlikely(idx > mvdev->max_idx)) - return false; + if (!(mvdev->actual_features & BIT_ULL(VIRTIO_NET_F_MQ))) { + if (!(mvdev->actual_features & BIT_ULL(VIRTIO_NET_F_CTRL_VQ))) + return idx < 2; + else + return idx < 3; + } - return true; + return idx <= mvdev->max_idx; } struct mlx5_vdpa_net { struct mlx5_vdpa_dev mvdev; struct mlx5_vdpa_net_resources res; struct virtio_net_config config; - struct mlx5_vdpa_virtqueue vqs[MLX5_MAX_SUPPORTED_VQS]; - struct vdpa_callback event_cbs[MLX5_MAX_SUPPORTED_VQS + 1]; + struct mlx5_vdpa_virtqueue *vqs; + struct vdpa_callback *event_cbs; /* Serialize vq resources creation and destruction. This is required * since memory map might change and we need to destroy and create @@ -876,8 +875,6 @@ static int create_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtque MLX5_SET(virtio_q, vq_ctx, umem_3_id, mvq->umem3.id); MLX5_SET(virtio_q, vq_ctx, umem_3_size, mvq->umem3.size); MLX5_SET(virtio_q, vq_ctx, pd, ndev->mvdev.res.pdn); - if (MLX5_CAP_DEV_VDPA_EMULATION(ndev->mvdev.mdev, eth_frame_offload_type)) - MLX5_SET(virtio_q, vq_ctx, virtio_version_1_0, 1); err = mlx5_cmd_exec(ndev->mvdev.mdev, in, inlen, out, sizeof(out)); if (err) @@ -1218,7 +1215,7 @@ static void suspend_vqs(struct mlx5_vdpa_net *ndev) { int i; - for (i = 0; i < MLX5_MAX_SUPPORTED_VQS; i++) + for (i = 0; i < ndev->mvdev.max_vqs; i++) suspend_vq(ndev, &ndev->vqs[i]); } @@ -1244,8 +1241,14 @@ static int create_rqt(struct mlx5_vdpa_net *ndev) void *in; int i, j; int err; + int num; - max_rqt = min_t(int, MLX5_MAX_SUPPORTED_VQS / 2, + if (!(ndev->mvdev.actual_features & BIT_ULL(VIRTIO_NET_F_MQ))) + num = 1; + else + num = ndev->cur_num_vqs / 2; + + max_rqt = min_t(int, roundup_pow_of_two(num), 1 << MLX5_CAP_GEN(ndev->mvdev.mdev, log_max_rqt_size)); if (max_rqt < 1) return -EOPNOTSUPP; @@ -1261,17 +1264,10 @@ static int create_rqt(struct mlx5_vdpa_net *ndev) MLX5_SET(rqtc, rqtc, list_q_type, MLX5_RQTC_LIST_Q_TYPE_VIRTIO_NET_Q); MLX5_SET(rqtc, rqtc, rqt_max_size, max_rqt); list = MLX5_ADDR_OF(rqtc, rqtc, rq_num[0]); - for (i = 0, j = 0; j < max_rqt; j++) { - if (!ndev->vqs[j].initialized) - continue; - - if (!vq_is_tx(ndev->vqs[j].index)) { - list[i] = cpu_to_be32(ndev->vqs[j].virtq_id); - i++; - } - } - MLX5_SET(rqtc, rqtc, rqt_actual_size, i); + for (i = 0, j = 0; i < max_rqt; i++, j += 2) + list[i] = cpu_to_be32(ndev->vqs[j % (2 * num)].virtq_id); + MLX5_SET(rqtc, rqtc, rqt_actual_size, max_rqt); err = mlx5_vdpa_create_rqt(&ndev->mvdev, in, inlen, &ndev->res.rqtn); kfree(in); if (err) @@ -1292,7 +1288,7 @@ static int modify_rqt(struct mlx5_vdpa_net *ndev, int num) int i, j; int err; - max_rqt = min_t(int, ndev->cur_num_vqs / 2, + max_rqt = min_t(int, roundup_pow_of_two(ndev->cur_num_vqs / 2), 1 << MLX5_CAP_GEN(ndev->mvdev.mdev, log_max_rqt_size)); if (max_rqt < 1) return -EOPNOTSUPP; @@ -1308,16 +1304,10 @@ static int modify_rqt(struct mlx5_vdpa_net *ndev, int num) MLX5_SET(rqtc, rqtc, list_q_type, MLX5_RQTC_LIST_Q_TYPE_VIRTIO_NET_Q); list = MLX5_ADDR_OF(rqtc, rqtc, rq_num[0]); - for (i = 0, j = 0; j < num; j++) { - if (!ndev->vqs[j].initialized) - continue; + for (i = 0, j = 0; i < max_rqt; i++, j += 2) + list[i] = cpu_to_be32(ndev->vqs[j % num].virtq_id); - if (!vq_is_tx(ndev->vqs[j].index)) { - list[i] = cpu_to_be32(ndev->vqs[j].virtq_id); - i++; - } - } - MLX5_SET(rqtc, rqtc, rqt_actual_size, i); + MLX5_SET(rqtc, rqtc, rqt_actual_size, max_rqt); err = mlx5_vdpa_modify_rqt(&ndev->mvdev, in, inlen, ndev->res.rqtn); kfree(in); if (err) @@ -1554,9 +1544,11 @@ static int change_num_qps(struct mlx5_vdpa_dev *mvdev, int newqps) return 0; clean_added: - for (--i; i >= cur_qps; --i) + for (--i; i >= 2 * cur_qps; --i) teardown_vq(ndev, &ndev->vqs[i]); + ndev->cur_num_vqs = 2 * cur_qps; + return err; } @@ -1581,9 +1573,6 @@ static virtio_net_ctrl_ack handle_ctrl_mq(struct mlx5_vdpa_dev *mvdev, u8 cmd) break; } - if (newqps & (newqps - 1)) - break; - if (!change_num_qps(mvdev, newqps)) status = VIRTIO_NET_OK; @@ -1880,21 +1869,29 @@ static u64 mlx_to_vritio_features(u16 dev_features) return result; } -static u64 mlx5_vdpa_get_features(struct vdpa_device *vdev) +static u64 get_supported_features(struct mlx5_core_dev *mdev) +{ + u64 mlx_vdpa_features = 0; + u16 dev_features; + + dev_features = MLX5_CAP_DEV_VDPA_EMULATION(mdev, device_features_bits_mask); + mlx_vdpa_features |= mlx_to_vritio_features(dev_features); + if (MLX5_CAP_DEV_VDPA_EMULATION(mdev, virtio_version_1_0)) + mlx_vdpa_features |= BIT_ULL(VIRTIO_F_VERSION_1); + mlx_vdpa_features |= BIT_ULL(VIRTIO_F_ACCESS_PLATFORM); + mlx_vdpa_features |= BIT_ULL(VIRTIO_NET_F_CTRL_VQ); + mlx_vdpa_features |= BIT_ULL(VIRTIO_NET_F_CTRL_MAC_ADDR); + mlx_vdpa_features |= BIT_ULL(VIRTIO_NET_F_MQ); + mlx_vdpa_features |= BIT_ULL(VIRTIO_NET_F_STATUS); + mlx_vdpa_features |= BIT_ULL(VIRTIO_NET_F_MTU); + + return mlx_vdpa_features; +} + +static u64 mlx5_vdpa_get_device_features(struct vdpa_device *vdev) { struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); - u16 dev_features; - - dev_features = MLX5_CAP_DEV_VDPA_EMULATION(mvdev->mdev, device_features_bits_mask); - ndev->mvdev.mlx_features |= mlx_to_vritio_features(dev_features); - if (MLX5_CAP_DEV_VDPA_EMULATION(mvdev->mdev, virtio_version_1_0)) - ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_F_VERSION_1); - ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_F_ACCESS_PLATFORM); - ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_NET_F_CTRL_VQ); - ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_NET_F_CTRL_MAC_ADDR); - ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_NET_F_MQ); - ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_NET_F_STATUS); print_features(mvdev, ndev->mvdev.mlx_features, false); return ndev->mvdev.mlx_features; @@ -1972,7 +1969,7 @@ static void update_cvq_info(struct mlx5_vdpa_dev *mvdev) } } -static int mlx5_vdpa_set_features(struct vdpa_device *vdev, u64 features) +static int mlx5_vdpa_set_driver_features(struct vdpa_device *vdev, u64 features) { struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); @@ -1985,6 +1982,11 @@ static int mlx5_vdpa_set_features(struct vdpa_device *vdev, u64 features) return err; ndev->mvdev.actual_features = features & ndev->mvdev.mlx_features; + if (ndev->mvdev.actual_features & BIT_ULL(VIRTIO_NET_F_MQ)) + ndev->cur_num_vqs = 2 * mlx5vdpa16_to_cpu(mvdev, ndev->config.max_virtqueue_pairs); + else + ndev->cur_num_vqs = 2; + update_cvq_info(mvdev); return err; } @@ -2235,7 +2237,8 @@ static int mlx5_vdpa_reset(struct vdpa_device *vdev) clear_vqs_ready(ndev); mlx5_vdpa_destroy_mr(&ndev->mvdev); ndev->mvdev.status = 0; - memset(ndev->event_cbs, 0, sizeof(ndev->event_cbs)); + ndev->cur_num_vqs = 0; + memset(ndev->event_cbs, 0, sizeof(*ndev->event_cbs) * (mvdev->max_vqs + 1)); ndev->mvdev.actual_features = 0; ++mvdev->generation; if (MLX5_CAP_GEN(mvdev->mdev, umem_uid_0)) { @@ -2308,6 +2311,8 @@ static void mlx5_vdpa_free(struct vdpa_device *vdev) } mlx5_vdpa_free_resources(&ndev->mvdev); mutex_destroy(&ndev->reslock); + kfree(ndev->event_cbs); + kfree(ndev->vqs); } static struct vdpa_notification_area mlx5_get_vq_notification(struct vdpa_device *vdev, u16 idx) @@ -2339,6 +2344,13 @@ static int mlx5_get_vq_irq(struct vdpa_device *vdv, u16 idx) return -EOPNOTSUPP; } +static u64 mlx5_vdpa_get_driver_features(struct vdpa_device *vdev) +{ + struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); + + return mvdev->actual_features; +} + static const struct vdpa_config_ops mlx5_vdpa_ops = { .set_vq_address = mlx5_vdpa_set_vq_address, .set_vq_num = mlx5_vdpa_set_vq_num, @@ -2351,8 +2363,9 @@ static const struct vdpa_config_ops mlx5_vdpa_ops = { .get_vq_notification = mlx5_get_vq_notification, .get_vq_irq = mlx5_get_vq_irq, .get_vq_align = mlx5_vdpa_get_vq_align, - .get_features = mlx5_vdpa_get_features, - .set_features = mlx5_vdpa_set_features, + .get_device_features = mlx5_vdpa_get_device_features, + .set_driver_features = mlx5_vdpa_set_driver_features, + .get_driver_features = mlx5_vdpa_get_driver_features, .set_config_cb = mlx5_vdpa_set_config_cb, .get_vq_num_max = mlx5_vdpa_get_vq_num_max, .get_device_id = mlx5_vdpa_get_device_id, @@ -2545,18 +2558,39 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name, return -EOPNOTSUPP; } - /* we save one virtqueue for control virtqueue should we require it */ max_vqs = MLX5_CAP_DEV_VDPA_EMULATION(mdev, max_num_virtio_queues); - max_vqs = min_t(u32, max_vqs, MLX5_MAX_SUPPORTED_VQS); + if (max_vqs < 2) { + dev_warn(mdev->device, + "%d virtqueues are supported. At least 2 are required\n", + max_vqs); + return -EAGAIN; + } + + if (add_config->mask & BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MAX_VQP)) { + if (add_config->net.max_vq_pairs > max_vqs / 2) + return -EINVAL; + max_vqs = min_t(u32, max_vqs, 2 * add_config->net.max_vq_pairs); + } else { + max_vqs = 2; + } ndev = vdpa_alloc_device(struct mlx5_vdpa_net, mvdev.vdev, mdev->device, &mlx5_vdpa_ops, name, false); if (IS_ERR(ndev)) return PTR_ERR(ndev); + ndev->mvdev.mlx_features = mgtdev->mgtdev.supported_features; ndev->mvdev.max_vqs = max_vqs; mvdev = &ndev->mvdev; mvdev->mdev = mdev; + + ndev->vqs = kcalloc(max_vqs, sizeof(*ndev->vqs), GFP_KERNEL); + ndev->event_cbs = kcalloc(max_vqs + 1, sizeof(*ndev->event_cbs), GFP_KERNEL); + if (!ndev->vqs || !ndev->event_cbs) { + err = -ENOMEM; + goto err_alloc; + } + init_mvqs(ndev); mutex_init(&ndev->reslock); config = &ndev->config; @@ -2612,9 +2646,8 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name, ndev->nb.notifier_call = event_handler; mlx5_notifier_register(mdev, &ndev->nb); - ndev->cur_num_vqs = 2 * mlx5_vdpa_max_qps(max_vqs); mvdev->vdev.mdev = &mgtdev->mgtdev; - err = _vdpa_register_device(&mvdev->vdev, ndev->cur_num_vqs + 1); + err = _vdpa_register_device(&mvdev->vdev, 2 * mlx5_vdpa_max_qps(max_vqs) + 1); if (err) goto err_reg; @@ -2634,6 +2667,7 @@ err_mpfs: mlx5_mpfs_del_mac(pfmdev, config->mac); err_mtu: mutex_destroy(&ndev->reslock); +err_alloc: put_device(&mvdev->vdev.dev); return err; } @@ -2676,7 +2710,11 @@ static int mlx5v_probe(struct auxiliary_device *adev, mgtdev->mgtdev.ops = &mdev_ops; mgtdev->mgtdev.device = mdev->device; mgtdev->mgtdev.id_table = id_table; - mgtdev->mgtdev.config_attr_mask = (1 << VDPA_ATTR_DEV_NET_CFG_MACADDR); + mgtdev->mgtdev.config_attr_mask = BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MACADDR) | + BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MAX_VQP); + mgtdev->mgtdev.max_supported_vqs = + MLX5_CAP_DEV_VDPA_EMULATION(mdev, max_num_virtio_queues) + 1; + mgtdev->mgtdev.supported_features = get_supported_features(mdev); mgtdev->madev = madev; err = vdpa_mgmtdev_register(&mgtdev->mgtdev); diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 09bbe53c3ac4..9846c9de4bfa 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -21,6 +21,14 @@ static LIST_HEAD(mdev_head); static DEFINE_MUTEX(vdpa_dev_mutex); static DEFINE_IDA(vdpa_index_ida); +void vdpa_set_status(struct vdpa_device *vdev, u8 status) +{ + mutex_lock(&vdev->cf_mutex); + vdev->config->set_status(vdev, status); + mutex_unlock(&vdev->cf_mutex); +} +EXPORT_SYMBOL(vdpa_set_status); + static struct genl_family vdpa_nl_family; static int vdpa_dev_probe(struct device *d) @@ -52,8 +60,81 @@ static void vdpa_dev_remove(struct device *d) drv->remove(vdev); } +static int vdpa_dev_match(struct device *dev, struct device_driver *drv) +{ + struct vdpa_device *vdev = dev_to_vdpa(dev); + + /* Check override first, and if set, only use the named driver */ + if (vdev->driver_override) + return strcmp(vdev->driver_override, drv->name) == 0; + + /* Currently devices must be supported by all vDPA bus drivers */ + return 1; +} + +static ssize_t driver_override_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct vdpa_device *vdev = dev_to_vdpa(dev); + const char *driver_override, *old; + char *cp; + + /* We need to keep extra room for a newline */ + if (count >= (PAGE_SIZE - 1)) + return -EINVAL; + + driver_override = kstrndup(buf, count, GFP_KERNEL); + if (!driver_override) + return -ENOMEM; + + cp = strchr(driver_override, '\n'); + if (cp) + *cp = '\0'; + + device_lock(dev); + old = vdev->driver_override; + if (strlen(driver_override)) { + vdev->driver_override = driver_override; + } else { + kfree(driver_override); + vdev->driver_override = NULL; + } + device_unlock(dev); + + kfree(old); + + return count; +} + +static ssize_t driver_override_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct vdpa_device *vdev = dev_to_vdpa(dev); + ssize_t len; + + device_lock(dev); + len = snprintf(buf, PAGE_SIZE, "%s\n", vdev->driver_override); + device_unlock(dev); + + return len; +} +static DEVICE_ATTR_RW(driver_override); + +static struct attribute *vdpa_dev_attrs[] = { + &dev_attr_driver_override.attr, + NULL, +}; + +static const struct attribute_group vdpa_dev_group = { + .attrs = vdpa_dev_attrs, +}; +__ATTRIBUTE_GROUPS(vdpa_dev); + static struct bus_type vdpa_bus = { .name = "vdpa", + .dev_groups = vdpa_dev_groups, + .match = vdpa_dev_match, .probe = vdpa_dev_probe, .remove = vdpa_dev_remove, }; @@ -68,6 +149,7 @@ static void vdpa_release_dev(struct device *d) ida_simple_remove(&vdpa_index_ida, vdev->index); mutex_destroy(&vdev->cf_mutex); + kfree(vdev->driver_override); kfree(vdev); } @@ -300,6 +382,21 @@ void vdpa_mgmtdev_unregister(struct vdpa_mgmt_dev *mdev) } EXPORT_SYMBOL_GPL(vdpa_mgmtdev_unregister); +static void vdpa_get_config_unlocked(struct vdpa_device *vdev, + unsigned int offset, + void *buf, unsigned int len) +{ + const struct vdpa_config_ops *ops = vdev->config; + + /* + * Config accesses aren't supposed to trigger before features are set. + * If it does happen we assume a legacy guest. + */ + if (!vdev->features_valid) + vdpa_set_features(vdev, 0, true); + ops->get_config(vdev, offset, buf, len); +} + /** * vdpa_get_config - Get one or more device configuration fields. * @vdev: vdpa device to operate on @@ -310,16 +407,8 @@ EXPORT_SYMBOL_GPL(vdpa_mgmtdev_unregister); void vdpa_get_config(struct vdpa_device *vdev, unsigned int offset, void *buf, unsigned int len) { - const struct vdpa_config_ops *ops = vdev->config; - mutex_lock(&vdev->cf_mutex); - /* - * Config accesses aren't supposed to trigger before features are set. - * If it does happen we assume a legacy guest. - */ - if (!vdev->features_valid) - vdpa_set_features(vdev, 0); - ops->get_config(vdev, offset, buf, len); + vdpa_get_config_unlocked(vdev, offset, buf, len); mutex_unlock(&vdev->cf_mutex); } EXPORT_SYMBOL_GPL(vdpa_get_config); @@ -414,6 +503,16 @@ static int vdpa_mgmtdev_fill(const struct vdpa_mgmt_dev *mdev, struct sk_buff *m err = -EMSGSIZE; goto msg_err; } + if (nla_put_u32(msg, VDPA_ATTR_DEV_MGMTDEV_MAX_VQS, + mdev->max_supported_vqs)) { + err = -EMSGSIZE; + goto msg_err; + } + if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_SUPPORTED_FEATURES, + mdev->supported_features, VDPA_ATTR_PAD)) { + err = -EMSGSIZE; + goto msg_err; + } genlmsg_end(msg, hdr); return 0; @@ -480,8 +579,9 @@ out: return msg->len; } -#define VDPA_DEV_NET_ATTRS_MASK ((1 << VDPA_ATTR_DEV_NET_CFG_MACADDR) | \ - (1 << VDPA_ATTR_DEV_NET_CFG_MTU)) +#define VDPA_DEV_NET_ATTRS_MASK (BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MACADDR) | \ + BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MTU) | \ + BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MAX_VQP)) static int vdpa_nl_cmd_dev_add_set_doit(struct sk_buff *skb, struct genl_info *info) { @@ -500,12 +600,22 @@ static int vdpa_nl_cmd_dev_add_set_doit(struct sk_buff *skb, struct genl_info *i if (nl_attrs[VDPA_ATTR_DEV_NET_CFG_MACADDR]) { macaddr = nla_data(nl_attrs[VDPA_ATTR_DEV_NET_CFG_MACADDR]); memcpy(config.net.mac, macaddr, sizeof(config.net.mac)); - config.mask |= (1 << VDPA_ATTR_DEV_NET_CFG_MACADDR); + config.mask |= BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MACADDR); } if (nl_attrs[VDPA_ATTR_DEV_NET_CFG_MTU]) { config.net.mtu = nla_get_u16(nl_attrs[VDPA_ATTR_DEV_NET_CFG_MTU]); - config.mask |= (1 << VDPA_ATTR_DEV_NET_CFG_MTU); + config.mask |= BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MTU); + } + if (nl_attrs[VDPA_ATTR_DEV_NET_CFG_MAX_VQP]) { + config.net.max_vq_pairs = + nla_get_u16(nl_attrs[VDPA_ATTR_DEV_NET_CFG_MAX_VQP]); + if (!config.net.max_vq_pairs) { + NL_SET_ERR_MSG_MOD(info->extack, + "At least one pair of VQs is required"); + return -EINVAL; + } + config.mask |= BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MAX_VQP); } /* Skip checking capability if user didn't prefer to configure any @@ -707,7 +817,7 @@ static int vdpa_dev_net_mq_config_fill(struct vdpa_device *vdev, { u16 val_u16; - if ((features & (1ULL << VIRTIO_NET_F_MQ)) == 0) + if ((features & BIT_ULL(VIRTIO_NET_F_MQ)) == 0) return 0; val_u16 = le16_to_cpu(config->max_virtqueue_pairs); @@ -720,7 +830,7 @@ static int vdpa_dev_net_config_fill(struct vdpa_device *vdev, struct sk_buff *ms u64 features; u16 val_u16; - vdpa_get_config(vdev, 0, &config, sizeof(config)); + vdpa_get_config_unlocked(vdev, 0, &config, sizeof(config)); if (nla_put(msg, VDPA_ATTR_DEV_NET_CFG_MACADDR, sizeof(config.mac), config.mac)) @@ -734,7 +844,10 @@ static int vdpa_dev_net_config_fill(struct vdpa_device *vdev, struct sk_buff *ms if (nla_put_u16(msg, VDPA_ATTR_DEV_NET_CFG_MTU, val_u16)) return -EMSGSIZE; - features = vdev->config->get_features(vdev); + features = vdev->config->get_driver_features(vdev); + if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_NEGOTIATED_FEATURES, features, + VDPA_ATTR_PAD)) + return -EMSGSIZE; return vdpa_dev_net_mq_config_fill(vdev, msg, features, &config); } @@ -745,12 +858,23 @@ vdpa_dev_config_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid, { u32 device_id; void *hdr; + u8 status; int err; + mutex_lock(&vdev->cf_mutex); + status = vdev->config->get_status(vdev); + if (!(status & VIRTIO_CONFIG_S_FEATURES_OK)) { + NL_SET_ERR_MSG_MOD(extack, "Features negotiation not completed"); + err = -EAGAIN; + goto out; + } + hdr = genlmsg_put(msg, portid, seq, &vdpa_nl_family, flags, VDPA_CMD_DEV_CONFIG_GET); - if (!hdr) - return -EMSGSIZE; + if (!hdr) { + err = -EMSGSIZE; + goto out; + } if (nla_put_string(msg, VDPA_ATTR_DEV_NAME, dev_name(&vdev->dev))) { err = -EMSGSIZE; @@ -774,11 +898,14 @@ vdpa_dev_config_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid, if (err) goto msg_err; + mutex_unlock(&vdev->cf_mutex); genlmsg_end(msg, hdr); return 0; msg_err: genlmsg_cancel(msg, hdr); +out: + mutex_unlock(&vdev->cf_mutex); return err; } diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index 41b0cd17fcba..ddbe142af09a 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -399,14 +399,14 @@ static u32 vdpasim_get_vq_align(struct vdpa_device *vdpa) return VDPASIM_QUEUE_ALIGN; } -static u64 vdpasim_get_features(struct vdpa_device *vdpa) +static u64 vdpasim_get_device_features(struct vdpa_device *vdpa) { struct vdpasim *vdpasim = vdpa_to_sim(vdpa); return vdpasim->dev_attr.supported_features; } -static int vdpasim_set_features(struct vdpa_device *vdpa, u64 features) +static int vdpasim_set_driver_features(struct vdpa_device *vdpa, u64 features) { struct vdpasim *vdpasim = vdpa_to_sim(vdpa); @@ -419,6 +419,13 @@ static int vdpasim_set_features(struct vdpa_device *vdpa, u64 features) return 0; } +static u64 vdpasim_get_driver_features(struct vdpa_device *vdpa) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + + return vdpasim->features; +} + static void vdpasim_set_config_cb(struct vdpa_device *vdpa, struct vdpa_callback *cb) { @@ -613,8 +620,9 @@ static const struct vdpa_config_ops vdpasim_config_ops = { .set_vq_state = vdpasim_set_vq_state, .get_vq_state = vdpasim_get_vq_state, .get_vq_align = vdpasim_get_vq_align, - .get_features = vdpasim_get_features, - .set_features = vdpasim_set_features, + .get_device_features = vdpasim_get_device_features, + .set_driver_features = vdpasim_set_driver_features, + .get_driver_features = vdpasim_get_driver_features, .set_config_cb = vdpasim_set_config_cb, .get_vq_num_max = vdpasim_get_vq_num_max, .get_device_id = vdpasim_get_device_id, @@ -642,8 +650,9 @@ static const struct vdpa_config_ops vdpasim_batch_config_ops = { .set_vq_state = vdpasim_set_vq_state, .get_vq_state = vdpasim_get_vq_state, .get_vq_align = vdpasim_get_vq_align, - .get_features = vdpasim_get_features, - .set_features = vdpasim_set_features, + .get_device_features = vdpasim_get_device_features, + .set_driver_features = vdpasim_set_driver_features, + .get_driver_features = vdpasim_get_driver_features, .set_config_cb = vdpasim_set_config_cb, .get_vq_num_max = vdpasim_get_vq_num_max, .get_device_id = vdpasim_get_device_id, diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c index 76dd24abc791..d5324f6fd8c7 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c @@ -191,6 +191,8 @@ static struct vdpa_mgmt_dev mgmt_dev = { .ops = &vdpasim_net_mgmtdev_ops, .config_attr_mask = (1 << VDPA_ATTR_DEV_NET_CFG_MACADDR | 1 << VDPA_ATTR_DEV_NET_CFG_MTU), + .max_supported_vqs = VDPASIM_NET_VQ_NUM, + .supported_features = VDPASIM_NET_FEATURES, }; static int __init vdpasim_net_init(void) diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c index eddcb64a910a..f85d1a08ed87 100644 --- a/drivers/vdpa/vdpa_user/vduse_dev.c +++ b/drivers/vdpa/vdpa_user/vduse_dev.c @@ -573,14 +573,14 @@ static u32 vduse_vdpa_get_vq_align(struct vdpa_device *vdpa) return dev->vq_align; } -static u64 vduse_vdpa_get_features(struct vdpa_device *vdpa) +static u64 vduse_vdpa_get_device_features(struct vdpa_device *vdpa) { struct vduse_dev *dev = vdpa_to_vduse(vdpa); return dev->device_features; } -static int vduse_vdpa_set_features(struct vdpa_device *vdpa, u64 features) +static int vduse_vdpa_set_driver_features(struct vdpa_device *vdpa, u64 features) { struct vduse_dev *dev = vdpa_to_vduse(vdpa); @@ -588,6 +588,13 @@ static int vduse_vdpa_set_features(struct vdpa_device *vdpa, u64 features) return 0; } +static u64 vduse_vdpa_get_driver_features(struct vdpa_device *vdpa) +{ + struct vduse_dev *dev = vdpa_to_vduse(vdpa); + + return dev->driver_features; +} + static void vduse_vdpa_set_config_cb(struct vdpa_device *vdpa, struct vdpa_callback *cb) { @@ -721,8 +728,9 @@ static const struct vdpa_config_ops vduse_vdpa_config_ops = { .set_vq_state = vduse_vdpa_set_vq_state, .get_vq_state = vduse_vdpa_get_vq_state, .get_vq_align = vduse_vdpa_get_vq_align, - .get_features = vduse_vdpa_get_features, - .set_features = vduse_vdpa_set_features, + .get_device_features = vduse_vdpa_get_device_features, + .set_driver_features = vduse_vdpa_set_driver_features, + .get_driver_features = vduse_vdpa_get_driver_features, .set_config_cb = vduse_vdpa_set_config_cb, .get_vq_num_max = vduse_vdpa_get_vq_num_max, .get_device_id = vduse_vdpa_get_device_id, @@ -1357,7 +1365,6 @@ err_domain: err_str: vduse_dev_destroy(dev); err: - kvfree(config_buf); return ret; } @@ -1408,6 +1415,8 @@ static long vduse_ioctl(struct file *file, unsigned int cmd, } config.name[VDUSE_NAME_MAX - 1] = '\0'; ret = vduse_create_dev(&config, buf, control->api_version); + if (ret) + kvfree(buf); break; } case VDUSE_DESTROY_DEV: { diff --git a/drivers/vdpa/virtio_pci/vp_vdpa.c b/drivers/vdpa/virtio_pci/vp_vdpa.c index e3ff7875e123..a57e381e830b 100644 --- a/drivers/vdpa/virtio_pci/vp_vdpa.c +++ b/drivers/vdpa/virtio_pci/vp_vdpa.c @@ -53,14 +53,14 @@ static struct virtio_pci_modern_device *vdpa_to_mdev(struct vdpa_device *vdpa) return &vp_vdpa->mdev; } -static u64 vp_vdpa_get_features(struct vdpa_device *vdpa) +static u64 vp_vdpa_get_device_features(struct vdpa_device *vdpa) { struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa); return vp_modern_get_features(mdev); } -static int vp_vdpa_set_features(struct vdpa_device *vdpa, u64 features) +static int vp_vdpa_set_driver_features(struct vdpa_device *vdpa, u64 features) { struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa); @@ -69,6 +69,13 @@ static int vp_vdpa_set_features(struct vdpa_device *vdpa, u64 features) return 0; } +static u64 vp_vdpa_get_driver_features(struct vdpa_device *vdpa) +{ + struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa); + + return vp_modern_get_driver_features(mdev); +} + static u8 vp_vdpa_get_status(struct vdpa_device *vdpa) { struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa); @@ -415,8 +422,9 @@ vp_vdpa_get_vq_notification(struct vdpa_device *vdpa, u16 qid) } static const struct vdpa_config_ops vp_vdpa_ops = { - .get_features = vp_vdpa_get_features, - .set_features = vp_vdpa_set_features, + .get_device_features = vp_vdpa_get_device_features, + .set_driver_features = vp_vdpa_set_driver_features, + .get_driver_features = vp_vdpa_get_driver_features, .get_status = vp_vdpa_get_status, .set_status = vp_vdpa_set_status, .reset = vp_vdpa_reset, diff --git a/drivers/vhost/test.c b/drivers/vhost/test.c index a09dedc79f68..05740cba1cd8 100644 --- a/drivers/vhost/test.c +++ b/drivers/vhost/test.c @@ -166,6 +166,7 @@ static int vhost_test_release(struct inode *inode, struct file *f) /* We do an extra flush before freeing memory, * since jobs can re-queue themselves. */ vhost_test_flush(n); + kfree(n->dev.vqs); kfree(n); return 0; } diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index e3c4f059b21a..851539807bc9 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -170,7 +170,7 @@ static long vhost_vdpa_set_status(struct vhost_vdpa *v, u8 __user *statusp) * Userspace shouldn't remove status bits unless reset the * status to 0. */ - if (status != 0 && (ops->get_status(vdpa) & ~status) != 0) + if (status != 0 && (status_old & ~status) != 0) return -EINVAL; if ((status_old & VIRTIO_CONFIG_S_DRIVER_OK) && !(status & VIRTIO_CONFIG_S_DRIVER_OK)) @@ -178,11 +178,11 @@ static long vhost_vdpa_set_status(struct vhost_vdpa *v, u8 __user *statusp) vhost_vdpa_unsetup_vq_irq(v, i); if (status == 0) { - ret = ops->reset(vdpa); + ret = vdpa_reset(vdpa); if (ret) return ret; } else - ops->set_status(vdpa, status); + vdpa_set_status(vdpa, status); if ((status & VIRTIO_CONFIG_S_DRIVER_OK) && !(status_old & VIRTIO_CONFIG_S_DRIVER_OK)) for (i = 0; i < nvqs; i++) @@ -195,7 +195,7 @@ static int vhost_vdpa_config_validate(struct vhost_vdpa *v, struct vhost_vdpa_config *c) { struct vdpa_device *vdpa = v->vdpa; - long size = vdpa->config->get_config_size(vdpa); + size_t size = vdpa->config->get_config_size(vdpa); if (c->len == 0 || c->off > size) return -EINVAL; @@ -262,7 +262,7 @@ static long vhost_vdpa_get_features(struct vhost_vdpa *v, u64 __user *featurep) const struct vdpa_config_ops *ops = vdpa->config; u64 features; - features = ops->get_features(vdpa); + features = ops->get_device_features(vdpa); if (copy_to_user(featurep, &features, sizeof(features))) return -EFAULT; @@ -286,7 +286,7 @@ static long vhost_vdpa_set_features(struct vhost_vdpa *v, u64 __user *featurep) if (copy_from_user(&features, featurep, sizeof(features))) return -EFAULT; - if (vdpa_set_features(vdpa, features)) + if (vdpa_set_features(vdpa, features, false)) return -EINVAL; return 0; diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index 236081afe9a2..00ac9db792a4 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -204,6 +204,12 @@ int virtio_finalize_features(struct virtio_device *dev) } EXPORT_SYMBOL_GPL(virtio_finalize_features); +void virtio_reset_device(struct virtio_device *dev) +{ + dev->config->reset(dev); +} +EXPORT_SYMBOL_GPL(virtio_reset_device); + static int virtio_dev_probe(struct device *_d) { int err, i; diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index c22ff0117b46..f4c34a2a6b8e 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -1056,7 +1056,7 @@ static void remove_common(struct virtio_balloon *vb) return_free_pages_to_mm(vb, ULONG_MAX); /* Now we reset the device so we can clean up the queues. */ - vb->vdev->config->reset(vb->vdev); + virtio_reset_device(vb->vdev); vb->vdev->config->del_vqs(vb->vdev); } diff --git a/drivers/virtio/virtio_input.c b/drivers/virtio/virtio_input.c index ce51ae165943..3aa46703872d 100644 --- a/drivers/virtio/virtio_input.c +++ b/drivers/virtio/virtio_input.c @@ -347,7 +347,7 @@ static void virtinput_remove(struct virtio_device *vdev) spin_unlock_irqrestore(&vi->lock, flags); input_unregister_device(vi->idev); - vdev->config->reset(vdev); + virtio_reset_device(vdev); while ((buf = virtqueue_detach_unused_buf(vi->sts)) != NULL) kfree(buf); vdev->config->del_vqs(vdev); diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c index 96e5a8782769..38becd8d578c 100644 --- a/drivers/virtio/virtio_mem.c +++ b/drivers/virtio/virtio_mem.c @@ -20,6 +20,7 @@ #include #include #include +#include #include @@ -592,7 +593,7 @@ static int virtio_mem_sbm_sb_states_prepare_next_mb(struct virtio_mem *vm) return -ENOMEM; mutex_lock(&vm->hotplug_mutex); - if (new_bitmap) + if (vm->sbm.sb_states) memcpy(new_bitmap, vm->sbm.sb_states, old_pages * PAGE_SIZE); old_bitmap = vm->sbm.sb_states; @@ -1120,15 +1121,18 @@ static void virtio_mem_clear_fake_offline(unsigned long pfn, */ static void virtio_mem_fake_online(unsigned long pfn, unsigned long nr_pages) { - const unsigned long max_nr_pages = MAX_ORDER_NR_PAGES; + unsigned long order = MAX_ORDER - 1; unsigned long i; /* - * We are always called at least with MAX_ORDER_NR_PAGES - * granularity/alignment (e.g., the way subblocks work). All pages - * inside such a block are alike. + * We might get called for ranges that don't cover properly aligned + * MAX_ORDER - 1 pages; however, we can only online properly aligned + * pages with an order of MAX_ORDER - 1 at maximum. */ - for (i = 0; i < nr_pages; i += max_nr_pages) { + while (!IS_ALIGNED(pfn | nr_pages, 1 << order)) + order--; + + for (i = 0; i < nr_pages; i += 1 << order) { struct page *page = pfn_to_page(pfn + i); /* @@ -1138,14 +1142,12 @@ static void virtio_mem_fake_online(unsigned long pfn, unsigned long nr_pages) * alike. */ if (PageDirty(page)) { - virtio_mem_clear_fake_offline(pfn + i, max_nr_pages, - false); - generic_online_page(page, MAX_ORDER - 1); + virtio_mem_clear_fake_offline(pfn + i, 1 << order, false); + generic_online_page(page, order); } else { - virtio_mem_clear_fake_offline(pfn + i, max_nr_pages, - true); - free_contig_range(pfn + i, max_nr_pages); - adjust_managed_page_count(page, max_nr_pages); + virtio_mem_clear_fake_offline(pfn + i, 1 << order, true); + free_contig_range(pfn + i, 1 << order); + adjust_managed_page_count(page, 1 << order); } } } @@ -1228,28 +1230,46 @@ static void virtio_mem_fake_offline_cancel_offline(unsigned long pfn, page_ref_inc(pfn_to_page(pfn + i)); } -static void virtio_mem_online_page_cb(struct page *page, unsigned int order) +static void virtio_mem_online_page(struct virtio_mem *vm, + struct page *page, unsigned int order) { - const unsigned long addr = page_to_phys(page); - unsigned long id, sb_id; - struct virtio_mem *vm; + const unsigned long start = page_to_phys(page); + const unsigned long end = start + PFN_PHYS(1 << order); + unsigned long addr, next, id, sb_id, count; bool do_online; - rcu_read_lock(); - list_for_each_entry_rcu(vm, &virtio_mem_devices, next) { - if (!virtio_mem_contains_range(vm, addr, PFN_PHYS(1 << order))) - continue; + /* + * We can get called with any order up to MAX_ORDER - 1. If our + * subblock size is smaller than that and we have a mixture of plugged + * and unplugged subblocks within such a page, we have to process in + * smaller granularity. In that case we'll adjust the order exactly once + * within the loop. + */ + for (addr = start; addr < end; ) { + next = addr + PFN_PHYS(1 << order); if (vm->in_sbm) { - /* - * We exploit here that subblocks have at least - * MAX_ORDER_NR_PAGES size/alignment - so we cannot - * cross subblocks within one call. - */ id = virtio_mem_phys_to_mb_id(addr); sb_id = virtio_mem_phys_to_sb_id(vm, addr); - do_online = virtio_mem_sbm_test_sb_plugged(vm, id, - sb_id, 1); + count = virtio_mem_phys_to_sb_id(vm, next - 1) - sb_id + 1; + + if (virtio_mem_sbm_test_sb_plugged(vm, id, sb_id, count)) { + /* Fully plugged. */ + do_online = true; + } else if (count == 1 || + virtio_mem_sbm_test_sb_unplugged(vm, id, sb_id, count)) { + /* Fully unplugged. */ + do_online = false; + } else { + /* + * Mixture, process sub-blocks instead. This + * will be at least the size of a pageblock. + * We'll run into this case exactly once. + */ + order = ilog2(vm->sbm.sb_size) - PAGE_SHIFT; + do_online = virtio_mem_sbm_test_sb_plugged(vm, id, sb_id, 1); + continue; + } } else { /* * If the whole block is marked fake offline, keep @@ -1260,18 +1280,38 @@ static void virtio_mem_online_page_cb(struct page *page, unsigned int order) VIRTIO_MEM_BBM_BB_FAKE_OFFLINE; } + if (do_online) + generic_online_page(pfn_to_page(PFN_DOWN(addr)), order); + else + virtio_mem_set_fake_offline(PFN_DOWN(addr), 1 << order, + false); + addr = next; + } +} + +static void virtio_mem_online_page_cb(struct page *page, unsigned int order) +{ + const unsigned long addr = page_to_phys(page); + struct virtio_mem *vm; + + rcu_read_lock(); + list_for_each_entry_rcu(vm, &virtio_mem_devices, next) { /* - * virtio_mem_set_fake_offline() might sleep, we don't need - * the device anymore. See virtio_mem_remove() how races + * Pages we're onlining will never cross memory blocks and, + * therefore, not virtio-mem devices. + */ + if (!virtio_mem_contains_range(vm, addr, PFN_PHYS(1 << order))) + continue; + + /* + * virtio_mem_set_fake_offline() might sleep. We can safely + * drop the RCU lock at this point because the device + * cannot go away. See virtio_mem_remove() how races * between memory onlining and device removal are handled. */ rcu_read_unlock(); - if (do_online) - generic_online_page(page, order); - else - virtio_mem_set_fake_offline(PFN_DOWN(addr), 1 << order, - false); + virtio_mem_online_page(vm, page, order); return; } rcu_read_unlock(); @@ -2438,8 +2478,6 @@ static int virtio_mem_init_hotplug(struct virtio_mem *vm) /* * We want subblocks to span at least MAX_ORDER_NR_PAGES and * pageblock_nr_pages pages. This: - * - Simplifies our page onlining code (virtio_mem_online_page_cb) - * and fake page onlining code (virtio_mem_fake_online). * - Is required for now for alloc_contig_range() to work reliably - * it doesn't properly handle smaller granularity on ZONE_NORMAL. */ @@ -2850,7 +2888,7 @@ static void virtio_mem_remove(struct virtio_device *vdev) virtio_mem_deinit_hotplug(vm); /* reset the device and cleanup the queues */ - vdev->config->reset(vdev); + virtio_reset_device(vdev); vdev->config->del_vqs(vdev); kfree(vm); diff --git a/drivers/virtio/virtio_pci_legacy.c b/drivers/virtio/virtio_pci_legacy.c index b3f8128b7983..34141b9abe27 100644 --- a/drivers/virtio/virtio_pci_legacy.c +++ b/drivers/virtio/virtio_pci_legacy.c @@ -138,7 +138,7 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, q_pfn = virtqueue_get_desc_addr(vq) >> VIRTIO_PCI_QUEUE_ADDR_SHIFT; if (q_pfn >> 32) { dev_err(&vp_dev->pci_dev->dev, - "platform bug: legacy virtio-mmio must not be used with RAM above 0x%llxGB\n", + "platform bug: legacy virtio-pci must not be used with RAM above 0x%llxGB\n", 0x1ULL << (32 + PAGE_SHIFT - 30)); err = -E2BIG; goto out_del_vq; diff --git a/drivers/virtio/virtio_pci_legacy_dev.c b/drivers/virtio/virtio_pci_legacy_dev.c index 9b97680dd02b..677d1f68bc9b 100644 --- a/drivers/virtio/virtio_pci_legacy_dev.c +++ b/drivers/virtio/virtio_pci_legacy_dev.c @@ -45,8 +45,10 @@ int vp_legacy_probe(struct virtio_pci_legacy_device *ldev) return rc; ldev->ioaddr = pci_iomap(pci_dev, 0, 0); - if (!ldev->ioaddr) + if (!ldev->ioaddr) { + rc = -EIO; goto err_iomap; + } ldev->isr = ldev->ioaddr + VIRTIO_PCI_ISR; diff --git a/drivers/virtio/virtio_pci_modern_dev.c b/drivers/virtio/virtio_pci_modern_dev.c index e11ed748e661..e8b3ff2b9fbc 100644 --- a/drivers/virtio/virtio_pci_modern_dev.c +++ b/drivers/virtio/virtio_pci_modern_dev.c @@ -345,7 +345,7 @@ err_map_common: EXPORT_SYMBOL_GPL(vp_modern_probe); /* - * vp_modern_probe: remove and cleanup the modern virtio pci device + * vp_modern_remove: remove and cleanup the modern virtio pci device * @mdev: the modern virtio-pci device */ void vp_modern_remove(struct virtio_pci_modern_device *mdev) diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 028b05d44546..962f1477b1fa 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -1197,8 +1197,10 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq, if (virtqueue_use_indirect(_vq, total_sg)) { err = virtqueue_add_indirect_packed(vq, sgs, total_sg, out_sgs, in_sgs, data, gfp); - if (err != -ENOMEM) + if (err != -ENOMEM) { + END_USE(vq); return err; + } /* fall back on direct */ } diff --git a/drivers/virtio/virtio_vdpa.c b/drivers/virtio/virtio_vdpa.c index f85f860bc10b..7767a7f0119b 100644 --- a/drivers/virtio/virtio_vdpa.c +++ b/drivers/virtio/virtio_vdpa.c @@ -91,9 +91,8 @@ static u8 virtio_vdpa_get_status(struct virtio_device *vdev) static void virtio_vdpa_set_status(struct virtio_device *vdev, u8 status) { struct vdpa_device *vdpa = vd_get_vdpa(vdev); - const struct vdpa_config_ops *ops = vdpa->config; - return ops->set_status(vdpa, status); + return vdpa_set_status(vdpa, status); } static void virtio_vdpa_reset(struct virtio_device *vdev) @@ -308,7 +307,7 @@ static u64 virtio_vdpa_get_features(struct virtio_device *vdev) struct vdpa_device *vdpa = vd_get_vdpa(vdev); const struct vdpa_config_ops *ops = vdpa->config; - return ops->get_features(vdpa); + return ops->get_device_features(vdpa); } static int virtio_vdpa_finalize_features(struct virtio_device *vdev) @@ -318,7 +317,7 @@ static int virtio_vdpa_finalize_features(struct virtio_device *vdev) /* Give virtio_ring a chance to accept features. */ vring_transport_features(vdev); - return vdpa_set_features(vdpa, vdev->features); + return vdpa_set_features(vdpa, vdev->features, false); } static const char *virtio_vdpa_bus_name(struct virtio_device *vdev) diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig index 1dc86eb1361a..c8fa79da23b3 100644 --- a/drivers/watchdog/Kconfig +++ b/drivers/watchdog/Kconfig @@ -207,6 +207,7 @@ config DA9055_WATCHDOG config DA9063_WATCHDOG tristate "Dialog DA9063 Watchdog" depends on MFD_DA9063 || COMPILE_TEST + depends on I2C select WATCHDOG_CORE help Support for the watchdog in the DA9063 PMIC. @@ -680,10 +681,10 @@ config MAX77620_WATCHDOG depends on MFD_MAX77620 || COMPILE_TEST select WATCHDOG_CORE help - This is the driver for the Max77620 watchdog timer. - Say 'Y' here to enable the watchdog timer support for - MAX77620 chips. To compile this driver as a module, - choose M here: the module will be called max77620_wdt. + This is the driver for the Max77620 watchdog timer. + Say 'Y' here to enable the watchdog timer support for + MAX77620 chips. To compile this driver as a module, + choose M here: the module will be called max77620_wdt. config IMX2_WDT tristate "IMX2+ Watchdog" @@ -822,6 +823,7 @@ config MESON_WATCHDOG config MEDIATEK_WATCHDOG tristate "Mediatek SoCs watchdog support" depends on ARCH_MEDIATEK || COMPILE_TEST + default ARCH_MEDIATEK select WATCHDOG_CORE select RESET_CONTROLLER help @@ -881,6 +883,14 @@ config RENESAS_RZAWDT This driver adds watchdog support for the integrated watchdogs in the Renesas RZ/A SoCs. These watchdogs can be used to reset a system. +config RENESAS_RZG2LWDT + tristate "Renesas RZ/G2L WDT Watchdog" + depends on ARCH_RENESAS || COMPILE_TEST + select WATCHDOG_CORE + help + This driver adds watchdog support for the integrated watchdogs in the + Renesas RZ/G2L SoCs. These watchdogs can be used to reset a system. + config ASPEED_WATCHDOG tristate "Aspeed BMC watchdog support" depends on ARCH_ASPEED || COMPILE_TEST @@ -940,6 +950,19 @@ config RTD119X_WATCHDOG Say Y here to include support for the watchdog timer in Realtek RTD1295 SoCs. +config REALTEK_OTTO_WDT + tristate "Realtek Otto MIPS watchdog support" + depends on MACH_REALTEK_RTL || COMPILE_TEST + depends on COMMON_CLK + select WATCHDOG_CORE + default MACH_REALTEK_RTL + help + Say Y here to include support for the watchdog timer on Realtek + RTL838x, RTL839x, RTL930x SoCs. This watchdog has pretimeout + notifications and system reset on timeout. + + When built as a module this will be called realtek_otto_wdt. + config SPRD_WATCHDOG tristate "Spreadtrum watchdog support" depends on ARCH_SPRD || COMPILE_TEST @@ -976,6 +999,18 @@ config MSC313E_WATCHDOG To compile this driver as a module, choose M here: the module will be called msc313e_wdt. +config APPLE_WATCHDOG + tristate "Apple SoC watchdog" + depends on ARCH_APPLE || COMPILE_TEST + select WATCHDOG_CORE + help + Say Y here to include support for the Watchdog found in Apple + SoCs such as the M1. Next to the common watchdog features this + driver is also required in order to reboot these SoCs. + + To compile this driver as a module, choose M here: the + module will be called apple_wdt. + # X86 (i386 + ia64 + x86_64) Architecture config ACQUIRE_WDT @@ -1440,26 +1475,26 @@ config TQMX86_WDT depends on X86 select WATCHDOG_CORE help - This is the driver for the hardware watchdog timer in the TQMX86 IO - controller found on some of their ComExpress Modules. + This is the driver for the hardware watchdog timer in the TQMX86 IO + controller found on some of their ComExpress Modules. - To compile this driver as a module, choose M here; the module - will be called tqmx86_wdt. + To compile this driver as a module, choose M here; the module + will be called tqmx86_wdt. - Most people will say N. + Most people will say N. config VIA_WDT tristate "VIA Watchdog Timer" depends on X86 && PCI select WATCHDOG_CORE help - This is the driver for the hardware watchdog timer on VIA - southbridge chipset CX700, VX800/VX820 or VX855/VX875. + This is the driver for the hardware watchdog timer on VIA + southbridge chipset CX700, VX800/VX820 or VX855/VX875. - To compile this driver as a module, choose M here; the module - will be called via_wdt. + To compile this driver as a module, choose M here; the module + will be called via_wdt. - Most people will say N. + Most people will say N. config W83627HF_WDT tristate "Watchdog timer for W83627HF/W83627DHG and compatibles" @@ -1707,16 +1742,6 @@ config OCTEON_WDT from the first interrupt, it is then only poked when the device is written. -config BCM63XX_WDT - tristate "Broadcom BCM63xx hardware watchdog" - depends on BCM63XX - help - Watchdog driver for the built in watchdog hardware in Broadcom - BCM63xx SoC. - - To compile this driver as a loadable module, choose M here. - The module will be called bcm63xx_wdt. - config BCM2835_WDT tristate "Broadcom BCM2835 hardware watchdog" depends on ARCH_BCM2835 || (OF && COMPILE_TEST) @@ -1751,15 +1776,16 @@ config BCM_KONA_WDT_DEBUG If in doubt, say 'N'. config BCM7038_WDT - tristate "BCM7038 Watchdog" + tristate "BCM63xx/BCM7038 Watchdog" select WATCHDOG_CORE depends on HAS_IOMEM - depends on ARCH_BRCMSTB || BMIPS_GENERIC || COMPILE_TEST + depends on ARCH_BRCMSTB || BMIPS_GENERIC || BCM63XX || COMPILE_TEST help - Watchdog driver for the built-in hardware in Broadcom 7038 and - later SoCs used in set-top boxes. BCM7038 was made public - during the 2004 CES, and since then, many Broadcom chips use this - watchdog block, including some cable modem chips. + Watchdog driver for the built-in hardware in Broadcom 7038 and + later SoCs used in set-top boxes. BCM7038 was made public + during the 2004 CES, and since then, many Broadcom chips use this + watchdog block, including some cable modem chips and DSL (63xx) + chips. config IMGPDC_WDT tristate "Imagination Technologies PDC Watchdog Timer" @@ -2120,12 +2146,12 @@ config KEEMBAY_WATCHDOG depends on ARCH_KEEMBAY || (ARM64 && COMPILE_TEST) select WATCHDOG_CORE help - This option enable support for an In-secure watchdog timer driver for - Intel Keem Bay SoC. This WDT has a 32 bit timer and decrements in every - count unit. An interrupt will be triggered, when the count crosses - the threshold configured in the register. + This option enable support for an In-secure watchdog timer driver for + Intel Keem Bay SoC. This WDT has a 32 bit timer and decrements in every + count unit. An interrupt will be triggered, when the count crosses + the threshold configured in the register. - To compile this driver as a module, choose M here: the - module will be called keembay_wdt. + To compile this driver as a module, choose M here: the + module will be called keembay_wdt. endif # WATCHDOG diff --git a/drivers/watchdog/Makefile b/drivers/watchdog/Makefile index 31b931846e32..f7da867e8782 100644 --- a/drivers/watchdog/Makefile +++ b/drivers/watchdog/Makefile @@ -84,6 +84,7 @@ obj-$(CONFIG_LPC18XX_WATCHDOG) += lpc18xx_wdt.o obj-$(CONFIG_BCM7038_WDT) += bcm7038_wdt.o obj-$(CONFIG_RENESAS_WDT) += renesas_wdt.o obj-$(CONFIG_RENESAS_RZAWDT) += rza_wdt.o +obj-$(CONFIG_RENESAS_RZG2LWDT) += rzg2l_wdt.o obj-$(CONFIG_ASPEED_WATCHDOG) += aspeed_wdt.o obj-$(CONFIG_STM32_WATCHDOG) += stm32_iwdg.o obj-$(CONFIG_UNIPHIER_WATCHDOG) += uniphier_wdt.o @@ -93,6 +94,7 @@ obj-$(CONFIG_PM8916_WATCHDOG) += pm8916_wdt.o obj-$(CONFIG_ARM_SMC_WATCHDOG) += arm_smc_wdt.o obj-$(CONFIG_VISCONTI_WATCHDOG) += visconti_wdt.o obj-$(CONFIG_MSC313E_WATCHDOG) += msc313e_wdt.o +obj-$(CONFIG_APPLE_WATCHDOG) += apple_wdt.o # X86 (i386 + ia64 + x86_64) Architecture obj-$(CONFIG_ACQUIRE_WDT) += acquirewdt.o @@ -154,7 +156,6 @@ obj-$(CONFIG_XILINX_WATCHDOG) += of_xilinx_wdt.o # MIPS Architecture obj-$(CONFIG_ATH79_WDT) += ath79_wdt.o obj-$(CONFIG_BCM47XX_WDT) += bcm47xx_wdt.o -obj-$(CONFIG_BCM63XX_WDT) += bcm63xx_wdt.o obj-$(CONFIG_RC32434_WDT) += rc32434_wdt.o obj-$(CONFIG_INDYDOG) += indydog.o obj-$(CONFIG_JZ4740_WDT) += jz4740_wdt.o @@ -171,6 +172,7 @@ obj-$(CONFIG_IMGPDC_WDT) += imgpdc_wdt.o obj-$(CONFIG_MT7621_WDT) += mt7621_wdt.o obj-$(CONFIG_PIC32_WDT) += pic32-wdt.o obj-$(CONFIG_PIC32_DMT) += pic32-dmt.o +obj-$(CONFIG_REALTEK_OTTO_WDT) += realtek_otto_wdt.o # PARISC Architecture diff --git a/drivers/watchdog/apple_wdt.c b/drivers/watchdog/apple_wdt.c new file mode 100644 index 000000000000..16aca21f13d6 --- /dev/null +++ b/drivers/watchdog/apple_wdt.c @@ -0,0 +1,226 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* + * Apple SoC Watchdog driver + * + * Copyright (C) The Asahi Linux Contributors + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * Apple Watchdog MMIO registers + * + * This HW block has three separate watchdogs. WD0 resets the machine + * to recovery mode and is not very useful for us. WD1 and WD2 trigger a normal + * machine reset. WD0 additionally supports a configurable interrupt. + * This information can be used to implement pretimeout support at a later time. + * + * APPLE_WDT_WDx_CUR_TIME is a simple counter incremented for each tick of the + * reference clock. It can also be overwritten to any value. + * Whenever APPLE_WDT_CTRL_RESET_EN is set in APPLE_WDT_WDx_CTRL and + * APPLE_WDT_WDx_CUR_TIME >= APPLE_WDT_WDx_BITE_TIME the entire machine is + * reset. + * Whenever APPLE_WDT_CTRL_IRQ_EN is set and APPLE_WDTx_WD1_CUR_TIME >= + * APPLE_WDTx_WD1_BARK_TIME an interrupt is triggered and + * APPLE_WDT_CTRL_IRQ_STATUS is set. The interrupt can be cleared by writing + * 1 to APPLE_WDT_CTRL_IRQ_STATUS. + */ +#define APPLE_WDT_WD0_CUR_TIME 0x00 +#define APPLE_WDT_WD0_BITE_TIME 0x04 +#define APPLE_WDT_WD0_BARK_TIME 0x08 +#define APPLE_WDT_WD0_CTRL 0x0c + +#define APPLE_WDT_WD1_CUR_TIME 0x10 +#define APPLE_WDT_WD1_BITE_TIME 0x14 +#define APPLE_WDT_WD1_CTRL 0x1c + +#define APPLE_WDT_WD2_CUR_TIME 0x20 +#define APPLE_WDT_WD2_BITE_TIME 0x24 +#define APPLE_WDT_WD2_CTRL 0x2c + +#define APPLE_WDT_CTRL_IRQ_EN BIT(0) +#define APPLE_WDT_CTRL_IRQ_STATUS BIT(1) +#define APPLE_WDT_CTRL_RESET_EN BIT(2) + +#define APPLE_WDT_TIMEOUT_DEFAULT 30 + +struct apple_wdt { + struct watchdog_device wdd; + void __iomem *regs; + unsigned long clk_rate; +}; + +static struct apple_wdt *to_apple_wdt(struct watchdog_device *wdd) +{ + return container_of(wdd, struct apple_wdt, wdd); +} + +static int apple_wdt_start(struct watchdog_device *wdd) +{ + struct apple_wdt *wdt = to_apple_wdt(wdd); + + writel_relaxed(0, wdt->regs + APPLE_WDT_WD1_CUR_TIME); + writel_relaxed(APPLE_WDT_CTRL_RESET_EN, wdt->regs + APPLE_WDT_WD1_CTRL); + + return 0; +} + +static int apple_wdt_stop(struct watchdog_device *wdd) +{ + struct apple_wdt *wdt = to_apple_wdt(wdd); + + writel_relaxed(0, wdt->regs + APPLE_WDT_WD1_CTRL); + + return 0; +} + +static int apple_wdt_ping(struct watchdog_device *wdd) +{ + struct apple_wdt *wdt = to_apple_wdt(wdd); + + writel_relaxed(0, wdt->regs + APPLE_WDT_WD1_CUR_TIME); + + return 0; +} + +static int apple_wdt_set_timeout(struct watchdog_device *wdd, unsigned int s) +{ + struct apple_wdt *wdt = to_apple_wdt(wdd); + + writel_relaxed(0, wdt->regs + APPLE_WDT_WD1_CUR_TIME); + writel_relaxed(wdt->clk_rate * s, wdt->regs + APPLE_WDT_WD1_BITE_TIME); + + wdd->timeout = s; + + return 0; +} + +static unsigned int apple_wdt_get_timeleft(struct watchdog_device *wdd) +{ + struct apple_wdt *wdt = to_apple_wdt(wdd); + u32 cur_time, reset_time; + + cur_time = readl_relaxed(wdt->regs + APPLE_WDT_WD1_CUR_TIME); + reset_time = readl_relaxed(wdt->regs + APPLE_WDT_WD1_BITE_TIME); + + return (reset_time - cur_time) / wdt->clk_rate; +} + +static int apple_wdt_restart(struct watchdog_device *wdd, unsigned long mode, + void *cmd) +{ + struct apple_wdt *wdt = to_apple_wdt(wdd); + + writel_relaxed(APPLE_WDT_CTRL_RESET_EN, wdt->regs + APPLE_WDT_WD1_CTRL); + writel_relaxed(0, wdt->regs + APPLE_WDT_WD1_BITE_TIME); + writel_relaxed(0, wdt->regs + APPLE_WDT_WD1_CUR_TIME); + + /* + * Flush writes and then wait for the SoC to reset. Even though the + * reset is queued almost immediately experiments have shown that it + * can take up to ~20-25ms until the SoC is actually reset. Just wait + * 50ms here to be safe. + */ + (void)readl_relaxed(wdt->regs + APPLE_WDT_WD1_CUR_TIME); + mdelay(50); + + return 0; +} + +static void apple_wdt_clk_disable_unprepare(void *data) +{ + clk_disable_unprepare(data); +} + +static struct watchdog_ops apple_wdt_ops = { + .owner = THIS_MODULE, + .start = apple_wdt_start, + .stop = apple_wdt_stop, + .ping = apple_wdt_ping, + .set_timeout = apple_wdt_set_timeout, + .get_timeleft = apple_wdt_get_timeleft, + .restart = apple_wdt_restart, +}; + +static struct watchdog_info apple_wdt_info = { + .identity = "Apple SoC Watchdog", + .options = WDIOF_MAGICCLOSE | WDIOF_KEEPALIVEPING | WDIOF_SETTIMEOUT, +}; + +static int apple_wdt_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct apple_wdt *wdt; + struct clk *clk; + u32 wdt_ctrl; + int ret; + + wdt = devm_kzalloc(dev, sizeof(*wdt), GFP_KERNEL); + if (!wdt) + return -ENOMEM; + + wdt->regs = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(wdt->regs)) + return PTR_ERR(wdt->regs); + + clk = devm_clk_get(dev, NULL); + if (IS_ERR(clk)) + return PTR_ERR(clk); + + ret = clk_prepare_enable(clk); + if (ret) + return ret; + + ret = devm_add_action_or_reset(dev, apple_wdt_clk_disable_unprepare, + clk); + if (ret) + return ret; + + wdt->clk_rate = clk_get_rate(clk); + if (!wdt->clk_rate) + return -EINVAL; + + wdt->wdd.ops = &apple_wdt_ops; + wdt->wdd.info = &apple_wdt_info; + wdt->wdd.max_timeout = U32_MAX / wdt->clk_rate; + wdt->wdd.timeout = APPLE_WDT_TIMEOUT_DEFAULT; + + wdt_ctrl = readl_relaxed(wdt->regs + APPLE_WDT_WD1_CTRL); + if (wdt_ctrl & APPLE_WDT_CTRL_RESET_EN) + set_bit(WDOG_HW_RUNNING, &wdt->wdd.status); + + watchdog_init_timeout(&wdt->wdd, 0, dev); + apple_wdt_set_timeout(&wdt->wdd, wdt->wdd.timeout); + watchdog_stop_on_unregister(&wdt->wdd); + watchdog_set_restart_priority(&wdt->wdd, 128); + + return devm_watchdog_register_device(dev, &wdt->wdd); +} + +static const struct of_device_id apple_wdt_of_match[] = { + { .compatible = "apple,wdt" }, + {}, +}; +MODULE_DEVICE_TABLE(of, apple_wdt_of_match); + +static struct platform_driver apple_wdt_driver = { + .driver = { + .name = "apple-watchdog", + .of_match_table = apple_wdt_of_match, + }, + .probe = apple_wdt_probe, +}; +module_platform_driver(apple_wdt_driver); + +MODULE_DESCRIPTION("Apple SoC watchdog driver"); +MODULE_AUTHOR("Sven Peter "); +MODULE_LICENSE("Dual MIT/GPL"); diff --git a/drivers/watchdog/bcm63xx_wdt.c b/drivers/watchdog/bcm63xx_wdt.c deleted file mode 100644 index 56cc262571a5..000000000000 --- a/drivers/watchdog/bcm63xx_wdt.c +++ /dev/null @@ -1,317 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0+ -/* - * Broadcom BCM63xx SoC watchdog driver - * - * Copyright (C) 2007, Miguel Gaio - * Copyright (C) 2008, Florian Fainelli - * - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include - -#define PFX KBUILD_MODNAME - -#define WDT_HZ 50000000 /* Fclk */ -#define WDT_DEFAULT_TIME 30 /* seconds */ -#define WDT_MAX_TIME 256 /* seconds */ - -static struct { - void __iomem *regs; - struct timer_list timer; - unsigned long inuse; - atomic_t ticks; -} bcm63xx_wdt_device; - -static int expect_close; - -static int wdt_time = WDT_DEFAULT_TIME; -static bool nowayout = WATCHDOG_NOWAYOUT; -module_param(nowayout, bool, 0); -MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default=" - __MODULE_STRING(WATCHDOG_NOWAYOUT) ")"); - -/* HW functions */ -static void bcm63xx_wdt_hw_start(void) -{ - bcm_writel(0xfffffffe, bcm63xx_wdt_device.regs + WDT_DEFVAL_REG); - bcm_writel(WDT_START_1, bcm63xx_wdt_device.regs + WDT_CTL_REG); - bcm_writel(WDT_START_2, bcm63xx_wdt_device.regs + WDT_CTL_REG); -} - -static void bcm63xx_wdt_hw_stop(void) -{ - bcm_writel(WDT_STOP_1, bcm63xx_wdt_device.regs + WDT_CTL_REG); - bcm_writel(WDT_STOP_2, bcm63xx_wdt_device.regs + WDT_CTL_REG); -} - -static void bcm63xx_wdt_isr(void *data) -{ - struct pt_regs *regs = get_irq_regs(); - - die(PFX " fire", regs); -} - -static void bcm63xx_timer_tick(struct timer_list *unused) -{ - if (!atomic_dec_and_test(&bcm63xx_wdt_device.ticks)) { - bcm63xx_wdt_hw_start(); - mod_timer(&bcm63xx_wdt_device.timer, jiffies + HZ); - } else - pr_crit("watchdog will restart system\n"); -} - -static void bcm63xx_wdt_pet(void) -{ - atomic_set(&bcm63xx_wdt_device.ticks, wdt_time); -} - -static void bcm63xx_wdt_start(void) -{ - bcm63xx_wdt_pet(); - bcm63xx_timer_tick(0); -} - -static void bcm63xx_wdt_pause(void) -{ - del_timer_sync(&bcm63xx_wdt_device.timer); - bcm63xx_wdt_hw_stop(); -} - -static int bcm63xx_wdt_settimeout(int new_time) -{ - if ((new_time <= 0) || (new_time > WDT_MAX_TIME)) - return -EINVAL; - - wdt_time = new_time; - - return 0; -} - -static int bcm63xx_wdt_open(struct inode *inode, struct file *file) -{ - if (test_and_set_bit(0, &bcm63xx_wdt_device.inuse)) - return -EBUSY; - - bcm63xx_wdt_start(); - return stream_open(inode, file); -} - -static int bcm63xx_wdt_release(struct inode *inode, struct file *file) -{ - if (expect_close == 42) - bcm63xx_wdt_pause(); - else { - pr_crit("Unexpected close, not stopping watchdog!\n"); - bcm63xx_wdt_start(); - } - clear_bit(0, &bcm63xx_wdt_device.inuse); - expect_close = 0; - return 0; -} - -static ssize_t bcm63xx_wdt_write(struct file *file, const char *data, - size_t len, loff_t *ppos) -{ - if (len) { - if (!nowayout) { - size_t i; - - /* In case it was set long ago */ - expect_close = 0; - - for (i = 0; i != len; i++) { - char c; - if (get_user(c, data + i)) - return -EFAULT; - if (c == 'V') - expect_close = 42; - } - } - bcm63xx_wdt_pet(); - } - return len; -} - -static struct watchdog_info bcm63xx_wdt_info = { - .identity = PFX, - .options = WDIOF_SETTIMEOUT | - WDIOF_KEEPALIVEPING | - WDIOF_MAGICCLOSE, -}; - - -static long bcm63xx_wdt_ioctl(struct file *file, unsigned int cmd, - unsigned long arg) -{ - void __user *argp = (void __user *)arg; - int __user *p = argp; - int new_value, retval = -EINVAL; - - switch (cmd) { - case WDIOC_GETSUPPORT: - return copy_to_user(argp, &bcm63xx_wdt_info, - sizeof(bcm63xx_wdt_info)) ? -EFAULT : 0; - - case WDIOC_GETSTATUS: - case WDIOC_GETBOOTSTATUS: - return put_user(0, p); - - case WDIOC_SETOPTIONS: - if (get_user(new_value, p)) - return -EFAULT; - - if (new_value & WDIOS_DISABLECARD) { - bcm63xx_wdt_pause(); - retval = 0; - } - if (new_value & WDIOS_ENABLECARD) { - bcm63xx_wdt_start(); - retval = 0; - } - - return retval; - - case WDIOC_KEEPALIVE: - bcm63xx_wdt_pet(); - return 0; - - case WDIOC_SETTIMEOUT: - if (get_user(new_value, p)) - return -EFAULT; - - if (bcm63xx_wdt_settimeout(new_value)) - return -EINVAL; - - bcm63xx_wdt_pet(); - - fallthrough; - - case WDIOC_GETTIMEOUT: - return put_user(wdt_time, p); - - default: - return -ENOTTY; - - } -} - -static const struct file_operations bcm63xx_wdt_fops = { - .owner = THIS_MODULE, - .llseek = no_llseek, - .write = bcm63xx_wdt_write, - .unlocked_ioctl = bcm63xx_wdt_ioctl, - .compat_ioctl = compat_ptr_ioctl, - .open = bcm63xx_wdt_open, - .release = bcm63xx_wdt_release, -}; - -static struct miscdevice bcm63xx_wdt_miscdev = { - .minor = WATCHDOG_MINOR, - .name = "watchdog", - .fops = &bcm63xx_wdt_fops, -}; - - -static int bcm63xx_wdt_probe(struct platform_device *pdev) -{ - int ret; - struct resource *r; - - timer_setup(&bcm63xx_wdt_device.timer, bcm63xx_timer_tick, 0); - - r = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!r) { - dev_err(&pdev->dev, "failed to get resources\n"); - return -ENODEV; - } - - bcm63xx_wdt_device.regs = devm_ioremap(&pdev->dev, r->start, - resource_size(r)); - if (!bcm63xx_wdt_device.regs) { - dev_err(&pdev->dev, "failed to remap I/O resources\n"); - return -ENXIO; - } - - ret = bcm63xx_timer_register(TIMER_WDT_ID, bcm63xx_wdt_isr, NULL); - if (ret < 0) { - dev_err(&pdev->dev, "failed to register wdt timer isr\n"); - return ret; - } - - if (bcm63xx_wdt_settimeout(wdt_time)) { - bcm63xx_wdt_settimeout(WDT_DEFAULT_TIME); - dev_info(&pdev->dev, - ": wdt_time value must be 1 <= wdt_time <= 256, using %d\n", - wdt_time); - } - - ret = misc_register(&bcm63xx_wdt_miscdev); - if (ret < 0) { - dev_err(&pdev->dev, "failed to register watchdog device\n"); - goto unregister_timer; - } - - dev_info(&pdev->dev, " started, timer margin: %d sec\n", - WDT_DEFAULT_TIME); - - return 0; - -unregister_timer: - bcm63xx_timer_unregister(TIMER_WDT_ID); - return ret; -} - -static int bcm63xx_wdt_remove(struct platform_device *pdev) -{ - if (!nowayout) - bcm63xx_wdt_pause(); - - misc_deregister(&bcm63xx_wdt_miscdev); - bcm63xx_timer_unregister(TIMER_WDT_ID); - return 0; -} - -static void bcm63xx_wdt_shutdown(struct platform_device *pdev) -{ - bcm63xx_wdt_pause(); -} - -static struct platform_driver bcm63xx_wdt_driver = { - .probe = bcm63xx_wdt_probe, - .remove = bcm63xx_wdt_remove, - .shutdown = bcm63xx_wdt_shutdown, - .driver = { - .name = "bcm63xx-wdt", - } -}; - -module_platform_driver(bcm63xx_wdt_driver); - -MODULE_AUTHOR("Miguel Gaio "); -MODULE_AUTHOR("Florian Fainelli "); -MODULE_DESCRIPTION("Driver for the Broadcom BCM63xx SoC watchdog"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS("platform:bcm63xx-wdt"); diff --git a/drivers/watchdog/bcm7038_wdt.c b/drivers/watchdog/bcm7038_wdt.c index acaaa0005d5b..8656a137e9a4 100644 --- a/drivers/watchdog/bcm7038_wdt.c +++ b/drivers/watchdog/bcm7038_wdt.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include @@ -133,8 +134,10 @@ static void bcm7038_clk_disable_unprepare(void *data) static int bcm7038_wdt_probe(struct platform_device *pdev) { + struct bcm7038_wdt_platform_data *pdata = pdev->dev.platform_data; struct device *dev = &pdev->dev; struct bcm7038_watchdog *wdt; + const char *clk_name = NULL; int err; wdt = devm_kzalloc(dev, sizeof(*wdt), GFP_KERNEL); @@ -147,7 +150,10 @@ static int bcm7038_wdt_probe(struct platform_device *pdev) if (IS_ERR(wdt->base)) return PTR_ERR(wdt->base); - wdt->clk = devm_clk_get(dev, NULL); + if (pdata && pdata->clk_name) + clk_name = pdata->clk_name; + + wdt->clk = devm_clk_get(dev, clk_name); /* If unable to get clock, use default frequency */ if (!IS_ERR(wdt->clk)) { err = clk_prepare_enable(wdt->clk); @@ -217,8 +223,15 @@ static const struct of_device_id bcm7038_wdt_match[] = { }; MODULE_DEVICE_TABLE(of, bcm7038_wdt_match); +static const struct platform_device_id bcm7038_wdt_devtype[] = { + { .name = "bcm63xx-wdt" }, + { /* sentinel */ }, +}; +MODULE_DEVICE_TABLE(platform, bcm7038_wdt_devtype); + static struct platform_driver bcm7038_wdt_driver = { .probe = bcm7038_wdt_probe, + .id_table = bcm7038_wdt_devtype, .driver = { .name = "bcm7038-wdt", .of_match_table = bcm7038_wdt_match, diff --git a/drivers/watchdog/da9063_wdt.c b/drivers/watchdog/da9063_wdt.c index d79ce64e26a9..9adad1862bbd 100644 --- a/drivers/watchdog/da9063_wdt.c +++ b/drivers/watchdog/da9063_wdt.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -169,14 +170,19 @@ static int da9063_wdt_restart(struct watchdog_device *wdd, unsigned long action, void *data) { struct da9063 *da9063 = watchdog_get_drvdata(wdd); + struct i2c_client *client = to_i2c_client(da9063->dev); int ret; - ret = regmap_write(da9063->regmap, DA9063_REG_CONTROL_F, - DA9063_SHUTDOWN); - if (ret) + /* Don't use regmap because it is not atomic safe */ + ret = i2c_smbus_write_byte_data(client, DA9063_REG_CONTROL_F, + DA9063_SHUTDOWN); + if (ret < 0) dev_alert(da9063->dev, "Failed to shutdown (err = %d)\n", ret); + /* wait for reset to assert... */ + mdelay(500); + return ret; } diff --git a/drivers/watchdog/davinci_wdt.c b/drivers/watchdog/davinci_wdt.c index e6eaba6bae5b..584a56893b81 100644 --- a/drivers/watchdog/davinci_wdt.c +++ b/drivers/watchdog/davinci_wdt.c @@ -134,7 +134,7 @@ static unsigned int davinci_wdt_get_timeleft(struct watchdog_device *wdd) timer_counter = ioread32(davinci_wdt->base + TIM12); timer_counter |= ((u64)ioread32(davinci_wdt->base + TIM34) << 32); - do_div(timer_counter, freq); + timer_counter = div64_ul(timer_counter, freq); return wdd->timeout - timer_counter; } diff --git a/drivers/watchdog/f71808e_wdt.c b/drivers/watchdog/f71808e_wdt.c index ee90c5f943f9..7f59c680de25 100644 --- a/drivers/watchdog/f71808e_wdt.c +++ b/drivers/watchdog/f71808e_wdt.c @@ -49,6 +49,7 @@ #define SIO_F81803_ID 0x1210 /* Chipset ID */ #define SIO_F81865_ID 0x0704 /* Chipset ID */ #define SIO_F81866_ID 0x1010 /* Chipset ID */ +#define SIO_F81966_ID 0x1502 /* F81804 chipset ID, same for f81966 */ #define F71808FG_REG_WDO_CONF 0xf0 #define F71808FG_REG_WDT_CONF 0xf5 @@ -105,7 +106,7 @@ MODULE_PARM_DESC(start_withtimeout, "Start watchdog timer on module load with" " given initial timeout. Zero (default) disables this feature."); enum chips { f71808fg, f71858fg, f71862fg, f71868, f71869, f71882fg, f71889fg, - f81803, f81865, f81866}; + f81803, f81865, f81866, f81966}; static const char * const fintek_wdt_names[] = { "f71808fg", @@ -118,6 +119,7 @@ static const char * const fintek_wdt_names[] = { "f81803", "f81865", "f81866", + "f81966" }; /* Super-I/O Function prototypes */ @@ -347,6 +349,7 @@ static int fintek_wdt_start(struct watchdog_device *wdd) break; case f81866: + case f81966: /* * GPIO1 Control Register when 27h BIT3:2 = 01 & BIT0 = 0. * The PIN 70(GPIO15/WDTRST) is controlled by 2Ch: @@ -373,7 +376,7 @@ static int fintek_wdt_start(struct watchdog_device *wdd) superio_select(wd->sioaddr, SIO_F71808FG_LD_WDT); superio_set_bit(wd->sioaddr, SIO_REG_ENABLE, 0); - if (wd->type == f81865 || wd->type == f81866) + if (wd->type == f81865 || wd->type == f81866 || wd->type == f81966) superio_set_bit(wd->sioaddr, F81865_REG_WDO_CONF, F81865_FLAG_WDOUT_EN); else @@ -580,6 +583,9 @@ static int __init fintek_wdt_find(int sioaddr) case SIO_F81866_ID: type = f81866; break; + case SIO_F81966_ID: + type = f81966; + break; default: pr_info("Unrecognized Fintek device: %04x\n", (unsigned int)devid); diff --git a/drivers/watchdog/meson_gxbb_wdt.c b/drivers/watchdog/meson_gxbb_wdt.c index 945f5e65db57..d3c9e2f6e63b 100644 --- a/drivers/watchdog/meson_gxbb_wdt.c +++ b/drivers/watchdog/meson_gxbb_wdt.c @@ -198,7 +198,6 @@ static int meson_gxbb_wdt_probe(struct platform_device *pdev) meson_gxbb_wdt_set_timeout(&data->wdt_dev, data->wdt_dev.timeout); - watchdog_stop_on_reboot(&data->wdt_dev); return devm_watchdog_register_device(dev, &data->wdt_dev); } diff --git a/drivers/watchdog/msc313e_wdt.c b/drivers/watchdog/msc313e_wdt.c index 0d497aa0fb7d..90171431fc59 100644 --- a/drivers/watchdog/msc313e_wdt.c +++ b/drivers/watchdog/msc313e_wdt.c @@ -120,6 +120,10 @@ static int msc313e_wdt_probe(struct platform_device *pdev) priv->wdev.max_timeout = U32_MAX / clk_get_rate(priv->clk); priv->wdev.timeout = MSC313E_WDT_DEFAULT_TIMEOUT; + /* If the period is non-zero the WDT is running */ + if (readw(priv->base + REG_WDT_MAX_PRD_L) | (readw(priv->base + REG_WDT_MAX_PRD_H) << 16)) + set_bit(WDOG_HW_RUNNING, &priv->wdev.status); + watchdog_set_drvdata(&priv->wdev, priv); watchdog_init_timeout(&priv->wdev, timeout, dev); diff --git a/drivers/watchdog/mtk_wdt.c b/drivers/watchdog/mtk_wdt.c index 543cf38bd04e..4577a76dd464 100644 --- a/drivers/watchdog/mtk_wdt.c +++ b/drivers/watchdog/mtk_wdt.c @@ -339,7 +339,7 @@ static int mtk_wdt_probe(struct platform_device *pdev) if (IS_ERR(mtk_wdt->wdt_base)) return PTR_ERR(mtk_wdt->wdt_base); - irq = platform_get_irq(pdev, 0); + irq = platform_get_irq_optional(pdev, 0); if (irq > 0) { err = devm_request_irq(&pdev->dev, irq, mtk_wdt_isr, 0, "wdt_bark", &mtk_wdt->wdt_dev); diff --git a/drivers/watchdog/realtek_otto_wdt.c b/drivers/watchdog/realtek_otto_wdt.c new file mode 100644 index 000000000000..60058a0c3ec4 --- /dev/null +++ b/drivers/watchdog/realtek_otto_wdt.c @@ -0,0 +1,384 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Realtek Otto MIPS platform watchdog + * + * Watchdog timer that will reset the system after timeout, using the selected + * reset mode. + * + * Counter scaling and timeouts: + * - Base prescale of (2 << 25), providing tick duration T_0: 168ms @ 200MHz + * - PRESCALE: logarithmic prescaler adding a factor of {1, 2, 4, 8} + * - Phase 1: Times out after (PHASE1 + 1) × PRESCALE × T_0 + * Generates an interrupt, WDT cannot be stopped after phase 1 + * - Phase 2: starts after phase 1, times out after (PHASE2 + 1) × PRESCALE × T_0 + * Resets the system according to RST_MODE + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define OTTO_WDT_REG_CNTR 0x0 +#define OTTO_WDT_CNTR_PING BIT(31) + +#define OTTO_WDT_REG_INTR 0x4 +#define OTTO_WDT_INTR_PHASE_1 BIT(31) +#define OTTO_WDT_INTR_PHASE_2 BIT(30) + +#define OTTO_WDT_REG_CTRL 0x8 +#define OTTO_WDT_CTRL_ENABLE BIT(31) +#define OTTO_WDT_CTRL_PRESCALE GENMASK(30, 29) +#define OTTO_WDT_CTRL_PHASE1 GENMASK(26, 22) +#define OTTO_WDT_CTRL_PHASE2 GENMASK(19, 15) +#define OTTO_WDT_CTRL_RST_MODE GENMASK(1, 0) +#define OTTO_WDT_MODE_SOC 0 +#define OTTO_WDT_MODE_CPU 1 +#define OTTO_WDT_MODE_SOFTWARE 2 +#define OTTO_WDT_CTRL_DEFAULT OTTO_WDT_MODE_CPU + +#define OTTO_WDT_PRESCALE_MAX 3 + +/* + * One higher than the max values contained in PHASE{1,2}, since a value of 0 + * corresponds to one tick. + */ +#define OTTO_WDT_PHASE_TICKS_MAX 32 + +/* + * The maximum reset delay is actually 2×32 ticks, but that would require large + * pretimeout values for timeouts longer than 32 ticks. Limit the maximum timeout + * to 32 + 1 to ensure small pretimeout values can be configured as expected. + */ +#define OTTO_WDT_TIMEOUT_TICKS_MAX (OTTO_WDT_PHASE_TICKS_MAX + 1) + +struct otto_wdt_ctrl { + struct watchdog_device wdev; + struct device *dev; + void __iomem *base; + unsigned int clk_rate_khz; + int irq_phase1; +}; + +static int otto_wdt_start(struct watchdog_device *wdev) +{ + struct otto_wdt_ctrl *ctrl = watchdog_get_drvdata(wdev); + u32 v; + + v = ioread32(ctrl->base + OTTO_WDT_REG_CTRL); + v |= OTTO_WDT_CTRL_ENABLE; + iowrite32(v, ctrl->base + OTTO_WDT_REG_CTRL); + + return 0; +} + +static int otto_wdt_stop(struct watchdog_device *wdev) +{ + struct otto_wdt_ctrl *ctrl = watchdog_get_drvdata(wdev); + u32 v; + + v = ioread32(ctrl->base + OTTO_WDT_REG_CTRL); + v &= ~OTTO_WDT_CTRL_ENABLE; + iowrite32(v, ctrl->base + OTTO_WDT_REG_CTRL); + + return 0; +} + +static int otto_wdt_ping(struct watchdog_device *wdev) +{ + struct otto_wdt_ctrl *ctrl = watchdog_get_drvdata(wdev); + + iowrite32(OTTO_WDT_CNTR_PING, ctrl->base + OTTO_WDT_REG_CNTR); + + return 0; +} + +static int otto_wdt_tick_ms(struct otto_wdt_ctrl *ctrl, int prescale) +{ + return DIV_ROUND_CLOSEST(1 << (25 + prescale), ctrl->clk_rate_khz); +} + +/* + * The timer asserts the PHASE1/PHASE2 IRQs when the number of ticks exceeds + * the value stored in those fields. This means each phase will run for at least + * one tick, so small values need to be clamped to correctly reflect the timeout. + */ +static inline unsigned int div_round_ticks(unsigned int val, unsigned int tick_duration, + unsigned int min_ticks) +{ + return max(min_ticks, DIV_ROUND_UP(val, tick_duration)); +} + +static int otto_wdt_determine_timeouts(struct watchdog_device *wdev, unsigned int timeout, + unsigned int pretimeout) +{ + struct otto_wdt_ctrl *ctrl = watchdog_get_drvdata(wdev); + unsigned int pretimeout_ms = pretimeout * 1000; + unsigned int timeout_ms = timeout * 1000; + unsigned int prescale_next = 0; + unsigned int phase1_ticks; + unsigned int phase2_ticks; + unsigned int total_ticks; + unsigned int prescale; + unsigned int tick_ms; + u32 v; + + do { + prescale = prescale_next; + if (prescale > OTTO_WDT_PRESCALE_MAX) + return -EINVAL; + + tick_ms = otto_wdt_tick_ms(ctrl, prescale); + total_ticks = div_round_ticks(timeout_ms, tick_ms, 2); + phase1_ticks = div_round_ticks(timeout_ms - pretimeout_ms, tick_ms, 1); + phase2_ticks = total_ticks - phase1_ticks; + + prescale_next++; + } while (phase1_ticks > OTTO_WDT_PHASE_TICKS_MAX + || phase2_ticks > OTTO_WDT_PHASE_TICKS_MAX); + + v = ioread32(ctrl->base + OTTO_WDT_REG_CTRL); + + v &= ~(OTTO_WDT_CTRL_PRESCALE | OTTO_WDT_CTRL_PHASE1 | OTTO_WDT_CTRL_PHASE2); + v |= FIELD_PREP(OTTO_WDT_CTRL_PHASE1, phase1_ticks - 1); + v |= FIELD_PREP(OTTO_WDT_CTRL_PHASE2, phase2_ticks - 1); + v |= FIELD_PREP(OTTO_WDT_CTRL_PRESCALE, prescale); + + iowrite32(v, ctrl->base + OTTO_WDT_REG_CTRL); + + timeout_ms = total_ticks * tick_ms; + ctrl->wdev.timeout = timeout_ms / 1000; + + pretimeout_ms = phase2_ticks * tick_ms; + ctrl->wdev.pretimeout = pretimeout_ms / 1000; + + return 0; +} + +static int otto_wdt_set_timeout(struct watchdog_device *wdev, unsigned int val) +{ + return otto_wdt_determine_timeouts(wdev, val, min(wdev->pretimeout, val - 1)); +} + +static int otto_wdt_set_pretimeout(struct watchdog_device *wdev, unsigned int val) +{ + return otto_wdt_determine_timeouts(wdev, wdev->timeout, val); +} + +static int otto_wdt_restart(struct watchdog_device *wdev, unsigned long reboot_mode, + void *data) +{ + struct otto_wdt_ctrl *ctrl = watchdog_get_drvdata(wdev); + u32 reset_mode; + u32 v; + + disable_irq(ctrl->irq_phase1); + + switch (reboot_mode) { + case REBOOT_SOFT: + reset_mode = OTTO_WDT_MODE_SOFTWARE; + break; + case REBOOT_WARM: + reset_mode = OTTO_WDT_MODE_CPU; + break; + default: + reset_mode = OTTO_WDT_MODE_SOC; + break; + } + + /* Configure for shortest timeout and wait for reset to occur */ + v = FIELD_PREP(OTTO_WDT_CTRL_RST_MODE, reset_mode) | OTTO_WDT_CTRL_ENABLE; + iowrite32(v, ctrl->base + OTTO_WDT_REG_CTRL); + + mdelay(3 * otto_wdt_tick_ms(ctrl, 0)); + + return 0; +} + +static irqreturn_t otto_wdt_phase1_isr(int irq, void *dev_id) +{ + struct otto_wdt_ctrl *ctrl = dev_id; + + iowrite32(OTTO_WDT_INTR_PHASE_1, ctrl->base + OTTO_WDT_REG_INTR); + dev_crit(ctrl->dev, "phase 1 timeout\n"); + watchdog_notify_pretimeout(&ctrl->wdev); + + return IRQ_HANDLED; +} + +static const struct watchdog_ops otto_wdt_ops = { + .owner = THIS_MODULE, + .start = otto_wdt_start, + .stop = otto_wdt_stop, + .ping = otto_wdt_ping, + .set_timeout = otto_wdt_set_timeout, + .set_pretimeout = otto_wdt_set_pretimeout, + .restart = otto_wdt_restart, +}; + +static const struct watchdog_info otto_wdt_info = { + .identity = "Realtek Otto watchdog timer", + .options = WDIOF_KEEPALIVEPING | + WDIOF_MAGICCLOSE | + WDIOF_SETTIMEOUT | + WDIOF_PRETIMEOUT, +}; + +static void otto_wdt_clock_action(void *data) +{ + clk_disable_unprepare(data); +} + +static int otto_wdt_probe_clk(struct otto_wdt_ctrl *ctrl) +{ + struct clk *clk = devm_clk_get(ctrl->dev, NULL); + int ret; + + if (IS_ERR(clk)) + return dev_err_probe(ctrl->dev, PTR_ERR(clk), "Failed to get clock\n"); + + ret = clk_prepare_enable(clk); + if (ret) + return dev_err_probe(ctrl->dev, ret, "Failed to enable clock\n"); + + ret = devm_add_action_or_reset(ctrl->dev, otto_wdt_clock_action, clk); + if (ret) + return ret; + + ctrl->clk_rate_khz = clk_get_rate(clk) / 1000; + if (ctrl->clk_rate_khz == 0) + return dev_err_probe(ctrl->dev, -ENXIO, "Failed to get clock rate\n"); + + return 0; +} + +static int otto_wdt_probe_reset_mode(struct otto_wdt_ctrl *ctrl) +{ + static const char *mode_property = "realtek,reset-mode"; + const struct fwnode_handle *node = ctrl->dev->fwnode; + int mode_count; + u32 mode; + u32 v; + + if (!node) + return -ENXIO; + + mode_count = fwnode_property_string_array_count(node, mode_property); + if (mode_count < 0) + return mode_count; + else if (mode_count == 0) + return 0; + else if (mode_count != 1) + return -EINVAL; + + if (fwnode_property_match_string(node, mode_property, "soc") == 0) + mode = OTTO_WDT_MODE_SOC; + else if (fwnode_property_match_string(node, mode_property, "cpu") == 0) + mode = OTTO_WDT_MODE_CPU; + else if (fwnode_property_match_string(node, mode_property, "software") == 0) + mode = OTTO_WDT_MODE_SOFTWARE; + else + return -EINVAL; + + v = ioread32(ctrl->base + OTTO_WDT_REG_CTRL); + v &= ~OTTO_WDT_CTRL_RST_MODE; + v |= FIELD_PREP(OTTO_WDT_CTRL_RST_MODE, mode); + iowrite32(v, ctrl->base + OTTO_WDT_REG_CTRL); + + return 0; +} + +static int otto_wdt_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct otto_wdt_ctrl *ctrl; + unsigned int max_tick_ms; + int ret; + + ctrl = devm_kzalloc(dev, sizeof(*ctrl), GFP_KERNEL); + if (!ctrl) + return -ENOMEM; + + ctrl->dev = dev; + ctrl->base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(ctrl->base)) + return PTR_ERR(ctrl->base); + + /* Clear any old interrupts and reset initial state */ + iowrite32(OTTO_WDT_INTR_PHASE_1 | OTTO_WDT_INTR_PHASE_2, + ctrl->base + OTTO_WDT_REG_INTR); + iowrite32(OTTO_WDT_CTRL_DEFAULT, ctrl->base + OTTO_WDT_REG_CTRL); + + ret = otto_wdt_probe_clk(ctrl); + if (ret) + return ret; + + ctrl->irq_phase1 = platform_get_irq_byname(pdev, "phase1"); + if (ctrl->irq_phase1 < 0) + return ctrl->irq_phase1; + + ret = devm_request_irq(dev, ctrl->irq_phase1, otto_wdt_phase1_isr, 0, + "realtek-otto-wdt", ctrl); + if (ret) + return dev_err_probe(dev, ret, "Failed to get IRQ for phase1\n"); + + ret = otto_wdt_probe_reset_mode(ctrl); + if (ret) + return dev_err_probe(dev, ret, "Invalid reset mode specified\n"); + + ctrl->wdev.parent = dev; + ctrl->wdev.info = &otto_wdt_info; + ctrl->wdev.ops = &otto_wdt_ops; + + /* + * Since pretimeout cannot be disabled, min. timeout is twice the + * subsystem resolution. Max. timeout is ca. 43s at a bus clock of 200MHz. + */ + ctrl->wdev.min_timeout = 2; + max_tick_ms = otto_wdt_tick_ms(ctrl, OTTO_WDT_PRESCALE_MAX); + ctrl->wdev.max_hw_heartbeat_ms = max_tick_ms * OTTO_WDT_TIMEOUT_TICKS_MAX; + ctrl->wdev.timeout = min(30U, ctrl->wdev.max_hw_heartbeat_ms / 1000); + + watchdog_set_drvdata(&ctrl->wdev, ctrl); + watchdog_init_timeout(&ctrl->wdev, 0, dev); + watchdog_stop_on_reboot(&ctrl->wdev); + watchdog_set_restart_priority(&ctrl->wdev, 128); + + ret = otto_wdt_determine_timeouts(&ctrl->wdev, ctrl->wdev.timeout, 1); + if (ret) + return dev_err_probe(dev, ret, "Failed to set timeout\n"); + + return devm_watchdog_register_device(dev, &ctrl->wdev); +} + +static const struct of_device_id otto_wdt_ids[] = { + { .compatible = "realtek,rtl8380-wdt" }, + { .compatible = "realtek,rtl8390-wdt" }, + { .compatible = "realtek,rtl9300-wdt" }, + { } +}; +MODULE_DEVICE_TABLE(of, otto_wdt_ids); + +static struct platform_driver otto_wdt_driver = { + .probe = otto_wdt_probe, + .driver = { + .name = "realtek-otto-watchdog", + .of_match_table = otto_wdt_ids, + }, +}; +module_platform_driver(otto_wdt_driver); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Sander Vanheule "); +MODULE_DESCRIPTION("Realtek Otto watchdog timer driver"); diff --git a/drivers/watchdog/rzg2l_wdt.c b/drivers/watchdog/rzg2l_wdt.c new file mode 100644 index 000000000000..6b426df34fd6 --- /dev/null +++ b/drivers/watchdog/rzg2l_wdt.c @@ -0,0 +1,263 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Renesas RZ/G2L WDT Watchdog Driver + * + * Copyright (C) 2021 Renesas Electronics Corporation + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define WDTCNT 0x00 +#define WDTSET 0x04 +#define WDTTIM 0x08 +#define WDTINT 0x0C +#define WDTCNT_WDTEN BIT(0) +#define WDTINT_INTDISP BIT(0) + +#define WDT_DEFAULT_TIMEOUT 60U + +/* Setting period time register only 12 bit set in WDTSET[31:20] */ +#define WDTSET_COUNTER_MASK (0xFFF00000) +#define WDTSET_COUNTER_VAL(f) ((f) << 20) + +#define F2CYCLE_NSEC(f) (1000000000 / (f)) + +static bool nowayout = WATCHDOG_NOWAYOUT; +module_param(nowayout, bool, 0); +MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default=" + __MODULE_STRING(WATCHDOG_NOWAYOUT) ")"); + +struct rzg2l_wdt_priv { + void __iomem *base; + struct watchdog_device wdev; + struct reset_control *rstc; + unsigned long osc_clk_rate; + unsigned long delay; +}; + +static void rzg2l_wdt_wait_delay(struct rzg2l_wdt_priv *priv) +{ + /* delay timer when change the setting register */ + ndelay(priv->delay); +} + +static u32 rzg2l_wdt_get_cycle_usec(unsigned long cycle, u32 wdttime) +{ + u64 timer_cycle_us = 1024 * 1024 * (wdttime + 1) * MICRO; + + return div64_ul(timer_cycle_us, cycle); +} + +static void rzg2l_wdt_write(struct rzg2l_wdt_priv *priv, u32 val, unsigned int reg) +{ + if (reg == WDTSET) + val &= WDTSET_COUNTER_MASK; + + writel_relaxed(val, priv->base + reg); + /* Registers other than the WDTINT is always synchronized with WDT_CLK */ + if (reg != WDTINT) + rzg2l_wdt_wait_delay(priv); +} + +static void rzg2l_wdt_init_timeout(struct watchdog_device *wdev) +{ + struct rzg2l_wdt_priv *priv = watchdog_get_drvdata(wdev); + u32 time_out; + + /* Clear Lapsed Time Register and clear Interrupt */ + rzg2l_wdt_write(priv, WDTINT_INTDISP, WDTINT); + /* 2 consecutive overflow cycle needed to trigger reset */ + time_out = (wdev->timeout * (MICRO / 2)) / + rzg2l_wdt_get_cycle_usec(priv->osc_clk_rate, 0); + rzg2l_wdt_write(priv, WDTSET_COUNTER_VAL(time_out), WDTSET); +} + +static int rzg2l_wdt_start(struct watchdog_device *wdev) +{ + struct rzg2l_wdt_priv *priv = watchdog_get_drvdata(wdev); + + reset_control_deassert(priv->rstc); + pm_runtime_get_sync(wdev->parent); + + /* Initialize time out */ + rzg2l_wdt_init_timeout(wdev); + + /* Initialize watchdog counter register */ + rzg2l_wdt_write(priv, 0, WDTTIM); + + /* Enable watchdog timer*/ + rzg2l_wdt_write(priv, WDTCNT_WDTEN, WDTCNT); + + return 0; +} + +static int rzg2l_wdt_stop(struct watchdog_device *wdev) +{ + struct rzg2l_wdt_priv *priv = watchdog_get_drvdata(wdev); + + pm_runtime_put(wdev->parent); + reset_control_assert(priv->rstc); + + return 0; +} + +static int rzg2l_wdt_restart(struct watchdog_device *wdev, + unsigned long action, void *data) +{ + struct rzg2l_wdt_priv *priv = watchdog_get_drvdata(wdev); + + /* Reset the module before we modify any register */ + reset_control_reset(priv->rstc); + pm_runtime_get_sync(wdev->parent); + + /* smallest counter value to reboot soon */ + rzg2l_wdt_write(priv, WDTSET_COUNTER_VAL(1), WDTSET); + + /* Enable watchdog timer*/ + rzg2l_wdt_write(priv, WDTCNT_WDTEN, WDTCNT); + + return 0; +} + +static const struct watchdog_info rzg2l_wdt_ident = { + .options = WDIOF_MAGICCLOSE | WDIOF_KEEPALIVEPING | WDIOF_SETTIMEOUT, + .identity = "Renesas RZ/G2L WDT Watchdog", +}; + +static int rzg2l_wdt_ping(struct watchdog_device *wdev) +{ + struct rzg2l_wdt_priv *priv = watchdog_get_drvdata(wdev); + + rzg2l_wdt_write(priv, WDTINT_INTDISP, WDTINT); + + return 0; +} + +static const struct watchdog_ops rzg2l_wdt_ops = { + .owner = THIS_MODULE, + .start = rzg2l_wdt_start, + .stop = rzg2l_wdt_stop, + .ping = rzg2l_wdt_ping, + .restart = rzg2l_wdt_restart, +}; + +static void rzg2l_wdt_reset_assert_pm_disable_put(void *data) +{ + struct watchdog_device *wdev = data; + struct rzg2l_wdt_priv *priv = watchdog_get_drvdata(wdev); + + pm_runtime_put(wdev->parent); + pm_runtime_disable(wdev->parent); + reset_control_assert(priv->rstc); +} + +static int rzg2l_wdt_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct rzg2l_wdt_priv *priv; + unsigned long pclk_rate; + struct clk *wdt_clk; + int ret; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(priv->base)) + return PTR_ERR(priv->base); + + /* Get watchdog main clock */ + wdt_clk = clk_get(&pdev->dev, "oscclk"); + if (IS_ERR(wdt_clk)) + return dev_err_probe(&pdev->dev, PTR_ERR(wdt_clk), "no oscclk"); + + priv->osc_clk_rate = clk_get_rate(wdt_clk); + clk_put(wdt_clk); + if (!priv->osc_clk_rate) + return dev_err_probe(&pdev->dev, -EINVAL, "oscclk rate is 0"); + + /* Get Peripheral clock */ + wdt_clk = clk_get(&pdev->dev, "pclk"); + if (IS_ERR(wdt_clk)) + return dev_err_probe(&pdev->dev, PTR_ERR(wdt_clk), "no pclk"); + + pclk_rate = clk_get_rate(wdt_clk); + clk_put(wdt_clk); + if (!pclk_rate) + return dev_err_probe(&pdev->dev, -EINVAL, "pclk rate is 0"); + + priv->delay = F2CYCLE_NSEC(priv->osc_clk_rate) * 6 + F2CYCLE_NSEC(pclk_rate) * 9; + + priv->rstc = devm_reset_control_get_exclusive(&pdev->dev, NULL); + if (IS_ERR(priv->rstc)) + return dev_err_probe(&pdev->dev, PTR_ERR(priv->rstc), + "failed to get cpg reset"); + + reset_control_deassert(priv->rstc); + pm_runtime_enable(&pdev->dev); + ret = pm_runtime_resume_and_get(&pdev->dev); + if (ret < 0) { + dev_err(dev, "pm_runtime_resume_and_get failed ret=%pe", ERR_PTR(ret)); + goto out_pm_get; + } + + priv->wdev.info = &rzg2l_wdt_ident; + priv->wdev.ops = &rzg2l_wdt_ops; + priv->wdev.parent = dev; + priv->wdev.min_timeout = 1; + priv->wdev.max_timeout = rzg2l_wdt_get_cycle_usec(priv->osc_clk_rate, 0xfff) / + USEC_PER_SEC; + priv->wdev.timeout = WDT_DEFAULT_TIMEOUT; + + watchdog_set_drvdata(&priv->wdev, priv); + ret = devm_add_action_or_reset(&pdev->dev, + rzg2l_wdt_reset_assert_pm_disable_put, + &priv->wdev); + if (ret < 0) + return ret; + + watchdog_set_nowayout(&priv->wdev, nowayout); + watchdog_stop_on_unregister(&priv->wdev); + + ret = watchdog_init_timeout(&priv->wdev, 0, dev); + if (ret) + dev_warn(dev, "Specified timeout invalid, using default"); + + return devm_watchdog_register_device(&pdev->dev, &priv->wdev); + +out_pm_get: + pm_runtime_disable(dev); + reset_control_assert(priv->rstc); + + return ret; +} + +static const struct of_device_id rzg2l_wdt_ids[] = { + { .compatible = "renesas,rzg2l-wdt", }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, rzg2l_wdt_ids); + +static struct platform_driver rzg2l_wdt_driver = { + .driver = { + .name = "rzg2l_wdt", + .of_match_table = rzg2l_wdt_ids, + }, + .probe = rzg2l_wdt_probe, +}; +module_platform_driver(rzg2l_wdt_driver); + +MODULE_DESCRIPTION("Renesas RZ/G2L WDT Watchdog Driver"); +MODULE_AUTHOR("Biju Das "); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/watchdog/s3c2410_wdt.c b/drivers/watchdog/s3c2410_wdt.c index 2395f353e52d..6db22f2e3a4f 100644 --- a/drivers/watchdog/s3c2410_wdt.c +++ b/drivers/watchdog/s3c2410_wdt.c @@ -56,13 +56,58 @@ #define EXYNOS5_RST_STAT_REG_OFFSET 0x0404 #define EXYNOS5_WDT_DISABLE_REG_OFFSET 0x0408 #define EXYNOS5_WDT_MASK_RESET_REG_OFFSET 0x040c -#define QUIRK_HAS_PMU_CONFIG (1 << 0) -#define QUIRK_HAS_RST_STAT (1 << 1) -#define QUIRK_HAS_WTCLRINT_REG (1 << 2) +#define EXYNOS850_CLUSTER0_NONCPU_OUT 0x1220 +#define EXYNOS850_CLUSTER0_NONCPU_INT_EN 0x1244 +#define EXYNOS850_CLUSTER1_NONCPU_OUT 0x1620 +#define EXYNOS850_CLUSTER1_NONCPU_INT_EN 0x1644 + +#define EXYNOS850_CLUSTER0_WDTRESET_BIT 24 +#define EXYNOS850_CLUSTER1_WDTRESET_BIT 23 + +/** + * DOC: Quirk flags for different Samsung watchdog IP-cores + * + * This driver supports multiple Samsung SoCs, each of which might have + * different set of registers and features supported. As watchdog block + * sometimes requires modifying PMU registers for proper functioning, register + * differences in both watchdog and PMU IP-cores should be accounted for. Quirk + * flags described below serve the purpose of telling the driver about mentioned + * SoC traits, and can be specified in driver data for each particular supported + * device. + * + * %QUIRK_HAS_WTCLRINT_REG: Watchdog block has WTCLRINT register. It's used to + * clear the interrupt once the interrupt service routine is complete. It's + * write-only, writing any values to this register clears the interrupt, but + * reading is not permitted. + * + * %QUIRK_HAS_PMU_MASK_RESET: PMU block has the register for disabling/enabling + * WDT reset request. On old SoCs it's usually called MASK_WDT_RESET_REQUEST, + * new SoCs have CLUSTERx_NONCPU_INT_EN register, which 'mask_bit' value is + * inverted compared to the former one. + * + * %QUIRK_HAS_PMU_RST_STAT: PMU block has RST_STAT (reset status) register, + * which contains bits indicating the reason for most recent CPU reset. If + * present, driver will use this register to check if previous reboot was due to + * watchdog timer reset. + * + * %QUIRK_HAS_PMU_AUTO_DISABLE: PMU block has AUTOMATIC_WDT_RESET_DISABLE + * register. If 'mask_bit' bit is set, PMU will disable WDT reset when + * corresponding processor is in reset state. + * + * %QUIRK_HAS_PMU_CNT_EN: PMU block has some register (e.g. CLUSTERx_NONCPU_OUT) + * with "watchdog counter enable" bit. That bit should be set to make watchdog + * counter running. + */ +#define QUIRK_HAS_WTCLRINT_REG (1 << 0) +#define QUIRK_HAS_PMU_MASK_RESET (1 << 1) +#define QUIRK_HAS_PMU_RST_STAT (1 << 2) +#define QUIRK_HAS_PMU_AUTO_DISABLE (1 << 3) +#define QUIRK_HAS_PMU_CNT_EN (1 << 4) /* These quirks require that we have a PMU register map */ -#define QUIRKS_HAVE_PMUREG (QUIRK_HAS_PMU_CONFIG | \ - QUIRK_HAS_RST_STAT) +#define QUIRKS_HAVE_PMUREG \ + (QUIRK_HAS_PMU_MASK_RESET | QUIRK_HAS_PMU_RST_STAT | \ + QUIRK_HAS_PMU_AUTO_DISABLE | QUIRK_HAS_PMU_CNT_EN) static bool nowayout = WATCHDOG_NOWAYOUT; static int tmr_margin; @@ -90,26 +135,33 @@ MODULE_PARM_DESC(soft_noboot, "Watchdog action, set to 1 to ignore reboots, 0 to * timer reset functionality. * @mask_reset_reg: Offset in pmureg for the register that masks the watchdog * timer reset functionality. + * @mask_reset_inv: If set, mask_reset_reg value will have inverted meaning. * @mask_bit: Bit number for the watchdog timer in the disable register and the * mask reset register. * @rst_stat_reg: Offset in pmureg for the register that has the reset status. * @rst_stat_bit: Bit number in the rst_stat register indicating a watchdog * reset. + * @cnt_en_reg: Offset in pmureg for the register that enables WDT counter. + * @cnt_en_bit: Bit number for "watchdog counter enable" in cnt_en register. * @quirks: A bitfield of quirks. */ struct s3c2410_wdt_variant { int disable_reg; int mask_reset_reg; + bool mask_reset_inv; int mask_bit; int rst_stat_reg; int rst_stat_bit; + int cnt_en_reg; + int cnt_en_bit; u32 quirks; }; struct s3c2410_wdt { struct device *dev; - struct clk *clock; + struct clk *bus_clk; /* for register interface (PCLK) */ + struct clk *src_clk; /* for WDT counter */ void __iomem *reg_base; unsigned int count; spinlock_t lock; @@ -136,8 +188,8 @@ static const struct s3c2410_wdt_variant drv_data_exynos5250 = { .mask_bit = 20, .rst_stat_reg = EXYNOS5_RST_STAT_REG_OFFSET, .rst_stat_bit = 20, - .quirks = QUIRK_HAS_PMU_CONFIG | QUIRK_HAS_RST_STAT \ - | QUIRK_HAS_WTCLRINT_REG, + .quirks = QUIRK_HAS_WTCLRINT_REG | QUIRK_HAS_PMU_MASK_RESET | \ + QUIRK_HAS_PMU_RST_STAT | QUIRK_HAS_PMU_AUTO_DISABLE, }; static const struct s3c2410_wdt_variant drv_data_exynos5420 = { @@ -146,8 +198,8 @@ static const struct s3c2410_wdt_variant drv_data_exynos5420 = { .mask_bit = 0, .rst_stat_reg = EXYNOS5_RST_STAT_REG_OFFSET, .rst_stat_bit = 9, - .quirks = QUIRK_HAS_PMU_CONFIG | QUIRK_HAS_RST_STAT \ - | QUIRK_HAS_WTCLRINT_REG, + .quirks = QUIRK_HAS_WTCLRINT_REG | QUIRK_HAS_PMU_MASK_RESET | \ + QUIRK_HAS_PMU_RST_STAT | QUIRK_HAS_PMU_AUTO_DISABLE, }; static const struct s3c2410_wdt_variant drv_data_exynos7 = { @@ -156,8 +208,32 @@ static const struct s3c2410_wdt_variant drv_data_exynos7 = { .mask_bit = 23, .rst_stat_reg = EXYNOS5_RST_STAT_REG_OFFSET, .rst_stat_bit = 23, /* A57 WDTRESET */ - .quirks = QUIRK_HAS_PMU_CONFIG | QUIRK_HAS_RST_STAT \ - | QUIRK_HAS_WTCLRINT_REG, + .quirks = QUIRK_HAS_WTCLRINT_REG | QUIRK_HAS_PMU_MASK_RESET | \ + QUIRK_HAS_PMU_RST_STAT | QUIRK_HAS_PMU_AUTO_DISABLE, +}; + +static const struct s3c2410_wdt_variant drv_data_exynos850_cl0 = { + .mask_reset_reg = EXYNOS850_CLUSTER0_NONCPU_INT_EN, + .mask_bit = 2, + .mask_reset_inv = true, + .rst_stat_reg = EXYNOS5_RST_STAT_REG_OFFSET, + .rst_stat_bit = EXYNOS850_CLUSTER0_WDTRESET_BIT, + .cnt_en_reg = EXYNOS850_CLUSTER0_NONCPU_OUT, + .cnt_en_bit = 7, + .quirks = QUIRK_HAS_WTCLRINT_REG | QUIRK_HAS_PMU_MASK_RESET | \ + QUIRK_HAS_PMU_RST_STAT | QUIRK_HAS_PMU_CNT_EN, +}; + +static const struct s3c2410_wdt_variant drv_data_exynos850_cl1 = { + .mask_reset_reg = EXYNOS850_CLUSTER1_NONCPU_INT_EN, + .mask_bit = 2, + .mask_reset_inv = true, + .rst_stat_reg = EXYNOS5_RST_STAT_REG_OFFSET, + .rst_stat_bit = EXYNOS850_CLUSTER1_WDTRESET_BIT, + .cnt_en_reg = EXYNOS850_CLUSTER1_NONCPU_OUT, + .cnt_en_bit = 7, + .quirks = QUIRK_HAS_WTCLRINT_REG | QUIRK_HAS_PMU_MASK_RESET | \ + QUIRK_HAS_PMU_RST_STAT | QUIRK_HAS_PMU_CNT_EN, }; static const struct of_device_id s3c2410_wdt_match[] = { @@ -171,6 +247,8 @@ static const struct of_device_id s3c2410_wdt_match[] = { .data = &drv_data_exynos5420 }, { .compatible = "samsung,exynos7-wdt", .data = &drv_data_exynos7 }, + { .compatible = "samsung,exynos850-wdt", + .data = &drv_data_exynos850_cl0 }, {}, }; MODULE_DEVICE_TABLE(of, s3c2410_wdt_match); @@ -187,9 +265,14 @@ MODULE_DEVICE_TABLE(platform, s3c2410_wdt_ids); /* functions */ -static inline unsigned int s3c2410wdt_max_timeout(struct clk *clock) +static inline unsigned long s3c2410wdt_get_freq(struct s3c2410_wdt *wdt) { - unsigned long freq = clk_get_rate(clock); + return clk_get_rate(wdt->src_clk ? wdt->src_clk : wdt->bus_clk); +} + +static inline unsigned int s3c2410wdt_max_timeout(struct s3c2410_wdt *wdt) +{ + const unsigned long freq = s3c2410wdt_get_freq(wdt); return S3C2410_WTCNT_MAXCNT / (freq / (S3C2410_WTCON_PRESCALE_MAX + 1) / S3C2410_WTCON_MAXDIV); @@ -200,35 +283,74 @@ static inline struct s3c2410_wdt *freq_to_wdt(struct notifier_block *nb) return container_of(nb, struct s3c2410_wdt, freq_transition); } -static int s3c2410wdt_mask_and_disable_reset(struct s3c2410_wdt *wdt, bool mask) +static int s3c2410wdt_disable_wdt_reset(struct s3c2410_wdt *wdt, bool mask) { + const u32 mask_val = BIT(wdt->drv_data->mask_bit); + const u32 val = mask ? mask_val : 0; int ret; - u32 mask_val = 1 << wdt->drv_data->mask_bit; - u32 val = 0; - /* No need to do anything if no PMU CONFIG needed */ - if (!(wdt->drv_data->quirks & QUIRK_HAS_PMU_CONFIG)) - return 0; - - if (mask) - val = mask_val; - - ret = regmap_update_bits(wdt->pmureg, - wdt->drv_data->disable_reg, - mask_val, val); - if (ret < 0) - goto error; - - ret = regmap_update_bits(wdt->pmureg, - wdt->drv_data->mask_reset_reg, - mask_val, val); - error: + ret = regmap_update_bits(wdt->pmureg, wdt->drv_data->disable_reg, + mask_val, val); if (ret < 0) dev_err(wdt->dev, "failed to update reg(%d)\n", ret); return ret; } +static int s3c2410wdt_mask_wdt_reset(struct s3c2410_wdt *wdt, bool mask) +{ + const u32 mask_val = BIT(wdt->drv_data->mask_bit); + const bool val_inv = wdt->drv_data->mask_reset_inv; + const u32 val = (mask ^ val_inv) ? mask_val : 0; + int ret; + + ret = regmap_update_bits(wdt->pmureg, wdt->drv_data->mask_reset_reg, + mask_val, val); + if (ret < 0) + dev_err(wdt->dev, "failed to update reg(%d)\n", ret); + + return ret; +} + +static int s3c2410wdt_enable_counter(struct s3c2410_wdt *wdt, bool en) +{ + const u32 mask_val = BIT(wdt->drv_data->cnt_en_bit); + const u32 val = en ? mask_val : 0; + int ret; + + ret = regmap_update_bits(wdt->pmureg, wdt->drv_data->cnt_en_reg, + mask_val, val); + if (ret < 0) + dev_err(wdt->dev, "failed to update reg(%d)\n", ret); + + return ret; +} + +static int s3c2410wdt_enable(struct s3c2410_wdt *wdt, bool en) +{ + int ret; + + if (wdt->drv_data->quirks & QUIRK_HAS_PMU_AUTO_DISABLE) { + ret = s3c2410wdt_disable_wdt_reset(wdt, !en); + if (ret < 0) + return ret; + } + + if (wdt->drv_data->quirks & QUIRK_HAS_PMU_MASK_RESET) { + ret = s3c2410wdt_mask_wdt_reset(wdt, !en); + if (ret < 0) + return ret; + } + + if (wdt->drv_data->quirks & QUIRK_HAS_PMU_CNT_EN) { + ret = s3c2410wdt_enable_counter(wdt, en); + if (ret < 0) + return ret; + } + + return 0; +} + static int s3c2410wdt_keepalive(struct watchdog_device *wdd) { struct s3c2410_wdt *wdt = watchdog_get_drvdata(wdd); @@ -300,7 +422,7 @@ static int s3c2410wdt_set_heartbeat(struct watchdog_device *wdd, unsigned int timeout) { struct s3c2410_wdt *wdt = watchdog_get_drvdata(wdd); - unsigned long freq = clk_get_rate(wdt->clock); + unsigned long freq = s3c2410wdt_get_freq(wdt); unsigned int count; unsigned int divisor = 1; unsigned long wtcon; @@ -482,7 +604,7 @@ static inline unsigned int s3c2410wdt_get_bootstatus(struct s3c2410_wdt *wdt) unsigned int rst_stat; int ret; - if (!(wdt->drv_data->quirks & QUIRK_HAS_RST_STAT)) + if (!(wdt->drv_data->quirks & QUIRK_HAS_PMU_RST_STAT)) return 0; ret = regmap_read(wdt->pmureg, wdt->drv_data->rst_stat_reg, &rst_stat); @@ -498,14 +620,40 @@ static inline const struct s3c2410_wdt_variant * s3c2410_get_wdt_drv_data(struct platform_device *pdev) { const struct s3c2410_wdt_variant *variant; + struct device *dev = &pdev->dev; - variant = of_device_get_match_data(&pdev->dev); + variant = of_device_get_match_data(dev); if (!variant) { /* Device matched by platform_device_id */ variant = (struct s3c2410_wdt_variant *) platform_get_device_id(pdev)->driver_data; } +#ifdef CONFIG_OF + /* Choose Exynos850 driver data w.r.t. cluster index */ + if (variant == &drv_data_exynos850_cl0) { + u32 index; + int err; + + err = of_property_read_u32(dev->of_node, + "samsung,cluster-index", &index); + if (err) { + dev_err(dev, "failed to get cluster index\n"); + return NULL; + } + + switch (index) { + case 0: + return &drv_data_exynos850_cl0; + case 1: + return &drv_data_exynos850_cl1; + default: + dev_err(dev, "wrong cluster index: %u\n", index); + return NULL; + } + } +#endif + return variant; } @@ -513,9 +661,8 @@ static int s3c2410wdt_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct s3c2410_wdt *wdt; - struct resource *wdt_irq; unsigned int wtcon; - int started = 0; + int wdt_irq; int ret; wdt = devm_kzalloc(dev, sizeof(*wdt), GFP_KERNEL); @@ -527,6 +674,9 @@ static int s3c2410wdt_probe(struct platform_device *pdev) wdt->wdt_device = s3c2410_wdd; wdt->drv_data = s3c2410_get_wdt_drv_data(pdev); + if (!wdt->drv_data) + return -EINVAL; + if (wdt->drv_data->quirks & QUIRKS_HAVE_PMUREG) { wdt->pmureg = syscon_regmap_lookup_by_phandle(dev->of_node, "samsung,syscon-phandle"); @@ -536,40 +686,52 @@ static int s3c2410wdt_probe(struct platform_device *pdev) } } - wdt_irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0); - if (wdt_irq == NULL) { - dev_err(dev, "no irq resource specified\n"); - ret = -ENOENT; - goto err; - } + wdt_irq = platform_get_irq(pdev, 0); + if (wdt_irq < 0) + return wdt_irq; /* get the memory region for the watchdog timer */ wdt->reg_base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(wdt->reg_base)) { - ret = PTR_ERR(wdt->reg_base); - goto err; + if (IS_ERR(wdt->reg_base)) + return PTR_ERR(wdt->reg_base); + + wdt->bus_clk = devm_clk_get(dev, "watchdog"); + if (IS_ERR(wdt->bus_clk)) { + dev_err(dev, "failed to find bus clock\n"); + return PTR_ERR(wdt->bus_clk); } - wdt->clock = devm_clk_get(dev, "watchdog"); - if (IS_ERR(wdt->clock)) { - dev_err(dev, "failed to find watchdog clock source\n"); - ret = PTR_ERR(wdt->clock); - goto err; - } - - ret = clk_prepare_enable(wdt->clock); + ret = clk_prepare_enable(wdt->bus_clk); if (ret < 0) { - dev_err(dev, "failed to enable clock\n"); + dev_err(dev, "failed to enable bus clock\n"); return ret; } + /* + * "watchdog_src" clock is optional; if it's not present -- just skip it + * and use "watchdog" clock as both bus and source clock. + */ + wdt->src_clk = devm_clk_get_optional(dev, "watchdog_src"); + if (IS_ERR(wdt->src_clk)) { + dev_err_probe(dev, PTR_ERR(wdt->src_clk), + "failed to get source clock\n"); + ret = PTR_ERR(wdt->src_clk); + goto err_bus_clk; + } + + ret = clk_prepare_enable(wdt->src_clk); + if (ret) { + dev_err(dev, "failed to enable source clock\n"); + goto err_bus_clk; + } + wdt->wdt_device.min_timeout = 1; - wdt->wdt_device.max_timeout = s3c2410wdt_max_timeout(wdt->clock); + wdt->wdt_device.max_timeout = s3c2410wdt_max_timeout(wdt); ret = s3c2410wdt_cpufreq_register(wdt); if (ret < 0) { dev_err(dev, "failed to register cpufreq\n"); - goto err_clk; + goto err_src_clk; } watchdog_set_drvdata(&wdt->wdt_device, wdt); @@ -581,19 +743,19 @@ static int s3c2410wdt_probe(struct platform_device *pdev) ret = s3c2410wdt_set_heartbeat(&wdt->wdt_device, wdt->wdt_device.timeout); if (ret) { - started = s3c2410wdt_set_heartbeat(&wdt->wdt_device, - S3C2410_WATCHDOG_DEFAULT_TIME); - - if (started == 0) - dev_info(dev, - "tmr_margin value out of range, default %d used\n", + ret = s3c2410wdt_set_heartbeat(&wdt->wdt_device, + S3C2410_WATCHDOG_DEFAULT_TIME); + if (ret == 0) { + dev_warn(dev, "tmr_margin value out of range, default %d used\n", S3C2410_WATCHDOG_DEFAULT_TIME); - else - dev_info(dev, "default timer value is out of range, cannot start\n"); + } else { + dev_err(dev, "failed to use default timeout\n"); + goto err_cpufreq; + } } - ret = devm_request_irq(dev, wdt_irq->start, s3c2410wdt_irq, 0, - pdev->name, pdev); + ret = devm_request_irq(dev, wdt_irq, s3c2410wdt_irq, 0, + pdev->name, pdev); if (ret != 0) { dev_err(dev, "failed to install irq (%d)\n", ret); goto err_cpufreq; @@ -605,25 +767,29 @@ static int s3c2410wdt_probe(struct platform_device *pdev) wdt->wdt_device.bootstatus = s3c2410wdt_get_bootstatus(wdt); wdt->wdt_device.parent = dev; + /* + * If "tmr_atboot" param is non-zero, start the watchdog right now. Also + * set WDOG_HW_RUNNING bit, so that watchdog core can kick the watchdog. + * + * If we're not enabling the watchdog, then ensure it is disabled if it + * has been left running from the bootloader or other source. + */ + if (tmr_atboot) { + dev_info(dev, "starting watchdog timer\n"); + s3c2410wdt_start(&wdt->wdt_device); + set_bit(WDOG_HW_RUNNING, &wdt->wdt_device.status); + } else { + s3c2410wdt_stop(&wdt->wdt_device); + } + ret = watchdog_register_device(&wdt->wdt_device); if (ret) goto err_cpufreq; - ret = s3c2410wdt_mask_and_disable_reset(wdt, false); + ret = s3c2410wdt_enable(wdt, true); if (ret < 0) goto err_unregister; - if (tmr_atboot && started == 0) { - dev_info(dev, "starting watchdog timer\n"); - s3c2410wdt_start(&wdt->wdt_device); - } else if (!tmr_atboot) { - /* if we're not enabling the watchdog, then ensure it is - * disabled if it has been left running from the bootloader - * or other source */ - - s3c2410wdt_stop(&wdt->wdt_device); - } - platform_set_drvdata(pdev, wdt); /* print out a statement of readiness */ @@ -643,10 +809,12 @@ static int s3c2410wdt_probe(struct platform_device *pdev) err_cpufreq: s3c2410wdt_cpufreq_deregister(wdt); - err_clk: - clk_disable_unprepare(wdt->clock); + err_src_clk: + clk_disable_unprepare(wdt->src_clk); + + err_bus_clk: + clk_disable_unprepare(wdt->bus_clk); - err: return ret; } @@ -655,7 +823,7 @@ static int s3c2410wdt_remove(struct platform_device *dev) int ret; struct s3c2410_wdt *wdt = platform_get_drvdata(dev); - ret = s3c2410wdt_mask_and_disable_reset(wdt, true); + ret = s3c2410wdt_enable(wdt, false); if (ret < 0) return ret; @@ -663,7 +831,8 @@ static int s3c2410wdt_remove(struct platform_device *dev) s3c2410wdt_cpufreq_deregister(wdt); - clk_disable_unprepare(wdt->clock); + clk_disable_unprepare(wdt->src_clk); + clk_disable_unprepare(wdt->bus_clk); return 0; } @@ -672,8 +841,7 @@ static void s3c2410wdt_shutdown(struct platform_device *dev) { struct s3c2410_wdt *wdt = platform_get_drvdata(dev); - s3c2410wdt_mask_and_disable_reset(wdt, true); - + s3c2410wdt_enable(wdt, false); s3c2410wdt_stop(&wdt->wdt_device); } @@ -688,7 +856,7 @@ static int s3c2410wdt_suspend(struct device *dev) wdt->wtcon_save = readl(wdt->reg_base + S3C2410_WTCON); wdt->wtdat_save = readl(wdt->reg_base + S3C2410_WTDAT); - ret = s3c2410wdt_mask_and_disable_reset(wdt, true); + ret = s3c2410wdt_enable(wdt, false); if (ret < 0) return ret; @@ -708,7 +876,7 @@ static int s3c2410wdt_resume(struct device *dev) writel(wdt->wtdat_save, wdt->reg_base + S3C2410_WTCNT);/* Reset count */ writel(wdt->wtcon_save, wdt->reg_base + S3C2410_WTCON); - ret = s3c2410wdt_mask_and_disable_reset(wdt, false); + ret = s3c2410wdt_enable(wdt, true); if (ret < 0) return ret; diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index d282caf9f037..ea00e1a91250 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -416,11 +416,17 @@ skip_rdma: from_kuid(&init_user_ns, ses->cred_uid)); spin_lock(&ses->chan_lock); + if (CIFS_CHAN_NEEDS_RECONNECT(ses, 0)) + seq_puts(m, "\tPrimary channel: DISCONNECTED "); + if (ses->chan_count > 1) { seq_printf(m, "\n\n\tExtra Channels: %zu ", ses->chan_count-1); - for (j = 1; j < ses->chan_count; j++) + for (j = 1; j < ses->chan_count; j++) { cifs_dump_channel(m, j, &ses->chans[j]); + if (CIFS_CHAN_NEEDS_RECONNECT(ses, j)) + seq_puts(m, "\tDISCONNECTED "); + } } spin_unlock(&ses->chan_lock); diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c index 353bd0dd7026..342717bf1dc2 100644 --- a/fs/cifs/cifs_spnego.c +++ b/fs/cifs/cifs_spnego.c @@ -84,9 +84,9 @@ struct key_type cifs_spnego_key_type = { /* get a key struct with a SPNEGO security blob, suitable for session setup */ struct key * -cifs_get_spnego_key(struct cifs_ses *sesInfo) +cifs_get_spnego_key(struct cifs_ses *sesInfo, + struct TCP_Server_Info *server) { - struct TCP_Server_Info *server = cifs_ses_server(sesInfo); struct sockaddr_in *sa = (struct sockaddr_in *) &server->dstaddr; struct sockaddr_in6 *sa6 = (struct sockaddr_in6 *) &server->dstaddr; char *description, *dp; diff --git a/fs/cifs/cifs_spnego.h b/fs/cifs/cifs_spnego.h index e6a0451877d4..7f102ffeb675 100644 --- a/fs/cifs/cifs_spnego.h +++ b/fs/cifs/cifs_spnego.h @@ -29,7 +29,8 @@ struct cifs_spnego_msg { #ifdef __KERNEL__ extern struct key_type cifs_spnego_key_type; -extern struct key *cifs_get_spnego_key(struct cifs_ses *sesInfo); +extern struct key *cifs_get_spnego_key(struct cifs_ses *sesInfo, + struct TCP_Server_Info *server); #endif /* KERNEL */ #endif /* _CIFS_SPNEGO_H */ diff --git a/fs/cifs/cifs_swn.c b/fs/cifs/cifs_swn.c index 23a1ed2fb769..8f386dd9939e 100644 --- a/fs/cifs/cifs_swn.c +++ b/fs/cifs/cifs_swn.c @@ -498,10 +498,10 @@ static int cifs_swn_reconnect(struct cifs_tcon *tcon, struct sockaddr_storage *a goto unlock; } - spin_lock(&GlobalMid_Lock); + spin_lock(&cifs_tcp_ses_lock); if (tcon->ses->server->tcpStatus != CifsExiting) tcon->ses->server->tcpStatus = CifsNeedReconnect; - spin_unlock(&GlobalMid_Lock); + spin_unlock(&cifs_tcp_ses_lock); unlock: mutex_unlock(&tcon->ses->server->srv_mutex); diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index d118282071b3..0912d8bbbac1 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -141,9 +141,13 @@ int cifs_sign_rqst(struct smb_rqst *rqst, struct TCP_Server_Info *server, if ((cifs_pdu == NULL) || (server == NULL)) return -EINVAL; + spin_lock(&cifs_tcp_ses_lock); if (!(cifs_pdu->Flags2 & SMBFLG2_SECURITY_SIGNATURE) || - server->tcpStatus == CifsNeedNegotiate) + server->tcpStatus == CifsNeedNegotiate) { + spin_unlock(&cifs_tcp_ses_lock); return rc; + } + spin_unlock(&cifs_tcp_ses_lock); if (!server->session_estab) { memcpy(cifs_pdu->Signature.SecuritySignature, "BSRSPYL", 8); diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index dca42aa87d30..36b2e0cb9736 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include "cifsfs.h" #include "cifspdu.h" @@ -202,7 +203,7 @@ cifs_read_super(struct super_block *sb) sb->s_time_max = ts.tv_sec; } - sb->s_magic = CIFS_MAGIC_NUMBER; + sb->s_magic = CIFS_SUPER_MAGIC; sb->s_op = &cifs_super_ops; sb->s_xattr = cifs_xattr_handlers; rc = super_setup_bdi(sb); @@ -773,7 +774,7 @@ cifs_get_root(struct smb3_fs_context *ctx, struct super_block *sb) sep = CIFS_DIR_SEP(cifs_sb); dentry = dget(sb->s_root); - p = s = full_path; + s = full_path; do { struct inode *dir = d_inode(dentry); diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index be74606724c7..f84978b76bb6 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -24,8 +24,6 @@ #include "../smbfs_common/smb2pdu.h" #include "smb2pdu.h" -#define CIFS_MAGIC_NUMBER 0xFF534D42 /* the first four bytes of SMB PDUs */ - #define SMB_PATH_MAX 260 #define CIFS_PORT 445 #define RFC1001_PORT 139 @@ -113,7 +111,13 @@ enum statusEnum { CifsGood, CifsExiting, CifsNeedReconnect, - CifsNeedNegotiate + CifsNeedNegotiate, + CifsInNegotiate, + CifsNeedSessSetup, + CifsInSessSetup, + CifsNeedTcon, + CifsInTcon, + CifsInFilesInvalidate }; enum securityEnum { @@ -263,13 +267,16 @@ struct smb_version_operations { /* check if we need to negotiate */ bool (*need_neg)(struct TCP_Server_Info *); /* negotiate to the server */ - int (*negotiate)(const unsigned int, struct cifs_ses *); + int (*negotiate)(const unsigned int xid, + struct cifs_ses *ses, + struct TCP_Server_Info *server); /* set negotiated write size */ unsigned int (*negotiate_wsize)(struct cifs_tcon *tcon, struct smb3_fs_context *ctx); /* set negotiated read size */ unsigned int (*negotiate_rsize)(struct cifs_tcon *tcon, struct smb3_fs_context *ctx); /* setup smb sessionn */ int (*sess_setup)(const unsigned int, struct cifs_ses *, + struct TCP_Server_Info *server, const struct nls_table *); /* close smb session */ int (*logoff)(const unsigned int, struct cifs_ses *); @@ -414,7 +421,8 @@ struct smb_version_operations { void (*set_lease_key)(struct inode *, struct cifs_fid *); /* generate new lease key */ void (*new_lease_key)(struct cifs_fid *); - int (*generate_signingkey)(struct cifs_ses *); + int (*generate_signingkey)(struct cifs_ses *ses, + struct TCP_Server_Info *server); int (*calc_signature)(struct smb_rqst *, struct TCP_Server_Info *, bool allocate_crypto); int (*set_integrity)(const unsigned int, struct cifs_tcon *tcon, @@ -582,7 +590,7 @@ struct TCP_Server_Info { char server_RFC1001_name[RFC1001_NAME_LEN_WITH_NULL]; struct smb_version_operations *ops; struct smb_version_values *vals; - /* updates to tcpStatus protected by GlobalMid_Lock */ + /* updates to tcpStatus protected by cifs_tcp_ses_lock */ enum statusEnum tcpStatus; /* what we think the status is */ char *hostname; /* hostname portion of UNC string */ struct socket *ssocket; @@ -920,7 +928,7 @@ struct cifs_ses { struct mutex session_mutex; struct TCP_Server_Info *server; /* pointer to server info */ int ses_count; /* reference counter */ - enum statusEnum status; /* updates protected by GlobalMid_Lock */ + enum statusEnum status; /* updates protected by cifs_tcp_ses_lock */ unsigned overrideSecFlg; /* if non-zero override global sec flags */ char *serverOS; /* name of operating system underlying server */ char *serverNOS; /* name of network operating system of server */ @@ -939,17 +947,13 @@ struct cifs_ses { struct ntlmssp_auth *ntlmssp; /* ciphertext, flags, server challenge */ enum securityEnum sectype; /* what security flavor was specified? */ bool sign; /* is signing required? */ - bool need_reconnect:1; /* connection reset, uid now invalid */ bool domainAuto:1; - bool binding:1; /* are we binding the session? */ __u16 session_flags; __u8 smb3signingkey[SMB3_SIGN_KEY_SIZE]; __u8 smb3encryptionkey[SMB3_ENC_DEC_KEY_SIZE]; __u8 smb3decryptionkey[SMB3_ENC_DEC_KEY_SIZE]; __u8 preauth_sha_hash[SMB2_PREAUTH_HASH_SIZE]; - __u8 binding_preauth_sha_hash[SMB2_PREAUTH_HASH_SIZE]; - /* * Network interfaces available on the server this session is * connected to. @@ -969,45 +973,34 @@ struct cifs_ses { spinlock_t chan_lock; /* ========= begin: protected by chan_lock ======== */ #define CIFS_MAX_CHANNELS 16 +#define CIFS_ALL_CHANNELS_SET(ses) \ + ((1UL << (ses)->chan_count) - 1) +#define CIFS_ALL_CHANS_NEED_RECONNECT(ses) \ + ((ses)->chans_need_reconnect == CIFS_ALL_CHANNELS_SET(ses)) +#define CIFS_SET_ALL_CHANS_NEED_RECONNECT(ses) \ + ((ses)->chans_need_reconnect = CIFS_ALL_CHANNELS_SET(ses)) +#define CIFS_CHAN_NEEDS_RECONNECT(ses, index) \ + test_bit((index), &(ses)->chans_need_reconnect) + struct cifs_chan chans[CIFS_MAX_CHANNELS]; - struct cifs_chan *binding_chan; size_t chan_count; size_t chan_max; atomic_t chan_seq; /* round robin state */ + + /* + * chans_need_reconnect is a bitmap indicating which of the channels + * under this smb session needs to be reconnected. + * If not multichannel session, only one bit will be used. + * + * We will ask for sess and tcon reconnection only if all the + * channels are marked for needing reconnection. This will + * enable the sessions on top to continue to live till any + * of the channels below are active. + */ + unsigned long chans_need_reconnect; /* ========= end: protected by chan_lock ======== */ }; -/* - * When binding a new channel, we need to access the channel which isn't fully - * established yet. - */ - -static inline -struct cifs_chan *cifs_ses_binding_channel(struct cifs_ses *ses) -{ - if (ses->binding) - return ses->binding_chan; - else - return NULL; -} - -/* - * Returns the server pointer of the session. When binding a new - * channel this returns the last channel which isn't fully established - * yet. - * - * This function should be use for negprot/sess.setup codepaths. For - * the other requests see cifs_pick_channel(). - */ -static inline -struct TCP_Server_Info *cifs_ses_server(struct cifs_ses *ses) -{ - if (ses->binding) - return ses->binding_chan->server; - else - return ses->server; -} - static inline bool cap_unix(struct cifs_ses *ses) { diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h index d2ff438fd31f..68b9a436af4b 100644 --- a/fs/cifs/cifspdu.h +++ b/fs/cifs/cifspdu.h @@ -2560,7 +2560,7 @@ typedef struct { __le32 EaSize; /* length of the xattrs */ __u8 ShortNameLength; __u8 Reserved; - __u8 ShortName[12]; + __u8 ShortName[24]; char FileName[1]; } __attribute__((packed)) FILE_BOTH_DIRECTORY_INFO; /* level 0x104 FFrsp data */ diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index 4f5a3e857df4..e0dc147e69a8 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -131,7 +131,8 @@ extern int SendReceiveBlockingLock(const unsigned int xid, struct smb_hdr *in_buf , struct smb_hdr *out_buf, int *bytes_returned); -extern int cifs_reconnect(struct TCP_Server_Info *server); +extern int cifs_reconnect(struct TCP_Server_Info *server, + bool mark_smb_session); extern int checkSMB(char *buf, unsigned int len, struct TCP_Server_Info *srvr); extern bool is_valid_oplock_break(char *, struct TCP_Server_Info *); extern bool backup_cred(struct cifs_sb_info *); @@ -164,6 +165,7 @@ extern int small_smb_init_no_tc(const int smb_cmd, const int wct, extern enum securityEnum select_sectype(struct TCP_Server_Info *server, enum securityEnum requested); extern int CIFS_SessSetup(const unsigned int xid, struct cifs_ses *ses, + struct TCP_Server_Info *server, const struct nls_table *nls_cp); extern struct timespec64 cifs_NTtimeToUnix(__le64 utc_nanoseconds_since_1601); extern u64 cifs_UnixTimeToNT(struct timespec64); @@ -293,11 +295,15 @@ extern int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const struct nls_table *nlsc); extern int cifs_negotiate_protocol(const unsigned int xid, - struct cifs_ses *ses); + struct cifs_ses *ses, + struct TCP_Server_Info *server); extern int cifs_setup_session(const unsigned int xid, struct cifs_ses *ses, + struct TCP_Server_Info *server, struct nls_table *nls_info); extern int cifs_enable_signing(struct TCP_Server_Info *server, bool mnt_sign_required); -extern int CIFSSMBNegotiate(const unsigned int xid, struct cifs_ses *ses); +extern int CIFSSMBNegotiate(const unsigned int xid, + struct cifs_ses *ses, + struct TCP_Server_Info *server); extern int CIFSTCon(const unsigned int xid, struct cifs_ses *ses, const char *tree, struct cifs_tcon *tcon, @@ -504,8 +510,10 @@ extern int cifs_verify_signature(struct smb_rqst *rqst, extern int setup_ntlmv2_rsp(struct cifs_ses *, const struct nls_table *); extern void cifs_crypto_secmech_release(struct TCP_Server_Info *server); extern int calc_seckey(struct cifs_ses *); -extern int generate_smb30signingkey(struct cifs_ses *); -extern int generate_smb311signingkey(struct cifs_ses *); +extern int generate_smb30signingkey(struct cifs_ses *ses, + struct TCP_Server_Info *server); +extern int generate_smb311signingkey(struct cifs_ses *ses, + struct TCP_Server_Info *server); extern int CIFSSMBCopy(unsigned int xid, struct cifs_tcon *source_tcon, @@ -601,6 +609,19 @@ bool is_server_using_iface(struct TCP_Server_Info *server, bool is_ses_using_iface(struct cifs_ses *ses, struct cifs_server_iface *iface); void cifs_ses_mark_for_reconnect(struct cifs_ses *ses); +unsigned int +cifs_ses_get_chan_index(struct cifs_ses *ses, + struct TCP_Server_Info *server); +void +cifs_chan_set_need_reconnect(struct cifs_ses *ses, + struct TCP_Server_Info *server); +void +cifs_chan_clear_need_reconnect(struct cifs_ses *ses, + struct TCP_Server_Info *server); +bool +cifs_chan_needs_reconnect(struct cifs_ses *ses, + struct TCP_Server_Info *server); + void extract_unc_hostname(const char *unc, const char **h, size_t *len); int copy_path_name(char *dst, const char *src); int smb2_parse_query_directory(struct cifs_tcon *tcon, struct kvec *rsp_iov, diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 243d17696f06..071e2f21a7db 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -73,6 +73,16 @@ cifs_mark_open_files_invalid(struct cifs_tcon *tcon) struct list_head *tmp; struct list_head *tmp1; + /* only send once per connect */ + spin_lock(&cifs_tcp_ses_lock); + if (tcon->ses->status != CifsGood || + tcon->tidStatus != CifsNeedReconnect) { + spin_unlock(&cifs_tcp_ses_lock); + return; + } + tcon->tidStatus = CifsInFilesInvalidate; + spin_unlock(&cifs_tcp_ses_lock); + /* list all files open on tree connection and mark them invalid */ spin_lock(&tcon->open_file_lock); list_for_each_safe(tmp, tmp1, &tcon->openFileList) { @@ -89,6 +99,11 @@ cifs_mark_open_files_invalid(struct cifs_tcon *tcon) memset(tcon->crfid.fid, 0, sizeof(struct cifs_fid)); mutex_unlock(&tcon->crfid.fid_mutex); + spin_lock(&cifs_tcp_ses_lock); + if (tcon->tidStatus == CifsInFilesInvalidate) + tcon->tidStatus = CifsNeedTcon; + spin_unlock(&cifs_tcp_ses_lock); + /* * BB Add call to invalidate_inodes(sb) for all superblocks mounted * to this tcon. @@ -120,15 +135,18 @@ cifs_reconnect_tcon(struct cifs_tcon *tcon, int smb_command) * only tree disconnect, open, and write, (and ulogoff which does not * have tcon) are allowed as we start force umount */ + spin_lock(&cifs_tcp_ses_lock); if (tcon->tidStatus == CifsExiting) { if (smb_command != SMB_COM_WRITE_ANDX && smb_command != SMB_COM_OPEN_ANDX && smb_command != SMB_COM_TREE_DISCONNECT) { + spin_unlock(&cifs_tcp_ses_lock); cifs_dbg(FYI, "can not send cmd %d while umounting\n", smb_command); return -ENODEV; } } + spin_unlock(&cifs_tcp_ses_lock); retries = server->nr_targets; @@ -148,8 +166,12 @@ cifs_reconnect_tcon(struct cifs_tcon *tcon, int smb_command) } /* are we still trying to reconnect? */ - if (server->tcpStatus != CifsNeedReconnect) + spin_lock(&cifs_tcp_ses_lock); + if (server->tcpStatus != CifsNeedReconnect) { + spin_unlock(&cifs_tcp_ses_lock); break; + } + spin_unlock(&cifs_tcp_ses_lock); if (retries && --retries) continue; @@ -166,31 +188,49 @@ cifs_reconnect_tcon(struct cifs_tcon *tcon, int smb_command) retries = server->nr_targets; } - if (!ses->need_reconnect && !tcon->need_reconnect) + spin_lock(&ses->chan_lock); + if (!cifs_chan_needs_reconnect(ses, server) && !tcon->need_reconnect) { + spin_unlock(&ses->chan_lock); return 0; + } + spin_unlock(&ses->chan_lock); nls_codepage = load_nls_default(); - /* - * need to prevent multiple threads trying to simultaneously - * reconnect the same SMB session - */ - mutex_lock(&ses->session_mutex); - /* * Recheck after acquire mutex. If another thread is negotiating * and the server never sends an answer the socket will be closed * and tcpStatus set to reconnect. */ + spin_lock(&cifs_tcp_ses_lock); if (server->tcpStatus == CifsNeedReconnect) { + spin_unlock(&cifs_tcp_ses_lock); rc = -EHOSTDOWN; - mutex_unlock(&ses->session_mutex); goto out; } + spin_unlock(&cifs_tcp_ses_lock); - rc = cifs_negotiate_protocol(0, ses); - if (rc == 0 && ses->need_reconnect) - rc = cifs_setup_session(0, ses, nls_codepage); + /* + * need to prevent multiple threads trying to simultaneously + * reconnect the same SMB session + */ + spin_lock(&ses->chan_lock); + if (!cifs_chan_needs_reconnect(ses, server)) { + spin_unlock(&ses->chan_lock); + + /* this means that we only need to tree connect */ + if (tcon->need_reconnect) + goto skip_sess_setup; + + rc = -EHOSTDOWN; + goto out; + } + spin_unlock(&ses->chan_lock); + + mutex_lock(&ses->session_mutex); + rc = cifs_negotiate_protocol(0, ses, server); + if (!rc) + rc = cifs_setup_session(0, ses, server, nls_codepage); /* do we need to reconnect tcon? */ if (rc || !tcon->need_reconnect) { @@ -198,6 +238,7 @@ cifs_reconnect_tcon(struct cifs_tcon *tcon, int smb_command) goto out; } +skip_sess_setup: cifs_mark_open_files_invalid(tcon); rc = cifs_tree_connect(0, tcon, nls_codepage); mutex_unlock(&ses->session_mutex); @@ -337,8 +378,13 @@ static int smb_init_no_reconnect(int smb_command, int wct, struct cifs_tcon *tcon, void **request_buf, void **response_buf) { - if (tcon->ses->need_reconnect || tcon->need_reconnect) + spin_lock(&tcon->ses->chan_lock); + if (cifs_chan_needs_reconnect(tcon->ses, tcon->ses->server) || + tcon->need_reconnect) { + spin_unlock(&tcon->ses->chan_lock); return -EHOSTDOWN; + } + spin_unlock(&tcon->ses->chan_lock); return __smb_init(smb_command, wct, tcon, request_buf, response_buf); } @@ -476,14 +522,15 @@ should_set_ext_sec_flag(enum securityEnum sectype) } int -CIFSSMBNegotiate(const unsigned int xid, struct cifs_ses *ses) +CIFSSMBNegotiate(const unsigned int xid, + struct cifs_ses *ses, + struct TCP_Server_Info *server) { NEGOTIATE_REQ *pSMB; NEGOTIATE_RSP *pSMBr; int rc = 0; int bytes_returned; int i; - struct TCP_Server_Info *server = ses->server; u16 count; if (!server) { @@ -600,8 +647,12 @@ CIFSSMBTDis(const unsigned int xid, struct cifs_tcon *tcon) * the tcon is no longer on the list, so no need to take lock before * checking this. */ - if ((tcon->need_reconnect) || (tcon->ses->need_reconnect)) - return 0; + spin_lock(&tcon->ses->chan_lock); + if ((tcon->need_reconnect) || CIFS_ALL_CHANS_NEED_RECONNECT(tcon->ses)) { + spin_unlock(&tcon->ses->chan_lock); + return -EIO; + } + spin_unlock(&tcon->ses->chan_lock); rc = small_smb_init(SMB_COM_TREE_DISCONNECT, 0, tcon, (void **)&smb_buffer); @@ -696,9 +747,14 @@ CIFSSMBLogoff(const unsigned int xid, struct cifs_ses *ses) return -EIO; mutex_lock(&ses->session_mutex); - if (ses->need_reconnect) + spin_lock(&ses->chan_lock); + if (CIFS_ALL_CHANS_NEED_RECONNECT(ses)) { + spin_unlock(&ses->chan_lock); goto session_already_dead; /* no need to send SMBlogoff if uid already closed due to reconnect */ + } + spin_unlock(&ses->chan_lock); + rc = small_smb_init(SMB_COM_LOGOFF_ANDX, 2, NULL, (void **)&pSMB); if (rc) { mutex_unlock(&ses->session_mutex); @@ -1401,7 +1457,7 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) if (server->ops->is_session_expired && server->ops->is_session_expired(buf)) { - cifs_reconnect(server); + cifs_reconnect(server, true); return -1; } diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 68ed29cff7e8..0f36deff790e 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -166,14 +166,17 @@ static void cifs_resolve_server(struct work_struct *work) * Mark all sessions and tcons for reconnect. * * @server needs to be previously set to CifsNeedReconnect. + * */ -static void cifs_mark_tcp_ses_conns_for_reconnect(struct TCP_Server_Info *server) +static void +cifs_mark_tcp_ses_conns_for_reconnect(struct TCP_Server_Info *server, + bool mark_smb_session) { + struct TCP_Server_Info *pserver; struct cifs_ses *ses; struct cifs_tcon *tcon; struct mid_q_entry *mid, *nmid; struct list_head retry_list; - struct TCP_Server_Info *pserver; server->maxBuf = 0; server->max_read = 0; @@ -191,16 +194,37 @@ static void cifs_mark_tcp_ses_conns_for_reconnect(struct TCP_Server_Info *server spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { - ses->need_reconnect = true; - list_for_each_entry(tcon, &ses->tcon_list, tcon_list) + spin_lock(&ses->chan_lock); + if (!mark_smb_session && cifs_chan_needs_reconnect(ses, server)) + goto next_session; + + cifs_chan_set_need_reconnect(ses, server); + + /* If all channels need reconnect, then tcon needs reconnect */ + if (!mark_smb_session && !CIFS_ALL_CHANS_NEED_RECONNECT(ses)) + goto next_session; + + ses->status = CifsNeedReconnect; + + list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { tcon->need_reconnect = true; + tcon->tidStatus = CifsNeedReconnect; + } if (ses->tcon_ipc) ses->tcon_ipc->need_reconnect = true; + +next_session: + spin_unlock(&ses->chan_lock); } spin_unlock(&cifs_tcp_ses_lock); + /* + * before reconnecting the tcp session, mark the smb session (uid) + * and the tid bad so they are not used until reconnected + */ + cifs_dbg(FYI, "%s: marking sessions and tcons for reconnect and tearing down socket\n", + __func__); /* do not want to be sending data on a socket we are freeing */ - cifs_dbg(FYI, "%s: tearing down socket\n", __func__); mutex_lock(&server->srv_mutex); if (server->ssocket) { cifs_dbg(FYI, "State: 0x%x Flags: 0x%lx\n", server->ssocket->state, @@ -248,16 +272,16 @@ static void cifs_mark_tcp_ses_conns_for_reconnect(struct TCP_Server_Info *server static bool cifs_tcp_ses_needs_reconnect(struct TCP_Server_Info *server, int num_targets) { - spin_lock(&GlobalMid_Lock); + spin_lock(&cifs_tcp_ses_lock); server->nr_targets = num_targets; if (server->tcpStatus == CifsExiting) { /* the demux thread will exit normally next time through the loop */ - spin_unlock(&GlobalMid_Lock); + spin_unlock(&cifs_tcp_ses_lock); wake_up(&server->response_q); return false; } server->tcpStatus = CifsNeedReconnect; - spin_unlock(&GlobalMid_Lock); + spin_unlock(&cifs_tcp_ses_lock); return true; } @@ -268,15 +292,21 @@ static bool cifs_tcp_ses_needs_reconnect(struct TCP_Server_Info *server, int num * mark all smb sessions as reconnecting for tcp session * reconnect tcp session * wake up waiters on reconnection? - (not needed currently) + * + * if mark_smb_session is passed as true, unconditionally mark + * the smb session (and tcon) for reconnect as well. This value + * doesn't really matter for non-multichannel scenario. + * */ -static int __cifs_reconnect(struct TCP_Server_Info *server) +static int __cifs_reconnect(struct TCP_Server_Info *server, + bool mark_smb_session) { int rc = 0; if (!cifs_tcp_ses_needs_reconnect(server, 1)) return 0; - cifs_mark_tcp_ses_conns_for_reconnect(server); + cifs_mark_tcp_ses_conns_for_reconnect(server, mark_smb_session); do { try_to_freeze(); @@ -299,10 +329,10 @@ static int __cifs_reconnect(struct TCP_Server_Info *server) } else { atomic_inc(&tcpSesReconnectCount); set_credits(server, 1); - spin_lock(&GlobalMid_Lock); + spin_lock(&cifs_tcp_ses_lock); if (server->tcpStatus != CifsExiting) server->tcpStatus = CifsNeedNegotiate; - spin_unlock(&GlobalMid_Lock); + spin_unlock(&cifs_tcp_ses_lock); cifs_swn_reset_server_dstaddr(server); mutex_unlock(&server->srv_mutex); } @@ -371,7 +401,9 @@ static int reconnect_target_unlocked(struct TCP_Server_Info *server, struct dfs_ return rc; } -static int reconnect_dfs_server(struct TCP_Server_Info *server) +static int +reconnect_dfs_server(struct TCP_Server_Info *server, + bool mark_smb_session) { int rc = 0; const char *refpath = server->current_fullpath + 1; @@ -395,7 +427,7 @@ static int reconnect_dfs_server(struct TCP_Server_Info *server) if (!cifs_tcp_ses_needs_reconnect(server, num_targets)) return 0; - cifs_mark_tcp_ses_conns_for_reconnect(server); + cifs_mark_tcp_ses_conns_for_reconnect(server, mark_smb_session); do { try_to_freeze(); @@ -416,10 +448,10 @@ static int reconnect_dfs_server(struct TCP_Server_Info *server) */ atomic_inc(&tcpSesReconnectCount); set_credits(server, 1); - spin_lock(&GlobalMid_Lock); + spin_lock(&cifs_tcp_ses_lock); if (server->tcpStatus != CifsExiting) server->tcpStatus = CifsNeedNegotiate; - spin_unlock(&GlobalMid_Lock); + spin_unlock(&cifs_tcp_ses_lock); cifs_swn_reset_server_dstaddr(server); mutex_unlock(&server->srv_mutex); } while (server->tcpStatus == CifsNeedReconnect); @@ -430,29 +462,32 @@ static int reconnect_dfs_server(struct TCP_Server_Info *server) dfs_cache_free_tgts(&tl); /* Need to set up echo worker again once connection has been established */ + spin_lock(&cifs_tcp_ses_lock); if (server->tcpStatus == CifsNeedNegotiate) mod_delayed_work(cifsiod_wq, &server->echo, 0); + spin_unlock(&cifs_tcp_ses_lock); + wake_up(&server->response_q); return rc; } -int cifs_reconnect(struct TCP_Server_Info *server) +int cifs_reconnect(struct TCP_Server_Info *server, bool mark_smb_session) { /* If tcp session is not an dfs connection, then reconnect to last target server */ spin_lock(&cifs_tcp_ses_lock); if (!server->is_dfs_conn || !server->origin_fullpath || !server->leaf_fullpath) { spin_unlock(&cifs_tcp_ses_lock); - return __cifs_reconnect(server); + return __cifs_reconnect(server, mark_smb_session); } spin_unlock(&cifs_tcp_ses_lock); - return reconnect_dfs_server(server); + return reconnect_dfs_server(server, mark_smb_session); } #else -int cifs_reconnect(struct TCP_Server_Info *server) +int cifs_reconnect(struct TCP_Server_Info *server, bool mark_smb_session) { - return __cifs_reconnect(server); + return __cifs_reconnect(server, mark_smb_session); } #endif @@ -534,15 +569,18 @@ server_unresponsive(struct TCP_Server_Info *server) * 65s kernel_recvmsg times out, and we see that we haven't gotten * a response in >60s. */ + spin_lock(&cifs_tcp_ses_lock); if ((server->tcpStatus == CifsGood || server->tcpStatus == CifsNeedNegotiate) && (!server->ops->can_echo || server->ops->can_echo(server)) && time_after(jiffies, server->lstrp + 3 * server->echo_interval)) { + spin_unlock(&cifs_tcp_ses_lock); cifs_server_dbg(VFS, "has not responded in %lu seconds. Reconnecting...\n", (3 * server->echo_interval) / HZ); - cifs_reconnect(server); + cifs_reconnect(server, false); return true; } + spin_unlock(&cifs_tcp_ses_lock); return false; } @@ -576,7 +614,7 @@ cifs_readv_from_socket(struct TCP_Server_Info *server, struct msghdr *smb_msg) /* reconnect if no credits and no requests in flight */ if (zero_credits(server)) { - cifs_reconnect(server); + cifs_reconnect(server, false); return -ECONNABORTED; } @@ -587,13 +625,18 @@ cifs_readv_from_socket(struct TCP_Server_Info *server, struct msghdr *smb_msg) else length = sock_recvmsg(server->ssocket, smb_msg, 0); - if (server->tcpStatus == CifsExiting) + spin_lock(&cifs_tcp_ses_lock); + if (server->tcpStatus == CifsExiting) { + spin_unlock(&cifs_tcp_ses_lock); return -ESHUTDOWN; + } if (server->tcpStatus == CifsNeedReconnect) { - cifs_reconnect(server); + spin_unlock(&cifs_tcp_ses_lock); + cifs_reconnect(server, false); return -ECONNABORTED; } + spin_unlock(&cifs_tcp_ses_lock); if (length == -ERESTARTSYS || length == -EAGAIN || @@ -610,7 +653,7 @@ cifs_readv_from_socket(struct TCP_Server_Info *server, struct msghdr *smb_msg) if (length <= 0) { cifs_dbg(FYI, "Received no data or error: %d\n", length); - cifs_reconnect(server); + cifs_reconnect(server, false); return -ECONNABORTED; } } @@ -689,11 +732,11 @@ is_smb_response(struct TCP_Server_Info *server, unsigned char type) * initialize frame). */ cifs_set_port((struct sockaddr *)&server->dstaddr, CIFS_PORT); - cifs_reconnect(server); + cifs_reconnect(server, true); break; default: cifs_server_dbg(VFS, "RFC 1002 unknown response type 0x%x\n", type); - cifs_reconnect(server); + cifs_reconnect(server, true); } return false; @@ -771,9 +814,9 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server) cancel_delayed_work_sync(&server->echo); cancel_delayed_work_sync(&server->resolve); - spin_lock(&GlobalMid_Lock); + spin_lock(&cifs_tcp_ses_lock); server->tcpStatus = CifsExiting; - spin_unlock(&GlobalMid_Lock); + spin_unlock(&cifs_tcp_ses_lock); wake_up_all(&server->response_q); /* check if we have blocked requests that need to free */ @@ -866,7 +909,7 @@ standard_receive3(struct TCP_Server_Info *server, struct mid_q_entry *mid) if (pdu_length > CIFSMaxBufSize + MAX_HEADER_SIZE(server) - server->vals->header_preamble_size) { cifs_server_dbg(VFS, "SMB response too long (%u bytes)\n", pdu_length); - cifs_reconnect(server); + cifs_reconnect(server, true); return -ECONNABORTED; } @@ -913,7 +956,7 @@ cifs_handle_standard(struct TCP_Server_Info *server, struct mid_q_entry *mid) if (server->ops->is_session_expired && server->ops->is_session_expired(buf)) { - cifs_reconnect(server); + cifs_reconnect(server, true); return -1; } @@ -1017,7 +1060,7 @@ next_pdu: server->vals->header_preamble_size) { cifs_server_dbg(VFS, "SMB response too short (%u bytes)\n", server->pdu_size); - cifs_reconnect(server); + cifs_reconnect(server, true); continue; } @@ -1069,7 +1112,7 @@ next_pdu: server->ops->is_status_io_timeout(buf)) { num_io_timeout++; if (num_io_timeout > NUM_STATUS_IO_TIMEOUT) { - cifs_reconnect(server); + cifs_reconnect(server, false); num_io_timeout = 0; continue; } @@ -1390,9 +1433,9 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect) else cancel_delayed_work_sync(&server->reconnect); - spin_lock(&GlobalMid_Lock); + spin_lock(&cifs_tcp_ses_lock); server->tcpStatus = CifsExiting; - spin_unlock(&GlobalMid_Lock); + spin_unlock(&cifs_tcp_ses_lock); cifs_crypto_secmech_release(server); @@ -1545,7 +1588,9 @@ smbd_connected: * to the struct since the kernel thread not created yet * no need to spinlock this update of tcpStatus */ + spin_lock(&cifs_tcp_ses_lock); tcp_ses->tcpStatus = CifsNeedNegotiate; + spin_unlock(&cifs_tcp_ses_lock); if ((ctx->max_credits < 20) || (ctx->max_credits > 60000)) tcp_ses->max_credits = SMB2_MAX_CREDITS_AVAILABLE; @@ -1762,15 +1807,13 @@ void cifs_put_smb_ses(struct cifs_ses *ses) spin_unlock(&cifs_tcp_ses_lock); return; } - spin_unlock(&cifs_tcp_ses_lock); /* ses_count can never go negative */ WARN_ON(ses->ses_count < 0); - spin_lock(&GlobalMid_Lock); if (ses->status == CifsGood) ses->status = CifsExiting; - spin_unlock(&GlobalMid_Lock); + spin_unlock(&cifs_tcp_ses_lock); cifs_free_ipc(ses); @@ -1987,11 +2030,13 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) cifs_dbg(FYI, "Existing smb sess found (status=%d)\n", ses->status); - mutex_lock(&ses->session_mutex); - if (ses->need_reconnect) { + spin_lock(&ses->chan_lock); + if (cifs_chan_needs_reconnect(ses, server)) { + spin_unlock(&ses->chan_lock); cifs_dbg(FYI, "Session needs reconnect\n"); - rc = cifs_negotiate_protocol(xid, ses); + mutex_lock(&ses->session_mutex); + rc = cifs_negotiate_protocol(xid, ses, server); if (rc) { mutex_unlock(&ses->session_mutex); /* problem -- put our ses reference */ @@ -2000,7 +2045,7 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) return ERR_PTR(rc); } - rc = cifs_setup_session(xid, ses, + rc = cifs_setup_session(xid, ses, server, ctx->local_nls); if (rc) { mutex_unlock(&ses->session_mutex); @@ -2009,8 +2054,11 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) free_xid(xid); return ERR_PTR(rc); } + mutex_unlock(&ses->session_mutex); + + spin_lock(&ses->chan_lock); } - mutex_unlock(&ses->session_mutex); + spin_unlock(&ses->chan_lock); /* existing SMB ses has a server reference already */ cifs_put_tcp_session(server, 0); @@ -2060,28 +2108,33 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) ses->sectype = ctx->sectype; ses->sign = ctx->sign; - mutex_lock(&ses->session_mutex); /* add server as first channel */ spin_lock(&ses->chan_lock); ses->chans[0].server = server; ses->chan_count = 1; ses->chan_max = ctx->multichannel ? ctx->max_channels:1; + ses->chans_need_reconnect = 1; spin_unlock(&ses->chan_lock); - rc = cifs_negotiate_protocol(xid, ses); + mutex_lock(&ses->session_mutex); + rc = cifs_negotiate_protocol(xid, ses, server); if (!rc) - rc = cifs_setup_session(xid, ses, ctx->local_nls); + rc = cifs_setup_session(xid, ses, server, ctx->local_nls); + mutex_unlock(&ses->session_mutex); /* each channel uses a different signing key */ memcpy(ses->chans[0].signkey, ses->smb3signingkey, sizeof(ses->smb3signingkey)); - mutex_unlock(&ses->session_mutex); if (rc) goto get_ses_fail; - /* success, put it on the list and add it as first channel */ + /* + * success, put it on the list and add it as first channel + * note: the session becomes active soon after this. So you'll + * need to lock before changing something in the session. + */ spin_lock(&cifs_tcp_ses_lock); list_add(&ses->smb_ses_list, &server->smb_ses_list); spin_unlock(&cifs_tcp_ses_lock); @@ -2161,6 +2214,9 @@ cifs_put_tcon(struct cifs_tcon *tcon) /* tc_count can never go negative */ WARN_ON(tcon->tc_count < 0); + list_del_init(&tcon->tcon_list); + spin_unlock(&cifs_tcp_ses_lock); + if (tcon->use_witness) { int rc; @@ -2171,9 +2227,6 @@ cifs_put_tcon(struct cifs_tcon *tcon) } } - list_del_init(&tcon->tcon_list); - spin_unlock(&cifs_tcp_ses_lock); - xid = get_xid(); if (ses->server->ops->tree_disconnect) ses->server->ops->tree_disconnect(xid, tcon); @@ -2290,10 +2343,6 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) } } - /* - * BB Do we need to wrap session_mutex around this TCon call and Unix - * SetFS as we do on SessSetup and reconnect? - */ xid = get_xid(); rc = ses->server->ops->tree_connect(xid, ses, ctx->UNC, tcon, ctx->local_nls); @@ -3029,12 +3078,15 @@ static int mount_get_conns(struct mount_ctx *mnt_ctx) * for just this mount. */ reset_cifs_unix_caps(xid, tcon, cifs_sb, ctx); + spin_lock(&cifs_tcp_ses_lock); if ((tcon->ses->server->tcpStatus == CifsNeedReconnect) && (le64_to_cpu(tcon->fsUnixInfo.Capability) & CIFS_UNIX_TRANSPORT_ENCRYPTION_MANDATORY_CAP)) { + spin_unlock(&cifs_tcp_ses_lock); rc = -EACCES; goto out; } + spin_unlock(&cifs_tcp_ses_lock); } else tcon->unix_ext = 0; /* server does not support them */ @@ -3709,7 +3761,9 @@ CIFSTCon(const unsigned int xid, struct cifs_ses *ses, if (rc == 0) { bool is_unicode; + spin_lock(&cifs_tcp_ses_lock); tcon->tidStatus = CifsGood; + spin_unlock(&cifs_tcp_ses_lock); tcon->need_reconnect = false; tcon->tid = smb_buffer_response->Tid; bcc_ptr = pByteArea(smb_buffer_response); @@ -3799,26 +3853,32 @@ cifs_umount(struct cifs_sb_info *cifs_sb) } int -cifs_negotiate_protocol(const unsigned int xid, struct cifs_ses *ses) +cifs_negotiate_protocol(const unsigned int xid, struct cifs_ses *ses, + struct TCP_Server_Info *server) { int rc = 0; - struct TCP_Server_Info *server = cifs_ses_server(ses); if (!server->ops->need_neg || !server->ops->negotiate) return -ENOSYS; /* only send once per connect */ - if (!server->ops->need_neg(server)) + spin_lock(&cifs_tcp_ses_lock); + if (!server->ops->need_neg(server) || + server->tcpStatus != CifsNeedNegotiate) { + spin_unlock(&cifs_tcp_ses_lock); return 0; + } + server->tcpStatus = CifsInNegotiate; + spin_unlock(&cifs_tcp_ses_lock); - rc = server->ops->negotiate(xid, ses); + rc = server->ops->negotiate(xid, ses, server); if (rc == 0) { - spin_lock(&GlobalMid_Lock); - if (server->tcpStatus == CifsNeedNegotiate) - server->tcpStatus = CifsGood; + spin_lock(&cifs_tcp_ses_lock); + if (server->tcpStatus == CifsInNegotiate) + server->tcpStatus = CifsNeedSessSetup; else rc = -EHOSTDOWN; - spin_unlock(&GlobalMid_Lock); + spin_unlock(&cifs_tcp_ses_lock); } return rc; @@ -3826,12 +3886,26 @@ cifs_negotiate_protocol(const unsigned int xid, struct cifs_ses *ses) int cifs_setup_session(const unsigned int xid, struct cifs_ses *ses, + struct TCP_Server_Info *server, struct nls_table *nls_info) { int rc = -ENOSYS; - struct TCP_Server_Info *server = cifs_ses_server(ses); + bool is_binding = false; - if (!ses->binding) { + /* only send once per connect */ + spin_lock(&cifs_tcp_ses_lock); + if (server->tcpStatus != CifsNeedSessSetup) { + spin_unlock(&cifs_tcp_ses_lock); + return 0; + } + ses->status = CifsInSessSetup; + spin_unlock(&cifs_tcp_ses_lock); + + spin_lock(&ses->chan_lock); + is_binding = !CIFS_ALL_CHANS_NEED_RECONNECT(ses); + spin_unlock(&ses->chan_lock); + + if (!is_binding) { ses->capabilities = server->capabilities; if (!linuxExtEnabled) ses->capabilities &= (~server->vals->cap_unix); @@ -3849,7 +3923,7 @@ cifs_setup_session(const unsigned int xid, struct cifs_ses *ses, server->sec_mode, server->capabilities, server->timeAdj); if (server->ops->sess_setup) - rc = server->ops->sess_setup(xid, ses, nls_info); + rc = server->ops->sess_setup(xid, ses, server, nls_info); if (rc) cifs_server_dbg(VFS, "Send error in SessSetup = %d\n", rc); @@ -4197,6 +4271,17 @@ static int __tree_connect_dfs_target(const unsigned int xid, struct cifs_tcon *t struct dfs_cache_tgt_iterator *tit; bool target_match; + /* only send once per connect */ + spin_lock(&cifs_tcp_ses_lock); + if (tcon->ses->status != CifsGood || + (tcon->tidStatus != CifsNew && + tcon->tidStatus != CifsNeedTcon)) { + spin_unlock(&cifs_tcp_ses_lock); + return 0; + } + tcon->tidStatus = CifsInTcon; + spin_unlock(&cifs_tcp_ses_lock); + extract_unc_hostname(server->hostname, &tcp_host, &tcp_host_len); tit = dfs_cache_get_tgt_iterator(tl); @@ -4355,6 +4440,17 @@ int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const stru { const struct smb_version_operations *ops = tcon->ses->server->ops; + /* only send once per connect */ + spin_lock(&cifs_tcp_ses_lock); + if (tcon->ses->status != CifsGood || + (tcon->tidStatus != CifsNew && + tcon->tidStatus != CifsNeedTcon)) { + spin_unlock(&cifs_tcp_ses_lock); + return 0; + } + tcon->tidStatus = CifsInTcon; + spin_unlock(&cifs_tcp_ses_lock); + return ops->tree_connect(xid, tcon->ses, tcon->treeName, tcon, nlsc); } #endif diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c index fa9fbd6a819c..43b16b6d108c 100644 --- a/fs/cifs/netmisc.c +++ b/fs/cifs/netmisc.c @@ -896,10 +896,10 @@ map_and_check_smb_error(struct mid_q_entry *mid, bool logErr) if (class == ERRSRV && code == ERRbaduid) { cifs_dbg(FYI, "Server returned 0x%x, reconnecting session...\n", code); - spin_lock(&GlobalMid_Lock); + spin_lock(&cifs_tcp_ses_lock); if (mid->server->tcpStatus != CifsExiting) mid->server->tcpStatus = CifsNeedReconnect; - spin_unlock(&GlobalMid_Lock); + spin_unlock(&cifs_tcp_ses_lock); } } diff --git a/fs/cifs/ntlmssp.h b/fs/cifs/ntlmssp.h index fe707f45da89..6d242af536cb 100644 --- a/fs/cifs/ntlmssp.h +++ b/fs/cifs/ntlmssp.h @@ -121,7 +121,9 @@ typedef struct _AUTHENTICATE_MESSAGE { int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len, struct cifs_ses *ses); int build_ntlmssp_negotiate_blob(unsigned char **pbuffer, u16 *buflen, struct cifs_ses *ses, + struct TCP_Server_Info *server, const struct nls_table *nls_cp); int build_ntlmssp_auth_blob(unsigned char **pbuffer, u16 *buflen, struct cifs_ses *ses, + struct TCP_Server_Info *server, const struct nls_table *nls_cp); diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index 035dc3e245dc..d12490e12be5 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -65,6 +65,53 @@ bool is_ses_using_iface(struct cifs_ses *ses, struct cifs_server_iface *iface) return false; } +unsigned int +cifs_ses_get_chan_index(struct cifs_ses *ses, + struct TCP_Server_Info *server) +{ + unsigned int i; + + for (i = 0; i < ses->chan_count; i++) { + if (ses->chans[i].server == server) + return i; + } + + /* If we didn't find the channel, it is likely a bug */ + WARN_ON(1); + return 0; +} + +void +cifs_chan_set_need_reconnect(struct cifs_ses *ses, + struct TCP_Server_Info *server) +{ + unsigned int chan_index = cifs_ses_get_chan_index(ses, server); + + set_bit(chan_index, &ses->chans_need_reconnect); + cifs_dbg(FYI, "Set reconnect bitmask for chan %u; now 0x%lx\n", + chan_index, ses->chans_need_reconnect); +} + +void +cifs_chan_clear_need_reconnect(struct cifs_ses *ses, + struct TCP_Server_Info *server) +{ + unsigned int chan_index = cifs_ses_get_chan_index(ses, server); + + clear_bit(chan_index, &ses->chans_need_reconnect); + cifs_dbg(FYI, "Cleared reconnect bitmask for chan %u; now 0x%lx\n", + chan_index, ses->chans_need_reconnect); +} + +bool +cifs_chan_needs_reconnect(struct cifs_ses *ses, + struct TCP_Server_Info *server) +{ + unsigned int chan_index = cifs_ses_get_chan_index(ses, server); + + return CIFS_CHAN_NEEDS_RECONNECT(ses, chan_index); +} + /* returns number of channels added */ int cifs_try_adding_channels(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses) { @@ -261,9 +308,8 @@ cifs_ses_add_channel(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses, chan_server = cifs_get_tcp_session(&ctx, ses->server); - mutex_lock(&ses->session_mutex); spin_lock(&ses->chan_lock); - chan = ses->binding_chan = &ses->chans[ses->chan_count]; + chan = &ses->chans[ses->chan_count]; chan->server = chan_server; if (IS_ERR(chan->server)) { rc = PTR_ERR(chan->server); @@ -271,8 +317,15 @@ cifs_ses_add_channel(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses, spin_unlock(&ses->chan_lock); goto out; } + ses->chan_count++; + atomic_set(&ses->chan_seq, 0); + + /* Mark this channel as needing connect/setup */ + cifs_chan_set_need_reconnect(ses, chan->server); + spin_unlock(&ses->chan_lock); + mutex_lock(&ses->session_mutex); /* * We need to allocate the server crypto now as we will need * to sign packets before we generate the channel signing key @@ -281,37 +334,29 @@ cifs_ses_add_channel(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses, rc = smb311_crypto_shash_allocate(chan->server); if (rc) { cifs_dbg(VFS, "%s: crypto alloc failed\n", __func__); + mutex_unlock(&ses->session_mutex); goto out; } - ses->binding = true; - rc = cifs_negotiate_protocol(xid, ses); - if (rc) - goto out; + rc = cifs_negotiate_protocol(xid, ses, chan->server); + if (!rc) + rc = cifs_setup_session(xid, ses, chan->server, cifs_sb->local_nls); - rc = cifs_setup_session(xid, ses, cifs_sb->local_nls); - if (rc) - goto out; - - /* success, put it on the list - * XXX: sharing ses between 2 tcp servers is not possible, the - * way "internal" linked lists works in linux makes element - * only able to belong to one list - * - * the binding session is already established so the rest of - * the code should be able to look it up, no need to add the - * ses to the new server. - */ - - spin_lock(&ses->chan_lock); - ses->chan_count++; - atomic_set(&ses->chan_seq, 0); - spin_unlock(&ses->chan_lock); + mutex_unlock(&ses->session_mutex); out: - ses->binding = false; - ses->binding_chan = NULL; - mutex_unlock(&ses->session_mutex); + if (rc && chan->server) { + spin_lock(&ses->chan_lock); + /* we rely on all bits beyond chan_count to be clear */ + cifs_chan_clear_need_reconnect(ses, chan->server); + ses->chan_count--; + /* + * chan_count should never reach 0 as at least the primary + * channel is always allocated + */ + WARN_ON(ses->chan_count < 1); + spin_unlock(&ses->chan_lock); + } if (rc && chan->server) cifs_put_tcp_session(chan->server, 0); @@ -325,14 +370,16 @@ void cifs_ses_mark_for_reconnect(struct cifs_ses *ses) int i; for (i = 0; i < ses->chan_count; i++) { - spin_lock(&GlobalMid_Lock); + spin_lock(&cifs_tcp_ses_lock); if (ses->chans[i].server->tcpStatus != CifsExiting) ses->chans[i].server->tcpStatus = CifsNeedReconnect; - spin_unlock(&GlobalMid_Lock); + spin_unlock(&cifs_tcp_ses_lock); } } -static __u32 cifs_ssetup_hdr(struct cifs_ses *ses, SESSION_SETUP_ANDX *pSMB) +static __u32 cifs_ssetup_hdr(struct cifs_ses *ses, + struct TCP_Server_Info *server, + SESSION_SETUP_ANDX *pSMB) { __u32 capabilities = 0; @@ -345,7 +392,7 @@ static __u32 cifs_ssetup_hdr(struct cifs_ses *ses, SESSION_SETUP_ANDX *pSMB) pSMB->req.MaxBufferSize = cpu_to_le16(min_t(u32, CIFSMaxBufSize + MAX_CIFS_HDR_SIZE - 4, USHRT_MAX)); - pSMB->req.MaxMpxCount = cpu_to_le16(ses->server->maxReq); + pSMB->req.MaxMpxCount = cpu_to_le16(server->maxReq); pSMB->req.VcNumber = cpu_to_le16(1); /* Now no need to set SMBFLG_CASELESS or obsolete CANONICAL PATH */ @@ -356,7 +403,7 @@ static __u32 cifs_ssetup_hdr(struct cifs_ses *ses, SESSION_SETUP_ANDX *pSMB) capabilities = CAP_LARGE_FILES | CAP_NT_SMBS | CAP_LEVEL_II_OPLOCKS | CAP_LARGE_WRITE_X | CAP_LARGE_READ_X; - if (ses->server->sign) + if (server->sign) pSMB->req.hdr.Flags2 |= SMBFLG2_SECURITY_SIGNATURE; if (ses->capabilities & CAP_UNICODE) { @@ -719,10 +766,10 @@ static inline void cifs_security_buffer_from_str(SECURITY_BUFFER *pbuf, int build_ntlmssp_negotiate_blob(unsigned char **pbuffer, u16 *buflen, struct cifs_ses *ses, + struct TCP_Server_Info *server, const struct nls_table *nls_cp) { int rc = 0; - struct TCP_Server_Info *server = cifs_ses_server(ses); NEGOTIATE_MESSAGE *sec_blob; __u32 flags; unsigned char *tmp; @@ -776,6 +823,7 @@ setup_ntlm_neg_ret: int build_ntlmssp_auth_blob(unsigned char **pbuffer, u16 *buflen, struct cifs_ses *ses, + struct TCP_Server_Info *server, const struct nls_table *nls_cp) { int rc; @@ -912,6 +960,7 @@ cifs_select_sectype(struct TCP_Server_Info *server, enum securityEnum requested) struct sess_data { unsigned int xid; struct cifs_ses *ses; + struct TCP_Server_Info *server; struct nls_table *nls_cp; void (*func)(struct sess_data *); int result; @@ -978,30 +1027,36 @@ static int sess_establish_session(struct sess_data *sess_data) { struct cifs_ses *ses = sess_data->ses; + struct TCP_Server_Info *server = sess_data->server; - mutex_lock(&ses->server->srv_mutex); - if (!ses->server->session_estab) { - if (ses->server->sign) { - ses->server->session_key.response = + mutex_lock(&server->srv_mutex); + if (!server->session_estab) { + if (server->sign) { + server->session_key.response = kmemdup(ses->auth_key.response, ses->auth_key.len, GFP_KERNEL); - if (!ses->server->session_key.response) { - mutex_unlock(&ses->server->srv_mutex); + if (!server->session_key.response) { + mutex_unlock(&server->srv_mutex); return -ENOMEM; } - ses->server->session_key.len = + server->session_key.len = ses->auth_key.len; } - ses->server->sequence_number = 0x2; - ses->server->session_estab = true; + server->sequence_number = 0x2; + server->session_estab = true; } - mutex_unlock(&ses->server->srv_mutex); + mutex_unlock(&server->srv_mutex); cifs_dbg(FYI, "CIFS session established successfully\n"); - spin_lock(&GlobalMid_Lock); + spin_lock(&ses->chan_lock); + cifs_chan_clear_need_reconnect(ses, server); + spin_unlock(&ses->chan_lock); + + /* Even if one channel is active, session is in good state */ + spin_lock(&cifs_tcp_ses_lock); + server->tcpStatus = CifsGood; ses->status = CifsGood; - ses->need_reconnect = false; - spin_unlock(&GlobalMid_Lock); + spin_unlock(&cifs_tcp_ses_lock); return 0; } @@ -1036,6 +1091,7 @@ sess_auth_ntlmv2(struct sess_data *sess_data) SESSION_SETUP_ANDX *pSMB; char *bcc_ptr; struct cifs_ses *ses = sess_data->ses; + struct TCP_Server_Info *server = sess_data->server; __u32 capabilities; __u16 bytes_remaining; @@ -1047,7 +1103,7 @@ sess_auth_ntlmv2(struct sess_data *sess_data) pSMB = (SESSION_SETUP_ANDX *)sess_data->iov[0].iov_base; bcc_ptr = sess_data->iov[2].iov_base; - capabilities = cifs_ssetup_hdr(ses, pSMB); + capabilities = cifs_ssetup_hdr(ses, server, pSMB); pSMB->req_no_secext.Capabilities = cpu_to_le32(capabilities); @@ -1145,6 +1201,7 @@ sess_auth_kerberos(struct sess_data *sess_data) SESSION_SETUP_ANDX *pSMB; char *bcc_ptr; struct cifs_ses *ses = sess_data->ses; + struct TCP_Server_Info *server = sess_data->server; __u32 capabilities; __u16 bytes_remaining; struct key *spnego_key = NULL; @@ -1159,9 +1216,9 @@ sess_auth_kerberos(struct sess_data *sess_data) pSMB = (SESSION_SETUP_ANDX *)sess_data->iov[0].iov_base; bcc_ptr = sess_data->iov[2].iov_base; - capabilities = cifs_ssetup_hdr(ses, pSMB); + capabilities = cifs_ssetup_hdr(ses, server, pSMB); - spnego_key = cifs_get_spnego_key(ses); + spnego_key = cifs_get_spnego_key(ses, server); if (IS_ERR(spnego_key)) { rc = PTR_ERR(spnego_key); spnego_key = NULL; @@ -1285,12 +1342,13 @@ _sess_auth_rawntlmssp_assemble_req(struct sess_data *sess_data) { SESSION_SETUP_ANDX *pSMB; struct cifs_ses *ses = sess_data->ses; + struct TCP_Server_Info *server = sess_data->server; __u32 capabilities; char *bcc_ptr; pSMB = (SESSION_SETUP_ANDX *)sess_data->iov[0].iov_base; - capabilities = cifs_ssetup_hdr(ses, pSMB); + capabilities = cifs_ssetup_hdr(ses, server, pSMB); if ((pSMB->req.hdr.Flags2 & SMBFLG2_UNICODE) == 0) { cifs_dbg(VFS, "NTLMSSP requires Unicode support\n"); return -ENOSYS; @@ -1324,6 +1382,7 @@ sess_auth_rawntlmssp_negotiate(struct sess_data *sess_data) struct smb_hdr *smb_buf; SESSION_SETUP_ANDX *pSMB; struct cifs_ses *ses = sess_data->ses; + struct TCP_Server_Info *server = sess_data->server; __u16 bytes_remaining; char *bcc_ptr; unsigned char *ntlmsspblob = NULL; @@ -1351,7 +1410,7 @@ sess_auth_rawntlmssp_negotiate(struct sess_data *sess_data) /* Build security blob before we assemble the request */ rc = build_ntlmssp_negotiate_blob(&ntlmsspblob, - &blob_len, ses, + &blob_len, ses, server, sess_data->nls_cp); if (rc) goto out; @@ -1426,6 +1485,7 @@ sess_auth_rawntlmssp_authenticate(struct sess_data *sess_data) struct smb_hdr *smb_buf; SESSION_SETUP_ANDX *pSMB; struct cifs_ses *ses = sess_data->ses; + struct TCP_Server_Info *server = sess_data->server; __u16 bytes_remaining; char *bcc_ptr; unsigned char *ntlmsspblob = NULL; @@ -1442,7 +1502,8 @@ sess_auth_rawntlmssp_authenticate(struct sess_data *sess_data) pSMB = (SESSION_SETUP_ANDX *)sess_data->iov[0].iov_base; smb_buf = (struct smb_hdr *)pSMB; rc = build_ntlmssp_auth_blob(&ntlmsspblob, - &blob_len, ses, sess_data->nls_cp); + &blob_len, ses, server, + sess_data->nls_cp); if (rc) goto out_free_ntlmsspblob; sess_data->iov[1].iov_len = blob_len; @@ -1526,11 +1587,13 @@ out: sess_data->result = rc; } -static int select_sec(struct cifs_ses *ses, struct sess_data *sess_data) +static int select_sec(struct sess_data *sess_data) { int type; + struct cifs_ses *ses = sess_data->ses; + struct TCP_Server_Info *server = sess_data->server; - type = cifs_select_sectype(ses->server, ses->sectype); + type = cifs_select_sectype(server, ses->sectype); cifs_dbg(FYI, "sess setup type %d\n", type); if (type == Unspecified) { cifs_dbg(VFS, "Unable to select appropriate authentication method!\n"); @@ -1561,7 +1624,8 @@ static int select_sec(struct cifs_ses *ses, struct sess_data *sess_data) } int CIFS_SessSetup(const unsigned int xid, struct cifs_ses *ses, - const struct nls_table *nls_cp) + struct TCP_Server_Info *server, + const struct nls_table *nls_cp) { int rc = 0; struct sess_data *sess_data; @@ -1575,15 +1639,16 @@ int CIFS_SessSetup(const unsigned int xid, struct cifs_ses *ses, if (!sess_data) return -ENOMEM; - rc = select_sec(ses, sess_data); - if (rc) - goto out; - sess_data->xid = xid; sess_data->ses = ses; + sess_data->server = server; sess_data->buf0_type = CIFS_NO_BUFFER; sess_data->nls_cp = (struct nls_table *) nls_cp; + rc = select_sec(sess_data); + if (rc) + goto out; + while (sess_data->func) sess_data->func(sess_data); diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index 3b83839fc2c2..8272c91e15ef 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -7,6 +7,7 @@ #include #include +#include #include "cifsglob.h" #include "cifsproto.h" #include "cifs_debug.h" @@ -163,7 +164,7 @@ cifs_get_next_mid(struct TCP_Server_Info *server) { __u64 mid = 0; __u16 last_mid, cur_mid; - bool collision; + bool collision, reconnect = false; spin_lock(&GlobalMid_Lock); @@ -215,7 +216,7 @@ cifs_get_next_mid(struct TCP_Server_Info *server) * an eventual reconnect to clean out the pending_mid_q. */ if (num_mids > 32768) - server->tcpStatus = CifsNeedReconnect; + reconnect = true; if (!collision) { mid = (__u64)cur_mid; @@ -225,6 +226,13 @@ cifs_get_next_mid(struct TCP_Server_Info *server) cur_mid++; } spin_unlock(&GlobalMid_Lock); + + if (reconnect) { + spin_lock(&cifs_tcp_ses_lock); + server->tcpStatus = CifsNeedReconnect; + spin_unlock(&cifs_tcp_ses_lock); + } + return mid; } @@ -414,14 +422,16 @@ cifs_need_neg(struct TCP_Server_Info *server) } static int -cifs_negotiate(const unsigned int xid, struct cifs_ses *ses) +cifs_negotiate(const unsigned int xid, + struct cifs_ses *ses, + struct TCP_Server_Info *server) { int rc; - rc = CIFSSMBNegotiate(xid, ses); + rc = CIFSSMBNegotiate(xid, ses, server); if (rc == -EAGAIN) { /* retry only once on 1st time connection */ - set_credits(ses->server, 1); - rc = CIFSSMBNegotiate(xid, ses); + set_credits(server, 1); + rc = CIFSSMBNegotiate(xid, ses, server); if (rc == -EAGAIN) rc = -EHOSTDOWN; } @@ -878,7 +888,7 @@ cifs_queryfs(const unsigned int xid, struct cifs_tcon *tcon, { int rc = -EOPNOTSUPP; - buf->f_type = CIFS_MAGIC_NUMBER; + buf->f_type = CIFS_SUPER_MAGIC; /* * We could add a second check for a QFS Unix capability bit diff --git a/fs/cifs/smb2glob.h b/fs/cifs/smb2glob.h index ca692b2283cd..4125fd113cfb 100644 --- a/fs/cifs/smb2glob.h +++ b/fs/cifs/smb2glob.h @@ -13,8 +13,6 @@ #ifndef _SMB2_GLOB_H #define _SMB2_GLOB_H -#define SMB2_MAGIC_NUMBER 0xFE534D42 - /* ***************************************************************** * Constants go here diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index cdcdef32759e..b25623e3fe3d 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -847,16 +847,17 @@ smb2_handle_cancelled_mid(struct mid_q_entry *mid, struct TCP_Server_Info *serve * SMB2 header. * * @ses: server session structure + * @server: pointer to server info * @iov: array containing the SMB request we will send to the server * @nvec: number of array entries for the iov */ int -smb311_update_preauth_hash(struct cifs_ses *ses, struct kvec *iov, int nvec) +smb311_update_preauth_hash(struct cifs_ses *ses, struct TCP_Server_Info *server, + struct kvec *iov, int nvec) { int i, rc; struct sdesc *d; struct smb2_hdr *hdr; - struct TCP_Server_Info *server = cifs_ses_server(ses); hdr = (struct smb2_hdr *)iov[0].iov_base; /* neg prot are always taken */ diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index c5b1dea54ebc..af5d0830bc8a 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -13,6 +13,7 @@ #include #include #include +#include #include "cifsfs.h" #include "cifsglob.h" #include "smb2pdu.h" @@ -121,9 +122,13 @@ smb2_add_credits(struct TCP_Server_Info *server, optype, scredits, add); } + spin_lock(&cifs_tcp_ses_lock); if (server->tcpStatus == CifsNeedReconnect - || server->tcpStatus == CifsExiting) + || server->tcpStatus == CifsExiting) { + spin_unlock(&cifs_tcp_ses_lock); return; + } + spin_unlock(&cifs_tcp_ses_lock); switch (rc) { case -1: @@ -208,11 +213,15 @@ smb2_wait_mtu_credits(struct TCP_Server_Info *server, unsigned int size, return rc; spin_lock(&server->req_lock); } else { + spin_unlock(&server->req_lock); + spin_lock(&cifs_tcp_ses_lock); if (server->tcpStatus == CifsExiting) { - spin_unlock(&server->req_lock); + spin_unlock(&cifs_tcp_ses_lock); return -ENOENT; } + spin_unlock(&cifs_tcp_ses_lock); + spin_lock(&server->req_lock); scredits = server->credits; /* can deadlock with reopen */ if (scredits <= 8) { @@ -384,14 +393,16 @@ smb2_need_neg(struct TCP_Server_Info *server) } static int -smb2_negotiate(const unsigned int xid, struct cifs_ses *ses) +smb2_negotiate(const unsigned int xid, + struct cifs_ses *ses, + struct TCP_Server_Info *server) { int rc; spin_lock(&GlobalMid_Lock); - cifs_ses_server(ses)->CurrentMid = 0; + server->CurrentMid = 0; spin_unlock(&GlobalMid_Lock); - rc = SMB2_negotiate(xid, ses); + rc = SMB2_negotiate(xid, ses, server); /* BB we probably don't need to retry with modern servers */ if (rc == -EAGAIN) rc = -EHOSTDOWN; @@ -2747,7 +2758,7 @@ smb2_queryfs(const unsigned int xid, struct cifs_tcon *tcon, goto qfs_exit; rsp = (struct smb2_query_info_rsp *)rsp_iov.iov_base; - buf->f_type = SMB2_MAGIC_NUMBER; + buf->f_type = SMB2_SUPER_MAGIC; info = (struct smb2_fs_full_size_info *)( le16_to_cpu(rsp->OutputBufferOffset) + (char *)rsp); rc = smb2_validate_iov(le16_to_cpu(rsp->OutputBufferOffset), @@ -2789,7 +2800,7 @@ smb311_queryfs(const unsigned int xid, struct cifs_tcon *tcon, rc = SMB311_posix_qfs_info(xid, tcon, fid.persistent_fid, fid.volatile_fid, buf); - buf->f_type = SMB2_MAGIC_NUMBER; + buf->f_type = SMB2_SUPER_MAGIC; SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); return rc; } @@ -4808,7 +4819,7 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, if (server->ops->is_session_expired && server->ops->is_session_expired(buf)) { if (!is_offloaded) - cifs_reconnect(server); + cifs_reconnect(server, true); return -1; } @@ -4981,10 +4992,12 @@ static void smb2_decrypt_offload(struct work_struct *work) mid->callback(mid); } else { + spin_lock(&cifs_tcp_ses_lock); spin_lock(&GlobalMid_Lock); if (dw->server->tcpStatus == CifsNeedReconnect) { mid->mid_state = MID_RETRY_NEEDED; spin_unlock(&GlobalMid_Lock); + spin_unlock(&cifs_tcp_ses_lock); mid->callback(mid); } else { mid->mid_state = MID_REQUEST_SUBMITTED; @@ -4992,6 +5005,7 @@ static void smb2_decrypt_offload(struct work_struct *work) list_add_tail(&mid->qhead, &dw->server->pending_mid_q); spin_unlock(&GlobalMid_Lock); + spin_unlock(&cifs_tcp_ses_lock); } } cifs_mid_q_entry_release(mid); @@ -5221,13 +5235,13 @@ smb3_receive_transform(struct TCP_Server_Info *server, sizeof(struct smb2_hdr)) { cifs_server_dbg(VFS, "Transform message is too small (%u)\n", pdu_length); - cifs_reconnect(server); + cifs_reconnect(server, true); return -ECONNABORTED; } if (pdu_length < orig_len + sizeof(struct smb2_transform_hdr)) { cifs_server_dbg(VFS, "Transform message is broken\n"); - cifs_reconnect(server); + cifs_reconnect(server, true); return -ECONNABORTED; } diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 8b3670388cda..8d471df69c59 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -162,6 +162,7 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon, if (smb2_command == SMB2_TREE_CONNECT || smb2_command == SMB2_IOCTL) return 0; + spin_lock(&cifs_tcp_ses_lock); if (tcon->tidStatus == CifsExiting) { /* * only tree disconnect, open, and write, @@ -171,11 +172,13 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon, if ((smb2_command != SMB2_WRITE) && (smb2_command != SMB2_CREATE) && (smb2_command != SMB2_TREE_DISCONNECT)) { + spin_unlock(&cifs_tcp_ses_lock); cifs_dbg(FYI, "can not send cmd %d while umounting\n", smb2_command); return -ENODEV; } } + spin_unlock(&cifs_tcp_ses_lock); if ((!tcon->ses) || (tcon->ses->status == CifsExiting) || (!tcon->ses->server) || !server) return -EIO; @@ -214,8 +217,12 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon, } /* are we still trying to reconnect? */ - if (server->tcpStatus != CifsNeedReconnect) + spin_lock(&cifs_tcp_ses_lock); + if (server->tcpStatus != CifsNeedReconnect) { + spin_unlock(&cifs_tcp_ses_lock); break; + } + spin_unlock(&cifs_tcp_ses_lock); if (retries && --retries) continue; @@ -232,64 +239,70 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon, retries = server->nr_targets; } - if (!tcon->ses->need_reconnect && !tcon->need_reconnect) + spin_lock(&ses->chan_lock); + if (!cifs_chan_needs_reconnect(ses, server) && !tcon->need_reconnect) { + spin_unlock(&ses->chan_lock); return 0; + } + cifs_dbg(FYI, "sess reconnect mask: 0x%lx, tcon reconnect: %d", + tcon->ses->chans_need_reconnect, + tcon->need_reconnect); + spin_unlock(&ses->chan_lock); nls_codepage = load_nls_default(); - /* - * need to prevent multiple threads trying to simultaneously reconnect - * the same SMB session - */ - mutex_lock(&tcon->ses->session_mutex); - /* * Recheck after acquire mutex. If another thread is negotiating * and the server never sends an answer the socket will be closed * and tcpStatus set to reconnect. */ + spin_lock(&cifs_tcp_ses_lock); if (server->tcpStatus == CifsNeedReconnect) { + spin_unlock(&cifs_tcp_ses_lock); rc = -EHOSTDOWN; - mutex_unlock(&tcon->ses->session_mutex); goto out; } + spin_unlock(&cifs_tcp_ses_lock); /* - * If we are reconnecting an extra channel, bind + * need to prevent multiple threads trying to simultaneously + * reconnect the same SMB session */ - if (CIFS_SERVER_IS_CHAN(server)) { - ses->binding = true; - ses->binding_chan = cifs_ses_find_chan(ses, server); - } + spin_lock(&ses->chan_lock); + if (!cifs_chan_needs_reconnect(ses, server)) { + spin_unlock(&ses->chan_lock); - rc = cifs_negotiate_protocol(0, tcon->ses); - if (!rc && tcon->ses->need_reconnect) { - rc = cifs_setup_session(0, tcon->ses, nls_codepage); + /* this means that we only need to tree connect */ + if (tcon->need_reconnect) + goto skip_sess_setup; + + goto out; + } + spin_unlock(&ses->chan_lock); + + mutex_lock(&ses->session_mutex); + rc = cifs_negotiate_protocol(0, ses, server); + if (!rc) { + rc = cifs_setup_session(0, ses, server, nls_codepage); if ((rc == -EACCES) && !tcon->retry) { + mutex_unlock(&ses->session_mutex); rc = -EHOSTDOWN; - ses->binding = false; - ses->binding_chan = NULL; - mutex_unlock(&tcon->ses->session_mutex); goto failed; } } - /* - * End of channel binding - */ - ses->binding = false; - ses->binding_chan = NULL; if (rc || !tcon->need_reconnect) { - mutex_unlock(&tcon->ses->session_mutex); + mutex_unlock(&ses->session_mutex); goto out; } +skip_sess_setup: cifs_mark_open_files_invalid(tcon); if (tcon->use_persistent) tcon->need_reopen_files = true; rc = cifs_tree_connect(0, tcon, nls_codepage); - mutex_unlock(&tcon->ses->session_mutex); + mutex_unlock(&ses->session_mutex); cifs_dbg(FYI, "reconnect tcon rc = %d\n", rc); if (rc) { @@ -833,7 +846,9 @@ add_posix_context(struct kvec *iov, unsigned int *num_iovec, umode_t mode) */ int -SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses) +SMB2_negotiate(const unsigned int xid, + struct cifs_ses *ses, + struct TCP_Server_Info *server) { struct smb_rqst rqst; struct smb2_negotiate_req *req; @@ -842,7 +857,6 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses) struct kvec rsp_iov; int rc = 0; int resp_buftype; - struct TCP_Server_Info *server = cifs_ses_server(ses); int blob_offset, blob_length; char *security_blob; int flags = CIFS_NEG_OP; @@ -1221,6 +1235,7 @@ smb2_select_sectype(struct TCP_Server_Info *server, enum securityEnum requested) struct SMB2_sess_data { unsigned int xid; struct cifs_ses *ses; + struct TCP_Server_Info *server; struct nls_table *nls_cp; void (*func)(struct SMB2_sess_data *); int result; @@ -1242,9 +1257,10 @@ SMB2_sess_alloc_buffer(struct SMB2_sess_data *sess_data) { int rc; struct cifs_ses *ses = sess_data->ses; + struct TCP_Server_Info *server = sess_data->server; struct smb2_sess_setup_req *req; - struct TCP_Server_Info *server = cifs_ses_server(ses); unsigned int total_len; + bool is_binding = false; rc = smb2_plain_req_init(SMB2_SESSION_SETUP, NULL, server, (void **) &req, @@ -1252,11 +1268,16 @@ SMB2_sess_alloc_buffer(struct SMB2_sess_data *sess_data) if (rc) return rc; - if (sess_data->ses->binding) { - req->hdr.SessionId = cpu_to_le64(sess_data->ses->Suid); + spin_lock(&ses->chan_lock); + is_binding = !CIFS_ALL_CHANS_NEED_RECONNECT(ses); + spin_unlock(&ses->chan_lock); + + if (is_binding) { + req->hdr.SessionId = cpu_to_le64(ses->Suid); req->hdr.Flags |= SMB2_FLAGS_SIGNED; req->PreviousSessionId = 0; req->Flags = SMB2_SESSION_REQ_FLAG_BINDING; + cifs_dbg(FYI, "Binding to sess id: %llx\n", ses->Suid); } else { /* First session, not a reauthenticate */ req->hdr.SessionId = 0; @@ -1266,6 +1287,8 @@ SMB2_sess_alloc_buffer(struct SMB2_sess_data *sess_data) */ req->PreviousSessionId = cpu_to_le64(sess_data->previous_session); req->Flags = 0; /* MBZ */ + cifs_dbg(FYI, "Fresh session. Previous: %llx\n", + sess_data->previous_session); } /* enough to enable echos and oplocks and one max size write */ @@ -1325,7 +1348,7 @@ SMB2_sess_sendreceive(struct SMB2_sess_data *sess_data) /* BB add code to build os and lm fields */ rc = cifs_send_recv(sess_data->xid, sess_data->ses, - cifs_ses_server(sess_data->ses), + sess_data->server, &rqst, &sess_data->buf0_type, CIFS_LOG_ERROR | CIFS_SESS_OP, &rsp_iov); @@ -1340,11 +1363,11 @@ SMB2_sess_establish_session(struct SMB2_sess_data *sess_data) { int rc = 0; struct cifs_ses *ses = sess_data->ses; - struct TCP_Server_Info *server = cifs_ses_server(ses); + struct TCP_Server_Info *server = sess_data->server; mutex_lock(&server->srv_mutex); if (server->ops->generate_signingkey) { - rc = server->ops->generate_signingkey(ses); + rc = server->ops->generate_signingkey(ses, server); if (rc) { cifs_dbg(FYI, "SMB3 session key generation failed\n"); @@ -1359,13 +1382,16 @@ SMB2_sess_establish_session(struct SMB2_sess_data *sess_data) mutex_unlock(&server->srv_mutex); cifs_dbg(FYI, "SMB2/3 session established successfully\n"); - /* keep existing ses state if binding */ - if (!ses->binding) { - spin_lock(&GlobalMid_Lock); - ses->status = CifsGood; - ses->need_reconnect = false; - spin_unlock(&GlobalMid_Lock); - } + + spin_lock(&ses->chan_lock); + cifs_chan_clear_need_reconnect(ses, server); + spin_unlock(&ses->chan_lock); + + /* Even if one channel is active, session is in good state */ + spin_lock(&cifs_tcp_ses_lock); + server->tcpStatus = CifsGood; + ses->status = CifsGood; + spin_unlock(&cifs_tcp_ses_lock); return rc; } @@ -1376,15 +1402,17 @@ SMB2_auth_kerberos(struct SMB2_sess_data *sess_data) { int rc; struct cifs_ses *ses = sess_data->ses; + struct TCP_Server_Info *server = sess_data->server; struct cifs_spnego_msg *msg; struct key *spnego_key = NULL; struct smb2_sess_setup_rsp *rsp = NULL; + bool is_binding = false; rc = SMB2_sess_alloc_buffer(sess_data); if (rc) goto out; - spnego_key = cifs_get_spnego_key(ses); + spnego_key = cifs_get_spnego_key(ses, server); if (IS_ERR(spnego_key)) { rc = PTR_ERR(spnego_key); if (rc == -ENOKEY) @@ -1405,8 +1433,12 @@ SMB2_auth_kerberos(struct SMB2_sess_data *sess_data) goto out_put_spnego_key; } + spin_lock(&ses->chan_lock); + is_binding = !CIFS_ALL_CHANS_NEED_RECONNECT(ses); + spin_unlock(&ses->chan_lock); + /* keep session key if binding */ - if (!ses->binding) { + if (!is_binding) { ses->auth_key.response = kmemdup(msg->data, msg->sesskey_len, GFP_KERNEL); if (!ses->auth_key.response) { @@ -1427,7 +1459,7 @@ SMB2_auth_kerberos(struct SMB2_sess_data *sess_data) rsp = (struct smb2_sess_setup_rsp *)sess_data->iov[0].iov_base; /* keep session id and flags if binding */ - if (!ses->binding) { + if (!is_binding) { ses->Suid = le64_to_cpu(rsp->hdr.SessionId); ses->session_flags = le16_to_cpu(rsp->SessionFlags); } @@ -1459,10 +1491,12 @@ SMB2_sess_auth_rawntlmssp_negotiate(struct SMB2_sess_data *sess_data) { int rc; struct cifs_ses *ses = sess_data->ses; + struct TCP_Server_Info *server = sess_data->server; struct smb2_sess_setup_rsp *rsp = NULL; unsigned char *ntlmssp_blob = NULL; bool use_spnego = false; /* else use raw ntlmssp */ u16 blob_length = 0; + bool is_binding = false; /* * If memory allocation is successful, caller of this function @@ -1480,7 +1514,7 @@ SMB2_sess_auth_rawntlmssp_negotiate(struct SMB2_sess_data *sess_data) goto out_err; rc = build_ntlmssp_negotiate_blob(&ntlmssp_blob, - &blob_length, ses, + &blob_length, ses, server, sess_data->nls_cp); if (rc) goto out_err; @@ -1519,8 +1553,12 @@ SMB2_sess_auth_rawntlmssp_negotiate(struct SMB2_sess_data *sess_data) cifs_dbg(FYI, "rawntlmssp session setup challenge phase\n"); + spin_lock(&ses->chan_lock); + is_binding = !CIFS_ALL_CHANS_NEED_RECONNECT(ses); + spin_unlock(&ses->chan_lock); + /* keep existing ses id and flags if binding */ - if (!ses->binding) { + if (!is_binding) { ses->Suid = le64_to_cpu(rsp->hdr.SessionId); ses->session_flags = le16_to_cpu(rsp->SessionFlags); } @@ -1545,11 +1583,13 @@ SMB2_sess_auth_rawntlmssp_authenticate(struct SMB2_sess_data *sess_data) { int rc; struct cifs_ses *ses = sess_data->ses; + struct TCP_Server_Info *server = sess_data->server; struct smb2_sess_setup_req *req; struct smb2_sess_setup_rsp *rsp = NULL; unsigned char *ntlmssp_blob = NULL; bool use_spnego = false; /* else use raw ntlmssp */ u16 blob_length = 0; + bool is_binding = false; rc = SMB2_sess_alloc_buffer(sess_data); if (rc) @@ -1558,8 +1598,9 @@ SMB2_sess_auth_rawntlmssp_authenticate(struct SMB2_sess_data *sess_data) req = (struct smb2_sess_setup_req *) sess_data->iov[0].iov_base; req->hdr.SessionId = cpu_to_le64(ses->Suid); - rc = build_ntlmssp_auth_blob(&ntlmssp_blob, &blob_length, ses, - sess_data->nls_cp); + rc = build_ntlmssp_auth_blob(&ntlmssp_blob, &blob_length, + ses, server, + sess_data->nls_cp); if (rc) { cifs_dbg(FYI, "build_ntlmssp_auth_blob failed %d\n", rc); goto out; @@ -1580,8 +1621,12 @@ SMB2_sess_auth_rawntlmssp_authenticate(struct SMB2_sess_data *sess_data) rsp = (struct smb2_sess_setup_rsp *)sess_data->iov[0].iov_base; + spin_lock(&ses->chan_lock); + is_binding = !CIFS_ALL_CHANS_NEED_RECONNECT(ses); + spin_unlock(&ses->chan_lock); + /* keep existing ses id and flags if binding */ - if (!ses->binding) { + if (!is_binding) { ses->Suid = le64_to_cpu(rsp->hdr.SessionId); ses->session_flags = le16_to_cpu(rsp->SessionFlags); } @@ -1612,11 +1657,13 @@ out: } static int -SMB2_select_sec(struct cifs_ses *ses, struct SMB2_sess_data *sess_data) +SMB2_select_sec(struct SMB2_sess_data *sess_data) { int type; + struct cifs_ses *ses = sess_data->ses; + struct TCP_Server_Info *server = sess_data->server; - type = smb2_select_sectype(cifs_ses_server(ses), ses->sectype); + type = smb2_select_sectype(server, ses->sectype); cifs_dbg(FYI, "sess setup type %d\n", type); if (type == Unspecified) { cifs_dbg(VFS, "Unable to select appropriate authentication method!\n"); @@ -1640,10 +1687,10 @@ SMB2_select_sec(struct cifs_ses *ses, struct SMB2_sess_data *sess_data) int SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses, + struct TCP_Server_Info *server, const struct nls_table *nls_cp) { int rc = 0; - struct TCP_Server_Info *server = cifs_ses_server(ses); struct SMB2_sess_data *sess_data; cifs_dbg(FYI, "Session Setup\n"); @@ -1657,15 +1704,17 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses, if (!sess_data) return -ENOMEM; - rc = SMB2_select_sec(ses, sess_data); - if (rc) - goto out; sess_data->xid = xid; sess_data->ses = ses; + sess_data->server = server; sess_data->buf0_type = CIFS_NO_BUFFER; sess_data->nls_cp = (struct nls_table *) nls_cp; sess_data->previous_session = ses->Suid; + rc = SMB2_select_sec(sess_data); + if (rc) + goto out; + /* * Initialize the session hash with the server one. */ @@ -1704,8 +1753,12 @@ SMB2_logoff(const unsigned int xid, struct cifs_ses *ses) return -EIO; /* no need to send SMB logoff if uid already closed due to reconnect */ - if (ses->need_reconnect) + spin_lock(&ses->chan_lock); + if (CIFS_ALL_CHANS_NEED_RECONNECT(ses)) { + spin_unlock(&ses->chan_lock); goto smb2_session_already_dead; + } + spin_unlock(&ses->chan_lock); rc = smb2_plain_req_init(SMB2_LOGOFF, NULL, ses->server, (void **) &req, &total_len); @@ -1867,7 +1920,9 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, tcon->share_flags = le32_to_cpu(rsp->ShareFlags); tcon->capabilities = rsp->Capabilities; /* we keep caps little endian */ tcon->maximal_access = le32_to_cpu(rsp->MaximalAccess); + spin_lock(&cifs_tcp_ses_lock); tcon->tidStatus = CifsGood; + spin_unlock(&cifs_tcp_ses_lock); tcon->need_reconnect = false; tcon->tid = le32_to_cpu(rsp->hdr.Id.SyncId.TreeId); strlcpy(tcon->treeName, tree, sizeof(tcon->treeName)); @@ -1913,8 +1968,13 @@ SMB2_tdis(const unsigned int xid, struct cifs_tcon *tcon) if (!ses || !(ses->server)) return -EIO; - if ((tcon->need_reconnect) || (tcon->ses->need_reconnect)) + spin_lock(&ses->chan_lock); + if ((tcon->need_reconnect) || + (CIFS_ALL_CHANS_NEED_RECONNECT(tcon->ses))) { + spin_unlock(&ses->chan_lock); return 0; + } + spin_unlock(&ses->chan_lock); close_cached_dir_lease(&tcon->crfid); @@ -3797,13 +3857,16 @@ SMB2_echo(struct TCP_Server_Info *server) .rq_nvec = 1 }; unsigned int total_len; - cifs_dbg(FYI, "In echo request\n"); + cifs_dbg(FYI, "In echo request for conn_id %lld\n", server->conn_id); + spin_lock(&cifs_tcp_ses_lock); if (server->tcpStatus == CifsNeedNegotiate) { + spin_unlock(&cifs_tcp_ses_lock); /* No need to send echo on newly established connections */ mod_delayed_work(cifsiod_wq, &server->reconnect, 0); return rc; } + spin_unlock(&cifs_tcp_ses_lock); rc = smb2_plain_req_init(SMB2_ECHO, NULL, server, (void **)&req, &total_len); diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 096fada16ebd..4a7062fd1c26 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -123,8 +123,11 @@ extern void smb2_set_related(struct smb_rqst *rqst); * SMB2 Worker functions - most of protocol specific implementation details * are contained within these calls. */ -extern int SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses); +extern int SMB2_negotiate(const unsigned int xid, + struct cifs_ses *ses, + struct TCP_Server_Info *server); extern int SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses, + struct TCP_Server_Info *server, const struct nls_table *nls_cp); extern int SMB2_logoff(const unsigned int xid, struct cifs_ses *ses); extern int SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, @@ -276,6 +279,7 @@ extern void smb2_copy_fs_info_to_kstatfs( struct kstatfs *kst); extern int smb311_crypto_shash_allocate(struct TCP_Server_Info *server); extern int smb311_update_preauth_hash(struct cifs_ses *ses, + struct TCP_Server_Info *server, struct kvec *iov, int nvec); extern int smb2_query_info_compound(const unsigned int xid, struct cifs_tcon *tcon, diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c index 2bf047b390a9..b70a49b4edc0 100644 --- a/fs/cifs/smb2transport.c +++ b/fs/cifs/smb2transport.c @@ -100,7 +100,8 @@ int smb2_get_sign_key(__u64 ses_id, struct TCP_Server_Info *server, u8 *key) goto out; found: - if (ses->binding) { + if (cifs_chan_needs_reconnect(ses, server) && + !CIFS_ALL_CHANS_NEED_RECONNECT(ses)) { /* * If we are in the process of binding a new channel * to an existing session, use the master connection @@ -390,12 +391,18 @@ struct derivation_triplet { static int generate_smb3signingkey(struct cifs_ses *ses, + struct TCP_Server_Info *server, const struct derivation_triplet *ptriplet) { int rc; -#ifdef CONFIG_CIFS_DEBUG_DUMP_KEYS - struct TCP_Server_Info *server = ses->server; -#endif + bool is_binding = false; + int chan_index = 0; + + spin_lock(&ses->chan_lock); + is_binding = !CIFS_ALL_CHANS_NEED_RECONNECT(ses); + chan_index = cifs_ses_get_chan_index(ses, server); + /* TODO: introduce ref counting for channels when the can be freed */ + spin_unlock(&ses->chan_lock); /* * All channels use the same encryption/decryption keys but @@ -407,10 +414,10 @@ generate_smb3signingkey(struct cifs_ses *ses, * master connection signing key stored in the session */ - if (ses->binding) { + if (is_binding) { rc = generate_key(ses, ptriplet->signing.label, ptriplet->signing.context, - cifs_ses_binding_channel(ses)->signkey, + ses->chans[chan_index].signkey, SMB3_SIGN_KEY_SIZE); if (rc) return rc; @@ -422,6 +429,7 @@ generate_smb3signingkey(struct cifs_ses *ses, if (rc) return rc; + /* safe to access primary channel, since it will never go away */ memcpy(ses->chans[0].signkey, ses->smb3signingkey, SMB3_SIGN_KEY_SIZE); @@ -470,7 +478,8 @@ generate_smb3signingkey(struct cifs_ses *ses, } int -generate_smb30signingkey(struct cifs_ses *ses) +generate_smb30signingkey(struct cifs_ses *ses, + struct TCP_Server_Info *server) { struct derivation_triplet triplet; @@ -494,11 +503,12 @@ generate_smb30signingkey(struct cifs_ses *ses) d->context.iov_base = "ServerOut"; d->context.iov_len = 10; - return generate_smb3signingkey(ses, &triplet); + return generate_smb3signingkey(ses, server, &triplet); } int -generate_smb311signingkey(struct cifs_ses *ses) +generate_smb311signingkey(struct cifs_ses *ses, + struct TCP_Server_Info *server) { struct derivation_triplet triplet; @@ -522,7 +532,7 @@ generate_smb311signingkey(struct cifs_ses *ses) d->context.iov_base = ses->preauth_sha_hash; d->context.iov_len = 64; - return generate_smb3signingkey(ses, &triplet); + return generate_smb3signingkey(ses, server, &triplet); } int @@ -624,8 +634,12 @@ smb2_sign_rqst(struct smb_rqst *rqst, struct TCP_Server_Info *server) if (!is_signed) return 0; - if (server->tcpStatus == CifsNeedNegotiate) + spin_lock(&cifs_tcp_ses_lock); + if (server->tcpStatus == CifsNeedNegotiate) { + spin_unlock(&cifs_tcp_ses_lock); return 0; + } + spin_unlock(&cifs_tcp_ses_lock); if (!is_binding && !server->session_estab) { strncpy(shdr->Signature, "BSRSPYL", 8); return 0; @@ -741,30 +755,41 @@ static int smb2_get_mid_entry(struct cifs_ses *ses, struct TCP_Server_Info *server, struct smb2_hdr *shdr, struct mid_q_entry **mid) { - if (server->tcpStatus == CifsExiting) + spin_lock(&cifs_tcp_ses_lock); + if (server->tcpStatus == CifsExiting) { + spin_unlock(&cifs_tcp_ses_lock); return -ENOENT; + } if (server->tcpStatus == CifsNeedReconnect) { + spin_unlock(&cifs_tcp_ses_lock); cifs_dbg(FYI, "tcp session dead - return to caller to retry\n"); return -EAGAIN; } if (server->tcpStatus == CifsNeedNegotiate && - shdr->Command != SMB2_NEGOTIATE) + shdr->Command != SMB2_NEGOTIATE) { + spin_unlock(&cifs_tcp_ses_lock); return -EAGAIN; + } if (ses->status == CifsNew) { if ((shdr->Command != SMB2_SESSION_SETUP) && - (shdr->Command != SMB2_NEGOTIATE)) + (shdr->Command != SMB2_NEGOTIATE)) { + spin_unlock(&cifs_tcp_ses_lock); return -EAGAIN; + } /* else ok - we are setting up session */ } if (ses->status == CifsExiting) { - if (shdr->Command != SMB2_LOGOFF) + if (shdr->Command != SMB2_LOGOFF) { + spin_unlock(&cifs_tcp_ses_lock); return -EAGAIN; + } /* else ok - we are shutting down the session */ } + spin_unlock(&cifs_tcp_ses_lock); *mid = smb2_mid_entry_alloc(shdr, server); if (*mid == NULL) @@ -837,9 +862,13 @@ smb2_setup_async_request(struct TCP_Server_Info *server, struct smb_rqst *rqst) (struct smb2_hdr *)rqst->rq_iov[0].iov_base; struct mid_q_entry *mid; + spin_lock(&cifs_tcp_ses_lock); if (server->tcpStatus == CifsNeedNegotiate && - shdr->Command != SMB2_NEGOTIATE) + shdr->Command != SMB2_NEGOTIATE) { + spin_unlock(&cifs_tcp_ses_lock); return ERR_PTR(-EAGAIN); + } + spin_unlock(&cifs_tcp_ses_lock); smb2_seq_num_into_buf(server, shdr); diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 61ea3d3f95b4..93f0e8c1ea23 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -430,9 +430,9 @@ unmask: * be taken as the remainder of this one. We need to kill the * socket so the server throws away the partial SMB */ - spin_lock(&GlobalMid_Lock); + spin_lock(&cifs_tcp_ses_lock); server->tcpStatus = CifsNeedReconnect; - spin_unlock(&GlobalMid_Lock); + spin_unlock(&cifs_tcp_ses_lock); trace_smb3_partial_send_reconnect(server->CurrentMid, server->conn_id, server->hostname); } @@ -578,10 +578,14 @@ wait_for_free_credits(struct TCP_Server_Info *server, const int num_credits, return -ERESTARTSYS; spin_lock(&server->req_lock); } else { + spin_unlock(&server->req_lock); + + spin_lock(&cifs_tcp_ses_lock); if (server->tcpStatus == CifsExiting) { - spin_unlock(&server->req_lock); + spin_unlock(&cifs_tcp_ses_lock); return -ENOENT; } + spin_unlock(&cifs_tcp_ses_lock); /* * For normal commands, reserve the last MAX_COMPOUND @@ -596,6 +600,7 @@ wait_for_free_credits(struct TCP_Server_Info *server, const int num_credits, * for servers that are slow to hand out credits on * new sessions. */ + spin_lock(&server->req_lock); if (!optype && num_credits == 1 && server->in_flight > 2 * MAX_COMPOUND && *credits <= MAX_COMPOUND) { @@ -723,28 +728,36 @@ cifs_wait_mtu_credits(struct TCP_Server_Info *server, unsigned int size, static int allocate_mid(struct cifs_ses *ses, struct smb_hdr *in_buf, struct mid_q_entry **ppmidQ) { + spin_lock(&cifs_tcp_ses_lock); if (ses->server->tcpStatus == CifsExiting) { + spin_unlock(&cifs_tcp_ses_lock); return -ENOENT; } if (ses->server->tcpStatus == CifsNeedReconnect) { + spin_unlock(&cifs_tcp_ses_lock); cifs_dbg(FYI, "tcp session dead - return to caller to retry\n"); return -EAGAIN; } if (ses->status == CifsNew) { if ((in_buf->Command != SMB_COM_SESSION_SETUP_ANDX) && - (in_buf->Command != SMB_COM_NEGOTIATE)) + (in_buf->Command != SMB_COM_NEGOTIATE)) { + spin_unlock(&cifs_tcp_ses_lock); return -EAGAIN; + } /* else ok - we are setting up session */ } if (ses->status == CifsExiting) { /* check if SMB session is bad because we are setting it up */ - if (in_buf->Command != SMB_COM_LOGOFF_ANDX) + if (in_buf->Command != SMB_COM_LOGOFF_ANDX) { + spin_unlock(&cifs_tcp_ses_lock); return -EAGAIN; + } /* else ok - we are shutting down session */ } + spin_unlock(&cifs_tcp_ses_lock); *ppmidQ = AllocMidQEntry(in_buf, ses->server); if (*ppmidQ == NULL) @@ -1044,19 +1057,11 @@ struct TCP_Server_Info *cifs_pick_channel(struct cifs_ses *ses) if (!ses) return NULL; - spin_lock(&ses->chan_lock); - if (!ses->binding) { - /* round robin */ - if (ses->chan_count > 1) { - index = (uint)atomic_inc_return(&ses->chan_seq); - index %= ses->chan_count; - } - spin_unlock(&ses->chan_lock); - return ses->chans[index].server; - } else { - spin_unlock(&ses->chan_lock); - return cifs_ses_server(ses); - } + /* round robin */ + index = (uint)atomic_inc_return(&ses->chan_seq); + index %= ses->chan_count; + + return ses->chans[index].server; } int @@ -1084,8 +1089,12 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, return -EIO; } - if (server->tcpStatus == CifsExiting) + spin_lock(&cifs_tcp_ses_lock); + if (server->tcpStatus == CifsExiting) { + spin_unlock(&cifs_tcp_ses_lock); return -ENOENT; + } + spin_unlock(&cifs_tcp_ses_lock); /* * Wait for all the requests to become available. @@ -1188,12 +1197,17 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, /* * Compounding is never used during session establish. */ + spin_lock(&cifs_tcp_ses_lock); if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP) || (optype & CIFS_SESS_OP)) { + spin_unlock(&cifs_tcp_ses_lock); + mutex_lock(&server->srv_mutex); - smb311_update_preauth_hash(ses, rqst[0].rq_iov, - rqst[0].rq_nvec); + smb311_update_preauth_hash(ses, server, rqst[0].rq_iov, rqst[0].rq_nvec); mutex_unlock(&server->srv_mutex); + + spin_lock(&cifs_tcp_ses_lock); } + spin_unlock(&cifs_tcp_ses_lock); for (i = 0; i < num_rqst; i++) { rc = wait_for_response(server, midQ[i]); @@ -1256,15 +1270,19 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, /* * Compounding is never used during session establish. */ + spin_lock(&cifs_tcp_ses_lock); if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP) || (optype & CIFS_SESS_OP)) { struct kvec iov = { .iov_base = resp_iov[0].iov_base, .iov_len = resp_iov[0].iov_len }; + spin_unlock(&cifs_tcp_ses_lock); mutex_lock(&server->srv_mutex); - smb311_update_preauth_hash(ses, &iov, 1); + smb311_update_preauth_hash(ses, server, &iov, 1); mutex_unlock(&server->srv_mutex); + spin_lock(&cifs_tcp_ses_lock); } + spin_unlock(&cifs_tcp_ses_lock); out: /* @@ -1353,8 +1371,12 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses, return -EIO; } - if (server->tcpStatus == CifsExiting) + spin_lock(&cifs_tcp_ses_lock); + if (server->tcpStatus == CifsExiting) { + spin_unlock(&cifs_tcp_ses_lock); return -ENOENT; + } + spin_unlock(&cifs_tcp_ses_lock); /* Ensure that we do not send more than 50 overlapping requests to the same server. We may make this configurable later or @@ -1494,8 +1516,12 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon, return -EIO; } - if (server->tcpStatus == CifsExiting) + spin_lock(&cifs_tcp_ses_lock); + if (server->tcpStatus == CifsExiting) { + spin_unlock(&cifs_tcp_ses_lock); return -ENOENT; + } + spin_unlock(&cifs_tcp_ses_lock); /* Ensure that we do not send more than 50 overlapping requests to the same server. We may make this configurable later or @@ -1553,10 +1579,12 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon, (server->tcpStatus != CifsNew))); /* Were we interrupted by a signal ? */ + spin_lock(&cifs_tcp_ses_lock); if ((rc == -ERESTARTSYS) && (midQ->mid_state == MID_REQUEST_SUBMITTED) && ((server->tcpStatus == CifsGood) || (server->tcpStatus == CifsNew))) { + spin_unlock(&cifs_tcp_ses_lock); if (in_buf->Command == SMB_COM_TRANSACTION2) { /* POSIX lock. We send a NT_CANCEL SMB to cause the @@ -1595,7 +1623,9 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon, /* We got the response - restart system call. */ rstart = 1; + spin_lock(&cifs_tcp_ses_lock); } + spin_unlock(&cifs_tcp_ses_lock); rc = cifs_sync_mid_result(midQ, server); if (rc != 0) diff --git a/fs/fs_context.c b/fs/fs_context.c index b7e43a780a62..24ce12f0db32 100644 --- a/fs/fs_context.c +++ b/fs/fs_context.c @@ -548,7 +548,7 @@ static int legacy_parse_param(struct fs_context *fc, struct fs_parameter *param) param->key); } - if (len > PAGE_SIZE - 2 - size) + if (size + len + 2 > PAGE_SIZE) return invalf(fc, "VFS: Legacy: Cumulative options too large"); if (strchr(param->key, ',') || (param->type == fs_value_is_string && diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c index 74e627109b79..9d737904d07c 100644 --- a/fs/fuse/virtio_fs.c +++ b/fs/fuse/virtio_fs.c @@ -891,7 +891,7 @@ static int virtio_fs_probe(struct virtio_device *vdev) return 0; out_vqs: - vdev->config->reset(vdev); + virtio_reset_device(vdev); virtio_fs_cleanup_vqs(vdev, fs); kfree(fs->vqs); @@ -923,7 +923,7 @@ static void virtio_fs_remove(struct virtio_device *vdev) list_del_init(&fs->list); virtio_fs_stop_all_queues(fs); virtio_fs_drain_all_queues_locked(fs); - vdev->config->reset(vdev); + virtio_reset_device(vdev); virtio_fs_cleanup_vqs(vdev, fs); vdev->priv = NULL; diff --git a/fs/orangefs/orangefs-bufmap.c b/fs/orangefs/orangefs-bufmap.c index 538e839590ef..b501dc07f922 100644 --- a/fs/orangefs/orangefs-bufmap.c +++ b/fs/orangefs/orangefs-bufmap.c @@ -176,7 +176,7 @@ orangefs_bufmap_free(struct orangefs_bufmap *bufmap) { kfree(bufmap->page_array); kfree(bufmap->desc_array); - kfree(bufmap->buffer_index_array); + bitmap_free(bufmap->buffer_index_array); kfree(bufmap); } @@ -226,8 +226,7 @@ orangefs_bufmap_alloc(struct ORANGEFS_dev_map_desc *user_desc) bufmap->desc_size = user_desc->size; bufmap->desc_shift = ilog2(bufmap->desc_size); - bufmap->buffer_index_array = - kzalloc(DIV_ROUND_UP(bufmap->desc_count, BITS_PER_LONG), GFP_KERNEL); + bufmap->buffer_index_array = bitmap_zalloc(bufmap->desc_count, GFP_KERNEL); if (!bufmap->buffer_index_array) goto out_free_bufmap; @@ -250,7 +249,7 @@ orangefs_bufmap_alloc(struct ORANGEFS_dev_map_desc *user_desc) out_free_desc_array: kfree(bufmap->desc_array); out_free_index_array: - kfree(bufmap->buffer_index_array); + bitmap_free(bufmap->buffer_index_array); out_free_bufmap: kfree(bufmap); out: diff --git a/fs/orangefs/orangefs-sysfs.c b/fs/orangefs/orangefs-sysfs.c index 3627ea946402..de80b62553bb 100644 --- a/fs/orangefs/orangefs-sysfs.c +++ b/fs/orangefs/orangefs-sysfs.c @@ -894,10 +894,11 @@ static struct attribute *orangefs_default_attrs[] = { &perf_time_interval_secs_attribute.attr, NULL, }; +ATTRIBUTE_GROUPS(orangefs_default); static struct kobj_type orangefs_ktype = { .sysfs_ops = &orangefs_sysfs_ops, - .default_attrs = orangefs_default_attrs, + .default_groups = orangefs_default_groups, }; static struct orangefs_attribute acache_hard_limit_attribute = @@ -931,10 +932,11 @@ static struct attribute *acache_orangefs_default_attrs[] = { &acache_timeout_msecs_attribute.attr, NULL, }; +ATTRIBUTE_GROUPS(acache_orangefs_default); static struct kobj_type acache_orangefs_ktype = { .sysfs_ops = &orangefs_sysfs_ops, - .default_attrs = acache_orangefs_default_attrs, + .default_groups = acache_orangefs_default_groups, }; static struct orangefs_attribute capcache_hard_limit_attribute = @@ -968,10 +970,11 @@ static struct attribute *capcache_orangefs_default_attrs[] = { &capcache_timeout_secs_attribute.attr, NULL, }; +ATTRIBUTE_GROUPS(capcache_orangefs_default); static struct kobj_type capcache_orangefs_ktype = { .sysfs_ops = &orangefs_sysfs_ops, - .default_attrs = capcache_orangefs_default_attrs, + .default_groups = capcache_orangefs_default_groups, }; static struct orangefs_attribute ccache_hard_limit_attribute = @@ -1005,10 +1008,11 @@ static struct attribute *ccache_orangefs_default_attrs[] = { &ccache_timeout_secs_attribute.attr, NULL, }; +ATTRIBUTE_GROUPS(ccache_orangefs_default); static struct kobj_type ccache_orangefs_ktype = { .sysfs_ops = &orangefs_sysfs_ops, - .default_attrs = ccache_orangefs_default_attrs, + .default_groups = ccache_orangefs_default_groups, }; static struct orangefs_attribute ncache_hard_limit_attribute = @@ -1042,10 +1046,11 @@ static struct attribute *ncache_orangefs_default_attrs[] = { &ncache_timeout_msecs_attribute.attr, NULL, }; +ATTRIBUTE_GROUPS(ncache_orangefs_default); static struct kobj_type ncache_orangefs_ktype = { .sysfs_ops = &orangefs_sysfs_ops, - .default_attrs = ncache_orangefs_default_attrs, + .default_groups = ncache_orangefs_default_groups, }; static struct orangefs_attribute pc_acache_attribute = @@ -1072,10 +1077,11 @@ static struct attribute *pc_orangefs_default_attrs[] = { &pc_ncache_attribute.attr, NULL, }; +ATTRIBUTE_GROUPS(pc_orangefs_default); static struct kobj_type pc_orangefs_ktype = { .sysfs_ops = &orangefs_sysfs_ops, - .default_attrs = pc_orangefs_default_attrs, + .default_groups = pc_orangefs_default_groups, }; static struct orangefs_attribute stats_reads_attribute = @@ -1095,10 +1101,11 @@ static struct attribute *stats_orangefs_default_attrs[] = { &stats_writes_attribute.attr, NULL, }; +ATTRIBUTE_GROUPS(stats_orangefs_default); static struct kobj_type stats_orangefs_ktype = { .sysfs_ops = &orangefs_sysfs_ops, - .default_attrs = stats_orangefs_default_attrs, + .default_groups = stats_orangefs_default_groups, }; static struct kobject *orangefs_obj; diff --git a/fs/super.c b/fs/super.c index 3bfc0f8fbd5b..a6405d44d4ca 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1423,8 +1423,8 @@ struct dentry *mount_nodev(struct file_system_type *fs_type, } EXPORT_SYMBOL(mount_nodev); -static int reconfigure_single(struct super_block *s, - int flags, void *data) +int reconfigure_single(struct super_block *s, + int flags, void *data) { struct fs_context *fc; int ret; diff --git a/include/crypto/blake2s.h b/include/crypto/blake2s.h index df3c6c2f9553..f9ffd39194eb 100644 --- a/include/crypto/blake2s.h +++ b/include/crypto/blake2s.h @@ -101,7 +101,4 @@ static inline void blake2s(u8 *out, const u8 *in, const u8 *key, blake2s_final(&state, out); } -void blake2s256_hmac(u8 *out, const u8 *in, const u8 *key, const size_t inlen, - const size_t keylen); - #endif /* _CRYPTO_BLAKE2S_H */ diff --git a/include/linux/dma/xilinx_dpdma.h b/include/linux/dma/xilinx_dpdma.h index 83a1377f03f8..02a4adf8921b 100644 --- a/include/linux/dma/xilinx_dpdma.h +++ b/include/linux/dma/xilinx_dpdma.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_DMA_XILINX_DPDMA_H #define __LINUX_DMA_XILINX_DPDMA_H diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 0349b35235e6..842d4f7ca752 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -50,6 +50,7 @@ enum dma_status { */ enum dma_transaction_type { DMA_MEMCPY, + DMA_MEMCPY_SG, DMA_XOR, DMA_PQ, DMA_XOR_VAL, @@ -887,6 +888,11 @@ struct dma_device { struct dma_async_tx_descriptor *(*device_prep_dma_memcpy)( struct dma_chan *chan, dma_addr_t dst, dma_addr_t src, size_t len, unsigned long flags); + struct dma_async_tx_descriptor *(*device_prep_dma_memcpy_sg)( + struct dma_chan *chan, + struct scatterlist *dst_sg, unsigned int dst_nents, + struct scatterlist *src_sg, unsigned int src_nents, + unsigned long flags); struct dma_async_tx_descriptor *(*device_prep_dma_xor)( struct dma_chan *chan, dma_addr_t dst, dma_addr_t *src, unsigned int src_cnt, size_t len, unsigned long flags); @@ -1047,6 +1053,20 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_memcpy( len, flags); } +static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_memcpy_sg( + struct dma_chan *chan, + struct scatterlist *dst_sg, unsigned int dst_nents, + struct scatterlist *src_sg, unsigned int src_nents, + unsigned long flags) +{ + if (!chan || !chan->device || !chan->device->device_prep_dma_memcpy_sg) + return NULL; + + return chan->device->device_prep_dma_memcpy_sg(chan, dst_sg, dst_nents, + src_sg, src_nents, + flags); +} + static inline bool dmaengine_is_metadata_mode_supported(struct dma_chan *chan, enum dma_desc_metadata_mode mode) { diff --git a/include/linux/efi.h b/include/linux/efi.h index 0de9fb1fdc5a..ccd4d3f91c98 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -148,6 +148,52 @@ typedef struct { u32 imagesize; } efi_capsule_header_t; +/* EFI_FIRMWARE_MANAGEMENT_CAPSULE_HEADER */ +struct efi_manage_capsule_header { + u32 ver; + u16 emb_drv_cnt; + u16 payload_cnt; + /* + * Variable-size array of the size given by the sum of + * emb_drv_cnt and payload_cnt. + */ + u64 offset_list[]; +} __packed; + +/* EFI_FIRMWARE_MANAGEMENT_CAPSULE_IMAGE_HEADER */ +struct efi_manage_capsule_image_header { + u32 ver; + efi_guid_t image_type_id; + u8 image_index; + u8 reserved_bytes[3]; + u32 image_size; + u32 vendor_code_size; + /* hw_ins was introduced in version 2 */ + u64 hw_ins; + /* capsule_support was introduced in version 3 */ + u64 capsule_support; +} __packed; + +/* WIN_CERTIFICATE */ +struct win_cert { + u32 len; + u16 rev; + u16 cert_type; +}; + +/* WIN_CERTIFICATE_UEFI_GUID */ +struct win_cert_uefi_guid { + struct win_cert hdr; + efi_guid_t cert_type; + u8 cert_data[]; +}; + +/* EFI_FIRMWARE_IMAGE_AUTHENTICATION */ +struct efi_image_auth { + u64 mon_count; + struct win_cert_uefi_guid auth_info; +}; + /* * EFI capsule flags */ diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index 6b54982fc5f3..13fa6f3df8e4 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -142,6 +142,8 @@ extern void put_fs_context(struct fs_context *fc); extern int vfs_parse_fs_param_source(struct fs_context *fc, struct fs_parameter *param); extern void fc_drop_locked(struct fs_context *fc); +int reconfigure_single(struct super_block *s, + int flags, void *data); /* * sget() wrappers to be called from the ->get_tree() op. diff --git a/include/linux/libata.h b/include/linux/libata.h index 2a8404b26083..605756f645be 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -39,25 +39,9 @@ * compile-time options: to be removed as soon as all the drivers are * converted to the new debugging mechanism */ -#undef ATA_DEBUG /* debugging output */ -#undef ATA_VERBOSE_DEBUG /* yet more debugging output */ #undef ATA_IRQ_TRAP /* define to ack screaming irqs */ -#undef ATA_NDEBUG /* define to disable quick runtime checks */ -/* note: prints function name for you */ -#ifdef ATA_DEBUG -#define DPRINTK(fmt, args...) printk(KERN_ERR "%s: " fmt, __func__, ## args) -#ifdef ATA_VERBOSE_DEBUG -#define VPRINTK(fmt, args...) printk(KERN_ERR "%s: " fmt, __func__, ## args) -#else -#define VPRINTK(fmt, args...) -#endif /* ATA_VERBOSE_DEBUG */ -#else -#define DPRINTK(fmt, args...) -#define VPRINTK(fmt, args...) -#endif /* ATA_DEBUG */ - #define ata_print_version_once(dev, version) \ ({ \ static bool __print_once; \ @@ -68,38 +52,6 @@ } \ }) -/* NEW: debug levels */ -#define HAVE_LIBATA_MSG 1 - -enum { - ATA_MSG_DRV = 0x0001, - ATA_MSG_INFO = 0x0002, - ATA_MSG_PROBE = 0x0004, - ATA_MSG_WARN = 0x0008, - ATA_MSG_MALLOC = 0x0010, - ATA_MSG_CTL = 0x0020, - ATA_MSG_INTR = 0x0040, - ATA_MSG_ERR = 0x0080, -}; - -#define ata_msg_drv(p) ((p)->msg_enable & ATA_MSG_DRV) -#define ata_msg_info(p) ((p)->msg_enable & ATA_MSG_INFO) -#define ata_msg_probe(p) ((p)->msg_enable & ATA_MSG_PROBE) -#define ata_msg_warn(p) ((p)->msg_enable & ATA_MSG_WARN) -#define ata_msg_malloc(p) ((p)->msg_enable & ATA_MSG_MALLOC) -#define ata_msg_ctl(p) ((p)->msg_enable & ATA_MSG_CTL) -#define ata_msg_intr(p) ((p)->msg_enable & ATA_MSG_INTR) -#define ata_msg_err(p) ((p)->msg_enable & ATA_MSG_ERR) - -static inline u32 ata_msg_init(int dval, int default_msg_enable_bits) -{ - if (dval < 0 || dval >= (sizeof(u32) * 8)) - return default_msg_enable_bits; /* should be 0x1 - only driver info msgs */ - if (!dval) - return 0; - return (1 << dval) - 1; -} - /* defines only for the constants which don't work well as enums */ #define ATA_TAG_POISON 0xfafbfcfdU @@ -191,7 +143,7 @@ enum { ATA_LFLAG_NO_LPM = (1 << 8), /* disable LPM on this link */ ATA_LFLAG_RST_ONCE = (1 << 9), /* limit recovery to one reset */ ATA_LFLAG_CHANGED = (1 << 10), /* LPM state changed on this link */ - ATA_LFLAG_NO_DB_DELAY = (1 << 11), /* no debounce delay on link resume */ + ATA_LFLAG_NO_DEBOUNCE_DELAY = (1 << 11), /* no debounce delay on link resume */ /* struct ata_port flags */ ATA_FLAG_SLAVE_POSS = (1 << 0), /* host supports slave dev */ @@ -884,7 +836,6 @@ struct ata_port { unsigned int hsm_task_state; - u32 msg_enable; struct list_head eh_done_q; wait_queue_head_t eh_wait_q; int eh_tries; @@ -933,7 +884,8 @@ struct ata_port_operations { void (*set_piomode)(struct ata_port *ap, struct ata_device *dev); void (*set_dmamode)(struct ata_port *ap, struct ata_device *dev); int (*set_mode)(struct ata_link *link, struct ata_device **r_failed_dev); - unsigned int (*read_id)(struct ata_device *dev, struct ata_taskfile *tf, u16 *id); + unsigned int (*read_id)(struct ata_device *dev, struct ata_taskfile *tf, + __le16 *id); void (*dev_config)(struct ata_device *dev); @@ -1160,13 +1112,15 @@ extern enum ata_completion_errors ata_noop_qc_prep(struct ata_queued_cmd *qc); extern void ata_sg_init(struct ata_queued_cmd *qc, struct scatterlist *sg, unsigned int n_elem); extern unsigned int ata_dev_classify(const struct ata_taskfile *tf); +extern unsigned int ata_port_classify(struct ata_port *ap, + const struct ata_taskfile *tf); extern void ata_dev_disable(struct ata_device *adev); extern void ata_id_string(const u16 *id, unsigned char *s, unsigned int ofs, unsigned int len); extern void ata_id_c_string(const u16 *id, unsigned char *s, unsigned int ofs, unsigned int len); extern unsigned int ata_do_dev_read_id(struct ata_device *dev, - struct ata_taskfile *tf, u16 *id); + struct ata_taskfile *tf, __le16 *id); extern void ata_qc_complete(struct ata_queued_cmd *qc); extern u64 ata_qc_get_active(struct ata_port *ap); extern void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd); @@ -1432,6 +1386,12 @@ extern const struct attribute_group *ata_common_sdev_groups[]; .tag_alloc_policy = BLK_TAG_ALLOC_RR, \ .slave_configure = ata_scsi_slave_config +#define ATA_SUBBASE_SHT_QD(drv_name, drv_qd) \ + __ATA_BASE_SHT(drv_name), \ + .can_queue = drv_qd, \ + .tag_alloc_policy = BLK_TAG_ALLOC_RR, \ + .slave_configure = ata_scsi_slave_config + #define ATA_BASE_SHT(drv_name) \ ATA_SUBBASE_SHT(drv_name), \ .sdev_groups = ata_common_sdev_groups @@ -1443,6 +1403,11 @@ extern const struct attribute_group *ata_ncq_sdev_groups[]; ATA_SUBBASE_SHT(drv_name), \ .sdev_groups = ata_ncq_sdev_groups, \ .change_queue_depth = ata_scsi_change_queue_depth + +#define ATA_NCQ_SHT_QD(drv_name, drv_qd) \ + ATA_SUBBASE_SHT_QD(drv_name, drv_qd), \ + .sdev_groups = ata_ncq_sdev_groups, \ + .change_queue_depth = ata_scsi_change_queue_depth #endif /* @@ -1487,51 +1452,61 @@ static inline int sata_srst_pmp(struct ata_link *link) return link->pmp; } -/* - * printk helpers - */ -__printf(3, 4) -void ata_port_printk(const struct ata_port *ap, const char *level, - const char *fmt, ...); -__printf(3, 4) -void ata_link_printk(const struct ata_link *link, const char *level, - const char *fmt, ...); -__printf(3, 4) -void ata_dev_printk(const struct ata_device *dev, const char *level, - const char *fmt, ...); +#define ata_port_printk(level, ap, fmt, ...) \ + pr_ ## level ("ata%u: " fmt, (ap)->print_id, ##__VA_ARGS__) #define ata_port_err(ap, fmt, ...) \ - ata_port_printk(ap, KERN_ERR, fmt, ##__VA_ARGS__) + ata_port_printk(err, ap, fmt, ##__VA_ARGS__) #define ata_port_warn(ap, fmt, ...) \ - ata_port_printk(ap, KERN_WARNING, fmt, ##__VA_ARGS__) + ata_port_printk(warn, ap, fmt, ##__VA_ARGS__) #define ata_port_notice(ap, fmt, ...) \ - ata_port_printk(ap, KERN_NOTICE, fmt, ##__VA_ARGS__) + ata_port_printk(notice, ap, fmt, ##__VA_ARGS__) #define ata_port_info(ap, fmt, ...) \ - ata_port_printk(ap, KERN_INFO, fmt, ##__VA_ARGS__) + ata_port_printk(info, ap, fmt, ##__VA_ARGS__) #define ata_port_dbg(ap, fmt, ...) \ - ata_port_printk(ap, KERN_DEBUG, fmt, ##__VA_ARGS__) + ata_port_printk(debug, ap, fmt, ##__VA_ARGS__) + +#define ata_link_printk(level, link, fmt, ...) \ +do { \ + if (sata_pmp_attached((link)->ap) || \ + (link)->ap->slave_link) \ + pr_ ## level ("ata%u.%02u: " fmt, \ + (link)->ap->print_id, \ + (link)->pmp, \ + ##__VA_ARGS__); \ + else \ + pr_ ## level ("ata%u: " fmt, \ + (link)->ap->print_id, \ + ##__VA_ARGS__); \ +} while (0) #define ata_link_err(link, fmt, ...) \ - ata_link_printk(link, KERN_ERR, fmt, ##__VA_ARGS__) + ata_link_printk(err, link, fmt, ##__VA_ARGS__) #define ata_link_warn(link, fmt, ...) \ - ata_link_printk(link, KERN_WARNING, fmt, ##__VA_ARGS__) + ata_link_printk(warn, link, fmt, ##__VA_ARGS__) #define ata_link_notice(link, fmt, ...) \ - ata_link_printk(link, KERN_NOTICE, fmt, ##__VA_ARGS__) + ata_link_printk(notice, link, fmt, ##__VA_ARGS__) #define ata_link_info(link, fmt, ...) \ - ata_link_printk(link, KERN_INFO, fmt, ##__VA_ARGS__) + ata_link_printk(info, link, fmt, ##__VA_ARGS__) #define ata_link_dbg(link, fmt, ...) \ - ata_link_printk(link, KERN_DEBUG, fmt, ##__VA_ARGS__) + ata_link_printk(debug, link, fmt, ##__VA_ARGS__) + +#define ata_dev_printk(level, dev, fmt, ...) \ + pr_ ## level("ata%u.%02u: " fmt, \ + (dev)->link->ap->print_id, \ + (dev)->link->pmp + (dev)->devno, \ + ##__VA_ARGS__) #define ata_dev_err(dev, fmt, ...) \ - ata_dev_printk(dev, KERN_ERR, fmt, ##__VA_ARGS__) + ata_dev_printk(err, dev, fmt, ##__VA_ARGS__) #define ata_dev_warn(dev, fmt, ...) \ - ata_dev_printk(dev, KERN_WARNING, fmt, ##__VA_ARGS__) + ata_dev_printk(warn, dev, fmt, ##__VA_ARGS__) #define ata_dev_notice(dev, fmt, ...) \ - ata_dev_printk(dev, KERN_NOTICE, fmt, ##__VA_ARGS__) + ata_dev_printk(notice, dev, fmt, ##__VA_ARGS__) #define ata_dev_info(dev, fmt, ...) \ - ata_dev_printk(dev, KERN_INFO, fmt, ##__VA_ARGS__) + ata_dev_printk(info, dev, fmt, ##__VA_ARGS__) #define ata_dev_dbg(dev, fmt, ...) \ - ata_dev_printk(dev, KERN_DEBUG, fmt, ##__VA_ARGS__) + ata_dev_printk(debug, dev, fmt, ##__VA_ARGS__) void ata_print_version(const struct device *dev, const char *version); @@ -2065,11 +2040,8 @@ static inline u8 ata_wait_idle(struct ata_port *ap) { u8 status = ata_sff_busy_wait(ap, ATA_BUSY | ATA_DRQ, 1000); -#ifdef ATA_DEBUG if (status != 0xff && (status & (ATA_BUSY | ATA_DRQ))) - ata_port_printk(ap, KERN_DEBUG, "abnormal Status 0x%X\n", - status); -#endif + ata_port_dbg(ap, "abnormal Status 0x%X\n", status); return status; } diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 3764c1b51b02..9db36dc5d4cf 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -119,31 +119,6 @@ struct page { atomic_long_t pp_frag_count; }; }; - struct { /* slab, slob and slub */ - union { - struct list_head slab_list; - struct { /* Partial pages */ - struct page *next; -#ifdef CONFIG_64BIT - int pages; /* Nr of pages left */ -#else - short int pages; -#endif - }; - }; - struct kmem_cache *slab_cache; /* not slob */ - /* Double-word boundary */ - void *freelist; /* first free object */ - union { - void *s_mem; /* slab: first object */ - unsigned long counters; /* SLUB */ - struct { /* SLUB */ - unsigned inuse:16; - unsigned objects:15; - unsigned frozen:1; - }; - }; - }; struct { /* Tail pages of compound page */ unsigned long compound_head; /* Bit zero is set */ @@ -207,9 +182,6 @@ struct page { * which are currently stored here. */ unsigned int page_type; - - unsigned int active; /* SLAB */ - int units; /* SLOB */ }; /* Usage count. *DO NOT USE DIRECTLY*. See page_ref.h */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 129421002443..1c3b6e5c8bfd 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -920,43 +920,6 @@ extern bool is_free_buddy_page(struct page *page); __PAGEFLAG(Isolated, isolated, PF_ANY); -/* - * If network-based swap is enabled, sl*b must keep track of whether pages - * were allocated from pfmemalloc reserves. - */ -static inline int PageSlabPfmemalloc(struct page *page) -{ - VM_BUG_ON_PAGE(!PageSlab(page), page); - return PageActive(page); -} - -/* - * A version of PageSlabPfmemalloc() for opportunistic checks where the page - * might have been freed under us and not be a PageSlab anymore. - */ -static inline int __PageSlabPfmemalloc(struct page *page) -{ - return PageActive(page); -} - -static inline void SetPageSlabPfmemalloc(struct page *page) -{ - VM_BUG_ON_PAGE(!PageSlab(page), page); - SetPageActive(page); -} - -static inline void __ClearPageSlabPfmemalloc(struct page *page) -{ - VM_BUG_ON_PAGE(!PageSlab(page), page); - __ClearPageActive(page); -} - -static inline void ClearPageSlabPfmemalloc(struct page *page) -{ - VM_BUG_ON_PAGE(!PageSlab(page), page); - ClearPageActive(page); -} - #ifdef CONFIG_MMU #define __PG_MLOCKED (1UL << PG_mlocked) #else diff --git a/include/linux/platform_data/bcm7038_wdt.h b/include/linux/platform_data/bcm7038_wdt.h new file mode 100644 index 000000000000..e18cfd9ec8f9 --- /dev/null +++ b/include/linux/platform_data/bcm7038_wdt.h @@ -0,0 +1,8 @@ +#ifndef __BCM7038_WDT_PDATA_H +#define __BCM7038_WDT_PDATA_H + +struct bcm7038_wdt_platform_data { + const char *clk_name; +}; + +#endif /* __BCM7038_WDT_PDATA_H */ diff --git a/include/linux/pm.h b/include/linux/pm.h index e1e9402180b9..f7d2be686359 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -8,6 +8,7 @@ #ifndef _LINUX_PM_H #define _LINUX_PM_H +#include #include #include #include @@ -357,13 +358,47 @@ struct dev_pm_ops { #define SET_RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) #endif +#define _DEFINE_DEV_PM_OPS(name, \ + suspend_fn, resume_fn, \ + runtime_suspend_fn, runtime_resume_fn, idle_fn) \ +const struct dev_pm_ops name = { \ + SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ + RUNTIME_PM_OPS(runtime_suspend_fn, runtime_resume_fn, idle_fn) \ +} + +#ifdef CONFIG_PM +#define _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, runtime_suspend_fn, \ + runtime_resume_fn, idle_fn, sec) \ + _DEFINE_DEV_PM_OPS(name, suspend_fn, resume_fn, runtime_suspend_fn, \ + runtime_resume_fn, idle_fn); \ + _EXPORT_SYMBOL(name, sec) +#else +#define _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, runtime_suspend_fn, \ + runtime_resume_fn, idle_fn, sec) \ +static __maybe_unused _DEFINE_DEV_PM_OPS(__static_##name, suspend_fn, \ + resume_fn, runtime_suspend_fn, \ + runtime_resume_fn, idle_fn) +#endif + /* * Use this if you want to use the same suspend and resume callbacks for suspend * to RAM and hibernation. + * + * If the underlying dev_pm_ops struct symbol has to be exported, use + * EXPORT_SIMPLE_DEV_PM_OPS() or EXPORT_GPL_SIMPLE_DEV_PM_OPS() instead. */ #define DEFINE_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ -static const struct dev_pm_ops name = { \ - SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ + _DEFINE_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL) + +#define EXPORT_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ + _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "") +#define EXPORT_GPL_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ + _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "_gpl") + +/* Deprecated. Use DEFINE_SIMPLE_DEV_PM_OPS() instead. */ +#define SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ +const struct dev_pm_ops __maybe_unused name = { \ + SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ } /* @@ -378,20 +413,10 @@ static const struct dev_pm_ops name = { \ * suspend and "early" resume callback pointers, .suspend_late() and * .resume_early(), to the same routines as .runtime_suspend() and * .runtime_resume(), respectively (and analogously for hibernation). + * + * Deprecated. You most likely don't want this macro. Use + * DEFINE_RUNTIME_DEV_PM_OPS() instead. */ -#define DEFINE_UNIVERSAL_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ -static const struct dev_pm_ops name = { \ - SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ - RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ -} - -/* Deprecated. Use DEFINE_SIMPLE_DEV_PM_OPS() instead. */ -#define SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ -const struct dev_pm_ops __maybe_unused name = { \ - SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ -} - -/* Deprecated. Use DEFINE_UNIVERSAL_DEV_PM_OPS() instead. */ #define UNIVERSAL_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ const struct dev_pm_ops __maybe_unused name = { \ SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 016de5776b6d..9f09601c465a 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -22,6 +22,30 @@ usage_count */ #define RPM_AUTO 0x08 /* Use autosuspend_delay */ +/* + * Use this for defining a set of PM operations to be used in all situations + * (system suspend, hibernation or runtime PM). + * + * Note that the behaviour differs from the deprecated UNIVERSAL_DEV_PM_OPS() + * macro, which uses the provided callbacks for both runtime PM and system + * sleep, while DEFINE_RUNTIME_DEV_PM_OPS() uses pm_runtime_force_suspend() + * and pm_runtime_force_resume() for its system sleep callbacks. + * + * If the underlying dev_pm_ops struct symbol has to be exported, use + * EXPORT_RUNTIME_DEV_PM_OPS() or EXPORT_GPL_RUNTIME_DEV_PM_OPS() instead. + */ +#define DEFINE_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ + _DEFINE_DEV_PM_OPS(name, pm_runtime_force_suspend, \ + pm_runtime_force_resume, suspend_fn, \ + resume_fn, idle_fn) + +#define EXPORT_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ + _EXPORT_DEV_PM_OPS(name, pm_runtime_force_suspend, pm_runtime_force_resume, \ + suspend_fn, resume_fn, idle_fn, "") +#define EXPORT_GPL_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ + _EXPORT_DEV_PM_OPS(name, pm_runtime_force_suspend, pm_runtime_force_resume, \ + suspend_fn, resume_fn, idle_fn, "_gpl") + #ifdef CONFIG_PM extern struct workqueue_struct *pm_wq; diff --git a/include/linux/switchtec.h b/include/linux/switchtec.h index be24056ac00f..48fabe36509e 100644 --- a/include/linux/switchtec.h +++ b/include/linux/switchtec.h @@ -337,8 +337,6 @@ enum { NTB_CTRL_REQ_ID_EN = 1 << 0, NTB_CTRL_LUT_EN = 1 << 0, - - NTB_PART_CTRL_ID_PROT_DIS = 1 << 0, }; struct ntb_ctrl_regs { diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index c3011ccda430..2de442ececae 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -64,6 +64,7 @@ struct vdpa_mgmt_dev; * struct vdpa_device - representation of a vDPA device * @dev: underlying device * @dma_dev: the actual device that is performing DMA + * @driver_override: driver name to force a match * @config: the configuration ops for this device. * @cf_mutex: Protects get and set access to configuration layout. * @index: device index @@ -76,6 +77,7 @@ struct vdpa_mgmt_dev; struct vdpa_device { struct device dev; struct device *dma_dev; + const char *driver_override; const struct vdpa_config_ops *config; struct mutex cf_mutex; /* Protects get/set config */ unsigned int index; @@ -99,6 +101,7 @@ struct vdpa_dev_set_config { struct { u8 mac[ETH_ALEN]; u16 mtu; + u16 max_vq_pairs; } net; u64 mask; }; @@ -155,7 +158,7 @@ struct vdpa_map_file { * @vdev: vdpa device * @idx: virtqueue index * @state: pointer to returned state (last_avail_idx) - * @get_vq_notification: Get the notification area for a virtqueue + * @get_vq_notification: Get the notification area for a virtqueue (optional) * @vdev: vdpa device * @idx: virtqueue index * Returns the notifcation area @@ -169,14 +172,17 @@ struct vdpa_map_file { * for the device * @vdev: vdpa device * Returns virtqueue algin requirement - * @get_features: Get virtio features supported by the device + * @get_device_features: Get virtio features supported by the device * @vdev: vdpa device * Returns the virtio features support by the * device - * @set_features: Set virtio features supported by the driver + * @set_driver_features: Set virtio features supported by the driver * @vdev: vdpa device * @features: feature support by the driver * Returns integer: success (0) or error (< 0) + * @get_driver_features: Get the virtio driver features in action + * @vdev: vdpa device + * Returns the virtio features accepted * @set_config_cb: Set the config interrupt callback * @vdev: vdpa device * @cb: virtio-vdev interrupt callback structure @@ -276,8 +282,9 @@ struct vdpa_config_ops { /* Device ops */ u32 (*get_vq_align)(struct vdpa_device *vdev); - u64 (*get_features)(struct vdpa_device *vdev); - int (*set_features)(struct vdpa_device *vdev, u64 features); + u64 (*get_device_features)(struct vdpa_device *vdev); + int (*set_driver_features)(struct vdpa_device *vdev, u64 features); + u64 (*get_driver_features)(struct vdpa_device *vdev); void (*set_config_cb)(struct vdpa_device *vdev, struct vdpa_callback *cb); u16 (*get_vq_num_max)(struct vdpa_device *vdev); @@ -385,23 +392,37 @@ static inline struct device *vdpa_get_dma_dev(struct vdpa_device *vdev) static inline int vdpa_reset(struct vdpa_device *vdev) { const struct vdpa_config_ops *ops = vdev->config; + int ret; + mutex_lock(&vdev->cf_mutex); vdev->features_valid = false; - return ops->reset(vdev); + ret = ops->reset(vdev); + mutex_unlock(&vdev->cf_mutex); + return ret; } -static inline int vdpa_set_features(struct vdpa_device *vdev, u64 features) +static inline int vdpa_set_features(struct vdpa_device *vdev, u64 features, bool locked) { const struct vdpa_config_ops *ops = vdev->config; + int ret; + + if (!locked) + mutex_lock(&vdev->cf_mutex); vdev->features_valid = true; - return ops->set_features(vdev, features); + ret = ops->set_driver_features(vdev, features); + if (!locked) + mutex_unlock(&vdev->cf_mutex); + + return ret; } void vdpa_get_config(struct vdpa_device *vdev, unsigned int offset, void *buf, unsigned int len); void vdpa_set_config(struct vdpa_device *dev, unsigned int offset, const void *buf, unsigned int length); +void vdpa_set_status(struct vdpa_device *vdev, u8 status); + /** * struct vdpa_mgmtdev_ops - vdpa device ops * @dev_add: Add a vdpa device using alloc and register @@ -438,6 +459,8 @@ struct vdpa_mgmt_dev { const struct virtio_device_id *id_table; u64 config_attr_mask; struct list_head list; + u64 supported_features; + u32 max_supported_vqs; }; int vdpa_mgmtdev_register(struct vdpa_mgmt_dev *mdev); diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 41edbc01ffa4..72292a62cd90 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -138,6 +138,7 @@ int virtio_finalize_features(struct virtio_device *dev); int virtio_device_freeze(struct virtio_device *dev); int virtio_device_restore(struct virtio_device *dev); #endif +void virtio_reset_device(struct virtio_device *dev); size_t virtio_max_dma_size(struct virtio_device *vdev); diff --git a/include/trace/events/libata.h b/include/trace/events/libata.h index ab69434e2329..d4e631aa976f 100644 --- a/include/trace/events/libata.h +++ b/include/trace/events/libata.h @@ -132,9 +132,37 @@ ata_protocol_name(ATAPI_PROT_PIO), \ ata_protocol_name(ATAPI_PROT_DMA)) +#define ata_class_name(class) { class, #class } +#define show_class_name(val) \ + __print_symbolic(val, \ + ata_class_name(ATA_DEV_UNKNOWN), \ + ata_class_name(ATA_DEV_ATA), \ + ata_class_name(ATA_DEV_ATA_UNSUP), \ + ata_class_name(ATA_DEV_ATAPI), \ + ata_class_name(ATA_DEV_ATAPI_UNSUP), \ + ata_class_name(ATA_DEV_PMP), \ + ata_class_name(ATA_DEV_PMP_UNSUP), \ + ata_class_name(ATA_DEV_SEMB), \ + ata_class_name(ATA_DEV_SEMB_UNSUP), \ + ata_class_name(ATA_DEV_ZAC), \ + ata_class_name(ATA_DEV_ZAC_UNSUP), \ + ata_class_name(ATA_DEV_NONE)) + +#define ata_sff_hsm_state_name(state) { state, #state } +#define show_sff_hsm_state_name(val) \ + __print_symbolic(val, \ + ata_sff_hsm_state_name(HSM_ST_IDLE), \ + ata_sff_hsm_state_name(HSM_ST_FIRST), \ + ata_sff_hsm_state_name(HSM_ST), \ + ata_sff_hsm_state_name(HSM_ST_LAST), \ + ata_sff_hsm_state_name(HSM_ST_ERR)) + const char *libata_trace_parse_status(struct trace_seq*, unsigned char); #define __parse_status(s) libata_trace_parse_status(p, s) +const char *libata_trace_parse_host_stat(struct trace_seq *, unsigned char); +#define __parse_host_stat(s) libata_trace_parse_host_stat(p, s) + const char *libata_trace_parse_eh_action(struct trace_seq *, unsigned int); #define __parse_eh_action(a) libata_trace_parse_eh_action(p, a) @@ -144,11 +172,14 @@ const char *libata_trace_parse_eh_err_mask(struct trace_seq *, unsigned int); const char *libata_trace_parse_qc_flags(struct trace_seq *, unsigned int); #define __parse_qc_flags(f) libata_trace_parse_qc_flags(p, f) +const char *libata_trace_parse_tf_flags(struct trace_seq *, unsigned int); +#define __parse_tf_flags(f) libata_trace_parse_tf_flags(p, f) + const char *libata_trace_parse_subcmd(struct trace_seq *, unsigned char, unsigned char, unsigned char); #define __parse_subcmd(c,f,h) libata_trace_parse_subcmd(p, c, f, h) -TRACE_EVENT(ata_qc_issue, +DECLARE_EVENT_CLASS(ata_qc_issue_template, TP_PROTO(struct ata_queued_cmd *qc), @@ -207,6 +238,14 @@ TRACE_EVENT(ata_qc_issue, __entry->dev) ); +DEFINE_EVENT(ata_qc_issue_template, ata_qc_prep, + TP_PROTO(struct ata_queued_cmd *qc), + TP_ARGS(qc)); + +DEFINE_EVENT(ata_qc_issue_template, ata_qc_issue, + TP_PROTO(struct ata_queued_cmd *qc), + TP_ARGS(qc)); + DECLARE_EVENT_CLASS(ata_qc_complete_template, TP_PROTO(struct ata_queued_cmd *qc), @@ -275,6 +314,128 @@ DEFINE_EVENT(ata_qc_complete_template, ata_qc_complete_done, TP_PROTO(struct ata_queued_cmd *qc), TP_ARGS(qc)); +TRACE_EVENT(ata_tf_load, + + TP_PROTO(struct ata_port *ap, const struct ata_taskfile *tf), + + TP_ARGS(ap, tf), + + TP_STRUCT__entry( + __field( unsigned int, ata_port ) + __field( unsigned char, cmd ) + __field( unsigned char, dev ) + __field( unsigned char, lbal ) + __field( unsigned char, lbam ) + __field( unsigned char, lbah ) + __field( unsigned char, nsect ) + __field( unsigned char, feature ) + __field( unsigned char, hob_lbal ) + __field( unsigned char, hob_lbam ) + __field( unsigned char, hob_lbah ) + __field( unsigned char, hob_nsect ) + __field( unsigned char, hob_feature ) + __field( unsigned char, proto ) + ), + + TP_fast_assign( + __entry->ata_port = ap->print_id; + __entry->proto = tf->protocol; + __entry->cmd = tf->command; + __entry->dev = tf->device; + __entry->lbal = tf->lbal; + __entry->lbam = tf->lbam; + __entry->lbah = tf->lbah; + __entry->hob_lbal = tf->hob_lbal; + __entry->hob_lbam = tf->hob_lbam; + __entry->hob_lbah = tf->hob_lbah; + __entry->feature = tf->feature; + __entry->hob_feature = tf->hob_feature; + __entry->nsect = tf->nsect; + __entry->hob_nsect = tf->hob_nsect; + ), + + TP_printk("ata_port=%u proto=%s cmd=%s%s " \ + " tf=(%02x/%02x:%02x:%02x:%02x:%02x/%02x:%02x:%02x:%02x:%02x/%02x)", + __entry->ata_port, + show_protocol_name(__entry->proto), + show_opcode_name(__entry->cmd), + __parse_subcmd(__entry->cmd, __entry->feature, __entry->hob_nsect), + __entry->cmd, __entry->feature, __entry->nsect, + __entry->lbal, __entry->lbam, __entry->lbah, + __entry->hob_feature, __entry->hob_nsect, + __entry->hob_lbal, __entry->hob_lbam, __entry->hob_lbah, + __entry->dev) +); + +DECLARE_EVENT_CLASS(ata_exec_command_template, + + TP_PROTO(struct ata_port *ap, const struct ata_taskfile *tf, unsigned int tag), + + TP_ARGS(ap, tf, tag), + + TP_STRUCT__entry( + __field( unsigned int, ata_port ) + __field( unsigned int, tag ) + __field( unsigned char, cmd ) + __field( unsigned char, feature ) + __field( unsigned char, hob_nsect ) + __field( unsigned char, proto ) + ), + + TP_fast_assign( + __entry->ata_port = ap->print_id; + __entry->tag = tag; + __entry->proto = tf->protocol; + __entry->cmd = tf->command; + __entry->feature = tf->feature; + __entry->hob_nsect = tf->hob_nsect; + ), + + TP_printk("ata_port=%u tag=%d proto=%s cmd=%s%s", + __entry->ata_port, __entry->tag, + show_protocol_name(__entry->proto), + show_opcode_name(__entry->cmd), + __parse_subcmd(__entry->cmd, __entry->feature, __entry->hob_nsect)) +); + +DEFINE_EVENT(ata_exec_command_template, ata_exec_command, + TP_PROTO(struct ata_port *ap, const struct ata_taskfile *tf, unsigned int tag), + TP_ARGS(ap, tf, tag)); + +DEFINE_EVENT(ata_exec_command_template, ata_bmdma_setup, + TP_PROTO(struct ata_port *ap, const struct ata_taskfile *tf, unsigned int tag), + TP_ARGS(ap, tf, tag)); + +DEFINE_EVENT(ata_exec_command_template, ata_bmdma_start, + TP_PROTO(struct ata_port *ap, const struct ata_taskfile *tf, unsigned int tag), + TP_ARGS(ap, tf, tag)); + +DEFINE_EVENT(ata_exec_command_template, ata_bmdma_stop, + TP_PROTO(struct ata_port *ap, const struct ata_taskfile *tf, unsigned int tag), + TP_ARGS(ap, tf, tag)); + +TRACE_EVENT(ata_bmdma_status, + + TP_PROTO(struct ata_port *ap, unsigned int host_stat), + + TP_ARGS(ap, host_stat), + + TP_STRUCT__entry( + __field( unsigned int, ata_port ) + __field( unsigned int, tag ) + __field( unsigned char, host_stat ) + ), + + TP_fast_assign( + __entry->ata_port = ap->print_id; + __entry->host_stat = host_stat; + ), + + TP_printk("ata_port=%u host_stat=%s", + __entry->ata_port, + __parse_host_stat(__entry->host_stat)) +); + TRACE_EVENT(ata_eh_link_autopsy, TP_PROTO(struct ata_device *dev, unsigned int eh_action, unsigned int eh_err_mask), @@ -329,6 +490,259 @@ TRACE_EVENT(ata_eh_link_autopsy_qc, __parse_eh_err_mask(__entry->eh_err_mask)) ); +DECLARE_EVENT_CLASS(ata_eh_action_template, + + TP_PROTO(struct ata_link *link, unsigned int devno, unsigned int eh_action), + + TP_ARGS(link, devno, eh_action), + + TP_STRUCT__entry( + __field( unsigned int, ata_port ) + __field( unsigned int, ata_dev ) + __field( unsigned int, eh_action ) + ), + + TP_fast_assign( + __entry->ata_port = link->ap->print_id; + __entry->ata_dev = link->pmp + devno; + __entry->eh_action = eh_action; + ), + + TP_printk("ata_port=%u ata_dev=%u eh_action=%s", + __entry->ata_port, __entry->ata_dev, + __parse_eh_action(__entry->eh_action)) +); + +DEFINE_EVENT(ata_eh_action_template, ata_eh_about_to_do, + TP_PROTO(struct ata_link *link, unsigned int devno, unsigned int eh_action), + TP_ARGS(link, devno, eh_action)); + +DEFINE_EVENT(ata_eh_action_template, ata_eh_done, + TP_PROTO(struct ata_link *link, unsigned int devno, unsigned int eh_action), + TP_ARGS(link, devno, eh_action)); + +DECLARE_EVENT_CLASS(ata_link_reset_begin_template, + + TP_PROTO(struct ata_link *link, unsigned int *class, unsigned long deadline), + + TP_ARGS(link, class, deadline), + + TP_STRUCT__entry( + __field( unsigned int, ata_port ) + __array( unsigned int, class, 2 ) + __field( unsigned long, deadline ) + ), + + TP_fast_assign( + __entry->ata_port = link->ap->print_id; + memcpy(__entry->class, class, 2); + __entry->deadline = deadline; + ), + + TP_printk("ata_port=%u deadline=%lu classes=[%s,%s]", + __entry->ata_port, __entry->deadline, + show_class_name(__entry->class[0]), + show_class_name(__entry->class[1])) +); + +DEFINE_EVENT(ata_link_reset_begin_template, ata_link_hardreset_begin, + TP_PROTO(struct ata_link *link, unsigned int *class, unsigned long deadline), + TP_ARGS(link, class, deadline)); + +DEFINE_EVENT(ata_link_reset_begin_template, ata_slave_hardreset_begin, + TP_PROTO(struct ata_link *link, unsigned int *class, unsigned long deadline), + TP_ARGS(link, class, deadline)); + +DEFINE_EVENT(ata_link_reset_begin_template, ata_link_softreset_begin, + TP_PROTO(struct ata_link *link, unsigned int *class, unsigned long deadline), + TP_ARGS(link, class, deadline)); + +DECLARE_EVENT_CLASS(ata_link_reset_end_template, + + TP_PROTO(struct ata_link *link, unsigned int *class, int rc), + + TP_ARGS(link, class, rc), + + TP_STRUCT__entry( + __field( unsigned int, ata_port ) + __array( unsigned int, class, 2 ) + __field( int, rc ) + ), + + TP_fast_assign( + __entry->ata_port = link->ap->print_id; + memcpy(__entry->class, class, 2); + __entry->rc = rc; + ), + + TP_printk("ata_port=%u rc=%d class=[%s,%s]", + __entry->ata_port, __entry->rc, + show_class_name(__entry->class[0]), + show_class_name(__entry->class[1])) +); + +DEFINE_EVENT(ata_link_reset_end_template, ata_link_hardreset_end, + TP_PROTO(struct ata_link *link, unsigned int *class, int rc), + TP_ARGS(link, class, rc)); + +DEFINE_EVENT(ata_link_reset_end_template, ata_slave_hardreset_end, + TP_PROTO(struct ata_link *link, unsigned int *class, int rc), + TP_ARGS(link, class, rc)); + +DEFINE_EVENT(ata_link_reset_end_template, ata_link_softreset_end, + TP_PROTO(struct ata_link *link, unsigned int *class, int rc), + TP_ARGS(link, class, rc)); + +DEFINE_EVENT(ata_link_reset_end_template, ata_link_postreset, + TP_PROTO(struct ata_link *link, unsigned int *class, int rc), + TP_ARGS(link, class, rc)); + +DEFINE_EVENT(ata_link_reset_end_template, ata_slave_postreset, + TP_PROTO(struct ata_link *link, unsigned int *class, int rc), + TP_ARGS(link, class, rc)); + +DECLARE_EVENT_CLASS(ata_port_eh_begin_template, + + TP_PROTO(struct ata_port *ap), + + TP_ARGS(ap), + + TP_STRUCT__entry( + __field( unsigned int, ata_port ) + ), + + TP_fast_assign( + __entry->ata_port = ap->print_id; + ), + + TP_printk("ata_port=%u", __entry->ata_port) +); + +DEFINE_EVENT(ata_port_eh_begin_template, ata_std_sched_eh, + TP_PROTO(struct ata_port *ap), + TP_ARGS(ap)); + +DEFINE_EVENT(ata_port_eh_begin_template, ata_port_freeze, + TP_PROTO(struct ata_port *ap), + TP_ARGS(ap)); + +DEFINE_EVENT(ata_port_eh_begin_template, ata_port_thaw, + TP_PROTO(struct ata_port *ap), + TP_ARGS(ap)); + +DECLARE_EVENT_CLASS(ata_sff_hsm_template, + + TP_PROTO(struct ata_queued_cmd *qc, unsigned char status), + + TP_ARGS(qc, status), + + TP_STRUCT__entry( + __field( unsigned int, ata_port ) + __field( unsigned int, ata_dev ) + __field( unsigned int, tag ) + __field( unsigned int, qc_flags ) + __field( unsigned int, protocol ) + __field( unsigned int, hsm_state ) + __field( unsigned char, dev_state ) + ), + + TP_fast_assign( + __entry->ata_port = qc->ap->print_id; + __entry->ata_dev = qc->dev->link->pmp + qc->dev->devno; + __entry->tag = qc->tag; + __entry->qc_flags = qc->flags; + __entry->protocol = qc->tf.protocol; + __entry->hsm_state = qc->ap->hsm_task_state; + __entry->dev_state = status; + ), + + TP_printk("ata_port=%u ata_dev=%u tag=%d proto=%s flags=%s task_state=%s dev_stat=0x%X", + __entry->ata_port, __entry->ata_dev, __entry->tag, + show_protocol_name(__entry->protocol), + __parse_qc_flags(__entry->qc_flags), + show_sff_hsm_state_name(__entry->hsm_state), + __entry->dev_state) +); + +DEFINE_EVENT(ata_sff_hsm_template, ata_sff_hsm_state, + TP_PROTO(struct ata_queued_cmd *qc, unsigned char state), + TP_ARGS(qc, state)); + +DEFINE_EVENT(ata_sff_hsm_template, ata_sff_hsm_command_complete, + TP_PROTO(struct ata_queued_cmd *qc, unsigned char state), + TP_ARGS(qc, state)); + +DEFINE_EVENT(ata_sff_hsm_template, ata_sff_port_intr, + TP_PROTO(struct ata_queued_cmd *qc, unsigned char state), + TP_ARGS(qc, state)); + +DECLARE_EVENT_CLASS(ata_transfer_data_template, + + TP_PROTO(struct ata_queued_cmd *qc, unsigned int offset, unsigned int count), + + TP_ARGS(qc, offset, count), + + TP_STRUCT__entry( + __field( unsigned int, ata_port ) + __field( unsigned int, ata_dev ) + __field( unsigned int, tag ) + __field( unsigned int, flags ) + __field( unsigned int, offset ) + __field( unsigned int, bytes ) + ), + + TP_fast_assign( + __entry->ata_port = qc->ap->print_id; + __entry->ata_dev = qc->dev->link->pmp + qc->dev->devno; + __entry->tag = qc->tag; + __entry->flags = qc->tf.flags; + __entry->offset = offset; + __entry->bytes = count; + ), + + TP_printk("ata_port=%u ata_dev=%u tag=%d flags=%s offset=%u bytes=%u", + __entry->ata_port, __entry->ata_dev, __entry->tag, + __parse_tf_flags(__entry->flags), + __entry->offset, __entry->bytes) +); + +DEFINE_EVENT(ata_transfer_data_template, ata_sff_pio_transfer_data, + TP_PROTO(struct ata_queued_cmd *qc, unsigned int offset, unsigned int count), + TP_ARGS(qc, offset, count)); + +DEFINE_EVENT(ata_transfer_data_template, atapi_pio_transfer_data, + TP_PROTO(struct ata_queued_cmd *qc, unsigned int offset, unsigned int count), + TP_ARGS(qc, offset, count)); + +DEFINE_EVENT(ata_transfer_data_template, atapi_send_cdb, + TP_PROTO(struct ata_queued_cmd *qc, unsigned int offset, unsigned int count), + TP_ARGS(qc, offset, count)); + +DECLARE_EVENT_CLASS(ata_sff_template, + + TP_PROTO(struct ata_port *ap), + + TP_ARGS(ap), + + TP_STRUCT__entry( + __field( unsigned int, ata_port ) + __field( unsigned char, hsm_state ) + ), + + TP_fast_assign( + __entry->ata_port = ap->print_id; + __entry->hsm_state = ap->hsm_task_state; + ), + + TP_printk("ata_port=%u task_state=%s", + __entry->ata_port, + show_sff_hsm_state_name(__entry->hsm_state)) +); + +DEFINE_EVENT(ata_sff_template, ata_sff_flush_pio_task, + TP_PROTO(struct ata_port *ap), + TP_ARGS(ap)); + #endif /* _TRACE_LIBATA_H */ /* This part must be outside protection */ diff --git a/include/trace/events/random.h b/include/trace/events/random.h index 3d7b432ca5f3..a2d9aa16a5d7 100644 --- a/include/trace/events/random.h +++ b/include/trace/events/random.h @@ -28,80 +28,71 @@ TRACE_EVENT(add_device_randomness, ); DECLARE_EVENT_CLASS(random__mix_pool_bytes, - TP_PROTO(const char *pool_name, int bytes, unsigned long IP), + TP_PROTO(int bytes, unsigned long IP), - TP_ARGS(pool_name, bytes, IP), + TP_ARGS(bytes, IP), TP_STRUCT__entry( - __field( const char *, pool_name ) __field( int, bytes ) __field(unsigned long, IP ) ), TP_fast_assign( - __entry->pool_name = pool_name; __entry->bytes = bytes; __entry->IP = IP; ), - TP_printk("%s pool: bytes %d caller %pS", - __entry->pool_name, __entry->bytes, (void *)__entry->IP) + TP_printk("input pool: bytes %d caller %pS", + __entry->bytes, (void *)__entry->IP) ); DEFINE_EVENT(random__mix_pool_bytes, mix_pool_bytes, - TP_PROTO(const char *pool_name, int bytes, unsigned long IP), + TP_PROTO(int bytes, unsigned long IP), - TP_ARGS(pool_name, bytes, IP) + TP_ARGS(bytes, IP) ); DEFINE_EVENT(random__mix_pool_bytes, mix_pool_bytes_nolock, - TP_PROTO(const char *pool_name, int bytes, unsigned long IP), + TP_PROTO(int bytes, unsigned long IP), - TP_ARGS(pool_name, bytes, IP) + TP_ARGS(bytes, IP) ); TRACE_EVENT(credit_entropy_bits, - TP_PROTO(const char *pool_name, int bits, int entropy_count, - unsigned long IP), + TP_PROTO(int bits, int entropy_count, unsigned long IP), - TP_ARGS(pool_name, bits, entropy_count, IP), + TP_ARGS(bits, entropy_count, IP), TP_STRUCT__entry( - __field( const char *, pool_name ) __field( int, bits ) __field( int, entropy_count ) __field(unsigned long, IP ) ), TP_fast_assign( - __entry->pool_name = pool_name; __entry->bits = bits; __entry->entropy_count = entropy_count; __entry->IP = IP; ), - TP_printk("%s pool: bits %d entropy_count %d caller %pS", - __entry->pool_name, __entry->bits, - __entry->entropy_count, (void *)__entry->IP) + TP_printk("input pool: bits %d entropy_count %d caller %pS", + __entry->bits, __entry->entropy_count, (void *)__entry->IP) ); TRACE_EVENT(debit_entropy, - TP_PROTO(const char *pool_name, int debit_bits), + TP_PROTO(int debit_bits), - TP_ARGS(pool_name, debit_bits), + TP_ARGS( debit_bits), TP_STRUCT__entry( - __field( const char *, pool_name ) __field( int, debit_bits ) ), TP_fast_assign( - __entry->pool_name = pool_name; __entry->debit_bits = debit_bits; ), - TP_printk("%s: debit_bits %d", __entry->pool_name, - __entry->debit_bits) + TP_printk("input pool: debit_bits %d", __entry->debit_bits) ); TRACE_EVENT(add_input_randomness, @@ -170,36 +161,31 @@ DEFINE_EVENT(random__get_random_bytes, get_random_bytes_arch, ); DECLARE_EVENT_CLASS(random__extract_entropy, - TP_PROTO(const char *pool_name, int nbytes, int entropy_count, - unsigned long IP), + TP_PROTO(int nbytes, int entropy_count, unsigned long IP), - TP_ARGS(pool_name, nbytes, entropy_count, IP), + TP_ARGS(nbytes, entropy_count, IP), TP_STRUCT__entry( - __field( const char *, pool_name ) __field( int, nbytes ) __field( int, entropy_count ) __field(unsigned long, IP ) ), TP_fast_assign( - __entry->pool_name = pool_name; __entry->nbytes = nbytes; __entry->entropy_count = entropy_count; __entry->IP = IP; ), - TP_printk("%s pool: nbytes %d entropy_count %d caller %pS", - __entry->pool_name, __entry->nbytes, __entry->entropy_count, - (void *)__entry->IP) + TP_printk("input pool: nbytes %d entropy_count %d caller %pS", + __entry->nbytes, __entry->entropy_count, (void *)__entry->IP) ); DEFINE_EVENT(random__extract_entropy, extract_entropy, - TP_PROTO(const char *pool_name, int nbytes, int entropy_count, - unsigned long IP), + TP_PROTO(int nbytes, int entropy_count, unsigned long IP), - TP_ARGS(pool_name, nbytes, entropy_count, IP) + TP_ARGS(nbytes, entropy_count, IP) ); TRACE_EVENT(urandom_read, diff --git a/include/uapi/linux/idxd.h b/include/uapi/linux/idxd.h index c750eac09fc9..a8f0ff75c430 100644 --- a/include/uapi/linux/idxd.h +++ b/include/uapi/linux/idxd.h @@ -28,6 +28,7 @@ enum idxd_scmd_stat { IDXD_SCMD_WQ_NONE_CONFIGURED = 0x800d0000, IDXD_SCMD_WQ_NO_SIZE = 0x800e0000, IDXD_SCMD_WQ_NO_PRIV = 0x800f0000, + IDXD_SCMD_WQ_IRQ_ERR = 0x80100000, }; #define IDXD_SCMD_SOFTERR_MASK 0x80000000 diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index 8ab81ea13424..dae5df88ab10 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -52,6 +52,7 @@ #define QNX6_SUPER_MAGIC 0x68191122 /* qnx6 fs detection */ #define AFS_FS_MAGIC 0x6B414653 + #define REISERFS_SUPER_MAGIC 0x52654973 /* used by gcc */ /* used by file system utilities that look at the superblock, etc. */ @@ -60,6 +61,9 @@ #define REISER2FS_JR_SUPER_MAGIC_STRING "ReIsEr3Fs" #define SMB_SUPER_MAGIC 0x517B +#define CIFS_SUPER_MAGIC 0xFF534D42 /* the first four bytes of SMB PDUs */ +#define SMB2_SUPER_MAGIC 0xFE534D42 + #define CGROUP_SUPER_MAGIC 0x27e0eb #define CGROUP2_SUPER_MAGIC 0x63677270 diff --git a/include/uapi/linux/pfrut.h b/include/uapi/linux/pfrut.h new file mode 100644 index 000000000000..42fa15f8310d --- /dev/null +++ b/include/uapi/linux/pfrut.h @@ -0,0 +1,262 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Platform Firmware Runtime Update header + * + * Copyright(c) 2021 Intel Corporation. All rights reserved. + */ +#ifndef __PFRUT_H__ +#define __PFRUT_H__ + +#include +#include + +#define PFRUT_IOCTL_MAGIC 0xEE + +/** + * PFRU_IOC_SET_REV - _IOW(PFRUT_IOCTL_MAGIC, 0x01, unsigned int) + * + * Return: + * * 0 - success + * * -EFAULT - fail to read the revision id + * * -EINVAL - user provides an invalid revision id + * + * Set the Revision ID for Platform Firmware Runtime Update. + */ +#define PFRU_IOC_SET_REV _IOW(PFRUT_IOCTL_MAGIC, 0x01, unsigned int) + +/** + * PFRU_IOC_STAGE - _IOW(PFRUT_IOCTL_MAGIC, 0x02, unsigned int) + * + * Return: + * * 0 - success + * * -EINVAL - stage phase returns invalid result + * + * Stage a capsule image from communication buffer and perform authentication. + */ +#define PFRU_IOC_STAGE _IOW(PFRUT_IOCTL_MAGIC, 0x02, unsigned int) + +/** + * PFRU_IOC_ACTIVATE - _IOW(PFRUT_IOCTL_MAGIC, 0x03, unsigned int) + * + * Return: + * * 0 - success + * * -EINVAL - activate phase returns invalid result + * + * Activate a previously staged capsule image. + */ +#define PFRU_IOC_ACTIVATE _IOW(PFRUT_IOCTL_MAGIC, 0x03, unsigned int) + +/** + * PFRU_IOC_STAGE_ACTIVATE - _IOW(PFRUT_IOCTL_MAGIC, 0x04, unsigned int) + * + * Return: + * * 0 - success + * * -EINVAL - stage/activate phase returns invalid result. + * + * Perform both stage and activation action. + */ +#define PFRU_IOC_STAGE_ACTIVATE _IOW(PFRUT_IOCTL_MAGIC, 0x04, unsigned int) + +/** + * PFRU_IOC_QUERY_CAP - _IOR(PFRUT_IOCTL_MAGIC, 0x05, + * struct pfru_update_cap_info) + * + * Return: + * * 0 - success + * * -EINVAL - query phase returns invalid result + * * -EFAULT - the result fails to be copied to userspace + * + * Retrieve information on the Platform Firmware Runtime Update capability. + * The information is a struct pfru_update_cap_info. + */ +#define PFRU_IOC_QUERY_CAP _IOR(PFRUT_IOCTL_MAGIC, 0x05, struct pfru_update_cap_info) + +/** + * struct pfru_payload_hdr - Capsule file payload header. + * + * @sig: Signature of this capsule file. + * @hdr_version: Revision of this header structure. + * @hdr_size: Size of this header, including the OemHeader bytes. + * @hw_ver: The supported firmware version. + * @rt_ver: Version of the code injection image. + * @platform_id: A platform specific GUID to specify the platform what + * this capsule image support. + */ +struct pfru_payload_hdr { + __u32 sig; + __u32 hdr_version; + __u32 hdr_size; + __u32 hw_ver; + __u32 rt_ver; + __u8 platform_id[16]; +}; + +enum pfru_dsm_status { + DSM_SUCCEED = 0, + DSM_FUNC_NOT_SUPPORT = 1, + DSM_INVAL_INPUT = 2, + DSM_HARDWARE_ERR = 3, + DSM_RETRY_SUGGESTED = 4, + DSM_UNKNOWN = 5, + DSM_FUNC_SPEC_ERR = 6, +}; + +/** + * struct pfru_update_cap_info - Runtime update capability information. + * + * @status: Indicator of whether this query succeed. + * @update_cap: Bitmap to indicate whether the feature is supported. + * @code_type: A buffer containing an image type GUID. + * @fw_version: Platform firmware version. + * @code_rt_version: Code injection runtime version for anti-rollback. + * @drv_type: A buffer containing an image type GUID. + * @drv_rt_version: The version of the driver update runtime code. + * @drv_svn: The secure version number(SVN) of the driver update runtime code. + * @platform_id: A buffer containing a platform ID GUID. + * @oem_id: A buffer containing an OEM ID GUID. + * @oem_info_len: Length of the buffer containing the vendor specific information. + */ +struct pfru_update_cap_info { + __u32 status; + __u32 update_cap; + + __u8 code_type[16]; + __u32 fw_version; + __u32 code_rt_version; + + __u8 drv_type[16]; + __u32 drv_rt_version; + __u32 drv_svn; + + __u8 platform_id[16]; + __u8 oem_id[16]; + + __u32 oem_info_len; +}; + +/** + * struct pfru_com_buf_info - Communication buffer information. + * + * @status: Indicator of whether this query succeed. + * @ext_status: Implementation specific query result. + * @addr_lo: Low 32bit physical address of the communication buffer to hold + * a runtime update package. + * @addr_hi: High 32bit physical address of the communication buffer to hold + * a runtime update package. + * @buf_size: Maximum size in bytes of the communication buffer. + */ +struct pfru_com_buf_info { + __u32 status; + __u32 ext_status; + __u64 addr_lo; + __u64 addr_hi; + __u32 buf_size; +}; + +/** + * struct pfru_updated_result - Platform firmware runtime update result information. + * @status: Indicator of whether this update succeed. + * @ext_status: Implementation specific update result. + * @low_auth_time: Low 32bit value of image authentication time in nanosecond. + * @high_auth_time: High 32bit value of image authentication time in nanosecond. + * @low_exec_time: Low 32bit value of image execution time in nanosecond. + * @high_exec_time: High 32bit value of image execution time in nanosecond. + */ +struct pfru_updated_result { + __u32 status; + __u32 ext_status; + __u64 low_auth_time; + __u64 high_auth_time; + __u64 low_exec_time; + __u64 high_exec_time; +}; + +/** + * struct pfrt_log_data_info - Log Data from telemetry service. + * @status: Indicator of whether this update succeed. + * @ext_status: Implementation specific update result. + * @chunk1_addr_lo: Low 32bit physical address of the telemetry data chunk1 + * starting address. + * @chunk1_addr_hi: High 32bit physical address of the telemetry data chunk1 + * starting address. + * @chunk2_addr_lo: Low 32bit physical address of the telemetry data chunk2 + * starting address. + * @chunk2_addr_hi: High 32bit physical address of the telemetry data chunk2 + * starting address. + * @max_data_size: Maximum supported size of data of all data chunks combined. + * @chunk1_size: Data size in bytes of the telemetry data chunk1 buffer. + * @chunk2_size: Data size in bytes of the telemetry data chunk2 buffer. + * @rollover_cnt: Number of times telemetry data buffer is overwritten + * since telemetry buffer reset. + * @reset_cnt: Number of times telemetry services resets that results in + * rollover count and data chunk buffers are reset. + */ +struct pfrt_log_data_info { + __u32 status; + __u32 ext_status; + __u64 chunk1_addr_lo; + __u64 chunk1_addr_hi; + __u64 chunk2_addr_lo; + __u64 chunk2_addr_hi; + __u32 max_data_size; + __u32 chunk1_size; + __u32 chunk2_size; + __u32 rollover_cnt; + __u32 reset_cnt; +}; + +/** + * struct pfrt_log_info - Telemetry log information. + * @log_level: The telemetry log level. + * @log_type: The telemetry log type(history and execution). + * @log_revid: The telemetry log revision id. + */ +struct pfrt_log_info { + __u32 log_level; + __u32 log_type; + __u32 log_revid; +}; + +/** + * PFRT_LOG_IOC_SET_INFO - _IOW(PFRUT_IOCTL_MAGIC, 0x06, + * struct pfrt_log_info) + * + * Return: + * * 0 - success + * * -EFAULT - fail to get the setting parameter + * * -EINVAL - fail to set the log level + * + * Set the PFRT log level and log type. The input information is + * a struct pfrt_log_info. + */ +#define PFRT_LOG_IOC_SET_INFO _IOW(PFRUT_IOCTL_MAGIC, 0x06, struct pfrt_log_info) + +/** + * PFRT_LOG_IOC_GET_INFO - _IOR(PFRUT_IOCTL_MAGIC, 0x07, + * struct pfrt_log_info) + * + * Return: + * * 0 - success + * * -EINVAL - fail to get the log level + * * -EFAULT - fail to copy the result back to userspace + * + * Retrieve log level and log type of the telemetry. The information is + * a struct pfrt_log_info. + */ +#define PFRT_LOG_IOC_GET_INFO _IOR(PFRUT_IOCTL_MAGIC, 0x07, struct pfrt_log_info) + +/** + * PFRT_LOG_IOC_GET_DATA_INFO - _IOR(PFRUT_IOCTL_MAGIC, 0x08, + * struct pfrt_log_data_info) + * + * Return: + * * 0 - success + * * -EINVAL - fail to get the log buffer information + * * -EFAULT - fail to copy the log buffer information to userspace + * + * Retrieve data information about the telemetry. The information + * is a struct pfrt_log_data_info. + */ +#define PFRT_LOG_IOC_GET_DATA_INFO _IOR(PFRUT_IOCTL_MAGIC, 0x08, struct pfrt_log_data_info) + +#endif /* __PFRUT_H__ */ diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index a252f06f9dfd..1061d8d2d09d 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -23,6 +23,9 @@ enum vdpa_command { enum vdpa_attr { VDPA_ATTR_UNSPEC, + /* Pad attribute for 64b alignment */ + VDPA_ATTR_PAD = VDPA_ATTR_UNSPEC, + /* bus name (optional) + dev name together make the parent device handle */ VDPA_ATTR_MGMTDEV_BUS_NAME, /* string */ VDPA_ATTR_MGMTDEV_DEV_NAME, /* string */ @@ -40,6 +43,9 @@ enum vdpa_attr { VDPA_ATTR_DEV_NET_CFG_MAX_VQP, /* u16 */ VDPA_ATTR_DEV_NET_CFG_MTU, /* u16 */ + VDPA_ATTR_DEV_NEGOTIATED_FEATURES, /* u64 */ + VDPA_ATTR_DEV_MGMTDEV_MAX_VQS, /* u32 */ + VDPA_ATTR_DEV_SUPPORTED_FEATURES, /* u64 */ /* new attributes must be added above here */ VDPA_ATTR_MAX, }; diff --git a/lib/Kconfig b/lib/Kconfig index 655b0e43f260..c20b68ad2bc3 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -122,6 +122,8 @@ config INDIRECT_IOMEM_FALLBACK mmio accesses when the IO memory address is not a registered emulated region. +source "lib/crypto/Kconfig" + config CRC_CCITT tristate "CRC-CCITT functions" help diff --git a/lib/crypto/Kconfig b/lib/crypto/Kconfig index 8620f38e117c..e8e525650cf2 100644 --- a/lib/crypto/Kconfig +++ b/lib/crypto/Kconfig @@ -1,5 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 +menu "Crypto library routines" + config CRYPTO_LIB_AES tristate @@ -31,7 +33,7 @@ config CRYPTO_ARCH_HAVE_LIB_CHACHA config CRYPTO_LIB_CHACHA_GENERIC tristate - select CRYPTO_ALGAPI + select XOR_BLOCKS help This symbol can be depended upon by arch implementations of the ChaCha library interface that require the generic code as a @@ -40,7 +42,8 @@ config CRYPTO_LIB_CHACHA_GENERIC of CRYPTO_LIB_CHACHA. config CRYPTO_LIB_CHACHA - tristate + tristate "ChaCha library interface" + depends on CRYPTO depends on CRYPTO_ARCH_HAVE_LIB_CHACHA || !CRYPTO_ARCH_HAVE_LIB_CHACHA select CRYPTO_LIB_CHACHA_GENERIC if CRYPTO_ARCH_HAVE_LIB_CHACHA=n help @@ -65,7 +68,7 @@ config CRYPTO_LIB_CURVE25519_GENERIC of CRYPTO_LIB_CURVE25519. config CRYPTO_LIB_CURVE25519 - tristate + tristate "Curve25519 scalar multiplication library" depends on CRYPTO_ARCH_HAVE_LIB_CURVE25519 || !CRYPTO_ARCH_HAVE_LIB_CURVE25519 select CRYPTO_LIB_CURVE25519_GENERIC if CRYPTO_ARCH_HAVE_LIB_CURVE25519=n help @@ -100,7 +103,7 @@ config CRYPTO_LIB_POLY1305_GENERIC of CRYPTO_LIB_POLY1305. config CRYPTO_LIB_POLY1305 - tristate + tristate "Poly1305 library interface" depends on CRYPTO_ARCH_HAVE_LIB_POLY1305 || !CRYPTO_ARCH_HAVE_LIB_POLY1305 select CRYPTO_LIB_POLY1305_GENERIC if CRYPTO_ARCH_HAVE_LIB_POLY1305=n help @@ -109,14 +112,18 @@ config CRYPTO_LIB_POLY1305 is available and enabled. config CRYPTO_LIB_CHACHA20POLY1305 - tristate + tristate "ChaCha20-Poly1305 AEAD support (8-byte nonce library version)" depends on CRYPTO_ARCH_HAVE_LIB_CHACHA || !CRYPTO_ARCH_HAVE_LIB_CHACHA depends on CRYPTO_ARCH_HAVE_LIB_POLY1305 || !CRYPTO_ARCH_HAVE_LIB_POLY1305 + depends on CRYPTO select CRYPTO_LIB_CHACHA select CRYPTO_LIB_POLY1305 + select CRYPTO_ALGAPI config CRYPTO_LIB_SHA256 tristate config CRYPTO_LIB_SM4 tristate + +endmenu diff --git a/lib/crypto/blake2s-selftest.c b/lib/crypto/blake2s-selftest.c index 5d9ea53be973..409e4b728770 100644 --- a/lib/crypto/blake2s-selftest.c +++ b/lib/crypto/blake2s-selftest.c @@ -15,7 +15,6 @@ * #include * * #include - * #include * * #define BLAKE2S_TESTVEC_COUNT 256 * @@ -58,16 +57,6 @@ * } * printf("};\n\n"); * - * printf("static const u8 blake2s_hmac_testvecs[][BLAKE2S_HASH_SIZE] __initconst = {\n"); - * - * HMAC(EVP_blake2s256(), key, sizeof(key), buf, sizeof(buf), hash, NULL); - * print_vec(hash, BLAKE2S_OUTBYTES); - * - * HMAC(EVP_blake2s256(), buf, sizeof(buf), key, sizeof(key), hash, NULL); - * print_vec(hash, BLAKE2S_OUTBYTES); - * - * printf("};\n"); - * * return 0; *} */ @@ -554,15 +543,6 @@ static const u8 blake2s_testvecs[][BLAKE2S_HASH_SIZE] __initconst = { 0xd6, 0x98, 0x6b, 0x07, 0x10, 0x65, 0x52, 0x65, }, }; -static const u8 blake2s_hmac_testvecs[][BLAKE2S_HASH_SIZE] __initconst = { - { 0xce, 0xe1, 0x57, 0x69, 0x82, 0xdc, 0xbf, 0x43, 0xad, 0x56, 0x4c, 0x70, - 0xed, 0x68, 0x16, 0x96, 0xcf, 0xa4, 0x73, 0xe8, 0xe8, 0xfc, 0x32, 0x79, - 0x08, 0x0a, 0x75, 0x82, 0xda, 0x3f, 0x05, 0x11, }, - { 0x77, 0x2f, 0x0c, 0x71, 0x41, 0xf4, 0x4b, 0x2b, 0xb3, 0xc6, 0xb6, 0xf9, - 0x60, 0xde, 0xe4, 0x52, 0x38, 0x66, 0xe8, 0xbf, 0x9b, 0x96, 0xc4, 0x9f, - 0x60, 0xd9, 0x24, 0x37, 0x99, 0xd6, 0xec, 0x31, }, -}; - bool __init blake2s_selftest(void) { u8 key[BLAKE2S_KEY_SIZE]; @@ -607,16 +587,5 @@ bool __init blake2s_selftest(void) } } - if (success) { - blake2s256_hmac(hash, buf, key, sizeof(buf), sizeof(key)); - success &= !memcmp(hash, blake2s_hmac_testvecs[0], BLAKE2S_HASH_SIZE); - - blake2s256_hmac(hash, key, buf, sizeof(key), sizeof(buf)); - success &= !memcmp(hash, blake2s_hmac_testvecs[1], BLAKE2S_HASH_SIZE); - - if (!success) - pr_err("blake2s256_hmac self-test: FAIL\n"); - } - return success; } diff --git a/lib/crypto/blake2s.c b/lib/crypto/blake2s.c index 244f2f5768f4..c71c09621c09 100644 --- a/lib/crypto/blake2s.c +++ b/lib/crypto/blake2s.c @@ -30,43 +30,6 @@ void blake2s_final(struct blake2s_state *state, u8 *out) } EXPORT_SYMBOL(blake2s_final); -void blake2s256_hmac(u8 *out, const u8 *in, const u8 *key, const size_t inlen, - const size_t keylen) -{ - struct blake2s_state state; - u8 x_key[BLAKE2S_BLOCK_SIZE] __aligned(__alignof__(u32)) = { 0 }; - u8 i_hash[BLAKE2S_HASH_SIZE] __aligned(__alignof__(u32)); - int i; - - if (keylen > BLAKE2S_BLOCK_SIZE) { - blake2s_init(&state, BLAKE2S_HASH_SIZE); - blake2s_update(&state, key, keylen); - blake2s_final(&state, x_key); - } else - memcpy(x_key, key, keylen); - - for (i = 0; i < BLAKE2S_BLOCK_SIZE; ++i) - x_key[i] ^= 0x36; - - blake2s_init(&state, BLAKE2S_HASH_SIZE); - blake2s_update(&state, x_key, BLAKE2S_BLOCK_SIZE); - blake2s_update(&state, in, inlen); - blake2s_final(&state, i_hash); - - for (i = 0; i < BLAKE2S_BLOCK_SIZE; ++i) - x_key[i] ^= 0x5c ^ 0x36; - - blake2s_init(&state, BLAKE2S_HASH_SIZE); - blake2s_update(&state, x_key, BLAKE2S_BLOCK_SIZE); - blake2s_update(&state, i_hash, BLAKE2S_HASH_SIZE); - blake2s_final(&state, i_hash); - - memcpy(out, i_hash, BLAKE2S_HASH_SIZE); - memzero_explicit(x_key, BLAKE2S_BLOCK_SIZE); - memzero_explicit(i_hash, BLAKE2S_HASH_SIZE); -} -EXPORT_SYMBOL(blake2s256_hmac); - static int __init blake2s_mod_init(void) { if (!IS_ENABLED(CONFIG_CRYPTO_MANAGER_DISABLE_TESTS) && diff --git a/lib/sha1.c b/lib/sha1.c index 9bd1935a1472..0494766fc574 100644 --- a/lib/sha1.c +++ b/lib/sha1.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include @@ -55,7 +56,8 @@ #define SHA_ROUND(t, input, fn, constant, A, B, C, D, E) do { \ __u32 TEMP = input(t); setW(t, TEMP); \ E += TEMP + rol32(A,5) + (fn) + (constant); \ - B = ror32(B, 2); } while (0) + B = ror32(B, 2); \ + TEMP = E; E = D; D = C; C = B; B = A; A = TEMP; } while (0) #define T_0_15(t, A, B, C, D, E) SHA_ROUND(t, SHA_SRC, (((C^D)&B)^D) , 0x5a827999, A, B, C, D, E ) #define T_16_19(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (((C^D)&B)^D) , 0x5a827999, A, B, C, D, E ) @@ -84,6 +86,7 @@ void sha1_transform(__u32 *digest, const char *data, __u32 *array) { __u32 A, B, C, D, E; + unsigned int i = 0; A = digest[0]; B = digest[1]; @@ -92,94 +95,24 @@ void sha1_transform(__u32 *digest, const char *data, __u32 *array) E = digest[4]; /* Round 1 - iterations 0-16 take their input from 'data' */ - T_0_15( 0, A, B, C, D, E); - T_0_15( 1, E, A, B, C, D); - T_0_15( 2, D, E, A, B, C); - T_0_15( 3, C, D, E, A, B); - T_0_15( 4, B, C, D, E, A); - T_0_15( 5, A, B, C, D, E); - T_0_15( 6, E, A, B, C, D); - T_0_15( 7, D, E, A, B, C); - T_0_15( 8, C, D, E, A, B); - T_0_15( 9, B, C, D, E, A); - T_0_15(10, A, B, C, D, E); - T_0_15(11, E, A, B, C, D); - T_0_15(12, D, E, A, B, C); - T_0_15(13, C, D, E, A, B); - T_0_15(14, B, C, D, E, A); - T_0_15(15, A, B, C, D, E); + for (; i < 16; ++i) + T_0_15(i, A, B, C, D, E); /* Round 1 - tail. Input from 512-bit mixing array */ - T_16_19(16, E, A, B, C, D); - T_16_19(17, D, E, A, B, C); - T_16_19(18, C, D, E, A, B); - T_16_19(19, B, C, D, E, A); + for (; i < 20; ++i) + T_16_19(i, A, B, C, D, E); /* Round 2 */ - T_20_39(20, A, B, C, D, E); - T_20_39(21, E, A, B, C, D); - T_20_39(22, D, E, A, B, C); - T_20_39(23, C, D, E, A, B); - T_20_39(24, B, C, D, E, A); - T_20_39(25, A, B, C, D, E); - T_20_39(26, E, A, B, C, D); - T_20_39(27, D, E, A, B, C); - T_20_39(28, C, D, E, A, B); - T_20_39(29, B, C, D, E, A); - T_20_39(30, A, B, C, D, E); - T_20_39(31, E, A, B, C, D); - T_20_39(32, D, E, A, B, C); - T_20_39(33, C, D, E, A, B); - T_20_39(34, B, C, D, E, A); - T_20_39(35, A, B, C, D, E); - T_20_39(36, E, A, B, C, D); - T_20_39(37, D, E, A, B, C); - T_20_39(38, C, D, E, A, B); - T_20_39(39, B, C, D, E, A); + for (; i < 40; ++i) + T_20_39(i, A, B, C, D, E); /* Round 3 */ - T_40_59(40, A, B, C, D, E); - T_40_59(41, E, A, B, C, D); - T_40_59(42, D, E, A, B, C); - T_40_59(43, C, D, E, A, B); - T_40_59(44, B, C, D, E, A); - T_40_59(45, A, B, C, D, E); - T_40_59(46, E, A, B, C, D); - T_40_59(47, D, E, A, B, C); - T_40_59(48, C, D, E, A, B); - T_40_59(49, B, C, D, E, A); - T_40_59(50, A, B, C, D, E); - T_40_59(51, E, A, B, C, D); - T_40_59(52, D, E, A, B, C); - T_40_59(53, C, D, E, A, B); - T_40_59(54, B, C, D, E, A); - T_40_59(55, A, B, C, D, E); - T_40_59(56, E, A, B, C, D); - T_40_59(57, D, E, A, B, C); - T_40_59(58, C, D, E, A, B); - T_40_59(59, B, C, D, E, A); + for (; i < 60; ++i) + T_40_59(i, A, B, C, D, E); /* Round 4 */ - T_60_79(60, A, B, C, D, E); - T_60_79(61, E, A, B, C, D); - T_60_79(62, D, E, A, B, C); - T_60_79(63, C, D, E, A, B); - T_60_79(64, B, C, D, E, A); - T_60_79(65, A, B, C, D, E); - T_60_79(66, E, A, B, C, D); - T_60_79(67, D, E, A, B, C); - T_60_79(68, C, D, E, A, B); - T_60_79(69, B, C, D, E, A); - T_60_79(70, A, B, C, D, E); - T_60_79(71, E, A, B, C, D); - T_60_79(72, D, E, A, B, C); - T_60_79(73, C, D, E, A, B); - T_60_79(74, B, C, D, E, A); - T_60_79(75, A, B, C, D, E); - T_60_79(76, E, A, B, C, D); - T_60_79(77, D, E, A, B, C); - T_60_79(78, C, D, E, A, B); - T_60_79(79, B, C, D, E, A); + for (; i < 80; ++i) + T_60_79(i, A, B, C, D, E); digest[0] += A; digest[1] += B; diff --git a/mm/slab.h b/mm/slab.h index 7edb7d23f141..c7f2abc2b154 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -67,14 +67,8 @@ struct slab { static_assert(offsetof(struct page, pg) == offsetof(struct slab, sl)) SLAB_MATCH(flags, __page_flags); SLAB_MATCH(compound_head, slab_list); /* Ensure bit 0 is clear */ -SLAB_MATCH(slab_list, slab_list); #ifndef CONFIG_SLOB SLAB_MATCH(rcu_head, rcu_head); -SLAB_MATCH(slab_cache, slab_cache); -#endif -#ifdef CONFIG_SLAB -SLAB_MATCH(s_mem, s_mem); -SLAB_MATCH(active, active); #endif SLAB_MATCH(_refcount, __page_refcount); #ifdef CONFIG_MEMCG diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index f7dc561ca516..b24a4fb0f0a2 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -721,7 +721,7 @@ static void p9_virtio_remove(struct virtio_device *vdev) mutex_unlock(&virtio_9p_lock); - vdev->config->reset(vdev); + virtio_reset_device(vdev); vdev->config->del_vqs(vdev); sysfs_remove_file(&(vdev->dev.kobj), &dev_attr_mount_tag.attr); diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 4f7c99dfd16c..fb3302fff627 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -665,7 +665,7 @@ static void virtio_vsock_remove(struct virtio_device *vdev) vsock_for_each_connected_socket(virtio_vsock_reset_sock); /* Stop all work handlers to make sure no one is accessing the device, - * so we can safely call vdev->config->reset(). + * so we can safely call virtio_reset_device(). */ mutex_lock(&vsock->rx_lock); vsock->rx_run = false; @@ -682,7 +682,7 @@ static void virtio_vsock_remove(struct virtio_device *vdev) /* Flush all device writes and interrupts, device will not use any * more buffers. */ - vdev->config->reset(vdev); + virtio_reset_device(vdev); mutex_lock(&vsock->rx_lock); while ((pkt = virtqueue_detach_unused_buf(vsock->vqs[VSOCK_VQ_RX]))) diff --git a/scripts/coccinelle/iterators/fen.cocci b/scripts/coccinelle/iterators/fen.cocci deleted file mode 100644 index b69f9665f4fb..000000000000 --- a/scripts/coccinelle/iterators/fen.cocci +++ /dev/null @@ -1,124 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/// These iterators only exit normally when the loop cursor is NULL, so there -/// is no point to call of_node_put on the final value. -/// -// Confidence: High -// Copyright: (C) 2010-2012 Nicolas Palix. -// Copyright: (C) 2010-2012 Julia Lawall, INRIA/LIP6. -// Copyright: (C) 2010-2012 Gilles Muller, INRIA/LiP6. -// URL: http://coccinelle.lip6.fr/ -// Comments: -// Options: --no-includes --include-headers - -virtual patch -virtual context -virtual org -virtual report - -@depends on patch@ -iterator name for_each_node_by_name; -expression np,E; -identifier l; -@@ - -for_each_node_by_name(np,...) { - ... when != break; - when != goto l; -} -... when != np = E -- of_node_put(np); - -@depends on patch@ -iterator name for_each_node_by_type; -expression np,E; -identifier l; -@@ - -for_each_node_by_type(np,...) { - ... when != break; - when != goto l; -} -... when != np = E -- of_node_put(np); - -@depends on patch@ -iterator name for_each_compatible_node; -expression np,E; -identifier l; -@@ - -for_each_compatible_node(np,...) { - ... when != break; - when != goto l; -} -... when != np = E -- of_node_put(np); - -@depends on patch@ -iterator name for_each_matching_node; -expression np,E; -identifier l; -@@ - -for_each_matching_node(np,...) { - ... when != break; - when != goto l; -} -... when != np = E -- of_node_put(np); - -// ---------------------------------------------------------------------- - -@r depends on !patch forall@ -//iterator name for_each_node_by_name; -//iterator name for_each_node_by_type; -//iterator name for_each_compatible_node; -//iterator name for_each_matching_node; -expression np,E; -identifier l; -position p1,p2; -@@ - -( -*for_each_node_by_name@p1(np,...) -{ - ... when != break; - when != goto l; -} -| -*for_each_node_by_type@p1(np,...) -{ - ... when != break; - when != goto l; -} -| -*for_each_compatible_node@p1(np,...) -{ - ... when != break; - when != goto l; -} -| -*for_each_matching_node@p1(np,...) -{ - ... when != break; - when != goto l; -} -) -... when != np = E -* of_node_put@p2(np); - -@script:python depends on org@ -p1 << r.p1; -p2 << r.p2; -@@ - -cocci.print_main("unneeded of_node_put",p2) -cocci.print_secs("iterator",p1) - -@script:python depends on report@ -p1 << r.p1; -p2 << r.p2; -@@ - -msg = "ERROR: of_node_put not needed after iterator on line %s" % (p1[0].line) -coccilib.report.print_report(p2[0], msg) diff --git a/scripts/coccinelle/misc/bugon.cocci b/scripts/coccinelle/misc/bugon.cocci deleted file mode 100644 index 8d595c358408..000000000000 --- a/scripts/coccinelle/misc/bugon.cocci +++ /dev/null @@ -1,63 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/// Use BUG_ON instead of a if condition followed by BUG. -/// -//# This makes an effort to find cases where BUG() follows an if -//# condition on an expression and replaces the if condition and BUG() -//# with a BUG_ON having the conditional expression of the if statement -//# as argument. -// -// Confidence: High -// Copyright: (C) 2014 Himangi Saraogi. -// Comments: -// Options: --no-includes --include-headers - -virtual patch -virtual context -virtual org -virtual report - -//---------------------------------------------------------- -// For context mode -//---------------------------------------------------------- - -@depends on context@ -expression e; -@@ - -*if (e) BUG(); - -//---------------------------------------------------------- -// For patch mode -//---------------------------------------------------------- - -@depends on patch@ -expression e; -@@ - --if (e) BUG(); -+BUG_ON(e); - -//---------------------------------------------------------- -// For org and report mode -//---------------------------------------------------------- - -@r depends on (org || report)@ -expression e; -position p; -@@ - - if (e) BUG@p (); - -@script:python depends on org@ -p << r.p; -@@ - -coccilib.org.print_todo(p[0], "WARNING use BUG_ON") - -@script:python depends on report@ -p << r.p; -@@ - -msg="WARNING: Use BUG_ON instead of if condition followed by BUG.\nPlease make sure the condition has no side effects (see conditional BUG_ON definition in include/asm-generic/bug.h)" -coccilib.report.print_report(p[0], msg) - diff --git a/sound/virtio/virtio_card.c b/sound/virtio/virtio_card.c index 150ab3e37013..e2847c040f75 100644 --- a/sound/virtio/virtio_card.c +++ b/sound/virtio/virtio_card.c @@ -350,7 +350,7 @@ static void virtsnd_remove(struct virtio_device *vdev) snd_card_free(snd->card); vdev->config->del_vqs(vdev); - vdev->config->reset(vdev); + virtio_reset_device(vdev); for (i = 0; snd->substreams && i < snd->nsubstreams; ++i) { struct virtio_pcm_substream *vss = &snd->substreams[i]; @@ -379,7 +379,7 @@ static int virtsnd_freeze(struct virtio_device *vdev) virtsnd_ctl_msg_cancel_all(snd); vdev->config->del_vqs(vdev); - vdev->config->reset(vdev); + virtio_reset_device(vdev); for (i = 0; i < snd->nsubstreams; ++i) cancel_work_sync(&snd->substreams[i].elapsed_period); diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index d5b5f2ab87a0..18de5f76f198 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -315,6 +315,7 @@ #define X86_FEATURE_AMD_SSBD (13*32+24) /* "" Speculative Store Bypass Disable */ #define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */ #define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */ +#define X86_FEATURE_CPPC (13*32+27) /* Collaborative Processor Performance Control */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ #define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 01e2650b9585..3faf0f97edb1 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -486,6 +486,23 @@ #define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f +/* AMD Collaborative Processor Performance Control MSRs */ +#define MSR_AMD_CPPC_CAP1 0xc00102b0 +#define MSR_AMD_CPPC_ENABLE 0xc00102b1 +#define MSR_AMD_CPPC_CAP2 0xc00102b2 +#define MSR_AMD_CPPC_REQ 0xc00102b3 +#define MSR_AMD_CPPC_STATUS 0xc00102b4 + +#define AMD_CPPC_LOWEST_PERF(x) (((x) >> 0) & 0xff) +#define AMD_CPPC_LOWNONLIN_PERF(x) (((x) >> 8) & 0xff) +#define AMD_CPPC_NOMINAL_PERF(x) (((x) >> 16) & 0xff) +#define AMD_CPPC_HIGHEST_PERF(x) (((x) >> 24) & 0xff) + +#define AMD_CPPC_MAX_PERF(x) (((x) & 0xff) << 0) +#define AMD_CPPC_MIN_PERF(x) (((x) & 0xff) << 8) +#define AMD_CPPC_DES_PERF(x) (((x) & 0xff) << 16) +#define AMD_CPPC_ENERGY_PERF_PREF(x) (((x) & 0xff) << 24) + /* Fam 17h MSRs */ #define MSR_F17H_IRPERF 0xc00000e9 diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index 1cc9da6e29c7..59cf2343f3d9 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -39,7 +39,7 @@ SYM_FUNC_START_WEAK(memcpy) rep movsq movl %edx, %ecx rep movsb - ret + RET SYM_FUNC_END(memcpy) SYM_FUNC_END_ALIAS(__memcpy) EXPORT_SYMBOL(memcpy) @@ -53,7 +53,7 @@ SYM_FUNC_START_LOCAL(memcpy_erms) movq %rdi, %rax movq %rdx, %rcx rep movsb - ret + RET SYM_FUNC_END(memcpy_erms) SYM_FUNC_START_LOCAL(memcpy_orig) @@ -137,7 +137,7 @@ SYM_FUNC_START_LOCAL(memcpy_orig) movq %r9, 1*8(%rdi) movq %r10, -2*8(%rdi, %rdx) movq %r11, -1*8(%rdi, %rdx) - retq + RET .p2align 4 .Lless_16bytes: cmpl $8, %edx @@ -149,7 +149,7 @@ SYM_FUNC_START_LOCAL(memcpy_orig) movq -1*8(%rsi, %rdx), %r9 movq %r8, 0*8(%rdi) movq %r9, -1*8(%rdi, %rdx) - retq + RET .p2align 4 .Lless_8bytes: cmpl $4, %edx @@ -162,7 +162,7 @@ SYM_FUNC_START_LOCAL(memcpy_orig) movl -4(%rsi, %rdx), %r8d movl %ecx, (%rdi) movl %r8d, -4(%rdi, %rdx) - retq + RET .p2align 4 .Lless_3bytes: subl $1, %edx @@ -180,7 +180,7 @@ SYM_FUNC_START_LOCAL(memcpy_orig) movb %cl, (%rdi) .Lend: - retq + RET SYM_FUNC_END(memcpy_orig) .popsection diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S index 9827ae267f96..d624f2bc42f1 100644 --- a/tools/arch/x86/lib/memset_64.S +++ b/tools/arch/x86/lib/memset_64.S @@ -40,7 +40,7 @@ SYM_FUNC_START(__memset) movl %edx,%ecx rep stosb movq %r9,%rax - ret + RET SYM_FUNC_END(__memset) SYM_FUNC_END_ALIAS(memset) EXPORT_SYMBOL(memset) @@ -63,7 +63,7 @@ SYM_FUNC_START_LOCAL(memset_erms) movq %rdx,%rcx rep stosb movq %r9,%rax - ret + RET SYM_FUNC_END(memset_erms) SYM_FUNC_START_LOCAL(memset_orig) @@ -125,7 +125,7 @@ SYM_FUNC_START_LOCAL(memset_orig) .Lende: movq %r10,%rax - ret + RET .Lbad_alignment: cmpq $7,%rdx diff --git a/tools/build/Build.include b/tools/build/Build.include index 2cf3b1bde86e..c2a95ab47379 100644 --- a/tools/build/Build.include +++ b/tools/build/Build.include @@ -99,7 +99,7 @@ cxx_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(CXXFLAGS) -D"BUILD_STR(s)=\#s" $(CXX ### ## HOSTCC C flags -host_c_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(KBUILD_HOSTCFLAGS) -D"BUILD_STR(s)=\#s" $(HOSTCFLAGS_$(basetarget).o) $(HOSTCFLAGS_$(obj)) +host_c_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(HOSTCFLAGS) -D"BUILD_STR(s)=\#s" $(HOSTCFLAGS_$(basetarget).o) $(HOSTCFLAGS_$(obj)) # output directory for tests below TMPOUT = .tmp_$$$$ diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index 3b810b53ba8b..642808520d92 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -1096,6 +1096,24 @@ extern "C" { #define DRM_IOCTL_SYNCOBJ_TRANSFER DRM_IOWR(0xCC, struct drm_syncobj_transfer) #define DRM_IOCTL_SYNCOBJ_TIMELINE_SIGNAL DRM_IOWR(0xCD, struct drm_syncobj_timeline_array) +/** + * DRM_IOCTL_MODE_GETFB2 - Get framebuffer metadata. + * + * This queries metadata about a framebuffer. User-space fills + * &drm_mode_fb_cmd2.fb_id as the input, and the kernels fills the rest of the + * struct as the output. + * + * If the client is DRM master or has &CAP_SYS_ADMIN, &drm_mode_fb_cmd2.handles + * will be filled with GEM buffer handles. Planes are valid until one has a + * zero handle -- this can be used to compute the number of planes. + * + * Otherwise, &drm_mode_fb_cmd2.handles will be zeroed and planes are valid + * until one has a zero &drm_mode_fb_cmd2.pitches. + * + * If the framebuffer has a format modifier, &DRM_MODE_FB_MODIFIERS will be set + * in &drm_mode_fb_cmd2.flags and &drm_mode_fb_cmd2.modifier will contain the + * modifier. Otherwise, user-space must ignore &drm_mode_fb_cmd2.modifier. + */ #define DRM_IOCTL_MODE_GETFB2 DRM_IOWR(0xCE, struct drm_mode_fb_cmd2) /* diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index bd8860eeb291..4cd39aaccbe7 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -1332,7 +1332,10 @@ union perf_mem_data_src { /* hop level */ #define PERF_MEM_HOPS_0 0x01 /* remote core, same node */ -/* 2-7 available */ +#define PERF_MEM_HOPS_1 0x02 /* remote node, same socket */ +#define PERF_MEM_HOPS_2 0x03 /* remote socket, same board */ +#define PERF_MEM_HOPS_3 0x04 /* remote board */ +/* 5-7 available */ #define PERF_MEM_HOPS_SHIFT 43 #define PERF_MEM_S(a, s) \ diff --git a/tools/lib/perf/Documentation/libperf.txt b/tools/lib/perf/Documentation/libperf.txt index 63ae5e0195ce..32c5051c24eb 100644 --- a/tools/lib/perf/Documentation/libperf.txt +++ b/tools/lib/perf/Documentation/libperf.txt @@ -48,6 +48,7 @@ SYNOPSIS int perf_cpu_map__nr(const struct perf_cpu_map *cpus); bool perf_cpu_map__empty(const struct perf_cpu_map *map); int perf_cpu_map__max(struct perf_cpu_map *map); + bool perf_cpu_map__has(const struct perf_cpu_map *map, int cpu); #define perf_cpu_map__for_each_cpu(cpu, idx, cpus) -- @@ -135,16 +136,16 @@ SYNOPSIS int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus, struct perf_thread_map *threads); void perf_evsel__close(struct perf_evsel *evsel); - void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu); + void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu_map_idx); int perf_evsel__mmap(struct perf_evsel *evsel, int pages); void perf_evsel__munmap(struct perf_evsel *evsel); - void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu, int thread); - int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, + void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu_map_idx, int thread); + int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int thread, struct perf_counts_values *count); int perf_evsel__enable(struct perf_evsel *evsel); - int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu); + int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx); int perf_evsel__disable(struct perf_evsel *evsel); - int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu); + int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu_map_idx); struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel); struct perf_thread_map *perf_evsel__threads(struct perf_evsel *evsel); struct perf_event_attr *perf_evsel__attr(struct perf_evsel *evsel); diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c index adaad3dddf6e..ee66760f1e63 100644 --- a/tools/lib/perf/cpumap.c +++ b/tools/lib/perf/cpumap.c @@ -10,15 +10,24 @@ #include #include -struct perf_cpu_map *perf_cpu_map__dummy_new(void) +static struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus) { - struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(int)); + struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(struct perf_cpu) * nr_cpus); if (cpus != NULL) { - cpus->nr = 1; - cpus->map[0] = -1; + cpus->nr = nr_cpus; refcount_set(&cpus->refcnt, 1); + } + return cpus; +} + +struct perf_cpu_map *perf_cpu_map__dummy_new(void) +{ + struct perf_cpu_map *cpus = perf_cpu_map__alloc(1); + + if (cpus) + cpus->map[0].cpu = -1; return cpus; } @@ -54,15 +63,12 @@ static struct perf_cpu_map *cpu_map__default_new(void) if (nr_cpus < 0) return NULL; - cpus = malloc(sizeof(*cpus) + nr_cpus * sizeof(int)); + cpus = perf_cpu_map__alloc(nr_cpus); if (cpus != NULL) { int i; for (i = 0; i < nr_cpus; ++i) - cpus->map[i] = i; - - cpus->nr = nr_cpus; - refcount_set(&cpus->refcnt, 1); + cpus->map[i].cpu = i; } return cpus; @@ -73,31 +79,32 @@ struct perf_cpu_map *perf_cpu_map__default_new(void) return cpu_map__default_new(); } -static int cmp_int(const void *a, const void *b) + +static int cmp_cpu(const void *a, const void *b) { - return *(const int *)a - *(const int*)b; + const struct perf_cpu *cpu_a = a, *cpu_b = b; + + return cpu_a->cpu - cpu_b->cpu; } -static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, int *tmp_cpus) +static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, const struct perf_cpu *tmp_cpus) { - size_t payload_size = nr_cpus * sizeof(int); - struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + payload_size); + size_t payload_size = nr_cpus * sizeof(struct perf_cpu); + struct perf_cpu_map *cpus = perf_cpu_map__alloc(nr_cpus); int i, j; if (cpus != NULL) { memcpy(cpus->map, tmp_cpus, payload_size); - qsort(cpus->map, nr_cpus, sizeof(int), cmp_int); + qsort(cpus->map, nr_cpus, sizeof(struct perf_cpu), cmp_cpu); /* Remove dups */ j = 0; for (i = 0; i < nr_cpus; i++) { - if (i == 0 || cpus->map[i] != cpus->map[i - 1]) - cpus->map[j++] = cpus->map[i]; + if (i == 0 || cpus->map[i].cpu != cpus->map[i - 1].cpu) + cpus->map[j++].cpu = cpus->map[i].cpu; } cpus->nr = j; assert(j <= nr_cpus); - refcount_set(&cpus->refcnt, 1); } - return cpus; } @@ -105,7 +112,7 @@ struct perf_cpu_map *perf_cpu_map__read(FILE *file) { struct perf_cpu_map *cpus = NULL; int nr_cpus = 0; - int *tmp_cpus = NULL, *tmp; + struct perf_cpu *tmp_cpus = NULL, *tmp; int max_entries = 0; int n, cpu, prev; char sep; @@ -124,24 +131,24 @@ struct perf_cpu_map *perf_cpu_map__read(FILE *file) if (new_max >= max_entries) { max_entries = new_max + MAX_NR_CPUS / 2; - tmp = realloc(tmp_cpus, max_entries * sizeof(int)); + tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu)); if (tmp == NULL) goto out_free_tmp; tmp_cpus = tmp; } while (++prev < cpu) - tmp_cpus[nr_cpus++] = prev; + tmp_cpus[nr_cpus++].cpu = prev; } if (nr_cpus == max_entries) { max_entries += MAX_NR_CPUS; - tmp = realloc(tmp_cpus, max_entries * sizeof(int)); + tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu)); if (tmp == NULL) goto out_free_tmp; tmp_cpus = tmp; } - tmp_cpus[nr_cpus++] = cpu; + tmp_cpus[nr_cpus++].cpu = cpu; if (n == 2 && sep == '-') prev = cpu; else @@ -179,7 +186,7 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list) unsigned long start_cpu, end_cpu = 0; char *p = NULL; int i, nr_cpus = 0; - int *tmp_cpus = NULL, *tmp; + struct perf_cpu *tmp_cpus = NULL, *tmp; int max_entries = 0; if (!cpu_list) @@ -220,17 +227,17 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list) for (; start_cpu <= end_cpu; start_cpu++) { /* check for duplicates */ for (i = 0; i < nr_cpus; i++) - if (tmp_cpus[i] == (int)start_cpu) + if (tmp_cpus[i].cpu == (int)start_cpu) goto invalid; if (nr_cpus == max_entries) { max_entries += MAX_NR_CPUS; - tmp = realloc(tmp_cpus, max_entries * sizeof(int)); + tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu)); if (tmp == NULL) goto invalid; tmp_cpus = tmp; } - tmp_cpus[nr_cpus++] = (int)start_cpu; + tmp_cpus[nr_cpus++].cpu = (int)start_cpu; } if (*p) ++p; @@ -250,12 +257,16 @@ out: return cpus; } -int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx) +struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx) { + struct perf_cpu result = { + .cpu = -1 + }; + if (cpus && idx < cpus->nr) return cpus->map[idx]; - return -1; + return result; } int perf_cpu_map__nr(const struct perf_cpu_map *cpus) @@ -265,21 +276,26 @@ int perf_cpu_map__nr(const struct perf_cpu_map *cpus) bool perf_cpu_map__empty(const struct perf_cpu_map *map) { - return map ? map->map[0] == -1 : true; + return map ? map->map[0].cpu == -1 : true; } -int perf_cpu_map__idx(struct perf_cpu_map *cpus, int cpu) +int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu) { - int low = 0, high = cpus->nr; + int low, high; + if (!cpus) + return -1; + + low = 0; + high = cpus->nr; while (low < high) { - int idx = (low + high) / 2, - cpu_at_idx = cpus->map[idx]; + int idx = (low + high) / 2; + struct perf_cpu cpu_at_idx = cpus->map[idx]; - if (cpu_at_idx == cpu) + if (cpu_at_idx.cpu == cpu.cpu) return idx; - if (cpu_at_idx > cpu) + if (cpu_at_idx.cpu > cpu.cpu) high = idx; else low = idx + 1; @@ -288,10 +304,19 @@ int perf_cpu_map__idx(struct perf_cpu_map *cpus, int cpu) return -1; } -int perf_cpu_map__max(struct perf_cpu_map *map) +bool perf_cpu_map__has(const struct perf_cpu_map *cpus, struct perf_cpu cpu) { + return perf_cpu_map__idx(cpus, cpu) != -1; +} + +struct perf_cpu perf_cpu_map__max(struct perf_cpu_map *map) +{ + struct perf_cpu result = { + .cpu = -1 + }; + // cpu_map__trim_new() qsort()s it, cpu_map__default_new() sorts it as well. - return map->nr > 0 ? map->map[map->nr - 1] : -1; + return map->nr > 0 ? map->map[map->nr - 1] : result; } /* @@ -305,7 +330,7 @@ int perf_cpu_map__max(struct perf_cpu_map *map) struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig, struct perf_cpu_map *other) { - int *tmp_cpus; + struct perf_cpu *tmp_cpus; int tmp_len; int i, j, k; struct perf_cpu_map *merged; @@ -319,19 +344,19 @@ struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig, if (!other) return orig; if (orig->nr == other->nr && - !memcmp(orig->map, other->map, orig->nr * sizeof(int))) + !memcmp(orig->map, other->map, orig->nr * sizeof(struct perf_cpu))) return orig; tmp_len = orig->nr + other->nr; - tmp_cpus = malloc(tmp_len * sizeof(int)); + tmp_cpus = malloc(tmp_len * sizeof(struct perf_cpu)); if (!tmp_cpus) return NULL; /* Standard merge algorithm from wikipedia */ i = j = k = 0; while (i < orig->nr && j < other->nr) { - if (orig->map[i] <= other->map[j]) { - if (orig->map[i] == other->map[j]) + if (orig->map[i].cpu <= other->map[j].cpu) { + if (orig->map[i].cpu == other->map[j].cpu) j++; tmp_cpus[k++] = orig->map[i++]; } else diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c index e37dfad31383..9a770bfdc804 100644 --- a/tools/lib/perf/evlist.c +++ b/tools/lib/perf/evlist.c @@ -407,7 +407,7 @@ perf_evlist__mmap_cb_get(struct perf_evlist *evlist, bool overwrite, int idx) static int perf_evlist__mmap_cb_mmap(struct perf_mmap *map, struct perf_mmap_param *mp, - int output, int cpu) + int output, struct perf_cpu cpu) { return perf_mmap__mmap(map, mp, output, cpu); } @@ -426,7 +426,7 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, int idx, struct perf_mmap_param *mp, int cpu_idx, int thread, int *_output, int *_output_overwrite) { - int evlist_cpu = perf_cpu_map__cpu(evlist->cpus, cpu_idx); + struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->cpus, cpu_idx); struct perf_evsel *evsel; int revent; @@ -643,14 +643,14 @@ perf_evlist__next_mmap(struct perf_evlist *evlist, struct perf_mmap *map, return overwrite ? evlist->mmap_ovw_first : evlist->mmap_first; } -void __perf_evlist__set_leader(struct list_head *list) +void __perf_evlist__set_leader(struct list_head *list, struct perf_evsel *leader) { - struct perf_evsel *evsel, *leader; + struct perf_evsel *first, *last, *evsel; - leader = list_entry(list->next, struct perf_evsel, node); - evsel = list_entry(list->prev, struct perf_evsel, node); + first = list_first_entry(list, struct perf_evsel, node); + last = list_last_entry(list, struct perf_evsel, node); - leader->nr_members = evsel->idx - leader->idx + 1; + leader->nr_members = last->idx - first->idx + 1; __perf_evlist__for_each_entry(list, evsel) evsel->leader = leader; @@ -659,7 +659,10 @@ void __perf_evlist__set_leader(struct list_head *list) void perf_evlist__set_leader(struct perf_evlist *evlist) { if (evlist->nr_entries) { + struct perf_evsel *first = list_entry(evlist->entries.next, + struct perf_evsel, node); + evlist->nr_groups = evlist->nr_entries > 1 ? 1 : 0; - __perf_evlist__set_leader(&evlist->entries); + __perf_evlist__set_leader(&evlist->entries, first); } } diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c index 8441e3e1aaac..7ea86a44eae5 100644 --- a/tools/lib/perf/evsel.c +++ b/tools/lib/perf/evsel.c @@ -43,18 +43,22 @@ void perf_evsel__delete(struct perf_evsel *evsel) free(evsel); } -#define FD(e, x, y) ((int *) xyarray__entry(e->fd, x, y)) -#define MMAP(e, x, y) (e->mmap ? ((struct perf_mmap *) xyarray__entry(e->mmap, x, y)) : NULL) +#define FD(_evsel, _cpu_map_idx, _thread) \ + ((int *)xyarray__entry(_evsel->fd, _cpu_map_idx, _thread)) +#define MMAP(_evsel, _cpu_map_idx, _thread) \ + (_evsel->mmap ? ((struct perf_mmap *) xyarray__entry(_evsel->mmap, _cpu_map_idx, _thread)) \ + : NULL) int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) { evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int)); if (evsel->fd) { - int cpu, thread; - for (cpu = 0; cpu < ncpus; cpu++) { + int idx, thread; + + for (idx = 0; idx < ncpus; idx++) { for (thread = 0; thread < nthreads; thread++) { - int *fd = FD(evsel, cpu, thread); + int *fd = FD(evsel, idx, thread); if (fd) *fd = -1; @@ -74,13 +78,13 @@ static int perf_evsel__alloc_mmap(struct perf_evsel *evsel, int ncpus, int nthre static int sys_perf_event_open(struct perf_event_attr *attr, - pid_t pid, int cpu, int group_fd, + pid_t pid, struct perf_cpu cpu, int group_fd, unsigned long flags) { - return syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags); + return syscall(__NR_perf_event_open, attr, pid, cpu.cpu, group_fd, flags); } -static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread, int *group_fd) +static int get_group_fd(struct perf_evsel *evsel, int cpu_map_idx, int thread, int *group_fd) { struct perf_evsel *leader = evsel->leader; int *fd; @@ -97,7 +101,7 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread, int *grou if (!leader->fd) return -ENOTCONN; - fd = FD(leader, cpu, thread); + fd = FD(leader, cpu_map_idx, thread); if (fd == NULL || *fd == -1) return -EBADF; @@ -109,7 +113,8 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread, int *grou int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus, struct perf_thread_map *threads) { - int cpu, thread, err = 0; + struct perf_cpu cpu; + int idx, thread, err = 0; if (cpus == NULL) { static struct perf_cpu_map *empty_cpu_map; @@ -139,21 +144,21 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus, perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0) return -ENOMEM; - for (cpu = 0; cpu < cpus->nr; cpu++) { + perf_cpu_map__for_each_cpu(cpu, idx, cpus) { for (thread = 0; thread < threads->nr; thread++) { int fd, group_fd, *evsel_fd; - evsel_fd = FD(evsel, cpu, thread); + evsel_fd = FD(evsel, idx, thread); if (evsel_fd == NULL) return -EINVAL; - err = get_group_fd(evsel, cpu, thread, &group_fd); + err = get_group_fd(evsel, idx, thread, &group_fd); if (err < 0) return err; fd = sys_perf_event_open(&evsel->attr, threads->map[thread].pid, - cpus->map[cpu], group_fd, 0); + cpu, group_fd, 0); if (fd < 0) return -errno; @@ -165,12 +170,12 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus, return err; } -static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu) +static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu_map_idx) { int thread; for (thread = 0; thread < xyarray__max_y(evsel->fd); ++thread) { - int *fd = FD(evsel, cpu, thread); + int *fd = FD(evsel, cpu_map_idx, thread); if (fd && *fd >= 0) { close(*fd); @@ -181,10 +186,8 @@ static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu) void perf_evsel__close_fd(struct perf_evsel *evsel) { - int cpu; - - for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) - perf_evsel__close_fd_cpu(evsel, cpu); + for (int idx = 0; idx < xyarray__max_x(evsel->fd); idx++) + perf_evsel__close_fd_cpu(evsel, idx); } void perf_evsel__free_fd(struct perf_evsel *evsel) @@ -202,29 +205,29 @@ void perf_evsel__close(struct perf_evsel *evsel) perf_evsel__free_fd(evsel); } -void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu) +void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu_map_idx) { if (evsel->fd == NULL) return; - perf_evsel__close_fd_cpu(evsel, cpu); + perf_evsel__close_fd_cpu(evsel, cpu_map_idx); } void perf_evsel__munmap(struct perf_evsel *evsel) { - int cpu, thread; + int idx, thread; if (evsel->fd == NULL || evsel->mmap == NULL) return; - for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) { + for (idx = 0; idx < xyarray__max_x(evsel->fd); idx++) { for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) { - int *fd = FD(evsel, cpu, thread); + int *fd = FD(evsel, idx, thread); if (fd == NULL || *fd < 0) continue; - perf_mmap__munmap(MMAP(evsel, cpu, thread)); + perf_mmap__munmap(MMAP(evsel, idx, thread)); } } @@ -234,7 +237,7 @@ void perf_evsel__munmap(struct perf_evsel *evsel) int perf_evsel__mmap(struct perf_evsel *evsel, int pages) { - int ret, cpu, thread; + int ret, idx, thread; struct perf_mmap_param mp = { .prot = PROT_READ | PROT_WRITE, .mask = (pages * page_size) - 1, @@ -246,15 +249,16 @@ int perf_evsel__mmap(struct perf_evsel *evsel, int pages) if (perf_evsel__alloc_mmap(evsel, xyarray__max_x(evsel->fd), xyarray__max_y(evsel->fd)) < 0) return -ENOMEM; - for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) { + for (idx = 0; idx < xyarray__max_x(evsel->fd); idx++) { for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) { - int *fd = FD(evsel, cpu, thread); + int *fd = FD(evsel, idx, thread); struct perf_mmap *map; + struct perf_cpu cpu = perf_cpu_map__cpu(evsel->cpus, idx); if (fd == NULL || *fd < 0) continue; - map = MMAP(evsel, cpu, thread); + map = MMAP(evsel, idx, thread); perf_mmap__init(map, NULL, false, NULL); ret = perf_mmap__mmap(map, &mp, *fd, cpu); @@ -268,14 +272,14 @@ int perf_evsel__mmap(struct perf_evsel *evsel, int pages) return 0; } -void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu, int thread) +void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu_map_idx, int thread) { - int *fd = FD(evsel, cpu, thread); + int *fd = FD(evsel, cpu_map_idx, thread); - if (fd == NULL || *fd < 0 || MMAP(evsel, cpu, thread) == NULL) + if (fd == NULL || *fd < 0 || MMAP(evsel, cpu_map_idx, thread) == NULL) return NULL; - return MMAP(evsel, cpu, thread)->base; + return MMAP(evsel, cpu_map_idx, thread)->base; } int perf_evsel__read_size(struct perf_evsel *evsel) @@ -303,19 +307,19 @@ int perf_evsel__read_size(struct perf_evsel *evsel) return size; } -int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, +int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int thread, struct perf_counts_values *count) { size_t size = perf_evsel__read_size(evsel); - int *fd = FD(evsel, cpu, thread); + int *fd = FD(evsel, cpu_map_idx, thread); memset(count, 0, sizeof(*count)); if (fd == NULL || *fd < 0) return -EINVAL; - if (MMAP(evsel, cpu, thread) && - !perf_mmap__read_self(MMAP(evsel, cpu, thread), count)) + if (MMAP(evsel, cpu_map_idx, thread) && + !perf_mmap__read_self(MMAP(evsel, cpu_map_idx, thread), count)) return 0; if (readn(*fd, count->values, size) <= 0) @@ -326,13 +330,13 @@ int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, static int perf_evsel__run_ioctl(struct perf_evsel *evsel, int ioc, void *arg, - int cpu) + int cpu_map_idx) { int thread; for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) { int err; - int *fd = FD(evsel, cpu, thread); + int *fd = FD(evsel, cpu_map_idx, thread); if (fd == NULL || *fd < 0) return -1; @@ -346,9 +350,9 @@ static int perf_evsel__run_ioctl(struct perf_evsel *evsel, return 0; } -int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu) +int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx) { - return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, cpu); + return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, cpu_map_idx); } int perf_evsel__enable(struct perf_evsel *evsel) @@ -361,9 +365,9 @@ int perf_evsel__enable(struct perf_evsel *evsel) return err; } -int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu) +int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu_map_idx) { - return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, NULL, cpu); + return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, NULL, cpu_map_idx); } int perf_evsel__disable(struct perf_evsel *evsel) @@ -431,3 +435,22 @@ void perf_evsel__free_id(struct perf_evsel *evsel) zfree(&evsel->id); evsel->ids = 0; } + +void perf_counts_values__scale(struct perf_counts_values *count, + bool scale, __s8 *pscaled) +{ + s8 scaled = 0; + + if (scale) { + if (count->run == 0) { + scaled = -1; + count->val = 0; + } else if (count->run < count->ena) { + scaled = 1; + count->val = (u64)((double)count->val * count->ena / count->run); + } + } + + if (pscaled) + *pscaled = scaled; +} diff --git a/tools/lib/perf/include/internal/cpumap.h b/tools/lib/perf/include/internal/cpumap.h index 840d4032587b..581f9ffb4237 100644 --- a/tools/lib/perf/include/internal/cpumap.h +++ b/tools/lib/perf/include/internal/cpumap.h @@ -4,16 +4,30 @@ #include +/** A wrapper around a CPU to avoid confusion with the perf_cpu_map's map's indices. */ +struct perf_cpu { + int cpu; +}; + +/** + * A sized, reference counted, sorted array of integers representing CPU + * numbers. This is commonly used to capture which CPUs a PMU is associated + * with. The indices into the cpumap are frequently used as they avoid having + * gaps if CPU numbers were used. For events associated with a pid, rather than + * a CPU, a single dummy map with an entry of -1 is used. + */ struct perf_cpu_map { refcount_t refcnt; + /** Length of the map array. */ int nr; - int map[]; + /** The CPU values. */ + struct perf_cpu map[]; }; #ifndef MAX_NR_CPUS #define MAX_NR_CPUS 2048 #endif -int perf_cpu_map__idx(struct perf_cpu_map *cpus, int cpu); +int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu); #endif /* __LIBPERF_INTERNAL_CPUMAP_H */ diff --git a/tools/lib/perf/include/internal/evlist.h b/tools/lib/perf/include/internal/evlist.h index f366dbad6a88..4cefade540bd 100644 --- a/tools/lib/perf/include/internal/evlist.h +++ b/tools/lib/perf/include/internal/evlist.h @@ -4,6 +4,7 @@ #include #include +#include #include #define PERF_EVLIST__HLIST_BITS 8 @@ -36,7 +37,7 @@ typedef void typedef struct perf_mmap* (*perf_evlist_mmap__cb_get_t)(struct perf_evlist*, bool, int); typedef int -(*perf_evlist_mmap__cb_mmap_t)(struct perf_mmap*, struct perf_mmap_param*, int, int); +(*perf_evlist_mmap__cb_mmap_t)(struct perf_mmap*, struct perf_mmap_param*, int, struct perf_cpu); struct perf_evlist_mmap_ops { perf_evlist_mmap__cb_idx_t idx; @@ -127,5 +128,5 @@ int perf_evlist__id_add_fd(struct perf_evlist *evlist, void perf_evlist__reset_id_hash(struct perf_evlist *evlist); -void __perf_evlist__set_leader(struct list_head *list); +void __perf_evlist__set_leader(struct list_head *list, struct perf_evsel *leader); #endif /* __LIBPERF_INTERNAL_EVLIST_H */ diff --git a/tools/lib/perf/include/internal/evsel.h b/tools/lib/perf/include/internal/evsel.h index 1f3eacbad2e8..cfc9ebd7968e 100644 --- a/tools/lib/perf/include/internal/evsel.h +++ b/tools/lib/perf/include/internal/evsel.h @@ -6,8 +6,8 @@ #include #include #include +#include -struct perf_cpu_map; struct perf_thread_map; struct xyarray; @@ -27,7 +27,7 @@ struct perf_sample_id { * queue number. */ int idx; - int cpu; + struct perf_cpu cpu; pid_t tid; /* Holds total ID period value for PERF_SAMPLE_READ processing. */ diff --git a/tools/lib/perf/include/internal/mmap.h b/tools/lib/perf/include/internal/mmap.h index 5e3422f40ed5..5a062af8e9d8 100644 --- a/tools/lib/perf/include/internal/mmap.h +++ b/tools/lib/perf/include/internal/mmap.h @@ -6,6 +6,7 @@ #include #include #include +#include /* perf sample has 16 bits size limit */ #define PERF_SAMPLE_MAX_SIZE (1 << 16) @@ -24,7 +25,7 @@ struct perf_mmap { void *base; int mask; int fd; - int cpu; + struct perf_cpu cpu; refcount_t refcnt; u64 prev; u64 start; @@ -46,7 +47,7 @@ size_t perf_mmap__mmap_len(struct perf_mmap *map); void perf_mmap__init(struct perf_mmap *map, struct perf_mmap *prev, bool overwrite, libperf_unmap_cb_t unmap_cb); int perf_mmap__mmap(struct perf_mmap *map, struct perf_mmap_param *mp, - int fd, int cpu); + int fd, struct perf_cpu cpu); void perf_mmap__munmap(struct perf_mmap *map); void perf_mmap__get(struct perf_mmap *map); void perf_mmap__put(struct perf_mmap *map); diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h index 7c27766ea0bf..15b8faafd615 100644 --- a/tools/lib/perf/include/perf/cpumap.h +++ b/tools/lib/perf/include/perf/cpumap.h @@ -3,11 +3,10 @@ #define __LIBPERF_CPUMAP_H #include +#include #include #include -struct perf_cpu_map; - LIBPERF_API struct perf_cpu_map *perf_cpu_map__dummy_new(void); LIBPERF_API struct perf_cpu_map *perf_cpu_map__default_new(void); LIBPERF_API struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list); @@ -16,10 +15,11 @@ LIBPERF_API struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map); LIBPERF_API struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig, struct perf_cpu_map *other); LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map); -LIBPERF_API int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx); +LIBPERF_API struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx); LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus); LIBPERF_API bool perf_cpu_map__empty(const struct perf_cpu_map *map); -LIBPERF_API int perf_cpu_map__max(struct perf_cpu_map *map); +LIBPERF_API struct perf_cpu perf_cpu_map__max(struct perf_cpu_map *map); +LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); #define perf_cpu_map__for_each_cpu(cpu, idx, cpus) \ for ((idx) = 0, (cpu) = perf_cpu_map__cpu(cpus, idx); \ diff --git a/tools/lib/perf/include/perf/evsel.h b/tools/lib/perf/include/perf/evsel.h index 60eae25076d3..2a9516b42d15 100644 --- a/tools/lib/perf/include/perf/evsel.h +++ b/tools/lib/perf/include/perf/evsel.h @@ -4,6 +4,8 @@ #include #include +#include +#include struct perf_evsel; struct perf_event_attr; @@ -26,18 +28,20 @@ LIBPERF_API void perf_evsel__delete(struct perf_evsel *evsel); LIBPERF_API int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus, struct perf_thread_map *threads); LIBPERF_API void perf_evsel__close(struct perf_evsel *evsel); -LIBPERF_API void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu); +LIBPERF_API void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu_map_idx); LIBPERF_API int perf_evsel__mmap(struct perf_evsel *evsel, int pages); LIBPERF_API void perf_evsel__munmap(struct perf_evsel *evsel); -LIBPERF_API void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu, int thread); -LIBPERF_API int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, +LIBPERF_API void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu_map_idx, int thread); +LIBPERF_API int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int thread, struct perf_counts_values *count); LIBPERF_API int perf_evsel__enable(struct perf_evsel *evsel); -LIBPERF_API int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu); +LIBPERF_API int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx); LIBPERF_API int perf_evsel__disable(struct perf_evsel *evsel); -LIBPERF_API int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu); +LIBPERF_API int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu_map_idx); LIBPERF_API struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel); LIBPERF_API struct perf_thread_map *perf_evsel__threads(struct perf_evsel *evsel); LIBPERF_API struct perf_event_attr *perf_evsel__attr(struct perf_evsel *evsel); +LIBPERF_API void perf_counts_values__scale(struct perf_counts_values *count, + bool scale, __s8 *pscaled); #endif /* __LIBPERF_EVSEL_H */ diff --git a/tools/lib/perf/libperf.map b/tools/lib/perf/libperf.map index 71468606e8a7..93696affda2e 100644 --- a/tools/lib/perf/libperf.map +++ b/tools/lib/perf/libperf.map @@ -10,6 +10,7 @@ LIBPERF_0.0.1 { perf_cpu_map__cpu; perf_cpu_map__empty; perf_cpu_map__max; + perf_cpu_map__has; perf_thread_map__new_dummy; perf_thread_map__set_pid; perf_thread_map__comm; @@ -50,6 +51,7 @@ LIBPERF_0.0.1 { perf_mmap__read_init; perf_mmap__read_done; perf_mmap__read_event; + perf_counts_values__scale; local: *; }; diff --git a/tools/lib/perf/mmap.c b/tools/lib/perf/mmap.c index c89dfa5f67b3..f7ee07cb5818 100644 --- a/tools/lib/perf/mmap.c +++ b/tools/lib/perf/mmap.c @@ -32,7 +32,7 @@ size_t perf_mmap__mmap_len(struct perf_mmap *map) } int perf_mmap__mmap(struct perf_mmap *map, struct perf_mmap_param *mp, - int fd, int cpu) + int fd, struct perf_cpu cpu) { map->prev = 0; map->mask = mp->mask; @@ -353,8 +353,6 @@ int perf_mmap__read_self(struct perf_mmap *map, struct perf_counts_values *count count->ena += delta; if (idx) count->run += delta; - - cnt = mul_u64_u64_div64(cnt, count->ena, count->run); } count->val = cnt; diff --git a/tools/lib/perf/tests/test-evlist.c b/tools/lib/perf/tests/test-evlist.c index ce91a582f0e4..b3479dfa9a1c 100644 --- a/tools/lib/perf/tests/test-evlist.c +++ b/tools/lib/perf/tests/test-evlist.c @@ -21,6 +21,9 @@ #include "tests.h" #include +#define EVENT_NUM 15 +#define WAIT_COUNT 100000000UL + static int libperf_print(enum libperf_print_level level, const char *fmt, va_list ap) { @@ -331,7 +334,8 @@ static int test_mmap_cpus(void) }; cpu_set_t saved_mask; char path[PATH_MAX]; - int id, err, cpu, tmp; + int id, err, tmp; + struct perf_cpu cpu; union perf_event *event; int count = 0; @@ -374,7 +378,7 @@ static int test_mmap_cpus(void) cpu_set_t mask; CPU_ZERO(&mask); - CPU_SET(cpu, &mask); + CPU_SET(cpu.cpu, &mask); err = sched_setaffinity(0, sizeof(mask), &mask); __T("sched_setaffinity failed", err == 0); @@ -413,6 +417,159 @@ static int test_mmap_cpus(void) return 0; } +static double display_error(long long average, + long long high, + long long low, + long long expected) +{ + double error; + + error = (((double)average - expected) / expected) * 100.0; + + __T_VERBOSE(" Expected: %lld\n", expected); + __T_VERBOSE(" High: %lld Low: %lld Average: %lld\n", + high, low, average); + + __T_VERBOSE(" Average Error = %.2f%%\n", error); + + return error; +} + +static int test_stat_multiplexing(void) +{ + struct perf_counts_values expected_counts = { .val = 0 }; + struct perf_counts_values counts[EVENT_NUM] = {{ .val = 0 },}; + struct perf_thread_map *threads; + struct perf_evlist *evlist; + struct perf_evsel *evsel; + struct perf_event_attr attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_INSTRUCTIONS, + .read_format = PERF_FORMAT_TOTAL_TIME_ENABLED | + PERF_FORMAT_TOTAL_TIME_RUNNING, + .disabled = 1, + }; + int err, i, nonzero = 0; + unsigned long count; + long long max = 0, min = 0, avg = 0; + double error = 0.0; + s8 scaled = 0; + + /* read for non-multiplexing event count */ + threads = perf_thread_map__new_dummy(); + __T("failed to create threads", threads); + + perf_thread_map__set_pid(threads, 0, 0); + + evsel = perf_evsel__new(&attr); + __T("failed to create evsel", evsel); + + err = perf_evsel__open(evsel, NULL, threads); + __T("failed to open evsel", err == 0); + + err = perf_evsel__enable(evsel); + __T("failed to enable evsel", err == 0); + + /* wait loop */ + count = WAIT_COUNT; + while (count--) + ; + + perf_evsel__read(evsel, 0, 0, &expected_counts); + __T("failed to read value for evsel", expected_counts.val != 0); + __T("failed to read non-multiplexing event count", + expected_counts.ena == expected_counts.run); + + err = perf_evsel__disable(evsel); + __T("failed to enable evsel", err == 0); + + perf_evsel__close(evsel); + perf_evsel__delete(evsel); + + perf_thread_map__put(threads); + + /* read for multiplexing event count */ + threads = perf_thread_map__new_dummy(); + __T("failed to create threads", threads); + + perf_thread_map__set_pid(threads, 0, 0); + + evlist = perf_evlist__new(); + __T("failed to create evlist", evlist); + + for (i = 0; i < EVENT_NUM; i++) { + evsel = perf_evsel__new(&attr); + __T("failed to create evsel", evsel); + + perf_evlist__add(evlist, evsel); + } + perf_evlist__set_maps(evlist, NULL, threads); + + err = perf_evlist__open(evlist); + __T("failed to open evsel", err == 0); + + perf_evlist__enable(evlist); + + /* wait loop */ + count = WAIT_COUNT; + while (count--) + ; + + i = 0; + perf_evlist__for_each_evsel(evlist, evsel) { + perf_evsel__read(evsel, 0, 0, &counts[i]); + __T("failed to read value for evsel", counts[i].val != 0); + i++; + } + + perf_evlist__disable(evlist); + + min = counts[0].val; + for (i = 0; i < EVENT_NUM; i++) { + __T_VERBOSE("Event %2d -- Raw count = %lu, run = %lu, enable = %lu\n", + i, counts[i].val, counts[i].run, counts[i].ena); + + perf_counts_values__scale(&counts[i], true, &scaled); + if (scaled == 1) { + __T_VERBOSE("\t Scaled count = %lu (%.2lf%%, %lu/%lu)\n", + counts[i].val, + (double)counts[i].run / (double)counts[i].ena * 100.0, + counts[i].run, counts[i].ena); + } else if (scaled == -1) { + __T_VERBOSE("\t Not Running\n"); + } else { + __T_VERBOSE("\t Not Scaling\n"); + } + + if (counts[i].val > max) + max = counts[i].val; + + if (counts[i].val < min) + min = counts[i].val; + + avg += counts[i].val; + + if (counts[i].val != 0) + nonzero++; + } + + if (nonzero != 0) + avg = avg / nonzero; + else + avg = 0; + + error = display_error(avg, max, min, expected_counts.val); + + __T("Error out of range!", ((error <= 1.0) && (error >= -1.0))); + + perf_evlist__close(evlist); + perf_evlist__delete(evlist); + + perf_thread_map__put(threads); + + return 0; +} + int test_evlist(int argc, char **argv) { __T_START; @@ -424,6 +581,7 @@ int test_evlist(int argc, char **argv) test_stat_thread_enable(); test_mmap_thread(); test_mmap_cpus(); + test_stat_multiplexing(); __T_END; return tests_failed == 0 ? 0 : -1; diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt index cd8ce6e8ec12..7e44b419d301 100644 --- a/tools/perf/Documentation/perf-buildid-cache.txt +++ b/tools/perf/Documentation/perf-buildid-cache.txt @@ -74,12 +74,15 @@ OPTIONS used when creating a uprobe for a process that resides in a different mount namespace from the perf(1) utility. ---debuginfod=URLs:: +--debuginfod[=URLs]:: Specify debuginfod URL to be used when retrieving perf.data binaries, it follows the same syntax as the DEBUGINFOD_URLS variable, like: buildid-cache.debuginfod=http://192.168.122.174:8002 + If the URLs is not specified, the value of DEBUGINFOD_URLS + system environment variable is used. + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-buildid-list[1] diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index 3bb75c1f25e8..0420e71698ee 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -587,6 +587,15 @@ record.*:: Use 'n' control blocks in asynchronous (Posix AIO) trace writing mode ('n' default: 1, max: 4). + record.debuginfod:: + Specify debuginfod URL to be used when cacheing perf.data binaries, + it follows the same syntax as the DEBUGINFOD_URLS variable, like: + + http://192.168.122.174:8002 + + If the URLs is 'system', the value of DEBUGINFOD_URLS system environment + variable is used. + diff.*:: diff.order:: This option sets the number of columns to sort the result. diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index 4dc8d0af19df..57384a97c04f 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -81,7 +81,11 @@ On AMD systems it is implemented using IBS (up to precise-level 2). The precise modifier works with event types 0x76 (cpu-cycles, CPU clocks not halted) and 0xC1 (micro-ops retired). Both events map to IBS execution sampling (IBS op) with the IBS Op Counter Control bit -(IbsOpCntCtl) set respectively (see AMD64 Architecture Programmer’s +(IbsOpCntCtl) set respectively (see the +Core Complex (CCX) -> Processor x86 Core -> Instruction Based Sampling (IBS) +section of the [AMD Processor Programming Reference (PPR)] relevant to the +family, model and stepping of the processor being used). + Manual Volume 2: System Programming, 13.3 Instruction-Based Sampling). Examples to use IBS: @@ -94,10 +98,12 @@ RAW HARDWARE EVENT DESCRIPTOR Even when an event is not available in a symbolic form within perf right now, it can be encoded in a per processor specific way. -For instance For x86 CPUs NNN represents the raw register encoding with the +For instance on x86 CPUs, N is a hexadecimal value that represents the raw register encoding with the layout of IA32_PERFEVTSELx MSRs (see [Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide] Figure 30-1 Layout -of IA32_PERFEVTSELx MSRs) or AMD's PerfEvtSeln (see [AMD64 Architecture Programmer’s Manual Volume 2: System Programming], Page 344, -Figure 13-7 Performance Event-Select Register (PerfEvtSeln)). +of IA32_PERFEVTSELx MSRs) or AMD's PERF_CTL MSRs (see the +Core Complex (CCX) -> Processor x86 Core -> MSR Registers section of the +[AMD Processor Programming Reference (PPR)] relevant to the family, model +and stepping of the processor being used). Note: Only the following bit fields can be set in x86 counter registers: event, umask, edge, inv, cmask. Esp. guest/host only and @@ -126,6 +132,38 @@ It's also possible to use pmu syntax: perf record -e cpu/r1a8/ ... perf record -e cpu/r0x1a8/ ... +Some processors, like those from AMD, support event codes and unit masks +larger than a byte. In such cases, the bits corresponding to the event +configuration parameters can be seen with: + + cat /sys/bus/event_source/devices//format/ + +Example: + +If the AMD docs for an EPYC 7713 processor describe an event as: + + Event Umask Event Mask + Num. Value Mnemonic Description + + 28FH 03H op_cache_hit_miss.op_cache_hit Counts Op Cache micro-tag + hit events. + +raw encoding of 0x0328F cannot be used since the upper nibble of the +EventSelect bits have to be specified via bits 32-35 as can be seen with: + + cat /sys/bus/event_source/devices/cpu/format/event + +raw encoding of 0x20000038F should be used instead: + + perf stat -e r20000038f -a sleep 1 + perf record -e r20000038f ... + +It's also possible to use pmu syntax: + + perf record -e r20000038f -a sleep 1 + perf record -e cpu/r20000038f/ ... + perf record -e cpu/r0x20000038f/ ... + You should refer to the processor specific documentation for getting these details. Some of them are referenced in the SEE ALSO section below. @@ -316,4 +354,4 @@ SEE ALSO linkperf:perf-stat[1], linkperf:perf-top[1], linkperf:perf-record[1], http://www.intel.com/sdm/[Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide], -http://support.amd.com/us/Processor_TechDocs/24593_APM_v2.pdf[AMD64 Architecture Programmer’s Manual Volume 2: System Programming] +https://bugzilla.kernel.org/show_bug.cgi?id=206537[AMD Processor Programming Reference (PPR)] diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 3cf7bac67239..9ccc75935bc5 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -30,8 +30,10 @@ OPTIONS - a symbolic event name (use 'perf list' to list all events) - - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a - hexadecimal event descriptor. + - a raw PMU event in the form of rN where N is a hexadecimal value + that represents the raw register encoding with the layout of the + event control registers as described by entries in + /sys/bus/event_sources/devices/cpu/format/*. - a symbolic or raw PMU event followed by an optional colon and a list of event modifiers, e.g., cpu-cycles:p. See the @@ -713,6 +715,15 @@ measurements: include::intel-hybrid.txt[] +--debuginfod[=URLs]:: + Specify debuginfod URL to be used when cacheing perf.data binaries, + it follows the same syntax as the DEBUGINFOD_URLS variable, like: + + http://192.168.122.174:8002 + + If the URLs is not specified, the value of DEBUGINFOD_URLS + system environment variable is used. + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-list[1], linkperf:perf-intel-pt[1] diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 7e6fb7cbc0f4..c06c341e72b9 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -36,8 +36,10 @@ report:: - a symbolic event name (use 'perf list' to list all events) - - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a - hexadecimal event descriptor. + - a raw PMU event in the form of rN where N is a hexadecimal value + that represents the raw register encoding with the layout of the + event control registers as described by entries in + /sys/bus/event_sources/devices/cpu/format/*. - a symbolic or raw PMU event followed by an optional colon and a list of event modifiers, e.g., cpu-cycles:p. See the @@ -493,6 +495,10 @@ This option can be enabled in perf config by setting the variable $ perf config stat.no-csv-summary=true +--cputype:: +Only enable events on applying cpu with this type for hybrid platform +(e.g. core or atom)" + EXAMPLES -------- diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index 9898a32b8d9c..cac3dfbee7d8 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -38,9 +38,10 @@ Default is to monitor all CPUS. -e :: --event=:: Select the PMU event. Selection can be a symbolic event name - (use 'perf list' to list all events) or a raw PMU - event (eventsel+umask) in the form of rNNN where NNN is a - hexadecimal event descriptor. + (use 'perf list' to list all events) or a raw PMU event in the form + of rN where N is a hexadecimal value that represents the raw register + encoding with the layout of the event control registers as described + by entries in /sys/bus/event_sources/devices/cpu/format/*. -E :: --entries=:: diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 3df74cf5651a..96ad944ca6a8 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -17,6 +17,7 @@ detected = $(shell echo "$(1)=y" >> $(OUTPUT).config-detected) detected_var = $(shell echo "$(1)=$($(1))" >> $(OUTPUT).config-detected) CFLAGS := $(EXTRA_CFLAGS) $(filter-out -Wnested-externs,$(EXTRA_WARNINGS)) +HOSTCFLAGS := $(filter-out -Wnested-externs,$(EXTRA_WARNINGS)) include $(srctree)/tools/scripts/Makefile.arch @@ -143,7 +144,10 @@ FEATURE_CHECK_LDFLAGS-libcrypto = -lcrypto ifdef CSINCLUDES LIBOPENCSD_CFLAGS := -I$(CSINCLUDES) endif -OPENCSDLIBS := -lopencsd_c_api -lopencsd -lstdc++ +OPENCSDLIBS := -lopencsd_c_api +ifeq ($(findstring -static,${LDFLAGS}),-static) + OPENCSDLIBS += -lopencsd -lstdc++ +endif ifdef CSLIBS LIBOPENCSD_LDFLAGS := -L$(CSLIBS) endif @@ -211,6 +215,7 @@ endif ifneq ($(WERROR),0) CORE_CFLAGS += -Werror CXXFLAGS += -Werror + HOSTCFLAGS += -Werror endif ifndef DEBUG @@ -290,6 +295,9 @@ CXXFLAGS += -ggdb3 CXXFLAGS += -funwind-tables CXXFLAGS += -Wno-strict-aliasing +HOSTCFLAGS += -Wall +HOSTCFLAGS += -Wextra + # Enforce a non-executable stack, as we may regress (again) in the future by # adding assembler files missing the .GNU-stack linker note. LDFLAGS += -Wl,-z,noexecstack diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 80522bcfafe0..ac861e42c8f7 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -226,7 +226,7 @@ else endif export srctree OUTPUT RM CC CXX LD AR CFLAGS CXXFLAGS V BISON FLEX AWK -export HOSTCC HOSTLD HOSTAR +export HOSTCC HOSTLD HOSTAR HOSTCFLAGS include $(srctree)/tools/build/Makefile.include @@ -1041,7 +1041,7 @@ SKEL_OUT := $(abspath $(OUTPUT)util/bpf_skel) SKEL_TMP_OUT := $(abspath $(SKEL_OUT)/.tmp) SKELETONS := $(SKEL_OUT)/bpf_prog_profiler.skel.h SKELETONS += $(SKEL_OUT)/bperf_leader.skel.h $(SKEL_OUT)/bperf_follower.skel.h -SKELETONS += $(SKEL_OUT)/bperf_cgroup.skel.h +SKELETONS += $(SKEL_OUT)/bperf_cgroup.skel.h $(SKEL_OUT)/func_latency.skel.h $(SKEL_TMP_OUT) $(LIBBPF_OUTPUT): $(Q)$(MKDIR) -p $@ diff --git a/tools/perf/arch/arm/include/perf_regs.h b/tools/perf/arch/arm/include/perf_regs.h index 4085419283d0..99a06550e25d 100644 --- a/tools/perf/arch/arm/include/perf_regs.h +++ b/tools/perf/arch/arm/include/perf_regs.h @@ -15,46 +15,4 @@ void perf_regs_load(u64 *regs); #define PERF_REG_IP PERF_REG_ARM_PC #define PERF_REG_SP PERF_REG_ARM_SP -static inline const char *__perf_reg_name(int id) -{ - switch (id) { - case PERF_REG_ARM_R0: - return "r0"; - case PERF_REG_ARM_R1: - return "r1"; - case PERF_REG_ARM_R2: - return "r2"; - case PERF_REG_ARM_R3: - return "r3"; - case PERF_REG_ARM_R4: - return "r4"; - case PERF_REG_ARM_R5: - return "r5"; - case PERF_REG_ARM_R6: - return "r6"; - case PERF_REG_ARM_R7: - return "r7"; - case PERF_REG_ARM_R8: - return "r8"; - case PERF_REG_ARM_R9: - return "r9"; - case PERF_REG_ARM_R10: - return "r10"; - case PERF_REG_ARM_FP: - return "fp"; - case PERF_REG_ARM_IP: - return "ip"; - case PERF_REG_ARM_SP: - return "sp"; - case PERF_REG_ARM_LR: - return "lr"; - case PERF_REG_ARM_PC: - return "pc"; - default: - return NULL; - } - - return NULL; -} - #endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index 293a23bf8be3..2e8b2c4365a0 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -203,9 +203,11 @@ static int cs_etm_set_option(struct auxtrace_record *itr, struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL); /* Set option of each CPU we have */ - for (i = 0; i < cpu__max_cpu(); i++) { - if (!cpu_map__has(event_cpus, i) || - !cpu_map__has(online_cpus, i)) + for (i = 0; i < cpu__max_cpu().cpu; i++) { + struct perf_cpu cpu = { .cpu = i, }; + + if (!perf_cpu_map__has(event_cpus, cpu) || + !perf_cpu_map__has(online_cpus, cpu)) continue; if (option & BIT(ETM_OPT_CTXTID)) { @@ -407,25 +409,6 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, } - /* Validate auxtrace_mmap_pages provided by user */ - if (opts->auxtrace_mmap_pages) { - unsigned int max_page = (KiB(128) / page_size); - size_t sz = opts->auxtrace_mmap_pages * (size_t)page_size; - - if (!privileged && - opts->auxtrace_mmap_pages > max_page) { - opts->auxtrace_mmap_pages = max_page; - pr_err("auxtrace too big, truncating to %d\n", - max_page); - } - - if (!is_power_of_2(sz)) { - pr_err("Invalid mmap size for %s: must be a power of 2\n", - CORESIGHT_ETM_PMU_NAME); - return -EINVAL; - } - } - if (opts->auxtrace_snapshot_mode) pr_debug2("%s snapshot size: %zu\n", CORESIGHT_ETM_PMU_NAME, opts->auxtrace_snapshot_size); @@ -541,9 +524,11 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused, /* cpu map is not empty, we have specific CPUs to work with */ if (!perf_cpu_map__empty(event_cpus)) { - for (i = 0; i < cpu__max_cpu(); i++) { - if (!cpu_map__has(event_cpus, i) || - !cpu_map__has(online_cpus, i)) + for (i = 0; i < cpu__max_cpu().cpu; i++) { + struct perf_cpu cpu = { .cpu = i, }; + + if (!perf_cpu_map__has(event_cpus, cpu) || + !perf_cpu_map__has(online_cpus, cpu)) continue; if (cs_etm_is_ete(itr, i)) @@ -555,8 +540,10 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused, } } else { /* get configuration for all CPUs in the system */ - for (i = 0; i < cpu__max_cpu(); i++) { - if (!cpu_map__has(online_cpus, i)) + for (i = 0; i < cpu__max_cpu().cpu; i++) { + struct perf_cpu cpu = { .cpu = i, }; + + if (!perf_cpu_map__has(online_cpus, cpu)) continue; if (cs_etm_is_ete(itr, i)) @@ -741,8 +728,10 @@ static int cs_etm_info_fill(struct auxtrace_record *itr, } else { /* Make sure all specified CPUs are online */ for (i = 0; i < perf_cpu_map__nr(event_cpus); i++) { - if (cpu_map__has(event_cpus, i) && - !cpu_map__has(online_cpus, i)) + struct perf_cpu cpu = { .cpu = i, }; + + if (perf_cpu_map__has(event_cpus, cpu) && + !perf_cpu_map__has(online_cpus, cpu)) return -EINVAL; } @@ -762,9 +751,12 @@ static int cs_etm_info_fill(struct auxtrace_record *itr, offset = CS_ETM_SNAPSHOT + 1; - for (i = 0; i < cpu__max_cpu() && offset < priv_size; i++) - if (cpu_map__has(cpu_map, i)) + for (i = 0; i < cpu__max_cpu().cpu && offset < priv_size; i++) { + struct perf_cpu cpu = { .cpu = i, }; + + if (perf_cpu_map__has(cpu_map, cpu)) cs_etm_get_metadata(i, &offset, itr, info); + } perf_cpu_map__put(online_cpus); diff --git a/tools/perf/arch/arm64/include/perf_regs.h b/tools/perf/arch/arm64/include/perf_regs.h index fa3e07459f76..35a3cc775b39 100644 --- a/tools/perf/arch/arm64/include/perf_regs.h +++ b/tools/perf/arch/arm64/include/perf_regs.h @@ -4,7 +4,9 @@ #include #include +#define perf_event_arm_regs perf_event_arm64_regs #include +#undef perf_event_arm_regs void perf_regs_load(u64 *regs); @@ -15,80 +17,4 @@ void perf_regs_load(u64 *regs); #define PERF_REG_IP PERF_REG_ARM64_PC #define PERF_REG_SP PERF_REG_ARM64_SP -static inline const char *__perf_reg_name(int id) -{ - switch (id) { - case PERF_REG_ARM64_X0: - return "x0"; - case PERF_REG_ARM64_X1: - return "x1"; - case PERF_REG_ARM64_X2: - return "x2"; - case PERF_REG_ARM64_X3: - return "x3"; - case PERF_REG_ARM64_X4: - return "x4"; - case PERF_REG_ARM64_X5: - return "x5"; - case PERF_REG_ARM64_X6: - return "x6"; - case PERF_REG_ARM64_X7: - return "x7"; - case PERF_REG_ARM64_X8: - return "x8"; - case PERF_REG_ARM64_X9: - return "x9"; - case PERF_REG_ARM64_X10: - return "x10"; - case PERF_REG_ARM64_X11: - return "x11"; - case PERF_REG_ARM64_X12: - return "x12"; - case PERF_REG_ARM64_X13: - return "x13"; - case PERF_REG_ARM64_X14: - return "x14"; - case PERF_REG_ARM64_X15: - return "x15"; - case PERF_REG_ARM64_X16: - return "x16"; - case PERF_REG_ARM64_X17: - return "x17"; - case PERF_REG_ARM64_X18: - return "x18"; - case PERF_REG_ARM64_X19: - return "x19"; - case PERF_REG_ARM64_X20: - return "x20"; - case PERF_REG_ARM64_X21: - return "x21"; - case PERF_REG_ARM64_X22: - return "x22"; - case PERF_REG_ARM64_X23: - return "x23"; - case PERF_REG_ARM64_X24: - return "x24"; - case PERF_REG_ARM64_X25: - return "x25"; - case PERF_REG_ARM64_X26: - return "x26"; - case PERF_REG_ARM64_X27: - return "x27"; - case PERF_REG_ARM64_X28: - return "x28"; - case PERF_REG_ARM64_X29: - return "x29"; - case PERF_REG_ARM64_SP: - return "sp"; - case PERF_REG_ARM64_LR: - return "lr"; - case PERF_REG_ARM64_PC: - return "pc"; - default: - return NULL; - } - - return NULL; -} - #endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/arm64/util/machine.c b/tools/perf/arch/arm64/util/machine.c index 7e7714290a87..d2ce31e28cd7 100644 --- a/tools/perf/arch/arm64/util/machine.c +++ b/tools/perf/arch/arm64/util/machine.c @@ -5,6 +5,8 @@ #include #include "debug.h" #include "symbol.h" +#include "callchain.h" +#include "record.h" /* On arm64, kernel text segment starts at high memory address, * for example 0xffff 0000 8xxx xxxx. Modules start at a low memory @@ -26,3 +28,8 @@ void arch__symbols__fixup_end(struct symbol *p, struct symbol *c) p->end = c->start; pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end); } + +void arch__add_leaf_frame_record_opts(struct record_opts *opts) +{ + opts->sample_user_regs |= sample_reg_masks[PERF_REG_ARM64_LR].mask; +} diff --git a/tools/perf/arch/arm64/util/pmu.c b/tools/perf/arch/arm64/util/pmu.c index d3a18f9c85f6..79124bba713e 100644 --- a/tools/perf/arch/arm64/util/pmu.c +++ b/tools/perf/arch/arm64/util/pmu.c @@ -15,7 +15,7 @@ const struct pmu_events_map *pmu_events_map__find(void) * The cpumap should cover all CPUs. Otherwise, some CPUs may * not support some events or have different event IDs. */ - if (pmu->cpus->nr != cpu__max_cpu()) + if (pmu->cpus->nr != cpu__max_cpu().cpu) return NULL; return perf_pmu__find_map(pmu); diff --git a/tools/perf/arch/csky/include/perf_regs.h b/tools/perf/arch/csky/include/perf_regs.h index 25ac3bdcb9d1..1afcc0e916c2 100644 --- a/tools/perf/arch/csky/include/perf_regs.h +++ b/tools/perf/arch/csky/include/perf_regs.h @@ -15,86 +15,4 @@ #define PERF_REG_IP PERF_REG_CSKY_PC #define PERF_REG_SP PERF_REG_CSKY_SP -static inline const char *__perf_reg_name(int id) -{ - switch (id) { - case PERF_REG_CSKY_A0: - return "a0"; - case PERF_REG_CSKY_A1: - return "a1"; - case PERF_REG_CSKY_A2: - return "a2"; - case PERF_REG_CSKY_A3: - return "a3"; - case PERF_REG_CSKY_REGS0: - return "regs0"; - case PERF_REG_CSKY_REGS1: - return "regs1"; - case PERF_REG_CSKY_REGS2: - return "regs2"; - case PERF_REG_CSKY_REGS3: - return "regs3"; - case PERF_REG_CSKY_REGS4: - return "regs4"; - case PERF_REG_CSKY_REGS5: - return "regs5"; - case PERF_REG_CSKY_REGS6: - return "regs6"; - case PERF_REG_CSKY_REGS7: - return "regs7"; - case PERF_REG_CSKY_REGS8: - return "regs8"; - case PERF_REG_CSKY_REGS9: - return "regs9"; - case PERF_REG_CSKY_SP: - return "sp"; - case PERF_REG_CSKY_LR: - return "lr"; - case PERF_REG_CSKY_PC: - return "pc"; -#if defined(__CSKYABIV2__) - case PERF_REG_CSKY_EXREGS0: - return "exregs0"; - case PERF_REG_CSKY_EXREGS1: - return "exregs1"; - case PERF_REG_CSKY_EXREGS2: - return "exregs2"; - case PERF_REG_CSKY_EXREGS3: - return "exregs3"; - case PERF_REG_CSKY_EXREGS4: - return "exregs4"; - case PERF_REG_CSKY_EXREGS5: - return "exregs5"; - case PERF_REG_CSKY_EXREGS6: - return "exregs6"; - case PERF_REG_CSKY_EXREGS7: - return "exregs7"; - case PERF_REG_CSKY_EXREGS8: - return "exregs8"; - case PERF_REG_CSKY_EXREGS9: - return "exregs9"; - case PERF_REG_CSKY_EXREGS10: - return "exregs10"; - case PERF_REG_CSKY_EXREGS11: - return "exregs11"; - case PERF_REG_CSKY_EXREGS12: - return "exregs12"; - case PERF_REG_CSKY_EXREGS13: - return "exregs13"; - case PERF_REG_CSKY_EXREGS14: - return "exregs14"; - case PERF_REG_CSKY_TLS: - return "tls"; - case PERF_REG_CSKY_HI: - return "hi"; - case PERF_REG_CSKY_LO: - return "lo"; -#endif - default: - return NULL; - } - - return NULL; -} - #endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/mips/include/perf_regs.h b/tools/perf/arch/mips/include/perf_regs.h index ee73b36a14d1..b8cd8bbb37ba 100644 --- a/tools/perf/arch/mips/include/perf_regs.h +++ b/tools/perf/arch/mips/include/perf_regs.h @@ -12,73 +12,4 @@ #define PERF_REGS_MASK ((1ULL << PERF_REG_MIPS_MAX) - 1) -static inline const char *__perf_reg_name(int id) -{ - switch (id) { - case PERF_REG_MIPS_PC: - return "PC"; - case PERF_REG_MIPS_R1: - return "$1"; - case PERF_REG_MIPS_R2: - return "$2"; - case PERF_REG_MIPS_R3: - return "$3"; - case PERF_REG_MIPS_R4: - return "$4"; - case PERF_REG_MIPS_R5: - return "$5"; - case PERF_REG_MIPS_R6: - return "$6"; - case PERF_REG_MIPS_R7: - return "$7"; - case PERF_REG_MIPS_R8: - return "$8"; - case PERF_REG_MIPS_R9: - return "$9"; - case PERF_REG_MIPS_R10: - return "$10"; - case PERF_REG_MIPS_R11: - return "$11"; - case PERF_REG_MIPS_R12: - return "$12"; - case PERF_REG_MIPS_R13: - return "$13"; - case PERF_REG_MIPS_R14: - return "$14"; - case PERF_REG_MIPS_R15: - return "$15"; - case PERF_REG_MIPS_R16: - return "$16"; - case PERF_REG_MIPS_R17: - return "$17"; - case PERF_REG_MIPS_R18: - return "$18"; - case PERF_REG_MIPS_R19: - return "$19"; - case PERF_REG_MIPS_R20: - return "$20"; - case PERF_REG_MIPS_R21: - return "$21"; - case PERF_REG_MIPS_R22: - return "$22"; - case PERF_REG_MIPS_R23: - return "$23"; - case PERF_REG_MIPS_R24: - return "$24"; - case PERF_REG_MIPS_R25: - return "$25"; - case PERF_REG_MIPS_R28: - return "$28"; - case PERF_REG_MIPS_R29: - return "$29"; - case PERF_REG_MIPS_R30: - return "$30"; - case PERF_REG_MIPS_R31: - return "$31"; - default: - break; - } - return NULL; -} - #endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/powerpc/include/perf_regs.h b/tools/perf/arch/powerpc/include/perf_regs.h index 93339d17acc4..9bb17c3f370b 100644 --- a/tools/perf/arch/powerpc/include/perf_regs.h +++ b/tools/perf/arch/powerpc/include/perf_regs.h @@ -19,70 +19,4 @@ void perf_regs_load(u64 *regs); #define PERF_REG_IP PERF_REG_POWERPC_NIP #define PERF_REG_SP PERF_REG_POWERPC_R1 -static const char *reg_names[] = { - [PERF_REG_POWERPC_R0] = "r0", - [PERF_REG_POWERPC_R1] = "r1", - [PERF_REG_POWERPC_R2] = "r2", - [PERF_REG_POWERPC_R3] = "r3", - [PERF_REG_POWERPC_R4] = "r4", - [PERF_REG_POWERPC_R5] = "r5", - [PERF_REG_POWERPC_R6] = "r6", - [PERF_REG_POWERPC_R7] = "r7", - [PERF_REG_POWERPC_R8] = "r8", - [PERF_REG_POWERPC_R9] = "r9", - [PERF_REG_POWERPC_R10] = "r10", - [PERF_REG_POWERPC_R11] = "r11", - [PERF_REG_POWERPC_R12] = "r12", - [PERF_REG_POWERPC_R13] = "r13", - [PERF_REG_POWERPC_R14] = "r14", - [PERF_REG_POWERPC_R15] = "r15", - [PERF_REG_POWERPC_R16] = "r16", - [PERF_REG_POWERPC_R17] = "r17", - [PERF_REG_POWERPC_R18] = "r18", - [PERF_REG_POWERPC_R19] = "r19", - [PERF_REG_POWERPC_R20] = "r20", - [PERF_REG_POWERPC_R21] = "r21", - [PERF_REG_POWERPC_R22] = "r22", - [PERF_REG_POWERPC_R23] = "r23", - [PERF_REG_POWERPC_R24] = "r24", - [PERF_REG_POWERPC_R25] = "r25", - [PERF_REG_POWERPC_R26] = "r26", - [PERF_REG_POWERPC_R27] = "r27", - [PERF_REG_POWERPC_R28] = "r28", - [PERF_REG_POWERPC_R29] = "r29", - [PERF_REG_POWERPC_R30] = "r30", - [PERF_REG_POWERPC_R31] = "r31", - [PERF_REG_POWERPC_NIP] = "nip", - [PERF_REG_POWERPC_MSR] = "msr", - [PERF_REG_POWERPC_ORIG_R3] = "orig_r3", - [PERF_REG_POWERPC_CTR] = "ctr", - [PERF_REG_POWERPC_LINK] = "link", - [PERF_REG_POWERPC_XER] = "xer", - [PERF_REG_POWERPC_CCR] = "ccr", - [PERF_REG_POWERPC_SOFTE] = "softe", - [PERF_REG_POWERPC_TRAP] = "trap", - [PERF_REG_POWERPC_DAR] = "dar", - [PERF_REG_POWERPC_DSISR] = "dsisr", - [PERF_REG_POWERPC_SIER] = "sier", - [PERF_REG_POWERPC_MMCRA] = "mmcra", - [PERF_REG_POWERPC_MMCR0] = "mmcr0", - [PERF_REG_POWERPC_MMCR1] = "mmcr1", - [PERF_REG_POWERPC_MMCR2] = "mmcr2", - [PERF_REG_POWERPC_MMCR3] = "mmcr3", - [PERF_REG_POWERPC_SIER2] = "sier2", - [PERF_REG_POWERPC_SIER3] = "sier3", - [PERF_REG_POWERPC_PMC1] = "pmc1", - [PERF_REG_POWERPC_PMC2] = "pmc2", - [PERF_REG_POWERPC_PMC3] = "pmc3", - [PERF_REG_POWERPC_PMC4] = "pmc4", - [PERF_REG_POWERPC_PMC5] = "pmc5", - [PERF_REG_POWERPC_PMC6] = "pmc6", - [PERF_REG_POWERPC_SDAR] = "sdar", - [PERF_REG_POWERPC_SIAR] = "siar", -}; - -static inline const char *__perf_reg_name(int id) -{ - return reg_names[id]; -} #endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/powerpc/util/event.c b/tools/perf/arch/powerpc/util/event.c index 3bf441257466..cf430a4c55b9 100644 --- a/tools/perf/arch/powerpc/util/event.c +++ b/tools/perf/arch/powerpc/util/event.c @@ -40,8 +40,12 @@ const char *arch_perf_header_entry(const char *se_header) { if (!strcmp(se_header, "Local INSTR Latency")) return "Finish Cyc"; - else if (!strcmp(se_header, "Pipeline Stage Cycle")) + else if (!strcmp(se_header, "INSTR Latency")) + return "Global Finish_cyc"; + else if (!strcmp(se_header, "Local Pipeline Stage Cycle")) return "Dispatch Cyc"; + else if (!strcmp(se_header, "Pipeline Stage Cycle")) + return "Global Dispatch_cyc"; return se_header; } @@ -49,5 +53,7 @@ int arch_support_sort_key(const char *sort_key) { if (!strcmp(sort_key, "p_stage_cyc")) return 1; + if (!strcmp(sort_key, "local_p_stage_cyc")) + return 1; return 0; } diff --git a/tools/perf/arch/riscv/include/perf_regs.h b/tools/perf/arch/riscv/include/perf_regs.h index 6b02a767c918..6944bf0de53e 100644 --- a/tools/perf/arch/riscv/include/perf_regs.h +++ b/tools/perf/arch/riscv/include/perf_regs.h @@ -19,78 +19,4 @@ #define PERF_REG_IP PERF_REG_RISCV_PC #define PERF_REG_SP PERF_REG_RISCV_SP -static inline const char *__perf_reg_name(int id) -{ - switch (id) { - case PERF_REG_RISCV_PC: - return "pc"; - case PERF_REG_RISCV_RA: - return "ra"; - case PERF_REG_RISCV_SP: - return "sp"; - case PERF_REG_RISCV_GP: - return "gp"; - case PERF_REG_RISCV_TP: - return "tp"; - case PERF_REG_RISCV_T0: - return "t0"; - case PERF_REG_RISCV_T1: - return "t1"; - case PERF_REG_RISCV_T2: - return "t2"; - case PERF_REG_RISCV_S0: - return "s0"; - case PERF_REG_RISCV_S1: - return "s1"; - case PERF_REG_RISCV_A0: - return "a0"; - case PERF_REG_RISCV_A1: - return "a1"; - case PERF_REG_RISCV_A2: - return "a2"; - case PERF_REG_RISCV_A3: - return "a3"; - case PERF_REG_RISCV_A4: - return "a4"; - case PERF_REG_RISCV_A5: - return "a5"; - case PERF_REG_RISCV_A6: - return "a6"; - case PERF_REG_RISCV_A7: - return "a7"; - case PERF_REG_RISCV_S2: - return "s2"; - case PERF_REG_RISCV_S3: - return "s3"; - case PERF_REG_RISCV_S4: - return "s4"; - case PERF_REG_RISCV_S5: - return "s5"; - case PERF_REG_RISCV_S6: - return "s6"; - case PERF_REG_RISCV_S7: - return "s7"; - case PERF_REG_RISCV_S8: - return "s8"; - case PERF_REG_RISCV_S9: - return "s9"; - case PERF_REG_RISCV_S10: - return "s10"; - case PERF_REG_RISCV_S11: - return "s11"; - case PERF_REG_RISCV_T3: - return "t3"; - case PERF_REG_RISCV_T4: - return "t4"; - case PERF_REG_RISCV_T5: - return "t5"; - case PERF_REG_RISCV_T6: - return "t6"; - default: - return NULL; - } - - return NULL; -} - #endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/s390/include/perf_regs.h b/tools/perf/arch/s390/include/perf_regs.h index ce3031526623..52fcc0891da6 100644 --- a/tools/perf/arch/s390/include/perf_regs.h +++ b/tools/perf/arch/s390/include/perf_regs.h @@ -14,82 +14,4 @@ void perf_regs_load(u64 *regs); #define PERF_REG_IP PERF_REG_S390_PC #define PERF_REG_SP PERF_REG_S390_R15 -static inline const char *__perf_reg_name(int id) -{ - switch (id) { - case PERF_REG_S390_R0: - return "R0"; - case PERF_REG_S390_R1: - return "R1"; - case PERF_REG_S390_R2: - return "R2"; - case PERF_REG_S390_R3: - return "R3"; - case PERF_REG_S390_R4: - return "R4"; - case PERF_REG_S390_R5: - return "R5"; - case PERF_REG_S390_R6: - return "R6"; - case PERF_REG_S390_R7: - return "R7"; - case PERF_REG_S390_R8: - return "R8"; - case PERF_REG_S390_R9: - return "R9"; - case PERF_REG_S390_R10: - return "R10"; - case PERF_REG_S390_R11: - return "R11"; - case PERF_REG_S390_R12: - return "R12"; - case PERF_REG_S390_R13: - return "R13"; - case PERF_REG_S390_R14: - return "R14"; - case PERF_REG_S390_R15: - return "R15"; - case PERF_REG_S390_FP0: - return "FP0"; - case PERF_REG_S390_FP1: - return "FP1"; - case PERF_REG_S390_FP2: - return "FP2"; - case PERF_REG_S390_FP3: - return "FP3"; - case PERF_REG_S390_FP4: - return "FP4"; - case PERF_REG_S390_FP5: - return "FP5"; - case PERF_REG_S390_FP6: - return "FP6"; - case PERF_REG_S390_FP7: - return "FP7"; - case PERF_REG_S390_FP8: - return "FP8"; - case PERF_REG_S390_FP9: - return "FP9"; - case PERF_REG_S390_FP10: - return "FP10"; - case PERF_REG_S390_FP11: - return "FP11"; - case PERF_REG_S390_FP12: - return "FP12"; - case PERF_REG_S390_FP13: - return "FP13"; - case PERF_REG_S390_FP14: - return "FP14"; - case PERF_REG_S390_FP15: - return "FP15"; - case PERF_REG_S390_MASK: - return "MASK"; - case PERF_REG_S390_PC: - return "PC"; - default: - return NULL; - } - - return NULL; -} - #endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h index cddc4cdc0d9b..16e23b722042 100644 --- a/tools/perf/arch/x86/include/perf_regs.h +++ b/tools/perf/arch/x86/include/perf_regs.h @@ -23,86 +23,4 @@ void perf_regs_load(u64 *regs); #define PERF_REG_IP PERF_REG_X86_IP #define PERF_REG_SP PERF_REG_X86_SP -static inline const char *__perf_reg_name(int id) -{ - switch (id) { - case PERF_REG_X86_AX: - return "AX"; - case PERF_REG_X86_BX: - return "BX"; - case PERF_REG_X86_CX: - return "CX"; - case PERF_REG_X86_DX: - return "DX"; - case PERF_REG_X86_SI: - return "SI"; - case PERF_REG_X86_DI: - return "DI"; - case PERF_REG_X86_BP: - return "BP"; - case PERF_REG_X86_SP: - return "SP"; - case PERF_REG_X86_IP: - return "IP"; - case PERF_REG_X86_FLAGS: - return "FLAGS"; - case PERF_REG_X86_CS: - return "CS"; - case PERF_REG_X86_SS: - return "SS"; - case PERF_REG_X86_DS: - return "DS"; - case PERF_REG_X86_ES: - return "ES"; - case PERF_REG_X86_FS: - return "FS"; - case PERF_REG_X86_GS: - return "GS"; -#ifdef HAVE_ARCH_X86_64_SUPPORT - case PERF_REG_X86_R8: - return "R8"; - case PERF_REG_X86_R9: - return "R9"; - case PERF_REG_X86_R10: - return "R10"; - case PERF_REG_X86_R11: - return "R11"; - case PERF_REG_X86_R12: - return "R12"; - case PERF_REG_X86_R13: - return "R13"; - case PERF_REG_X86_R14: - return "R14"; - case PERF_REG_X86_R15: - return "R15"; -#endif /* HAVE_ARCH_X86_64_SUPPORT */ - -#define XMM(x) \ - case PERF_REG_X86_XMM ## x: \ - case PERF_REG_X86_XMM ## x + 1: \ - return "XMM" #x; - XMM(0) - XMM(1) - XMM(2) - XMM(3) - XMM(4) - XMM(5) - XMM(6) - XMM(7) - XMM(8) - XMM(9) - XMM(10) - XMM(11) - XMM(12) - XMM(13) - XMM(14) - XMM(15) -#undef XMM - default: - return NULL; - } - - return NULL; -} - #endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c index 0b0951030a2f..f924246eff78 100644 --- a/tools/perf/arch/x86/util/evlist.c +++ b/tools/perf/arch/x86/util/evlist.c @@ -17,3 +17,20 @@ int arch_evlist__add_default_attrs(struct evlist *evlist) else return parse_events(evlist, TOPDOWN_L1_EVENTS, NULL); } + +struct evsel *arch_evlist__leader(struct list_head *list) +{ + struct evsel *evsel, *first; + + first = list_first_entry(list, struct evsel, core.node); + + if (!pmu_have_event("cpu", "slots")) + return first; + + __evlist__for_each_entry(list, evsel) { + if (evsel->pmu_name && !strcmp(evsel->pmu_name, "cpu") && + evsel->name && strstr(evsel->name, "slots")) + return evsel; + } + return first; +} diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c index ddaca75c3bc0..1a17ec83d3c4 100644 --- a/tools/perf/bench/epoll-ctl.c +++ b/tools/perf/bench/epoll-ctl.c @@ -253,7 +253,7 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) if (!noaffinity) { CPU_ZERO(&cpuset); - CPU_SET(cpu->map[i % cpu->nr], &cpuset); + CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset); if (ret) diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c index 79d13dbc0a47..0d1dd8879197 100644 --- a/tools/perf/bench/epoll-wait.c +++ b/tools/perf/bench/epoll-wait.c @@ -342,7 +342,7 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) if (!noaffinity) { CPU_ZERO(&cpuset); - CPU_SET(cpu->map[i % cpu->nr], &cpuset); + CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset); if (ret) diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c index fcdea3e44937..9627b6ab8670 100644 --- a/tools/perf/bench/futex-hash.c +++ b/tools/perf/bench/futex-hash.c @@ -177,7 +177,7 @@ int bench_futex_hash(int argc, const char **argv) goto errmem; CPU_ZERO(&cpuset); - CPU_SET(cpu->map[i % cpu->nr], &cpuset); + CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset); if (ret) diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c index 137890f78e17..a512a320df74 100644 --- a/tools/perf/bench/futex-lock-pi.c +++ b/tools/perf/bench/futex-lock-pi.c @@ -136,7 +136,7 @@ static void create_threads(struct worker *w, pthread_attr_t thread_attr, worker[i].futex = &global_futex; CPU_ZERO(&cpuset); - CPU_SET(cpu->map[i % cpu->nr], &cpuset); + CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c index f7a5ffebb940..aca47ce8b1e7 100644 --- a/tools/perf/bench/futex-requeue.c +++ b/tools/perf/bench/futex-requeue.c @@ -131,7 +131,7 @@ static void block_threads(pthread_t *w, /* create and block all threads */ for (i = 0; i < params.nthreads; i++) { CPU_ZERO(&cpuset); - CPU_SET(cpu->map[i % cpu->nr], &cpuset); + CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c index 0983f40b4b40..888ee6037945 100644 --- a/tools/perf/bench/futex-wake-parallel.c +++ b/tools/perf/bench/futex-wake-parallel.c @@ -152,7 +152,7 @@ static void block_threads(pthread_t *w, pthread_attr_t thread_attr, /* create and block all threads */ for (i = 0; i < params.nthreads; i++) { CPU_ZERO(&cpuset); - CPU_SET(cpu->map[i % cpu->nr], &cpuset); + CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c index 2226a475e782..aa82db51c0ab 100644 --- a/tools/perf/bench/futex-wake.c +++ b/tools/perf/bench/futex-wake.c @@ -105,7 +105,7 @@ static void block_threads(pthread_t *w, /* create and block all threads */ for (i = 0; i < params.nthreads; i++) { CPU_ZERO(&cpuset); - CPU_SET(cpu->map[i % cpu->nr], &cpuset); + CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c index d0895162c2ba..d291f3a8af5f 100644 --- a/tools/perf/builtin-bench.c +++ b/tools/perf/builtin-bench.c @@ -226,7 +226,6 @@ static void run_collection(struct collection *coll) if (!bench->fn) break; printf("# Running %s/%s benchmark...\n", coll->name, bench->name); - fflush(stdout); argv[1] = bench->name; run_bench(coll->name, bench->name, bench->fn, 1, argv); @@ -247,6 +246,9 @@ int cmd_bench(int argc, const char **argv) struct collection *coll; int ret = 0; + /* Unbuffered output */ + setvbuf(stdout, NULL, _IONBF, 0); + if (argc < 2) { /* No collection specified. */ print_usage(); @@ -300,7 +302,6 @@ int cmd_bench(int argc, const char **argv) if (bench_format == BENCH_FORMAT_DEFAULT) printf("# Running '%s/%s' benchmark:\n", coll->name, bench->name); - fflush(stdout); ret = run_bench(coll->name, bench->name, bench->fn, argc-1, argv+1); goto end; } diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index 0db3cfc04c47..cd381693658b 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -351,10 +351,14 @@ static int build_id_cache__show_all(void) static int perf_buildid_cache_config(const char *var, const char *value, void *cb) { - const char **debuginfod = cb; + struct perf_debuginfod *di = cb; - if (!strcmp(var, "buildid-cache.debuginfod")) - *debuginfod = strdup(value); + if (!strcmp(var, "buildid-cache.debuginfod")) { + di->urls = strdup(value); + if (!di->urls) + return -ENOMEM; + di->set = true; + } return 0; } @@ -373,8 +377,8 @@ int cmd_buildid_cache(int argc, const char **argv) *purge_name_list_str = NULL, *missing_filename = NULL, *update_name_list_str = NULL, - *kcore_filename = NULL, - *debuginfod = NULL; + *kcore_filename = NULL; + struct perf_debuginfod debuginfod = { }; char sbuf[STRERR_BUFSIZE]; struct perf_data data = { @@ -399,8 +403,10 @@ int cmd_buildid_cache(int argc, const char **argv) OPT_BOOLEAN('f', "force", &force, "don't complain, do it"), OPT_STRING('u', "update", &update_name_list_str, "file list", "file(s) to update"), - OPT_STRING(0, "debuginfod", &debuginfod, "debuginfod url", - "set debuginfod url"), + OPT_STRING_OPTARG_SET(0, "debuginfod", &debuginfod.urls, + &debuginfod.set, "debuginfod urls", + "Enable debuginfod data retrieval from DEBUGINFOD_URLS or specified urls", + "system"), OPT_INCR('v', "verbose", &verbose, "be more verbose"), OPT_INTEGER(0, "target-ns", &ns_id, "target pid for namespace context"), OPT_END() @@ -425,10 +431,7 @@ int cmd_buildid_cache(int argc, const char **argv) if (argc || !(list_files || opts_flag)) usage_with_options(buildid_cache_usage, buildid_cache_options); - if (debuginfod) { - pr_debug("DEBUGINFOD_URLS=%s\n", debuginfod); - setenv("DEBUGINFOD_URLS", debuginfod, 1); - } + perf_debuginfod_setup(&debuginfod); /* -l is exclusive. It can not be used with other options. */ if (list_files && opts_flag) { diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index b5c67ef73862..77dd4afacca4 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -2015,7 +2015,8 @@ static int setup_nodes(struct perf_session *session) { struct numa_node *n; unsigned long **nodes; - int node, cpu; + int node, idx; + struct perf_cpu cpu; int *cpu2node; if (c2c.node_info > 2) @@ -2038,8 +2039,8 @@ static int setup_nodes(struct perf_session *session) if (!cpu2node) return -ENOMEM; - for (cpu = 0; cpu < c2c.cpus_cnt; cpu++) - cpu2node[cpu] = -1; + for (idx = 0; idx < c2c.cpus_cnt; idx++) + cpu2node[idx] = -1; c2c.cpu2node = cpu2node; @@ -2057,13 +2058,13 @@ static int setup_nodes(struct perf_session *session) if (perf_cpu_map__empty(map)) continue; - for (cpu = 0; cpu < map->nr; cpu++) { - set_bit(map->map[cpu], set); + perf_cpu_map__for_each_cpu(cpu, idx, map) { + set_bit(cpu.cpu, set); - if (WARN_ONCE(cpu2node[map->map[cpu]] != -1, "node/cpu topology bug")) + if (WARN_ONCE(cpu2node[cpu.cpu] != -1, "node/cpu topology bug")) return -EINVAL; - cpu2node[map->map[cpu]] = node; + cpu2node[cpu.cpu] = node; } } diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index 87cb11a7a3ee..71452599f87d 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -13,7 +13,9 @@ #include #include #include +#include #include +#include #include #include @@ -28,36 +30,12 @@ #include "strfilter.h" #include "util/cap.h" #include "util/config.h" +#include "util/ftrace.h" #include "util/units.h" #include "util/parse-sublevel-options.h" #define DEFAULT_TRACER "function_graph" -struct perf_ftrace { - struct evlist *evlist; - struct target target; - const char *tracer; - struct list_head filters; - struct list_head notrace; - struct list_head graph_funcs; - struct list_head nograph_funcs; - int graph_depth; - unsigned long percpu_buffer_size; - bool inherit; - int func_stack_trace; - int func_irq_info; - int graph_nosleep_time; - int graph_noirqs; - int graph_verbose; - int graph_thresh; - unsigned int initial_delay; -}; - -struct filter_entry { - struct list_head list; - char name[]; -}; - static volatile int workload_exec_errno; static bool done; @@ -303,7 +281,7 @@ static int set_tracing_cpumask(struct perf_cpu_map *cpumap) int ret; int last_cpu; - last_cpu = cpu_map__cpu(cpumap, cpumap->nr - 1); + last_cpu = perf_cpu_map__cpu(cpumap, cpumap->nr - 1).cpu; mask_size = last_cpu / 4 + 2; /* one more byte for EOS */ mask_size += last_cpu / 32; /* ',' is needed for every 32th cpus */ @@ -565,7 +543,24 @@ static int set_tracing_options(struct perf_ftrace *ftrace) return 0; } -static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv) +static void select_tracer(struct perf_ftrace *ftrace) +{ + bool graph = !list_empty(&ftrace->graph_funcs) || + !list_empty(&ftrace->nograph_funcs); + bool func = !list_empty(&ftrace->filters) || + !list_empty(&ftrace->notrace); + + /* The function_graph has priority over function tracer. */ + if (graph) + ftrace->tracer = "function_graph"; + else if (func) + ftrace->tracer = "function"; + /* Otherwise, the default tracer is used. */ + + pr_debug("%s tracer is used\n", ftrace->tracer); +} + +static int __cmd_ftrace(struct perf_ftrace *ftrace) { char *trace_file; int trace_fd; @@ -586,10 +581,7 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv) return -1; } - signal(SIGINT, sig_handler); - signal(SIGUSR1, sig_handler); - signal(SIGCHLD, sig_handler); - signal(SIGPIPE, sig_handler); + select_tracer(ftrace); if (reset_tracing_files(ftrace) < 0) { pr_err("failed to reset ftrace\n"); @@ -600,11 +592,6 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv) if (write_tracing_file("trace", "0") < 0) goto out; - if (argc && evlist__prepare_workload(ftrace->evlist, &ftrace->target, argv, false, - ftrace__workload_exec_failed_signal) < 0) { - goto out; - } - if (set_tracing_options(ftrace) < 0) goto out_reset; @@ -693,6 +680,270 @@ out: return (done && !workload_exec_errno) ? 0 : -1; } +static void make_histogram(int buckets[], char *buf, size_t len, char *linebuf) +{ + char *p, *q; + char *unit; + double num; + int i; + + /* ensure NUL termination */ + buf[len] = '\0'; + + /* handle data line by line */ + for (p = buf; (q = strchr(p, '\n')) != NULL; p = q + 1) { + *q = '\0'; + /* move it to the line buffer */ + strcat(linebuf, p); + + /* + * parse trace output to get function duration like in + * + * # tracer: function_graph + * # + * # CPU DURATION FUNCTION CALLS + * # | | | | | | | + * 1) + 10.291 us | do_filp_open(); + * 1) 4.889 us | do_filp_open(); + * 1) 6.086 us | do_filp_open(); + * + */ + if (linebuf[0] == '#') + goto next; + + /* ignore CPU */ + p = strchr(linebuf, ')'); + if (p == NULL) + p = linebuf; + + while (*p && !isdigit(*p) && (*p != '|')) + p++; + + /* no duration */ + if (*p == '\0' || *p == '|') + goto next; + + num = strtod(p, &unit); + if (!unit || strncmp(unit, " us", 3)) + goto next; + + i = log2(num); + if (i < 0) + i = 0; + if (i >= NUM_BUCKET) + i = NUM_BUCKET - 1; + + buckets[i]++; + +next: + /* empty the line buffer for the next output */ + linebuf[0] = '\0'; + } + + /* preserve any remaining output (before newline) */ + strcat(linebuf, p); +} + +static void display_histogram(int buckets[]) +{ + int i; + int total = 0; + int bar_total = 46; /* to fit in 80 column */ + char bar[] = "###############################################"; + int bar_len; + + for (i = 0; i < NUM_BUCKET; i++) + total += buckets[i]; + + if (total == 0) { + printf("No data found\n"); + return; + } + + printf("# %14s | %10s | %-*s |\n", + " DURATION ", "COUNT", bar_total, "GRAPH"); + + bar_len = buckets[0] * bar_total / total; + printf(" %4d - %-4d %s | %10d | %.*s%*s |\n", + 0, 1, "us", buckets[0], bar_len, bar, bar_total - bar_len, ""); + + for (i = 1; i < NUM_BUCKET - 1; i++) { + int start = (1 << (i - 1)); + int stop = 1 << i; + const char *unit = "us"; + + if (start >= 1024) { + start >>= 10; + stop >>= 10; + unit = "ms"; + } + bar_len = buckets[i] * bar_total / total; + printf(" %4d - %-4d %s | %10d | %.*s%*s |\n", + start, stop, unit, buckets[i], bar_len, bar, + bar_total - bar_len, ""); + } + + bar_len = buckets[NUM_BUCKET - 1] * bar_total / total; + printf(" %4d - %-4s %s | %10d | %.*s%*s |\n", + 1, "...", " s", buckets[NUM_BUCKET - 1], bar_len, bar, + bar_total - bar_len, ""); + +} + +static int prepare_func_latency(struct perf_ftrace *ftrace) +{ + char *trace_file; + int fd; + + if (ftrace->target.use_bpf) + return perf_ftrace__latency_prepare_bpf(ftrace); + + if (reset_tracing_files(ftrace) < 0) { + pr_err("failed to reset ftrace\n"); + return -1; + } + + /* reset ftrace buffer */ + if (write_tracing_file("trace", "0") < 0) + return -1; + + if (set_tracing_options(ftrace) < 0) + return -1; + + /* force to use the function_graph tracer to track duration */ + if (write_tracing_file("current_tracer", "function_graph") < 0) { + pr_err("failed to set current_tracer to function_graph\n"); + return -1; + } + + trace_file = get_tracing_file("trace_pipe"); + if (!trace_file) { + pr_err("failed to open trace_pipe\n"); + return -1; + } + + fd = open(trace_file, O_RDONLY); + if (fd < 0) + pr_err("failed to open trace_pipe\n"); + + put_tracing_file(trace_file); + return fd; +} + +static int start_func_latency(struct perf_ftrace *ftrace) +{ + if (ftrace->target.use_bpf) + return perf_ftrace__latency_start_bpf(ftrace); + + if (write_tracing_file("tracing_on", "1") < 0) { + pr_err("can't enable tracing\n"); + return -1; + } + + return 0; +} + +static int stop_func_latency(struct perf_ftrace *ftrace) +{ + if (ftrace->target.use_bpf) + return perf_ftrace__latency_stop_bpf(ftrace); + + write_tracing_file("tracing_on", "0"); + return 0; +} + +static int read_func_latency(struct perf_ftrace *ftrace, int buckets[]) +{ + if (ftrace->target.use_bpf) + return perf_ftrace__latency_read_bpf(ftrace, buckets); + + return 0; +} + +static int cleanup_func_latency(struct perf_ftrace *ftrace) +{ + if (ftrace->target.use_bpf) + return perf_ftrace__latency_cleanup_bpf(ftrace); + + reset_tracing_files(ftrace); + return 0; +} + +static int __cmd_latency(struct perf_ftrace *ftrace) +{ + int trace_fd; + char buf[4096]; + char line[256]; + struct pollfd pollfd = { + .events = POLLIN, + }; + int buckets[NUM_BUCKET] = { }; + + if (!(perf_cap__capable(CAP_PERFMON) || + perf_cap__capable(CAP_SYS_ADMIN))) { + pr_err("ftrace only works for %s!\n", +#ifdef HAVE_LIBCAP_SUPPORT + "users with the CAP_PERFMON or CAP_SYS_ADMIN capability" +#else + "root" +#endif + ); + return -1; + } + + trace_fd = prepare_func_latency(ftrace); + if (trace_fd < 0) + goto out; + + fcntl(trace_fd, F_SETFL, O_NONBLOCK); + pollfd.fd = trace_fd; + + if (start_func_latency(ftrace) < 0) + goto out; + + evlist__start_workload(ftrace->evlist); + + line[0] = '\0'; + while (!done) { + if (poll(&pollfd, 1, -1) < 0) + break; + + if (pollfd.revents & POLLIN) { + int n = read(trace_fd, buf, sizeof(buf) - 1); + if (n < 0) + break; + + make_histogram(buckets, buf, n, line); + } + } + + stop_func_latency(ftrace); + + if (workload_exec_errno) { + const char *emsg = str_error_r(workload_exec_errno, buf, sizeof(buf)); + pr_err("workload failed: %s\n", emsg); + goto out; + } + + /* read remaining buffer contents */ + while (!ftrace->target.use_bpf) { + int n = read(trace_fd, buf, sizeof(buf) - 1); + if (n <= 0) + break; + make_histogram(buckets, buf, n, line); + } + + read_func_latency(ftrace, buckets); + + display_histogram(buckets); + +out: + close(trace_fd); + cleanup_func_latency(ftrace); + + return (done && !workload_exec_errno) ? 0 : -1; +} + static int perf_ftrace_config(const char *var, const char *value, void *cb) { struct perf_ftrace *ftrace = cb; @@ -855,22 +1106,11 @@ static int parse_graph_tracer_opts(const struct option *opt, return 0; } -static void select_tracer(struct perf_ftrace *ftrace) -{ - bool graph = !list_empty(&ftrace->graph_funcs) || - !list_empty(&ftrace->nograph_funcs); - bool func = !list_empty(&ftrace->filters) || - !list_empty(&ftrace->notrace); - - /* The function_graph has priority over function tracer. */ - if (graph) - ftrace->tracer = "function_graph"; - else if (func) - ftrace->tracer = "function"; - /* Otherwise, the default tracer is used. */ - - pr_debug("%s tracer is used\n", ftrace->tracer); -} +enum perf_ftrace_subcommand { + PERF_FTRACE_NONE, + PERF_FTRACE_TRACE, + PERF_FTRACE_LATENCY, +}; int cmd_ftrace(int argc, const char **argv) { @@ -879,17 +1119,7 @@ int cmd_ftrace(int argc, const char **argv) .tracer = DEFAULT_TRACER, .target = { .uid = UINT_MAX, }, }; - const char * const ftrace_usage[] = { - "perf ftrace [] []", - "perf ftrace [] -- []", - NULL - }; - const struct option ftrace_options[] = { - OPT_STRING('t', "tracer", &ftrace.tracer, "tracer", - "Tracer to use: function_graph(default) or function"), - OPT_CALLBACK_DEFAULT('F', "funcs", NULL, "[FILTER]", - "Show available functions to filter", - opt_list_avail_functions, "*"), + const struct option common_options[] = { OPT_STRING('p', "pid", &ftrace.target.pid, "pid", "Trace on existing process id"), /* TODO: Add short option -t after -t/--tracer can be removed. */ @@ -901,6 +1131,14 @@ int cmd_ftrace(int argc, const char **argv) "System-wide collection from all CPUs"), OPT_STRING('C', "cpu", &ftrace.target.cpu_list, "cpu", "List of cpus to monitor"), + OPT_END() + }; + const struct option ftrace_options[] = { + OPT_STRING('t', "tracer", &ftrace.tracer, "tracer", + "Tracer to use: function_graph(default) or function"), + OPT_CALLBACK_DEFAULT('F', "funcs", NULL, "[FILTER]", + "Show available functions to filter", + opt_list_avail_functions, "*"), OPT_CALLBACK('T', "trace-funcs", &ftrace.filters, "func", "Trace given functions using function tracer", parse_filter_func), @@ -923,24 +1161,65 @@ int cmd_ftrace(int argc, const char **argv) "Trace children processes"), OPT_UINTEGER('D', "delay", &ftrace.initial_delay, "Number of milliseconds to wait before starting tracing after program start"), - OPT_END() + OPT_PARENT(common_options), }; + const struct option latency_options[] = { + OPT_CALLBACK('T', "trace-funcs", &ftrace.filters, "func", + "Show latency of given function", parse_filter_func), +#ifdef HAVE_BPF_SKEL + OPT_BOOLEAN('b', "use-bpf", &ftrace.target.use_bpf, + "Use BPF to measure function latency"), +#endif + OPT_PARENT(common_options), + }; + const struct option *options = ftrace_options; + + const char * const ftrace_usage[] = { + "perf ftrace [] []", + "perf ftrace [] -- [] []", + "perf ftrace {trace|latency} [] []", + "perf ftrace {trace|latency} [] -- [] []", + NULL + }; + enum perf_ftrace_subcommand subcmd = PERF_FTRACE_NONE; INIT_LIST_HEAD(&ftrace.filters); INIT_LIST_HEAD(&ftrace.notrace); INIT_LIST_HEAD(&ftrace.graph_funcs); INIT_LIST_HEAD(&ftrace.nograph_funcs); + signal(SIGINT, sig_handler); + signal(SIGUSR1, sig_handler); + signal(SIGCHLD, sig_handler); + signal(SIGPIPE, sig_handler); + ret = perf_config(perf_ftrace_config, &ftrace); if (ret < 0) return -1; - argc = parse_options(argc, argv, ftrace_options, ftrace_usage, - PARSE_OPT_STOP_AT_NON_OPTION); - if (!argc && target__none(&ftrace.target)) - ftrace.target.system_wide = true; + if (argc > 1) { + if (!strcmp(argv[1], "trace")) { + subcmd = PERF_FTRACE_TRACE; + } else if (!strcmp(argv[1], "latency")) { + subcmd = PERF_FTRACE_LATENCY; + options = latency_options; + } - select_tracer(&ftrace); + if (subcmd != PERF_FTRACE_NONE) { + argc--; + argv++; + } + } + /* for backward compatibility */ + if (subcmd == PERF_FTRACE_NONE) + subcmd = PERF_FTRACE_TRACE; + + argc = parse_options(argc, argv, options, ftrace_usage, + PARSE_OPT_STOP_AT_NON_OPTION); + if (argc < 0) { + ret = -EINVAL; + goto out_delete_filters; + } ret = target__validate(&ftrace.target); if (ret) { @@ -961,7 +1240,35 @@ int cmd_ftrace(int argc, const char **argv) if (ret < 0) goto out_delete_evlist; - ret = __cmd_ftrace(&ftrace, argc, argv); + if (argc) { + ret = evlist__prepare_workload(ftrace.evlist, &ftrace.target, + argv, false, + ftrace__workload_exec_failed_signal); + if (ret < 0) + goto out_delete_evlist; + } + + switch (subcmd) { + case PERF_FTRACE_TRACE: + if (!argc && target__none(&ftrace.target)) + ftrace.target.system_wide = true; + ret = __cmd_ftrace(&ftrace); + break; + case PERF_FTRACE_LATENCY: + if (list_empty(&ftrace.filters)) { + pr_err("Should provide a function to measure\n"); + parse_options_usage(ftrace_usage, options, "T", 1); + ret = -EINVAL; + goto out_delete_evlist; + } + ret = __cmd_latency(&ftrace); + break; + case PERF_FTRACE_NONE: + default: + pr_err("Invalid subcommand\n"); + ret = -EINVAL; + break; + } out_delete_evlist: evlist__delete(ftrace.evlist); diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index da03a341c63c..99d7ff9a8eff 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -192,7 +192,7 @@ static int evsel__process_alloc_node_event(struct evsel *evsel, struct perf_samp int ret = evsel__process_alloc_event(evsel, sample); if (!ret) { - int node1 = cpu__get_node(sample->cpu), + int node1 = cpu__get_node((struct perf_cpu){.cpu = sample->cpu}), node2 = evsel__intval(evsel, sample, "node"); if (node1 != node2) diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 0338b813585a..bb716c953d02 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -111,6 +111,7 @@ struct record { unsigned long long samples; struct mmap_cpu_mask affinity_mask; unsigned long output_max_size; /* = 0: unlimited */ + struct perf_debuginfod debuginfod; }; static volatile int done; @@ -2177,6 +2178,12 @@ static int perf_record_config(const char *var, const char *value, void *cb) rec->opts.nr_cblocks = nr_cblocks_default; } #endif + if (!strcmp(var, "record.debuginfod")) { + rec->debuginfod.urls = strdup(value); + if (!rec->debuginfod.urls) + return -ENOMEM; + rec->debuginfod.set = true; + } return 0; } @@ -2267,6 +2274,10 @@ out_free: return ret; } +void __weak arch__add_leaf_frame_record_opts(struct record_opts *opts __maybe_unused) +{ +} + static int parse_control_option(const struct option *opt, const char *str, int unset __maybe_unused) @@ -2663,6 +2674,10 @@ static struct option __record_options[] = { parse_control_option), OPT_CALLBACK(0, "synth", &record.opts, "no|all|task|mmap|cgroup", "Fine-tune event synthesis: default=all", parse_record_synth_option), + OPT_STRING_OPTARG_SET(0, "debuginfod", &record.debuginfod.urls, + &record.debuginfod.set, "debuginfod urls", + "Enable debuginfod data retrieval from DEBUGINFOD_URLS or specified urls", + "system"), OPT_END() }; @@ -2716,6 +2731,8 @@ int cmd_record(int argc, const char **argv) if (err) return err; + perf_debuginfod_setup(&record.debuginfod); + /* Make system wide (-a) the default target. */ if (!argc && target__none(&rec->opts.target)) rec->opts.target.system_wide = true; @@ -2792,7 +2809,7 @@ int cmd_record(int argc, const char **argv) symbol__init(NULL); if (rec->opts.affinity != PERF_AFFINITY_SYS) { - rec->affinity_mask.nbits = cpu__max_cpu(); + rec->affinity_mask.nbits = cpu__max_cpu().cpu; rec->affinity_mask.bits = bitmap_zalloc(rec->affinity_mask.nbits); if (!rec->affinity_mask.bits) { pr_err("Failed to allocate thread mask for %zd cpus\n", rec->affinity_mask.nbits); @@ -2898,6 +2915,10 @@ int cmd_record(int argc, const char **argv) } rec->opts.target.hybrid = perf_pmu__has_hybrid(); + + if (callchain_param.enabled && callchain_param.record_mode == CALLCHAIN_FP) + arch__add_leaf_frame_record_opts(&rec->opts); + err = -ENOMEM; if (evlist__create_maps(rec->evlist, &rec->opts.target) < 0) usage_with_options(record_usage, record_options); diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 8ae400429870..1dd92d8c9279 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -410,7 +410,7 @@ static int report__setup_sample_type(struct report *rep) } } - callchain_param_setup(sample_type); + callchain_param_setup(sample_type, perf_env__arch(&rep->session->header.env)); if (rep->stitch_lbr && (callchain_param.record_mode != CALLCHAIN_LBR)) { ui__warning("Can't find LBR callchain. Switch off --stitch-lbr.\n" @@ -1127,7 +1127,7 @@ static int process_attr(struct perf_tool *tool __maybe_unused, * on events sample_type. */ sample_type = evlist__combined_sample_type(*pevlist); - callchain_param_setup(sample_type); + callchain_param_setup(sample_type, perf_env__arch((*pevlist)->env)); return 0; } diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 4527f632ebe4..72d446de9c60 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -167,7 +167,7 @@ struct trace_sched_handler { struct perf_sched_map { DECLARE_BITMAP(comp_cpus_mask, MAX_CPUS); - int *comp_cpus; + struct perf_cpu *comp_cpus; bool comp; struct perf_thread_map *color_pids; const char *color_pids_str; @@ -191,7 +191,7 @@ struct perf_sched { * Track the current task - that way we can know whether there's any * weird events, such as a task being switched away that is not current. */ - int max_cpu; + struct perf_cpu max_cpu; u32 curr_pid[MAX_CPUS]; struct thread *curr_thread[MAX_CPUS]; char next_shortname1; @@ -1535,28 +1535,31 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel, int new_shortname; u64 timestamp0, timestamp = sample->time; s64 delta; - int i, this_cpu = sample->cpu; + int i; + struct perf_cpu this_cpu = { + .cpu = sample->cpu, + }; int cpus_nr; bool new_cpu = false; const char *color = PERF_COLOR_NORMAL; char stimestamp[32]; - BUG_ON(this_cpu >= MAX_CPUS || this_cpu < 0); + BUG_ON(this_cpu.cpu >= MAX_CPUS || this_cpu.cpu < 0); - if (this_cpu > sched->max_cpu) + if (this_cpu.cpu > sched->max_cpu.cpu) sched->max_cpu = this_cpu; if (sched->map.comp) { cpus_nr = bitmap_weight(sched->map.comp_cpus_mask, MAX_CPUS); - if (!test_and_set_bit(this_cpu, sched->map.comp_cpus_mask)) { + if (!test_and_set_bit(this_cpu.cpu, sched->map.comp_cpus_mask)) { sched->map.comp_cpus[cpus_nr++] = this_cpu; new_cpu = true; } } else - cpus_nr = sched->max_cpu; + cpus_nr = sched->max_cpu.cpu; - timestamp0 = sched->cpu_last_switched[this_cpu]; - sched->cpu_last_switched[this_cpu] = timestamp; + timestamp0 = sched->cpu_last_switched[this_cpu.cpu]; + sched->cpu_last_switched[this_cpu.cpu] = timestamp; if (timestamp0) delta = timestamp - timestamp0; else @@ -1577,7 +1580,7 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel, return -1; } - sched->curr_thread[this_cpu] = thread__get(sched_in); + sched->curr_thread[this_cpu.cpu] = thread__get(sched_in); printf(" "); @@ -1608,8 +1611,10 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel, } for (i = 0; i < cpus_nr; i++) { - int cpu = sched->map.comp ? sched->map.comp_cpus[i] : i; - struct thread *curr_thread = sched->curr_thread[cpu]; + struct perf_cpu cpu = { + .cpu = sched->map.comp ? sched->map.comp_cpus[i].cpu : i, + }; + struct thread *curr_thread = sched->curr_thread[cpu.cpu]; struct thread_runtime *curr_tr; const char *pid_color = color; const char *cpu_color = color; @@ -1617,19 +1622,19 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel, if (curr_thread && thread__has_color(curr_thread)) pid_color = COLOR_PIDS; - if (sched->map.cpus && !cpu_map__has(sched->map.cpus, cpu)) + if (sched->map.cpus && !perf_cpu_map__has(sched->map.cpus, cpu)) continue; - if (sched->map.color_cpus && cpu_map__has(sched->map.color_cpus, cpu)) + if (sched->map.color_cpus && perf_cpu_map__has(sched->map.color_cpus, cpu)) cpu_color = COLOR_CPUS; - if (cpu != this_cpu) + if (cpu.cpu != this_cpu.cpu) color_fprintf(stdout, color, " "); else color_fprintf(stdout, cpu_color, "*"); - if (sched->curr_thread[cpu]) { - curr_tr = thread__get_runtime(sched->curr_thread[cpu]); + if (sched->curr_thread[cpu.cpu]) { + curr_tr = thread__get_runtime(sched->curr_thread[cpu.cpu]); if (curr_tr == NULL) { thread__put(sched_in); return -1; @@ -1639,7 +1644,7 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel, color_fprintf(stdout, color, " "); } - if (sched->map.cpus && !cpu_map__has(sched->map.cpus, this_cpu)) + if (sched->map.cpus && !perf_cpu_map__has(sched->map.cpus, this_cpu)) goto out; timestamp__scnprintf_usec(timestamp, stimestamp, sizeof(stimestamp)); @@ -1929,7 +1934,7 @@ static char *timehist_get_commstr(struct thread *thread) static void timehist_header(struct perf_sched *sched) { - u32 ncpus = sched->max_cpu + 1; + u32 ncpus = sched->max_cpu.cpu + 1; u32 i, j; printf("%15s %6s ", "time", "cpu"); @@ -2008,7 +2013,7 @@ static void timehist_print_sample(struct perf_sched *sched, struct thread_runtime *tr = thread__priv(thread); const char *next_comm = evsel__strval(evsel, sample, "next_comm"); const u32 next_pid = evsel__intval(evsel, sample, "next_pid"); - u32 max_cpus = sched->max_cpu + 1; + u32 max_cpus = sched->max_cpu.cpu + 1; char tstr[64]; char nstr[30]; u64 wait_time; @@ -2389,7 +2394,7 @@ static void timehist_print_wakeup_event(struct perf_sched *sched, timestamp__scnprintf_usec(sample->time, tstr, sizeof(tstr)); printf("%15s [%04d] ", tstr, sample->cpu); if (sched->show_cpu_visual) - printf(" %*s ", sched->max_cpu + 1, ""); + printf(" %*s ", sched->max_cpu.cpu + 1, ""); printf(" %-*s ", comm_width, timehist_get_commstr(thread)); @@ -2449,13 +2454,13 @@ static void timehist_print_migration_event(struct perf_sched *sched, { struct thread *thread; char tstr[64]; - u32 max_cpus = sched->max_cpu + 1; + u32 max_cpus; u32 ocpu, dcpu; if (sched->summary_only) return; - max_cpus = sched->max_cpu + 1; + max_cpus = sched->max_cpu.cpu + 1; ocpu = evsel__intval(evsel, sample, "orig_cpu"); dcpu = evsel__intval(evsel, sample, "dest_cpu"); @@ -2918,7 +2923,7 @@ static void timehist_print_summary(struct perf_sched *sched, printf(" Total scheduling time (msec): "); print_sched_time(hist_time, 2); - printf(" (x %d)\n", sched->max_cpu); + printf(" (x %d)\n", sched->max_cpu.cpu); } typedef int (*sched_handler)(struct perf_tool *tool, @@ -2935,9 +2940,11 @@ static int perf_timehist__process_sample(struct perf_tool *tool, { struct perf_sched *sched = container_of(tool, struct perf_sched, tool); int err = 0; - int this_cpu = sample->cpu; + struct perf_cpu this_cpu = { + .cpu = sample->cpu, + }; - if (this_cpu > sched->max_cpu) + if (this_cpu.cpu > sched->max_cpu.cpu) sched->max_cpu = this_cpu; if (evsel->handler != NULL) { @@ -3054,10 +3061,10 @@ static int perf_sched__timehist(struct perf_sched *sched) goto out; /* pre-allocate struct for per-CPU idle stats */ - sched->max_cpu = session->header.env.nr_cpus_online; - if (sched->max_cpu == 0) - sched->max_cpu = 4; - if (init_idle_threads(sched->max_cpu)) + sched->max_cpu.cpu = session->header.env.nr_cpus_online; + if (sched->max_cpu.cpu == 0) + sched->max_cpu.cpu = 4; + if (init_idle_threads(sched->max_cpu.cpu)) goto out; /* summary_only implies summary option, but don't overwrite summary if set */ @@ -3209,10 +3216,10 @@ static int setup_map_cpus(struct perf_sched *sched) { struct perf_cpu_map *map; - sched->max_cpu = sysconf(_SC_NPROCESSORS_CONF); + sched->max_cpu.cpu = sysconf(_SC_NPROCESSORS_CONF); if (sched->map.comp) { - sched->map.comp_cpus = zalloc(sched->max_cpu * sizeof(int)); + sched->map.comp_cpus = zalloc(sched->max_cpu.cpu * sizeof(int)); if (!sched->map.comp_cpus) return -1; } diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index c82b033e8942..ecd4f99a6c14 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -15,6 +15,7 @@ #include "util/symbol.h" #include "util/thread.h" #include "util/trace-event.h" +#include "util/env.h" #include "util/evlist.h" #include "util/evsel.h" #include "util/evsel_fprintf.h" @@ -648,7 +649,7 @@ out: return 0; } -static int perf_sample__fprintf_regs(struct regs_dump *regs, uint64_t mask, +static int perf_sample__fprintf_regs(struct regs_dump *regs, uint64_t mask, const char *arch, FILE *fp) { unsigned i = 0, r; @@ -661,7 +662,7 @@ static int perf_sample__fprintf_regs(struct regs_dump *regs, uint64_t mask, for_each_set_bit(r, (unsigned long *) &mask, sizeof(mask) * 8) { u64 val = regs->regs[i++]; - printed += fprintf(fp, "%5s:0x%"PRIx64" ", perf_reg_name(r), val); + printed += fprintf(fp, "%5s:0x%"PRIx64" ", perf_reg_name(r, arch), val); } return printed; @@ -718,17 +719,17 @@ tod_scnprintf(struct perf_script *script, char *buf, int buflen, } static int perf_sample__fprintf_iregs(struct perf_sample *sample, - struct perf_event_attr *attr, FILE *fp) + struct perf_event_attr *attr, const char *arch, FILE *fp) { return perf_sample__fprintf_regs(&sample->intr_regs, - attr->sample_regs_intr, fp); + attr->sample_regs_intr, arch, fp); } static int perf_sample__fprintf_uregs(struct perf_sample *sample, - struct perf_event_attr *attr, FILE *fp) + struct perf_event_attr *attr, const char *arch, FILE *fp) { return perf_sample__fprintf_regs(&sample->user_regs, - attr->sample_regs_user, fp); + attr->sample_regs_user, arch, fp); } static int perf_sample__fprintf_start(struct perf_script *script, @@ -2000,6 +2001,7 @@ static void process_event(struct perf_script *script, struct evsel_script *es = evsel->priv; FILE *fp = es->fp; char str[PAGE_SIZE_NAME_LEN]; + const char *arch = perf_env__arch(machine->env); if (output[type].fields == 0) return; @@ -2066,10 +2068,10 @@ static void process_event(struct perf_script *script, } if (PRINT_FIELD(IREGS)) - perf_sample__fprintf_iregs(sample, attr, fp); + perf_sample__fprintf_iregs(sample, attr, arch, fp); if (PRINT_FIELD(UREGS)) - perf_sample__fprintf_uregs(sample, attr, fp); + perf_sample__fprintf_uregs(sample, attr, arch, fp); if (PRINT_FIELD(BRSTACK)) perf_sample__fprintf_brstack(sample, thread, attr, fp); @@ -2113,8 +2115,8 @@ static struct scripting_ops *scripting_ops; static void __process_stat(struct evsel *counter, u64 tstamp) { int nthreads = perf_thread_map__nr(counter->core.threads); - int ncpus = evsel__nr_cpus(counter); - int cpu, thread; + int idx, thread; + struct perf_cpu cpu; static int header_printed; if (counter->core.system_wide) @@ -2127,13 +2129,13 @@ static void __process_stat(struct evsel *counter, u64 tstamp) } for (thread = 0; thread < nthreads; thread++) { - for (cpu = 0; cpu < ncpus; cpu++) { + perf_cpu_map__for_each_cpu(cpu, idx, evsel__cpus(counter)) { struct perf_counts_values *counts; - counts = perf_counts(counter->counts, cpu, thread); + counts = perf_counts(counter->counts, idx, thread); printf("%3d %8d %15" PRIu64 " %15" PRIu64 " %15" PRIu64 " %15" PRIu64 " %s\n", - counter->core.cpus->map[cpu], + cpu.cpu, perf_thread_map__pid(counter->core.threads, thread), counts->val, counts->ena, @@ -2316,7 +2318,7 @@ static int process_attr(struct perf_tool *tool, union perf_event *event, * on events sample_type. */ sample_type = evlist__combined_sample_type(evlist); - callchain_param_setup(sample_type); + callchain_param_setup(sample_type, perf_env__arch((*pevlist)->env)); /* Enable fields for callchain entries */ if (symbol_conf.use_callchain && @@ -3466,16 +3468,7 @@ static void script__setup_sample_type(struct perf_script *script) struct perf_session *session = script->session; u64 sample_type = evlist__combined_sample_type(session->evlist); - if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain) { - if ((sample_type & PERF_SAMPLE_REGS_USER) && - (sample_type & PERF_SAMPLE_STACK_USER)) { - callchain_param.record_mode = CALLCHAIN_DWARF; - dwarf_callchain_users = true; - } else if (sample_type & PERF_SAMPLE_BRANCH_STACK) - callchain_param.record_mode = CALLCHAIN_LBR; - else - callchain_param.record_mode = CALLCHAIN_FP; - } + callchain_param_setup(sample_type, perf_env__arch(session->machines.host.env)); if (script->stitch_lbr && (callchain_param.record_mode != CALLCHAIN_LBR)) { pr_warning("Can't find LBR callchain. Switch off --stitch-lbr.\n" diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 7974933dbc77..973ade18b72a 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -234,7 +234,7 @@ static bool cpus_map_matched(struct evsel *a, struct evsel *b) return false; for (int i = 0; i < a->core.cpus->nr; i++) { - if (a->core.cpus->map[i] != b->core.cpus->map[i]) + if (a->core.cpus->map[i].cpu != b->core.cpus->map[i].cpu) return false; } @@ -327,34 +327,35 @@ static int write_stat_round_event(u64 tm, u64 type) #define SID(e, x, y) xyarray__entry(e->core.sample_id, x, y) -static int evsel__write_stat_event(struct evsel *counter, u32 cpu, u32 thread, +static int evsel__write_stat_event(struct evsel *counter, int cpu_map_idx, u32 thread, struct perf_counts_values *count) { - struct perf_sample_id *sid = SID(counter, cpu, thread); + struct perf_sample_id *sid = SID(counter, cpu_map_idx, thread); + struct perf_cpu cpu = perf_cpu_map__cpu(evsel__cpus(counter), cpu_map_idx); return perf_event__synthesize_stat(NULL, cpu, thread, sid->id, count, process_synthesized_event, NULL); } -static int read_single_counter(struct evsel *counter, int cpu, +static int read_single_counter(struct evsel *counter, int cpu_map_idx, int thread, struct timespec *rs) { if (counter->tool_event == PERF_TOOL_DURATION_TIME) { u64 val = rs->tv_nsec + rs->tv_sec*1000000000ULL; struct perf_counts_values *count = - perf_counts(counter->counts, cpu, thread); + perf_counts(counter->counts, cpu_map_idx, thread); count->ena = count->run = val; count->val = val; return 0; } - return evsel__read_counter(counter, cpu, thread); + return evsel__read_counter(counter, cpu_map_idx, thread); } /* * Read out the results of a single counter: * do not aggregate counts across CPUs in system-wide mode */ -static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu) +static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu_map_idx) { int nthreads = perf_thread_map__nr(evsel_list->core.threads); int thread; @@ -368,24 +369,24 @@ static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu) for (thread = 0; thread < nthreads; thread++) { struct perf_counts_values *count; - count = perf_counts(counter->counts, cpu, thread); + count = perf_counts(counter->counts, cpu_map_idx, thread); /* * The leader's group read loads data into its group members * (via evsel__read_counter()) and sets their count->loaded. */ - if (!perf_counts__is_loaded(counter->counts, cpu, thread) && - read_single_counter(counter, cpu, thread, rs)) { + if (!perf_counts__is_loaded(counter->counts, cpu_map_idx, thread) && + read_single_counter(counter, cpu_map_idx, thread, rs)) { counter->counts->scaled = -1; - perf_counts(counter->counts, cpu, thread)->ena = 0; - perf_counts(counter->counts, cpu, thread)->run = 0; + perf_counts(counter->counts, cpu_map_idx, thread)->ena = 0; + perf_counts(counter->counts, cpu_map_idx, thread)->run = 0; return -1; } - perf_counts__set_loaded(counter->counts, cpu, thread, false); + perf_counts__set_loaded(counter->counts, cpu_map_idx, thread, false); if (STAT_RECORD) { - if (evsel__write_stat_event(counter, cpu, thread, count)) { + if (evsel__write_stat_event(counter, cpu_map_idx, thread, count)) { pr_err("failed to write stat event\n"); return -1; } @@ -395,7 +396,8 @@ static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu) fprintf(stat_config.output, "%s: %d: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n", evsel__name(counter), - cpu, + perf_cpu_map__cpu(evsel__cpus(counter), + cpu_map_idx).cpu, count->val, count->ena, count->run); } } @@ -405,36 +407,33 @@ static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu) static int read_affinity_counters(struct timespec *rs) { - struct evsel *counter; - struct affinity affinity; - int i, ncpus, cpu; + struct evlist_cpu_iterator evlist_cpu_itr; + struct affinity saved_affinity, *affinity; if (all_counters_use_bpf) return 0; - if (affinity__setup(&affinity) < 0) - return -1; - - ncpus = perf_cpu_map__nr(evsel_list->core.all_cpus); if (!target__has_cpu(&target) || target__has_per_thread(&target)) - ncpus = 1; - evlist__for_each_cpu(evsel_list, i, cpu) { - if (i >= ncpus) - break; - affinity__set(&affinity, cpu); + affinity = NULL; + else if (affinity__setup(&saved_affinity) < 0) + return -1; + else + affinity = &saved_affinity; - evlist__for_each_entry(evsel_list, counter) { - if (evsel__cpu_iter_skip(counter, cpu)) - continue; - if (evsel__is_bpf(counter)) - continue; - if (!counter->err) { - counter->err = read_counter_cpu(counter, rs, - counter->cpu_iter - 1); - } + evlist__for_each_cpu(evlist_cpu_itr, evsel_list, affinity) { + struct evsel *counter = evlist_cpu_itr.evsel; + + if (evsel__is_bpf(counter)) + continue; + + if (!counter->err) { + counter->err = read_counter_cpu(counter, rs, + evlist_cpu_itr.cpu_map_idx); } } - affinity__cleanup(&affinity); + if (affinity) + affinity__cleanup(&saved_affinity); + return 0; } @@ -788,8 +787,9 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx) int status = 0; const bool forks = (argc > 0); bool is_pipe = STAT_RECORD ? perf_stat.data.is_pipe : false; + struct evlist_cpu_iterator evlist_cpu_itr; struct affinity affinity; - int i, cpu, err; + int err; bool second_pass = false; if (forks) { @@ -813,56 +813,53 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx) all_counters_use_bpf = false; } - evlist__for_each_cpu (evsel_list, i, cpu) { + evlist__for_each_cpu(evlist_cpu_itr, evsel_list, &affinity) { + counter = evlist_cpu_itr.evsel; + /* * bperf calls evsel__open_per_cpu() in bperf__load(), so * no need to call it again here. */ if (target.use_bpf) break; - affinity__set(&affinity, cpu); - evlist__for_each_entry(evsel_list, counter) { - if (evsel__cpu_iter_skip(counter, cpu)) - continue; - if (counter->reset_group || counter->errored) - continue; - if (evsel__is_bpf(counter)) - continue; + if (counter->reset_group || counter->errored) + continue; + if (evsel__is_bpf(counter)) + continue; try_again: - if (create_perf_stat_counter(counter, &stat_config, &target, - counter->cpu_iter - 1) < 0) { - - /* - * Weak group failed. We cannot just undo this here - * because earlier CPUs might be in group mode, and the kernel - * doesn't support mixing group and non group reads. Defer - * it to later. - * Don't close here because we're in the wrong affinity. - */ - if ((errno == EINVAL || errno == EBADF) && - evsel__leader(counter) != counter && - counter->weak_group) { - evlist__reset_weak_group(evsel_list, counter, false); - assert(counter->reset_group); - second_pass = true; - continue; - } - - switch (stat_handle_error(counter)) { - case COUNTER_FATAL: - return -1; - case COUNTER_RETRY: - goto try_again; - case COUNTER_SKIP: - continue; - default: - break; - } + if (create_perf_stat_counter(counter, &stat_config, &target, + evlist_cpu_itr.cpu_map_idx) < 0) { + /* + * Weak group failed. We cannot just undo this here + * because earlier CPUs might be in group mode, and the kernel + * doesn't support mixing group and non group reads. Defer + * it to later. + * Don't close here because we're in the wrong affinity. + */ + if ((errno == EINVAL || errno == EBADF) && + evsel__leader(counter) != counter && + counter->weak_group) { + evlist__reset_weak_group(evsel_list, counter, false); + assert(counter->reset_group); + second_pass = true; + continue; } - counter->supported = true; + + switch (stat_handle_error(counter)) { + case COUNTER_FATAL: + return -1; + case COUNTER_RETRY: + goto try_again; + case COUNTER_SKIP: + continue; + default: + break; + } + } + counter->supported = true; } if (second_pass) { @@ -871,42 +868,40 @@ try_again: * and also close errored counters. */ - evlist__for_each_cpu(evsel_list, i, cpu) { - affinity__set(&affinity, cpu); - /* First close errored or weak retry */ - evlist__for_each_entry(evsel_list, counter) { - if (!counter->reset_group && !counter->errored) - continue; - if (evsel__cpu_iter_skip_no_inc(counter, cpu)) - continue; - perf_evsel__close_cpu(&counter->core, counter->cpu_iter); - } - /* Now reopen weak */ - evlist__for_each_entry(evsel_list, counter) { - if (!counter->reset_group && !counter->errored) - continue; - if (evsel__cpu_iter_skip(counter, cpu)) - continue; - if (!counter->reset_group) - continue; -try_again_reset: - pr_debug2("reopening weak %s\n", evsel__name(counter)); - if (create_perf_stat_counter(counter, &stat_config, &target, - counter->cpu_iter - 1) < 0) { + /* First close errored or weak retry */ + evlist__for_each_cpu(evlist_cpu_itr, evsel_list, &affinity) { + counter = evlist_cpu_itr.evsel; - switch (stat_handle_error(counter)) { - case COUNTER_FATAL: - return -1; - case COUNTER_RETRY: - goto try_again_reset; - case COUNTER_SKIP: - continue; - default: - break; - } + if (!counter->reset_group && !counter->errored) + continue; + + perf_evsel__close_cpu(&counter->core, evlist_cpu_itr.cpu_map_idx); + } + /* Now reopen weak */ + evlist__for_each_cpu(evlist_cpu_itr, evsel_list, &affinity) { + counter = evlist_cpu_itr.evsel; + + if (!counter->reset_group && !counter->errored) + continue; + if (!counter->reset_group) + continue; +try_again_reset: + pr_debug2("reopening weak %s\n", evsel__name(counter)); + if (create_perf_stat_counter(counter, &stat_config, &target, + evlist_cpu_itr.cpu_map_idx) < 0) { + + switch (stat_handle_error(counter)) { + case COUNTER_FATAL: + return -1; + case COUNTER_RETRY: + goto try_again_reset; + case COUNTER_SKIP: + continue; + default: + break; } - counter->supported = true; } + counter->supported = true; } } affinity__cleanup(&affinity); @@ -1168,6 +1163,26 @@ static int parse_stat_cgroups(const struct option *opt, return parse_cgroups(opt, str, unset); } +static int parse_hybrid_type(const struct option *opt, + const char *str, + int unset __maybe_unused) +{ + struct evlist *evlist = *(struct evlist **)opt->value; + + if (!list_empty(&evlist->core.entries)) { + fprintf(stderr, "Must define cputype before events/metrics\n"); + return -1; + } + + evlist->hybrid_pmu_name = perf_pmu__hybrid_type_to_pmu(str); + if (!evlist->hybrid_pmu_name) { + fprintf(stderr, "--cputype %s is not supported!\n", str); + return -1; + } + + return 0; +} + static struct option stat_options[] = { OPT_BOOLEAN('T', "transaction", &transaction_run, "hardware transaction statistics"), @@ -1282,6 +1297,10 @@ static struct option stat_options[] = { "don't print 'summary' for CSV summary output"), OPT_BOOLEAN(0, "quiet", &stat_config.quiet, "don't print output (useful with record)"), + OPT_CALLBACK(0, "cputype", &evsel_list, "hybrid cpu type", + "Only enable events on applying cpu with this type " + "for hybrid platform (e.g. core or atom)", + parse_hybrid_type), #ifdef HAVE_LIBPFM OPT_CALLBACK(0, "pfm-events", &evsel_list, "event", "libpfm4 event selector. use 'perf list' to list available events", @@ -1298,70 +1317,75 @@ static struct option stat_options[] = { OPT_END() }; +static const char *const aggr_mode__string[] = { + [AGGR_CORE] = "core", + [AGGR_DIE] = "die", + [AGGR_GLOBAL] = "global", + [AGGR_NODE] = "node", + [AGGR_NONE] = "none", + [AGGR_SOCKET] = "socket", + [AGGR_THREAD] = "thread", + [AGGR_UNSET] = "unset", +}; + static struct aggr_cpu_id perf_stat__get_socket(struct perf_stat_config *config __maybe_unused, - struct perf_cpu_map *map, int cpu) + struct perf_cpu cpu) { - return cpu_map__get_socket(map, cpu, NULL); + return aggr_cpu_id__socket(cpu, /*data=*/NULL); } static struct aggr_cpu_id perf_stat__get_die(struct perf_stat_config *config __maybe_unused, - struct perf_cpu_map *map, int cpu) + struct perf_cpu cpu) { - return cpu_map__get_die(map, cpu, NULL); + return aggr_cpu_id__die(cpu, /*data=*/NULL); } static struct aggr_cpu_id perf_stat__get_core(struct perf_stat_config *config __maybe_unused, - struct perf_cpu_map *map, int cpu) + struct perf_cpu cpu) { - return cpu_map__get_core(map, cpu, NULL); + return aggr_cpu_id__core(cpu, /*data=*/NULL); } static struct aggr_cpu_id perf_stat__get_node(struct perf_stat_config *config __maybe_unused, - struct perf_cpu_map *map, int cpu) + struct perf_cpu cpu) { - return cpu_map__get_node(map, cpu, NULL); + return aggr_cpu_id__node(cpu, /*data=*/NULL); } static struct aggr_cpu_id perf_stat__get_aggr(struct perf_stat_config *config, - aggr_get_id_t get_id, struct perf_cpu_map *map, int idx) + aggr_get_id_t get_id, struct perf_cpu cpu) { - int cpu; - struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); + struct aggr_cpu_id id = aggr_cpu_id__empty(); - if (idx >= map->nr) - return id; + if (aggr_cpu_id__is_empty(&config->cpus_aggr_map->map[cpu.cpu])) + config->cpus_aggr_map->map[cpu.cpu] = get_id(config, cpu); - cpu = map->map[idx]; - - if (cpu_map__aggr_cpu_id_is_empty(config->cpus_aggr_map->map[cpu])) - config->cpus_aggr_map->map[cpu] = get_id(config, map, idx); - - id = config->cpus_aggr_map->map[cpu]; + id = config->cpus_aggr_map->map[cpu.cpu]; return id; } static struct aggr_cpu_id perf_stat__get_socket_cached(struct perf_stat_config *config, - struct perf_cpu_map *map, int idx) + struct perf_cpu cpu) { - return perf_stat__get_aggr(config, perf_stat__get_socket, map, idx); + return perf_stat__get_aggr(config, perf_stat__get_socket, cpu); } static struct aggr_cpu_id perf_stat__get_die_cached(struct perf_stat_config *config, - struct perf_cpu_map *map, int idx) + struct perf_cpu cpu) { - return perf_stat__get_aggr(config, perf_stat__get_die, map, idx); + return perf_stat__get_aggr(config, perf_stat__get_die, cpu); } static struct aggr_cpu_id perf_stat__get_core_cached(struct perf_stat_config *config, - struct perf_cpu_map *map, int idx) + struct perf_cpu cpu) { - return perf_stat__get_aggr(config, perf_stat__get_core, map, idx); + return perf_stat__get_aggr(config, perf_stat__get_core, cpu); } static struct aggr_cpu_id perf_stat__get_node_cached(struct perf_stat_config *config, - struct perf_cpu_map *map, int idx) + struct perf_cpu cpu) { - return perf_stat__get_aggr(config, perf_stat__get_node, map, idx); + return perf_stat__get_aggr(config, perf_stat__get_node, cpu); } static bool term_percore_set(void) @@ -1376,54 +1400,67 @@ static bool term_percore_set(void) return false; } -static int perf_stat_init_aggr_mode(void) +static aggr_cpu_id_get_t aggr_mode__get_aggr(enum aggr_mode aggr_mode) { - int nr; - - switch (stat_config.aggr_mode) { + switch (aggr_mode) { case AGGR_SOCKET: - if (cpu_map__build_socket_map(evsel_list->core.cpus, &stat_config.aggr_map)) { - perror("cannot build socket map"); - return -1; - } - stat_config.aggr_get_id = perf_stat__get_socket_cached; - break; + return aggr_cpu_id__socket; case AGGR_DIE: - if (cpu_map__build_die_map(evsel_list->core.cpus, &stat_config.aggr_map)) { - perror("cannot build die map"); - return -1; - } - stat_config.aggr_get_id = perf_stat__get_die_cached; - break; + return aggr_cpu_id__die; case AGGR_CORE: - if (cpu_map__build_core_map(evsel_list->core.cpus, &stat_config.aggr_map)) { - perror("cannot build core map"); - return -1; - } - stat_config.aggr_get_id = perf_stat__get_core_cached; - break; + return aggr_cpu_id__core; case AGGR_NODE: - if (cpu_map__build_node_map(evsel_list->core.cpus, &stat_config.aggr_map)) { - perror("cannot build core map"); - return -1; - } - stat_config.aggr_get_id = perf_stat__get_node_cached; - break; + return aggr_cpu_id__node; case AGGR_NONE: - if (term_percore_set()) { - if (cpu_map__build_core_map(evsel_list->core.cpus, - &stat_config.aggr_map)) { - perror("cannot build core map"); - return -1; - } - stat_config.aggr_get_id = perf_stat__get_core_cached; - } - break; + if (term_percore_set()) + return aggr_cpu_id__core; + + return NULL; case AGGR_GLOBAL: case AGGR_THREAD: case AGGR_UNSET: default: - break; + return NULL; + } +} + +static aggr_get_id_t aggr_mode__get_id(enum aggr_mode aggr_mode) +{ + switch (aggr_mode) { + case AGGR_SOCKET: + return perf_stat__get_socket_cached; + case AGGR_DIE: + return perf_stat__get_die_cached; + case AGGR_CORE: + return perf_stat__get_core_cached; + case AGGR_NODE: + return perf_stat__get_node_cached; + case AGGR_NONE: + if (term_percore_set()) { + return perf_stat__get_core_cached; + } + return NULL; + case AGGR_GLOBAL: + case AGGR_THREAD: + case AGGR_UNSET: + default: + return NULL; + } +} + +static int perf_stat_init_aggr_mode(void) +{ + int nr; + aggr_cpu_id_get_t get_id = aggr_mode__get_aggr(stat_config.aggr_mode); + + if (get_id) { + stat_config.aggr_map = cpu_aggr_map__new(evsel_list->core.cpus, + get_id, /*data=*/NULL); + if (!stat_config.aggr_map) { + pr_err("cannot build %s map", aggr_mode__string[stat_config.aggr_mode]); + return -1; + } + stat_config.aggr_get_id = aggr_mode__get_id(stat_config.aggr_mode); } /* @@ -1431,7 +1468,7 @@ static int perf_stat_init_aggr_mode(void) * taking the highest cpu number to be the size of * the aggregation translate cpumap. */ - nr = perf_cpu_map__max(evsel_list->core.cpus); + nr = perf_cpu_map__max(evsel_list->core.cpus).cpu; stat_config.cpus_aggr_map = cpu_aggr_map__empty_new(nr + 1); return stat_config.cpus_aggr_map ? 0 : -ENOMEM; } @@ -1459,169 +1496,139 @@ static void perf_stat__exit_aggr_mode(void) stat_config.cpus_aggr_map = NULL; } -static inline int perf_env__get_cpu(struct perf_env *env, struct perf_cpu_map *map, int idx) -{ - int cpu; - - if (idx > map->nr) - return -1; - - cpu = map->map[idx]; - - if (cpu >= env->nr_cpus_avail) - return -1; - - return cpu; -} - -static struct aggr_cpu_id perf_env__get_socket(struct perf_cpu_map *map, int idx, void *data) +static struct aggr_cpu_id perf_env__get_socket_aggr_by_cpu(struct perf_cpu cpu, void *data) { struct perf_env *env = data; - int cpu = perf_env__get_cpu(env, map, idx); - struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); + struct aggr_cpu_id id = aggr_cpu_id__empty(); - if (cpu != -1) - id.socket = env->cpu[cpu].socket_id; + if (cpu.cpu != -1) + id.socket = env->cpu[cpu.cpu].socket_id; return id; } -static struct aggr_cpu_id perf_env__get_die(struct perf_cpu_map *map, int idx, void *data) +static struct aggr_cpu_id perf_env__get_die_aggr_by_cpu(struct perf_cpu cpu, void *data) { struct perf_env *env = data; - struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); - int cpu = perf_env__get_cpu(env, map, idx); + struct aggr_cpu_id id = aggr_cpu_id__empty(); - if (cpu != -1) { + if (cpu.cpu != -1) { /* * die_id is relative to socket, so start * with the socket ID and then add die to * make a unique ID. */ - id.socket = env->cpu[cpu].socket_id; - id.die = env->cpu[cpu].die_id; + id.socket = env->cpu[cpu.cpu].socket_id; + id.die = env->cpu[cpu.cpu].die_id; } return id; } -static struct aggr_cpu_id perf_env__get_core(struct perf_cpu_map *map, int idx, void *data) +static struct aggr_cpu_id perf_env__get_core_aggr_by_cpu(struct perf_cpu cpu, void *data) { struct perf_env *env = data; - struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); - int cpu = perf_env__get_cpu(env, map, idx); + struct aggr_cpu_id id = aggr_cpu_id__empty(); - if (cpu != -1) { + if (cpu.cpu != -1) { /* * core_id is relative to socket and die, * we need a global id. So we set * socket, die id and core id */ - id.socket = env->cpu[cpu].socket_id; - id.die = env->cpu[cpu].die_id; - id.core = env->cpu[cpu].core_id; + id.socket = env->cpu[cpu.cpu].socket_id; + id.die = env->cpu[cpu.cpu].die_id; + id.core = env->cpu[cpu.cpu].core_id; } return id; } -static struct aggr_cpu_id perf_env__get_node(struct perf_cpu_map *map, int idx, void *data) +static struct aggr_cpu_id perf_env__get_node_aggr_by_cpu(struct perf_cpu cpu, void *data) { - int cpu = perf_env__get_cpu(data, map, idx); - struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); + struct aggr_cpu_id id = aggr_cpu_id__empty(); id.node = perf_env__numa_node(data, cpu); return id; } -static int perf_env__build_socket_map(struct perf_env *env, struct perf_cpu_map *cpus, - struct cpu_aggr_map **sockp) -{ - return cpu_map__build_map(cpus, sockp, perf_env__get_socket, env); -} - -static int perf_env__build_die_map(struct perf_env *env, struct perf_cpu_map *cpus, - struct cpu_aggr_map **diep) -{ - return cpu_map__build_map(cpus, diep, perf_env__get_die, env); -} - -static int perf_env__build_core_map(struct perf_env *env, struct perf_cpu_map *cpus, - struct cpu_aggr_map **corep) -{ - return cpu_map__build_map(cpus, corep, perf_env__get_core, env); -} - -static int perf_env__build_node_map(struct perf_env *env, struct perf_cpu_map *cpus, - struct cpu_aggr_map **nodep) -{ - return cpu_map__build_map(cpus, nodep, perf_env__get_node, env); -} - static struct aggr_cpu_id perf_stat__get_socket_file(struct perf_stat_config *config __maybe_unused, - struct perf_cpu_map *map, int idx) + struct perf_cpu cpu) { - return perf_env__get_socket(map, idx, &perf_stat.session->header.env); + return perf_env__get_socket_aggr_by_cpu(cpu, &perf_stat.session->header.env); } static struct aggr_cpu_id perf_stat__get_die_file(struct perf_stat_config *config __maybe_unused, - struct perf_cpu_map *map, int idx) + struct perf_cpu cpu) { - return perf_env__get_die(map, idx, &perf_stat.session->header.env); + return perf_env__get_die_aggr_by_cpu(cpu, &perf_stat.session->header.env); } static struct aggr_cpu_id perf_stat__get_core_file(struct perf_stat_config *config __maybe_unused, - struct perf_cpu_map *map, int idx) + struct perf_cpu cpu) { - return perf_env__get_core(map, idx, &perf_stat.session->header.env); + return perf_env__get_core_aggr_by_cpu(cpu, &perf_stat.session->header.env); } static struct aggr_cpu_id perf_stat__get_node_file(struct perf_stat_config *config __maybe_unused, - struct perf_cpu_map *map, int idx) + struct perf_cpu cpu) { - return perf_env__get_node(map, idx, &perf_stat.session->header.env); + return perf_env__get_node_aggr_by_cpu(cpu, &perf_stat.session->header.env); } -static int perf_stat_init_aggr_mode_file(struct perf_stat *st) +static aggr_cpu_id_get_t aggr_mode__get_aggr_file(enum aggr_mode aggr_mode) { - struct perf_env *env = &st->session->header.env; - - switch (stat_config.aggr_mode) { + switch (aggr_mode) { case AGGR_SOCKET: - if (perf_env__build_socket_map(env, evsel_list->core.cpus, &stat_config.aggr_map)) { - perror("cannot build socket map"); - return -1; - } - stat_config.aggr_get_id = perf_stat__get_socket_file; - break; + return perf_env__get_socket_aggr_by_cpu; case AGGR_DIE: - if (perf_env__build_die_map(env, evsel_list->core.cpus, &stat_config.aggr_map)) { - perror("cannot build die map"); - return -1; - } - stat_config.aggr_get_id = perf_stat__get_die_file; - break; + return perf_env__get_die_aggr_by_cpu; case AGGR_CORE: - if (perf_env__build_core_map(env, evsel_list->core.cpus, &stat_config.aggr_map)) { - perror("cannot build core map"); - return -1; - } - stat_config.aggr_get_id = perf_stat__get_core_file; - break; + return perf_env__get_core_aggr_by_cpu; case AGGR_NODE: - if (perf_env__build_node_map(env, evsel_list->core.cpus, &stat_config.aggr_map)) { - perror("cannot build core map"); - return -1; - } - stat_config.aggr_get_id = perf_stat__get_node_file; - break; + return perf_env__get_node_aggr_by_cpu; case AGGR_NONE: case AGGR_GLOBAL: case AGGR_THREAD: case AGGR_UNSET: default: - break; + return NULL; } +} +static aggr_get_id_t aggr_mode__get_id_file(enum aggr_mode aggr_mode) +{ + switch (aggr_mode) { + case AGGR_SOCKET: + return perf_stat__get_socket_file; + case AGGR_DIE: + return perf_stat__get_die_file; + case AGGR_CORE: + return perf_stat__get_core_file; + case AGGR_NODE: + return perf_stat__get_node_file; + case AGGR_NONE: + case AGGR_GLOBAL: + case AGGR_THREAD: + case AGGR_UNSET: + default: + return NULL; + } +} + +static int perf_stat_init_aggr_mode_file(struct perf_stat *st) +{ + struct perf_env *env = &st->session->header.env; + aggr_cpu_id_get_t get_id = aggr_mode__get_aggr_file(stat_config.aggr_mode); + + if (!get_id) + return 0; + + stat_config.aggr_map = cpu_aggr_map__new(evsel_list->core.cpus, get_id, env); + if (!stat_config.aggr_map) { + pr_err("cannot build %s map", aggr_mode__string[stat_config.aggr_mode]); + return -1; + } + stat_config.aggr_get_id = aggr_mode__get_id_file(stat_config.aggr_mode); return 0; } diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 273237a9c5e6..32844d8a0ea5 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -3964,6 +3964,9 @@ static int trace__run(struct trace *trace, int argc, const char **argv) evlist__add(evlist, pgfault_min); } + /* Enable ignoring missing threads when -u/-p option is defined. */ + trace->opts.ignore_missing_thread = trace->opts.target.uid != UINT_MAX || trace->opts.target.pid; + if (trace->sched && evlist__add_newtp(evlist, "sched", "sched_stat_runtime", trace__sched_stat_runtime)) goto out_error_sched_stat_runtime; diff --git a/tools/perf/dlfilters/dlfilter-test-api-v0.c b/tools/perf/dlfilters/dlfilter-test-api-v0.c index 7565a1852c74..b17eb52a0694 100644 --- a/tools/perf/dlfilters/dlfilter-test-api-v0.c +++ b/tools/perf/dlfilters/dlfilter-test-api-v0.c @@ -308,8 +308,6 @@ int filter_event_early(void *data, const struct perf_dlfilter_sample *sample, vo int filter_event(void *data, const struct perf_dlfilter_sample *sample, void *ctx) { - struct filter_data *d = data; - pr_debug("%s API\n", __func__); return do_checks(data, sample, ctx, false); diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/branch.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/branch.json new file mode 100644 index 000000000000..79f2016c53b0 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/branch.json @@ -0,0 +1,8 @@ +[ + { + "ArchStdEvent": "BR_MIS_PRED" + }, + { + "ArchStdEvent": "BR_PRED" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/bus.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/bus.json new file mode 100644 index 000000000000..579c1c993d17 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/bus.json @@ -0,0 +1,20 @@ +[ + { + "ArchStdEvent": "CPU_CYCLES" + }, + { + "ArchStdEvent": "BUS_ACCESS" + }, + { + "ArchStdEvent": "BUS_CYCLES" + }, + { + "ArchStdEvent": "BUS_ACCESS_RD" + }, + { + "ArchStdEvent": "BUS_ACCESS_WR" + }, + { + "ArchStdEvent": "CNT_CYCLES" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/cache.json new file mode 100644 index 000000000000..0141f749bff3 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/cache.json @@ -0,0 +1,155 @@ +[ + { + "ArchStdEvent": "L1I_CACHE_REFILL" + }, + { + "ArchStdEvent": "L1I_TLB_REFILL" + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL" + }, + { + "ArchStdEvent": "L1D_CACHE" + }, + { + "ArchStdEvent": "L1D_TLB_REFILL" + }, + { + "ArchStdEvent": "L1I_CACHE" + }, + { + "ArchStdEvent": "L1D_CACHE_WB" + }, + { + "ArchStdEvent": "L2D_CACHE" + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL" + }, + { + "ArchStdEvent": "L2D_CACHE_WB" + }, + { + "ArchStdEvent": "L2D_CACHE_ALLOCATE" + }, + { + "ArchStdEvent": "L1D_TLB" + }, + { + "ArchStdEvent": "L1I_TLB" + }, + { + "ArchStdEvent": "L3D_CACHE_ALLOCATE" + }, + { + "ArchStdEvent": "L3D_CACHE_REFILL" + }, + { + "ArchStdEvent": "L3D_CACHE" + }, + { + "ArchStdEvent": "L2D_TLB_REFILL" + }, + { + "ArchStdEvent": "L2D_TLB" + }, + { + "ArchStdEvent": "DTLB_WALK" + }, + { + "ArchStdEvent": "ITLB_WALK" + }, + { + "ArchStdEvent": "LL_CACHE_RD" + }, + { + "ArchStdEvent": "LL_CACHE_MISS_RD" + }, + { + "ArchStdEvent": "L1D_CACHE_LMISS_RD" + }, + { + "ArchStdEvent": "L1D_CACHE_RD" + }, + { + "ArchStdEvent": "L1D_CACHE_WR" + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_RD" + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_WR" + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_INNER" + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_OUTER" + }, + { + "ArchStdEvent": "L1D_CACHE_WB_VICTIM" + }, + { + "ArchStdEvent": "L1D_CACHE_WB_CLEAN" + }, + { + "ArchStdEvent": "L1D_CACHE_INVAL" + }, + { + "ArchStdEvent": "L1D_TLB_REFILL_RD" + }, + { + "ArchStdEvent": "L1D_TLB_REFILL_WR" + }, + { + "ArchStdEvent": "L1D_TLB_RD" + }, + { + "ArchStdEvent": "L1D_TLB_WR" + }, + { + "ArchStdEvent": "L2D_CACHE_RD" + }, + { + "ArchStdEvent": "L2D_CACHE_WR" + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_RD" + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_WR" + }, + { + "ArchStdEvent": "L2D_CACHE_WB_VICTIM" + }, + { + "ArchStdEvent": "L2D_CACHE_WB_CLEAN" + }, + { + "ArchStdEvent": "L2D_CACHE_INVAL" + }, + { + "ArchStdEvent": "L2D_TLB_REFILL_RD" + }, + { + "ArchStdEvent": "L2D_TLB_REFILL_WR" + }, + { + "ArchStdEvent": "L2D_TLB_RD" + }, + { + "ArchStdEvent": "L2D_TLB_WR" + }, + { + "ArchStdEvent": "L3D_CACHE_RD" + }, + { + "ArchStdEvent": "L1I_CACHE_LMISS" + }, + { + "ArchStdEvent": "L2D_CACHE_LMISS_RD" + }, + { + "ArchStdEvent": "L3D_CACHE_LMISS_RD" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/exception.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/exception.json new file mode 100644 index 000000000000..344a2d552ad5 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/exception.json @@ -0,0 +1,47 @@ +[ + { + "ArchStdEvent": "EXC_TAKEN" + }, + { + "ArchStdEvent": "MEMORY_ERROR" + }, + { + "ArchStdEvent": "EXC_UNDEF" + }, + { + "ArchStdEvent": "EXC_SVC" + }, + { + "ArchStdEvent": "EXC_PABORT" + }, + { + "ArchStdEvent": "EXC_DABORT" + }, + { + "ArchStdEvent": "EXC_IRQ" + }, + { + "ArchStdEvent": "EXC_FIQ" + }, + { + "ArchStdEvent": "EXC_SMC" + }, + { + "ArchStdEvent": "EXC_HVC" + }, + { + "ArchStdEvent": "EXC_TRAP_PABORT" + }, + { + "ArchStdEvent": "EXC_TRAP_DABORT" + }, + { + "ArchStdEvent": "EXC_TRAP_OTHER" + }, + { + "ArchStdEvent": "EXC_TRAP_IRQ" + }, + { + "ArchStdEvent": "EXC_TRAP_FIQ" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/instruction.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/instruction.json new file mode 100644 index 000000000000..e57cd55937c6 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/instruction.json @@ -0,0 +1,143 @@ +[ + { + "ArchStdEvent": "SW_INCR" + }, + { + "ArchStdEvent": "INST_RETIRED" + }, + { + "ArchStdEvent": "EXC_RETURN" + }, + { + "ArchStdEvent": "CID_WRITE_RETIRED" + }, + { + "ArchStdEvent": "INST_SPEC" + }, + { + "ArchStdEvent": "TTBR_WRITE_RETIRED" + }, + { + "ArchStdEvent": "BR_RETIRED" + }, + { + "ArchStdEvent": "BR_MIS_PRED_RETIRED" + }, + { + "ArchStdEvent": "OP_RETIRED" + }, + { + "ArchStdEvent": "OP_SPEC" + }, + { + "ArchStdEvent": "LDREX_SPEC" + }, + { + "ArchStdEvent": "STREX_PASS_SPEC" + }, + { + "ArchStdEvent": "STREX_FAIL_SPEC" + }, + { + "ArchStdEvent": "STREX_SPEC" + }, + { + "ArchStdEvent": "LD_SPEC" + }, + { + "ArchStdEvent": "ST_SPEC" + }, + { + "ArchStdEvent": "DP_SPEC" + }, + { + "ArchStdEvent": "ASE_SPEC" + }, + { + "ArchStdEvent": "VFP_SPEC" + }, + { + "ArchStdEvent": "PC_WRITE_SPEC" + }, + { + "ArchStdEvent": "CRYPTO_SPEC" + }, + { + "ArchStdEvent": "BR_IMMED_SPEC" + }, + { + "ArchStdEvent": "BR_RETURN_SPEC" + }, + { + "ArchStdEvent": "BR_INDIRECT_SPEC" + }, + { + "ArchStdEvent": "ISB_SPEC" + }, + { + "ArchStdEvent": "DSB_SPEC" + }, + { + "ArchStdEvent": "DMB_SPEC" + }, + { + "ArchStdEvent": "RC_LD_SPEC" + }, + { + "ArchStdEvent": "RC_ST_SPEC" + }, + { + "ArchStdEvent": "ASE_INST_SPEC" + }, + { + "ArchStdEvent": "SVE_INST_SPEC" + }, + { + "ArchStdEvent": "FP_HP_SPEC" + }, + { + "ArchStdEvent": "FP_SP_SPEC" + }, + { + "ArchStdEvent": "FP_DP_SPEC" + }, + { + "ArchStdEvent": "SVE_PRED_SPEC" + }, + { + "ArchStdEvent": "SVE_PRED_EMPTY_SPEC" + }, + { + "ArchStdEvent": "SVE_PRED_FULL_SPEC" + }, + { + "ArchStdEvent": "SVE_PRED_PARTIAL_SPEC" + }, + { + "ArchStdEvent": "SVE_PRED_NOT_FULL_SPEC" + }, + { + "ArchStdEvent": "SVE_LDFF_SPEC" + }, + { + "ArchStdEvent": "SVE_LDFF_FAULT_SPEC" + }, + { + "ArchStdEvent": "FP_SCALE_OPS_SPEC" + }, + { + "ArchStdEvent": "FP_FIXED_OPS_SPEC" + }, + { + "ArchStdEvent": "ASE_SVE_INT8_SPEC" + }, + { + "ArchStdEvent": "ASE_SVE_INT16_SPEC" + }, + { + "ArchStdEvent": "ASE_SVE_INT32_SPEC" + }, + { + "ArchStdEvent": "ASE_SVE_INT64_SPEC" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/memory.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/memory.json new file mode 100644 index 000000000000..e522113aeb96 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/memory.json @@ -0,0 +1,38 @@ +[ + { + "ArchStdEvent": "MEM_ACCESS" + }, + { + "ArchStdEvent": "MEM_ACCESS_RD" + }, + { + "ArchStdEvent": "MEM_ACCESS_WR" + }, + { + "ArchStdEvent": "UNALIGNED_LD_SPEC" + }, + { + "ArchStdEvent": "UNALIGNED_ST_SPEC" + }, + { + "ArchStdEvent": "UNALIGNED_LDST_SPEC" + }, + { + "ArchStdEvent": "LDST_ALIGN_LAT" + }, + { + "ArchStdEvent": "LD_ALIGN_LAT" + }, + { + "ArchStdEvent": "ST_ALIGN_LAT" + }, + { + "ArchStdEvent": "MEM_ACCESS_CHECKED" + }, + { + "ArchStdEvent": "MEM_ACCESS_CHECKED_RD" + }, + { + "ArchStdEvent": "MEM_ACCESS_CHECKED_WR" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/other.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/other.json new file mode 100644 index 000000000000..20d8365756c5 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/other.json @@ -0,0 +1,5 @@ +[ + { + "ArchStdEvent": "REMOTE_ACCESS" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/pipeline.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/pipeline.json new file mode 100644 index 000000000000..f9fae15f7555 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/pipeline.json @@ -0,0 +1,23 @@ +[ + { + "ArchStdEvent": "STALL_FRONTEND" + }, + { + "ArchStdEvent": "STALL_BACKEND" + }, + { + "ArchStdEvent": "STALL" + }, + { + "ArchStdEvent": "STALL_SLOT_BACKEND" + }, + { + "ArchStdEvent": "STALL_SLOT_FRONTEND" + }, + { + "ArchStdEvent": "STALL_SLOT" + }, + { + "ArchStdEvent": "STALL_BACKEND_MEM" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/spe.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/spe.json new file mode 100644 index 000000000000..20f2165c85fe --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/spe.json @@ -0,0 +1,14 @@ +[ + { + "ArchStdEvent": "SAMPLE_POP" + }, + { + "ArchStdEvent": "SAMPLE_FEED" + }, + { + "ArchStdEvent": "SAMPLE_FILTRATE" + }, + { + "ArchStdEvent": "SAMPLE_COLLISION" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/trace.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/trace.json new file mode 100644 index 000000000000..3116135c59e2 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/trace.json @@ -0,0 +1,29 @@ +[ + { + "ArchStdEvent": "TRB_WRAP" + }, + { + "ArchStdEvent": "TRCEXTOUT0" + }, + { + "ArchStdEvent": "TRCEXTOUT1" + }, + { + "ArchStdEvent": "TRCEXTOUT2" + }, + { + "ArchStdEvent": "TRCEXTOUT3" + }, + { + "ArchStdEvent": "CTI_TRIGOUT4" + }, + { + "ArchStdEvent": "CTI_TRIGOUT5" + }, + { + "ArchStdEvent": "CTI_TRIGOUT6" + }, + { + "ArchStdEvent": "CTI_TRIGOUT7" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/armv8-common-and-microarch.json b/tools/perf/pmu-events/arch/arm64/common-and-microarch.json similarity index 76% rename from tools/perf/pmu-events/arch/arm64/armv8-common-and-microarch.json rename to tools/perf/pmu-events/arch/arm64/common-and-microarch.json index 423767510aff..80d7a70829a0 100644 --- a/tools/perf/pmu-events/arch/arm64/armv8-common-and-microarch.json +++ b/tools/perf/pmu-events/arch/arm64/common-and-microarch.json @@ -299,6 +299,30 @@ "EventName": "STALL_SLOT", "BriefDescription": "No operation sent for execution on a slot" }, + { + "PublicDescription": "Sample Population", + "EventCode": "0x4000", + "EventName": "SAMPLE_POP", + "BriefDescription": "Sample Population" + }, + { + "PublicDescription": "Sample Taken", + "EventCode": "0x4001", + "EventName": "SAMPLE_FEED", + "BriefDescription": "Sample Taken" + }, + { + "PublicDescription": "Sample Taken and not removed by filtering", + "EventCode": "0x4002", + "EventName": "SAMPLE_FILTRATE", + "BriefDescription": "Sample Taken and not removed by filtering" + }, + { + "PublicDescription": "Sample collided with previous sample", + "EventCode": "0x4003", + "EventName": "SAMPLE_COLLISION", + "BriefDescription": "Sample collided with previous sample" + }, { "PublicDescription": "Constant frequency cycles. The counter increments at a constant frequency equal to the rate of increment of the system counter, CNTPCT_EL0.", "EventCode": "0x4004", @@ -329,6 +353,96 @@ "EventName": "L3D_CACHE_LMISS_RD", "BriefDescription": "Level 3 data cache long-latency read miss" }, + { + "PublicDescription": "Trace buffer current write pointer wrapped", + "EventCode": "0x400C", + "EventName": "TRB_WRAP", + "BriefDescription": "Trace buffer current write pointer wrapped" + }, + { + "PublicDescription": "PE Trace Unit external output 0", + "EventCode": "0x4010", + "EventName": "TRCEXTOUT0", + "BriefDescription": "PE Trace Unit external output 0" + }, + { + "PublicDescription": "PE Trace Unit external output 1", + "EventCode": "0x4011", + "EventName": "TRCEXTOUT1", + "BriefDescription": "PE Trace Unit external output 1" + }, + { + "PublicDescription": "PE Trace Unit external output 2", + "EventCode": "0x4012", + "EventName": "TRCEXTOUT2", + "BriefDescription": "PE Trace Unit external output 2" + }, + { + "PublicDescription": "PE Trace Unit external output 3", + "EventCode": "0x4013", + "EventName": "TRCEXTOUT3", + "BriefDescription": "PE Trace Unit external output 3" + }, + { + "PublicDescription": "Cross-trigger Interface output trigger 4", + "EventCode": "0x4018", + "EventName": "CTI_TRIGOUT4", + "BriefDescription": "Cross-trigger Interface output trigger 4" + }, + { + "PublicDescription": "Cross-trigger Interface output trigger 5 ", + "EventCode": "0x4019", + "EventName": "CTI_TRIGOUT5", + "BriefDescription": "Cross-trigger Interface output trigger 5 " + }, + { + "PublicDescription": "Cross-trigger Interface output trigger 6", + "EventCode": "0x401A", + "EventName": "CTI_TRIGOUT6", + "BriefDescription": "Cross-trigger Interface output trigger 6" + }, + { + "PublicDescription": "Cross-trigger Interface output trigger 7", + "EventCode": "0x401B", + "EventName": "CTI_TRIGOUT7", + "BriefDescription": "Cross-trigger Interface output trigger 7" + }, + { + "PublicDescription": "Access with additional latency from alignment", + "EventCode": "0x4020", + "EventName": "LDST_ALIGN_LAT", + "BriefDescription": "Access with additional latency from alignment" + }, + { + "PublicDescription": "Load with additional latency from alignment", + "EventCode": "0x4021", + "EventName": "LD_ALIGN_LAT", + "BriefDescription": "Load with additional latency from alignment" + }, + { + "PublicDescription": "Store with additional latency from alignment", + "EventCode": "0x4022", + "EventName": "ST_ALIGN_LAT", + "BriefDescription": "Store with additional latency from alignment" + }, + { + "PublicDescription": "Checked data memory access", + "EventCode": "0x4024", + "EventName": "MEM_ACCESS_CHECKED", + "BriefDescription": "Checked data memory access" + }, + { + "PublicDescription": "Checked data memory access, read", + "EventCode": "0x4025", + "EventName": "MEM_ACCESS_CHECKED_RD", + "BriefDescription": "Checked data memory access, read" + }, + { + "PublicDescription": "Checked data memory access, write", + "EventCode": "0x4026", + "EventName": "MEM_ACCESS_CHECKED_WR", + "BriefDescription": "Checked data memory access, write" + }, { "PublicDescription": "SIMD Instruction architecturally executed.", "EventCode": "0x8000", @@ -341,6 +455,18 @@ "EventName": "SVE_INST_RETIRED", "BriefDescription": "Instruction architecturally executed, SVE." }, + { + "PublicDescription": "ASE operations speculatively executed", + "EventCode": "0x8005", + "EventName": "ASE_INST_SPEC", + "BriefDescription": "ASE operations speculatively executed" + }, + { + "PublicDescription": "SVE operations speculatively executed", + "EventCode": "0x8006", + "EventName": "SVE_INST_SPEC", + "BriefDescription": "SVE operations speculatively executed" + }, { "PublicDescription": "Microarchitectural operation, Operations speculatively executed.", "EventCode": "0x8008", @@ -359,6 +485,24 @@ "EventName": "FP_SPEC", "BriefDescription": "Floating-point Operations speculatively executed." }, + { + "PublicDescription": "Floating-point half-precision operations speculatively executed", + "EventCode": "0x8014", + "EventName": "FP_HP_SPEC", + "BriefDescription": "Floating-point half-precision operations speculatively executed" + }, + { + "PublicDescription": "Floating-point single-precision operations speculatively executed", + "EventCode": "0x8018", + "EventName": "FP_SP_SPEC", + "BriefDescription": "Floating-point single-precision operations speculatively executed" + }, + { + "PublicDescription": "Floating-point double-precision operations speculatively executed", + "EventCode": "0x801C", + "EventName": "FP_DP_SPEC", + "BriefDescription": "Floating-point double-precision operations speculatively executed" + }, { "PublicDescription": "Floating-point FMA Operations speculatively executed.", "EventCode": "0x8028", @@ -389,6 +533,30 @@ "EventName": "SVE_PRED_SPEC", "BriefDescription": "SVE predicated Operations speculatively executed." }, + { + "PublicDescription": "SVE predicated operations with no active predicates speculatively executed", + "EventCode": "0x8075", + "EventName": "SVE_PRED_EMPTY_SPEC", + "BriefDescription": "SVE predicated operations with no active predicates speculatively executed" + }, + { + "PublicDescription": "SVE predicated operations speculatively executed with all active predicates", + "EventCode": "0x8076", + "EventName": "SVE_PRED_FULL_SPEC", + "BriefDescription": "SVE predicated operations speculatively executed with all active predicates" + }, + { + "PublicDescription": "SVE predicated operations speculatively executed with partially active predicates", + "EventCode": "0x8077", + "EventName": "SVE_PRED_PARTIAL_SPEC", + "BriefDescription": "SVE predicated operations speculatively executed with partially active predicates" + }, + { + "PublicDescription": "SVE predicated operations with empty or partially active predicates", + "EventCode": "0x8079", + "EventName": "SVE_PRED_NOT_FULL_SPEC", + "BriefDescription": "SVE predicated operations with empty or partially active predicates" + }, { "PublicDescription": "SVE MOVPRFX Operations speculatively executed.", "EventCode": "0x807C", @@ -497,6 +665,12 @@ "EventName": "SVE_LDFF_SPEC", "BriefDescription": "SVE First-fault load Operations speculatively executed." }, + { + "PublicDescription": "SVE first-fault load operations speculatively executed which set FFR bit to 0", + "EventCode": "0x80BD", + "EventName": "SVE_LDFF_FAULT_SPEC", + "BriefDescription": "SVE first-fault load operations speculatively executed which set FFR bit to 0" + }, { "PublicDescription": "Scalable floating-point element Operations speculatively executed.", "EventCode": "0x80C0", @@ -544,5 +718,29 @@ "EventCode": "0x80C7", "EventName": "FP_DP_FIXED_OPS_SPEC", "BriefDescription": "Non-scalable double-precision floating-point element Operations speculatively executed." + }, + { + "PublicDescription": "Advanced SIMD and SVE 8-bit integer operations speculatively executed", + "EventCode": "0x80E3", + "EventName": "ASE_SVE_INT8_SPEC", + "BriefDescription": "Advanced SIMD and SVE 8-bit integer operations speculatively executed" + }, + { + "PublicDescription": "Advanced SIMD and SVE 16-bit integer operations speculatively executed", + "EventCode": "0x80E7", + "EventName": "ASE_SVE_INT16_SPEC", + "BriefDescription": "Advanced SIMD and SVE 16-bit integer operations speculatively executed" + }, + { + "PublicDescription": "Advanced SIMD and SVE 32-bit integer operations speculatively executed", + "EventCode": "0x80EB", + "EventName": "ASE_SVE_INT32_SPEC", + "BriefDescription": "Advanced SIMD and SVE 32-bit integer operations speculatively executed" + }, + { + "PublicDescription": "Advanced SIMD and SVE 64-bit integer operations speculatively executed", + "EventCode": "0x80EF", + "EventName": "ASE_SVE_INT64_SPEC", + "BriefDescription": "Advanced SIMD and SVE 64-bit integer operations speculatively executed" } ] diff --git a/tools/perf/pmu-events/arch/arm64/mapfile.csv b/tools/perf/pmu-events/arch/arm64/mapfile.csv index 31d8b57ca9bb..b899db48c12a 100644 --- a/tools/perf/pmu-events/arch/arm64/mapfile.csv +++ b/tools/perf/pmu-events/arch/arm64/mapfile.csv @@ -19,6 +19,7 @@ 0x00000000410fd0b0,v1,arm/cortex-a76-n1,core 0x00000000410fd0c0,v1,arm/cortex-a76-n1,core 0x00000000410fd400,v1,arm/neoverse-v1,core +0x00000000410fd490,v1,arm/neoverse-n2,core 0x00000000420f5160,v1,cavium/thunderx2,core 0x00000000430f0af0,v1,cavium/thunderx2,core 0x00000000460f0010,v1,fujitsu/a64fx,core diff --git a/tools/perf/pmu-events/arch/arm64/armv8-recommended.json b/tools/perf/pmu-events/arch/arm64/recommended.json similarity index 96% rename from tools/perf/pmu-events/arch/arm64/armv8-recommended.json rename to tools/perf/pmu-events/arch/arm64/recommended.json index d0a19866563d..210afa856091 100644 --- a/tools/perf/pmu-events/arch/arm64/armv8-recommended.json +++ b/tools/perf/pmu-events/arch/arm64/recommended.json @@ -148,305 +148,305 @@ "EventCode": "0x60", "EventName": "BUS_ACCESS_RD", "BriefDescription": "Bus access read" - }, - { + }, + { "PublicDescription": "Bus access write", "EventCode": "0x61", "EventName": "BUS_ACCESS_WR", "BriefDescription": "Bus access write" - }, - { + }, + { "PublicDescription": "Bus access, Normal, Cacheable, Shareable", "EventCode": "0x62", "EventName": "BUS_ACCESS_SHARED", "BriefDescription": "Bus access, Normal, Cacheable, Shareable" - }, - { + }, + { "PublicDescription": "Bus access, not Normal, Cacheable, Shareable", "EventCode": "0x63", "EventName": "BUS_ACCESS_NOT_SHARED", "BriefDescription": "Bus access, not Normal, Cacheable, Shareable" - }, - { + }, + { "PublicDescription": "Bus access, Normal", "EventCode": "0x64", "EventName": "BUS_ACCESS_NORMAL", "BriefDescription": "Bus access, Normal" - }, - { + }, + { "PublicDescription": "Bus access, peripheral", "EventCode": "0x65", "EventName": "BUS_ACCESS_PERIPH", "BriefDescription": "Bus access, peripheral" - }, - { + }, + { "PublicDescription": "Data memory access, read", "EventCode": "0x66", "EventName": "MEM_ACCESS_RD", "BriefDescription": "Data memory access, read" - }, - { + }, + { "PublicDescription": "Data memory access, write", "EventCode": "0x67", "EventName": "MEM_ACCESS_WR", "BriefDescription": "Data memory access, write" - }, - { + }, + { "PublicDescription": "Unaligned access, read", "EventCode": "0x68", "EventName": "UNALIGNED_LD_SPEC", "BriefDescription": "Unaligned access, read" - }, - { + }, + { "PublicDescription": "Unaligned access, write", "EventCode": "0x69", "EventName": "UNALIGNED_ST_SPEC", "BriefDescription": "Unaligned access, write" - }, - { + }, + { "PublicDescription": "Unaligned access", "EventCode": "0x6a", "EventName": "UNALIGNED_LDST_SPEC", "BriefDescription": "Unaligned access" - }, - { + }, + { "PublicDescription": "Exclusive operation speculatively executed, LDREX or LDX", "EventCode": "0x6c", "EventName": "LDREX_SPEC", "BriefDescription": "Exclusive operation speculatively executed, LDREX or LDX" - }, - { + }, + { "PublicDescription": "Exclusive operation speculatively executed, STREX or STX pass", "EventCode": "0x6d", "EventName": "STREX_PASS_SPEC", "BriefDescription": "Exclusive operation speculatively executed, STREX or STX pass" - }, - { + }, + { "PublicDescription": "Exclusive operation speculatively executed, STREX or STX fail", "EventCode": "0x6e", "EventName": "STREX_FAIL_SPEC", "BriefDescription": "Exclusive operation speculatively executed, STREX or STX fail" - }, - { + }, + { "PublicDescription": "Exclusive operation speculatively executed, STREX or STX", "EventCode": "0x6f", "EventName": "STREX_SPEC", "BriefDescription": "Exclusive operation speculatively executed, STREX or STX" - }, - { + }, + { "PublicDescription": "Operation speculatively executed, load", "EventCode": "0x70", "EventName": "LD_SPEC", "BriefDescription": "Operation speculatively executed, load" - }, - { + }, + { "PublicDescription": "Operation speculatively executed, store", "EventCode": "0x71", "EventName": "ST_SPEC", "BriefDescription": "Operation speculatively executed, store" - }, - { + }, + { "PublicDescription": "Operation speculatively executed, load or store", "EventCode": "0x72", "EventName": "LDST_SPEC", "BriefDescription": "Operation speculatively executed, load or store" - }, - { + }, + { "PublicDescription": "Operation speculatively executed, integer data processing", "EventCode": "0x73", "EventName": "DP_SPEC", "BriefDescription": "Operation speculatively executed, integer data processing" - }, - { + }, + { "PublicDescription": "Operation speculatively executed, Advanced SIMD instruction", "EventCode": "0x74", "EventName": "ASE_SPEC", "BriefDescription": "Operation speculatively executed, Advanced SIMD instruction" - }, - { + }, + { "PublicDescription": "Operation speculatively executed, floating-point instruction", "EventCode": "0x75", "EventName": "VFP_SPEC", "BriefDescription": "Operation speculatively executed, floating-point instruction" - }, - { + }, + { "PublicDescription": "Operation speculatively executed, software change of the PC", "EventCode": "0x76", "EventName": "PC_WRITE_SPEC", "BriefDescription": "Operation speculatively executed, software change of the PC" - }, - { + }, + { "PublicDescription": "Operation speculatively executed, Cryptographic instruction", "EventCode": "0x77", "EventName": "CRYPTO_SPEC", "BriefDescription": "Operation speculatively executed, Cryptographic instruction" - }, - { + }, + { "PublicDescription": "Branch speculatively executed, immediate branch", "EventCode": "0x78", "EventName": "BR_IMMED_SPEC", "BriefDescription": "Branch speculatively executed, immediate branch" - }, - { + }, + { "PublicDescription": "Branch speculatively executed, procedure return", "EventCode": "0x79", "EventName": "BR_RETURN_SPEC", "BriefDescription": "Branch speculatively executed, procedure return" - }, - { + }, + { "PublicDescription": "Branch speculatively executed, indirect branch", "EventCode": "0x7a", "EventName": "BR_INDIRECT_SPEC", "BriefDescription": "Branch speculatively executed, indirect branch" - }, - { + }, + { "PublicDescription": "Barrier speculatively executed, ISB", "EventCode": "0x7c", "EventName": "ISB_SPEC", "BriefDescription": "Barrier speculatively executed, ISB" - }, - { + }, + { "PublicDescription": "Barrier speculatively executed, DSB", "EventCode": "0x7d", "EventName": "DSB_SPEC", "BriefDescription": "Barrier speculatively executed, DSB" - }, - { + }, + { "PublicDescription": "Barrier speculatively executed, DMB", "EventCode": "0x7e", "EventName": "DMB_SPEC", "BriefDescription": "Barrier speculatively executed, DMB" - }, - { + }, + { "PublicDescription": "Exception taken, Other synchronous", "EventCode": "0x81", "EventName": "EXC_UNDEF", "BriefDescription": "Exception taken, Other synchronous" - }, - { + }, + { "PublicDescription": "Exception taken, Supervisor Call", "EventCode": "0x82", "EventName": "EXC_SVC", "BriefDescription": "Exception taken, Supervisor Call" - }, - { + }, + { "PublicDescription": "Exception taken, Instruction Abort", "EventCode": "0x83", "EventName": "EXC_PABORT", "BriefDescription": "Exception taken, Instruction Abort" - }, - { + }, + { "PublicDescription": "Exception taken, Data Abort and SError", "EventCode": "0x84", "EventName": "EXC_DABORT", "BriefDescription": "Exception taken, Data Abort and SError" - }, - { + }, + { "PublicDescription": "Exception taken, IRQ", "EventCode": "0x86", "EventName": "EXC_IRQ", "BriefDescription": "Exception taken, IRQ" - }, - { + }, + { "PublicDescription": "Exception taken, FIQ", "EventCode": "0x87", "EventName": "EXC_FIQ", "BriefDescription": "Exception taken, FIQ" - }, - { + }, + { "PublicDescription": "Exception taken, Secure Monitor Call", "EventCode": "0x88", "EventName": "EXC_SMC", "BriefDescription": "Exception taken, Secure Monitor Call" - }, - { + }, + { "PublicDescription": "Exception taken, Hypervisor Call", "EventCode": "0x8a", "EventName": "EXC_HVC", "BriefDescription": "Exception taken, Hypervisor Call" - }, - { + }, + { "PublicDescription": "Exception taken, Instruction Abort not taken locally", "EventCode": "0x8b", "EventName": "EXC_TRAP_PABORT", "BriefDescription": "Exception taken, Instruction Abort not taken locally" - }, - { + }, + { "PublicDescription": "Exception taken, Data Abort or SError not taken locally", "EventCode": "0x8c", "EventName": "EXC_TRAP_DABORT", "BriefDescription": "Exception taken, Data Abort or SError not taken locally" - }, - { + }, + { "PublicDescription": "Exception taken, Other traps not taken locally", "EventCode": "0x8d", "EventName": "EXC_TRAP_OTHER", "BriefDescription": "Exception taken, Other traps not taken locally" - }, - { + }, + { "PublicDescription": "Exception taken, IRQ not taken locally", "EventCode": "0x8e", "EventName": "EXC_TRAP_IRQ", "BriefDescription": "Exception taken, IRQ not taken locally" - }, - { + }, + { "PublicDescription": "Exception taken, FIQ not taken locally", "EventCode": "0x8f", "EventName": "EXC_TRAP_FIQ", "BriefDescription": "Exception taken, FIQ not taken locally" - }, - { + }, + { "PublicDescription": "Release consistency operation speculatively executed, Load-Acquire", "EventCode": "0x90", "EventName": "RC_LD_SPEC", "BriefDescription": "Release consistency operation speculatively executed, Load-Acquire" - }, - { + }, + { "PublicDescription": "Release consistency operation speculatively executed, Store-Release", "EventCode": "0x91", "EventName": "RC_ST_SPEC", "BriefDescription": "Release consistency operation speculatively executed, Store-Release" - }, - { + }, + { "PublicDescription": "Attributable Level 3 data or unified cache access, read", "EventCode": "0xa0", "EventName": "L3D_CACHE_RD", "BriefDescription": "Attributable Level 3 data or unified cache access, read" - }, - { + }, + { "PublicDescription": "Attributable Level 3 data or unified cache access, write", "EventCode": "0xa1", "EventName": "L3D_CACHE_WR", "BriefDescription": "Attributable Level 3 data or unified cache access, write" - }, - { + }, + { "PublicDescription": "Attributable Level 3 data or unified cache refill, read", "EventCode": "0xa2", "EventName": "L3D_CACHE_REFILL_RD", "BriefDescription": "Attributable Level 3 data or unified cache refill, read" - }, - { + }, + { "PublicDescription": "Attributable Level 3 data or unified cache refill, write", "EventCode": "0xa3", "EventName": "L3D_CACHE_REFILL_WR", "BriefDescription": "Attributable Level 3 data or unified cache refill, write" - }, - { + }, + { "PublicDescription": "Attributable Level 3 data or unified cache Write-Back, victim", "EventCode": "0xa6", "EventName": "L3D_CACHE_WB_VICTIM", "BriefDescription": "Attributable Level 3 data or unified cache Write-Back, victim" - }, - { + }, + { "PublicDescription": "Attributable Level 3 data or unified cache Write-Back, cache clean", "EventCode": "0xa7", "EventName": "L3D_CACHE_WB_CLEAN", "BriefDescription": "Attributable Level 3 data or unified cache Write-Back, cache clean" - }, - { + }, + { "PublicDescription": "Attributable Level 3 data or unified cache access, invalidate", "EventCode": "0xa8", "EventName": "L3D_CACHE_INVAL", "BriefDescription": "Attributable Level 3 data or unified cache access, invalidate" - } + } ] diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index 2e7c4153875b..1a57c3f81dd4 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -672,8 +672,6 @@ static int json_events(const char *fn, addfield(map, &je.metric_constraint, "", "", val); } else if (json_streq(map, field, "MetricExpr")) { addfield(map, &je.metric_expr, "", "", val); - for (s = je.metric_expr; *s; s++) - *s = tolower(*s); } else if (json_streq(map, field, "ArchStdEvent")) { addfield(map, &arch_std, "", "", val); for (s = arch_std; *s; s++) diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index 803ca426f8e6..af2b37ef7c70 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -65,6 +65,7 @@ perf-y += pe-file-parsing.o perf-y += expand-cgroup.o perf-y += perf-time-to-tsc.o perf-y += dlfilter-test.o +perf-y += sigtrap.o $(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build $(call rule_mkdir) diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c index 0f73e300f207..56fba08a3037 100644 --- a/tools/perf/tests/attr.c +++ b/tools/perf/tests/attr.c @@ -65,7 +65,7 @@ do { \ #define WRITE_ASS(field, fmt) __WRITE_ASS(field, fmt, attr->field) -static int store_event(struct perf_event_attr *attr, pid_t pid, int cpu, +static int store_event(struct perf_event_attr *attr, pid_t pid, struct perf_cpu cpu, int fd, int group_fd, unsigned long flags) { FILE *file; @@ -93,7 +93,7 @@ static int store_event(struct perf_event_attr *attr, pid_t pid, int cpu, /* syscall arguments */ __WRITE_ASS(fd, "d", fd); __WRITE_ASS(group_fd, "d", group_fd); - __WRITE_ASS(cpu, "d", cpu); + __WRITE_ASS(cpu, "d", cpu.cpu); __WRITE_ASS(pid, "d", pid); __WRITE_ASS(flags, "lu", flags); @@ -144,7 +144,7 @@ static int store_event(struct perf_event_attr *attr, pid_t pid, int cpu, return 0; } -void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu, +void test_attr__open(struct perf_event_attr *attr, pid_t pid, struct perf_cpu cpu, int fd, int group_fd, unsigned long flags) { int errno_saved = errno; diff --git a/tools/perf/tests/bitmap.c b/tools/perf/tests/bitmap.c index 384856347236..0bf399c49849 100644 --- a/tools/perf/tests/bitmap.c +++ b/tools/perf/tests/bitmap.c @@ -18,7 +18,7 @@ static unsigned long *get_bitmap(const char *str, int nbits) if (map && bm) { for (i = 0; i < map->nr; i++) - set_bit(map->map[i], bm); + set_bit(map->map[i].cpu, bm); } if (map) diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index 8cb5a1c3489e..fac3717d9ba1 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -107,6 +107,7 @@ static struct test_suite *generic_tests[] = { &suite__expand_cgroup_events, &suite__perf_time_to_tsc, &suite__dlfilter, + &suite__sigtrap, NULL, }; @@ -420,7 +421,7 @@ static int run_shell_tests(int argc, const char *argv[], int i, int width, continue; st.file = ent->d_name; - pr_info("%2d: %-*s:", i, width, test_suite.desc); + pr_info("%3d: %-*s:", i, width, test_suite.desc); if (intlist__find(skiplist, i)) { color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (user override)\n"); @@ -470,7 +471,7 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist) continue; } - pr_info("%2d: %-*s:", i, width, test_description(t, -1)); + pr_info("%3d: %-*s:", i, width, test_description(t, -1)); if (intlist__find(skiplist, i)) { color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (user override)\n"); @@ -510,7 +511,7 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist) curr, argc, argv)) continue; - pr_info("%2d.%1d: %-*s:", i, subi + 1, subw, + pr_info("%3d.%1d: %-*s:", i, subi + 1, subw, test_description(t, subi)); test_and_print(t, subi); } @@ -545,7 +546,7 @@ static int perf_test__list_shell(int argc, const char **argv, int i) if (!perf_test__matches(t.desc, curr, argc, argv)) continue; - pr_info("%2d: %s\n", i, t.desc); + pr_info("%3d: %s\n", i, t.desc); } @@ -567,14 +568,14 @@ static int perf_test__list(int argc, const char **argv) if (!perf_test__matches(test_description(t, -1), curr, argc, argv)) continue; - pr_info("%2d: %s\n", i, test_description(t, -1)); + pr_info("%3d: %s\n", i, test_description(t, -1)); if (has_subtests(t)) { int subn = num_subtests(t); int subi; for (subi = 0; subi < subn; subi++) - pr_info("%2d:%1d: %s\n", i, subi + 1, + pr_info("%3d:%1d: %s\n", i, subi + 1, test_description(t, subi)); } } @@ -606,6 +607,9 @@ int cmd_test(int argc, const char **argv) if (ret < 0) return ret; + /* Unbuffered output */ + setvbuf(stdout, NULL, _IONBF, 0); + argc = parse_options_subcommand(argc, argv, test_options, test_subcommands, test_usage, 0); if (argc >= 1 && !strcmp(argv[0], "list")) return perf_test__list(argc - 1, argv + 1); diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c index 89a155092f85..84e87e31f119 100644 --- a/tools/perf/tests/cpumap.c +++ b/tools/perf/tests/cpumap.c @@ -38,7 +38,7 @@ static int process_event_mask(struct perf_tool *tool __maybe_unused, TEST_ASSERT_VAL("wrong nr", map->nr == 20); for (i = 0; i < 20; i++) { - TEST_ASSERT_VAL("wrong cpu", map->map[i] == i); + TEST_ASSERT_VAL("wrong cpu", map->map[i].cpu == i); } perf_cpu_map__put(map); @@ -67,8 +67,8 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused, map = cpu_map__new_data(data); TEST_ASSERT_VAL("wrong nr", map->nr == 2); - TEST_ASSERT_VAL("wrong cpu", map->map[0] == 1); - TEST_ASSERT_VAL("wrong cpu", map->map[1] == 256); + TEST_ASSERT_VAL("wrong cpu", map->map[0].cpu == 1); + TEST_ASSERT_VAL("wrong cpu", map->map[1].cpu == 256); TEST_ASSERT_VAL("wrong refcnt", refcount_read(&map->refcnt) == 1); perf_cpu_map__put(map); return 0; diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c index d01532d40acb..16b6d6f47f38 100644 --- a/tools/perf/tests/event_update.c +++ b/tools/perf/tests/event_update.c @@ -76,9 +76,9 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused, TEST_ASSERT_VAL("wrong id", ev->id == 123); TEST_ASSERT_VAL("wrong type", ev->type == PERF_EVENT_UPDATE__CPUS); TEST_ASSERT_VAL("wrong cpus", map->nr == 3); - TEST_ASSERT_VAL("wrong cpus", map->map[0] == 1); - TEST_ASSERT_VAL("wrong cpus", map->map[1] == 2); - TEST_ASSERT_VAL("wrong cpus", map->map[2] == 3); + TEST_ASSERT_VAL("wrong cpus", map->map[0].cpu == 1); + TEST_ASSERT_VAL("wrong cpus", map->map[1].cpu == 2); + TEST_ASSERT_VAL("wrong cpus", map->map[2].cpu == 3); perf_cpu_map__put(map); return 0; } diff --git a/tools/perf/tests/mem2node.c b/tools/perf/tests/mem2node.c index b17b86391383..f4a4aba33f76 100644 --- a/tools/perf/tests/mem2node.c +++ b/tools/perf/tests/mem2node.c @@ -31,7 +31,7 @@ static unsigned long *get_bitmap(const char *str, int nbits) if (map && bm) { for (i = 0; i < map->nr; i++) { - set_bit(map->map[i], bm); + set_bit(map->map[i].cpu, bm); } } diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c index 90b2feda31ac..0ad62914b4d7 100644 --- a/tools/perf/tests/mmap-basic.c +++ b/tools/perf/tests/mmap-basic.c @@ -59,11 +59,11 @@ static int test__basic_mmap(struct test_suite *test __maybe_unused, int subtest } CPU_ZERO(&cpu_set); - CPU_SET(cpus->map[0], &cpu_set); + CPU_SET(cpus->map[0].cpu, &cpu_set); sched_setaffinity(0, sizeof(cpu_set), &cpu_set); if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) { pr_debug("sched_setaffinity() failed on CPU %d: %s ", - cpus->map[0], str_error_r(errno, sbuf, sizeof(sbuf))); + cpus->map[0].cpu, str_error_r(errno, sbuf, sizeof(sbuf))); goto out_free_cpus; } diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c index cd3dd463783f..1ab362323d25 100644 --- a/tools/perf/tests/openat-syscall-all-cpus.c +++ b/tools/perf/tests/openat-syscall-all-cpus.c @@ -22,7 +22,8 @@ static int test__openat_syscall_event_on_all_cpus(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { - int err = -1, fd, cpu; + int err = -1, fd, idx; + struct perf_cpu cpu; struct perf_cpu_map *cpus; struct evsel *evsel; unsigned int nr_openat_calls = 111, i; @@ -58,23 +59,23 @@ static int test__openat_syscall_event_on_all_cpus(struct test_suite *test __mayb goto out_evsel_delete; } - for (cpu = 0; cpu < cpus->nr; ++cpu) { - unsigned int ncalls = nr_openat_calls + cpu; + perf_cpu_map__for_each_cpu(cpu, idx, cpus) { + unsigned int ncalls = nr_openat_calls + idx; /* * XXX eventually lift this restriction in a way that * keeps perf building on older glibc installations * without CPU_ALLOC. 1024 cpus in 2010 still seems * a reasonable upper limit tho :-) */ - if (cpus->map[cpu] >= CPU_SETSIZE) { - pr_debug("Ignoring CPU %d\n", cpus->map[cpu]); + if (cpu.cpu >= CPU_SETSIZE) { + pr_debug("Ignoring CPU %d\n", cpu.cpu); continue; } - CPU_SET(cpus->map[cpu], &cpu_set); + CPU_SET(cpu.cpu, &cpu_set); if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) { pr_debug("sched_setaffinity() failed on CPU %d: %s ", - cpus->map[cpu], + cpu.cpu, str_error_r(errno, sbuf, sizeof(sbuf))); goto out_close_fd; } @@ -82,37 +83,29 @@ static int test__openat_syscall_event_on_all_cpus(struct test_suite *test __mayb fd = openat(0, "/etc/passwd", O_RDONLY); close(fd); } - CPU_CLR(cpus->map[cpu], &cpu_set); + CPU_CLR(cpu.cpu, &cpu_set); } - /* - * Here we need to explicitly preallocate the counts, as if - * we use the auto allocation it will allocate just for 1 cpu, - * as we start by cpu 0. - */ - if (evsel__alloc_counts(evsel, cpus->nr, 1) < 0) { - pr_debug("evsel__alloc_counts(ncpus=%d)\n", cpus->nr); - goto out_close_fd; - } + evsel->core.cpus = perf_cpu_map__get(cpus); err = 0; - for (cpu = 0; cpu < cpus->nr; ++cpu) { + perf_cpu_map__for_each_cpu(cpu, idx, cpus) { unsigned int expected; - if (cpus->map[cpu] >= CPU_SETSIZE) + if (cpu.cpu >= CPU_SETSIZE) continue; - if (evsel__read_on_cpu(evsel, cpu, 0) < 0) { + if (evsel__read_on_cpu(evsel, idx, 0) < 0) { pr_debug("evsel__read_on_cpu\n"); err = -1; break; } - expected = nr_openat_calls + cpu; - if (perf_counts(evsel->counts, cpu, 0)->val != expected) { + expected = nr_openat_calls + idx; + if (perf_counts(evsel->counts, idx, 0)->val != expected) { pr_debug("evsel__read_on_cpu: expected to intercept %d calls on cpu %d, got %" PRIu64 "\n", - expected, cpus->map[cpu], perf_counts(evsel->counts, cpu, 0)->val); + expected, cpu.cpu, perf_counts(evsel->counts, idx, 0)->val); err = -1; } } diff --git a/tools/perf/tests/shell/stat_all_metricgroups.sh b/tools/perf/tests/shell/stat_all_metricgroups.sh index de24d374ce24..cb35e488809a 100755 --- a/tools/perf/tests/shell/stat_all_metricgroups.sh +++ b/tools/perf/tests/shell/stat_all_metricgroups.sh @@ -6,7 +6,7 @@ set -e for m in $(perf list --raw-dump metricgroups); do echo "Testing $m" - perf stat -M "$m" true + perf stat -M "$m" -a true done exit 0 diff --git a/tools/perf/tests/sigtrap.c b/tools/perf/tests/sigtrap.c new file mode 100644 index 000000000000..1f147fe6595f --- /dev/null +++ b/tools/perf/tests/sigtrap.c @@ -0,0 +1,177 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Basic test for sigtrap support. + * + * Copyright (C) 2021, Google LLC. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "cloexec.h" +#include "debug.h" +#include "event.h" +#include "tests.h" +#include "../perf-sys.h" + +/* + * PowerPC and S390 do not support creation of instruction breakpoints using the + * perf_event interface. + * + * Just disable the test for these architectures until these issues are + * resolved. + */ +#if defined(__powerpc__) || defined(__s390x__) +#define BP_ACCOUNT_IS_SUPPORTED 0 +#else +#define BP_ACCOUNT_IS_SUPPORTED 1 +#endif + +#define NUM_THREADS 5 + +static struct { + int tids_want_signal; /* Which threads still want a signal. */ + int signal_count; /* Sanity check number of signals received. */ + volatile int iterate_on; /* Variable to set breakpoint on. */ + siginfo_t first_siginfo; /* First observed siginfo_t. */ +} ctx; + +#define TEST_SIG_DATA (~(unsigned long)(&ctx.iterate_on)) + +static struct perf_event_attr make_event_attr(void) +{ + struct perf_event_attr attr = { + .type = PERF_TYPE_BREAKPOINT, + .size = sizeof(attr), + .sample_period = 1, + .disabled = 1, + .bp_addr = (unsigned long)&ctx.iterate_on, + .bp_type = HW_BREAKPOINT_RW, + .bp_len = HW_BREAKPOINT_LEN_1, + .inherit = 1, /* Children inherit events ... */ + .inherit_thread = 1, /* ... but only cloned with CLONE_THREAD. */ + .remove_on_exec = 1, /* Required by sigtrap. */ + .sigtrap = 1, /* Request synchronous SIGTRAP on event. */ + .sig_data = TEST_SIG_DATA, + .exclude_kernel = 1, /* To allow */ + .exclude_hv = 1, /* running as !root */ + }; + return attr; +} + +static void +sigtrap_handler(int signum __maybe_unused, siginfo_t *info, void *ucontext __maybe_unused) +{ + if (!__atomic_fetch_add(&ctx.signal_count, 1, __ATOMIC_RELAXED)) + ctx.first_siginfo = *info; + __atomic_fetch_sub(&ctx.tids_want_signal, syscall(SYS_gettid), __ATOMIC_RELAXED); +} + +static void *test_thread(void *arg) +{ + pthread_barrier_t *barrier = (pthread_barrier_t *)arg; + pid_t tid = syscall(SYS_gettid); + int i; + + pthread_barrier_wait(barrier); + + __atomic_fetch_add(&ctx.tids_want_signal, tid, __ATOMIC_RELAXED); + for (i = 0; i < ctx.iterate_on - 1; i++) + __atomic_fetch_add(&ctx.tids_want_signal, tid, __ATOMIC_RELAXED); + + return NULL; +} + +static int run_test_threads(pthread_t *threads, pthread_barrier_t *barrier) +{ + int i; + + pthread_barrier_wait(barrier); + for (i = 0; i < NUM_THREADS; i++) + TEST_ASSERT_EQUAL("pthread_join() failed", pthread_join(threads[i], NULL), 0); + + return TEST_OK; +} + +static int run_stress_test(int fd, pthread_t *threads, pthread_barrier_t *barrier) +{ + int ret; + + ctx.iterate_on = 3000; + + TEST_ASSERT_EQUAL("misfired signal?", ctx.signal_count, 0); + TEST_ASSERT_EQUAL("enable failed", ioctl(fd, PERF_EVENT_IOC_ENABLE, 0), 0); + ret = run_test_threads(threads, barrier); + TEST_ASSERT_EQUAL("disable failed", ioctl(fd, PERF_EVENT_IOC_DISABLE, 0), 0); + + TEST_ASSERT_EQUAL("unexpected sigtraps", ctx.signal_count, NUM_THREADS * ctx.iterate_on); + TEST_ASSERT_EQUAL("missing signals or incorrectly delivered", ctx.tids_want_signal, 0); + TEST_ASSERT_VAL("unexpected si_addr", ctx.first_siginfo.si_addr == &ctx.iterate_on); +#if 0 /* FIXME: enable when libc's signal.h has si_perf_{type,data} */ + TEST_ASSERT_EQUAL("unexpected si_perf_type", ctx.first_siginfo.si_perf_type, + PERF_TYPE_BREAKPOINT); + TEST_ASSERT_EQUAL("unexpected si_perf_data", ctx.first_siginfo.si_perf_data, + TEST_SIG_DATA); +#endif + + return ret; +} + +static int test__sigtrap(struct test_suite *test __maybe_unused, int subtest __maybe_unused) +{ + struct perf_event_attr attr = make_event_attr(); + struct sigaction action = {}; + struct sigaction oldact; + pthread_t threads[NUM_THREADS]; + pthread_barrier_t barrier; + char sbuf[STRERR_BUFSIZE]; + int i, fd, ret = TEST_FAIL; + + if (!BP_ACCOUNT_IS_SUPPORTED) { + pr_debug("Test not supported on this architecture"); + return TEST_SKIP; + } + + pthread_barrier_init(&barrier, NULL, NUM_THREADS + 1); + + action.sa_flags = SA_SIGINFO | SA_NODEFER; + action.sa_sigaction = sigtrap_handler; + sigemptyset(&action.sa_mask); + if (sigaction(SIGTRAP, &action, &oldact)) { + pr_debug("FAILED sigaction(): %s\n", str_error_r(errno, sbuf, sizeof(sbuf))); + goto out; + } + + fd = sys_perf_event_open(&attr, 0, -1, -1, perf_event_open_cloexec_flag()); + if (fd < 0) { + pr_debug("FAILED sys_perf_event_open(): %s\n", str_error_r(errno, sbuf, sizeof(sbuf))); + goto out_restore_sigaction; + } + + for (i = 0; i < NUM_THREADS; i++) { + if (pthread_create(&threads[i], NULL, test_thread, &barrier)) { + pr_debug("FAILED pthread_create(): %s\n", str_error_r(errno, sbuf, sizeof(sbuf))); + goto out_close_perf_event; + } + } + + ret = run_stress_test(fd, threads, &barrier); + +out_close_perf_event: + close(fd); +out_restore_sigaction: + sigaction(SIGTRAP, &oldact, NULL); +out: + pthread_barrier_destroy(&barrier); + return ret; +} + +DEFINE_SUITE("Sigtrap", sigtrap); diff --git a/tools/perf/tests/stat.c b/tools/perf/tests/stat.c index 2eb096b5e6da..500974040fe3 100644 --- a/tools/perf/tests/stat.c +++ b/tools/perf/tests/stat.c @@ -87,7 +87,8 @@ static int test__synthesize_stat(struct test_suite *test __maybe_unused, int sub count.run = 300; TEST_ASSERT_VAL("failed to synthesize stat_config", - !perf_event__synthesize_stat(NULL, 1, 2, 3, &count, process_stat_event, NULL)); + !perf_event__synthesize_stat(NULL, (struct perf_cpu){.cpu = 1}, 2, 3, + &count, process_stat_event, NULL)); return 0; } diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index 8f65098110fc..5bbb8f6a48fc 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -146,6 +146,7 @@ DECLARE_SUITE(pe_file_parsing); DECLARE_SUITE(expand_cgroup_events); DECLARE_SUITE(perf_time_to_tsc); DECLARE_SUITE(dlfilter); +DECLARE_SUITE(sigtrap); /* * PowerPC and S390 do not support creation of instruction breakpoints using the diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c index 869986139146..c4ef0c7002f1 100644 --- a/tools/perf/tests/topology.c +++ b/tools/perf/tests/topology.c @@ -112,62 +112,83 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map) TEST_ASSERT_VAL("Session header CPU map not set", session->header.env.cpu); for (i = 0; i < session->header.env.nr_cpus_avail; i++) { - if (!cpu_map__has(map, i)) + struct perf_cpu cpu = { .cpu = i }; + + if (!perf_cpu_map__has(map, cpu)) continue; pr_debug("CPU %d, core %d, socket %d\n", i, session->header.env.cpu[i].core_id, session->header.env.cpu[i].socket_id); } + // Test that CPU ID contains socket, die, core and CPU + for (i = 0; i < map->nr; i++) { + id = aggr_cpu_id__cpu(perf_cpu_map__cpu(map, i), NULL); + TEST_ASSERT_VAL("Cpu map - CPU ID doesn't match", map->map[i].cpu == id.cpu.cpu); + + TEST_ASSERT_VAL("Cpu map - Core ID doesn't match", + session->header.env.cpu[map->map[i].cpu].core_id == id.core); + TEST_ASSERT_VAL("Cpu map - Socket ID doesn't match", + session->header.env.cpu[map->map[i].cpu].socket_id == id.socket); + + TEST_ASSERT_VAL("Cpu map - Die ID doesn't match", + session->header.env.cpu[map->map[i].cpu].die_id == id.die); + TEST_ASSERT_VAL("Cpu map - Node ID is set", id.node == -1); + TEST_ASSERT_VAL("Cpu map - Thread is set", id.thread == -1); + } + // Test that core ID contains socket, die and core for (i = 0; i < map->nr; i++) { - id = cpu_map__get_core(map, i, NULL); + id = aggr_cpu_id__core(perf_cpu_map__cpu(map, i), NULL); TEST_ASSERT_VAL("Core map - Core ID doesn't match", - session->header.env.cpu[map->map[i]].core_id == id.core); + session->header.env.cpu[map->map[i].cpu].core_id == id.core); TEST_ASSERT_VAL("Core map - Socket ID doesn't match", - session->header.env.cpu[map->map[i]].socket_id == id.socket); + session->header.env.cpu[map->map[i].cpu].socket_id == id.socket); TEST_ASSERT_VAL("Core map - Die ID doesn't match", - session->header.env.cpu[map->map[i]].die_id == id.die); + session->header.env.cpu[map->map[i].cpu].die_id == id.die); TEST_ASSERT_VAL("Core map - Node ID is set", id.node == -1); TEST_ASSERT_VAL("Core map - Thread is set", id.thread == -1); } // Test that die ID contains socket and die for (i = 0; i < map->nr; i++) { - id = cpu_map__get_die(map, i, NULL); + id = aggr_cpu_id__die(perf_cpu_map__cpu(map, i), NULL); TEST_ASSERT_VAL("Die map - Socket ID doesn't match", - session->header.env.cpu[map->map[i]].socket_id == id.socket); + session->header.env.cpu[map->map[i].cpu].socket_id == id.socket); TEST_ASSERT_VAL("Die map - Die ID doesn't match", - session->header.env.cpu[map->map[i]].die_id == id.die); + session->header.env.cpu[map->map[i].cpu].die_id == id.die); TEST_ASSERT_VAL("Die map - Node ID is set", id.node == -1); TEST_ASSERT_VAL("Die map - Core is set", id.core == -1); + TEST_ASSERT_VAL("Die map - CPU is set", id.cpu.cpu == -1); TEST_ASSERT_VAL("Die map - Thread is set", id.thread == -1); } // Test that socket ID contains only socket for (i = 0; i < map->nr; i++) { - id = cpu_map__get_socket(map, i, NULL); + id = aggr_cpu_id__socket(perf_cpu_map__cpu(map, i), NULL); TEST_ASSERT_VAL("Socket map - Socket ID doesn't match", - session->header.env.cpu[map->map[i]].socket_id == id.socket); + session->header.env.cpu[map->map[i].cpu].socket_id == id.socket); TEST_ASSERT_VAL("Socket map - Node ID is set", id.node == -1); TEST_ASSERT_VAL("Socket map - Die ID is set", id.die == -1); TEST_ASSERT_VAL("Socket map - Core is set", id.core == -1); + TEST_ASSERT_VAL("Socket map - CPU is set", id.cpu.cpu == -1); TEST_ASSERT_VAL("Socket map - Thread is set", id.thread == -1); } // Test that node ID contains only node for (i = 0; i < map->nr; i++) { - id = cpu_map__get_node(map, i, NULL); + id = aggr_cpu_id__node(perf_cpu_map__cpu(map, i), NULL); TEST_ASSERT_VAL("Node map - Node ID doesn't match", cpu__get_node(map->map[i]) == id.node); TEST_ASSERT_VAL("Node map - Socket is set", id.socket == -1); TEST_ASSERT_VAL("Node map - Die ID is set", id.die == -1); TEST_ASSERT_VAL("Node map - Core is set", id.core == -1); + TEST_ASSERT_VAL("Node map - CPU is set", id.cpu.cpu == -1); TEST_ASSERT_VAL("Node map - Thread is set", id.thread == -1); } perf_session__delete(session); diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index e81c2493efdf..44ba900828f6 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -966,6 +966,7 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel, .opts = opts, }; int ret = -1, err; + int not_annotated = list_empty(¬es->src->source); if (sym == NULL) return -1; @@ -973,13 +974,15 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel, if (ms->map->dso->annotate_warned) return -1; - err = symbol__annotate2(ms, evsel, opts, &browser.arch); - if (err) { - char msg[BUFSIZ]; - ms->map->dso->annotate_warned = true; - symbol__strerror_disassemble(ms, err, msg, sizeof(msg)); - ui__error("Couldn't annotate %s:\n%s", sym->name, msg); - goto out_free_offsets; + if (not_annotated) { + err = symbol__annotate2(ms, evsel, opts, &browser.arch); + if (err) { + char msg[BUFSIZ]; + ms->map->dso->annotate_warned = true; + symbol__strerror_disassemble(ms, err, msg, sizeof(msg)); + ui__error("Couldn't annotate %s:\n%s", sym->name, msg); + goto out_free_offsets; + } } ui_helpline__push("Press ESC to exit"); @@ -994,9 +997,11 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel, ret = annotate_browser__run(&browser, evsel, hbt); - annotated_source__purge(notes->src); + if(not_annotated) + annotated_source__purge(notes->src); out_free_offsets: - zfree(¬es->offsets); + if(not_annotated) + zfree(¬es->offsets); return ret; } diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 2e5bfbb69960..2a403cefcaf2 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -1,3 +1,4 @@ +perf-y += arm64-frame-pointer-unwind-support.o perf-y += annotate.o perf-y += block-info.o perf-y += block-range.o @@ -144,6 +145,7 @@ perf-$(CONFIG_LIBBPF) += bpf-loader.o perf-$(CONFIG_LIBBPF) += bpf_map.o perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter.o perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter_cgroup.o +perf-$(CONFIG_PERF_BPF_SKEL) += bpf_ftrace.o perf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o perf-$(CONFIG_LIBELF) += symbol-elf.o perf-$(CONFIG_LIBELF) += probe-file.o diff --git a/tools/perf/util/affinity.c b/tools/perf/util/affinity.c index 7b12bd7a3080..f1e30d566db3 100644 --- a/tools/perf/util/affinity.c +++ b/tools/perf/util/affinity.c @@ -11,7 +11,7 @@ static int get_cpu_set_size(void) { - int sz = cpu__max_cpu() + 8 - 1; + int sz = cpu__max_cpu().cpu + 8 - 1; /* * sched_getaffinity doesn't like masks smaller than the kernel. * Hopefully that's big enough. diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c index 3fc528c9270c..5e390a1a79ab 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c @@ -179,6 +179,8 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder) decoder->record.phys_addr = ip; break; case ARM_SPE_COUNTER: + if (idx == SPE_CNT_PKT_HDR_INDEX_TOTAL_LAT) + decoder->record.latency = payload; break; case ARM_SPE_CONTEXT: decoder->record.context_id = payload; diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h index 46a8556a9e95..69b31084d6be 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h @@ -33,6 +33,7 @@ struct arm_spe_record { enum arm_spe_sample_type type; int err; u32 op; + u32 latency; u64 from_ip; u64 to_ip; u64 timestamp; diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c index fccac06b573a..d2b64e3f588b 100644 --- a/tools/perf/util/arm-spe.c +++ b/tools/perf/util/arm-spe.c @@ -58,6 +58,8 @@ struct arm_spe { u8 sample_branch; u8 sample_remote_access; u8 sample_memory; + u8 sample_instructions; + u64 instructions_sample_period; u64 l1d_miss_id; u64 l1d_access_id; @@ -68,6 +70,7 @@ struct arm_spe { u64 branch_miss_id; u64 remote_access_id; u64 memory_id; + u64 instructions_id; u64 kernel_start; @@ -90,6 +93,7 @@ struct arm_spe_queue { u64 time; u64 timestamp; struct thread *thread; + u64 period_instructions; }; static void arm_spe_dump(struct arm_spe *spe __maybe_unused, @@ -202,6 +206,7 @@ static struct arm_spe_queue *arm_spe__alloc_queue(struct arm_spe *spe, speq->pid = -1; speq->tid = -1; speq->cpu = -1; + speq->period_instructions = 0; /* params set */ params.get_trace = arm_spe_get_trace; @@ -330,6 +335,7 @@ static int arm_spe__synth_mem_sample(struct arm_spe_queue *speq, sample.addr = record->virt_addr; sample.phys_addr = record->phys_addr; sample.data_src = data_src; + sample.weight = record->latency; return arm_spe_deliver_synth_event(spe, speq, event, &sample); } @@ -347,6 +353,36 @@ static int arm_spe__synth_branch_sample(struct arm_spe_queue *speq, sample.id = spe_events_id; sample.stream_id = spe_events_id; sample.addr = record->to_ip; + sample.weight = record->latency; + + return arm_spe_deliver_synth_event(spe, speq, event, &sample); +} + +static int arm_spe__synth_instruction_sample(struct arm_spe_queue *speq, + u64 spe_events_id, u64 data_src) +{ + struct arm_spe *spe = speq->spe; + struct arm_spe_record *record = &speq->decoder->record; + union perf_event *event = speq->event_buf; + struct perf_sample sample = { .ip = 0, }; + + /* + * Handles perf instruction sampling period. + */ + speq->period_instructions++; + if (speq->period_instructions < spe->instructions_sample_period) + return 0; + speq->period_instructions = 0; + + arm_spe_prep_sample(spe, speq, event, &sample); + + sample.id = spe_events_id; + sample.stream_id = spe_events_id; + sample.addr = record->virt_addr; + sample.phys_addr = record->phys_addr; + sample.data_src = data_src; + sample.period = spe->instructions_sample_period; + sample.weight = record->latency; return arm_spe_deliver_synth_event(spe, speq, event, &sample); } @@ -480,6 +516,12 @@ static int arm_spe_sample(struct arm_spe_queue *speq) return err; } + if (spe->sample_instructions) { + err = arm_spe__synth_instruction_sample(speq, spe->instructions_id, data_src); + if (err) + return err; + } + return 0; } @@ -993,7 +1035,8 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session) attr.type = PERF_TYPE_HARDWARE; attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK; attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID | - PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC; + PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC | + PERF_SAMPLE_WEIGHT; if (spe->timeless_decoding) attr.sample_type &= ~(u64)PERF_SAMPLE_TIME; else @@ -1107,8 +1150,30 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session) return err; spe->memory_id = id; arm_spe_set_event_name(evlist, id, "memory"); + id += 1; } + if (spe->synth_opts.instructions) { + if (spe->synth_opts.period_type != PERF_ITRACE_PERIOD_INSTRUCTIONS) { + pr_warning("Only instruction-based sampling period is currently supported by Arm SPE.\n"); + goto synth_instructions_out; + } + if (spe->synth_opts.period > 1) + pr_warning("Arm SPE has a hardware-based sample period.\n" + "Additional instruction events will be discarded by --itrace\n"); + + spe->sample_instructions = true; + attr.config = PERF_COUNT_HW_INSTRUCTIONS; + attr.sample_period = spe->synth_opts.period; + spe->instructions_sample_period = attr.sample_period; + err = arm_spe_synth_event(session, &attr, id); + if (err) + return err; + spe->instructions_id = id; + arm_spe_set_event_name(evlist, id, "instructions"); + } +synth_instructions_out: + return 0; } diff --git a/tools/perf/util/arm64-frame-pointer-unwind-support.c b/tools/perf/util/arm64-frame-pointer-unwind-support.c new file mode 100644 index 000000000000..2242a885fbd7 --- /dev/null +++ b/tools/perf/util/arm64-frame-pointer-unwind-support.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "arm64-frame-pointer-unwind-support.h" +#include "callchain.h" +#include "event.h" +#include "perf_regs.h" // SMPL_REG_MASK +#include "unwind.h" + +#define perf_event_arm_regs perf_event_arm64_regs +#include "../../arch/arm64/include/uapi/asm/perf_regs.h" +#undef perf_event_arm_regs + +struct entries { + u64 stack[2]; + size_t length; +}; + +static bool get_leaf_frame_caller_enabled(struct perf_sample *sample) +{ + return callchain_param.record_mode == CALLCHAIN_FP && sample->user_regs.regs + && sample->user_regs.mask & SMPL_REG_MASK(PERF_REG_ARM64_LR); +} + +static int add_entry(struct unwind_entry *entry, void *arg) +{ + struct entries *entries = arg; + + entries->stack[entries->length++] = entry->ip; + return 0; +} + +u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thread, int usr_idx) +{ + int ret; + struct entries entries = {}; + struct regs_dump old_regs = sample->user_regs; + + if (!get_leaf_frame_caller_enabled(sample)) + return 0; + + /* + * If PC and SP are not recorded, get the value of PC from the stack + * and set its mask. SP is not used when doing the unwinding but it + * still needs to be set to prevent failures. + */ + + if (!(sample->user_regs.mask & SMPL_REG_MASK(PERF_REG_ARM64_PC))) { + sample->user_regs.cache_mask |= SMPL_REG_MASK(PERF_REG_ARM64_PC); + sample->user_regs.cache_regs[PERF_REG_ARM64_PC] = sample->callchain->ips[usr_idx+1]; + } + + if (!(sample->user_regs.mask & SMPL_REG_MASK(PERF_REG_ARM64_SP))) { + sample->user_regs.cache_mask |= SMPL_REG_MASK(PERF_REG_ARM64_SP); + sample->user_regs.cache_regs[PERF_REG_ARM64_SP] = 0; + } + + ret = unwind__get_entries(add_entry, &entries, thread, sample, 2); + sample->user_regs = old_regs; + + if (ret || entries.length != 2) + return ret; + + return callchain_param.order == ORDER_CALLER ? entries.stack[0] : entries.stack[1]; +} diff --git a/tools/perf/util/arm64-frame-pointer-unwind-support.h b/tools/perf/util/arm64-frame-pointer-unwind-support.h new file mode 100644 index 000000000000..32af9ce94398 --- /dev/null +++ b/tools/perf/util/arm64-frame-pointer-unwind-support.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PERF_ARM_FRAME_POINTER_UNWIND_SUPPORT_H +#define __PERF_ARM_FRAME_POINTER_UNWIND_SUPPORT_H + +#include "event.h" +#include "thread.h" + +u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thread, int user_idx); + +#endif /* __PERF_ARM_FRAME_POINTER_UNWIND_SUPPORT_H */ diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index c679394b898d..5632efc44738 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -123,7 +123,7 @@ int auxtrace_mmap__mmap(struct auxtrace_mmap *mm, mm->prev = 0; mm->idx = mp->idx; mm->tid = mp->tid; - mm->cpu = mp->cpu; + mm->cpu = mp->cpu.cpu; if (!mp->len) { mm->base = NULL; @@ -180,7 +180,7 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp, else mp->tid = -1; } else { - mp->cpu = -1; + mp->cpu.cpu = -1; mp->tid = perf_thread_map__pid(evlist->core.threads, idx); } } @@ -292,7 +292,7 @@ static int auxtrace_queues__queue_buffer(struct auxtrace_queues *queues, if (!queue->set) { queue->set = true; queue->tid = buffer->tid; - queue->cpu = buffer->cpu; + queue->cpu = buffer->cpu.cpu; } buffer->buffer_nr = queues->next_buffer_nr++; @@ -339,11 +339,11 @@ static int auxtrace_queues__split_buffer(struct auxtrace_queues *queues, return 0; } -static bool filter_cpu(struct perf_session *session, int cpu) +static bool filter_cpu(struct perf_session *session, struct perf_cpu cpu) { unsigned long *cpu_bitmap = session->itrace_synth_opts->cpu_bitmap; - return cpu_bitmap && cpu != -1 && !test_bit(cpu, cpu_bitmap); + return cpu_bitmap && cpu.cpu != -1 && !test_bit(cpu.cpu, cpu_bitmap); } static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues, @@ -399,7 +399,7 @@ int auxtrace_queues__add_event(struct auxtrace_queues *queues, struct auxtrace_buffer buffer = { .pid = -1, .tid = event->auxtrace.tid, - .cpu = event->auxtrace.cpu, + .cpu = { event->auxtrace.cpu }, .data_offset = data_offset, .offset = event->auxtrace.offset, .reference = event->auxtrace.reference, diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index bbf0d78c6401..19910b9011f3 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -15,6 +15,7 @@ #include #include #include +#include #include #include @@ -240,7 +241,7 @@ struct auxtrace_buffer { size_t size; pid_t pid; pid_t tid; - int cpu; + struct perf_cpu cpu; void *data; off_t data_offset; void *mmap_addr; @@ -350,7 +351,7 @@ struct auxtrace_mmap_params { int prot; int idx; pid_t tid; - int cpu; + struct perf_cpu cpu; }; /** diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index 528aeb0ab79d..7ecfaac7536a 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -424,7 +424,7 @@ preproc_gen_prologue(struct bpf_program *prog, int n, size_t prologue_cnt = 0; int i, err; - if (IS_ERR(priv) || !priv || priv->is_tp) + if (IS_ERR_OR_NULL(priv) || priv->is_tp) goto errout; pev = &priv->pev; @@ -573,7 +573,7 @@ static int hook_load_preprocessor(struct bpf_program *prog) bool need_prologue = false; int err, i; - if (IS_ERR(priv) || !priv) { + if (IS_ERR_OR_NULL(priv)) { pr_debug("Internal error when hook preprocessor\n"); return -BPF_LOADER_ERRNO__INTERNAL; } @@ -645,8 +645,11 @@ int bpf__probe(struct bpf_object *obj) goto out; priv = bpf_program__priv(prog); - if (IS_ERR(priv) || !priv) { - err = PTR_ERR(priv); + if (IS_ERR_OR_NULL(priv)) { + if (!priv) + err = -BPF_LOADER_ERRNO__INTERNAL; + else + err = PTR_ERR(priv); goto out; } @@ -696,7 +699,7 @@ int bpf__unprobe(struct bpf_object *obj) struct bpf_prog_priv *priv = bpf_program__priv(prog); int i; - if (IS_ERR(priv) || !priv || priv->is_tp) + if (IS_ERR_OR_NULL(priv) || priv->is_tp) continue; for (i = 0; i < priv->pev.ntevs; i++) { @@ -754,7 +757,7 @@ int bpf__foreach_event(struct bpf_object *obj, struct perf_probe_event *pev; int i, fd; - if (IS_ERR(priv) || !priv) { + if (IS_ERR_OR_NULL(priv)) { pr_debug("bpf: failed to get private field\n"); return -BPF_LOADER_ERRNO__INTERNAL; } diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c index 5a97fd7d0a71..3ce8d03cb7ec 100644 --- a/tools/perf/util/bpf_counter.c +++ b/tools/perf/util/bpf_counter.c @@ -265,7 +265,7 @@ static int bpf_program_profiler__read(struct evsel *evsel) return 0; } -static int bpf_program_profiler__install_pe(struct evsel *evsel, int cpu, +static int bpf_program_profiler__install_pe(struct evsel *evsel, int cpu_map_idx, int fd) { struct bpf_prog_profiler_bpf *skel; @@ -277,7 +277,7 @@ static int bpf_program_profiler__install_pe(struct evsel *evsel, int cpu, assert(skel != NULL); ret = bpf_map_update_elem(bpf_map__fd(skel->maps.events), - &cpu, &fd, BPF_ANY); + &cpu_map_idx, &fd, BPF_ANY); if (ret) return ret; } @@ -554,7 +554,7 @@ static int bperf__load(struct evsel *evsel, struct target *target) filter_type == BPERF_FILTER_TGID) key = evsel->core.threads->map[i].pid; else if (filter_type == BPERF_FILTER_CPU) - key = evsel->core.cpus->map[i]; + key = evsel->core.cpus->map[i].cpu; else break; @@ -580,12 +580,12 @@ out: return err; } -static int bperf__install_pe(struct evsel *evsel, int cpu, int fd) +static int bperf__install_pe(struct evsel *evsel, int cpu_map_idx, int fd) { struct bperf_leader_bpf *skel = evsel->leader_skel; return bpf_map_update_elem(bpf_map__fd(skel->maps.events), - &cpu, &fd, BPF_ANY); + &cpu_map_idx, &fd, BPF_ANY); } /* @@ -598,7 +598,7 @@ static int bperf_sync_counters(struct evsel *evsel) num_cpu = all_cpu_map->nr; for (i = 0; i < num_cpu; i++) { - cpu = all_cpu_map->map[i]; + cpu = all_cpu_map->map[i].cpu; bperf_trigger_reading(evsel->bperf_leader_prog_fd, cpu); } return 0; @@ -619,15 +619,17 @@ static int bperf__disable(struct evsel *evsel) static int bperf__read(struct evsel *evsel) { struct bperf_follower_bpf *skel = evsel->follower_skel; - __u32 num_cpu_bpf = cpu__max_cpu(); + __u32 num_cpu_bpf = cpu__max_cpu().cpu; struct bpf_perf_event_value values[num_cpu_bpf]; int reading_map_fd, err = 0; - __u32 i, j, num_cpu; + __u32 i; + int j; bperf_sync_counters(evsel); reading_map_fd = bpf_map__fd(skel->maps.accum_readings); for (i = 0; i < bpf_map__max_entries(skel->maps.accum_readings); i++) { + struct perf_cpu entry; __u32 cpu; err = bpf_map_lookup_elem(reading_map_fd, &i, values); @@ -637,16 +639,15 @@ static int bperf__read(struct evsel *evsel) case BPERF_FILTER_GLOBAL: assert(i == 0); - num_cpu = all_cpu_map->nr; - for (j = 0; j < num_cpu; j++) { - cpu = all_cpu_map->map[j]; + perf_cpu_map__for_each_cpu(entry, j, all_cpu_map) { + cpu = entry.cpu; perf_counts(evsel->counts, cpu, 0)->val = values[cpu].counter; perf_counts(evsel->counts, cpu, 0)->ena = values[cpu].enabled; perf_counts(evsel->counts, cpu, 0)->run = values[cpu].running; } break; case BPERF_FILTER_CPU: - cpu = evsel->core.cpus->map[i]; + cpu = evsel->core.cpus->map[i].cpu; perf_counts(evsel->counts, i, 0)->val = values[cpu].counter; perf_counts(evsel->counts, i, 0)->ena = values[cpu].enabled; perf_counts(evsel->counts, i, 0)->run = values[cpu].running; @@ -771,11 +772,11 @@ static inline bool bpf_counter_skip(struct evsel *evsel) evsel->follower_skel == NULL; } -int bpf_counter__install_pe(struct evsel *evsel, int cpu, int fd) +int bpf_counter__install_pe(struct evsel *evsel, int cpu_map_idx, int fd) { if (bpf_counter_skip(evsel)) return 0; - return evsel->bpf_counter_ops->install_pe(evsel, cpu, fd); + return evsel->bpf_counter_ops->install_pe(evsel, cpu_map_idx, fd); } int bpf_counter__load(struct evsel *evsel, struct target *target) diff --git a/tools/perf/util/bpf_counter.h b/tools/perf/util/bpf_counter.h index 65ebaa6694fb..4dbf26408b69 100644 --- a/tools/perf/util/bpf_counter.h +++ b/tools/perf/util/bpf_counter.h @@ -16,7 +16,7 @@ typedef int (*bpf_counter_evsel_op)(struct evsel *evsel); typedef int (*bpf_counter_evsel_target_op)(struct evsel *evsel, struct target *target); typedef int (*bpf_counter_evsel_install_pe_op)(struct evsel *evsel, - int cpu, + int cpu_map_idx, int fd); struct bpf_counter_ops { @@ -40,7 +40,7 @@ int bpf_counter__enable(struct evsel *evsel); int bpf_counter__disable(struct evsel *evsel); int bpf_counter__read(struct evsel *evsel); void bpf_counter__destroy(struct evsel *evsel); -int bpf_counter__install_pe(struct evsel *evsel, int cpu, int fd); +int bpf_counter__install_pe(struct evsel *evsel, int cpu_map_idx, int fd); #else /* HAVE_BPF_SKEL */ diff --git a/tools/perf/util/bpf_counter_cgroup.c b/tools/perf/util/bpf_counter_cgroup.c index cbc6c2bca488..631e34a0b66f 100644 --- a/tools/perf/util/bpf_counter_cgroup.c +++ b/tools/perf/util/bpf_counter_cgroup.c @@ -48,7 +48,7 @@ static int bperf_load_program(struct evlist *evlist) struct cgroup *cgrp, *leader_cgrp; __u32 i, cpu; __u32 nr_cpus = evlist->core.all_cpus->nr; - int total_cpus = cpu__max_cpu(); + int total_cpus = cpu__max_cpu().cpu; int map_size, map_fd; int prog_fd, err; @@ -125,7 +125,7 @@ static int bperf_load_program(struct evlist *evlist) for (cpu = 0; cpu < nr_cpus; cpu++) { int fd = FD(evsel, cpu); __u32 idx = evsel->core.idx * total_cpus + - evlist->core.all_cpus->map[cpu]; + evlist->core.all_cpus->map[cpu].cpu; err = bpf_map_update_elem(map_fd, &idx, &fd, BPF_ANY); @@ -212,7 +212,7 @@ static int bperf_cgrp__sync_counters(struct evlist *evlist) int prog_fd = bpf_program__fd(skel->progs.trigger_read); for (i = 0; i < nr_cpus; i++) { - cpu = evlist->core.all_cpus->map[i]; + cpu = evlist->core.all_cpus->map[i].cpu; bperf_trigger_reading(prog_fd, cpu); } @@ -245,7 +245,7 @@ static int bperf_cgrp__read(struct evsel *evsel) { struct evlist *evlist = evsel->evlist; int i, cpu, nr_cpus = evlist->core.all_cpus->nr; - int total_cpus = cpu__max_cpu(); + int total_cpus = cpu__max_cpu().cpu; struct perf_counts_values *counts; struct bpf_perf_event_value *values; int reading_map_fd, err = 0; @@ -272,7 +272,7 @@ static int bperf_cgrp__read(struct evsel *evsel) } for (i = 0; i < nr_cpus; i++) { - cpu = evlist->core.all_cpus->map[i]; + cpu = evlist->core.all_cpus->map[i].cpu; counts = perf_counts(evsel->counts, i, 0); counts->val = values[cpu].counter; diff --git a/tools/perf/util/bpf_ftrace.c b/tools/perf/util/bpf_ftrace.c new file mode 100644 index 000000000000..d756cc66eef3 --- /dev/null +++ b/tools/perf/util/bpf_ftrace.c @@ -0,0 +1,152 @@ +#include +#include +#include +#include + +#include + +#include "util/ftrace.h" +#include "util/cpumap.h" +#include "util/thread_map.h" +#include "util/debug.h" +#include "util/evlist.h" +#include "util/bpf_counter.h" + +#include "util/bpf_skel/func_latency.skel.h" + +static struct func_latency_bpf *skel; + +int perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace) +{ + int fd, err; + int i, ncpus = 1, ntasks = 1; + struct filter_entry *func; + + if (!list_is_singular(&ftrace->filters)) { + pr_err("ERROR: %s target function(s).\n", + list_empty(&ftrace->filters) ? "No" : "Too many"); + return -1; + } + + func = list_first_entry(&ftrace->filters, struct filter_entry, list); + + skel = func_latency_bpf__open(); + if (!skel) { + pr_err("Failed to open func latency skeleton\n"); + return -1; + } + + /* don't need to set cpu filter for system-wide mode */ + if (ftrace->target.cpu_list) { + ncpus = perf_cpu_map__nr(ftrace->evlist->core.cpus); + bpf_map__set_max_entries(skel->maps.cpu_filter, ncpus); + } + + if (target__has_task(&ftrace->target) || target__none(&ftrace->target)) { + ntasks = perf_thread_map__nr(ftrace->evlist->core.threads); + bpf_map__set_max_entries(skel->maps.task_filter, ntasks); + } + + set_max_rlimit(); + + err = func_latency_bpf__load(skel); + if (err) { + pr_err("Failed to load func latency skeleton\n"); + goto out; + } + + if (ftrace->target.cpu_list) { + u32 cpu; + u8 val = 1; + + skel->bss->has_cpu = 1; + fd = bpf_map__fd(skel->maps.cpu_filter); + + for (i = 0; i < ncpus; i++) { + cpu = perf_cpu_map__cpu(ftrace->evlist->core.cpus, i).cpu; + bpf_map_update_elem(fd, &cpu, &val, BPF_ANY); + } + } + + if (target__has_task(&ftrace->target) || target__none(&ftrace->target)) { + u32 pid; + u8 val = 1; + + skel->bss->has_task = 1; + fd = bpf_map__fd(skel->maps.task_filter); + + for (i = 0; i < ntasks; i++) { + pid = perf_thread_map__pid(ftrace->evlist->core.threads, i); + bpf_map_update_elem(fd, &pid, &val, BPF_ANY); + } + } + + skel->links.func_begin = bpf_program__attach_kprobe(skel->progs.func_begin, + false, func->name); + if (IS_ERR(skel->links.func_begin)) { + pr_err("Failed to attach fentry program\n"); + err = PTR_ERR(skel->links.func_begin); + goto out; + } + + skel->links.func_end = bpf_program__attach_kprobe(skel->progs.func_end, + true, func->name); + if (IS_ERR(skel->links.func_end)) { + pr_err("Failed to attach fexit program\n"); + err = PTR_ERR(skel->links.func_end); + goto out; + } + + /* XXX: we don't actually use this fd - just for poll() */ + return open("/dev/null", O_RDONLY); + +out: + return err; +} + +int perf_ftrace__latency_start_bpf(struct perf_ftrace *ftrace __maybe_unused) +{ + skel->bss->enabled = 1; + return 0; +} + +int perf_ftrace__latency_stop_bpf(struct perf_ftrace *ftrace __maybe_unused) +{ + skel->bss->enabled = 0; + return 0; +} + +int perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace __maybe_unused, + int buckets[]) +{ + int i, fd, err; + u32 idx; + u64 *hist; + int ncpus = cpu__max_cpu().cpu; + + fd = bpf_map__fd(skel->maps.latency); + + hist = calloc(ncpus, sizeof(*hist)); + if (hist == NULL) + return -ENOMEM; + + for (idx = 0; idx < NUM_BUCKET; idx++) { + err = bpf_map_lookup_elem(fd, &idx, hist); + if (err) { + buckets[idx] = 0; + continue; + } + + for (i = 0; i < ncpus; i++) + buckets[idx] += hist[i]; + } + + free(hist); + return 0; +} + +int perf_ftrace__latency_cleanup_bpf(struct perf_ftrace *ftrace __maybe_unused) +{ + func_latency_bpf__destroy(skel); + return 0; +} diff --git a/tools/perf/util/bpf_skel/func_latency.bpf.c b/tools/perf/util/bpf_skel/func_latency.bpf.c new file mode 100644 index 000000000000..ea94187fe443 --- /dev/null +++ b/tools/perf/util/bpf_skel/func_latency.bpf.c @@ -0,0 +1,114 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +// Copyright (c) 2021 Google +#include "vmlinux.h" +#include +#include + +// This should be in sync with "util/ftrace.h" +#define NUM_BUCKET 22 + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(__u64)); + __uint(value_size, sizeof(__u64)); + __uint(max_entries, 10000); +} functime SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u8)); + __uint(max_entries, 1); +} cpu_filter SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u8)); + __uint(max_entries, 1); +} task_filter SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u64)); + __uint(max_entries, NUM_BUCKET); +} latency SEC(".maps"); + + +int enabled = 0; +int has_cpu = 0; +int has_task = 0; + +SEC("kprobe/func") +int BPF_PROG(func_begin) +{ + __u64 key, now; + + if (!enabled) + return 0; + + key = bpf_get_current_pid_tgid(); + + if (has_cpu) { + __u32 cpu = bpf_get_smp_processor_id(); + __u8 *ok; + + ok = bpf_map_lookup_elem(&cpu_filter, &cpu); + if (!ok) + return 0; + } + + if (has_task) { + __u32 pid = key & 0xffffffff; + __u8 *ok; + + ok = bpf_map_lookup_elem(&task_filter, &pid); + if (!ok) + return 0; + } + + now = bpf_ktime_get_ns(); + + // overwrite timestamp for nested functions + bpf_map_update_elem(&functime, &key, &now, BPF_ANY); + return 0; +} + +SEC("kretprobe/func") +int BPF_PROG(func_end) +{ + __u64 tid; + __u64 *start; + + if (!enabled) + return 0; + + tid = bpf_get_current_pid_tgid(); + + start = bpf_map_lookup_elem(&functime, &tid); + if (start) { + __s64 delta = bpf_ktime_get_ns() - *start; + __u32 key; + __u64 *hist; + + bpf_map_delete_elem(&functime, &tid); + + if (delta < 0) + return 0; + + // calculate index using delta in usec + for (key = 0; key < (NUM_BUCKET - 1); key++) { + if (delta < ((1000UL) << key)) + break; + } + + hist = bpf_map_lookup_elem(&latency, &key); + if (!hist) + return 0; + + *hist += 1; + } + + return 0; +} diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 8e2777133bd9..131207b91d15 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -1600,7 +1600,7 @@ void callchain_cursor_reset(struct callchain_cursor *cursor) map__zput(node->ms.map); } -void callchain_param_setup(u64 sample_type) +void callchain_param_setup(u64 sample_type, const char *arch) { if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain) { if ((sample_type & PERF_SAMPLE_REGS_USER) && @@ -1612,6 +1612,18 @@ void callchain_param_setup(u64 sample_type) else callchain_param.record_mode = CALLCHAIN_FP; } + + /* + * It's necessary to use libunwind to reliably determine the caller of + * a leaf function on aarch64, as otherwise we cannot know whether to + * start from the LR or FP. + * + * Always starting from the LR can result in duplicate or entirely + * erroneous entries. Always skipping the LR and starting from the FP + * can result in missing entries. + */ + if (callchain_param.record_mode == CALLCHAIN_FP && !strcmp(arch, "arm64")) + dwarf_callchain_users = true; } static bool chain_match(struct callchain_list *base_chain, diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 5824134f983b..d95615daed73 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -280,6 +280,8 @@ static inline int arch_skip_callchain_idx(struct thread *thread __maybe_unused, } #endif +void arch__add_leaf_frame_record_opts(struct record_opts *opts); + char *callchain_list__sym_name(struct callchain_list *cl, char *bf, size_t bfsize, bool show_dso); char *callchain_node__scnprintf_value(struct callchain_node *node, @@ -298,7 +300,7 @@ int callchain_branch_counts(struct callchain_root *root, u64 *branch_count, u64 *predicted_count, u64 *abort_count, u64 *cycles_count); -void callchain_param_setup(u64 sample_type); +void callchain_param_setup(u64 sample_type, const char *arch); bool callchain_cnode_matched(struct callchain_node *base_cnode, struct callchain_node *pair_cnode); diff --git a/tools/perf/util/counts.c b/tools/perf/util/counts.c index 582f3aeaf5e4..2b81707b9dba 100644 --- a/tools/perf/util/counts.c +++ b/tools/perf/util/counts.c @@ -4,6 +4,7 @@ #include #include "evsel.h" #include "counts.h" +#include #include struct perf_counts *perf_counts__new(int ncpus, int nthreads) @@ -55,9 +56,12 @@ void evsel__reset_counts(struct evsel *evsel) perf_counts__reset(evsel->counts); } -int evsel__alloc_counts(struct evsel *evsel, int ncpus, int nthreads) +int evsel__alloc_counts(struct evsel *evsel) { - evsel->counts = perf_counts__new(ncpus, nthreads); + struct perf_cpu_map *cpus = evsel__cpus(evsel); + int nthreads = perf_thread_map__nr(evsel->core.threads); + + evsel->counts = perf_counts__new(cpus ? cpus->nr : 1, nthreads); return evsel->counts != NULL ? 0 : -ENOMEM; } diff --git a/tools/perf/util/counts.h b/tools/perf/util/counts.h index 7ff36bf6d644..5de275194f2b 100644 --- a/tools/perf/util/counts.h +++ b/tools/perf/util/counts.h @@ -18,21 +18,21 @@ struct perf_counts { static inline struct perf_counts_values* -perf_counts(struct perf_counts *counts, int cpu, int thread) +perf_counts(struct perf_counts *counts, int cpu_map_idx, int thread) { - return xyarray__entry(counts->values, cpu, thread); + return xyarray__entry(counts->values, cpu_map_idx, thread); } static inline bool -perf_counts__is_loaded(struct perf_counts *counts, int cpu, int thread) +perf_counts__is_loaded(struct perf_counts *counts, int cpu_map_idx, int thread) { - return *((bool *) xyarray__entry(counts->loaded, cpu, thread)); + return *((bool *) xyarray__entry(counts->loaded, cpu_map_idx, thread)); } static inline void -perf_counts__set_loaded(struct perf_counts *counts, int cpu, int thread, bool loaded) +perf_counts__set_loaded(struct perf_counts *counts, int cpu_map_idx, int thread, bool loaded) { - *((bool *) xyarray__entry(counts->loaded, cpu, thread)) = loaded; + *((bool *) xyarray__entry(counts->loaded, cpu_map_idx, thread)) = loaded; } struct perf_counts *perf_counts__new(int ncpus, int nthreads); @@ -40,7 +40,7 @@ void perf_counts__delete(struct perf_counts *counts); void perf_counts__reset(struct perf_counts *counts); void evsel__reset_counts(struct evsel *evsel); -int evsel__alloc_counts(struct evsel *evsel, int ncpus, int nthreads); +int evsel__alloc_counts(struct evsel *evsel); void evsel__free_counts(struct evsel *evsel); #endif /* __PERF_COUNTS_H */ diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 87d3eca9b872..12b2243222b0 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -13,9 +13,13 @@ #include #include -static int max_cpu_num; -static int max_present_cpu_num; +static struct perf_cpu max_cpu_num; +static struct perf_cpu max_present_cpu_num; static int max_node_num; +/** + * The numa node X as read from /sys/devices/system/node/nodeX indexed by the + * CPU number. + */ static int *cpunode_map; static struct perf_cpu_map *cpu_map__from_entries(struct cpu_map_entries *cpus) @@ -33,9 +37,9 @@ static struct perf_cpu_map *cpu_map__from_entries(struct cpu_map_entries *cpus) * otherwise it would become 65535. */ if (cpus->cpu[i] == (u16) -1) - map->map[i] = -1; + map->map[i].cpu = -1; else - map->map[i] = (int) cpus->cpu[i]; + map->map[i].cpu = (int) cpus->cpu[i]; } } @@ -54,7 +58,7 @@ static struct perf_cpu_map *cpu_map__from_mask(struct perf_record_record_cpu_map int cpu, i = 0; for_each_set_bit(cpu, mask->mask, nbits) - map->map[i++] = cpu; + map->map[i++].cpu = cpu; } return map; @@ -87,7 +91,7 @@ struct perf_cpu_map *perf_cpu_map__empty_new(int nr) cpus->nr = nr; for (i = 0; i < nr; i++) - cpus->map[i] = -1; + cpus->map[i].cpu = -1; refcount_set(&cpus->refcnt, 1); } @@ -104,7 +108,7 @@ struct cpu_aggr_map *cpu_aggr_map__empty_new(int nr) cpus->nr = nr; for (i = 0; i < nr; i++) - cpus->map[i] = cpu_map__empty_aggr_cpu_id(); + cpus->map[i] = aggr_cpu_id__empty(); refcount_set(&cpus->refcnt, 1); } @@ -122,28 +126,21 @@ static int cpu__get_topology_int(int cpu, const char *name, int *value) return sysfs__read_int(path, value); } -int cpu_map__get_socket_id(int cpu) +int cpu__get_socket_id(struct perf_cpu cpu) { - int value, ret = cpu__get_topology_int(cpu, "physical_package_id", &value); + int value, ret = cpu__get_topology_int(cpu.cpu, "physical_package_id", &value); return ret ?: value; } -struct aggr_cpu_id cpu_map__get_socket(struct perf_cpu_map *map, int idx, - void *data __maybe_unused) +struct aggr_cpu_id aggr_cpu_id__socket(struct perf_cpu cpu, void *data __maybe_unused) { - int cpu; - struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); + struct aggr_cpu_id id = aggr_cpu_id__empty(); - if (idx > map->nr) - return id; - - cpu = map->map[idx]; - - id.socket = cpu_map__get_socket_id(cpu); + id.socket = cpu__get_socket_id(cpu); return id; } -static int cmp_aggr_cpu_id(const void *a_pointer, const void *b_pointer) +static int aggr_cpu_id__cmp(const void *a_pointer, const void *b_pointer) { struct aggr_cpu_id *a = (struct aggr_cpu_id *)a_pointer; struct aggr_cpu_id *b = (struct aggr_cpu_id *)b_pointer; @@ -160,57 +157,64 @@ static int cmp_aggr_cpu_id(const void *a_pointer, const void *b_pointer) return a->thread - b->thread; } -int cpu_map__build_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **res, - struct aggr_cpu_id (*f)(struct perf_cpu_map *map, int cpu, void *data), - void *data) +struct cpu_aggr_map *cpu_aggr_map__new(const struct perf_cpu_map *cpus, + aggr_cpu_id_get_t get_id, + void *data) { - int nr = cpus->nr; - struct cpu_aggr_map *c = cpu_aggr_map__empty_new(nr); - int cpu, s2; - struct aggr_cpu_id s1; + int idx; + struct perf_cpu cpu; + struct cpu_aggr_map *c = cpu_aggr_map__empty_new(cpus->nr); if (!c) - return -1; + return NULL; /* Reset size as it may only be partially filled */ c->nr = 0; - for (cpu = 0; cpu < nr; cpu++) { - s1 = f(cpus, cpu, data); - for (s2 = 0; s2 < c->nr; s2++) { - if (cpu_map__compare_aggr_cpu_id(s1, c->map[s2])) + perf_cpu_map__for_each_cpu(cpu, idx, cpus) { + bool duplicate = false; + struct aggr_cpu_id cpu_id = get_id(cpu, data); + + for (int j = 0; j < c->nr; j++) { + if (aggr_cpu_id__equal(&cpu_id, &c->map[j])) { + duplicate = true; break; + } } - if (s2 == c->nr) { - c->map[c->nr] = s1; + if (!duplicate) { + c->map[c->nr] = cpu_id; c->nr++; } } - /* ensure we process id in increasing order */ - qsort(c->map, c->nr, sizeof(struct aggr_cpu_id), cmp_aggr_cpu_id); + /* Trim. */ + if (c->nr != cpus->nr) { + struct cpu_aggr_map *trimmed_c = + realloc(c, + sizeof(struct cpu_aggr_map) + sizeof(struct aggr_cpu_id) * c->nr); + + if (trimmed_c) + c = trimmed_c; + } + /* ensure we process id in increasing order */ + qsort(c->map, c->nr, sizeof(struct aggr_cpu_id), aggr_cpu_id__cmp); + + return c; - *res = c; - return 0; } -int cpu_map__get_die_id(int cpu) +int cpu__get_die_id(struct perf_cpu cpu) { - int value, ret = cpu__get_topology_int(cpu, "die_id", &value); + int value, ret = cpu__get_topology_int(cpu.cpu, "die_id", &value); return ret ?: value; } -struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data) +struct aggr_cpu_id aggr_cpu_id__die(struct perf_cpu cpu, void *data) { - int cpu, die; - struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); + struct aggr_cpu_id id; + int die; - if (idx > map->nr) - return id; - - cpu = map->map[idx]; - - die = cpu_map__get_die_id(cpu); + die = cpu__get_die_id(cpu); /* There is no die_id on legacy system. */ if (die == -1) die = 0; @@ -220,79 +224,59 @@ struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *dat * with the socket ID and then add die to * make a unique ID. */ - id = cpu_map__get_socket(map, idx, data); - if (cpu_map__aggr_cpu_id_is_empty(id)) + id = aggr_cpu_id__socket(cpu, data); + if (aggr_cpu_id__is_empty(&id)) return id; id.die = die; return id; } -int cpu_map__get_core_id(int cpu) +int cpu__get_core_id(struct perf_cpu cpu) { - int value, ret = cpu__get_topology_int(cpu, "core_id", &value); + int value, ret = cpu__get_topology_int(cpu.cpu, "core_id", &value); return ret ?: value; } -int cpu_map__get_node_id(int cpu) +struct aggr_cpu_id aggr_cpu_id__core(struct perf_cpu cpu, void *data) { - return cpu__get_node(cpu); -} + struct aggr_cpu_id id; + int core = cpu__get_core_id(cpu); -struct aggr_cpu_id cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data) -{ - int cpu; - struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); - - if (idx > map->nr) - return id; - - cpu = map->map[idx]; - - cpu = cpu_map__get_core_id(cpu); - - /* cpu_map__get_die returns a struct with socket and die set*/ - id = cpu_map__get_die(map, idx, data); - if (cpu_map__aggr_cpu_id_is_empty(id)) + /* aggr_cpu_id__die returns a struct with socket and die set. */ + id = aggr_cpu_id__die(cpu, data); + if (aggr_cpu_id__is_empty(&id)) return id; /* * core_id is relative to socket and die, we need a global id. * So we combine the result from cpu_map__get_die with the core id */ - id.core = cpu; + id.core = core; return id; + } -struct aggr_cpu_id cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data __maybe_unused) +struct aggr_cpu_id aggr_cpu_id__cpu(struct perf_cpu cpu, void *data) { - struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); + struct aggr_cpu_id id; - if (idx < 0 || idx >= map->nr) + /* aggr_cpu_id__core returns a struct with socket, die and core set. */ + id = aggr_cpu_id__core(cpu, data); + if (aggr_cpu_id__is_empty(&id)) return id; - id.node = cpu_map__get_node_id(map->map[idx]); + id.cpu = cpu; return id; + } -int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **sockp) +struct aggr_cpu_id aggr_cpu_id__node(struct perf_cpu cpu, void *data __maybe_unused) { - return cpu_map__build_map(cpus, sockp, cpu_map__get_socket, NULL); -} + struct aggr_cpu_id id = aggr_cpu_id__empty(); -int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **diep) -{ - return cpu_map__build_map(cpus, diep, cpu_map__get_die, NULL); -} - -int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **corep) -{ - return cpu_map__build_map(cpus, corep, cpu_map__get_core, NULL); -} - -int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **numap) -{ - return cpu_map__build_map(cpus, numap, cpu_map__get_node, NULL); + id.node = cpu__get_node(cpu); + return id; } /* setup simple routines to easily access node numbers given a cpu number */ @@ -335,8 +319,8 @@ static void set_max_cpu_num(void) int ret = -1; /* set up default */ - max_cpu_num = 4096; - max_present_cpu_num = 4096; + max_cpu_num.cpu = 4096; + max_present_cpu_num.cpu = 4096; mnt = sysfs__mountpoint(); if (!mnt) @@ -349,7 +333,7 @@ static void set_max_cpu_num(void) goto out; } - ret = get_max_num(path, &max_cpu_num); + ret = get_max_num(path, &max_cpu_num.cpu); if (ret) goto out; @@ -360,11 +344,11 @@ static void set_max_cpu_num(void) goto out; } - ret = get_max_num(path, &max_present_cpu_num); + ret = get_max_num(path, &max_present_cpu_num.cpu); out: if (ret) - pr_err("Failed to read max cpus, using default of %d\n", max_cpu_num); + pr_err("Failed to read max cpus, using default of %d\n", max_cpu_num.cpu); } /* Determine highest possible node in the system for sparse allocation */ @@ -403,31 +387,31 @@ int cpu__max_node(void) return max_node_num; } -int cpu__max_cpu(void) +struct perf_cpu cpu__max_cpu(void) { - if (unlikely(!max_cpu_num)) + if (unlikely(!max_cpu_num.cpu)) set_max_cpu_num(); return max_cpu_num; } -int cpu__max_present_cpu(void) +struct perf_cpu cpu__max_present_cpu(void) { - if (unlikely(!max_present_cpu_num)) + if (unlikely(!max_present_cpu_num.cpu)) set_max_cpu_num(); return max_present_cpu_num; } -int cpu__get_node(int cpu) +int cpu__get_node(struct perf_cpu cpu) { if (unlikely(cpunode_map == NULL)) { pr_debug("cpu_map not initialized\n"); return -1; } - return cpunode_map[cpu]; + return cpunode_map[cpu.cpu]; } static int init_cpunode_map(void) @@ -437,13 +421,13 @@ static int init_cpunode_map(void) set_max_cpu_num(); set_max_node_num(); - cpunode_map = calloc(max_cpu_num, sizeof(int)); + cpunode_map = calloc(max_cpu_num.cpu, sizeof(int)); if (!cpunode_map) { pr_err("%s: calloc failed\n", __func__); return -1; } - for (i = 0; i < max_cpu_num; i++) + for (i = 0; i < max_cpu_num.cpu; i++) cpunode_map[i] = -1; return 0; @@ -502,47 +486,39 @@ int cpu__setup_cpunode_map(void) return 0; } -bool cpu_map__has(struct perf_cpu_map *cpus, int cpu) -{ - return perf_cpu_map__idx(cpus, cpu) != -1; -} - -int cpu_map__cpu(struct perf_cpu_map *cpus, int idx) -{ - return cpus->map[idx]; -} - size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size) { - int i, cpu, start = -1; + int i, start = -1; bool first = true; size_t ret = 0; #define COMMA first ? "" : "," for (i = 0; i < map->nr + 1; i++) { + struct perf_cpu cpu = { .cpu = INT_MAX }; bool last = i == map->nr; - cpu = last ? INT_MAX : map->map[i]; + if (!last) + cpu = map->map[i]; if (start == -1) { start = i; if (last) { ret += snprintf(buf + ret, size - ret, "%s%d", COMMA, - map->map[i]); + map->map[i].cpu); } - } else if (((i - start) != (cpu - map->map[start])) || last) { + } else if (((i - start) != (cpu.cpu - map->map[start].cpu)) || last) { int end = i - 1; if (start == end) { ret += snprintf(buf + ret, size - ret, "%s%d", COMMA, - map->map[start]); + map->map[start].cpu); } else { ret += snprintf(buf + ret, size - ret, "%s%d-%d", COMMA, - map->map[start], map->map[end]); + map->map[start].cpu, map->map[end].cpu); } first = false; start = i; @@ -569,23 +545,23 @@ size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size) int i, cpu; char *ptr = buf; unsigned char *bitmap; - int last_cpu = cpu_map__cpu(map, map->nr - 1); + struct perf_cpu last_cpu = perf_cpu_map__cpu(map, map->nr - 1); if (buf == NULL) return 0; - bitmap = zalloc(last_cpu / 8 + 1); + bitmap = zalloc(last_cpu.cpu / 8 + 1); if (bitmap == NULL) { buf[0] = '\0'; return 0; } for (i = 0; i < map->nr; i++) { - cpu = cpu_map__cpu(map, i); + cpu = perf_cpu_map__cpu(map, i).cpu; bitmap[cpu / 8] |= 1 << (cpu % 8); } - for (cpu = last_cpu / 4 * 4; cpu >= 0; cpu -= 4) { + for (cpu = last_cpu.cpu / 4 * 4; cpu >= 0; cpu -= 4) { unsigned char bits = bitmap[cpu / 8]; if (cpu % 8) @@ -614,32 +590,35 @@ const struct perf_cpu_map *cpu_map__online(void) /* thread unsafe */ return online; } -bool cpu_map__compare_aggr_cpu_id(struct aggr_cpu_id a, struct aggr_cpu_id b) +bool aggr_cpu_id__equal(const struct aggr_cpu_id *a, const struct aggr_cpu_id *b) { - return a.thread == b.thread && - a.node == b.node && - a.socket == b.socket && - a.die == b.die && - a.core == b.core; + return a->thread == b->thread && + a->node == b->node && + a->socket == b->socket && + a->die == b->die && + a->core == b->core && + a->cpu.cpu == b->cpu.cpu; } -bool cpu_map__aggr_cpu_id_is_empty(struct aggr_cpu_id a) +bool aggr_cpu_id__is_empty(const struct aggr_cpu_id *a) { - return a.thread == -1 && - a.node == -1 && - a.socket == -1 && - a.die == -1 && - a.core == -1; + return a->thread == -1 && + a->node == -1 && + a->socket == -1 && + a->die == -1 && + a->core == -1 && + a->cpu.cpu == -1; } -struct aggr_cpu_id cpu_map__empty_aggr_cpu_id(void) +struct aggr_cpu_id aggr_cpu_id__empty(void) { struct aggr_cpu_id ret = { .thread = -1, .node = -1, .socket = -1, .die = -1, - .core = -1 + .core = -1, + .cpu = (struct perf_cpu){ .cpu = -1 }, }; return ret; } diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index a27eeaf086e8..0d3c2006a15d 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -2,71 +2,135 @@ #ifndef __PERF_CPUMAP_H #define __PERF_CPUMAP_H +#include #include #include #include #include +/** Identify where counts are aggregated, -1 implies not to aggregate. */ struct aggr_cpu_id { + /** A value in the range 0 to number of threads. */ int thread; + /** The numa node X as read from /sys/devices/system/node/nodeX. */ int node; + /** + * The socket number as read from + * /sys/devices/system/cpu/cpuX/topology/physical_package_id. + */ int socket; + /** The die id as read from /sys/devices/system/cpu/cpuX/topology/die_id. */ int die; + /** The core id as read from /sys/devices/system/cpu/cpuX/topology/core_id. */ int core; + /** CPU aggregation, note there is one CPU for each SMT thread. */ + struct perf_cpu cpu; }; +/** A collection of aggr_cpu_id values, the "built" version is sorted and uniqued. */ struct cpu_aggr_map { refcount_t refcnt; + /** Number of valid entries. */ int nr; + /** The entries. */ struct aggr_cpu_id map[]; }; struct perf_record_cpu_map_data; struct perf_cpu_map *perf_cpu_map__empty_new(int nr); -struct cpu_aggr_map *cpu_aggr_map__empty_new(int nr); struct perf_cpu_map *cpu_map__new_data(struct perf_record_cpu_map_data *data); size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size); size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size); size_t cpu_map__fprintf(struct perf_cpu_map *map, FILE *fp); -int cpu_map__get_socket_id(int cpu); -struct aggr_cpu_id cpu_map__get_socket(struct perf_cpu_map *map, int idx, void *data); -int cpu_map__get_die_id(int cpu); -struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data); -int cpu_map__get_core_id(int cpu); -struct aggr_cpu_id cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data); -int cpu_map__get_node_id(int cpu); -struct aggr_cpu_id cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data); -int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **sockp); -int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **diep); -int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **corep); -int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **nodep); const struct perf_cpu_map *cpu_map__online(void); /* thread unsafe */ -static inline int cpu_map__socket(struct perf_cpu_map *sock, int s) -{ - if (!sock || s > sock->nr || s < 0) - return 0; - return sock->map[s]; -} - int cpu__setup_cpunode_map(void); int cpu__max_node(void); -int cpu__max_cpu(void); -int cpu__max_present_cpu(void); -int cpu__get_node(int cpu); +struct perf_cpu cpu__max_cpu(void); +struct perf_cpu cpu__max_present_cpu(void); -int cpu_map__build_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **res, - struct aggr_cpu_id (*f)(struct perf_cpu_map *map, int cpu, void *data), - void *data); +/** + * cpu_map__is_dummy - Events associated with a pid, rather than a CPU, use a single dummy map with an entry of -1. + */ +static inline bool cpu_map__is_dummy(struct perf_cpu_map *cpus) +{ + return cpus->nr == 1 && cpus->map[0].cpu == -1; +} -int cpu_map__cpu(struct perf_cpu_map *cpus, int idx); -bool cpu_map__has(struct perf_cpu_map *cpus, int cpu); +/** + * cpu__get_node - Returns the numa node X as read from + * /sys/devices/system/node/nodeX for the given CPU. + */ +int cpu__get_node(struct perf_cpu cpu); +/** + * cpu__get_socket_id - Returns the socket number as read from + * /sys/devices/system/cpu/cpuX/topology/physical_package_id for the given CPU. + */ +int cpu__get_socket_id(struct perf_cpu cpu); +/** + * cpu__get_die_id - Returns the die id as read from + * /sys/devices/system/cpu/cpuX/topology/die_id for the given CPU. + */ +int cpu__get_die_id(struct perf_cpu cpu); +/** + * cpu__get_core_id - Returns the core id as read from + * /sys/devices/system/cpu/cpuX/topology/core_id for the given CPU. + */ +int cpu__get_core_id(struct perf_cpu cpu); -bool cpu_map__compare_aggr_cpu_id(struct aggr_cpu_id a, struct aggr_cpu_id b); -bool cpu_map__aggr_cpu_id_is_empty(struct aggr_cpu_id a); -struct aggr_cpu_id cpu_map__empty_aggr_cpu_id(void); +/** + * cpu_aggr_map__empty_new - Create a cpu_aggr_map of size nr with every entry + * being empty. + */ +struct cpu_aggr_map *cpu_aggr_map__empty_new(int nr); + +typedef struct aggr_cpu_id (*aggr_cpu_id_get_t)(struct perf_cpu cpu, void *data); + +/** + * cpu_aggr_map__new - Create a cpu_aggr_map with an aggr_cpu_id for each cpu in + * cpus. The aggr_cpu_id is created with 'get_id' that may have a data value + * passed to it. The cpu_aggr_map is sorted with duplicate values removed. + */ +struct cpu_aggr_map *cpu_aggr_map__new(const struct perf_cpu_map *cpus, + aggr_cpu_id_get_t get_id, + void *data); + +bool aggr_cpu_id__equal(const struct aggr_cpu_id *a, const struct aggr_cpu_id *b); +bool aggr_cpu_id__is_empty(const struct aggr_cpu_id *a); +struct aggr_cpu_id aggr_cpu_id__empty(void); + + +/** + * aggr_cpu_id__socket - Create an aggr_cpu_id with the socket populated with + * the socket for cpu. The function signature is compatible with + * aggr_cpu_id_get_t. + */ +struct aggr_cpu_id aggr_cpu_id__socket(struct perf_cpu cpu, void *data); +/** + * aggr_cpu_id__die - Create an aggr_cpu_id with the die and socket populated + * with the die and socket for cpu. The function signature is compatible with + * aggr_cpu_id_get_t. + */ +struct aggr_cpu_id aggr_cpu_id__die(struct perf_cpu cpu, void *data); +/** + * aggr_cpu_id__core - Create an aggr_cpu_id with the core, die and socket + * populated with the core, die and socket for cpu. The function signature is + * compatible with aggr_cpu_id_get_t. + */ +struct aggr_cpu_id aggr_cpu_id__core(struct perf_cpu cpu, void *data); +/** + * aggr_cpu_id__core - Create an aggr_cpu_id with the cpu, core, die and socket + * populated with the cpu, core, die and socket for cpu. The function signature + * is compatible with aggr_cpu_id_get_t. + */ +struct aggr_cpu_id aggr_cpu_id__cpu(struct perf_cpu cpu, void *data); +/** + * aggr_cpu_id__node - Create an aggr_cpu_id with the numa node populated for + * cpu. The function signature is compatible with aggr_cpu_id_get_t. + */ +struct aggr_cpu_id aggr_cpu_id__node(struct perf_cpu cpu, void *data); #endif /* __PERF_CPUMAP_H */ diff --git a/tools/perf/util/cputopo.c b/tools/perf/util/cputopo.c index 51b429c86f98..e20b835a1194 100644 --- a/tools/perf/util/cputopo.c +++ b/tools/perf/util/cputopo.c @@ -165,7 +165,8 @@ static bool has_die_topology(void) if (uname(&uts) < 0) return false; - if (strncmp(uts.machine, "x86_64", 6)) + if (strncmp(uts.machine, "x86_64", 6) && + strncmp(uts.machine, "s390x", 5)) return false; scnprintf(filename, MAXPATHLEN, DIE_CPUS_FMT, @@ -187,7 +188,7 @@ struct cpu_topology *cpu_topology__new(void) struct perf_cpu_map *map; bool has_die = has_die_topology(); - ncpus = cpu__max_present_cpu(); + ncpus = cpu__max_present_cpu().cpu; /* build online CPU map */ map = perf_cpu_map__new(NULL); @@ -218,7 +219,7 @@ struct cpu_topology *cpu_topology__new(void) tp->core_cpus_list = addr; for (i = 0; i < nr; i++) { - if (!cpu_map__has(map, i)) + if (!perf_cpu_map__has(map, (struct perf_cpu){ .cpu = i })) continue; ret = build_cpu_topology(tp, i); @@ -333,7 +334,7 @@ struct numa_topology *numa_topology__new(void) tp->nr = nr; for (i = 0; i < nr; i++) { - if (load_numa_node(&tp->nodes[i], node_map->map[i])) { + if (load_numa_node(&tp->nodes[i], node_map->map[i].cpu)) { numa_topology__delete(tp); tp = NULL; break; diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index 2c06abf6dcd2..65e6c22f38e4 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -179,7 +179,7 @@ static int trace_event_printer(enum binary_printer_ops op, break; case BINARY_PRINT_CHAR_DATA: printed += color_fprintf(fp, color, "%c", - isprint(ch) ? ch : '.'); + isprint(ch) && isascii(ch) ? ch : '.'); break; case BINARY_PRINT_CHAR_PAD: printed += color_fprintf(fp, color, " "); diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index b9904896eb97..579e44c59914 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -285,13 +285,13 @@ out_enomem: int perf_env__read_cpu_topology_map(struct perf_env *env) { - int cpu, nr_cpus; + int idx, nr_cpus; if (env->cpu != NULL) return 0; if (env->nr_cpus_avail == 0) - env->nr_cpus_avail = cpu__max_present_cpu(); + env->nr_cpus_avail = cpu__max_present_cpu().cpu; nr_cpus = env->nr_cpus_avail; if (nr_cpus == -1) @@ -301,10 +301,12 @@ int perf_env__read_cpu_topology_map(struct perf_env *env) if (env->cpu == NULL) return -ENOMEM; - for (cpu = 0; cpu < nr_cpus; ++cpu) { - env->cpu[cpu].core_id = cpu_map__get_core_id(cpu); - env->cpu[cpu].socket_id = cpu_map__get_socket_id(cpu); - env->cpu[cpu].die_id = cpu_map__get_die_id(cpu); + for (idx = 0; idx < nr_cpus; ++idx) { + struct perf_cpu cpu = { .cpu = idx }; + + env->cpu[idx].core_id = cpu__get_core_id(cpu); + env->cpu[idx].socket_id = cpu__get_socket_id(cpu); + env->cpu[idx].die_id = cpu__get_die_id(cpu); } env->nr_cpus_avail = nr_cpus; @@ -381,7 +383,7 @@ static int perf_env__read_arch(struct perf_env *env) static int perf_env__read_nr_cpus_avail(struct perf_env *env) { if (env->nr_cpus_avail == 0) - env->nr_cpus_avail = cpu__max_present_cpu(); + env->nr_cpus_avail = cpu__max_present_cpu().cpu; return env->nr_cpus_avail ? 0 : -ENOENT; } @@ -487,7 +489,7 @@ const char *perf_env__pmu_mappings(struct perf_env *env) return env->pmu_mappings; } -int perf_env__numa_node(struct perf_env *env, int cpu) +int perf_env__numa_node(struct perf_env *env, struct perf_cpu cpu) { if (!env->nr_numa_map) { struct numa_node *nn; @@ -495,7 +497,7 @@ int perf_env__numa_node(struct perf_env *env, int cpu) for (i = 0; i < env->nr_numa_nodes; i++) { nn = &env->numa_nodes[i]; - nr = max(nr, perf_cpu_map__max(nn->map)); + nr = max(nr, perf_cpu_map__max(nn->map).cpu); } nr++; @@ -514,13 +516,14 @@ int perf_env__numa_node(struct perf_env *env, int cpu) env->nr_numa_map = nr; for (i = 0; i < env->nr_numa_nodes; i++) { - int tmp, j; + struct perf_cpu tmp; + int j; nn = &env->numa_nodes[i]; - perf_cpu_map__for_each_cpu(j, tmp, nn->map) - env->numa_map[j] = i; + perf_cpu_map__for_each_cpu(tmp, j, nn->map) + env->numa_map[tmp.cpu] = i; } } - return cpu >= 0 && cpu < env->nr_numa_map ? env->numa_map[cpu] : -1; + return cpu.cpu >= 0 && cpu.cpu < env->nr_numa_map ? env->numa_map[cpu.cpu] : -1; } diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h index 163e5ec503a2..a3541f98e1fc 100644 --- a/tools/perf/util/env.h +++ b/tools/perf/util/env.h @@ -4,6 +4,7 @@ #include #include +#include "cpumap.h" #include "rwsem.h" struct perf_cpu_map; @@ -170,5 +171,5 @@ struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env, bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node); struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id); -int perf_env__numa_node(struct perf_env *env, int cpu); +int perf_env__numa_node(struct perf_env *env, struct perf_cpu cpu); #endif /* __PERF_ENV_H */ diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 5f92319ce258..6e88d404b5b3 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -342,36 +342,65 @@ static int evlist__nr_threads(struct evlist *evlist, struct evsel *evsel) return perf_thread_map__nr(evlist->core.threads); } -void evlist__cpu_iter_start(struct evlist *evlist) +struct evlist_cpu_iterator evlist__cpu_begin(struct evlist *evlist, struct affinity *affinity) { - struct evsel *pos; + struct evlist_cpu_iterator itr = { + .container = evlist, + .evsel = evlist__first(evlist), + .cpu_map_idx = 0, + .evlist_cpu_map_idx = 0, + .evlist_cpu_map_nr = perf_cpu_map__nr(evlist->core.all_cpus), + .cpu = (struct perf_cpu){ .cpu = -1}, + .affinity = affinity, + }; - /* - * Reset the per evsel cpu_iter. This is needed because - * each evsel's cpumap may have a different index space, - * and some operations need the index to modify - * the FD xyarray (e.g. open, close) - */ - evlist__for_each_entry(evlist, pos) - pos->cpu_iter = 0; -} - -bool evsel__cpu_iter_skip_no_inc(struct evsel *ev, int cpu) -{ - if (ev->cpu_iter >= ev->core.cpus->nr) - return true; - if (cpu >= 0 && ev->core.cpus->map[ev->cpu_iter] != cpu) - return true; - return false; -} - -bool evsel__cpu_iter_skip(struct evsel *ev, int cpu) -{ - if (!evsel__cpu_iter_skip_no_inc(ev, cpu)) { - ev->cpu_iter++; - return false; + if (itr.affinity) { + itr.cpu = perf_cpu_map__cpu(evlist->core.all_cpus, 0); + affinity__set(itr.affinity, itr.cpu.cpu); + itr.cpu_map_idx = perf_cpu_map__idx(itr.evsel->core.cpus, itr.cpu); + /* + * If this CPU isn't in the evsel's cpu map then advance through + * the list. + */ + if (itr.cpu_map_idx == -1) + evlist_cpu_iterator__next(&itr); } - return true; + return itr; +} + +void evlist_cpu_iterator__next(struct evlist_cpu_iterator *evlist_cpu_itr) +{ + while (evlist_cpu_itr->evsel != evlist__last(evlist_cpu_itr->container)) { + evlist_cpu_itr->evsel = evsel__next(evlist_cpu_itr->evsel); + evlist_cpu_itr->cpu_map_idx = + perf_cpu_map__idx(evlist_cpu_itr->evsel->core.cpus, + evlist_cpu_itr->cpu); + if (evlist_cpu_itr->cpu_map_idx != -1) + return; + } + evlist_cpu_itr->evlist_cpu_map_idx++; + if (evlist_cpu_itr->evlist_cpu_map_idx < evlist_cpu_itr->evlist_cpu_map_nr) { + evlist_cpu_itr->evsel = evlist__first(evlist_cpu_itr->container); + evlist_cpu_itr->cpu = + perf_cpu_map__cpu(evlist_cpu_itr->container->core.all_cpus, + evlist_cpu_itr->evlist_cpu_map_idx); + if (evlist_cpu_itr->affinity) + affinity__set(evlist_cpu_itr->affinity, evlist_cpu_itr->cpu.cpu); + evlist_cpu_itr->cpu_map_idx = + perf_cpu_map__idx(evlist_cpu_itr->evsel->core.cpus, + evlist_cpu_itr->cpu); + /* + * If this CPU isn't in the evsel's cpu map then advance through + * the list. + */ + if (evlist_cpu_itr->cpu_map_idx == -1) + evlist_cpu_iterator__next(evlist_cpu_itr); + } +} + +bool evlist_cpu_iterator__end(const struct evlist_cpu_iterator *evlist_cpu_itr) +{ + return evlist_cpu_itr->evlist_cpu_map_idx >= evlist_cpu_itr->evlist_cpu_map_nr; } static int evsel__strcmp(struct evsel *pos, char *evsel_name) @@ -400,31 +429,26 @@ static int evlist__is_enabled(struct evlist *evlist) static void __evlist__disable(struct evlist *evlist, char *evsel_name) { struct evsel *pos; + struct evlist_cpu_iterator evlist_cpu_itr; struct affinity affinity; - int cpu, i, imm = 0; bool has_imm = false; if (affinity__setup(&affinity) < 0) return; /* Disable 'immediate' events last */ - for (imm = 0; imm <= 1; imm++) { - evlist__for_each_cpu(evlist, i, cpu) { - affinity__set(&affinity, cpu); - - evlist__for_each_entry(evlist, pos) { - if (evsel__strcmp(pos, evsel_name)) - continue; - if (evsel__cpu_iter_skip(pos, cpu)) - continue; - if (pos->disabled || !evsel__is_group_leader(pos) || !pos->core.fd) - continue; - if (pos->immediate) - has_imm = true; - if (pos->immediate != imm) - continue; - evsel__disable_cpu(pos, pos->cpu_iter - 1); - } + for (int imm = 0; imm <= 1; imm++) { + evlist__for_each_cpu(evlist_cpu_itr, evlist, &affinity) { + pos = evlist_cpu_itr.evsel; + if (evsel__strcmp(pos, evsel_name)) + continue; + if (pos->disabled || !evsel__is_group_leader(pos) || !pos->core.fd) + continue; + if (pos->immediate) + has_imm = true; + if (pos->immediate != imm) + continue; + evsel__disable_cpu(pos, evlist_cpu_itr.cpu_map_idx); } if (!has_imm) break; @@ -462,24 +486,19 @@ void evlist__disable_evsel(struct evlist *evlist, char *evsel_name) static void __evlist__enable(struct evlist *evlist, char *evsel_name) { struct evsel *pos; + struct evlist_cpu_iterator evlist_cpu_itr; struct affinity affinity; - int cpu, i; if (affinity__setup(&affinity) < 0) return; - evlist__for_each_cpu(evlist, i, cpu) { - affinity__set(&affinity, cpu); - - evlist__for_each_entry(evlist, pos) { - if (evsel__strcmp(pos, evsel_name)) - continue; - if (evsel__cpu_iter_skip(pos, cpu)) - continue; - if (!evsel__is_group_leader(pos) || !pos->core.fd) - continue; - evsel__enable_cpu(pos, pos->cpu_iter - 1); - } + evlist__for_each_cpu(evlist_cpu_itr, evlist, &affinity) { + pos = evlist_cpu_itr.evsel; + if (evsel__strcmp(pos, evsel_name)) + continue; + if (!evsel__is_group_leader(pos) || !pos->core.fd) + continue; + evsel__enable_cpu(pos, evlist_cpu_itr.cpu_map_idx); } affinity__cleanup(&affinity); evlist__for_each_entry(evlist, pos) { @@ -800,7 +819,7 @@ perf_evlist__mmap_cb_get(struct perf_evlist *_evlist, bool overwrite, int idx) static int perf_evlist__mmap_cb_mmap(struct perf_mmap *_map, struct perf_mmap_param *_mp, - int output, int cpu) + int output, struct perf_cpu cpu) { struct mmap *map = container_of(_map, struct mmap, core); struct mmap_params *mp = container_of(_mp, struct mmap_params, core); @@ -1264,14 +1283,14 @@ void evlist__set_selected(struct evlist *evlist, struct evsel *evsel) void evlist__close(struct evlist *evlist) { struct evsel *evsel; + struct evlist_cpu_iterator evlist_cpu_itr; struct affinity affinity; - int cpu, i; /* * With perf record core.cpus is usually NULL. * Use the old method to handle this for now. */ - if (!evlist->core.cpus) { + if (!evlist->core.cpus || cpu_map__is_dummy(evlist->core.cpus)) { evlist__for_each_entry_reverse(evlist, evsel) evsel__close(evsel); return; @@ -1279,15 +1298,12 @@ void evlist__close(struct evlist *evlist) if (affinity__setup(&affinity) < 0) return; - evlist__for_each_cpu(evlist, i, cpu) { - affinity__set(&affinity, cpu); - evlist__for_each_entry_reverse(evlist, evsel) { - if (evsel__cpu_iter_skip(evsel, cpu)) - continue; - perf_evsel__close_cpu(&evsel->core, evsel->cpu_iter - 1); - } + evlist__for_each_cpu(evlist_cpu_itr, evlist, &affinity) { + perf_evsel__close_cpu(&evlist_cpu_itr.evsel->core, + evlist_cpu_itr.cpu_map_idx); } + affinity__cleanup(&affinity); evlist__for_each_entry_reverse(evlist, evsel) { perf_evsel__free_fd(&evsel->core); diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 97bfb8d0be4f..64cba56fbc74 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -64,6 +64,7 @@ struct evlist { struct evsel *selected; struct events_stats stats; struct perf_env *env; + const char *hybrid_pmu_name; void (*trace_event_sample_raw)(struct evlist *evlist, union perf_event *event, struct perf_sample *sample); @@ -110,6 +111,7 @@ int __evlist__add_default_attrs(struct evlist *evlist, __evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array)) int arch_evlist__add_default_attrs(struct evlist *evlist); +struct evsel *arch_evlist__leader(struct list_head *list); int evlist__add_dummy(struct evlist *evlist); @@ -325,17 +327,53 @@ void evlist__to_front(struct evlist *evlist, struct evsel *move_evsel); #define evlist__for_each_entry_safe(evlist, tmp, evsel) \ __evlist__for_each_entry_safe(&(evlist)->core.entries, tmp, evsel) -#define evlist__for_each_cpu(evlist, index, cpu) \ - evlist__cpu_iter_start(evlist); \ - perf_cpu_map__for_each_cpu (cpu, index, (evlist)->core.all_cpus) +/** Iterator state for evlist__for_each_cpu */ +struct evlist_cpu_iterator { + /** The list being iterated through. */ + struct evlist *container; + /** The current evsel of the iterator. */ + struct evsel *evsel; + /** The CPU map index corresponding to the evsel->core.cpus for the current CPU. */ + int cpu_map_idx; + /** + * The CPU map index corresponding to evlist->core.all_cpus for the + * current CPU. Distinct from cpu_map_idx as the evsel's cpu map may + * contain fewer entries. + */ + int evlist_cpu_map_idx; + /** The number of CPU map entries in evlist->core.all_cpus. */ + int evlist_cpu_map_nr; + /** The current CPU of the iterator. */ + struct perf_cpu cpu; + /** If present, used to set the affinity when switching between CPUs. */ + struct affinity *affinity; +}; + +/** + * evlist__for_each_cpu - without affinity, iterate over the evlist. With + * affinity, iterate over all CPUs and then the evlist + * for each evsel on that CPU. When switching between + * CPUs the affinity is set to the CPU to avoid IPIs + * during syscalls. + * @evlist_cpu_itr: the iterator instance. + * @evlist: evlist instance to iterate. + * @affinity: NULL or used to set the affinity to the current CPU. + */ +#define evlist__for_each_cpu(evlist_cpu_itr, evlist, affinity) \ + for ((evlist_cpu_itr) = evlist__cpu_begin(evlist, affinity); \ + !evlist_cpu_iterator__end(&evlist_cpu_itr); \ + evlist_cpu_iterator__next(&evlist_cpu_itr)) + +/** Returns an iterator set to the first CPU/evsel of evlist. */ +struct evlist_cpu_iterator evlist__cpu_begin(struct evlist *evlist, struct affinity *affinity); +/** Move to next element in iterator, updating CPU, evsel and the affinity. */ +void evlist_cpu_iterator__next(struct evlist_cpu_iterator *evlist_cpu_itr); +/** Returns true when iterator is at the end of the CPUs and evlist. */ +bool evlist_cpu_iterator__end(const struct evlist_cpu_iterator *evlist_cpu_itr); struct evsel *evlist__get_tracking_event(struct evlist *evlist); void evlist__set_tracking_event(struct evlist *evlist, struct evsel *tracking_evsel); -void evlist__cpu_iter_start(struct evlist *evlist); -bool evsel__cpu_iter_skip(struct evsel *ev, int cpu); -bool evsel__cpu_iter_skip_no_inc(struct evsel *ev, int cpu); - struct evsel *evlist__find_evsel_by_str(struct evlist *evlist, const char *str); struct evsel *evlist__event2evsel(struct evlist *evlist, union perf_event *event); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index f29d37004f55..2f6b18af49e5 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1372,9 +1372,9 @@ int evsel__append_addr_filter(struct evsel *evsel, const char *filter) } /* Caller has to clear disabled after going through all CPUs. */ -int evsel__enable_cpu(struct evsel *evsel, int cpu) +int evsel__enable_cpu(struct evsel *evsel, int cpu_map_idx) { - return perf_evsel__enable_cpu(&evsel->core, cpu); + return perf_evsel__enable_cpu(&evsel->core, cpu_map_idx); } int evsel__enable(struct evsel *evsel) @@ -1387,9 +1387,9 @@ int evsel__enable(struct evsel *evsel) } /* Caller has to set disabled after going through all CPUs. */ -int evsel__disable_cpu(struct evsel *evsel, int cpu) +int evsel__disable_cpu(struct evsel *evsel, int cpu_map_idx) { - return perf_evsel__disable_cpu(&evsel->core, cpu); + return perf_evsel__disable_cpu(&evsel->core, cpu_map_idx); } int evsel__disable(struct evsel *evsel) @@ -1455,7 +1455,7 @@ void evsel__delete(struct evsel *evsel) free(evsel); } -void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread, +void evsel__compute_deltas(struct evsel *evsel, int cpu_map_idx, int thread, struct perf_counts_values *count) { struct perf_counts_values tmp; @@ -1463,12 +1463,12 @@ void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread, if (!evsel->prev_raw_counts) return; - if (cpu == -1) { + if (cpu_map_idx == -1) { tmp = evsel->prev_raw_counts->aggr; evsel->prev_raw_counts->aggr = *count; } else { - tmp = *perf_counts(evsel->prev_raw_counts, cpu, thread); - *perf_counts(evsel->prev_raw_counts, cpu, thread) = *count; + tmp = *perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread); + *perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread) = *count; } count->val = count->val - tmp.val; @@ -1476,46 +1476,28 @@ void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread, count->run = count->run - tmp.run; } -void perf_counts_values__scale(struct perf_counts_values *count, - bool scale, s8 *pscaled) +static int evsel__read_one(struct evsel *evsel, int cpu_map_idx, int thread) { - s8 scaled = 0; + struct perf_counts_values *count = perf_counts(evsel->counts, cpu_map_idx, thread); - if (scale) { - if (count->run == 0) { - scaled = -1; - count->val = 0; - } else if (count->run < count->ena) { - scaled = 1; - count->val = (u64)((double) count->val * count->ena / count->run); - } - } - - if (pscaled) - *pscaled = scaled; + return perf_evsel__read(&evsel->core, cpu_map_idx, thread, count); } -static int evsel__read_one(struct evsel *evsel, int cpu, int thread) -{ - struct perf_counts_values *count = perf_counts(evsel->counts, cpu, thread); - - return perf_evsel__read(&evsel->core, cpu, thread, count); -} - -static void evsel__set_count(struct evsel *counter, int cpu, int thread, u64 val, u64 ena, u64 run) +static void evsel__set_count(struct evsel *counter, int cpu_map_idx, int thread, + u64 val, u64 ena, u64 run) { struct perf_counts_values *count; - count = perf_counts(counter->counts, cpu, thread); + count = perf_counts(counter->counts, cpu_map_idx, thread); count->val = val; count->ena = ena; count->run = run; - perf_counts__set_loaded(counter->counts, cpu, thread, true); + perf_counts__set_loaded(counter->counts, cpu_map_idx, thread, true); } -static int evsel__process_group_data(struct evsel *leader, int cpu, int thread, u64 *data) +static int evsel__process_group_data(struct evsel *leader, int cpu_map_idx, int thread, u64 *data) { u64 read_format = leader->core.attr.read_format; struct sample_read_value *v; @@ -1534,7 +1516,7 @@ static int evsel__process_group_data(struct evsel *leader, int cpu, int thread, v = (struct sample_read_value *) data; - evsel__set_count(leader, cpu, thread, v[0].value, ena, run); + evsel__set_count(leader, cpu_map_idx, thread, v[0].value, ena, run); for (i = 1; i < nr; i++) { struct evsel *counter; @@ -1543,13 +1525,13 @@ static int evsel__process_group_data(struct evsel *leader, int cpu, int thread, if (!counter) return -EINVAL; - evsel__set_count(counter, cpu, thread, v[i].value, ena, run); + evsel__set_count(counter, cpu_map_idx, thread, v[i].value, ena, run); } return 0; } -static int evsel__read_group(struct evsel *leader, int cpu, int thread) +static int evsel__read_group(struct evsel *leader, int cpu_map_idx, int thread) { struct perf_stat_evsel *ps = leader->stats; u64 read_format = leader->core.attr.read_format; @@ -1570,67 +1552,67 @@ static int evsel__read_group(struct evsel *leader, int cpu, int thread) ps->group_data = data; } - if (FD(leader, cpu, thread) < 0) + if (FD(leader, cpu_map_idx, thread) < 0) return -EINVAL; - if (readn(FD(leader, cpu, thread), data, size) <= 0) + if (readn(FD(leader, cpu_map_idx, thread), data, size) <= 0) return -errno; - return evsel__process_group_data(leader, cpu, thread, data); + return evsel__process_group_data(leader, cpu_map_idx, thread, data); } -int evsel__read_counter(struct evsel *evsel, int cpu, int thread) +int evsel__read_counter(struct evsel *evsel, int cpu_map_idx, int thread) { u64 read_format = evsel->core.attr.read_format; if (read_format & PERF_FORMAT_GROUP) - return evsel__read_group(evsel, cpu, thread); + return evsel__read_group(evsel, cpu_map_idx, thread); - return evsel__read_one(evsel, cpu, thread); + return evsel__read_one(evsel, cpu_map_idx, thread); } -int __evsel__read_on_cpu(struct evsel *evsel, int cpu, int thread, bool scale) +int __evsel__read_on_cpu(struct evsel *evsel, int cpu_map_idx, int thread, bool scale) { struct perf_counts_values count; size_t nv = scale ? 3 : 1; - if (FD(evsel, cpu, thread) < 0) + if (FD(evsel, cpu_map_idx, thread) < 0) return -EINVAL; - if (evsel->counts == NULL && evsel__alloc_counts(evsel, cpu + 1, thread + 1) < 0) + if (evsel->counts == NULL && evsel__alloc_counts(evsel) < 0) return -ENOMEM; - if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) <= 0) + if (readn(FD(evsel, cpu_map_idx, thread), &count, nv * sizeof(u64)) <= 0) return -errno; - evsel__compute_deltas(evsel, cpu, thread, &count); + evsel__compute_deltas(evsel, cpu_map_idx, thread, &count); perf_counts_values__scale(&count, scale, NULL); - *perf_counts(evsel->counts, cpu, thread) = count; + *perf_counts(evsel->counts, cpu_map_idx, thread) = count; return 0; } static int evsel__match_other_cpu(struct evsel *evsel, struct evsel *other, - int cpu) + int cpu_map_idx) { - int cpuid; + struct perf_cpu cpu; - cpuid = perf_cpu_map__cpu(evsel->core.cpus, cpu); - return perf_cpu_map__idx(other->core.cpus, cpuid); + cpu = perf_cpu_map__cpu(evsel->core.cpus, cpu_map_idx); + return perf_cpu_map__idx(other->core.cpus, cpu); } -static int evsel__hybrid_group_cpu(struct evsel *evsel, int cpu) +static int evsel__hybrid_group_cpu_map_idx(struct evsel *evsel, int cpu_map_idx) { struct evsel *leader = evsel__leader(evsel); if ((evsel__is_hybrid(evsel) && !evsel__is_hybrid(leader)) || (!evsel__is_hybrid(evsel) && evsel__is_hybrid(leader))) { - return evsel__match_other_cpu(evsel, leader, cpu); + return evsel__match_other_cpu(evsel, leader, cpu_map_idx); } - return cpu; + return cpu_map_idx; } -static int get_group_fd(struct evsel *evsel, int cpu, int thread) +static int get_group_fd(struct evsel *evsel, int cpu_map_idx, int thread) { struct evsel *leader = evsel__leader(evsel); int fd; @@ -1644,11 +1626,11 @@ static int get_group_fd(struct evsel *evsel, int cpu, int thread) */ BUG_ON(!leader->core.fd); - cpu = evsel__hybrid_group_cpu(evsel, cpu); - if (cpu == -1) + cpu_map_idx = evsel__hybrid_group_cpu_map_idx(evsel, cpu_map_idx); + if (cpu_map_idx == -1) return -1; - fd = FD(leader, cpu, thread); + fd = FD(leader, cpu_map_idx, thread); BUG_ON(fd == -1); return fd; @@ -1662,16 +1644,16 @@ static void evsel__remove_fd(struct evsel *pos, int nr_cpus, int nr_threads, int } static int update_fds(struct evsel *evsel, - int nr_cpus, int cpu_idx, + int nr_cpus, int cpu_map_idx, int nr_threads, int thread_idx) { struct evsel *pos; - if (cpu_idx >= nr_cpus || thread_idx >= nr_threads) + if (cpu_map_idx >= nr_cpus || thread_idx >= nr_threads) return -EINVAL; evlist__for_each_entry(evsel->evlist, pos) { - nr_cpus = pos != evsel ? nr_cpus : cpu_idx; + nr_cpus = pos != evsel ? nr_cpus : cpu_map_idx; evsel__remove_fd(pos, nr_cpus, nr_threads, thread_idx); @@ -1685,10 +1667,10 @@ static int update_fds(struct evsel *evsel, return 0; } -bool evsel__ignore_missing_thread(struct evsel *evsel, - int nr_cpus, int cpu, - struct perf_thread_map *threads, - int thread, int err) +static bool evsel__ignore_missing_thread(struct evsel *evsel, + int nr_cpus, int cpu_map_idx, + struct perf_thread_map *threads, + int thread, int err) { pid_t ignore_pid = perf_thread_map__pid(threads, thread); @@ -1711,7 +1693,7 @@ bool evsel__ignore_missing_thread(struct evsel *evsel, * We should remove fd for missing_thread first * because thread_map__remove() will decrease threads->nr. */ - if (update_fds(evsel, nr_cpus, cpu, threads->nr, thread)) + if (update_fds(evsel, nr_cpus, cpu_map_idx, threads->nr, thread)) return false; if (thread_map__remove(threads, thread)) @@ -1993,9 +1975,9 @@ bool evsel__increase_rlimit(enum rlimit_action *set_rlimit) static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, struct perf_thread_map *threads, - int start_cpu, int end_cpu) + int start_cpu_map_idx, int end_cpu_map_idx) { - int cpu, thread, nthreads; + int idx, thread, nthreads; int pid = -1, err, old_errno; enum rlimit_action set_rlimit = NO_CHANGE; @@ -2022,7 +2004,7 @@ fallback_missing_features: display_attr(&evsel->core.attr); - for (cpu = start_cpu; cpu < end_cpu; cpu++) { + for (idx = start_cpu_map_idx; idx < end_cpu_map_idx; idx++) { for (thread = 0; thread < nthreads; thread++) { int fd, group_fd; @@ -2033,17 +2015,17 @@ retry_open: if (!evsel->cgrp && !evsel->core.system_wide) pid = perf_thread_map__pid(threads, thread); - group_fd = get_group_fd(evsel, cpu, thread); + group_fd = get_group_fd(evsel, idx, thread); test_attr__ready(); pr_debug2_peo("sys_perf_event_open: pid %d cpu %d group_fd %d flags %#lx", - pid, cpus->map[cpu], group_fd, evsel->open_flags); + pid, cpus->map[idx].cpu, group_fd, evsel->open_flags); - fd = sys_perf_event_open(&evsel->core.attr, pid, cpus->map[cpu], + fd = sys_perf_event_open(&evsel->core.attr, pid, cpus->map[idx].cpu, group_fd, evsel->open_flags); - FD(evsel, cpu, thread) = fd; + FD(evsel, idx, thread) = fd; if (fd < 0) { err = -errno; @@ -2053,10 +2035,10 @@ retry_open: goto try_fallback; } - bpf_counter__install_pe(evsel, cpu, fd); + bpf_counter__install_pe(evsel, idx, fd); if (unlikely(test_attr__enabled)) { - test_attr__open(&evsel->core.attr, pid, cpus->map[cpu], + test_attr__open(&evsel->core.attr, pid, cpus->map[idx], fd, group_fd, evsel->open_flags); } @@ -2097,7 +2079,7 @@ try_fallback: if (evsel__precise_ip_fallback(evsel)) goto retry_open; - if (evsel__ignore_missing_thread(evsel, cpus->nr, cpu, threads, thread, err)) { + if (evsel__ignore_missing_thread(evsel, cpus->nr, idx, threads, thread, err)) { /* We just removed 1 thread, so lower the upper nthreads limit. */ nthreads--; @@ -2112,7 +2094,7 @@ try_fallback: if (err == -EMFILE && evsel__increase_rlimit(&set_rlimit)) goto retry_open; - if (err != -EINVAL || cpu > 0 || thread > 0) + if (err != -EINVAL || idx > 0 || thread > 0) goto out_close; if (evsel__detect_missing_features(evsel)) @@ -2124,12 +2106,12 @@ out_close: old_errno = errno; do { while (--thread >= 0) { - if (FD(evsel, cpu, thread) >= 0) - close(FD(evsel, cpu, thread)); - FD(evsel, cpu, thread) = -1; + if (FD(evsel, idx, thread) >= 0) + close(FD(evsel, idx, thread)); + FD(evsel, idx, thread) = -1; } thread = nthreads; - } while (--cpu >= 0); + } while (--idx >= 0); errno = old_errno; return err; } @@ -2146,13 +2128,13 @@ void evsel__close(struct evsel *evsel) perf_evsel__free_id(&evsel->core); } -int evsel__open_per_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int cpu) +int evsel__open_per_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int cpu_map_idx) { - if (cpu == -1) + if (cpu_map_idx == -1) return evsel__open_cpu(evsel, cpus, NULL, 0, cpus ? cpus->nr : 1); - return evsel__open_cpu(evsel, cpus, NULL, cpu, cpu + 1); + return evsel__open_cpu(evsel, cpus, NULL, cpu_map_idx, cpu_map_idx + 1); } int evsel__open_per_thread(struct evsel *evsel, struct perf_thread_map *threads) @@ -2952,6 +2934,10 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target, return scnprintf(msg, size, "wrong clockid (%d).", clockid); if (perf_missing_features.aux_output) return scnprintf(msg, size, "The 'aux_output' feature is not supported, update the kernel."); + if (!target__has_cpu(target)) + return scnprintf(msg, size, + "Invalid event (%s) in per-thread mode, enable system wide with '-a'.", + evsel__name(evsel)); break; case ENODATA: return scnprintf(msg, size, "Cannot collect data source with the load latency event alone. " @@ -2975,15 +2961,15 @@ struct perf_env *evsel__env(struct evsel *evsel) static int store_evsel_ids(struct evsel *evsel, struct evlist *evlist) { - int cpu, thread; + int cpu_map_idx, thread; - for (cpu = 0; cpu < xyarray__max_x(evsel->core.fd); cpu++) { + for (cpu_map_idx = 0; cpu_map_idx < xyarray__max_x(evsel->core.fd); cpu_map_idx++) { for (thread = 0; thread < xyarray__max_y(evsel->core.fd); thread++) { - int fd = FD(evsel, cpu, thread); + int fd = FD(evsel, cpu_map_idx, thread); if (perf_evlist__id_add_fd(&evlist->core, &evsel->core, - cpu, thread, fd) < 0) + cpu_map_idx, thread, fd) < 0) return -1; } } diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 29d49a8c1e92..5720ceebffac 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -121,7 +121,6 @@ struct evsel { bool errored; struct hashmap *per_pkg_mask; int err; - int cpu_iter; struct { evsel__sb_cb_t *cb; void *data; @@ -195,9 +194,6 @@ static inline int evsel__nr_cpus(struct evsel *evsel) return evsel__cpus(evsel)->nr; } -void perf_counts_values__scale(struct perf_counts_values *count, - bool scale, s8 *pscaled); - void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread, struct perf_counts_values *count); @@ -288,12 +284,12 @@ void arch_evsel__fixup_new_cycles(struct perf_event_attr *attr); int evsel__set_filter(struct evsel *evsel, const char *filter); int evsel__append_tp_filter(struct evsel *evsel, const char *filter); int evsel__append_addr_filter(struct evsel *evsel, const char *filter); -int evsel__enable_cpu(struct evsel *evsel, int cpu); +int evsel__enable_cpu(struct evsel *evsel, int cpu_map_idx); int evsel__enable(struct evsel *evsel); int evsel__disable(struct evsel *evsel); -int evsel__disable_cpu(struct evsel *evsel, int cpu); +int evsel__disable_cpu(struct evsel *evsel, int cpu_map_idx); -int evsel__open_per_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int cpu); +int evsel__open_per_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int cpu_map_idx); int evsel__open_per_thread(struct evsel *evsel, struct perf_thread_map *threads); int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus, struct perf_thread_map *threads); @@ -305,10 +301,6 @@ bool evsel__detect_missing_features(struct evsel *evsel); enum rlimit_action { NO_CHANGE, SET_TO_MAX, INCREASED_MAX }; bool evsel__increase_rlimit(enum rlimit_action *set_rlimit); -bool evsel__ignore_missing_thread(struct evsel *evsel, - int nr_cpus, int cpu, - struct perf_thread_map *threads, - int thread, int err); bool evsel__precise_ip_fallback(struct evsel *evsel); struct perf_sample; @@ -337,32 +329,32 @@ static inline bool evsel__match2(struct evsel *e1, struct evsel *e2) (e1->core.attr.config == e2->core.attr.config); } -int evsel__read_counter(struct evsel *evsel, int cpu, int thread); +int evsel__read_counter(struct evsel *evsel, int cpu_map_idx, int thread); -int __evsel__read_on_cpu(struct evsel *evsel, int cpu, int thread, bool scale); +int __evsel__read_on_cpu(struct evsel *evsel, int cpu_map_idx, int thread, bool scale); /** * evsel__read_on_cpu - Read out the results on a CPU and thread * * @evsel - event selector to read value - * @cpu - CPU of interest + * @cpu_map_idx - CPU of interest * @thread - thread of interest */ -static inline int evsel__read_on_cpu(struct evsel *evsel, int cpu, int thread) +static inline int evsel__read_on_cpu(struct evsel *evsel, int cpu_map_idx, int thread) { - return __evsel__read_on_cpu(evsel, cpu, thread, false); + return __evsel__read_on_cpu(evsel, cpu_map_idx, thread, false); } /** * evsel__read_on_cpu_scaled - Read out the results on a CPU and thread, scaled * * @evsel - event selector to read value - * @cpu - CPU of interest + * @cpu_map_idx - CPU of interest * @thread - thread of interest */ -static inline int evsel__read_on_cpu_scaled(struct evsel *evsel, int cpu, int thread) +static inline int evsel__read_on_cpu_scaled(struct evsel *evsel, int cpu_map_idx, int thread) { - return __evsel__read_on_cpu(evsel, cpu, thread, true); + return __evsel__read_on_cpu(evsel, cpu_map_idx, thread, true); } int evsel__parse_sample(struct evsel *evsel, union perf_event *event, diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c index 666b59baeb70..675f318ce7c1 100644 --- a/tools/perf/util/expr.c +++ b/tools/perf/util/expr.c @@ -405,12 +405,17 @@ double expr_id_data__source_count(const struct expr_id_data *data) double expr__get_literal(const char *literal) { static struct cpu_topology *topology; + double result = NAN; - if (!strcmp("#smt_on", literal)) - return smt_on() > 0 ? 1.0 : 0.0; + if (!strcasecmp("#smt_on", literal)) { + result = smt_on() > 0 ? 1.0 : 0.0; + goto out; + } - if (!strcmp("#num_cpus", literal)) - return cpu__max_present_cpu(); + if (!strcmp("#num_cpus", literal)) { + result = cpu__max_present_cpu().cpu; + goto out; + } /* * Assume that topology strings are consistent, such as CPUs "0-1" @@ -422,16 +427,24 @@ double expr__get_literal(const char *literal) topology = cpu_topology__new(); if (!topology) { pr_err("Error creating CPU topology"); - return NAN; + goto out; } } - if (!strcmp("#num_packages", literal)) - return topology->package_cpus_lists; - if (!strcmp("#num_dies", literal)) - return topology->die_cpus_lists; - if (!strcmp("#num_cores", literal)) - return topology->core_cpus_lists; + if (!strcmp("#num_packages", literal)) { + result = topology->package_cpus_lists; + goto out; + } + if (!strcmp("#num_dies", literal)) { + result = topology->die_cpus_lists; + goto out; + } + if (!strcmp("#num_cores", literal)) { + result = topology->core_cpus_lists; + goto out; + } pr_err("Unrecognized literal '%s'", literal); - return NAN; +out: + pr_debug2("literal: %s = %f\n", literal, result); + return result; } diff --git a/tools/perf/util/ftrace.h b/tools/perf/util/ftrace.h new file mode 100644 index 000000000000..887f68a185f7 --- /dev/null +++ b/tools/perf/util/ftrace.h @@ -0,0 +1,81 @@ +#ifndef __PERF_FTRACE_H__ +#define __PERF_FTRACE_H__ + +#include + +#include "target.h" + +struct evlist; + +struct perf_ftrace { + struct evlist *evlist; + struct target target; + const char *tracer; + struct list_head filters; + struct list_head notrace; + struct list_head graph_funcs; + struct list_head nograph_funcs; + unsigned long percpu_buffer_size; + bool inherit; + int graph_depth; + int func_stack_trace; + int func_irq_info; + int graph_nosleep_time; + int graph_noirqs; + int graph_verbose; + int graph_thresh; + unsigned int initial_delay; +}; + +struct filter_entry { + struct list_head list; + char name[]; +}; + +#define NUM_BUCKET 22 /* 20 + 2 (for outliers in both direction) */ + +#ifdef HAVE_BPF_SKEL + +int perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace); +int perf_ftrace__latency_start_bpf(struct perf_ftrace *ftrace); +int perf_ftrace__latency_stop_bpf(struct perf_ftrace *ftrace); +int perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace, + int buckets[]); +int perf_ftrace__latency_cleanup_bpf(struct perf_ftrace *ftrace); + +#else /* !HAVE_BPF_SKEL */ + +static inline int +perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace __maybe_unused) +{ + return -1; +} + +static inline int +perf_ftrace__latency_start_bpf(struct perf_ftrace *ftrace __maybe_unused) +{ + return -1; +} + +static inline int +perf_ftrace__latency_stop_bpf(struct perf_ftrace *ftrace __maybe_unused) +{ + return -1; +} + +static inline int +perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace __maybe_unused, + int buckets[] __maybe_unused) +{ + return -1; +} + +static inline int +perf_ftrace__latency_cleanup_bpf(struct perf_ftrace *ftrace __maybe_unused) +{ + return -1; +} + +#endif /* HAVE_BPF_SKEL */ + +#endif /* __PERF_FTRACE_H__ */ diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index e3c1a532d059..6da12e522edc 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -472,7 +472,7 @@ static int write_nrcpus(struct feat_fd *ff, u32 nrc, nra; int ret; - nrc = cpu__max_present_cpu(); + nrc = cpu__max_present_cpu().cpu; nr = sysconf(_SC_NPROCESSORS_ONLN); if (nr < 0) @@ -1163,7 +1163,7 @@ static int build_caches(struct cpu_cache_level caches[], u32 *cntp) u32 nr, cpu; u16 level; - nr = cpu__max_cpu(); + nr = cpu__max_cpu().cpu; for (cpu = 0; cpu < nr; cpu++) { for (level = 0; level < MAX_CACHE_LVL; level++) { @@ -1195,7 +1195,7 @@ static int build_caches(struct cpu_cache_level caches[], u32 *cntp) static int write_cache(struct feat_fd *ff, struct evlist *evlist __maybe_unused) { - u32 max_caches = cpu__max_cpu() * MAX_CACHE_LVL; + u32 max_caches = cpu__max_cpu().cpu * MAX_CACHE_LVL; struct cpu_cache_level caches[max_caches]; u32 cnt = 0, i, version = 1; int ret; diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index b776465e04ef..0a8033b09e28 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -211,7 +211,9 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) hists__new_col_len(hists, HISTC_MEM_BLOCKED, 10); hists__new_col_len(hists, HISTC_LOCAL_INS_LAT, 13); hists__new_col_len(hists, HISTC_GLOBAL_INS_LAT, 13); - hists__new_col_len(hists, HISTC_P_STAGE_CYC, 13); + hists__new_col_len(hists, HISTC_LOCAL_P_STAGE_CYC, 13); + hists__new_col_len(hists, HISTC_GLOBAL_P_STAGE_CYC, 13); + if (symbol_conf.nanosecs) hists__new_col_len(hists, HISTC_TIME, 16); else diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 621f35ae1efa..2a15e22fb89c 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -75,7 +75,8 @@ enum hist_column { HISTC_MEM_BLOCKED, HISTC_LOCAL_INS_LAT, HISTC_GLOBAL_INS_LAT, - HISTC_P_STAGE_CYC, + HISTC_LOCAL_P_STAGE_CYC, + HISTC_GLOBAL_P_STAGE_CYC, HISTC_NR_COLS, /* Last entry */ }; diff --git a/tools/perf/util/libunwind/arm64.c b/tools/perf/util/libunwind/arm64.c index c397be0c2e32..15f60fd09424 100644 --- a/tools/perf/util/libunwind/arm64.c +++ b/tools/perf/util/libunwind/arm64.c @@ -23,7 +23,9 @@ #include "unwind.h" #include "libunwind-aarch64.h" +#define perf_event_arm_regs perf_event_arm64_regs #include <../../../../arch/arm64/include/uapi/asm/perf_regs.h> +#undef perf_event_arm_regs #include "../../arch/arm64/util/unwind-libunwind.c" /* NO_LIBUNWIND_DEBUG_FRAME is a feature flag for local libunwind, diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index fb8496df8432..3901440aeff9 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -34,6 +34,7 @@ #include "bpf-event.h" #include // page_size #include "cgroup.h" +#include "arm64-frame-pointer-unwind-support.h" #include #include @@ -2710,6 +2711,15 @@ static int find_prev_cpumode(struct ip_callchain *chain, struct thread *thread, return err; } +static u64 get_leaf_frame_caller(struct perf_sample *sample, + struct thread *thread, int usr_idx) +{ + if (machine__normalized_is(thread->maps->machine, "arm64")) + return get_leaf_frame_caller_aarch64(sample, thread, usr_idx); + else + return 0; +} + static int thread__resolve_callchain_sample(struct thread *thread, struct callchain_cursor *cursor, struct evsel *evsel, @@ -2723,9 +2733,10 @@ static int thread__resolve_callchain_sample(struct thread *thread, struct ip_callchain *chain = sample->callchain; int chain_nr = 0; u8 cpumode = PERF_RECORD_MISC_USER; - int i, j, err, nr_entries; + int i, j, err, nr_entries, usr_idx; int skip_idx = -1; int first_call = 0; + u64 leaf_frame_caller; if (chain) chain_nr = chain->nr; @@ -2850,6 +2861,34 @@ check_calls: continue; } + /* + * PERF_CONTEXT_USER allows us to locate where the user stack ends. + * Depending on callchain_param.order and the position of PERF_CONTEXT_USER, + * the index will be different in order to add the missing frame + * at the right place. + */ + + usr_idx = callchain_param.order == ORDER_CALLEE ? j-2 : j-1; + + if (usr_idx >= 0 && chain->ips[usr_idx] == PERF_CONTEXT_USER) { + + leaf_frame_caller = get_leaf_frame_caller(sample, thread, usr_idx); + + /* + * check if leaf_frame_Caller != ip to not add the same + * value twice. + */ + + if (leaf_frame_caller && leaf_frame_caller != ip) { + + err = add_callchain_ip(thread, cursor, parent, + root_al, &cpumode, leaf_frame_caller, + false, NULL, NULL, 0); + if (err) + return (err < 0) ? err : 0; + } + } + err = add_callchain_ip(thread, cursor, parent, root_al, &cpumode, ip, false, NULL, NULL, 0); @@ -3079,14 +3118,19 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid, } /* - * Compares the raw arch string. N.B. see instead perf_env__arch() if a - * normalized arch is needed. + * Compares the raw arch string. N.B. see instead perf_env__arch() or + * machine__normalized_is() if a normalized arch is needed. */ bool machine__is(struct machine *machine, const char *arch) { return machine && !strcmp(perf_env__raw_arch(machine->env), arch); } +bool machine__normalized_is(struct machine *machine, const char *arch) +{ + return machine && !strcmp(perf_env__arch(machine->env), arch); +} + int machine__nr_cpus_avail(struct machine *machine) { return machine ? perf_env__nr_cpus_avail(machine->env) : 0; diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index a143087eeb47..c5a45dc8df4c 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -208,6 +208,7 @@ static inline bool machine__is_host(struct machine *machine) } bool machine__is(struct machine *machine, const char *arch); +bool machine__normalized_is(struct machine *machine, const char *arch); int machine__nr_cpus_avail(struct machine *machine); struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid); diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index 3167b4628b6d..ed0ab838bcc5 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -309,6 +309,9 @@ static const char * const mem_hops[] = { * to be set with mem_hops field. */ "core, same node", + "node, same socket", + "socket, same board", + "board", }; int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info) @@ -316,7 +319,7 @@ int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info) size_t i, l = 0; u64 m = PERF_MEM_LVL_NA; u64 hit, miss; - int printed; + int printed = 0; if (mem_info) m = mem_info->data_src.mem_lvl; @@ -335,18 +338,22 @@ int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info) l += 7; } - if (mem_info && mem_info->data_src.mem_hops) + /* + * Incase mem_hops field is set, we can skip printing data source via + * PERF_MEM_LVL namespace. + */ + if (mem_info && mem_info->data_src.mem_hops) { l += scnprintf(out + l, sz - l, "%s ", mem_hops[mem_info->data_src.mem_hops]); - - printed = 0; - for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) { - if (!(m & 0x1)) - continue; - if (printed++) { - strcat(out, " or "); - l += 4; + } else { + for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) { + if (!(m & 0x1)) + continue; + if (printed++) { + strcat(out, " or "); + l += 4; + } + l += scnprintf(out + l, sz - l, mem_lvl[i]); } - l += scnprintf(out + l, sz - l, mem_lvl[i]); } if (mem_info && mem_info->data_src.mem_lvl_num) { diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index fffe02aae3ed..d8492e339521 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -209,8 +209,8 @@ static struct metric *metric__new(const struct pmu_event *pe, m->metric_name = pe->metric_name; m->modifier = modifier ? strdup(modifier) : NULL; if (modifier && !m->modifier) { - free(m); expr__ctx_free(m->pctx); + free(m); return NULL; } m->metric_expr = pe->metric_expr; @@ -314,7 +314,7 @@ static int setup_metric_events(struct hashmap *ids, */ metric_id = evsel__metric_id(ev); evlist__for_each_entry_continue(metric_evlist, ev) { - if (!strcmp(evsel__metric_id(metric_events[i]), metric_id)) + if (!strcmp(evsel__metric_id(ev), metric_id)) ev->metric_leader = metric_events[i]; } } @@ -1115,13 +1115,27 @@ out: return ret; } +/** + * metric_list_cmp - list_sort comparator that sorts metrics with more events to + * the front. duration_time is excluded from the count. + */ static int metric_list_cmp(void *priv __maybe_unused, const struct list_head *l, const struct list_head *r) { const struct metric *left = container_of(l, struct metric, nd); const struct metric *right = container_of(r, struct metric, nd); + struct expr_id_data *data; + int left_count, right_count; - return hashmap__size(right->pctx->ids) - hashmap__size(left->pctx->ids); + left_count = hashmap__size(left->pctx->ids); + if (!expr__get_id(left->pctx, "duration_time", &data)) + left_count--; + + right_count = hashmap__size(right->pctx->ids); + if (!expr__get_id(right->pctx, "duration_time", &data)) + right_count--; + + return right_count - left_count; } /** @@ -1299,14 +1313,16 @@ err_out: /** * parse_ids - Build the event string for the ids and parse them creating an * evlist. The encoded metric_ids are decoded. + * @metric_no_merge: is metric sharing explicitly disabled. * @fake_pmu: used when testing metrics not supported by the current CPU. * @ids: the event identifiers parsed from a metric. * @modifier: any modifiers added to the events. * @has_constraint: false if events should be placed in a weak group. * @out_evlist: the created list of events. */ -static int parse_ids(struct perf_pmu *fake_pmu, struct expr_parse_ctx *ids, - const char *modifier, bool has_constraint, struct evlist **out_evlist) +static int parse_ids(bool metric_no_merge, struct perf_pmu *fake_pmu, + struct expr_parse_ctx *ids, const char *modifier, + bool has_constraint, struct evlist **out_evlist) { struct parse_events_error parse_error; struct evlist *parsed_evlist; @@ -1314,12 +1330,19 @@ static int parse_ids(struct perf_pmu *fake_pmu, struct expr_parse_ctx *ids, int ret; *out_evlist = NULL; - if (hashmap__size(ids->ids) == 0) { + if (!metric_no_merge || hashmap__size(ids->ids) == 0) { char *tmp; /* - * No ids/events in the expression parsing context. Events may - * have been removed because of constant evaluation, e.g.: - * event1 if #smt_on else 0 + * We may fail to share events between metrics because + * duration_time isn't present in one metric. For example, a + * ratio of cache misses doesn't need duration_time but the same + * events may be used for a misses per second. Events without + * sharing implies multiplexing, that is best avoided, so place + * duration_time in every group. + * + * Also, there may be no ids/events in the expression parsing + * context because of constant evaluation, e.g.: + * event1 if #smt_on else 0 * Add a duration_time event to avoid a parse error on an empty * string. */ @@ -1387,7 +1410,8 @@ static int parse_groups(struct evlist *perf_evlist, const char *str, ret = build_combined_expr_ctx(&metric_list, &combined); if (!ret && combined && hashmap__size(combined->ids)) { - ret = parse_ids(fake_pmu, combined, /*modifier=*/NULL, + ret = parse_ids(metric_no_merge, fake_pmu, combined, + /*modifier=*/NULL, /*has_constraint=*/true, &combined_evlist); } @@ -1435,7 +1459,7 @@ static int parse_groups(struct evlist *perf_evlist, const char *str, } } if (!metric_evlist) { - ret = parse_ids(fake_pmu, m->pctx, m->modifier, + ret = parse_ids(metric_no_merge, fake_pmu, m->pctx, m->modifier, m->has_constraint, &m->evlist); if (ret) goto out; diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c index 23ecdba9e670..12261ed8c15b 100644 --- a/tools/perf/util/mmap.c +++ b/tools/perf/util/mmap.c @@ -94,7 +94,7 @@ static void perf_mmap__aio_free(struct mmap *map, int idx) } } -static int perf_mmap__aio_bind(struct mmap *map, int idx, int cpu, int affinity) +static int perf_mmap__aio_bind(struct mmap *map, int idx, struct perf_cpu cpu, int affinity) { void *data; size_t mmap_len; @@ -138,7 +138,7 @@ static void perf_mmap__aio_free(struct mmap *map, int idx) } static int perf_mmap__aio_bind(struct mmap *map __maybe_unused, int idx __maybe_unused, - int cpu __maybe_unused, int affinity __maybe_unused) + struct perf_cpu cpu __maybe_unused, int affinity __maybe_unused) { return 0; } @@ -240,7 +240,8 @@ void mmap__munmap(struct mmap *map) static void build_node_mask(int node, struct mmap_cpu_mask *mask) { - int c, cpu, nr_cpus; + int idx, nr_cpus; + struct perf_cpu cpu; const struct perf_cpu_map *cpu_map = NULL; cpu_map = cpu_map__online(); @@ -248,16 +249,16 @@ static void build_node_mask(int node, struct mmap_cpu_mask *mask) return; nr_cpus = perf_cpu_map__nr(cpu_map); - for (c = 0; c < nr_cpus; c++) { - cpu = cpu_map->map[c]; /* map c index to online cpu index */ + for (idx = 0; idx < nr_cpus; idx++) { + cpu = cpu_map->map[idx]; /* map c index to online cpu index */ if (cpu__get_node(cpu) == node) - set_bit(cpu, mask->bits); + set_bit(cpu.cpu, mask->bits); } } static int perf_mmap__setup_affinity_mask(struct mmap *map, struct mmap_params *mp) { - map->affinity_mask.nbits = cpu__max_cpu(); + map->affinity_mask.nbits = cpu__max_cpu().cpu; map->affinity_mask.bits = bitmap_zalloc(map->affinity_mask.nbits); if (!map->affinity_mask.bits) return -1; @@ -265,12 +266,12 @@ static int perf_mmap__setup_affinity_mask(struct mmap *map, struct mmap_params * if (mp->affinity == PERF_AFFINITY_NODE && cpu__max_node() > 1) build_node_mask(cpu__get_node(map->core.cpu), &map->affinity_mask); else if (mp->affinity == PERF_AFFINITY_CPU) - set_bit(map->core.cpu, map->affinity_mask.bits); + set_bit(map->core.cpu.cpu, map->affinity_mask.bits); return 0; } -int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu) +int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, struct perf_cpu cpu) { if (perf_mmap__mmap(&map->core, &mp->core, fd, cpu)) { pr_debug2("failed to mmap perf event ring buffer, error %d\n", diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h index 8e259b9610f8..83f6bd4d4082 100644 --- a/tools/perf/util/mmap.h +++ b/tools/perf/util/mmap.h @@ -7,6 +7,7 @@ #include #include #include +#include #include #include // for cpu_set_t #ifdef HAVE_AIO_SUPPORT @@ -52,7 +53,7 @@ struct mmap_params { struct auxtrace_mmap_params auxtrace_mp; }; -int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu); +int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, struct perf_cpu cpu); void mmap__munmap(struct mmap *map); union perf_event *perf_mmap__read_forward(struct mmap *map); diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c index 608b20c72a5c..48aa3217300b 100644 --- a/tools/perf/util/namespaces.c +++ b/tools/perf/util/namespaces.c @@ -60,17 +60,49 @@ void namespaces__free(struct namespaces *namespaces) free(namespaces); } +static int nsinfo__get_nspid(struct nsinfo *nsi, const char *path) +{ + FILE *f = NULL; + char *statln = NULL; + size_t linesz = 0; + char *nspid; + + f = fopen(path, "r"); + if (f == NULL) + return -1; + + while (getline(&statln, &linesz, f) != -1) { + /* Use tgid if CONFIG_PID_NS is not defined. */ + if (strstr(statln, "Tgid:") != NULL) { + nsi->tgid = (pid_t)strtol(strrchr(statln, '\t'), + NULL, 10); + nsi->nstgid = nsi->tgid; + } + + if (strstr(statln, "NStgid:") != NULL) { + nspid = strrchr(statln, '\t'); + nsi->nstgid = (pid_t)strtol(nspid, NULL, 10); + /* + * If innermost tgid is not the first, process is in a different + * PID namespace. + */ + nsi->in_pidns = (statln + sizeof("NStgid:") - 1) != nspid; + break; + } + } + + fclose(f); + free(statln); + return 0; +} + int nsinfo__init(struct nsinfo *nsi) { char oldns[PATH_MAX]; char spath[PATH_MAX]; char *newns = NULL; - char *statln = NULL; - char *nspid; struct stat old_stat; struct stat new_stat; - FILE *f = NULL; - size_t linesz = 0; int rv = -1; if (snprintf(oldns, PATH_MAX, "/proc/self/ns/mnt") >= PATH_MAX) @@ -100,34 +132,9 @@ int nsinfo__init(struct nsinfo *nsi) if (snprintf(spath, PATH_MAX, "/proc/%d/status", nsi->pid) >= PATH_MAX) goto out; - f = fopen(spath, "r"); - if (f == NULL) - goto out; - - while (getline(&statln, &linesz, f) != -1) { - /* Use tgid if CONFIG_PID_NS is not defined. */ - if (strstr(statln, "Tgid:") != NULL) { - nsi->tgid = (pid_t)strtol(strrchr(statln, '\t'), - NULL, 10); - nsi->nstgid = nsi->tgid; - } - - if (strstr(statln, "NStgid:") != NULL) { - nspid = strrchr(statln, '\t'); - nsi->nstgid = (pid_t)strtol(nspid, NULL, 10); - /* If innermost tgid is not the first, process is in a different - * PID namespace. - */ - nsi->in_pidns = (statln + sizeof("NStgid:") - 1) != nspid; - break; - } - } - rv = 0; + rv = nsinfo__get_nspid(nsi, spath); out: - if (f != NULL) - (void) fclose(f); - free(statln); free(newns); return rv; } @@ -299,3 +306,12 @@ int nsinfo__stat(const char *filename, struct stat *st, struct nsinfo *nsi) return ret; } + +bool nsinfo__is_in_root_namespace(void) +{ + struct nsinfo nsi; + + memset(&nsi, 0x0, sizeof(nsi)); + nsinfo__get_nspid(&nsi, "/proc/self/status"); + return !nsi.in_pidns; +} diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h index ad9775db7b9c..9ceea9643507 100644 --- a/tools/perf/util/namespaces.h +++ b/tools/perf/util/namespaces.h @@ -59,6 +59,8 @@ void nsinfo__mountns_exit(struct nscookie *nc); char *nsinfo__realpath(const char *path, struct nsinfo *nsi); int nsinfo__stat(const char *filename, struct stat *st, struct nsinfo *nsi); +bool nsinfo__is_in_root_namespace(void); + static inline void __nsinfo__zput(struct nsinfo **nsip) { if (nsip) { diff --git a/tools/perf/util/parse-events-hybrid.c b/tools/perf/util/parse-events-hybrid.c index 9fc86971027b..284f8eabd3b9 100644 --- a/tools/perf/util/parse-events-hybrid.c +++ b/tools/perf/util/parse-events-hybrid.c @@ -63,10 +63,13 @@ static int create_event_hybrid(__u32 config_type, int *idx, static int pmu_cmp(struct parse_events_state *parse_state, struct perf_pmu *pmu) { - if (!parse_state->hybrid_pmu_name) - return 0; + if (parse_state->evlist && parse_state->evlist->hybrid_pmu_name) + return strcmp(parse_state->evlist->hybrid_pmu_name, pmu->name); - return strcmp(parse_state->hybrid_pmu_name, pmu->name); + if (parse_state->hybrid_pmu_name) + return strcmp(parse_state->hybrid_pmu_name, pmu->name); + + return 0; } static int add_hw_hybrid(struct parse_events_state *parse_state, diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index ba74fdf74af9..acf20ce98ce9 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1824,6 +1824,11 @@ out: return ret; } +__weak struct evsel *arch_evlist__leader(struct list_head *list) +{ + return list_first_entry(list, struct evsel, core.node); +} + void parse_events__set_leader(char *name, struct list_head *list, struct parse_events_state *parse_state) { @@ -1837,9 +1842,10 @@ void parse_events__set_leader(char *name, struct list_head *list, if (parse_events__set_leader_for_uncore_aliase(name, list, parse_state)) return; - __perf_evlist__set_leader(list); - leader = list_entry(list->next, struct evsel, core.node); + leader = arch_evlist__leader(list); + __perf_evlist__set_leader(list, &leader->core); leader->group_name = name ? strdup(name) : NULL; + list_move(&leader->core.node, list); } /* list_event is assumed to point to malloc'ed memory */ diff --git a/tools/perf/util/perf_api_probe.c b/tools/perf/util/perf_api_probe.c index 020411682a3c..734d006d9a8c 100644 --- a/tools/perf/util/perf_api_probe.c +++ b/tools/perf/util/perf_api_probe.c @@ -11,7 +11,7 @@ typedef void (*setup_probe_fn_t)(struct evsel *evsel); -static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str) +static int perf_do_probe_api(setup_probe_fn_t fn, struct perf_cpu cpu, const char *str) { struct evlist *evlist; struct evsel *evsel; @@ -29,7 +29,7 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str) evsel = evlist__first(evlist); while (1) { - fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, -1, flags); + fd = sys_perf_event_open(&evsel->core.attr, pid, cpu.cpu, -1, flags); if (fd < 0) { if (pid == -1 && errno == EACCES) { pid = 0; @@ -43,7 +43,7 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str) fn(evsel); - fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, -1, flags); + fd = sys_perf_event_open(&evsel->core.attr, pid, cpu.cpu, -1, flags); if (fd < 0) { if (errno == EINVAL) err = -EINVAL; @@ -61,7 +61,8 @@ static bool perf_probe_api(setup_probe_fn_t fn) { const char *try[] = {"cycles:u", "instructions:u", "cpu-clock:u", NULL}; struct perf_cpu_map *cpus; - int cpu, ret, i = 0; + struct perf_cpu cpu; + int ret, i = 0; cpus = perf_cpu_map__new(NULL); if (!cpus) @@ -136,15 +137,17 @@ bool perf_can_record_cpu_wide(void) .exclude_kernel = 1, }; struct perf_cpu_map *cpus; - int cpu, fd; + struct perf_cpu cpu; + int fd; cpus = perf_cpu_map__new(NULL); if (!cpus) return false; + cpu = cpus->map[0]; perf_cpu_map__put(cpus); - fd = sys_perf_event_open(&attr, -1, cpu, -1, 0); + fd = sys_perf_event_open(&attr, -1, cpu.cpu, -1, 0); if (fd < 0) return false; close(fd); diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c index 06a7461ba864..a982e40ee5a9 100644 --- a/tools/perf/util/perf_regs.c +++ b/tools/perf/util/perf_regs.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include +#include #include "perf_regs.h" #include "event.h" @@ -20,6 +21,671 @@ uint64_t __weak arch__user_reg_mask(void) } #ifdef HAVE_PERF_REGS_SUPPORT + +#define perf_event_arm_regs perf_event_arm64_regs +#include "../../arch/arm64/include/uapi/asm/perf_regs.h" +#undef perf_event_arm_regs + +#include "../../arch/arm/include/uapi/asm/perf_regs.h" +#include "../../arch/csky/include/uapi/asm/perf_regs.h" +#include "../../arch/mips/include/uapi/asm/perf_regs.h" +#include "../../arch/powerpc/include/uapi/asm/perf_regs.h" +#include "../../arch/riscv/include/uapi/asm/perf_regs.h" +#include "../../arch/s390/include/uapi/asm/perf_regs.h" +#include "../../arch/x86/include/uapi/asm/perf_regs.h" + +static const char *__perf_reg_name_arm64(int id) +{ + switch (id) { + case PERF_REG_ARM64_X0: + return "x0"; + case PERF_REG_ARM64_X1: + return "x1"; + case PERF_REG_ARM64_X2: + return "x2"; + case PERF_REG_ARM64_X3: + return "x3"; + case PERF_REG_ARM64_X4: + return "x4"; + case PERF_REG_ARM64_X5: + return "x5"; + case PERF_REG_ARM64_X6: + return "x6"; + case PERF_REG_ARM64_X7: + return "x7"; + case PERF_REG_ARM64_X8: + return "x8"; + case PERF_REG_ARM64_X9: + return "x9"; + case PERF_REG_ARM64_X10: + return "x10"; + case PERF_REG_ARM64_X11: + return "x11"; + case PERF_REG_ARM64_X12: + return "x12"; + case PERF_REG_ARM64_X13: + return "x13"; + case PERF_REG_ARM64_X14: + return "x14"; + case PERF_REG_ARM64_X15: + return "x15"; + case PERF_REG_ARM64_X16: + return "x16"; + case PERF_REG_ARM64_X17: + return "x17"; + case PERF_REG_ARM64_X18: + return "x18"; + case PERF_REG_ARM64_X19: + return "x19"; + case PERF_REG_ARM64_X20: + return "x20"; + case PERF_REG_ARM64_X21: + return "x21"; + case PERF_REG_ARM64_X22: + return "x22"; + case PERF_REG_ARM64_X23: + return "x23"; + case PERF_REG_ARM64_X24: + return "x24"; + case PERF_REG_ARM64_X25: + return "x25"; + case PERF_REG_ARM64_X26: + return "x26"; + case PERF_REG_ARM64_X27: + return "x27"; + case PERF_REG_ARM64_X28: + return "x28"; + case PERF_REG_ARM64_X29: + return "x29"; + case PERF_REG_ARM64_SP: + return "sp"; + case PERF_REG_ARM64_LR: + return "lr"; + case PERF_REG_ARM64_PC: + return "pc"; + default: + return NULL; + } + + return NULL; +} + +static const char *__perf_reg_name_arm(int id) +{ + switch (id) { + case PERF_REG_ARM_R0: + return "r0"; + case PERF_REG_ARM_R1: + return "r1"; + case PERF_REG_ARM_R2: + return "r2"; + case PERF_REG_ARM_R3: + return "r3"; + case PERF_REG_ARM_R4: + return "r4"; + case PERF_REG_ARM_R5: + return "r5"; + case PERF_REG_ARM_R6: + return "r6"; + case PERF_REG_ARM_R7: + return "r7"; + case PERF_REG_ARM_R8: + return "r8"; + case PERF_REG_ARM_R9: + return "r9"; + case PERF_REG_ARM_R10: + return "r10"; + case PERF_REG_ARM_FP: + return "fp"; + case PERF_REG_ARM_IP: + return "ip"; + case PERF_REG_ARM_SP: + return "sp"; + case PERF_REG_ARM_LR: + return "lr"; + case PERF_REG_ARM_PC: + return "pc"; + default: + return NULL; + } + + return NULL; +} + +static const char *__perf_reg_name_csky(int id) +{ + switch (id) { + case PERF_REG_CSKY_A0: + return "a0"; + case PERF_REG_CSKY_A1: + return "a1"; + case PERF_REG_CSKY_A2: + return "a2"; + case PERF_REG_CSKY_A3: + return "a3"; + case PERF_REG_CSKY_REGS0: + return "regs0"; + case PERF_REG_CSKY_REGS1: + return "regs1"; + case PERF_REG_CSKY_REGS2: + return "regs2"; + case PERF_REG_CSKY_REGS3: + return "regs3"; + case PERF_REG_CSKY_REGS4: + return "regs4"; + case PERF_REG_CSKY_REGS5: + return "regs5"; + case PERF_REG_CSKY_REGS6: + return "regs6"; + case PERF_REG_CSKY_REGS7: + return "regs7"; + case PERF_REG_CSKY_REGS8: + return "regs8"; + case PERF_REG_CSKY_REGS9: + return "regs9"; + case PERF_REG_CSKY_SP: + return "sp"; + case PERF_REG_CSKY_LR: + return "lr"; + case PERF_REG_CSKY_PC: + return "pc"; +#if defined(__CSKYABIV2__) + case PERF_REG_CSKY_EXREGS0: + return "exregs0"; + case PERF_REG_CSKY_EXREGS1: + return "exregs1"; + case PERF_REG_CSKY_EXREGS2: + return "exregs2"; + case PERF_REG_CSKY_EXREGS3: + return "exregs3"; + case PERF_REG_CSKY_EXREGS4: + return "exregs4"; + case PERF_REG_CSKY_EXREGS5: + return "exregs5"; + case PERF_REG_CSKY_EXREGS6: + return "exregs6"; + case PERF_REG_CSKY_EXREGS7: + return "exregs7"; + case PERF_REG_CSKY_EXREGS8: + return "exregs8"; + case PERF_REG_CSKY_EXREGS9: + return "exregs9"; + case PERF_REG_CSKY_EXREGS10: + return "exregs10"; + case PERF_REG_CSKY_EXREGS11: + return "exregs11"; + case PERF_REG_CSKY_EXREGS12: + return "exregs12"; + case PERF_REG_CSKY_EXREGS13: + return "exregs13"; + case PERF_REG_CSKY_EXREGS14: + return "exregs14"; + case PERF_REG_CSKY_TLS: + return "tls"; + case PERF_REG_CSKY_HI: + return "hi"; + case PERF_REG_CSKY_LO: + return "lo"; +#endif + default: + return NULL; + } + + return NULL; +} + +static const char *__perf_reg_name_mips(int id) +{ + switch (id) { + case PERF_REG_MIPS_PC: + return "PC"; + case PERF_REG_MIPS_R1: + return "$1"; + case PERF_REG_MIPS_R2: + return "$2"; + case PERF_REG_MIPS_R3: + return "$3"; + case PERF_REG_MIPS_R4: + return "$4"; + case PERF_REG_MIPS_R5: + return "$5"; + case PERF_REG_MIPS_R6: + return "$6"; + case PERF_REG_MIPS_R7: + return "$7"; + case PERF_REG_MIPS_R8: + return "$8"; + case PERF_REG_MIPS_R9: + return "$9"; + case PERF_REG_MIPS_R10: + return "$10"; + case PERF_REG_MIPS_R11: + return "$11"; + case PERF_REG_MIPS_R12: + return "$12"; + case PERF_REG_MIPS_R13: + return "$13"; + case PERF_REG_MIPS_R14: + return "$14"; + case PERF_REG_MIPS_R15: + return "$15"; + case PERF_REG_MIPS_R16: + return "$16"; + case PERF_REG_MIPS_R17: + return "$17"; + case PERF_REG_MIPS_R18: + return "$18"; + case PERF_REG_MIPS_R19: + return "$19"; + case PERF_REG_MIPS_R20: + return "$20"; + case PERF_REG_MIPS_R21: + return "$21"; + case PERF_REG_MIPS_R22: + return "$22"; + case PERF_REG_MIPS_R23: + return "$23"; + case PERF_REG_MIPS_R24: + return "$24"; + case PERF_REG_MIPS_R25: + return "$25"; + case PERF_REG_MIPS_R28: + return "$28"; + case PERF_REG_MIPS_R29: + return "$29"; + case PERF_REG_MIPS_R30: + return "$30"; + case PERF_REG_MIPS_R31: + return "$31"; + default: + break; + } + return NULL; +} + +static const char *__perf_reg_name_powerpc(int id) +{ + switch (id) { + case PERF_REG_POWERPC_R0: + return "r0"; + case PERF_REG_POWERPC_R1: + return "r1"; + case PERF_REG_POWERPC_R2: + return "r2"; + case PERF_REG_POWERPC_R3: + return "r3"; + case PERF_REG_POWERPC_R4: + return "r4"; + case PERF_REG_POWERPC_R5: + return "r5"; + case PERF_REG_POWERPC_R6: + return "r6"; + case PERF_REG_POWERPC_R7: + return "r7"; + case PERF_REG_POWERPC_R8: + return "r8"; + case PERF_REG_POWERPC_R9: + return "r9"; + case PERF_REG_POWERPC_R10: + return "r10"; + case PERF_REG_POWERPC_R11: + return "r11"; + case PERF_REG_POWERPC_R12: + return "r12"; + case PERF_REG_POWERPC_R13: + return "r13"; + case PERF_REG_POWERPC_R14: + return "r14"; + case PERF_REG_POWERPC_R15: + return "r15"; + case PERF_REG_POWERPC_R16: + return "r16"; + case PERF_REG_POWERPC_R17: + return "r17"; + case PERF_REG_POWERPC_R18: + return "r18"; + case PERF_REG_POWERPC_R19: + return "r19"; + case PERF_REG_POWERPC_R20: + return "r20"; + case PERF_REG_POWERPC_R21: + return "r21"; + case PERF_REG_POWERPC_R22: + return "r22"; + case PERF_REG_POWERPC_R23: + return "r23"; + case PERF_REG_POWERPC_R24: + return "r24"; + case PERF_REG_POWERPC_R25: + return "r25"; + case PERF_REG_POWERPC_R26: + return "r26"; + case PERF_REG_POWERPC_R27: + return "r27"; + case PERF_REG_POWERPC_R28: + return "r28"; + case PERF_REG_POWERPC_R29: + return "r29"; + case PERF_REG_POWERPC_R30: + return "r30"; + case PERF_REG_POWERPC_R31: + return "r31"; + case PERF_REG_POWERPC_NIP: + return "nip"; + case PERF_REG_POWERPC_MSR: + return "msr"; + case PERF_REG_POWERPC_ORIG_R3: + return "orig_r3"; + case PERF_REG_POWERPC_CTR: + return "ctr"; + case PERF_REG_POWERPC_LINK: + return "link"; + case PERF_REG_POWERPC_XER: + return "xer"; + case PERF_REG_POWERPC_CCR: + return "ccr"; + case PERF_REG_POWERPC_SOFTE: + return "softe"; + case PERF_REG_POWERPC_TRAP: + return "trap"; + case PERF_REG_POWERPC_DAR: + return "dar"; + case PERF_REG_POWERPC_DSISR: + return "dsisr"; + case PERF_REG_POWERPC_SIER: + return "sier"; + case PERF_REG_POWERPC_MMCRA: + return "mmcra"; + case PERF_REG_POWERPC_MMCR0: + return "mmcr0"; + case PERF_REG_POWERPC_MMCR1: + return "mmcr1"; + case PERF_REG_POWERPC_MMCR2: + return "mmcr2"; + case PERF_REG_POWERPC_MMCR3: + return "mmcr3"; + case PERF_REG_POWERPC_SIER2: + return "sier2"; + case PERF_REG_POWERPC_SIER3: + return "sier3"; + case PERF_REG_POWERPC_PMC1: + return "pmc1"; + case PERF_REG_POWERPC_PMC2: + return "pmc2"; + case PERF_REG_POWERPC_PMC3: + return "pmc3"; + case PERF_REG_POWERPC_PMC4: + return "pmc4"; + case PERF_REG_POWERPC_PMC5: + return "pmc5"; + case PERF_REG_POWERPC_PMC6: + return "pmc6"; + case PERF_REG_POWERPC_SDAR: + return "sdar"; + case PERF_REG_POWERPC_SIAR: + return "siar"; + default: + break; + } + return NULL; +} + +static const char *__perf_reg_name_riscv(int id) +{ + switch (id) { + case PERF_REG_RISCV_PC: + return "pc"; + case PERF_REG_RISCV_RA: + return "ra"; + case PERF_REG_RISCV_SP: + return "sp"; + case PERF_REG_RISCV_GP: + return "gp"; + case PERF_REG_RISCV_TP: + return "tp"; + case PERF_REG_RISCV_T0: + return "t0"; + case PERF_REG_RISCV_T1: + return "t1"; + case PERF_REG_RISCV_T2: + return "t2"; + case PERF_REG_RISCV_S0: + return "s0"; + case PERF_REG_RISCV_S1: + return "s1"; + case PERF_REG_RISCV_A0: + return "a0"; + case PERF_REG_RISCV_A1: + return "a1"; + case PERF_REG_RISCV_A2: + return "a2"; + case PERF_REG_RISCV_A3: + return "a3"; + case PERF_REG_RISCV_A4: + return "a4"; + case PERF_REG_RISCV_A5: + return "a5"; + case PERF_REG_RISCV_A6: + return "a6"; + case PERF_REG_RISCV_A7: + return "a7"; + case PERF_REG_RISCV_S2: + return "s2"; + case PERF_REG_RISCV_S3: + return "s3"; + case PERF_REG_RISCV_S4: + return "s4"; + case PERF_REG_RISCV_S5: + return "s5"; + case PERF_REG_RISCV_S6: + return "s6"; + case PERF_REG_RISCV_S7: + return "s7"; + case PERF_REG_RISCV_S8: + return "s8"; + case PERF_REG_RISCV_S9: + return "s9"; + case PERF_REG_RISCV_S10: + return "s10"; + case PERF_REG_RISCV_S11: + return "s11"; + case PERF_REG_RISCV_T3: + return "t3"; + case PERF_REG_RISCV_T4: + return "t4"; + case PERF_REG_RISCV_T5: + return "t5"; + case PERF_REG_RISCV_T6: + return "t6"; + default: + return NULL; + } + + return NULL; +} + +static const char *__perf_reg_name_s390(int id) +{ + switch (id) { + case PERF_REG_S390_R0: + return "R0"; + case PERF_REG_S390_R1: + return "R1"; + case PERF_REG_S390_R2: + return "R2"; + case PERF_REG_S390_R3: + return "R3"; + case PERF_REG_S390_R4: + return "R4"; + case PERF_REG_S390_R5: + return "R5"; + case PERF_REG_S390_R6: + return "R6"; + case PERF_REG_S390_R7: + return "R7"; + case PERF_REG_S390_R8: + return "R8"; + case PERF_REG_S390_R9: + return "R9"; + case PERF_REG_S390_R10: + return "R10"; + case PERF_REG_S390_R11: + return "R11"; + case PERF_REG_S390_R12: + return "R12"; + case PERF_REG_S390_R13: + return "R13"; + case PERF_REG_S390_R14: + return "R14"; + case PERF_REG_S390_R15: + return "R15"; + case PERF_REG_S390_FP0: + return "FP0"; + case PERF_REG_S390_FP1: + return "FP1"; + case PERF_REG_S390_FP2: + return "FP2"; + case PERF_REG_S390_FP3: + return "FP3"; + case PERF_REG_S390_FP4: + return "FP4"; + case PERF_REG_S390_FP5: + return "FP5"; + case PERF_REG_S390_FP6: + return "FP6"; + case PERF_REG_S390_FP7: + return "FP7"; + case PERF_REG_S390_FP8: + return "FP8"; + case PERF_REG_S390_FP9: + return "FP9"; + case PERF_REG_S390_FP10: + return "FP10"; + case PERF_REG_S390_FP11: + return "FP11"; + case PERF_REG_S390_FP12: + return "FP12"; + case PERF_REG_S390_FP13: + return "FP13"; + case PERF_REG_S390_FP14: + return "FP14"; + case PERF_REG_S390_FP15: + return "FP15"; + case PERF_REG_S390_MASK: + return "MASK"; + case PERF_REG_S390_PC: + return "PC"; + default: + return NULL; + } + + return NULL; +} + +static const char *__perf_reg_name_x86(int id) +{ + switch (id) { + case PERF_REG_X86_AX: + return "AX"; + case PERF_REG_X86_BX: + return "BX"; + case PERF_REG_X86_CX: + return "CX"; + case PERF_REG_X86_DX: + return "DX"; + case PERF_REG_X86_SI: + return "SI"; + case PERF_REG_X86_DI: + return "DI"; + case PERF_REG_X86_BP: + return "BP"; + case PERF_REG_X86_SP: + return "SP"; + case PERF_REG_X86_IP: + return "IP"; + case PERF_REG_X86_FLAGS: + return "FLAGS"; + case PERF_REG_X86_CS: + return "CS"; + case PERF_REG_X86_SS: + return "SS"; + case PERF_REG_X86_DS: + return "DS"; + case PERF_REG_X86_ES: + return "ES"; + case PERF_REG_X86_FS: + return "FS"; + case PERF_REG_X86_GS: + return "GS"; + case PERF_REG_X86_R8: + return "R8"; + case PERF_REG_X86_R9: + return "R9"; + case PERF_REG_X86_R10: + return "R10"; + case PERF_REG_X86_R11: + return "R11"; + case PERF_REG_X86_R12: + return "R12"; + case PERF_REG_X86_R13: + return "R13"; + case PERF_REG_X86_R14: + return "R14"; + case PERF_REG_X86_R15: + return "R15"; + +#define XMM(x) \ + case PERF_REG_X86_XMM ## x: \ + case PERF_REG_X86_XMM ## x + 1: \ + return "XMM" #x; + XMM(0) + XMM(1) + XMM(2) + XMM(3) + XMM(4) + XMM(5) + XMM(6) + XMM(7) + XMM(8) + XMM(9) + XMM(10) + XMM(11) + XMM(12) + XMM(13) + XMM(14) + XMM(15) +#undef XMM + default: + return NULL; + } + + return NULL; +} + +const char *perf_reg_name(int id, const char *arch) +{ + const char *reg_name = NULL; + + if (!strcmp(arch, "csky")) + reg_name = __perf_reg_name_csky(id); + else if (!strcmp(arch, "mips")) + reg_name = __perf_reg_name_mips(id); + else if (!strcmp(arch, "powerpc")) + reg_name = __perf_reg_name_powerpc(id); + else if (!strcmp(arch, "riscv")) + reg_name = __perf_reg_name_riscv(id); + else if (!strcmp(arch, "s390")) + reg_name = __perf_reg_name_s390(id); + else if (!strcmp(arch, "x86")) + reg_name = __perf_reg_name_x86(id); + else if (!strcmp(arch, "arm")) + reg_name = __perf_reg_name_arm(id); + else if (!strcmp(arch, "arm64")) + reg_name = __perf_reg_name_arm64(id); + + return reg_name ?: "unknown"; +} + int perf_reg_value(u64 *valp, struct regs_dump *regs, int id) { int i, idx = 0; diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h index eeac181ebccf..ce1127af05e4 100644 --- a/tools/perf/util/perf_regs.h +++ b/tools/perf/util/perf_regs.h @@ -11,8 +11,11 @@ struct sample_reg { const char *name; uint64_t mask; }; -#define SMPL_REG(n, b) { .name = #n, .mask = 1ULL << (b) } -#define SMPL_REG2(n, b) { .name = #n, .mask = 3ULL << (b) } + +#define SMPL_REG_MASK(b) (1ULL << (b)) +#define SMPL_REG(n, b) { .name = #n, .mask = SMPL_REG_MASK(b) } +#define SMPL_REG2_MASK(b) (3ULL << (b)) +#define SMPL_REG2(n, b) { .name = #n, .mask = SMPL_REG2_MASK(b) } #define SMPL_REG_END { .name = NULL } enum { @@ -31,22 +34,16 @@ extern const struct sample_reg sample_reg_masks[]; #define DWARF_MINIMAL_REGS ((1ULL << PERF_REG_IP) | (1ULL << PERF_REG_SP)) +const char *perf_reg_name(int id, const char *arch); int perf_reg_value(u64 *valp, struct regs_dump *regs, int id); -static inline const char *perf_reg_name(int id) -{ - const char *reg_name = __perf_reg_name(id); - - return reg_name ?: "unknown"; -} - #else #define PERF_REGS_MASK 0 #define PERF_REGS_MAX 0 #define DWARF_MINIMAL_REGS PERF_REGS_MASK -static inline const char *perf_reg_name(int id __maybe_unused) +static inline const char *perf_reg_name(int id __maybe_unused, const char *arch __maybe_unused) { return "unknown"; } diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 82c7f034d91a..f3e5131f183c 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -1059,7 +1059,7 @@ static struct mmap *get_md(struct evlist *evlist, int cpu) for (i = 0; i < evlist->core.nr_mmaps; i++) { struct mmap *md = &evlist->mmap[i]; - if (md->core.cpu == cpu) + if (md->core.cpu.cpu == cpu) return md; } @@ -1445,7 +1445,7 @@ error: * Dummy, to avoid dragging all the test_attr infrastructure in the python * binding. */ -void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu, +void test_attr__open(struct perf_event_attr *attr, pid_t pid, struct perf_cpu cpu, int fd, int group_fd, unsigned long flags) { } diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index bff669b615ee..20461f174991 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -106,7 +106,7 @@ void evlist__config(struct evlist *evlist, struct record_opts *opts, struct call if (opts->group) evlist__set_leader(evlist); - if (evlist->core.cpus->map[0] < 0) + if (evlist->core.cpus->map[0].cpu < 0) opts->no_inherit = true; use_comm_exec = perf_can_comm_exec(); @@ -229,7 +229,8 @@ bool evlist__can_select_event(struct evlist *evlist, const char *str) { struct evlist *temp_evlist; struct evsel *evsel; - int err, fd, cpu; + int err, fd; + struct perf_cpu cpu = { .cpu = 0 }; bool ret = false; pid_t pid = -1; @@ -246,14 +247,16 @@ bool evlist__can_select_event(struct evlist *evlist, const char *str) if (!evlist || perf_cpu_map__empty(evlist->core.cpus)) { struct perf_cpu_map *cpus = perf_cpu_map__new(NULL); - cpu = cpus ? cpus->map[0] : 0; + if (cpus) + cpu = cpus->map[0]; + perf_cpu_map__put(cpus); } else { cpu = evlist->core.cpus->map[0]; } while (1) { - fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, -1, + fd = sys_perf_event_open(&evsel->core.attr, pid, cpu.cpu, -1, perf_event_open_cloexec_flag()); if (fd < 0) { if (pid == -1 && errno == EACCES) { diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index d1f1501ce7fc..f5ad0e62227a 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -36,6 +36,7 @@ #include "../debug.h" #include "../dso.h" #include "../callchain.h" +#include "../env.h" #include "../evsel.h" #include "../event.h" #include "../thread.h" @@ -687,7 +688,7 @@ static void set_sample_datasrc_in_dict(PyObject *dict, _PyUnicode_FromString(decode)); } -static void regs_map(struct regs_dump *regs, uint64_t mask, char *bf, int size) +static void regs_map(struct regs_dump *regs, uint64_t mask, const char *arch, char *bf, int size) { unsigned int i = 0, r; int printed = 0; @@ -702,7 +703,7 @@ static void regs_map(struct regs_dump *regs, uint64_t mask, char *bf, int size) printed += scnprintf(bf + printed, size - printed, "%5s:0x%" PRIx64 " ", - perf_reg_name(r), val); + perf_reg_name(r, arch), val); } } @@ -711,6 +712,7 @@ static void set_regs_in_dict(PyObject *dict, struct evsel *evsel) { struct perf_event_attr *attr = &evsel->core.attr; + const char *arch = perf_env__arch(evsel__env(evsel)); /* * Here value 28 is a constant size which can be used to print @@ -722,12 +724,12 @@ static void set_regs_in_dict(PyObject *dict, int size = __sw_hweight64(attr->sample_regs_intr) * 28; char bf[size]; - regs_map(&sample->intr_regs, attr->sample_regs_intr, bf, sizeof(bf)); + regs_map(&sample->intr_regs, attr->sample_regs_intr, arch, bf, sizeof(bf)); pydict_set_item_string_decref(dict, "iregs", _PyUnicode_FromString(bf)); - regs_map(&sample->user_regs, attr->sample_regs_user, bf, sizeof(bf)); + regs_map(&sample->user_regs, attr->sample_regs_user, arch, bf, sizeof(bf)); pydict_set_item_string_decref(dict, "uregs", _PyUnicode_FromString(bf)); @@ -1555,7 +1557,7 @@ static void get_handler_name(char *str, size_t size, } static void -process_stat(struct evsel *counter, int cpu, int thread, u64 tstamp, +process_stat(struct evsel *counter, struct perf_cpu cpu, int thread, u64 tstamp, struct perf_counts_values *count) { PyObject *handler, *t; @@ -1575,7 +1577,7 @@ process_stat(struct evsel *counter, int cpu, int thread, u64 tstamp, return; } - PyTuple_SetItem(t, n++, _PyLong_FromLong(cpu)); + PyTuple_SetItem(t, n++, _PyLong_FromLong(cpu.cpu)); PyTuple_SetItem(t, n++, _PyLong_FromLong(thread)); tuple_set_u64(t, n++, tstamp); @@ -1599,7 +1601,7 @@ static void python_process_stat(struct perf_stat_config *config, int cpu, thread; if (config->aggr_mode == AGGR_GLOBAL) { - process_stat(counter, -1, -1, tstamp, + process_stat(counter, (struct perf_cpu){ .cpu = -1 }, -1, tstamp, &counter->counts->aggr); return; } diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index d8857d1b6d7c..f19348dddd55 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -15,6 +15,7 @@ #include "map_symbol.h" #include "branch.h" #include "debug.h" +#include "env.h" #include "evlist.h" #include "evsel.h" #include "memswap.h" @@ -1168,7 +1169,7 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack) } } -static void regs_dump__printf(u64 mask, u64 *regs) +static void regs_dump__printf(u64 mask, u64 *regs, const char *arch) { unsigned rid, i = 0; @@ -1176,7 +1177,7 @@ static void regs_dump__printf(u64 mask, u64 *regs) u64 val = regs[i++]; printf(".... %-5s 0x%016" PRIx64 "\n", - perf_reg_name(rid), val); + perf_reg_name(rid, arch), val); } } @@ -1194,7 +1195,7 @@ static inline const char *regs_dump_abi(struct regs_dump *d) return regs_abi[d->abi]; } -static void regs__printf(const char *type, struct regs_dump *regs) +static void regs__printf(const char *type, struct regs_dump *regs, const char *arch) { u64 mask = regs->mask; @@ -1203,23 +1204,23 @@ static void regs__printf(const char *type, struct regs_dump *regs) mask, regs_dump_abi(regs)); - regs_dump__printf(mask, regs->regs); + regs_dump__printf(mask, regs->regs, arch); } -static void regs_user__printf(struct perf_sample *sample) +static void regs_user__printf(struct perf_sample *sample, const char *arch) { struct regs_dump *user_regs = &sample->user_regs; if (user_regs->regs) - regs__printf("user", user_regs); + regs__printf("user", user_regs, arch); } -static void regs_intr__printf(struct perf_sample *sample) +static void regs_intr__printf(struct perf_sample *sample, const char *arch) { struct regs_dump *intr_regs = &sample->intr_regs; if (intr_regs->regs) - regs__printf("intr", intr_regs); + regs__printf("intr", intr_regs, arch); } static void stack_user__printf(struct stack_dump *dump) @@ -1304,7 +1305,7 @@ char *get_page_size_name(u64 size, char *str) } static void dump_sample(struct evsel *evsel, union perf_event *event, - struct perf_sample *sample) + struct perf_sample *sample, const char *arch) { u64 sample_type; char str[PAGE_SIZE_NAME_LEN]; @@ -1325,10 +1326,10 @@ static void dump_sample(struct evsel *evsel, union perf_event *event, branch_stack__printf(sample, evsel__has_branch_callstack(evsel)); if (sample_type & PERF_SAMPLE_REGS_USER) - regs_user__printf(sample); + regs_user__printf(sample, arch); if (sample_type & PERF_SAMPLE_REGS_INTR) - regs_intr__printf(sample); + regs_intr__printf(sample, arch); if (sample_type & PERF_SAMPLE_STACK_USER) stack_user__printf(&sample->user_stack); @@ -1502,7 +1503,7 @@ static int machines__deliver_event(struct machines *machines, ++evlist->stats.nr_unknown_id; return 0; } - dump_sample(evsel, event, sample); + dump_sample(evsel, event, sample, perf_env__arch(machine->env)); if (machine == NULL) { ++evlist->stats.nr_unprocessable_samples; return 0; @@ -2537,15 +2538,15 @@ int perf_session__cpu_bitmap(struct perf_session *session, } for (i = 0; i < map->nr; i++) { - int cpu = map->map[i]; + struct perf_cpu cpu = map->map[i]; - if (cpu >= nr_cpus) { + if (cpu.cpu >= nr_cpus) { pr_err("Requested CPU %d too large. " - "Consider raising MAX_NR_CPUS\n", cpu); + "Consider raising MAX_NR_CPUS\n", cpu.cpu); goto out_delete_map; } - set_bit(cpu, cpu_bitmap); + set_bit(cpu.cpu, cpu_bitmap); } err = 0; @@ -2597,7 +2598,7 @@ int perf_event__process_id_index(struct perf_session *session, if (!sid) return -ENOENT; sid->idx = e->idx; - sid->cpu = e->cpu; + sid->cpu.cpu = e->cpu; sid->tid = e->tid; } return 0; diff --git a/tools/perf/util/smt.c b/tools/perf/util/smt.c index 34f1b1b1176c..2b0a36ebf27a 100644 --- a/tools/perf/util/smt.c +++ b/tools/perf/util/smt.c @@ -5,6 +5,56 @@ #include "api/fs/fs.h" #include "smt.h" +/** + * hweight_str - Returns the number of bits set in str. Stops at first non-hex + * or ',' character. + */ +static int hweight_str(char *str) +{ + int result = 0; + + while (*str) { + switch (*str++) { + case '0': + case ',': + break; + case '1': + case '2': + case '4': + case '8': + result++; + break; + case '3': + case '5': + case '6': + case '9': + case 'a': + case 'A': + case 'c': + case 'C': + result += 2; + break; + case '7': + case 'b': + case 'B': + case 'd': + case 'D': + case 'e': + case 'E': + result += 3; + break; + case 'f': + case 'F': + result += 4; + break; + default: + goto done; + } + } +done: + return result; +} + int smt_on(void) { static bool cached; @@ -15,9 +65,12 @@ int smt_on(void) if (cached) return cached_result; - if (sysfs__read_int("devices/system/cpu/smt/active", &cached_result) >= 0) - goto done; + if (sysfs__read_int("devices/system/cpu/smt/active", &cached_result) >= 0) { + cached = true; + return cached_result; + } + cached_result = 0; ncpu = sysconf(_SC_NPROCESSORS_CONF); for (cpu = 0; cpu < ncpu; cpu++) { unsigned long long siblings; @@ -26,27 +79,21 @@ int smt_on(void) char fn[256]; snprintf(fn, sizeof fn, - "devices/system/cpu/cpu%d/topology/core_cpus", cpu); + "devices/system/cpu/cpu%d/topology/thread_siblings", cpu); if (sysfs__read_str(fn, &str, &strlen) < 0) { snprintf(fn, sizeof fn, - "devices/system/cpu/cpu%d/topology/thread_siblings", - cpu); + "devices/system/cpu/cpu%d/topology/core_cpus", cpu); if (sysfs__read_str(fn, &str, &strlen) < 0) continue; } /* Entry is hex, but does not have 0x, so need custom parser */ - siblings = strtoull(str, NULL, 16); + siblings = hweight_str(str); free(str); - if (hweight64(siblings) > 1) { + if (siblings > 1) { cached_result = 1; - cached = true; break; } } - if (!cached) { - cached_result = 0; -done: - cached = true; - } + cached = true; return cached_result; } diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index d9a106f0edb2..cfba8c337783 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -37,7 +37,7 @@ const char default_parent_pattern[] = "^sys_|^do_page_fault"; const char *parent_pattern = default_parent_pattern; const char *default_sort_order = "comm,dso,symbol"; const char default_branch_sort_order[] = "comm,dso_from,symbol_from,symbol_to,cycles"; -const char default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked,blocked,local_ins_lat,p_stage_cyc"; +const char default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked,blocked,local_ins_lat,local_p_stage_cyc"; const char default_top_sort_order[] = "dso,symbol"; const char default_diff_sort_order[] = "dso,symbol"; const char default_tracepoint_sort_order[] = "trace"; @@ -46,8 +46,8 @@ const char *field_order; regex_t ignore_callees_regex; int have_ignore_callees = 0; enum sort_mode sort__mode = SORT_MODE__NORMAL; -const char *dynamic_headers[] = {"local_ins_lat", "p_stage_cyc"}; -const char *arch_specific_sort_keys[] = {"p_stage_cyc"}; +static const char *const dynamic_headers[] = {"local_ins_lat", "ins_lat", "local_p_stage_cyc", "p_stage_cyc"}; +static const char *const arch_specific_sort_keys[] = {"local_p_stage_cyc", "p_stage_cyc"}; /* * Replaces all occurrences of a char used with the: @@ -1392,22 +1392,37 @@ struct sort_entry sort_global_ins_lat = { }; static int64_t -sort__global_p_stage_cyc_cmp(struct hist_entry *left, struct hist_entry *right) +sort__p_stage_cyc_cmp(struct hist_entry *left, struct hist_entry *right) { return left->p_stage_cyc - right->p_stage_cyc; } +static int hist_entry__global_p_stage_cyc_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + return repsep_snprintf(bf, size, "%-*u", width, + he->p_stage_cyc * he->stat.nr_events); +} + + static int hist_entry__p_stage_cyc_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { return repsep_snprintf(bf, size, "%-*u", width, he->p_stage_cyc); } -struct sort_entry sort_p_stage_cyc = { - .se_header = "Pipeline Stage Cycle", - .se_cmp = sort__global_p_stage_cyc_cmp, +struct sort_entry sort_local_p_stage_cyc = { + .se_header = "Local Pipeline Stage Cycle", + .se_cmp = sort__p_stage_cyc_cmp, .se_snprintf = hist_entry__p_stage_cyc_snprintf, - .se_width_idx = HISTC_P_STAGE_CYC, + .se_width_idx = HISTC_LOCAL_P_STAGE_CYC, +}; + +struct sort_entry sort_global_p_stage_cyc = { + .se_header = "Pipeline Stage Cycle", + .se_cmp = sort__p_stage_cyc_cmp, + .se_snprintf = hist_entry__global_p_stage_cyc_snprintf, + .se_width_idx = HISTC_GLOBAL_P_STAGE_CYC, }; struct sort_entry sort_mem_daddr_sym = { @@ -1858,7 +1873,8 @@ static struct sort_dimension common_sort_dimensions[] = { DIM(SORT_CODE_PAGE_SIZE, "code_page_size", sort_code_page_size), DIM(SORT_LOCAL_INS_LAT, "local_ins_lat", sort_local_ins_lat), DIM(SORT_GLOBAL_INS_LAT, "ins_lat", sort_global_ins_lat), - DIM(SORT_PIPELINE_STAGE_CYC, "p_stage_cyc", sort_p_stage_cyc), + DIM(SORT_LOCAL_PIPELINE_STAGE_CYC, "local_p_stage_cyc", sort_local_p_stage_cyc), + DIM(SORT_GLOBAL_PIPELINE_STAGE_CYC, "p_stage_cyc", sort_global_p_stage_cyc), }; #undef DIM diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 7b7145501933..f994261888e1 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -235,7 +235,8 @@ enum sort_type { SORT_CODE_PAGE_SIZE, SORT_LOCAL_INS_LAT, SORT_GLOBAL_INS_LAT, - SORT_PIPELINE_STAGE_CYC, + SORT_LOCAL_PIPELINE_STAGE_CYC, + SORT_GLOBAL_PIPELINE_STAGE_CYC, /* branch stack specific sort keys */ __SORT_BRANCH_STACK, diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 588601000f3f..5db83e51ceef 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -4,6 +4,7 @@ #include #include #include +#include #include "color.h" #include "counts.h" #include "evlist.h" @@ -120,11 +121,10 @@ static void aggr_printout(struct perf_stat_config *config, id.die, config->csv_output ? 0 : -3, id.core, config->csv_sep); - } else if (id.core > -1) { + } else if (id.cpu.cpu > -1) { fprintf(config->output, "CPU%*d%s", config->csv_output ? 0 : -7, - evsel__cpus(evsel)->map[id.core], - config->csv_sep); + id.cpu.cpu, config->csv_sep); } break; case AGGR_THREAD: @@ -327,26 +327,24 @@ static void print_metric_header(struct perf_stat_config *config, fprintf(os->fh, "%*s ", config->metric_only_len, unit); } -static int first_shadow_cpu(struct perf_stat_config *config, - struct evsel *evsel, struct aggr_cpu_id id) +static int first_shadow_cpu_map_idx(struct perf_stat_config *config, + struct evsel *evsel, const struct aggr_cpu_id *id) { - struct evlist *evlist = evsel->evlist; - int i; + struct perf_cpu_map *cpus = evsel__cpus(evsel); + struct perf_cpu cpu; + int idx; if (config->aggr_mode == AGGR_NONE) - return id.core; + return perf_cpu_map__idx(cpus, id->cpu); if (!config->aggr_get_id) return 0; - for (i = 0; i < evsel__nr_cpus(evsel); i++) { - int cpu2 = evsel__cpus(evsel)->map[i]; + perf_cpu_map__for_each_cpu(cpu, idx, cpus) { + struct aggr_cpu_id cpu_id = config->aggr_get_id(config, cpu); - if (cpu_map__compare_aggr_cpu_id( - config->aggr_get_id(config, evlist->core.cpus, cpu2), - id)) { - return cpu2; - } + if (aggr_cpu_id__equal(&cpu_id, id)) + return idx; } return 0; } @@ -505,7 +503,7 @@ static void printout(struct perf_stat_config *config, struct aggr_cpu_id id, int } perf_stat__print_shadow_stats(config, counter, uval, - first_shadow_cpu(config, counter, id), + first_shadow_cpu_map_idx(config, counter, &id), &out, &config->metric_events, st); if (!config->csv_output && !config->metric_only) { print_noise(config, counter, noise); @@ -516,23 +514,26 @@ static void printout(struct perf_stat_config *config, struct aggr_cpu_id id, int static void aggr_update_shadow(struct perf_stat_config *config, struct evlist *evlist) { - int cpu, s; + int idx, s; + struct perf_cpu cpu; struct aggr_cpu_id s2, id; u64 val; struct evsel *counter; + struct perf_cpu_map *cpus; for (s = 0; s < config->aggr_map->nr; s++) { id = config->aggr_map->map[s]; evlist__for_each_entry(evlist, counter) { + cpus = evsel__cpus(counter); val = 0; - for (cpu = 0; cpu < evsel__nr_cpus(counter); cpu++) { - s2 = config->aggr_get_id(config, evlist->core.cpus, cpu); - if (!cpu_map__compare_aggr_cpu_id(s2, id)) + perf_cpu_map__for_each_cpu(cpu, idx, cpus) { + s2 = config->aggr_get_id(config, cpu); + if (!aggr_cpu_id__equal(&s2, &id)) continue; - val += perf_counts(counter->counts, cpu, 0)->val; + val += perf_counts(counter->counts, idx, 0)->val; } perf_stat__update_shadow_stats(counter, val, - first_shadow_cpu(config, counter, id), + first_shadow_cpu_map_idx(config, counter, &id), &rt_stat); } } @@ -627,25 +628,28 @@ struct aggr_data { u64 ena, run, val; struct aggr_cpu_id id; int nr; - int cpu; + int cpu_map_idx; }; static void aggr_cb(struct perf_stat_config *config, struct evsel *counter, void *data, bool first) { struct aggr_data *ad = data; - int cpu; + int idx; + struct perf_cpu cpu; + struct perf_cpu_map *cpus; struct aggr_cpu_id s2; - for (cpu = 0; cpu < evsel__nr_cpus(counter); cpu++) { + cpus = evsel__cpus(counter); + perf_cpu_map__for_each_cpu(cpu, idx, cpus) { struct perf_counts_values *counts; - s2 = config->aggr_get_id(config, evsel__cpus(counter), cpu); - if (!cpu_map__compare_aggr_cpu_id(s2, ad->id)) + s2 = config->aggr_get_id(config, cpu); + if (!aggr_cpu_id__equal(&s2, &ad->id)) continue; if (first) ad->nr++; - counts = perf_counts(counter->counts, cpu, 0); + counts = perf_counts(counter->counts, idx, 0); /* * When any result is bad, make them all to give * consistent output in interval mode. @@ -665,7 +669,7 @@ static void aggr_cb(struct perf_stat_config *config, static void print_counter_aggrdata(struct perf_stat_config *config, struct evsel *counter, int s, char *prefix, bool metric_only, - bool *first, int cpu) + bool *first, struct perf_cpu cpu) { struct aggr_data ad; FILE *output = config->output; @@ -695,10 +699,9 @@ static void print_counter_aggrdata(struct perf_stat_config *config, fprintf(output, "%s", prefix); uval = val * counter->scale; - if (cpu != -1) { - id = cpu_map__empty_aggr_cpu_id(); - id.core = cpu; - } + if (cpu.cpu != -1) + id = aggr_cpu_id__cpu(cpu, /*data=*/NULL); + printout(config, id, nr, counter, uval, prefix, run, ena, 1.0, &rt_stat); if (!metric_only) @@ -731,8 +734,8 @@ static void print_aggr(struct perf_stat_config *config, first = true; evlist__for_each_entry(evlist, counter) { print_counter_aggrdata(config, counter, s, - prefix, metric_only, - &first, -1); + prefix, metric_only, + &first, (struct perf_cpu){ .cpu = -1 }); } if (metric_only) fputc('\n', output); @@ -778,7 +781,7 @@ static struct perf_aggr_thread_value *sort_aggr_thread( continue; buf[i].counter = counter; - buf[i].id = cpu_map__empty_aggr_cpu_id(); + buf[i].id = aggr_cpu_id__empty(); buf[i].id.thread = thread; buf[i].uval = uval; buf[i].val = val; @@ -866,7 +869,7 @@ static void print_counter_aggr(struct perf_stat_config *config, fprintf(output, "%s", prefix); uval = cd.avg * counter->scale; - printout(config, cpu_map__empty_aggr_cpu_id(), 0, counter, uval, prefix, cd.avg_running, + printout(config, aggr_cpu_id__empty(), 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled, cd.avg, &rt_stat); if (!metric_only) fprintf(output, "\n"); @@ -878,9 +881,9 @@ static void counter_cb(struct perf_stat_config *config __maybe_unused, { struct aggr_data *ad = data; - ad->val += perf_counts(counter->counts, ad->cpu, 0)->val; - ad->ena += perf_counts(counter->counts, ad->cpu, 0)->ena; - ad->run += perf_counts(counter->counts, ad->cpu, 0)->run; + ad->val += perf_counts(counter->counts, ad->cpu_map_idx, 0)->val; + ad->ena += perf_counts(counter->counts, ad->cpu_map_idx, 0)->ena; + ad->run += perf_counts(counter->counts, ad->cpu_map_idx, 0)->run; } /* @@ -893,11 +896,12 @@ static void print_counter(struct perf_stat_config *config, FILE *output = config->output; u64 ena, run, val; double uval; - int cpu; + int idx; + struct perf_cpu cpu; struct aggr_cpu_id id; - for (cpu = 0; cpu < evsel__nr_cpus(counter); cpu++) { - struct aggr_data ad = { .cpu = cpu }; + perf_cpu_map__for_each_cpu(cpu, idx, evsel__cpus(counter)) { + struct aggr_data ad = { .cpu_map_idx = idx }; if (!collect_data(config, counter, counter_cb, &ad)) return; @@ -909,8 +913,7 @@ static void print_counter(struct perf_stat_config *config, fprintf(output, "%s", prefix); uval = val * counter->scale; - id = cpu_map__empty_aggr_cpu_id(); - id.core = cpu; + id = aggr_cpu_id__cpu(cpu, /*data=*/NULL); printout(config, id, 0, counter, uval, prefix, run, ena, 1.0, &rt_stat); @@ -922,29 +925,32 @@ static void print_no_aggr_metric(struct perf_stat_config *config, struct evlist *evlist, char *prefix) { - int cpu; - int nrcpus = 0; - struct evsel *counter; - u64 ena, run, val; - double uval; - struct aggr_cpu_id id; + int all_idx; + struct perf_cpu cpu; - nrcpus = evlist->core.cpus->nr; - for (cpu = 0; cpu < nrcpus; cpu++) { + perf_cpu_map__for_each_cpu(cpu, all_idx, evlist->core.cpus) { + struct evsel *counter; bool first = true; if (prefix) fputs(prefix, config->output); evlist__for_each_entry(evlist, counter) { - id = cpu_map__empty_aggr_cpu_id(); - id.core = cpu; + u64 ena, run, val; + double uval; + struct aggr_cpu_id id; + int counter_idx = perf_cpu_map__idx(evsel__cpus(counter), cpu); + + if (counter_idx < 0) + continue; + + id = aggr_cpu_id__cpu(cpu, /*data=*/NULL); if (first) { aggr_printout(config, counter, id, 0); first = false; } - val = perf_counts(counter->counts, cpu, 0)->val; - ena = perf_counts(counter->counts, cpu, 0)->ena; - run = perf_counts(counter->counts, cpu, 0)->run; + val = perf_counts(counter->counts, counter_idx, 0)->val; + ena = perf_counts(counter->counts, counter_idx, 0)->ena; + run = perf_counts(counter->counts, counter_idx, 0)->run; uval = val * counter->scale; printout(config, id, 0, counter, uval, prefix, @@ -1208,19 +1214,23 @@ static void print_percore_thread(struct perf_stat_config *config, { int s; struct aggr_cpu_id s2, id; + struct perf_cpu_map *cpus; bool first = true; + int idx; + struct perf_cpu cpu; - for (int i = 0; i < evsel__nr_cpus(counter); i++) { - s2 = config->aggr_get_id(config, evsel__cpus(counter), i); + cpus = evsel__cpus(counter); + perf_cpu_map__for_each_cpu(cpu, idx, cpus) { + s2 = config->aggr_get_id(config, cpu); for (s = 0; s < config->aggr_map->nr; s++) { id = config->aggr_map->map[s]; - if (cpu_map__compare_aggr_cpu_id(s2, id)) + if (aggr_cpu_id__equal(&s2, &id)) break; } print_counter_aggrdata(config, counter, s, prefix, false, - &first, i); + &first, cpu); } } @@ -1243,8 +1253,8 @@ static void print_percore(struct perf_stat_config *config, fprintf(output, "%s", prefix); print_counter_aggrdata(config, counter, s, - prefix, metric_only, - &first, -1); + prefix, metric_only, + &first, (struct perf_cpu){ .cpu = -1 }); } if (metric_only) diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 5c7308efa768..10af7804e482 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -32,7 +32,7 @@ struct saved_value { struct evsel *evsel; enum stat_type type; int ctx; - int cpu; + int cpu_map_idx; struct cgroup *cgrp; struct runtime_stat *stat; struct stats stats; @@ -47,8 +47,8 @@ static int saved_value_cmp(struct rb_node *rb_node, const void *entry) rb_node); const struct saved_value *b = entry; - if (a->cpu != b->cpu) - return a->cpu - b->cpu; + if (a->cpu_map_idx != b->cpu_map_idx) + return a->cpu_map_idx - b->cpu_map_idx; /* * Previously the rbtree was used to link generic metrics. @@ -105,7 +105,7 @@ static void saved_value_delete(struct rblist *rblist __maybe_unused, } static struct saved_value *saved_value_lookup(struct evsel *evsel, - int cpu, + int cpu_map_idx, bool create, enum stat_type type, int ctx, @@ -115,7 +115,7 @@ static struct saved_value *saved_value_lookup(struct evsel *evsel, struct rblist *rblist; struct rb_node *nd; struct saved_value dm = { - .cpu = cpu, + .cpu_map_idx = cpu_map_idx, .evsel = evsel, .type = type, .ctx = ctx, @@ -213,10 +213,10 @@ struct runtime_stat_data { static void update_runtime_stat(struct runtime_stat *st, enum stat_type type, - int cpu, u64 count, + int cpu_map_idx, u64 count, struct runtime_stat_data *rsd) { - struct saved_value *v = saved_value_lookup(NULL, cpu, true, type, + struct saved_value *v = saved_value_lookup(NULL, cpu_map_idx, true, type, rsd->ctx, st, rsd->cgrp); if (v) @@ -229,7 +229,7 @@ static void update_runtime_stat(struct runtime_stat *st, * instruction rates, etc: */ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, - int cpu, struct runtime_stat *st) + int cpu_map_idx, struct runtime_stat *st) { u64 count_ns = count; struct saved_value *v; @@ -241,88 +241,88 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, count *= counter->scale; if (evsel__is_clock(counter)) - update_runtime_stat(st, STAT_NSECS, cpu, count_ns, &rsd); + update_runtime_stat(st, STAT_NSECS, cpu_map_idx, count_ns, &rsd); else if (evsel__match(counter, HARDWARE, HW_CPU_CYCLES)) - update_runtime_stat(st, STAT_CYCLES, cpu, count, &rsd); + update_runtime_stat(st, STAT_CYCLES, cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, CYCLES_IN_TX)) - update_runtime_stat(st, STAT_CYCLES_IN_TX, cpu, count, &rsd); + update_runtime_stat(st, STAT_CYCLES_IN_TX, cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, TRANSACTION_START)) - update_runtime_stat(st, STAT_TRANSACTION, cpu, count, &rsd); + update_runtime_stat(st, STAT_TRANSACTION, cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, ELISION_START)) - update_runtime_stat(st, STAT_ELISION, cpu, count, &rsd); + update_runtime_stat(st, STAT_ELISION, cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, TOPDOWN_TOTAL_SLOTS)) update_runtime_stat(st, STAT_TOPDOWN_TOTAL_SLOTS, - cpu, count, &rsd); + cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_ISSUED)) update_runtime_stat(st, STAT_TOPDOWN_SLOTS_ISSUED, - cpu, count, &rsd); + cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_RETIRED)) update_runtime_stat(st, STAT_TOPDOWN_SLOTS_RETIRED, - cpu, count, &rsd); + cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_BUBBLES)) update_runtime_stat(st, STAT_TOPDOWN_FETCH_BUBBLES, - cpu, count, &rsd); + cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, TOPDOWN_RECOVERY_BUBBLES)) update_runtime_stat(st, STAT_TOPDOWN_RECOVERY_BUBBLES, - cpu, count, &rsd); + cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, TOPDOWN_RETIRING)) update_runtime_stat(st, STAT_TOPDOWN_RETIRING, - cpu, count, &rsd); + cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, TOPDOWN_BAD_SPEC)) update_runtime_stat(st, STAT_TOPDOWN_BAD_SPEC, - cpu, count, &rsd); + cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, TOPDOWN_FE_BOUND)) update_runtime_stat(st, STAT_TOPDOWN_FE_BOUND, - cpu, count, &rsd); + cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, TOPDOWN_BE_BOUND)) update_runtime_stat(st, STAT_TOPDOWN_BE_BOUND, - cpu, count, &rsd); + cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, TOPDOWN_HEAVY_OPS)) update_runtime_stat(st, STAT_TOPDOWN_HEAVY_OPS, - cpu, count, &rsd); + cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, TOPDOWN_BR_MISPREDICT)) update_runtime_stat(st, STAT_TOPDOWN_BR_MISPREDICT, - cpu, count, &rsd); + cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_LAT)) update_runtime_stat(st, STAT_TOPDOWN_FETCH_LAT, - cpu, count, &rsd); + cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, TOPDOWN_MEM_BOUND)) update_runtime_stat(st, STAT_TOPDOWN_MEM_BOUND, - cpu, count, &rsd); + cpu_map_idx, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) update_runtime_stat(st, STAT_STALLED_CYCLES_FRONT, - cpu, count, &rsd); + cpu_map_idx, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND)) update_runtime_stat(st, STAT_STALLED_CYCLES_BACK, - cpu, count, &rsd); + cpu_map_idx, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS)) - update_runtime_stat(st, STAT_BRANCHES, cpu, count, &rsd); + update_runtime_stat(st, STAT_BRANCHES, cpu_map_idx, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES)) - update_runtime_stat(st, STAT_CACHEREFS, cpu, count, &rsd); + update_runtime_stat(st, STAT_CACHEREFS, cpu_map_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1D)) - update_runtime_stat(st, STAT_L1_DCACHE, cpu, count, &rsd); + update_runtime_stat(st, STAT_L1_DCACHE, cpu_map_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1I)) - update_runtime_stat(st, STAT_L1_ICACHE, cpu, count, &rsd); + update_runtime_stat(st, STAT_L1_ICACHE, cpu_map_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_LL)) - update_runtime_stat(st, STAT_LL_CACHE, cpu, count, &rsd); + update_runtime_stat(st, STAT_LL_CACHE, cpu_map_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_DTLB)) - update_runtime_stat(st, STAT_DTLB_CACHE, cpu, count, &rsd); + update_runtime_stat(st, STAT_DTLB_CACHE, cpu_map_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_ITLB)) - update_runtime_stat(st, STAT_ITLB_CACHE, cpu, count, &rsd); + update_runtime_stat(st, STAT_ITLB_CACHE, cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, SMI_NUM)) - update_runtime_stat(st, STAT_SMI_NUM, cpu, count, &rsd); + update_runtime_stat(st, STAT_SMI_NUM, cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, APERF)) - update_runtime_stat(st, STAT_APERF, cpu, count, &rsd); + update_runtime_stat(st, STAT_APERF, cpu_map_idx, count, &rsd); if (counter->collect_stat) { - v = saved_value_lookup(counter, cpu, true, STAT_NONE, 0, st, + v = saved_value_lookup(counter, cpu_map_idx, true, STAT_NONE, 0, st, rsd.cgrp); update_stats(&v->stats, count); if (counter->metric_leader) v->metric_total += count; } else if (counter->metric_leader) { v = saved_value_lookup(counter->metric_leader, - cpu, true, STAT_NONE, 0, st, rsd.cgrp); + cpu_map_idx, true, STAT_NONE, 0, st, rsd.cgrp); v->metric_total += count; v->metric_other++; } @@ -464,12 +464,12 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list) } static double runtime_stat_avg(struct runtime_stat *st, - enum stat_type type, int cpu, + enum stat_type type, int cpu_map_idx, struct runtime_stat_data *rsd) { struct saved_value *v; - v = saved_value_lookup(NULL, cpu, false, type, rsd->ctx, st, rsd->cgrp); + v = saved_value_lookup(NULL, cpu_map_idx, false, type, rsd->ctx, st, rsd->cgrp); if (!v) return 0.0; @@ -477,12 +477,12 @@ static double runtime_stat_avg(struct runtime_stat *st, } static double runtime_stat_n(struct runtime_stat *st, - enum stat_type type, int cpu, + enum stat_type type, int cpu_map_idx, struct runtime_stat_data *rsd) { struct saved_value *v; - v = saved_value_lookup(NULL, cpu, false, type, rsd->ctx, st, rsd->cgrp); + v = saved_value_lookup(NULL, cpu_map_idx, false, type, rsd->ctx, st, rsd->cgrp); if (!v) return 0.0; @@ -490,7 +490,7 @@ static double runtime_stat_n(struct runtime_stat *st, } static void print_stalled_cycles_frontend(struct perf_stat_config *config, - int cpu, double avg, + int cpu_map_idx, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st, struct runtime_stat_data *rsd) @@ -498,7 +498,7 @@ static void print_stalled_cycles_frontend(struct perf_stat_config *config, double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(st, STAT_CYCLES, cpu, rsd); + total = runtime_stat_avg(st, STAT_CYCLES, cpu_map_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -513,7 +513,7 @@ static void print_stalled_cycles_frontend(struct perf_stat_config *config, } static void print_stalled_cycles_backend(struct perf_stat_config *config, - int cpu, double avg, + int cpu_map_idx, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st, struct runtime_stat_data *rsd) @@ -521,7 +521,7 @@ static void print_stalled_cycles_backend(struct perf_stat_config *config, double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(st, STAT_CYCLES, cpu, rsd); + total = runtime_stat_avg(st, STAT_CYCLES, cpu_map_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -532,7 +532,7 @@ static void print_stalled_cycles_backend(struct perf_stat_config *config, } static void print_branch_misses(struct perf_stat_config *config, - int cpu, double avg, + int cpu_map_idx, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st, struct runtime_stat_data *rsd) @@ -540,7 +540,7 @@ static void print_branch_misses(struct perf_stat_config *config, double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(st, STAT_BRANCHES, cpu, rsd); + total = runtime_stat_avg(st, STAT_BRANCHES, cpu_map_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -551,7 +551,7 @@ static void print_branch_misses(struct perf_stat_config *config, } static void print_l1_dcache_misses(struct perf_stat_config *config, - int cpu, double avg, + int cpu_map_idx, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st, struct runtime_stat_data *rsd) @@ -559,7 +559,7 @@ static void print_l1_dcache_misses(struct perf_stat_config *config, double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(st, STAT_L1_DCACHE, cpu, rsd); + total = runtime_stat_avg(st, STAT_L1_DCACHE, cpu_map_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -570,7 +570,7 @@ static void print_l1_dcache_misses(struct perf_stat_config *config, } static void print_l1_icache_misses(struct perf_stat_config *config, - int cpu, double avg, + int cpu_map_idx, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st, struct runtime_stat_data *rsd) @@ -578,7 +578,7 @@ static void print_l1_icache_misses(struct perf_stat_config *config, double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(st, STAT_L1_ICACHE, cpu, rsd); + total = runtime_stat_avg(st, STAT_L1_ICACHE, cpu_map_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -588,7 +588,7 @@ static void print_l1_icache_misses(struct perf_stat_config *config, } static void print_dtlb_cache_misses(struct perf_stat_config *config, - int cpu, double avg, + int cpu_map_idx, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st, struct runtime_stat_data *rsd) @@ -596,7 +596,7 @@ static void print_dtlb_cache_misses(struct perf_stat_config *config, double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(st, STAT_DTLB_CACHE, cpu, rsd); + total = runtime_stat_avg(st, STAT_DTLB_CACHE, cpu_map_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -606,7 +606,7 @@ static void print_dtlb_cache_misses(struct perf_stat_config *config, } static void print_itlb_cache_misses(struct perf_stat_config *config, - int cpu, double avg, + int cpu_map_idx, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st, struct runtime_stat_data *rsd) @@ -614,7 +614,7 @@ static void print_itlb_cache_misses(struct perf_stat_config *config, double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(st, STAT_ITLB_CACHE, cpu, rsd); + total = runtime_stat_avg(st, STAT_ITLB_CACHE, cpu_map_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -624,7 +624,7 @@ static void print_itlb_cache_misses(struct perf_stat_config *config, } static void print_ll_cache_misses(struct perf_stat_config *config, - int cpu, double avg, + int cpu_map_idx, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st, struct runtime_stat_data *rsd) @@ -632,7 +632,7 @@ static void print_ll_cache_misses(struct perf_stat_config *config, double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(st, STAT_LL_CACHE, cpu, rsd); + total = runtime_stat_avg(st, STAT_LL_CACHE, cpu_map_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -690,61 +690,61 @@ static double sanitize_val(double x) return x; } -static double td_total_slots(int cpu, struct runtime_stat *st, +static double td_total_slots(int cpu_map_idx, struct runtime_stat *st, struct runtime_stat_data *rsd) { - return runtime_stat_avg(st, STAT_TOPDOWN_TOTAL_SLOTS, cpu, rsd); + return runtime_stat_avg(st, STAT_TOPDOWN_TOTAL_SLOTS, cpu_map_idx, rsd); } -static double td_bad_spec(int cpu, struct runtime_stat *st, +static double td_bad_spec(int cpu_map_idx, struct runtime_stat *st, struct runtime_stat_data *rsd) { double bad_spec = 0; double total_slots; double total; - total = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_ISSUED, cpu, rsd) - - runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED, cpu, rsd) + - runtime_stat_avg(st, STAT_TOPDOWN_RECOVERY_BUBBLES, cpu, rsd); + total = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_ISSUED, cpu_map_idx, rsd) - + runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED, cpu_map_idx, rsd) + + runtime_stat_avg(st, STAT_TOPDOWN_RECOVERY_BUBBLES, cpu_map_idx, rsd); - total_slots = td_total_slots(cpu, st, rsd); + total_slots = td_total_slots(cpu_map_idx, st, rsd); if (total_slots) bad_spec = total / total_slots; return sanitize_val(bad_spec); } -static double td_retiring(int cpu, struct runtime_stat *st, +static double td_retiring(int cpu_map_idx, struct runtime_stat *st, struct runtime_stat_data *rsd) { double retiring = 0; - double total_slots = td_total_slots(cpu, st, rsd); + double total_slots = td_total_slots(cpu_map_idx, st, rsd); double ret_slots = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED, - cpu, rsd); + cpu_map_idx, rsd); if (total_slots) retiring = ret_slots / total_slots; return retiring; } -static double td_fe_bound(int cpu, struct runtime_stat *st, +static double td_fe_bound(int cpu_map_idx, struct runtime_stat *st, struct runtime_stat_data *rsd) { double fe_bound = 0; - double total_slots = td_total_slots(cpu, st, rsd); + double total_slots = td_total_slots(cpu_map_idx, st, rsd); double fetch_bub = runtime_stat_avg(st, STAT_TOPDOWN_FETCH_BUBBLES, - cpu, rsd); + cpu_map_idx, rsd); if (total_slots) fe_bound = fetch_bub / total_slots; return fe_bound; } -static double td_be_bound(int cpu, struct runtime_stat *st, +static double td_be_bound(int cpu_map_idx, struct runtime_stat *st, struct runtime_stat_data *rsd) { - double sum = (td_fe_bound(cpu, st, rsd) + - td_bad_spec(cpu, st, rsd) + - td_retiring(cpu, st, rsd)); + double sum = (td_fe_bound(cpu_map_idx, st, rsd) + + td_bad_spec(cpu_map_idx, st, rsd) + + td_retiring(cpu_map_idx, st, rsd)); if (sum == 0) return 0; return sanitize_val(1.0 - sum); @@ -755,15 +755,15 @@ static double td_be_bound(int cpu, struct runtime_stat *st, * the ratios we need to recreate the sum. */ -static double td_metric_ratio(int cpu, enum stat_type type, +static double td_metric_ratio(int cpu_map_idx, enum stat_type type, struct runtime_stat *stat, struct runtime_stat_data *rsd) { - double sum = runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, cpu, rsd) + - runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, cpu, rsd) + - runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, cpu, rsd) + - runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, cpu, rsd); - double d = runtime_stat_avg(stat, type, cpu, rsd); + double sum = runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, cpu_map_idx, rsd) + + runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, cpu_map_idx, rsd) + + runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, cpu_map_idx, rsd) + + runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, cpu_map_idx, rsd); + double d = runtime_stat_avg(stat, type, cpu_map_idx, rsd); if (sum) return d / sum; @@ -775,23 +775,23 @@ static double td_metric_ratio(int cpu, enum stat_type type, * We allow two missing. */ -static bool full_td(int cpu, struct runtime_stat *stat, +static bool full_td(int cpu_map_idx, struct runtime_stat *stat, struct runtime_stat_data *rsd) { int c = 0; - if (runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, cpu, rsd) > 0) + if (runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, cpu_map_idx, rsd) > 0) c++; - if (runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, cpu, rsd) > 0) + if (runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, cpu_map_idx, rsd) > 0) c++; - if (runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, cpu, rsd) > 0) + if (runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, cpu_map_idx, rsd) > 0) c++; - if (runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, cpu, rsd) > 0) + if (runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, cpu_map_idx, rsd) > 0) c++; return c >= 2; } -static void print_smi_cost(struct perf_stat_config *config, int cpu, +static void print_smi_cost(struct perf_stat_config *config, int cpu_map_idx, struct perf_stat_output_ctx *out, struct runtime_stat *st, struct runtime_stat_data *rsd) @@ -799,9 +799,9 @@ static void print_smi_cost(struct perf_stat_config *config, int cpu, double smi_num, aperf, cycles, cost = 0.0; const char *color = NULL; - smi_num = runtime_stat_avg(st, STAT_SMI_NUM, cpu, rsd); - aperf = runtime_stat_avg(st, STAT_APERF, cpu, rsd); - cycles = runtime_stat_avg(st, STAT_CYCLES, cpu, rsd); + smi_num = runtime_stat_avg(st, STAT_SMI_NUM, cpu_map_idx, rsd); + aperf = runtime_stat_avg(st, STAT_APERF, cpu_map_idx, rsd); + cycles = runtime_stat_avg(st, STAT_CYCLES, cpu_map_idx, rsd); if ((cycles == 0) || (aperf == 0)) return; @@ -818,7 +818,7 @@ static void print_smi_cost(struct perf_stat_config *config, int cpu, static int prepare_metric(struct evsel **metric_events, struct metric_ref *metric_refs, struct expr_parse_ctx *pctx, - int cpu, + int cpu_map_idx, struct runtime_stat *st) { double scale; @@ -836,7 +836,7 @@ static int prepare_metric(struct evsel **metric_events, scale = 1e-9; source_count = 1; } else { - v = saved_value_lookup(metric_events[i], cpu, false, + v = saved_value_lookup(metric_events[i], cpu_map_idx, false, STAT_NONE, 0, st, metric_events[i]->cgrp); if (!v) @@ -874,7 +874,7 @@ static void generic_metric(struct perf_stat_config *config, const char *metric_name, const char *metric_unit, int runtime, - int cpu, + int cpu_map_idx, struct perf_stat_output_ctx *out, struct runtime_stat *st) { @@ -889,7 +889,7 @@ static void generic_metric(struct perf_stat_config *config, return; pctx->runtime = runtime; - i = prepare_metric(metric_events, metric_refs, pctx, cpu, st); + i = prepare_metric(metric_events, metric_refs, pctx, cpu_map_idx, st); if (i < 0) { expr__ctx_free(pctx); return; @@ -934,7 +934,7 @@ static void generic_metric(struct perf_stat_config *config, expr__ctx_free(pctx); } -double test_generic_metric(struct metric_expr *mexp, int cpu, struct runtime_stat *st) +double test_generic_metric(struct metric_expr *mexp, int cpu_map_idx, struct runtime_stat *st) { struct expr_parse_ctx *pctx; double ratio = 0.0; @@ -943,7 +943,7 @@ double test_generic_metric(struct metric_expr *mexp, int cpu, struct runtime_sta if (!pctx) return NAN; - if (prepare_metric(mexp->metric_events, mexp->metric_refs, pctx, cpu, st) < 0) + if (prepare_metric(mexp->metric_events, mexp->metric_refs, pctx, cpu_map_idx, st) < 0) goto out; if (expr__parse(&ratio, pctx, mexp->metric_expr)) @@ -956,7 +956,7 @@ out: void perf_stat__print_shadow_stats(struct perf_stat_config *config, struct evsel *evsel, - double avg, int cpu, + double avg, int cpu_map_idx, struct perf_stat_output_ctx *out, struct rblist *metric_events, struct runtime_stat *st) @@ -975,7 +975,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, if (config->iostat_run) { iostat_print_metric(config, evsel, out); } else if (evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) { - total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd); + total = runtime_stat_avg(st, STAT_CYCLES, cpu_map_idx, &rsd); if (total) { ratio = avg / total; @@ -985,11 +985,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, print_metric(config, ctxp, NULL, NULL, "insn per cycle", 0); } - total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT, cpu, &rsd); + total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT, cpu_map_idx, &rsd); total = max(total, runtime_stat_avg(st, STAT_STALLED_CYCLES_BACK, - cpu, &rsd)); + cpu_map_idx, &rsd)); if (total && avg) { out->new_line(config, ctxp); @@ -999,8 +999,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ratio); } } else if (evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) { - if (runtime_stat_n(st, STAT_BRANCHES, cpu, &rsd) != 0) - print_branch_misses(config, cpu, avg, out, st, &rsd); + if (runtime_stat_n(st, STAT_BRANCHES, cpu_map_idx, &rsd) != 0) + print_branch_misses(config, cpu_map_idx, avg, out, st, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all branches", 0); } else if ( @@ -1009,8 +1009,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(st, STAT_L1_DCACHE, cpu, &rsd) != 0) - print_l1_dcache_misses(config, cpu, avg, out, st, &rsd); + if (runtime_stat_n(st, STAT_L1_DCACHE, cpu_map_idx, &rsd) != 0) + print_l1_dcache_misses(config, cpu_map_idx, avg, out, st, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all L1-dcache accesses", 0); } else if ( @@ -1019,8 +1019,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(st, STAT_L1_ICACHE, cpu, &rsd) != 0) - print_l1_icache_misses(config, cpu, avg, out, st, &rsd); + if (runtime_stat_n(st, STAT_L1_ICACHE, cpu_map_idx, &rsd) != 0) + print_l1_icache_misses(config, cpu_map_idx, avg, out, st, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all L1-icache accesses", 0); } else if ( @@ -1029,8 +1029,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(st, STAT_DTLB_CACHE, cpu, &rsd) != 0) - print_dtlb_cache_misses(config, cpu, avg, out, st, &rsd); + if (runtime_stat_n(st, STAT_DTLB_CACHE, cpu_map_idx, &rsd) != 0) + print_dtlb_cache_misses(config, cpu_map_idx, avg, out, st, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all dTLB cache accesses", 0); } else if ( @@ -1039,8 +1039,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(st, STAT_ITLB_CACHE, cpu, &rsd) != 0) - print_itlb_cache_misses(config, cpu, avg, out, st, &rsd); + if (runtime_stat_n(st, STAT_ITLB_CACHE, cpu_map_idx, &rsd) != 0) + print_itlb_cache_misses(config, cpu_map_idx, avg, out, st, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all iTLB cache accesses", 0); } else if ( @@ -1049,27 +1049,27 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(st, STAT_LL_CACHE, cpu, &rsd) != 0) - print_ll_cache_misses(config, cpu, avg, out, st, &rsd); + if (runtime_stat_n(st, STAT_LL_CACHE, cpu_map_idx, &rsd) != 0) + print_ll_cache_misses(config, cpu_map_idx, avg, out, st, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all LL-cache accesses", 0); } else if (evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) { - total = runtime_stat_avg(st, STAT_CACHEREFS, cpu, &rsd); + total = runtime_stat_avg(st, STAT_CACHEREFS, cpu_map_idx, &rsd); if (total) ratio = avg * 100 / total; - if (runtime_stat_n(st, STAT_CACHEREFS, cpu, &rsd) != 0) + if (runtime_stat_n(st, STAT_CACHEREFS, cpu_map_idx, &rsd) != 0) print_metric(config, ctxp, NULL, "%8.3f %%", "of all cache refs", ratio); else print_metric(config, ctxp, NULL, NULL, "of all cache refs", 0); } else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) { - print_stalled_cycles_frontend(config, cpu, avg, out, st, &rsd); + print_stalled_cycles_frontend(config, cpu_map_idx, avg, out, st, &rsd); } else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) { - print_stalled_cycles_backend(config, cpu, avg, out, st, &rsd); + print_stalled_cycles_backend(config, cpu_map_idx, avg, out, st, &rsd); } else if (evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) { - total = runtime_stat_avg(st, STAT_NSECS, cpu, &rsd); + total = runtime_stat_avg(st, STAT_NSECS, cpu_map_idx, &rsd); if (total) { ratio = avg / total; @@ -1078,7 +1078,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, print_metric(config, ctxp, NULL, NULL, "Ghz", 0); } } else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) { - total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd); + total = runtime_stat_avg(st, STAT_CYCLES, cpu_map_idx, &rsd); if (total) print_metric(config, ctxp, NULL, @@ -1088,8 +1088,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, print_metric(config, ctxp, NULL, NULL, "transactional cycles", 0); } else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) { - total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd); - total2 = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu, &rsd); + total = runtime_stat_avg(st, STAT_CYCLES, cpu_map_idx, &rsd); + total2 = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu_map_idx, &rsd); if (total2 < avg) total2 = avg; @@ -1099,19 +1099,19 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, else print_metric(config, ctxp, NULL, NULL, "aborted cycles", 0); } else if (perf_stat_evsel__is(evsel, TRANSACTION_START)) { - total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu, &rsd); + total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu_map_idx, &rsd); if (avg) ratio = total / avg; - if (runtime_stat_n(st, STAT_CYCLES_IN_TX, cpu, &rsd) != 0) + if (runtime_stat_n(st, STAT_CYCLES_IN_TX, cpu_map_idx, &rsd) != 0) print_metric(config, ctxp, NULL, "%8.0f", "cycles / transaction", ratio); else print_metric(config, ctxp, NULL, NULL, "cycles / transaction", 0); } else if (perf_stat_evsel__is(evsel, ELISION_START)) { - total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu, &rsd); + total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu_map_idx, &rsd); if (avg) ratio = total / avg; @@ -1124,28 +1124,28 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, else print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0); } else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) { - double fe_bound = td_fe_bound(cpu, st, &rsd); + double fe_bound = td_fe_bound(cpu_map_idx, st, &rsd); if (fe_bound > 0.2) color = PERF_COLOR_RED; print_metric(config, ctxp, color, "%8.1f%%", "frontend bound", fe_bound * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_RETIRED)) { - double retiring = td_retiring(cpu, st, &rsd); + double retiring = td_retiring(cpu_map_idx, st, &rsd); if (retiring > 0.7) color = PERF_COLOR_GREEN; print_metric(config, ctxp, color, "%8.1f%%", "retiring", retiring * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_RECOVERY_BUBBLES)) { - double bad_spec = td_bad_spec(cpu, st, &rsd); + double bad_spec = td_bad_spec(cpu_map_idx, st, &rsd); if (bad_spec > 0.1) color = PERF_COLOR_RED; print_metric(config, ctxp, color, "%8.1f%%", "bad speculation", bad_spec * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_ISSUED)) { - double be_bound = td_be_bound(cpu, st, &rsd); + double be_bound = td_be_bound(cpu_map_idx, st, &rsd); const char *name = "backend bound"; static int have_recovery_bubbles = -1; @@ -1158,14 +1158,14 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, if (be_bound > 0.2) color = PERF_COLOR_RED; - if (td_total_slots(cpu, st, &rsd) > 0) + if (td_total_slots(cpu_map_idx, st, &rsd) > 0) print_metric(config, ctxp, color, "%8.1f%%", name, be_bound * 100.); else print_metric(config, ctxp, NULL, NULL, name, 0); } else if (perf_stat_evsel__is(evsel, TOPDOWN_RETIRING) && - full_td(cpu, st, &rsd)) { - double retiring = td_metric_ratio(cpu, + full_td(cpu_map_idx, st, &rsd)) { + double retiring = td_metric_ratio(cpu_map_idx, STAT_TOPDOWN_RETIRING, st, &rsd); if (retiring > 0.7) @@ -1173,8 +1173,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, print_metric(config, ctxp, color, "%8.1f%%", "retiring", retiring * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_FE_BOUND) && - full_td(cpu, st, &rsd)) { - double fe_bound = td_metric_ratio(cpu, + full_td(cpu_map_idx, st, &rsd)) { + double fe_bound = td_metric_ratio(cpu_map_idx, STAT_TOPDOWN_FE_BOUND, st, &rsd); if (fe_bound > 0.2) @@ -1182,8 +1182,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, print_metric(config, ctxp, color, "%8.1f%%", "frontend bound", fe_bound * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_BE_BOUND) && - full_td(cpu, st, &rsd)) { - double be_bound = td_metric_ratio(cpu, + full_td(cpu_map_idx, st, &rsd)) { + double be_bound = td_metric_ratio(cpu_map_idx, STAT_TOPDOWN_BE_BOUND, st, &rsd); if (be_bound > 0.2) @@ -1191,8 +1191,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, print_metric(config, ctxp, color, "%8.1f%%", "backend bound", be_bound * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_BAD_SPEC) && - full_td(cpu, st, &rsd)) { - double bad_spec = td_metric_ratio(cpu, + full_td(cpu_map_idx, st, &rsd)) { + double bad_spec = td_metric_ratio(cpu_map_idx, STAT_TOPDOWN_BAD_SPEC, st, &rsd); if (bad_spec > 0.1) @@ -1200,11 +1200,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, print_metric(config, ctxp, color, "%8.1f%%", "bad speculation", bad_spec * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_HEAVY_OPS) && - full_td(cpu, st, &rsd) && (config->topdown_level > 1)) { - double retiring = td_metric_ratio(cpu, + full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) { + double retiring = td_metric_ratio(cpu_map_idx, STAT_TOPDOWN_RETIRING, st, &rsd); - double heavy_ops = td_metric_ratio(cpu, + double heavy_ops = td_metric_ratio(cpu_map_idx, STAT_TOPDOWN_HEAVY_OPS, st, &rsd); double light_ops = retiring - heavy_ops; @@ -1220,11 +1220,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, print_metric(config, ctxp, color, "%8.1f%%", "light operations", light_ops * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_BR_MISPREDICT) && - full_td(cpu, st, &rsd) && (config->topdown_level > 1)) { - double bad_spec = td_metric_ratio(cpu, + full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) { + double bad_spec = td_metric_ratio(cpu_map_idx, STAT_TOPDOWN_BAD_SPEC, st, &rsd); - double br_mis = td_metric_ratio(cpu, + double br_mis = td_metric_ratio(cpu_map_idx, STAT_TOPDOWN_BR_MISPREDICT, st, &rsd); double m_clears = bad_spec - br_mis; @@ -1240,11 +1240,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, print_metric(config, ctxp, color, "%8.1f%%", "machine clears", m_clears * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_LAT) && - full_td(cpu, st, &rsd) && (config->topdown_level > 1)) { - double fe_bound = td_metric_ratio(cpu, + full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) { + double fe_bound = td_metric_ratio(cpu_map_idx, STAT_TOPDOWN_FE_BOUND, st, &rsd); - double fetch_lat = td_metric_ratio(cpu, + double fetch_lat = td_metric_ratio(cpu_map_idx, STAT_TOPDOWN_FETCH_LAT, st, &rsd); double fetch_bw = fe_bound - fetch_lat; @@ -1260,11 +1260,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, print_metric(config, ctxp, color, "%8.1f%%", "fetch bandwidth", fetch_bw * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_MEM_BOUND) && - full_td(cpu, st, &rsd) && (config->topdown_level > 1)) { - double be_bound = td_metric_ratio(cpu, + full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) { + double be_bound = td_metric_ratio(cpu_map_idx, STAT_TOPDOWN_BE_BOUND, st, &rsd); - double mem_bound = td_metric_ratio(cpu, + double mem_bound = td_metric_ratio(cpu_map_idx, STAT_TOPDOWN_MEM_BOUND, st, &rsd); double core_bound = be_bound - mem_bound; @@ -1281,12 +1281,12 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, core_bound * 100.); } else if (evsel->metric_expr) { generic_metric(config, evsel->metric_expr, evsel->metric_events, NULL, - evsel->name, evsel->metric_name, NULL, 1, cpu, out, st); - } else if (runtime_stat_n(st, STAT_NSECS, cpu, &rsd) != 0) { + evsel->name, evsel->metric_name, NULL, 1, cpu_map_idx, out, st); + } else if (runtime_stat_n(st, STAT_NSECS, cpu_map_idx, &rsd) != 0) { char unit = ' '; char unit_buf[10] = "/sec"; - total = runtime_stat_avg(st, STAT_NSECS, cpu, &rsd); + total = runtime_stat_avg(st, STAT_NSECS, cpu_map_idx, &rsd); if (total) ratio = convert_unit_double(1000000000.0 * avg / total, &unit); @@ -1294,7 +1294,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit); print_metric(config, ctxp, NULL, "%8.3f", unit_buf, ratio); } else if (perf_stat_evsel__is(evsel, SMI_NUM)) { - print_smi_cost(config, cpu, out, st, &rsd); + print_smi_cost(config, cpu_map_idx, out, st, &rsd); } else { num = 0; } @@ -1307,7 +1307,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, out->new_line(config, ctxp); generic_metric(config, mexp->metric_expr, mexp->metric_events, mexp->metric_refs, evsel->name, mexp->metric_name, - mexp->metric_unit, mexp->runtime, cpu, out, st); + mexp->metric_unit, mexp->runtime, cpu_map_idx, out, st); } } if (num == 0) diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 09ea334586f2..ee6f03481215 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -152,11 +152,13 @@ static void evsel__free_stat_priv(struct evsel *evsel) zfree(&evsel->stats); } -static int evsel__alloc_prev_raw_counts(struct evsel *evsel, int ncpus, int nthreads) +static int evsel__alloc_prev_raw_counts(struct evsel *evsel) { + int cpu_map_nr = evsel__nr_cpus(evsel); + int nthreads = perf_thread_map__nr(evsel->core.threads); struct perf_counts *counts; - counts = perf_counts__new(ncpus, nthreads); + counts = perf_counts__new(cpu_map_nr, nthreads); if (counts) evsel->prev_raw_counts = counts; @@ -177,12 +179,9 @@ static void evsel__reset_prev_raw_counts(struct evsel *evsel) static int evsel__alloc_stats(struct evsel *evsel, bool alloc_raw) { - int ncpus = evsel__nr_cpus(evsel); - int nthreads = perf_thread_map__nr(evsel->core.threads); - if (evsel__alloc_stat_priv(evsel) < 0 || - evsel__alloc_counts(evsel, ncpus, nthreads) < 0 || - (alloc_raw && evsel__alloc_prev_raw_counts(evsel, ncpus, nthreads) < 0)) + evsel__alloc_counts(evsel) < 0 || + (alloc_raw && evsel__alloc_prev_raw_counts(evsel) < 0)) return -ENOMEM; return 0; @@ -293,11 +292,12 @@ static bool pkg_id_equal(const void *__key1, const void *__key2, return *key1 == *key2; } -static int check_per_pkg(struct evsel *counter, - struct perf_counts_values *vals, int cpu, bool *skip) +static int check_per_pkg(struct evsel *counter, struct perf_counts_values *vals, + int cpu_map_idx, bool *skip) { struct hashmap *mask = counter->per_pkg_mask; struct perf_cpu_map *cpus = evsel__cpus(counter); + struct perf_cpu cpu = perf_cpu_map__cpu(cpus, cpu_map_idx); int s, d, ret = 0; uint64_t *key; @@ -328,7 +328,7 @@ static int check_per_pkg(struct evsel *counter, if (!(vals->run && vals->ena)) return 0; - s = cpu_map__get_socket(cpus, cpu, NULL).socket; + s = cpu__get_socket_id(cpu); if (s < 0) return -1; @@ -336,7 +336,7 @@ static int check_per_pkg(struct evsel *counter, * On multi-die system, die_id > 0. On no-die system, die_id = 0. * We use hashmap(socket, die) to check the used socket+die pair. */ - d = cpu_map__get_die(cpus, cpu, NULL).die; + d = cpu__get_die_id(cpu); if (d < 0) return -1; @@ -345,9 +345,10 @@ static int check_per_pkg(struct evsel *counter, return -ENOMEM; *key = (uint64_t)d << 32 | s; - if (hashmap__find(mask, (void *)key, NULL)) + if (hashmap__find(mask, (void *)key, NULL)) { *skip = true; - else + free(key); + } else ret = hashmap__add(mask, (void *)key, (void *)1); return ret; @@ -355,14 +356,14 @@ static int check_per_pkg(struct evsel *counter, static int process_counter_values(struct perf_stat_config *config, struct evsel *evsel, - int cpu, int thread, + int cpu_map_idx, int thread, struct perf_counts_values *count) { struct perf_counts_values *aggr = &evsel->counts->aggr; static struct perf_counts_values zero; bool skip = false; - if (check_per_pkg(evsel, count, cpu, &skip)) { + if (check_per_pkg(evsel, count, cpu_map_idx, &skip)) { pr_err("failed to read per-pkg counter\n"); return -1; } @@ -378,11 +379,11 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel, case AGGR_NODE: case AGGR_NONE: if (!evsel->snapshot) - evsel__compute_deltas(evsel, cpu, thread, count); + evsel__compute_deltas(evsel, cpu_map_idx, thread, count); perf_counts_values__scale(count, config->scale, NULL); if ((config->aggr_mode == AGGR_NONE) && (!evsel->percore)) { perf_stat__update_shadow_stats(evsel, count->val, - cpu, &rt_stat); + cpu_map_idx, &rt_stat); } if (config->aggr_mode == AGGR_THREAD) { @@ -411,15 +412,15 @@ static int process_counter_maps(struct perf_stat_config *config, { int nthreads = perf_thread_map__nr(counter->core.threads); int ncpus = evsel__nr_cpus(counter); - int cpu, thread; + int idx, thread; if (counter->core.system_wide) nthreads = 1; for (thread = 0; thread < nthreads; thread++) { - for (cpu = 0; cpu < ncpus; cpu++) { - if (process_counter_values(config, counter, cpu, thread, - perf_counts(counter->counts, cpu, thread))) + for (idx = 0; idx < ncpus; idx++) { + if (process_counter_values(config, counter, idx, thread, + perf_counts(counter->counts, idx, thread))) return -1; } } @@ -531,7 +532,7 @@ size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp) int create_perf_stat_counter(struct evsel *evsel, struct perf_stat_config *config, struct target *target, - int cpu) + int cpu_map_idx) { struct perf_event_attr *attr = &evsel->core.attr; struct evsel *leader = evsel__leader(evsel); @@ -585,7 +586,7 @@ int create_perf_stat_counter(struct evsel *evsel, } if (target__has_cpu(target) && !target__has_per_thread(target)) - return evsel__open_per_cpu(evsel, evsel__cpus(evsel), cpu); + return evsel__open_per_cpu(evsel, evsel__cpus(evsel), cpu_map_idx); return evsel__open_per_thread(evsel, evsel->core.threads); } diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 32c8527de347..335d19cc3063 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -108,8 +108,7 @@ struct runtime_stat { struct rblist value_list; }; -typedef struct aggr_cpu_id (*aggr_get_id_t)(struct perf_stat_config *config, - struct perf_cpu_map *m, int cpu); +typedef struct aggr_cpu_id (*aggr_get_id_t)(struct perf_stat_config *config, struct perf_cpu cpu); struct perf_stat_config { enum aggr_mode aggr_mode; @@ -209,7 +208,7 @@ void perf_stat__init_shadow_stats(void); void perf_stat__reset_shadow_stats(void); void perf_stat__reset_shadow_per_stat(struct runtime_stat *st); void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, - int cpu, struct runtime_stat *st); + int cpu_map_idx, struct runtime_stat *st); struct perf_stat_output_ctx { void *ctx; print_metric_t print_metric; @@ -249,10 +248,10 @@ size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp); int create_perf_stat_counter(struct evsel *evsel, struct perf_stat_config *config, struct target *target, - int cpu); + int cpu_map_idx); void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *config, struct target *_target, struct timespec *ts, int argc, const char **argv); struct metric_expr; -double test_generic_metric(struct metric_expr *mexp, int cpu, struct runtime_stat *st); +double test_generic_metric(struct metric_expr *mexp, int cpu_map_idx, struct runtime_stat *st); #endif diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c index 96f941e01681..4c9f211249db 100644 --- a/tools/perf/util/svghelper.c +++ b/tools/perf/util/svghelper.c @@ -728,7 +728,7 @@ static int str_to_bitmap(char *s, cpumask_t *b, int nr_cpus) int i; int ret = 0; struct perf_cpu_map *m; - int c; + struct perf_cpu c; m = perf_cpu_map__new(s); if (!m) @@ -736,12 +736,12 @@ static int str_to_bitmap(char *s, cpumask_t *b, int nr_cpus) for (i = 0; i < m->nr; i++) { c = m->map[i]; - if (c >= nr_cpus) { + if (c.cpu >= nr_cpus) { ret = -1; break; } - set_bit(c, cpumask_bits(b)); + set_bit(c.cpu, cpumask_bits(b)); } perf_cpu_map__put(m); diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index 198982109f0f..c9ba8050cc2b 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -1191,7 +1191,7 @@ static void synthesize_cpus(struct cpu_map_entries *cpus, cpus->nr = map->nr; for (i = 0; i < map->nr; i++) - cpus->cpu[i] = map->map[i]; + cpus->cpu[i] = map->map[i].cpu; } static void synthesize_mask(struct perf_record_record_cpu_map *mask, @@ -1203,7 +1203,7 @@ static void synthesize_mask(struct perf_record_record_cpu_map *mask, mask->long_size = sizeof(long); for (i = 0; i < map->nr; i++) - set_bit(map->map[i], mask->mask); + set_bit(map->map[i].cpu, mask->mask); } static size_t cpus_size(struct perf_cpu_map *map) @@ -1219,7 +1219,7 @@ static size_t mask_size(struct perf_cpu_map *map, int *max) for (i = 0; i < map->nr; i++) { /* bit position of the cpu is + 1 */ - int bit = map->map[i] + 1; + int bit = map->map[i].cpu + 1; if (bit > *max) *max = bit; @@ -1354,7 +1354,7 @@ int perf_event__synthesize_stat_config(struct perf_tool *tool, } int perf_event__synthesize_stat(struct perf_tool *tool, - u32 cpu, u32 thread, u64 id, + struct perf_cpu cpu, u32 thread, u64 id, struct perf_counts_values *count, perf_event__handler_t process, struct machine *machine) @@ -1366,7 +1366,7 @@ int perf_event__synthesize_stat(struct perf_tool *tool, event.header.misc = 0; event.id = id; - event.cpu = cpu; + event.cpu = cpu.cpu; event.thread = thread; event.val = count->val; event.ena = count->ena; @@ -1763,7 +1763,7 @@ int perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_ } e->idx = sid->idx; - e->cpu = sid->cpu; + e->cpu = sid->cpu.cpu; e->tid = sid->tid; } } diff --git a/tools/perf/util/synthetic-events.h b/tools/perf/util/synthetic-events.h index c931433bacbf..78a0450db164 100644 --- a/tools/perf/util/synthetic-events.h +++ b/tools/perf/util/synthetic-events.h @@ -6,6 +6,7 @@ #include // pid_t #include #include +#include struct auxtrace_record; struct dso; @@ -63,7 +64,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo int perf_event__synthesize_stat_config(struct perf_tool *tool, struct perf_stat_config *config, perf_event__handler_t process, struct machine *machine); int perf_event__synthesize_stat_events(struct perf_stat_config *config, struct perf_tool *tool, struct evlist *evlist, perf_event__handler_t process, bool attrs); int perf_event__synthesize_stat_round(struct perf_tool *tool, u64 time, u64 type, perf_event__handler_t process, struct machine *machine); -int perf_event__synthesize_stat(struct perf_tool *tool, u32 cpu, u32 thread, u64 id, struct perf_counts_values *count, perf_event__handler_t process, struct machine *machine); +int perf_event__synthesize_stat(struct perf_tool *tool, struct perf_cpu cpu, u32 thread, u64 id, struct perf_counts_values *count, perf_event__handler_t process, struct machine *machine); int perf_event__synthesize_thread_map2(struct perf_tool *tool, struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine); int perf_event__synthesize_thread_map(struct perf_tool *tool, struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine, bool needs_mmap, bool mmap_data); int perf_event__synthesize_threads(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine, bool needs_mmap, bool mmap_data, unsigned int nr_threads_synthesize); diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index df3c4671be72..fb4f6616b5fa 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -416,3 +416,18 @@ char *perf_exe(char *buf, int len) } return strcpy(buf, "perf"); } + +void perf_debuginfod_setup(struct perf_debuginfod *di) +{ + /* + * By default '!di->set' we clear DEBUGINFOD_URLS, so debuginfod + * processing is not triggered, otherwise we set it to 'di->urls' + * value. If 'di->urls' is "system" we keep DEBUGINFOD_URLS value. + */ + if (!di->set) + setenv("DEBUGINFOD_URLS", "", 1); + else if (di->urls && strcmp(di->urls, "system")) + setenv("DEBUGINFOD_URLS", di->urls, 1); + + pr_debug("DEBUGINFOD_URLS=%s\n", getenv("DEBUGINFOD_URLS")); +} diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 9f0d36ba77f2..7b625cbd2dd8 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -11,6 +11,9 @@ #include #include #include +#ifndef __cplusplus +#include +#endif /* General helper functions */ void usage(const char *err) __noreturn; @@ -66,6 +69,12 @@ extern bool test_attr__enabled; void test_attr__ready(void); void test_attr__init(void); struct perf_event_attr; -void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu, +void test_attr__open(struct perf_event_attr *attr, pid_t pid, struct perf_cpu cpu, int fd, int group_fd, unsigned long flags); + +struct perf_debuginfod { + const char *urls; + bool set; +}; +void perf_debuginfod_setup(struct perf_debuginfod *di); #endif /* GIT_COMPAT_UTIL_H */ diff --git a/tools/power/acpi/.gitignore b/tools/power/acpi/.gitignore index 0b319fc8bb17..eada0297ef88 100644 --- a/tools/power/acpi/.gitignore +++ b/tools/power/acpi/.gitignore @@ -2,4 +2,5 @@ /acpidbg /acpidump /ec +/pfrut /include/ diff --git a/tools/power/acpi/Makefile b/tools/power/acpi/Makefile index a249c50ebf55..5ff1d9c864d0 100644 --- a/tools/power/acpi/Makefile +++ b/tools/power/acpi/Makefile @@ -9,18 +9,18 @@ include ../../scripts/Makefile.include .NOTPARALLEL: -all: acpidbg acpidump ec -clean: acpidbg_clean acpidump_clean ec_clean -install: acpidbg_install acpidump_install ec_install -uninstall: acpidbg_uninstall acpidump_uninstall ec_uninstall +all: acpidbg acpidump ec pfrut +clean: acpidbg_clean acpidump_clean ec_clean pfrut_clean +install: acpidbg_install acpidump_install ec_install pfrut_install +uninstall: acpidbg_uninstall acpidump_uninstall ec_uninstall pfrut_uninstall -acpidbg acpidump ec: FORCE +acpidbg acpidump ec pfrut: FORCE $(call descend,tools/$@,all) -acpidbg_clean acpidump_clean ec_clean: +acpidbg_clean acpidump_clean ec_clean pfrut_clean: $(call descend,tools/$(@:_clean=),clean) -acpidbg_install acpidump_install ec_install: +acpidbg_install acpidump_install ec_install pfrut_install: $(call descend,tools/$(@:_install=),install) -acpidbg_uninstall acpidump_uninstall ec_uninstall: +acpidbg_uninstall acpidump_uninstall ec_uninstall pfrut_uninstall: $(call descend,tools/$(@:_uninstall=),uninstall) .PHONY: FORCE diff --git a/tools/power/acpi/Makefile.rules b/tools/power/acpi/Makefile.rules index 1d7616f5d0ae..b71aada77688 100644 --- a/tools/power/acpi/Makefile.rules +++ b/tools/power/acpi/Makefile.rules @@ -9,7 +9,7 @@ objdir := $(OUTPUT)tools/$(TOOL)/ toolobjs := $(addprefix $(objdir),$(TOOL_OBJS)) $(OUTPUT)$(TOOL): $(toolobjs) FORCE $(ECHO) " LD " $(subst $(OUTPUT),,$@) - $(QUIET) $(LD) $(CFLAGS) $(LDFLAGS) $(toolobjs) -L$(OUTPUT) -o $@ + $(QUIET) $(LD) $(CFLAGS) $(toolobjs) $(LDFLAGS) -L$(OUTPUT) -o $@ $(ECHO) " STRIP " $(subst $(OUTPUT),,$@) $(QUIET) $(STRIPCMD) $@ diff --git a/tools/power/acpi/man/pfrut.8 b/tools/power/acpi/man/pfrut.8 new file mode 100644 index 000000000000..3db574770e8d --- /dev/null +++ b/tools/power/acpi/man/pfrut.8 @@ -0,0 +1,137 @@ +.TH "PFRUT" "8" "October 2021" "pfrut 1.0" "" +.hy +.SH Name +.PP +pfrut \- Platform Firmware Runtime Update and Telemetry tool +.SH SYNOPSIS +.PP +\f[B]pfrut\f[R] [\f[I]Options\f[R]] +.SH DESCRIPTION +.PP +The PFRUT(Platform Firmware Runtime Update and Telemetry) kernel interface is designed +to +.PD 0 +.P +.PD +interact with the platform firmware interface defined in the +.PD 0 +.P +.PD +Management Mode Firmware Runtime +Update (https://uefi.org/sites/default/files/resources/Intel_MM_OS_Interface_Spec_Rev100.pdf) +.PD 0 +.P +.PD +\f[B]pfrut\f[R] is the tool to interact with the kernel interface. +.PD 0 +.P +.PD +.SH OPTIONS +.TP +.B \f[B]\-h\f[R], \f[B]\-\-help\f[R] +Display helper information. +.TP +.B \f[B]\-l\f[R], \f[B]\-\-load\f[R] +Load the capsule file into the system. +To be more specific, the capsule file will be copied to the +communication buffer. +.TP +.B \f[B]\-s\f[R], \f[B]\-\-stage\f[R] +Stage the capsule image from communication buffer into Management Mode +and perform authentication. +.TP +.B \f[B]\-a\f[R], \f[B]\-\-activate\f[R] +Activate a previous staged capsule image. +.TP +.B \f[B]\-u\f[R], \f[B]\-\-update\f[R] +Perform both stage and activation actions. +.TP +.B \f[B]\-q\f[R], \f[B]\-\-query\f[R] +Query the update capability. +.TP +.B \f[B]\-d\f[R], \f[B]\-\-setrev\f[R] +Set the revision ID of code injection/driver update. +.TP +.B \f[B]\-D\f[R], \f[B]\-\-setrevlog\f[R] +Set the revision ID of telemetry. +.TP +.B \f[B]\-G\f[R], \f[B]\-\-getloginfo\f[R] +Get telemetry log information and print it out. +.TP +.B \f[B]\-T\f[R], \f[B]\-\-type\f[R] +Set the telemetry log data type. +.TP +.B \f[B]\-L\f[R], \f[B]\-\-level\f[R] +Set the telemetry log level. +.TP +.B \f[B]\-R\f[R], \f[B]\-\-read\f[R] +Read all the telemetry data and print it out. +.SH EXAMPLES +.PP +\f[B]pfrut \-G\f[R] +.PP +log_level:4 +.PD 0 +.P +.PD +log_type:0 +.PD 0 +.P +.PD +log_revid:2 +.PD 0 +.P +.PD +max_data_size:65536 +.PD 0 +.P +.PD +chunk1_size:0 +.PD 0 +.P +.PD +chunk2_size:1401 +.PD 0 +.P +.PD +rollover_cnt:0 +.PD 0 +.P +.PD +reset_cnt:4 +.PP +\f[B]pfru \-q\f[R] +.PP +code injection image type:794bf8b2\-6e7b\-454e\-885f\-3fb9bb185402 +.PD 0 +.P +.PD +fw_version:0 +.PD 0 +.P +.PD +code_rt_version:1 +.PD 0 +.P +.PD +driver update image type:0e5f0b14\-f849\-7945\-ad81\-bc7b6d2bb245 +.PD 0 +.P +.PD +drv_rt_version:0 +.PD 0 +.P +.PD +drv_svn:0 +.PD 0 +.P +.PD +platform id:39214663\-b1a8\-4eaa\-9024\-f2bb53ea4723 +.PD 0 +.P +.PD +oem id:a36db54f\-ea2a\-e14e\-b7c4\-b5780e51ba3d +.PP +\f[B]pfrut \-l yours.cap \-u \-T 1 \-L 4\f[R] +.SH AUTHORS +Chen Yu. diff --git a/tools/power/acpi/tools/pfrut/Makefile b/tools/power/acpi/tools/pfrut/Makefile new file mode 100644 index 000000000000..61c1a96fd433 --- /dev/null +++ b/tools/power/acpi/tools/pfrut/Makefile @@ -0,0 +1,23 @@ +# SPDX-License-Identifier: GPL-2.0+ + +include ../../Makefile.config + +TOOL = pfrut +EXTRA_INSTALL = install-man +EXTRA_UNINSTALL = uninstall-man + +CFLAGS += -Wall -O2 +CFLAGS += -DPFRUT_HEADER='"../../../../../include/uapi/linux/pfrut.h"' +LDFLAGS += -luuid + +TOOL_OBJS = \ + pfrut.o + +include ../../Makefile.rules + +install-man: $(srctree)/man/pfrut.8 + $(ECHO) " INST " pfrut.8 + $(QUIET) $(INSTALL_DATA) -D $< $(DESTDIR)$(mandir)/man8/pfrut.8 +uninstall-man: + $(ECHO) " UNINST " pfrut.8 + $(QUIET) rm -f $(DESTDIR)$(mandir)/man8/pfrut.8 diff --git a/tools/power/acpi/tools/pfrut/pfrut.c b/tools/power/acpi/tools/pfrut/pfrut.c new file mode 100644 index 000000000000..d79c335594b2 --- /dev/null +++ b/tools/power/acpi/tools/pfrut/pfrut.c @@ -0,0 +1,424 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Platform Firmware Runtime Update tool to do Management + * Mode code injection/driver update and telemetry retrieval. + * + * This tool uses the interfaces provided by pfr_update and + * pfr_telemetry drivers. These interfaces are exposed via + * /dev/pfr_update and /dev/pfr_telemetry. Write operation + * on the /dev/pfr_update is to load the EFI capsule into + * kernel space. Mmap/read operations on /dev/pfr_telemetry + * could be used to read the telemetry data to user space. + */ +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include PFRUT_HEADER + +char *capsule_name; +int action, query_cap, log_type, log_level, log_read, log_getinfo, + revid, log_revid; +int set_log_level, set_log_type, + set_revid, set_log_revid; + +char *progname; + +#define LOG_ERR 0 +#define LOG_WARN 1 +#define LOG_INFO 2 +#define LOG_VERB 4 +#define LOG_EXEC_IDX 0 +#define LOG_HISTORY_IDX 1 +#define REVID_1 1 +#define REVID_2 2 + +static int valid_log_level(int level) +{ + return level == LOG_ERR || level == LOG_WARN || + level == LOG_INFO || level == LOG_VERB; +} + +static int valid_log_type(int type) +{ + return type == LOG_EXEC_IDX || type == LOG_HISTORY_IDX; +} + +static inline int valid_log_revid(int id) +{ + return id == REVID_1 || id == REVID_2; +} + +static void help(void) +{ + fprintf(stderr, + "usage: %s [OPTIONS]\n" + " code injection:\n" + " -l, --load\n" + " -s, --stage\n" + " -a, --activate\n" + " -u, --update [stage and activate]\n" + " -q, --query\n" + " -d, --revid update\n" + " telemetry:\n" + " -G, --getloginfo\n" + " -T, --type(0:execution, 1:history)\n" + " -L, --level(0, 1, 2, 4)\n" + " -R, --read\n" + " -D, --revid log\n", + progname); +} + +char *option_string = "l:sauqd:GT:L:RD:h"; +static struct option long_options[] = { + {"load", required_argument, 0, 'l'}, + {"stage", no_argument, 0, 's'}, + {"activate", no_argument, 0, 'a'}, + {"update", no_argument, 0, 'u'}, + {"query", no_argument, 0, 'q'}, + {"getloginfo", no_argument, 0, 'G'}, + {"type", required_argument, 0, 'T'}, + {"level", required_argument, 0, 'L'}, + {"read", no_argument, 0, 'R'}, + {"setrev", required_argument, 0, 'd'}, + {"setrevlog", required_argument, 0, 'D'}, + {"help", no_argument, 0, 'h'}, + {} +}; + +static void parse_options(int argc, char **argv) +{ + int option_index = 0; + char *pathname; + int opt; + + pathname = strdup(argv[0]); + progname = basename(pathname); + + while ((opt = getopt_long_only(argc, argv, option_string, + long_options, &option_index)) != -1) { + switch (opt) { + case 'l': + capsule_name = optarg; + break; + case 's': + action = 1; + break; + case 'a': + action = 2; + break; + case 'u': + action = 3; + break; + case 'q': + query_cap = 1; + break; + case 'G': + log_getinfo = 1; + break; + case 'T': + log_type = atoi(optarg); + set_log_type = 1; + break; + case 'L': + log_level = atoi(optarg); + set_log_level = 1; + break; + case 'R': + log_read = 1; + break; + case 'd': + revid = atoi(optarg); + set_revid = 1; + break; + case 'D': + log_revid = atoi(optarg); + set_log_revid = 1; + break; + case 'h': + help(); + exit(0); + default: + break; + } + } +} + +void print_cap(struct pfru_update_cap_info *cap) +{ + char *uuid; + + uuid = malloc(37); + if (!uuid) { + perror("Can not allocate uuid buffer\n"); + exit(1); + } + + uuid_unparse(cap->code_type, uuid); + printf("code injection image type:%s\n", uuid); + printf("fw_version:%d\n", cap->fw_version); + printf("code_rt_version:%d\n", cap->code_rt_version); + + uuid_unparse(cap->drv_type, uuid); + printf("driver update image type:%s\n", uuid); + printf("drv_rt_version:%d\n", cap->drv_rt_version); + printf("drv_svn:%d\n", cap->drv_svn); + + uuid_unparse(cap->platform_id, uuid); + printf("platform id:%s\n", uuid); + uuid_unparse(cap->oem_id, uuid); + printf("oem id:%s\n", uuid); + printf("oem information length:%d\n", cap->oem_info_len); + + free(uuid); +} + +int main(int argc, char *argv[]) +{ + int fd_update, fd_update_log, fd_capsule; + struct pfrt_log_data_info data_info; + struct pfrt_log_info info; + struct pfru_update_cap_info cap; + void *addr_map_capsule; + struct stat st; + char *log_buf; + int ret = 0; + + if (getuid() != 0) { + printf("Please run the tool as root - Exiting.\n"); + return 1; + } + + parse_options(argc, argv); + + fd_update = open("/dev/acpi_pfr_update0", O_RDWR); + if (fd_update < 0) { + printf("PFRU device not supported - Quit...\n"); + return 1; + } + + fd_update_log = open("/dev/acpi_pfr_telemetry0", O_RDWR); + if (fd_update_log < 0) { + printf("PFRT device not supported - Quit...\n"); + return 1; + } + + if (query_cap) { + ret = ioctl(fd_update, PFRU_IOC_QUERY_CAP, &cap); + if (ret) + perror("Query Update Capability info failed."); + else + print_cap(&cap); + + close(fd_update); + close(fd_update_log); + + return ret; + } + + if (log_getinfo) { + ret = ioctl(fd_update_log, PFRT_LOG_IOC_GET_DATA_INFO, &data_info); + if (ret) { + perror("Get telemetry data info failed."); + close(fd_update); + close(fd_update_log); + + return 1; + } + + ret = ioctl(fd_update_log, PFRT_LOG_IOC_GET_INFO, &info); + if (ret) { + perror("Get telemetry info failed."); + close(fd_update); + close(fd_update_log); + + return 1; + } + + printf("log_level:%d\n", info.log_level); + printf("log_type:%d\n", info.log_type); + printf("log_revid:%d\n", info.log_revid); + printf("max_data_size:%d\n", data_info.max_data_size); + printf("chunk1_size:%d\n", data_info.chunk1_size); + printf("chunk2_size:%d\n", data_info.chunk2_size); + printf("rollover_cnt:%d\n", data_info.rollover_cnt); + printf("reset_cnt:%d\n", data_info.reset_cnt); + + return 0; + } + + info.log_level = -1; + info.log_type = -1; + info.log_revid = -1; + + if (set_log_level) { + if (!valid_log_level(log_level)) { + printf("Invalid log level %d\n", + log_level); + } else { + info.log_level = log_level; + } + } + + if (set_log_type) { + if (!valid_log_type(log_type)) { + printf("Invalid log type %d\n", + log_type); + } else { + info.log_type = log_type; + } + } + + if (set_log_revid) { + if (!valid_log_revid(log_revid)) { + printf("Invalid log revid %d, unchanged.\n", + log_revid); + } else { + info.log_revid = log_revid; + } + } + + ret = ioctl(fd_update_log, PFRT_LOG_IOC_SET_INFO, &info); + if (ret) { + perror("Log information set failed.(log_level, log_type, log_revid)"); + close(fd_update); + close(fd_update_log); + + return 1; + } + + if (set_revid) { + ret = ioctl(fd_update, PFRU_IOC_SET_REV, &revid); + if (ret) { + perror("pfru update revid set failed"); + close(fd_update); + close(fd_update_log); + + return 1; + } + + printf("pfru update revid set to %d\n", revid); + } + + if (capsule_name) { + fd_capsule = open(capsule_name, O_RDONLY); + if (fd_capsule < 0) { + perror("Can not open capsule file..."); + close(fd_update); + close(fd_update_log); + + return 1; + } + + if (fstat(fd_capsule, &st) < 0) { + perror("Can not fstat capsule file..."); + close(fd_capsule); + close(fd_update); + close(fd_update_log); + + return 1; + } + + addr_map_capsule = mmap(NULL, st.st_size, PROT_READ, MAP_SHARED, + fd_capsule, 0); + if (addr_map_capsule == MAP_FAILED) { + perror("Failed to mmap capsule file."); + close(fd_capsule); + close(fd_update); + close(fd_update_log); + + return 1; + } + + ret = write(fd_update, (char *)addr_map_capsule, st.st_size); + printf("Load %d bytes of capsule file into the system\n", + ret); + + if (ret == -1) { + perror("Failed to load capsule file"); + close(fd_capsule); + close(fd_update); + close(fd_update_log); + + return 1; + } + + munmap(addr_map_capsule, st.st_size); + close(fd_capsule); + printf("Load done.\n"); + } + + if (action) { + if (action == 1) { + ret = ioctl(fd_update, PFRU_IOC_STAGE, NULL); + } else if (action == 2) { + ret = ioctl(fd_update, PFRU_IOC_ACTIVATE, NULL); + } else if (action == 3) { + ret = ioctl(fd_update, PFRU_IOC_STAGE_ACTIVATE, NULL); + } else { + close(fd_update); + close(fd_update_log); + + return 1; + } + printf("Update finished, return %d\n", ret); + } + + close(fd_update); + + if (log_read) { + void *p_mmap; + int max_data_sz; + + ret = ioctl(fd_update_log, PFRT_LOG_IOC_GET_DATA_INFO, &data_info); + if (ret) { + perror("Get telemetry data info failed."); + close(fd_update_log); + + return 1; + } + + max_data_sz = data_info.max_data_size; + if (!max_data_sz) { + printf("No telemetry data available.\n"); + close(fd_update_log); + + return 1; + } + + log_buf = malloc(max_data_sz + 1); + if (!log_buf) { + perror("log_buf allocate failed."); + close(fd_update_log); + + return 1; + } + + p_mmap = mmap(NULL, max_data_sz, PROT_READ, MAP_SHARED, fd_update_log, 0); + if (p_mmap == MAP_FAILED) { + perror("mmap error."); + close(fd_update_log); + + return 1; + } + + memcpy(log_buf, p_mmap, max_data_sz); + log_buf[max_data_sz] = '\0'; + printf("%s\n", log_buf); + free(log_buf); + + munmap(p_mmap, max_data_sz); + } + + close(fd_update_log); + + return 0; +}