diff options
| author | Jakub Kicinski <kuba@kernel.org> | 2024-05-31 14:09:20 -0700 |
|---|---|---|
| committer | Jakub Kicinski <kuba@kernel.org> | 2024-05-31 14:10:28 -0700 |
| commit | e19de2064fdf6f1f2488e36cf3927c3f1d01803c (patch) | |
| tree | 3af14944616afdc409c97e012fb3d82cd1fa78ff | |
| parent | ccf23c916ca35239a924ec8649cc88b1ef25d3d9 (diff) | |
| parent | d8ec19857b095b39d114ae299713bd8ea6c1e66a (diff) | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Cross-merge networking fixes after downstream PR.
Conflicts:
drivers/net/ethernet/ti/icssg/icssg_classifier.c
abd5576b9c57 ("net: ti: icssg-prueth: Add support for ICSSG switch firmware")
56a5cf538c3f ("net: ti: icssg-prueth: Fix start counter for ft1 filter")
https://lore.kernel.org/all/20240531123822.3bb7eadf@canb.auug.org.au/
No other adjacent changes.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
533 files changed, 8067 insertions, 2711 deletions
@@ -572,7 +572,7 @@ Sarangdhar Joshi <spjoshi@codeaurora.org> Sascha Hauer <s.hauer@pengutronix.de> Sahitya Tummala <quic_stummala@quicinc.com> <stummala@codeaurora.org> Sathishkumar Muruganandam <quic_murugana@quicinc.com> <murugana@codeaurora.org> -Satya Priya <quic_c_skakit@quicinc.com> <skakit@codeaurora.org> +Satya Priya <quic_skakitap@quicinc.com> <quic_c_skakit@quicinc.com> <skakit@codeaurora.org> S.ÇaÄŸlar Onur <caglar@pardus.org.tr> Sayali Lokhande <quic_sayalil@quicinc.com> <sayalil@codeaurora.org> Sean Christopherson <seanjc@google.com> <sean.j.christopherson@intel.com> diff --git a/Documentation/devicetree/bindings/input/qcom,pm8xxx-vib.yaml b/Documentation/devicetree/bindings/input/qcom,pm8xxx-vib.yaml index c8832cd0d7da..2025d6a5423e 100644 --- a/Documentation/devicetree/bindings/input/qcom,pm8xxx-vib.yaml +++ b/Documentation/devicetree/bindings/input/qcom,pm8xxx-vib.yaml @@ -11,10 +11,18 @@ maintainers: properties: compatible: - enum: - - qcom,pm8058-vib - - qcom,pm8916-vib - - qcom,pm8921-vib + oneOf: + - enum: + - qcom,pm8058-vib + - qcom,pm8916-vib + - qcom,pm8921-vib + - qcom,pmi632-vib + - items: + - enum: + - qcom,pm7250b-vib + - qcom,pm7325b-vib + - qcom,pm7550ba-vib + - const: qcom,pmi632-vib reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.yaml b/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.yaml index f2808cb4d99d..745e57c05176 100644 --- a/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.yaml +++ b/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.yaml @@ -39,7 +39,9 @@ properties: - edt,edt-ft5406 - edt,edt-ft5506 - evervision,ev-ft5726 + - focaltech,ft5452 - focaltech,ft6236 + - focaltech,ft8719 reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/net/pse-pd/microchip,pd692x0.yaml b/Documentation/devicetree/bindings/net/pse-pd/microchip,pd692x0.yaml index 828439398fdf..fd4244fceced 100644 --- a/Documentation/devicetree/bindings/net/pse-pd/microchip,pd692x0.yaml +++ b/Documentation/devicetree/bindings/net/pse-pd/microchip,pd692x0.yaml @@ -24,6 +24,7 @@ properties: managers: type: object + additionalProperties: false description: List of the PD69208T4/PD69204T4/PD69208M PSE managers. Each manager have 4 or 8 physical ports according to the chip version. No need to @@ -47,8 +48,9 @@ properties: - "#size-cells" patternProperties: - "^manager@0[0-9a-b]$": + "^manager@[0-9a-b]$": type: object + additionalProperties: false description: PD69208T4/PD69204T4/PD69208M PSE manager exposing 4 or 8 physical ports. @@ -69,9 +71,14 @@ properties: patternProperties: '^port@[0-7]$': type: object + additionalProperties: false + + properties: + reg: + maxItems: 1 + required: - reg - additionalProperties: false required: - reg diff --git a/Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml b/Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml index 4147adb11e10..6992d56832bf 100644 --- a/Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml +++ b/Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml @@ -29,13 +29,31 @@ properties: of the ports conversion matrix that establishes relationship between the logical ports and the physical channels. type: object + additionalProperties: false + + properties: + "#address-cells": + const: 1 + + "#size-cells": + const: 0 patternProperties: '^channel@[0-7]$': type: object + additionalProperties: false + + properties: + reg: + maxItems: 1 + required: - reg + required: + - "#address-cells" + - "#size-cells" + unevaluatedProperties: false required: diff --git a/Documentation/devicetree/bindings/rtc/alphascale,asm9260-rtc.txt b/Documentation/devicetree/bindings/rtc/alphascale,asm9260-rtc.txt deleted file mode 100644 index 76ebca568db9..000000000000 --- a/Documentation/devicetree/bindings/rtc/alphascale,asm9260-rtc.txt +++ /dev/null @@ -1,19 +0,0 @@ -* Alphascale asm9260 SoC Real Time Clock - -Required properties: -- compatible: Should be "alphascale,asm9260-rtc" -- reg: Physical base address of the controller and length - of memory mapped region. -- interrupts: IRQ line for the RTC. -- clocks: Reference to the clock entry. -- clock-names: should contain: - * "ahb" for the SoC RTC clock - -Example: -rtc0: rtc@800a0000 { - compatible = "alphascale,asm9260-rtc"; - reg = <0x800a0000 0x100>; - clocks = <&acc CLKID_AHB_RTC>; - clock-names = "ahb"; - interrupts = <2>; -}; diff --git a/Documentation/devicetree/bindings/rtc/alphascale,asm9260-rtc.yaml b/Documentation/devicetree/bindings/rtc/alphascale,asm9260-rtc.yaml new file mode 100644 index 000000000000..f955a7f638ad --- /dev/null +++ b/Documentation/devicetree/bindings/rtc/alphascale,asm9260-rtc.yaml @@ -0,0 +1,50 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/rtc/alphascale,asm9260-rtc.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Alphascale asm9260 SoC Real Time Clock + +maintainers: + - Javier Carrasco <javier.carrasco.cruz@gmail.com> + +allOf: + - $ref: rtc.yaml# + +properties: + compatible: + const: alphascale,asm9260-rtc + + reg: + maxItems: 1 + + clocks: + maxItems: 1 + + clock-names: + const: ahb + + interrupts: + maxItems: 1 + +required: + - compatible + - reg + - clocks + - clock-names + - interrupts + +unevaluatedProperties: false + +examples: + - | + #include <dt-bindings/clock/alphascale,asm9260.h> + + rtc@800a0000 { + compatible = "alphascale,asm9260-rtc"; + reg = <0x800a0000 0x100>; + clocks = <&acc CLKID_AHB_RTC>; + clock-names = "ahb"; + interrupts = <2>; + }; diff --git a/Documentation/devicetree/bindings/rtc/armada-380-rtc.txt b/Documentation/devicetree/bindings/rtc/armada-380-rtc.txt deleted file mode 100644 index c3c9a1226f9a..000000000000 --- a/Documentation/devicetree/bindings/rtc/armada-380-rtc.txt +++ /dev/null @@ -1,24 +0,0 @@ -* Real Time Clock of the Armada 38x/7K/8K SoCs - -RTC controller for the Armada 38x, 7K and 8K SoCs - -Required properties: -- compatible : Should be one of the following: - "marvell,armada-380-rtc" for Armada 38x SoC - "marvell,armada-8k-rtc" for Aramda 7K/8K SoCs -- reg: a list of base address and size pairs, one for each entry in - reg-names -- reg names: should contain: - * "rtc" for the RTC registers - * "rtc-soc" for the SoC related registers and among them the one - related to the interrupt. -- interrupts: IRQ line for the RTC. - -Example: - -rtc@a3800 { - compatible = "marvell,armada-380-rtc"; - reg = <0xa3800 0x20>, <0x184a0 0x0c>; - reg-names = "rtc", "rtc-soc"; - interrupts = <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH>; -}; diff --git a/Documentation/devicetree/bindings/rtc/digicolor-rtc.txt b/Documentation/devicetree/bindings/rtc/digicolor-rtc.txt deleted file mode 100644 index d464986012cd..000000000000 --- a/Documentation/devicetree/bindings/rtc/digicolor-rtc.txt +++ /dev/null @@ -1,17 +0,0 @@ -Conexant Digicolor Real Time Clock controller - -This binding currently supports the CX92755 SoC. - -Required properties: -- compatible: should be "cnxt,cx92755-rtc" -- reg: physical base address of the controller and length of memory mapped - region. -- interrupts: rtc alarm interrupt - -Example: - - rtc@f0000c30 { - compatible = "cnxt,cx92755-rtc"; - reg = <0xf0000c30 0x18>; - interrupts = <25>; - }; diff --git a/Documentation/devicetree/bindings/rtc/fsl,stmp3xxx-rtc.yaml b/Documentation/devicetree/bindings/rtc/fsl,stmp3xxx-rtc.yaml new file mode 100644 index 000000000000..534de4196a4f --- /dev/null +++ b/Documentation/devicetree/bindings/rtc/fsl,stmp3xxx-rtc.yaml @@ -0,0 +1,51 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/rtc/fsl,stmp3xxx-rtc.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: STMP3xxx/i.MX28 Time Clock Controller + +maintainers: + - Javier Carrasco <javier.carrasco.cruz@gmail.com> + +allOf: + - $ref: rtc.yaml# + +properties: + compatible: + oneOf: + - items: + - enum: + - fsl,imx28-rtc + - fsl,imx23-rtc + - const: fsl,stmp3xxx-rtc + - const: fsl,stmp3xxx-rtc + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + stmp,crystal-freq: + description: + Override crystal frequency as determined from fuse bits. + Use <0> for "no crystal". + $ref: /schemas/types.yaml#/definitions/uint32 + enum: [0, 32000, 32768] + +required: + - compatible + - reg + - interrupts + +unevaluatedProperties: false + +examples: + - | + rtc@80056000 { + compatible = "fsl,imx28-rtc", "fsl,stmp3xxx-rtc"; + reg = <0x80056000 2000>; + interrupts = <29>; + }; diff --git a/Documentation/devicetree/bindings/rtc/google,goldfish-rtc.txt b/Documentation/devicetree/bindings/rtc/google,goldfish-rtc.txt deleted file mode 100644 index 634312dd95ca..000000000000 --- a/Documentation/devicetree/bindings/rtc/google,goldfish-rtc.txt +++ /dev/null @@ -1,17 +0,0 @@ -Android Goldfish RTC - -Android Goldfish RTC device used by Android emulator. - -Required properties: - -- compatible : should contain "google,goldfish-rtc" -- reg : <registers mapping> -- interrupts : <interrupt mapping> - -Example: - - goldfish_timer@9020000 { - compatible = "google,goldfish-rtc"; - reg = <0x9020000 0x1000>; - interrupts = <0x3>; - }; diff --git a/Documentation/devicetree/bindings/rtc/lpc32xx-rtc.txt b/Documentation/devicetree/bindings/rtc/lpc32xx-rtc.txt deleted file mode 100644 index a87a1e9bc060..000000000000 --- a/Documentation/devicetree/bindings/rtc/lpc32xx-rtc.txt +++ /dev/null @@ -1,15 +0,0 @@ -* NXP LPC32xx SoC Real Time Clock controller - -Required properties: -- compatible: must be "nxp,lpc3220-rtc" -- reg: physical base address of the controller and length of memory mapped - region. -- interrupts: The RTC interrupt - -Example: - - rtc@40024000 { - compatible = "nxp,lpc3220-rtc"; - reg = <0x40024000 0x1000>; - interrupts = <52 0>; - }; diff --git a/Documentation/devicetree/bindings/rtc/marvell,armada-380-rtc.yaml b/Documentation/devicetree/bindings/rtc/marvell,armada-380-rtc.yaml new file mode 100644 index 000000000000..adf3ba0cd09f --- /dev/null +++ b/Documentation/devicetree/bindings/rtc/marvell,armada-380-rtc.yaml @@ -0,0 +1,51 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/rtc/marvell,armada-380-rtc.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: RTC controller for the Armada 38x, 7K and 8K SoCs + +maintainers: + - Javier Carrasco <javier.carrasco.cruz@gmail.com> + +allOf: + - $ref: rtc.yaml# + +properties: + compatible: + enum: + - marvell,armada-380-rtc + - marvell,armada-8k-rtc + + reg: + items: + - description: RTC base address size + - description: Base address and size of SoC related registers + + reg-names: + items: + - const: rtc + - const: rtc-soc + + interrupts: + maxItems: 1 + +required: + - compatible + - reg + - reg-names + - interrupts + +unevaluatedProperties: false + +examples: + - | + #include <dt-bindings/interrupt-controller/arm-gic.h> + + rtc@a3800 { + compatible = "marvell,armada-380-rtc"; + reg = <0xa3800 0x20>, <0x184a0 0x0c>; + reg-names = "rtc", "rtc-soc"; + interrupts = <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH>; + }; diff --git a/Documentation/devicetree/bindings/rtc/marvell,pxa-rtc.yaml b/Documentation/devicetree/bindings/rtc/marvell,pxa-rtc.yaml new file mode 100644 index 000000000000..43d68681a1bf --- /dev/null +++ b/Documentation/devicetree/bindings/rtc/marvell,pxa-rtc.yaml @@ -0,0 +1,40 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/rtc/marvell,pxa-rtc.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: PXA Real Time Clock + +maintainers: + - Javier Carrasco <javier.carrasco.cruz@gmail.com> + +allOf: + - $ref: rtc.yaml# + +properties: + compatible: + const: marvell,pxa-rtc + + reg: + maxItems: 1 + + interrupts: + items: + - description: 1 Hz + - description: Alarm + +required: + - compatible + - reg + - interrupts + +unevaluatedProperties: false + +examples: + - | + rtc@40900000 { + compatible = "marvell,pxa-rtc"; + reg = <0x40900000 0x3c>; + interrupts = <30>, <31>; + }; diff --git a/Documentation/devicetree/bindings/rtc/maxim,ds1742.txt b/Documentation/devicetree/bindings/rtc/maxim,ds1742.txt deleted file mode 100644 index d0f937c355b5..000000000000 --- a/Documentation/devicetree/bindings/rtc/maxim,ds1742.txt +++ /dev/null @@ -1,12 +0,0 @@ -* Maxim (Dallas) DS1742/DS1743 Real Time Clock - -Required properties: -- compatible: Should contain "maxim,ds1742". -- reg: Physical base address of the RTC and length of memory - mapped region. - -Example: - rtc: rtc@10000000 { - compatible = "maxim,ds1742"; - reg = <0x10000000 0x800>; - }; diff --git a/Documentation/devicetree/bindings/rtc/nxp,lpc1788-rtc.txt b/Documentation/devicetree/bindings/rtc/nxp,lpc1788-rtc.txt deleted file mode 100644 index 3c97bd180592..000000000000 --- a/Documentation/devicetree/bindings/rtc/nxp,lpc1788-rtc.txt +++ /dev/null @@ -1,21 +0,0 @@ -NXP LPC1788 real-time clock - -The LPC1788 RTC provides calendar and clock functionality -together with periodic tick and alarm interrupt support. - -Required properties: -- compatible : must contain "nxp,lpc1788-rtc" -- reg : Specifies base physical address and size of the registers. -- interrupts : A single interrupt specifier. -- clocks : Must contain clock specifiers for rtc and register clock -- clock-names : Must contain "rtc" and "reg" - See ../clocks/clock-bindings.txt for details. - -Example: -rtc: rtc@40046000 { - compatible = "nxp,lpc1788-rtc"; - reg = <0x40046000 0x1000>; - interrupts = <47>; - clocks = <&creg_clk 0>, <&ccu1 CLK_CPU_BUS>; - clock-names = "rtc", "reg"; -}; diff --git a/Documentation/devicetree/bindings/rtc/nxp,lpc1788-rtc.yaml b/Documentation/devicetree/bindings/rtc/nxp,lpc1788-rtc.yaml new file mode 100644 index 000000000000..e88b847a1cc5 --- /dev/null +++ b/Documentation/devicetree/bindings/rtc/nxp,lpc1788-rtc.yaml @@ -0,0 +1,58 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/rtc/nxp,lpc1788-rtc.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: NXP LPC1788 real-time clock + +description: + The LPC1788 RTC provides calendar and clock functionality + together with periodic tick and alarm interrupt support. + +maintainers: + - Javier Carrasco <javier.carrasco.cruz@gmail.com> + +allOf: + - $ref: rtc.yaml# + +properties: + compatible: + const: nxp,lpc1788-rtc + + reg: + maxItems: 1 + + clocks: + items: + - description: RTC clock + - description: Register clock + + clock-names: + items: + - const: rtc + - const: reg + + interrupts: + maxItems: 1 + +required: + - compatible + - reg + - clocks + - clock-names + - interrupts + +unevaluatedProperties: false + +examples: + - | + #include <dt-bindings/clock/lpc18xx-ccu.h> + + rtc@40046000 { + compatible = "nxp,lpc1788-rtc"; + reg = <0x40046000 0x1000>; + clocks = <&creg_clk 0>, <&ccu1 CLK_CPU_BUS>; + clock-names = "rtc", "reg"; + interrupts = <47>; + }; diff --git a/Documentation/devicetree/bindings/rtc/orion-rtc.txt b/Documentation/devicetree/bindings/rtc/orion-rtc.txt deleted file mode 100644 index 3bf63ffa5160..000000000000 --- a/Documentation/devicetree/bindings/rtc/orion-rtc.txt +++ /dev/null @@ -1,18 +0,0 @@ -* Mvebu Real Time Clock - -RTC controller for the Kirkwood, the Dove, the Armada 370 and the -Armada XP SoCs - -Required properties: -- compatible : Should be "marvell,orion-rtc" -- reg: physical base address of the controller and length of memory mapped - region. -- interrupts: IRQ line for the RTC. - -Example: - -rtc@10300 { - compatible = "marvell,orion-rtc"; - reg = <0xd0010300 0x20>; - interrupts = <50>; -}; diff --git a/Documentation/devicetree/bindings/rtc/pxa-rtc.txt b/Documentation/devicetree/bindings/rtc/pxa-rtc.txt deleted file mode 100644 index 8c6672a1b7d7..000000000000 --- a/Documentation/devicetree/bindings/rtc/pxa-rtc.txt +++ /dev/null @@ -1,14 +0,0 @@ -* PXA RTC - -PXA specific RTC driver. - -Required properties: -- compatible : Should be "marvell,pxa-rtc" - -Examples: - -rtc@40900000 { - compatible = "marvell,pxa-rtc"; - reg = <0x40900000 0x3c>; - interrupts = <30 31>; -}; diff --git a/Documentation/devicetree/bindings/rtc/rtc-aspeed.txt b/Documentation/devicetree/bindings/rtc/rtc-aspeed.txt deleted file mode 100644 index 2e956b3dc276..000000000000 --- a/Documentation/devicetree/bindings/rtc/rtc-aspeed.txt +++ /dev/null @@ -1,22 +0,0 @@ -ASPEED BMC RTC -============== - -Required properties: - - compatible: should be one of the following - * aspeed,ast2400-rtc for the ast2400 - * aspeed,ast2500-rtc for the ast2500 - * aspeed,ast2600-rtc for the ast2600 - - - reg: physical base address of the controller and length of memory mapped - region - - - interrupts: The interrupt number - -Example: - - rtc@1e781000 { - compatible = "aspeed,ast2400-rtc"; - reg = <0x1e781000 0x18>; - interrupts = <22>; - status = "disabled"; - }; diff --git a/Documentation/devicetree/bindings/rtc/spear-rtc.txt b/Documentation/devicetree/bindings/rtc/spear-rtc.txt deleted file mode 100644 index fecf8e4ad4b4..000000000000 --- a/Documentation/devicetree/bindings/rtc/spear-rtc.txt +++ /dev/null @@ -1,15 +0,0 @@ -* SPEAr RTC - -Required properties: -- compatible : "st,spear600-rtc" -- reg : Address range of the rtc registers -- interrupt: Should contain the rtc interrupt number - -Example: - - rtc@fc000000 { - compatible = "st,spear600-rtc"; - reg = <0xfc000000 0x1000>; - interrupt-parent = <&vic1>; - interrupts = <12>; - }; diff --git a/Documentation/devicetree/bindings/rtc/stmp3xxx-rtc.txt b/Documentation/devicetree/bindings/rtc/stmp3xxx-rtc.txt deleted file mode 100644 index fa6a94226669..000000000000 --- a/Documentation/devicetree/bindings/rtc/stmp3xxx-rtc.txt +++ /dev/null @@ -1,21 +0,0 @@ -* STMP3xxx/i.MX28 Time Clock controller - -Required properties: -- compatible: should be one of the following. - * "fsl,stmp3xxx-rtc" -- reg: physical base address of the controller and length of memory mapped - region. -- interrupts: rtc alarm interrupt - -Optional properties: -- stmp,crystal-freq: override crystal frequency as determined from fuse bits. - Only <32000> and <32768> are possible for the hardware. Use <0> for - "no crystal". - -Example: - -rtc@80056000 { - compatible = "fsl,imx28-rtc", "fsl,stmp3xxx-rtc"; - reg = <0x80056000 2000>; - interrupts = <29>; -}; diff --git a/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml b/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml index c9e3c5262c21..fffd759c603f 100644 --- a/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml +++ b/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml @@ -24,6 +24,14 @@ properties: - abracon,abb5zes3 # AB-RTCMC-32.768kHz-EOZ9: Real Time Clock/Calendar Module with I2C Interface - abracon,abeoz9 + # ASPEED BMC ast2400 Real-time Clock + - aspeed,ast2400-rtc + # ASPEED BMC ast2500 Real-time Clock + - aspeed,ast2500-rtc + # ASPEED BMC ast2600 Real-time Clock + - aspeed,ast2600-rtc + # Conexant Digicolor Real Time Clock Controller + - cnxt,cx92755-rtc # I2C, 32-Bit Binary Counter Watchdog RTC with Trickle Charger and Reset Input/Output - dallas,ds1374 # Dallas DS1672 Real-time Clock @@ -38,19 +46,28 @@ properties: - epson,rx8025 - epson,rx8035 # I2C-BUS INTERFACE REAL TIME CLOCK MODULE with Battery Backed RAM + - epson,rx8111 - epson,rx8571 # I2C-BUS INTERFACE REAL TIME CLOCK MODULE - epson,rx8581 + # Android Goldfish Real-time Clock + - google,goldfish-rtc # Intersil ISL1208 Low Power RTC with Battery Backed SRAM - isil,isl1208 # Intersil ISL1218 Low Power RTC with Battery Backed SRAM - isil,isl1218 + # Mvebu Real-time Clock + - marvell,orion-rtc + # Maxim DS1742/DS1743 Real-time Clock + - maxim,ds1742 # SPI-BUS INTERFACE REAL TIME CLOCK MODULE - maxim,mcp795 # Real Time Clock Module with I2C-Bus - microcrystal,rv3029 # Real Time Clock - microcrystal,rv8523 + # NXP LPC32xx SoC Real-time Clock + - nxp,lpc3220-rtc # Real-time Clock Module - pericom,pt7c4338 # I2C bus SERIAL INTERFACE REAL-TIME CLOCK IC @@ -67,6 +84,10 @@ properties: - ricoh,rv5c387a # 2-wire CMOS real-time clock - sii,s35390a + # ST SPEAr Real-time Clock + - st,spear600-rtc + # VIA/Wondermedia VT8500 Real-time Clock + - via,vt8500-rtc # I2C bus SERIAL INTERFACE REAL-TIME CLOCK IC - whwave,sd3078 # Xircom X1205 I2C RTC diff --git a/Documentation/devicetree/bindings/rtc/via,vt8500-rtc.txt b/Documentation/devicetree/bindings/rtc/via,vt8500-rtc.txt deleted file mode 100644 index 3c0484c49582..000000000000 --- a/Documentation/devicetree/bindings/rtc/via,vt8500-rtc.txt +++ /dev/null @@ -1,15 +0,0 @@ -VIA/Wondermedia VT8500 Realtime Clock Controller ------------------------------------------------------ - -Required properties: -- compatible : "via,vt8500-rtc" -- reg : Should contain 1 register ranges(address and length) -- interrupts : alarm interrupt - -Example: - - rtc@d8100000 { - compatible = "via,vt8500-rtc"; - reg = <0xd8100000 0x10000>; - interrupts = <48>; - }; diff --git a/Documentation/devicetree/bindings/sound/st,stm32-sai.yaml b/Documentation/devicetree/bindings/sound/st,stm32-sai.yaml index b46a4778807d..68f97b462598 100644 --- a/Documentation/devicetree/bindings/sound/st,stm32-sai.yaml +++ b/Documentation/devicetree/bindings/sound/st,stm32-sai.yaml @@ -72,7 +72,7 @@ patternProperties: properties: compatible: description: Compatible for SAI sub-block A or B. - pattern: "st,stm32-sai-sub-[ab]" + pattern: "^st,stm32-sai-sub-[ab]$" "#sound-dai-cells": const: 0 diff --git a/Documentation/filesystems/ceph.rst b/Documentation/filesystems/ceph.rst index 085f309ece60..6d2276a87a5a 100644 --- a/Documentation/filesystems/ceph.rst +++ b/Documentation/filesystems/ceph.rst @@ -67,12 +67,15 @@ Snapshot names have two limitations: more than 255 characters, and `<node-id>` takes 13 characters, the long snapshot names can take as much as 255 - 1 - 1 - 13 = 240. -Ceph also provides some recursive accounting on directories for nested -files and bytes. That is, a 'getfattr -d foo' on any directory in the -system will reveal the total number of nested regular files and -subdirectories, and a summation of all nested file sizes. This makes -the identification of large disk space consumers relatively quick, as -no 'du' or similar recursive scan of the file system is required. +Ceph also provides some recursive accounting on directories for nested files +and bytes. You can run the commands:: + + getfattr -n ceph.dir.rfiles /some/dir + getfattr -n ceph.dir.rbytes /some/dir + +to get the total number of nested files and their combined size, respectively. +This makes the identification of large disk space consumers relatively quick, +as no 'du' or similar recursive scan of the file system is required. Finally, Ceph also allows quotas to be set on any directory in the system. The quota can restrict the number of bytes or the number of files stored diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst index 4d97258a7954..7c3a565ffbef 100644 --- a/Documentation/filesystems/proc.rst +++ b/Documentation/filesystems/proc.rst @@ -961,13 +961,14 @@ Provides information about memory allocations at all locations in the code base. Each allocation in the code is identified by its source file, line number, module (if originates from a loadable module) and the function calling the allocation. The number of bytes allocated and number of calls at each -location are reported. +location are reported. The first line indicates the version of the file, the +second line is the header listing fields in the file. Example output. :: - > sort -rn /proc/allocinfo + > tail -n +3 /proc/allocinfo | sort -rn 127664128 31168 mm/page_ext.c:270 func:alloc_page_ext 56373248 4737 mm/slub.c:2259 func:alloc_slab_page 14880768 3633 mm/readahead.c:247 func:page_cache_ra_unbounded diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index 11a32373365a..959755be4d7f 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -350,6 +350,10 @@ attribute-sets: buffer space, host descriptors etc. type: uint - + name: rx-csum-complete + doc: Number of packets that were marked as CHECKSUM_COMPLETE. + type: uint + - name: rx-csum-unnecessary doc: Number of packets that were marked as CHECKSUM_UNNECESSARY. type: uint diff --git a/Documentation/process/maintainer-netdev.rst b/Documentation/process/maintainer-netdev.rst index fd96e4a3cef9..5e1fcfad1c4c 100644 --- a/Documentation/process/maintainer-netdev.rst +++ b/Documentation/process/maintainer-netdev.rst @@ -227,7 +227,7 @@ preferably including links to previous postings, for example:: The amount of mooing will depend on packet rate so should match the diurnal cycle quite well. - Signed-of-by: Joe Defarmer <joe@barn.org> + Signed-off-by: Joe Defarmer <joe@barn.org> --- v3: - add a note about time-of-day mooing fluctuation to the commit message diff --git a/Documentation/sound/hd-audio/notes.rst b/Documentation/sound/hd-audio/notes.rst index a9e35b1f87bd..ef6a4513cce7 100644 --- a/Documentation/sound/hd-audio/notes.rst +++ b/Documentation/sound/hd-audio/notes.rst @@ -15,7 +15,7 @@ problem is broken BIOS, and the rest is the driver implementation. This document explains the brief trouble-shooting and debugging methods for the HD-audio hardware. -The HD-audio component consists of two parts: the controller chip and +The HD-audio component consists of two parts: the controller chip and the codec chips on the HD-audio bus. Linux provides a single driver for all controllers, snd-hda-intel. Although the driver name contains a word of a well-known hardware vendor, it's not specific to it but for @@ -81,7 +81,7 @@ the wake-up timing. It wakes up a few samples before actually processing the data on the buffer. This caused a lot of problems, for example, with ALSA dmix or JACK. Since 2.6.27 kernel, the driver puts an artificial delay to the wake up timing. This delay is controlled -via ``bdl_pos_adj`` option. +via ``bdl_pos_adj`` option. When ``bdl_pos_adj`` is a negative value (as default), it's assigned to an appropriate value depending on the controller chip. For Intel @@ -144,7 +144,7 @@ see a regression wrt the sound quality (stuttering, etc) or a lock-up in the recent kernel, try to pass ``enable_msi=0`` option to disable MSI. If it works, you can add the known bad device to the blacklist defined in hda_intel.c. In such a case, please report and give the -patch back to the upstream developer. +patch back to the upstream developer. HD-Audio Codec @@ -375,7 +375,7 @@ HD-Audio Reconfiguration ------------------------ This is an experimental feature to allow you re-configure the HD-audio codec dynamically without reloading the driver. The following sysfs -files are available under each codec-hwdep device directory (e.g. +files are available under each codec-hwdep device directory (e.g. /sys/class/sound/hwC0D0): vendor_id @@ -433,7 +433,7 @@ re-configure based on that state, run like below: :: # echo 0x14 0x9993013f > /sys/class/sound/hwC0D0/user_pin_configs - # echo 1 > /sys/class/sound/hwC0D0/reconfig + # echo 1 > /sys/class/sound/hwC0D0/reconfig Hint Strings @@ -494,7 +494,7 @@ indep_hp (bool) mixer control, if available add_stereo_mix_input (bool) add the stereo mix (analog-loopback mix) to the input mux if - available + available add_jack_modes (bool) add "xxx Jack Mode" enum controls to each I/O jack for allowing to change the headphone amp and mic bias VREF capabilities @@ -504,7 +504,7 @@ power_save_node (bool) stream states power_down_unused (bool) power down the unused widgets, a subset of power_save_node, and - will be dropped in future + will be dropped in future add_hp_mic (bool) add the headphone to capture source if possible hp_mic_detect (bool) @@ -603,7 +603,7 @@ present. The patch module option is specific to each card instance, and you need to give one file name for each instance, separated by commas. -For example, if you have two cards, one for an on-board analog and one +For example, if you have two cards, one for an on-board analog and one for an HDMI video board, you may pass patch option like below: :: diff --git a/Documentation/userspace-api/index.rst b/Documentation/userspace-api/index.rst index afecfe3cc4a8..5926115ec0ed 100644 --- a/Documentation/userspace-api/index.rst +++ b/Documentation/userspace-api/index.rst @@ -20,6 +20,7 @@ System calls futex2 ebpf/index ioctl/index + mseal Security-related interfaces =========================== diff --git a/Documentation/userspace-api/mseal.rst b/Documentation/userspace-api/mseal.rst new file mode 100644 index 000000000000..4132eec995a3 --- /dev/null +++ b/Documentation/userspace-api/mseal.rst @@ -0,0 +1,199 @@ +.. SPDX-License-Identifier: GPL-2.0 + +===================== +Introduction of mseal +===================== + +:Author: Jeff Xu <jeffxu@chromium.org> + +Modern CPUs support memory permissions such as RW and NX bits. The memory +permission feature improves security stance on memory corruption bugs, i.e. +the attacker can’t just write to arbitrary memory and point the code to it, +the memory has to be marked with X bit, or else an exception will happen. + +Memory sealing additionally protects the mapping itself against +modifications. This is useful to mitigate memory corruption issues where a +corrupted pointer is passed to a memory management system. For example, +such an attacker primitive can break control-flow integrity guarantees +since read-only memory that is supposed to be trusted can become writable +or .text pages can get remapped. Memory sealing can automatically be +applied by the runtime loader to seal .text and .rodata pages and +applications can additionally seal security critical data at runtime. + +A similar feature already exists in the XNU kernel with the +VM_FLAGS_PERMANENT flag [1] and on OpenBSD with the mimmutable syscall [2]. + +User API +======== +mseal() +----------- +The mseal() syscall has the following signature: + +``int mseal(void addr, size_t len, unsigned long flags)`` + +**addr/len**: virtual memory address range. + +The address range set by ``addr``/``len`` must meet: + - The start address must be in an allocated VMA. + - The start address must be page aligned. + - The end address (``addr`` + ``len``) must be in an allocated VMA. + - no gap (unallocated memory) between start and end address. + +The ``len`` will be paged aligned implicitly by the kernel. + +**flags**: reserved for future use. + +**return values**: + +- ``0``: Success. + +- ``-EINVAL``: + - Invalid input ``flags``. + - The start address (``addr``) is not page aligned. + - Address range (``addr`` + ``len``) overflow. + +- ``-ENOMEM``: + - The start address (``addr``) is not allocated. + - The end address (``addr`` + ``len``) is not allocated. + - A gap (unallocated memory) between start and end address. + +- ``-EPERM``: + - sealing is supported only on 64-bit CPUs, 32-bit is not supported. + +- For above error cases, users can expect the given memory range is + unmodified, i.e. no partial update. + +- There might be other internal errors/cases not listed here, e.g. + error during merging/splitting VMAs, or the process reaching the max + number of supported VMAs. In those cases, partial updates to the given + memory range could happen. However, those cases should be rare. + +**Blocked operations after sealing**: + Unmapping, moving to another location, and shrinking the size, + via munmap() and mremap(), can leave an empty space, therefore + can be replaced with a VMA with a new set of attributes. + + Moving or expanding a different VMA into the current location, + via mremap(). + + Modifying a VMA via mmap(MAP_FIXED). + + Size expansion, via mremap(), does not appear to pose any + specific risks to sealed VMAs. It is included anyway because + the use case is unclear. In any case, users can rely on + merging to expand a sealed VMA. + + mprotect() and pkey_mprotect(). + + Some destructive madvice() behaviors (e.g. MADV_DONTNEED) + for anonymous memory, when users don't have write permission to the + memory. Those behaviors can alter region contents by discarding pages, + effectively a memset(0) for anonymous memory. + + Kernel will return -EPERM for blocked operations. + + For blocked operations, one can expect the given address is unmodified, + i.e. no partial update. Note, this is different from existing mm + system call behaviors, where partial updates are made till an error is + found and returned to userspace. To give an example: + + Assume following code sequence: + + - ptr = mmap(null, 8192, PROT_NONE); + - munmap(ptr + 4096, 4096); + - ret1 = mprotect(ptr, 8192, PROT_READ); + - mseal(ptr, 4096); + - ret2 = mprotect(ptr, 8192, PROT_NONE); + + ret1 will be -ENOMEM, the page from ptr is updated to PROT_READ. + + ret2 will be -EPERM, the page remains to be PROT_READ. + +**Note**: + +- mseal() only works on 64-bit CPUs, not 32-bit CPU. + +- users can call mseal() multiple times, mseal() on an already sealed memory + is a no-action (not error). + +- munseal() is not supported. + +Use cases: +========== +- glibc: + The dynamic linker, during loading ELF executables, can apply sealing to + non-writable memory segments. + +- Chrome browser: protect some security sensitive data-structures. + +Notes on which memory to seal: +============================== + +It might be important to note that sealing changes the lifetime of a mapping, +i.e. the sealed mapping won’t be unmapped till the process terminates or the +exec system call is invoked. Applications can apply sealing to any virtual +memory region from userspace, but it is crucial to thoroughly analyze the +mapping's lifetime prior to apply the sealing. + +For example: + +- aio/shm + + aio/shm can call mmap()/munmap() on behalf of userspace, e.g. ksys_shmdt() in + shm.c. The lifetime of those mapping are not tied to the lifetime of the + process. If those memories are sealed from userspace, then munmap() will fail, + causing leaks in VMA address space during the lifetime of the process. + +- Brk (heap) + + Currently, userspace applications can seal parts of the heap by calling + malloc() and mseal(). + let's assume following calls from user space: + + - ptr = malloc(size); + - mprotect(ptr, size, RO); + - mseal(ptr, size); + - free(ptr); + + Technically, before mseal() is added, the user can change the protection of + the heap by calling mprotect(RO). As long as the user changes the protection + back to RW before free(), the memory range can be reused. + + Adding mseal() into the picture, however, the heap is then sealed partially, + the user can still free it, but the memory remains to be RO. If the address + is re-used by the heap manager for another malloc, the process might crash + soon after. Therefore, it is important not to apply sealing to any memory + that might get recycled. + + Furthermore, even if the application never calls the free() for the ptr, + the heap manager may invoke the brk system call to shrink the size of the + heap. In the kernel, the brk-shrink will call munmap(). Consequently, + depending on the location of the ptr, the outcome of brk-shrink is + nondeterministic. + + +Additional notes: +================= +As Jann Horn pointed out in [3], there are still a few ways to write +to RO memory, which is, in a way, by design. Those cases are not covered +by mseal(). If applications want to block such cases, sandbox tools (such as +seccomp, LSM, etc) might be considered. + +Those cases are: + +- Write to read-only memory through /proc/self/mem interface. +- Write to read-only memory through ptrace (such as PTRACE_POKETEXT). +- userfaultfd. + +The idea that inspired this patch comes from Stephen Röttger’s work in V8 +CFI [4]. Chrome browser in ChromeOS will be the first user of this API. + +Reference: +========== +[1] https://github.com/apple-oss-distributions/xnu/blob/1031c584a5e37aff177559b9f69dbd3c8c3fd30a/osfmk/mach/vm_statistics.h#L274 + +[2] https://man.openbsd.org/mimmutable.2 + +[3] https://lore.kernel.org/lkml/CAG48ez3ShUYey+ZAFsU2i1RpQn0a5eOs2hzQ426FkcgnfUGLvA@mail.gmail.com + +[4] https://docs.google.com/document/d/1O2jwK4dxI3nRcOJuPYkonhTkNQfbmwdvxQMyXgeaRHo/edit#heading=h.bvaojj9fu6hc diff --git a/MAINTAINERS b/MAINTAINERS index 27367ad339ea..ba231d2f3a4e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1500,7 +1500,6 @@ F: drivers/irqchip/irq-goldfish-pic.c ANDROID GOLDFISH RTC DRIVER M: Jiaxun Yang <jiaxun.yang@flygoat.com> S: Supported -F: Documentation/devicetree/bindings/rtc/google,goldfish-rtc.txt F: drivers/rtc/rtc-goldfish.c AOA (Apple Onboard Audio) ALSA DRIVER @@ -3855,6 +3854,7 @@ BPF JIT for ARM64 M: Daniel Borkmann <daniel@iogearbox.net> M: Alexei Starovoitov <ast@kernel.org> M: Puranjay Mohan <puranjay@kernel.org> +R: Xu Kuohai <xukuohai@huaweicloud.com> L: bpf@vger.kernel.org S: Supported F: arch/arm64/net/ @@ -21317,7 +21317,7 @@ F: arch/riscv/boot/dts/starfive/ STARFIVE DWMAC GLUE LAYER M: Emil Renner Berthing <kernel@esmil.dk> -M: Samin Guo <samin.guo@starfivetech.com> +M: Minda Chen <minda.chen@starfivetech.com> S: Maintained F: Documentation/devicetree/bindings/net/starfive,jh7110-dwmac.yaml F: drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c @@ -1,9 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 -PATCHLEVEL = 9 +PATCHLEVEL = 10 SUBLEVEL = 0 -EXTRAVERSION = -NAME = Hurr durr I'ma ninja sloth +EXTRAVERSION = -rc1 +NAME = Baby Opossum Posse # *DOCUMENTATION* # To see a list of typical targets execute "make help" diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl index 26cce7e7f70b..74720667fe09 100644 --- a/arch/alpha/kernel/syscalls/syscall.tbl +++ b/arch/alpha/kernel/syscalls/syscall.tbl @@ -501,3 +501,4 @@ 569 common lsm_get_self_attr sys_lsm_get_self_attr 570 common lsm_set_self_attr sys_lsm_set_self_attr 571 common lsm_list_modules sys_lsm_list_modules +572 common mseal sys_mseal diff --git a/arch/arc/net/bpf_jit.h b/arch/arc/net/bpf_jit.h index ec44873c42d1..495f3023e4c1 100644 --- a/arch/arc/net/bpf_jit.h +++ b/arch/arc/net/bpf_jit.h @@ -39,7 +39,7 @@ /************** Functions that the back-end must provide **************/ /* Extension for 32-bit operations. */ -inline u8 zext(u8 *buf, u8 rd); +u8 zext(u8 *buf, u8 rd); /***** Moves *****/ u8 mov_r32(u8 *buf, u8 rd, u8 rs, u8 sign_ext); u8 mov_r32_i32(u8 *buf, u8 reg, s32 imm); diff --git a/arch/arc/net/bpf_jit_arcv2.c b/arch/arc/net/bpf_jit_arcv2.c index 31bfb6e9ce00..4458e409ca0a 100644 --- a/arch/arc/net/bpf_jit_arcv2.c +++ b/arch/arc/net/bpf_jit_arcv2.c @@ -62,7 +62,7 @@ enum { * If/when we decide to add ARCv2 instructions that do use register pairs, * the mapping, hopefully, doesn't need to be revisited. */ -const u8 bpf2arc[][2] = { +static const u8 bpf2arc[][2] = { /* Return value from in-kernel function, and exit value from eBPF */ [BPF_REG_0] = {ARC_R_8, ARC_R_9}, /* Arguments from eBPF program to in-kernel function */ @@ -1302,7 +1302,7 @@ static u8 arc_b(u8 *buf, s32 offset) /************* Packers (Deal with BPF_REGs) **************/ -inline u8 zext(u8 *buf, u8 rd) +u8 zext(u8 *buf, u8 rd) { if (rd != BPF_REG_FP) return arc_movi_r(buf, REG_HI(rd), 0); @@ -2235,6 +2235,7 @@ u8 gen_swap(u8 *buf, u8 rd, u8 size, u8 endian, bool force, bool do_zext) break; default: /* The caller must have handled this. */ + break; } } else { /* @@ -2253,6 +2254,7 @@ u8 gen_swap(u8 *buf, u8 rd, u8 size, u8 endian, bool force, bool do_zext) break; default: /* The caller must have handled this. */ + break; } } @@ -2517,7 +2519,7 @@ u8 arc_epilogue(u8 *buf, u32 usage, u16 frame_size) #define JCC64_NR_OF_JMPS 3 /* Number of jumps in jcc64 template. */ #define JCC64_INSNS_TO_END 3 /* Number of insn. inclusive the 2nd jmp to end. */ #define JCC64_SKIP_JMP 1 /* Index of the "skip" jump to "end". */ -const struct { +static const struct { /* * "jit_off" is common between all "jmp[]" and is coupled with * "cond" of each "jmp[]" instance. e.g.: @@ -2883,7 +2885,7 @@ u8 gen_jmp_64(u8 *buf, u8 rd, u8 rs, u8 cond, u32 curr_off, u32 targ_off) * The "ARC_CC_SET" becomes "CC_unequal" because of the "tst" * instruction that precedes the conditional branch. */ -const u8 arcv2_32_jmps[ARC_CC_LAST] = { +static const u8 arcv2_32_jmps[ARC_CC_LAST] = { [ARC_CC_UGT] = CC_great_u, [ARC_CC_UGE] = CC_great_eq_u, [ARC_CC_ULT] = CC_less_u, diff --git a/arch/arc/net/bpf_jit_core.c b/arch/arc/net/bpf_jit_core.c index 6f6b4ffccf2c..e3628922c24a 100644 --- a/arch/arc/net/bpf_jit_core.c +++ b/arch/arc/net/bpf_jit_core.c @@ -159,7 +159,7 @@ static void jit_dump(const struct jit_context *ctx) /* Initialise the context so there's no garbage. */ static int jit_ctx_init(struct jit_context *ctx, struct bpf_prog *prog) { - memset(ctx, 0, sizeof(ctx)); + memset(ctx, 0, sizeof(*ctx)); ctx->orig_prog = prog; @@ -167,7 +167,7 @@ static int jit_ctx_init(struct jit_context *ctx, struct bpf_prog *prog) ctx->prog = bpf_jit_blind_constants(prog); if (IS_ERR(ctx->prog)) return PTR_ERR(ctx->prog); - ctx->blinded = (ctx->prog == ctx->orig_prog ? false : true); + ctx->blinded = (ctx->prog != ctx->orig_prog); /* If the verifier doesn't zero-extend, then we have to do it. */ ctx->do_zext = !ctx->prog->aux->verifier_zext; @@ -1182,12 +1182,12 @@ static int jit_prepare(struct jit_context *ctx) } /* - * All the "handle_*()" functions have been called before by the - * "jit_prepare()". If there was an error, we would know by now. - * Therefore, no extra error checking at this point, other than - * a sanity check at the end that expects the calculated length - * (jit.len) to be equal to the length of generated instructions - * (jit.index). + * jit_compile() is the real compilation phase. jit_prepare() is + * invoked before jit_compile() as a dry-run to make sure everything + * will go OK and allocate the necessary memory. + * + * In the end, jit_compile() checks if it has produced the same number + * of instructions as jit_prepare() would. */ static int jit_compile(struct jit_context *ctx) { @@ -1407,9 +1407,9 @@ static struct bpf_prog *do_extra_pass(struct bpf_prog *prog) /* * This function may be invoked twice for the same stream of BPF - * instructions. The "extra pass" happens, when there are "call"s - * involved that their addresses are not known during the first - * invocation. + * instructions. The "extra pass" happens, when there are + * (re)locations involved that their addresses are not known + * during the first run. */ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) { diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index b6c9e01e14f5..2ed7d229c8f9 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -475,3 +475,4 @@ 459 common lsm_get_self_attr sys_lsm_get_self_attr 460 common lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index 491b2b9bd553..1346579f802f 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -39,7 +39,7 @@ #define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5) #define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800) -#define __NR_compat_syscalls 462 +#define __NR_compat_syscalls 463 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 7118282d1c79..266b96acc014 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -929,6 +929,8 @@ __SYSCALL(__NR_lsm_get_self_attr, sys_lsm_get_self_attr) __SYSCALL(__NR_lsm_set_self_attr, sys_lsm_set_self_attr) #define __NR_lsm_list_modules 461 __SYSCALL(__NR_lsm_list_modules, sys_lsm_list_modules) +#define __NR_mseal 462 +__SYSCALL(__NR_mseal, sys_mseal) /* * Please add new compat syscalls above this comment and update diff --git a/arch/arm64/kernel/patching.c b/arch/arm64/kernel/patching.c index 255534930368..945df74005c7 100644 --- a/arch/arm64/kernel/patching.c +++ b/arch/arm64/kernel/patching.c @@ -36,7 +36,7 @@ static void __kprobes *patch_map(void *addr, int fixmap) if (image) page = phys_to_page(__pa_symbol(addr)); - else if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) + else if (IS_ENABLED(CONFIG_EXECMEM)) page = vmalloc_to_page(addr); else return addr; diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index 7fd43fd4c9f2..22a3cbd4c602 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -461,3 +461,4 @@ 459 common lsm_get_self_attr sys_lsm_get_self_attr 460 common lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl index b00ab2cabab9..2b81a6bd78b2 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -467,3 +467,4 @@ 459 common lsm_get_self_attr sys_lsm_get_self_attr 460 common lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index 83cfc9eb6b88..cc869f5d5693 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -400,3 +400,4 @@ 459 n32 lsm_get_self_attr sys_lsm_get_self_attr 460 n32 lsm_set_self_attr sys_lsm_set_self_attr 461 n32 lsm_list_modules sys_lsm_list_modules +462 n32 mseal sys_mseal diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl index 532b855df589..1464c6be6eb3 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -376,3 +376,4 @@ 459 n64 lsm_get_self_attr sys_lsm_get_self_attr 460 n64 lsm_set_self_attr sys_lsm_set_self_attr 461 n64 lsm_list_modules sys_lsm_list_modules +462 n64 mseal sys_mseal diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index f45c9530ea93..008ebe60263e 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -449,3 +449,4 @@ 459 o32 lsm_get_self_attr sys_lsm_get_self_attr 460 o32 lsm_set_self_attr sys_lsm_set_self_attr 461 o32 lsm_list_modules sys_lsm_list_modules +462 o32 mseal sys_mseal diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index b236a84c4e12..b13c21373974 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -460,3 +460,4 @@ 459 common lsm_get_self_attr sys_lsm_get_self_attr 460 common lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 17173b82ca21..3656f1ca7a21 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -548,3 +548,4 @@ 459 common lsm_get_self_attr sys_lsm_get_self_attr 460 common lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 08db25006e35..58d3dcfebea2 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -129,7 +129,7 @@ config RISCV select HAVE_DMA_CONTIGUOUS if MMU select HAVE_DYNAMIC_FTRACE if !XIP_KERNEL && MMU && (CLANG_SUPPORTS_DYNAMIC_FTRACE || GCC_SUPPORTS_DYNAMIC_FTRACE) select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS - select HAVE_DYNAMIC_FTRACE_WITH_REGS if HAVE_DYNAMIC_FTRACE + select HAVE_DYNAMIC_FTRACE_WITH_ARGS if HAVE_DYNAMIC_FTRACE select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_GRAPH_RETVAL if HAVE_FUNCTION_GRAPH_TRACER @@ -141,6 +141,13 @@ config RISCV select HAVE_GCC_PLUGINS select HAVE_GENERIC_VDSO if MMU && 64BIT select HAVE_IRQ_TIME_ACCOUNTING + select HAVE_KERNEL_BZIP2 if !XIP_KERNEL && !EFI_ZBOOT + select HAVE_KERNEL_GZIP if !XIP_KERNEL && !EFI_ZBOOT + select HAVE_KERNEL_LZ4 if !XIP_KERNEL && !EFI_ZBOOT + select HAVE_KERNEL_LZMA if !XIP_KERNEL && !EFI_ZBOOT + select HAVE_KERNEL_LZO if !XIP_KERNEL && !EFI_ZBOOT + select HAVE_KERNEL_UNCOMPRESSED if !XIP_KERNEL && !EFI_ZBOOT + select HAVE_KERNEL_ZSTD if !XIP_KERNEL && !EFI_ZBOOT select HAVE_KPROBES if !XIP_KERNEL select HAVE_KPROBES_ON_FTRACE if !XIP_KERNEL select HAVE_KRETPROBES if !XIP_KERNEL @@ -170,7 +177,6 @@ config RISCV select LOCK_MM_AND_FIND_VMA select MMU_GATHER_RCU_TABLE_FREE if SMP && MMU select MODULES_USE_ELF_RELA if MODULES - select MODULE_SECTIONS if MODULES select OF select OF_EARLY_FLATTREE select OF_IRQ @@ -873,6 +879,7 @@ config PARAVIRT_TIME_ACCOUNTING config RELOCATABLE bool "Build a relocatable kernel" depends on MMU && 64BIT && !XIP_KERNEL + select MODULE_SECTIONS if MODULES help This builds a kernel as a Position Independent Executable (PIE), which retains all relocation metadata required to relocate the diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index ec47787acd89..06de9d365088 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -154,6 +154,21 @@ endif endif endif +boot := arch/riscv/boot +boot-image-y := Image +boot-image-$(CONFIG_KERNEL_BZIP2) := Image.bz2 +boot-image-$(CONFIG_KERNEL_GZIP) := Image.gz +boot-image-$(CONFIG_KERNEL_LZ4) := Image.lz4 +boot-image-$(CONFIG_KERNEL_LZMA) := Image.lzma +boot-image-$(CONFIG_KERNEL_LZO) := Image.lzo +boot-image-$(CONFIG_KERNEL_ZSTD) := Image.zst +ifdef CONFIG_RISCV_M_MODE +boot-image-$(CONFIG_ARCH_CANAAN) := loader.bin +endif +boot-image-$(CONFIG_EFI_ZBOOT) := vmlinuz.efi +boot-image-$(CONFIG_XIP_KERNEL) := xipImage +KBUILD_IMAGE := $(boot)/$(boot-image-y) + libs-y += arch/riscv/lib/ libs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a @@ -171,21 +186,19 @@ endif vdso-install-y += arch/riscv/kernel/vdso/vdso.so.dbg vdso-install-$(CONFIG_COMPAT) += arch/riscv/kernel/compat_vdso/compat_vdso.so.dbg -BOOT_TARGETS := Image Image.gz loader loader.bin xipImage vmlinuz.efi +BOOT_TARGETS := Image Image.gz Image.bz2 Image.lz4 Image.lzma Image.lzo Image.zst loader loader.bin xipImage vmlinuz.efi all: $(notdir $(KBUILD_IMAGE)) loader.bin: loader -Image.gz loader vmlinuz.efi: Image +Image.gz Image.bz2 Image.lz4 Image.lzma Image.lzo Image.zst loader xipImage vmlinuz.efi: Image + $(BOOT_TARGETS): vmlinux $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@ @$(kecho) ' Kernel: $(boot)/$@ is ready' -Image.%: Image - $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@ - -install: KBUILD_IMAGE := $(boot)/Image -zinstall: KBUILD_IMAGE := $(boot)/Image.gz +# the install target always installs KBUILD_IMAGE (which may be compressed) +# but keep the zinstall target for compatibility with older releases install zinstall: $(call cmd,install) @@ -206,3 +219,20 @@ rv32_defconfig: PHONY += rv32_nommu_virt_defconfig rv32_nommu_virt_defconfig: $(Q)$(MAKE) -f $(srctree)/Makefile nommu_virt_defconfig 32-bit.config + +define archhelp + echo ' Image - Uncompressed kernel image (arch/riscv/boot/Image)' + echo ' Image.gz - Compressed kernel image (arch/riscv/boot/Image.gz)' + echo ' Image.bz2 - Compressed kernel image (arch/riscv/boot/Image.bz2)' + echo ' Image.lz4 - Compressed kernel image (arch/riscv/boot/Image.lz4)' + echo ' Image.lzma - Compressed kernel image (arch/riscv/boot/Image.lzma)' + echo ' Image.lzo - Compressed kernel image (arch/riscv/boot/Image.lzo)' + echo ' Image.zst - Compressed kernel image (arch/riscv/boot/Image.zst)' + echo ' vmlinuz.efi - Compressed EFI kernel image (arch/riscv/boot/vmlinuz.efi)' + echo ' Default when CONFIG_EFI_ZBOOT=y' + echo ' xipImage - Execute-in-place kernel image (arch/riscv/boot/xipImage)' + echo ' Default when CONFIG_XIP_KERNEL=y' + echo ' install - Install kernel using (your) ~/bin/$(INSTALLKERNEL) or' + echo ' (distribution) /sbin/$(INSTALLKERNEL) or install to ' + echo ' $$(INSTALL_PATH)' +endef diff --git a/arch/riscv/boot/install.sh b/arch/riscv/boot/install.sh index 4c63f3f0643d..a8df7591513a 100755 --- a/arch/riscv/boot/install.sh +++ b/arch/riscv/boot/install.sh @@ -17,15 +17,18 @@ # $3 - kernel map file # $4 - default install path (blank if root directory) -if [ "$(basename $2)" = "Image.gz" ]; then +case "${2##*/}" in # Compressed install +Image.*|vmlinuz.efi) echo "Installing compressed kernel" base=vmlinuz -else + ;; # Normal install +*) echo "Installing normal kernel" base=vmlinux -fi + ;; +esac if [ -f $4/$base-$1 ]; then mv $4/$base-$1 $4/$base-$1.old diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h index dd8d07146116..ce79c558a4c8 100644 --- a/arch/riscv/include/asm/cacheflush.h +++ b/arch/riscv/include/asm/cacheflush.h @@ -13,6 +13,12 @@ static inline void local_flush_icache_all(void) asm volatile ("fence.i" ::: "memory"); } +static inline void local_flush_icache_range(unsigned long start, + unsigned long end) +{ + local_flush_icache_all(); +} + #define PG_dcache_clean PG_arch_1 static inline void flush_dcache_folio(struct folio *folio) diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h index 1276d7d9ca8b..9eb31a7ea0aa 100644 --- a/arch/riscv/include/asm/ftrace.h +++ b/arch/riscv/include/asm/ftrace.h @@ -124,20 +124,82 @@ struct dyn_ftrace; int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec); #define ftrace_init_nop ftrace_init_nop -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS +#define arch_ftrace_get_regs(regs) NULL struct ftrace_ops; -struct ftrace_regs; +struct ftrace_regs { + unsigned long epc; + unsigned long ra; + unsigned long sp; + unsigned long s0; + unsigned long t1; + union { + unsigned long args[8]; + struct { + unsigned long a0; + unsigned long a1; + unsigned long a2; + unsigned long a3; + unsigned long a4; + unsigned long a5; + unsigned long a6; + unsigned long a7; + }; + }; +}; + +static __always_inline unsigned long ftrace_regs_get_instruction_pointer(const struct ftrace_regs + *fregs) +{ + return fregs->epc; +} + +static __always_inline void ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, + unsigned long pc) +{ + fregs->epc = pc; +} + +static __always_inline unsigned long ftrace_regs_get_stack_pointer(const struct ftrace_regs *fregs) +{ + return fregs->sp; +} + +static __always_inline unsigned long ftrace_regs_get_argument(struct ftrace_regs *fregs, + unsigned int n) +{ + if (n < 8) + return fregs->args[n]; + return 0; +} + +static __always_inline unsigned long ftrace_regs_get_return_value(const struct ftrace_regs *fregs) +{ + return fregs->a0; +} + +static __always_inline void ftrace_regs_set_return_value(struct ftrace_regs *fregs, + unsigned long ret) +{ + fregs->a0 = ret; +} + +static __always_inline void ftrace_override_function_with_return(struct ftrace_regs *fregs) +{ + fregs->epc = fregs->ra; +} + +int ftrace_regs_query_register_offset(const char *name); + void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs); #define ftrace_graph_func ftrace_graph_func -static inline void __arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr) +static inline void arch_ftrace_set_direct_caller(struct ftrace_regs *fregs, unsigned long addr) { - regs->t1 = addr; + fregs->t1 = addr; } -#define arch_ftrace_set_direct_caller(fregs, addr) \ - __arch_ftrace_set_direct_caller(&(fregs)->regs, addr) -#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */ #endif /* __ASSEMBLY__ */ diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h index 221a5c1ee287..8c36a8818432 100644 --- a/arch/riscv/include/asm/pgtable-64.h +++ b/arch/riscv/include/asm/pgtable-64.h @@ -16,8 +16,6 @@ extern bool pgtable_l5_enabled; #define PGDIR_SHIFT_L3 30 #define PGDIR_SHIFT_L4 39 #define PGDIR_SHIFT_L5 48 -#define PGDIR_SIZE_L3 (_AC(1, UL) << PGDIR_SHIFT_L3) - #define PGDIR_SHIFT (pgtable_l5_enabled ? PGDIR_SHIFT_L5 : \ (pgtable_l4_enabled ? PGDIR_SHIFT_L4 : PGDIR_SHIFT_L3)) /* Size of region mapped by a page global directory */ diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 55a7c3ec246b..aad8b8ca51f1 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -880,7 +880,7 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte) */ #ifdef CONFIG_64BIT #define TASK_SIZE_64 (PGDIR_SIZE * PTRS_PER_PGD / 2) -#define TASK_SIZE_MIN (PGDIR_SIZE_L3 * PTRS_PER_PGD / 2) +#define TASK_SIZE_MAX LONG_MAX #ifdef CONFIG_COMPAT #define TASK_SIZE_32 (_AC(0x80000000, UL) - PAGE_SIZE) @@ -892,7 +892,6 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte) #else #define TASK_SIZE FIXADDR_START -#define TASK_SIZE_MIN TASK_SIZE #endif #else /* CONFIG_MMU */ diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h index 9186e7984672..1079e214fe85 100644 --- a/arch/riscv/include/asm/sbi.h +++ b/arch/riscv/include/asm/sbi.h @@ -382,6 +382,8 @@ static inline int sbi_remote_fence_i(const struct cpumask *cpu_mask) { return -1 static inline void sbi_init(void) {} #endif /* CONFIG_RISCV_SBI */ +unsigned long riscv_get_mvendorid(void); +unsigned long riscv_get_marchid(void); unsigned long riscv_cached_mvendorid(unsigned int cpu_id); unsigned long riscv_cached_marchid(unsigned int cpu_id); unsigned long riscv_cached_mimpid(unsigned int cpu_id); diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c index a03129f40c46..b09ca5f944f7 100644 --- a/arch/riscv/kernel/asm-offsets.c +++ b/arch/riscv/kernel/asm-offsets.c @@ -9,6 +9,7 @@ #include <linux/kbuild.h> #include <linux/mm.h> #include <linux/sched.h> +#include <linux/ftrace.h> #include <linux/suspend.h> #include <asm/kvm_host.h> #include <asm/thread_info.h> @@ -488,4 +489,21 @@ void asm_offsets(void) DEFINE(STACKFRAME_SIZE_ON_STACK, ALIGN(sizeof(struct stackframe), STACK_ALIGN)); OFFSET(STACKFRAME_FP, stackframe, fp); OFFSET(STACKFRAME_RA, stackframe, ra); + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS + DEFINE(FREGS_SIZE_ON_STACK, ALIGN(sizeof(struct ftrace_regs), STACK_ALIGN)); + DEFINE(FREGS_EPC, offsetof(struct ftrace_regs, epc)); + DEFINE(FREGS_RA, offsetof(struct ftrace_regs, ra)); + DEFINE(FREGS_SP, offsetof(struct ftrace_regs, sp)); + DEFINE(FREGS_S0, offsetof(struct ftrace_regs, s0)); + DEFINE(FREGS_T1, offsetof(struct ftrace_regs, t1)); + DEFINE(FREGS_A0, offsetof(struct ftrace_regs, a0)); + DEFINE(FREGS_A1, offsetof(struct ftrace_regs, a1)); + DEFINE(FREGS_A2, offsetof(struct ftrace_regs, a2)); + DEFINE(FREGS_A3, offsetof(struct ftrace_regs, a3)); + DEFINE(FREGS_A4, offsetof(struct ftrace_regs, a4)); + DEFINE(FREGS_A5, offsetof(struct ftrace_regs, a5)); + DEFINE(FREGS_A6, offsetof(struct ftrace_regs, a6)); + DEFINE(FREGS_A7, offsetof(struct ftrace_regs, a7)); +#endif } diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c index d11d6320fb0d..c1f3655238fd 100644 --- a/arch/riscv/kernel/cpu.c +++ b/arch/riscv/kernel/cpu.c @@ -139,6 +139,34 @@ int riscv_of_parent_hartid(struct device_node *node, unsigned long *hartid) return -1; } +unsigned long __init riscv_get_marchid(void) +{ + struct riscv_cpuinfo *ci = this_cpu_ptr(&riscv_cpuinfo); + +#if IS_ENABLED(CONFIG_RISCV_SBI) + ci->marchid = sbi_spec_is_0_1() ? 0 : sbi_get_marchid(); +#elif IS_ENABLED(CONFIG_RISCV_M_MODE) + ci->marchid = csr_read(CSR_MARCHID); +#else + ci->marchid = 0; +#endif + return ci->marchid; +} + +unsigned long __init riscv_get_mvendorid(void) +{ + struct riscv_cpuinfo *ci = this_cpu_ptr(&riscv_cpuinfo); + +#if IS_ENABLED(CONFIG_RISCV_SBI) + ci->mvendorid = sbi_spec_is_0_1() ? 0 : sbi_get_mvendorid(); +#elif IS_ENABLED(CONFIG_RISCV_M_MODE) + ci->mvendorid = csr_read(CSR_MVENDORID); +#else + ci->mvendorid = 0; +#endif + return ci->mvendorid; +} + DEFINE_PER_CPU(struct riscv_cpuinfo, riscv_cpuinfo); unsigned long riscv_cached_mvendorid(unsigned int cpu_id) @@ -170,12 +198,16 @@ static int riscv_cpuinfo_starting(unsigned int cpu) struct riscv_cpuinfo *ci = this_cpu_ptr(&riscv_cpuinfo); #if IS_ENABLED(CONFIG_RISCV_SBI) - ci->mvendorid = sbi_spec_is_0_1() ? 0 : sbi_get_mvendorid(); - ci->marchid = sbi_spec_is_0_1() ? 0 : sbi_get_marchid(); + if (!ci->mvendorid) + ci->mvendorid = sbi_spec_is_0_1() ? 0 : sbi_get_mvendorid(); + if (!ci->marchid) + ci->marchid = sbi_spec_is_0_1() ? 0 : sbi_get_marchid(); ci->mimpid = sbi_spec_is_0_1() ? 0 : sbi_get_mimpid(); #elif IS_ENABLED(CONFIG_RISCV_M_MODE) - ci->mvendorid = csr_read(CSR_MVENDORID); - ci->marchid = csr_read(CSR_MARCHID); + if (!ci->mvendorid) + ci->mvendorid = csr_read(CSR_MVENDORID); + if (!ci->marchid) + ci->marchid = csr_read(CSR_MARCHID); ci->mimpid = csr_read(CSR_MIMPID); #else ci->mvendorid = 0; diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index 3ed2359eae35..5ef48cb20ee1 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -490,6 +490,8 @@ static void __init riscv_fill_hwcap_from_isa_string(unsigned long *isa2hwcap) struct acpi_table_header *rhct; acpi_status status; unsigned int cpu; + u64 boot_vendorid; + u64 boot_archid; if (!acpi_disabled) { status = acpi_get_table(ACPI_SIG_RHCT, 0, &rhct); @@ -497,6 +499,9 @@ static void __init riscv_fill_hwcap_from_isa_string(unsigned long *isa2hwcap) return; } + boot_vendorid = riscv_get_mvendorid(); + boot_archid = riscv_get_marchid(); + for_each_possible_cpu(cpu) { struct riscv_isainfo *isainfo = &hart_isa[cpu]; unsigned long this_hwcap = 0; @@ -544,8 +549,7 @@ static void __init riscv_fill_hwcap_from_isa_string(unsigned long *isa2hwcap) * CPU cores with the ratified spec will contain non-zero * marchid. */ - if (acpi_disabled && riscv_cached_mvendorid(cpu) == THEAD_VENDOR_ID && - riscv_cached_marchid(cpu) == 0x0) { + if (acpi_disabled && boot_vendorid == THEAD_VENDOR_ID && boot_archid == 0x0) { this_hwcap &= ~isa2hwcap[RISCV_ISA_EXT_v]; clear_bit(RISCV_ISA_EXT_v, isainfo->isa); } @@ -599,7 +603,7 @@ static int __init riscv_fill_hwcap_from_ext_list(unsigned long *isa2hwcap) if (ext->subset_ext_size) { for (int j = 0; j < ext->subset_ext_size; j++) { - if (riscv_isa_extension_check(ext->subset_ext_ids[i])) + if (riscv_isa_extension_check(ext->subset_ext_ids[j])) set_bit(ext->subset_ext_ids[j], isainfo->isa); } } diff --git a/arch/riscv/kernel/fpu.S b/arch/riscv/kernel/fpu.S index 2c543f130f93..327cf527dd7e 100644 --- a/arch/riscv/kernel/fpu.S +++ b/arch/riscv/kernel/fpu.S @@ -211,7 +211,7 @@ SYM_FUNC_START(put_f64_reg) SYM_FUNC_END(put_f64_reg) /* - * put_f64_reg - Get a 64 bits FP register value and returned it or store it to + * get_f64_reg - Get a 64 bits FP register value and returned it or store it to * a pointer. * a0 = FP register index to be retrieved * a1 = If xlen == 32, pointer which should be loaded with the FP register value diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c index 4f4987a6d83d..87cbd86576b2 100644 --- a/arch/riscv/kernel/ftrace.c +++ b/arch/riscv/kernel/ftrace.c @@ -120,6 +120,9 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) out = ftrace_make_nop(mod, rec, MCOUNT_ADDR); mutex_unlock(&text_mutex); + if (!mod) + local_flush_icache_range(rec->ip, rec->ip + MCOUNT_INSN_SIZE); + return out; } @@ -127,10 +130,6 @@ int ftrace_update_ftrace_func(ftrace_func_t func) { int ret = __ftrace_modify_call((unsigned long)&ftrace_call, (unsigned long)func, true, true); - if (!ret) { - ret = __ftrace_modify_call((unsigned long)&ftrace_regs_call, - (unsigned long)func, true, true); - } return ret; } @@ -172,7 +171,7 @@ void arch_ftrace_update_code(int command) } #endif -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr) { @@ -214,16 +213,13 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, } #ifdef CONFIG_DYNAMIC_FTRACE -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs) { - struct pt_regs *regs = arch_ftrace_get_regs(fregs); - unsigned long *parent = (unsigned long *)®s->ra; - - prepare_ftrace_return(parent, ip, frame_pointer(regs)); + prepare_ftrace_return(&fregs->ra, ip, fregs->s0); } -#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ +#else /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */ extern void ftrace_graph_call(void); int ftrace_enable_ftrace_graph_caller(void) { @@ -236,6 +232,6 @@ int ftrace_disable_ftrace_graph_caller(void) return __ftrace_modify_call((unsigned long)&ftrace_graph_call, (unsigned long)&prepare_ftrace_return, false, true); } -#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */ #endif /* CONFIG_DYNAMIC_FTRACE */ #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/riscv/kernel/mcount-dyn.S b/arch/riscv/kernel/mcount-dyn.S index b7561288e8da..745dd4c4a69c 100644 --- a/arch/riscv/kernel/mcount-dyn.S +++ b/arch/riscv/kernel/mcount-dyn.S @@ -56,138 +56,77 @@ addi sp, sp, ABI_SIZE_ON_STACK .endm -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS /** -* SAVE_ABI_REGS - save regs against the pt_regs struct -* -* @all: tell if saving all the regs -* -* If all is set, all the regs will be saved, otherwise only ABI -* related regs (a0-a7,epc,ra and optional s0) will be saved. +* SAVE_ABI_REGS - save regs against the ftrace_regs struct * * After the stack is established, * * 0(sp) stores the PC of the traced function which can be accessed -* by &(fregs)->regs->epc in tracing function. Note that the real +* by &(fregs)->epc in tracing function. Note that the real * function entry address should be computed with -FENTRY_RA_OFFSET. * * 8(sp) stores the function return address (i.e. parent IP) that -* can be accessed by &(fregs)->regs->ra in tracing function. +* can be accessed by &(fregs)->ra in tracing function. * * The other regs are saved at the respective localtion and accessed -* by the respective pt_regs member. +* by the respective ftrace_regs member. * * Here is the layout of stack for your reference. * * PT_SIZE_ON_STACK -> +++++++++ * + ..... + -* + t3-t6 + -* + s2-s11+ * + a0-a7 + --++++-> ftrace_caller saved -* + s1 + + -* + s0 + --+ -* + t0-t2 + + -* + tp + + -* + gp + + +* + t1 + --++++-> direct tramp address +* + s0 + --+ // frame pointer * + sp + + * + ra + --+ // parent IP * sp -> + epc + --+ // PC * +++++++++ **/ - .macro SAVE_ABI_REGS, all=0 - addi sp, sp, -PT_SIZE_ON_STACK - - REG_S t0, PT_EPC(sp) - REG_S x1, PT_RA(sp) - - // save the ABI regs - - REG_S x10, PT_A0(sp) - REG_S x11, PT_A1(sp) - REG_S x12, PT_A2(sp) - REG_S x13, PT_A3(sp) - REG_S x14, PT_A4(sp) - REG_S x15, PT_A5(sp) - REG_S x16, PT_A6(sp) - REG_S x17, PT_A7(sp) - - // save the leftover regs + .macro SAVE_ABI_REGS + mv t4, sp // Save original SP in T4 + addi sp, sp, -FREGS_SIZE_ON_STACK - .if \all == 1 - REG_S x2, PT_SP(sp) - REG_S x3, PT_GP(sp) - REG_S x4, PT_TP(sp) - REG_S x5, PT_T0(sp) - REG_S x6, PT_T1(sp) - REG_S x7, PT_T2(sp) - REG_S x8, PT_S0(sp) - REG_S x9, PT_S1(sp) - REG_S x18, PT_S2(sp) - REG_S x19, PT_S3(sp) - REG_S x20, PT_S4(sp) - REG_S x21, PT_S5(sp) - REG_S x22, PT_S6(sp) - REG_S x23, PT_S7(sp) - REG_S x24, PT_S8(sp) - REG_S x25, PT_S9(sp) - REG_S x26, PT_S10(sp) - REG_S x27, PT_S11(sp) - REG_S x28, PT_T3(sp) - REG_S x29, PT_T4(sp) - REG_S x30, PT_T5(sp) - REG_S x31, PT_T6(sp) - - // save s0 if FP_TEST defined - - .else + REG_S t0, FREGS_EPC(sp) + REG_S x1, FREGS_RA(sp) + REG_S t4, FREGS_SP(sp) // Put original SP on stack #ifdef HAVE_FUNCTION_GRAPH_FP_TEST - REG_S x8, PT_S0(sp) + REG_S x8, FREGS_S0(sp) #endif - .endif + REG_S x6, FREGS_T1(sp) + + // save the arguments + REG_S x10, FREGS_A0(sp) + REG_S x11, FREGS_A1(sp) + REG_S x12, FREGS_A2(sp) + REG_S x13, FREGS_A3(sp) + REG_S x14, FREGS_A4(sp) + REG_S x15, FREGS_A5(sp) + REG_S x16, FREGS_A6(sp) + REG_S x17, FREGS_A7(sp) .endm .macro RESTORE_ABI_REGS, all=0 - REG_L t0, PT_EPC(sp) - REG_L x1, PT_RA(sp) - REG_L x10, PT_A0(sp) - REG_L x11, PT_A1(sp) - REG_L x12, PT_A2(sp) - REG_L x13, PT_A3(sp) - REG_L x14, PT_A4(sp) - REG_L x15, PT_A5(sp) - REG_L x16, PT_A6(sp) - REG_L x17, PT_A7(sp) - - .if \all == 1 - REG_L x2, PT_SP(sp) - REG_L x3, PT_GP(sp) - REG_L x4, PT_TP(sp) - REG_L x6, PT_T1(sp) - REG_L x7, PT_T2(sp) - REG_L x8, PT_S0(sp) - REG_L x9, PT_S1(sp) - REG_L x18, PT_S2(sp) - REG_L x19, PT_S3(sp) - REG_L x20, PT_S4(sp) - REG_L x21, PT_S5(sp) - REG_L x22, PT_S6(sp) - REG_L x23, PT_S7(sp) - REG_L x24, PT_S8(sp) - REG_L x25, PT_S9(sp) - REG_L x26, PT_S10(sp) - REG_L x27, PT_S11(sp) - REG_L x28, PT_T3(sp) - REG_L x29, PT_T4(sp) - REG_L x30, PT_T5(sp) - REG_L x31, PT_T6(sp) - - .else + REG_L t0, FREGS_EPC(sp) + REG_L x1, FREGS_RA(sp) #ifdef HAVE_FUNCTION_GRAPH_FP_TEST - REG_L x8, PT_S0(sp) + REG_L x8, FREGS_S0(sp) #endif - .endif - addi sp, sp, PT_SIZE_ON_STACK + REG_L x6, FREGS_T1(sp) + + // restore the arguments + REG_L x10, FREGS_A0(sp) + REG_L x11, FREGS_A1(sp) + REG_L x12, FREGS_A2(sp) + REG_L x13, FREGS_A3(sp) + REG_L x14, FREGS_A4(sp) + REG_L x15, FREGS_A5(sp) + REG_L x16, FREGS_A6(sp) + REG_L x17, FREGS_A7(sp) + + addi sp, sp, FREGS_SIZE_ON_STACK .endm .macro PREPARE_ARGS @@ -198,9 +137,9 @@ mv a3, sp .endm -#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */ -#ifndef CONFIG_DYNAMIC_FTRACE_WITH_REGS +#ifndef CONFIG_DYNAMIC_FTRACE_WITH_ARGS SYM_FUNC_START(ftrace_caller) SAVE_ABI @@ -227,33 +166,23 @@ SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL) jr t0 SYM_FUNC_END(ftrace_caller) -#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ -SYM_FUNC_START(ftrace_regs_caller) +#else /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */ +SYM_FUNC_START(ftrace_caller) mv t1, zero - SAVE_ABI_REGS 1 + SAVE_ABI_REGS PREPARE_ARGS -SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL) +SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) call ftrace_stub - RESTORE_ABI_REGS 1 + RESTORE_ABI_REGS bnez t1, .Ldirect jr t0 .Ldirect: jr t1 -SYM_FUNC_END(ftrace_regs_caller) - -SYM_FUNC_START(ftrace_caller) - SAVE_ABI_REGS 0 - PREPARE_ARGS - -SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) - call ftrace_stub - - RESTORE_ABI_REGS 0 - jr t0 SYM_FUNC_END(ftrace_caller) -#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ + +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */ #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS SYM_CODE_START(ftrace_stub_direct_tramp) diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index 4b3c50da48ba..1319b29ce3b5 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -224,7 +224,7 @@ asmlinkage __visible void smp_callin(void) riscv_ipi_enable(); numa_add_cpu(curr_cpuid); - set_cpu_online(curr_cpuid, 1); + set_cpu_online(curr_cpuid, true); if (has_vector()) { if (riscv_v_setup_vsize()) diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 64a9c093aef9..528ec7cc9a62 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -18,6 +18,16 @@ extern asmlinkage void ret_from_exception(void); +static inline int fp_is_valid(unsigned long fp, unsigned long sp) +{ + unsigned long low, high; + + low = sp + sizeof(struct stackframe); + high = ALIGN(sp, THREAD_SIZE); + + return !(fp < low || fp > high || fp & 0x07); +} + void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, bool (*fn)(void *, unsigned long), void *arg) { @@ -41,21 +51,19 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, } for (;;) { - unsigned long low, high; struct stackframe *frame; if (unlikely(!__kernel_text_address(pc) || (level++ >= 0 && !fn(arg, pc)))) break; - /* Validate frame pointer */ - low = sp + sizeof(struct stackframe); - high = ALIGN(sp, THREAD_SIZE); - if (unlikely(fp < low || fp > high || fp & 0x7)) + if (unlikely(!fp_is_valid(fp, sp))) break; + /* Unwind stack frame */ frame = (struct stackframe *)fp - 1; sp = fp; - if (regs && (regs->epc == pc) && (frame->fp & 0x7)) { + if (regs && (regs->epc == pc) && fp_is_valid(frame->ra, sp)) { + /* We hit function where ra is not saved on the stack */ fp = frame->ra; pc = regs->ra; } else { diff --git a/arch/riscv/lib/uaccess.S b/arch/riscv/lib/uaccess.S index bc22c078aba8..1399d797d81b 100644 --- a/arch/riscv/lib/uaccess.S +++ b/arch/riscv/lib/uaccess.S @@ -44,7 +44,7 @@ SYM_FUNC_START(fallback_scalar_usercopy) * Use byte copy only if too small. * SZREG holds 4 for RV32 and 8 for RV64 */ - li a3, 9*SZREG /* size must be larger than size in word_copy */ + li a3, 9*SZREG-1 /* size must >= (word_copy stride + SZREG-1) */ bltu a2, a3, .Lbyte_copy_tail /* @@ -103,7 +103,7 @@ SYM_FUNC_START(fallback_scalar_usercopy) fixup REG_S t4, 7*SZREG(a0), 10f addi a0, a0, 8*SZREG addi a1, a1, 8*SZREG - bltu a0, t0, 2b + bleu a0, t0, 2b addi t0, t0, 8*SZREG /* revert to original value */ j .Lbyte_copy_tail diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 5224f3733802..b3fcf7d67efb 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -293,8 +293,8 @@ void handle_page_fault(struct pt_regs *regs) if (unlikely(access_error(cause, vma))) { vma_end_read(vma); count_vm_vma_lock_event(VMA_LOCK_SUCCESS); - tsk->thread.bad_cause = cause; - bad_area_nosemaphore(regs, SEGV_ACCERR, addr); + tsk->thread.bad_cause = SEGV_ACCERR; + bad_area_nosemaphore(regs, code, addr); return; } diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 7e12925fc660..e3218d65f21d 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -683,6 +683,9 @@ void __init create_pgd_mapping(pgd_t *pgdp, static uintptr_t __init best_map_size(phys_addr_t pa, uintptr_t va, phys_addr_t size) { + if (debug_pagealloc_enabled()) + return PAGE_SIZE; + if (pgtable_l5_enabled && !(pa & (P4D_SIZE - 1)) && !(va & (P4D_SIZE - 1)) && size >= P4D_SIZE) return P4D_SIZE; diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c index 410056a50aa9..271d01a5ba4d 100644 --- a/arch/riscv/mm/pageattr.c +++ b/arch/riscv/mm/pageattr.c @@ -387,17 +387,33 @@ int set_direct_map_default_noflush(struct page *page) } #ifdef CONFIG_DEBUG_PAGEALLOC +static int debug_pagealloc_set_page(pte_t *pte, unsigned long addr, void *data) +{ + int enable = *(int *)data; + + unsigned long val = pte_val(ptep_get(pte)); + + if (enable) + val |= _PAGE_PRESENT; + else + val &= ~_PAGE_PRESENT; + + set_pte(pte, __pte(val)); + + return 0; +} + void __kernel_map_pages(struct page *page, int numpages, int enable) { if (!debug_pagealloc_enabled()) return; - if (enable) - __set_memory((unsigned long)page_address(page), numpages, - __pgprot(_PAGE_PRESENT), __pgprot(0)); - else - __set_memory((unsigned long)page_address(page), numpages, - __pgprot(0), __pgprot(_PAGE_PRESENT)); + unsigned long start = (unsigned long)page_address(page); + unsigned long size = PAGE_SIZE * numpages; + + apply_to_existing_page_range(&init_mm, start, size, debug_pagealloc_set_page, &enable); + + flush_tlb_kernel_range(start, start + size); } #endif diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index 095bb86339a7..bd0fee24ad10 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -464,3 +464,4 @@ 459 common lsm_get_self_attr sys_lsm_get_self_attr sys_lsm_get_self_attr 460 common lsm_set_self_attr sys_lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal sys_mseal diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index 86fe269f0220..bbf83a2db986 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -464,3 +464,4 @@ 459 common lsm_get_self_attr sys_lsm_get_self_attr 460 common lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index b23d59313589..ac6c281ccfe0 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -507,3 +507,4 @@ 459 common lsm_get_self_attr sys_lsm_get_self_attr 460 common lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal diff --git a/arch/um/Makefile b/arch/um/Makefile index 34957dcb88b9..00b63bac5eff 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -20,7 +20,7 @@ endif ARCH_DIR := arch/um # We require bash because the vmlinux link and loader script cpp use bash # features. -SHELL := /bin/bash +SHELL := bash MODE_INCLUDE += -I$(srctree)/$(ARCH_DIR)/include/shared/skas diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c index ffc5cb92fa36..d82bc3fdb86e 100644 --- a/arch/um/drivers/line.c +++ b/arch/um/drivers/line.c @@ -676,24 +676,26 @@ void register_winch_irq(int fd, int tty_fd, int pid, struct tty_port *port, goto cleanup; } - *winch = ((struct winch) { .list = LIST_HEAD_INIT(winch->list), - .fd = fd, + *winch = ((struct winch) { .fd = fd, .tty_fd = tty_fd, .pid = pid, .port = port, .stack = stack }); + spin_lock(&winch_handler_lock); + list_add(&winch->list, &winch_handlers); + spin_unlock(&winch_handler_lock); + if (um_request_irq(WINCH_IRQ, fd, IRQ_READ, winch_interrupt, IRQF_SHARED, "winch", winch) < 0) { printk(KERN_ERR "register_winch_irq - failed to register " "IRQ\n"); + spin_lock(&winch_handler_lock); + list_del(&winch->list); + spin_unlock(&winch_handler_lock); goto out_free; } - spin_lock(&winch_handler_lock); - list_add(&winch->list, &winch_handlers); - spin_unlock(&winch_handler_lock); - return; out_free: diff --git a/arch/um/drivers/pcap_kern.c b/arch/um/drivers/pcap_kern.c index 25ee2c97ca21..d9bf95d7867b 100644 --- a/arch/um/drivers/pcap_kern.c +++ b/arch/um/drivers/pcap_kern.c @@ -15,7 +15,7 @@ struct pcap_init { char *filter; }; -void pcap_init_kern(struct net_device *dev, void *data) +static void pcap_init_kern(struct net_device *dev, void *data) { struct uml_net_private *pri; struct pcap_data *ppri; @@ -50,7 +50,7 @@ static const struct net_kern_info pcap_kern_info = { .write = pcap_write, }; -int pcap_setup(char *str, char **mac_out, void *data) +static int pcap_setup(char *str, char **mac_out, void *data) { struct pcap_init *init = data; char *remain, *host_if = NULL, *options[2] = { NULL, NULL }; diff --git a/arch/um/drivers/rtc_kern.c b/arch/um/drivers/rtc_kern.c index 97ceb205cfe6..3a1582219c4b 100644 --- a/arch/um/drivers/rtc_kern.c +++ b/arch/um/drivers/rtc_kern.c @@ -168,16 +168,15 @@ cleanup: return err; } -static int uml_rtc_remove(struct platform_device *pdev) +static void uml_rtc_remove(struct platform_device *pdev) { device_init_wakeup(&pdev->dev, 0); uml_rtc_cleanup(); - return 0; } static struct platform_driver uml_rtc_driver = { .probe = uml_rtc_probe, - .remove = uml_rtc_remove, + .remove_new = uml_rtc_remove, .driver = { .name = "uml-rtc", }, diff --git a/arch/um/drivers/slirp_user.c b/arch/um/drivers/slirp_user.c index 8f633e2e5f3d..97228aa080cb 100644 --- a/arch/um/drivers/slirp_user.c +++ b/arch/um/drivers/slirp_user.c @@ -49,7 +49,7 @@ static int slirp_tramp(char **argv, int fd) static int slirp_open(void *data) { struct slirp_data *pri = data; - int fds[2], pid, err; + int fds[2], err; err = os_pipe(fds, 1, 1); if (err) @@ -60,7 +60,6 @@ static int slirp_open(void *data) printk(UM_KERN_ERR "slirp_tramp failed - errno = %d\n", -err); goto out; } - pid = err; pri->slave = fds[1]; pri->slip.pos = 0; diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index 63fc062add70..ef805eaa9e01 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -1092,7 +1092,7 @@ static int __init ubd_init(void) if (irq_req_buffer == NULL) { printk(KERN_ERR "Failed to initialize ubd buffering\n"); - return -1; + return -ENOMEM; } io_req_buffer = kmalloc_array(UBD_REQ_BUFFER_SIZE, sizeof(struct io_thread_req *), @@ -1103,7 +1103,7 @@ static int __init ubd_init(void) if (io_req_buffer == NULL) { printk(KERN_ERR "Failed to initialize ubd buffering\n"); - return -1; + return -ENOMEM; } platform_driver_register(&ubd_driver); mutex_lock(&ubd_lock); diff --git a/arch/um/drivers/ubd_user.c b/arch/um/drivers/ubd_user.c index a1afe414ce48..b4f8b8e60564 100644 --- a/arch/um/drivers/ubd_user.c +++ b/arch/um/drivers/ubd_user.c @@ -23,7 +23,7 @@ #include <os.h> #include <poll.h> -struct pollfd kernel_pollfd; +static struct pollfd kernel_pollfd; int start_io_thread(unsigned long sp, int *fd_out) { diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c index dc2feae789cb..4279793b11b7 100644 --- a/arch/um/drivers/vector_kern.c +++ b/arch/um/drivers/vector_kern.c @@ -141,7 +141,7 @@ static bool get_bpf_flash(struct arglist *def) if (allow != NULL) { if (kstrtoul(allow, 10, &result) == 0) - return (allow > 0); + return result > 0; } return false; } @@ -712,11 +712,9 @@ static struct vector_device *find_device(int n) static int vector_parse(char *str, int *index_out, char **str_out, char **error_out) { - int n, len, err; + int n, err; char *start = str; - len = strlen(str); - while ((*str != ':') && (strlen(str) > 1)) str++; if (*str != ':') { diff --git a/arch/um/drivers/virtio_uml.c b/arch/um/drivers/virtio_uml.c index 8adca2000e51..77faa2cf3a13 100644 --- a/arch/um/drivers/virtio_uml.c +++ b/arch/um/drivers/virtio_uml.c @@ -1241,12 +1241,11 @@ error_free: return rc; } -static int virtio_uml_remove(struct platform_device *pdev) +static void virtio_uml_remove(struct platform_device *pdev) { struct virtio_uml_device *vu_dev = platform_get_drvdata(pdev); unregister_virtio_device(&vu_dev->vdev); - return 0; } /* Command line device list */ @@ -1445,7 +1444,7 @@ static int virtio_uml_resume(struct platform_device *pdev) static struct platform_driver virtio_uml_driver = { .probe = virtio_uml_probe, - .remove = virtio_uml_remove, + .remove_new = virtio_uml_remove, .driver = { .name = "virtio-uml", .of_match_table = virtio_uml_match, diff --git a/arch/um/include/asm/kasan.h b/arch/um/include/asm/kasan.h index 0d6547f4ec85..f97bb1f7b851 100644 --- a/arch/um/include/asm/kasan.h +++ b/arch/um/include/asm/kasan.h @@ -24,7 +24,6 @@ #ifdef CONFIG_KASAN void kasan_init(void); -void kasan_map_memory(void *start, unsigned long len); extern int kasan_um_is_ready; #ifdef CONFIG_STATIC_LINK diff --git a/arch/um/include/asm/mmu.h b/arch/um/include/asm/mmu.h index a7555e43ed14..f2923c767bb9 100644 --- a/arch/um/include/asm/mmu.h +++ b/arch/um/include/asm/mmu.h @@ -14,8 +14,6 @@ typedef struct mm_context { struct uml_arch_mm_context arch; } mm_context_t; -extern void __switch_mm(struct mm_id * mm_idp); - /* Avoid tangled inclusion with asm/ldt.h */ extern long init_new_ldt(struct mm_context *to_mm, struct mm_context *from_mm); extern void free_ldt(struct mm_context *mm); diff --git a/arch/um/include/asm/processor-generic.h b/arch/um/include/asm/processor-generic.h index 6c3779541845..5a7c05275aa7 100644 --- a/arch/um/include/asm/processor-generic.h +++ b/arch/um/include/asm/processor-generic.h @@ -94,7 +94,6 @@ extern struct cpuinfo_um boot_cpu_data; #define current_cpu_data boot_cpu_data #define cache_line_size() (boot_cpu_data.cache_alignment) -extern unsigned long get_thread_reg(int reg, jmp_buf *buf); #define KSTK_REG(tsk, reg) get_thread_reg(reg, &tsk->thread.switch_buf) extern unsigned long __get_wchan(struct task_struct *p); diff --git a/arch/um/include/asm/ptrace-generic.h b/arch/um/include/asm/ptrace-generic.h index adf91ef553ae..4696f24d1492 100644 --- a/arch/um/include/asm/ptrace-generic.h +++ b/arch/um/include/asm/ptrace-generic.h @@ -36,6 +36,9 @@ extern long subarch_ptrace(struct task_struct *child, long request, extern unsigned long getreg(struct task_struct *child, int regno); extern int putreg(struct task_struct *child, int regno, unsigned long value); +extern int poke_user(struct task_struct *child, long addr, long data); +extern int peek_user(struct task_struct *child, long addr, long data); + extern int arch_set_tls(struct task_struct *new, unsigned long tls); extern void clear_flushed_tls(struct task_struct *task); extern int syscall_trace_enter(struct pt_regs *regs); diff --git a/arch/um/include/shared/as-layout.h b/arch/um/include/shared/as-layout.h index 9ec3015bc5e2..c22f46a757dc 100644 --- a/arch/um/include/shared/as-layout.h +++ b/arch/um/include/shared/as-layout.h @@ -31,7 +31,6 @@ #include <sysdep/ptrace.h> struct cpu_task { - int pid; void *task; }; diff --git a/arch/um/include/shared/kern_util.h b/arch/um/include/shared/kern_util.h index 789b83013f35..95521b1f5b20 100644 --- a/arch/um/include/shared/kern_util.h +++ b/arch/um/include/shared/kern_util.h @@ -41,6 +41,7 @@ extern void uml_pm_wake(void); extern int start_uml(void); extern void paging_init(void); +extern int parse_iomem(char *str, int *add); extern void uml_cleanup(void); extern void do_uml_exitcalls(void); @@ -66,4 +67,6 @@ extern void fatal_sigsegv(void) __attribute__ ((noreturn)); void um_idle_sleep(void); +void kasan_map_memory(void *start, size_t len); + #endif diff --git a/arch/um/include/shared/skas/mm_id.h b/arch/um/include/shared/skas/mm_id.h index e82e203f5f41..92dbf727e384 100644 --- a/arch/um/include/shared/skas/mm_id.h +++ b/arch/um/include/shared/skas/mm_id.h @@ -15,4 +15,6 @@ struct mm_id { int kill; }; +void __switch_mm(struct mm_id *mm_idp); + #endif diff --git a/arch/um/include/shared/um_malloc.h b/arch/um/include/shared/um_malloc.h index bf503658f08e..815dd03e8707 100644 --- a/arch/um/include/shared/um_malloc.h +++ b/arch/um/include/shared/um_malloc.h @@ -13,7 +13,7 @@ extern void kfree(const void *ptr); extern void *vmalloc_noprof(unsigned long size); #define vmalloc(...) vmalloc_noprof(__VA_ARGS__) -extern void vfree(void *ptr); +extern void vfree(const void *ptr); #endif /* __UM_MALLOC_H__ */ diff --git a/arch/um/kernel/kmsg_dump.c b/arch/um/kernel/kmsg_dump.c index 427dd5a61a38..4382cf02a6d1 100644 --- a/arch/um/kernel/kmsg_dump.c +++ b/arch/um/kernel/kmsg_dump.c @@ -57,7 +57,7 @@ static struct kmsg_dumper kmsg_dumper = { .dump = kmsg_dumper_stdout }; -int __init kmsg_dumper_stdout_init(void) +static int __init kmsg_dumper_stdout_init(void) { return kmsg_dump_register(&kmsg_dumper); } diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index 38d5a71a579b..ca91accd64fc 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -12,12 +12,14 @@ #include <linux/slab.h> #include <asm/fixmap.h> #include <asm/page.h> +#include <asm/pgalloc.h> #include <as-layout.h> #include <init.h> #include <kern.h> #include <kern_util.h> #include <mem_user.h> #include <os.h> +#include <um_malloc.h> #include <linux/sched/task.h> #ifdef CONFIG_KASAN diff --git a/arch/um/kernel/physmem.c b/arch/um/kernel/physmem.c index 91485119ae67..fb2adfb49945 100644 --- a/arch/um/kernel/physmem.c +++ b/arch/um/kernel/physmem.c @@ -12,6 +12,7 @@ #include <as-layout.h> #include <init.h> #include <kern.h> +#include <kern_util.h> #include <mem_user.h> #include <os.h> @@ -161,8 +162,6 @@ __uml_setup("mem=", uml_mem_setup, " Example: mem=64M\n\n" ); -extern int __init parse_iomem(char *str, int *add); - __uml_setup("iomem=", parse_iomem, "iomem=<name>,<file>\n" " Configure <file> as an IO memory region named <name>.\n\n" diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index ab95648e93e1..d2134802f6a8 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -15,6 +15,7 @@ #include <linux/proc_fs.h> #include <linux/ptrace.h> #include <linux/random.h> +#include <linux/cpu.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/sched/debug.h> @@ -26,6 +27,8 @@ #include <linux/resume_user_mode.h> #include <asm/current.h> #include <asm/mmu_context.h> +#include <asm/switch_to.h> +#include <asm/exec.h> #include <linux/uaccess.h> #include <as-layout.h> #include <kern_util.h> @@ -40,24 +43,7 @@ * cares about its entry, so it's OK if another processor is modifying its * entry. */ -struct cpu_task cpu_tasks[NR_CPUS] = { [0 ... NR_CPUS - 1] = { -1, NULL } }; - -static inline int external_pid(void) -{ - /* FIXME: Need to look up userspace_pid by cpu */ - return userspace_pid[0]; -} - -int pid_to_processor_id(int pid) -{ - int i; - - for (i = 0; i < ncpus; i++) { - if (cpu_tasks[i].pid == pid) - return i; - } - return -1; -} +struct cpu_task cpu_tasks[NR_CPUS] = { [0 ... NR_CPUS - 1] = { NULL } }; void free_stack(unsigned long stack, int order) { @@ -78,13 +64,10 @@ unsigned long alloc_stack(int order, int atomic) static inline void set_current(struct task_struct *task) { - cpu_tasks[task_thread_info(task)->cpu] = ((struct cpu_task) - { external_pid(), task }); + cpu_tasks[task_thread_info(task)->cpu] = ((struct cpu_task) { task }); } -extern void arch_switch_to(struct task_struct *to); - -void *__switch_to(struct task_struct *from, struct task_struct *to) +struct task_struct *__switch_to(struct task_struct *from, struct task_struct *to) { to->thread.prev_sched = from; set_current(to); @@ -119,7 +102,7 @@ int get_current_pid(void) */ void new_thread_handler(void) { - int (*fn)(void *), n; + int (*fn)(void *); void *arg; if (current->thread.prev_sched != NULL) @@ -132,12 +115,12 @@ void new_thread_handler(void) /* * callback returns only if the kernel thread execs a process */ - n = fn(arg); + fn(arg); userspace(¤t->thread.regs.regs, current_thread_info()->aux_fp_regs); } /* Called magically, see new_thread_handler above */ -void fork_handler(void) +static void fork_handler(void) { force_flush_all(); @@ -216,7 +199,6 @@ void um_idle_sleep(void) void arch_cpu_idle(void) { - cpu_tasks[current_thread_info()->cpu].pid = os_getpid(); um_idle_sleep(); } @@ -250,32 +232,22 @@ char *uml_strdup(const char *string) } EXPORT_SYMBOL(uml_strdup); -int copy_to_user_proc(void __user *to, void *from, int size) -{ - return copy_to_user(to, from, size); -} - int copy_from_user_proc(void *to, void __user *from, int size) { return copy_from_user(to, from, size); } -int clear_user_proc(void __user *buf, int size) -{ - return clear_user(buf, size); -} - static atomic_t using_sysemu = ATOMIC_INIT(0); int sysemu_supported; -void set_using_sysemu(int value) +static void set_using_sysemu(int value) { if (value > sysemu_supported) return; atomic_set(&using_sysemu, value); } -int get_using_sysemu(void) +static int get_using_sysemu(void) { return atomic_read(&using_sysemu); } @@ -313,7 +285,7 @@ static const struct proc_ops sysemu_proc_ops = { .proc_write = sysemu_proc_write, }; -int __init make_proc_sysemu(void) +static int __init make_proc_sysemu(void) { struct proc_dir_entry *ent; if (!sysemu_supported) diff --git a/arch/um/kernel/ptrace.c b/arch/um/kernel/ptrace.c index 6600a2782796..2124624b7817 100644 --- a/arch/um/kernel/ptrace.c +++ b/arch/um/kernel/ptrace.c @@ -35,9 +35,6 @@ void ptrace_disable(struct task_struct *child) user_disable_single_step(child); } -extern int peek_user(struct task_struct * child, long addr, long data); -extern int poke_user(struct task_struct * child, long addr, long data); - long arch_ptrace(struct task_struct *child, long request, unsigned long addr, unsigned long data) { diff --git a/arch/um/kernel/reboot.c b/arch/um/kernel/reboot.c index 48c0610d506e..25840eee1068 100644 --- a/arch/um/kernel/reboot.c +++ b/arch/um/kernel/reboot.c @@ -9,6 +9,7 @@ #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/oom.h> +#include <linux/reboot.h> #include <kern_util.h> #include <os.h> #include <skas.h> diff --git a/arch/um/kernel/skas/mmu.c b/arch/um/kernel/skas/mmu.c index 656fe16c9b63..aeed1c2aaf3c 100644 --- a/arch/um/kernel/skas/mmu.c +++ b/arch/um/kernel/skas/mmu.c @@ -10,6 +10,7 @@ #include <asm/pgalloc.h> #include <asm/sections.h> +#include <asm/mmu_context.h> #include <as-layout.h> #include <os.h> #include <skas.h> diff --git a/arch/um/kernel/skas/process.c b/arch/um/kernel/skas/process.c index f2ac134c9752..99a5cbb36083 100644 --- a/arch/um/kernel/skas/process.c +++ b/arch/um/kernel/skas/process.c @@ -12,17 +12,14 @@ #include <kern.h> #include <os.h> #include <skas.h> +#include <kern_util.h> extern void start_kernel(void); static int __init start_kernel_proc(void *unused) { - int pid; - block_signals_trace(); - pid = os_getpid(); - cpu_tasks[0].pid = pid; cpu_tasks[0].task = current; start_kernel(); diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c index 3e270da6b6f6..a8bfe8be1526 100644 --- a/arch/um/kernel/time.c +++ b/arch/um/kernel/time.c @@ -19,6 +19,7 @@ #include <asm/param.h> #include <kern_util.h> #include <os.h> +#include <linux/delay.h> #include <linux/time-internal.h> #include <linux/um_timetravel.h> #include <shared/init.h> @@ -319,7 +320,7 @@ void time_travel_add_event_rel(struct time_travel_event *e, time_travel_add_event(e, time_travel_time + delay_ns); } -void time_travel_periodic_timer(struct time_travel_event *e) +static void time_travel_periodic_timer(struct time_travel_event *e) { time_travel_add_event(&time_travel_timer_event, time_travel_time + time_travel_timer_interval); @@ -812,7 +813,7 @@ unsigned long calibrate_delay_is_known(void) return 0; } -int setup_time_travel(char *str) +static int setup_time_travel(char *str) { if (strcmp(str, "=inf-cpu") == 0) { time_travel_mode = TT_MODE_INFCPU; @@ -862,7 +863,7 @@ __uml_help(setup_time_travel, "devices using it, assuming the device has the right capabilities.\n" "The optional ID is a 64-bit integer that's sent to the central scheduler.\n"); -int setup_time_travel_start(char *str) +static int setup_time_travel_start(char *str) { int err; diff --git a/arch/um/kernel/tlb.c b/arch/um/kernel/tlb.c index 7d050ab0f78a..8784f03fa4a6 100644 --- a/arch/um/kernel/tlb.c +++ b/arch/um/kernel/tlb.c @@ -8,6 +8,7 @@ #include <linux/sched/signal.h> #include <asm/tlbflush.h> +#include <asm/mmu_context.h> #include <as-layout.h> #include <mem_user.h> #include <os.h> @@ -576,12 +577,6 @@ void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, } EXPORT_SYMBOL(flush_tlb_range); -void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, - unsigned long end) -{ - fix_range(mm, start, end, 0); -} - void flush_tlb_mm(struct mm_struct *mm) { struct vm_area_struct *vma; diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 7a9820797eae..e95f805e5004 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -23,6 +23,7 @@ #include <asm/cpufeature.h> #include <asm/sections.h> #include <asm/setup.h> +#include <asm/text-patching.h> #include <as-layout.h> #include <arch.h> #include <init.h> diff --git a/arch/um/kernel/um_arch.h b/arch/um/kernel/um_arch.h index 1e07fb7ee35e..46e731ab9dfc 100644 --- a/arch/um/kernel/um_arch.h +++ b/arch/um/kernel/um_arch.h @@ -11,4 +11,6 @@ extern void __init uml_dtb_init(void); static inline void uml_dtb_init(void) { } #endif +extern int __init read_initrd(void); + #endif diff --git a/arch/um/os-Linux/drivers/ethertap_kern.c b/arch/um/os-Linux/drivers/ethertap_kern.c index 3182e759d8de..5e5ee40680ce 100644 --- a/arch/um/os-Linux/drivers/ethertap_kern.c +++ b/arch/um/os-Linux/drivers/ethertap_kern.c @@ -63,7 +63,7 @@ const struct net_kern_info ethertap_kern_info = { .write = etap_write, }; -int ethertap_setup(char *str, char **mac_out, void *data) +static int ethertap_setup(char *str, char **mac_out, void *data) { struct ethertap_init *init = data; diff --git a/arch/um/os-Linux/drivers/tuntap_kern.c b/arch/um/os-Linux/drivers/tuntap_kern.c index adcb6717be6f..ff022d9cf0dd 100644 --- a/arch/um/os-Linux/drivers/tuntap_kern.c +++ b/arch/um/os-Linux/drivers/tuntap_kern.c @@ -53,7 +53,7 @@ const struct net_kern_info tuntap_kern_info = { .write = tuntap_write, }; -int tuntap_setup(char *str, char **mac_out, void *data) +static int tuntap_setup(char *str, char **mac_out, void *data) { struct tuntap_init *init = data; diff --git a/arch/um/os-Linux/elf_aux.c b/arch/um/os-Linux/elf_aux.c index 344ac403fb5d..0a0f91cf4d6d 100644 --- a/arch/um/os-Linux/elf_aux.c +++ b/arch/um/os-Linux/elf_aux.c @@ -13,6 +13,7 @@ #include <init.h> #include <elf_user.h> #include <mem_user.h> +#include "internal.h" typedef Elf32_auxv_t elf_auxv_t; diff --git a/arch/um/os-Linux/internal.h b/arch/um/os-Linux/internal.h new file mode 100644 index 000000000000..317fca190c2b --- /dev/null +++ b/arch/um/os-Linux/internal.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __UM_OS_LINUX_INTERNAL_H +#define __UM_OS_LINUX_INTERNAL_H + +/* + * elf_aux.c + */ +void scan_elf_aux(char **envp); + +/* + * mem.c + */ +void check_tmpexec(void); + +/* + * skas/process.c + */ +void wait_stub_done(int pid); + +#endif /* __UM_OS_LINUX_INTERNAL_H */ diff --git a/arch/um/os-Linux/main.c b/arch/um/os-Linux/main.c index c8a42ecbd7a2..f98ff79cdbf7 100644 --- a/arch/um/os-Linux/main.c +++ b/arch/um/os-Linux/main.c @@ -16,6 +16,7 @@ #include <kern_util.h> #include <os.h> #include <um_malloc.h> +#include "internal.h" #define PGD_BOUND (4 * 1024 * 1024) #define STACKSIZE (8 * 1024 * 1024) @@ -102,8 +103,6 @@ static void setup_env_path(void) } } -extern void scan_elf_aux( char **envp); - int __init main(int argc, char **argv, char **envp) { char **new_argv; @@ -184,6 +183,11 @@ int __init main(int argc, char **argv, char **envp) extern void *__real_malloc(int); +/* workaround for -Wmissing-prototypes warnings */ +void *__wrap_malloc(int size); +void *__wrap_calloc(int n, int size); +void __wrap_free(void *ptr); + void *__wrap_malloc(int size) { void *ret; diff --git a/arch/um/os-Linux/mem.c b/arch/um/os-Linux/mem.c index 8530b2e08604..cf44d386f23c 100644 --- a/arch/um/os-Linux/mem.c +++ b/arch/um/os-Linux/mem.c @@ -15,7 +15,9 @@ #include <sys/vfs.h> #include <linux/magic.h> #include <init.h> +#include <kern_util.h> #include <os.h> +#include "internal.h" /* * kasan_map_memory - maps memory from @start with a size of @len. diff --git a/arch/um/os-Linux/signal.c b/arch/um/os-Linux/signal.c index 24a403a70a02..787cfb9a0308 100644 --- a/arch/um/os-Linux/signal.c +++ b/arch/um/os-Linux/signal.c @@ -72,7 +72,7 @@ static int signals_blocked; static unsigned int signals_pending; static unsigned int signals_active = 0; -void sig_handler(int sig, struct siginfo *si, mcontext_t *mc) +static void sig_handler(int sig, struct siginfo *si, mcontext_t *mc) { int enabled = signals_enabled; @@ -108,7 +108,7 @@ static void timer_real_alarm_handler(mcontext_t *mc) timer_handler(SIGALRM, NULL, ®s); } -void timer_alarm_handler(int sig, struct siginfo *unused_si, mcontext_t *mc) +static void timer_alarm_handler(int sig, struct siginfo *unused_si, mcontext_t *mc) { int enabled; diff --git a/arch/um/os-Linux/skas/mem.c b/arch/um/os-Linux/skas/mem.c index 953fb10f3f93..1f9c1bffc3a6 100644 --- a/arch/um/os-Linux/skas/mem.c +++ b/arch/um/os-Linux/skas/mem.c @@ -17,11 +17,10 @@ #include <skas.h> #include <sysdep/ptrace.h> #include <sysdep/stub.h> +#include "../internal.h" extern char batch_syscall_stub[], __syscall_stub_start[]; -extern void wait_stub_done(int pid); - static inline unsigned long *check_init_stack(struct mm_id * mm_idp, unsigned long *stack) { diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c index 1f5c3f2523d1..41a288dcfc34 100644 --- a/arch/um/os-Linux/skas/process.c +++ b/arch/um/os-Linux/skas/process.c @@ -23,6 +23,7 @@ #include <skas.h> #include <sysdep/stub.h> #include <linux/threads.h> +#include "../internal.h" int is_skas_winch(int pid, int fd, void *data) { diff --git a/arch/um/os-Linux/start_up.c b/arch/um/os-Linux/start_up.c index 8b0e98ab842c..89ad9f4f865c 100644 --- a/arch/um/os-Linux/start_up.c +++ b/arch/um/os-Linux/start_up.c @@ -20,10 +20,12 @@ #include <asm/unistd.h> #include <init.h> #include <os.h> +#include <kern_util.h> #include <mem_user.h> #include <ptrace_user.h> #include <registers.h> #include <skas.h> +#include "internal.h" static void ptrace_child(void) { @@ -221,8 +223,6 @@ static void __init check_ptrace(void) check_sysemu(); } -extern void check_tmpexec(void); - static void __init check_coredump_limit(void) { struct rlimit lim; diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index c5d614d28a75..74777a97e394 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -248,6 +248,7 @@ config UNWINDER_ORC config UNWINDER_FRAME_POINTER bool "Frame pointer unwinder" + select ARCH_WANT_FRAME_POINTERS select FRAME_POINTER help This option enables the frame pointer unwinder for unwinding kernel @@ -271,7 +272,3 @@ config UNWINDER_GUESS overhead. endchoice - -config FRAME_POINTER - depends on !UNWINDER_ORC && !UNWINDER_GUESS - bool diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 5b25d2a58aeb..ef031655b2d3 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -1223,14 +1223,14 @@ DEFINE_XTS_ALG(vaes_avx10_512, "xts-aes-vaes-avx10_512", 800); * implementation with ymm registers (256-bit vectors) will be used instead. */ static const struct x86_cpu_id zmm_exclusion_list[] = { - { .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_SKYLAKE_X }, - { .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_ICELAKE_X }, - { .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_ICELAKE_D }, - { .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_ICELAKE }, - { .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_ICELAKE_L }, - { .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_ICELAKE_NNPI }, - { .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_TIGERLAKE_L }, - { .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_TIGERLAKE }, + X86_MATCH_VFM(INTEL_SKYLAKE_X, 0), + X86_MATCH_VFM(INTEL_ICELAKE_X, 0), + X86_MATCH_VFM(INTEL_ICELAKE_D, 0), + X86_MATCH_VFM(INTEL_ICELAKE, 0), + X86_MATCH_VFM(INTEL_ICELAKE_L, 0), + X86_MATCH_VFM(INTEL_ICELAKE_NNPI, 0), + X86_MATCH_VFM(INTEL_TIGERLAKE_L, 0), + X86_MATCH_VFM(INTEL_TIGERLAKE, 0), /* Allow Rocket Lake and later, and Sapphire Rapids and later. */ /* Also allow AMD CPUs (starting with Zen 4, the first with AVX-512). */ {}, diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 5f8591ce7f25..7fd1f57ad3d3 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -466,3 +466,4 @@ 459 i386 lsm_get_self_attr sys_lsm_get_self_attr 460 i386 lsm_set_self_attr sys_lsm_set_self_attr 461 i386 lsm_list_modules sys_lsm_list_modules +462 i386 mseal sys_mseal diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index cc78226ffc35..a396f6e6ab5b 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -383,6 +383,7 @@ 459 common lsm_get_self_attr sys_lsm_get_self_attr 460 common lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal # # Due to a historical design error, certain syscalls are numbered differently diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h index 970a232009c3..b6325ee30871 100644 --- a/arch/x86/include/asm/cpu_device_id.h +++ b/arch/x86/include/asm/cpu_device_id.h @@ -53,6 +53,9 @@ #define X86_CENTAUR_FAM6_C7_D 0xd #define X86_CENTAUR_FAM6_NANO 0xf +/* x86_cpu_id::flags */ +#define X86_CPU_ID_FLAG_ENTRY_VALID BIT(0) + #define X86_STEPPINGS(mins, maxs) GENMASK(maxs, mins) /** * X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE - Base macro for CPU matching @@ -79,6 +82,7 @@ .model = _model, \ .steppings = _steppings, \ .feature = _feature, \ + .flags = X86_CPU_ID_FLAG_ENTRY_VALID, \ .driver_data = (unsigned long) _data \ } @@ -89,6 +93,7 @@ .model = _model, \ .steppings = _steppings, \ .feature = _feature, \ + .flags = X86_CPU_ID_FLAG_ENTRY_VALID, \ .driver_data = (unsigned long) _data \ } diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 9eec52925fa3..557318145038 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -1035,7 +1035,8 @@ static void __vector_schedule_cleanup(struct apic_chip_data *apicd) add_timer_on(&cl->timer, cpu); } } else { - apicd->prev_vector = 0; + pr_warn("IRQ %u schedule cleanup for offline CPU %u\n", apicd->irq, cpu); + free_moved_vector(apicd); } raw_spin_unlock(&vector_lock); } @@ -1072,6 +1073,7 @@ void irq_complete_move(struct irq_cfg *cfg) */ void irq_force_complete_move(struct irq_desc *desc) { + unsigned int cpu = smp_processor_id(); struct apic_chip_data *apicd; struct irq_data *irqd; unsigned int vector; @@ -1096,10 +1098,11 @@ void irq_force_complete_move(struct irq_desc *desc) goto unlock; /* - * If prev_vector is empty, no action required. + * If prev_vector is empty or the descriptor is neither currently + * nor previously on the outgoing CPU no action required. */ vector = apicd->prev_vector; - if (!vector) + if (!vector || (apicd->cpu != cpu && apicd->prev_cpu != cpu)) goto unlock; /* diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c index 8651643bddae..8e7de733320a 100644 --- a/arch/x86/kernel/cpu/match.c +++ b/arch/x86/kernel/cpu/match.c @@ -38,9 +38,7 @@ const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match) const struct x86_cpu_id *m; struct cpuinfo_x86 *c = &boot_cpu_data; - for (m = match; - m->vendor | m->family | m->model | m->steppings | m->feature; - m++) { + for (m = match; m->flags & X86_CPU_ID_FLAG_ENTRY_VALID; m++) { if (m->vendor != X86_VENDOR_ANY && c->x86_vendor != m->vendor) continue; if (m->family != X86_FAMILY_ANY && c->x86 != m->family) diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index d17c9b71eb4a..621a151ccf7d 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -128,6 +128,9 @@ static void topo_set_cpuids(unsigned int cpu, u32 apic_id, u32 acpi_id) static __init bool check_for_real_bsp(u32 apic_id) { + bool is_bsp = false, has_apic_base = boot_cpu_data.x86 >= 6; + u64 msr; + /* * There is no real good way to detect whether this a kdump() * kernel, but except on the Voyager SMP monstrosity which is not @@ -144,17 +147,61 @@ static __init bool check_for_real_bsp(u32 apic_id) if (topo_info.real_bsp_apic_id != BAD_APICID) return false; + /* + * Check whether the enumeration order is broken by evaluating the + * BSP bit in the APICBASE MSR. If the CPU does not have the + * APICBASE MSR then the BSP detection is not possible and the + * kernel must rely on the firmware enumeration order. + */ + if (has_apic_base) { + rdmsrl(MSR_IA32_APICBASE, msr); + is_bsp = !!(msr & MSR_IA32_APICBASE_BSP); + } + if (apic_id == topo_info.boot_cpu_apic_id) { - topo_info.real_bsp_apic_id = apic_id; - return false; + /* + * If the boot CPU has the APIC BSP bit set then the + * firmware enumeration is agreeing. If the CPU does not + * have the APICBASE MSR then the only choice is to trust + * the enumeration order. + */ + if (is_bsp || !has_apic_base) { + topo_info.real_bsp_apic_id = apic_id; + return false; + } + /* + * If the boot APIC is enumerated first, but the APICBASE + * MSR does not have the BSP bit set, then there is no way + * to discover the real BSP here. Assume a crash kernel and + * limit the number of CPUs to 1 as an INIT to the real BSP + * would reset the machine. + */ + pr_warn("Enumerated BSP APIC %x is not marked in APICBASE MSR\n", apic_id); + pr_warn("Assuming crash kernel. Limiting to one CPU to prevent machine INIT\n"); + set_nr_cpu_ids(1); + goto fwbug; } - pr_warn("Boot CPU APIC ID not the first enumerated APIC ID: %x > %x\n", + pr_warn("Boot CPU APIC ID not the first enumerated APIC ID: %x != %x\n", topo_info.boot_cpu_apic_id, apic_id); + + if (is_bsp) { + /* + * The boot CPU has the APIC BSP bit set. Use it and complain + * about the broken firmware enumeration. + */ + topo_info.real_bsp_apic_id = topo_info.boot_cpu_apic_id; + goto fwbug; + } + pr_warn("Crash kernel detected. Disabling real BSP to prevent machine INIT\n"); topo_info.real_bsp_apic_id = apic_id; return true; + +fwbug: + pr_warn(FW_BUG "APIC enumeration order not specification compliant\n"); + return false; } static unsigned int topo_unit_count(u32 lvlid, enum x86_topology_domains at_level, diff --git a/arch/x86/um/asm/ptrace.h b/arch/x86/um/asm/ptrace.h index 83822fd42204..2fef3da55533 100644 --- a/arch/x86/um/asm/ptrace.h +++ b/arch/x86/um/asm/ptrace.h @@ -54,6 +54,8 @@ extern int ptrace_get_thread_area(struct task_struct *child, int idx, extern int ptrace_set_thread_area(struct task_struct *child, int idx, struct user_desc __user *user_desc); +extern int arch_switch_tls(struct task_struct *to); + #else #define PT_REGS_R8(r) UPT_R8(&(r)->regs) @@ -83,5 +85,9 @@ extern long arch_prctl(struct task_struct *task, int option, unsigned long __user *addr); #endif + #define user_stack_pointer(regs) PT_REGS_SP(regs) + +extern void arch_switch_to(struct task_struct *to); + #endif /* __UM_X86_PTRACE_H */ diff --git a/arch/x86/um/bugs_32.c b/arch/x86/um/bugs_32.c index 33daff4dade4..d29929efcc07 100644 --- a/arch/x86/um/bugs_32.c +++ b/arch/x86/um/bugs_32.c @@ -3,6 +3,7 @@ * Licensed under the GPL */ +#include <arch.h> #include <signal.h> #include <kern_util.h> #include <longjmp.h> diff --git a/arch/x86/um/bugs_64.c b/arch/x86/um/bugs_64.c index 8cc8256c698d..b01295e8a676 100644 --- a/arch/x86/um/bugs_64.c +++ b/arch/x86/um/bugs_64.c @@ -4,6 +4,7 @@ * Licensed under the GPL */ +#include <arch.h> #include <sysdep/ptrace.h> void arch_check_bugs(void) diff --git a/arch/x86/um/elfcore.c b/arch/x86/um/elfcore.c index 650cdbbdaf45..ef50662fc40d 100644 --- a/arch/x86/um/elfcore.c +++ b/arch/x86/um/elfcore.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/elf.h> +#include <linux/elfcore.h> #include <linux/coredump.h> #include <linux/fs.h> #include <linux/mm.h> diff --git a/arch/x86/um/fault.c b/arch/x86/um/fault.c index 84ac7f7b0257..0dde4d613a87 100644 --- a/arch/x86/um/fault.c +++ b/arch/x86/um/fault.c @@ -3,6 +3,7 @@ * Licensed under the GPL */ +#include <arch.h> #include <sysdep/ptrace.h> /* These two are from asm-um/uaccess.h and linux/module.h, check them. */ diff --git a/arch/x86/um/os-Linux/mcontext.c b/arch/x86/um/os-Linux/mcontext.c index 49c3744cac37..e80ab7d28117 100644 --- a/arch/x86/um/os-Linux/mcontext.c +++ b/arch/x86/um/os-Linux/mcontext.c @@ -3,6 +3,7 @@ #define __FRAME_OFFSETS #include <asm/ptrace.h> #include <sysdep/ptrace.h> +#include <sysdep/mcontext.h> void get_regs_from_mc(struct uml_pt_regs *regs, mcontext_t *mc) { diff --git a/arch/x86/um/os-Linux/registers.c b/arch/x86/um/os-Linux/registers.c index df8f4b4bf98b..f3638dd09cec 100644 --- a/arch/x86/um/os-Linux/registers.c +++ b/arch/x86/um/os-Linux/registers.c @@ -17,7 +17,7 @@ #include <linux/elf.h> #include <registers.h> -int have_xstate_support; +static int have_xstate_support; int save_i387_registers(int pid, unsigned long *fp_regs) { diff --git a/arch/x86/um/os-Linux/tls.c b/arch/x86/um/os-Linux/tls.c index 3e1b1bf6acbc..eed9efe29ade 100644 --- a/arch/x86/um/os-Linux/tls.c +++ b/arch/x86/um/os-Linux/tls.c @@ -6,6 +6,7 @@ #include <sys/syscall.h> #include <unistd.h> +#include <os.h> #include <sysdep/tls.h> #ifndef PTRACE_GET_THREAD_AREA diff --git a/arch/x86/um/ptrace_32.c b/arch/x86/um/ptrace_32.c index 7f1abde2c84b..b0a71c6cdc6e 100644 --- a/arch/x86/um/ptrace_32.c +++ b/arch/x86/um/ptrace_32.c @@ -10,8 +10,6 @@ #include <registers.h> #include <skas.h> -extern int arch_switch_tls(struct task_struct *to); - void arch_switch_to(struct task_struct *to) { int err = arch_switch_tls(to); diff --git a/arch/x86/um/shared/sysdep/archsetjmp.h b/arch/x86/um/shared/sysdep/archsetjmp.h index 166cedbab926..8c81d1a604a9 100644 --- a/arch/x86/um/shared/sysdep/archsetjmp.h +++ b/arch/x86/um/shared/sysdep/archsetjmp.h @@ -1,6 +1,13 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __X86_UM_SYSDEP_ARCHSETJMP_H +#define __X86_UM_SYSDEP_ARCHSETJMP_H + #ifdef __i386__ #include "archsetjmp_32.h" #else #include "archsetjmp_64.h" #endif + +unsigned long get_thread_reg(int reg, jmp_buf *buf); + +#endif /* __X86_UM_SYSDEP_ARCHSETJMP_H */ diff --git a/arch/x86/um/shared/sysdep/kernel-offsets.h b/arch/x86/um/shared/sysdep/kernel-offsets.h index a004bffb7b8d..48de3a71f845 100644 --- a/arch/x86/um/shared/sysdep/kernel-offsets.h +++ b/arch/x86/um/shared/sysdep/kernel-offsets.h @@ -6,6 +6,9 @@ #include <linux/kbuild.h> #include <asm/mman.h> +/* workaround for a warning with -Wmissing-prototypes */ +void foo(void); + void foo(void) { #include <common-offsets.h> diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c index 263e1d08f216..2cc8c2309022 100644 --- a/arch/x86/um/signal.c +++ b/arch/x86/um/signal.c @@ -8,6 +8,7 @@ #include <linux/personality.h> #include <linux/ptrace.h> #include <linux/kernel.h> +#include <linux/syscalls.h> #include <asm/unistd.h> #include <linux/uaccess.h> #include <asm/ucontext.h> @@ -155,7 +156,7 @@ static int copy_sc_from_user(struct pt_regs *regs, struct sigcontext __user *from) { struct sigcontext sc; - int err, pid; + int err; /* Always make any pending restarted system calls return -EINTR */ current->restart_block.fn = do_no_restart_syscall; @@ -201,10 +202,10 @@ static int copy_sc_from_user(struct pt_regs *regs, #undef GETREG - pid = userspace_pid[current_thread_info()->cpu]; #ifdef CONFIG_X86_32 if (have_fpx_regs) { struct user_fxsr_struct fpx; + int pid = userspace_pid[current_thread_info()->cpu]; err = copy_from_user(&fpx, &((struct _fpstate __user *)sc.fpstate)->_fxsr_env[0], @@ -240,7 +241,7 @@ static int copy_sc_to_user(struct sigcontext __user *to, { struct sigcontext sc; struct faultinfo * fi = ¤t->thread.arch.faultinfo; - int err, pid; + int err; memset(&sc, 0, sizeof(struct sigcontext)); #define PUTREG(regno, regname) sc.regname = regs->regs.gp[HOST_##regno] @@ -288,10 +289,9 @@ static int copy_sc_to_user(struct sigcontext __user *to, if (err) return 1; - pid = userspace_pid[current_thread_info()->cpu]; - #ifdef CONFIG_X86_32 if (have_fpx_regs) { + int pid = userspace_pid[current_thread_info()->cpu]; struct user_fxsr_struct fpx; err = save_fpx_registers(pid, (unsigned long *) &fpx); @@ -450,7 +450,7 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig, return 0; } -long sys_sigreturn(void) +SYSCALL_DEFINE0(sigreturn) { unsigned long sp = PT_REGS_SP(¤t->thread.regs); struct sigframe __user *frame = (struct sigframe __user *)(sp - 8); @@ -557,7 +557,7 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig, } #endif -long sys_rt_sigreturn(void) +SYSCALL_DEFINE0(rt_sigreturn) { unsigned long sp = PT_REGS_SP(¤t->thread.regs); struct rt_sigframe __user *frame = diff --git a/arch/x86/um/tls_32.c b/arch/x86/um/tls_32.c index 66162eafd8e8..d301deee041f 100644 --- a/arch/x86/um/tls_32.c +++ b/arch/x86/um/tls_32.c @@ -20,7 +20,7 @@ static int host_supports_tls = -1; int host_gdt_entry_tls_min; -int do_set_thread_area(struct user_desc *info) +static int do_set_thread_area(struct user_desc *info) { int ret; u32 cpu; @@ -36,22 +36,6 @@ int do_set_thread_area(struct user_desc *info) return ret; } -int do_get_thread_area(struct user_desc *info) -{ - int ret; - u32 cpu; - - cpu = get_cpu(); - ret = os_get_thread_area(info, userspace_pid[cpu]); - put_cpu(); - - if (ret) - printk(KERN_ERR "PTRACE_GET_THREAD_AREA failed, err = %d, " - "index = %d\n", ret, info->entry_number); - - return ret; -} - /* * sys_get_thread_area: get a yet unused TLS descriptor index. * XXX: Consider leaving one free slot for glibc usage at first place. This must @@ -231,7 +215,6 @@ out: return ret; } -/* XXX: use do_get_thread_area to read the host value? I'm not at all sure! */ static int get_tls_entry(struct task_struct *task, struct user_desc *info, int idx) { diff --git a/arch/x86/um/user-offsets.c b/arch/x86/um/user-offsets.c index e54a9814ccf1..1c77d9946199 100644 --- a/arch/x86/um/user-offsets.c +++ b/arch/x86/um/user-offsets.c @@ -14,6 +14,9 @@ COMMENT(#val " / sizeof(unsigned long)"); \ DEFINE(sym, val / sizeof(unsigned long)) +/* workaround for a warning with -Wmissing-prototypes */ +void foo(void); + void foo(void) { #ifdef __i386__ diff --git a/arch/x86/um/vdso/um_vdso.c b/arch/x86/um/vdso/um_vdso.c index ff0f3b4b6c45..cbae2584124f 100644 --- a/arch/x86/um/vdso/um_vdso.c +++ b/arch/x86/um/vdso/um_vdso.c @@ -13,6 +13,12 @@ #include <linux/getcpu.h> #include <asm/unistd.h> +/* workaround for -Wmissing-prototypes warnings */ +int __vdso_clock_gettime(clockid_t clock, struct __kernel_old_timespec *ts); +int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz); +__kernel_old_time_t __vdso_time(__kernel_old_time_t *t); +long __vdso_getcpu(unsigned int *cpu, unsigned int *node, struct getcpu_cache *unused); + int __vdso_clock_gettime(clockid_t clock, struct __kernel_old_timespec *ts) { long ret; @@ -54,7 +60,7 @@ __kernel_old_time_t __vdso_time(__kernel_old_time_t *t) __kernel_old_time_t time(__kernel_old_time_t *t) __attribute__((weak, alias("__vdso_time"))); long -__vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused) +__vdso_getcpu(unsigned int *cpu, unsigned int *node, struct getcpu_cache *unused) { /* * UML does not support SMP, we can cheat here. :) @@ -68,5 +74,5 @@ __vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused) return 0; } -long getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *tcache) +long getcpu(unsigned int *cpu, unsigned int *node, struct getcpu_cache *tcache) __attribute__((weak, alias("__vdso_getcpu"))); diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 5f3a69f6ec34..0305485edcd3 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -379,3 +379,36 @@ void __init xen_add_extra_mem(unsigned long start_pfn, unsigned long n_pfns) memblock_reserve(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns)); } + +#ifdef CONFIG_XEN_UNPOPULATED_ALLOC +int __init arch_xen_unpopulated_init(struct resource **res) +{ + unsigned int i; + + if (!xen_domain()) + return -ENODEV; + + /* Must be set strictly before calling xen_free_unpopulated_pages(). */ + *res = &iomem_resource; + + /* + * Initialize with pages from the extra memory regions (see + * arch/x86/xen/setup.c). + */ + for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { + unsigned int j; + + for (j = 0; j < xen_extra_mem[i].n_pfns; j++) { + struct page *pg = + pfn_to_page(xen_extra_mem[i].start_pfn + j); + + xen_free_unpopulated_pages(1, &pg); + } + + /* Zero so region is not also added to the balloon driver. */ + xen_extra_mem[i].n_pfns = 0; + } + + return 0; +} +#endif diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 9bdc3b656b2c..99918beccd80 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -555,7 +555,6 @@ int xen_alloc_p2m_entry(unsigned long pfn) /* Separately check the mid mfn level */ unsigned long missing_mfn; unsigned long mid_mfn_mfn; - unsigned long old_mfn; mid_mfn = alloc_p2m_page(); if (!mid_mfn) @@ -565,12 +564,12 @@ int xen_alloc_p2m_entry(unsigned long pfn) missing_mfn = virt_to_mfn(p2m_mid_missing_mfn); mid_mfn_mfn = virt_to_mfn(mid_mfn); - old_mfn = cmpxchg(top_mfn_p, missing_mfn, mid_mfn_mfn); - if (old_mfn != missing_mfn) { - free_p2m_page(mid_mfn); - mid_mfn = mfn_to_virt(old_mfn); - } else { + /* try_cmpxchg() updates missing_mfn on failure. */ + if (try_cmpxchg(top_mfn_p, &missing_mfn, mid_mfn_mfn)) { p2m_top_mfn_p[topidx] = mid_mfn; + } else { + free_p2m_page(mid_mfn); + mid_mfn = mfn_to_virt(missing_mfn); } } } else { diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl index dd116598fb25..67083fc1b2f5 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -432,3 +432,4 @@ 459 common lsm_get_self_attr sys_lsm_get_self_attr 460 common lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 4b1a35ab0ea4..37e6cc91d576 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -322,6 +322,7 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk, blkg->q = disk->queue; INIT_LIST_HEAD(&blkg->q_node); blkg->blkcg = blkcg; + blkg->iostat.blkg = blkg; #ifdef CONFIG_BLK_CGROUP_PUNT_BIO spin_lock_init(&blkg->async_bio_lock); bio_list_init(&blkg->async_bios); @@ -618,12 +619,45 @@ restart: spin_unlock_irq(&q->queue_lock); } +static void blkg_iostat_set(struct blkg_iostat *dst, struct blkg_iostat *src) +{ + int i; + + for (i = 0; i < BLKG_IOSTAT_NR; i++) { + dst->bytes[i] = src->bytes[i]; + dst->ios[i] = src->ios[i]; + } +} + +static void __blkg_clear_stat(struct blkg_iostat_set *bis) +{ + struct blkg_iostat cur = {0}; + unsigned long flags; + + flags = u64_stats_update_begin_irqsave(&bis->sync); + blkg_iostat_set(&bis->cur, &cur); + blkg_iostat_set(&bis->last, &cur); + u64_stats_update_end_irqrestore(&bis->sync, flags); +} + +static void blkg_clear_stat(struct blkcg_gq *blkg) +{ + int cpu; + + for_each_possible_cpu(cpu) { + struct blkg_iostat_set *s = per_cpu_ptr(blkg->iostat_cpu, cpu); + + __blkg_clear_stat(s); + } + __blkg_clear_stat(&blkg->iostat); +} + static int blkcg_reset_stats(struct cgroup_subsys_state *css, struct cftype *cftype, u64 val) { struct blkcg *blkcg = css_to_blkcg(css); struct blkcg_gq *blkg; - int i, cpu; + int i; mutex_lock(&blkcg_pol_mutex); spin_lock_irq(&blkcg->lock); @@ -634,18 +668,7 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css, * anyway. If you get hit by a race, retry. */ hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) { - for_each_possible_cpu(cpu) { - struct blkg_iostat_set *bis = - per_cpu_ptr(blkg->iostat_cpu, cpu); - memset(bis, 0, sizeof(*bis)); - - /* Re-initialize the cleared blkg_iostat_set */ - u64_stats_init(&bis->sync); - bis->blkg = blkg; - } - memset(&blkg->iostat, 0, sizeof(blkg->iostat)); - u64_stats_init(&blkg->iostat.sync); - + blkg_clear_stat(blkg); for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; @@ -948,16 +971,6 @@ void blkg_conf_exit(struct blkg_conf_ctx *ctx) } EXPORT_SYMBOL_GPL(blkg_conf_exit); -static void blkg_iostat_set(struct blkg_iostat *dst, struct blkg_iostat *src) -{ - int i; - - for (i = 0; i < BLKG_IOSTAT_NR; i++) { - dst->bytes[i] = src->bytes[i]; - dst->ios[i] = src->ios[i]; - } -} - static void blkg_iostat_add(struct blkg_iostat *dst, struct blkg_iostat *src) { int i; @@ -1023,7 +1036,19 @@ static void __blkcg_rstat_flush(struct blkcg *blkcg, int cpu) struct blkg_iostat cur; unsigned int seq; + /* + * Order assignment of `next_bisc` from `bisc->lnode.next` in + * llist_for_each_entry_safe and clearing `bisc->lqueued` for + * avoiding to assign `next_bisc` with new next pointer added + * in blk_cgroup_bio_start() in case of re-ordering. + * + * The pair barrier is implied in llist_add() in blk_cgroup_bio_start(). + */ + smp_mb(); + WRITE_ONCE(bisc->lqueued, false); + if (bisc == &blkg->iostat) + goto propagate_up; /* propagate up to parent only */ /* fetch the current per-cpu values */ do { @@ -1033,10 +1058,24 @@ static void __blkcg_rstat_flush(struct blkcg *blkcg, int cpu) blkcg_iostat_update(blkg, &cur, &bisc->last); +propagate_up: /* propagate global delta to parent (unless that's root) */ - if (parent && parent->parent) + if (parent && parent->parent) { blkcg_iostat_update(parent, &blkg->iostat.cur, &blkg->iostat.last); + /* + * Queue parent->iostat to its blkcg's lockless + * list to propagate up to the grandparent if the + * iostat hasn't been queued yet. + */ + if (!parent->iostat.lqueued) { + struct llist_head *plhead; + + plhead = per_cpu_ptr(parent->blkcg->lhead, cpu); + llist_add(&parent->iostat.lnode, plhead); + parent->iostat.lqueued = true; + } + } } raw_spin_unlock_irqrestore(&blkg_stat_lock, flags); out: diff --git a/block/blk-core.c b/block/blk-core.c index ea44b13af9af..82c3ae22d76d 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -615,9 +615,14 @@ static inline blk_status_t blk_check_zone_append(struct request_queue *q, static void __submit_bio(struct bio *bio) { + /* If plug is not used, add new plug here to cache nsecs time. */ + struct blk_plug plug; + if (unlikely(!blk_crypto_bio_prep(&bio))) return; + blk_start_plug(&plug); + if (!bdev_test_flag(bio->bi_bdev, BD_HAS_SUBMIT_BIO)) { blk_mq_submit_bio(bio); } else if (likely(bio_queue_enter(bio) == 0)) { @@ -626,6 +631,8 @@ static void __submit_bio(struct bio *bio) disk->fops->submit_bio(bio); blk_queue_exit(disk->queue); } + + blk_finish_plug(&plug); } /* @@ -650,13 +657,11 @@ static void __submit_bio(struct bio *bio) static void __submit_bio_noacct(struct bio *bio) { struct bio_list bio_list_on_stack[2]; - struct blk_plug plug; BUG_ON(bio->bi_next); bio_list_init(&bio_list_on_stack[0]); current->bio_list = bio_list_on_stack; - blk_start_plug(&plug); do { struct request_queue *q = bdev_get_queue(bio->bi_bdev); @@ -690,23 +695,19 @@ static void __submit_bio_noacct(struct bio *bio) bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]); } while ((bio = bio_list_pop(&bio_list_on_stack[0]))); - blk_finish_plug(&plug); current->bio_list = NULL; } static void __submit_bio_noacct_mq(struct bio *bio) { struct bio_list bio_list[2] = { }; - struct blk_plug plug; current->bio_list = bio_list; - blk_start_plug(&plug); do { __submit_bio(bio); } while ((bio = bio_list_pop(&bio_list[0]))); - blk_finish_plug(&plug); current->bio_list = NULL; } diff --git a/block/blk-mq.c b/block/blk-mq.c index fc364a226e95..3b4df8e5ac9e 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -3545,12 +3545,28 @@ static int blk_mq_hctx_notify_offline(unsigned int cpu, struct hlist_node *node) return 0; } +/* + * Check if one CPU is mapped to the specified hctx + * + * Isolated CPUs have been ruled out from hctx->cpumask, which is supposed + * to be used for scheduling kworker only. For other usage, please call this + * helper for checking if one CPU belongs to the specified hctx + */ +static bool blk_mq_cpu_mapped_to_hctx(unsigned int cpu, + const struct blk_mq_hw_ctx *hctx) +{ + struct blk_mq_hw_ctx *mapped_hctx = blk_mq_map_queue_type(hctx->queue, + hctx->type, cpu); + + return mapped_hctx == hctx; +} + static int blk_mq_hctx_notify_online(unsigned int cpu, struct hlist_node *node) { struct blk_mq_hw_ctx *hctx = hlist_entry_safe(node, struct blk_mq_hw_ctx, cpuhp_online); - if (cpumask_test_cpu(cpu, hctx->cpumask)) + if (blk_mq_cpu_mapped_to_hctx(cpu, hctx)) clear_bit(BLK_MQ_S_INACTIVE, &hctx->state); return 0; } @@ -3568,7 +3584,7 @@ static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node) enum hctx_type type; hctx = hlist_entry_safe(node, struct blk_mq_hw_ctx, cpuhp_dead); - if (!cpumask_test_cpu(cpu, hctx->cpumask)) + if (!blk_mq_cpu_mapped_to_hctx(cpu, hctx)) return 0; ctx = __blk_mq_get_ctx(hctx->queue, cpu); diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 80aaca18bfb0..0be180f9a789 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -39,11 +39,6 @@ struct latency_bucket { int samples; }; -struct avg_latency_bucket { - unsigned long latency; /* ns / 1024 */ - bool valid; -}; - struct throtl_data { /* service tree for active throtl groups */ diff --git a/block/t10-pi.c b/block/t10-pi.c index d90892fd6f2a..f4cc91156da1 100644 --- a/block/t10-pi.c +++ b/block/t10-pi.c @@ -495,5 +495,5 @@ const struct blk_integrity_profile ext_pi_type3_crc64 = { }; EXPORT_SYMBOL_GPL(ext_pi_type3_crc64); -MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("T10 Protection Information module"); MODULE_LICENSE("GPL"); diff --git a/drivers/accessibility/speakup/main.c b/drivers/accessibility/speakup/main.c index 736c2eb8c0f3..f677ad2177c2 100644 --- a/drivers/accessibility/speakup/main.c +++ b/drivers/accessibility/speakup/main.c @@ -574,7 +574,7 @@ static u_long get_word(struct vc_data *vc) } attr_ch = get_char(vc, (u_short *)tmp_pos, &spk_attr); buf[cnt++] = attr_ch; - while (tmpx < vc->vc_cols - 1 && cnt < sizeof(buf) - 1) { + while (tmpx < vc->vc_cols - 1 && cnt < ARRAY_SIZE(buf) - 1) { tmp_pos += 2; tmpx++; ch = get_char(vc, (u_short *)tmp_pos, &temp); diff --git a/drivers/base/regmap/regmap-kunit.c b/drivers/base/regmap/regmap-kunit.c index 9c5314785fc2..be32cd4e84da 100644 --- a/drivers/base/regmap/regmap-kunit.c +++ b/drivers/base/regmap/regmap-kunit.c @@ -609,12 +609,19 @@ static void stride(struct kunit *test) config.reg_stride = 2; config.num_reg_defaults = BLOCK_TEST_SIZE / 2; + /* + * Allow one extra register so that the read/written arrays + * are sized big enough to include an entry for the odd + * address past the final reg_default register. + */ + config.max_register = BLOCK_TEST_SIZE; + map = gen_regmap(test, &config, &data); KUNIT_ASSERT_FALSE(test, IS_ERR(map)); if (IS_ERR(map)) return; - /* Only even registers can be accessed, try both read and write */ + /* Only even addresses can be accessed, try both read and write */ for (i = 0; i < BLOCK_TEST_SIZE; i++) { data->read[i] = false; data->written[i] = false; diff --git a/drivers/block/brd.c b/drivers/block/brd.c index b900fe9e0030..558d8e670566 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -222,6 +222,23 @@ out: return err; } +static void brd_do_discard(struct brd_device *brd, sector_t sector, u32 size) +{ + sector_t aligned_sector = (sector + PAGE_SECTORS) & ~PAGE_SECTORS; + struct page *page; + + size -= (aligned_sector - sector) * SECTOR_SIZE; + xa_lock(&brd->brd_pages); + while (size >= PAGE_SIZE && aligned_sector < rd_size * 2) { + page = __xa_erase(&brd->brd_pages, aligned_sector >> PAGE_SECTORS_SHIFT); + if (page) + __free_page(page); + aligned_sector += PAGE_SECTORS; + size -= PAGE_SIZE; + } + xa_unlock(&brd->brd_pages); +} + static void brd_submit_bio(struct bio *bio) { struct brd_device *brd = bio->bi_bdev->bd_disk->private_data; @@ -229,6 +246,12 @@ static void brd_submit_bio(struct bio *bio) struct bio_vec bvec; struct bvec_iter iter; + if (unlikely(op_is_discard(bio->bi_opf))) { + brd_do_discard(brd, sector, bio->bi_iter.bi_size); + bio_endio(bio); + return; + } + bio_for_each_segment(bvec, bio, iter) { unsigned int len = bvec.bv_len; int err; @@ -309,6 +332,9 @@ static int brd_alloc(int i) * is harmless) */ .physical_block_size = PAGE_SIZE, + .max_hw_discard_sectors = UINT_MAX, + .max_discard_segments = 1, + .discard_granularity = PAGE_SIZE, }; list_for_each_entry(brd, &brd_devices, brd_list) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 9d4ec9273bf9..22a79a62cc4e 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -222,7 +222,7 @@ static ssize_t pid_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); - struct nbd_device *nbd = (struct nbd_device *)disk->private_data; + struct nbd_device *nbd = disk->private_data; return sprintf(buf, "%d\n", nbd->pid); } @@ -236,7 +236,7 @@ static ssize_t backend_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); - struct nbd_device *nbd = (struct nbd_device *)disk->private_data; + struct nbd_device *nbd = disk->private_data; return sprintf(buf, "%s\n", nbd->backend ?: ""); } @@ -588,7 +588,10 @@ static inline int was_interrupted(int result) return result == -ERESTARTSYS || result == -EINTR; } -/* always call with the tx_lock held */ +/* + * Returns BLK_STS_RESOURCE if the caller should retry after a delay. Returns + * -EAGAIN if the caller should requeue @cmd. Returns -EIO if sending failed. + */ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) { struct request *req = blk_mq_rq_from_pdu(cmd); @@ -598,13 +601,15 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) struct nbd_request request = {.magic = htonl(NBD_REQUEST_MAGIC)}; struct kvec iov = {.iov_base = &request, .iov_len = sizeof(request)}; struct iov_iter from; - unsigned long size = blk_rq_bytes(req); struct bio *bio; u64 handle; u32 type; u32 nbd_cmd_flags = 0; int sent = nsock->sent, skip = 0; + lockdep_assert_held(&cmd->lock); + lockdep_assert_held(&nsock->tx_lock); + iov_iter_kvec(&from, ITER_SOURCE, &iov, 1, sizeof(request)); type = req_to_nbd_cmd_type(req); @@ -644,7 +649,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) request.type = htonl(type | nbd_cmd_flags); if (type != NBD_CMD_FLUSH) { request.from = cpu_to_be64((u64)blk_rq_pos(req) << 9); - request.len = htonl(size); + request.len = htonl(blk_rq_bytes(req)); } handle = nbd_cmd_handle(cmd); request.cookie = cpu_to_be64(handle); @@ -669,7 +674,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) nsock->sent = sent; } set_bit(NBD_CMD_REQUEUED, &cmd->flags); - return BLK_STS_RESOURCE; + return (__force int)BLK_STS_RESOURCE; } dev_err_ratelimited(disk_to_dev(nbd->disk), "Send control failed (result %d)\n", result); @@ -710,7 +715,7 @@ send_pages: nsock->pending = req; nsock->sent = sent; set_bit(NBD_CMD_REQUEUED, &cmd->flags); - return BLK_STS_RESOURCE; + return (__force int)BLK_STS_RESOURCE; } dev_err(disk_to_dev(nbd->disk), "Send data failed (result %d)\n", @@ -1007,7 +1012,7 @@ static int wait_for_reconnect(struct nbd_device *nbd) return !test_bit(NBD_RT_DISCONNECTED, &config->runtime_flags); } -static int nbd_handle_cmd(struct nbd_cmd *cmd, int index) +static blk_status_t nbd_handle_cmd(struct nbd_cmd *cmd, int index) { struct request *req = blk_mq_rq_from_pdu(cmd); struct nbd_device *nbd = cmd->nbd; @@ -1015,18 +1020,20 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index) struct nbd_sock *nsock; int ret; + lockdep_assert_held(&cmd->lock); + config = nbd_get_config_unlocked(nbd); if (!config) { dev_err_ratelimited(disk_to_dev(nbd->disk), "Socks array is empty\n"); - return -EINVAL; + return BLK_STS_IOERR; } if (index >= config->num_connections) { dev_err_ratelimited(disk_to_dev(nbd->disk), "Attempted send on invalid socket\n"); nbd_config_put(nbd); - return -EINVAL; + return BLK_STS_IOERR; } cmd->status = BLK_STS_OK; again: @@ -1049,7 +1056,7 @@ again: */ sock_shutdown(nbd); nbd_config_put(nbd); - return -EIO; + return BLK_STS_IOERR; } goto again; } @@ -1062,7 +1069,7 @@ again: blk_mq_start_request(req); if (unlikely(nsock->pending && nsock->pending != req)) { nbd_requeue_cmd(cmd); - ret = 0; + ret = BLK_STS_OK; goto out; } /* @@ -1081,19 +1088,19 @@ again: "Request send failed, requeueing\n"); nbd_mark_nsock_dead(nbd, nsock, 1); nbd_requeue_cmd(cmd); - ret = 0; + ret = BLK_STS_OK; } out: mutex_unlock(&nsock->tx_lock); nbd_config_put(nbd); - return ret; + return ret < 0 ? BLK_STS_IOERR : (__force blk_status_t)ret; } static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { struct nbd_cmd *cmd = blk_mq_rq_to_pdu(bd->rq); - int ret; + blk_status_t ret; /* * Since we look at the bio's to send the request over the network we @@ -1113,10 +1120,6 @@ static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx, * appropriate. */ ret = nbd_handle_cmd(cmd, hctx->queue_num); - if (ret < 0) - ret = BLK_STS_IOERR; - else if (!ret) - ret = BLK_STS_OK; mutex_unlock(&cmd->lock); return ret; diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index 4005a8b685e8..eb023d267369 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -413,13 +413,25 @@ static int nullb_update_nr_hw_queues(struct nullb_device *dev, static int nullb_apply_submit_queues(struct nullb_device *dev, unsigned int submit_queues) { - return nullb_update_nr_hw_queues(dev, submit_queues, dev->poll_queues); + int ret; + + mutex_lock(&lock); + ret = nullb_update_nr_hw_queues(dev, submit_queues, dev->poll_queues); + mutex_unlock(&lock); + + return ret; } static int nullb_apply_poll_queues(struct nullb_device *dev, unsigned int poll_queues) { - return nullb_update_nr_hw_queues(dev, dev->submit_queues, poll_queues); + int ret; + + mutex_lock(&lock); + ret = nullb_update_nr_hw_queues(dev, dev->submit_queues, poll_queues); + mutex_unlock(&lock); + + return ret; } NULLB_DEVICE_ATTR(size, ulong, NULL); @@ -468,28 +480,31 @@ static ssize_t nullb_device_power_store(struct config_item *item, if (ret < 0) return ret; + ret = count; + mutex_lock(&lock); if (!dev->power && newp) { if (test_and_set_bit(NULLB_DEV_FL_UP, &dev->flags)) - return count; + goto out; + ret = null_add_dev(dev); if (ret) { clear_bit(NULLB_DEV_FL_UP, &dev->flags); - return ret; + goto out; } set_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags); dev->power = newp; } else if (dev->power && !newp) { if (test_and_clear_bit(NULLB_DEV_FL_UP, &dev->flags)) { - mutex_lock(&lock); dev->power = newp; null_del_dev(dev->nullb); - mutex_unlock(&lock); } clear_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags); } - return count; +out: + mutex_unlock(&lock); + return ret; } CONFIGFS_ATTR(nullb_device_, power); @@ -1218,7 +1233,7 @@ static int null_transfer(struct nullb *nullb, struct page *page, return err; } -static int null_handle_rq(struct nullb_cmd *cmd) +static blk_status_t null_handle_rq(struct nullb_cmd *cmd) { struct request *rq = blk_mq_rq_from_pdu(cmd); struct nullb *nullb = cmd->nq->dev->nullb; @@ -1932,15 +1947,12 @@ static int null_add_dev(struct nullb_device *dev) nullb->q->queuedata = nullb; blk_queue_flag_set(QUEUE_FLAG_NONROT, nullb->q); - mutex_lock(&lock); rv = ida_alloc(&nullb_indexes, GFP_KERNEL); - if (rv < 0) { - mutex_unlock(&lock); + if (rv < 0) goto out_cleanup_disk; - } + nullb->index = rv; dev->index = rv; - mutex_unlock(&lock); if (config_item_name(&dev->group.cg_item)) { /* Use configfs dir name as the device name */ @@ -1969,9 +1981,7 @@ static int null_add_dev(struct nullb_device *dev) if (rv) goto out_ida_free; - mutex_lock(&lock); list_add_tail(&nullb->list, &nullb_list); - mutex_unlock(&lock); pr_info("disk %s created\n", nullb->disk_name); @@ -2020,7 +2030,9 @@ static int null_create_dev(void) if (!dev) return -ENOMEM; + mutex_lock(&lock); ret = null_add_dev(dev); + mutex_unlock(&lock); if (ret) { null_free_dev(dev); return ret; diff --git a/drivers/block/null_blk/trace.h b/drivers/block/null_blk/trace.h index ef2d05d5f0df..82b8f6a5e5f0 100644 --- a/drivers/block/null_blk/trace.h +++ b/drivers/block/null_blk/trace.h @@ -36,7 +36,12 @@ TRACE_EVENT(nullb_zone_op, TP_ARGS(cmd, zone_no, zone_cond), TP_STRUCT__entry( __array(char, disk, DISK_NAME_LEN) - __field(enum req_op, op) + /* + * __field() uses is_signed_type(). is_signed_type() does not + * support bitwise types. Use __field_struct() instead because + * it does not use is_signed_type(). + */ + __field_struct(enum req_op, op) __field(unsigned int, zone_no) __field(unsigned int, zone_cond) ), diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 176657dce3e3..4e159948c912 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -2178,6 +2178,7 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd) .virt_boundary_mask = p->virt_boundary_mask, .max_segments = USHRT_MAX, .max_segment_size = UINT_MAX, + .dma_alignment = 3, }; struct gendisk *disk; int ret = -EINVAL; diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index a5e07270e0d4..20c90ebb3a3f 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -2358,7 +2358,7 @@ static int cdrom_ioctl_timed_media_change(struct cdrom_device_info *cdi, return -EFAULT; tmp_info.media_flags = 0; - if (tmp_info.last_media_change - cdi->last_media_change_ms < 0) + if (cdi->last_media_change_ms > tmp_info.last_media_change) tmp_info.media_flags |= MEDIA_CHANGED_FLAG; tmp_info.last_media_change = cdi->last_media_change_ms; diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c index f5c71a617a99..4084df65c9fa 100644 --- a/drivers/char/hw_random/core.c +++ b/drivers/char/hw_random/core.c @@ -64,19 +64,6 @@ static size_t rng_buffer_size(void) return RNG_BUFFER_SIZE; } -static void add_early_randomness(struct hwrng *rng) -{ - int bytes_read; - - mutex_lock(&reading_mutex); - bytes_read = rng_get_data(rng, rng_fillbuf, 32, 0); - mutex_unlock(&reading_mutex); - if (bytes_read > 0) { - size_t entropy = bytes_read * 8 * rng->quality / 1024; - add_hwgenerator_randomness(rng_fillbuf, bytes_read, entropy, false); - } -} - static inline void cleanup_rng(struct kref *kref) { struct hwrng *rng = container_of(kref, struct hwrng, ref); @@ -340,13 +327,12 @@ static ssize_t rng_current_store(struct device *dev, const char *buf, size_t len) { int err; - struct hwrng *rng, *old_rng, *new_rng; + struct hwrng *rng, *new_rng; err = mutex_lock_interruptible(&rng_mutex); if (err) return -ERESTARTSYS; - old_rng = current_rng; if (sysfs_streq(buf, "")) { err = enable_best_rng(); } else { @@ -362,11 +348,8 @@ static ssize_t rng_current_store(struct device *dev, new_rng = get_current_rng_nolock(); mutex_unlock(&rng_mutex); - if (new_rng) { - if (new_rng != old_rng) - add_early_randomness(new_rng); + if (new_rng) put_rng(new_rng); - } return err ? : len; } @@ -544,7 +527,6 @@ int hwrng_register(struct hwrng *rng) { int err = -EINVAL; struct hwrng *tmp; - bool is_new_current = false; if (!rng->name || (!rng->data_read && !rng->read)) goto out; @@ -573,25 +555,8 @@ int hwrng_register(struct hwrng *rng) err = set_current_rng(rng); if (err) goto out_unlock; - /* to use current_rng in add_early_randomness() we need - * to take a ref - */ - is_new_current = true; - kref_get(&rng->ref); } mutex_unlock(&rng_mutex); - if (is_new_current || !rng->init) { - /* - * Use a new device's input to add some randomness to - * the system. If this rng device isn't going to be - * used right away, its init function hasn't been - * called yet by set_current_rng(); so only use the - * randomness from devices that don't need an init callback - */ - add_early_randomness(rng); - } - if (is_new_current) - put_rng(rng); return 0; out_unlock: mutex_unlock(&rng_mutex); @@ -602,12 +567,11 @@ EXPORT_SYMBOL_GPL(hwrng_register); void hwrng_unregister(struct hwrng *rng) { - struct hwrng *old_rng, *new_rng; + struct hwrng *new_rng; int err; mutex_lock(&rng_mutex); - old_rng = current_rng; list_del(&rng->list); complete_all(&rng->dying); if (current_rng == rng) { @@ -626,11 +590,8 @@ void hwrng_unregister(struct hwrng *rng) } else mutex_unlock(&rng_mutex); - if (new_rng) { - if (old_rng != new_rng) - add_early_randomness(new_rng); + if (new_rng) put_rng(new_rng); - } wait_for_completion(&rng->cleanup_done); } diff --git a/drivers/char/ipmi/Makefile b/drivers/char/ipmi/Makefile index cb6138b8ded9..e0944547c9d0 100644 --- a/drivers/char/ipmi/Makefile +++ b/drivers/char/ipmi/Makefile @@ -5,13 +5,10 @@ ipmi_si-y := ipmi_si_intf.o ipmi_kcs_sm.o ipmi_smic_sm.o ipmi_bt_sm.o \ ipmi_si_hotmod.o ipmi_si_hardcode.o ipmi_si_platform.o \ - ipmi_si_port_io.o ipmi_si_mem_io.o -ifdef CONFIG_PCI -ipmi_si-y += ipmi_si_pci.o -endif -ifdef CONFIG_PARISC -ipmi_si-y += ipmi_si_parisc.o -endif + ipmi_si_mem_io.o +ipmi_si-$(CONFIG_HAS_IOPORT) += ipmi_si_port_io.o +ipmi_si-$(CONFIG_PCI) += ipmi_si_pci.o +ipmi_si-$(CONFIG_PARISC) += ipmi_si_parisc.o obj-$(CONFIG_IPMI_HANDLER) += ipmi_msghandler.o obj-$(CONFIG_IPMI_DEVICE_INTERFACE) += ipmi_devintf.o diff --git a/drivers/char/ipmi/bt-bmc.c b/drivers/char/ipmi/bt-bmc.c index 7450904e330a..b8b9c07d3b5d 100644 --- a/drivers/char/ipmi/bt-bmc.c +++ b/drivers/char/ipmi/bt-bmc.c @@ -459,14 +459,13 @@ static int bt_bmc_probe(struct platform_device *pdev) return 0; } -static int bt_bmc_remove(struct platform_device *pdev) +static void bt_bmc_remove(struct platform_device *pdev) { struct bt_bmc *bt_bmc = dev_get_drvdata(&pdev->dev); misc_deregister(&bt_bmc->miscdev); if (bt_bmc->irq < 0) del_timer_sync(&bt_bmc->poll_timer); - return 0; } static const struct of_device_id bt_bmc_match[] = { @@ -482,7 +481,7 @@ static struct platform_driver bt_bmc_driver = { .of_match_table = bt_bmc_match, }, .probe = bt_bmc_probe, - .remove = bt_bmc_remove, + .remove_new = bt_bmc_remove, }; module_platform_driver(bt_bmc_driver); diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index b0eedc4595b3..e12b531f5c2f 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -41,7 +41,7 @@ static struct ipmi_recv_msg *ipmi_alloc_recv_msg(void); static int ipmi_init_msghandler(void); -static void smi_recv_tasklet(struct tasklet_struct *t); +static void smi_recv_work(struct work_struct *t); static void handle_new_recv_msgs(struct ipmi_smi *intf); static void need_waiter(struct ipmi_smi *intf); static int handle_one_recv_msg(struct ipmi_smi *intf, @@ -498,13 +498,13 @@ struct ipmi_smi { /* * Messages queued for delivery. If delivery fails (out of memory * for instance), They will stay in here to be processed later in a - * periodic timer interrupt. The tasklet is for handling received + * periodic timer interrupt. The workqueue is for handling received * messages directly from the handler. */ spinlock_t waiting_rcv_msgs_lock; struct list_head waiting_rcv_msgs; atomic_t watchdog_pretimeouts_to_deliver; - struct tasklet_struct recv_tasklet; + struct work_struct recv_work; spinlock_t xmit_msgs_lock; struct list_head xmit_msgs; @@ -704,7 +704,7 @@ static void clean_up_interface_data(struct ipmi_smi *intf) struct cmd_rcvr *rcvr, *rcvr2; struct list_head list; - tasklet_kill(&intf->recv_tasklet); + cancel_work_sync(&intf->recv_work); free_smi_msg_list(&intf->waiting_rcv_msgs); free_recv_msg_list(&intf->waiting_events); @@ -1319,7 +1319,7 @@ static void free_user(struct kref *ref) { struct ipmi_user *user = container_of(ref, struct ipmi_user, refcount); - /* SRCU cleanup must happen in task context. */ + /* SRCU cleanup must happen in workqueue context. */ queue_work(remove_work_wq, &user->remove_work); } @@ -3605,8 +3605,7 @@ int ipmi_add_smi(struct module *owner, intf->curr_seq = 0; spin_lock_init(&intf->waiting_rcv_msgs_lock); INIT_LIST_HEAD(&intf->waiting_rcv_msgs); - tasklet_setup(&intf->recv_tasklet, - smi_recv_tasklet); + INIT_WORK(&intf->recv_work, smi_recv_work); atomic_set(&intf->watchdog_pretimeouts_to_deliver, 0); spin_lock_init(&intf->xmit_msgs_lock); INIT_LIST_HEAD(&intf->xmit_msgs); @@ -4779,7 +4778,7 @@ static void handle_new_recv_msgs(struct ipmi_smi *intf) * To preserve message order, quit if we * can't handle a message. Add the message * back at the head, this is safe because this - * tasklet is the only thing that pulls the + * workqueue is the only thing that pulls the * messages. */ list_add(&smi_msg->link, &intf->waiting_rcv_msgs); @@ -4812,10 +4811,10 @@ static void handle_new_recv_msgs(struct ipmi_smi *intf) } } -static void smi_recv_tasklet(struct tasklet_struct *t) +static void smi_recv_work(struct work_struct *t) { unsigned long flags = 0; /* keep us warning-free. */ - struct ipmi_smi *intf = from_tasklet(intf, t, recv_tasklet); + struct ipmi_smi *intf = from_work(intf, t, recv_work); int run_to_completion = intf->run_to_completion; struct ipmi_smi_msg *newmsg = NULL; @@ -4866,7 +4865,7 @@ void ipmi_smi_msg_received(struct ipmi_smi *intf, /* * To preserve message order, we keep a queue and deliver from - * a tasklet. + * a workqueue. */ if (!run_to_completion) spin_lock_irqsave(&intf->waiting_rcv_msgs_lock, flags); @@ -4887,9 +4886,9 @@ void ipmi_smi_msg_received(struct ipmi_smi *intf, spin_unlock_irqrestore(&intf->xmit_msgs_lock, flags); if (run_to_completion) - smi_recv_tasklet(&intf->recv_tasklet); + smi_recv_work(&intf->recv_work); else - tasklet_schedule(&intf->recv_tasklet); + queue_work(system_bh_wq, &intf->recv_work); } EXPORT_SYMBOL(ipmi_smi_msg_received); @@ -4899,7 +4898,7 @@ void ipmi_smi_watchdog_pretimeout(struct ipmi_smi *intf) return; atomic_set(&intf->watchdog_pretimeouts_to_deliver, 1); - tasklet_schedule(&intf->recv_tasklet); + queue_work(system_bh_wq, &intf->recv_work); } EXPORT_SYMBOL(ipmi_smi_watchdog_pretimeout); @@ -5068,7 +5067,7 @@ static bool ipmi_timeout_handler(struct ipmi_smi *intf, flags); } - tasklet_schedule(&intf->recv_tasklet); + queue_work(system_bh_wq, &intf->recv_work); return need_timer; } diff --git a/drivers/char/ipmi/ipmi_powernv.c b/drivers/char/ipmi/ipmi_powernv.c index da22a8cbe68e..c59a86eb58c7 100644 --- a/drivers/char/ipmi/ipmi_powernv.c +++ b/drivers/char/ipmi/ipmi_powernv.c @@ -281,15 +281,13 @@ err_free: return rc; } -static int ipmi_powernv_remove(struct platform_device *pdev) +static void ipmi_powernv_remove(struct platform_device *pdev) { struct ipmi_smi_powernv *smi = dev_get_drvdata(&pdev->dev); ipmi_unregister_smi(smi->intf); free_irq(smi->irq, smi); irq_dispose_mapping(smi->irq); - - return 0; } static const struct of_device_id ipmi_powernv_match[] = { @@ -304,7 +302,7 @@ static struct platform_driver powernv_ipmi_driver = { .of_match_table = ipmi_powernv_match, }, .probe = ipmi_powernv_probe, - .remove = ipmi_powernv_remove, + .remove_new = ipmi_powernv_remove, }; diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c index 5cd031f3fc97..eea23a3b966e 100644 --- a/drivers/char/ipmi/ipmi_si_intf.c +++ b/drivers/char/ipmi/ipmi_si_intf.c @@ -1882,7 +1882,8 @@ int ipmi_si_add_smi(struct si_sm_io *io) } if (!io->io_setup) { - if (io->addr_space == IPMI_IO_ADDR_SPACE) { + if (IS_ENABLED(CONFIG_HAS_IOPORT) && + io->addr_space == IPMI_IO_ADDR_SPACE) { io->io_setup = ipmi_si_port_setup; } else if (io->addr_space == IPMI_MEM_ADDR_SPACE) { io->io_setup = ipmi_si_mem_setup; diff --git a/drivers/char/ipmi/ipmi_si_pci.c b/drivers/char/ipmi/ipmi_si_pci.c index 74fa2055868b..b83d55685b22 100644 --- a/drivers/char/ipmi/ipmi_si_pci.c +++ b/drivers/char/ipmi/ipmi_si_pci.c @@ -97,6 +97,9 @@ static int ipmi_pci_probe(struct pci_dev *pdev, } if (pci_resource_flags(pdev, 0) & IORESOURCE_IO) { + if (!IS_ENABLED(CONFIG_HAS_IOPORT)) + return -ENXIO; + io.addr_space = IPMI_IO_ADDR_SPACE; io.io_setup = ipmi_si_port_setup; } else { diff --git a/drivers/char/ipmi/ipmi_si_platform.c b/drivers/char/ipmi/ipmi_si_platform.c index cd2edd8f8a03..96ba85648120 100644 --- a/drivers/char/ipmi/ipmi_si_platform.c +++ b/drivers/char/ipmi/ipmi_si_platform.c @@ -405,11 +405,9 @@ static int ipmi_probe(struct platform_device *pdev) return platform_ipmi_probe(pdev); } -static int ipmi_remove(struct platform_device *pdev) +static void ipmi_remove(struct platform_device *pdev) { ipmi_si_remove_by_dev(&pdev->dev); - - return 0; } static int pdev_match_name(struct device *dev, const void *data) @@ -447,7 +445,7 @@ struct platform_driver ipmi_platform_driver = { .acpi_match_table = ACPI_PTR(acpi_ipmi_match), }, .probe = ipmi_probe, - .remove = ipmi_remove, + .remove_new = ipmi_remove, .id_table = si_plat_ids }; diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c index 1f7600c361e6..3f509a22217b 100644 --- a/drivers/char/ipmi/ipmi_ssif.c +++ b/drivers/char/ipmi/ipmi_ssif.c @@ -2071,7 +2071,7 @@ static int ssif_platform_probe(struct platform_device *dev) return dmi_ipmi_probe(dev); } -static int ssif_platform_remove(struct platform_device *dev) +static void ssif_platform_remove(struct platform_device *dev) { struct ssif_addr_info *addr_info = dev_get_drvdata(&dev->dev); @@ -2079,7 +2079,6 @@ static int ssif_platform_remove(struct platform_device *dev) list_del(&addr_info->link); kfree(addr_info); mutex_unlock(&ssif_infos_mutex); - return 0; } static const struct platform_device_id ssif_plat_ids[] = { @@ -2092,7 +2091,7 @@ static struct platform_driver ipmi_driver = { .name = DEVICE_NAME, }, .probe = ssif_platform_probe, - .remove = ssif_platform_remove, + .remove_new = ssif_platform_remove, .id_table = ssif_plat_ids }; diff --git a/drivers/char/ipmi/kcs_bmc_aspeed.c b/drivers/char/ipmi/kcs_bmc_aspeed.c index 72640da55380..227bf06c7ca4 100644 --- a/drivers/char/ipmi/kcs_bmc_aspeed.c +++ b/drivers/char/ipmi/kcs_bmc_aspeed.c @@ -641,7 +641,7 @@ static int aspeed_kcs_probe(struct platform_device *pdev) return 0; } -static int aspeed_kcs_remove(struct platform_device *pdev) +static void aspeed_kcs_remove(struct platform_device *pdev) { struct aspeed_kcs_bmc *priv = platform_get_drvdata(pdev); struct kcs_bmc_device *kcs_bmc = &priv->kcs_bmc; @@ -656,8 +656,6 @@ static int aspeed_kcs_remove(struct platform_device *pdev) priv->obe.remove = true; spin_unlock_irq(&priv->obe.lock); del_timer_sync(&priv->obe.timer); - - return 0; } static const struct of_device_id ast_kcs_bmc_match[] = { @@ -674,7 +672,7 @@ static struct platform_driver ast_kcs_bmc_driver = { .of_match_table = ast_kcs_bmc_match, }, .probe = aspeed_kcs_probe, - .remove = aspeed_kcs_remove, + .remove_new = aspeed_kcs_remove, }; module_platform_driver(ast_kcs_bmc_driver); diff --git a/drivers/char/ipmi/kcs_bmc_npcm7xx.c b/drivers/char/ipmi/kcs_bmc_npcm7xx.c index 7961fec56476..07710198233a 100644 --- a/drivers/char/ipmi/kcs_bmc_npcm7xx.c +++ b/drivers/char/ipmi/kcs_bmc_npcm7xx.c @@ -218,7 +218,7 @@ static int npcm7xx_kcs_probe(struct platform_device *pdev) return 0; } -static int npcm7xx_kcs_remove(struct platform_device *pdev) +static void npcm7xx_kcs_remove(struct platform_device *pdev) { struct npcm7xx_kcs_bmc *priv = platform_get_drvdata(pdev); struct kcs_bmc_device *kcs_bmc = &priv->kcs_bmc; @@ -227,8 +227,6 @@ static int npcm7xx_kcs_remove(struct platform_device *pdev) npcm7xx_kcs_enable_channel(kcs_bmc, false); npcm7xx_kcs_irq_mask_update(kcs_bmc, (KCS_BMC_EVENT_TYPE_IBF | KCS_BMC_EVENT_TYPE_OBE), 0); - - return 0; } static const struct of_device_id npcm_kcs_bmc_match[] = { @@ -243,7 +241,7 @@ static struct platform_driver npcm_kcs_bmc_driver = { .of_match_table = npcm_kcs_bmc_match, }, .probe = npcm7xx_kcs_probe, - .remove = npcm7xx_kcs_remove, + .remove_new = npcm7xx_kcs_remove, }; module_platform_driver(npcm_kcs_bmc_driver); diff --git a/drivers/char/tpm/Kconfig b/drivers/char/tpm/Kconfig index e63a6a17793c..cf0be8a7939d 100644 --- a/drivers/char/tpm/Kconfig +++ b/drivers/char/tpm/Kconfig @@ -29,7 +29,7 @@ if TCG_TPM config TCG_TPM2_HMAC bool "Use HMAC and encrypted transactions on the TPM bus" - default y + default X86_64 select CRYPTO_ECDH select CRYPTO_LIB_AESCFB select CRYPTO_LIB_SHA256 diff --git a/drivers/char/tpm/tpm-buf.c b/drivers/char/tpm/tpm-buf.c index 647c6ca92ac3..cad0048bcc3c 100644 --- a/drivers/char/tpm/tpm-buf.c +++ b/drivers/char/tpm/tpm-buf.c @@ -223,30 +223,4 @@ u32 tpm_buf_read_u32(struct tpm_buf *buf, off_t *offset) } EXPORT_SYMBOL_GPL(tpm_buf_read_u32); -static u16 tpm_buf_tag(struct tpm_buf *buf) -{ - struct tpm_header *head = (struct tpm_header *)buf->data; - - return be16_to_cpu(head->tag); -} - -/** - * tpm_buf_parameters - return the TPM response parameters area of the tpm_buf - * @buf: tpm_buf to use - * - * Where the parameters are located depends on the tag of a TPM - * command (it's immediately after the header for TPM_ST_NO_SESSIONS - * or 4 bytes after for TPM_ST_SESSIONS). Evaluate this and return a - * pointer to the first byte of the parameters area. - * - * @return: pointer to parameters area - */ -u8 *tpm_buf_parameters(struct tpm_buf *buf) -{ - int offset = TPM_HEADER_SIZE; - - if (tpm_buf_tag(buf) == TPM2_ST_SESSIONS) - offset += 4; - return &buf->data[offset]; -} diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c index 0cdf892ec2a7..1e856259219e 100644 --- a/drivers/char/tpm/tpm2-cmd.c +++ b/drivers/char/tpm/tpm2-cmd.c @@ -281,6 +281,7 @@ struct tpm2_get_random_out { int tpm2_get_random(struct tpm_chip *chip, u8 *dest, size_t max) { struct tpm2_get_random_out *out; + struct tpm_header *head; struct tpm_buf buf; u32 recd; u32 num_bytes = max; @@ -288,6 +289,7 @@ int tpm2_get_random(struct tpm_chip *chip, u8 *dest, size_t max) int total = 0; int retries = 5; u8 *dest_ptr = dest; + off_t offset; if (!num_bytes || max > TPM_MAX_RNG_DATA) return -EINVAL; @@ -320,7 +322,13 @@ int tpm2_get_random(struct tpm_chip *chip, u8 *dest, size_t max) goto out; } - out = (struct tpm2_get_random_out *)tpm_buf_parameters(&buf); + head = (struct tpm_header *)buf.data; + offset = TPM_HEADER_SIZE; + /* Skip the parameter size field: */ + if (be16_to_cpu(head->tag) == TPM2_ST_SESSIONS) + offset += 4; + + out = (struct tpm2_get_random_out *)&buf.data[offset]; recd = min_t(u32, be16_to_cpu(out->size), num_bytes); if (tpm_buf_length(&buf) < TPM_HEADER_SIZE + diff --git a/drivers/char/tpm/tpm2-sessions.c b/drivers/char/tpm/tpm2-sessions.c index ea8860661876..907ac9956a78 100644 --- a/drivers/char/tpm/tpm2-sessions.c +++ b/drivers/char/tpm/tpm2-sessions.c @@ -80,6 +80,9 @@ /* maximum number of names the TPM must remember for authorization */ #define AUTH_MAX_NAMES 3 +#define AES_KEY_BYTES AES_KEYSIZE_128 +#define AES_KEY_BITS (AES_KEY_BYTES*8) + static int tpm2_create_primary(struct tpm_chip *chip, u32 hierarchy, u32 *handle, u8 *name); @@ -954,6 +957,20 @@ int tpm2_start_auth_session(struct tpm_chip *chip) } EXPORT_SYMBOL(tpm2_start_auth_session); +/* + * A mask containing the object attributes for the kernel held null primary key + * used in HMAC encryption. For more information on specific attributes look up + * to "8.3 TPMA_OBJECT (Object Attributes)". + */ +#define TPM2_OA_NULL_KEY ( \ + TPM2_OA_NO_DA | \ + TPM2_OA_FIXED_TPM | \ + TPM2_OA_FIXED_PARENT | \ + TPM2_OA_SENSITIVE_DATA_ORIGIN | \ + TPM2_OA_USER_WITH_AUTH | \ + TPM2_OA_DECRYPT | \ + TPM2_OA_RESTRICTED) + /** * tpm2_parse_create_primary() - parse the data returned from TPM_CC_CREATE_PRIMARY * @@ -1018,7 +1035,7 @@ static int tpm2_parse_create_primary(struct tpm_chip *chip, struct tpm_buf *buf, val = tpm_buf_read_u32(buf, &offset_t); /* object properties */ - if (val != TPM2_OA_TMPL) + if (val != TPM2_OA_NULL_KEY) return -EINVAL; /* auth policy (empty) */ @@ -1178,7 +1195,7 @@ static int tpm2_create_primary(struct tpm_chip *chip, u32 hierarchy, tpm_buf_append_u16(&template, TPM_ALG_SHA256); /* object properties */ - tpm_buf_append_u32(&template, TPM2_OA_TMPL); + tpm_buf_append_u32(&template, TPM2_OA_NULL_KEY); /* sauth policy (empty) */ tpm_buf_append_u16(&template, 0); diff --git a/drivers/char/tpm/tpm_tis_spi_main.c b/drivers/char/tpm/tpm_tis_spi_main.c index 3f9eaf27b41b..c9eca24bbad4 100644 --- a/drivers/char/tpm/tpm_tis_spi_main.c +++ b/drivers/char/tpm/tpm_tis_spi_main.c @@ -37,6 +37,7 @@ #include "tpm_tis_spi.h" #define MAX_SPI_FRAMESIZE 64 +#define SPI_HDRSIZE 4 /* * TCG SPI flow control is documented in section 6.4 of the spec[1]. In short, @@ -247,7 +248,7 @@ static int tpm_tis_spi_write_bytes(struct tpm_tis_data *data, u32 addr, int tpm_tis_spi_init(struct spi_device *spi, struct tpm_tis_spi_phy *phy, int irq, const struct tpm_tis_phy_ops *phy_ops) { - phy->iobuf = devm_kmalloc(&spi->dev, MAX_SPI_FRAMESIZE, GFP_KERNEL); + phy->iobuf = devm_kmalloc(&spi->dev, SPI_HDRSIZE + MAX_SPI_FRAMESIZE, GFP_KERNEL); if (!phy->iobuf) return -ENOMEM; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c index 7ba05f030dd1..e3738d417245 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c @@ -455,6 +455,9 @@ void amdgpu_amdkfd_get_local_mem_info(struct amdgpu_device *adev, else mem_info->local_mem_size_private = KFD_XCP_MEMORY_SIZE(adev, xcp->id); + } else if (adev->flags & AMD_IS_APU) { + mem_info->local_mem_size_public = (ttm_tt_pages_limit() << PAGE_SHIFT); + mem_info->local_mem_size_private = 0; } else { mem_info->local_mem_size_public = adev->gmc.visible_vram_size; mem_info->local_mem_size_private = adev->gmc.real_vram_size - @@ -824,6 +827,8 @@ u64 amdgpu_amdkfd_xcp_memory_size(struct amdgpu_device *adev, int xcp_id) } do_div(tmp, adev->xcp_mgr->num_xcp_per_mem_partition); return ALIGN_DOWN(tmp, PAGE_SIZE); + } else if (adev->flags & AMD_IS_APU) { + return (ttm_tt_pages_limit() << PAGE_SHIFT); } else { return adev->gmc.real_vram_size; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index e4d4e55c08ad..8975cf41a91a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -196,7 +196,7 @@ int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev, return -EINVAL; vram_size = KFD_XCP_MEMORY_SIZE(adev, xcp_id); - if (adev->gmc.is_app_apu) { + if (adev->gmc.is_app_apu || adev->flags & AMD_IS_APU) { system_mem_needed = size; ttm_mem_needed = size; } @@ -232,7 +232,8 @@ int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev, "adev reference can't be null when vram is used"); if (adev && xcp_id >= 0) { adev->kfd.vram_used[xcp_id] += vram_needed; - adev->kfd.vram_used_aligned[xcp_id] += adev->gmc.is_app_apu ? + adev->kfd.vram_used_aligned[xcp_id] += + (adev->gmc.is_app_apu || adev->flags & AMD_IS_APU) ? vram_needed : ALIGN(vram_needed, VRAM_AVAILABLITY_ALIGN); } @@ -260,7 +261,7 @@ void amdgpu_amdkfd_unreserve_mem_limit(struct amdgpu_device *adev, if (adev) { adev->kfd.vram_used[xcp_id] -= size; - if (adev->gmc.is_app_apu) { + if (adev->gmc.is_app_apu || adev->flags & AMD_IS_APU) { adev->kfd.vram_used_aligned[xcp_id] -= size; kfd_mem_limit.system_mem_used -= size; kfd_mem_limit.ttm_mem_used -= size; @@ -889,7 +890,7 @@ static int kfd_mem_attach(struct amdgpu_device *adev, struct kgd_mem *mem, * if peer device has large BAR. In contrast, access over xGMI is * allowed for both small and large BAR configurations of peer device */ - if ((adev != bo_adev && !adev->gmc.is_app_apu) && + if ((adev != bo_adev && !(adev->gmc.is_app_apu || adev->flags & AMD_IS_APU)) && ((mem->domain == AMDGPU_GEM_DOMAIN_VRAM) || (mem->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_DOORBELL) || (mem->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP))) { @@ -1188,7 +1189,8 @@ static int reserve_bo_and_cond_vms(struct kgd_mem *mem, int ret; ctx->sync = &mem->sync; - drm_exec_init(&ctx->exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0); + drm_exec_init(&ctx->exec, DRM_EXEC_INTERRUPTIBLE_WAIT | + DRM_EXEC_IGNORE_DUPLICATES, 0); drm_exec_until_all_locked(&ctx->exec) { ctx->n_vms = 0; list_for_each_entry(entry, &mem->attachments, list) { @@ -1656,7 +1658,7 @@ size_t amdgpu_amdkfd_get_available_memory(struct amdgpu_device *adev, - atomic64_read(&adev->vram_pin_size) - reserved_for_pt; - if (adev->gmc.is_app_apu) { + if (adev->gmc.is_app_apu || adev->flags & AMD_IS_APU) { system_mem_available = no_system_mem_limit ? kfd_mem_limit.max_system_mem_limit : kfd_mem_limit.max_system_mem_limit - @@ -1704,7 +1706,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( if (flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM) { domain = alloc_domain = AMDGPU_GEM_DOMAIN_VRAM; - if (adev->gmc.is_app_apu) { + if (adev->gmc.is_app_apu || adev->flags & AMD_IS_APU) { domain = AMDGPU_GEM_DOMAIN_GTT; alloc_domain = AMDGPU_GEM_DOMAIN_GTT; alloc_flags = 0; @@ -1951,7 +1953,7 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu( if (size) { if (!is_imported && (mem->bo->preferred_domains == AMDGPU_GEM_DOMAIN_VRAM || - (adev->gmc.is_app_apu && + ((adev->gmc.is_app_apu || adev->flags & AMD_IS_APU) && mem->bo->preferred_domains == AMDGPU_GEM_DOMAIN_GTT))) *size = bo_size; else @@ -2373,8 +2375,9 @@ static int import_obj_create(struct amdgpu_device *adev, (*mem)->dmabuf = dma_buf; (*mem)->bo = bo; (*mem)->va = va; - (*mem)->domain = (bo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM) && !adev->gmc.is_app_apu ? - AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT; + (*mem)->domain = (bo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM) && + !(adev->gmc.is_app_apu || adev->flags & AMD_IS_APU) ? + AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT; (*mem)->mapped_to_gpu_memory = 0; (*mem)->process_info = avm->process_info; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c index a6d64bdbbb14..108003bdf1e9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c @@ -212,6 +212,7 @@ union igp_info { struct atom_integrated_system_info_v1_11 v11; struct atom_integrated_system_info_v1_12 v12; struct atom_integrated_system_info_v2_1 v21; + struct atom_integrated_system_info_v2_3 v23; }; union umc_info { @@ -360,6 +361,20 @@ amdgpu_atomfirmware_get_vram_info(struct amdgpu_device *adev, if (vram_type) *vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type); break; + case 3: + mem_channel_number = igp_info->v23.umachannelnumber; + if (!mem_channel_number) + mem_channel_number = 1; + mem_type = igp_info->v23.memorytype; + if (mem_type == LpDdr5MemType) + mem_channel_width = 32; + else + mem_channel_width = 64; + if (vram_width) + *vram_width = mem_channel_number * mem_channel_width; + if (vram_type) + *vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type); + break; default: return -EINVAL; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index 4bcfbeac48fb..4816fcb9803a 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -1023,7 +1023,7 @@ int kgd2kfd_init_zone_device(struct amdgpu_device *adev) if (amdgpu_ip_version(adev, GC_HWIP, 0) < IP_VERSION(9, 0, 1)) return -EINVAL; - if (adev->gmc.is_app_apu) + if (adev->gmc.is_app_apu || adev->flags & AMD_IS_APU) return 0; pgmap = &kfddev->pgmap; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 386875e6eb96..069b81eeea03 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -2619,7 +2619,8 @@ svm_range_best_restore_location(struct svm_range *prange, return -1; } - if (node->adev->gmc.is_app_apu) + if (node->adev->gmc.is_app_apu || + node->adev->flags & AMD_IS_APU) return 0; if (prange->preferred_loc == gpuid || @@ -3337,7 +3338,8 @@ svm_range_best_prefetch_location(struct svm_range *prange) goto out; } - if (bo_node->adev->gmc.is_app_apu) { + if (bo_node->adev->gmc.is_app_apu || + bo_node->adev->flags & AMD_IS_APU) { best_loc = 0; goto out; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h index 026863a0abcd..9c37bd0567ef 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h @@ -201,7 +201,8 @@ void svm_range_list_lock_and_flush_work(struct svm_range_list *svms, struct mm_s * is initialized to not 0 when page migration register device memory. */ #define KFD_IS_SVM_API_SUPPORTED(adev) ((adev)->kfd.pgmap.type != 0 ||\ - (adev)->gmc.is_app_apu) + (adev)->gmc.is_app_apu ||\ + ((adev)->flags & AMD_IS_APU)) void svm_range_bo_unref_async(struct svm_range_bo *svm_bo); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index c27063305a13..2c36f3d00ca2 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -363,7 +363,7 @@ void dm_helpers_dp_mst_send_payload_allocation( mst_state = to_drm_dp_mst_topology_state(mst_mgr->base.state); new_payload = drm_atomic_get_mst_payload_state(mst_state, aconnector->mst_output_port); - ret = drm_dp_add_payload_part2(mst_mgr, mst_state->base.state, new_payload); + ret = drm_dp_add_payload_part2(mst_mgr, new_payload); if (ret) { amdgpu_dm_set_mst_status(&aconnector->mst_status, diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h index af3eebb4c9bc..1acb2d2c5597 100644 --- a/drivers/gpu/drm/amd/include/atomfirmware.h +++ b/drivers/gpu/drm/amd/include/atomfirmware.h @@ -1657,6 +1657,49 @@ struct atom_integrated_system_info_v2_2 uint32_t reserved4[189]; }; +struct uma_carveout_option { + char optionName[29]; //max length of string is 28chars + '\0'. Current design is for "minimum", "Medium", "High". This makes entire struct size 64bits + uint8_t memoryCarvedGb; //memory carved out with setting + uint8_t memoryRemainingGb; //memory remaining on system + union { + struct _flags { + uint8_t Auto : 1; + uint8_t Custom : 1; + uint8_t Reserved : 6; + } flags; + uint8_t all8; + } uma_carveout_option_flags; +}; + +struct atom_integrated_system_info_v2_3 { + struct atom_common_table_header table_header; + uint32_t vbios_misc; // enum of atom_system_vbiosmisc_def + uint32_t gpucapinfo; // enum of atom_system_gpucapinf_def + uint32_t system_config; + uint32_t cpucapinfo; + uint16_t gpuclk_ss_percentage; // unit of 0.001%, 1000 mean 1% + uint16_t gpuclk_ss_type; + uint16_t dpphy_override; // bit vector, enum of atom_sysinfo_dpphy_override_def + uint8_t memorytype; // enum of atom_dmi_t17_mem_type_def, APU memory type indication. + uint8_t umachannelnumber; // number of memory channels + uint8_t htc_hyst_limit; + uint8_t htc_tmp_limit; + uint8_t reserved1; // dp_ss_control + uint8_t gpu_package_id; + struct edp_info_table edp1_info; + struct edp_info_table edp2_info; + uint32_t reserved2[8]; + struct atom_external_display_connection_info extdispconninfo; + uint8_t UMACarveoutVersion; + uint8_t UMACarveoutIndexMax; + uint8_t UMACarveoutTypeDefault; + uint8_t UMACarveoutIndexDefault; + uint8_t UMACarveoutType; //Auto or Custom + uint8_t UMACarveoutIndex; + struct uma_carveout_option UMASizeControlOption[20]; + uint8_t reserved3[110]; +}; + // system_config enum atom_system_vbiosmisc_def{ INTEGRATED_SYSTEM_INFO__GET_EDID_CALLBACK_FUNC_SUPPORT = 0x01, diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c index dd21b81bd28f..66ccb61e2a66 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c +++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c @@ -953,7 +953,8 @@ static int adv7511_bridge_attach(struct drm_bridge *bridge, int ret = 0; if (adv->next_bridge) { - ret = drm_bridge_attach(bridge->encoder, adv->next_bridge, bridge, flags); + ret = drm_bridge_attach(bridge->encoder, adv->next_bridge, bridge, + flags | DRM_BRIDGE_ATTACH_NO_CONNECTOR); if (ret) return ret; } diff --git a/drivers/gpu/drm/display/drm_dp_mst_topology.c b/drivers/gpu/drm/display/drm_dp_mst_topology.c index 3577786b5db2..7f8e1cfbe19d 100644 --- a/drivers/gpu/drm/display/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/display/drm_dp_mst_topology.c @@ -3421,7 +3421,6 @@ EXPORT_SYMBOL(drm_dp_remove_payload_part2); /** * drm_dp_add_payload_part2() - Execute payload update part 2 * @mgr: Manager to use. - * @state: The global atomic state * @payload: The payload to update * * If @payload was successfully assigned a starting time slot by drm_dp_add_payload_part1(), this @@ -3430,14 +3429,13 @@ EXPORT_SYMBOL(drm_dp_remove_payload_part2); * Returns: 0 on success, negative error code on failure. */ int drm_dp_add_payload_part2(struct drm_dp_mst_topology_mgr *mgr, - struct drm_atomic_state *state, struct drm_dp_mst_atomic_payload *payload) { int ret = 0; /* Skip failed payloads */ if (payload->payload_allocation_status != DRM_DP_MST_PAYLOAD_ALLOCATION_DFP) { - drm_dbg_kms(state->dev, "Part 1 of payload creation for %s failed, skipping part 2\n", + drm_dbg_kms(mgr->dev, "Part 1 of payload creation for %s failed, skipping part 2\n", payload->port->connector->name); return -EIO; } diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c index 1daf778cf6fa..94f8c34fc293 100644 --- a/drivers/gpu/drm/drm_buddy.c +++ b/drivers/gpu/drm/drm_buddy.c @@ -524,11 +524,11 @@ __alloc_range_bias(struct drm_buddy *mm, continue; } + if (!fallback && block_incompatible(block, flags)) + continue; + if (contains(start, end, block_start, block_end) && order == drm_buddy_block_order(block)) { - if (!fallback && block_incompatible(block, flags)) - continue; - /* * Find the free block within the range. */ diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c index c772ba19c547..715d2f59f565 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c @@ -1241,7 +1241,7 @@ static void intel_mst_enable_dp(struct intel_atomic_state *state, if (first_mst_stream) intel_ddi_wait_for_fec_status(encoder, pipe_config, true); - drm_dp_add_payload_part2(&intel_dp->mst_mgr, &state->base, + drm_dp_add_payload_part2(&intel_dp->mst_mgr, drm_atomic_get_mst_payload_state(mst_state, connector->port)); if (DISPLAY_VER(dev_priv) >= 12) diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 0c3d88ad0b0e..88728a0b2c25 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -915,7 +915,7 @@ nv50_msto_cleanup(struct drm_atomic_state *state, msto->disabled = false; drm_dp_remove_payload_part2(mgr, new_mst_state, old_payload, new_payload); } else if (msto->enabled) { - drm_dp_add_payload_part2(mgr, state, new_payload); + drm_dp_add_payload_part2(mgr, new_payload); msto->enabled = false; } } diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c index f465fe93b1f7..d56909071de6 100644 --- a/drivers/gpu/drm/nouveau/nouveau_abi16.c +++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c @@ -272,6 +272,9 @@ nouveau_abi16_ioctl_getparam(ABI16_IOCTL_ARGS) getparam->value = (u64)ttm_resource_manager_usage(vram_mgr); break; } + case NOUVEAU_GETPARAM_HAS_VMA_TILEMODE: + getparam->value = 1; + break; default: NV_PRINTK(dbg, cli, "unknown parameter %lld\n", getparam->param); return -EINVAL; diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 1e2d28fd10dc..70fb003a6666 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -241,28 +241,28 @@ nouveau_bo_alloc(struct nouveau_cli *cli, u64 *size, int *align, u32 domain, } nvbo->contig = !(tile_flags & NOUVEAU_GEM_TILE_NONCONTIG); - if (!nouveau_cli_uvmm(cli) || internal) { - /* for BO noVM allocs, don't assign kinds */ - if (cli->device.info.family >= NV_DEVICE_INFO_V0_FERMI) { - nvbo->kind = (tile_flags & 0x0000ff00) >> 8; - if (!nvif_mmu_kind_valid(mmu, nvbo->kind)) { - kfree(nvbo); - return ERR_PTR(-EINVAL); - } - nvbo->comp = mmu->kind[nvbo->kind] != nvbo->kind; - } else if (cli->device.info.family >= NV_DEVICE_INFO_V0_TESLA) { - nvbo->kind = (tile_flags & 0x00007f00) >> 8; - nvbo->comp = (tile_flags & 0x00030000) >> 16; - if (!nvif_mmu_kind_valid(mmu, nvbo->kind)) { - kfree(nvbo); - return ERR_PTR(-EINVAL); - } - } else { - nvbo->zeta = (tile_flags & 0x00000007); + if (cli->device.info.family >= NV_DEVICE_INFO_V0_FERMI) { + nvbo->kind = (tile_flags & 0x0000ff00) >> 8; + if (!nvif_mmu_kind_valid(mmu, nvbo->kind)) { + kfree(nvbo); + return ERR_PTR(-EINVAL); + } + + nvbo->comp = mmu->kind[nvbo->kind] != nvbo->kind; + } else if (cli->device.info.family >= NV_DEVICE_INFO_V0_TESLA) { + nvbo->kind = (tile_flags & 0x00007f00) >> 8; + nvbo->comp = (tile_flags & 0x00030000) >> 16; + if (!nvif_mmu_kind_valid(mmu, nvbo->kind)) { + kfree(nvbo); + return ERR_PTR(-EINVAL); } - nvbo->mode = tile_mode; + } else { + nvbo->zeta = (tile_flags & 0x00000007); + } + nvbo->mode = tile_mode; + if (!nouveau_cli_uvmm(cli) || internal) { /* Determine the desirable target GPU page size for the buffer. */ for (i = 0; i < vmm->page_nr; i++) { /* Because we cannot currently allow VMM maps to fail @@ -304,12 +304,6 @@ nouveau_bo_alloc(struct nouveau_cli *cli, u64 *size, int *align, u32 domain, } nvbo->page = vmm->page[pi].shift; } else { - /* reject other tile flags when in VM mode. */ - if (tile_mode) - return ERR_PTR(-EINVAL); - if (tile_flags & ~NOUVEAU_GEM_TILE_NONCONTIG) - return ERR_PTR(-EINVAL); - /* Determine the desirable target GPU page size for the buffer. */ for (i = 0; i < vmm->page_nr; i++) { /* Because we cannot currently allow VMM maps to fail diff --git a/drivers/gpu/drm/panthor/panthor_device.c b/drivers/gpu/drm/panthor/panthor_device.c index 75276cbeba20..4082c8f2951d 100644 --- a/drivers/gpu/drm/panthor/panthor_device.c +++ b/drivers/gpu/drm/panthor/panthor_device.c @@ -129,13 +129,8 @@ static void panthor_device_reset_work(struct work_struct *work) panthor_gpu_l2_power_on(ptdev); panthor_mmu_post_reset(ptdev); ret = panthor_fw_post_reset(ptdev); - if (ret) - goto out_dev_exit; - atomic_set(&ptdev->reset.pending, 0); - panthor_sched_post_reset(ptdev); - -out_dev_exit: + panthor_sched_post_reset(ptdev, ret != 0); drm_dev_exit(cookie); if (ret) { @@ -293,6 +288,7 @@ static const struct panthor_exception_info panthor_exception_infos[] = { PANTHOR_EXCEPTION(ACTIVE), PANTHOR_EXCEPTION(CS_RES_TERM), PANTHOR_EXCEPTION(CS_CONFIG_FAULT), + PANTHOR_EXCEPTION(CS_UNRECOVERABLE), PANTHOR_EXCEPTION(CS_ENDPOINT_FAULT), PANTHOR_EXCEPTION(CS_BUS_FAULT), PANTHOR_EXCEPTION(CS_INSTR_INVALID), diff --git a/drivers/gpu/drm/panthor/panthor_device.h b/drivers/gpu/drm/panthor/panthor_device.h index 2fdd671b38fd..e388c0472ba7 100644 --- a/drivers/gpu/drm/panthor/panthor_device.h +++ b/drivers/gpu/drm/panthor/panthor_device.h @@ -216,6 +216,7 @@ enum drm_panthor_exception_type { DRM_PANTHOR_EXCEPTION_CS_RES_TERM = 0x0f, DRM_PANTHOR_EXCEPTION_MAX_NON_FAULT = 0x3f, DRM_PANTHOR_EXCEPTION_CS_CONFIG_FAULT = 0x40, + DRM_PANTHOR_EXCEPTION_CS_UNRECOVERABLE = 0x41, DRM_PANTHOR_EXCEPTION_CS_ENDPOINT_FAULT = 0x44, DRM_PANTHOR_EXCEPTION_CS_BUS_FAULT = 0x48, DRM_PANTHOR_EXCEPTION_CS_INSTR_INVALID = 0x49, diff --git a/drivers/gpu/drm/panthor/panthor_fw.c b/drivers/gpu/drm/panthor/panthor_fw.c index fedf9627453f..857f3f11258a 100644 --- a/drivers/gpu/drm/panthor/panthor_fw.c +++ b/drivers/gpu/drm/panthor/panthor_fw.c @@ -453,7 +453,7 @@ panthor_fw_alloc_queue_iface_mem(struct panthor_device *ptdev, ret = panthor_kernel_bo_vmap(mem); if (ret) { - panthor_kernel_bo_destroy(panthor_fw_vm(ptdev), mem); + panthor_kernel_bo_destroy(mem); return ERR_PTR(ret); } @@ -1134,7 +1134,7 @@ void panthor_fw_unplug(struct panthor_device *ptdev) panthor_fw_stop(ptdev); list_for_each_entry(section, &ptdev->fw->sections, node) - panthor_kernel_bo_destroy(panthor_fw_vm(ptdev), section->mem); + panthor_kernel_bo_destroy(section->mem); /* We intentionally don't call panthor_vm_idle() and let * panthor_mmu_unplug() release the AS we acquired with @@ -1142,6 +1142,7 @@ void panthor_fw_unplug(struct panthor_device *ptdev) * state to keep the active_refcnt balanced. */ panthor_vm_put(ptdev->fw->vm); + ptdev->fw->vm = NULL; panthor_gpu_power_off(ptdev, L2, ptdev->gpu_info.l2_present, 20000); } diff --git a/drivers/gpu/drm/panthor/panthor_gem.c b/drivers/gpu/drm/panthor/panthor_gem.c index d6483266d0c2..38f560864879 100644 --- a/drivers/gpu/drm/panthor/panthor_gem.c +++ b/drivers/gpu/drm/panthor/panthor_gem.c @@ -26,18 +26,18 @@ static void panthor_gem_free_object(struct drm_gem_object *obj) /** * panthor_kernel_bo_destroy() - Destroy a kernel buffer object - * @vm: The VM this BO was mapped to. * @bo: Kernel buffer object to destroy. If NULL or an ERR_PTR(), the destruction * is skipped. */ -void panthor_kernel_bo_destroy(struct panthor_vm *vm, - struct panthor_kernel_bo *bo) +void panthor_kernel_bo_destroy(struct panthor_kernel_bo *bo) { + struct panthor_vm *vm; int ret; if (IS_ERR_OR_NULL(bo)) return; + vm = bo->vm; panthor_kernel_bo_vunmap(bo); if (drm_WARN_ON(bo->obj->dev, @@ -53,6 +53,7 @@ void panthor_kernel_bo_destroy(struct panthor_vm *vm, drm_gem_object_put(bo->obj); out_free_bo: + panthor_vm_put(vm); kfree(bo); } @@ -106,6 +107,7 @@ panthor_kernel_bo_create(struct panthor_device *ptdev, struct panthor_vm *vm, if (ret) goto err_free_va; + kbo->vm = panthor_vm_get(vm); bo->exclusive_vm_root_gem = panthor_vm_root_gem(vm); drm_gem_object_get(bo->exclusive_vm_root_gem); bo->base.base.resv = bo->exclusive_vm_root_gem->resv; diff --git a/drivers/gpu/drm/panthor/panthor_gem.h b/drivers/gpu/drm/panthor/panthor_gem.h index 3bccba394d00..e43021cf6d45 100644 --- a/drivers/gpu/drm/panthor/panthor_gem.h +++ b/drivers/gpu/drm/panthor/panthor_gem.h @@ -62,6 +62,11 @@ struct panthor_kernel_bo { struct drm_gem_object *obj; /** + * @vm: VM this private buffer is attached to. + */ + struct panthor_vm *vm; + + /** * @va_node: VA space allocated to this GEM. */ struct drm_mm_node va_node; @@ -136,7 +141,6 @@ panthor_kernel_bo_create(struct panthor_device *ptdev, struct panthor_vm *vm, size_t size, u32 bo_flags, u32 vm_map_flags, u64 gpu_va); -void panthor_kernel_bo_destroy(struct panthor_vm *vm, - struct panthor_kernel_bo *bo); +void panthor_kernel_bo_destroy(struct panthor_kernel_bo *bo); #endif /* __PANTHOR_GEM_H__ */ diff --git a/drivers/gpu/drm/panthor/panthor_heap.c b/drivers/gpu/drm/panthor/panthor_heap.c index 143fa35f2e74..3796a9eb22af 100644 --- a/drivers/gpu/drm/panthor/panthor_heap.c +++ b/drivers/gpu/drm/panthor/panthor_heap.c @@ -127,7 +127,7 @@ static void panthor_free_heap_chunk(struct panthor_vm *vm, heap->chunk_count--; mutex_unlock(&heap->lock); - panthor_kernel_bo_destroy(vm, chunk->bo); + panthor_kernel_bo_destroy(chunk->bo); kfree(chunk); } @@ -183,7 +183,7 @@ static int panthor_alloc_heap_chunk(struct panthor_device *ptdev, return 0; err_destroy_bo: - panthor_kernel_bo_destroy(vm, chunk->bo); + panthor_kernel_bo_destroy(chunk->bo); err_free_chunk: kfree(chunk); @@ -253,8 +253,8 @@ int panthor_heap_destroy(struct panthor_heap_pool *pool, u32 handle) * @pool: Pool to instantiate the heap context from. * @initial_chunk_count: Number of chunk allocated at initialization time. * Must be at least 1. - * @chunk_size: The size of each chunk. Must be a power of two between 256k - * and 2M. + * @chunk_size: The size of each chunk. Must be page-aligned and lie in the + * [128k:8M] range. * @max_chunks: Maximum number of chunks that can be allocated. * @target_in_flight: Maximum number of in-flight render passes. * @heap_ctx_gpu_va: Pointer holding the GPU address of the allocated heap @@ -281,8 +281,11 @@ int panthor_heap_create(struct panthor_heap_pool *pool, if (initial_chunk_count == 0) return -EINVAL; - if (hweight32(chunk_size) != 1 || - chunk_size < SZ_256K || chunk_size > SZ_2M) + if (initial_chunk_count > max_chunks) + return -EINVAL; + + if (!IS_ALIGNED(chunk_size, PAGE_SIZE) || + chunk_size < SZ_128K || chunk_size > SZ_8M) return -EINVAL; down_read(&pool->lock); @@ -320,7 +323,8 @@ int panthor_heap_create(struct panthor_heap_pool *pool, if (!pool->vm) { ret = -EINVAL; } else { - ret = xa_alloc(&pool->xa, &id, heap, XA_LIMIT(1, MAX_HEAPS_PER_POOL), GFP_KERNEL); + ret = xa_alloc(&pool->xa, &id, heap, + XA_LIMIT(0, MAX_HEAPS_PER_POOL - 1), GFP_KERNEL); if (!ret) { void *gpu_ctx = panthor_get_heap_ctx(pool, id); @@ -391,7 +395,7 @@ int panthor_heap_return_chunk(struct panthor_heap_pool *pool, mutex_unlock(&heap->lock); if (removed) { - panthor_kernel_bo_destroy(pool->vm, chunk->bo); + panthor_kernel_bo_destroy(chunk->bo); kfree(chunk); ret = 0; } else { @@ -410,6 +414,13 @@ out_unlock: * @renderpasses_in_flight: Number of render passes currently in-flight. * @pending_frag_count: Number of fragment jobs waiting for execution/completion. * @new_chunk_gpu_va: Pointer used to return the chunk VA. + * + * Return: + * - 0 if a new heap was allocated + * - -ENOMEM if the tiler context reached the maximum number of chunks + * or if too many render passes are in-flight + * or if the allocation failed + * - -EINVAL if any of the arguments passed to panthor_heap_grow() is invalid */ int panthor_heap_grow(struct panthor_heap_pool *pool, u64 heap_gpu_va, @@ -439,10 +450,7 @@ int panthor_heap_grow(struct panthor_heap_pool *pool, * handler provided by the userspace driver, if any). */ if (renderpasses_in_flight > heap->target_in_flight || - (pending_frag_count > 0 && heap->chunk_count >= heap->max_chunks)) { - ret = -EBUSY; - goto out_unlock; - } else if (heap->chunk_count >= heap->max_chunks) { + heap->chunk_count >= heap->max_chunks) { ret = -ENOMEM; goto out_unlock; } @@ -536,7 +544,7 @@ panthor_heap_pool_create(struct panthor_device *ptdev, struct panthor_vm *vm) pool->vm = vm; pool->ptdev = ptdev; init_rwsem(&pool->lock); - xa_init_flags(&pool->xa, XA_FLAGS_ALLOC1); + xa_init_flags(&pool->xa, XA_FLAGS_ALLOC); kref_init(&pool->refcount); pool->gpu_contexts = panthor_kernel_bo_create(ptdev, vm, bosize, @@ -587,7 +595,7 @@ void panthor_heap_pool_destroy(struct panthor_heap_pool *pool) drm_WARN_ON(&pool->ptdev->base, panthor_heap_destroy_locked(pool, i)); if (!IS_ERR_OR_NULL(pool->gpu_contexts)) - panthor_kernel_bo_destroy(pool->vm, pool->gpu_contexts); + panthor_kernel_bo_destroy(pool->gpu_contexts); /* Reflects the fact the pool has been destroyed. */ pool->vm = NULL; diff --git a/drivers/gpu/drm/panthor/panthor_sched.c b/drivers/gpu/drm/panthor/panthor_sched.c index 7f16a4a14e9a..79ffcbc41d78 100644 --- a/drivers/gpu/drm/panthor/panthor_sched.c +++ b/drivers/gpu/drm/panthor/panthor_sched.c @@ -826,8 +826,8 @@ static void group_free_queue(struct panthor_group *group, struct panthor_queue * panthor_queue_put_syncwait_obj(queue); - panthor_kernel_bo_destroy(group->vm, queue->ringbuf); - panthor_kernel_bo_destroy(panthor_fw_vm(group->ptdev), queue->iface.mem); + panthor_kernel_bo_destroy(queue->ringbuf); + panthor_kernel_bo_destroy(queue->iface.mem); kfree(queue); } @@ -837,15 +837,14 @@ static void group_release_work(struct work_struct *work) struct panthor_group *group = container_of(work, struct panthor_group, release_work); - struct panthor_device *ptdev = group->ptdev; u32 i; for (i = 0; i < group->queue_count; i++) group_free_queue(group, group->queues[i]); - panthor_kernel_bo_destroy(panthor_fw_vm(ptdev), group->suspend_buf); - panthor_kernel_bo_destroy(panthor_fw_vm(ptdev), group->protm_suspend_buf); - panthor_kernel_bo_destroy(group->vm, group->syncobjs); + panthor_kernel_bo_destroy(group->suspend_buf); + panthor_kernel_bo_destroy(group->protm_suspend_buf); + panthor_kernel_bo_destroy(group->syncobjs); panthor_vm_put(group->vm); kfree(group); @@ -1281,7 +1280,16 @@ cs_slot_process_fatal_event_locked(struct panthor_device *ptdev, if (group) group->fatal_queues |= BIT(cs_id); - sched_queue_delayed_work(sched, tick, 0); + if (CS_EXCEPTION_TYPE(fatal) == DRM_PANTHOR_EXCEPTION_CS_UNRECOVERABLE) { + /* If this exception is unrecoverable, queue a reset, and make + * sure we stop scheduling groups until the reset has happened. + */ + panthor_device_schedule_reset(ptdev); + cancel_delayed_work(&sched->tick_work); + } else { + sched_queue_delayed_work(sched, tick, 0); + } + drm_warn(&ptdev->base, "CSG slot %d CS slot: %d\n" "CS_FATAL.EXCEPTION_TYPE: 0x%x (%s)\n" @@ -1385,7 +1393,12 @@ static int group_process_tiler_oom(struct panthor_group *group, u32 cs_id) pending_frag_count, &new_chunk_va); } - if (ret && ret != -EBUSY) { + /* If the heap context doesn't have memory for us, we want to let the + * FW try to reclaim memory by waiting for fragment jobs to land or by + * executing the tiler OOM exception handler, which is supposed to + * implement incremental rendering. + */ + if (ret && ret != -ENOMEM) { drm_warn(&ptdev->base, "Failed to extend the tiler heap\n"); group->fatal_queues |= BIT(cs_id); sched_queue_delayed_work(sched, tick, 0); @@ -2720,15 +2733,22 @@ void panthor_sched_pre_reset(struct panthor_device *ptdev) mutex_unlock(&sched->reset.lock); } -void panthor_sched_post_reset(struct panthor_device *ptdev) +void panthor_sched_post_reset(struct panthor_device *ptdev, bool reset_failed) { struct panthor_scheduler *sched = ptdev->scheduler; struct panthor_group *group, *group_tmp; mutex_lock(&sched->reset.lock); - list_for_each_entry_safe(group, group_tmp, &sched->reset.stopped_groups, run_node) + list_for_each_entry_safe(group, group_tmp, &sched->reset.stopped_groups, run_node) { + /* Consider all previously running group as terminated if the + * reset failed. + */ + if (reset_failed) + group->state = PANTHOR_CS_GROUP_TERMINATED; + panthor_group_start(group); + } /* We're done resetting the GPU, clear the reset.in_progress bit so we can * kick the scheduler. @@ -2736,9 +2756,11 @@ void panthor_sched_post_reset(struct panthor_device *ptdev) atomic_set(&sched->reset.in_progress, false); mutex_unlock(&sched->reset.lock); - sched_queue_delayed_work(sched, tick, 0); - - sched_queue_work(sched, sync_upd); + /* No need to queue a tick and update syncs if the reset failed. */ + if (!reset_failed) { + sched_queue_delayed_work(sched, tick, 0); + sched_queue_work(sched, sync_upd); + } } static void group_sync_upd_work(struct work_struct *work) diff --git a/drivers/gpu/drm/panthor/panthor_sched.h b/drivers/gpu/drm/panthor/panthor_sched.h index 66438b1f331f..3a30d2328b30 100644 --- a/drivers/gpu/drm/panthor/panthor_sched.h +++ b/drivers/gpu/drm/panthor/panthor_sched.h @@ -40,7 +40,7 @@ void panthor_group_pool_destroy(struct panthor_file *pfile); int panthor_sched_init(struct panthor_device *ptdev); void panthor_sched_unplug(struct panthor_device *ptdev); void panthor_sched_pre_reset(struct panthor_device *ptdev); -void panthor_sched_post_reset(struct panthor_device *ptdev); +void panthor_sched_post_reset(struct panthor_device *ptdev, bool reset_failed); void panthor_sched_suspend(struct panthor_device *ptdev); void panthor_sched_resume(struct panthor_device *ptdev); diff --git a/drivers/gpu/drm/xlnx/zynqmp_disp.c b/drivers/gpu/drm/xlnx/zynqmp_disp.c index 13157da0089e..c9fb432d4cbd 100644 --- a/drivers/gpu/drm/xlnx/zynqmp_disp.c +++ b/drivers/gpu/drm/xlnx/zynqmp_disp.c @@ -940,7 +940,7 @@ zynqmp_disp_layer_find_format(struct zynqmp_disp_layer *layer, * zynqmp_disp_layer_find_live_format - Find format information for given * media bus format * @layer: The layer - * @drm_fmt: Media bus format to search + * @media_bus_format: Media bus format to search * * Search display subsystem format information corresponding to the given media * bus format @media_bus_format for the @layer, and return a pointer to the @@ -981,7 +981,7 @@ u32 *zynqmp_disp_layer_drm_formats(struct zynqmp_disp_layer *layer, unsigned int i; u32 *formats; - if (WARN_ON(!layer->mode == ZYNQMP_DPSUB_LAYER_NONLIVE)) { + if (WARN_ON(layer->mode != ZYNQMP_DPSUB_LAYER_NONLIVE)) { *num_formats = 0; return NULL; } @@ -1117,7 +1117,7 @@ void zynqmp_disp_layer_set_format(struct zynqmp_disp_layer *layer, /** * zynqmp_disp_layer_set_live_format - Set the live video layer format * @layer: The layer - * @info: The format info + * @media_bus_format: Media bus format to set * * NOTE: This function should not be used to set format for non-live video * layer. Use zynqmp_disp_layer_set_format() instead. diff --git a/drivers/i3c/device.c b/drivers/i3c/device.c index 1a6a8703dbc3..e80e48756914 100644 --- a/drivers/i3c/device.c +++ b/drivers/i3c/device.c @@ -27,6 +27,10 @@ * This function can sleep and thus cannot be called in atomic context. * * Return: 0 in case of success, a negative error core otherwise. + * -EAGAIN: controller lost address arbitration. Target + * (IBI, HJ or controller role request) win the bus. Client + * driver needs to resend the 'xfers' some time later. + * See I3C spec ver 1.1.1 09-Jun-2021. Section: 5.1.2.2.3. */ int i3c_device_do_priv_xfers(struct i3c_device *dev, struct i3c_priv_xfer *xfers, diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c index f32c591ae325..3b4d6a8edca3 100644 --- a/drivers/i3c/master.c +++ b/drivers/i3c/master.c @@ -13,6 +13,7 @@ #include <linux/kernel.h> #include <linux/list.h> #include <linux/of.h> +#include <linux/pm_runtime.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/workqueue.h> @@ -2812,6 +2813,10 @@ int i3c_master_register(struct i3c_master_controller *master, i3c_bus_notify(i3cbus, I3C_NOTIFY_BUS_ADD); + pm_runtime_no_callbacks(&master->dev); + pm_suspend_ignore_children(&master->dev, true); + pm_runtime_enable(&master->dev); + /* * We're done initializing the bus and the controller, we can now * register I3C devices discovered during the initial DAA. @@ -2849,6 +2854,7 @@ void i3c_master_unregister(struct i3c_master_controller *master) i3c_master_i2c_adapter_cleanup(master); i3c_master_unregister_i3c_devs(master); i3c_master_bus_cleanup(master); + pm_runtime_disable(&master->dev); device_unregister(&master->dev); } EXPORT_SYMBOL_GPL(i3c_master_unregister); diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c index 276153e10f5a..0ec00e644bd4 100644 --- a/drivers/i3c/master/dw-i3c-master.c +++ b/drivers/i3c/master/dw-i3c-master.c @@ -1136,6 +1136,23 @@ static void dw_i3c_master_free_ibi(struct i3c_dev_desc *dev) data->ibi_pool = NULL; } +static void dw_i3c_master_enable_sir_signal(struct dw_i3c_master *master, bool enable) +{ + u32 reg; + + reg = readl(master->regs + INTR_STATUS_EN); + reg &= ~INTR_IBI_THLD_STAT; + if (enable) + reg |= INTR_IBI_THLD_STAT; + writel(reg, master->regs + INTR_STATUS_EN); + + reg = readl(master->regs + INTR_SIGNAL_EN); + reg &= ~INTR_IBI_THLD_STAT; + if (enable) + reg |= INTR_IBI_THLD_STAT; + writel(reg, master->regs + INTR_SIGNAL_EN); +} + static void dw_i3c_master_set_sir_enabled(struct dw_i3c_master *master, struct i3c_dev_desc *dev, u8 idx, bool enable) @@ -1170,23 +1187,34 @@ static void dw_i3c_master_set_sir_enabled(struct dw_i3c_master *master, } writel(reg, master->regs + IBI_SIR_REQ_REJECT); - if (global) { - reg = readl(master->regs + INTR_STATUS_EN); - reg &= ~INTR_IBI_THLD_STAT; - if (enable) - reg |= INTR_IBI_THLD_STAT; - writel(reg, master->regs + INTR_STATUS_EN); - - reg = readl(master->regs + INTR_SIGNAL_EN); - reg &= ~INTR_IBI_THLD_STAT; - if (enable) - reg |= INTR_IBI_THLD_STAT; - writel(reg, master->regs + INTR_SIGNAL_EN); - } + if (global) + dw_i3c_master_enable_sir_signal(master, enable); + spin_unlock_irqrestore(&master->devs_lock, flags); } +static int dw_i3c_master_enable_hotjoin(struct i3c_master_controller *m) +{ + struct dw_i3c_master *master = to_dw_i3c_master(m); + + dw_i3c_master_enable_sir_signal(master, true); + writel(readl(master->regs + DEVICE_CTRL) & ~DEV_CTRL_HOT_JOIN_NACK, + master->regs + DEVICE_CTRL); + + return 0; +} + +static int dw_i3c_master_disable_hotjoin(struct i3c_master_controller *m) +{ + struct dw_i3c_master *master = to_dw_i3c_master(m); + + writel(readl(master->regs + DEVICE_CTRL) | DEV_CTRL_HOT_JOIN_NACK, + master->regs + DEVICE_CTRL); + + return 0; +} + static int dw_i3c_master_enable_ibi(struct i3c_dev_desc *dev) { struct dw_i3c_i2c_dev_data *data = i3c_dev_get_master_data(dev); @@ -1326,6 +1354,8 @@ static void dw_i3c_master_irq_handle_ibis(struct dw_i3c_master *master) if (IBI_TYPE_SIRQ(reg)) { dw_i3c_master_handle_ibi_sir(master, reg); + } else if (IBI_TYPE_HJ(reg)) { + queue_work(master->base.wq, &master->hj_work); } else { len = IBI_QUEUE_STATUS_DATA_LEN(reg); dev_info(&master->base.dev, @@ -1393,6 +1423,8 @@ static const struct i3c_master_controller_ops dw_mipi_i3c_ibi_ops = { .enable_ibi = dw_i3c_master_enable_ibi, .disable_ibi = dw_i3c_master_disable_ibi, .recycle_ibi_slot = dw_i3c_master_recycle_ibi_slot, + .enable_hotjoin = dw_i3c_master_enable_hotjoin, + .disable_hotjoin = dw_i3c_master_disable_hotjoin, }; /* default platform ops implementations */ @@ -1412,6 +1444,14 @@ static const struct dw_i3c_platform_ops dw_i3c_platform_ops_default = { .set_dat_ibi = dw_i3c_platform_set_dat_ibi_nop, }; +static void dw_i3c_hj_work(struct work_struct *work) +{ + struct dw_i3c_master *master = + container_of(work, typeof(*master), hj_work); + + i3c_master_do_daa(&master->base); +} + int dw_i3c_common_probe(struct dw_i3c_master *master, struct platform_device *pdev) { @@ -1469,6 +1509,7 @@ int dw_i3c_common_probe(struct dw_i3c_master *master, if (master->ibi_capable) ops = &dw_mipi_i3c_ibi_ops; + INIT_WORK(&master->hj_work, dw_i3c_hj_work); ret = i3c_master_register(&master->base, &pdev->dev, ops, false); if (ret) goto err_assert_rst; diff --git a/drivers/i3c/master/dw-i3c-master.h b/drivers/i3c/master/dw-i3c-master.h index ab862c5d15fe..4ab94aa72252 100644 --- a/drivers/i3c/master/dw-i3c-master.h +++ b/drivers/i3c/master/dw-i3c-master.h @@ -57,6 +57,8 @@ struct dw_i3c_master { /* platform-specific data */ const struct dw_i3c_platform_ops *platform_ops; + + struct work_struct hj_work; }; struct dw_i3c_platform_ops { diff --git a/drivers/i3c/master/svc-i3c-master.c b/drivers/i3c/master/svc-i3c-master.c index 5ee4db68988e..bb299ce02ccc 100644 --- a/drivers/i3c/master/svc-i3c-master.c +++ b/drivers/i3c/master/svc-i3c-master.c @@ -415,6 +415,19 @@ static void svc_i3c_master_ibi_work(struct work_struct *work) int ret; mutex_lock(&master->lock); + /* + * IBIWON may be set before SVC_I3C_MCTRL_REQUEST_AUTO_IBI, causing + * readl_relaxed_poll_timeout() to return immediately. Consequently, + * ibitype will be 0 since it was last updated only after the 8th SCL + * cycle, leading to missed client IBI handlers. + * + * A typical scenario is when IBIWON occurs and bus arbitration is lost + * at svc_i3c_master_priv_xfers(). + * + * Clear SVC_I3C_MINT_IBIWON before sending SVC_I3C_MCTRL_REQUEST_AUTO_IBI. + */ + writel(SVC_I3C_MINT_IBIWON, master->regs + SVC_I3C_MSTATUS); + /* Acknowledge the incoming interrupt with the AUTOIBI mechanism */ writel(SVC_I3C_MCTRL_REQUEST_AUTO_IBI | SVC_I3C_MCTRL_IBIRESP_AUTO, @@ -429,9 +442,6 @@ static void svc_i3c_master_ibi_work(struct work_struct *work) goto reenable_ibis; } - /* Clear the interrupt status */ - writel(SVC_I3C_MINT_IBIWON, master->regs + SVC_I3C_MSTATUS); - status = readl(master->regs + SVC_I3C_MSTATUS); ibitype = SVC_I3C_MSTATUS_IBITYPE(status); ibiaddr = SVC_I3C_MSTATUS_IBIADDR(status); @@ -1080,7 +1090,7 @@ static int svc_i3c_master_xfer(struct svc_i3c_master *master, * and yield the above events handler. */ if (SVC_I3C_MSTATUS_IBIWON(reg)) { - ret = -ENXIO; + ret = -EAGAIN; *actual_len = 0; goto emit_stop; } diff --git a/drivers/input/ff-core.c b/drivers/input/ff-core.c index 16231fe080b0..609a5f01761b 100644 --- a/drivers/input/ff-core.c +++ b/drivers/input/ff-core.c @@ -9,8 +9,10 @@ /* #define DEBUG */ #include <linux/input.h> +#include <linux/limits.h> #include <linux/module.h> #include <linux/mutex.h> +#include <linux/overflow.h> #include <linux/sched.h> #include <linux/slab.h> @@ -315,9 +317,8 @@ int input_ff_create(struct input_dev *dev, unsigned int max_effects) return -EINVAL; } - ff_dev_size = sizeof(struct ff_device) + - max_effects * sizeof(struct file *); - if (ff_dev_size < max_effects) /* overflow */ + ff_dev_size = struct_size(ff, effect_owners, max_effects); + if (ff_dev_size == SIZE_MAX) /* overflow */ return -EINVAL; ff = kzalloc(ff_dev_size, GFP_KERNEL); diff --git a/drivers/input/input.c b/drivers/input/input.c index 711485437567..fd4997ba263c 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -1378,19 +1378,19 @@ static int input_print_modalias_bits(char *buf, int size, char name, const unsigned long *bm, unsigned int min_bit, unsigned int max_bit) { - int len = 0, i; + int bit = min_bit; + int len = 0; len += snprintf(buf, max(size, 0), "%c", name); - for (i = min_bit; i < max_bit; i++) - if (bm[BIT_WORD(i)] & BIT_MASK(i)) - len += snprintf(buf + len, max(size - len, 0), "%X,", i); + for_each_set_bit_from(bit, bm, max_bit) + len += snprintf(buf + len, max(size - len, 0), "%X,", bit); return len; } -static int input_print_modalias(char *buf, int size, const struct input_dev *id, - int add_cr) +static int input_print_modalias_parts(char *buf, int size, int full_len, + const struct input_dev *id) { - int len; + int len, klen, remainder, space; len = snprintf(buf, max(size, 0), "input:b%04Xv%04Xp%04Xe%04X-", @@ -1399,8 +1399,48 @@ static int input_print_modalias(char *buf, int size, const struct input_dev *id, len += input_print_modalias_bits(buf + len, size - len, 'e', id->evbit, 0, EV_MAX); - len += input_print_modalias_bits(buf + len, size - len, + + /* + * Calculate the remaining space in the buffer making sure we + * have place for the terminating 0. + */ + space = max(size - (len + 1), 0); + + klen = input_print_modalias_bits(buf + len, size - len, 'k', id->keybit, KEY_MIN_INTERESTING, KEY_MAX); + len += klen; + + /* + * If we have more data than we can fit in the buffer, check + * if we can trim key data to fit in the rest. We will indicate + * that key data is incomplete by adding "+" sign at the end, like + * this: * "k1,2,3,45,+,". + * + * Note that we shortest key info (if present) is "k+," so we + * can only try to trim if key data is longer than that. + */ + if (full_len && size < full_len + 1 && klen > 3) { + remainder = full_len - len; + /* + * We can only trim if we have space for the remainder + * and also for at least "k+," which is 3 more characters. + */ + if (remainder <= space - 3) { + /* + * We are guaranteed to have 'k' in the buffer, so + * we need at least 3 additional bytes for storing + * "+," in addition to the remainder. + */ + for (int i = size - 1 - remainder - 3; i >= 0; i--) { + if (buf[i] == 'k' || buf[i] == ',') { + strcpy(buf + i + 1, "+,"); + len = i + 3; /* Not counting '\0' */ + break; + } + } + } + } + len += input_print_modalias_bits(buf + len, size - len, 'r', id->relbit, 0, REL_MAX); len += input_print_modalias_bits(buf + len, size - len, @@ -1416,12 +1456,25 @@ static int input_print_modalias(char *buf, int size, const struct input_dev *id, len += input_print_modalias_bits(buf + len, size - len, 'w', id->swbit, 0, SW_MAX); - if (add_cr) - len += snprintf(buf + len, max(size - len, 0), "\n"); - return len; } +static int input_print_modalias(char *buf, int size, const struct input_dev *id) +{ + int full_len; + + /* + * Printing is done in 2 passes: first one figures out total length + * needed for the modalias string, second one will try to trim key + * data in case when buffer is too small for the entire modalias. + * If the buffer is too small regardless, it will fill as much as it + * can (without trimming key data) into the buffer and leave it to + * the caller to figure out what to do with the result. + */ + full_len = input_print_modalias_parts(NULL, 0, 0, id); + return input_print_modalias_parts(buf, size, full_len, id); +} + static ssize_t input_dev_show_modalias(struct device *dev, struct device_attribute *attr, char *buf) @@ -1429,7 +1482,9 @@ static ssize_t input_dev_show_modalias(struct device *dev, struct input_dev *id = to_input_dev(dev); ssize_t len; - len = input_print_modalias(buf, PAGE_SIZE, id, 1); + len = input_print_modalias(buf, PAGE_SIZE, id); + if (len < PAGE_SIZE - 2) + len += snprintf(buf + len, PAGE_SIZE - len, "\n"); return min_t(int, len, PAGE_SIZE); } @@ -1641,6 +1696,23 @@ static int input_add_uevent_bm_var(struct kobj_uevent_env *env, return 0; } +/* + * This is a pretty gross hack. When building uevent data the driver core + * may try adding more environment variables to kobj_uevent_env without + * telling us, so we have no idea how much of the buffer we can use to + * avoid overflows/-ENOMEM elsewhere. To work around this let's artificially + * reduce amount of memory we will use for the modalias environment variable. + * + * The potential additions are: + * + * SEQNUM=18446744073709551615 - (%llu - 28 bytes) + * HOME=/ (6 bytes) + * PATH=/sbin:/bin:/usr/sbin:/usr/bin (34 bytes) + * + * 68 bytes total. Allow extra buffer - 96 bytes + */ +#define UEVENT_ENV_EXTRA_LEN 96 + static int input_add_uevent_modalias_var(struct kobj_uevent_env *env, const struct input_dev *dev) { @@ -1650,9 +1722,11 @@ static int input_add_uevent_modalias_var(struct kobj_uevent_env *env, return -ENOMEM; len = input_print_modalias(&env->buf[env->buflen - 1], - sizeof(env->buf) - env->buflen, - dev, 0); - if (len >= (sizeof(env->buf) - env->buflen)) + (int)sizeof(env->buf) - env->buflen - + UEVENT_ENV_EXTRA_LEN, + dev); + if (len >= ((int)sizeof(env->buf) - env->buflen - + UEVENT_ENV_EXTRA_LEN)) return -ENOMEM; env->buflen += len; diff --git a/drivers/input/joystick/adafruit-seesaw.c b/drivers/input/joystick/adafruit-seesaw.c index 1b9279f024cc..5c775ca886a5 100644 --- a/drivers/input/joystick/adafruit-seesaw.c +++ b/drivers/input/joystick/adafruit-seesaw.c @@ -56,7 +56,7 @@ #define SEESAW_GAMEPAD_POLL_MIN 8 #define SEESAW_GAMEPAD_POLL_MAX 32 -static const unsigned long SEESAW_BUTTON_MASK = +static const u32 SEESAW_BUTTON_MASK = BIT(SEESAW_BUTTON_A) | BIT(SEESAW_BUTTON_B) | BIT(SEESAW_BUTTON_X) | BIT(SEESAW_BUTTON_Y) | BIT(SEESAW_BUTTON_START) | BIT(SEESAW_BUTTON_SELECT); @@ -64,6 +64,7 @@ static const unsigned long SEESAW_BUTTON_MASK = struct seesaw_gamepad { struct input_dev *input_dev; struct i2c_client *i2c_client; + u32 button_state; }; struct seesaw_data { @@ -178,10 +179,20 @@ static int seesaw_read_data(struct i2c_client *client, struct seesaw_data *data) return 0; } +static int seesaw_open(struct input_dev *input) +{ + struct seesaw_gamepad *private = input_get_drvdata(input); + + private->button_state = 0; + + return 0; +} + static void seesaw_poll(struct input_dev *input) { struct seesaw_gamepad *private = input_get_drvdata(input); struct seesaw_data data; + unsigned long changed; int err, i; err = seesaw_read_data(private->i2c_client, &data); @@ -194,8 +205,11 @@ static void seesaw_poll(struct input_dev *input) input_report_abs(input, ABS_X, data.x); input_report_abs(input, ABS_Y, data.y); - for_each_set_bit(i, &SEESAW_BUTTON_MASK, - BITS_PER_TYPE(SEESAW_BUTTON_MASK)) { + data.button_state &= SEESAW_BUTTON_MASK; + changed = private->button_state ^ data.button_state; + private->button_state = data.button_state; + + for_each_set_bit(i, &changed, fls(SEESAW_BUTTON_MASK)) { if (!sparse_keymap_report_event(input, i, data.button_state & BIT(i), false)) @@ -253,6 +267,7 @@ static int seesaw_probe(struct i2c_client *client) seesaw->input_dev->id.bustype = BUS_I2C; seesaw->input_dev->name = "Adafruit Seesaw Gamepad"; seesaw->input_dev->phys = "i2c/" SEESAW_DEVICE_NAME; + seesaw->input_dev->open = seesaw_open; input_set_drvdata(seesaw->input_dev, seesaw); input_set_abs_params(seesaw->input_dev, ABS_X, 0, SEESAW_JOYSTICK_MAX_AXIS, diff --git a/drivers/input/joystick/as5011.c b/drivers/input/joystick/as5011.c index f1822c19a289..407062bcc84b 100644 --- a/drivers/input/joystick/as5011.c +++ b/drivers/input/joystick/as5011.c @@ -337,7 +337,7 @@ static void as5011_remove(struct i2c_client *client) } static const struct i2c_device_id as5011_id[] = { - { MODULE_DEVICE_ALIAS, 0 }, + { MODULE_DEVICE_ALIAS }, { } }; MODULE_DEVICE_TABLE(i2c, as5011_id); diff --git a/drivers/input/joystick/qwiic-joystick.c b/drivers/input/joystick/qwiic-joystick.c index 7d88d76b14d6..6f989d00d3ec 100644 --- a/drivers/input/joystick/qwiic-joystick.c +++ b/drivers/input/joystick/qwiic-joystick.c @@ -126,8 +126,8 @@ MODULE_DEVICE_TABLE(of, of_qwiic_match); #endif /* CONFIG_OF */ static const struct i2c_device_id qwiic_id_table[] = { - { KBUILD_MODNAME, 0 }, - { }, + { KBUILD_MODNAME }, + { } }; MODULE_DEVICE_TABLE(i2c, qwiic_id_table); diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index 6fadaddb2b90..70f0654c58b6 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -342,6 +342,7 @@ static const struct xpad_device { { 0x20d6, 0x2001, "BDA Xbox Series X Wired Controller", 0, XTYPE_XBOXONE }, { 0x20d6, 0x2009, "PowerA Enhanced Wired Controller for Xbox Series X|S", 0, XTYPE_XBOXONE }, { 0x20d6, 0x281f, "PowerA Wired Controller For Xbox 360", 0, XTYPE_XBOX360 }, + { 0x2345, 0xe00b, "Machenike G5 Pro Controller", 0, XTYPE_XBOX360 }, { 0x24c6, 0x5000, "Razer Atrox Arcade Stick", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 }, { 0x24c6, 0x5300, "PowerA MINI PROEX Controller", 0, XTYPE_XBOX360 }, { 0x24c6, 0x5303, "Xbox Airflo wired controller", 0, XTYPE_XBOX360 }, @@ -512,6 +513,7 @@ static const struct usb_device_id xpad_table[] = { XPAD_XBOX360_VENDOR(0x1bad), /* Harmonix Rock Band guitar and drums */ XPAD_XBOX360_VENDOR(0x20d6), /* PowerA controllers */ XPAD_XBOXONE_VENDOR(0x20d6), /* PowerA controllers */ + XPAD_XBOX360_VENDOR(0x2345), /* Machenike Controllers */ XPAD_XBOX360_VENDOR(0x24c6), /* PowerA controllers */ XPAD_XBOXONE_VENDOR(0x24c6), /* PowerA controllers */ XPAD_XBOX360_VENDOR(0x2563), /* OneXPlayer Gamepad */ diff --git a/drivers/input/keyboard/adp5588-keys.c b/drivers/input/keyboard/adp5588-keys.c index 61e8e43e9c2b..1b0279393df4 100644 --- a/drivers/input/keyboard/adp5588-keys.c +++ b/drivers/input/keyboard/adp5588-keys.c @@ -832,8 +832,8 @@ static int adp5588_resume(struct device *dev) static DEFINE_SIMPLE_DEV_PM_OPS(adp5588_dev_pm_ops, adp5588_suspend, adp5588_resume); static const struct i2c_device_id adp5588_id[] = { - { "adp5588-keys", 0 }, - { "adp5587-keys", 0 }, + { "adp5588-keys" }, + { "adp5587-keys" }, { } }; MODULE_DEVICE_TABLE(i2c, adp5588_id); diff --git a/drivers/input/keyboard/cros_ec_keyb.c b/drivers/input/keyboard/cros_ec_keyb.c index 30678a34cf64..12eb9df180ee 100644 --- a/drivers/input/keyboard/cros_ec_keyb.c +++ b/drivers/input/keyboard/cros_ec_keyb.c @@ -35,7 +35,6 @@ * @rows: Number of rows in the keypad * @cols: Number of columns in the keypad * @row_shift: log2 or number of rows, rounded up - * @keymap_data: Matrix keymap data used to convert to keyscan values * @ghost_filter: true to enable the matrix key-ghosting filter * @valid_keys: bitmap of existing keys for each matrix column * @old_kb_state: bitmap of keys pressed last scan @@ -50,7 +49,6 @@ struct cros_ec_keyb { unsigned int rows; unsigned int cols; int row_shift; - const struct matrix_keymap_data *keymap_data; bool ghost_filter; uint8_t *valid_keys; uint8_t *old_kb_state; diff --git a/drivers/input/keyboard/cypress-sf.c b/drivers/input/keyboard/cypress-sf.c index 2bacd9d80ecf..eb1d0720784d 100644 --- a/drivers/input/keyboard/cypress-sf.c +++ b/drivers/input/keyboard/cypress-sf.c @@ -209,7 +209,7 @@ static DEFINE_SIMPLE_DEV_PM_OPS(cypress_sf_pm_ops, cypress_sf_suspend, cypress_sf_resume); static struct i2c_device_id cypress_sf_id_table[] = { - { CYPRESS_SF_DEV_NAME, 0 }, + { CYPRESS_SF_DEV_NAME }, { } }; MODULE_DEVICE_TABLE(i2c, cypress_sf_id_table); diff --git a/drivers/input/keyboard/dlink-dir685-touchkeys.c b/drivers/input/keyboard/dlink-dir685-touchkeys.c index 6c065eff5a5a..993cdbda509e 100644 --- a/drivers/input/keyboard/dlink-dir685-touchkeys.c +++ b/drivers/input/keyboard/dlink-dir685-touchkeys.c @@ -127,7 +127,7 @@ static int dir685_tk_probe(struct i2c_client *client) } static const struct i2c_device_id dir685_tk_id[] = { - { "dir685tk", 0 }, + { "dir685tk" }, { } }; MODULE_DEVICE_TABLE(i2c, dir685_tk_id); diff --git a/drivers/input/keyboard/lm8323.c b/drivers/input/keyboard/lm8323.c index 7bee93e9b0f5..cf67ba13477a 100644 --- a/drivers/input/keyboard/lm8323.c +++ b/drivers/input/keyboard/lm8323.c @@ -792,7 +792,7 @@ static int lm8323_resume(struct device *dev) static DEFINE_SIMPLE_DEV_PM_OPS(lm8323_pm_ops, lm8323_suspend, lm8323_resume); static const struct i2c_device_id lm8323_id[] = { - { "lm8323", 0 }, + { "lm8323" }, { } }; diff --git a/drivers/input/keyboard/lm8333.c b/drivers/input/keyboard/lm8333.c index 1c070c499c85..384baabf9924 100644 --- a/drivers/input/keyboard/lm8333.c +++ b/drivers/input/keyboard/lm8333.c @@ -194,7 +194,7 @@ static int lm8333_probe(struct i2c_client *client) } static const struct i2c_device_id lm8333_id[] = { - { "lm8333", 0 }, + { "lm8333" }, { } }; MODULE_DEVICE_TABLE(i2c, lm8333_id); diff --git a/drivers/input/keyboard/lpc32xx-keys.c b/drivers/input/keyboard/lpc32xx-keys.c index 322a87807159..423035be86fb 100644 --- a/drivers/input/keyboard/lpc32xx-keys.c +++ b/drivers/input/keyboard/lpc32xx-keys.c @@ -57,14 +57,13 @@ struct lpc32xx_kscan_drv { struct input_dev *input; struct clk *clk; void __iomem *kscan_base; - unsigned int irq; u32 matrix_sz; /* Size of matrix in XxY, ie. 3 = 3x3 */ u32 deb_clks; /* Debounce clocks (based on 32KHz clock) */ u32 scan_delay; /* Scan delay (based on 32KHz clock) */ - unsigned short *keymap; /* Pointer to key map for the scan matrix */ unsigned int row_shift; + unsigned short *keymap; /* Pointer to key map for the scan matrix */ u8 lastkeystates[8]; }; diff --git a/drivers/input/keyboard/matrix_keypad.c b/drivers/input/keyboard/matrix_keypad.c index 695c03e075b5..7a56f3d3aacd 100644 --- a/drivers/input/keyboard/matrix_keypad.c +++ b/drivers/input/keyboard/matrix_keypad.c @@ -37,7 +37,6 @@ struct matrix_keypad { spinlock_t lock; bool scan_pending; bool stopped; - bool gpio_all_disabled; }; /* diff --git a/drivers/input/keyboard/max7359_keypad.c b/drivers/input/keyboard/max7359_keypad.c index faab7691c219..c10726b5e4d1 100644 --- a/drivers/input/keyboard/max7359_keypad.c +++ b/drivers/input/keyboard/max7359_keypad.c @@ -270,7 +270,7 @@ static int max7359_resume(struct device *dev) static DEFINE_SIMPLE_DEV_PM_OPS(max7359_pm, max7359_suspend, max7359_resume); static const struct i2c_device_id max7359_ids[] = { - { "max7359", 0 }, + { "max7359" }, { } }; MODULE_DEVICE_TABLE(i2c, max7359_ids); diff --git a/drivers/input/keyboard/mpr121_touchkey.c b/drivers/input/keyboard/mpr121_touchkey.c index d434753afab1..21827d2497fa 100644 --- a/drivers/input/keyboard/mpr121_touchkey.c +++ b/drivers/input/keyboard/mpr121_touchkey.c @@ -369,7 +369,7 @@ static int mpr_resume(struct device *dev) static DEFINE_SIMPLE_DEV_PM_OPS(mpr121_touchkey_pm_ops, mpr_suspend, mpr_resume); static const struct i2c_device_id mpr121_id[] = { - { "mpr121_touchkey", 0 }, + { "mpr121_touchkey" }, { } }; MODULE_DEVICE_TABLE(i2c, mpr121_id); diff --git a/drivers/input/keyboard/qt1070.c b/drivers/input/keyboard/qt1070.c index 9b093b042bf1..b3db2c7d0957 100644 --- a/drivers/input/keyboard/qt1070.c +++ b/drivers/input/keyboard/qt1070.c @@ -234,8 +234,8 @@ static int qt1070_resume(struct device *dev) static DEFINE_SIMPLE_DEV_PM_OPS(qt1070_pm_ops, qt1070_suspend, qt1070_resume); static const struct i2c_device_id qt1070_id[] = { - { "qt1070", 0 }, - { }, + { "qt1070" }, + { } }; MODULE_DEVICE_TABLE(i2c, qt1070_id); diff --git a/drivers/input/keyboard/qt2160.c b/drivers/input/keyboard/qt2160.c index 7e3b09642ab7..53f5255fd19d 100644 --- a/drivers/input/keyboard/qt2160.c +++ b/drivers/input/keyboard/qt2160.c @@ -393,7 +393,7 @@ static int qt2160_probe(struct i2c_client *client) } static const struct i2c_device_id qt2160_idtable[] = { - { "qt2160", 0, }, + { "qt2160" }, { } }; diff --git a/drivers/input/keyboard/stmpe-keypad.c b/drivers/input/keyboard/stmpe-keypad.c index 2013c0afd0c3..ef2f44027894 100644 --- a/drivers/input/keyboard/stmpe-keypad.c +++ b/drivers/input/keyboard/stmpe-keypad.c @@ -413,7 +413,6 @@ static void stmpe_keypad_remove(struct platform_device *pdev) static struct platform_driver stmpe_keypad_driver = { .driver.name = "stmpe-keypad", - .driver.owner = THIS_MODULE, .probe = stmpe_keypad_probe, .remove_new = stmpe_keypad_remove, }; diff --git a/drivers/input/keyboard/tca6416-keypad.c b/drivers/input/keyboard/tca6416-keypad.c index 677bc4baa5d1..fbc674d7b9f0 100644 --- a/drivers/input/keyboard/tca6416-keypad.c +++ b/drivers/input/keyboard/tca6416-keypad.c @@ -32,11 +32,6 @@ static const struct i2c_device_id tca6416_id[] = { }; MODULE_DEVICE_TABLE(i2c, tca6416_id); -struct tca6416_drv_data { - struct input_dev *input; - struct tca6416_button data[]; -}; - struct tca6416_keypad_chip { uint16_t reg_output; uint16_t reg_direction; @@ -45,7 +40,6 @@ struct tca6416_keypad_chip { struct i2c_client *client; struct input_dev *input; int io_size; - int irqnum; u16 pinmask; bool use_polling; struct tca6416_button buttons[]; diff --git a/drivers/input/keyboard/tm2-touchkey.c b/drivers/input/keyboard/tm2-touchkey.c index 0fd761ae052f..55d699d9037d 100644 --- a/drivers/input/keyboard/tm2-touchkey.c +++ b/drivers/input/keyboard/tm2-touchkey.c @@ -326,8 +326,8 @@ static DEFINE_SIMPLE_DEV_PM_OPS(tm2_touchkey_pm_ops, tm2_touchkey_suspend, tm2_touchkey_resume); static const struct i2c_device_id tm2_touchkey_id_table[] = { - { TM2_TOUCHKEY_DEV_NAME, 0 }, - { }, + { TM2_TOUCHKEY_DEV_NAME }, + { } }; MODULE_DEVICE_TABLE(i2c, tm2_touchkey_id_table); diff --git a/drivers/input/misc/ad714x-i2c.c b/drivers/input/misc/ad714x-i2c.c index 679fcfea942c..2adb7a058362 100644 --- a/drivers/input/misc/ad714x-i2c.c +++ b/drivers/input/misc/ad714x-i2c.c @@ -72,11 +72,11 @@ static int ad714x_i2c_probe(struct i2c_client *client) } static const struct i2c_device_id ad714x_id[] = { - { "ad7142_captouch", 0 }, - { "ad7143_captouch", 0 }, - { "ad7147_captouch", 0 }, - { "ad7147a_captouch", 0 }, - { "ad7148_captouch", 0 }, + { "ad7142_captouch" }, + { "ad7143_captouch" }, + { "ad7147_captouch" }, + { "ad7147a_captouch" }, + { "ad7148_captouch" }, { } }; MODULE_DEVICE_TABLE(i2c, ad714x_id); diff --git a/drivers/input/misc/adxl34x-i2c.c b/drivers/input/misc/adxl34x-i2c.c index 6b880e282d99..d4014e367c77 100644 --- a/drivers/input/misc/adxl34x-i2c.c +++ b/drivers/input/misc/adxl34x-i2c.c @@ -106,7 +106,7 @@ static void adxl34x_i2c_remove(struct i2c_client *client) } static const struct i2c_device_id adxl34x_id[] = { - { "adxl34x", 0 }, + { "adxl34x" }, { } }; diff --git a/drivers/input/misc/apanel.c b/drivers/input/misc/apanel.c index b5219bbe856d..d43aebd785b7 100644 --- a/drivers/input/misc/apanel.c +++ b/drivers/input/misc/apanel.c @@ -192,7 +192,7 @@ static void apanel_shutdown(struct i2c_client *client) } static const struct i2c_device_id apanel_id[] = { - { "fujitsu_apanel", 0 }, + { "fujitsu_apanel" }, { } }; MODULE_DEVICE_TABLE(i2c, apanel_id); diff --git a/drivers/input/misc/atmel_captouch.c b/drivers/input/misc/atmel_captouch.c index b6a30044e814..f9744cf0ca80 100644 --- a/drivers/input/misc/atmel_captouch.c +++ b/drivers/input/misc/atmel_captouch.c @@ -257,7 +257,7 @@ static const struct of_device_id atmel_captouch_of_id[] = { MODULE_DEVICE_TABLE(of, atmel_captouch_of_id); static const struct i2c_device_id atmel_captouch_id[] = { - { "atmel_captouch", 0 }, + { "atmel_captouch" }, { } }; MODULE_DEVICE_TABLE(i2c, atmel_captouch_id); diff --git a/drivers/input/misc/bma150.c b/drivers/input/misc/bma150.c index 0fb4cc628f29..4cc2a0dcaa75 100644 --- a/drivers/input/misc/bma150.c +++ b/drivers/input/misc/bma150.c @@ -536,9 +536,9 @@ static int __maybe_unused bma150_resume(struct device *dev) static UNIVERSAL_DEV_PM_OPS(bma150_pm, bma150_suspend, bma150_resume, NULL); static const struct i2c_device_id bma150_id[] = { - { "bma150", 0 }, - { "smb380", 0 }, - { "bma023", 0 }, + { "bma150" }, + { "smb380" }, + { "bma023" }, { } }; diff --git a/drivers/input/misc/cma3000_d0x_i2c.c b/drivers/input/misc/cma3000_d0x_i2c.c index a4dfb3052dc0..f892c5b1e4bd 100644 --- a/drivers/input/misc/cma3000_d0x_i2c.c +++ b/drivers/input/misc/cma3000_d0x_i2c.c @@ -90,8 +90,8 @@ static const struct dev_pm_ops cma3000_i2c_pm_ops = { }; static const struct i2c_device_id cma3000_i2c_id[] = { - { "cma3000_d01", 0 }, - { }, + { "cma3000_d01" }, + { } }; MODULE_DEVICE_TABLE(i2c, cma3000_i2c_id); diff --git a/drivers/input/misc/da7280.c b/drivers/input/misc/da7280.c index c1fa75c0f970..1629b7ea4cbd 100644 --- a/drivers/input/misc/da7280.c +++ b/drivers/input/misc/da7280.c @@ -230,7 +230,6 @@ struct da7280_haptic { struct i2c_client *client; struct pwm_device *pwm_dev; - bool legacy; struct work_struct work; int val; u16 gain; diff --git a/drivers/input/misc/drv260x.c b/drivers/input/misc/drv260x.c index 6717e3c9549b..61b503835aa6 100644 --- a/drivers/input/misc/drv260x.c +++ b/drivers/input/misc/drv260x.c @@ -600,7 +600,7 @@ out: static DEFINE_SIMPLE_DEV_PM_OPS(drv260x_pm_ops, drv260x_suspend, drv260x_resume); static const struct i2c_device_id drv260x_id[] = { - { "drv2605l", 0 }, + { "drv2605l" }, { } }; MODULE_DEVICE_TABLE(i2c, drv260x_id); diff --git a/drivers/input/misc/drv2665.c b/drivers/input/misc/drv2665.c index de27e6079d84..f98e4d765307 100644 --- a/drivers/input/misc/drv2665.c +++ b/drivers/input/misc/drv2665.c @@ -283,7 +283,7 @@ out: static DEFINE_SIMPLE_DEV_PM_OPS(drv2665_pm_ops, drv2665_suspend, drv2665_resume); static const struct i2c_device_id drv2665_id[] = { - { "drv2665", 0 }, + { "drv2665" }, { } }; MODULE_DEVICE_TABLE(i2c, drv2665_id); diff --git a/drivers/input/misc/drv2667.c b/drivers/input/misc/drv2667.c index 11c5855256e8..ad49845374b9 100644 --- a/drivers/input/misc/drv2667.c +++ b/drivers/input/misc/drv2667.c @@ -460,7 +460,7 @@ out: static DEFINE_SIMPLE_DEV_PM_OPS(drv2667_pm_ops, drv2667_suspend, drv2667_resume); static const struct i2c_device_id drv2667_id[] = { - { "drv2667", 0 }, + { "drv2667" }, { } }; MODULE_DEVICE_TABLE(i2c, drv2667_id); diff --git a/drivers/input/misc/ims-pcu.c b/drivers/input/misc/ims-pcu.c index 6e8cc28debd9..80d16c92a08b 100644 --- a/drivers/input/misc/ims-pcu.c +++ b/drivers/input/misc/ims-pcu.c @@ -42,8 +42,8 @@ struct ims_pcu_backlight { #define IMS_PCU_PART_NUMBER_LEN 15 #define IMS_PCU_SERIAL_NUMBER_LEN 8 #define IMS_PCU_DOM_LEN 8 -#define IMS_PCU_FW_VERSION_LEN (9 + 1) -#define IMS_PCU_BL_VERSION_LEN (9 + 1) +#define IMS_PCU_FW_VERSION_LEN 16 +#define IMS_PCU_BL_VERSION_LEN 16 #define IMS_PCU_BL_RESET_REASON_LEN (2 + 1) #define IMS_PCU_PCU_B_DEVICE_ID 5 diff --git a/drivers/input/misc/kxtj9.c b/drivers/input/misc/kxtj9.c index d47269b10e9a..837682cb2a7d 100644 --- a/drivers/input/misc/kxtj9.c +++ b/drivers/input/misc/kxtj9.c @@ -531,8 +531,8 @@ static int kxtj9_resume(struct device *dev) static DEFINE_SIMPLE_DEV_PM_OPS(kxtj9_pm_ops, kxtj9_suspend, kxtj9_resume); static const struct i2c_device_id kxtj9_id[] = { - { NAME, 0 }, - { }, + { NAME }, + { } }; MODULE_DEVICE_TABLE(i2c, kxtj9_id); diff --git a/drivers/input/misc/mma8450.c b/drivers/input/misc/mma8450.c index 662b436d765b..08412239b8e6 100644 --- a/drivers/input/misc/mma8450.c +++ b/drivers/input/misc/mma8450.c @@ -186,8 +186,8 @@ static int mma8450_probe(struct i2c_client *c) } static const struct i2c_device_id mma8450_id[] = { - { MMA8450_DRV_NAME, 0 }, - { }, + { MMA8450_DRV_NAME }, + { } }; MODULE_DEVICE_TABLE(i2c, mma8450_id); diff --git a/drivers/input/misc/pcf8574_keypad.c b/drivers/input/misc/pcf8574_keypad.c index 536cedeb38e6..3632cb206e34 100644 --- a/drivers/input/misc/pcf8574_keypad.c +++ b/drivers/input/misc/pcf8574_keypad.c @@ -189,7 +189,7 @@ static DEFINE_SIMPLE_DEV_PM_OPS(pcf8574_kp_pm_ops, pcf8574_kp_suspend, pcf8574_kp_resume); static const struct i2c_device_id pcf8574_kp_id[] = { - { DRV_NAME, 0 }, + { DRV_NAME }, { } }; MODULE_DEVICE_TABLE(i2c, pcf8574_kp_id); diff --git a/drivers/input/misc/pm8xxx-vibrator.c b/drivers/input/misc/pm8xxx-vibrator.c index 5c288fe7accf..381b06473279 100644 --- a/drivers/input/misc/pm8xxx-vibrator.c +++ b/drivers/input/misc/pm8xxx-vibrator.c @@ -11,36 +11,57 @@ #include <linux/regmap.h> #include <linux/slab.h> -#define VIB_MAX_LEVEL_mV (3100) -#define VIB_MIN_LEVEL_mV (1200) -#define VIB_MAX_LEVELS (VIB_MAX_LEVEL_mV - VIB_MIN_LEVEL_mV) +#define VIB_MAX_LEVEL_mV(vib) (vib->drv2_addr ? 3544 : 3100) +#define VIB_MIN_LEVEL_mV(vib) (vib->drv2_addr ? 1504 : 1200) +#define VIB_PER_STEP_mV(vib) (vib->drv2_addr ? 8 : 100) +#define VIB_MAX_LEVELS(vib) \ + (VIB_MAX_LEVEL_mV(vib) - VIB_MIN_LEVEL_mV(vib) + VIB_PER_STEP_mV(vib)) #define MAX_FF_SPEED 0xff struct pm8xxx_regs { - unsigned int enable_addr; + unsigned int enable_offset; unsigned int enable_mask; - unsigned int drv_addr; + unsigned int drv_offset; unsigned int drv_mask; unsigned int drv_shift; + unsigned int drv2_offset; + unsigned int drv2_mask; + unsigned int drv2_shift; unsigned int drv_en_manual_mask; + bool drv_in_step; }; static const struct pm8xxx_regs pm8058_regs = { - .drv_addr = 0x4A, - .drv_mask = 0xf8, + .drv_offset = 0, + .drv_mask = GENMASK(7, 3), .drv_shift = 3, .drv_en_manual_mask = 0xfc, + .drv_in_step = true, }; static struct pm8xxx_regs pm8916_regs = { - .enable_addr = 0xc046, + .enable_offset = 0x46, .enable_mask = BIT(7), - .drv_addr = 0xc041, - .drv_mask = 0x1F, + .drv_offset = 0x41, + .drv_mask = GENMASK(4, 0), .drv_shift = 0, .drv_en_manual_mask = 0, + .drv_in_step = true, +}; + +static struct pm8xxx_regs pmi632_regs = { + .enable_offset = 0x46, + .enable_mask = BIT(7), + .drv_offset = 0x40, + .drv_mask = GENMASK(7, 0), + .drv_shift = 0, + .drv2_offset = 0x41, + .drv2_mask = GENMASK(3, 0), + .drv2_shift = 8, + .drv_en_manual_mask = 0, + .drv_in_step = false, }; /** @@ -49,6 +70,9 @@ static struct pm8xxx_regs pm8916_regs = { * @work: work structure to set the vibration parameters * @regmap: regmap for register read/write * @regs: registers' info + * @enable_addr: vibrator enable register + * @drv_addr: vibrator drive strength register + * @drv2_addr: vibrator drive strength upper byte register * @speed: speed of vibration set from userland * @active: state of vibrator * @level: level of vibration to set in the chip @@ -59,6 +83,9 @@ struct pm8xxx_vib { struct work_struct work; struct regmap *regmap; const struct pm8xxx_regs *regs; + unsigned int enable_addr; + unsigned int drv_addr; + unsigned int drv2_addr; int speed; int level; bool active; @@ -76,20 +103,31 @@ static int pm8xxx_vib_set(struct pm8xxx_vib *vib, bool on) unsigned int val = vib->reg_vib_drv; const struct pm8xxx_regs *regs = vib->regs; + if (regs->drv_in_step) + vib->level /= VIB_PER_STEP_mV(vib); + if (on) val |= (vib->level << regs->drv_shift) & regs->drv_mask; else val &= ~regs->drv_mask; - rc = regmap_write(vib->regmap, regs->drv_addr, val); + rc = regmap_write(vib->regmap, vib->drv_addr, val); if (rc < 0) return rc; vib->reg_vib_drv = val; + if (regs->drv2_mask) { + val = vib->level << regs->drv2_shift; + rc = regmap_write_bits(vib->regmap, vib->drv2_addr, + regs->drv2_mask, on ? val : 0); + if (rc < 0) + return rc; + } + if (regs->enable_mask) - rc = regmap_update_bits(vib->regmap, regs->enable_addr, - regs->enable_mask, on ? ~0 : 0); + rc = regmap_update_bits(vib->regmap, vib->enable_addr, + regs->enable_mask, on ? regs->enable_mask : 0); return rc; } @@ -101,26 +139,24 @@ static int pm8xxx_vib_set(struct pm8xxx_vib *vib, bool on) static void pm8xxx_work_handler(struct work_struct *work) { struct pm8xxx_vib *vib = container_of(work, struct pm8xxx_vib, work); - const struct pm8xxx_regs *regs = vib->regs; - int rc; unsigned int val; + int rc; - rc = regmap_read(vib->regmap, regs->drv_addr, &val); + rc = regmap_read(vib->regmap, vib->drv_addr, &val); if (rc < 0) return; /* - * pmic vibrator supports voltage ranges from 1.2 to 3.1V, so + * pmic vibrator supports voltage ranges from MIN_LEVEL to MAX_LEVEL, so * scale the level to fit into these ranges. */ if (vib->speed) { vib->active = true; - vib->level = ((VIB_MAX_LEVELS * vib->speed) / MAX_FF_SPEED) + - VIB_MIN_LEVEL_mV; - vib->level /= 100; + vib->level = VIB_MIN_LEVEL_mV(vib); + vib->level += mult_frac(VIB_MAX_LEVELS(vib), vib->speed, MAX_FF_SPEED); } else { vib->active = false; - vib->level = VIB_MIN_LEVEL_mV / 100; + vib->level = VIB_MIN_LEVEL_mV(vib); } pm8xxx_vib_set(vib, vib->active); @@ -168,7 +204,7 @@ static int pm8xxx_vib_probe(struct platform_device *pdev) struct pm8xxx_vib *vib; struct input_dev *input_dev; int error; - unsigned int val; + unsigned int val, reg_base = 0; const struct pm8xxx_regs *regs; vib = devm_kzalloc(&pdev->dev, sizeof(*vib), GFP_KERNEL); @@ -186,15 +222,22 @@ static int pm8xxx_vib_probe(struct platform_device *pdev) INIT_WORK(&vib->work, pm8xxx_work_handler); vib->vib_input_dev = input_dev; + error = fwnode_property_read_u32(pdev->dev.fwnode, "reg", ®_base); + if (error < 0) + return dev_err_probe(&pdev->dev, error, "Failed to read reg address\n"); + regs = of_device_get_match_data(&pdev->dev); + vib->enable_addr = reg_base + regs->enable_offset; + vib->drv_addr = reg_base + regs->drv_offset; + vib->drv2_addr = reg_base + regs->drv2_offset; /* operate in manual mode */ - error = regmap_read(vib->regmap, regs->drv_addr, &val); + error = regmap_read(vib->regmap, vib->drv_addr, &val); if (error < 0) return error; val &= regs->drv_en_manual_mask; - error = regmap_write(vib->regmap, regs->drv_addr, val); + error = regmap_write(vib->regmap, vib->drv_addr, val); if (error < 0) return error; @@ -241,6 +284,7 @@ static const struct of_device_id pm8xxx_vib_id_table[] = { { .compatible = "qcom,pm8058-vib", .data = &pm8058_regs }, { .compatible = "qcom,pm8921-vib", .data = &pm8058_regs }, { .compatible = "qcom,pm8916-vib", .data = &pm8916_regs }, + { .compatible = "qcom,pmi632-vib", .data = &pmi632_regs }, { } }; MODULE_DEVICE_TABLE(of, pm8xxx_vib_id_table); diff --git a/drivers/input/mouse/cyapa.c b/drivers/input/mouse/cyapa.c index 5979deabe23d..2f2d925a55d7 100644 --- a/drivers/input/mouse/cyapa.c +++ b/drivers/input/mouse/cyapa.c @@ -1347,10 +1347,16 @@ static int cyapa_suspend(struct device *dev) u8 power_mode; int error; - error = mutex_lock_interruptible(&cyapa->state_sync_lock); + error = mutex_lock_interruptible(&cyapa->input->mutex); if (error) return error; + error = mutex_lock_interruptible(&cyapa->state_sync_lock); + if (error) { + mutex_unlock(&cyapa->input->mutex); + return error; + } + /* * Runtime PM is enable only when device is in operational mode and * users in use, so need check it before disable it to @@ -1385,6 +1391,8 @@ static int cyapa_suspend(struct device *dev) cyapa->irq_wake = (enable_irq_wake(client->irq) == 0); mutex_unlock(&cyapa->state_sync_lock); + mutex_unlock(&cyapa->input->mutex); + return 0; } @@ -1394,6 +1402,7 @@ static int cyapa_resume(struct device *dev) struct cyapa *cyapa = i2c_get_clientdata(client); int error; + mutex_lock(&cyapa->input->mutex); mutex_lock(&cyapa->state_sync_lock); if (device_may_wakeup(dev) && cyapa->irq_wake) { @@ -1412,6 +1421,7 @@ static int cyapa_resume(struct device *dev) enable_irq(client->irq); mutex_unlock(&cyapa->state_sync_lock); + mutex_unlock(&cyapa->input->mutex); return 0; } @@ -1449,8 +1459,8 @@ static const struct dev_pm_ops cyapa_pm_ops = { }; static const struct i2c_device_id cyapa_id_table[] = { - { "cyapa", 0 }, - { }, + { "cyapa" }, + { } }; MODULE_DEVICE_TABLE(i2c, cyapa_id_table); diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c index 8a72c200ccb5..c2aec5c360b3 100644 --- a/drivers/input/mouse/elan_i2c_core.c +++ b/drivers/input/mouse/elan_i2c_core.c @@ -1392,8 +1392,8 @@ err: static DEFINE_SIMPLE_DEV_PM_OPS(elan_pm_ops, elan_suspend, elan_resume); static const struct i2c_device_id elan_id[] = { - { DRIVER_NAME, 0 }, - { }, + { DRIVER_NAME }, + { } }; MODULE_DEVICE_TABLE(i2c, elan_id); diff --git a/drivers/input/mouse/synaptics_i2c.c b/drivers/input/mouse/synaptics_i2c.c index af5cc64c622d..56e9ba396858 100644 --- a/drivers/input/mouse/synaptics_i2c.c +++ b/drivers/input/mouse/synaptics_i2c.c @@ -630,8 +630,8 @@ static DEFINE_SIMPLE_DEV_PM_OPS(synaptics_i2c_pm, synaptics_i2c_suspend, synaptics_i2c_resume); static const struct i2c_device_id synaptics_i2c_id_table[] = { - { "synaptics_i2c", 0 }, - { }, + { "synaptics_i2c" }, + { } }; MODULE_DEVICE_TABLE(i2c, synaptics_i2c_id_table); diff --git a/drivers/input/rmi4/rmi_i2c.c b/drivers/input/rmi4/rmi_i2c.c index 091d4e23b629..3c0c5fd44702 100644 --- a/drivers/input/rmi4/rmi_i2c.c +++ b/drivers/input/rmi4/rmi_i2c.c @@ -365,7 +365,7 @@ static const struct dev_pm_ops rmi_i2c_pm = { }; static const struct i2c_device_id rmi_id[] = { - { "rmi4_i2c", 0 }, + { "rmi4_i2c" }, { } }; MODULE_DEVICE_TABLE(i2c, rmi_id); diff --git a/drivers/input/rmi4/rmi_smbus.c b/drivers/input/rmi4/rmi_smbus.c index b0b099b5528a..f3d0b40721df 100644 --- a/drivers/input/rmi4/rmi_smbus.c +++ b/drivers/input/rmi4/rmi_smbus.c @@ -413,7 +413,7 @@ static const struct dev_pm_ops rmi_smb_pm = { }; static const struct i2c_device_id rmi_id[] = { - { "rmi4_smbus", 0 }, + { "rmi4_smbus" }, { } }; MODULE_DEVICE_TABLE(i2c, rmi_id); diff --git a/drivers/input/serio/ioc3kbd.c b/drivers/input/serio/ioc3kbd.c index 50552dc7b4f5..676b0bda3d72 100644 --- a/drivers/input/serio/ioc3kbd.c +++ b/drivers/input/serio/ioc3kbd.c @@ -200,9 +200,16 @@ static void ioc3kbd_remove(struct platform_device *pdev) serio_unregister_port(d->aux); } +static const struct platform_device_id ioc3kbd_id_table[] = { + { "ioc3-kbd", }, + { } +}; +MODULE_DEVICE_TABLE(platform, ioc3kbd_id_table); + static struct platform_driver ioc3kbd_driver = { .probe = ioc3kbd_probe, .remove_new = ioc3kbd_remove, + .id_table = ioc3kbd_id_table, .driver = { .name = "ioc3-kbd", }, diff --git a/drivers/input/touchscreen/ad7879-i2c.c b/drivers/input/touchscreen/ad7879-i2c.c index 5c094ab74698..e5b99312c3d9 100644 --- a/drivers/input/touchscreen/ad7879-i2c.c +++ b/drivers/input/touchscreen/ad7879-i2c.c @@ -42,8 +42,8 @@ static int ad7879_i2c_probe(struct i2c_client *client) } static const struct i2c_device_id ad7879_id[] = { - { "ad7879", 0 }, - { "ad7889", 0 }, + { "ad7879" }, + { "ad7889" }, { } }; MODULE_DEVICE_TABLE(i2c, ad7879_id); diff --git a/drivers/input/touchscreen/ar1021_i2c.c b/drivers/input/touchscreen/ar1021_i2c.c index 64dfb749386f..8a588202447d 100644 --- a/drivers/input/touchscreen/ar1021_i2c.c +++ b/drivers/input/touchscreen/ar1021_i2c.c @@ -164,8 +164,8 @@ static DEFINE_SIMPLE_DEV_PM_OPS(ar1021_i2c_pm, ar1021_i2c_suspend, ar1021_i2c_resume); static const struct i2c_device_id ar1021_i2c_id[] = { - { "ar1021", 0 }, - { }, + { "ar1021" }, + { } }; MODULE_DEVICE_TABLE(i2c, ar1021_i2c_id); diff --git a/drivers/input/touchscreen/atmel_mxt_ts.c b/drivers/input/touchscreen/atmel_mxt_ts.c index 542a31448c8f..8a606bd441ae 100644 --- a/drivers/input/touchscreen/atmel_mxt_ts.c +++ b/drivers/input/touchscreen/atmel_mxt_ts.c @@ -3443,11 +3443,11 @@ MODULE_DEVICE_TABLE(acpi, mxt_acpi_id); #endif static const struct i2c_device_id mxt_id[] = { - { "qt602240_ts", 0 }, - { "atmel_mxt_ts", 0 }, - { "atmel_mxt_tp", 0 }, - { "maxtouch", 0 }, - { "mXT224", 0 }, + { "qt602240_ts" }, + { "atmel_mxt_ts" }, + { "atmel_mxt_tp" }, + { "maxtouch" }, + { "mXT224" }, { } }; MODULE_DEVICE_TABLE(i2c, mxt_id); diff --git a/drivers/input/touchscreen/auo-pixcir-ts.c b/drivers/input/touchscreen/auo-pixcir-ts.c index 90c682e7407f..8db2a112a476 100644 --- a/drivers/input/touchscreen/auo-pixcir-ts.c +++ b/drivers/input/touchscreen/auo-pixcir-ts.c @@ -617,7 +617,7 @@ static int auo_pixcir_probe(struct i2c_client *client) } static const struct i2c_device_id auo_pixcir_idtable[] = { - { "auo_pixcir_ts", 0 }, + { "auo_pixcir_ts" }, { } }; MODULE_DEVICE_TABLE(i2c, auo_pixcir_idtable); diff --git a/drivers/input/touchscreen/bu21013_ts.c b/drivers/input/touchscreen/bu21013_ts.c index 652439a79e21..6baebb7ec089 100644 --- a/drivers/input/touchscreen/bu21013_ts.c +++ b/drivers/input/touchscreen/bu21013_ts.c @@ -597,7 +597,7 @@ static int bu21013_resume(struct device *dev) static DEFINE_SIMPLE_DEV_PM_OPS(bu21013_dev_pm_ops, bu21013_suspend, bu21013_resume); static const struct i2c_device_id bu21013_id[] = { - { DRIVER_TP, 0 }, + { DRIVER_TP }, { } }; MODULE_DEVICE_TABLE(i2c, bu21013_id); diff --git a/drivers/input/touchscreen/bu21029_ts.c b/drivers/input/touchscreen/bu21029_ts.c index e1dfbd92ab64..686d0a6b1570 100644 --- a/drivers/input/touchscreen/bu21029_ts.c +++ b/drivers/input/touchscreen/bu21029_ts.c @@ -441,7 +441,7 @@ static int bu21029_resume(struct device *dev) static DEFINE_SIMPLE_DEV_PM_OPS(bu21029_pm_ops, bu21029_suspend, bu21029_resume); static const struct i2c_device_id bu21029_ids[] = { - { DRIVER_NAME, 0 }, + { DRIVER_NAME }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(i2c, bu21029_ids); diff --git a/drivers/input/touchscreen/chipone_icn8505.c b/drivers/input/touchscreen/chipone_icn8505.c index b56954830b33..c1b4fc28fa8d 100644 --- a/drivers/input/touchscreen/chipone_icn8505.c +++ b/drivers/input/touchscreen/chipone_icn8505.c @@ -68,7 +68,6 @@ struct icn8505_touch_data { struct icn8505_data { struct i2c_client *client; struct input_dev *input; - struct gpio_desc *wake_gpio; struct touchscreen_properties prop; char firmware_name[32]; }; diff --git a/drivers/input/touchscreen/cy8ctma140.c b/drivers/input/touchscreen/cy8ctma140.c index ea3895167b82..567c9dcaac91 100644 --- a/drivers/input/touchscreen/cy8ctma140.c +++ b/drivers/input/touchscreen/cy8ctma140.c @@ -322,7 +322,7 @@ static DEFINE_SIMPLE_DEV_PM_OPS(cy8ctma140_pm, cy8ctma140_suspend, cy8ctma140_resume); static const struct i2c_device_id cy8ctma140_idtable[] = { - { CY8CTMA140_NAME, 0 }, + { CY8CTMA140_NAME }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(i2c, cy8ctma140_idtable); diff --git a/drivers/input/touchscreen/cyttsp4_i2c.c b/drivers/input/touchscreen/cyttsp4_i2c.c index 80a6890cd45a..da32c151def5 100644 --- a/drivers/input/touchscreen/cyttsp4_i2c.c +++ b/drivers/input/touchscreen/cyttsp4_i2c.c @@ -50,7 +50,7 @@ static void cyttsp4_i2c_remove(struct i2c_client *client) } static const struct i2c_device_id cyttsp4_i2c_id[] = { - { CYTTSP4_I2C_NAME, 0 }, + { CYTTSP4_I2C_NAME }, { } }; MODULE_DEVICE_TABLE(i2c, cyttsp4_i2c_id); diff --git a/drivers/input/touchscreen/cyttsp5.c b/drivers/input/touchscreen/cyttsp5.c index 68527ede5c0e..3ca246ab192e 100644 --- a/drivers/input/touchscreen/cyttsp5.c +++ b/drivers/input/touchscreen/cyttsp5.c @@ -935,7 +935,7 @@ static const struct of_device_id cyttsp5_of_match[] = { MODULE_DEVICE_TABLE(of, cyttsp5_of_match); static const struct i2c_device_id cyttsp5_i2c_id[] = { - { CYTTSP5_NAME, 0, }, + { CYTTSP5_NAME }, { } }; MODULE_DEVICE_TABLE(i2c, cyttsp5_i2c_id); diff --git a/drivers/input/touchscreen/cyttsp_i2c.c b/drivers/input/touchscreen/cyttsp_i2c.c index 127a8fda1da4..bf13b3448a6b 100644 --- a/drivers/input/touchscreen/cyttsp_i2c.c +++ b/drivers/input/touchscreen/cyttsp_i2c.c @@ -48,7 +48,7 @@ static int cyttsp_i2c_probe(struct i2c_client *client) } static const struct i2c_device_id cyttsp_i2c_id[] = { - { CY_I2C_NAME, 0 }, + { CY_I2C_NAME }, { } }; MODULE_DEVICE_TABLE(i2c, cyttsp_i2c_id); diff --git a/drivers/input/touchscreen/edt-ft5x06.c b/drivers/input/touchscreen/edt-ft5x06.c index 2a1db1134476..06ec0f2e18ae 100644 --- a/drivers/input/touchscreen/edt-ft5x06.c +++ b/drivers/input/touchscreen/edt-ft5x06.c @@ -1462,6 +1462,10 @@ static const struct edt_i2c_chip_data edt_ft5x06_data = { .max_support_points = 5, }; +static const struct edt_i2c_chip_data edt_ft5452_data = { + .max_support_points = 5, +}; + static const struct edt_i2c_chip_data edt_ft5506_data = { .max_support_points = 10, }; @@ -1470,12 +1474,18 @@ static const struct edt_i2c_chip_data edt_ft6236_data = { .max_support_points = 2, }; +static const struct edt_i2c_chip_data edt_ft8719_data = { + .max_support_points = 10, +}; + static const struct i2c_device_id edt_ft5x06_ts_id[] = { { .name = "edt-ft5x06", .driver_data = (long)&edt_ft5x06_data }, { .name = "edt-ft5506", .driver_data = (long)&edt_ft5506_data }, { .name = "ev-ft5726", .driver_data = (long)&edt_ft5506_data }, + { .name = "ft5452", .driver_data = (long)&edt_ft5452_data }, /* Note no edt- prefix for compatibility with the ft6236.c driver */ { .name = "ft6236", .driver_data = (long)&edt_ft6236_data }, + { .name = "ft8719", .driver_data = (long)&edt_ft8719_data }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(i2c, edt_ft5x06_ts_id); @@ -1486,8 +1496,10 @@ static const struct of_device_id edt_ft5x06_of_match[] = { { .compatible = "edt,edt-ft5406", .data = &edt_ft5x06_data }, { .compatible = "edt,edt-ft5506", .data = &edt_ft5506_data }, { .compatible = "evervision,ev-ft5726", .data = &edt_ft5506_data }, + { .compatible = "focaltech,ft5452", .data = &edt_ft5452_data }, /* Note focaltech vendor prefix for compatibility with ft6236.c */ { .compatible = "focaltech,ft6236", .data = &edt_ft6236_data }, + { .compatible = "focaltech,ft8719", .data = &edt_ft8719_data }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, edt_ft5x06_of_match); diff --git a/drivers/input/touchscreen/eeti_ts.c b/drivers/input/touchscreen/eeti_ts.c index 5e4167f6c63e..48c69788b84a 100644 --- a/drivers/input/touchscreen/eeti_ts.c +++ b/drivers/input/touchscreen/eeti_ts.c @@ -273,7 +273,7 @@ static int eeti_ts_resume(struct device *dev) static DEFINE_SIMPLE_DEV_PM_OPS(eeti_ts_pm, eeti_ts_suspend, eeti_ts_resume); static const struct i2c_device_id eeti_ts_id[] = { - { "eeti_ts", 0 }, + { "eeti_ts" }, { } }; MODULE_DEVICE_TABLE(i2c, eeti_ts_id); diff --git a/drivers/input/touchscreen/egalax_ts.c b/drivers/input/touchscreen/egalax_ts.c index a7f7e7308267..f4e950920e84 100644 --- a/drivers/input/touchscreen/egalax_ts.c +++ b/drivers/input/touchscreen/egalax_ts.c @@ -218,7 +218,7 @@ static int egalax_ts_probe(struct i2c_client *client) } static const struct i2c_device_id egalax_ts_id[] = { - { "egalax_ts", 0 }, + { "egalax_ts" }, { } }; MODULE_DEVICE_TABLE(i2c, egalax_ts_id); diff --git a/drivers/input/touchscreen/ektf2127.c b/drivers/input/touchscreen/ektf2127.c index cc3103b9cbfb..ab8159e1c99d 100644 --- a/drivers/input/touchscreen/ektf2127.c +++ b/drivers/input/touchscreen/ektf2127.c @@ -335,8 +335,8 @@ MODULE_DEVICE_TABLE(of, ektf2127_of_match); #endif static const struct i2c_device_id ektf2127_i2c_id[] = { - { "ektf2127", 0 }, - { "ektf2132", 0 }, + { "ektf2127" }, + { "ektf2132" }, {} }; MODULE_DEVICE_TABLE(i2c, ektf2127_i2c_id); diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c index b068ff8afbc9..435714f18c23 100644 --- a/drivers/input/touchscreen/goodix.c +++ b/drivers/input/touchscreen/goodix.c @@ -1510,7 +1510,7 @@ static int goodix_resume(struct device *dev) static DEFINE_SIMPLE_DEV_PM_OPS(goodix_pm_ops, goodix_suspend, goodix_resume); static const struct i2c_device_id goodix_ts_id[] = { - { "GDIX1001:00", 0 }, + { "GDIX1001:00" }, { } }; MODULE_DEVICE_TABLE(i2c, goodix_ts_id); diff --git a/drivers/input/touchscreen/goodix_berlin_i2c.c b/drivers/input/touchscreen/goodix_berlin_i2c.c index 6ed9aa8088cb..2e7098078838 100644 --- a/drivers/input/touchscreen/goodix_berlin_i2c.c +++ b/drivers/input/touchscreen/goodix_berlin_i2c.c @@ -47,7 +47,7 @@ static int goodix_berlin_i2c_probe(struct i2c_client *client) } static const struct i2c_device_id goodix_berlin_i2c_id[] = { - { "gt9916", 0 }, + { "gt9916" }, { } }; diff --git a/drivers/input/touchscreen/hideep.c b/drivers/input/touchscreen/hideep.c index eae90676f4e5..682abbbe5bd6 100644 --- a/drivers/input/touchscreen/hideep.c +++ b/drivers/input/touchscreen/hideep.c @@ -1095,7 +1095,7 @@ static int hideep_probe(struct i2c_client *client) } static const struct i2c_device_id hideep_i2c_id[] = { - { HIDEEP_I2C_NAME, 0 }, + { HIDEEP_I2C_NAME }, { } }; MODULE_DEVICE_TABLE(i2c, hideep_i2c_id); diff --git a/drivers/input/touchscreen/himax_hx83112b.c b/drivers/input/touchscreen/himax_hx83112b.c index 4f6609dcdef3..bafabd06dabc 100644 --- a/drivers/input/touchscreen/himax_hx83112b.c +++ b/drivers/input/touchscreen/himax_hx83112b.c @@ -335,7 +335,7 @@ static int himax_resume(struct device *dev) static DEFINE_SIMPLE_DEV_PM_OPS(himax_pm_ops, himax_suspend, himax_resume); static const struct i2c_device_id himax_ts_id[] = { - { "hx83112b", 0 }, + { "hx83112b" }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(i2c, himax_ts_id); diff --git a/drivers/input/touchscreen/ilitek_ts_i2c.c b/drivers/input/touchscreen/ilitek_ts_i2c.c index fc4e39b6651a..3eb762896345 100644 --- a/drivers/input/touchscreen/ilitek_ts_i2c.c +++ b/drivers/input/touchscreen/ilitek_ts_i2c.c @@ -634,8 +634,8 @@ static int ilitek_resume(struct device *dev) static DEFINE_SIMPLE_DEV_PM_OPS(ilitek_pm_ops, ilitek_suspend, ilitek_resume); static const struct i2c_device_id ilitek_ts_i2c_id[] = { - { ILITEK_TS_NAME, 0 }, - { }, + { ILITEK_TS_NAME }, + { } }; MODULE_DEVICE_TABLE(i2c, ilitek_ts_i2c_id); diff --git a/drivers/input/touchscreen/max11801_ts.c b/drivers/input/touchscreen/max11801_ts.c index 8be6dade118c..f39633fc8dc2 100644 --- a/drivers/input/touchscreen/max11801_ts.c +++ b/drivers/input/touchscreen/max11801_ts.c @@ -213,7 +213,7 @@ static int max11801_ts_probe(struct i2c_client *client) } static const struct i2c_device_id max11801_ts_id[] = { - {"max11801", 0}, + { "max11801" }, { } }; MODULE_DEVICE_TABLE(i2c, max11801_ts_id); diff --git a/drivers/input/touchscreen/mcs5000_ts.c b/drivers/input/touchscreen/mcs5000_ts.c index ac28019ba4c3..5aff8dcda0dc 100644 --- a/drivers/input/touchscreen/mcs5000_ts.c +++ b/drivers/input/touchscreen/mcs5000_ts.c @@ -266,7 +266,7 @@ static DEFINE_SIMPLE_DEV_PM_OPS(mcs5000_ts_pm, mcs5000_ts_suspend, mcs5000_ts_resume); static const struct i2c_device_id mcs5000_ts_id[] = { - { "mcs5000_ts", 0 }, + { "mcs5000_ts" }, { } }; MODULE_DEVICE_TABLE(i2c, mcs5000_ts_id); diff --git a/drivers/input/touchscreen/melfas_mip4.c b/drivers/input/touchscreen/melfas_mip4.c index 78e1c63e530e..b99a0e3c4084 100644 --- a/drivers/input/touchscreen/melfas_mip4.c +++ b/drivers/input/touchscreen/melfas_mip4.c @@ -1569,8 +1569,8 @@ MODULE_DEVICE_TABLE(acpi, mip4_acpi_match); #endif static const struct i2c_device_id mip4_i2c_ids[] = { - { MIP4_DEVICE_NAME, 0 }, - { }, + { MIP4_DEVICE_NAME }, + { } }; MODULE_DEVICE_TABLE(i2c, mip4_i2c_ids); diff --git a/drivers/input/touchscreen/migor_ts.c b/drivers/input/touchscreen/migor_ts.c index 2384ea69a3f8..7511a134e302 100644 --- a/drivers/input/touchscreen/migor_ts.c +++ b/drivers/input/touchscreen/migor_ts.c @@ -211,7 +211,7 @@ static int migor_ts_resume(struct device *dev) static DEFINE_SIMPLE_DEV_PM_OPS(migor_ts_pm, migor_ts_suspend, migor_ts_resume); static const struct i2c_device_id migor_ts_id[] = { - { "migor_ts", 0 }, + { "migor_ts" }, { } }; MODULE_DEVICE_TABLE(i2c, migor_ts_id); diff --git a/drivers/input/touchscreen/mms114.c b/drivers/input/touchscreen/mms114.c index af233b6a16d9..9f947044c4d9 100644 --- a/drivers/input/touchscreen/mms114.c +++ b/drivers/input/touchscreen/mms114.c @@ -677,7 +677,7 @@ static int mms114_resume(struct device *dev) static DEFINE_SIMPLE_DEV_PM_OPS(mms114_pm_ops, mms114_suspend, mms114_resume); static const struct i2c_device_id mms114_id[] = { - { "mms114", 0 }, + { "mms114" }, { } }; MODULE_DEVICE_TABLE(i2c, mms114_id); diff --git a/drivers/input/touchscreen/raydium_i2c_ts.c b/drivers/input/touchscreen/raydium_i2c_ts.c index 13c500e776f6..92d75057de2d 100644 --- a/drivers/input/touchscreen/raydium_i2c_ts.c +++ b/drivers/input/touchscreen/raydium_i2c_ts.c @@ -1227,8 +1227,8 @@ static DEFINE_SIMPLE_DEV_PM_OPS(raydium_i2c_pm_ops, raydium_i2c_suspend, raydium_i2c_resume); static const struct i2c_device_id raydium_i2c_id[] = { - { "raydium_i2c", 0 }, - { "rm32380", 0 }, + { "raydium_i2c" }, + { "rm32380" }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(i2c, raydium_i2c_id); diff --git a/drivers/input/touchscreen/rohm_bu21023.c b/drivers/input/touchscreen/rohm_bu21023.c index 4493ad0c9322..06fa3a19d266 100644 --- a/drivers/input/touchscreen/rohm_bu21023.c +++ b/drivers/input/touchscreen/rohm_bu21023.c @@ -1165,7 +1165,7 @@ static int rohm_bu21023_i2c_probe(struct i2c_client *client) } static const struct i2c_device_id rohm_bu21023_i2c_id[] = { - { BU21023_NAME, 0 }, + { BU21023_NAME }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(i2c, rohm_bu21023_i2c_id); diff --git a/drivers/input/touchscreen/s6sy761.c b/drivers/input/touchscreen/s6sy761.c index 149cc2c4925e..a529217e748f 100644 --- a/drivers/input/touchscreen/s6sy761.c +++ b/drivers/input/touchscreen/s6sy761.c @@ -520,8 +520,8 @@ MODULE_DEVICE_TABLE(of, s6sy761_of_match); #endif static const struct i2c_device_id s6sy761_id[] = { - { "s6sy761", 0 }, - { }, + { "s6sy761" }, + { } }; MODULE_DEVICE_TABLE(i2c, s6sy761_id); diff --git a/drivers/input/touchscreen/silead.c b/drivers/input/touchscreen/silead.c index 62f562ad5026..bbd366dcb69a 100644 --- a/drivers/input/touchscreen/silead.c +++ b/drivers/input/touchscreen/silead.c @@ -785,12 +785,12 @@ static int silead_ts_resume(struct device *dev) static DEFINE_SIMPLE_DEV_PM_OPS(silead_ts_pm, silead_ts_suspend, silead_ts_resume); static const struct i2c_device_id silead_ts_id[] = { - { "gsl1680", 0 }, - { "gsl1688", 0 }, - { "gsl3670", 0 }, - { "gsl3675", 0 }, - { "gsl3692", 0 }, - { "mssl1680", 0 }, + { "gsl1680" }, + { "gsl1688" }, + { "gsl3670" }, + { "gsl3675" }, + { "gsl3692" }, + { "mssl1680" }, { } }; MODULE_DEVICE_TABLE(i2c, silead_ts_id); diff --git a/drivers/input/touchscreen/sis_i2c.c b/drivers/input/touchscreen/sis_i2c.c index ed56cb546f39..2023c6df416f 100644 --- a/drivers/input/touchscreen/sis_i2c.c +++ b/drivers/input/touchscreen/sis_i2c.c @@ -374,8 +374,8 @@ MODULE_DEVICE_TABLE(of, sis_ts_dt_ids); #endif static const struct i2c_device_id sis_ts_id[] = { - { SIS_I2C_NAME, 0 }, - { "9200-ts", 0 }, + { SIS_I2C_NAME }, + { "9200-ts" }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(i2c, sis_ts_id); diff --git a/drivers/input/touchscreen/stmfts.c b/drivers/input/touchscreen/stmfts.c index 85010fa07908..119cd26851cf 100644 --- a/drivers/input/touchscreen/stmfts.c +++ b/drivers/input/touchscreen/stmfts.c @@ -789,8 +789,8 @@ MODULE_DEVICE_TABLE(of, stmfts_of_match); #endif static const struct i2c_device_id stmfts_id[] = { - { "stmfts", 0 }, - { }, + { "stmfts" }, + { } }; MODULE_DEVICE_TABLE(i2c, stmfts_id); diff --git a/drivers/input/touchscreen/sur40.c b/drivers/input/touchscreen/sur40.c index ae3aab428337..5f2cf8881e72 100644 --- a/drivers/input/touchscreen/sur40.c +++ b/drivers/input/touchscreen/sur40.c @@ -421,7 +421,7 @@ static void sur40_report_blob(struct sur40_blob *blob, struct input_dev *input) if (blob->type != SUR40_TOUCH) return; - slotnum = input_mt_get_slot_by_key(input, blob->blob_id); + slotnum = input_mt_get_slot_by_key(input, le16_to_cpu(blob->blob_id)); if (slotnum < 0 || slotnum >= MAX_CONTACTS) return; diff --git a/drivers/input/touchscreen/tsc2004.c b/drivers/input/touchscreen/tsc2004.c index 89c5248f66f6..b673098535ad 100644 --- a/drivers/input/touchscreen/tsc2004.c +++ b/drivers/input/touchscreen/tsc2004.c @@ -48,7 +48,7 @@ static void tsc2004_remove(struct i2c_client *i2c) } static const struct i2c_device_id tsc2004_idtable[] = { - { "tsc2004", 0 }, + { "tsc2004" }, { } }; MODULE_DEVICE_TABLE(i2c, tsc2004_idtable); diff --git a/drivers/input/touchscreen/tsc2007_core.c b/drivers/input/touchscreen/tsc2007_core.c index b3655250d4a7..8d832a372b89 100644 --- a/drivers/input/touchscreen/tsc2007_core.c +++ b/drivers/input/touchscreen/tsc2007_core.c @@ -400,7 +400,7 @@ static int tsc2007_probe(struct i2c_client *client) } static const struct i2c_device_id tsc2007_idtable[] = { - { "tsc2007", 0 }, + { "tsc2007" }, { } }; diff --git a/drivers/input/touchscreen/wacom_i2c.c b/drivers/input/touchscreen/wacom_i2c.c index f389f9c004a9..486230985bf0 100644 --- a/drivers/input/touchscreen/wacom_i2c.c +++ b/drivers/input/touchscreen/wacom_i2c.c @@ -253,8 +253,8 @@ static int wacom_i2c_resume(struct device *dev) static DEFINE_SIMPLE_DEV_PM_OPS(wacom_i2c_pm, wacom_i2c_suspend, wacom_i2c_resume); static const struct i2c_device_id wacom_i2c_id[] = { - { "WAC_I2C_EMR", 0 }, - { }, + { "WAC_I2C_EMR" }, + { } }; MODULE_DEVICE_TABLE(i2c, wacom_i2c_id); diff --git a/drivers/input/touchscreen/wdt87xx_i2c.c b/drivers/input/touchscreen/wdt87xx_i2c.c index 32c7be54434c..698fc7e0ee7f 100644 --- a/drivers/input/touchscreen/wdt87xx_i2c.c +++ b/drivers/input/touchscreen/wdt87xx_i2c.c @@ -1148,7 +1148,7 @@ static int wdt87xx_resume(struct device *dev) static DEFINE_SIMPLE_DEV_PM_OPS(wdt87xx_pm_ops, wdt87xx_suspend, wdt87xx_resume); static const struct i2c_device_id wdt87xx_dev_id[] = { - { WDT87XX_NAME, 0 }, + { WDT87XX_NAME }, { } }; MODULE_DEVICE_TABLE(i2c, wdt87xx_dev_id); diff --git a/drivers/input/touchscreen/zet6223.c b/drivers/input/touchscreen/zet6223.c index 1a034471f103..27333fded9a9 100644 --- a/drivers/input/touchscreen/zet6223.c +++ b/drivers/input/touchscreen/zet6223.c @@ -25,8 +25,6 @@ struct zet6223_ts { struct i2c_client *client; struct input_dev *input; - struct regulator *vcc; - struct regulator *vio; struct touchscreen_properties prop; struct regulator_bulk_data supplies[2]; u16 max_x; @@ -238,7 +236,7 @@ static const struct of_device_id zet6223_of_match[] = { MODULE_DEVICE_TABLE(of, zet6223_of_match); static const struct i2c_device_id zet6223_id[] = { - { "zet6223", 0}, + { "zet6223" }, { } }; MODULE_DEVICE_TABLE(i2c, zet6223_id); diff --git a/drivers/input/touchscreen/zforce_ts.c b/drivers/input/touchscreen/zforce_ts.c index 5680075f0bb8..fdf2d1e770c8 100644 --- a/drivers/input/touchscreen/zforce_ts.c +++ b/drivers/input/touchscreen/zforce_ts.c @@ -923,7 +923,7 @@ static int zforce_probe(struct i2c_client *client) } static struct i2c_device_id zforce_idtable[] = { - { "zforce-ts", 0 }, + { "zforce-ts" }, { } }; MODULE_DEVICE_TABLE(i2c, zforce_idtable); diff --git a/drivers/irqchip/irq-riscv-imsic-early.c b/drivers/irqchip/irq-riscv-imsic-early.c index 886418ec06cb..4fbb37074d29 100644 --- a/drivers/irqchip/irq-riscv-imsic-early.c +++ b/drivers/irqchip/irq-riscv-imsic-early.c @@ -49,7 +49,7 @@ static int __init imsic_ipi_domain_init(void) return virq < 0 ? virq : -ENOMEM; /* Set vIRQ range */ - riscv_ipi_set_virq_range(virq, IMSIC_NR_IPI, true); + riscv_ipi_set_virq_range(virq, IMSIC_NR_IPI); /* Announce that IMSIC is providing IPIs */ pr_info("%pfwP: providing IPIs using interrupt %d\n", imsic->fwnode, IMSIC_IPI_ID); diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 1e0085cd9a9a..2818e24e2a51 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -3142,7 +3142,7 @@ phy_interface_t ksz_get_xmii(struct ksz_device *dev, int port, bool gbit) else interface = PHY_INTERFACE_MODE_MII; } else if (val == bitval[P_RMII_SEL]) { - interface = PHY_INTERFACE_MODE_RGMII; + interface = PHY_INTERFACE_MODE_RMII; } else { interface = PHY_INTERFACE_MODE_RGMII; if (data8 & P_RGMII_ID_EG_ENABLE) diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index 2d8a66ea82fa..713a595370bf 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -312,7 +312,6 @@ static int ena_com_init_io_sq(struct ena_com_dev *ena_dev, struct ena_com_io_sq *io_sq) { size_t size; - int dev_node = 0; memset(&io_sq->desc_addr, 0x0, sizeof(io_sq->desc_addr)); @@ -325,12 +324,9 @@ static int ena_com_init_io_sq(struct ena_com_dev *ena_dev, size = io_sq->desc_entry_size * io_sq->q_depth; if (io_sq->mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_HOST) { - dev_node = dev_to_node(ena_dev->dmadev); - set_dev_node(ena_dev->dmadev, ctx->numa_node); io_sq->desc_addr.virt_addr = dma_alloc_coherent(ena_dev->dmadev, size, &io_sq->desc_addr.phys_addr, GFP_KERNEL); - set_dev_node(ena_dev->dmadev, dev_node); if (!io_sq->desc_addr.virt_addr) { io_sq->desc_addr.virt_addr = dma_alloc_coherent(ena_dev->dmadev, size, @@ -354,10 +350,7 @@ static int ena_com_init_io_sq(struct ena_com_dev *ena_dev, size = (size_t)io_sq->bounce_buf_ctrl.buffer_size * io_sq->bounce_buf_ctrl.buffers_num; - dev_node = dev_to_node(ena_dev->dmadev); - set_dev_node(ena_dev->dmadev, ctx->numa_node); io_sq->bounce_buf_ctrl.base_buffer = devm_kzalloc(ena_dev->dmadev, size, GFP_KERNEL); - set_dev_node(ena_dev->dmadev, dev_node); if (!io_sq->bounce_buf_ctrl.base_buffer) io_sq->bounce_buf_ctrl.base_buffer = devm_kzalloc(ena_dev->dmadev, size, GFP_KERNEL); @@ -397,7 +390,6 @@ static int ena_com_init_io_cq(struct ena_com_dev *ena_dev, struct ena_com_io_cq *io_cq) { size_t size; - int prev_node = 0; memset(&io_cq->cdesc_addr, 0x0, sizeof(io_cq->cdesc_addr)); @@ -409,11 +401,8 @@ static int ena_com_init_io_cq(struct ena_com_dev *ena_dev, size = io_cq->cdesc_entry_size_in_bytes * io_cq->q_depth; - prev_node = dev_to_node(ena_dev->dmadev); - set_dev_node(ena_dev->dmadev, ctx->numa_node); io_cq->cdesc_addr.virt_addr = dma_alloc_coherent(ena_dev->dmadev, size, &io_cq->cdesc_addr.phys_addr, GFP_KERNEL); - set_dev_node(ena_dev->dmadev, prev_node); if (!io_cq->cdesc_addr.virt_addr) { io_cq->cdesc_addr.virt_addr = dma_alloc_coherent(ena_dev->dmadev, size, &io_cq->cdesc_addr.phys_addr, diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index f604119efc80..5f26fc3ad655 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -1117,18 +1117,30 @@ static int enic_set_vf_port(struct net_device *netdev, int vf, pp->request = nla_get_u8(port[IFLA_PORT_REQUEST]); if (port[IFLA_PORT_PROFILE]) { + if (nla_len(port[IFLA_PORT_PROFILE]) != PORT_PROFILE_MAX) { + memcpy(pp, &prev_pp, sizeof(*pp)); + return -EINVAL; + } pp->set |= ENIC_SET_NAME; memcpy(pp->name, nla_data(port[IFLA_PORT_PROFILE]), PORT_PROFILE_MAX); } if (port[IFLA_PORT_INSTANCE_UUID]) { + if (nla_len(port[IFLA_PORT_INSTANCE_UUID]) != PORT_UUID_MAX) { + memcpy(pp, &prev_pp, sizeof(*pp)); + return -EINVAL; + } pp->set |= ENIC_SET_INSTANCE; memcpy(pp->instance_uuid, nla_data(port[IFLA_PORT_INSTANCE_UUID]), PORT_UUID_MAX); } if (port[IFLA_PORT_HOST_UUID]) { + if (nla_len(port[IFLA_PORT_HOST_UUID]) != PORT_UUID_MAX) { + memcpy(pp, &prev_pp, sizeof(*pp)); + return -EINVAL; + } pp->set |= ENIC_SET_HOST; memcpy(pp->host_uuid, nla_data(port[IFLA_PORT_HOST_UUID]), PORT_UUID_MAX); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index a72d8a2eb0b3..881ece735dcf 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -4130,6 +4130,14 @@ free_queue_mem: return ret; } +static void fec_enet_deinit(struct net_device *ndev) +{ + struct fec_enet_private *fep = netdev_priv(ndev); + + netif_napi_del(&fep->napi); + fec_enet_free_queue(ndev); +} + #ifdef CONFIG_OF static int fec_reset_phy(struct platform_device *pdev) { @@ -4524,6 +4532,7 @@ failed_register: fec_enet_mii_remove(fep); failed_mii_init: failed_irq: + fec_enet_deinit(ndev); failed_init: fec_ptp_stop(pdev); failed_reset: @@ -4587,6 +4596,7 @@ fec_drv_remove(struct platform_device *pdev) pm_runtime_put_noidle(&pdev->dev); pm_runtime_disable(&pdev->dev); + fec_enet_deinit(ndev); free_netdev(ndev); } diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index f9e94be36e97..2e98a2a0bead 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -1225,6 +1225,28 @@ s32 e1000_enable_ulp_lpt_lp(struct e1000_hw *hw, bool to_sx) } release: + /* Switching PHY interface always returns MDI error + * so disable retry mechanism to avoid wasting time + */ + e1000e_disable_phy_retry(hw); + + /* Force SMBus mode in PHY */ + ret_val = e1000_read_phy_reg_hv_locked(hw, CV_SMB_CTRL, &phy_reg); + if (ret_val) { + e1000e_enable_phy_retry(hw); + hw->phy.ops.release(hw); + goto out; + } + phy_reg |= CV_SMB_CTRL_FORCE_SMBUS; + e1000_write_phy_reg_hv_locked(hw, CV_SMB_CTRL, phy_reg); + + e1000e_enable_phy_retry(hw); + + /* Force SMBus mode in MAC */ + mac_reg = er32(CTRL_EXT); + mac_reg |= E1000_CTRL_EXT_FORCE_SMBUS; + ew32(CTRL_EXT, mac_reg); + hw->phy.ops.release(hw); out: if (ret_val) diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 220d62fca55d..da5c59daf8ba 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -6623,7 +6623,6 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime) struct e1000_hw *hw = &adapter->hw; u32 ctrl, ctrl_ext, rctl, status, wufc; int retval = 0; - u16 smb_ctrl; /* Runtime suspend should only enable wakeup for link changes */ if (runtime) @@ -6697,23 +6696,6 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime) if (retval) return retval; } - - /* Force SMBUS to allow WOL */ - /* Switching PHY interface always returns MDI error - * so disable retry mechanism to avoid wasting time - */ - e1000e_disable_phy_retry(hw); - - e1e_rphy(hw, CV_SMB_CTRL, &smb_ctrl); - smb_ctrl |= CV_SMB_CTRL_FORCE_SMBUS; - e1e_wphy(hw, CV_SMB_CTRL, smb_ctrl); - - e1000e_enable_phy_retry(hw); - - /* Force SMBus mode in MAC */ - ctrl_ext = er32(CTRL_EXT); - ctrl_ext |= E1000_CTRL_EXT_FORCE_SMBUS; - ew32(CTRL_EXT, ctrl_ext); } /* Ensure that the appropriate bits are set in LPI_CTRL diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 1f188c052828..284c3fad5a6e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -11171,6 +11171,8 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit, ret = i40e_reset(pf); if (!ret) i40e_rebuild(pf, reinit, lock_acquired); + else + dev_err(&pf->pdev->dev, "%s: i40e_reset() FAILED", __func__); } /** @@ -16335,6 +16337,139 @@ unmap: } /** + * i40e_enable_mc_magic_wake - enable multicast magic packet wake up + * using the mac_address_write admin q function + * @pf: pointer to i40e_pf struct + **/ +static void i40e_enable_mc_magic_wake(struct i40e_pf *pf) +{ + struct i40e_vsi *main_vsi = i40e_pf_get_main_vsi(pf); + struct i40e_hw *hw = &pf->hw; + u8 mac_addr[6]; + u16 flags = 0; + int ret; + + /* Get current MAC address in case it's an LAA */ + if (main_vsi && main_vsi->netdev) { + ether_addr_copy(mac_addr, main_vsi->netdev->dev_addr); + } else { + dev_err(&pf->pdev->dev, + "Failed to retrieve MAC address; using default\n"); + ether_addr_copy(mac_addr, hw->mac.addr); + } + + /* The FW expects the mac address write cmd to first be called with + * one of these flags before calling it again with the multicast + * enable flags. + */ + flags = I40E_AQC_WRITE_TYPE_LAA_WOL; + + if (hw->func_caps.flex10_enable && hw->partition_id != 1) + flags = I40E_AQC_WRITE_TYPE_LAA_ONLY; + + ret = i40e_aq_mac_address_write(hw, flags, mac_addr, NULL); + if (ret) { + dev_err(&pf->pdev->dev, + "Failed to update MAC address registers; cannot enable Multicast Magic packet wake up"); + return; + } + + flags = I40E_AQC_MC_MAG_EN + | I40E_AQC_WOL_PRESERVE_ON_PFR + | I40E_AQC_WRITE_TYPE_UPDATE_MC_MAG; + ret = i40e_aq_mac_address_write(hw, flags, mac_addr, NULL); + if (ret) + dev_err(&pf->pdev->dev, + "Failed to enable Multicast Magic Packet wake up\n"); +} + +/** + * i40e_io_suspend - suspend all IO operations + * @pf: pointer to i40e_pf struct + * + **/ +static int i40e_io_suspend(struct i40e_pf *pf) +{ + struct i40e_hw *hw = &pf->hw; + + set_bit(__I40E_DOWN, pf->state); + + /* Ensure service task will not be running */ + del_timer_sync(&pf->service_timer); + cancel_work_sync(&pf->service_task); + + /* Client close must be called explicitly here because the timer + * has been stopped. + */ + i40e_notify_client_of_netdev_close(pf, false); + + if (test_bit(I40E_HW_CAP_WOL_MC_MAGIC_PKT_WAKE, pf->hw.caps) && + pf->wol_en) + i40e_enable_mc_magic_wake(pf); + + /* Since we're going to destroy queues during the + * i40e_clear_interrupt_scheme() we should hold the RTNL lock for this + * whole section + */ + rtnl_lock(); + + i40e_prep_for_reset(pf); + + wr32(hw, I40E_PFPM_APM, (pf->wol_en ? I40E_PFPM_APM_APME_MASK : 0)); + wr32(hw, I40E_PFPM_WUFC, (pf->wol_en ? I40E_PFPM_WUFC_MAG_MASK : 0)); + + /* Clear the interrupt scheme and release our IRQs so that the system + * can safely hibernate even when there are a large number of CPUs. + * Otherwise hibernation might fail when mapping all the vectors back + * to CPU0. + */ + i40e_clear_interrupt_scheme(pf); + + rtnl_unlock(); + + return 0; +} + +/** + * i40e_io_resume - resume IO operations + * @pf: pointer to i40e_pf struct + * + **/ +static int i40e_io_resume(struct i40e_pf *pf) +{ + struct device *dev = &pf->pdev->dev; + int err; + + /* We need to hold the RTNL lock prior to restoring interrupt schemes, + * since we're going to be restoring queues + */ + rtnl_lock(); + + /* We cleared the interrupt scheme when we suspended, so we need to + * restore it now to resume device functionality. + */ + err = i40e_restore_interrupt_scheme(pf); + if (err) { + dev_err(dev, "Cannot restore interrupt scheme: %d\n", + err); + } + + clear_bit(__I40E_DOWN, pf->state); + i40e_reset_and_rebuild(pf, false, true); + + rtnl_unlock(); + + /* Clear suspended state last after everything is recovered */ + clear_bit(__I40E_SUSPENDED, pf->state); + + /* Restart the service task */ + mod_timer(&pf->service_timer, + round_jiffies(jiffies + pf->service_timer_period)); + + return 0; +} + +/** * i40e_pci_error_detected - warning that something funky happened in PCI land * @pdev: PCI device information struct * @error: the type of PCI error @@ -16358,7 +16493,7 @@ static pci_ers_result_t i40e_pci_error_detected(struct pci_dev *pdev, /* shutdown all operations */ if (!test_bit(__I40E_SUSPENDED, pf->state)) - i40e_prep_for_reset(pf); + i40e_io_suspend(pf); /* Request a slot reset */ return PCI_ERS_RESULT_NEED_RESET; @@ -16380,7 +16515,8 @@ static pci_ers_result_t i40e_pci_error_slot_reset(struct pci_dev *pdev) u32 reg; dev_dbg(&pdev->dev, "%s\n", __func__); - if (pci_enable_device_mem(pdev)) { + /* enable I/O and memory of the device */ + if (pci_enable_device(pdev)) { dev_info(&pdev->dev, "Cannot re-enable PCI device after reset.\n"); result = PCI_ERS_RESULT_DISCONNECT; @@ -16443,54 +16579,7 @@ static void i40e_pci_error_resume(struct pci_dev *pdev) if (test_bit(__I40E_SUSPENDED, pf->state)) return; - i40e_handle_reset_warning(pf, false); -} - -/** - * i40e_enable_mc_magic_wake - enable multicast magic packet wake up - * using the mac_address_write admin q function - * @pf: pointer to i40e_pf struct - **/ -static void i40e_enable_mc_magic_wake(struct i40e_pf *pf) -{ - struct i40e_vsi *main_vsi = i40e_pf_get_main_vsi(pf); - struct i40e_hw *hw = &pf->hw; - u8 mac_addr[6]; - u16 flags = 0; - int ret; - - /* Get current MAC address in case it's an LAA */ - if (main_vsi && main_vsi->netdev) { - ether_addr_copy(mac_addr, main_vsi->netdev->dev_addr); - } else { - dev_err(&pf->pdev->dev, - "Failed to retrieve MAC address; using default\n"); - ether_addr_copy(mac_addr, hw->mac.addr); - } - - /* The FW expects the mac address write cmd to first be called with - * one of these flags before calling it again with the multicast - * enable flags. - */ - flags = I40E_AQC_WRITE_TYPE_LAA_WOL; - - if (hw->func_caps.flex10_enable && hw->partition_id != 1) - flags = I40E_AQC_WRITE_TYPE_LAA_ONLY; - - ret = i40e_aq_mac_address_write(hw, flags, mac_addr, NULL); - if (ret) { - dev_err(&pf->pdev->dev, - "Failed to update MAC address registers; cannot enable Multicast Magic packet wake up"); - return; - } - - flags = I40E_AQC_MC_MAG_EN - | I40E_AQC_WOL_PRESERVE_ON_PFR - | I40E_AQC_WRITE_TYPE_UPDATE_MC_MAG; - ret = i40e_aq_mac_address_write(hw, flags, mac_addr, NULL); - if (ret) - dev_err(&pf->pdev->dev, - "Failed to enable Multicast Magic Packet wake up\n"); + i40e_io_resume(pf); } /** @@ -16552,48 +16641,11 @@ static void i40e_shutdown(struct pci_dev *pdev) static int i40e_suspend(struct device *dev) { struct i40e_pf *pf = dev_get_drvdata(dev); - struct i40e_hw *hw = &pf->hw; /* If we're already suspended, then there is nothing to do */ if (test_and_set_bit(__I40E_SUSPENDED, pf->state)) return 0; - - set_bit(__I40E_DOWN, pf->state); - - /* Ensure service task will not be running */ - del_timer_sync(&pf->service_timer); - cancel_work_sync(&pf->service_task); - - /* Client close must be called explicitly here because the timer - * has been stopped. - */ - i40e_notify_client_of_netdev_close(pf, false); - - if (test_bit(I40E_HW_CAP_WOL_MC_MAGIC_PKT_WAKE, pf->hw.caps) && - pf->wol_en) - i40e_enable_mc_magic_wake(pf); - - /* Since we're going to destroy queues during the - * i40e_clear_interrupt_scheme() we should hold the RTNL lock for this - * whole section - */ - rtnl_lock(); - - i40e_prep_for_reset(pf); - - wr32(hw, I40E_PFPM_APM, (pf->wol_en ? I40E_PFPM_APM_APME_MASK : 0)); - wr32(hw, I40E_PFPM_WUFC, (pf->wol_en ? I40E_PFPM_WUFC_MAG_MASK : 0)); - - /* Clear the interrupt scheme and release our IRQs so that the system - * can safely hibernate even when there are a large number of CPUs. - * Otherwise hibernation might fail when mapping all the vectors back - * to CPU0. - */ - i40e_clear_interrupt_scheme(pf); - - rtnl_unlock(); - - return 0; + return i40e_io_suspend(pf); } /** @@ -16603,39 +16655,11 @@ static int i40e_suspend(struct device *dev) static int i40e_resume(struct device *dev) { struct i40e_pf *pf = dev_get_drvdata(dev); - int err; /* If we're not suspended, then there is nothing to do */ if (!test_bit(__I40E_SUSPENDED, pf->state)) return 0; - - /* We need to hold the RTNL lock prior to restoring interrupt schemes, - * since we're going to be restoring queues - */ - rtnl_lock(); - - /* We cleared the interrupt scheme when we suspended, so we need to - * restore it now to resume device functionality. - */ - err = i40e_restore_interrupt_scheme(pf); - if (err) { - dev_err(dev, "Cannot restore interrupt scheme: %d\n", - err); - } - - clear_bit(__I40E_DOWN, pf->state); - i40e_reset_and_rebuild(pf, false, true); - - rtnl_unlock(); - - /* Clear suspended state last after everything is recovered */ - clear_bit(__I40E_SUSPENDED, pf->state); - - /* Restart the service task */ - mod_timer(&pf->service_timer, - round_jiffies(jiffies + pf->service_timer_period)); - - return 0; + return i40e_io_resume(pf); } static const struct pci_error_handlers i40e_err_handler = { diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c index c4b69655cdf5..704e9ad5144e 100644 --- a/drivers/net/ethernet/intel/ice/devlink/devlink.c +++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c @@ -1388,7 +1388,7 @@ enum ice_param_id { ICE_DEVLINK_PARAM_ID_TX_SCHED_LAYERS, }; -static const struct devlink_param ice_devlink_params[] = { +static const struct devlink_param ice_dvl_rdma_params[] = { DEVLINK_PARAM_GENERIC(ENABLE_ROCE, BIT(DEVLINK_PARAM_CMODE_RUNTIME), ice_devlink_enable_roce_get, ice_devlink_enable_roce_set, @@ -1397,6 +1397,9 @@ static const struct devlink_param ice_devlink_params[] = { ice_devlink_enable_iw_get, ice_devlink_enable_iw_set, ice_devlink_enable_iw_validate), +}; + +static const struct devlink_param ice_dvl_sched_params[] = { DEVLINK_PARAM_DRIVER(ICE_DEVLINK_PARAM_ID_TX_SCHED_LAYERS, "tx_scheduling_layers", DEVLINK_PARAM_TYPE_U8, @@ -1464,21 +1467,31 @@ int ice_devlink_register_params(struct ice_pf *pf) { struct devlink *devlink = priv_to_devlink(pf); struct ice_hw *hw = &pf->hw; - size_t params_size; + int status; - params_size = ARRAY_SIZE(ice_devlink_params); + status = devl_params_register(devlink, ice_dvl_rdma_params, + ARRAY_SIZE(ice_dvl_rdma_params)); + if (status) + return status; - if (!hw->func_caps.common_cap.tx_sched_topo_comp_mode_en) - params_size--; + if (hw->func_caps.common_cap.tx_sched_topo_comp_mode_en) + status = devl_params_register(devlink, ice_dvl_sched_params, + ARRAY_SIZE(ice_dvl_sched_params)); - return devl_params_register(devlink, ice_devlink_params, - params_size); + return status; } void ice_devlink_unregister_params(struct ice_pf *pf) { - devl_params_unregister(priv_to_devlink(pf), ice_devlink_params, - ARRAY_SIZE(ice_devlink_params)); + struct devlink *devlink = priv_to_devlink(pf); + struct ice_hw *hw = &pf->hw; + + devl_params_unregister(devlink, ice_dvl_rdma_params, + ARRAY_SIZE(ice_dvl_rdma_params)); + + if (hw->func_caps.common_cap.tx_sched_topo_comp_mode_en) + devl_params_unregister(devlink, ice_dvl_sched_params, + ARRAY_SIZE(ice_dvl_sched_params)); } #define ICE_DEVLINK_READ_BLK_SIZE (1024 * 1024) diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 5649b257e631..24716a3b494c 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -3148,6 +3148,16 @@ ice_get_link_speed_based_on_phy_type(u64 phy_type_low, u64 phy_type_high) case ICE_PHY_TYPE_HIGH_100G_AUI2: speed_phy_type_high = ICE_AQ_LINK_SPEED_100GB; break; + case ICE_PHY_TYPE_HIGH_200G_CR4_PAM4: + case ICE_PHY_TYPE_HIGH_200G_SR4: + case ICE_PHY_TYPE_HIGH_200G_FR4: + case ICE_PHY_TYPE_HIGH_200G_LR4: + case ICE_PHY_TYPE_HIGH_200G_DR4: + case ICE_PHY_TYPE_HIGH_200G_KR4_PAM4: + case ICE_PHY_TYPE_HIGH_200G_AUI4_AOC_ACC: + case ICE_PHY_TYPE_HIGH_200G_AUI4: + speed_phy_type_high = ICE_AQ_LINK_SPEED_200GB; + break; default: speed_phy_type_high = ICE_AQ_LINK_SPEED_UNKNOWN; break; diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c index 2e9ad27cb9d1..6e8f2aab6080 100644 --- a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c @@ -45,14 +45,15 @@ int ice_vsi_add_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan) return -EINVAL; err = ice_fltr_add_vlan(vsi, vlan); - if (err && err != -EEXIST) { + if (!err) + vsi->num_vlan++; + else if (err == -EEXIST) + err = 0; + else dev_err(ice_pf_to_dev(vsi->back), "Failure Adding VLAN %d on VSI %i, status %d\n", vlan->vid, vsi->vsi_num, err); - return err; - } - vsi->num_vlan++; - return 0; + return err; } /** diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c index 52ceda6306a3..f1ee5584e8fa 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_lib.c +++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c @@ -1394,6 +1394,7 @@ static int idpf_vport_open(struct idpf_vport *vport, bool alloc_res) } idpf_rx_init_buf_tail(vport); + idpf_vport_intr_ena(vport); err = idpf_send_config_queues_msg(vport); if (err) { diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index 285da2177ee4..b023704bbbda 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -3746,9 +3746,9 @@ static void idpf_vport_intr_ena_irq_all(struct idpf_vport *vport) */ void idpf_vport_intr_deinit(struct idpf_vport *vport) { + idpf_vport_intr_dis_irq_all(vport); idpf_vport_intr_napi_dis_all(vport); idpf_vport_intr_napi_del_all(vport); - idpf_vport_intr_dis_irq_all(vport); idpf_vport_intr_rel_irq(vport); } @@ -4179,7 +4179,6 @@ int idpf_vport_intr_init(struct idpf_vport *vport) idpf_vport_intr_map_vector_to_qs(vport); idpf_vport_intr_napi_add_all(vport); - idpf_vport_intr_napi_ena_all(vport); err = vport->adapter->dev_ops.reg_ops.intr_reg_init(vport); if (err) @@ -4193,17 +4192,20 @@ int idpf_vport_intr_init(struct idpf_vport *vport) if (err) goto unroll_vectors_alloc; - idpf_vport_intr_ena_irq_all(vport); - return 0; unroll_vectors_alloc: - idpf_vport_intr_napi_dis_all(vport); idpf_vport_intr_napi_del_all(vport); return err; } +void idpf_vport_intr_ena(struct idpf_vport *vport) +{ + idpf_vport_intr_napi_ena_all(vport); + idpf_vport_intr_ena_irq_all(vport); +} + /** * idpf_config_rss - Send virtchnl messages to configure RSS * @vport: virtual port diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h index 3d046b81e507..551391e20464 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h @@ -990,6 +990,7 @@ int idpf_vport_intr_alloc(struct idpf_vport *vport); void idpf_vport_intr_update_itr_ena_irq(struct idpf_q_vector *q_vector); void idpf_vport_intr_deinit(struct idpf_vport *vport); int idpf_vport_intr_init(struct idpf_vport *vport); +void idpf_vport_intr_ena(struct idpf_vport *vport); enum pkt_hash_types idpf_ptype_to_htype(const struct idpf_rx_ptype_decoded *decoded); int idpf_config_rss(struct idpf_vport *vport); int idpf_init_rss(struct idpf_vport *vport); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c index 070711df612e..edac008099c0 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c @@ -1422,7 +1422,10 @@ static int otx2_qos_leaf_to_inner(struct otx2_nic *pfvf, u16 classid, otx2_qos_read_txschq_cfg(pfvf, node, old_cfg); /* delete the txschq nodes allocated for this node */ + otx2_qos_disable_sq(pfvf, qid); + otx2_qos_free_hw_node_schq(pfvf, node); otx2_qos_free_sw_node_schq(pfvf, node); + pfvf->qos.qid_to_sqmap[qid] = OTX2_QOS_INVALID_SQ; /* mark this node as htb inner node */ WRITE_ONCE(node->qid, OTX2_QOS_QID_INNER); @@ -1632,6 +1635,7 @@ static int otx2_qos_leaf_del_last(struct otx2_nic *pfvf, u16 classid, bool force dwrr_del_node = true; /* destroy the leaf node */ + otx2_qos_disable_sq(pfvf, qid); otx2_qos_destroy_node(pfvf, node); pfvf->qos.qid_to_sqmap[qid] = OTX2_QOS_INVALID_SQ; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h index caa34b9c161e..33e32584b07f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h @@ -102,8 +102,14 @@ static inline void mlx5e_udp_gso_handle_tx_skb(struct sk_buff *skb) { int payload_len = skb_shinfo(skb)->gso_size + sizeof(struct udphdr); + struct udphdr *udphdr; - udp_hdr(skb)->len = htons(payload_len); + if (skb->encapsulation) + udphdr = (struct udphdr *)skb_inner_transport_header(skb); + else + udphdr = udp_hdr(skb); + + udphdr->len = htons(payload_len); } struct mlx5e_accel_tx_state { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c index 41a2543a52cd..e51b03d4c717 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c @@ -750,8 +750,7 @@ err_fs: err_fs_ft: if (rx->allow_tunnel_mode) mlx5_eswitch_unblock_encap(mdev); - mlx5_del_flow_rules(rx->status.rule); - mlx5_modify_header_dealloc(mdev, rx->status.modify_hdr); + mlx5_ipsec_rx_status_destroy(ipsec, rx); err_add: mlx5_destroy_flow_table(rx->ft.status); err_fs_ft_status: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h index 82064614846f..359050f0b54d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h @@ -97,18 +97,11 @@ mlx5e_ipsec_feature_check(struct sk_buff *skb, netdev_features_t features) if (!x || !x->xso.offload_handle) goto out_disable; - if (xo->inner_ipproto) { - /* Cannot support tunnel packet over IPsec tunnel mode - * because we cannot offload three IP header csum - */ - if (x->props.mode == XFRM_MODE_TUNNEL) - goto out_disable; - - /* Only support UDP or TCP L4 checksum */ - if (xo->inner_ipproto != IPPROTO_UDP && - xo->inner_ipproto != IPPROTO_TCP) - goto out_disable; - } + /* Only support UDP or TCP L4 checksum */ + if (xo->inner_ipproto && + xo->inner_ipproto != IPPROTO_UDP && + xo->inner_ipproto != IPPROTO_TCP) + goto out_disable; return features; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index b758bc72ac36..c53c99dde558 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3886,7 +3886,7 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) mlx5e_fold_sw_stats64(priv, stats); } - stats->rx_dropped = priv->stats.qcnt.rx_out_of_buffer; + stats->rx_missed_errors = priv->stats.qcnt.rx_out_of_buffer; stats->rx_length_errors = PPORT_802_3_GET(pstats, a_in_range_length_errors) + diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index e211c41cec06..e1ed214e8651 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -1186,6 +1186,9 @@ void mlx5e_stats_ts_get(struct mlx5e_priv *priv, ts_stats->err = 0; ts_stats->lost = 0; + if (!ptp) + goto out; + /* Aggregate stats across all TCs */ for (i = 0; i < ptp->num_tc; i++) { struct mlx5e_ptp_cq_stats *stats = @@ -1214,6 +1217,7 @@ void mlx5e_stats_ts_get(struct mlx5e_priv *priv, } } +out: mutex_unlock(&priv->state_lock); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 099bf1078889..b09e9abd39f3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -153,7 +153,11 @@ mlx5e_tx_get_gso_ihs(struct mlx5e_txqsq *sq, struct sk_buff *skb, int *hopbyhop) *hopbyhop = 0; if (skb->encapsulation) { - ihs = skb_inner_tcp_all_headers(skb); + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) + ihs = skb_inner_transport_offset(skb) + + sizeof(struct udphdr); + else + ihs = skb_inner_tcp_all_headers(skb); stats->tso_inner_packets++; stats->tso_inner_bytes += skb->len - ihs; } else { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index f7f0476a4a58..d0871c46b8c5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -719,6 +719,7 @@ bool mlx5_lag_check_prereq(struct mlx5_lag *ldev) struct mlx5_core_dev *dev; u8 mode; #endif + bool roce_support; int i; for (i = 0; i < ldev->ports; i++) @@ -743,6 +744,11 @@ bool mlx5_lag_check_prereq(struct mlx5_lag *ldev) if (mlx5_sriov_is_enabled(ldev->pf[i].dev)) return false; #endif + roce_support = mlx5_get_roce_state(ldev->pf[MLX5_LAG_P1].dev); + for (i = 1; i < ldev->ports; i++) + if (mlx5_get_roce_state(ldev->pf[i].dev) != roce_support) + return false; + return true; } @@ -910,8 +916,10 @@ static void mlx5_do_bond(struct mlx5_lag *ldev) } else if (roce_lag) { dev0->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; mlx5_rescan_drivers_locked(dev0); - for (i = 1; i < ldev->ports; i++) - mlx5_nic_vport_enable_roce(ldev->pf[i].dev); + for (i = 1; i < ldev->ports; i++) { + if (mlx5_get_roce_state(ldev->pf[i].dev)) + mlx5_nic_vport_enable_roce(ldev->pf[i].dev); + } } else if (shared_fdb) { int i; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c index dd5d186dc614..f6deb5a3f820 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c @@ -100,10 +100,6 @@ static bool ft_create_alias_supported(struct mlx5_core_dev *dev) static bool mlx5_sd_is_supported(struct mlx5_core_dev *dev, u8 host_buses) { - /* Feature is currently implemented for PFs only */ - if (!mlx5_core_is_pf(dev)) - return false; - /* Honor the SW implementation limit */ if (host_buses > MLX5_SD_MAX_GROUP_SZ) return false; @@ -162,6 +158,14 @@ static int sd_init(struct mlx5_core_dev *dev) bool sdm; int err; + /* Feature is currently implemented for PFs only */ + if (!mlx5_core_is_pf(dev)) + return 0; + + /* Block on embedded CPU PFs */ + if (mlx5_core_is_ecpf(dev)) + return 0; + if (!MLX5_CAP_MCAM_REG(dev, mpir)) return 0; diff --git a/drivers/net/ethernet/ti/icssg/icssg_classifier.c b/drivers/net/ethernet/ti/icssg/icssg_classifier.c index 8dee737639b6..f7d21da1a0fb 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_classifier.c +++ b/drivers/net/ethernet/ti/icssg/icssg_classifier.c @@ -455,7 +455,7 @@ void icssg_ft1_set_mac_addr(struct regmap *miig_rt, int slice, u8 *mac_addr) { const u8 mask_addr[] = { 0, 0, 0, 0, 0, 0, }; - rx_class_ft1_set_start_len(miig_rt, slice, 6, 6); + rx_class_ft1_set_start_len(miig_rt, slice, ETH_ALEN, ETH_ALEN); rx_class_ft1_set_da(miig_rt, slice, 0, mac_addr); rx_class_ft1_set_da_mask(miig_rt, slice, 0, mask_addr); rx_class_ft1_cfg_set_type(miig_rt, slice, 0, FT1_CFG_TYPE_EQ); diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index 2d5b021b4ea6..fef4eff7753a 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -439,7 +439,7 @@ static noinline_for_stack int ipvlan_process_v4_outbound(struct sk_buff *skb) memset(IPCB(skb), 0, sizeof(*IPCB(skb))); - err = ip_local_out(net, skb->sk, skb); + err = ip_local_out(net, NULL, skb); if (unlikely(net_xmit_eval(err))) DEV_STATS_INC(dev, tx_errors); else @@ -494,7 +494,7 @@ static int ipvlan_process_v6_outbound(struct sk_buff *skb) memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); - err = ip6_local_out(dev_net(dev), skb->sk, skb); + err = ip6_local_out(dev_net(dev), NULL, skb); if (unlikely(net_xmit_eval(err))) DEV_STATS_INC(dev, tx_errors); else diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c index a4d2e76a8d58..16789cd446e9 100644 --- a/drivers/net/netkit.c +++ b/drivers/net/netkit.c @@ -55,6 +55,7 @@ static void netkit_prep_forward(struct sk_buff *skb, bool xnet) skb_scrub_packet(skb, xnet); skb->priority = 0; nf_skip_egress(skb, true); + skb_reset_mac_header(skb); } static struct netkit *netkit_priv(const struct net_device *dev) @@ -78,6 +79,7 @@ static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev) skb_orphan_frags(skb, GFP_ATOMIC))) goto drop; netkit_prep_forward(skb, !net_eq(dev_net(dev), dev_net(peer))); + eth_skb_pkt_type(skb, peer); skb->dev = peer; entry = rcu_dereference(nk->active); if (entry) @@ -85,7 +87,7 @@ static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev) switch (ret) { case NETKIT_NEXT: case NETKIT_PASS: - skb->protocol = eth_type_trans(skb, skb->dev); + eth_skb_pull_mac(skb); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); if (likely(__netif_rx(skb) == NET_RX_SUCCESS)) { dev_sw_netstats_tx_add(dev, 1, len); @@ -155,6 +157,16 @@ static void netkit_set_multicast(struct net_device *dev) /* Nothing to do, we receive whatever gets pushed to us! */ } +static int netkit_set_macaddr(struct net_device *dev, void *sa) +{ + struct netkit *nk = netkit_priv(dev); + + if (nk->mode != NETKIT_L2) + return -EOPNOTSUPP; + + return eth_mac_addr(dev, sa); +} + static void netkit_set_headroom(struct net_device *dev, int headroom) { struct netkit *nk = netkit_priv(dev), *nk2; @@ -198,6 +210,7 @@ static const struct net_device_ops netkit_netdev_ops = { .ndo_start_xmit = netkit_xmit, .ndo_set_rx_mode = netkit_set_multicast, .ndo_set_rx_headroom = netkit_set_headroom, + .ndo_set_mac_address = netkit_set_macaddr, .ndo_get_iflink = netkit_get_iflink, .ndo_get_peer_dev = netkit_peer_dev, .ndo_get_stats64 = netkit_get_stats, @@ -300,9 +313,11 @@ static int netkit_validate(struct nlattr *tb[], struct nlattr *data[], if (!attr) return 0; - NL_SET_ERR_MSG_ATTR(extack, attr, - "Setting Ethernet address is not supported"); - return -EOPNOTSUPP; + if (nla_len(attr) != ETH_ALEN) + return -EINVAL; + if (!is_valid_ether_addr(nla_data(attr))) + return -EADDRNOTAVAIL; + return 0; } static struct rtnl_link_ops netkit_link_ops; @@ -365,6 +380,9 @@ static int netkit_new_link(struct net *src_net, struct net_device *dev, strscpy(ifname, "nk%d", IFNAMSIZ); ifname_assign_type = NET_NAME_ENUM; } + if (mode != NETKIT_L2 && + (tb[IFLA_ADDRESS] || tbp[IFLA_ADDRESS])) + return -EOPNOTSUPP; net = rtnl_link_get_net(src_net, tbp); if (IS_ERR(net)) @@ -379,7 +397,7 @@ static int netkit_new_link(struct net *src_net, struct net_device *dev, netif_inherit_tso_max(peer, dev); - if (mode == NETKIT_L2) + if (mode == NETKIT_L2 && !(ifmp && tbp[IFLA_ADDRESS])) eth_hw_addr_random(peer); if (ifmp && dev->ifindex) peer->ifindex = ifmp->ifi_index; @@ -402,7 +420,7 @@ static int netkit_new_link(struct net *src_net, struct net_device *dev, if (err < 0) goto err_configure_peer; - if (mode == NETKIT_L2) + if (mode == NETKIT_L2 && !tb[IFLA_ADDRESS]) eth_hw_addr_random(dev); if (tb[IFLA_IFNAME]) nla_strscpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ); diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 13e30ea7eec5..2b8f8b7f1517 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -4029,7 +4029,7 @@ static int lan8841_config_intr(struct phy_device *phydev) if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { err = phy_read(phydev, LAN8814_INTS); - if (err) + if (err < 0) return err; /* Enable / disable interrupts. It is OK to enable PTP interrupt @@ -4045,6 +4045,14 @@ static int lan8841_config_intr(struct phy_device *phydev) return err; err = phy_read(phydev, LAN8814_INTS); + if (err < 0) + return err; + + /* Getting a positive value doesn't mean that is an error, it + * just indicates what was the status. Therefore make sure to + * clear the value and say that there is no error. + */ + err = 0; } return err; @@ -5327,6 +5335,7 @@ static struct phy_driver ksphy_driver[] = { /* PHY_BASIC_FEATURES */ .probe = kszphy_probe, .config_init = ksz8061_config_init, + .soft_reset = genphy_soft_reset, .config_intr = kszphy_config_intr, .handle_interrupt = kszphy_handle_interrupt, .suspend = kszphy_suspend, diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index cbea24666479..8e82184be5e7 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -879,7 +879,7 @@ static int smsc95xx_start_rx_path(struct usbnet *dev) static int smsc95xx_reset(struct usbnet *dev) { struct smsc95xx_priv *pdata = dev->driver_priv; - u32 read_buf, write_buf, burst_cap; + u32 read_buf, burst_cap; int ret = 0, timeout; netif_dbg(dev, ifup, dev->net, "entering smsc95xx_reset\n"); @@ -1003,10 +1003,13 @@ static int smsc95xx_reset(struct usbnet *dev) return ret; netif_dbg(dev, ifup, dev->net, "ID_REV = 0x%08x\n", read_buf); + ret = smsc95xx_read_reg(dev, LED_GPIO_CFG, &read_buf); + if (ret < 0) + return ret; /* Configure GPIO pins as LED outputs */ - write_buf = LED_GPIO_CFG_SPD_LED | LED_GPIO_CFG_LNK_LED | - LED_GPIO_CFG_FDX_LED; - ret = smsc95xx_write_reg(dev, LED_GPIO_CFG, write_buf); + read_buf |= LED_GPIO_CFG_SPD_LED | LED_GPIO_CFG_LNK_LED | + LED_GPIO_CFG_FDX_LED; + ret = smsc95xx_write_reg(dev, LED_GPIO_CFG, read_buf); if (ret < 0) return ret; diff --git a/drivers/nfc/virtual_ncidev.c b/drivers/nfc/virtual_ncidev.c index 590b038e449e..6b89d596ba9a 100644 --- a/drivers/nfc/virtual_ncidev.c +++ b/drivers/nfc/virtual_ncidev.c @@ -125,6 +125,10 @@ static ssize_t virtual_ncidev_write(struct file *file, kfree_skb(skb); return -EFAULT; } + if (strnlen(skb->data, count) != count) { + kfree_skb(skb); + return -EINVAL; + } nci_recv_frame(vdev->ndev, skb); return count; diff --git a/drivers/nvme/host/auth.c b/drivers/nvme/host/auth.c index a264b3ae078b..371e14f0a203 100644 --- a/drivers/nvme/host/auth.c +++ b/drivers/nvme/host/auth.c @@ -730,7 +730,7 @@ static void nvme_queue_auth_work(struct work_struct *work) NVME_AUTH_DHCHAP_MESSAGE_CHALLENGE); if (ret) { chap->status = ret; - chap->error = -ECONNREFUSED; + chap->error = -EKEYREJECTED; return; } @@ -797,7 +797,7 @@ static void nvme_queue_auth_work(struct work_struct *work) NVME_AUTH_DHCHAP_MESSAGE_SUCCESS1); if (ret) { chap->status = ret; - chap->error = -ECONNREFUSED; + chap->error = -EKEYREJECTED; return; } @@ -818,7 +818,7 @@ static void nvme_queue_auth_work(struct work_struct *work) ret = nvme_auth_process_dhchap_success1(ctrl, chap); if (ret) { /* Controller authentication failed */ - chap->error = -ECONNREFUSED; + chap->error = -EKEYREJECTED; goto fail2; } diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index bf7615cb36ee..954f850f113a 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -383,14 +383,14 @@ static inline enum nvme_disposition nvme_decide_disposition(struct request *req) if (likely(nvme_req(req)->status == 0)) return COMPLETE; - if ((nvme_req(req)->status & 0x7ff) == NVME_SC_AUTH_REQUIRED) - return AUTHENTICATE; - if (blk_noretry_request(req) || (nvme_req(req)->status & NVME_SC_DNR) || nvme_req(req)->retries >= nvme_max_retries) return COMPLETE; + if ((nvme_req(req)->status & 0x7ff) == NVME_SC_AUTH_REQUIRED) + return AUTHENTICATE; + if (req->cmd_flags & REQ_NVME_MPATH) { if (nvme_is_path_error(nvme_req(req)->status) || blk_queue_dying(req->q)) diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 1f0ea1f32d22..c6ad2148c2e0 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -428,12 +428,6 @@ static void nvmf_connect_cmd_prep(struct nvme_ctrl *ctrl, u16 qid, * fabrics-protocol connection of the NVMe Admin queue between the * host system device and the allocated NVMe controller on the * target system via a NVMe Fabrics "Connect" command. - * - * Return: - * 0: success - * > 0: NVMe error status code - * < 0: Linux errno error code - * */ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl) { @@ -467,7 +461,7 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl) if (result & NVME_CONNECT_AUTHREQ_ASCR) { dev_warn(ctrl->device, "qid 0: secure concatenation is not supported\n"); - ret = NVME_SC_AUTH_REQUIRED; + ret = -EOPNOTSUPP; goto out_free_data; } /* Authentication required */ @@ -475,14 +469,14 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl) if (ret) { dev_warn(ctrl->device, "qid 0: authentication setup failed\n"); - ret = NVME_SC_AUTH_REQUIRED; goto out_free_data; } ret = nvme_auth_wait(ctrl, 0); - if (ret) + if (ret) { dev_warn(ctrl->device, - "qid 0: authentication failed\n"); - else + "qid 0: authentication failed, error %d\n", + ret); + } else dev_info(ctrl->device, "qid 0: authenticated\n"); } @@ -542,7 +536,7 @@ int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid) if (result & NVME_CONNECT_AUTHREQ_ASCR) { dev_warn(ctrl->device, "qid 0: secure concatenation is not supported\n"); - ret = NVME_SC_AUTH_REQUIRED; + ret = -EOPNOTSUPP; goto out_free_data; } /* Authentication required */ @@ -550,12 +544,13 @@ int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid) if (ret) { dev_warn(ctrl->device, "qid %d: authentication setup failed\n", qid); - ret = NVME_SC_AUTH_REQUIRED; - } else { - ret = nvme_auth_wait(ctrl, qid); - if (ret) - dev_warn(ctrl->device, - "qid %u: authentication failed\n", qid); + goto out_free_data; + } + ret = nvme_auth_wait(ctrl, qid); + if (ret) { + dev_warn(ctrl->device, + "qid %u: authentication failed, error %d\n", + qid, ret); } } out_free_data: @@ -564,8 +559,26 @@ out_free_data: } EXPORT_SYMBOL_GPL(nvmf_connect_io_queue); -bool nvmf_should_reconnect(struct nvme_ctrl *ctrl) +/* + * Evaluate the status information returned by the transport in order to decided + * if a reconnect attempt should be scheduled. + * + * Do not retry when: + * + * - the DNR bit is set and the specification states no further connect + * attempts with the same set of paramenters should be attempted. + * + * - when the authentication attempt fails, because the key was invalid. + * This error code is set on the host side. + */ +bool nvmf_should_reconnect(struct nvme_ctrl *ctrl, int status) { + if (status > 0 && (status & NVME_SC_DNR)) + return false; + + if (status == -EKEYREJECTED) + return false; + if (ctrl->opts->max_reconnects == -1 || ctrl->nr_reconnects < ctrl->opts->max_reconnects) return true; diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index 37c974c38dcb..602135910ae9 100644 --- a/drivers/nvme/host/fabrics.h +++ b/drivers/nvme/host/fabrics.h @@ -223,7 +223,7 @@ int nvmf_register_transport(struct nvmf_transport_ops *ops); void nvmf_unregister_transport(struct nvmf_transport_ops *ops); void nvmf_free_options(struct nvmf_ctrl_options *opts); int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size); -bool nvmf_should_reconnect(struct nvme_ctrl *ctrl); +bool nvmf_should_reconnect(struct nvme_ctrl *ctrl, int status); bool nvmf_ip_options_match(struct nvme_ctrl *ctrl, struct nvmf_ctrl_options *opts); void nvmf_set_io_queues(struct nvmf_ctrl_options *opts, u32 nr_io_queues, diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index a5b29e9ad342..f0b081332749 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -3310,12 +3310,10 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status) dev_info(ctrl->ctrl.device, "NVME-FC{%d}: reset: Reconnect attempt failed (%d)\n", ctrl->cnum, status); - if (status > 0 && (status & NVME_SC_DNR)) - recon = false; } else if (time_after_eq(jiffies, rport->dev_loss_end)) recon = false; - if (recon && nvmf_should_reconnect(&ctrl->ctrl)) { + if (recon && nvmf_should_reconnect(&ctrl->ctrl, status)) { if (portptr->port_state == FC_OBJSTATE_ONLINE) dev_info(ctrl->ctrl.device, "NVME-FC{%d}: Reconnect attempt in %ld " diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 05532c281177..cacc56f4bbf4 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -1148,7 +1148,7 @@ static inline int nvme_auth_negotiate(struct nvme_ctrl *ctrl, int qid) } static inline int nvme_auth_wait(struct nvme_ctrl *ctrl, int qid) { - return NVME_SC_AUTH_REQUIRED; + return -EPROTONOSUPPORT; } static inline void nvme_auth_free(struct nvme_ctrl *ctrl) {}; #endif diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 366f0bb4ebfc..51a62b0c645a 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -982,7 +982,8 @@ free_ctrl: kfree(ctrl); } -static void nvme_rdma_reconnect_or_remove(struct nvme_rdma_ctrl *ctrl) +static void nvme_rdma_reconnect_or_remove(struct nvme_rdma_ctrl *ctrl, + int status) { enum nvme_ctrl_state state = nvme_ctrl_state(&ctrl->ctrl); @@ -992,7 +993,7 @@ static void nvme_rdma_reconnect_or_remove(struct nvme_rdma_ctrl *ctrl) return; } - if (nvmf_should_reconnect(&ctrl->ctrl)) { + if (nvmf_should_reconnect(&ctrl->ctrl, status)) { dev_info(ctrl->ctrl.device, "Reconnecting in %d seconds...\n", ctrl->ctrl.opts->reconnect_delay); queue_delayed_work(nvme_wq, &ctrl->reconnect_work, @@ -1104,10 +1105,12 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work) { struct nvme_rdma_ctrl *ctrl = container_of(to_delayed_work(work), struct nvme_rdma_ctrl, reconnect_work); + int ret; ++ctrl->ctrl.nr_reconnects; - if (nvme_rdma_setup_ctrl(ctrl, false)) + ret = nvme_rdma_setup_ctrl(ctrl, false); + if (ret) goto requeue; dev_info(ctrl->ctrl.device, "Successfully reconnected (%d attempts)\n", @@ -1118,9 +1121,9 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work) return; requeue: - dev_info(ctrl->ctrl.device, "Failed reconnect attempt %d\n", - ctrl->ctrl.nr_reconnects); - nvme_rdma_reconnect_or_remove(ctrl); + dev_info(ctrl->ctrl.device, "Failed reconnect attempt %d/%d\n", + ctrl->ctrl.nr_reconnects, ctrl->ctrl.opts->max_reconnects); + nvme_rdma_reconnect_or_remove(ctrl, ret); } static void nvme_rdma_error_recovery_work(struct work_struct *work) @@ -1145,7 +1148,7 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work) return; } - nvme_rdma_reconnect_or_remove(ctrl); + nvme_rdma_reconnect_or_remove(ctrl, 0); } static void nvme_rdma_error_recovery(struct nvme_rdma_ctrl *ctrl) @@ -2169,6 +2172,7 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work) { struct nvme_rdma_ctrl *ctrl = container_of(work, struct nvme_rdma_ctrl, ctrl.reset_work); + int ret; nvme_stop_ctrl(&ctrl->ctrl); nvme_rdma_shutdown_ctrl(ctrl, false); @@ -2179,14 +2183,15 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work) return; } - if (nvme_rdma_setup_ctrl(ctrl, false)) + ret = nvme_rdma_setup_ctrl(ctrl, false); + if (ret) goto out_fail; return; out_fail: ++ctrl->ctrl.nr_reconnects; - nvme_rdma_reconnect_or_remove(ctrl); + nvme_rdma_reconnect_or_remove(ctrl, ret); } static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = { diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 28bc2f373cfa..8b5e4327fe83 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -2161,7 +2161,8 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl, nvme_tcp_destroy_io_queues(ctrl, remove); } -static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl) +static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl, + int status) { enum nvme_ctrl_state state = nvme_ctrl_state(ctrl); @@ -2171,13 +2172,14 @@ static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl) return; } - if (nvmf_should_reconnect(ctrl)) { + if (nvmf_should_reconnect(ctrl, status)) { dev_info(ctrl->device, "Reconnecting in %d seconds...\n", ctrl->opts->reconnect_delay); queue_delayed_work(nvme_wq, &to_tcp_ctrl(ctrl)->connect_work, ctrl->opts->reconnect_delay * HZ); } else { - dev_info(ctrl->device, "Removing controller...\n"); + dev_info(ctrl->device, "Removing controller (%d)...\n", + status); nvme_delete_ctrl(ctrl); } } @@ -2258,23 +2260,25 @@ static void nvme_tcp_reconnect_ctrl_work(struct work_struct *work) struct nvme_tcp_ctrl *tcp_ctrl = container_of(to_delayed_work(work), struct nvme_tcp_ctrl, connect_work); struct nvme_ctrl *ctrl = &tcp_ctrl->ctrl; + int ret; ++ctrl->nr_reconnects; - if (nvme_tcp_setup_ctrl(ctrl, false)) + ret = nvme_tcp_setup_ctrl(ctrl, false); + if (ret) goto requeue; - dev_info(ctrl->device, "Successfully reconnected (%d attempt)\n", - ctrl->nr_reconnects); + dev_info(ctrl->device, "Successfully reconnected (attempt %d/%d)\n", + ctrl->nr_reconnects, ctrl->opts->max_reconnects); ctrl->nr_reconnects = 0; return; requeue: - dev_info(ctrl->device, "Failed reconnect attempt %d\n", - ctrl->nr_reconnects); - nvme_tcp_reconnect_or_remove(ctrl); + dev_info(ctrl->device, "Failed reconnect attempt %d/%d\n", + ctrl->nr_reconnects, ctrl->opts->max_reconnects); + nvme_tcp_reconnect_or_remove(ctrl, ret); } static void nvme_tcp_error_recovery_work(struct work_struct *work) @@ -2301,7 +2305,7 @@ static void nvme_tcp_error_recovery_work(struct work_struct *work) return; } - nvme_tcp_reconnect_or_remove(ctrl); + nvme_tcp_reconnect_or_remove(ctrl, 0); } static void nvme_tcp_teardown_ctrl(struct nvme_ctrl *ctrl, bool shutdown) @@ -2321,6 +2325,7 @@ static void nvme_reset_ctrl_work(struct work_struct *work) { struct nvme_ctrl *ctrl = container_of(work, struct nvme_ctrl, reset_work); + int ret; nvme_stop_ctrl(ctrl); nvme_tcp_teardown_ctrl(ctrl, false); @@ -2334,14 +2339,15 @@ static void nvme_reset_ctrl_work(struct work_struct *work) return; } - if (nvme_tcp_setup_ctrl(ctrl, false)) + ret = nvme_tcp_setup_ctrl(ctrl, false); + if (ret) goto out_fail; return; out_fail: ++ctrl->nr_reconnects; - nvme_tcp_reconnect_or_remove(ctrl); + nvme_tcp_reconnect_or_remove(ctrl, ret); } static void nvme_tcp_stop_ctrl(struct nvme_ctrl *ctrl) diff --git a/drivers/nvme/target/auth.c b/drivers/nvme/target/auth.c index 4f08362aee8b..7d2633940f9b 100644 --- a/drivers/nvme/target/auth.c +++ b/drivers/nvme/target/auth.c @@ -44,6 +44,7 @@ int nvmet_auth_set_key(struct nvmet_host *host, const char *secret, dhchap_secret = kstrdup(secret, GFP_KERNEL); if (!dhchap_secret) return -ENOMEM; + down_write(&nvmet_config_sem); if (set_ctrl) { kfree(host->dhchap_ctrl_secret); host->dhchap_ctrl_secret = strim(dhchap_secret); @@ -53,6 +54,7 @@ int nvmet_auth_set_key(struct nvmet_host *host, const char *secret, host->dhchap_secret = strim(dhchap_secret); host->dhchap_key_hash = key_hash; } + up_write(&nvmet_config_sem); return 0; } @@ -124,12 +126,11 @@ int nvmet_setup_dhgroup(struct nvmet_ctrl *ctrl, u8 dhgroup_id) return ret; } -int nvmet_setup_auth(struct nvmet_ctrl *ctrl) +u8 nvmet_setup_auth(struct nvmet_ctrl *ctrl) { int ret = 0; struct nvmet_host_link *p; struct nvmet_host *host = NULL; - const char *hash_name; down_read(&nvmet_config_sem); if (nvmet_is_disc_subsys(ctrl->subsys)) @@ -147,13 +148,16 @@ int nvmet_setup_auth(struct nvmet_ctrl *ctrl) } if (!host) { pr_debug("host %s not found\n", ctrl->hostnqn); - ret = -EPERM; + ret = NVME_AUTH_DHCHAP_FAILURE_FAILED; goto out_unlock; } ret = nvmet_setup_dhgroup(ctrl, host->dhchap_dhgroup_id); - if (ret < 0) + if (ret < 0) { pr_warn("Failed to setup DH group"); + ret = NVME_AUTH_DHCHAP_FAILURE_DHGROUP_UNUSABLE; + goto out_unlock; + } if (!host->dhchap_secret) { pr_debug("No authentication provided\n"); @@ -164,12 +168,6 @@ int nvmet_setup_auth(struct nvmet_ctrl *ctrl) pr_debug("Re-use existing hash ID %d\n", ctrl->shash_id); } else { - hash_name = nvme_auth_hmac_name(host->dhchap_hash_id); - if (!hash_name) { - pr_warn("Hash ID %d invalid\n", host->dhchap_hash_id); - ret = -EINVAL; - goto out_unlock; - } ctrl->shash_id = host->dhchap_hash_id; } @@ -178,7 +176,7 @@ int nvmet_setup_auth(struct nvmet_ctrl *ctrl) ctrl->host_key = nvme_auth_extract_key(host->dhchap_secret + 10, host->dhchap_key_hash); if (IS_ERR(ctrl->host_key)) { - ret = PTR_ERR(ctrl->host_key); + ret = NVME_AUTH_DHCHAP_FAILURE_NOT_USABLE; ctrl->host_key = NULL; goto out_free_hash; } @@ -196,7 +194,7 @@ int nvmet_setup_auth(struct nvmet_ctrl *ctrl) ctrl->ctrl_key = nvme_auth_extract_key(host->dhchap_ctrl_secret + 10, host->dhchap_ctrl_key_hash); if (IS_ERR(ctrl->ctrl_key)) { - ret = PTR_ERR(ctrl->ctrl_key); + ret = NVME_AUTH_DHCHAP_FAILURE_NOT_USABLE; ctrl->ctrl_key = NULL; goto out_free_hash; } diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index 7fda69395c1e..7c43a0ad6877 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -2007,11 +2007,17 @@ static struct config_group nvmet_ports_group; static ssize_t nvmet_host_dhchap_key_show(struct config_item *item, char *page) { - u8 *dhchap_secret = to_host(item)->dhchap_secret; + u8 *dhchap_secret; + ssize_t ret; + down_read(&nvmet_config_sem); + dhchap_secret = to_host(item)->dhchap_secret; if (!dhchap_secret) - return sprintf(page, "\n"); - return sprintf(page, "%s\n", dhchap_secret); + ret = sprintf(page, "\n"); + else + ret = sprintf(page, "%s\n", dhchap_secret); + up_read(&nvmet_config_sem); + return ret; } static ssize_t nvmet_host_dhchap_key_store(struct config_item *item, @@ -2035,10 +2041,16 @@ static ssize_t nvmet_host_dhchap_ctrl_key_show(struct config_item *item, char *page) { u8 *dhchap_secret = to_host(item)->dhchap_ctrl_secret; + ssize_t ret; + down_read(&nvmet_config_sem); + dhchap_secret = to_host(item)->dhchap_ctrl_secret; if (!dhchap_secret) - return sprintf(page, "\n"); - return sprintf(page, "%s\n", dhchap_secret); + ret = sprintf(page, "\n"); + else + ret = sprintf(page, "%s\n", dhchap_secret); + up_read(&nvmet_config_sem); + return ret; } static ssize_t nvmet_host_dhchap_ctrl_key_store(struct config_item *item, diff --git a/drivers/nvme/target/fabrics-cmd-auth.c b/drivers/nvme/target/fabrics-cmd-auth.c index eb7785be0ca7..d61b8c6ff3b2 100644 --- a/drivers/nvme/target/fabrics-cmd-auth.c +++ b/drivers/nvme/target/fabrics-cmd-auth.c @@ -31,7 +31,7 @@ void nvmet_auth_sq_init(struct nvmet_sq *sq) sq->dhchap_step = NVME_AUTH_DHCHAP_MESSAGE_NEGOTIATE; } -static u16 nvmet_auth_negotiate(struct nvmet_req *req, void *d) +static u8 nvmet_auth_negotiate(struct nvmet_req *req, void *d) { struct nvmet_ctrl *ctrl = req->sq->ctrl; struct nvmf_auth_dhchap_negotiate_data *data = d; @@ -109,7 +109,7 @@ static u16 nvmet_auth_negotiate(struct nvmet_req *req, void *d) return 0; } -static u16 nvmet_auth_reply(struct nvmet_req *req, void *d) +static u8 nvmet_auth_reply(struct nvmet_req *req, void *d) { struct nvmet_ctrl *ctrl = req->sq->ctrl; struct nvmf_auth_dhchap_reply_data *data = d; @@ -172,7 +172,7 @@ static u16 nvmet_auth_reply(struct nvmet_req *req, void *d) return 0; } -static u16 nvmet_auth_failure2(void *d) +static u8 nvmet_auth_failure2(void *d) { struct nvmf_auth_dhchap_failure_data *data = d; @@ -186,6 +186,7 @@ void nvmet_execute_auth_send(struct nvmet_req *req) void *d; u32 tl; u16 status = 0; + u8 dhchap_status; if (req->cmd->auth_send.secp != NVME_AUTH_DHCHAP_PROTOCOL_IDENTIFIER) { status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; @@ -237,30 +238,32 @@ void nvmet_execute_auth_send(struct nvmet_req *req) if (data->auth_type == NVME_AUTH_COMMON_MESSAGES) { if (data->auth_id == NVME_AUTH_DHCHAP_MESSAGE_NEGOTIATE) { /* Restart negotiation */ - pr_debug("%s: ctrl %d qid %d reset negotiation\n", __func__, - ctrl->cntlid, req->sq->qid); + pr_debug("%s: ctrl %d qid %d reset negotiation\n", + __func__, ctrl->cntlid, req->sq->qid); if (!req->sq->qid) { - if (nvmet_setup_auth(ctrl) < 0) { - status = NVME_SC_INTERNAL; - pr_err("ctrl %d qid 0 failed to setup" - "re-authentication", + dhchap_status = nvmet_setup_auth(ctrl); + if (dhchap_status) { + pr_err("ctrl %d qid 0 failed to setup re-authentication\n", ctrl->cntlid); - goto done_failure1; + req->sq->dhchap_status = dhchap_status; + req->sq->dhchap_step = + NVME_AUTH_DHCHAP_MESSAGE_FAILURE1; + goto done_kfree; } } - req->sq->dhchap_step = NVME_AUTH_DHCHAP_MESSAGE_NEGOTIATE; + req->sq->dhchap_step = + NVME_AUTH_DHCHAP_MESSAGE_NEGOTIATE; } else if (data->auth_id != req->sq->dhchap_step) goto done_failure1; /* Validate negotiation parameters */ - status = nvmet_auth_negotiate(req, d); - if (status == 0) + dhchap_status = nvmet_auth_negotiate(req, d); + if (dhchap_status == 0) req->sq->dhchap_step = NVME_AUTH_DHCHAP_MESSAGE_CHALLENGE; else { req->sq->dhchap_step = NVME_AUTH_DHCHAP_MESSAGE_FAILURE1; - req->sq->dhchap_status = status; - status = 0; + req->sq->dhchap_status = dhchap_status; } goto done_kfree; } @@ -284,15 +287,14 @@ void nvmet_execute_auth_send(struct nvmet_req *req) switch (data->auth_id) { case NVME_AUTH_DHCHAP_MESSAGE_REPLY: - status = nvmet_auth_reply(req, d); - if (status == 0) + dhchap_status = nvmet_auth_reply(req, d); + if (dhchap_status == 0) req->sq->dhchap_step = NVME_AUTH_DHCHAP_MESSAGE_SUCCESS1; else { req->sq->dhchap_step = NVME_AUTH_DHCHAP_MESSAGE_FAILURE1; - req->sq->dhchap_status = status; - status = 0; + req->sq->dhchap_status = dhchap_status; } goto done_kfree; case NVME_AUTH_DHCHAP_MESSAGE_SUCCESS2: @@ -301,13 +303,12 @@ void nvmet_execute_auth_send(struct nvmet_req *req) __func__, ctrl->cntlid, req->sq->qid); goto done_kfree; case NVME_AUTH_DHCHAP_MESSAGE_FAILURE2: - status = nvmet_auth_failure2(d); - if (status) { + dhchap_status = nvmet_auth_failure2(d); + if (dhchap_status) { pr_warn("ctrl %d qid %d: authentication failed (%d)\n", - ctrl->cntlid, req->sq->qid, status); - req->sq->dhchap_status = status; + ctrl->cntlid, req->sq->qid, dhchap_status); + req->sq->dhchap_status = dhchap_status; req->sq->authenticated = false; - status = 0; } goto done_kfree; default: diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c index b23f4cf840bd..042b379cbb36 100644 --- a/drivers/nvme/target/fabrics-cmd.c +++ b/drivers/nvme/target/fabrics-cmd.c @@ -211,7 +211,7 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req) struct nvmf_connect_data *d; struct nvmet_ctrl *ctrl = NULL; u16 status; - int ret; + u8 dhchap_status; if (!nvmet_check_transfer_len(req, sizeof(struct nvmf_connect_data))) return; @@ -254,11 +254,12 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req) uuid_copy(&ctrl->hostid, &d->hostid); - ret = nvmet_setup_auth(ctrl); - if (ret < 0) { - pr_err("Failed to setup authentication, error %d\n", ret); + dhchap_status = nvmet_setup_auth(ctrl); + if (dhchap_status) { + pr_err("Failed to setup authentication, dhchap status %u\n", + dhchap_status); nvmet_ctrl_put(ctrl); - if (ret == -EPERM) + if (dhchap_status == NVME_AUTH_DHCHAP_FAILURE_FAILED) status = (NVME_SC_CONNECT_INVALID_HOST | NVME_SC_DNR); else status = NVME_SC_INTERNAL; diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index c1306de1f4dd..2f22b07eab29 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -113,8 +113,8 @@ struct nvmet_sq { bool authenticated; struct delayed_work auth_expired_work; u16 dhchap_tid; - u16 dhchap_status; - int dhchap_step; + u8 dhchap_status; + u8 dhchap_step; u8 *dhchap_c1; u8 *dhchap_c2; u32 dhchap_s1; @@ -714,7 +714,7 @@ void nvmet_execute_auth_receive(struct nvmet_req *req); int nvmet_auth_set_key(struct nvmet_host *host, const char *secret, bool set_ctrl); int nvmet_auth_set_host_hash(struct nvmet_host *host, const char *hash); -int nvmet_setup_auth(struct nvmet_ctrl *ctrl); +u8 nvmet_setup_auth(struct nvmet_ctrl *ctrl); void nvmet_auth_sq_init(struct nvmet_sq *sq); void nvmet_destroy_auth(struct nvmet_ctrl *ctrl); void nvmet_auth_sq_free(struct nvmet_sq *sq); @@ -733,7 +733,7 @@ int nvmet_auth_ctrl_exponential(struct nvmet_req *req, int nvmet_auth_ctrl_sesskey(struct nvmet_req *req, u8 *buf, int buf_size); #else -static inline int nvmet_setup_auth(struct nvmet_ctrl *ctrl) +static inline u8 nvmet_setup_auth(struct nvmet_ctrl *ctrl) { return 0; } diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 6e1b4140cde0..689bb5d3cfdc 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -1806,18 +1806,14 @@ static int nvmet_rdma_cm_handler(struct rdma_cm_id *cm_id, static void nvmet_rdma_delete_ctrl(struct nvmet_ctrl *ctrl) { - struct nvmet_rdma_queue *queue; + struct nvmet_rdma_queue *queue, *n; -restart: mutex_lock(&nvmet_rdma_queue_mutex); - list_for_each_entry(queue, &nvmet_rdma_queue_list, queue_list) { - if (queue->nvme_sq.ctrl == ctrl) { - list_del_init(&queue->queue_list); - mutex_unlock(&nvmet_rdma_queue_mutex); - - __nvmet_rdma_queue_disconnect(queue); - goto restart; - } + list_for_each_entry_safe(queue, n, &nvmet_rdma_queue_list, queue_list) { + if (queue->nvme_sq.ctrl != ctrl) + continue; + list_del_init(&queue->queue_list); + __nvmet_rdma_queue_disconnect(queue); } mutex_unlock(&nvmet_rdma_queue_mutex); } diff --git a/drivers/pmdomain/imx/gpcv2.c b/drivers/pmdomain/imx/gpcv2.c index 4b828d74a606..856eaac0ec14 100644 --- a/drivers/pmdomain/imx/gpcv2.c +++ b/drivers/pmdomain/imx/gpcv2.c @@ -393,6 +393,17 @@ static int imx_pgc_power_up(struct generic_pm_domain *genpd) * automatically there. Just add a delay and suppose the handshake finish * after that. */ + + /* + * For some BLK-CTL module (eg. AudioMix on i.MX8MP) doesn't have BUS + * clk-en bit, it is better to add delay here, as the BLK-CTL module + * doesn't need to care about how it is powered up. + * + * regmap_read_bypassed() is to make sure the above write IO transaction + * already reaches target before udelay() + */ + regmap_read_bypassed(domain->regmap, domain->regs->hsk, ®_val); + udelay(5); } /* Disable reset clocks for all devices in the domain */ diff --git a/drivers/regulator/bd71828-regulator.c b/drivers/regulator/bd71828-regulator.c index 08d4ee369287..dd871ffe979c 100644 --- a/drivers/regulator/bd71828-regulator.c +++ b/drivers/regulator/bd71828-regulator.c @@ -206,14 +206,11 @@ static const struct bd71828_regulator_data bd71828_rdata[] = { .suspend_reg = BD71828_REG_BUCK1_SUSP_VOLT, .suspend_mask = BD71828_MASK_BUCK1267_VOLT, .suspend_on_mask = BD71828_MASK_SUSP_EN, - .lpsr_on_mask = BD71828_MASK_LPSR_EN, /* * LPSR voltage is same as SUSPEND voltage. Allow - * setting it so that regulator can be set enabled at - * LPSR state + * only enabling/disabling regulator for LPSR state */ - .lpsr_reg = BD71828_REG_BUCK1_SUSP_VOLT, - .lpsr_mask = BD71828_MASK_BUCK1267_VOLT, + .lpsr_on_mask = BD71828_MASK_LPSR_EN, }, .reg_inits = buck1_inits, .reg_init_amnt = ARRAY_SIZE(buck1_inits), @@ -288,13 +285,7 @@ static const struct bd71828_regulator_data bd71828_rdata[] = { ROHM_DVS_LEVEL_SUSPEND | ROHM_DVS_LEVEL_LPSR, .run_reg = BD71828_REG_BUCK3_VOLT, - .idle_reg = BD71828_REG_BUCK3_VOLT, - .suspend_reg = BD71828_REG_BUCK3_VOLT, - .lpsr_reg = BD71828_REG_BUCK3_VOLT, .run_mask = BD71828_MASK_BUCK3_VOLT, - .idle_mask = BD71828_MASK_BUCK3_VOLT, - .suspend_mask = BD71828_MASK_BUCK3_VOLT, - .lpsr_mask = BD71828_MASK_BUCK3_VOLT, .idle_on_mask = BD71828_MASK_IDLE_EN, .suspend_on_mask = BD71828_MASK_SUSP_EN, .lpsr_on_mask = BD71828_MASK_LPSR_EN, @@ -329,13 +320,7 @@ static const struct bd71828_regulator_data bd71828_rdata[] = { ROHM_DVS_LEVEL_SUSPEND | ROHM_DVS_LEVEL_LPSR, .run_reg = BD71828_REG_BUCK4_VOLT, - .idle_reg = BD71828_REG_BUCK4_VOLT, - .suspend_reg = BD71828_REG_BUCK4_VOLT, - .lpsr_reg = BD71828_REG_BUCK4_VOLT, .run_mask = BD71828_MASK_BUCK4_VOLT, - .idle_mask = BD71828_MASK_BUCK4_VOLT, - .suspend_mask = BD71828_MASK_BUCK4_VOLT, - .lpsr_mask = BD71828_MASK_BUCK4_VOLT, .idle_on_mask = BD71828_MASK_IDLE_EN, .suspend_on_mask = BD71828_MASK_SUSP_EN, .lpsr_on_mask = BD71828_MASK_LPSR_EN, @@ -370,13 +355,7 @@ static const struct bd71828_regulator_data bd71828_rdata[] = { ROHM_DVS_LEVEL_SUSPEND | ROHM_DVS_LEVEL_LPSR, .run_reg = BD71828_REG_BUCK5_VOLT, - .idle_reg = BD71828_REG_BUCK5_VOLT, - .suspend_reg = BD71828_REG_BUCK5_VOLT, - .lpsr_reg = BD71828_REG_BUCK5_VOLT, .run_mask = BD71828_MASK_BUCK5_VOLT, - .idle_mask = BD71828_MASK_BUCK5_VOLT, - .suspend_mask = BD71828_MASK_BUCK5_VOLT, - .lpsr_mask = BD71828_MASK_BUCK5_VOLT, .idle_on_mask = BD71828_MASK_IDLE_EN, .suspend_on_mask = BD71828_MASK_SUSP_EN, .lpsr_on_mask = BD71828_MASK_LPSR_EN, @@ -493,13 +472,7 @@ static const struct bd71828_regulator_data bd71828_rdata[] = { ROHM_DVS_LEVEL_SUSPEND | ROHM_DVS_LEVEL_LPSR, .run_reg = BD71828_REG_LDO1_VOLT, - .idle_reg = BD71828_REG_LDO1_VOLT, - .suspend_reg = BD71828_REG_LDO1_VOLT, - .lpsr_reg = BD71828_REG_LDO1_VOLT, .run_mask = BD71828_MASK_LDO_VOLT, - .idle_mask = BD71828_MASK_LDO_VOLT, - .suspend_mask = BD71828_MASK_LDO_VOLT, - .lpsr_mask = BD71828_MASK_LDO_VOLT, .idle_on_mask = BD71828_MASK_IDLE_EN, .suspend_on_mask = BD71828_MASK_SUSP_EN, .lpsr_on_mask = BD71828_MASK_LPSR_EN, @@ -533,13 +506,7 @@ static const struct bd71828_regulator_data bd71828_rdata[] = { ROHM_DVS_LEVEL_SUSPEND | ROHM_DVS_LEVEL_LPSR, .run_reg = BD71828_REG_LDO2_VOLT, - .idle_reg = BD71828_REG_LDO2_VOLT, - .suspend_reg = BD71828_REG_LDO2_VOLT, - .lpsr_reg = BD71828_REG_LDO2_VOLT, .run_mask = BD71828_MASK_LDO_VOLT, - .idle_mask = BD71828_MASK_LDO_VOLT, - .suspend_mask = BD71828_MASK_LDO_VOLT, - .lpsr_mask = BD71828_MASK_LDO_VOLT, .idle_on_mask = BD71828_MASK_IDLE_EN, .suspend_on_mask = BD71828_MASK_SUSP_EN, .lpsr_on_mask = BD71828_MASK_LPSR_EN, @@ -573,13 +540,7 @@ static const struct bd71828_regulator_data bd71828_rdata[] = { ROHM_DVS_LEVEL_SUSPEND | ROHM_DVS_LEVEL_LPSR, .run_reg = BD71828_REG_LDO3_VOLT, - .idle_reg = BD71828_REG_LDO3_VOLT, - .suspend_reg = BD71828_REG_LDO3_VOLT, - .lpsr_reg = BD71828_REG_LDO3_VOLT, .run_mask = BD71828_MASK_LDO_VOLT, - .idle_mask = BD71828_MASK_LDO_VOLT, - .suspend_mask = BD71828_MASK_LDO_VOLT, - .lpsr_mask = BD71828_MASK_LDO_VOLT, .idle_on_mask = BD71828_MASK_IDLE_EN, .suspend_on_mask = BD71828_MASK_SUSP_EN, .lpsr_on_mask = BD71828_MASK_LPSR_EN, @@ -614,13 +575,7 @@ static const struct bd71828_regulator_data bd71828_rdata[] = { ROHM_DVS_LEVEL_SUSPEND | ROHM_DVS_LEVEL_LPSR, .run_reg = BD71828_REG_LDO4_VOLT, - .idle_reg = BD71828_REG_LDO4_VOLT, - .suspend_reg = BD71828_REG_LDO4_VOLT, - .lpsr_reg = BD71828_REG_LDO4_VOLT, .run_mask = BD71828_MASK_LDO_VOLT, - .idle_mask = BD71828_MASK_LDO_VOLT, - .suspend_mask = BD71828_MASK_LDO_VOLT, - .lpsr_mask = BD71828_MASK_LDO_VOLT, .idle_on_mask = BD71828_MASK_IDLE_EN, .suspend_on_mask = BD71828_MASK_SUSP_EN, .lpsr_on_mask = BD71828_MASK_LPSR_EN, @@ -655,13 +610,7 @@ static const struct bd71828_regulator_data bd71828_rdata[] = { ROHM_DVS_LEVEL_SUSPEND | ROHM_DVS_LEVEL_LPSR, .run_reg = BD71828_REG_LDO5_VOLT, - .idle_reg = BD71828_REG_LDO5_VOLT, - .suspend_reg = BD71828_REG_LDO5_VOLT, - .lpsr_reg = BD71828_REG_LDO5_VOLT, .run_mask = BD71828_MASK_LDO_VOLT, - .idle_mask = BD71828_MASK_LDO_VOLT, - .suspend_mask = BD71828_MASK_LDO_VOLT, - .lpsr_mask = BD71828_MASK_LDO_VOLT, .idle_on_mask = BD71828_MASK_IDLE_EN, .suspend_on_mask = BD71828_MASK_SUSP_EN, .lpsr_on_mask = BD71828_MASK_LPSR_EN, @@ -720,9 +669,6 @@ static const struct bd71828_regulator_data bd71828_rdata[] = { .suspend_reg = BD71828_REG_LDO7_VOLT, .lpsr_reg = BD71828_REG_LDO7_VOLT, .run_mask = BD71828_MASK_LDO_VOLT, - .idle_mask = BD71828_MASK_LDO_VOLT, - .suspend_mask = BD71828_MASK_LDO_VOLT, - .lpsr_mask = BD71828_MASK_LDO_VOLT, .idle_on_mask = BD71828_MASK_IDLE_EN, .suspend_on_mask = BD71828_MASK_SUSP_EN, .lpsr_on_mask = BD71828_MASK_LPSR_EN, diff --git a/drivers/regulator/helpers.c b/drivers/regulator/helpers.c index d49268336553..6e1ace660b8c 100644 --- a/drivers/regulator/helpers.c +++ b/drivers/regulator/helpers.c @@ -161,6 +161,32 @@ int regulator_get_voltage_sel_pickable_regmap(struct regulator_dev *rdev) } EXPORT_SYMBOL_GPL(regulator_get_voltage_sel_pickable_regmap); +static int write_separate_vsel_and_range(struct regulator_dev *rdev, + unsigned int sel, unsigned int range) +{ + bool range_updated; + int ret; + + ret = regmap_update_bits_base(rdev->regmap, rdev->desc->vsel_range_reg, + rdev->desc->vsel_range_mask, + range, &range_updated, false, false); + if (ret) + return ret; + + /* + * Some PMICs treat the vsel_reg same as apply-bit. Force it to be + * written if the range changed, even if the old selector was same as + * the new one + */ + if (rdev->desc->range_applied_by_vsel && range_updated) + return regmap_write_bits(rdev->regmap, + rdev->desc->vsel_reg, + rdev->desc->vsel_mask, sel); + + return regmap_update_bits(rdev->regmap, rdev->desc->vsel_reg, + rdev->desc->vsel_mask, sel); +} + /** * regulator_set_voltage_sel_pickable_regmap - pickable range set_voltage_sel * @@ -199,21 +225,12 @@ int regulator_set_voltage_sel_pickable_regmap(struct regulator_dev *rdev, range = rdev->desc->linear_range_selectors_bitfield[i]; range <<= ffs(rdev->desc->vsel_range_mask) - 1; - if (rdev->desc->vsel_reg == rdev->desc->vsel_range_reg) { - ret = regmap_update_bits(rdev->regmap, - rdev->desc->vsel_reg, + if (rdev->desc->vsel_reg == rdev->desc->vsel_range_reg) + ret = regmap_update_bits(rdev->regmap, rdev->desc->vsel_reg, rdev->desc->vsel_range_mask | rdev->desc->vsel_mask, sel | range); - } else { - ret = regmap_update_bits(rdev->regmap, - rdev->desc->vsel_range_reg, - rdev->desc->vsel_range_mask, range); - if (ret) - return ret; - - ret = regmap_update_bits(rdev->regmap, rdev->desc->vsel_reg, - rdev->desc->vsel_mask, sel); - } + else + ret = write_separate_vsel_and_range(rdev, sel, range); if (ret) return ret; diff --git a/drivers/regulator/rohm-regulator.c b/drivers/regulator/rohm-regulator.c index 0e2418ed957c..4b95ca01959c 100644 --- a/drivers/regulator/rohm-regulator.c +++ b/drivers/regulator/rohm-regulator.c @@ -46,6 +46,7 @@ static int set_dvs_level(const struct regulator_desc *desc, continue; if (ret == uv) { i <<= ffs(desc->vsel_mask) - 1; + ret = regmap_update_bits(regmap, reg, mask, i); if (omask && !ret) ret = regmap_update_bits(regmap, oreg, omask, @@ -53,6 +54,9 @@ static int set_dvs_level(const struct regulator_desc *desc, break; } } + if (i == desc->n_voltages) + pr_warn("Unsupported %s voltage %u\n", prop, uv); + return ret; } diff --git a/drivers/regulator/tps6287x-regulator.c b/drivers/regulator/tps6287x-regulator.c index 9b7c3d77789e..3c9d79e003e4 100644 --- a/drivers/regulator/tps6287x-regulator.c +++ b/drivers/regulator/tps6287x-regulator.c @@ -115,6 +115,7 @@ static struct regulator_desc tps6287x_reg = { .vsel_mask = 0xFF, .vsel_range_reg = TPS6287X_CTRL2, .vsel_range_mask = TPS6287X_CTRL2_VRANGE, + .range_applied_by_vsel = true, .ramp_reg = TPS6287X_CTRL1, .ramp_mask = TPS6287X_CTRL1_VRAMP, .ramp_delay_table = tps6287x_ramp_table, diff --git a/drivers/regulator/tps6594-regulator.c b/drivers/regulator/tps6594-regulator.c index 9e7886bd4149..4a859f4c0f83 100644 --- a/drivers/regulator/tps6594-regulator.c +++ b/drivers/regulator/tps6594-regulator.c @@ -400,30 +400,30 @@ static struct tps6594_regulator_irq_type *tps65224_ldos_irq_types[] = { static const struct regulator_desc tps6594_multi_regs[] = { TPS6594_REGULATOR("BUCK12", "buck12", TPS6594_BUCK_1, REGULATOR_VOLTAGE, tps6594_bucks_ops, TPS6594_MASK_BUCKS_VSET, - TPS6594_REG_BUCKX_VOUT_1(1), + TPS6594_REG_BUCKX_VOUT_1(0), TPS6594_MASK_BUCKS_VSET, - TPS6594_REG_BUCKX_CTRL(1), + TPS6594_REG_BUCKX_CTRL(0), TPS6594_BIT_BUCK_EN, 0, 0, bucks_ranges, 4, 4000, 0, NULL, 0, 0), TPS6594_REGULATOR("BUCK34", "buck34", TPS6594_BUCK_3, REGULATOR_VOLTAGE, tps6594_bucks_ops, TPS6594_MASK_BUCKS_VSET, - TPS6594_REG_BUCKX_VOUT_1(3), + TPS6594_REG_BUCKX_VOUT_1(2), TPS6594_MASK_BUCKS_VSET, - TPS6594_REG_BUCKX_CTRL(3), + TPS6594_REG_BUCKX_CTRL(2), TPS6594_BIT_BUCK_EN, 0, 0, bucks_ranges, 4, 0, 0, NULL, 0, 0), TPS6594_REGULATOR("BUCK123", "buck123", TPS6594_BUCK_1, REGULATOR_VOLTAGE, tps6594_bucks_ops, TPS6594_MASK_BUCKS_VSET, - TPS6594_REG_BUCKX_VOUT_1(1), + TPS6594_REG_BUCKX_VOUT_1(0), TPS6594_MASK_BUCKS_VSET, - TPS6594_REG_BUCKX_CTRL(1), + TPS6594_REG_BUCKX_CTRL(0), TPS6594_BIT_BUCK_EN, 0, 0, bucks_ranges, 4, 4000, 0, NULL, 0, 0), TPS6594_REGULATOR("BUCK1234", "buck1234", TPS6594_BUCK_1, REGULATOR_VOLTAGE, tps6594_bucks_ops, TPS6594_MASK_BUCKS_VSET, - TPS6594_REG_BUCKX_VOUT_1(1), + TPS6594_REG_BUCKX_VOUT_1(0), TPS6594_MASK_BUCKS_VSET, - TPS6594_REG_BUCKX_CTRL(1), + TPS6594_REG_BUCKX_CTRL(0), TPS6594_BIT_BUCK_EN, 0, 0, bucks_ranges, 4, 4000, 0, NULL, 0, 0), }; diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig index c63e32d012f2..2a95b05982ad 100644 --- a/drivers/rtc/Kconfig +++ b/drivers/rtc/Kconfig @@ -664,6 +664,16 @@ config RTC_DRV_RX8010 This driver can also be built as a module. If so, the module will be called rtc-rx8010. +config RTC_DRV_RX8111 + tristate "Epson RX8111" + select REGMAP_I2C + depends on I2C + help + If you say yes here you will get support for the Epson RX8111 RTC. + + This driver can also be built as a module. If so, the module will be + called rtc-rx8111. + config RTC_DRV_RX8581 tristate "Epson RX-8571/RX-8581" select REGMAP_I2C diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile index 6efff381c484..3004e372f25f 100644 --- a/drivers/rtc/Makefile +++ b/drivers/rtc/Makefile @@ -154,6 +154,7 @@ obj-$(CONFIG_RTC_DRV_RX4581) += rtc-rx4581.o obj-$(CONFIG_RTC_DRV_RX6110) += rtc-rx6110.o obj-$(CONFIG_RTC_DRV_RX8010) += rtc-rx8010.o obj-$(CONFIG_RTC_DRV_RX8025) += rtc-rx8025.o +obj-$(CONFIG_RTC_DRV_RX8111) += rtc-rx8111.o obj-$(CONFIG_RTC_DRV_RX8581) += rtc-rx8581.o obj-$(CONFIG_RTC_DRV_RZN1) += rtc-rzn1.o obj-$(CONFIG_RTC_DRV_S35390A) += rtc-s35390a.o diff --git a/drivers/rtc/lib_test.c b/drivers/rtc/lib_test.c index 225c859d6da5..3893a202e9ea 100644 --- a/drivers/rtc/lib_test.c +++ b/drivers/rtc/lib_test.c @@ -27,17 +27,17 @@ static void advance_date(int *year, int *month, int *mday, int *yday) } /* - * Checks every day in a 160000 years interval starting on 1970-01-01 + * Check every day in specified number of years interval starting on 1970-01-01 * against the expected result. */ -static void rtc_time64_to_tm_test_date_range(struct kunit *test) +static void rtc_time64_to_tm_test_date_range(struct kunit *test, int years) { /* - * 160000 years = (160000 / 400) * 400 years - * = (160000 / 400) * 146097 days - * = (160000 / 400) * 146097 * 86400 seconds + * years = (years / 400) * 400 years + * = (years / 400) * 146097 days + * = (years / 400) * 146097 * 86400 seconds */ - time64_t total_secs = ((time64_t) 160000) / 400 * 146097 * 86400; + time64_t total_secs = ((time64_t)years) / 400 * 146097 * 86400; int year = 1970; int month = 1; @@ -66,8 +66,27 @@ static void rtc_time64_to_tm_test_date_range(struct kunit *test) } } +/* + * Checks every day in a 160000 years interval starting on 1970-01-01 + * against the expected result. + */ +static void rtc_time64_to_tm_test_date_range_160000(struct kunit *test) +{ + rtc_time64_to_tm_test_date_range(test, 160000); +} + +/* + * Checks every day in a 1000 years interval starting on 1970-01-01 + * against the expected result. + */ +static void rtc_time64_to_tm_test_date_range_1000(struct kunit *test) +{ + rtc_time64_to_tm_test_date_range(test, 1000); +} + static struct kunit_case rtc_lib_test_cases[] = { - KUNIT_CASE(rtc_time64_to_tm_test_date_range), + KUNIT_CASE(rtc_time64_to_tm_test_date_range_1000), + KUNIT_CASE_SLOW(rtc_time64_to_tm_test_date_range_160000), {} }; diff --git a/drivers/rtc/rtc-cros-ec.c b/drivers/rtc/rtc-cros-ec.c index 0cd397c04ff0..f57462c7b2c6 100644 --- a/drivers/rtc/rtc-cros-ec.c +++ b/drivers/rtc/rtc-cros-ec.c @@ -5,6 +5,7 @@ // Author: Stephen Barber <smbarber@chromium.org> #include <linux/kernel.h> +#include <linux/mod_devicetable.h> #include <linux/module.h> #include <linux/platform_data/cros_ec_commands.h> #include <linux/platform_data/cros_ec_proto.h> @@ -392,6 +393,12 @@ static void cros_ec_rtc_remove(struct platform_device *pdev) dev_err(dev, "failed to unregister notifier\n"); } +static const struct platform_device_id cros_ec_rtc_id[] = { + { DRV_NAME, 0 }, + {} +}; +MODULE_DEVICE_TABLE(platform, cros_ec_rtc_id); + static struct platform_driver cros_ec_rtc_driver = { .probe = cros_ec_rtc_probe, .remove_new = cros_ec_rtc_remove, @@ -399,6 +406,7 @@ static struct platform_driver cros_ec_rtc_driver = { .name = DRV_NAME, .pm = &cros_ec_rtc_pm_ops, }, + .id_table = cros_ec_rtc_id, }; module_platform_driver(cros_ec_rtc_driver); @@ -406,4 +414,3 @@ module_platform_driver(cros_ec_rtc_driver); MODULE_DESCRIPTION("RTC driver for Chrome OS ECs"); MODULE_AUTHOR("Stephen Barber <smbarber@chromium.org>"); MODULE_LICENSE("GPL v2"); -MODULE_ALIAS("platform:" DRV_NAME); diff --git a/drivers/rtc/rtc-mcp795.c b/drivers/rtc/rtc-mcp795.c index 0d515b3df571..e12f0f806ec4 100644 --- a/drivers/rtc/rtc-mcp795.c +++ b/drivers/rtc/rtc-mcp795.c @@ -450,4 +450,3 @@ module_spi_driver(mcp795_driver); MODULE_DESCRIPTION("MCP795 RTC SPI Driver"); MODULE_AUTHOR("Josef Gajdusek <atx@atx.name>"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("spi:mcp795"); diff --git a/drivers/rtc/rtc-nct3018y.c b/drivers/rtc/rtc-nct3018y.c index 076d8b99f913..7a8b4de893b8 100644 --- a/drivers/rtc/rtc-nct3018y.c +++ b/drivers/rtc/rtc-nct3018y.c @@ -517,12 +517,15 @@ static int nct3018y_probe(struct i2c_client *client) if (nct3018y->part_num < 0) { dev_dbg(&client->dev, "Failed to read NCT3018Y_REG_PART.\n"); return nct3018y->part_num; - } else if (nct3018y->part_num == NCT3018Y_REG_PART_NCT3018Y) { - flags = NCT3018Y_BIT_HF; - err = i2c_smbus_write_byte_data(client, NCT3018Y_REG_CTRL, flags); - if (err < 0) { - dev_dbg(&client->dev, "Unable to write NCT3018Y_REG_CTRL.\n"); - return err; + } else { + nct3018y->part_num &= 0x03; /* Part number is corresponding to bit 0 and 1 */ + if (nct3018y->part_num == NCT3018Y_REG_PART_NCT3018Y) { + flags = NCT3018Y_BIT_HF; + err = i2c_smbus_write_byte_data(client, NCT3018Y_REG_CTRL, flags); + if (err < 0) { + dev_dbg(&client->dev, "Unable to write NCT3018Y_REG_CTRL.\n"); + return err; + } } } diff --git a/drivers/rtc/rtc-pcf8563.c b/drivers/rtc/rtc-pcf8563.c index ea82b89d8929..1949d7473310 100644 --- a/drivers/rtc/rtc-pcf8563.c +++ b/drivers/rtc/rtc-pcf8563.c @@ -527,7 +527,6 @@ static int pcf8563_probe(struct i2c_client *client) i2c_set_clientdata(client, pcf8563); pcf8563->client = client; - device_set_wakeup_capable(&client->dev, 1); /* Set timer to lowest frequency to save power (ref Haoyu datasheet) */ buf = PCF8563_TMRC_1_60; @@ -553,6 +552,7 @@ static int pcf8563_probe(struct i2c_client *client) /* the pcf8563 alarm only supports a minute accuracy */ set_bit(RTC_FEATURE_ALARM_RES_MINUTE, pcf8563->rtc->features); clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, pcf8563->rtc->features); + clear_bit(RTC_FEATURE_ALARM, pcf8563->rtc->features); pcf8563->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000; pcf8563->rtc->range_max = RTC_TIMESTAMP_END_2099; pcf8563->rtc->set_start_time = true; @@ -573,7 +573,12 @@ static int pcf8563_probe(struct i2c_client *client) return err; } } else { - clear_bit(RTC_FEATURE_ALARM, pcf8563->rtc->features); + client->irq = 0; + } + + if (client->irq > 0 || device_property_read_bool(&client->dev, "wakeup-source")) { + device_init_wakeup(&client->dev, true); + set_bit(RTC_FEATURE_ALARM, pcf8563->rtc->features); } err = devm_rtc_register_device(pcf8563->rtc); diff --git a/drivers/rtc/rtc-rx6110.c b/drivers/rtc/rtc-rx6110.c index 834274db8c3f..af6dd6ccbe3b 100644 --- a/drivers/rtc/rtc-rx6110.c +++ b/drivers/rtc/rtc-rx6110.c @@ -330,7 +330,7 @@ static int rx6110_probe(struct rx6110_data *rx6110, struct device *dev) } #if IS_ENABLED(CONFIG_SPI_MASTER) -static struct regmap_config regmap_spi_config = { +static const struct regmap_config regmap_spi_config = { .reg_bits = 8, .val_bits = 8, .max_register = RX6110_REG_IRQ, @@ -410,7 +410,7 @@ static void rx6110_spi_unregister(void) #endif /* CONFIG_SPI_MASTER */ #if IS_ENABLED(CONFIG_I2C) -static struct regmap_config regmap_i2c_config = { +static const struct regmap_config regmap_i2c_config = { .reg_bits = 8, .val_bits = 8, .max_register = RX6110_REG_IRQ, diff --git a/drivers/rtc/rtc-rx8111.c b/drivers/rtc/rtc-rx8111.c new file mode 100644 index 000000000000..8450d9f0b566 --- /dev/null +++ b/drivers/rtc/rtc-rx8111.c @@ -0,0 +1,368 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Driver for Epson RX8111 RTC. + * + * Copyright (C) 2023 Axis Communications AB + */ + +#include <linux/bcd.h> +#include <linux/bitfield.h> +#include <linux/i2c.h> +#include <linux/module.h> +#include <linux/regmap.h> + +#include <linux/rtc.h> + +#define RX8111_REG_SEC 0x10 /* Second counter. */ +#define RX8111_REG_MIN 0x11 /* Minute counter */ +#define RX8111_REG_HOUR 0x12 /* Hour counter. */ +#define RX8111_REG_WEEK 0x13 /* Week day counter. */ +#define RX8111_REG_DAY 0x14 /* Month day counter. */ +#define RX8111_REG_MONTH 0x15 /* Month counter. */ +#define RX8111_REG_YEAR 0x16 /* Year counter. */ + +#define RX8111_REG_ALARM_MIN 0x17 /* Alarm minute. */ +#define RX8111_REG_ALARM_HOUR 0x18 /* Alarm hour. */ +#define RX8111_REG_ALARM_WEEK_DAY 0x19 /* Alarm week or month day. */ + +#define RX8111_REG_TIMER_COUNTER0 0x1a /* Timer counter LSB. */ +#define RX8111_REG_TIMER_COUNTER1 0x1b /* Timer counter. */ +#define RX8111_REG_TIMER_COUNTER2 0x1c /* Timer counter MSB. */ + +#define RX8111_REG_EXT 0x1d /* Extension register. */ +#define RX8111_REG_FLAG 0x1e /* Flag register. */ +#define RX8111_REG_CTRL 0x1f /* Control register. */ + +#define RX8111_REG_TS_1_1000_SEC 0x20 /* Timestamp 256 or 512 Hz . */ +#define RX8111_REG_TS_1_100_SEC 0x21 /* Timestamp 1 - 128 Hz. */ +#define RX8111_REG_TS_SEC 0x22 /* Timestamp second. */ +#define RX8111_REG_TS_MIN 0x23 /* Timestamp minute. */ +#define RX8111_REG_TS_HOUR 0x24 /* Timestamp hour. */ +#define RX8111_REG_TS_WEEK 0x25 /* Timestamp week day. */ +#define RX8111_REG_TS_DAY 0x26 /* Timestamp month day. */ +#define RX8111_REG_TS_MONTH 0x27 /* Timestamp month. */ +#define RX8111_REG_TS_YEAR 0x28 /* Timestamp year. */ +#define RX8111_REG_TS_STATUS 0x29 /* Timestamp status. */ + +#define RX8111_REG_EVIN_SETTING 0x2b /* Timestamp trigger setting. */ +#define RX8111_REG_ALARM_SEC 0x2c /* Alarm second. */ +#define RX8111_REG_TIMER_CTRL 0x2d /* Timer control. */ +#define RX8111_REG_TS_CTRL0 0x2e /* Timestamp control 0. */ +#define RX8111_REG_CMD_TRIGGER 0x2f /* Timestamp trigger. */ +#define RX8111_REG_PWR_SWITCH_CTRL 0x32 /* Power switch control. */ +#define RX8111_REG_STATUS_MON 0x33 /* Status monitor. */ +#define RX8111_REG_TS_CTRL1 0x34 /* Timestamp control 1. */ +#define RX8111_REG_TS_CTRL2 0x35 /* Timestamp control 2. */ +#define RX8111_REG_TS_CTRL3 0x36 /* Timestamp control 3. */ + +#define RX8111_FLAG_XST_BIT BIT(0) +#define RX8111_FLAG_VLF_BIT BIT(1) + +#define RX8111_TIME_BUF_SZ (RX8111_REG_YEAR - RX8111_REG_SEC + 1) + +enum rx8111_regfield { + /* RX8111_REG_EXT. */ + RX8111_REGF_TSEL0, + RX8111_REGF_TSEL1, + RX8111_REGF_ETS, + RX8111_REGF_WADA, + RX8111_REGF_TE, + RX8111_REGF_USEL, + RX8111_REGF_FSEL0, + RX8111_REGF_FSEL1, + + /* RX8111_REG_FLAG. */ + RX8111_REGF_XST, + RX8111_REGF_VLF, + RX8111_REGF_EVF, + RX8111_REGF_AF, + RX8111_REGF_TF, + RX8111_REGF_UF, + RX8111_REGF_POR, + + /* RX8111_REG_CTRL. */ + RX8111_REGF_STOP, + RX8111_REGF_EIE, + RX8111_REGF_AIE, + RX8111_REGF_TIE, + RX8111_REGF_UIE, + + /* RX8111_REG_PWR_SWITCH_CTRL. */ + RX8111_REGF_SMPT0, + RX8111_REGF_SMPT1, + RX8111_REGF_SWSEL0, + RX8111_REGF_SWSEL1, + RX8111_REGF_INIEN, + RX8111_REGF_CHGEN, + + /* RX8111_REG_STATUS_MON. */ + RX8111_REGF_VLOW, + + /* Sentinel value. */ + RX8111_REGF_MAX +}; + +static const struct reg_field rx8111_regfields[] = { + [RX8111_REGF_TSEL0] = REG_FIELD(RX8111_REG_EXT, 0, 0), + [RX8111_REGF_TSEL1] = REG_FIELD(RX8111_REG_EXT, 1, 1), + [RX8111_REGF_ETS] = REG_FIELD(RX8111_REG_EXT, 2, 2), + [RX8111_REGF_WADA] = REG_FIELD(RX8111_REG_EXT, 3, 3), + [RX8111_REGF_TE] = REG_FIELD(RX8111_REG_EXT, 4, 4), + [RX8111_REGF_USEL] = REG_FIELD(RX8111_REG_EXT, 5, 5), + [RX8111_REGF_FSEL0] = REG_FIELD(RX8111_REG_EXT, 6, 6), + [RX8111_REGF_FSEL1] = REG_FIELD(RX8111_REG_EXT, 7, 7), + + [RX8111_REGF_XST] = REG_FIELD(RX8111_REG_FLAG, 0, 0), + [RX8111_REGF_VLF] = REG_FIELD(RX8111_REG_FLAG, 1, 1), + [RX8111_REGF_EVF] = REG_FIELD(RX8111_REG_FLAG, 2, 2), + [RX8111_REGF_AF] = REG_FIELD(RX8111_REG_FLAG, 3, 3), + [RX8111_REGF_TF] = REG_FIELD(RX8111_REG_FLAG, 4, 4), + [RX8111_REGF_UF] = REG_FIELD(RX8111_REG_FLAG, 5, 5), + [RX8111_REGF_POR] = REG_FIELD(RX8111_REG_FLAG, 7, 7), + + [RX8111_REGF_STOP] = REG_FIELD(RX8111_REG_CTRL, 0, 0), + [RX8111_REGF_EIE] = REG_FIELD(RX8111_REG_CTRL, 2, 2), + [RX8111_REGF_AIE] = REG_FIELD(RX8111_REG_CTRL, 3, 3), + [RX8111_REGF_TIE] = REG_FIELD(RX8111_REG_CTRL, 4, 4), + [RX8111_REGF_UIE] = REG_FIELD(RX8111_REG_CTRL, 5, 5), + + [RX8111_REGF_SMPT0] = REG_FIELD(RX8111_REG_PWR_SWITCH_CTRL, 0, 0), + [RX8111_REGF_SMPT1] = REG_FIELD(RX8111_REG_PWR_SWITCH_CTRL, 1, 1), + [RX8111_REGF_SWSEL0] = REG_FIELD(RX8111_REG_PWR_SWITCH_CTRL, 2, 2), + [RX8111_REGF_SWSEL1] = REG_FIELD(RX8111_REG_PWR_SWITCH_CTRL, 3, 3), + [RX8111_REGF_INIEN] = REG_FIELD(RX8111_REG_PWR_SWITCH_CTRL, 6, 6), + [RX8111_REGF_CHGEN] = REG_FIELD(RX8111_REG_PWR_SWITCH_CTRL, 7, 7), + + [RX8111_REGF_VLOW] = REG_FIELD(RX8111_REG_STATUS_MON, 1, 1), +}; + +static const struct regmap_config rx8111_regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .max_register = RX8111_REG_TS_CTRL3, +}; + +struct rx8111_data { + struct regmap *regmap; + struct regmap_field *regfields[RX8111_REGF_MAX]; + struct device *dev; + struct rtc_device *rtc; +}; + +static int rx8111_read_vl_flag(struct rx8111_data *data, unsigned int *vlval) +{ + int ret; + + ret = regmap_field_read(data->regfields[RX8111_REGF_VLF], vlval); + if (ret) + dev_dbg(data->dev, "Could not read VL flag (%d)", ret); + + return ret; +} + +static int rx8111_read_time(struct device *dev, struct rtc_time *tm) +{ + struct rx8111_data *data = dev_get_drvdata(dev); + u8 buf[RX8111_TIME_BUF_SZ]; + unsigned int regval; + int ret; + + /* Check status. */ + ret = regmap_read(data->regmap, RX8111_REG_FLAG, ®val); + if (ret) { + dev_dbg(data->dev, "Could not read flag register (%d)\n", ret); + return ret; + } + + if (FIELD_GET(RX8111_FLAG_XST_BIT, regval)) { + dev_dbg(data->dev, + "Crystal oscillation stopped, time is not reliable\n"); + return -EINVAL; + } + + if (FIELD_GET(RX8111_FLAG_VLF_BIT, regval)) { + dev_dbg(data->dev, + "Low voltage detected, time is not reliable\n"); + return -EINVAL; + } + + ret = regmap_field_read(data->regfields[RX8111_REGF_STOP], ®val); + if (ret) { + dev_dbg(data->dev, "Could not read clock status (%d)\n", ret); + return ret; + } + + if (regval) { + dev_dbg(data->dev, "Clock stopped, time is not reliable\n"); + return -EINVAL; + } + + /* Read time. */ + ret = regmap_bulk_read(data->regmap, RX8111_REG_SEC, buf, + ARRAY_SIZE(buf)); + if (ret) { + dev_dbg(data->dev, "Could not bulk read time (%d)\n", ret); + return ret; + } + + tm->tm_sec = bcd2bin(buf[0]); + tm->tm_min = bcd2bin(buf[1]); + tm->tm_hour = bcd2bin(buf[2]); + tm->tm_wday = ffs(buf[3]) - 1; + tm->tm_mday = bcd2bin(buf[4]); + tm->tm_mon = bcd2bin(buf[5]) - 1; + tm->tm_year = bcd2bin(buf[6]) + 100; + + return 0; +} + +static int rx8111_set_time(struct device *dev, struct rtc_time *tm) +{ + struct rx8111_data *data = dev_get_drvdata(dev); + u8 buf[RX8111_TIME_BUF_SZ]; + int ret; + + buf[0] = bin2bcd(tm->tm_sec); + buf[1] = bin2bcd(tm->tm_min); + buf[2] = bin2bcd(tm->tm_hour); + buf[3] = BIT(tm->tm_wday); + buf[4] = bin2bcd(tm->tm_mday); + buf[5] = bin2bcd(tm->tm_mon + 1); + buf[6] = bin2bcd(tm->tm_year - 100); + + ret = regmap_clear_bits(data->regmap, RX8111_REG_FLAG, + RX8111_FLAG_XST_BIT | RX8111_FLAG_VLF_BIT); + if (ret) + return ret; + + /* Stop the clock. */ + ret = regmap_field_write(data->regfields[RX8111_REGF_STOP], 1); + if (ret) { + dev_dbg(data->dev, "Could not stop the clock (%d)\n", ret); + return ret; + } + + /* Set the time. */ + ret = regmap_bulk_write(data->regmap, RX8111_REG_SEC, buf, + ARRAY_SIZE(buf)); + if (ret) { + dev_dbg(data->dev, "Could not bulk write time (%d)\n", ret); + + /* + * We don't bother with trying to start the clock again. We + * check for this in rx8111_read_time() (and thus force user to + * call rx8111_set_time() to try again). + */ + return ret; + } + + /* Start the clock. */ + ret = regmap_field_write(data->regfields[RX8111_REGF_STOP], 0); + if (ret) { + dev_dbg(data->dev, "Could not start the clock (%d)\n", ret); + return ret; + } + + return 0; +} + +static int rx8111_ioctl(struct device *dev, unsigned int cmd, unsigned long arg) +{ + struct rx8111_data *data = dev_get_drvdata(dev); + unsigned int regval; + unsigned int vlval; + int ret; + + switch (cmd) { + case RTC_VL_READ: + ret = rx8111_read_vl_flag(data, ®val); + if (ret) + return ret; + + vlval = regval ? RTC_VL_DATA_INVALID : 0; + + ret = regmap_field_read(data->regfields[RX8111_REGF_VLOW], + ®val); + if (ret) + return ret; + + vlval |= regval ? RTC_VL_BACKUP_LOW : 0; + + return put_user(vlval, (typeof(vlval) __user *)arg); + default: + return -ENOIOCTLCMD; + } +} + +static const struct rtc_class_ops rx8111_rtc_ops = { + .read_time = rx8111_read_time, + .set_time = rx8111_set_time, + .ioctl = rx8111_ioctl, +}; + +static int rx8111_probe(struct i2c_client *client) +{ + struct rx8111_data *data; + struct rtc_device *rtc; + size_t i; + + data = devm_kmalloc(&client->dev, sizeof(*data), GFP_KERNEL); + if (!data) { + dev_dbg(&client->dev, "Could not allocate device data\n"); + return -ENOMEM; + } + + data->dev = &client->dev; + dev_set_drvdata(data->dev, data); + + data->regmap = devm_regmap_init_i2c(client, &rx8111_regmap_config); + if (IS_ERR(data->regmap)) { + dev_dbg(data->dev, "Could not initialize regmap\n"); + return PTR_ERR(data->regmap); + } + + for (i = 0; i < RX8111_REGF_MAX; ++i) { + data->regfields[i] = devm_regmap_field_alloc( + data->dev, data->regmap, rx8111_regfields[i]); + if (IS_ERR(data->regfields[i])) { + dev_dbg(data->dev, + "Could not allocate register field %zu\n", i); + return PTR_ERR(data->regfields[i]); + } + } + + rtc = devm_rtc_allocate_device(data->dev); + if (IS_ERR(rtc)) { + dev_dbg(data->dev, "Could not allocate rtc device\n"); + return PTR_ERR(rtc); + } + + rtc->ops = &rx8111_rtc_ops; + rtc->range_min = RTC_TIMESTAMP_BEGIN_2000; + rtc->range_max = RTC_TIMESTAMP_END_2099; + + clear_bit(RTC_FEATURE_ALARM, rtc->features); + + return devm_rtc_register_device(rtc); +} + +static const struct of_device_id rx8111_of_match[] = { + { + .compatible = "epson,rx8111", + }, + {} +}; +MODULE_DEVICE_TABLE(of, rx8111_of_match); + +static struct i2c_driver rx8111_driver = { + .driver = { + .name = "rtc-rx8111", + .of_match_table = rx8111_of_match, + }, + .probe = rx8111_probe, +}; +module_i2c_driver(rx8111_driver); + +MODULE_AUTHOR("Waqar Hameed <waqar.hameed@axis.com>"); +MODULE_DESCRIPTION("Epson RX8111 RTC driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index f5b0d91d32a7..be35f7334ecd 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -245,16 +245,18 @@ enum gsm_encoding { enum gsm_mux_state { GSM_SEARCH, - GSM_START, - GSM_ADDRESS, - GSM_CONTROL, - GSM_LEN, - GSM_DATA, - GSM_FCS, - GSM_OVERRUN, - GSM_LEN0, - GSM_LEN1, - GSM_SSOF, + GSM0_ADDRESS, + GSM0_CONTROL, + GSM0_LEN0, + GSM0_LEN1, + GSM0_DATA, + GSM0_FCS, + GSM0_SSOF, + GSM1_START, + GSM1_ADDRESS, + GSM1_CONTROL, + GSM1_DATA, + GSM1_OVERRUN, }; /* @@ -2847,6 +2849,30 @@ invalid: return; } +/** + * gsm0_receive_state_check_and_fix - check and correct receive state + * @gsm: gsm data for this ldisc instance + * + * Ensures that the current receive state is valid for basic option mode. + */ + +static void gsm0_receive_state_check_and_fix(struct gsm_mux *gsm) +{ + switch (gsm->state) { + case GSM_SEARCH: + case GSM0_ADDRESS: + case GSM0_CONTROL: + case GSM0_LEN0: + case GSM0_LEN1: + case GSM0_DATA: + case GSM0_FCS: + case GSM0_SSOF: + break; + default: + gsm->state = GSM_SEARCH; + break; + } +} /** * gsm0_receive - perform processing for non-transparency @@ -2860,26 +2886,27 @@ static void gsm0_receive(struct gsm_mux *gsm, u8 c) { unsigned int len; + gsm0_receive_state_check_and_fix(gsm); switch (gsm->state) { case GSM_SEARCH: /* SOF marker */ if (c == GSM0_SOF) { - gsm->state = GSM_ADDRESS; + gsm->state = GSM0_ADDRESS; gsm->address = 0; gsm->len = 0; gsm->fcs = INIT_FCS; } break; - case GSM_ADDRESS: /* Address EA */ + case GSM0_ADDRESS: /* Address EA */ gsm->fcs = gsm_fcs_add(gsm->fcs, c); if (gsm_read_ea(&gsm->address, c)) - gsm->state = GSM_CONTROL; + gsm->state = GSM0_CONTROL; break; - case GSM_CONTROL: /* Control Byte */ + case GSM0_CONTROL: /* Control Byte */ gsm->fcs = gsm_fcs_add(gsm->fcs, c); gsm->control = c; - gsm->state = GSM_LEN0; + gsm->state = GSM0_LEN0; break; - case GSM_LEN0: /* Length EA */ + case GSM0_LEN0: /* Length EA */ gsm->fcs = gsm_fcs_add(gsm->fcs, c); if (gsm_read_ea(&gsm->len, c)) { if (gsm->len > gsm->mru) { @@ -2889,14 +2916,14 @@ static void gsm0_receive(struct gsm_mux *gsm, u8 c) } gsm->count = 0; if (!gsm->len) - gsm->state = GSM_FCS; + gsm->state = GSM0_FCS; else - gsm->state = GSM_DATA; + gsm->state = GSM0_DATA; break; } - gsm->state = GSM_LEN1; + gsm->state = GSM0_LEN1; break; - case GSM_LEN1: + case GSM0_LEN1: gsm->fcs = gsm_fcs_add(gsm->fcs, c); len = c; gsm->len |= len << 7; @@ -2907,26 +2934,29 @@ static void gsm0_receive(struct gsm_mux *gsm, u8 c) } gsm->count = 0; if (!gsm->len) - gsm->state = GSM_FCS; + gsm->state = GSM0_FCS; else - gsm->state = GSM_DATA; + gsm->state = GSM0_DATA; break; - case GSM_DATA: /* Data */ + case GSM0_DATA: /* Data */ gsm->buf[gsm->count++] = c; - if (gsm->count == gsm->len) { + if (gsm->count >= MAX_MRU) { + gsm->bad_size++; + gsm->state = GSM_SEARCH; + } else if (gsm->count >= gsm->len) { /* Calculate final FCS for UI frames over all data */ if ((gsm->control & ~PF) != UIH) { gsm->fcs = gsm_fcs_add_block(gsm->fcs, gsm->buf, gsm->count); } - gsm->state = GSM_FCS; + gsm->state = GSM0_FCS; } break; - case GSM_FCS: /* FCS follows the packet */ + case GSM0_FCS: /* FCS follows the packet */ gsm->fcs = gsm_fcs_add(gsm->fcs, c); - gsm->state = GSM_SSOF; + gsm->state = GSM0_SSOF; break; - case GSM_SSOF: + case GSM0_SSOF: gsm->state = GSM_SEARCH; if (c == GSM0_SOF) gsm_queue(gsm); @@ -2940,6 +2970,29 @@ static void gsm0_receive(struct gsm_mux *gsm, u8 c) } /** + * gsm1_receive_state_check_and_fix - check and correct receive state + * @gsm: gsm data for this ldisc instance + * + * Ensures that the current receive state is valid for advanced option mode. + */ + +static void gsm1_receive_state_check_and_fix(struct gsm_mux *gsm) +{ + switch (gsm->state) { + case GSM_SEARCH: + case GSM1_START: + case GSM1_ADDRESS: + case GSM1_CONTROL: + case GSM1_DATA: + case GSM1_OVERRUN: + break; + default: + gsm->state = GSM_SEARCH; + break; + } +} + +/** * gsm1_receive - perform processing for non-transparency * @gsm: gsm data for this ldisc instance * @c: character @@ -2949,6 +3002,7 @@ static void gsm0_receive(struct gsm_mux *gsm, u8 c) static void gsm1_receive(struct gsm_mux *gsm, u8 c) { + gsm1_receive_state_check_and_fix(gsm); /* handle XON/XOFF */ if ((c & ISO_IEC_646_MASK) == XON) { gsm->constipated = true; @@ -2961,11 +3015,11 @@ static void gsm1_receive(struct gsm_mux *gsm, u8 c) } if (c == GSM1_SOF) { /* EOF is only valid in frame if we have got to the data state */ - if (gsm->state == GSM_DATA) { + if (gsm->state == GSM1_DATA) { if (gsm->count < 1) { /* Missing FSC */ gsm->malformed++; - gsm->state = GSM_START; + gsm->state = GSM1_START; return; } /* Remove the FCS from data */ @@ -2981,14 +3035,14 @@ static void gsm1_receive(struct gsm_mux *gsm, u8 c) gsm->fcs = gsm_fcs_add(gsm->fcs, gsm->buf[gsm->count]); gsm->len = gsm->count; gsm_queue(gsm); - gsm->state = GSM_START; + gsm->state = GSM1_START; return; } /* Any partial frame was a runt so go back to start */ - if (gsm->state != GSM_START) { + if (gsm->state != GSM1_START) { if (gsm->state != GSM_SEARCH) gsm->malformed++; - gsm->state = GSM_START; + gsm->state = GSM1_START; } /* A SOF in GSM_START means we are still reading idling or framing bytes */ @@ -3009,30 +3063,30 @@ static void gsm1_receive(struct gsm_mux *gsm, u8 c) gsm->escape = false; } switch (gsm->state) { - case GSM_START: /* First byte after SOF */ + case GSM1_START: /* First byte after SOF */ gsm->address = 0; - gsm->state = GSM_ADDRESS; + gsm->state = GSM1_ADDRESS; gsm->fcs = INIT_FCS; fallthrough; - case GSM_ADDRESS: /* Address continuation */ + case GSM1_ADDRESS: /* Address continuation */ gsm->fcs = gsm_fcs_add(gsm->fcs, c); if (gsm_read_ea(&gsm->address, c)) - gsm->state = GSM_CONTROL; + gsm->state = GSM1_CONTROL; break; - case GSM_CONTROL: /* Control Byte */ + case GSM1_CONTROL: /* Control Byte */ gsm->fcs = gsm_fcs_add(gsm->fcs, c); gsm->control = c; gsm->count = 0; - gsm->state = GSM_DATA; + gsm->state = GSM1_DATA; break; - case GSM_DATA: /* Data */ - if (gsm->count > gsm->mru) { /* Allow one for the FCS */ - gsm->state = GSM_OVERRUN; + case GSM1_DATA: /* Data */ + if (gsm->count > gsm->mru || gsm->count > MAX_MRU) { /* Allow one for the FCS */ + gsm->state = GSM1_OVERRUN; gsm->bad_size++; } else gsm->buf[gsm->count++] = c; break; - case GSM_OVERRUN: /* Over-long - eg a dropped SOF */ + case GSM1_OVERRUN: /* Over-long - eg a dropped SOF */ break; default: pr_debug("%s: unhandled state: %d\n", __func__, gsm->state); diff --git a/drivers/tty/serial/8250/8250_bcm7271.c b/drivers/tty/serial/8250/8250_bcm7271.c index de270863eb5e..2569ca69223f 100644 --- a/drivers/tty/serial/8250/8250_bcm7271.c +++ b/drivers/tty/serial/8250/8250_bcm7271.c @@ -673,18 +673,46 @@ static void init_real_clk_rates(struct device *dev, struct brcmuart_priv *priv) clk_set_rate(priv->baud_mux_clk, priv->default_mux_rate); } +static u32 find_quot(struct device *dev, u32 freq, u32 baud, u32 *percent) +{ + u32 quot; + u32 rate; + u64 hires_rate; + u64 hires_baud; + u64 hires_err; + + rate = freq / 16; + quot = DIV_ROUND_CLOSEST(rate, baud); + if (!quot) + return 0; + + /* increase resolution to get xx.xx percent */ + hires_rate = div_u64((u64)rate * 10000, (u64)quot); + hires_baud = (u64)baud * 10000; + + /* get the delta */ + if (hires_rate > hires_baud) + hires_err = (hires_rate - hires_baud); + else + hires_err = (hires_baud - hires_rate); + + *percent = (unsigned long)DIV_ROUND_CLOSEST_ULL(hires_err, baud); + + dev_dbg(dev, "Baud rate: %u, MUX Clk: %u, Error: %u.%u%%\n", + baud, freq, *percent / 100, *percent % 100); + + return quot; +} + static void set_clock_mux(struct uart_port *up, struct brcmuart_priv *priv, u32 baud) { u32 percent; u32 best_percent = UINT_MAX; u32 quot; + u32 freq; u32 best_quot = 1; - u32 rate; - int best_index = -1; - u64 hires_rate; - u64 hires_baud; - u64 hires_err; + u32 best_freq = 0; int rc; int i; int real_baud; @@ -693,44 +721,35 @@ static void set_clock_mux(struct uart_port *up, struct brcmuart_priv *priv, if (priv->baud_mux_clk == NULL) return; - /* Find the closest match for specified baud */ - for (i = 0; i < ARRAY_SIZE(priv->real_rates); i++) { - if (priv->real_rates[i] == 0) - continue; - rate = priv->real_rates[i] / 16; - quot = DIV_ROUND_CLOSEST(rate, baud); - if (!quot) - continue; - - /* increase resolution to get xx.xx percent */ - hires_rate = (u64)rate * 10000; - hires_baud = (u64)baud * 10000; - - hires_err = div_u64(hires_rate, (u64)quot); - - /* get the delta */ - if (hires_err > hires_baud) - hires_err = (hires_err - hires_baud); - else - hires_err = (hires_baud - hires_err); - - percent = (unsigned long)DIV_ROUND_CLOSEST_ULL(hires_err, baud); - dev_dbg(up->dev, - "Baud rate: %u, MUX Clk: %u, Error: %u.%u%%\n", - baud, priv->real_rates[i], percent / 100, - percent % 100); - if (percent < best_percent) { - best_percent = percent; - best_index = i; - best_quot = quot; + /* Try default_mux_rate first */ + quot = find_quot(up->dev, priv->default_mux_rate, baud, &percent); + if (quot) { + best_percent = percent; + best_freq = priv->default_mux_rate; + best_quot = quot; + } + /* If more than 1% error, find the closest match for specified baud */ + if (best_percent > 100) { + for (i = 0; i < ARRAY_SIZE(priv->real_rates); i++) { + freq = priv->real_rates[i]; + if (freq == 0 || freq == priv->default_mux_rate) + continue; + quot = find_quot(up->dev, freq, baud, &percent); + if (!quot) + continue; + + if (percent < best_percent) { + best_percent = percent; + best_freq = freq; + best_quot = quot; + } } } - if (best_index == -1) { + if (!best_freq) { dev_err(up->dev, "Error, %d BAUD rate is too fast.\n", baud); return; } - rate = priv->real_rates[best_index]; - rc = clk_set_rate(priv->baud_mux_clk, rate); + rc = clk_set_rate(priv->baud_mux_clk, best_freq); if (rc) dev_err(up->dev, "Error selecting BAUD MUX clock\n"); @@ -739,8 +758,8 @@ static void set_clock_mux(struct uart_port *up, struct brcmuart_priv *priv, dev_err(up->dev, "Error, baud: %d has %u.%u%% error\n", baud, percent / 100, percent % 100); - real_baud = rate / 16 / best_quot; - dev_dbg(up->dev, "Selecting BAUD MUX rate: %u\n", rate); + real_baud = best_freq / 16 / best_quot; + dev_dbg(up->dev, "Selecting BAUD MUX rate: %u\n", best_freq); dev_dbg(up->dev, "Requested baud: %u, Actual baud: %u\n", baud, real_baud); @@ -749,7 +768,7 @@ static void set_clock_mux(struct uart_port *up, struct brcmuart_priv *priv, i += (i / 2); priv->char_wait = ns_to_ktime(i); - up->uartclk = rate; + up->uartclk = best_freq; } static void brcmstb_set_termios(struct uart_port *up, diff --git a/drivers/tty/serial/8250/8250_mtk.c b/drivers/tty/serial/8250/8250_mtk.c index c365a349421a..b9cca210e171 100644 --- a/drivers/tty/serial/8250/8250_mtk.c +++ b/drivers/tty/serial/8250/8250_mtk.c @@ -209,15 +209,19 @@ static int mtk8250_startup(struct uart_port *port) static void mtk8250_shutdown(struct uart_port *port) { -#ifdef CONFIG_SERIAL_8250_DMA struct uart_8250_port *up = up_to_u8250p(port); struct mtk8250_data *data = port->private_data; + int irq = data->rx_wakeup_irq; +#ifdef CONFIG_SERIAL_8250_DMA if (up->dma) data->rx_status = DMA_RX_SHUTDOWN; #endif - return serial8250_do_shutdown(port); + serial8250_do_shutdown(port); + + if (irq >= 0) + serial8250_do_set_mctrl(&up->port, TIOCM_RTS); } static void mtk8250_disable_intrs(struct uart_8250_port *up, int mask) diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c index 03cf30e20b75..bf0065d1c8e9 100644 --- a/drivers/tty/serial/sc16is7xx.c +++ b/drivers/tty/serial/sc16is7xx.c @@ -555,16 +555,28 @@ static bool sc16is7xx_regmap_noinc(struct device *dev, unsigned int reg) return reg == SC16IS7XX_RHR_REG; } +/* + * Configure programmable baud rate generator (divisor) according to the + * desired baud rate. + * + * From the datasheet, the divisor is computed according to: + * + * XTAL1 input frequency + * ----------------------- + * prescaler + * divisor = --------------------------- + * baud-rate x sampling-rate + */ static int sc16is7xx_set_baud(struct uart_port *port, int baud) { struct sc16is7xx_one *one = to_sc16is7xx_one(port, port); u8 lcr; - u8 prescaler = 0; + unsigned int prescaler = 1; unsigned long clk = port->uartclk, div = clk / 16 / baud; if (div >= BIT(16)) { - prescaler = SC16IS7XX_MCR_CLKSEL_BIT; - div /= 4; + prescaler = 4; + div /= prescaler; } /* Enable enhanced features */ @@ -574,9 +586,10 @@ static int sc16is7xx_set_baud(struct uart_port *port, int baud) SC16IS7XX_EFR_ENABLE_BIT); sc16is7xx_efr_unlock(port); + /* If bit MCR_CLKSEL is set, the divide by 4 prescaler is activated. */ sc16is7xx_port_update(port, SC16IS7XX_MCR_REG, SC16IS7XX_MCR_CLKSEL_BIT, - prescaler); + prescaler == 1 ? 0 : SC16IS7XX_MCR_CLKSEL_BIT); /* Backup LCR and access special register set (DLL/DLH) */ lcr = sc16is7xx_port_read(port, SC16IS7XX_LCR_REG); @@ -592,7 +605,7 @@ static int sc16is7xx_set_baud(struct uart_port *port, int baud) /* Restore LCR and access to general register set */ sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, lcr); - return DIV_ROUND_CLOSEST(clk / 16, div); + return DIV_ROUND_CLOSEST((clk / prescaler) / 16, div); } static void sc16is7xx_handle_rx(struct uart_port *port, unsigned int rxlen, diff --git a/drivers/xen/xenbus/Makefile b/drivers/xen/xenbus/Makefile index 0c7532110815..b0d69602214e 100644 --- a/drivers/xen/xenbus/Makefile +++ b/drivers/xen/xenbus/Makefile @@ -1,15 +1,13 @@ # SPDX-License-Identifier: GPL-2.0 obj-y += xenbus.o -obj-y += xenbus_dev_frontend.o -xenbus-objs = -xenbus-objs += xenbus_client.o -xenbus-objs += xenbus_comms.o -xenbus-objs += xenbus_xs.o -xenbus-objs += xenbus_probe.o +xenbus-y := xenbus_client.o +xenbus-y += xenbus_comms.o +xenbus-y += xenbus_xs.o +xenbus-y += xenbus_probe.o -xenbus-be-objs-$(CONFIG_XEN_BACKEND) += xenbus_probe_backend.o -xenbus-objs += $(xenbus-be-objs-y) +xenbus-$(CONFIG_XEN_BACKEND) += xenbus_probe_backend.o +obj-y += xenbus_dev_frontend.o obj-$(CONFIG_XEN_BACKEND) += xenbus_dev_backend.o obj-$(CONFIG_XEN_XENBUS_FRONTEND) += xenbus_probe_frontend.o diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c index 3205e5d724c8..1a9ded0cddcb 100644 --- a/drivers/xen/xenbus/xenbus_probe.c +++ b/drivers/xen/xenbus/xenbus_probe.c @@ -65,13 +65,17 @@ #include "xenbus.h" -static int xs_init_irq; +static int xs_init_irq = -1; int xen_store_evtchn; EXPORT_SYMBOL_GPL(xen_store_evtchn); struct xenstore_domain_interface *xen_store_interface; EXPORT_SYMBOL_GPL(xen_store_interface); +#define XS_INTERFACE_READY \ + ((xen_store_interface != NULL) && \ + (xen_store_interface->connection == XENSTORE_CONNECTED)) + enum xenstore_init xen_store_domain_type; EXPORT_SYMBOL_GPL(xen_store_domain_type); @@ -751,19 +755,19 @@ static void xenbus_probe(void) { xenstored_ready = 1; - if (!xen_store_interface) { + if (!xen_store_interface) xen_store_interface = memremap(xen_store_gfn << XEN_PAGE_SHIFT, XEN_PAGE_SIZE, MEMREMAP_WB); - /* - * Now it is safe to free the IRQ used for xenstore late - * initialization. No need to unbind: it is about to be - * bound again from xb_init_comms. Note that calling - * unbind_from_irqhandler now would result in xen_evtchn_close() - * being called and the event channel not being enabled again - * afterwards, resulting in missed event notifications. - */ + /* + * Now it is safe to free the IRQ used for xenstore late + * initialization. No need to unbind: it is about to be + * bound again from xb_init_comms. Note that calling + * unbind_from_irqhandler now would result in xen_evtchn_close() + * being called and the event channel not being enabled again + * afterwards, resulting in missed event notifications. + */ + if (xs_init_irq >= 0) free_irq(xs_init_irq, &xb_waitq); - } /* * In the HVM case, xenbus_init() deferred its call to @@ -822,7 +826,7 @@ static int __init xenbus_probe_initcall(void) if (xen_store_domain_type == XS_PV || (xen_store_domain_type == XS_HVM && !xs_hvm_defer_init_for_callback() && - xen_store_interface != NULL)) + XS_INTERFACE_READY)) xenbus_probe(); /* @@ -831,7 +835,7 @@ static int __init xenbus_probe_initcall(void) * started, then probe. It will be triggered when communication * starts happening, by waiting on xb_waitq. */ - if (xen_store_domain_type == XS_LOCAL || xen_store_interface == NULL) { + if (xen_store_domain_type == XS_LOCAL || !XS_INTERFACE_READY) { struct task_struct *probe_task; probe_task = kthread_run(xenbus_probe_thread, NULL, @@ -1014,6 +1018,12 @@ static int __init xenbus_init(void) xen_store_interface = memremap(xen_store_gfn << XEN_PAGE_SHIFT, XEN_PAGE_SIZE, MEMREMAP_WB); + if (!xen_store_interface) { + pr_err("%s: cannot map HVM_PARAM_STORE_PFN=%llx\n", + __func__, v); + err = -EINVAL; + goto out_error; + } if (xen_store_interface->connection != XENSTORE_CONNECTED) wait = true; } diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c index f16f73581634..01338d4c2d9e 100644 --- a/fs/9p/vfs_dentry.c +++ b/fs/9p/vfs_dentry.c @@ -48,12 +48,17 @@ static int v9fs_cached_dentry_delete(const struct dentry *dentry) static void v9fs_dentry_release(struct dentry *dentry) { struct hlist_node *p, *n; + struct hlist_head head; p9_debug(P9_DEBUG_VFS, " dentry: %pd (%p)\n", dentry, dentry); - hlist_for_each_safe(p, n, (struct hlist_head *)&dentry->d_fsdata) + + spin_lock(&dentry->d_lock); + hlist_move_list((struct hlist_head *)&dentry->d_fsdata, &head); + spin_unlock(&dentry->d_lock); + + hlist_for_each_safe(p, n, &head) p9_fid_put(hlist_entry(p, struct p9_fid, dlist)); - dentry->d_fsdata = NULL; } static int v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags) diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 7a3308d77606..fd72fc38c8f5 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -348,6 +348,7 @@ void v9fs_evict_inode(struct inode *inode) __le32 __maybe_unused version; if (!is_bad_inode(inode)) { + netfs_wait_for_outstanding_io(inode); truncate_inode_pages_final(&inode->i_data); version = cpu_to_le32(v9inode->qid.version); diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 94fc049aff58..15bb7989c387 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -648,6 +648,7 @@ void afs_evict_inode(struct inode *inode) ASSERTCMP(inode->i_ino, ==, vnode->fid.vnode); + netfs_wait_for_outstanding_io(inode); truncate_inode_pages_final(&inode->i_data); afs_set_cache_aux(vnode, &aux); diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c index 97f50e9fd9eb..297487ee8323 100644 --- a/fs/afs/mntpt.c +++ b/fs/afs/mntpt.c @@ -140,6 +140,11 @@ static int afs_mntpt_set_params(struct fs_context *fc, struct dentry *mntpt) put_page(page); if (ret < 0) return ret; + + /* Don't cross a backup volume mountpoint from a backup volume */ + if (src_as->volume && src_as->volume->type == AFSVL_BACKVOL && + ctx->type == AFSVL_BACKVOL) + return -ENODEV; } return 0; diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h index 1bebba881d89..d801e19cb489 100644 --- a/fs/bcachefs/bcachefs_format.h +++ b/fs/bcachefs/bcachefs_format.h @@ -1555,6 +1555,12 @@ enum btree_id { BTREE_ID_NR }; +/* + * Maximum number of btrees that we will _ever_ have under the current scheme, + * where we refer to them with bitfields + */ +#define BTREE_ID_NR_MAX 64 + static inline bool btree_id_is_alloc(enum btree_id id) { switch (id) { diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c index 5bf98cb8b15d..d3bcb4e4e230 100644 --- a/fs/bcachefs/btree_iter.c +++ b/fs/bcachefs/btree_iter.c @@ -332,6 +332,8 @@ out: void bch2_assert_pos_locked(struct btree_trans *trans, enum btree_id id, struct bpos pos, bool key_cache) { + bch2_trans_verify_not_unlocked(trans); + struct btree_path *path; struct trans_for_each_path_inorder_iter iter; struct printbuf buf = PRINTBUF; diff --git a/fs/bcachefs/btree_iter.h b/fs/bcachefs/btree_iter.h index eab2a25bdc7a..798eb1c47966 100644 --- a/fs/bcachefs/btree_iter.h +++ b/fs/bcachefs/btree_iter.h @@ -838,7 +838,7 @@ __bch2_btree_iter_peek_and_restart(struct btree_trans *trans, #define drop_locks_do(_trans, _do) \ ({ \ bch2_trans_unlock(_trans); \ - _do ?: bch2_trans_relock(_trans); \ + (_do) ?: bch2_trans_relock(_trans); \ }) #define allocate_dropping_locks_errcode(_trans, _do) \ diff --git a/fs/bcachefs/buckets.c b/fs/bcachefs/buckets.c index e28d28ac2a13..b469586517a8 100644 --- a/fs/bcachefs/buckets.c +++ b/fs/bcachefs/buckets.c @@ -479,9 +479,8 @@ int bch2_check_fix_ptrs(struct btree_trans *trans, percpu_down_read(&c->mark_lock); - rcu_read_lock(); bkey_for_each_ptr_decode(k.k, ptrs_c, p, entry_c) { - struct bch_dev *ca = bch2_dev_rcu(c, p.ptr.dev); + struct bch_dev *ca = bch2_dev_tryget(c, p.ptr.dev); if (!ca) { if (fsck_err(c, ptr_to_invalid_device, "pointer to missing device %u\n" @@ -558,7 +557,7 @@ int bch2_check_fix_ptrs(struct btree_trans *trans, do_update = true; if (data_type != BCH_DATA_btree && p.ptr.gen != g->gen) - continue; + goto next; if (fsck_err_on(bucket_data_type_mismatch(g->data_type, data_type), c, ptr_bucket_data_type_mismatch, @@ -601,8 +600,9 @@ int bch2_check_fix_ptrs(struct btree_trans *trans, bch2_bkey_val_to_text(&buf, c, k), buf.buf))) do_update = true; } +next: + bch2_dev_put(ca); } - rcu_read_unlock(); if (do_update) { if (flags & BTREE_TRIGGER_is_root) { @@ -638,9 +638,10 @@ int bch2_check_fix_ptrs(struct btree_trans *trans, } else { struct bkey_ptrs ptrs; union bch_extent_entry *entry; + + rcu_read_lock(); restart_drop_ptrs: ptrs = bch2_bkey_ptrs(bkey_i_to_s(new)); - rcu_read_lock(); bkey_for_each_ptr_decode(bkey_i_to_s(new).k, ptrs, p, entry) { struct bch_dev *ca = bch2_dev_rcu(c, p.ptr.dev); struct bucket *g = PTR_GC_BUCKET(ca, &p.ptr); @@ -1464,7 +1465,7 @@ int bch2_trans_mark_dev_sbs_flags(struct bch_fs *c, for_each_online_member(c, ca) { int ret = bch2_trans_mark_dev_sb(c, ca, flags); if (ret) { - bch2_dev_put(ca); + percpu_ref_put(&ca->io_ref); return ret; } } diff --git a/fs/bcachefs/checksum.c b/fs/bcachefs/checksum.c index 85198f391e9c..3bd3aba90d8f 100644 --- a/fs/bcachefs/checksum.c +++ b/fs/bcachefs/checksum.c @@ -233,7 +233,7 @@ struct bch_csum bch2_checksum(struct bch_fs *c, unsigned type, return ret; } default: - BUG(); + return (struct bch_csum) {}; } } @@ -307,7 +307,7 @@ static struct bch_csum __bch2_checksum_bio(struct bch_fs *c, unsigned type, return ret; } default: - BUG(); + return (struct bch_csum) {}; } } @@ -352,8 +352,12 @@ int __bch2_encrypt_bio(struct bch_fs *c, unsigned type, bytes += bv.bv_len; } - sg_mark_end(sg - 1); - return do_encrypt_sg(c->chacha20, nonce, sgl, bytes); + if (sg != sgl) { + sg_mark_end(sg - 1); + return do_encrypt_sg(c->chacha20, nonce, sgl, bytes); + } + + return ret; } struct bch_csum bch2_checksum_merge(unsigned type, struct bch_csum a, @@ -648,26 +652,26 @@ err: static int bch2_alloc_ciphers(struct bch_fs *c) { - int ret; - - if (!c->chacha20) - c->chacha20 = crypto_alloc_sync_skcipher("chacha20", 0, 0); - ret = PTR_ERR_OR_ZERO(c->chacha20); + if (c->chacha20) + return 0; + struct crypto_sync_skcipher *chacha20 = crypto_alloc_sync_skcipher("chacha20", 0, 0); + int ret = PTR_ERR_OR_ZERO(chacha20); if (ret) { bch_err(c, "error requesting chacha20 module: %s", bch2_err_str(ret)); return ret; } - if (!c->poly1305) - c->poly1305 = crypto_alloc_shash("poly1305", 0, 0); - ret = PTR_ERR_OR_ZERO(c->poly1305); - + struct crypto_shash *poly1305 = crypto_alloc_shash("poly1305", 0, 0); + ret = PTR_ERR_OR_ZERO(poly1305); if (ret) { bch_err(c, "error requesting poly1305 module: %s", bch2_err_str(ret)); + crypto_free_sync_skcipher(chacha20); return ret; } + c->chacha20 = chacha20; + c->poly1305 = poly1305; return 0; } @@ -762,11 +766,11 @@ err: void bch2_fs_encryption_exit(struct bch_fs *c) { - if (!IS_ERR_OR_NULL(c->poly1305)) + if (c->poly1305) crypto_free_shash(c->poly1305); - if (!IS_ERR_OR_NULL(c->chacha20)) + if (c->chacha20) crypto_free_sync_skcipher(c->chacha20); - if (!IS_ERR_OR_NULL(c->sha256)) + if (c->sha256) crypto_free_shash(c->sha256); } @@ -779,6 +783,7 @@ int bch2_fs_encryption_init(struct bch_fs *c) c->sha256 = crypto_alloc_shash("sha256", 0, 0); ret = PTR_ERR_OR_ZERO(c->sha256); if (ret) { + c->sha256 = NULL; bch_err(c, "error requesting sha256 module: %s", bch2_err_str(ret)); goto out; } diff --git a/fs/bcachefs/dirent.c b/fs/bcachefs/dirent.c index 6bbf9a7d9e4d..c67460d8205d 100644 --- a/fs/bcachefs/dirent.c +++ b/fs/bcachefs/dirent.c @@ -15,6 +15,9 @@ static unsigned bch2_dirent_name_bytes(struct bkey_s_c_dirent d) { + if (bkey_val_bytes(d.k) < offsetof(struct bch_dirent, d_name)) + return 0; + unsigned bkey_u64s = bkey_val_u64s(d.k); unsigned bkey_bytes = bkey_u64s * sizeof(u64); u64 last_u64 = ((u64*)d.v)[bkey_u64s - 1]; diff --git a/fs/bcachefs/fs-io-buffered.c b/fs/bcachefs/fs-io-buffered.c index b0a33fabadf8..6b69e5cd68dd 100644 --- a/fs/bcachefs/fs-io-buffered.c +++ b/fs/bcachefs/fs-io-buffered.c @@ -257,7 +257,6 @@ void bch2_readahead(struct readahead_control *ractl) struct bch_inode_info *inode = to_bch_ei(ractl->mapping->host); struct bch_fs *c = inode->v.i_sb->s_fs_info; struct bch_io_opts opts; - struct btree_trans *trans = bch2_trans_get(c); struct folio *folio; struct readpages_iter readpages_iter; @@ -269,6 +268,7 @@ void bch2_readahead(struct readahead_control *ractl) bch2_pagecache_add_get(inode); + struct btree_trans *trans = bch2_trans_get(c); while ((folio = readpage_iter_peek(&readpages_iter))) { unsigned n = min_t(unsigned, readpages_iter.folios.nr - @@ -289,10 +289,10 @@ void bch2_readahead(struct readahead_control *ractl) &readpages_iter); bch2_trans_unlock(trans); } + bch2_trans_put(trans); bch2_pagecache_add_put(inode); - bch2_trans_put(trans); darray_exit(&readpages_iter.folios); } diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c index fd851f10d11c..96040a95cf46 100644 --- a/fs/bcachefs/fs.c +++ b/fs/bcachefs/fs.c @@ -188,8 +188,7 @@ static struct bch_inode_info *bch2_inode_insert(struct bch_fs *c, struct bch_ino BUG_ON(!old); if (unlikely(old != inode)) { - __destroy_inode(&inode->v); - kmem_cache_free(bch2_inode_cache, inode); + discard_new_inode(&inode->v); inode = old; } else { mutex_lock(&c->vfs_inodes_lock); @@ -1145,6 +1144,8 @@ static int bch2_open(struct inode *vinode, struct file *file) return ret; } + file->f_mode |= FMODE_CAN_ODIRECT; + return generic_file_open(vinode, file); } @@ -1237,7 +1238,6 @@ static const struct address_space_operations bch_address_space_operations = { .write_end = bch2_write_end, .invalidate_folio = bch2_invalidate_folio, .release_folio = bch2_release_folio, - .direct_IO = noop_direct_IO, #ifdef CONFIG_MIGRATION .migrate_folio = filemap_migrate_folio, #endif diff --git a/fs/bcachefs/printbuf.c b/fs/bcachefs/printbuf.c index 8b0369185f5c..9f529e4c1b16 100644 --- a/fs/bcachefs/printbuf.c +++ b/fs/bcachefs/printbuf.c @@ -45,6 +45,13 @@ int bch2_printbuf_make_room(struct printbuf *out, unsigned extra) unsigned new_size = roundup_pow_of_two(out->size + extra); + /* Sanity check... */ + if (new_size > PAGE_SIZE << MAX_PAGE_ORDER) { + out->allocation_failure = true; + out->overflow = true; + return -ENOMEM; + } + /* * Note: output buffer must be freeable with kfree(), it's not required * that the user use printbuf_exit(). diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c index 1266916ac03f..cf513fc79ce4 100644 --- a/fs/bcachefs/recovery.c +++ b/fs/bcachefs/recovery.c @@ -35,6 +35,9 @@ void bch2_btree_lost_data(struct bch_fs *c, enum btree_id btree) { + if (btree >= BTREE_ID_NR_MAX) + return; + u64 b = BIT_ULL(btree); if (!(c->sb.btrees_lost_data & b)) { @@ -808,9 +811,11 @@ use_clean: clear_bit(BCH_FS_fsck_running, &c->flags); /* fsync if we fixed errors */ - if (test_bit(BCH_FS_errors_fixed, &c->flags)) { + if (test_bit(BCH_FS_errors_fixed, &c->flags) && + bch2_write_ref_tryget(c, BCH_WRITE_REF_fsync)) { bch2_journal_flush_all_pins(&c->journal); bch2_journal_meta(&c->journal); + bch2_write_ref_put(c, BCH_WRITE_REF_fsync); } /* If we fixed errors, verify that fs is actually clean now: */ diff --git a/fs/bcachefs/replicas.c b/fs/bcachefs/replicas.c index bd1d5d085e23..57a1f09cca09 100644 --- a/fs/bcachefs/replicas.c +++ b/fs/bcachefs/replicas.c @@ -23,14 +23,12 @@ static int bch2_memcmp(const void *l, const void *r, const void *priv) static void verify_replicas_entry(struct bch_replicas_entry_v1 *e) { #ifdef CONFIG_BCACHEFS_DEBUG - unsigned i; - BUG_ON(e->data_type >= BCH_DATA_NR); BUG_ON(!e->nr_devs); BUG_ON(e->nr_required > 1 && e->nr_required >= e->nr_devs); - for (i = 0; i + 1 < e->nr_devs; i++) + for (unsigned i = 0; i + 1 < e->nr_devs; i++) BUG_ON(e->devs[i] >= e->devs[i + 1]); #endif } @@ -192,24 +190,17 @@ cpu_replicas_add_entry(struct bch_fs *c, struct bch_replicas_cpu *old, struct bch_replicas_entry_v1 *new_entry) { - unsigned i; struct bch_replicas_cpu new = { .nr = old->nr + 1, .entry_size = max_t(unsigned, old->entry_size, replicas_entry_bytes(new_entry)), }; - for (i = 0; i < new_entry->nr_devs; i++) - BUG_ON(!bch2_dev_exists(c, new_entry->devs[i])); - - BUG_ON(!new_entry->data_type); - verify_replicas_entry(new_entry); - new.entries = kcalloc(new.nr, new.entry_size, GFP_KERNEL); if (!new.entries) return new; - for (i = 0; i < old->nr; i++) + for (unsigned i = 0; i < old->nr; i++) memcpy(cpu_replicas_entry(&new, i), cpu_replicas_entry(old, i), old->entry_size); @@ -230,8 +221,6 @@ static inline int __replicas_entry_idx(struct bch_replicas_cpu *r, if (unlikely(entry_size > r->entry_size)) return -1; - verify_replicas_entry(search); - #define entry_cmp(_l, _r) memcmp(_l, _r, entry_size) idx = eytzinger0_find(r->entries, r->nr, r->entry_size, entry_cmp, search); @@ -524,13 +513,16 @@ int bch2_replicas_gc_start(struct bch_fs *c, unsigned typemask) c->replicas_gc.nr = 0; c->replicas_gc.entry_size = 0; - for_each_cpu_replicas_entry(&c->replicas, e) - if (!((1 << e->data_type) & typemask)) { + for_each_cpu_replicas_entry(&c->replicas, e) { + /* Preserve unknown data types */ + if (e->data_type >= BCH_DATA_NR || + !((1 << e->data_type) & typemask)) { c->replicas_gc.nr++; c->replicas_gc.entry_size = max_t(unsigned, c->replicas_gc.entry_size, replicas_entry_bytes(e)); } + } c->replicas_gc.entries = kcalloc(c->replicas_gc.nr, c->replicas_gc.entry_size, @@ -542,7 +534,8 @@ int bch2_replicas_gc_start(struct bch_fs *c, unsigned typemask) } for_each_cpu_replicas_entry(&c->replicas, e) - if (!((1 << e->data_type) & typemask)) + if (e->data_type >= BCH_DATA_NR || + !((1 << e->data_type) & typemask)) memcpy(cpu_replicas_entry(&c->replicas_gc, i++), e, c->replicas_gc.entry_size); @@ -998,7 +991,7 @@ unsigned bch2_sb_dev_has_data(struct bch_sb *sb, unsigned dev) { struct bch_sb_field_replicas *replicas; struct bch_sb_field_replicas_v0 *replicas_v0; - unsigned i, data_has = 0; + unsigned data_has = 0; replicas = bch2_sb_field_get(sb, replicas); replicas_v0 = bch2_sb_field_get(sb, replicas_v0); @@ -1006,17 +999,26 @@ unsigned bch2_sb_dev_has_data(struct bch_sb *sb, unsigned dev) if (replicas) { struct bch_replicas_entry_v1 *r; - for_each_replicas_entry(replicas, r) - for (i = 0; i < r->nr_devs; i++) + for_each_replicas_entry(replicas, r) { + if (r->data_type >= sizeof(data_has) * 8) + continue; + + for (unsigned i = 0; i < r->nr_devs; i++) if (r->devs[i] == dev) data_has |= 1 << r->data_type; + } + } else if (replicas_v0) { struct bch_replicas_entry_v0 *r; - for_each_replicas_entry_v0(replicas_v0, r) - for (i = 0; i < r->nr_devs; i++) + for_each_replicas_entry_v0(replicas_v0, r) { + if (r->data_type >= sizeof(data_has) * 8) + continue; + + for (unsigned i = 0; i < r->nr_devs; i++) if (r->devs[i] == dev) data_has |= 1 << r->data_type; + } } diff --git a/fs/bcachefs/sb-errors_types.h b/fs/bcachefs/sb-errors_types.h index 87324747351a..666599d3fb9d 100644 --- a/fs/bcachefs/sb-errors_types.h +++ b/fs/bcachefs/sb-errors_types.h @@ -273,7 +273,9 @@ x(dup_backpointer_to_bad_csum_extent, 265) \ x(btree_bitmap_not_marked, 266) \ x(sb_clean_entry_overrun, 267) \ - x(btree_ptr_v2_written_0, 268) + x(btree_ptr_v2_written_0, 268) \ + x(subvol_snapshot_bad, 269) \ + x(subvol_inode_bad, 270) enum bch_sb_error_id { #define x(t, n) BCH_FSCK_ERR_##t = n, diff --git a/fs/bcachefs/snapshot.h b/fs/bcachefs/snapshot.h index bd5d74269d15..ab13d8f4b41e 100644 --- a/fs/bcachefs/snapshot.h +++ b/fs/bcachefs/snapshot.h @@ -176,12 +176,9 @@ static inline bool bch2_snapshot_is_ancestor(struct bch_fs *c, u32 id, u32 ances static inline bool bch2_snapshot_has_children(struct bch_fs *c, u32 id) { - const struct snapshot_t *t; - bool ret; - rcu_read_lock(); - t = snapshot_t(c, id); - ret = (t->children[0]|t->children[1]) != 0; + const struct snapshot_t *t = snapshot_t(c, id); + bool ret = t && (t->children[0]|t->children[1]) != 0; rcu_read_unlock(); return ret; diff --git a/fs/bcachefs/subvolume.c b/fs/bcachefs/subvolume.c index 132213761ef6..dfc9cf305756 100644 --- a/fs/bcachefs/subvolume.c +++ b/fs/bcachefs/subvolume.c @@ -210,12 +210,21 @@ int bch2_check_subvol_children(struct bch_fs *c) int bch2_subvolume_invalid(struct bch_fs *c, struct bkey_s_c k, enum bch_validate_flags flags, struct printbuf *err) { + struct bkey_s_c_subvolume subvol = bkey_s_c_to_subvolume(k); int ret = 0; bkey_fsck_err_on(bkey_lt(k.k->p, SUBVOL_POS_MIN) || bkey_gt(k.k->p, SUBVOL_POS_MAX), c, err, subvol_pos_bad, "invalid pos"); + + bkey_fsck_err_on(!subvol.v->snapshot, c, err, + subvol_snapshot_bad, + "invalid snapshot"); + + bkey_fsck_err_on(!subvol.v->inode, c, err, + subvol_inode_bad, + "invalid inode"); fsck_err: return ret; } diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c index 294a9d35a9f2..2206a8dee693 100644 --- a/fs/bcachefs/super.c +++ b/fs/bcachefs/super.c @@ -551,9 +551,9 @@ static void __bch2_fs_free(struct bch_fs *c) bch2_fs_io_read_exit(c); bch2_fs_buckets_waiting_for_journal_exit(c); bch2_fs_btree_interior_update_exit(c); - bch2_fs_btree_iter_exit(c); bch2_fs_btree_key_cache_exit(&c->btree_key_cache); bch2_fs_btree_cache_exit(c); + bch2_fs_btree_iter_exit(c); bch2_fs_replicas_exit(c); bch2_fs_journal_exit(&c->journal); bch2_io_clock_exit(&c->io_clock[WRITE]); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 47d48233b592..3774c191e36d 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -477,7 +477,7 @@ again: if (path->slots[0] >= nritems) { ret = btrfs_next_leaf(root, path); if (ret) { - if (ret > 1) + if (ret > 0) return -ENOENT; return ret; } diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index eb28141d5c37..fc2a7ea26354 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -468,6 +468,7 @@ int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info) } if (!qgroup) { struct btrfs_qgroup *prealloc; + struct btrfs_root *tree_root = fs_info->tree_root; prealloc = kzalloc(sizeof(*prealloc), GFP_KERNEL); if (!prealloc) { @@ -475,6 +476,25 @@ int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info) goto out; } qgroup = add_qgroup_rb(fs_info, prealloc, found_key.offset); + /* + * If a qgroup exists for a subvolume ID, it is possible + * that subvolume has been deleted, in which case + * re-using that ID would lead to incorrect accounting. + * + * Ensure that we skip any such subvol ids. + * + * We don't need to lock because this is only called + * during mount before we start doing things like creating + * subvolumes. + */ + if (is_fstree(qgroup->qgroupid) && + qgroup->qgroupid > tree_root->free_objectid) + /* + * Don't need to check against BTRFS_LAST_FREE_OBJECTID, + * as it will get checked on the next call to + * btrfs_get_free_objectid. + */ + tree_root->free_objectid = qgroup->qgroupid + 1; } ret = btrfs_sysfs_add_one_qgroup(fs_info, qgroup); if (ret < 0) @@ -3820,14 +3840,14 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid, /* we're resuming qgroup rescan at mount time */ if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN)) { - btrfs_warn(fs_info, + btrfs_debug(fs_info, "qgroup rescan init failed, qgroup rescan is not queued"); ret = -EINVAL; } else if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON)) { - btrfs_warn(fs_info, + btrfs_debug(fs_info, "qgroup rescan init failed, qgroup is not enabled"); - ret = -EINVAL; + ret = -ENOTCONN; } if (ret) @@ -3838,14 +3858,12 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid, if (init_flags) { if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN) { - btrfs_warn(fs_info, - "qgroup rescan is already in progress"); ret = -EINPROGRESS; } else if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON)) { - btrfs_warn(fs_info, + btrfs_debug(fs_info, "qgroup rescan init failed, qgroup is not enabled"); - ret = -EINVAL; + ret = -ENOTCONN; } else if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED) { /* Quota disable is in progress */ ret = -EBUSY; diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 4b22cfe9a98c..afd6932f5e89 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -2100,7 +2100,7 @@ static int scrub_simple_mirror(struct scrub_ctx *sctx, struct btrfs_fs_info *fs_info = sctx->fs_info; const u64 logical_end = logical_start + logical_length; u64 cur_logical = logical_start; - int ret; + int ret = 0; /* The range must be inside the bg */ ASSERT(logical_start >= bg->start && logical_end <= bg->start + bg->length); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 2dbc930a20f7..f05cce7c8b8d 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -119,6 +119,7 @@ enum { Opt_thread_pool, Opt_treelog, Opt_user_subvol_rm_allowed, + Opt_norecovery, /* Rescue options */ Opt_rescue, @@ -245,6 +246,8 @@ static const struct fs_parameter_spec btrfs_fs_parameters[] = { __fsparam(NULL, "nologreplay", Opt_nologreplay, fs_param_deprecated, NULL), /* Deprecated, with alias rescue=usebackuproot */ __fsparam(NULL, "usebackuproot", Opt_usebackuproot, fs_param_deprecated, NULL), + /* For compatibility only, alias for "rescue=nologreplay". */ + fsparam_flag("norecovery", Opt_norecovery), /* Debugging options. */ fsparam_flag_no("enospc_debug", Opt_enospc_debug), @@ -438,6 +441,11 @@ static int btrfs_parse_param(struct fs_context *fc, struct fs_parameter *param) "'nologreplay' is deprecated, use 'rescue=nologreplay' instead"); btrfs_set_opt(ctx->mount_opt, NOLOGREPLAY); break; + case Opt_norecovery: + btrfs_info(NULL, +"'norecovery' is for compatibility only, recommended to use 'rescue=nologreplay'"); + btrfs_set_opt(ctx->mount_opt, NOLOGREPLAY); + break; case Opt_flushoncommit: if (result.negated) btrfs_clear_opt(ctx->mount_opt, FLUSHONCOMMIT); diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 9b43fa493219..947a87576f6c 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1290,7 +1290,7 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx, struct btrfs_chunk_map *map) { struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace; - struct btrfs_device *device = map->stripes[zone_idx].dev; + struct btrfs_device *device; int dev_replace_is_ongoing = 0; unsigned int nofs_flag; struct blk_zone zone; @@ -1298,7 +1298,11 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx, info->physical = map->stripes[zone_idx].physical; + down_read(&dev_replace->rwsem); + device = map->stripes[zone_idx].dev; + if (!device->bdev) { + up_read(&dev_replace->rwsem); info->alloc_offset = WP_MISSING_DEV; return 0; } @@ -1308,6 +1312,7 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx, __set_bit(zone_idx, active); if (!btrfs_dev_is_sequential(device, info->physical)) { + up_read(&dev_replace->rwsem); info->alloc_offset = WP_CONVENTIONAL; return 0; } @@ -1315,11 +1320,9 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx, /* This zone will be used for allocation, so mark this zone non-empty. */ btrfs_dev_clear_zone_empty(device, info->physical); - down_read(&dev_replace->rwsem); dev_replace_is_ongoing = btrfs_dev_replace_is_ongoing(dev_replace); if (dev_replace_is_ongoing && dev_replace->tgtdev != NULL) btrfs_dev_clear_zone_empty(dev_replace->tgtdev, info->physical); - up_read(&dev_replace->rwsem); /* * The group is mapped to a sequential zone. Get the zone write pointer @@ -1330,6 +1333,7 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx, ret = btrfs_get_dev_zone(device, info->physical, &zone); memalloc_nofs_restore(nofs_flag); if (ret) { + up_read(&dev_replace->rwsem); if (ret != -EIO && ret != -EOPNOTSUPP) return ret; info->alloc_offset = WP_MISSING_DEV; @@ -1341,6 +1345,7 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx, "zoned: unexpected conventional zone %llu on device %s (devid %llu)", zone.start << SECTOR_SHIFT, rcu_str_deref(device->name), device->devid); + up_read(&dev_replace->rwsem); return -EIO; } @@ -1368,6 +1373,8 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx, break; } + up_read(&dev_replace->rwsem); + return 0; } diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 0e9f56eaba1e..82a2e2a06a65 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1336,8 +1336,12 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry) struct inode *inode = d_inode(dentry); struct ceph_mds_request *req; bool try_async = ceph_test_mount_opt(fsc, ASYNC_DIROPS); + struct dentry *dn; int err = -EROFS; int op; + char *path; + int pathlen; + u64 pathbase; if (ceph_snap(dir) == CEPH_SNAPDIR) { /* rmdir .snap/foo is RMSNAP */ @@ -1351,6 +1355,30 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry) CEPH_MDS_OP_RMDIR : CEPH_MDS_OP_UNLINK; } else goto out; + + dn = d_find_alias(dir); + if (!dn) { + try_async = false; + } else { + path = ceph_mdsc_build_path(mdsc, dn, &pathlen, &pathbase, 0); + if (IS_ERR(path)) { + try_async = false; + err = 0; + } else { + err = ceph_mds_check_access(mdsc, path, MAY_WRITE); + } + ceph_mdsc_free_path(path, pathlen); + dput(dn); + + /* For none EACCES cases will let the MDS do the mds auth check */ + if (err == -EACCES) { + return err; + } else if (err < 0) { + try_async = false; + err = 0; + } + } + retry: req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS); if (IS_ERR(req)) { diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 16873d07692f..4b8d59ebda00 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -366,6 +366,12 @@ int ceph_open(struct inode *inode, struct file *file) struct ceph_file_info *fi = file->private_data; int err; int flags, fmode, wanted; + struct dentry *dentry; + char *path; + int pathlen; + u64 pathbase; + bool do_sync = false; + int mask = MAY_READ; if (fi) { doutc(cl, "file %p is already opened\n", file); @@ -387,6 +393,31 @@ int ceph_open(struct inode *inode, struct file *file) fmode = ceph_flags_to_mode(flags); wanted = ceph_caps_for_mode(fmode); + if (fmode & CEPH_FILE_MODE_WR) + mask |= MAY_WRITE; + dentry = d_find_alias(inode); + if (!dentry) { + do_sync = true; + } else { + path = ceph_mdsc_build_path(mdsc, dentry, &pathlen, &pathbase, 0); + if (IS_ERR(path)) { + do_sync = true; + err = 0; + } else { + err = ceph_mds_check_access(mdsc, path, mask); + } + ceph_mdsc_free_path(path, pathlen); + dput(dentry); + + /* For none EACCES cases will let the MDS do the mds auth check */ + if (err == -EACCES) { + return err; + } else if (err < 0) { + do_sync = true; + err = 0; + } + } + /* snapped files are read-only */ if (ceph_snap(inode) != CEPH_NOSNAP && (file->f_mode & FMODE_WRITE)) return -EROFS; @@ -402,7 +433,7 @@ int ceph_open(struct inode *inode, struct file *file) * asynchronously. */ spin_lock(&ci->i_ceph_lock); - if (__ceph_is_any_real_caps(ci) && + if (!do_sync && __ceph_is_any_real_caps(ci) && (((fmode & CEPH_FILE_MODE_WR) == 0) || ci->i_auth_cap)) { int mds_wanted = __ceph_caps_mds_wanted(ci, true); int issued = __ceph_caps_issued(ci, NULL); @@ -420,7 +451,7 @@ int ceph_open(struct inode *inode, struct file *file) ceph_check_caps(ci, 0); return ceph_init_file(inode, file, fmode); - } else if (ceph_snap(inode) != CEPH_NOSNAP && + } else if (!do_sync && ceph_snap(inode) != CEPH_NOSNAP && (ci->i_snap_caps & wanted) == wanted) { __ceph_touch_fmode(ci, mdsc, fmode); spin_unlock(&ci->i_ceph_lock); @@ -759,6 +790,9 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, bool try_async = ceph_test_mount_opt(fsc, ASYNC_DIROPS); int mask; int err; + char *path; + int pathlen; + u64 pathbase; doutc(cl, "%p %llx.%llx dentry %p '%pd' %s flags %d mode 0%o\n", dir, ceph_vinop(dir), dentry, dentry, @@ -776,6 +810,34 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, */ flags &= ~O_TRUNC; + dn = d_find_alias(dir); + if (!dn) { + try_async = false; + } else { + path = ceph_mdsc_build_path(mdsc, dn, &pathlen, &pathbase, 0); + if (IS_ERR(path)) { + try_async = false; + err = 0; + } else { + int fmode = ceph_flags_to_mode(flags); + + mask = MAY_READ; + if (fmode & CEPH_FILE_MODE_WR) + mask |= MAY_WRITE; + err = ceph_mds_check_access(mdsc, path, mask); + } + ceph_mdsc_free_path(path, pathlen); + dput(dn); + + /* For none EACCES cases will let the MDS do the mds auth check */ + if (err == -EACCES) { + return err; + } else if (err < 0) { + try_async = false; + err = 0; + } + } + retry: if (flags & O_CREAT) { if (ceph_quota_is_max_files_exceeded(dir)) diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 99561fddcb38..249ddfbb1b03 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -2482,6 +2482,34 @@ int __ceph_setattr(struct mnt_idmap *idmap, struct inode *inode, bool lock_snap_rwsem = false; bool fill_fscrypt; int truncate_retry = 20; /* The RMW will take around 50ms */ + struct dentry *dentry; + char *path; + int pathlen; + u64 pathbase; + bool do_sync = false; + + dentry = d_find_alias(inode); + if (!dentry) { + do_sync = true; + } else { + path = ceph_mdsc_build_path(mdsc, dentry, &pathlen, &pathbase, 0); + if (IS_ERR(path)) { + do_sync = true; + err = 0; + } else { + err = ceph_mds_check_access(mdsc, path, MAY_WRITE); + } + ceph_mdsc_free_path(path, pathlen); + dput(dentry); + + /* For none EACCES cases will let the MDS do the mds auth check */ + if (err == -EACCES) { + return err; + } else if (err < 0) { + do_sync = true; + err = 0; + } + } retry: prealloc_cf = ceph_alloc_cap_flush(); @@ -2528,7 +2556,7 @@ retry: /* It should never be re-set once set */ WARN_ON_ONCE(ci->fscrypt_auth); - if (issued & CEPH_CAP_AUTH_EXCL) { + if (!do_sync && (issued & CEPH_CAP_AUTH_EXCL)) { dirtied |= CEPH_CAP_AUTH_EXCL; kfree(ci->fscrypt_auth); ci->fscrypt_auth = (u8 *)cia->fscrypt_auth; @@ -2557,7 +2585,7 @@ retry: ceph_vinop(inode), from_kuid(&init_user_ns, inode->i_uid), from_kuid(&init_user_ns, attr->ia_uid)); - if (issued & CEPH_CAP_AUTH_EXCL) { + if (!do_sync && (issued & CEPH_CAP_AUTH_EXCL)) { inode->i_uid = fsuid; dirtied |= CEPH_CAP_AUTH_EXCL; } else if ((issued & CEPH_CAP_AUTH_SHARED) == 0 || @@ -2575,7 +2603,7 @@ retry: ceph_vinop(inode), from_kgid(&init_user_ns, inode->i_gid), from_kgid(&init_user_ns, attr->ia_gid)); - if (issued & CEPH_CAP_AUTH_EXCL) { + if (!do_sync && (issued & CEPH_CAP_AUTH_EXCL)) { inode->i_gid = fsgid; dirtied |= CEPH_CAP_AUTH_EXCL; } else if ((issued & CEPH_CAP_AUTH_SHARED) == 0 || @@ -2589,7 +2617,7 @@ retry: if (ia_valid & ATTR_MODE) { doutc(cl, "%p %llx.%llx mode 0%o -> 0%o\n", inode, ceph_vinop(inode), inode->i_mode, attr->ia_mode); - if (issued & CEPH_CAP_AUTH_EXCL) { + if (!do_sync && (issued & CEPH_CAP_AUTH_EXCL)) { inode->i_mode = attr->ia_mode; dirtied |= CEPH_CAP_AUTH_EXCL; } else if ((issued & CEPH_CAP_AUTH_SHARED) == 0 || @@ -2608,11 +2636,11 @@ retry: inode, ceph_vinop(inode), atime.tv_sec, atime.tv_nsec, attr->ia_atime.tv_sec, attr->ia_atime.tv_nsec); - if (issued & CEPH_CAP_FILE_EXCL) { + if (!do_sync && (issued & CEPH_CAP_FILE_EXCL)) { ci->i_time_warp_seq++; inode_set_atime_to_ts(inode, attr->ia_atime); dirtied |= CEPH_CAP_FILE_EXCL; - } else if ((issued & CEPH_CAP_FILE_WR) && + } else if (!do_sync && (issued & CEPH_CAP_FILE_WR) && timespec64_compare(&atime, &attr->ia_atime) < 0) { inode_set_atime_to_ts(inode, attr->ia_atime); @@ -2648,7 +2676,7 @@ retry: CEPH_FSCRYPT_BLOCK_SIZE)); req->r_fscrypt_file = attr->ia_size; fill_fscrypt = true; - } else if ((issued & CEPH_CAP_FILE_EXCL) && attr->ia_size >= isize) { + } else if (!do_sync && (issued & CEPH_CAP_FILE_EXCL) && attr->ia_size >= isize) { if (attr->ia_size > isize) { i_size_write(inode, attr->ia_size); inode->i_blocks = calc_inode_blocks(attr->ia_size); @@ -2685,11 +2713,11 @@ retry: inode, ceph_vinop(inode), mtime.tv_sec, mtime.tv_nsec, attr->ia_mtime.tv_sec, attr->ia_mtime.tv_nsec); - if (issued & CEPH_CAP_FILE_EXCL) { + if (!do_sync && (issued & CEPH_CAP_FILE_EXCL)) { ci->i_time_warp_seq++; inode_set_mtime_to_ts(inode, attr->ia_mtime); dirtied |= CEPH_CAP_FILE_EXCL; - } else if ((issued & CEPH_CAP_FILE_WR) && + } else if (!do_sync && (issued & CEPH_CAP_FILE_WR) && timespec64_compare(&mtime, &attr->ia_mtime) < 0) { inode_set_mtime_to_ts(inode, attr->ia_mtime); dirtied |= CEPH_CAP_FILE_WR; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 360b686c3c67..c2157f6e0c69 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -4112,10 +4112,13 @@ static void handle_session(struct ceph_mds_session *session, void *p = msg->front.iov_base; void *end = p + msg->front.iov_len; struct ceph_mds_session_head *h; - u32 op; + struct ceph_mds_cap_auth *cap_auths = NULL; + u32 op, cap_auths_num = 0; u64 seq, features = 0; int wake = 0; bool blocklisted = false; + u32 i; + /* decode */ ceph_decode_need(&p, end, sizeof(*h), bad); @@ -4160,7 +4163,101 @@ static void handle_session(struct ceph_mds_session *session, } } + if (msg_version >= 6) { + ceph_decode_32_safe(&p, end, cap_auths_num, bad); + doutc(cl, "cap_auths_num %d\n", cap_auths_num); + + if (cap_auths_num && op != CEPH_SESSION_OPEN) { + WARN_ON_ONCE(op != CEPH_SESSION_OPEN); + goto skip_cap_auths; + } + + cap_auths = kcalloc(cap_auths_num, + sizeof(struct ceph_mds_cap_auth), + GFP_KERNEL); + if (!cap_auths) { + pr_err_client(cl, "No memory for cap_auths\n"); + return; + } + + for (i = 0; i < cap_auths_num; i++) { + u32 _len, j; + + /* struct_v, struct_compat, and struct_len in MDSCapAuth */ + ceph_decode_skip_n(&p, end, 2 + sizeof(u32), bad); + + /* struct_v, struct_compat, and struct_len in MDSCapMatch */ + ceph_decode_skip_n(&p, end, 2 + sizeof(u32), bad); + ceph_decode_64_safe(&p, end, cap_auths[i].match.uid, bad); + ceph_decode_32_safe(&p, end, _len, bad); + if (_len) { + cap_auths[i].match.gids = kcalloc(_len, sizeof(u32), + GFP_KERNEL); + if (!cap_auths[i].match.gids) { + pr_err_client(cl, "No memory for gids\n"); + goto fail; + } + + cap_auths[i].match.num_gids = _len; + for (j = 0; j < _len; j++) + ceph_decode_32_safe(&p, end, + cap_auths[i].match.gids[j], + bad); + } + + ceph_decode_32_safe(&p, end, _len, bad); + if (_len) { + cap_auths[i].match.path = kcalloc(_len + 1, sizeof(char), + GFP_KERNEL); + if (!cap_auths[i].match.path) { + pr_err_client(cl, "No memory for path\n"); + goto fail; + } + ceph_decode_copy(&p, cap_auths[i].match.path, _len); + + /* Remove the tailing '/' */ + while (_len && cap_auths[i].match.path[_len - 1] == '/') { + cap_auths[i].match.path[_len - 1] = '\0'; + _len -= 1; + } + } + + ceph_decode_32_safe(&p, end, _len, bad); + if (_len) { + cap_auths[i].match.fs_name = kcalloc(_len + 1, sizeof(char), + GFP_KERNEL); + if (!cap_auths[i].match.fs_name) { + pr_err_client(cl, "No memory for fs_name\n"); + goto fail; + } + ceph_decode_copy(&p, cap_auths[i].match.fs_name, _len); + } + + ceph_decode_8_safe(&p, end, cap_auths[i].match.root_squash, bad); + ceph_decode_8_safe(&p, end, cap_auths[i].readable, bad); + ceph_decode_8_safe(&p, end, cap_auths[i].writeable, bad); + doutc(cl, "uid %lld, num_gids %u, path %s, fs_name %s, root_squash %d, readable %d, writeable %d\n", + cap_auths[i].match.uid, cap_auths[i].match.num_gids, + cap_auths[i].match.path, cap_auths[i].match.fs_name, + cap_auths[i].match.root_squash, + cap_auths[i].readable, cap_auths[i].writeable); + } + } + +skip_cap_auths: mutex_lock(&mdsc->mutex); + if (op == CEPH_SESSION_OPEN) { + if (mdsc->s_cap_auths) { + for (i = 0; i < mdsc->s_cap_auths_num; i++) { + kfree(mdsc->s_cap_auths[i].match.gids); + kfree(mdsc->s_cap_auths[i].match.path); + kfree(mdsc->s_cap_auths[i].match.fs_name); + } + kfree(mdsc->s_cap_auths); + } + mdsc->s_cap_auths_num = cap_auths_num; + mdsc->s_cap_auths = cap_auths; + } if (op == CEPH_SESSION_CLOSE) { ceph_get_mds_session(session); __unregister_session(mdsc, session); @@ -4290,6 +4387,13 @@ bad: pr_err_client(cl, "corrupt message mds%d len %d\n", mds, (int)msg->front.iov_len); ceph_msg_dump(msg); +fail: + for (i = 0; i < cap_auths_num; i++) { + kfree(cap_auths[i].match.gids); + kfree(cap_auths[i].match.path); + kfree(cap_auths[i].match.fs_name); + } + kfree(cap_auths); return; } @@ -5499,6 +5603,170 @@ void send_flush_mdlog(struct ceph_mds_session *s) mutex_unlock(&s->s_mutex); } +static int ceph_mds_auth_match(struct ceph_mds_client *mdsc, + struct ceph_mds_cap_auth *auth, + char *tpath) +{ + const struct cred *cred = get_current_cred(); + u32 caller_uid = from_kuid(&init_user_ns, cred->fsuid); + u32 caller_gid = from_kgid(&init_user_ns, cred->fsgid); + struct ceph_client *cl = mdsc->fsc->client; + const char *spath = mdsc->fsc->mount_options->server_path; + bool gid_matched = false; + u32 gid, tlen, len; + int i, j; + + doutc(cl, "match.uid %lld\n", auth->match.uid); + if (auth->match.uid != MDS_AUTH_UID_ANY) { + if (auth->match.uid != caller_uid) + return 0; + if (auth->match.num_gids) { + for (i = 0; i < auth->match.num_gids; i++) { + if (caller_gid == auth->match.gids[i]) + gid_matched = true; + } + if (!gid_matched && cred->group_info->ngroups) { + for (i = 0; i < cred->group_info->ngroups; i++) { + gid = from_kgid(&init_user_ns, + cred->group_info->gid[i]); + for (j = 0; j < auth->match.num_gids; j++) { + if (gid == auth->match.gids[j]) { + gid_matched = true; + break; + } + } + if (gid_matched) + break; + } + } + if (!gid_matched) + return 0; + } + } + + /* path match */ + if (auth->match.path) { + if (!tpath) + return 0; + + tlen = strlen(tpath); + len = strlen(auth->match.path); + if (len) { + char *_tpath = tpath; + bool free_tpath = false; + int m, n; + + doutc(cl, "server path %s, tpath %s, match.path %s\n", + spath, tpath, auth->match.path); + if (spath && (m = strlen(spath)) != 1) { + /* mount path + '/' + tpath + an extra space */ + n = m + 1 + tlen + 1; + _tpath = kmalloc(n, GFP_NOFS); + if (!_tpath) + return -ENOMEM; + /* remove the leading '/' */ + snprintf(_tpath, n, "%s/%s", spath + 1, tpath); + free_tpath = true; + tlen = strlen(_tpath); + } + + /* + * Please note the tailing '/' for match.path has already + * been removed when parsing. + * + * Remove the tailing '/' for the target path. + */ + while (tlen && _tpath[tlen - 1] == '/') { + _tpath[tlen - 1] = '\0'; + tlen -= 1; + } + doutc(cl, "_tpath %s\n", _tpath); + + /* + * In case first == _tpath && tlen == len: + * match.path=/foo --> /foo _path=/foo --> match + * match.path=/foo/ --> /foo _path=/foo --> match + * + * In case first == _tmatch.path && tlen > len: + * match.path=/foo/ --> /foo _path=/foo/ --> match + * match.path=/foo --> /foo _path=/foo/ --> match + * match.path=/foo/ --> /foo _path=/foo/d --> match + * match.path=/foo --> /foo _path=/food --> mismatch + * + * All the other cases --> mismatch + */ + char *first = strstr(_tpath, auth->match.path); + if (first != _tpath) { + if (free_tpath) + kfree(_tpath); + return 0; + } + + if (tlen > len && _tpath[len] != '/') { + if (free_tpath) + kfree(_tpath); + return 0; + } + } + } + + doutc(cl, "matched\n"); + return 1; +} + +int ceph_mds_check_access(struct ceph_mds_client *mdsc, char *tpath, int mask) +{ + const struct cred *cred = get_current_cred(); + u32 caller_uid = from_kuid(&init_user_ns, cred->fsuid); + u32 caller_gid = from_kgid(&init_user_ns, cred->fsgid); + struct ceph_mds_cap_auth *rw_perms_s = NULL; + struct ceph_client *cl = mdsc->fsc->client; + bool root_squash_perms = true; + int i, err; + + doutc(cl, "tpath '%s', mask %d, caller_uid %d, caller_gid %d\n", + tpath, mask, caller_uid, caller_gid); + + for (i = 0; i < mdsc->s_cap_auths_num; i++) { + struct ceph_mds_cap_auth *s = &mdsc->s_cap_auths[i]; + + err = ceph_mds_auth_match(mdsc, s, tpath); + if (err < 0) { + return err; + } else if (err > 0) { + /* always follow the last auth caps' permision */ + root_squash_perms = true; + rw_perms_s = NULL; + if ((mask & MAY_WRITE) && s->writeable && + s->match.root_squash && (!caller_uid || !caller_gid)) + root_squash_perms = false; + + if (((mask & MAY_WRITE) && !s->writeable) || + ((mask & MAY_READ) && !s->readable)) + rw_perms_s = s; + } + } + + doutc(cl, "root_squash_perms %d, rw_perms_s %p\n", root_squash_perms, + rw_perms_s); + if (root_squash_perms && rw_perms_s == NULL) { + doutc(cl, "access allowed\n"); + return 0; + } + + if (!root_squash_perms) { + doutc(cl, "root_squash is enabled and user(%d %d) isn't allowed to write", + caller_uid, caller_gid); + } + if (rw_perms_s) { + doutc(cl, "mds auth caps readable/writeable %d/%d while request r/w %d/%d", + rw_perms_s->readable, rw_perms_s->writeable, + !!(mask & MAY_READ), !!(mask & MAY_WRITE)); + } + doutc(cl, "access denied\n"); + return -EACCES; +} + /* * called before mount is ro, and before dentries are torn down. * (hmm, does this still race with new lookups?) diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index b88e80415224..cfa18cf915a0 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -35,8 +35,9 @@ enum ceph_feature_type { CEPHFS_FEATURE_32BITS_RETRY_FWD, CEPHFS_FEATURE_NEW_SNAPREALM_INFO, CEPHFS_FEATURE_HAS_OWNER_UIDGID, + CEPHFS_FEATURE_MDS_AUTH_CAPS_CHECK, - CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_HAS_OWNER_UIDGID, + CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_MDS_AUTH_CAPS_CHECK, }; #define CEPHFS_FEATURES_CLIENT_SUPPORTED { \ @@ -52,6 +53,7 @@ enum ceph_feature_type { CEPHFS_FEATURE_OP_GETVXATTR, \ CEPHFS_FEATURE_32BITS_RETRY_FWD, \ CEPHFS_FEATURE_HAS_OWNER_UIDGID, \ + CEPHFS_FEATURE_MDS_AUTH_CAPS_CHECK, \ } /* @@ -71,6 +73,24 @@ enum ceph_feature_type { struct ceph_fs_client; struct ceph_cap; +#define MDS_AUTH_UID_ANY -1 + +struct ceph_mds_cap_match { + s64 uid; /* default to MDS_AUTH_UID_ANY */ + u32 num_gids; + u32 *gids; /* use these GIDs */ + char *path; /* require path to be child of this + (may be "" or "/" for any) */ + char *fs_name; + bool root_squash; /* default to false */ +}; + +struct ceph_mds_cap_auth { + struct ceph_mds_cap_match match; + bool readable; + bool writeable; +}; + /* * parsed info about a single inode. pointers are into the encoded * on-wire structures within the mds reply message payload. @@ -513,6 +533,9 @@ struct ceph_mds_client { struct rw_semaphore pool_perm_rwsem; struct rb_root pool_perm_tree; + u32 s_cap_auths_num; + struct ceph_mds_cap_auth *s_cap_auths; + char nodename[__NEW_UTS_LEN + 1]; }; @@ -581,6 +604,9 @@ extern void ceph_queue_cap_unlink_work(struct ceph_mds_client *mdsc); extern int ceph_iterate_session_caps(struct ceph_mds_session *session, int (*cb)(struct inode *, int mds, void *), void *arg); +extern int ceph_mds_check_access(struct ceph_mds_client *mdsc, char *tpath, + int mask); + extern void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc); static inline void ceph_mdsc_free_path(char *path, int len) diff --git a/fs/dcache.c b/fs/dcache.c index 1ee6404b430b..407095188f83 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -2360,17 +2360,19 @@ EXPORT_SYMBOL(d_hash_and_lookup); * - unhash this dentry and free it. * * Usually, we want to just turn this into - * a negative dentry, but certain workloads can - * generate a large number of negative dentries. - * Therefore, it would be better to simply - * unhash it. + * a negative dentry, but if anybody else is + * currently using the dentry or the inode + * we can't do that and we fall back on removing + * it from the hash queues and waiting for + * it to be deleted later when it has no users */ /** * d_delete - delete a dentry * @dentry: The dentry to delete * - * Remove the dentry from the hash queues so it can be deleted later. + * Turn the dentry into a negative dentry if possible, otherwise + * remove it from the hash queues so it can be deleted later */ void d_delete(struct dentry * dentry) @@ -2379,8 +2381,6 @@ void d_delete(struct dentry * dentry) spin_lock(&inode->i_lock); spin_lock(&dentry->d_lock); - __d_drop(dentry); - /* * Are we the only user? */ @@ -2388,6 +2388,7 @@ void d_delete(struct dentry * dentry) dentry->d_flags &= ~DCACHE_CANT_MOUNT; dentry_unlink_inode(dentry); } else { + __d_drop(dentry); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); } diff --git a/fs/erofs/data.c b/fs/erofs/data.c index 5fc03c1e2757..8be60797ea2f 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -72,10 +72,10 @@ void erofs_init_metabuf(struct erofs_buf *buf, struct super_block *sb) } void *erofs_read_metabuf(struct erofs_buf *buf, struct super_block *sb, - erofs_blk_t blkaddr, enum erofs_kmap_type type) + erofs_off_t offset, enum erofs_kmap_type type) { erofs_init_metabuf(buf, sb); - return erofs_bread(buf, erofs_pos(sb, blkaddr), type); + return erofs_bread(buf, offset, type); } static int erofs_map_blocks_flatmode(struct inode *inode, @@ -152,7 +152,7 @@ int erofs_map_blocks(struct inode *inode, struct erofs_map_blocks *map) pos = ALIGN(erofs_iloc(inode) + vi->inode_isize + vi->xattr_isize, unit) + unit * chunknr; - kaddr = erofs_read_metabuf(&buf, sb, erofs_blknr(sb, pos), EROFS_KMAP); + kaddr = erofs_read_metabuf(&buf, sb, pos, EROFS_KMAP); if (IS_ERR(kaddr)) { err = PTR_ERR(kaddr); goto out; @@ -163,7 +163,7 @@ int erofs_map_blocks(struct inode *inode, struct erofs_map_blocks *map) /* handle block map */ if (!(vi->chunkformat & EROFS_CHUNK_FORMAT_INDEXES)) { - __le32 *blkaddr = kaddr + erofs_blkoff(sb, pos); + __le32 *blkaddr = kaddr; if (le32_to_cpu(*blkaddr) == EROFS_NULL_ADDR) { map->m_flags = 0; @@ -174,7 +174,7 @@ int erofs_map_blocks(struct inode *inode, struct erofs_map_blocks *map) goto out_unlock; } /* parse chunk indexes */ - idx = kaddr + erofs_blkoff(sb, pos); + idx = kaddr; switch (le32_to_cpu(idx->blkaddr)) { case EROFS_NULL_ADDR: map->m_flags = 0; @@ -294,11 +294,10 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, struct erofs_buf buf = __EROFS_BUF_INITIALIZER; iomap->type = IOMAP_INLINE; - ptr = erofs_read_metabuf(&buf, sb, - erofs_blknr(sb, mdev.m_pa), EROFS_KMAP); + ptr = erofs_read_metabuf(&buf, sb, mdev.m_pa, EROFS_KMAP); if (IS_ERR(ptr)) return PTR_ERR(ptr); - iomap->inline_data = ptr + erofs_blkoff(sb, mdev.m_pa); + iomap->inline_data = ptr; iomap->private = buf.base; } else { iomap->type = IOMAP_MAPPED; diff --git a/fs/erofs/decompressor_deflate.c b/fs/erofs/decompressor_deflate.c index 81e65c453ef0..3a3461561a3c 100644 --- a/fs/erofs/decompressor_deflate.c +++ b/fs/erofs/decompressor_deflate.c @@ -46,39 +46,15 @@ int __init z_erofs_deflate_init(void) /* by default, use # of possible CPUs instead */ if (!z_erofs_deflate_nstrms) z_erofs_deflate_nstrms = num_possible_cpus(); - - for (; z_erofs_deflate_avail_strms < z_erofs_deflate_nstrms; - ++z_erofs_deflate_avail_strms) { - struct z_erofs_deflate *strm; - - strm = kzalloc(sizeof(*strm), GFP_KERNEL); - if (!strm) - goto out_failed; - - /* XXX: in-kernel zlib cannot shrink windowbits currently */ - strm->z.workspace = vmalloc(zlib_inflate_workspacesize()); - if (!strm->z.workspace) { - kfree(strm); - goto out_failed; - } - - spin_lock(&z_erofs_deflate_lock); - strm->next = z_erofs_deflate_head; - z_erofs_deflate_head = strm; - spin_unlock(&z_erofs_deflate_lock); - } return 0; - -out_failed: - erofs_err(NULL, "failed to allocate zlib workspace"); - z_erofs_deflate_exit(); - return -ENOMEM; } int z_erofs_load_deflate_config(struct super_block *sb, struct erofs_super_block *dsb, void *data, int size) { struct z_erofs_deflate_cfgs *dfl = data; + static DEFINE_MUTEX(deflate_resize_mutex); + static bool inited; if (!dfl || size < sizeof(struct z_erofs_deflate_cfgs)) { erofs_err(sb, "invalid deflate cfgs, size=%u", size); @@ -89,9 +65,36 @@ int z_erofs_load_deflate_config(struct super_block *sb, erofs_err(sb, "unsupported windowbits %u", dfl->windowbits); return -EOPNOTSUPP; } + mutex_lock(&deflate_resize_mutex); + if (!inited) { + for (; z_erofs_deflate_avail_strms < z_erofs_deflate_nstrms; + ++z_erofs_deflate_avail_strms) { + struct z_erofs_deflate *strm; + + strm = kzalloc(sizeof(*strm), GFP_KERNEL); + if (!strm) + goto failed; + /* XXX: in-kernel zlib cannot customize windowbits */ + strm->z.workspace = vmalloc(zlib_inflate_workspacesize()); + if (!strm->z.workspace) { + kfree(strm); + goto failed; + } + spin_lock(&z_erofs_deflate_lock); + strm->next = z_erofs_deflate_head; + z_erofs_deflate_head = strm; + spin_unlock(&z_erofs_deflate_lock); + } + inited = true; + } + mutex_unlock(&deflate_resize_mutex); erofs_info(sb, "EXPERIMENTAL DEFLATE feature in use. Use at your own risk!"); return 0; +failed: + mutex_unlock(&deflate_resize_mutex); + z_erofs_deflate_exit(); + return -ENOMEM; } int z_erofs_deflate_decompress(struct z_erofs_decompress_req *rq, diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c index 62da538d91cb..fda16eedafb5 100644 --- a/fs/erofs/fscache.c +++ b/fs/erofs/fscache.c @@ -273,21 +273,15 @@ static int erofs_fscache_data_read_slice(struct erofs_fscache_rq *req) if (map.m_flags & EROFS_MAP_META) { struct erofs_buf buf = __EROFS_BUF_INITIALIZER; struct iov_iter iter; - erofs_blk_t blknr; - size_t offset, size; + size_t size = map.m_llen; void *src; - /* For tail packing layout, the offset may be non-zero. */ - offset = erofs_blkoff(sb, map.m_pa); - blknr = erofs_blknr(sb, map.m_pa); - size = map.m_llen; - - src = erofs_read_metabuf(&buf, sb, blknr, EROFS_KMAP); + src = erofs_read_metabuf(&buf, sb, map.m_pa, EROFS_KMAP); if (IS_ERR(src)) return PTR_ERR(src); iov_iter_xarray(&iter, ITER_DEST, &mapping->i_pages, pos, PAGE_SIZE); - if (copy_to_iter(src + offset, size, &iter) != size) { + if (copy_to_iter(src, size, &iter) != size) { erofs_put_metabuf(&buf); return -EFAULT; } diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c index 0eb0e6f933c3..5f6439a63af7 100644 --- a/fs/erofs/inode.c +++ b/fs/erofs/inode.c @@ -26,7 +26,7 @@ static void *erofs_read_inode(struct erofs_buf *buf, blkaddr = erofs_blknr(sb, inode_loc); *ofs = erofs_blkoff(sb, inode_loc); - kaddr = erofs_read_metabuf(buf, sb, blkaddr, EROFS_KMAP); + kaddr = erofs_read_metabuf(buf, sb, erofs_pos(sb, blkaddr), EROFS_KMAP); if (IS_ERR(kaddr)) { erofs_err(sb, "failed to get inode (nid: %llu) page, err %ld", vi->nid, PTR_ERR(kaddr)); @@ -66,7 +66,7 @@ static void *erofs_read_inode(struct erofs_buf *buf, goto err_out; } memcpy(copied, dic, gotten); - kaddr = erofs_read_metabuf(buf, sb, blkaddr + 1, + kaddr = erofs_read_metabuf(buf, sb, erofs_pos(sb, blkaddr + 1), EROFS_KMAP); if (IS_ERR(kaddr)) { erofs_err(sb, "failed to get inode payload block (nid: %llu), err %ld", diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 00bbb288c08c..0c1b44ac9524 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -64,15 +64,12 @@ enum { }; struct erofs_mount_opts { -#ifdef CONFIG_EROFS_FS_ZIP /* current strategy of how to use managed cache */ unsigned char cache_strategy; /* strategy of sync decompression (0 - auto, 1 - force on, 2 - force off) */ unsigned int sync_decompress; - /* threshold for decompression synchronously */ unsigned int max_sync_decompress_pages; -#endif unsigned int mount_opt; }; @@ -406,7 +403,7 @@ void *erofs_bread(struct erofs_buf *buf, erofs_off_t offset, enum erofs_kmap_type type); void erofs_init_metabuf(struct erofs_buf *buf, struct super_block *sb); void *erofs_read_metabuf(struct erofs_buf *buf, struct super_block *sb, - erofs_blk_t blkaddr, enum erofs_kmap_type type); + erofs_off_t offset, enum erofs_kmap_type type); int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *dev); int erofs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len); diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 348ef1660e50..c93bd24d2771 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -178,12 +178,10 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb, struct erofs_fscache *fscache; struct erofs_deviceslot *dis; struct file *bdev_file; - void *ptr; - ptr = erofs_read_metabuf(buf, sb, erofs_blknr(sb, *pos), EROFS_KMAP); - if (IS_ERR(ptr)) - return PTR_ERR(ptr); - dis = ptr + erofs_blkoff(sb, *pos); + dis = erofs_read_metabuf(buf, sb, *pos, EROFS_KMAP); + if (IS_ERR(dis)) + return PTR_ERR(dis); if (!sbi->devs->flatdev && !dif->path) { if (!dis->tag[0]) { @@ -943,26 +941,14 @@ static int erofs_show_options(struct seq_file *seq, struct dentry *root) struct erofs_sb_info *sbi = EROFS_SB(root->d_sb); struct erofs_mount_opts *opt = &sbi->opt; -#ifdef CONFIG_EROFS_FS_XATTR - if (test_opt(opt, XATTR_USER)) - seq_puts(seq, ",user_xattr"); - else - seq_puts(seq, ",nouser_xattr"); -#endif -#ifdef CONFIG_EROFS_FS_POSIX_ACL - if (test_opt(opt, POSIX_ACL)) - seq_puts(seq, ",acl"); - else - seq_puts(seq, ",noacl"); -#endif -#ifdef CONFIG_EROFS_FS_ZIP - if (opt->cache_strategy == EROFS_ZIP_CACHE_DISABLED) - seq_puts(seq, ",cache_strategy=disabled"); - else if (opt->cache_strategy == EROFS_ZIP_CACHE_READAHEAD) - seq_puts(seq, ",cache_strategy=readahead"); - else if (opt->cache_strategy == EROFS_ZIP_CACHE_READAROUND) - seq_puts(seq, ",cache_strategy=readaround"); -#endif + if (IS_ENABLED(CONFIG_EROFS_FS_XATTR)) + seq_puts(seq, test_opt(opt, XATTR_USER) ? + ",user_xattr" : ",nouser_xattr"); + if (IS_ENABLED(CONFIG_EROFS_FS_POSIX_ACL)) + seq_puts(seq, test_opt(opt, POSIX_ACL) ? ",acl" : ",noacl"); + if (IS_ENABLED(CONFIG_EROFS_FS_ZIP)) + seq_printf(seq, ",cache_strategy=%s", + erofs_param_cache_strategy[opt->cache_strategy].name); if (test_opt(opt, DAX_ALWAYS)) seq_puts(seq, ",dax=always"); if (test_opt(opt, DAX_NEVER)) diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 283c9c3a611d..d6fe002a4a71 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -868,7 +868,7 @@ static int z_erofs_pcluster_begin(struct z_erofs_decompress_frontend *fe) } else { void *mptr; - mptr = erofs_read_metabuf(&map->buf, sb, blknr, EROFS_NO_KMAP); + mptr = erofs_read_metabuf(&map->buf, sb, map->m_pa, EROFS_NO_KMAP); if (IS_ERR(mptr)) { ret = PTR_ERR(mptr); erofs_err(sb, "failed to get inline data %d", ret); diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index 0a2454d8bcc1..9b248ee5fef2 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -34,13 +34,13 @@ static int z_erofs_load_full_lcluster(struct z_erofs_maprecorder *m, unsigned int advise; m->kaddr = erofs_read_metabuf(&m->map->buf, inode->i_sb, - erofs_blknr(inode->i_sb, pos), EROFS_KMAP); + pos, EROFS_KMAP); if (IS_ERR(m->kaddr)) return PTR_ERR(m->kaddr); m->nextpackoff = pos + sizeof(struct z_erofs_lcluster_index); m->lcn = lcn; - di = m->kaddr + erofs_blkoff(inode->i_sb, pos); + di = m->kaddr; advise = le16_to_cpu(di->di_advise); m->type = advise & Z_EROFS_LI_LCLUSTER_TYPE_MASK; @@ -109,7 +109,7 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m, { struct erofs_inode *const vi = EROFS_I(m->inode); const unsigned int lclusterbits = vi->z_logical_clusterbits; - unsigned int vcnt, base, lo, lobits, encodebits, nblk, eofs; + unsigned int vcnt, lo, lobits, encodebits, nblk, bytes; int i; u8 *in, type; bool big_pcluster; @@ -127,11 +127,11 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m, big_pcluster = vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1; lobits = max(lclusterbits, ilog2(Z_EROFS_LI_D0_CBLKCNT) + 1U); encodebits = ((vcnt << amortizedshift) - sizeof(__le32)) * 8 / vcnt; - eofs = erofs_blkoff(m->inode->i_sb, pos); - base = round_down(eofs, vcnt << amortizedshift); - in = m->kaddr + base; + bytes = pos & ((vcnt << amortizedshift) - 1); - i = (eofs - base) >> amortizedshift; + in = m->kaddr - bytes; + + i = bytes >> amortizedshift; lo = decode_compactedbits(lobits, in, encodebits * i, &type); m->type = type; @@ -256,7 +256,7 @@ static int z_erofs_load_compact_lcluster(struct z_erofs_maprecorder *m, out: pos += lcn * (1 << amortizedshift); m->kaddr = erofs_read_metabuf(&m->map->buf, inode->i_sb, - erofs_blknr(inode->i_sb, pos), EROFS_KMAP); + pos, EROFS_KMAP); if (IS_ERR(m->kaddr)) return PTR_ERR(m->kaddr); return unpack_compacted_index(m, amortizedshift, pos, lookahead); @@ -570,7 +570,6 @@ static int z_erofs_fill_inode_lazy(struct inode *inode) int err, headnr; erofs_off_t pos; struct erofs_buf buf = __EROFS_BUF_INITIALIZER; - void *kaddr; struct z_erofs_map_header *h; if (test_bit(EROFS_I_Z_INITED_BIT, &vi->flags)) { @@ -590,13 +589,12 @@ static int z_erofs_fill_inode_lazy(struct inode *inode) goto out_unlock; pos = ALIGN(erofs_iloc(inode) + vi->inode_isize + vi->xattr_isize, 8); - kaddr = erofs_read_metabuf(&buf, sb, erofs_blknr(sb, pos), EROFS_KMAP); - if (IS_ERR(kaddr)) { - err = PTR_ERR(kaddr); + h = erofs_read_metabuf(&buf, sb, pos, EROFS_KMAP); + if (IS_ERR(h)) { + err = PTR_ERR(h); goto out_unlock; } - h = kaddr + erofs_blkoff(sb, pos); /* * if the highest bit of the 8-byte map header is set, the whole file * is stored in the packed inode. The rest bits keeps z_fragmentoff. diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 41c8f0c68ef5..c5802a459334 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -898,11 +898,11 @@ static bool iomap_write_end(struct iomap_iter *iter, loff_t pos, size_t len, static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i) { loff_t length = iomap_length(iter); - size_t chunk = PAGE_SIZE << MAX_PAGECACHE_ORDER; loff_t pos = iter->pos; ssize_t total_written = 0; long status = 0; struct address_space *mapping = iter->inode->i_mapping; + size_t chunk = mapping_max_folio_size(mapping); unsigned int bdp_flags = (iter->flags & IOMAP_NOWAIT) ? BDP_ASYNC : 0; do { diff --git a/fs/jffs2/background.c b/fs/jffs2/background.c index 6da92ecaf66d..bb0ee1a59e71 100644 --- a/fs/jffs2/background.c +++ b/fs/jffs2/background.c @@ -44,8 +44,8 @@ int jffs2_start_garbage_collect_thread(struct jffs2_sb_info *c) tsk = kthread_run(jffs2_garbage_collect_thread, c, "jffs2_gcd_mtd%d", c->mtd->index); if (IS_ERR(tsk)) { - pr_warn("fork failed for JFFS2 garbage collect thread: %ld\n", - -PTR_ERR(tsk)); + pr_warn("fork failed for JFFS2 garbage collect thread: %pe\n", + tsk); complete(&c->gc_thread_exit); ret = PTR_ERR(tsk); } else { diff --git a/fs/jffs2/malloc.c b/fs/jffs2/malloc.c index ce1189793288..411de8b361b2 100644 --- a/fs/jffs2/malloc.c +++ b/fs/jffs2/malloc.c @@ -33,27 +33,19 @@ static struct kmem_cache *xattr_ref_cache; int __init jffs2_create_slab_caches(void) { - full_dnode_slab = kmem_cache_create("jffs2_full_dnode", - sizeof(struct jffs2_full_dnode), - 0, 0, NULL); + full_dnode_slab = KMEM_CACHE(jffs2_full_dnode, 0); if (!full_dnode_slab) goto err; - raw_dirent_slab = kmem_cache_create("jffs2_raw_dirent", - sizeof(struct jffs2_raw_dirent), - 0, SLAB_HWCACHE_ALIGN, NULL); + raw_dirent_slab = KMEM_CACHE(jffs2_raw_dirent, SLAB_HWCACHE_ALIGN); if (!raw_dirent_slab) goto err; - raw_inode_slab = kmem_cache_create("jffs2_raw_inode", - sizeof(struct jffs2_raw_inode), - 0, SLAB_HWCACHE_ALIGN, NULL); + raw_inode_slab = KMEM_CACHE(jffs2_raw_inode, SLAB_HWCACHE_ALIGN); if (!raw_inode_slab) goto err; - tmp_dnode_info_slab = kmem_cache_create("jffs2_tmp_dnode", - sizeof(struct jffs2_tmp_dnode_info), - 0, 0, NULL); + tmp_dnode_info_slab = KMEM_CACHE(jffs2_tmp_dnode_info, 0); if (!tmp_dnode_info_slab) goto err; @@ -63,28 +55,20 @@ int __init jffs2_create_slab_caches(void) if (!raw_node_ref_slab) goto err; - node_frag_slab = kmem_cache_create("jffs2_node_frag", - sizeof(struct jffs2_node_frag), - 0, 0, NULL); + node_frag_slab = KMEM_CACHE(jffs2_node_frag, 0); if (!node_frag_slab) goto err; - inode_cache_slab = kmem_cache_create("jffs2_inode_cache", - sizeof(struct jffs2_inode_cache), - 0, 0, NULL); + inode_cache_slab = KMEM_CACHE(jffs2_inode_cache, 0); if (!inode_cache_slab) goto err; #ifdef CONFIG_JFFS2_FS_XATTR - xattr_datum_cache = kmem_cache_create("jffs2_xattr_datum", - sizeof(struct jffs2_xattr_datum), - 0, 0, NULL); + xattr_datum_cache = KMEM_CACHE(jffs2_xattr_datum, 0); if (!xattr_datum_cache) goto err; - xattr_ref_cache = kmem_cache_create("jffs2_xattr_ref", - sizeof(struct jffs2_xattr_ref), - 0, 0, NULL); + xattr_ref_cache = KMEM_CACHE(jffs2_xattr_ref, 0); if (!xattr_ref_cache) goto err; #endif diff --git a/fs/jffs2/nodemgmt.c b/fs/jffs2/nodemgmt.c index a7bbe879cfc3..bbab2bdc71b6 100644 --- a/fs/jffs2/nodemgmt.c +++ b/fs/jffs2/nodemgmt.c @@ -49,28 +49,31 @@ static int jffs2_rp_can_write(struct jffs2_sb_info *c) return 0; } +static int jffs2_do_reserve_space(struct jffs2_sb_info *c, uint32_t minsize, + uint32_t *len, uint32_t sumsize); + /** * jffs2_reserve_space - request physical space to write nodes to flash * @c: superblock info * @minsize: Minimum acceptable size of allocation * @len: Returned value of allocation length * @prio: Allocation type - ALLOC_{NORMAL,DELETION} + * @sumsize: summary size requested or JFFS2_SUMMARY_NOSUM_SIZE for no summary + * + * Requests a block of physical space on the flash. * - * Requests a block of physical space on the flash. Returns zero for success - * and puts 'len' into the appropriate place, or returns -ENOSPC or other - * error if appropriate. Doesn't return len since that's + * Returns: %0 for success and puts 'len' into the appropriate place, + * or returns -ENOSPC or other error if appropriate. + * Doesn't return len since that's already returned in @len. * - * If it returns zero, jffs2_reserve_space() also downs the per-filesystem + * If it returns %0, jffs2_reserve_space() also downs the per-filesystem * allocation semaphore, to prevent more than one allocation from being - * active at any time. The semaphore is later released by jffs2_commit_allocation() + * active at any time. The semaphore is later released by jffs2_commit_allocation(). * * jffs2_reserve_space() may trigger garbage collection in order to make room * for the requested allocation. */ -static int jffs2_do_reserve_space(struct jffs2_sb_info *c, uint32_t minsize, - uint32_t *len, uint32_t sumsize); - int jffs2_reserve_space(struct jffs2_sb_info *c, uint32_t minsize, uint32_t *len, int prio, uint32_t sumsize) { @@ -488,13 +491,16 @@ static int jffs2_do_reserve_space(struct jffs2_sb_info *c, uint32_t minsize, /** * jffs2_add_physical_node_ref - add a physical node reference to the list * @c: superblock info - * @new: new node reference to add + * @ofs: offset in the block * @len: length of this physical node + * @ic: inode cache pointer * * Should only be used to report nodes for which space has been allocated * by jffs2_reserve_space. * * Must be called with the alloc_sem held. + * + * Returns: pointer to new node on success or -errno code on error */ struct jffs2_raw_node_ref *jffs2_add_physical_node_ref(struct jffs2_sb_info *c, diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c index aede1be4dc0c..4545f885c41e 100644 --- a/fs/jffs2/super.c +++ b/fs/jffs2/super.c @@ -58,6 +58,7 @@ static void jffs2_i_init_once(void *foo) struct jffs2_inode_info *f = foo; mutex_init(&f->sem); + f->target = NULL; inode_init_once(&f->vfs_inode); } diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c index 1121601536d1..07bc1fd43530 100644 --- a/fs/netfs/buffered_write.c +++ b/fs/netfs/buffered_write.c @@ -181,7 +181,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, struct folio *folio, *writethrough = NULL; enum netfs_how_to_modify howto; enum netfs_folio_trace trace; - unsigned int bdp_flags = (iocb->ki_flags & IOCB_SYNC) ? 0: BDP_ASYNC; + unsigned int bdp_flags = (iocb->ki_flags & IOCB_NOWAIT) ? BDP_ASYNC : 0; ssize_t written = 0, ret, ret2; loff_t i_size, pos = iocb->ki_pos, from, to; size_t max_chunk = PAGE_SIZE << MAX_PAGECACHE_ORDER; diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c index 608ba6416919..e14cd53ac9fd 100644 --- a/fs/netfs/direct_write.c +++ b/fs/netfs/direct_write.c @@ -12,7 +12,7 @@ static void netfs_cleanup_dio_write(struct netfs_io_request *wreq) { struct inode *inode = wreq->inode; - unsigned long long end = wreq->start + wreq->len; + unsigned long long end = wreq->start + wreq->transferred; if (!wreq->error && i_size_read(inode) < end) { @@ -27,7 +27,7 @@ static void netfs_cleanup_dio_write(struct netfs_io_request *wreq) * Perform an unbuffered write where we may have to do an RMW operation on an * encrypted file. This can also be used for direct I/O writes. */ -static ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *iter, +ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *iter, struct netfs_group *netfs_group) { struct netfs_io_request *wreq; @@ -117,6 +117,7 @@ out: netfs_put_request(wreq, false, netfs_rreq_trace_put_return); return ret; } +EXPORT_SYMBOL(netfs_unbuffered_write_iter_locked); /** * netfs_unbuffered_write_iter - Unbuffered write to a file diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c index c90d482b1650..f4a642727479 100644 --- a/fs/netfs/objects.c +++ b/fs/netfs/objects.c @@ -72,6 +72,7 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, } } + atomic_inc(&ctx->io_count); trace_netfs_rreq_ref(rreq->debug_id, 1, netfs_rreq_trace_new); netfs_proc_add_rreq(rreq); netfs_stat(&netfs_n_rh_rreq); @@ -124,6 +125,7 @@ static void netfs_free_request(struct work_struct *work) { struct netfs_io_request *rreq = container_of(work, struct netfs_io_request, work); + struct netfs_inode *ictx = netfs_inode(rreq->inode); unsigned int i; trace_netfs_rreq(rreq, netfs_rreq_trace_free); @@ -142,6 +144,9 @@ static void netfs_free_request(struct work_struct *work) } kvfree(rreq->direct_bv); } + + if (atomic_dec_and_test(&ictx->io_count)) + wake_up_var(&ictx->io_count); call_rcu(&rreq->rcu, netfs_free_request_rcu); } diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c index 60112e4b2c5e..426cf87aaf2e 100644 --- a/fs/netfs/write_collect.c +++ b/fs/netfs/write_collect.c @@ -510,7 +510,7 @@ reassess_streams: * stream has a gap that can be jumped. */ if (notes & SOME_EMPTY) { - unsigned long long jump_to = wreq->start + wreq->len; + unsigned long long jump_to = wreq->start + READ_ONCE(wreq->submitted); for (s = 0; s < NR_IO_STREAMS; s++) { stream = &wreq->io_streams[s]; @@ -690,10 +690,11 @@ void netfs_write_collection_worker(struct work_struct *work) wake_up_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS); if (wreq->iocb) { - wreq->iocb->ki_pos += wreq->transferred; + size_t written = min(wreq->transferred, wreq->len); + wreq->iocb->ki_pos += written; if (wreq->iocb->ki_complete) wreq->iocb->ki_complete( - wreq->iocb, wreq->error ? wreq->error : wreq->transferred); + wreq->iocb, wreq->error ? wreq->error : written); wreq->iocb = VFS_PTR_POISON; } diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index e190043bc0da..3aa86e268f40 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -254,7 +254,7 @@ static void netfs_issue_write(struct netfs_io_request *wreq, stream->construct = NULL; if (subreq->start + subreq->len > wreq->start + wreq->submitted) - wreq->len = wreq->submitted = subreq->start + subreq->len - wreq->start; + WRITE_ONCE(wreq->submitted, subreq->start + subreq->len - wreq->start); netfs_do_issue_write(stream, subreq); } @@ -636,7 +636,12 @@ int netfs_end_writethrough(struct netfs_io_request *wreq, struct writeback_contr mutex_unlock(&ictx->wb_lock); - ret = wreq->error; + if (wreq->iocb) { + ret = -EIOCBQUEUED; + } else { + wait_on_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS, TASK_UNINTERRUPTIBLE); + ret = wreq->error; + } netfs_put_request(wreq, false, netfs_rreq_trace_put_return); return ret; } diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index f7e32d76e34d..57249f040dfc 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -33,12 +33,12 @@ config NFS_FS config NFS_V2 tristate "NFS client support for NFS version 2" depends on NFS_FS - default y + default n help This option enables support for version 2 of the NFS protocol (RFC 1094) in the kernel's NFS client. - If unsure, say Y. + If unsure, say N. config NFS_V3 tristate "NFS client support for NFS version 3" diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index ac505671efbd..342930996226 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -56,6 +56,8 @@ static int nfs_readdir(struct file *, struct dir_context *); static int nfs_fsync_dir(struct file *, loff_t, loff_t, int); static loff_t nfs_llseek_dir(struct file *, loff_t, int); static void nfs_readdir_clear_array(struct folio *); +static int nfs_do_create(struct inode *dir, struct dentry *dentry, + umode_t mode, int open_flags); const struct file_operations nfs_dir_operations = { .llseek = nfs_llseek_dir, @@ -2243,6 +2245,41 @@ static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags) #endif /* CONFIG_NFSV4 */ +int nfs_atomic_open_v23(struct inode *dir, struct dentry *dentry, + struct file *file, unsigned int open_flags, + umode_t mode) +{ + + /* Same as look+open from lookup_open(), but with different O_TRUNC + * handling. + */ + int error = 0; + + if (open_flags & O_CREAT) { + file->f_mode |= FMODE_CREATED; + error = nfs_do_create(dir, dentry, mode, open_flags); + if (error) + return error; + return finish_open(file, dentry, NULL); + } else if (d_in_lookup(dentry)) { + /* The only flags nfs_lookup considers are + * LOOKUP_EXCL and LOOKUP_RENAME_TARGET, and + * we want those to be zero so the lookup isn't skipped. + */ + struct dentry *res = nfs_lookup(dir, dentry, 0); + + d_lookup_done(dentry); + if (unlikely(res)) { + if (IS_ERR(res)) + return PTR_ERR(res); + return finish_no_open(file, res); + } + } + return finish_no_open(file, NULL); + +} +EXPORT_SYMBOL_GPL(nfs_atomic_open_v23); + struct dentry * nfs_add_or_obtain(struct dentry *dentry, struct nfs_fh *fhandle, struct nfs_fattr *fattr) @@ -2303,18 +2340,23 @@ EXPORT_SYMBOL_GPL(nfs_instantiate); * that the operation succeeded on the server, but an error in the * reply path made it appear to have failed. */ -int nfs_create(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode, bool excl) +static int nfs_do_create(struct inode *dir, struct dentry *dentry, + umode_t mode, int open_flags) { struct iattr attr; - int open_flags = excl ? O_CREAT | O_EXCL : O_CREAT; int error; + open_flags |= O_CREAT; + dfprintk(VFS, "NFS: create(%s/%lu), %pd\n", dir->i_sb->s_id, dir->i_ino, dentry); attr.ia_mode = mode; attr.ia_valid = ATTR_MODE; + if (open_flags & O_TRUNC) { + attr.ia_size = 0; + attr.ia_valid |= ATTR_SIZE; + } trace_nfs_create_enter(dir, dentry, open_flags); error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags); @@ -2326,6 +2368,12 @@ out_err: d_drop(dentry); return error; } + +int nfs_create(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) +{ + return nfs_do_create(dir, dentry, mode, excl ? O_EXCL : 0); +} EXPORT_SYMBOL_GPL(nfs_create); /* diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index ce8f8934bca5..29d84dc66ca3 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -605,14 +605,6 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo, dprintk("--> %s\n", __func__); - /* FIXME: remove this check when layout segment support is added */ - if (lgr->range.offset != 0 || - lgr->range.length != NFS4_MAX_UINT64) { - dprintk("%s Only whole file layouts supported. Use MDS i/o\n", - __func__); - goto out; - } - if (fl->pattern_offset > lgr->range.offset) { dprintk("%s pattern_offset %lld too large\n", __func__, fl->pattern_offset); @@ -875,15 +867,15 @@ static void filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) { - pnfs_generic_pg_check_layout(pgio); + pnfs_generic_pg_check_layout(pgio, req); if (!pgio->pg_lseg) { pgio->pg_lseg = fl_pnfs_update_layout(pgio->pg_inode, nfs_req_openctx(req), - 0, - NFS4_MAX_UINT64, + req_offset(req), + req->wb_bytes, IOMODE_READ, false, - GFP_KERNEL); + nfs_io_gfp_mask()); if (IS_ERR(pgio->pg_lseg)) { pgio->pg_error = PTR_ERR(pgio->pg_lseg); pgio->pg_lseg = NULL; @@ -899,15 +891,15 @@ static void filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) { - pnfs_generic_pg_check_layout(pgio); + pnfs_generic_pg_check_layout(pgio, req); if (!pgio->pg_lseg) { pgio->pg_lseg = fl_pnfs_update_layout(pgio->pg_inode, nfs_req_openctx(req), - 0, - NFS4_MAX_UINT64, + req_offset(req), + req->wb_bytes, IOMODE_RW, false, - GFP_NOFS); + nfs_io_gfp_mask()); if (IS_ERR(pgio->pg_lseg)) { pgio->pg_error = PTR_ERR(pgio->pg_lseg); pgio->pg_lseg = NULL; diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 3e724cb7ef01..24188af56d5b 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -823,14 +823,6 @@ ff_layout_pg_get_read(struct nfs_pageio_descriptor *pgio, } static void -ff_layout_pg_check_layout(struct nfs_pageio_descriptor *pgio, - struct nfs_page *req) -{ - pnfs_generic_pg_check_layout(pgio); - pnfs_generic_pg_check_range(pgio, req); -} - -static void ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) { @@ -840,7 +832,7 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio, u32 ds_idx; retry: - ff_layout_pg_check_layout(pgio, req); + pnfs_generic_pg_check_layout(pgio, req); /* Use full layout for now */ if (!pgio->pg_lseg) { ff_layout_pg_get_read(pgio, req, false); @@ -895,7 +887,7 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio, u32 i; retry: - ff_layout_pg_check_layout(pgio, req); + pnfs_generic_pg_check_layout(pgio, req); if (!pgio->pg_lseg) { pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, nfs_req_openctx(req), diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c index d0a0956f8a13..6c9f3f6645dd 100644 --- a/fs/nfs/fs_context.c +++ b/fs/nfs/fs_context.c @@ -600,9 +600,11 @@ static int nfs_fs_context_parse_param(struct fs_context *fc, break; case Opt_lock: if (result.negated) { + ctx->lock_status = NFS_LOCK_NOLOCK; ctx->flags |= NFS_MOUNT_NONLM; ctx->flags |= (NFS_MOUNT_LOCAL_FLOCK | NFS_MOUNT_LOCAL_FCNTL); } else { + ctx->lock_status = NFS_LOCK_LOCK; ctx->flags &= ~NFS_MOUNT_NONLM; ctx->flags &= ~(NFS_MOUNT_LOCAL_FLOCK | NFS_MOUNT_LOCAL_FCNTL); } @@ -1112,9 +1114,12 @@ static int nfs23_parse_monolithic(struct fs_context *fc, ctx->acdirmax = data->acdirmax; ctx->need_mount = false; - memcpy(sap, &data->addr, sizeof(data->addr)); - ctx->nfs_server.addrlen = sizeof(data->addr); - ctx->nfs_server.port = ntohs(data->addr.sin_port); + if (!is_remount_fc(fc)) { + memcpy(sap, &data->addr, sizeof(data->addr)); + ctx->nfs_server.addrlen = sizeof(data->addr); + ctx->nfs_server.port = ntohs(data->addr.sin_port); + } + if (sap->ss_family != AF_INET || !nfs_verify_server_address(sap)) goto out_no_address; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 06253695fe53..9f0f4534744b 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -112,6 +112,7 @@ struct nfs_fs_context { unsigned short protofamily; unsigned short mountfamily; bool has_sec_mnt_opts; + int lock_status; struct { union { @@ -153,6 +154,12 @@ struct nfs_fs_context { } clone_data; }; +enum nfs_lock_status { + NFS_LOCK_NOT_SET = 0, + NFS_LOCK_LOCK = 1, + NFS_LOCK_NOLOCK = 2, +}; + #define nfs_errorf(fc, fmt, ...) ((fc)->log.log ? \ errorf(fc, fmt, ## __VA_ARGS__) : \ ({ dprintk(fmt "\n", ## __VA_ARGS__); })) @@ -710,9 +717,9 @@ unsigned long nfs_block_bits(unsigned long bsize, unsigned char *nrbitsp) if ((bsize & (bsize - 1)) || nrbitsp) { unsigned char nrbits; - for (nrbits = 31; nrbits && !(bsize & (1 << nrbits)); nrbits--) + for (nrbits = 31; nrbits && !(bsize & (1UL << nrbits)); nrbits--) ; - bsize = 1 << nrbits; + bsize = 1UL << nrbits; if (nrbitsp) *nrbitsp = nrbits; } diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index cbbe3f0193b8..74bda639a7cf 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -986,6 +986,7 @@ static int nfs3_have_delegation(struct inode *inode, fmode_t flags) static const struct inode_operations nfs3_dir_inode_operations = { .create = nfs_create, + .atomic_open = nfs_atomic_open_v23, .lookup = nfs_lookup, .link = nfs_link, .unlink = nfs_unlink, diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index ea390db94b62..c93c12063b3a 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5456,7 +5456,7 @@ static bool nfs4_read_plus_not_supported(struct rpc_task *task, struct rpc_message *msg = &task->tk_msg; if (msg->rpc_proc == &nfs4_procedures[NFSPROC4_CLNT_READ_PLUS] && - server->caps & NFS_CAP_READ_PLUS && task->tk_status == -ENOTSUPP) { + task->tk_status == -ENOTSUPP) { server->caps &= ~NFS_CAP_READ_PLUS; msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ]; rpc_restart_call_prepare(task); diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 662e86ea3a2d..5b452411e8fd 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -2116,6 +2116,7 @@ static int nfs4_try_migration(struct nfs_server *server, const struct cred *cred { struct nfs_client *clp = server->nfs_client; struct nfs4_fs_locations *locations = NULL; + struct nfs_fattr *fattr; struct inode *inode; struct page *page; int status, result; @@ -2125,19 +2126,16 @@ static int nfs4_try_migration(struct nfs_server *server, const struct cred *cred (unsigned long long)server->fsid.minor, clp->cl_hostname); - result = 0; page = alloc_page(GFP_KERNEL); locations = kmalloc(sizeof(struct nfs4_fs_locations), GFP_KERNEL); - if (page == NULL || locations == NULL) { - dprintk("<-- %s: no memory\n", __func__); - goto out; - } - locations->fattr = nfs_alloc_fattr(); - if (locations->fattr == NULL) { + fattr = nfs_alloc_fattr(); + if (page == NULL || locations == NULL || fattr == NULL) { dprintk("<-- %s: no memory\n", __func__); + result = 0; goto out; } + locations->fattr = fattr; inode = d_inode(server->super->s_root); result = nfs4_proc_get_locations(server, NFS_FH(inode), locations, page, cred); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index a5cc6199127f..b5834728f31b 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -2705,38 +2705,28 @@ pnfs_layout_return_unused_byclid(struct nfs_client *clp, &range); } +/* Check if we have we have a valid layout but if there isn't an intersection + * between the request and the pgio->pg_lseg, put this pgio->pg_lseg away. + */ void -pnfs_generic_pg_check_layout(struct nfs_pageio_descriptor *pgio) +pnfs_generic_pg_check_layout(struct nfs_pageio_descriptor *pgio, + struct nfs_page *req) { if (pgio->pg_lseg == NULL || - test_bit(NFS_LSEG_VALID, &pgio->pg_lseg->pls_flags)) + (test_bit(NFS_LSEG_VALID, &pgio->pg_lseg->pls_flags) && + pnfs_lseg_request_intersecting(pgio->pg_lseg, req))) return; pnfs_put_lseg(pgio->pg_lseg); pgio->pg_lseg = NULL; } EXPORT_SYMBOL_GPL(pnfs_generic_pg_check_layout); -/* - * Check for any intersection between the request and the pgio->pg_lseg, - * and if none, put this pgio->pg_lseg away. - */ -void -pnfs_generic_pg_check_range(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) -{ - if (pgio->pg_lseg && !pnfs_lseg_request_intersecting(pgio->pg_lseg, req)) { - pnfs_put_lseg(pgio->pg_lseg); - pgio->pg_lseg = NULL; - } -} -EXPORT_SYMBOL_GPL(pnfs_generic_pg_check_range); - void pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) { u64 rd_size; - pnfs_generic_pg_check_layout(pgio); - pnfs_generic_pg_check_range(pgio, req); + pnfs_generic_pg_check_layout(pgio, req); if (pgio->pg_lseg == NULL) { if (pgio->pg_dreq == NULL) rd_size = i_size_read(pgio->pg_inode) - req_offset(req); @@ -2766,8 +2756,7 @@ void pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req, u64 wb_size) { - pnfs_generic_pg_check_layout(pgio); - pnfs_generic_pg_check_range(pgio, req); + pnfs_generic_pg_check_layout(pgio, req); if (pgio->pg_lseg == NULL) { pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, nfs_req_openctx(req), diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index db57a85500ee..fa5beeaaf5da 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -257,8 +257,7 @@ void pnfs_put_lseg(struct pnfs_layout_segment *lseg); void set_pnfs_layoutdriver(struct nfs_server *, const struct nfs_fh *, struct nfs_fsinfo *); void unset_pnfs_layoutdriver(struct nfs_server *); -void pnfs_generic_pg_check_layout(struct nfs_pageio_descriptor *pgio); -void pnfs_generic_pg_check_range(struct nfs_pageio_descriptor *pgio, struct nfs_page *req); +void pnfs_generic_pg_check_layout(struct nfs_pageio_descriptor *pgio, struct nfs_page *req); void pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *, struct nfs_page *); int pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc); void pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index ad3a321ae997..d105e5b2659d 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -695,6 +695,7 @@ static int nfs_have_delegation(struct inode *inode, fmode_t flags) static const struct inode_operations nfs_dir_inode_operations = { .create = nfs_create, .lookup = nfs_lookup, + .atomic_open = nfs_atomic_open_v23, .link = nfs_link, .unlink = nfs_unlink, .symlink = nfs_symlink, diff --git a/fs/nfs/super.c b/fs/nfs/super.c index dc03f98f7616..cbbd4866b0b7 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -901,6 +901,16 @@ static struct nfs_server *nfs_try_mount_request(struct fs_context *fc) rpc_authflavor_t authlist[NFS_MAX_SECFLAVORS]; unsigned int authlist_len = ARRAY_SIZE(authlist); + /* make sure 'nolock'/'lock' override the 'local_lock' mount option */ + if (ctx->lock_status) { + if (ctx->lock_status == NFS_LOCK_NOLOCK) { + ctx->flags |= NFS_MOUNT_NONLM; + ctx->flags |= (NFS_MOUNT_LOCAL_FLOCK | NFS_MOUNT_LOCAL_FCNTL); + } else { + ctx->flags &= ~NFS_MOUNT_NONLM; + ctx->flags &= ~(NFS_MOUNT_LOCAL_FLOCK | NFS_MOUNT_LOCAL_FCNTL); + } + } status = nfs_request_mount(fc, ctx->mntfh, authlist, &authlist_len); if (status) return ERR_PTR(status); diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 6be7dd423fbd..60d4f59f7665 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -2118,8 +2118,10 @@ static void nilfs_segctor_start_timer(struct nilfs_sc_info *sci) { spin_lock(&sci->sc_state_lock); if (!(sci->sc_state & NILFS_SEGCTOR_COMMIT)) { - sci->sc_timer.expires = jiffies + sci->sc_interval; - add_timer(&sci->sc_timer); + if (sci->sc_task) { + sci->sc_timer.expires = jiffies + sci->sc_interval; + add_timer(&sci->sc_timer); + } sci->sc_state |= NILFS_SEGCTOR_COMMIT; } spin_unlock(&sci->sc_state_lock); @@ -2166,19 +2168,36 @@ static int nilfs_segctor_sync(struct nilfs_sc_info *sci) struct nilfs_segctor_wait_request wait_req; int err = 0; - spin_lock(&sci->sc_state_lock); init_wait(&wait_req.wq); wait_req.err = 0; atomic_set(&wait_req.done, 0); + init_waitqueue_entry(&wait_req.wq, current); + + /* + * To prevent a race issue where completion notifications from the + * log writer thread are missed, increment the request sequence count + * "sc_seq_request" and insert a wait queue entry using the current + * sequence number into the "sc_wait_request" queue at the same time + * within the lock section of "sc_state_lock". + */ + spin_lock(&sci->sc_state_lock); wait_req.seq = ++sci->sc_seq_request; + add_wait_queue(&sci->sc_wait_request, &wait_req.wq); spin_unlock(&sci->sc_state_lock); - init_waitqueue_entry(&wait_req.wq, current); - add_wait_queue(&sci->sc_wait_request, &wait_req.wq); - set_current_state(TASK_INTERRUPTIBLE); wake_up(&sci->sc_wait_daemon); for (;;) { + set_current_state(TASK_INTERRUPTIBLE); + + /* + * Synchronize only while the log writer thread is alive. + * Leave flushing out after the log writer thread exits to + * the cleanup work in nilfs_segctor_destroy(). + */ + if (!sci->sc_task) + break; + if (atomic_read(&wait_req.done)) { err = wait_req.err; break; @@ -2194,7 +2213,7 @@ static int nilfs_segctor_sync(struct nilfs_sc_info *sci) return err; } -static void nilfs_segctor_wakeup(struct nilfs_sc_info *sci, int err) +static void nilfs_segctor_wakeup(struct nilfs_sc_info *sci, int err, bool force) { struct nilfs_segctor_wait_request *wrq, *n; unsigned long flags; @@ -2202,7 +2221,7 @@ static void nilfs_segctor_wakeup(struct nilfs_sc_info *sci, int err) spin_lock_irqsave(&sci->sc_wait_request.lock, flags); list_for_each_entry_safe(wrq, n, &sci->sc_wait_request.head, wq.entry) { if (!atomic_read(&wrq->done) && - nilfs_cnt32_ge(sci->sc_seq_done, wrq->seq)) { + (force || nilfs_cnt32_ge(sci->sc_seq_done, wrq->seq))) { wrq->err = err; atomic_set(&wrq->done, 1); } @@ -2320,10 +2339,21 @@ int nilfs_construct_dsync_segment(struct super_block *sb, struct inode *inode, */ static void nilfs_segctor_accept(struct nilfs_sc_info *sci) { + bool thread_is_alive; + spin_lock(&sci->sc_state_lock); sci->sc_seq_accepted = sci->sc_seq_request; + thread_is_alive = (bool)sci->sc_task; spin_unlock(&sci->sc_state_lock); - del_timer_sync(&sci->sc_timer); + + /* + * This function does not race with the log writer thread's + * termination. Therefore, deleting sc_timer, which should not be + * done after the log writer thread exits, can be done safely outside + * the area protected by sc_state_lock. + */ + if (thread_is_alive) + del_timer_sync(&sci->sc_timer); } /** @@ -2340,7 +2370,7 @@ static void nilfs_segctor_notify(struct nilfs_sc_info *sci, int mode, int err) if (mode == SC_LSEG_SR) { sci->sc_state &= ~NILFS_SEGCTOR_COMMIT; sci->sc_seq_done = sci->sc_seq_accepted; - nilfs_segctor_wakeup(sci, err); + nilfs_segctor_wakeup(sci, err, false); sci->sc_flush_request = 0; } else { if (mode == SC_FLUSH_FILE) @@ -2349,7 +2379,7 @@ static void nilfs_segctor_notify(struct nilfs_sc_info *sci, int mode, int err) sci->sc_flush_request &= ~FLUSH_DAT_BIT; /* re-enable timer if checkpoint creation was not done */ - if ((sci->sc_state & NILFS_SEGCTOR_COMMIT) && + if ((sci->sc_state & NILFS_SEGCTOR_COMMIT) && sci->sc_task && time_before(jiffies, sci->sc_timer.expires)) add_timer(&sci->sc_timer); } @@ -2539,6 +2569,7 @@ static int nilfs_segctor_thread(void *arg) int timeout = 0; sci->sc_timer_task = current; + timer_setup(&sci->sc_timer, nilfs_construction_timeout, 0); /* start sync. */ sci->sc_task = current; @@ -2606,6 +2637,7 @@ static int nilfs_segctor_thread(void *arg) end_thread: /* end sync. */ sci->sc_task = NULL; + timer_shutdown_sync(&sci->sc_timer); wake_up(&sci->sc_wait_task); /* for nilfs_segctor_kill_thread() */ spin_unlock(&sci->sc_state_lock); return 0; @@ -2669,7 +2701,6 @@ static struct nilfs_sc_info *nilfs_segctor_new(struct super_block *sb, INIT_LIST_HEAD(&sci->sc_gc_inodes); INIT_LIST_HEAD(&sci->sc_iput_queue); INIT_WORK(&sci->sc_iput_work, nilfs_iput_work_func); - timer_setup(&sci->sc_timer, nilfs_construction_timeout, 0); sci->sc_interval = HZ * NILFS_SC_DEFAULT_TIMEOUT; sci->sc_mjcp_freq = HZ * NILFS_SC_DEFAULT_SR_FREQ; @@ -2723,6 +2754,13 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci) || sci->sc_seq_request != sci->sc_seq_done); spin_unlock(&sci->sc_state_lock); + /* + * Forcibly wake up tasks waiting in nilfs_segctor_sync(), which can + * be called from delayed iput() via nilfs_evict_inode() and can race + * with the above log writer thread termination. + */ + nilfs_segctor_wakeup(sci, 0, true); + if (flush_work(&sci->sc_iput_work)) flag = true; @@ -2748,7 +2786,6 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci) down_write(&nilfs->ns_segctor_sem); - timer_shutdown_sync(&sci->sc_timer); kfree(sci); } diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c index 7aadf5010999..8e6bcdf99770 100644 --- a/fs/ntfs3/attrib.c +++ b/fs/ntfs3/attrib.c @@ -2558,3 +2558,35 @@ undo_insert_range: goto out; } + +/* + * attr_force_nonresident + * + * Convert default data attribute into non resident form. + */ +int attr_force_nonresident(struct ntfs_inode *ni) +{ + int err; + struct ATTRIB *attr; + struct ATTR_LIST_ENTRY *le = NULL; + struct mft_inode *mi; + + attr = ni_find_attr(ni, NULL, &le, ATTR_DATA, NULL, 0, NULL, &mi); + if (!attr) { + ntfs_bad_inode(&ni->vfs_inode, "no data attribute"); + return -ENOENT; + } + + if (attr->non_res) { + /* Already non resident. */ + return 0; + } + + down_write(&ni->file.run_lock); + err = attr_make_nonresident(ni, attr, le, mi, + le32_to_cpu(attr->res.data_size), + &ni->file.run, &attr, NULL); + up_write(&ni->file.run_lock); + + return err; +} diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c index 263635199b60..1937e8e612f8 100644 --- a/fs/ntfs3/dir.c +++ b/fs/ntfs3/dir.c @@ -475,6 +475,7 @@ static int ntfs_readdir(struct file *file, struct dir_context *ctx) vbo = (u64)bit << index_bits; if (vbo >= i_size) { ntfs_inode_err(dir, "Looks like your dir is corrupt"); + ctx->pos = eod; err = -EINVAL; goto out; } diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index b73969e05052..2f903b6ce157 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -578,6 +578,15 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len) /* Check new size. */ u8 cluster_bits = sbi->cluster_bits; + /* Be sure file is non resident. */ + if (is_resident(ni)) { + ni_lock(ni); + err = attr_force_nonresident(ni); + ni_unlock(ni); + if (err) + goto out; + } + /* generic/213: expected -ENOSPC instead of -EFBIG. */ if (!is_supported_holes) { loff_t to_alloc = new_size - inode_get_bytes(inode); diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c index 7f27382e0ce2..0008670939a4 100644 --- a/fs/ntfs3/frecord.c +++ b/fs/ntfs3/frecord.c @@ -2636,7 +2636,7 @@ int ni_read_frame(struct ntfs_inode *ni, u64 frame_vbo, struct page **pages, goto out1; } - pages_disk = kzalloc(npages_disk * sizeof(struct page *), GFP_NOFS); + pages_disk = kcalloc(npages_disk, sizeof(*pages_disk), GFP_NOFS); if (!pages_disk) { err = -ENOMEM; goto out2; diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c index 855519713bf7..d7807d255dfe 100644 --- a/fs/ntfs3/fslog.c +++ b/fs/ntfs3/fslog.c @@ -517,7 +517,7 @@ static inline bool is_rst_area_valid(const struct RESTART_HDR *rhdr) seq_bits -= 1; } - if (seq_bits != ra->seq_num_bits) + if (seq_bits != le32_to_cpu(ra->seq_num_bits)) return false; /* The log page data offset and record header length must be quad-aligned. */ @@ -1184,7 +1184,8 @@ out: static int log_read_rst(struct ntfs_log *log, bool first, struct restart_info *info) { - u32 skip, vbo; + u32 skip; + u64 vbo; struct RESTART_HDR *r_page = NULL; /* Determine which restart area we are looking for. */ diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c index 43796aaa3d97..d0f15bbf78f6 100644 --- a/fs/ntfs3/index.c +++ b/fs/ntfs3/index.c @@ -1534,6 +1534,11 @@ static int indx_add_allocate(struct ntfs_index *indx, struct ntfs_inode *ni, goto out1; } + if (data_size <= le64_to_cpu(alloc->nres.data_size)) { + /* Reuse index. */ + goto out; + } + /* Increase allocation. */ err = attr_set_size(ni, ATTR_ALLOC, in->name, in->name_len, &indx->alloc_run, data_size, &data_size, true, @@ -1547,6 +1552,7 @@ static int indx_add_allocate(struct ntfs_index *indx, struct ntfs_inode *ni, if (in->name == I30_NAME) i_size_write(&ni->vfs_inode, data_size); +out: *vbn = bit << indx->idx2vbn_bits; return 0; diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index d273eda1cf45..0f1664db94ad 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -37,7 +37,7 @@ static struct inode *ntfs_read_mft(struct inode *inode, bool is_dir; unsigned long ino = inode->i_ino; u32 rp_fa = 0, asize, t32; - u16 roff, rsize, names = 0; + u16 roff, rsize, names = 0, links = 0; const struct ATTR_FILE_NAME *fname = NULL; const struct INDEX_ROOT *root; struct REPARSE_DATA_BUFFER rp; // 0x18 bytes @@ -200,11 +200,12 @@ next_attr: rsize < SIZEOF_ATTRIBUTE_FILENAME) goto out; + names += 1; fname = Add2Ptr(attr, roff); if (fname->type == FILE_NAME_DOS) goto next_attr; - names += 1; + links += 1; if (name && name->len == fname->name_len && !ntfs_cmp_names_cpu(name, (struct le_str *)&fname->name_len, NULL, false)) @@ -429,7 +430,7 @@ end_enum: ni->mi.dirty = true; } - set_nlink(inode, names); + set_nlink(inode, links); if (S_ISDIR(mode)) { ni->std_fa |= FILE_ATTRIBUTE_DIRECTORY; @@ -576,13 +577,18 @@ static noinline int ntfs_get_block_vbo(struct inode *inode, u64 vbo, clear_buffer_uptodate(bh); if (is_resident(ni)) { - ni_lock(ni); - err = attr_data_read_resident(ni, &folio->page); - ni_unlock(ni); - - if (!err) - set_buffer_uptodate(bh); + bh->b_blocknr = RESIDENT_LCN; bh->b_size = block_size; + if (!folio) { + err = 0; + } else { + ni_lock(ni); + err = attr_data_read_resident(ni, &folio->page); + ni_unlock(ni); + + if (!err) + set_buffer_uptodate(bh); + } return err; } @@ -1216,11 +1222,10 @@ out: * * NOTE: if fnd != NULL (ntfs_atomic_open) then @dir is locked */ -struct inode *ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, - const struct cpu_str *uni, umode_t mode, - dev_t dev, const char *symname, u32 size, - struct ntfs_fnd *fnd) +int ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, const struct cpu_str *uni, + umode_t mode, dev_t dev, const char *symname, u32 size, + struct ntfs_fnd *fnd) { int err; struct super_block *sb = dir->i_sb; @@ -1245,6 +1250,9 @@ struct inode *ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir, struct REPARSE_DATA_BUFFER *rp = NULL; bool rp_inserted = false; + /* New file will be resident or non resident. */ + const bool new_file_resident = 1; + if (!fnd) ni_lock_dir(dir_ni); @@ -1484,7 +1492,7 @@ struct inode *ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir, attr->size = cpu_to_le32(SIZEOF_RESIDENT); attr->name_off = SIZEOF_RESIDENT_LE; attr->res.data_off = SIZEOF_RESIDENT_LE; - } else if (S_ISREG(mode)) { + } else if (!new_file_resident && S_ISREG(mode)) { /* * Regular file. Create empty non resident data attribute. */ @@ -1727,12 +1735,10 @@ out1: if (!fnd) ni_unlock(dir_ni); - if (err) - return ERR_PTR(err); - - unlock_new_inode(inode); + if (!err) + unlock_new_inode(inode); - return inode; + return err; } int ntfs_link_inode(struct inode *inode, struct dentry *dentry) diff --git a/fs/ntfs3/namei.c b/fs/ntfs3/namei.c index 084d19d78397..71498421ce60 100644 --- a/fs/ntfs3/namei.c +++ b/fs/ntfs3/namei.c @@ -107,12 +107,8 @@ static struct dentry *ntfs_lookup(struct inode *dir, struct dentry *dentry, static int ntfs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { - struct inode *inode; - - inode = ntfs_create_inode(idmap, dir, dentry, NULL, S_IFREG | mode, 0, - NULL, 0, NULL); - - return IS_ERR(inode) ? PTR_ERR(inode) : 0; + return ntfs_create_inode(idmap, dir, dentry, NULL, S_IFREG | mode, 0, + NULL, 0, NULL); } /* @@ -123,12 +119,8 @@ static int ntfs_create(struct mnt_idmap *idmap, struct inode *dir, static int ntfs_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { - struct inode *inode; - - inode = ntfs_create_inode(idmap, dir, dentry, NULL, mode, rdev, NULL, 0, - NULL); - - return IS_ERR(inode) ? PTR_ERR(inode) : 0; + return ntfs_create_inode(idmap, dir, dentry, NULL, mode, rdev, NULL, 0, + NULL); } /* @@ -200,15 +192,12 @@ static int ntfs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { u32 size = strlen(symname); - struct inode *inode; if (unlikely(ntfs3_forced_shutdown(dir->i_sb))) return -EIO; - inode = ntfs_create_inode(idmap, dir, dentry, NULL, S_IFLNK | 0777, 0, - symname, size, NULL); - - return IS_ERR(inode) ? PTR_ERR(inode) : 0; + return ntfs_create_inode(idmap, dir, dentry, NULL, S_IFLNK | 0777, 0, + symname, size, NULL); } /* @@ -217,12 +206,8 @@ static int ntfs_symlink(struct mnt_idmap *idmap, struct inode *dir, static int ntfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { - struct inode *inode; - - inode = ntfs_create_inode(idmap, dir, dentry, NULL, S_IFDIR | mode, 0, - NULL, 0, NULL); - - return IS_ERR(inode) ? PTR_ERR(inode) : 0; + return ntfs_create_inode(idmap, dir, dentry, NULL, S_IFDIR | mode, 0, + NULL, 0, NULL); } /* @@ -358,95 +343,6 @@ out: return err; } -/* - * ntfs_atomic_open - * - * inode_operations::atomic_open - */ -static int ntfs_atomic_open(struct inode *dir, struct dentry *dentry, - struct file *file, u32 flags, umode_t mode) -{ - int err; - struct inode *inode; - struct ntfs_fnd *fnd = NULL; - struct ntfs_inode *ni = ntfs_i(dir); - struct dentry *d = NULL; - struct cpu_str *uni = __getname(); - bool locked = false; - - if (!uni) - return -ENOMEM; - - err = ntfs_nls_to_utf16(ni->mi.sbi, dentry->d_name.name, - dentry->d_name.len, uni, NTFS_NAME_LEN, - UTF16_HOST_ENDIAN); - if (err < 0) - goto out; - -#ifdef CONFIG_NTFS3_FS_POSIX_ACL - if (IS_POSIXACL(dir)) { - /* - * Load in cache current acl to avoid ni_lock(dir): - * ntfs_create_inode -> ntfs_init_acl -> posix_acl_create -> - * ntfs_get_acl -> ntfs_get_acl_ex -> ni_lock - */ - struct posix_acl *p = get_inode_acl(dir, ACL_TYPE_DEFAULT); - - if (IS_ERR(p)) { - err = PTR_ERR(p); - goto out; - } - posix_acl_release(p); - } -#endif - - if (d_in_lookup(dentry)) { - ni_lock_dir(ni); - locked = true; - fnd = fnd_get(); - if (!fnd) { - err = -ENOMEM; - goto out1; - } - - d = d_splice_alias(dir_search_u(dir, uni, fnd), dentry); - if (IS_ERR(d)) { - err = PTR_ERR(d); - d = NULL; - goto out2; - } - - if (d) - dentry = d; - } - - if (!(flags & O_CREAT) || d_really_is_positive(dentry)) { - err = finish_no_open(file, d); - goto out2; - } - - file->f_mode |= FMODE_CREATED; - - /* - * fnd contains tree's path to insert to. - * If fnd is not NULL then dir is locked. - */ - inode = ntfs_create_inode(file_mnt_idmap(file), dir, dentry, uni, - mode, 0, NULL, 0, fnd); - err = IS_ERR(inode) ? PTR_ERR(inode) : - finish_open(file, dentry, ntfs_file_open); - dput(d); - -out2: - fnd_put(fnd); -out1: - if (locked) - ni_unlock(ni); -out: - __putname(uni); - return err; -} - struct dentry *ntfs3_get_parent(struct dentry *child) { struct inode *inode = d_inode(child); @@ -612,7 +508,6 @@ const struct inode_operations ntfs_dir_inode_operations = { .setattr = ntfs3_setattr, .getattr = ntfs_getattr, .listxattr = ntfs_listxattr, - .atomic_open = ntfs_atomic_open, .fiemap = ntfs_fiemap, }; diff --git a/fs/ntfs3/ntfs.h b/fs/ntfs3/ntfs.h index 9c7478150a03..3d6143c7abc0 100644 --- a/fs/ntfs3/ntfs.h +++ b/fs/ntfs3/ntfs.h @@ -59,7 +59,7 @@ struct GUID { struct cpu_str { u8 len; u8 unused; - u16 name[10]; + u16 name[]; }; struct le_str { diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index c018fad4c037..f9ed6d2b065d 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -452,6 +452,7 @@ int attr_allocate_frame(struct ntfs_inode *ni, CLST frame, size_t compr_size, int attr_collapse_range(struct ntfs_inode *ni, u64 vbo, u64 bytes); int attr_insert_range(struct ntfs_inode *ni, u64 vbo, u64 bytes); int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes, u32 *frame_size); +int attr_force_nonresident(struct ntfs_inode *ni); /* Functions from attrlist.c */ void al_destroy(struct ntfs_inode *ni); @@ -716,11 +717,10 @@ int ntfs_sync_inode(struct inode *inode); int ntfs_flush_inodes(struct super_block *sb, struct inode *i1, struct inode *i2); int inode_write_data(struct inode *inode, const void *data, size_t bytes); -struct inode *ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, - const struct cpu_str *uni, umode_t mode, - dev_t dev, const char *symname, u32 size, - struct ntfs_fnd *fnd); +int ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, const struct cpu_str *uni, + umode_t mode, dev_t dev, const char *symname, u32 size, + struct ntfs_fnd *fnd); int ntfs_link_inode(struct inode *inode, struct dentry *dentry); int ntfs_unlink_inode(struct inode *dir, const struct dentry *dentry); void ntfs_evict_inode(struct inode *inode); diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c index 6aa3a9d44df1..6c76503edc20 100644 --- a/fs/ntfs3/record.c +++ b/fs/ntfs3/record.c @@ -534,16 +534,9 @@ bool mi_remove_attr(struct ntfs_inode *ni, struct mft_inode *mi, if (aoff + asize > used) return false; - if (ni && is_attr_indexed(attr)) { + if (ni && is_attr_indexed(attr) && attr->type == ATTR_NAME) { u16 links = le16_to_cpu(ni->mi.mrec->hard_links); - struct ATTR_FILE_NAME *fname = - attr->type != ATTR_NAME ? - NULL : - resident_data_ex(attr, - SIZEOF_ATTRIBUTE_FILENAME); - if (fname && fname->type == FILE_NAME_DOS) { - /* Do not decrease links count deleting DOS name. */ - } else if (!links) { + if (!links) { /* minor error. Not critical. */ } else { ni->mi.mrec->hard_links = cpu_to_le16(links - 1); diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index f41e01c5676a..27fbde2701b6 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -1861,8 +1861,6 @@ static int __init init_ntfs_fs(void) { int err; - pr_info("ntfs3: Max link count %u\n", NTFS_LINK_MAX); - if (IS_ENABLED(CONFIG_NTFS3_FS_POSIX_ACL)) pr_info("ntfs3: Enabled Linux POSIX ACLs support\n"); if (IS_ENABLED(CONFIG_NTFS3_64BIT_CLUSTER)) diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c index 53e7d1fa036a..73785dece7a7 100644 --- a/fs/ntfs3/xattr.c +++ b/fs/ntfs3/xattr.c @@ -219,8 +219,11 @@ static ssize_t ntfs_list_ea(struct ntfs_inode *ni, char *buffer, if (!ea->name_len) break; - if (ea->name_len > ea_size) + if (ea->name_len > ea_size) { + ntfs_set_state(ni->mi.sbi, NTFS_DIRTY_ERROR); + err = -EINVAL; /* corrupted fs */ break; + } if (buffer) { /* Check if we can use field ea->name */ diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index e5a5f015ff03..f8d35f993fe5 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -970,12 +970,17 @@ static int show_smaps_rollup(struct seq_file *m, void *v) break; /* Case 1 and 2 above */ - if (vma->vm_start >= last_vma_end) + if (vma->vm_start >= last_vma_end) { + smap_gather_stats(vma, &mss, 0); + last_vma_end = vma->vm_end; continue; + } /* Case 4 above */ - if (vma->vm_end > last_vma_end) + if (vma->vm_end > last_vma_end) { smap_gather_stats(vma, &mss, last_vma_end); + last_vma_end = vma->vm_end; + } } } for_each_vma(vmi, vma); diff --git a/fs/signalfd.c b/fs/signalfd.c index 4a5614442dbf..ec7b2da2477a 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -282,14 +282,10 @@ static int do_signalfd4(int ufd, sigset_t *mask, int flags) if (IS_ERR(file)) { put_unused_fd(ufd); kfree(ctx); - return ufd; + return PTR_ERR(file); } file->f_mode |= FMODE_NOWAIT; - /* - * When we call this, the initialization must be complete, since - * anon_inode_getfd() will install the fd. - */ fd_install(ufd, file); } else { struct fd f = fdget(ufd); diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index ec5b639f421a..bb86fc0641d8 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -431,6 +431,7 @@ cifs_free_inode(struct inode *inode) static void cifs_evict_inode(struct inode *inode) { + netfs_wait_for_outstanding_io(inode); truncate_inode_pages_final(&inode->i_data); if (inode->i_state & I_PINNING_NETFS_WB) cifs_fscache_unuse_inode_cookie(inode, true); @@ -1226,7 +1227,7 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off, struct cifsFileInfo *smb_file_src = src_file->private_data; struct cifsFileInfo *smb_file_target = dst_file->private_data; struct cifs_tcon *target_tcon, *src_tcon; - unsigned long long destend, fstart, fend, new_size; + unsigned long long destend, fstart, fend, old_size, new_size; unsigned int xid; int rc; @@ -1293,6 +1294,7 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off, goto unlock; if (fend > target_cifsi->netfs.zero_point) target_cifsi->netfs.zero_point = fend + 1; + old_size = target_cifsi->netfs.remote_i_size; /* Discard all the folios that overlap the destination region. */ cifs_dbg(FYI, "about to discard pages %llx-%llx\n", fstart, fend); @@ -1305,9 +1307,8 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off, if (target_tcon->ses->server->ops->duplicate_extents) { rc = target_tcon->ses->server->ops->duplicate_extents(xid, smb_file_src, smb_file_target, off, len, destoff); - if (rc == 0 && new_size > i_size_read(target_inode)) { + if (rc == 0 && new_size > old_size) { truncate_setsize(target_inode, new_size); - netfs_resize_file(&target_cifsi->netfs, new_size, true); fscache_resize_cookie(cifs_inode_cookie(target_inode), new_size); } diff --git a/fs/smb/client/cifsfs.h b/fs/smb/client/cifsfs.h index 87310f05d397..62d5fee3e5eb 100644 --- a/fs/smb/client/cifsfs.h +++ b/fs/smb/client/cifsfs.h @@ -147,6 +147,6 @@ extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ /* when changing internal version - update following two lines at same time */ -#define SMB3_PRODUCT_BUILD 48 -#define CIFS_VERSION "2.48" +#define SMB3_PRODUCT_BUILD 49 +#define CIFS_VERSION "2.49" #endif /* _CIFSFS_H */ diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 9d38294a7e68..9d5c2440abfc 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -3189,6 +3189,28 @@ static void cifs_swap_deactivate(struct file *file) /* do we need to unpin (or unlock) the file */ } +/** + * cifs_swap_rw - SMB3 address space operation for swap I/O + * @iocb: target I/O control block + * @iter: I/O buffer + * + * Perform IO to the swap-file. This is much like direct IO. + */ +static int cifs_swap_rw(struct kiocb *iocb, struct iov_iter *iter) +{ + ssize_t ret; + + WARN_ON_ONCE(iov_iter_count(iter) != PAGE_SIZE); + + if (iov_iter_rw(iter) == READ) + ret = netfs_unbuffered_read_iter_locked(iocb, iter); + else + ret = netfs_unbuffered_write_iter_locked(iocb, iter, NULL); + if (ret < 0) + return ret; + return 0; +} + const struct address_space_operations cifs_addr_ops = { .read_folio = netfs_read_folio, .readahead = netfs_readahead, @@ -3204,6 +3226,7 @@ const struct address_space_operations cifs_addr_ops = { */ .swap_activate = cifs_swap_activate, .swap_deactivate = cifs_swap_deactivate, + .swap_rw = cifs_swap_rw, }; /* diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index ef18cd30f66c..4ce6c3121a7e 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -2028,6 +2028,7 @@ smb2_duplicate_extents(const unsigned int xid, * size will be queried on next revalidate, but it is important * to make sure that file's cached size is updated immediately */ + netfs_resize_file(netfs_inode(inode), dest_off + len, true); cifs_setsize(inode, dest_off + len); } rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid, @@ -3636,6 +3637,7 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon, rc = smb2_copychunk_range(xid, cfile, cfile, off, count, off + len); if (rc < 0) goto out_2; + cifsi->netfs.zero_point = new_eof; rc = smb3_zero_data(file, tcon, off, len, xid); if (rc < 0) diff --git a/fs/smb/server/mgmt/share_config.c b/fs/smb/server/mgmt/share_config.c index a2f0a2edceb8..e0a6b758094f 100644 --- a/fs/smb/server/mgmt/share_config.c +++ b/fs/smb/server/mgmt/share_config.c @@ -165,8 +165,12 @@ static struct ksmbd_share_config *share_config_request(struct unicode_map *um, share->path = kstrndup(ksmbd_share_config_path(resp), path_len, GFP_KERNEL); - if (share->path) + if (share->path) { share->path_sz = strlen(share->path); + while (share->path_sz > 1 && + share->path[share->path_sz - 1] == '/') + share->path[--share->path_sz] = '\0'; + } share->create_mask = resp->create_mask; share->directory_mask = resp->directory_mask; share->force_create_mode = resp->force_create_mode; diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index b9d9116fc2b3..a8f52c4ebbda 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -610,19 +610,24 @@ static int oplock_break_pending(struct oplock_info *opinfo, int req_op_level) if (opinfo->op_state == OPLOCK_CLOSING) return -ENOENT; else if (opinfo->level <= req_op_level) { - if (opinfo->is_lease && - opinfo->o_lease->state != - (SMB2_LEASE_HANDLE_CACHING_LE | - SMB2_LEASE_READ_CACHING_LE)) + if (opinfo->is_lease == false) + return 1; + + if (opinfo->o_lease->state != + (SMB2_LEASE_HANDLE_CACHING_LE | + SMB2_LEASE_READ_CACHING_LE)) return 1; } } if (opinfo->level <= req_op_level) { - if (opinfo->is_lease && - opinfo->o_lease->state != - (SMB2_LEASE_HANDLE_CACHING_LE | - SMB2_LEASE_READ_CACHING_LE)) { + if (opinfo->is_lease == false) { + wake_up_oplock_break(opinfo); + return 1; + } + if (opinfo->o_lease->state != + (SMB2_LEASE_HANDLE_CACHING_LE | + SMB2_LEASE_READ_CACHING_LE)) { wake_up_oplock_break(opinfo); return 1; } diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index 0256afdd4acf..5d88c184f0fc 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -37,7 +37,6 @@ static DEFINE_MUTEX(eventfs_mutex); struct eventfs_root_inode { struct eventfs_inode ei; - struct inode *parent_inode; struct dentry *events_dir; }; @@ -50,8 +49,12 @@ static struct eventfs_root_inode *get_root_inode(struct eventfs_inode *ei) /* Just try to make something consistent and unique */ static int eventfs_dir_ino(struct eventfs_inode *ei) { - if (!ei->ino) + if (!ei->ino) { ei->ino = get_next_ino(); + /* Must not have the file inode number */ + if (ei->ino == EVENTFS_FILE_INODE_INO) + ei->ino = get_next_ino(); + } return ei->ino; } @@ -207,7 +210,9 @@ static int eventfs_set_attr(struct mnt_idmap *idmap, struct dentry *dentry, * determined by the parent directory. */ if (dentry->d_inode->i_mode & S_IFDIR) { - update_attr(&ei->attr, iattr); + /* Just use the inode permissions for the events directory */ + if (!ei->is_events) + update_attr(&ei->attr, iattr); } else { name = dentry->d_name.name; @@ -225,70 +230,9 @@ static int eventfs_set_attr(struct mnt_idmap *idmap, struct dentry *dentry, return ret; } -static void update_events_attr(struct eventfs_inode *ei, struct super_block *sb) -{ - struct eventfs_root_inode *rei; - struct inode *parent; - - rei = get_root_inode(ei); - - /* Use the parent inode permissions unless root set its permissions */ - parent = rei->parent_inode; - - if (rei->ei.attr.mode & EVENTFS_SAVE_UID) - ei->attr.uid = rei->ei.attr.uid; - else - ei->attr.uid = parent->i_uid; - - if (rei->ei.attr.mode & EVENTFS_SAVE_GID) - ei->attr.gid = rei->ei.attr.gid; - else - ei->attr.gid = parent->i_gid; -} - -static void set_top_events_ownership(struct inode *inode) -{ - struct tracefs_inode *ti = get_tracefs(inode); - struct eventfs_inode *ei = ti->private; - - /* The top events directory doesn't get automatically updated */ - if (!ei || !ei->is_events) - return; - - update_events_attr(ei, inode->i_sb); - - if (!(ei->attr.mode & EVENTFS_SAVE_UID)) - inode->i_uid = ei->attr.uid; - - if (!(ei->attr.mode & EVENTFS_SAVE_GID)) - inode->i_gid = ei->attr.gid; -} - -static int eventfs_get_attr(struct mnt_idmap *idmap, - const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int flags) -{ - struct dentry *dentry = path->dentry; - struct inode *inode = d_backing_inode(dentry); - - set_top_events_ownership(inode); - - generic_fillattr(idmap, request_mask, inode, stat); - return 0; -} - -static int eventfs_permission(struct mnt_idmap *idmap, - struct inode *inode, int mask) -{ - set_top_events_ownership(inode); - return generic_permission(idmap, inode, mask); -} - static const struct inode_operations eventfs_dir_inode_operations = { .lookup = eventfs_root_lookup, .setattr = eventfs_set_attr, - .getattr = eventfs_get_attr, - .permission = eventfs_permission, }; static const struct inode_operations eventfs_file_inode_operations = { @@ -301,84 +245,109 @@ static const struct file_operations eventfs_file_operations = { .llseek = generic_file_llseek, }; -/* - * On a remount of tracefs, if UID or GID options are set, then - * the mount point inode permissions should be used. - * Reset the saved permission flags appropriately. - */ -void eventfs_remount(struct tracefs_inode *ti, bool update_uid, bool update_gid) +static void eventfs_set_attrs(struct eventfs_inode *ei, bool update_uid, kuid_t uid, + bool update_gid, kgid_t gid, int level) { - struct eventfs_inode *ei = ti->private; + struct eventfs_inode *ei_child; - if (!ei) + /* Update events/<system>/<event> */ + if (WARN_ON_ONCE(level > 3)) return; - if (update_uid) + if (update_uid) { ei->attr.mode &= ~EVENTFS_SAVE_UID; + ei->attr.uid = uid; + } - if (update_gid) + if (update_gid) { ei->attr.mode &= ~EVENTFS_SAVE_GID; + ei->attr.gid = gid; + } + + list_for_each_entry(ei_child, &ei->children, list) { + eventfs_set_attrs(ei_child, update_uid, uid, update_gid, gid, level + 1); + } if (!ei->entry_attrs) return; for (int i = 0; i < ei->nr_entries; i++) { - if (update_uid) + if (update_uid) { ei->entry_attrs[i].mode &= ~EVENTFS_SAVE_UID; - if (update_gid) + ei->entry_attrs[i].uid = uid; + } + if (update_gid) { ei->entry_attrs[i].mode &= ~EVENTFS_SAVE_GID; + ei->entry_attrs[i].gid = gid; + } } + } -/* Return the evenfs_inode of the "events" directory */ -static struct eventfs_inode *eventfs_find_events(struct dentry *dentry) +/* + * On a remount of tracefs, if UID or GID options are set, then + * the mount point inode permissions should be used. + * Reset the saved permission flags appropriately. + */ +void eventfs_remount(struct tracefs_inode *ti, bool update_uid, bool update_gid) { - struct eventfs_inode *ei; + struct eventfs_inode *ei = ti->private; - do { - // The parent is stable because we do not do renames - dentry = dentry->d_parent; - // ... and directories always have d_fsdata - ei = dentry->d_fsdata; + /* Only the events directory does the updates */ + if (!ei || !ei->is_events || ei->is_freed) + return; - /* - * If the ei is being freed, the ownership of the children - * doesn't matter. - */ - if (ei->is_freed) - return NULL; + eventfs_set_attrs(ei, update_uid, ti->vfs_inode.i_uid, + update_gid, ti->vfs_inode.i_gid, 0); +} - // Walk upwards until you find the events inode - } while (!ei->is_events); +static void update_inode_attr(struct inode *inode, umode_t mode, + struct eventfs_attr *attr, struct eventfs_root_inode *rei) +{ + if (attr && attr->mode & EVENTFS_SAVE_MODE) + inode->i_mode = attr->mode & EVENTFS_MODE_MASK; + else + inode->i_mode = mode; - update_events_attr(ei, dentry->d_sb); + if (attr && attr->mode & EVENTFS_SAVE_UID) + inode->i_uid = attr->uid; + else + inode->i_uid = rei->ei.attr.uid; - return ei; + if (attr && attr->mode & EVENTFS_SAVE_GID) + inode->i_gid = attr->gid; + else + inode->i_gid = rei->ei.attr.gid; } -static void update_inode_attr(struct dentry *dentry, struct inode *inode, - struct eventfs_attr *attr, umode_t mode) +static struct inode *eventfs_get_inode(struct dentry *dentry, struct eventfs_attr *attr, + umode_t mode, struct eventfs_inode *ei) { - struct eventfs_inode *events_ei = eventfs_find_events(dentry); + struct eventfs_root_inode *rei; + struct eventfs_inode *pei; + struct tracefs_inode *ti; + struct inode *inode; - if (!events_ei) - return; + inode = tracefs_get_inode(dentry->d_sb); + if (!inode) + return NULL; - inode->i_mode = mode; - inode->i_uid = events_ei->attr.uid; - inode->i_gid = events_ei->attr.gid; + ti = get_tracefs(inode); + ti->private = ei; + ti->flags |= TRACEFS_EVENT_INODE; - if (!attr) - return; + /* Find the top dentry that holds the "events" directory */ + do { + dentry = dentry->d_parent; + /* Directories always have d_fsdata */ + pei = dentry->d_fsdata; + } while (!pei->is_events); - if (attr->mode & EVENTFS_SAVE_MODE) - inode->i_mode = attr->mode & EVENTFS_MODE_MASK; + rei = get_root_inode(pei); - if (attr->mode & EVENTFS_SAVE_UID) - inode->i_uid = attr->uid; + update_inode_attr(inode, mode, attr, rei); - if (attr->mode & EVENTFS_SAVE_GID) - inode->i_gid = attr->gid; + return inode; } /** @@ -401,7 +370,6 @@ static struct dentry *lookup_file(struct eventfs_inode *parent_ei, void *data, const struct file_operations *fop) { - struct tracefs_inode *ti; struct inode *inode; if (!(mode & S_IFMT)) @@ -410,13 +378,11 @@ static struct dentry *lookup_file(struct eventfs_inode *parent_ei, if (WARN_ON_ONCE(!S_ISREG(mode))) return ERR_PTR(-EIO); - inode = tracefs_get_inode(dentry->d_sb); + /* Only directories have ti->private set to an ei, not files */ + inode = eventfs_get_inode(dentry, attr, mode, NULL); if (unlikely(!inode)) return ERR_PTR(-ENOMEM); - /* If the user updated the directory's attributes, use them */ - update_inode_attr(dentry, inode, attr, mode); - inode->i_op = &eventfs_file_inode_operations; inode->i_fop = fop; inode->i_private = data; @@ -424,9 +390,6 @@ static struct dentry *lookup_file(struct eventfs_inode *parent_ei, /* All files will have the same inode number */ inode->i_ino = EVENTFS_FILE_INODE_INO; - ti = get_tracefs(inode); - ti->flags |= TRACEFS_EVENT_INODE; - // Files have their parent's ei as their fsdata dentry->d_fsdata = get_ei(parent_ei); @@ -446,28 +409,19 @@ static struct dentry *lookup_file(struct eventfs_inode *parent_ei, static struct dentry *lookup_dir_entry(struct dentry *dentry, struct eventfs_inode *pei, struct eventfs_inode *ei) { - struct tracefs_inode *ti; struct inode *inode; + umode_t mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO; - inode = tracefs_get_inode(dentry->d_sb); + inode = eventfs_get_inode(dentry, &ei->attr, mode, ei); if (unlikely(!inode)) return ERR_PTR(-ENOMEM); - /* If the user updated the directory's attributes, use them */ - update_inode_attr(dentry, inode, &ei->attr, - S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO); - inode->i_op = &eventfs_dir_inode_operations; inode->i_fop = &eventfs_file_operations; /* All directories will have the same inode number */ inode->i_ino = eventfs_dir_ino(ei); - ti = get_tracefs(inode); - ti->flags |= TRACEFS_EVENT_INODE; - /* Only directories have ti->private set to an ei, not files */ - ti->private = ei; - dentry->d_fsdata = get_ei(ei); d_add(dentry, inode); @@ -828,7 +782,6 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry // Note: we have a ref to the dentry from tracefs_start_creating() rei = get_root_inode(ei); rei->events_dir = dentry; - rei->parent_inode = d_inode(dentry->d_sb->s_root); ei->entries = entries; ei->nr_entries = size; @@ -838,14 +791,12 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry uid = d_inode(dentry->d_parent)->i_uid; gid = d_inode(dentry->d_parent)->i_gid; - ei->attr.uid = uid; - ei->attr.gid = gid; - /* - * When the "events" directory is created, it takes on the - * permissions of its parent. But can be reset on remount. + * The ei->attr will be used as the default values for the + * files beneath this directory. */ - ei->attr.mode |= EVENTFS_SAVE_UID | EVENTFS_SAVE_GID; + ei->attr.uid = uid; + ei->attr.gid = gid; INIT_LIST_HEAD(&ei->children); INIT_LIST_HEAD(&ei->list); diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index a827f6a716c4..7c29f4afc23d 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -373,12 +373,21 @@ static int tracefs_apply_options(struct super_block *sb, bool remount) rcu_read_lock(); list_for_each_entry_rcu(ti, &tracefs_inodes, list) { - if (update_uid) + if (update_uid) { ti->flags &= ~TRACEFS_UID_PERM_SET; + ti->vfs_inode.i_uid = fsi->uid; + } - if (update_gid) + if (update_gid) { ti->flags &= ~TRACEFS_GID_PERM_SET; - + ti->vfs_inode.i_gid = fsi->gid; + } + + /* + * Note, the above ti->vfs_inode updates are + * used in eventfs_remount() so they must come + * before calling it. + */ if (ti->flags & TRACEFS_EVENT_INODE) eventfs_remount(ti, update_uid, update_gid); } @@ -417,10 +426,26 @@ static int tracefs_show_options(struct seq_file *m, struct dentry *root) return 0; } +static int tracefs_drop_inode(struct inode *inode) +{ + struct tracefs_inode *ti = get_tracefs(inode); + + /* + * This inode is being freed and cannot be used for + * eventfs. Clear the flag so that it doesn't call into + * eventfs during the remount flag updates. The eventfs_inode + * gets freed after an RCU cycle, so the content will still + * be safe if the iteration is going on now. + */ + ti->flags &= ~TRACEFS_EVENT_INODE; + + return 1; +} + static const struct super_operations tracefs_super_operations = { .alloc_inode = tracefs_alloc_inode, .free_inode = tracefs_free_inode, - .drop_inode = generic_delete_inode, + .drop_inode = tracefs_drop_inode, .statfs = simple_statfs, .show_options = tracefs_show_options, }; @@ -446,22 +471,7 @@ static int tracefs_d_revalidate(struct dentry *dentry, unsigned int flags) return !(ei && ei->is_freed); } -static void tracefs_d_iput(struct dentry *dentry, struct inode *inode) -{ - struct tracefs_inode *ti = get_tracefs(inode); - - /* - * This inode is being freed and cannot be used for - * eventfs. Clear the flag so that it doesn't call into - * eventfs during the remount flag updates. The eventfs_inode - * gets freed after an RCU cycle, so the content will still - * be safe if the iteration is going on now. - */ - ti->flags &= ~TRACEFS_EVENT_INODE; -} - static const struct dentry_operations tracefs_dentry_operations = { - .d_iput = tracefs_d_iput, .d_revalidate = tracefs_d_revalidate, .d_release = tracefs_d_release, }; diff --git a/include/drm/display/drm_dp_mst_helper.h b/include/drm/display/drm_dp_mst_helper.h index 3546b58a121b..cfe096389d94 100644 --- a/include/drm/display/drm_dp_mst_helper.h +++ b/include/drm/display/drm_dp_mst_helper.h @@ -871,7 +871,6 @@ int drm_dp_add_payload_part1(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_topology_state *mst_state, struct drm_dp_mst_atomic_payload *payload); int drm_dp_add_payload_part2(struct drm_dp_mst_topology_mgr *mgr, - struct drm_atomic_state *state, struct drm_dp_mst_atomic_payload *payload); void drm_dp_remove_payload_part1(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_topology_state *mst_state, diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h index afc9e259a2d3..abd24016a900 100644 --- a/include/linux/alloc_tag.h +++ b/include/linux/alloc_tag.h @@ -11,6 +11,7 @@ #include <linux/preempt.h> #include <asm/percpu.h> #include <linux/cpumask.h> +#include <linux/smp.h> #include <linux/static_key.h> #include <linux/irqflags.h> diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 2ad1ffa4ccb9..0ed47d00549b 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -636,6 +636,14 @@ static inline void eth_skb_pkt_type(struct sk_buff *skb, } } +static inline struct ethhdr *eth_skb_pull_mac(struct sk_buff *skb) +{ + struct ethhdr *eth = (struct ethhdr *)skb->data; + + skb_pull_inline(skb, ETH_HLEN); + return eth; +} + /** * eth_skb_pad - Pad buffer to mininum number of octets for Ethernet frame * @skb: Buffer to pad diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index d658ae729a02..7e0f340bf363 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -75,17 +75,30 @@ void __write_overflow_field(size_t avail, size_t wanted) __compiletime_warning(" __ret; \ }) -#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) +#if defined(__SANITIZE_ADDRESS__) + +#if !defined(CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX) && !defined(CONFIG_GENERIC_ENTRY) +extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset); +extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove); +extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy); +#elif defined(CONFIG_KASAN_GENERIC) +extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(__asan_memset); +extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(__asan_memmove); +extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(__asan_memcpy); +#else /* CONFIG_KASAN_SW_TAGS */ +extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(__hwasan_memset); +extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(__hwasan_memmove); +extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(__hwasan_memcpy); +#endif + extern void *__underlying_memchr(const void *p, int c, __kernel_size_t size) __RENAME(memchr); extern int __underlying_memcmp(const void *p, const void *q, __kernel_size_t size) __RENAME(memcmp); -extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy); -extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove); -extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset); extern char *__underlying_strcat(char *p, const char *q) __RENAME(strcat); extern char *__underlying_strcpy(char *p, const char *q) __RENAME(strcpy); extern __kernel_size_t __underlying_strlen(const char *p) __RENAME(strlen); extern char *__underlying_strncat(char *p, const char *q, __kernel_size_t count) __RENAME(strncat); extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) __RENAME(strncpy); + #else #if defined(__SANITIZE_MEMORY__) @@ -110,6 +123,7 @@ extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) #define __underlying_strlen __builtin_strlen #define __underlying_strncat __builtin_strncat #define __underlying_strncpy __builtin_strncpy + #endif /** diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index e3a83ebd1b33..800995c425e0 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -819,7 +819,8 @@ static inline int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) extern int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr); #if defined(CONFIG_DYNAMIC_FTRACE_WITH_REGS) || \ - defined(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS) + defined(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS) || \ + defined(CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS) /** * ftrace_modify_call - convert from one addr to another (no nop) * @rec: the call site record (e.g. mcount/fentry) diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index f468763478ae..5df52e15f7d6 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -10308,9 +10308,9 @@ struct mlx5_ifc_mcam_access_reg_bits { u8 mfrl[0x1]; u8 regs_39_to_32[0x8]; - u8 regs_31_to_10[0x16]; + u8 regs_31_to_11[0x15]; u8 mtmp[0x1]; - u8 regs_8_to_0[0x9]; + u8 regs_9_to_0[0xa]; }; struct mlx5_ifc_mcam_access_reg_bits1 { diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 7a9a07ea451b..4338b1b4ac44 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -690,6 +690,8 @@ struct x86_cpu_id { __u16 model; __u16 steppings; __u16 feature; /* bit index */ + /* Solely for kernel-internal use: DO NOT EXPORT to userspace! */ + __u16 flags; kernel_ulong_t driver_data; }; diff --git a/include/linux/netfs.h b/include/linux/netfs.h index ca56a4428043..3ca3906bb8da 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -68,6 +68,7 @@ struct netfs_inode { loff_t remote_i_size; /* Size of the remote file */ loff_t zero_point; /* Size after which we assume there's no data * on the server */ + atomic_t io_count; /* Number of outstanding reqs */ unsigned long flags; #define NETFS_ICTX_ODIRECT 0 /* The file has DIO in progress */ #define NETFS_ICTX_UNBUFFERED 1 /* I/O should not use the pagecache */ @@ -400,6 +401,8 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, ssize_t netfs_buffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *from, struct netfs_group *netfs_group); ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from); +ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *iter, + struct netfs_group *netfs_group); ssize_t netfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from); /* Address operations API */ @@ -472,6 +475,7 @@ static inline void netfs_inode_init(struct netfs_inode *ctx, ctx->remote_i_size = i_size_read(&ctx->inode); ctx->zero_point = LLONG_MAX; ctx->flags = 0; + atomic_set(&ctx->io_count, 0); #if IS_ENABLED(CONFIG_FSCACHE) ctx->cache = NULL; #endif @@ -515,4 +519,20 @@ static inline struct fscache_cookie *netfs_i_cookie(struct netfs_inode *ctx) #endif } +/** + * netfs_wait_for_outstanding_io - Wait for outstanding I/O to complete + * @ctx: The netfs inode to wait on + * + * Wait for outstanding I/O requests of any type to complete. This is intended + * to be called from inode eviction routines. This makes sure that any + * resources held by those requests are cleaned up before we let the inode get + * cleaned up. + */ +static inline void netfs_wait_for_outstanding_io(struct inode *inode) +{ + struct netfs_inode *ictx = netfs_inode(inode); + + wait_var_event(&ictx->io_count, atomic_read(&ictx->io_count) == 0); +} + #endif /* _LINUX_NETFS_H */ diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index d59116ac8209..039898d70954 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -561,6 +561,9 @@ extern int nfs_may_open(struct inode *inode, const struct cred *cred, int openfl extern void nfs_access_zap_cache(struct inode *inode); extern int nfs_access_get_cached(struct inode *inode, const struct cred *cred, u32 *mask, bool may_block); +extern int nfs_atomic_open_v23(struct inode *dir, struct dentry *dentry, + struct file *file, unsigned int open_flags, + umode_t mode); /* * linux/fs/nfs/symlink.c diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 3d69589c00a4..ee633712bba0 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -346,6 +346,19 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) m->gfp_mask = mask; } +/* + * There are some parts of the kernel which assume that PMD entries + * are exactly HPAGE_PMD_ORDER. Those should be fixed, but until then, + * limit the maximum allocation order to PMD size. I'm not aware of any + * assumptions about maximum order if THP are disabled, but 8 seems like + * a good order (that's 1MB if you're using 4kB pages) + */ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define MAX_PAGECACHE_ORDER HPAGE_PMD_ORDER +#else +#define MAX_PAGECACHE_ORDER 8 +#endif + /** * mapping_set_large_folios() - Indicate the file supports large folios. * @mapping: The file. @@ -372,6 +385,14 @@ static inline bool mapping_large_folio_support(struct address_space *mapping) test_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); } +/* Return the maximum folio size for this pagecache mapping, in bytes. */ +static inline size_t mapping_max_folio_size(struct address_space *mapping) +{ + if (mapping_large_folio_support(mapping)) + return PAGE_SIZE << MAX_PAGECACHE_ORDER; + return PAGE_SIZE; +} + static inline int filemap_nr_thps(struct address_space *mapping) { #ifdef CONFIG_READ_ONLY_THP_FOR_FS @@ -530,19 +551,6 @@ static inline void *detach_page_private(struct page *page) return folio_detach_private(page_folio(page)); } -/* - * There are some parts of the kernel which assume that PMD entries - * are exactly HPAGE_PMD_ORDER. Those should be fixed, but until then, - * limit the maximum allocation order to PMD size. I'm not aware of any - * assumptions about maximum order if THP are disabled, but 8 seems like - * a good order (that's 1MB if you're using 4kB pages) - */ -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -#define MAX_PAGECACHE_ORDER HPAGE_PMD_ORDER -#else -#define MAX_PAGECACHE_ORDER 8 -#endif - #ifdef CONFIG_NUMA struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order); #else diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 22a07c0900a4..f230a472ccd3 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -299,6 +299,8 @@ enum regulator_type { * @vsel_range_reg: Register for range selector when using pickable ranges * and ``regulator_map_*_voltage_*_pickable`` functions. * @vsel_range_mask: Mask for register bitfield used for range selector + * @range_applied_by_vsel: A flag to indicate that changes to vsel_range_reg + * are only effective after vsel_reg is written * @vsel_reg: Register for selector when using ``regulator_map_*_voltage_*`` * @vsel_mask: Mask for register bitfield used for selector * @vsel_step: Specify the resolution of selector stepping when setting @@ -389,6 +391,7 @@ struct regulator_desc { unsigned int vsel_range_reg; unsigned int vsel_range_mask; + bool range_applied_by_vsel; unsigned int vsel_reg; unsigned int vsel_mask; unsigned int vsel_step; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index e619ac10cd23..9104952d323d 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -821,6 +821,7 @@ asmlinkage long sys_process_mrelease(int pidfd, unsigned int flags); asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size, unsigned long prot, unsigned long pgoff, unsigned long flags); +asmlinkage long sys_mseal(unsigned long start, size_t len, unsigned long flags); asmlinkage long sys_mbind(unsigned long start, unsigned long len, unsigned long mode, const unsigned long __user *nmask, diff --git a/include/linux/tpm.h b/include/linux/tpm.h index c17e4efbb2e5..21a67dc9efe8 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -394,21 +394,6 @@ enum tpm2_object_attributes { TPM2_OA_SIGN = BIT(18), }; -/* - * definitions for the canonical template. These are mandated - * by the TCG key template documents - */ - -#define AES_KEY_BYTES AES_KEYSIZE_128 -#define AES_KEY_BITS (AES_KEY_BYTES*8) -#define TPM2_OA_TMPL (TPM2_OA_NO_DA | \ - TPM2_OA_FIXED_TPM | \ - TPM2_OA_FIXED_PARENT | \ - TPM2_OA_SENSITIVE_DATA_ORIGIN | \ - TPM2_OA_USER_WITH_AUTH | \ - TPM2_OA_DECRYPT | \ - TPM2_OA_RESTRICTED) - enum tpm2_session_attributes { TPM2_SA_CONTINUE_SESSION = BIT(0), TPM2_SA_AUDIT_EXCLUSIVE = BIT(1), @@ -437,8 +422,6 @@ u8 tpm_buf_read_u8(struct tpm_buf *buf, off_t *offset); u16 tpm_buf_read_u16(struct tpm_buf *buf, off_t *offset); u32 tpm_buf_read_u32(struct tpm_buf *buf, off_t *offset); -u8 *tpm_buf_parameters(struct tpm_buf *buf); - /* * Check if TPM device is in the firmware upgrade mode. */ diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index 6d1c8541183d..3a9001a042a5 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -24,7 +24,7 @@ struct dst_ops { void (*destroy)(struct dst_entry *); void (*ifdown)(struct dst_entry *, struct net_device *dev); - struct dst_entry * (*negative_advice)(struct dst_entry *); + void (*negative_advice)(struct sock *sk, struct dst_entry *); void (*link_failure)(struct sk_buff *); void (*update_pmtu)(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index b088d131aeb0..7e8477057f3d 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -45,16 +45,17 @@ struct pp_alloc_cache { /** * struct page_pool_params - page pool parameters + * @fast: params accessed frequently on hotpath * @order: 2^order pages on allocation * @pool_size: size of the ptr_ring * @nid: NUMA node id to allocate from pages from * @dev: device, for DMA pre-mapping purposes - * @netdev: netdev this pool will serve (leave as NULL if none or multiple) * @napi: NAPI which is the sole consumer of pages, otherwise NULL * @dma_dir: DMA mapping direction * @max_len: max DMA sync memory size for PP_FLAG_DMA_SYNC_DEV * @offset: DMA sync address offset for PP_FLAG_DMA_SYNC_DEV - * @netdev: corresponding &net_device for Netlink introspection + * @slow: params with slowpath access only (initialization and Netlink) + * @netdev: netdev this pool will serve (leave as NULL if none or multiple) * @flags: PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV, PP_FLAG_SYSTEM_POOL */ struct page_pool_params { diff --git a/include/net/request_sock.h b/include/net/request_sock.h index d88c0dfc2d46..ebcb8896bffc 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -285,4 +285,16 @@ static inline int reqsk_queue_len_young(const struct request_sock_queue *queue) return atomic_read(&queue->young); } +/* RFC 7323 2.3 Using the Window Scale Option + * The window field (SEG.WND) of every outgoing segment, with the + * exception of <SYN> segments, MUST be right-shifted by + * Rcv.Wind.Shift bits. + * + * This means the SEG.WND carried in SYNACK can not exceed 65535. + * We use this property to harden TCP stack while in NEW_SYN_RECV state. + */ +static inline u32 tcp_synack_window(const struct request_sock *req) +{ + return min(req->rsk_rcv_wnd, 65535U); +} #endif /* _REQUEST_SOCK_H */ diff --git a/include/net/sock.h b/include/net/sock.h index 5f4d0629348f..953c8dc4e259 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2063,17 +2063,10 @@ sk_dst_get(const struct sock *sk) static inline void __dst_negative_advice(struct sock *sk) { - struct dst_entry *ndst, *dst = __sk_dst_get(sk); + struct dst_entry *dst = __sk_dst_get(sk); - if (dst && dst->ops->negative_advice) { - ndst = dst->ops->negative_advice(dst); - - if (ndst != dst) { - rcu_assign_pointer(sk->sk_dst_cache, ndst); - sk_tx_queue_clear(sk); - WRITE_ONCE(sk->sk_dst_pending_confirm, 0); - } - } + if (dst && dst->ops->negative_advice) + dst->ops->negative_advice(sk, dst); } static inline void dst_negative_advice(struct sock *sk) diff --git a/include/sound/tas2781-dsp.h b/include/sound/tas2781-dsp.h index ea9af2726a53..7fba7ea26a4b 100644 --- a/include/sound/tas2781-dsp.h +++ b/include/sound/tas2781-dsp.h @@ -2,7 +2,7 @@ // // ALSA SoC Texas Instruments TAS2781 Audio Smart Amplifier // -// Copyright (C) 2022 - 2023 Texas Instruments Incorporated +// Copyright (C) 2022 - 2024 Texas Instruments Incorporated // https://www.ti.com // // The TAS2781 driver implements a flexible and configurable @@ -13,8 +13,8 @@ // Author: Kevin Lu <kevin-lu@ti.com> // -#ifndef __TASDEVICE_DSP_H__ -#define __TASDEVICE_DSP_H__ +#ifndef __TAS2781_DSP_H__ +#define __TAS2781_DSP_H__ #define MAIN_ALL_DEVICES 0x0d #define MAIN_DEVICE_A 0x01 @@ -180,7 +180,6 @@ void tasdevice_calbin_remove(void *context); int tasdevice_select_tuningprm_cfg(void *context, int prm, int cfg_no, int rca_conf_no); int tasdevice_prmg_load(void *context, int prm_no); -int tasdevice_prmg_calibdata_load(void *context, int prm_no); void tasdevice_tuning_switch(void *context, int state); int tas2781_load_calibration(void *context, char *file_name, unsigned short i); diff --git a/include/trace/events/nbd.h b/include/trace/events/nbd.h index 9849956f34d8..390d98a05c9d 100644 --- a/include/trace/events/nbd.h +++ b/include/trace/events/nbd.h @@ -72,7 +72,7 @@ DECLARE_EVENT_CLASS(nbd_send_request, ), TP_fast_assign( - __entry->nbd_request = 0; + __entry->nbd_request = NULL; __entry->dev_index = index; __entry->request = rq; ), diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 75f00965ab15..d983c48a3b6a 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -842,8 +842,11 @@ __SYSCALL(__NR_lsm_set_self_attr, sys_lsm_set_self_attr) #define __NR_lsm_list_modules 461 __SYSCALL(__NR_lsm_list_modules, sys_lsm_list_modules) +#define __NR_mseal 462 +__SYSCALL(__NR_mseal, sys_mseal) + #undef __NR_syscalls -#define __NR_syscalls 462 +#define __NR_syscalls 463 /* * 32 bit systems traditionally used different diff --git a/include/uapi/drm/nouveau_drm.h b/include/uapi/drm/nouveau_drm.h index 8ad8d1cd1566..dd87f8f30793 100644 --- a/include/uapi/drm/nouveau_drm.h +++ b/include/uapi/drm/nouveau_drm.h @@ -68,6 +68,13 @@ extern "C" { */ #define NOUVEAU_GETPARAM_VRAM_USED 19 +/* + * NOUVEAU_GETPARAM_HAS_VMA_TILEMODE + * + * Query whether tile mode and PTE kind are accepted with VM allocs or not. + */ +#define NOUVEAU_GETPARAM_HAS_VMA_TILEMODE 20 + struct drm_nouveau_getparam { __u64 param; __u64 value; diff --git a/include/uapi/drm/panthor_drm.h b/include/uapi/drm/panthor_drm.h index dadb05ab1235..aaed8e12ad0b 100644 --- a/include/uapi/drm/panthor_drm.h +++ b/include/uapi/drm/panthor_drm.h @@ -895,13 +895,21 @@ struct drm_panthor_tiler_heap_create { /** @vm_id: VM ID the tiler heap should be mapped to */ __u32 vm_id; - /** @initial_chunk_count: Initial number of chunks to allocate. */ + /** @initial_chunk_count: Initial number of chunks to allocate. Must be at least one. */ __u32 initial_chunk_count; - /** @chunk_size: Chunk size. Must be a power of two at least 256KB large. */ + /** + * @chunk_size: Chunk size. + * + * Must be page-aligned and lie in the [128k:8M] range. + */ __u32 chunk_size; - /** @max_chunks: Maximum number of chunks that can be allocated. */ + /** + * @max_chunks: Maximum number of chunks that can be allocated. + * + * Must be at least @initial_chunk_count. + */ __u32 max_chunks; /** @@ -931,7 +939,11 @@ struct drm_panthor_tiler_heap_create { * struct drm_panthor_tiler_heap_destroy - Arguments passed to DRM_IOCTL_PANTHOR_TILER_HEAP_DESTROY */ struct drm_panthor_tiler_heap_destroy { - /** @handle: Handle of the tiler heap to destroy */ + /** + * @handle: Handle of the tiler heap to destroy. + * + * Must be a valid heap handle returned by DRM_IOCTL_PANTHOR_TILER_HEAP_CREATE. + */ __u32 handle; /** @pad: Padding field, MBZ. */ diff --git a/include/uapi/linux/cn_proc.h b/include/uapi/linux/cn_proc.h index f2afb7cc4926..18e3745b86cd 100644 --- a/include/uapi/linux/cn_proc.h +++ b/include/uapi/linux/cn_proc.h @@ -69,8 +69,7 @@ struct proc_input { static inline enum proc_cn_event valid_event(enum proc_cn_event ev_type) { - ev_type &= PROC_EVENT_ALL; - return ev_type; + return (enum proc_cn_event)(ev_type & PROC_EVENT_ALL); } /* diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index a8188202413e..43742ac5b00d 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -148,6 +148,7 @@ enum { NETDEV_A_QSTATS_RX_ALLOC_FAIL, NETDEV_A_QSTATS_RX_HW_DROPS, NETDEV_A_QSTATS_RX_HW_DROP_OVERRUNS, + NETDEV_A_QSTATS_RX_CSUM_COMPLETE, NETDEV_A_QSTATS_RX_CSUM_UNNECESSARY, NETDEV_A_QSTATS_RX_CSUM_NONE, NETDEV_A_QSTATS_RX_CSUM_BAD, diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 86fd72f6a1c2..816e93e7f949 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2597,13 +2597,11 @@ static unsigned long rings_size(struct io_ring_ctx *ctx, unsigned int sq_entries #endif if (ctx->flags & IORING_SETUP_NO_SQARRAY) { - if (sq_offset) - *sq_offset = SIZE_MAX; + *sq_offset = SIZE_MAX; return off; } - if (sq_offset) - *sq_offset = off; + *sq_offset = off; sq_array_size = array_size(sizeof(u32), sq_entries); if (sq_array_size == SIZE_MAX) diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c index 554c7212aa46..b3722e5275e7 100644 --- a/io_uring/sqpoll.c +++ b/io_uring/sqpoll.c @@ -238,11 +238,13 @@ static unsigned int io_sq_tw(struct llist_node **retry_list, int max_entries) if (*retry_list) { *retry_list = io_handle_tw_list(*retry_list, &count, max_entries); if (count >= max_entries) - return count; + goto out; max_entries -= count; } - *retry_list = tctx_task_work_run(tctx, max_entries, &count); +out: + if (task_work_pending(current)) + task_work_run(); return count; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 77da1f438bec..48f3a9acdef3 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8882,7 +8882,8 @@ static bool may_update_sockmap(struct bpf_verifier_env *env, int func_id) enum bpf_attach_type eatype = env->prog->expected_attach_type; enum bpf_prog_type type = resolve_prog_type(env->prog); - if (func_id != BPF_FUNC_map_update_elem) + if (func_id != BPF_FUNC_map_update_elem && + func_id != BPF_FUNC_map_delete_elem) return false; /* It's not possible to get access to a locked struct sock in these @@ -8893,6 +8894,11 @@ static bool may_update_sockmap(struct bpf_verifier_env *env, int func_id) if (eatype == BPF_TRACE_ITER) return true; break; + case BPF_PROG_TYPE_SOCK_OPS: + /* map_update allowed only via dedicated helpers with event type checks */ + if (func_id == BPF_FUNC_map_delete_elem) + return true; + break; case BPF_PROG_TYPE_SOCKET_FILTER: case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_SCHED_ACT: @@ -8988,7 +8994,6 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, case BPF_MAP_TYPE_SOCKMAP: if (func_id != BPF_FUNC_sk_redirect_map && func_id != BPF_FUNC_sock_map_update && - func_id != BPF_FUNC_map_delete_elem && func_id != BPF_FUNC_msg_redirect_map && func_id != BPF_FUNC_sk_select_reuseport && func_id != BPF_FUNC_map_lookup_elem && @@ -8998,7 +9003,6 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, case BPF_MAP_TYPE_SOCKHASH: if (func_id != BPF_FUNC_sk_redirect_hash && func_id != BPF_FUNC_sock_hash_update && - func_id != BPF_FUNC_map_delete_elem && func_id != BPF_FUNC_msg_redirect_hash && func_id != BPF_FUNC_sk_select_reuseport && func_id != BPF_FUNC_map_lookup_elem && diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c index 75cadbc3c232..eb8628390156 100644 --- a/kernel/irq/cpuhotplug.c +++ b/kernel/irq/cpuhotplug.c @@ -70,6 +70,14 @@ static bool migrate_one_irq(struct irq_desc *desc) } /* + * Complete an eventually pending irq move cleanup. If this + * interrupt was moved in hard irq context, then the vectors need + * to be cleaned up. It can't wait until this interrupt actually + * happens and this CPU was involved. + */ + irq_force_complete_move(desc); + + /* * No move required, if: * - Interrupt is per cpu * - Interrupt is not started @@ -88,14 +96,6 @@ static bool migrate_one_irq(struct irq_desc *desc) } /* - * Complete an eventually pending irq move cleanup. If this - * interrupt was moved in hard irq context, then the vectors need - * to be cleaned up. It can't wait until this interrupt actually - * happens and this CPU was involved. - */ - irq_force_complete_move(desc); - - /* * If there is a setaffinity pending, then try to reuse the pending * mask, so the last change of the affinity does not get lost. If * there is no move pending or the pending mask does not contain diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 88ac3652fcf2..07e99c936ba5 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -160,7 +160,10 @@ static int irq_find_free_area(unsigned int from, unsigned int cnt) static unsigned int irq_find_at_or_after(unsigned int offset) { unsigned long index = offset; - struct irq_desc *desc = mt_find(&sparse_irqs, &index, nr_irqs); + struct irq_desc *desc; + + guard(rcu)(); + desc = mt_find(&sparse_irqs, &index, nr_irqs); return desc ? irq_desc_get_irq(desc) : nr_irqs; } diff --git a/kernel/power/swap.c b/kernel/power/swap.c index d9abb7ab031d..753b8dd42a59 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -1595,7 +1595,7 @@ int swsusp_check(bool exclusive) put: if (error) - fput(hib_resume_bdev_file); + bdev_fput(hib_resume_bdev_file); else pr_debug("Image signature found, resuming\n"); } else { diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index faad00cce269..d7eee421d4bc 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -196,6 +196,7 @@ COND_SYSCALL(migrate_pages); COND_SYSCALL(move_pages); COND_SYSCALL(set_mempolicy_home_node); COND_SYSCALL(cachestat); +COND_SYSCALL(mseal); COND_SYSCALL(perf_event_open); COND_SYSCALL(accept4); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index f5154c051d2c..6249dac61701 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -3295,7 +3295,7 @@ static int uprobe_prog_run(struct bpf_uprobe *uprobe, struct bpf_run_ctx *old_run_ctx; int err = 0; - if (link->task && current != link->task) + if (link->task && current->mm != link->task->mm) return 0; if (sleepable) @@ -3396,8 +3396,9 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr upath = u64_to_user_ptr(attr->link_create.uprobe_multi.path); uoffsets = u64_to_user_ptr(attr->link_create.uprobe_multi.offsets); cnt = attr->link_create.uprobe_multi.cnt; + pid = attr->link_create.uprobe_multi.pid; - if (!upath || !uoffsets || !cnt) + if (!upath || !uoffsets || !cnt || pid < 0) return -EINVAL; if (cnt > MAX_UPROBE_MULTI_CNT) return -E2BIG; @@ -3421,11 +3422,8 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr goto error_path_put; } - pid = attr->link_create.uprobe_multi.pid; if (pid) { - rcu_read_lock(); - task = get_pid_task(find_vpid(pid), PIDTYPE_PID); - rcu_read_unlock(); + task = get_pid_task(find_vpid(pid), PIDTYPE_TGID); if (!task) { err = -ESRCH; goto error_path_put; diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 5e263c141574..39877c80d6cb 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -554,6 +554,10 @@ static int parse_btf_field(char *fieldname, const struct btf_type *type, anon_offs = 0; field = btf_find_struct_member(ctx->btf, type, fieldname, &anon_offs); + if (IS_ERR(field)) { + trace_probe_log_err(ctx->offset, BAD_BTF_TID); + return PTR_ERR(field); + } if (!field) { trace_probe_log_err(ctx->offset, NO_BTF_FIELD); return -ENOENT; diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 8541fa1494ae..c98e3b3386ba 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -970,19 +970,17 @@ static struct uprobe_cpu_buffer *prepare_uprobe_buffer(struct trace_uprobe *tu, static void __uprobe_trace_func(struct trace_uprobe *tu, unsigned long func, struct pt_regs *regs, - struct uprobe_cpu_buffer **ucbp, + struct uprobe_cpu_buffer *ucb, struct trace_event_file *trace_file) { struct uprobe_trace_entry_head *entry; struct trace_event_buffer fbuffer; - struct uprobe_cpu_buffer *ucb; void *data; int size, esize; struct trace_event_call *call = trace_probe_event_call(&tu->tp); WARN_ON(call != trace_file->event_call); - ucb = prepare_uprobe_buffer(tu, regs, ucbp); if (WARN_ON_ONCE(ucb->dsize > PAGE_SIZE)) return; @@ -1014,13 +1012,16 @@ static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs, struct uprobe_cpu_buffer **ucbp) { struct event_file_link *link; + struct uprobe_cpu_buffer *ucb; if (is_ret_probe(tu)) return 0; + ucb = prepare_uprobe_buffer(tu, regs, ucbp); + rcu_read_lock(); trace_probe_for_each_link_rcu(link, &tu->tp) - __uprobe_trace_func(tu, 0, regs, ucbp, link->file); + __uprobe_trace_func(tu, 0, regs, ucb, link->file); rcu_read_unlock(); return 0; @@ -1031,10 +1032,13 @@ static void uretprobe_trace_func(struct trace_uprobe *tu, unsigned long func, struct uprobe_cpu_buffer **ucbp) { struct event_file_link *link; + struct uprobe_cpu_buffer *ucb; + + ucb = prepare_uprobe_buffer(tu, regs, ucbp); rcu_read_lock(); trace_probe_for_each_link_rcu(link, &tu->tp) - __uprobe_trace_func(tu, func, regs, ucbp, link->file); + __uprobe_trace_func(tu, func, regs, ucb, link->file); rcu_read_unlock(); } diff --git a/lib/Kconfig.ubsan b/lib/Kconfig.ubsan index e81e1ac4a919..bdda600f8dfb 100644 --- a/lib/Kconfig.ubsan +++ b/lib/Kconfig.ubsan @@ -4,6 +4,7 @@ config ARCH_HAS_UBSAN menuconfig UBSAN bool "Undefined behaviour sanity checker" + depends on ARCH_HAS_UBSAN help This option enables the Undefined Behaviour sanity checker. Compile-time instrumentation is used to detect various undefined diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c index 531dbe2f5456..11ed973ac359 100644 --- a/lib/alloc_tag.c +++ b/lib/alloc_tag.c @@ -16,47 +16,60 @@ EXPORT_SYMBOL(_shared_alloc_tag); DEFINE_STATIC_KEY_MAYBE(CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT, mem_alloc_profiling_key); +struct allocinfo_private { + struct codetag_iterator iter; + bool print_header; +}; + static void *allocinfo_start(struct seq_file *m, loff_t *pos) { - struct codetag_iterator *iter; + struct allocinfo_private *priv; struct codetag *ct; loff_t node = *pos; - iter = kzalloc(sizeof(*iter), GFP_KERNEL); - m->private = iter; - if (!iter) + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + m->private = priv; + if (!priv) return NULL; + priv->print_header = (node == 0); codetag_lock_module_list(alloc_tag_cttype, true); - *iter = codetag_get_ct_iter(alloc_tag_cttype); - while ((ct = codetag_next_ct(iter)) != NULL && node) + priv->iter = codetag_get_ct_iter(alloc_tag_cttype); + while ((ct = codetag_next_ct(&priv->iter)) != NULL && node) node--; - return ct ? iter : NULL; + return ct ? priv : NULL; } static void *allocinfo_next(struct seq_file *m, void *arg, loff_t *pos) { - struct codetag_iterator *iter = (struct codetag_iterator *)arg; - struct codetag *ct = codetag_next_ct(iter); + struct allocinfo_private *priv = (struct allocinfo_private *)arg; + struct codetag *ct = codetag_next_ct(&priv->iter); (*pos)++; if (!ct) return NULL; - return iter; + return priv; } static void allocinfo_stop(struct seq_file *m, void *arg) { - struct codetag_iterator *iter = (struct codetag_iterator *)m->private; + struct allocinfo_private *priv = (struct allocinfo_private *)m->private; - if (iter) { + if (priv) { codetag_lock_module_list(alloc_tag_cttype, false); - kfree(iter); + kfree(priv); } } +static void print_allocinfo_header(struct seq_buf *buf) +{ + /* Output format version, so we can change it. */ + seq_buf_printf(buf, "allocinfo - version: 1.0\n"); + seq_buf_printf(buf, "# <size> <calls> <tag info>\n"); +} + static void alloc_tag_to_text(struct seq_buf *out, struct codetag *ct) { struct alloc_tag *tag = ct_to_alloc_tag(ct); @@ -71,13 +84,17 @@ static void alloc_tag_to_text(struct seq_buf *out, struct codetag *ct) static int allocinfo_show(struct seq_file *m, void *arg) { - struct codetag_iterator *iter = (struct codetag_iterator *)arg; + struct allocinfo_private *priv = (struct allocinfo_private *)arg; char *bufp; size_t n = seq_get_buf(m, &bufp); struct seq_buf buf; seq_buf_init(&buf, bufp, n); - alloc_tag_to_text(&buf, iter->ct); + if (priv->print_header) { + print_allocinfo_header(&buf); + priv->print_header = false; + } + alloc_tag_to_text(&buf, priv->iter.ct); seq_commit(m, seq_buf_used(&buf)); return 0; } diff --git a/lib/fortify_kunit.c b/lib/fortify_kunit.c index d2377e00caab..39da5b3bc649 100644 --- a/lib/fortify_kunit.c +++ b/lib/fortify_kunit.c @@ -990,7 +990,7 @@ static void fortify_test_memcmp(struct kunit *test) KUNIT_ASSERT_EQ(test, memcmp(one, two, one_len), 0); KUNIT_EXPECT_EQ(test, fortify_read_overflows, 0); /* Still in bounds, but no longer matching. */ - KUNIT_ASSERT_EQ(test, memcmp(one, two, one_len + 1), -32); + KUNIT_ASSERT_LT(test, memcmp(one, two, one_len + 1), 0); KUNIT_EXPECT_EQ(test, fortify_read_overflows, 0); /* Catch too-large ranges. */ diff --git a/mm/Makefile b/mm/Makefile index 85f29ef7bedd..8fb85acda1b1 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -43,6 +43,10 @@ ifdef CONFIG_CROSS_MEMORY_ATTACH mmu-$(CONFIG_MMU) += process_vm_access.o endif +ifdef CONFIG_64BIT +mmu-$(CONFIG_MMU) += mseal.o +endif + obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ maccess.o page-writeback.o folio-compat.o \ readahead.o swap.o truncate.o vmscan.o shrinker.o \ diff --git a/mm/internal.h b/mm/internal.h index 2adabe369403..b2c75b12014e 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -1435,6 +1435,43 @@ void __meminit __init_single_page(struct page *page, unsigned long pfn, unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority); +#ifdef CONFIG_64BIT +/* VM is sealed, in vm_flags */ +#define VM_SEALED _BITUL(63) +#endif + +#ifdef CONFIG_64BIT +static inline int can_do_mseal(unsigned long flags) +{ + if (flags) + return -EINVAL; + + return 0; +} + +bool can_modify_mm(struct mm_struct *mm, unsigned long start, + unsigned long end); +bool can_modify_mm_madv(struct mm_struct *mm, unsigned long start, + unsigned long end, int behavior); +#else +static inline int can_do_mseal(unsigned long flags) +{ + return -EPERM; +} + +static inline bool can_modify_mm(struct mm_struct *mm, unsigned long start, + unsigned long end) +{ + return true; +} + +static inline bool can_modify_mm_madv(struct mm_struct *mm, unsigned long start, + unsigned long end, int behavior) +{ + return true; +} +#endif + #ifdef CONFIG_SHRINKER_DEBUG static inline __printf(2, 0) int shrinker_debugfs_name_alloc( struct shrinker *shrinker, const char *fmt, va_list ap) @@ -2153,7 +2153,6 @@ again: INIT_HLIST_HEAD(&stable_node_dup->hlist); stable_node_dup->kpfn = kpfn; - folio_set_stable_node(kfolio, stable_node_dup); stable_node_dup->rmap_hlist_len = 0; DO_NUMA(stable_node_dup->nid = nid); if (!need_chain) { @@ -2172,6 +2171,8 @@ again: stable_node_chain_add_dup(stable_node_dup, stable_node); } + folio_set_stable_node(kfolio, stable_node_dup); + return stable_node_dup; } diff --git a/mm/madvise.c b/mm/madvise.c index c8ba3f3eb54d..a77893462b92 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -1401,6 +1401,7 @@ int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, * -EIO - an I/O error occurred while paging in data. * -EBADF - map exists, but area maps something that isn't a file. * -EAGAIN - a kernel resource was temporarily unavailable. + * -EPERM - memory is sealed. */ int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior) { @@ -1444,6 +1445,15 @@ int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int beh start = untagged_addr_remote(mm, start); end = start + len; + /* + * Check if the address range is sealed for do_madvise(). + * can_modify_mm_madv assumes we have acquired the lock on MM. + */ + if (unlikely(!can_modify_mm_madv(mm, start, end, behavior))) { + error = -EPERM; + goto out; + } + blk_start_plug(&plug); switch (behavior) { case MADV_POPULATE_READ: @@ -1456,6 +1466,8 @@ int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int beh break; } blk_finish_plug(&plug); + +out: if (write) mmap_write_unlock(mm); else diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 16ada4fb02b7..d3c830e817e3 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1221,7 +1221,7 @@ static int me_huge_page(struct page_state *ps, struct page *p) * subpages. */ folio_put(folio); - if (__page_handle_poison(p) >= 0) { + if (__page_handle_poison(p) > 0) { page_ref_inc(p); res = MF_RECOVERED; } else { @@ -2091,7 +2091,7 @@ retry: */ if (res == 0) { folio_unlock(folio); - if (__page_handle_poison(p) >= 0) { + if (__page_handle_poison(p) > 0) { page_ref_inc(p); res = MF_RECOVERED; } else { @@ -2546,6 +2546,13 @@ int unpoison_memory(unsigned long pfn) goto unlock_mutex; } + if (is_huge_zero_folio(folio)) { + unpoison_pr_info("Unpoison: huge zero page is not supported %#lx\n", + pfn, &unpoison_rs); + ret = -EOPNOTSUPP; + goto unlock_mutex; + } + if (!PageHWPoison(p)) { unpoison_pr_info("Unpoison: Page was already unpoisoned %#lx\n", pfn, &unpoison_rs); diff --git a/mm/mmap.c b/mm/mmap.c index d6d8ab119b72..83b4682ec85c 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1255,6 +1255,16 @@ unsigned long do_mmap(struct file *file, unsigned long addr, if (mm->map_count > sysctl_max_map_count) return -ENOMEM; + /* + * addr is returned from get_unmapped_area, + * There are two cases: + * 1> MAP_FIXED == false + * unallocated memory, no need to check sealing. + * 1> MAP_FIXED == true + * sealing is checked inside mmap_region when + * do_vmi_munmap is called. + */ + if (prot == PROT_EXEC) { pkey = execute_only_pkey(mm); if (pkey < 0) @@ -2727,6 +2737,14 @@ int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm, if (end == start) return -EINVAL; + /* + * Check if memory is sealed before arch_unmap. + * Prevent unmapping a sealed VMA. + * can_modify_mm assumes we have acquired the lock on MM. + */ + if (unlikely(!can_modify_mm(mm, start, end))) + return -EPERM; + /* arch_unmap() might do unmaps itself. */ arch_unmap(mm, start, end); @@ -2789,7 +2807,10 @@ unsigned long mmap_region(struct file *file, unsigned long addr, } /* Unmap any existing mapping in the area */ - if (do_vmi_munmap(&vmi, mm, addr, len, uf, false)) + error = do_vmi_munmap(&vmi, mm, addr, len, uf, false); + if (error == -EPERM) + return error; + else if (error) return -ENOMEM; /* @@ -3139,6 +3160,14 @@ int do_vma_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, { struct mm_struct *mm = vma->vm_mm; + /* + * Check if memory is sealed before arch_unmap. + * Prevent unmapping a sealed VMA. + * can_modify_mm assumes we have acquired the lock on MM. + */ + if (unlikely(!can_modify_mm(mm, start, end))) + return -EPERM; + arch_unmap(mm, start, end); return do_vmi_align_munmap(vmi, vma, mm, start, end, uf, unlock); } diff --git a/mm/mprotect.c b/mm/mprotect.c index 94878c39ee32..8c6cd8825273 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -32,6 +32,7 @@ #include <linux/sched/sysctl.h> #include <linux/userfaultfd_k.h> #include <linux/memory-tiers.h> +#include <uapi/linux/mman.h> #include <asm/cacheflush.h> #include <asm/mmu_context.h> #include <asm/tlbflush.h> @@ -744,6 +745,15 @@ static int do_mprotect_pkey(unsigned long start, size_t len, } } + /* + * checking if memory is sealed. + * can_modify_mm assumes we have acquired the lock on MM. + */ + if (unlikely(!can_modify_mm(current->mm, start, end))) { + error = -EPERM; + goto out; + } + prev = vma_prev(&vmi); if (start > vma->vm_start) prev = vma; diff --git a/mm/mremap.c b/mm/mremap.c index f5aba752d35f..5f96bc5ee918 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -902,7 +902,25 @@ static unsigned long mremap_to(unsigned long addr, unsigned long old_len, if ((mm->map_count + 2) >= sysctl_max_map_count - 3) return -ENOMEM; + /* + * In mremap_to(). + * Move a VMA to another location, check if src addr is sealed. + * + * Place can_modify_mm here because mremap_to() + * does its own checking for address range, and we only + * check the sealing after passing those checks. + * + * can_modify_mm assumes we have acquired the lock on MM. + */ + if (unlikely(!can_modify_mm(mm, addr, addr + old_len))) + return -EPERM; + if (flags & MREMAP_FIXED) { + /* + * In mremap_to(). + * VMA is moved to dst address, and munmap dst first. + * do_munmap will check if dst is sealed. + */ ret = do_munmap(mm, new_addr, new_len, uf_unmap_early); if (ret) goto out; @@ -1062,6 +1080,19 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, } /* + * Below is shrink/expand case (not mremap_to()) + * Check if src address is sealed, if so, reject. + * In other words, prevent shrinking or expanding a sealed VMA. + * + * Place can_modify_mm here so we can keep the logic related to + * shrink/expand together. + */ + if (unlikely(!can_modify_mm(mm, addr, addr + old_len))) { + ret = -EPERM; + goto out; + } + + /* * Always allow a shrinking remap: that just unmaps * the unnecessary pages.. * do_vmi_munmap does all the needed commit accounting, and diff --git a/mm/mseal.c b/mm/mseal.c new file mode 100644 index 000000000000..bf783bba8ed0 --- /dev/null +++ b/mm/mseal.c @@ -0,0 +1,307 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Implement mseal() syscall. + * + * Copyright (c) 2023,2024 Google, Inc. + * + * Author: Jeff Xu <jeffxu@chromium.org> + */ + +#include <linux/mempolicy.h> +#include <linux/mman.h> +#include <linux/mm.h> +#include <linux/mm_inline.h> +#include <linux/mmu_context.h> +#include <linux/syscalls.h> +#include <linux/sched.h> +#include "internal.h" + +static inline bool vma_is_sealed(struct vm_area_struct *vma) +{ + return (vma->vm_flags & VM_SEALED); +} + +static inline void set_vma_sealed(struct vm_area_struct *vma) +{ + vm_flags_set(vma, VM_SEALED); +} + +/* + * check if a vma is sealed for modification. + * return true, if modification is allowed. + */ +static bool can_modify_vma(struct vm_area_struct *vma) +{ + if (unlikely(vma_is_sealed(vma))) + return false; + + return true; +} + +static bool is_madv_discard(int behavior) +{ + return behavior & + (MADV_FREE | MADV_DONTNEED | MADV_DONTNEED_LOCKED | + MADV_REMOVE | MADV_DONTFORK | MADV_WIPEONFORK); +} + +static bool is_ro_anon(struct vm_area_struct *vma) +{ + /* check anonymous mapping. */ + if (vma->vm_file || vma->vm_flags & VM_SHARED) + return false; + + /* + * check for non-writable: + * PROT=RO or PKRU is not writeable. + */ + if (!(vma->vm_flags & VM_WRITE) || + !arch_vma_access_permitted(vma, true, false, false)) + return true; + + return false; +} + +/* + * Check if the vmas of a memory range are allowed to be modified. + * the memory ranger can have a gap (unallocated memory). + * return true, if it is allowed. + */ +bool can_modify_mm(struct mm_struct *mm, unsigned long start, unsigned long end) +{ + struct vm_area_struct *vma; + + VMA_ITERATOR(vmi, mm, start); + + /* going through each vma to check. */ + for_each_vma_range(vmi, vma, end) { + if (unlikely(!can_modify_vma(vma))) + return false; + } + + /* Allow by default. */ + return true; +} + +/* + * Check if the vmas of a memory range are allowed to be modified by madvise. + * the memory ranger can have a gap (unallocated memory). + * return true, if it is allowed. + */ +bool can_modify_mm_madv(struct mm_struct *mm, unsigned long start, unsigned long end, + int behavior) +{ + struct vm_area_struct *vma; + + VMA_ITERATOR(vmi, mm, start); + + if (!is_madv_discard(behavior)) + return true; + + /* going through each vma to check. */ + for_each_vma_range(vmi, vma, end) + if (unlikely(is_ro_anon(vma) && !can_modify_vma(vma))) + return false; + + /* Allow by default. */ + return true; +} + +static int mseal_fixup(struct vma_iterator *vmi, struct vm_area_struct *vma, + struct vm_area_struct **prev, unsigned long start, + unsigned long end, vm_flags_t newflags) +{ + int ret = 0; + vm_flags_t oldflags = vma->vm_flags; + + if (newflags == oldflags) + goto out; + + vma = vma_modify_flags(vmi, *prev, vma, start, end, newflags); + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); + goto out; + } + + set_vma_sealed(vma); +out: + *prev = vma; + return ret; +} + +/* + * Check for do_mseal: + * 1> start is part of a valid vma. + * 2> end is part of a valid vma. + * 3> No gap (unallocated address) between start and end. + * 4> map is sealable. + */ +static int check_mm_seal(unsigned long start, unsigned long end) +{ + struct vm_area_struct *vma; + unsigned long nstart = start; + + VMA_ITERATOR(vmi, current->mm, start); + + /* going through each vma to check. */ + for_each_vma_range(vmi, vma, end) { + if (vma->vm_start > nstart) + /* unallocated memory found. */ + return -ENOMEM; + + if (vma->vm_end >= end) + return 0; + + nstart = vma->vm_end; + } + + return -ENOMEM; +} + +/* + * Apply sealing. + */ +static int apply_mm_seal(unsigned long start, unsigned long end) +{ + unsigned long nstart; + struct vm_area_struct *vma, *prev; + + VMA_ITERATOR(vmi, current->mm, start); + + vma = vma_iter_load(&vmi); + /* + * Note: check_mm_seal should already checked ENOMEM case. + * so vma should not be null, same for the other ENOMEM cases. + */ + prev = vma_prev(&vmi); + if (start > vma->vm_start) + prev = vma; + + nstart = start; + for_each_vma_range(vmi, vma, end) { + int error; + unsigned long tmp; + vm_flags_t newflags; + + newflags = vma->vm_flags | VM_SEALED; + tmp = vma->vm_end; + if (tmp > end) + tmp = end; + error = mseal_fixup(&vmi, vma, &prev, nstart, tmp, newflags); + if (error) + return error; + nstart = vma_iter_end(&vmi); + } + + return 0; +} + +/* + * mseal(2) seals the VM's meta data from + * selected syscalls. + * + * addr/len: VM address range. + * + * The address range by addr/len must meet: + * start (addr) must be in a valid VMA. + * end (addr + len) must be in a valid VMA. + * no gap (unallocated memory) between start and end. + * start (addr) must be page aligned. + * + * len: len will be page aligned implicitly. + * + * Below VMA operations are blocked after sealing. + * 1> Unmapping, moving to another location, and shrinking + * the size, via munmap() and mremap(), can leave an empty + * space, therefore can be replaced with a VMA with a new + * set of attributes. + * 2> Moving or expanding a different vma into the current location, + * via mremap(). + * 3> Modifying a VMA via mmap(MAP_FIXED). + * 4> Size expansion, via mremap(), does not appear to pose any + * specific risks to sealed VMAs. It is included anyway because + * the use case is unclear. In any case, users can rely on + * merging to expand a sealed VMA. + * 5> mprotect and pkey_mprotect. + * 6> Some destructive madvice() behavior (e.g. MADV_DONTNEED) + * for anonymous memory, when users don't have write permission to the + * memory. Those behaviors can alter region contents by discarding pages, + * effectively a memset(0) for anonymous memory. + * + * flags: reserved. + * + * return values: + * zero: success. + * -EINVAL: + * invalid input flags. + * start address is not page aligned. + * Address arange (start + len) overflow. + * -ENOMEM: + * addr is not a valid address (not allocated). + * end (start + len) is not a valid address. + * a gap (unallocated memory) between start and end. + * -EPERM: + * - In 32 bit architecture, sealing is not supported. + * Note: + * user can call mseal(2) multiple times, adding a seal on an + * already sealed memory is a no-action (no error). + * + * unseal() is not supported. + */ +static int do_mseal(unsigned long start, size_t len_in, unsigned long flags) +{ + size_t len; + int ret = 0; + unsigned long end; + struct mm_struct *mm = current->mm; + + ret = can_do_mseal(flags); + if (ret) + return ret; + + start = untagged_addr(start); + if (!PAGE_ALIGNED(start)) + return -EINVAL; + + len = PAGE_ALIGN(len_in); + /* Check to see whether len was rounded up from small -ve to zero. */ + if (len_in && !len) + return -EINVAL; + + end = start + len; + if (end < start) + return -EINVAL; + + if (end == start) + return 0; + + if (mmap_write_lock_killable(mm)) + return -EINTR; + + /* + * First pass, this helps to avoid + * partial sealing in case of error in input address range, + * e.g. ENOMEM error. + */ + ret = check_mm_seal(start, end); + if (ret) + goto out; + + /* + * Second pass, this should success, unless there are errors + * from vma_modify_flags, e.g. merge/split error, or process + * reaching the max supported VMAs, however, those cases shall + * be rare. + */ + ret = apply_mm_seal(start, end); + +out: + mmap_write_unlock(current->mm); + return ret; +} + +SYSCALL_DEFINE3(mseal, unsigned long, start, size_t, len, unsigned long, + flags) +{ + return do_mseal(start, len, flags); +} diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 6641be0ca80b..5d3aa2dc88a8 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -3498,7 +3498,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid, { unsigned int nr_allocated = 0; gfp_t alloc_gfp = gfp; - bool nofail = false; + bool nofail = gfp & __GFP_NOFAIL; struct page *page; int i; @@ -3555,12 +3555,11 @@ vm_area_alloc_pages(gfp_t gfp, int nid, * and compaction etc. */ alloc_gfp &= ~__GFP_NOFAIL; - nofail = true; } /* High-order pages or fallback path if "bulk" fails. */ while (nr_allocated < nr_pages) { - if (fatal_signal_pending(current)) + if (!nofail && fatal_signal_pending(current)) break; if (nid == NUMA_NO_NODE) diff --git a/net/9p/client.c b/net/9p/client.c index 00774656eeac..5cd94721d974 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -236,6 +236,8 @@ static int p9_fcall_init(struct p9_client *c, struct p9_fcall *fc, if (!fc->sdata) return -ENOMEM; fc->capacity = alloc_msize; + fc->id = 0; + fc->tag = P9_NOTAG; return 0; } diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 9402889840bf..d3dbb92153f2 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -423,9 +423,6 @@ static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test, struct sock *sk; int err = 0; - if (irqs_disabled()) - return -EOPNOTSUPP; /* locks here are hardirq-unsafe */ - spin_lock_bh(&stab->lock); sk = *psk; if (!sk_test || sk_test == sk) @@ -948,9 +945,6 @@ static long sock_hash_delete_elem(struct bpf_map *map, void *key) struct bpf_shtab_elem *elem; int ret = -ENOENT; - if (irqs_disabled()) - return -EOPNOTSUPP; /* locks here are hardirq-unsafe */ - hash = sock_hash_bucket_hash(key, key_size); bucket = sock_hash_select_bucket(htab, hash); @@ -1680,19 +1674,23 @@ void sock_map_close(struct sock *sk, long timeout) lock_sock(sk); rcu_read_lock(); - psock = sk_psock_get(sk); - if (unlikely(!psock)) { - rcu_read_unlock(); - release_sock(sk); - saved_close = READ_ONCE(sk->sk_prot)->close; - } else { + psock = sk_psock(sk); + if (likely(psock)) { saved_close = psock->saved_close; sock_map_remove_links(sk, psock); + psock = sk_psock_get(sk); + if (unlikely(!psock)) + goto no_psock; rcu_read_unlock(); sk_psock_stop(psock); release_sock(sk); cancel_delayed_work_sync(&psock->work); sk_psock_put(sk, psock); + } else { + saved_close = READ_ONCE(sk->sk_prot)->close; +no_psock: + rcu_read_unlock(); + release_sock(sk); } /* Make sure we do not recurse. This is a bug. diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 049c3adeb850..4e3651101b86 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -161,9 +161,7 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev) skb->dev = dev; skb_reset_mac_header(skb); - eth = (struct ethhdr *)skb->data; - skb_pull_inline(skb, ETH_HLEN); - + eth = eth_skb_pull_mac(skb); eth_skb_pkt_type(skb, dev); /* diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index e03ba4a21c39..b24d74616637 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1532,7 +1532,7 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb) } NAPI_GRO_CB(skb)->flush |= flush; - NAPI_GRO_CB(skb)->inner_network_offset = off; + NAPI_GRO_CB(skb)->network_offsets[NAPI_GRO_CB(skb)->encap_mark] = off; /* Note : No need to call skb_gro_postpull_rcsum() here, * as we already checked checksum over ipv4 header was 0 diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 96accde527da..f3892ee9dfb3 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1887,10 +1887,11 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) goto done; if (fillargs.ifindex) { - err = -ENODEV; dev = dev_get_by_index_rcu(tgt_net, fillargs.ifindex); - if (!dev) + if (!dev) { + err = -ENODEV; goto done; + } in_dev = __in_dev_get_rcu(dev); if (!in_dev) goto done; @@ -1902,7 +1903,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) cb->seq = inet_base_seq(tgt_net); - for_each_netdev_dump(net, dev, ctx->ifindex) { + for_each_netdev_dump(tgt_net, dev, ctx->ifindex) { in_dev = __in_dev_get_rcu(dev); if (!in_dev) continue; diff --git a/net/ipv4/netfilter/nf_tproxy_ipv4.c b/net/ipv4/netfilter/nf_tproxy_ipv4.c index 69e331799604..73e66a088e25 100644 --- a/net/ipv4/netfilter/nf_tproxy_ipv4.c +++ b/net/ipv4/netfilter/nf_tproxy_ipv4.c @@ -58,6 +58,8 @@ __be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr) laddr = 0; indev = __in_dev_get_rcu(skb->dev); + if (!indev) + return daddr; in_dev_for_each_ifa_rcu(ifa, indev) { if (ifa->ifa_flags & IFA_F_SECONDARY) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 5fd54103174f..b3073d1c8f8f 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -129,7 +129,8 @@ struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ipv4_default_advmss(const struct dst_entry *dst); INDIRECT_CALLABLE_SCOPE unsigned int ipv4_mtu(const struct dst_entry *dst); -static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst); +static void ipv4_negative_advice(struct sock *sk, + struct dst_entry *dst); static void ipv4_link_failure(struct sk_buff *skb); static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, @@ -825,22 +826,15 @@ static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buf __ip_do_redirect(rt, skb, &fl4, true); } -static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst) +static void ipv4_negative_advice(struct sock *sk, + struct dst_entry *dst) { struct rtable *rt = dst_rtable(dst); - struct dst_entry *ret = dst; - if (rt) { - if (dst->obsolete > 0) { - ip_rt_put(rt); - ret = NULL; - } else if ((rt->rt_flags & RTCF_REDIRECTED) || - rt->dst.expires) { - ip_rt_put(rt); - ret = NULL; - } - } - return ret; + if ((dst->obsolete > 0) || + (rt->rt_flags & RTCF_REDIRECTED) || + rt->dst.expires) + sk_dst_reset(sk); } /* diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 041c7eda9abe..59d5b064f233 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1139,14 +1139,9 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, #endif } - /* RFC 7323 2.3 - * The window field (SEG.WND) of every outgoing segment, with the - * exception of <SYN> segments, MUST be right-shifted by - * Rcv.Wind.Shift bits: - */ tcp_v4_send_ack(sk, skb, seq, tcp_rsk(req)->rcv_nxt, - req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, + tcp_synack_window(req) >> inet_rsk(req)->rcv_wscale, tcp_rsk_tsval(tcp_rsk(req)), READ_ONCE(req->ts_recent), 0, &key, diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index b93619b2384b..538c06f95918 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -783,8 +783,11 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, /* RFC793: "first check sequence number". */ - if (paws_reject || !tcp_in_window(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq, - tcp_rsk(req)->rcv_nxt, tcp_rsk(req)->rcv_nxt + req->rsk_rcv_wnd)) { + if (paws_reject || !tcp_in_window(TCP_SKB_CB(skb)->seq, + TCP_SKB_CB(skb)->end_seq, + tcp_rsk(req)->rcv_nxt, + tcp_rsk(req)->rcv_nxt + + tcp_synack_window(req))) { /* Out of window: send ACK and drop. */ if (!(flg & TCP_FLAG_RST) && !tcp_oow_rate_limited(sock_net(sk), skb, diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index bd5aff97d8b1..9822163428b0 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -236,7 +236,7 @@ INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head, if (unlikely(!iph)) goto out; - NAPI_GRO_CB(skb)->inner_network_offset = off; + NAPI_GRO_CB(skb)->network_offsets[NAPI_GRO_CB(skb)->encap_mark] = off; flush += ntohs(iph->payload_len) != skb->len - hlen; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index bbc2a0dd9314..a504b88ec06b 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -87,7 +87,8 @@ struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ip6_default_advmss(const struct dst_entry *dst); INDIRECT_CALLABLE_SCOPE unsigned int ip6_mtu(const struct dst_entry *dst); -static struct dst_entry *ip6_negative_advice(struct dst_entry *); +static void ip6_negative_advice(struct sock *sk, + struct dst_entry *dst); static void ip6_dst_destroy(struct dst_entry *); static void ip6_dst_ifdown(struct dst_entry *, struct net_device *dev); @@ -2770,24 +2771,24 @@ INDIRECT_CALLABLE_SCOPE struct dst_entry *ip6_dst_check(struct dst_entry *dst, } EXPORT_INDIRECT_CALLABLE(ip6_dst_check); -static struct dst_entry *ip6_negative_advice(struct dst_entry *dst) +static void ip6_negative_advice(struct sock *sk, + struct dst_entry *dst) { struct rt6_info *rt = dst_rt6_info(dst); - if (rt) { - if (rt->rt6i_flags & RTF_CACHE) { - rcu_read_lock(); - if (rt6_check_expired(rt)) { - rt6_remove_exception_rt(rt); - dst = NULL; - } - rcu_read_unlock(); - } else { - dst_release(dst); - dst = NULL; + if (rt->rt6i_flags & RTF_CACHE) { + rcu_read_lock(); + if (rt6_check_expired(rt)) { + /* counteract the dst_release() in sk_dst_reset() */ + dst_hold(dst); + sk_dst_reset(sk); + + rt6_remove_exception_rt(rt); } + rcu_read_unlock(); + return; } - return dst; + sk_dst_reset(sk); } static void ip6_link_failure(struct sk_buff *skb) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 1ac7502e1bf5..5fe4365de89d 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1268,15 +1268,10 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV * sk->sk_state == TCP_SYN_RECV -> for Fast Open. */ - /* RFC 7323 2.3 - * The window field (SEG.WND) of every outgoing segment, with the - * exception of <SYN> segments, MUST be right-shifted by - * Rcv.Wind.Shift bits: - */ tcp_v6_send_ack(sk, skb, (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, tcp_rsk(req)->rcv_nxt, - req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, + tcp_synack_window(req) >> inet_rsk(req)->rcv_wscale, tcp_rsk_tsval(tcp_rsk(req)), READ_ONCE(req->ts_recent), sk->sk_bound_dev_if, &key, ipv6_get_dsfield(ipv6_hdr(skb)), 0, diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 6c3f28bc59b3..54e2a1dd7f5f 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -549,6 +549,9 @@ list_set_cancel_gc(struct ip_set *set) if (SET_WITH_TIMEOUT(set)) timer_shutdown_sync(&map->gc); + + /* Flush list to drop references to other ipsets */ + list_set_flush(set); } static const struct ip_set_type_variant set_variant = { diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 00f4bd21c59b..f1c31757e496 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -169,7 +169,9 @@ instance_destroy_rcu(struct rcu_head *head) struct nfqnl_instance *inst = container_of(head, struct nfqnl_instance, rcu); + rcu_read_lock(); nfqnl_flush(inst, NULL, 0); + rcu_read_unlock(); kfree(inst); module_put(THIS_MODULE); } diff --git a/net/netfilter/nft_fib.c b/net/netfilter/nft_fib.c index 37cfe6dd712d..b58f62195ff3 100644 --- a/net/netfilter/nft_fib.c +++ b/net/netfilter/nft_fib.c @@ -35,11 +35,9 @@ int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, switch (priv->result) { case NFT_FIB_RESULT_OIF: case NFT_FIB_RESULT_OIFNAME: - hooks = (1 << NF_INET_PRE_ROUTING); - if (priv->flags & NFTA_FIB_F_IIF) { - hooks |= (1 << NF_INET_LOCAL_IN) | - (1 << NF_INET_FORWARD); - } + hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_FORWARD); break; case NFT_FIB_RESULT_ADDRTYPE: if (priv->flags & NFTA_FIB_F_IIF) diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 0a689c8e0295..0c43d748e23a 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -45,36 +45,27 @@ nft_payload_copy_vlan(u32 *d, const struct sk_buff *skb, u8 offset, u8 len) int mac_off = skb_mac_header(skb) - skb->data; u8 *vlanh, *dst_u8 = (u8 *) d; struct vlan_ethhdr veth; - u8 vlan_hlen = 0; - - if ((skb->protocol == htons(ETH_P_8021AD) || - skb->protocol == htons(ETH_P_8021Q)) && - offset >= VLAN_ETH_HLEN && offset < VLAN_ETH_HLEN + VLAN_HLEN) - vlan_hlen += VLAN_HLEN; vlanh = (u8 *) &veth; - if (offset < VLAN_ETH_HLEN + vlan_hlen) { + if (offset < VLAN_ETH_HLEN) { u8 ethlen = len; - if (vlan_hlen && - skb_copy_bits(skb, mac_off, &veth, VLAN_ETH_HLEN) < 0) - return false; - else if (!nft_payload_rebuild_vlan_hdr(skb, mac_off, &veth)) + if (!nft_payload_rebuild_vlan_hdr(skb, mac_off, &veth)) return false; - if (offset + len > VLAN_ETH_HLEN + vlan_hlen) - ethlen -= offset + len - VLAN_ETH_HLEN - vlan_hlen; + if (offset + len > VLAN_ETH_HLEN) + ethlen -= offset + len - VLAN_ETH_HLEN; - memcpy(dst_u8, vlanh + offset - vlan_hlen, ethlen); + memcpy(dst_u8, vlanh + offset, ethlen); len -= ethlen; if (len == 0) return true; dst_u8 += ethlen; - offset = ETH_HLEN + vlan_hlen; + offset = ETH_HLEN; } else { - offset -= VLAN_HLEN + vlan_hlen; + offset -= VLAN_HLEN; } return skb_copy_bits(skb, offset + mac_off, dst_u8, len) == 0; @@ -154,12 +145,12 @@ int nft_payload_inner_offset(const struct nft_pktinfo *pkt) return pkt->inneroff; } -static bool nft_payload_need_vlan_copy(const struct nft_payload *priv) +static bool nft_payload_need_vlan_adjust(u32 offset, u32 len) { - unsigned int len = priv->offset + priv->len; + unsigned int boundary = offset + len; /* data past ether src/dst requested, copy needed */ - if (len > offsetof(struct ethhdr, h_proto)) + if (boundary > offsetof(struct ethhdr, h_proto)) return true; return false; @@ -183,7 +174,7 @@ void nft_payload_eval(const struct nft_expr *expr, goto err; if (skb_vlan_tag_present(skb) && - nft_payload_need_vlan_copy(priv)) { + nft_payload_need_vlan_adjust(priv->offset, priv->len)) { if (!nft_payload_copy_vlan(dest, skb, priv->offset, priv->len)) goto err; @@ -810,21 +801,79 @@ struct nft_payload_set { u8 csum_flags; }; +/* This is not struct vlan_hdr. */ +struct nft_payload_vlan_hdr { + __be16 h_vlan_proto; + __be16 h_vlan_TCI; +}; + +static bool +nft_payload_set_vlan(const u32 *src, struct sk_buff *skb, u8 offset, u8 len, + int *vlan_hlen) +{ + struct nft_payload_vlan_hdr *vlanh; + __be16 vlan_proto; + u16 vlan_tci; + + if (offset >= offsetof(struct vlan_ethhdr, h_vlan_encapsulated_proto)) { + *vlan_hlen = VLAN_HLEN; + return true; + } + + switch (offset) { + case offsetof(struct vlan_ethhdr, h_vlan_proto): + if (len == 2) { + vlan_proto = nft_reg_load_be16(src); + skb->vlan_proto = vlan_proto; + } else if (len == 4) { + vlanh = (struct nft_payload_vlan_hdr *)src; + __vlan_hwaccel_put_tag(skb, vlanh->h_vlan_proto, + ntohs(vlanh->h_vlan_TCI)); + } else { + return false; + } + break; + case offsetof(struct vlan_ethhdr, h_vlan_TCI): + if (len != 2) + return false; + + vlan_tci = ntohs(nft_reg_load_be16(src)); + skb->vlan_tci = vlan_tci; + break; + default: + return false; + } + + return true; +} + static void nft_payload_set_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_payload_set *priv = nft_expr_priv(expr); - struct sk_buff *skb = pkt->skb; const u32 *src = ®s->data[priv->sreg]; - int offset, csum_offset; + int offset, csum_offset, vlan_hlen = 0; + struct sk_buff *skb = pkt->skb; __wsum fsum, tsum; switch (priv->base) { case NFT_PAYLOAD_LL_HEADER: if (!skb_mac_header_was_set(skb)) goto err; - offset = skb_mac_header(skb) - skb->data; + + if (skb_vlan_tag_present(skb) && + nft_payload_need_vlan_adjust(priv->offset, priv->len)) { + if (!nft_payload_set_vlan(src, skb, + priv->offset, priv->len, + &vlan_hlen)) + goto err; + + if (!vlan_hlen) + return; + } + + offset = skb_mac_header(skb) - skb->data - vlan_hlen; break; case NFT_PAYLOAD_NETWORK_HEADER: offset = skb_network_offset(skb); diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 1ab17e8a7260..937a0c513c17 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1151,11 +1151,6 @@ static int parse_taprio_schedule(struct taprio_sched *q, struct nlattr **tb, list_for_each_entry(entry, &new->entries, list) cycle = ktime_add_ns(cycle, entry->interval); - if (!cycle) { - NL_SET_ERR_MSG(extack, "'cycle_time' can never be 0"); - return -EINVAL; - } - if (cycle < 0 || cycle > INT_MAX) { NL_SET_ERR_MSG(extack, "'cycle_time' is too big"); return -EINVAL; @@ -1164,6 +1159,11 @@ static int parse_taprio_schedule(struct taprio_sched *q, struct nlattr **tb, new->cycle_time = cycle; } + if (new->cycle_time < new->num_entries * length_to_duration(q, ETH_ZLEN)) { + NL_SET_ERR_MSG(extack, "'cycle_time' is too small"); + return -EINVAL; + } + taprio_calculate_gate_durations(q, new); return 0; @@ -1848,6 +1848,9 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, } q->flags = taprio_flags; + /* Needed for length_to_duration() during netlink attribute parsing */ + taprio_set_picos_per_byte(dev, q); + err = taprio_parse_mqprio_opt(dev, mqprio, extack, q->flags); if (err < 0) return err; @@ -1907,7 +1910,6 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, if (err < 0) goto free_sched; - taprio_set_picos_per_byte(dev, q); taprio_update_queue_max_sdu(q, new_admin, stab); if (FULL_OFFLOAD_IS_ENABLED(q->flags)) diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 28f3749f6dc6..cfd1b1bf7e35 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1071,6 +1071,7 @@ struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *old, .authflavor = old->cl_auth->au_flavor, .cred = old->cl_cred, .stats = old->cl_stats, + .timeout = old->cl_timeout, }; struct rpc_clnt *clnt; int err; @@ -2698,8 +2699,19 @@ rpc_decode_header(struct rpc_task *task, struct xdr_stream *xdr) goto out_msg_denied; error = rpcauth_checkverf(task, xdr); - if (error) + if (error) { + struct rpc_cred *cred = task->tk_rqstp->rq_cred; + + if (!test_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags)) { + rpcauth_invalcred(task); + if (!task->tk_cred_retry) + goto out_err; + task->tk_cred_retry--; + trace_rpc__stale_creds(task); + return -EKEYREJECTED; + } goto out_verifier; + } p = xdr_inline_decode(xdr, sizeof(*p)); if (!p) diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 4f8d7efa469f..432557a553e7 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -244,7 +244,11 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event) case RDMA_CM_EVENT_DEVICE_REMOVAL: pr_info("rpcrdma: removing device %s for %pISpc\n", ep->re_id->device->name, sap); - fallthrough; + switch (xchg(&ep->re_connect_status, -ENODEV)) { + case 0: goto wake_connect_worker; + case 1: goto disconnected; + } + return 0; case RDMA_CM_EVENT_ADDR_CHANGE: ep->re_connect_status = -ENODEV; goto disconnected; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index e4af6616e1df..25b49efc0926 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -731,7 +731,7 @@ static int unix_listen(struct socket *sock, int backlog) if (sock->type != SOCK_STREAM && sock->type != SOCK_SEQPACKET) goto out; /* Only stream/seqpacket sockets accept */ err = -EINVAL; - if (!u->addr) + if (!READ_ONCE(u->addr)) goto out; /* No listens on an unbound socket */ unix_state_lock(sk); if (sk->sk_state != TCP_CLOSE && sk->sk_state != TCP_LISTEN) @@ -1131,8 +1131,8 @@ static struct sock *unix_find_other(struct net *net, static int unix_autobind(struct sock *sk) { - unsigned int new_hash, old_hash = sk->sk_hash; struct unix_sock *u = unix_sk(sk); + unsigned int new_hash, old_hash; struct net *net = sock_net(sk); struct unix_address *addr; u32 lastnum, ordernum; @@ -1155,6 +1155,7 @@ static int unix_autobind(struct sock *sk) addr->name->sun_family = AF_UNIX; refcount_set(&addr->refcnt, 1); + old_hash = sk->sk_hash; ordernum = get_random_u32(); lastnum = ordernum & 0xFFFFF; retry: @@ -1195,8 +1196,8 @@ static int unix_bind_bsd(struct sock *sk, struct sockaddr_un *sunaddr, { umode_t mode = S_IFSOCK | (SOCK_INODE(sk->sk_socket)->i_mode & ~current_umask()); - unsigned int new_hash, old_hash = sk->sk_hash; struct unix_sock *u = unix_sk(sk); + unsigned int new_hash, old_hash; struct net *net = sock_net(sk); struct mnt_idmap *idmap; struct unix_address *addr; @@ -1234,6 +1235,7 @@ static int unix_bind_bsd(struct sock *sk, struct sockaddr_un *sunaddr, if (u->addr) goto out_unlock; + old_hash = sk->sk_hash; new_hash = unix_bsd_hash(d_backing_inode(dentry)); unix_table_double_lock(net, old_hash, new_hash); u->path.mnt = mntget(parent.mnt); @@ -1261,8 +1263,8 @@ out: static int unix_bind_abstract(struct sock *sk, struct sockaddr_un *sunaddr, int addr_len) { - unsigned int new_hash, old_hash = sk->sk_hash; struct unix_sock *u = unix_sk(sk); + unsigned int new_hash, old_hash; struct net *net = sock_net(sk); struct unix_address *addr; int err; @@ -1280,6 +1282,7 @@ static int unix_bind_abstract(struct sock *sk, struct sockaddr_un *sunaddr, goto out_mutex; } + old_hash = sk->sk_hash; new_hash = unix_abstract_hash(addr->name, addr->len, sk->sk_type); unix_table_double_lock(net, old_hash, new_hash); @@ -1369,7 +1372,7 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr, if ((test_bit(SOCK_PASSCRED, &sock->flags) || test_bit(SOCK_PASSPIDFD, &sock->flags)) && - !unix_sk(sk)->addr) { + !READ_ONCE(unix_sk(sk)->addr)) { err = unix_autobind(sk); if (err) goto out; @@ -1481,7 +1484,8 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, goto out; if ((test_bit(SOCK_PASSCRED, &sock->flags) || - test_bit(SOCK_PASSPIDFD, &sock->flags)) && !u->addr) { + test_bit(SOCK_PASSPIDFD, &sock->flags)) && + !READ_ONCE(u->addr)) { err = unix_autobind(sk); if (err) goto out; @@ -1950,7 +1954,8 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, } if ((test_bit(SOCK_PASSCRED, &sock->flags) || - test_bit(SOCK_PASSPIDFD, &sock->flags)) && !u->addr) { + test_bit(SOCK_PASSPIDFD, &sock->flags)) && + !READ_ONCE(u->addr)) { err = unix_autobind(sk); if (err) goto out; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 475b904fe68b..66e07de2de35 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3910,15 +3910,10 @@ static void xfrm_link_failure(struct sk_buff *skb) /* Impossible. Such dst must be popped before reaches point of failure. */ } -static struct dst_entry *xfrm_negative_advice(struct dst_entry *dst) +static void xfrm_negative_advice(struct sock *sk, struct dst_entry *dst) { - if (dst) { - if (dst->obsolete) { - dst_release(dst); - dst = NULL; - } - } - return dst; + if (dst->obsolete) + sk_dst_reset(sk); } static void xfrm_init_pmtu(struct xfrm_dst **bundle, int nr) diff --git a/security/loadpin/Kconfig b/security/loadpin/Kconfig index 6724eaba3d36..848f8b4a6019 100644 --- a/security/loadpin/Kconfig +++ b/security/loadpin/Kconfig @@ -14,6 +14,9 @@ config SECURITY_LOADPIN config SECURITY_LOADPIN_ENFORCE bool "Enforce LoadPin at boot" depends on SECURITY_LOADPIN + # Module compression breaks LoadPin unless modules are decompressed in + # the kernel. + depends on !MODULES || (MODULE_COMPRESS_NONE || MODULE_DECOMPRESS) help If selected, LoadPin will enforce pinning at boot. If not selected, it can be enabled at boot with the kernel parameter diff --git a/sound/core/init.c b/sound/core/init.c index 6b127864a1a3..4e52bbe32786 100644 --- a/sound/core/init.c +++ b/sound/core/init.c @@ -50,7 +50,7 @@ MODULE_PARM_DESC(slots, "Module names assigned to the slots."); static int module_slot_match(struct module *module, int idx) { int match = 1; -#ifdef MODULE +#ifdef CONFIG_MODULES const char *s1, *s2; if (!module || !*module->name || !slots[idx]) @@ -77,7 +77,7 @@ static int module_slot_match(struct module *module, int idx) if (!c1) break; } -#endif /* MODULE */ +#endif /* CONFIG_MODULES */ return match; } @@ -311,10 +311,8 @@ static int snd_card_init(struct snd_card *card, struct device *parent, } card->dev = parent; card->number = idx; -#ifdef MODULE - WARN_ON(!module); + WARN_ON(IS_MODULE(CONFIG_SND) && !module); card->module = module; -#endif INIT_LIST_HEAD(&card->devices); init_rwsem(&card->controls_rwsem); rwlock_init(&card->ctl_files_rwlock); @@ -969,7 +967,7 @@ void snd_card_info_read_oss(struct snd_info_buffer *buffer) #endif -#ifdef MODULE +#ifdef CONFIG_MODULES static void snd_card_module_info_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { @@ -997,7 +995,7 @@ int __init snd_card_info_init(void) if (snd_info_register(entry) < 0) return -ENOMEM; /* freed in error path */ -#ifdef MODULE +#ifdef CONFIG_MODULES entry = snd_info_create_module_entry(THIS_MODULE, "modules", NULL); if (!entry) return -ENOMEM; diff --git a/sound/core/timer.c b/sound/core/timer.c index 4d2ee99c12a3..d104adc75a8b 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -544,6 +544,14 @@ static int snd_timer_start1(struct snd_timer_instance *timeri, SNDRV_TIMER_IFLG_START)) return -EBUSY; + /* check the actual time for the start tick; + * bail out as error if it's way too low (< 100us) + */ + if (start) { + if ((u64)snd_timer_hw_resolution(timer) * ticks < 100000) + return -EINVAL; + } + if (start) timeri->ticks = timeri->cticks = ticks; else if (!timeri->cticks) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index a696943aec0d..e3c0b9d5552d 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -10194,8 +10194,11 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8c70, "HP EliteBook 835 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c71, "HP EliteBook 845 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c72, "HP EliteBook 865 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c89, "HP ProBook 460 G11", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c8a, "HP EliteBook 630", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c8c, "HP EliteBook 660", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c8d, "HP ProBook 440 G11", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c8e, "HP ProBook 460 G11", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c90, "HP EliteBook 640", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c91, "HP EliteBook 660", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c96, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), @@ -12028,6 +12031,7 @@ enum { ALC897_FIXUP_LENOVO_HEADSET_MODE, ALC897_FIXUP_HEADSET_MIC_PIN2, ALC897_FIXUP_UNIS_H3C_X500S, + ALC897_FIXUP_HEADSET_MIC_PIN3, }; static const struct hda_fixup alc662_fixups[] = { @@ -12474,10 +12478,18 @@ static const struct hda_fixup alc662_fixups[] = { {} }, }, + [ALC897_FIXUP_HEADSET_MIC_PIN3] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x03a11050 }, /* use as headset mic */ + { } + }, + }, }; static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x1019, 0x9087, "ECS", ALC662_FIXUP_ASUS_MODE2), + SND_PCI_QUIRK(0x1019, 0x9859, "JP-IK LEAP W502", ALC897_FIXUP_HEADSET_MIC_PIN3), SND_PCI_QUIRK(0x1025, 0x022f, "Acer Aspire One", ALC662_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x1025, 0x0241, "Packard Bell DOTS", ALC662_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x1025, 0x0308, "Acer Aspire 8942G", ALC662_FIXUP_ASPIRE), diff --git a/sound/soc/codecs/es8326.c b/sound/soc/codecs/es8326.c index 833ea52638ab..03b539ba540f 100644 --- a/sound/soc/codecs/es8326.c +++ b/sound/soc/codecs/es8326.c @@ -829,8 +829,8 @@ static void es8326_jack_detect_handler(struct work_struct *work) /* mute adc when mic path switch */ regmap_write(es8326->regmap, ES8326_ADC1_SRC, 0x44); regmap_write(es8326->regmap, ES8326_ADC2_SRC, 0x66); - es8326->hp = 0; } + es8326->hp = 0; regmap_update_bits(es8326->regmap, ES8326_HPDET_TYPE, 0x03, 0x01); regmap_write(es8326->regmap, ES8326_SYS_BIAS, 0x0a); regmap_update_bits(es8326->regmap, ES8326_HP_DRIVER_REF, 0x0f, 0x03); @@ -981,7 +981,7 @@ static int es8326_resume(struct snd_soc_component *component) regmap_write(es8326->regmap, ES8326_ANA_LP, 0xf0); usleep_range(10000, 15000); regmap_write(es8326->regmap, ES8326_HPJACK_TIMER, 0xd9); - regmap_write(es8326->regmap, ES8326_ANA_MICBIAS, 0xcb); + regmap_write(es8326->regmap, ES8326_ANA_MICBIAS, 0xd8); /* set headphone default type and detect pin */ regmap_write(es8326->regmap, ES8326_HPDET_TYPE, 0x83); regmap_write(es8326->regmap, ES8326_CLK_RESAMPLE, 0x05); @@ -1018,7 +1018,7 @@ static int es8326_resume(struct snd_soc_component *component) regmap_write(es8326->regmap, ES8326_ANA_VSEL, 0x7F); /* select vdda as micbias source */ - regmap_write(es8326->regmap, ES8326_VMIDLOW, 0x23); + regmap_write(es8326->regmap, ES8326_VMIDLOW, 0x03); /* set dac dsmclip = 1 */ regmap_write(es8326->regmap, ES8326_DAC_DSM, 0x08); regmap_write(es8326->regmap, ES8326_DAC_VPPSCALE, 0x15); diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c index 05f574bf8b8f..cdb7ff7020e9 100644 --- a/sound/soc/codecs/rt5645.c +++ b/sound/soc/codecs/rt5645.c @@ -81,6 +81,7 @@ static const struct reg_sequence init_list[] = { static const struct reg_sequence rt5650_init_list[] = { {0xf6, 0x0100}, {RT5645_PWR_ANLG1, 0x02}, + {RT5645_IL_CMD3, 0x0018}, }; static const struct reg_default rt5645_reg[] = { diff --git a/sound/soc/codecs/tas2552.c b/sound/soc/codecs/tas2552.c index 40f5f27e74c0..a7ed59ec49a6 100644 --- a/sound/soc/codecs/tas2552.c +++ b/sound/soc/codecs/tas2552.c @@ -2,7 +2,8 @@ /* * tas2552.c - ALSA SoC Texas Instruments TAS2552 Mono Audio Amplifier * - * Copyright (C) 2014 Texas Instruments Incorporated - https://www.ti.com + * Copyright (C) 2014 - 2024 Texas Instruments Incorporated - + * https://www.ti.com * * Author: Dan Murphy <dmurphy@ti.com> */ @@ -119,12 +120,14 @@ static const struct snd_soc_dapm_widget tas2552_dapm_widgets[] = &tas2552_input_mux_control), SND_SOC_DAPM_AIF_IN("DAC IN", "DAC Playback", 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_OUT("ASI OUT", "DAC Capture", 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_DAC("DAC", NULL, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_OUT_DRV("ClassD", TAS2552_CFG_2, 7, 0, NULL, 0), SND_SOC_DAPM_SUPPLY("PLL", TAS2552_CFG_2, 3, 0, NULL, 0), SND_SOC_DAPM_POST("Post Event", tas2552_post_event), - SND_SOC_DAPM_OUTPUT("OUT") + SND_SOC_DAPM_OUTPUT("OUT"), + SND_SOC_DAPM_INPUT("DMIC") }; static const struct snd_soc_dapm_route tas2552_audio_map[] = { @@ -134,6 +137,7 @@ static const struct snd_soc_dapm_route tas2552_audio_map[] = { {"ClassD", NULL, "Input selection"}, {"OUT", NULL, "ClassD"}, {"ClassD", NULL, "PLL"}, + {"ASI OUT", NULL, "DMIC"} }; #ifdef CONFIG_PM @@ -538,6 +542,13 @@ static struct snd_soc_dai_driver tas2552_dai[] = { .rates = SNDRV_PCM_RATE_8000_192000, .formats = TAS2552_FORMATS, }, + .capture = { + .stream_name = "Capture", + .channels_min = 2, + .channels_max = 2, + .rates = SNDRV_PCM_RATE_8000_192000, + .formats = TAS2552_FORMATS, + }, .ops = &tas2552_speaker_dai_ops, }, }; diff --git a/sound/soc/codecs/tas2781-fmwlib.c b/sound/soc/codecs/tas2781-fmwlib.c index a6be81adcb83..265a8ca25cbb 100644 --- a/sound/soc/codecs/tas2781-fmwlib.c +++ b/sound/soc/codecs/tas2781-fmwlib.c @@ -2151,6 +2151,24 @@ static int tasdevice_load_data(struct tasdevice_priv *tas_priv, return ret; } +static void tasdev_load_calibrated_data(struct tasdevice_priv *priv, int i) +{ + struct tasdevice_calibration *cal; + struct tasdevice_fw *cal_fmw; + + cal_fmw = priv->tasdevice[i].cali_data_fmw; + + /* No calibrated data for current devices, playback will go ahead. */ + if (!cal_fmw) + return; + + cal = cal_fmw->calibrations; + if (cal) + return; + + load_calib_data(priv, &cal->dev_data); +} + int tasdevice_select_tuningprm_cfg(void *context, int prm_no, int cfg_no, int rca_conf_no) { @@ -2210,21 +2228,9 @@ int tasdevice_select_tuningprm_cfg(void *context, int prm_no, for (i = 0; i < tas_priv->ndev; i++) { if (tas_priv->tasdevice[i].is_loaderr == true) continue; - else if (tas_priv->tasdevice[i].is_loaderr == false - && tas_priv->tasdevice[i].is_loading == true) { - struct tasdevice_fw *cal_fmw = - tas_priv->tasdevice[i].cali_data_fmw; - - if (cal_fmw) { - struct tasdevice_calibration - *cal = cal_fmw->calibrations; - - if (cal) - load_calib_data(tas_priv, - &(cal->dev_data)); - } + if (tas_priv->tasdevice[i].is_loaderr == false && + tas_priv->tasdevice[i].is_loading == true) tas_priv->tasdevice[i].cur_prog = prm_no; - } } } @@ -2245,11 +2251,15 @@ int tasdevice_select_tuningprm_cfg(void *context, int prm_no, tasdevice_load_data(tas_priv, &(conf->dev_data)); for (i = 0; i < tas_priv->ndev; i++) { if (tas_priv->tasdevice[i].is_loaderr == true) { - status |= 1 << (i + 4); + status |= BIT(i + 4); continue; - } else if (tas_priv->tasdevice[i].is_loaderr == false - && tas_priv->tasdevice[i].is_loading == true) + } + + if (tas_priv->tasdevice[i].is_loaderr == false && + tas_priv->tasdevice[i].is_loading == true) { + tasdev_load_calibrated_data(tas_priv, i); tas_priv->tasdevice[i].cur_conf = cfg_no; + } } } else dev_dbg(tas_priv->dev, "%s: Unneeded loading dsp conf %d\n", @@ -2308,65 +2318,6 @@ out: } EXPORT_SYMBOL_NS_GPL(tasdevice_prmg_load, SND_SOC_TAS2781_FMWLIB); -int tasdevice_prmg_calibdata_load(void *context, int prm_no) -{ - struct tasdevice_priv *tas_priv = (struct tasdevice_priv *) context; - struct tasdevice_fw *tas_fmw = tas_priv->fmw; - struct tasdevice_prog *program; - int prog_status = 0; - int i; - - if (!tas_fmw) { - dev_err(tas_priv->dev, "%s: Firmware is NULL\n", __func__); - goto out; - } - - if (prm_no >= tas_fmw->nr_programs) { - dev_err(tas_priv->dev, - "%s: prm(%d) is not in range of Programs %u\n", - __func__, prm_no, tas_fmw->nr_programs); - goto out; - } - - for (i = 0, prog_status = 0; i < tas_priv->ndev; i++) { - if (prm_no >= 0 && tas_priv->tasdevice[i].cur_prog != prm_no) { - tas_priv->tasdevice[i].cur_conf = -1; - tas_priv->tasdevice[i].is_loading = true; - prog_status++; - } - tas_priv->tasdevice[i].is_loaderr = false; - } - - if (prog_status) { - program = &(tas_fmw->programs[prm_no]); - tasdevice_load_data(tas_priv, &(program->dev_data)); - for (i = 0; i < tas_priv->ndev; i++) { - if (tas_priv->tasdevice[i].is_loaderr == true) - continue; - else if (tas_priv->tasdevice[i].is_loaderr == false - && tas_priv->tasdevice[i].is_loading == true) { - struct tasdevice_fw *cal_fmw = - tas_priv->tasdevice[i].cali_data_fmw; - - if (cal_fmw) { - struct tasdevice_calibration *cal = - cal_fmw->calibrations; - - if (cal) - load_calib_data(tas_priv, - &(cal->dev_data)); - } - tas_priv->tasdevice[i].cur_prog = prm_no; - } - } - } - -out: - return prog_status; -} -EXPORT_SYMBOL_NS_GPL(tasdevice_prmg_calibdata_load, - SND_SOC_TAS2781_FMWLIB); - void tasdevice_tuning_switch(void *context, int state) { struct tasdevice_priv *tas_priv = (struct tasdevice_priv *) context; diff --git a/sound/soc/codecs/tas2781-i2c.c b/sound/soc/codecs/tas2781-i2c.c index b5abff230e43..9350972dfefe 100644 --- a/sound/soc/codecs/tas2781-i2c.c +++ b/sound/soc/codecs/tas2781-i2c.c @@ -2,7 +2,7 @@ // // ALSA SoC Texas Instruments TAS2563/TAS2781 Audio Smart Amplifier // -// Copyright (C) 2022 - 2023 Texas Instruments Incorporated +// Copyright (C) 2022 - 2024 Texas Instruments Incorporated // https://www.ti.com // // The TAS2563/TAS2781 driver implements a flexible and configurable @@ -414,7 +414,7 @@ static void tasdevice_fw_ready(const struct firmware *fmw, __func__, tas_priv->cal_binaryname[i]); } - tasdevice_prmg_calibdata_load(tas_priv, 0); + tasdevice_prmg_load(tas_priv, 0); tas_priv->cur_prog = 0; out: if (tas_priv->fw_state == TASDEVICE_DSP_FW_FAIL) { diff --git a/sound/soc/intel/boards/sof_sdw_rt_sdca_jack_common.c b/sound/soc/intel/boards/sof_sdw_rt_sdca_jack_common.c index 701b0372f59e..012195c50519 100644 --- a/sound/soc/intel/boards/sof_sdw_rt_sdca_jack_common.c +++ b/sound/soc/intel/boards/sof_sdw_rt_sdca_jack_common.c @@ -109,7 +109,7 @@ int rt_sdca_jack_rtd_init(struct snd_soc_pcm_runtime *rtd, struct snd_soc_dai *d return -ENOMEM; for (i = 0; i < ARRAY_SIZE(need_sdca_suffix); i++) { - if (strstr(codec_dai->name, need_sdca_suffix[i])) { + if (strstr(component->name_prefix, need_sdca_suffix[i])) { /* Add -sdca suffix for existing UCMs */ card->components = devm_kasprintf(card->dev, GFP_KERNEL, "%s-sdca", card->components); diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 2f961f0e9378..58156fbca02c 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1740,7 +1740,7 @@ static void mbox3_set_format_quirk(struct snd_usb_substream *subs, u32 current_rate; // Get current rate from card and check if changing it is needed - snd_usb_ctl_msg(subs->dev, usb_sndctrlpipe(subs->dev, 0), + snd_usb_ctl_msg(subs->dev, usb_rcvctrlpipe(subs->dev, 0), 0x01, 0x21 | USB_DIR_IN, 0x0100, 0x8101, &buff4, 4); current_rate = le32_to_cpu(buff4); dev_dbg(&subs->dev->dev, @@ -1765,7 +1765,7 @@ static void mbox3_set_format_quirk(struct snd_usb_substream *subs, // Check whether the change was successful buff4 = 0; - snd_usb_ctl_msg(subs->dev, usb_sndctrlpipe(subs->dev, 0), + snd_usb_ctl_msg(subs->dev, usb_rcvctrlpipe(subs->dev, 0), 0x01, 0x21 | USB_DIR_IN, 0x0100, 0x8101, &buff4, 4); if (new_rate != le32_to_cpu(buff4)) dev_warn(&subs->dev->dev, "MBOX3: Couldn't set the sample rate"); diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c index d9520cb826b3..af393c7dee1f 100644 --- a/tools/bpf/resolve_btfids/main.c +++ b/tools/bpf/resolve_btfids/main.c @@ -728,7 +728,7 @@ static int sets_patch(struct object *obj) static int symbols_patch(struct object *obj) { - int err; + off_t err; if (__symbols_patch(obj, &obj->structs) || __symbols_patch(obj, &obj->unions) || diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index a8188202413e..43742ac5b00d 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -148,6 +148,7 @@ enum { NETDEV_A_QSTATS_RX_ALLOC_FAIL, NETDEV_A_QSTATS_RX_HW_DROPS, NETDEV_A_QSTATS_RX_HW_DROP_OVERRUNS, + NETDEV_A_QSTATS_RX_CSUM_COMPLETE, NETDEV_A_QSTATS_RX_CSUM_UNNECESSARY, NETDEV_A_QSTATS_RX_CSUM_NONE, NETDEV_A_QSTATS_RX_CSUM_BAD, diff --git a/tools/lib/bpf/features.c b/tools/lib/bpf/features.c index a336786a22a3..3df0125ed5fa 100644 --- a/tools/lib/bpf/features.c +++ b/tools/lib/bpf/features.c @@ -392,11 +392,40 @@ static int probe_uprobe_multi_link(int token_fd) link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts); err = -errno; /* close() can clobber errno */ + if (link_fd >= 0 || err != -EBADF) { + close(link_fd); + close(prog_fd); + return 0; + } + + /* Initial multi-uprobe support in kernel didn't handle PID filtering + * correctly (it was doing thread filtering, not process filtering). + * So now we'll detect if PID filtering logic was fixed, and, if not, + * we'll pretend multi-uprobes are not supported, if not. + * Multi-uprobes are used in USDT attachment logic, and we need to be + * conservative here, because multi-uprobe selection happens early at + * load time, while the use of PID filtering is known late at + * attachment time, at which point it's too late to undo multi-uprobe + * selection. + * + * Creating uprobe with pid == -1 for (invalid) '/' binary will fail + * early with -EINVAL on kernels with fixed PID filtering logic; + * otherwise -ESRCH would be returned if passed correct binary path + * (but we'll just get -BADF, of course). + */ + link_opts.uprobe_multi.pid = -1; /* invalid PID */ + link_opts.uprobe_multi.path = "/"; /* invalid path */ + link_opts.uprobe_multi.offsets = &offset; + link_opts.uprobe_multi.cnt = 1; + + link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts); + err = -errno; /* close() can clobber errno */ + if (link_fd >= 0) close(link_fd); close(prog_fd); - return link_fd < 0 && err == -EBADF; + return link_fd < 0 && err == -EINVAL; } static int probe_kern_bpf_cookie(int token_fd) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 30f958069076..6ed0f9c5581d 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1549,7 +1549,7 @@ static int parse_events_add_pmu(struct parse_events_state *parse_state, } int parse_events_multi_pmu_add(struct parse_events_state *parse_state, - const char *event_name, u64 hw_config, + const char *event_name, const struct parse_events_terms *const_parsed_terms, struct list_head **listp, void *loc_) { @@ -1557,8 +1557,8 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, struct list_head *list = NULL; struct perf_pmu *pmu = NULL; YYLTYPE *loc = loc_; - int ok = 0, core_ok = 0; - const char *tmp; + int ok = 0; + const char *config; struct parse_events_terms parsed_terms; *listp = NULL; @@ -1571,15 +1571,15 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, return ret; } - tmp = strdup(event_name); - if (!tmp) + config = strdup(event_name); + if (!config) goto out_err; if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, - tmp, /*num=*/1, /*novalue=*/true, + config, /*num=*/1, /*novalue=*/true, loc, /*loc_val=*/NULL) < 0) { - zfree(&tmp); + zfree(&config); goto out_err; } list_add_tail(&term->list, &parsed_terms.terms); @@ -1610,8 +1610,6 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, pr_debug("%s -> %s/%s/\n", event_name, pmu->name, sb.buf); strbuf_release(&sb); ok++; - if (pmu->is_core) - core_ok++; } } @@ -1628,18 +1626,6 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, } } - if (hw_config != PERF_COUNT_HW_MAX && !core_ok) { - /* - * The event wasn't found on core PMUs but it has a hardware - * config version to try. - */ - if (!parse_events_add_numeric(parse_state, list, - PERF_TYPE_HARDWARE, hw_config, - const_parsed_terms, - /*wildcard=*/true)) - ok++; - } - out_err: parse_events_terms__exit(&parsed_terms); if (ok) @@ -1693,8 +1679,7 @@ int parse_events_multi_pmu_add_or_add_pmu(struct parse_events_state *parse_state /* Failure to add, assume event_or_pmu is an event name. */ zfree(listp); - if (!parse_events_multi_pmu_add(parse_state, event_or_pmu, PERF_COUNT_HW_MAX, - const_parsed_terms, listp, loc)) + if (!parse_events_multi_pmu_add(parse_state, event_or_pmu, const_parsed_terms, listp, loc)) return 0; if (asprintf(&help, "Unable to find PMU or event on a PMU of '%s'", event_or_pmu) < 0) diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index f2baa69fff98..e13de2c8b706 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -237,7 +237,7 @@ struct evsel *parse_events__add_event(int idx, struct perf_event_attr *attr, struct perf_pmu *pmu); int parse_events_multi_pmu_add(struct parse_events_state *parse_state, - const char *event_name, u64 hw_config, + const char *event_name, const struct parse_events_terms *const_parsed_terms, struct list_head **listp, void *loc); diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 99d585d272e0..16045c383ada 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -113,12 +113,12 @@ do { \ yyless(0); \ } while (0) -static int sym(yyscan_t scanner, int config) +static int sym(yyscan_t scanner, int type, int config) { YYSTYPE *yylval = parse_events_get_lval(scanner); - yylval->num = config; - return PE_VALUE_SYM_SW; + yylval->num = (type << 16) + config; + return type == PERF_TYPE_HARDWARE ? PE_VALUE_SYM_HW : PE_VALUE_SYM_SW; } static int tool(yyscan_t scanner, enum perf_tool_event event) @@ -137,13 +137,13 @@ static int term(yyscan_t scanner, enum parse_events__term_type type) return PE_TERM; } -static int hw(yyscan_t scanner, int config) +static int hw_term(yyscan_t scanner, int config) { YYSTYPE *yylval = parse_events_get_lval(scanner); char *text = parse_events_get_text(scanner); - yylval->hardware_event.str = strdup(text); - yylval->hardware_event.num = config; + yylval->hardware_term.str = strdup(text); + yylval->hardware_term.num = PERF_TYPE_HARDWARE + config; return PE_TERM_HW; } @@ -330,16 +330,16 @@ percore { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_PERCORE); } aux-output { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT); } aux-sample-size { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE); } metric-id { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_METRIC_ID); } -cpu-cycles|cycles { return hw(yyscanner, PERF_COUNT_HW_CPU_CYCLES); } -stalled-cycles-frontend|idle-cycles-frontend { return hw(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); } -stalled-cycles-backend|idle-cycles-backend { return hw(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); } -instructions { return hw(yyscanner, PERF_COUNT_HW_INSTRUCTIONS); } -cache-references { return hw(yyscanner, PERF_COUNT_HW_CACHE_REFERENCES); } -cache-misses { return hw(yyscanner, PERF_COUNT_HW_CACHE_MISSES); } -branch-instructions|branches { return hw(yyscanner, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); } -branch-misses { return hw(yyscanner, PERF_COUNT_HW_BRANCH_MISSES); } -bus-cycles { return hw(yyscanner, PERF_COUNT_HW_BUS_CYCLES); } -ref-cycles { return hw(yyscanner, PERF_COUNT_HW_REF_CPU_CYCLES); } +cpu-cycles|cycles { return hw_term(yyscanner, PERF_COUNT_HW_CPU_CYCLES); } +stalled-cycles-frontend|idle-cycles-frontend { return hw_term(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); } +stalled-cycles-backend|idle-cycles-backend { return hw_term(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); } +instructions { return hw_term(yyscanner, PERF_COUNT_HW_INSTRUCTIONS); } +cache-references { return hw_term(yyscanner, PERF_COUNT_HW_CACHE_REFERENCES); } +cache-misses { return hw_term(yyscanner, PERF_COUNT_HW_CACHE_MISSES); } +branch-instructions|branches { return hw_term(yyscanner, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); } +branch-misses { return hw_term(yyscanner, PERF_COUNT_HW_BRANCH_MISSES); } +bus-cycles { return hw_term(yyscanner, PERF_COUNT_HW_BUS_CYCLES); } +ref-cycles { return hw_term(yyscanner, PERF_COUNT_HW_REF_CPU_CYCLES); } r{num_raw_hex} { return str(yyscanner, PE_RAW); } r0x{num_raw_hex} { return str(yyscanner, PE_RAW); } , { return ','; } @@ -383,31 +383,31 @@ r0x{num_raw_hex} { return str(yyscanner, PE_RAW); } <<EOF>> { BEGIN(INITIAL); } } -cpu-cycles|cycles { return hw(yyscanner, PERF_COUNT_HW_CPU_CYCLES); } -stalled-cycles-frontend|idle-cycles-frontend { return hw(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); } -stalled-cycles-backend|idle-cycles-backend { return hw(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); } -instructions { return hw(yyscanner, PERF_COUNT_HW_INSTRUCTIONS); } -cache-references { return hw(yyscanner, PERF_COUNT_HW_CACHE_REFERENCES); } -cache-misses { return hw(yyscanner, PERF_COUNT_HW_CACHE_MISSES); } -branch-instructions|branches { return hw(yyscanner, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); } -branch-misses { return hw(yyscanner, PERF_COUNT_HW_BRANCH_MISSES); } -bus-cycles { return hw(yyscanner, PERF_COUNT_HW_BUS_CYCLES); } -ref-cycles { return hw(yyscanner, PERF_COUNT_HW_REF_CPU_CYCLES); } -cpu-clock { return sym(yyscanner, PERF_COUNT_SW_CPU_CLOCK); } -task-clock { return sym(yyscanner, PERF_COUNT_SW_TASK_CLOCK); } -page-faults|faults { return sym(yyscanner, PERF_COUNT_SW_PAGE_FAULTS); } -minor-faults { return sym(yyscanner, PERF_COUNT_SW_PAGE_FAULTS_MIN); } -major-faults { return sym(yyscanner, PERF_COUNT_SW_PAGE_FAULTS_MAJ); } -context-switches|cs { return sym(yyscanner, PERF_COUNT_SW_CONTEXT_SWITCHES); } -cpu-migrations|migrations { return sym(yyscanner, PERF_COUNT_SW_CPU_MIGRATIONS); } -alignment-faults { return sym(yyscanner, PERF_COUNT_SW_ALIGNMENT_FAULTS); } -emulation-faults { return sym(yyscanner, PERF_COUNT_SW_EMULATION_FAULTS); } -dummy { return sym(yyscanner, PERF_COUNT_SW_DUMMY); } +cpu-cycles|cycles { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CPU_CYCLES); } +stalled-cycles-frontend|idle-cycles-frontend { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); } +stalled-cycles-backend|idle-cycles-backend { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); } +instructions { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS); } +cache-references { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_REFERENCES); } +cache-misses { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_MISSES); } +branch-instructions|branches { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); } +branch-misses { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_MISSES); } +bus-cycles { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BUS_CYCLES); } +ref-cycles { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_REF_CPU_CYCLES); } +cpu-clock { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_CLOCK); } +task-clock { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_TASK_CLOCK); } +page-faults|faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS); } +minor-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MIN); } +major-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MAJ); } +context-switches|cs { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CONTEXT_SWITCHES); } +cpu-migrations|migrations { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_MIGRATIONS); } +alignment-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); } +emulation-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); } +dummy { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); } duration_time { return tool(yyscanner, PERF_TOOL_DURATION_TIME); } user_time { return tool(yyscanner, PERF_TOOL_USER_TIME); } system_time { return tool(yyscanner, PERF_TOOL_SYSTEM_TIME); } -bpf-output { return sym(yyscanner, PERF_COUNT_SW_BPF_OUTPUT); } -cgroup-switches { return sym(yyscanner, PERF_COUNT_SW_CGROUP_SWITCHES); } +bpf-output { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); } +cgroup-switches { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CGROUP_SWITCHES); } {lc_type} { return str(yyscanner, PE_LEGACY_CACHE); } {lc_type}-{lc_op_result} { return str(yyscanner, PE_LEGACY_CACHE); } diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index c94a3994177e..b3c51f06cbdc 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -55,7 +55,7 @@ static void free_list_evsel(struct list_head* list_evsel) %} %token PE_START_EVENTS PE_START_TERMS -%token PE_VALUE PE_VALUE_SYM_SW PE_TERM +%token PE_VALUE PE_VALUE_SYM_HW PE_VALUE_SYM_SW PE_TERM %token PE_VALUE_SYM_TOOL %token PE_EVENT_NAME %token PE_RAW PE_NAME @@ -66,10 +66,12 @@ static void free_list_evsel(struct list_head* list_evsel) %token PE_DRV_CFG_TERM %token PE_TERM_HW %type <num> PE_VALUE +%type <num> PE_VALUE_SYM_HW %type <num> PE_VALUE_SYM_SW %type <num> PE_VALUE_SYM_TOOL %type <mod> PE_MODIFIER_EVENT %type <term_type> PE_TERM +%type <num> value_sym %type <str> PE_RAW %type <str> PE_NAME %type <str> PE_LEGACY_CACHE @@ -85,7 +87,6 @@ static void free_list_evsel(struct list_head* list_evsel) %type <list_terms> opt_pmu_config %destructor { parse_events_terms__delete ($$); } <list_terms> %type <list_evsel> event_pmu -%type <list_evsel> event_legacy_hardware %type <list_evsel> event_legacy_symbol %type <list_evsel> event_legacy_cache %type <list_evsel> event_legacy_mem @@ -103,8 +104,8 @@ static void free_list_evsel(struct list_head* list_evsel) %destructor { free_list_evsel ($$); } <list_evsel> %type <tracepoint_name> tracepoint_name %destructor { free ($$.sys); free ($$.event); } <tracepoint_name> -%type <hardware_event> PE_TERM_HW -%destructor { free ($$.str); } <hardware_event> +%type <hardware_term> PE_TERM_HW +%destructor { free ($$.str); } <hardware_term> %union { @@ -119,10 +120,10 @@ static void free_list_evsel(struct list_head* list_evsel) char *sys; char *event; } tracepoint_name; - struct hardware_event { + struct hardware_term { char *str; u64 num; - } hardware_event; + } hardware_term; } %% @@ -265,7 +266,6 @@ PE_EVENT_NAME event_def event_def event_def: event_pmu | - event_legacy_hardware | event_legacy_symbol | event_legacy_cache sep_dc | event_legacy_mem sep_dc | @@ -292,7 +292,7 @@ PE_NAME sep_dc struct list_head *list; int err; - err = parse_events_multi_pmu_add(_parse_state, $1, PERF_COUNT_HW_MAX, NULL, &list, &@1); + err = parse_events_multi_pmu_add(_parse_state, $1, NULL, &list, &@1); if (err < 0) { struct parse_events_state *parse_state = _parse_state; struct parse_events_error *error = parse_state->error; @@ -308,45 +308,24 @@ PE_NAME sep_dc $$ = list; } -event_legacy_hardware: -PE_TERM_HW opt_pmu_config -{ - /* List of created evsels. */ - struct list_head *list = NULL; - int err = parse_events_multi_pmu_add(_parse_state, $1.str, $1.num, $2, &list, &@1); - - free($1.str); - parse_events_terms__delete($2); - if (err) - PE_ABORT(err); - - $$ = list; -} +value_sym: +PE_VALUE_SYM_HW | -PE_TERM_HW sep_dc -{ - struct list_head *list; - int err; - - err = parse_events_multi_pmu_add(_parse_state, $1.str, $1.num, NULL, &list, &@1); - free($1.str); - if (err) - PE_ABORT(err); - $$ = list; -} +PE_VALUE_SYM_SW event_legacy_symbol: -PE_VALUE_SYM_SW '/' event_config '/' +value_sym '/' event_config '/' { struct list_head *list; + int type = $1 >> 16; + int config = $1 & 255; int err; + bool wildcard = (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_HW_CACHE); list = alloc_list(); if (!list) YYNOMEM; - err = parse_events_add_numeric(_parse_state, list, - /*type=*/PERF_TYPE_SOFTWARE, /*config=*/$1, - $3, /*wildcard=*/false); + err = parse_events_add_numeric(_parse_state, list, type, config, $3, wildcard); parse_events_terms__delete($3); if (err) { free_list_evsel(list); @@ -355,17 +334,18 @@ PE_VALUE_SYM_SW '/' event_config '/' $$ = list; } | -PE_VALUE_SYM_SW sep_slash_slash_dc +value_sym sep_slash_slash_dc { struct list_head *list; + int type = $1 >> 16; + int config = $1 & 255; + bool wildcard = (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_HW_CACHE); int err; list = alloc_list(); if (!list) YYNOMEM; - err = parse_events_add_numeric(_parse_state, list, - /*type=*/PERF_TYPE_SOFTWARE, /*config=*/$1, - /*head_config=*/NULL, /*wildcard=*/false); + err = parse_events_add_numeric(_parse_state, list, type, config, /*head_config=*/NULL, wildcard); if (err) PE_ABORT(err); $$ = list; diff --git a/tools/testing/selftests/bpf/prog_tests/tc_netkit.c b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c index 15ee7b2fc410..b9135720024c 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_netkit.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c @@ -73,6 +73,16 @@ static int create_netkit(int mode, int policy, int peer_policy, int *ifindex, "up primary"); ASSERT_OK(system("ip addr add dev " netkit_name " 10.0.0.1/24"), "addr primary"); + + if (mode == NETKIT_L3) { + ASSERT_EQ(system("ip link set dev " netkit_name + " addr ee:ff:bb:cc:aa:dd 2> /dev/null"), 512, + "set hwaddress"); + } else { + ASSERT_OK(system("ip link set dev " netkit_name + " addr ee:ff:bb:cc:aa:dd"), + "set hwaddress"); + } if (same_netns) { ASSERT_OK(system("ip link set dev " netkit_peer " up"), "up peer"); @@ -89,6 +99,16 @@ static int create_netkit(int mode, int policy, int peer_policy, int *ifindex, return err; } +static void move_netkit(void) +{ + ASSERT_OK(system("ip link set " netkit_peer " netns foo"), + "move peer"); + ASSERT_OK(system("ip netns exec foo ip link set dev " + netkit_peer " up"), "up peer"); + ASSERT_OK(system("ip netns exec foo ip addr add dev " + netkit_peer " 10.0.0.2/24"), "addr peer"); +} + static void destroy_netkit(void) { ASSERT_OK(system("ip link del dev " netkit_name), "del primary"); @@ -685,3 +705,77 @@ void serial_test_tc_netkit_neigh_links(void) serial_test_tc_netkit_neigh_links_target(NETKIT_L2, BPF_NETKIT_PRIMARY); serial_test_tc_netkit_neigh_links_target(NETKIT_L3, BPF_NETKIT_PRIMARY); } + +static void serial_test_tc_netkit_pkt_type_mode(int mode) +{ + LIBBPF_OPTS(bpf_netkit_opts, optl_nk); + LIBBPF_OPTS(bpf_tcx_opts, optl_tcx); + int err, ifindex, ifindex2; + struct test_tc_link *skel; + struct bpf_link *link; + + err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS, + &ifindex, true); + if (err) + return; + + ifindex2 = if_nametoindex(netkit_peer); + ASSERT_NEQ(ifindex, ifindex2, "ifindex_1_2"); + + skel = test_tc_link__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, + BPF_NETKIT_PRIMARY), 0, "tc1_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc7, + BPF_TCX_INGRESS), 0, "tc7_attach_type"); + + err = test_tc_link__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0); + assert_mprog_count_ifindex(ifindex2, BPF_TCX_INGRESS, 0); + + link = bpf_program__attach_netkit(skel->progs.tc1, ifindex, &optl_nk); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc1 = link; + + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 1); + assert_mprog_count_ifindex(ifindex2, BPF_TCX_INGRESS, 0); + + link = bpf_program__attach_tcx(skel->progs.tc7, ifindex2, &optl_tcx); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc7 = link; + + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 1); + assert_mprog_count_ifindex(ifindex2, BPF_TCX_INGRESS, 1); + + move_netkit(); + + tc_skel_reset_all_seen(skel); + skel->bss->set_type = true; + ASSERT_EQ(send_icmp(), 0, "icmp_pkt"); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc7, true, "seen_tc7"); + + ASSERT_EQ(skel->bss->seen_host, true, "seen_host"); + ASSERT_EQ(skel->bss->seen_mcast, true, "seen_mcast"); +cleanup: + test_tc_link__destroy(skel); + + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0); + destroy_netkit(); +} + +void serial_test_tc_netkit_pkt_type(void) +{ + serial_test_tc_netkit_pkt_type_mode(NETKIT_L2); + serial_test_tc_netkit_pkt_type_mode(NETKIT_L3); +} diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c index 8269cdee33ae..bf6ca8e3eb13 100644 --- a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c +++ b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c @@ -1,12 +1,14 @@ // SPDX-License-Identifier: GPL-2.0 #include <unistd.h> +#include <pthread.h> #include <test_progs.h> #include "uprobe_multi.skel.h" #include "uprobe_multi_bench.skel.h" #include "uprobe_multi_usdt.skel.h" #include "bpf/libbpf_internal.h" #include "testing_helpers.h" +#include "../sdt.h" static char test_data[] = "test_data"; @@ -25,9 +27,17 @@ noinline void uprobe_multi_func_3(void) asm volatile (""); } +noinline void usdt_trigger(void) +{ + STAP_PROBE(test, pid_filter_usdt); +} + struct child { int go[2]; + int c2p[2]; /* child -> parent channel */ int pid; + int tid; + pthread_t thread; }; static void release_child(struct child *child) @@ -38,6 +48,10 @@ static void release_child(struct child *child) return; close(child->go[1]); close(child->go[0]); + if (child->thread) + pthread_join(child->thread, NULL); + close(child->c2p[0]); + close(child->c2p[1]); if (child->pid > 0) waitpid(child->pid, &child_status, 0); } @@ -63,7 +77,7 @@ static struct child *spawn_child(void) if (pipe(child.go)) return NULL; - child.pid = fork(); + child.pid = child.tid = fork(); if (child.pid < 0) { release_child(&child); errno = EINVAL; @@ -82,6 +96,7 @@ static struct child *spawn_child(void) uprobe_multi_func_1(); uprobe_multi_func_2(); uprobe_multi_func_3(); + usdt_trigger(); exit(errno); } @@ -89,6 +104,67 @@ static struct child *spawn_child(void) return &child; } +static void *child_thread(void *ctx) +{ + struct child *child = ctx; + int c = 0, err; + + child->tid = syscall(SYS_gettid); + + /* let parent know we are ready */ + err = write(child->c2p[1], &c, 1); + if (err != 1) + pthread_exit(&err); + + /* wait for parent's kick */ + err = read(child->go[0], &c, 1); + if (err != 1) + pthread_exit(&err); + + uprobe_multi_func_1(); + uprobe_multi_func_2(); + uprobe_multi_func_3(); + usdt_trigger(); + + err = 0; + pthread_exit(&err); +} + +static struct child *spawn_thread(void) +{ + static struct child child; + int c, err; + + /* pipe to notify child to execute the trigger functions */ + if (pipe(child.go)) + return NULL; + /* pipe to notify parent that child thread is ready */ + if (pipe(child.c2p)) { + close(child.go[0]); + close(child.go[1]); + return NULL; + } + + child.pid = getpid(); + + err = pthread_create(&child.thread, NULL, child_thread, &child); + if (err) { + err = -errno; + close(child.go[0]); + close(child.go[1]); + close(child.c2p[0]); + close(child.c2p[1]); + errno = -err; + return NULL; + } + + err = read(child.c2p[0], &c, 1); + if (!ASSERT_EQ(err, 1, "child_thread_ready")) + return NULL; + + return &child; +} + static void uprobe_multi_test_run(struct uprobe_multi *skel, struct child *child) { skel->bss->uprobe_multi_func_1_addr = (__u64) uprobe_multi_func_1; @@ -103,15 +179,23 @@ static void uprobe_multi_test_run(struct uprobe_multi *skel, struct child *child * passed at the probe attach. */ skel->bss->pid = child ? 0 : getpid(); + skel->bss->expect_pid = child ? child->pid : 0; + + /* trigger all probes, if we are testing child *process*, just to make + * sure that PID filtering doesn't let through activations from wrong + * PIDs; when we test child *thread*, we don't want to do this to + * avoid double counting number of triggering events + */ + if (!child || !child->thread) { + uprobe_multi_func_1(); + uprobe_multi_func_2(); + uprobe_multi_func_3(); + usdt_trigger(); + } if (child) kick_child(child); - /* trigger all probes */ - uprobe_multi_func_1(); - uprobe_multi_func_2(); - uprobe_multi_func_3(); - /* * There are 2 entry and 2 exit probe called for each uprobe_multi_func_[123] * function and each slepable probe (6) increments uprobe_multi_sleep_result. @@ -126,8 +210,12 @@ static void uprobe_multi_test_run(struct uprobe_multi *skel, struct child *child ASSERT_EQ(skel->bss->uprobe_multi_sleep_result, 6, "uprobe_multi_sleep_result"); - if (child) + ASSERT_FALSE(skel->bss->bad_pid_seen, "bad_pid_seen"); + + if (child) { ASSERT_EQ(skel->bss->child_pid, child->pid, "uprobe_multi_child_pid"); + ASSERT_EQ(skel->bss->child_tid, child->tid, "uprobe_multi_child_tid"); + } } static void test_skel_api(void) @@ -190,8 +278,24 @@ __test_attach_api(const char *binary, const char *pattern, struct bpf_uprobe_mul if (!ASSERT_OK_PTR(skel->links.uprobe_extra, "bpf_program__attach_uprobe_multi")) goto cleanup; + /* Attach (uprobe-backed) USDTs */ + skel->links.usdt_pid = bpf_program__attach_usdt(skel->progs.usdt_pid, pid, binary, + "test", "pid_filter_usdt", NULL); + if (!ASSERT_OK_PTR(skel->links.usdt_pid, "attach_usdt_pid")) + goto cleanup; + + skel->links.usdt_extra = bpf_program__attach_usdt(skel->progs.usdt_extra, -1, binary, + "test", "pid_filter_usdt", NULL); + if (!ASSERT_OK_PTR(skel->links.usdt_extra, "attach_usdt_extra")) + goto cleanup; + uprobe_multi_test_run(skel, child); + ASSERT_FALSE(skel->bss->bad_pid_seen_usdt, "bad_pid_seen_usdt"); + if (child) { + ASSERT_EQ(skel->bss->child_pid_usdt, child->pid, "usdt_multi_child_pid"); + ASSERT_EQ(skel->bss->child_tid_usdt, child->tid, "usdt_multi_child_tid"); + } cleanup: uprobe_multi__destroy(skel); } @@ -210,6 +314,13 @@ test_attach_api(const char *binary, const char *pattern, struct bpf_uprobe_multi return; __test_attach_api(binary, pattern, opts, child); + + /* pid filter (thread) */ + child = spawn_thread(); + if (!ASSERT_OK_PTR(child, "spawn_thread")) + return; + + __test_attach_api(binary, pattern, opts, child); } static void test_attach_api_pattern(void) @@ -397,7 +508,7 @@ static void test_attach_api_fails(void) link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts); if (!ASSERT_ERR(link_fd, "link_fd")) goto cleanup; - ASSERT_EQ(link_fd, -ESRCH, "pid_is_wrong"); + ASSERT_EQ(link_fd, -EINVAL, "pid_is_wrong"); cleanup: if (link_fd >= 0) @@ -495,6 +606,13 @@ static void test_link_api(void) return; __test_link_api(child); + + /* pid filter (thread) */ + child = spawn_thread(); + if (!ASSERT_OK_PTR(child, "spawn_thread")) + return; + + __test_link_api(child); } static void test_bench_attach_uprobe(void) diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c index c60db8beeb73..1c9c4ec1be11 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier.c @@ -67,6 +67,7 @@ #include "verifier_search_pruning.skel.h" #include "verifier_sock.skel.h" #include "verifier_sock_addr.skel.h" +#include "verifier_sockmap_mutate.skel.h" #include "verifier_spill_fill.skel.h" #include "verifier_spin_lock.skel.h" #include "verifier_stack_ptr.skel.h" @@ -183,6 +184,7 @@ void test_verifier_sdiv(void) { RUN(verifier_sdiv); } void test_verifier_search_pruning(void) { RUN(verifier_search_pruning); } void test_verifier_sock(void) { RUN(verifier_sock); } void test_verifier_sock_addr(void) { RUN(verifier_sock_addr); } +void test_verifier_sockmap_mutate(void) { RUN(verifier_sockmap_mutate); } void test_verifier_spill_fill(void) { RUN(verifier_spill_fill); } void test_verifier_spin_lock(void) { RUN(verifier_spin_lock); } void test_verifier_stack_ptr(void) { RUN(verifier_stack_ptr); } diff --git a/tools/testing/selftests/bpf/progs/test_tc_link.c b/tools/testing/selftests/bpf/progs/test_tc_link.c index 992400acb957..ab3eae3d6af8 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_link.c +++ b/tools/testing/selftests/bpf/progs/test_tc_link.c @@ -4,7 +4,8 @@ #include <linux/bpf.h> #include <linux/if_ether.h> - +#include <linux/stddef.h> +#include <linux/if_packet.h> #include <bpf/bpf_endian.h> #include <bpf/bpf_helpers.h> @@ -16,7 +17,13 @@ bool seen_tc3; bool seen_tc4; bool seen_tc5; bool seen_tc6; +bool seen_tc7; + +bool set_type; + bool seen_eth; +bool seen_host; +bool seen_mcast; SEC("tc/ingress") int tc1(struct __sk_buff *skb) @@ -28,8 +35,16 @@ int tc1(struct __sk_buff *skb) if (bpf_skb_load_bytes(skb, 0, ð, sizeof(eth))) goto out; seen_eth = eth.h_proto == bpf_htons(ETH_P_IP); + seen_host = skb->pkt_type == PACKET_HOST; + if (seen_host && set_type) { + eth.h_dest[0] = 4; + if (bpf_skb_store_bytes(skb, 0, ð, sizeof(eth), 0)) + goto fail; + bpf_skb_change_type(skb, PACKET_MULTICAST); + } out: seen_tc1 = true; +fail: return TCX_NEXT; } @@ -67,3 +82,21 @@ int tc6(struct __sk_buff *skb) seen_tc6 = true; return TCX_PASS; } + +SEC("tc/ingress") +int tc7(struct __sk_buff *skb) +{ + struct ethhdr eth = {}; + + if (skb->protocol != __bpf_constant_htons(ETH_P_IP)) + goto out; + if (bpf_skb_load_bytes(skb, 0, ð, sizeof(eth))) + goto out; + if (eth.h_dest[0] == 4 && set_type) { + seen_mcast = skb->pkt_type == PACKET_MULTICAST; + bpf_skb_change_type(skb, PACKET_HOST); + } +out: + seen_tc7 = true; + return TCX_PASS; +} diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi.c b/tools/testing/selftests/bpf/progs/uprobe_multi.c index 419d9aa28fce..44190efcdba2 100644 --- a/tools/testing/selftests/bpf/progs/uprobe_multi.c +++ b/tools/testing/selftests/bpf/progs/uprobe_multi.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 -#include <linux/bpf.h> +#include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include <stdbool.h> +#include <bpf/usdt.bpf.h> char _license[] SEC("license") = "GPL"; @@ -22,6 +22,13 @@ __u64 uprobe_multi_sleep_result = 0; int pid = 0; int child_pid = 0; +int child_tid = 0; +int child_pid_usdt = 0; +int child_tid_usdt = 0; + +int expect_pid = 0; +bool bad_pid_seen = false; +bool bad_pid_seen_usdt = false; bool test_cookie = false; void *user_ptr = 0; @@ -36,11 +43,19 @@ static __always_inline bool verify_sleepable_user_copy(void) static void uprobe_multi_check(void *ctx, bool is_return, bool is_sleep) { - child_pid = bpf_get_current_pid_tgid() >> 32; + __u64 cur_pid_tgid = bpf_get_current_pid_tgid(); + __u32 cur_pid; - if (pid && child_pid != pid) + cur_pid = cur_pid_tgid >> 32; + if (pid && cur_pid != pid) return; + if (expect_pid && cur_pid != expect_pid) + bad_pid_seen = true; + + child_pid = cur_pid_tgid >> 32; + child_tid = (__u32)cur_pid_tgid; + __u64 cookie = test_cookie ? bpf_get_attach_cookie(ctx) : 0; __u64 addr = bpf_get_func_ip(ctx); @@ -97,5 +112,32 @@ int uretprobe_sleep(struct pt_regs *ctx) SEC("uprobe.multi//proc/self/exe:uprobe_multi_func_*") int uprobe_extra(struct pt_regs *ctx) { + /* we need this one just to mix PID-filtered and global uprobes */ + return 0; +} + +SEC("usdt") +int usdt_pid(struct pt_regs *ctx) +{ + __u64 cur_pid_tgid = bpf_get_current_pid_tgid(); + __u32 cur_pid; + + cur_pid = cur_pid_tgid >> 32; + if (pid && cur_pid != pid) + return 0; + + if (expect_pid && cur_pid != expect_pid) + bad_pid_seen_usdt = true; + + child_pid_usdt = cur_pid_tgid >> 32; + child_tid_usdt = (__u32)cur_pid_tgid; + + return 0; +} + +SEC("usdt") +int usdt_extra(struct pt_regs *ctx) +{ + /* we need this one just to mix PID-filtered and global USDT probes */ return 0; } diff --git a/tools/testing/selftests/bpf/progs/verifier_sockmap_mutate.c b/tools/testing/selftests/bpf/progs/verifier_sockmap_mutate.c new file mode 100644 index 000000000000..fe4b123187b8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_sockmap_mutate.c @@ -0,0 +1,187 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#include "bpf_misc.h" + +#define __always_unused __attribute__((unused)) + +char _license[] SEC("license") = "GPL"; + +struct sock { +} __attribute__((preserve_access_index)); + +struct bpf_iter__sockmap { + union { + struct sock *sk; + }; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKHASH); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} sockhash SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} sockmap SEC(".maps"); + +enum { CG_OK = 1 }; + +int zero = 0; + +static __always_inline void test_sockmap_delete(void) +{ + bpf_map_delete_elem(&sockmap, &zero); + bpf_map_delete_elem(&sockhash, &zero); +} + +static __always_inline void test_sockmap_update(void *sk) +{ + if (sk) { + bpf_map_update_elem(&sockmap, &zero, sk, BPF_ANY); + bpf_map_update_elem(&sockhash, &zero, sk, BPF_ANY); + } +} + +static __always_inline void test_sockmap_lookup_and_update(void) +{ + struct bpf_sock *sk = bpf_map_lookup_elem(&sockmap, &zero); + + if (sk) { + test_sockmap_update(sk); + bpf_sk_release(sk); + } +} + +static __always_inline void test_sockmap_mutate(void *sk) +{ + test_sockmap_delete(); + test_sockmap_update(sk); +} + +static __always_inline void test_sockmap_lookup_and_mutate(void) +{ + test_sockmap_delete(); + test_sockmap_lookup_and_update(); +} + +SEC("action") +__success +int test_sched_act(struct __sk_buff *skb) +{ + test_sockmap_mutate(skb->sk); + return 0; +} + +SEC("classifier") +__success +int test_sched_cls(struct __sk_buff *skb) +{ + test_sockmap_mutate(skb->sk); + return 0; +} + +SEC("flow_dissector") +__success +int test_flow_dissector_delete(struct __sk_buff *skb __always_unused) +{ + test_sockmap_delete(); + return 0; +} + +SEC("flow_dissector") +__failure __msg("program of this type cannot use helper bpf_sk_release") +int test_flow_dissector_update(struct __sk_buff *skb __always_unused) +{ + test_sockmap_lookup_and_update(); /* no access to skb->sk */ + return 0; +} + +SEC("iter/sockmap") +__success +int test_trace_iter(struct bpf_iter__sockmap *ctx) +{ + test_sockmap_mutate(ctx->sk); + return 0; +} + +SEC("raw_tp/kfree") +__failure __msg("cannot update sockmap in this context") +int test_raw_tp_delete(const void *ctx __always_unused) +{ + test_sockmap_delete(); + return 0; +} + +SEC("raw_tp/kfree") +__failure __msg("cannot update sockmap in this context") +int test_raw_tp_update(const void *ctx __always_unused) +{ + test_sockmap_lookup_and_update(); + return 0; +} + +SEC("sk_lookup") +__success +int test_sk_lookup(struct bpf_sk_lookup *ctx) +{ + test_sockmap_mutate(ctx->sk); + return 0; +} + +SEC("sk_reuseport") +__success +int test_sk_reuseport(struct sk_reuseport_md *ctx) +{ + test_sockmap_mutate(ctx->sk); + return 0; +} + +SEC("socket") +__success +int test_socket_filter(struct __sk_buff *skb) +{ + test_sockmap_mutate(skb->sk); + return 0; +} + +SEC("sockops") +__success +int test_sockops_delete(struct bpf_sock_ops *ctx __always_unused) +{ + test_sockmap_delete(); + return CG_OK; +} + +SEC("sockops") +__failure __msg("cannot update sockmap in this context") +int test_sockops_update(struct bpf_sock_ops *ctx) +{ + test_sockmap_update(ctx->sk); + return CG_OK; +} + +SEC("sockops") +__success +int test_sockops_update_dedicated(struct bpf_sock_ops *ctx) +{ + bpf_sock_map_update(ctx, &sockmap, &zero, BPF_ANY); + bpf_sock_hash_update(ctx, &sockhash, &zero, BPF_ANY); + return CG_OK; +} + +SEC("xdp") +__success +int test_xdp(struct xdp_md *ctx __always_unused) +{ + test_sockmap_lookup_and_mutate(); + return XDP_PASS; +} diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore index d26e962f2ac4..0b9ab987601c 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -47,3 +47,5 @@ mkdirty va_high_addr_switch hugetlb_fault_after_madv hugetlb_madv_vs_map +mseal_test +seal_elf diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 60b8feb6a5ec..3b49bc3d0a3b 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -59,6 +59,8 @@ TEST_GEN_FILES += mlock2-tests TEST_GEN_FILES += mrelease_test TEST_GEN_FILES += mremap_dontunmap TEST_GEN_FILES += mremap_test +TEST_GEN_FILES += mseal_test +TEST_GEN_FILES += seal_elf TEST_GEN_FILES += on-fault-limit TEST_GEN_FILES += pagemap_ioctl TEST_GEN_FILES += thuge-gen diff --git a/tools/testing/selftests/mm/compaction_test.c b/tools/testing/selftests/mm/compaction_test.c index 4f42eb7d7636..e140558e6f53 100644 --- a/tools/testing/selftests/mm/compaction_test.c +++ b/tools/testing/selftests/mm/compaction_test.c @@ -82,12 +82,16 @@ int prereq(void) return -1; } -int check_compaction(unsigned long mem_free, unsigned int hugepage_size) +int check_compaction(unsigned long mem_free, unsigned long hugepage_size, + unsigned long initial_nr_hugepages) { + unsigned long nr_hugepages_ul; int fd, ret = -1; int compaction_index = 0; - char initial_nr_hugepages[10] = {0}; - char nr_hugepages[10] = {0}; + char nr_hugepages[20] = {0}; + char init_nr_hugepages[20] = {0}; + + sprintf(init_nr_hugepages, "%lu", initial_nr_hugepages); /* We want to test with 80% of available memory. Else, OOM killer comes in to play */ @@ -101,21 +105,6 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size) goto out; } - if (read(fd, initial_nr_hugepages, sizeof(initial_nr_hugepages)) <= 0) { - ksft_print_msg("Failed to read from /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); - goto close_fd; - } - - /* Start with the initial condition of 0 huge pages*/ - if (write(fd, "0", sizeof(char)) != sizeof(char)) { - ksft_print_msg("Failed to write 0 to /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); - goto close_fd; - } - - lseek(fd, 0, SEEK_SET); - /* Request a large number of huge pages. The Kernel will allocate as much as it can */ if (write(fd, "100000", (6*sizeof(char))) != (6*sizeof(char))) { @@ -134,22 +123,27 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size) /* We should have been able to request at least 1/3 rd of the memory in huge pages */ - compaction_index = mem_free/(atoi(nr_hugepages) * hugepage_size); + nr_hugepages_ul = strtoul(nr_hugepages, NULL, 10); + if (!nr_hugepages_ul) { + ksft_print_msg("ERROR: No memory is available as huge pages\n"); + goto close_fd; + } + compaction_index = mem_free/(nr_hugepages_ul * hugepage_size); lseek(fd, 0, SEEK_SET); - if (write(fd, initial_nr_hugepages, strlen(initial_nr_hugepages)) - != strlen(initial_nr_hugepages)) { + if (write(fd, init_nr_hugepages, strlen(init_nr_hugepages)) + != strlen(init_nr_hugepages)) { ksft_print_msg("Failed to write value to /proc/sys/vm/nr_hugepages: %s\n", strerror(errno)); goto close_fd; } - ksft_print_msg("Number of huge pages allocated = %d\n", - atoi(nr_hugepages)); + ksft_print_msg("Number of huge pages allocated = %lu\n", + nr_hugepages_ul); if (compaction_index > 3) { - ksft_print_msg("ERROR: Less that 1/%d of memory is available\n" + ksft_print_msg("ERROR: Less than 1/%d of memory is available\n" "as huge pages\n", compaction_index); goto close_fd; } @@ -163,6 +157,41 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size) return ret; } +int set_zero_hugepages(unsigned long *initial_nr_hugepages) +{ + int fd, ret = -1; + char nr_hugepages[20] = {0}; + + fd = open("/proc/sys/vm/nr_hugepages", O_RDWR | O_NONBLOCK); + if (fd < 0) { + ksft_print_msg("Failed to open /proc/sys/vm/nr_hugepages: %s\n", + strerror(errno)); + goto out; + } + if (read(fd, nr_hugepages, sizeof(nr_hugepages)) <= 0) { + ksft_print_msg("Failed to read from /proc/sys/vm/nr_hugepages: %s\n", + strerror(errno)); + goto close_fd; + } + + lseek(fd, 0, SEEK_SET); + + /* Start with the initial condition of 0 huge pages */ + if (write(fd, "0", sizeof(char)) != sizeof(char)) { + ksft_print_msg("Failed to write 0 to /proc/sys/vm/nr_hugepages: %s\n", + strerror(errno)); + goto close_fd; + } + + *initial_nr_hugepages = strtoul(nr_hugepages, NULL, 10); + ret = 0; + + close_fd: + close(fd); + + out: + return ret; +} int main(int argc, char **argv) { @@ -173,6 +202,7 @@ int main(int argc, char **argv) unsigned long mem_free = 0; unsigned long hugepage_size = 0; long mem_fragmentable_MB = 0; + unsigned long initial_nr_hugepages; ksft_print_header(); @@ -181,6 +211,10 @@ int main(int argc, char **argv) ksft_set_plan(1); + /* Start the test without hugepages reducing mem_free */ + if (set_zero_hugepages(&initial_nr_hugepages)) + ksft_exit_fail(); + lim.rlim_cur = RLIM_INFINITY; lim.rlim_max = RLIM_INFINITY; if (setrlimit(RLIMIT_MEMLOCK, &lim)) @@ -224,7 +258,8 @@ int main(int argc, char **argv) entry = entry->next; } - if (check_compaction(mem_free, hugepage_size) == 0) + if (check_compaction(mem_free, hugepage_size, + initial_nr_hugepages) == 0) ksft_exit_pass(); ksft_exit_fail(); diff --git a/tools/testing/selftests/mm/gup_test.c b/tools/testing/selftests/mm/gup_test.c index bd335cf9bc0e..bdeaac67ff9a 100644 --- a/tools/testing/selftests/mm/gup_test.c +++ b/tools/testing/selftests/mm/gup_test.c @@ -1,3 +1,4 @@ +#define __SANE_USERSPACE_TYPES__ // Use ll64 #include <fcntl.h> #include <errno.h> #include <stdio.h> diff --git a/tools/testing/selftests/mm/mseal_test.c b/tools/testing/selftests/mm/mseal_test.c new file mode 100644 index 000000000000..41998cf1dcf5 --- /dev/null +++ b/tools/testing/selftests/mm/mseal_test.c @@ -0,0 +1,1894 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#include <linux/mman.h> +#include <sys/mman.h> +#include <stdint.h> +#include <unistd.h> +#include <string.h> +#include <sys/time.h> +#include <sys/resource.h> +#include <stdbool.h> +#include "../kselftest.h" +#include <syscall.h> +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <fcntl.h> +#include <sys/ioctl.h> +#include <sys/vfs.h> +#include <sys/stat.h> + +/* + * need those definition for manually build using gcc. + * gcc -I ../../../../usr/include -DDEBUG -O3 -DDEBUG -O3 mseal_test.c -o mseal_test + */ +#ifndef PKEY_DISABLE_ACCESS +# define PKEY_DISABLE_ACCESS 0x1 +#endif + +#ifndef PKEY_DISABLE_WRITE +# define PKEY_DISABLE_WRITE 0x2 +#endif + +#ifndef PKEY_BITS_PER_PKEY +#define PKEY_BITS_PER_PKEY 2 +#endif + +#ifndef PKEY_MASK +#define PKEY_MASK (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE) +#endif + +#define FAIL_TEST_IF_FALSE(c) do {\ + if (!(c)) {\ + ksft_test_result_fail("%s, line:%d\n", __func__, __LINE__);\ + goto test_end;\ + } \ + } \ + while (0) + +#define SKIP_TEST_IF_FALSE(c) do {\ + if (!(c)) {\ + ksft_test_result_skip("%s, line:%d\n", __func__, __LINE__);\ + goto test_end;\ + } \ + } \ + while (0) + + +#define TEST_END_CHECK() {\ + ksft_test_result_pass("%s\n", __func__);\ + return;\ +test_end:\ + return;\ +} + +#ifndef u64 +#define u64 unsigned long long +#endif + +static unsigned long get_vma_size(void *addr, int *prot) +{ + FILE *maps; + char line[256]; + int size = 0; + uintptr_t addr_start, addr_end; + char protstr[5]; + *prot = 0; + + maps = fopen("/proc/self/maps", "r"); + if (!maps) + return 0; + + while (fgets(line, sizeof(line), maps)) { + if (sscanf(line, "%lx-%lx %4s", &addr_start, &addr_end, protstr) == 3) { + if (addr_start == (uintptr_t) addr) { + size = addr_end - addr_start; + if (protstr[0] == 'r') + *prot |= 0x4; + if (protstr[1] == 'w') + *prot |= 0x2; + if (protstr[2] == 'x') + *prot |= 0x1; + break; + } + } + } + fclose(maps); + return size; +} + +/* + * define sys_xyx to call syscall directly. + */ +static int sys_mseal(void *start, size_t len) +{ + int sret; + + errno = 0; + sret = syscall(__NR_mseal, start, len, 0); + return sret; +} + +static int sys_mprotect(void *ptr, size_t size, unsigned long prot) +{ + int sret; + + errno = 0; + sret = syscall(__NR_mprotect, ptr, size, prot); + return sret; +} + +static int sys_mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot, + unsigned long pkey) +{ + int sret; + + errno = 0; + sret = syscall(__NR_pkey_mprotect, ptr, size, orig_prot, pkey); + return sret; +} + +static void *sys_mmap(void *addr, unsigned long len, unsigned long prot, + unsigned long flags, unsigned long fd, unsigned long offset) +{ + void *sret; + + errno = 0; + sret = (void *) syscall(__NR_mmap, addr, len, prot, + flags, fd, offset); + return sret; +} + +static int sys_munmap(void *ptr, size_t size) +{ + int sret; + + errno = 0; + sret = syscall(__NR_munmap, ptr, size); + return sret; +} + +static int sys_madvise(void *start, size_t len, int types) +{ + int sret; + + errno = 0; + sret = syscall(__NR_madvise, start, len, types); + return sret; +} + +static int sys_pkey_alloc(unsigned long flags, unsigned long init_val) +{ + int ret = syscall(__NR_pkey_alloc, flags, init_val); + + return ret; +} + +static unsigned int __read_pkey_reg(void) +{ + unsigned int pkey_reg = 0; +#if defined(__i386__) || defined(__x86_64__) /* arch */ + unsigned int eax, edx; + unsigned int ecx = 0; + + asm volatile(".byte 0x0f,0x01,0xee\n\t" + : "=a" (eax), "=d" (edx) + : "c" (ecx)); + pkey_reg = eax; +#endif + return pkey_reg; +} + +static void __write_pkey_reg(u64 pkey_reg) +{ +#if defined(__i386__) || defined(__x86_64__) /* arch */ + unsigned int eax = pkey_reg; + unsigned int ecx = 0; + unsigned int edx = 0; + + asm volatile(".byte 0x0f,0x01,0xef\n\t" + : : "a" (eax), "c" (ecx), "d" (edx)); +#endif +} + +static unsigned long pkey_bit_position(int pkey) +{ + return pkey * PKEY_BITS_PER_PKEY; +} + +static u64 set_pkey_bits(u64 reg, int pkey, u64 flags) +{ + unsigned long shift = pkey_bit_position(pkey); + + /* mask out bits from pkey in old value */ + reg &= ~((u64)PKEY_MASK << shift); + /* OR in new bits for pkey */ + reg |= (flags & PKEY_MASK) << shift; + return reg; +} + +static void set_pkey(int pkey, unsigned long pkey_value) +{ + u64 new_pkey_reg; + + new_pkey_reg = set_pkey_bits(__read_pkey_reg(), pkey, pkey_value); + __write_pkey_reg(new_pkey_reg); +} + +static void setup_single_address(int size, void **ptrOut) +{ + void *ptr; + + ptr = sys_mmap(NULL, size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + *ptrOut = ptr; +} + +static void setup_single_address_rw(int size, void **ptrOut) +{ + void *ptr; + unsigned long mapflags = MAP_ANONYMOUS | MAP_PRIVATE; + + ptr = sys_mmap(NULL, size, PROT_READ | PROT_WRITE, mapflags, -1, 0); + *ptrOut = ptr; +} + +static int clean_single_address(void *ptr, int size) +{ + int ret; + ret = munmap(ptr, size); + return ret; +} + +static int seal_single_address(void *ptr, int size) +{ + int ret; + ret = sys_mseal(ptr, size); + return ret; +} + +bool seal_support(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + + ptr = sys_mmap(NULL, page_size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + if (ptr == (void *) -1) + return false; + + ret = sys_mseal(ptr, page_size); + if (ret < 0) + return false; + + return true; +} + +bool pkey_supported(void) +{ +#if defined(__i386__) || defined(__x86_64__) /* arch */ + int pkey = sys_pkey_alloc(0, 0); + + if (pkey > 0) + return true; +#endif + return false; +} + +static void test_seal_addseal(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_unmapped_start(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* munmap 2 pages from ptr. */ + ret = sys_munmap(ptr, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* mprotect will fail because 2 pages from ptr are unmapped. */ + ret = sys_mprotect(ptr, size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(ret < 0); + + /* mseal will fail because 2 pages from ptr are unmapped. */ + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(ret < 0); + + ret = sys_mseal(ptr + 2 * page_size, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_unmapped_middle(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* munmap 2 pages from ptr + page. */ + ret = sys_munmap(ptr + page_size, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* mprotect will fail, since middle 2 pages are unmapped. */ + ret = sys_mprotect(ptr, size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(ret < 0); + + /* mseal will fail as well. */ + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(ret < 0); + + /* we still can add seal to the first page and last page*/ + ret = sys_mseal(ptr, page_size); + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_mseal(ptr + 3 * page_size, page_size); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_unmapped_end(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* unmap last 2 pages. */ + ret = sys_munmap(ptr + 2 * page_size, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* mprotect will fail since last 2 pages are unmapped. */ + ret = sys_mprotect(ptr, size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(ret < 0); + + /* mseal will fail as well. */ + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(ret < 0); + + /* The first 2 pages is not sealed, and can add seals */ + ret = sys_mseal(ptr, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_multiple_vmas(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split the vma into 3. */ + ret = sys_mprotect(ptr + page_size, 2 * page_size, + PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* mprotect will get applied to all 4 pages - 3 VMAs. */ + ret = sys_mprotect(ptr, size, PROT_READ); + FAIL_TEST_IF_FALSE(!ret); + + /* use mprotect to split the vma into 3. */ + ret = sys_mprotect(ptr + page_size, 2 * page_size, + PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* mseal get applied to all 4 pages - 3 VMAs. */ + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_split_start(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split at middle */ + ret = sys_mprotect(ptr, 2 * page_size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* seal the first page, this will split the VMA */ + ret = sys_mseal(ptr, page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* add seal to the remain 3 pages */ + ret = sys_mseal(ptr + page_size, 3 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_split_end(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split at middle */ + ret = sys_mprotect(ptr, 2 * page_size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* seal the last page */ + ret = sys_mseal(ptr + 3 * page_size, page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* Adding seals to the first 3 pages */ + ret = sys_mseal(ptr, 3 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_invalid_input(void) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(8 * page_size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + ret = clean_single_address(ptr + 4 * page_size, 4 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* invalid flag */ + ret = syscall(__NR_mseal, ptr, size, 0x20); + FAIL_TEST_IF_FALSE(ret < 0); + + /* unaligned address */ + ret = sys_mseal(ptr + 1, 2 * page_size); + FAIL_TEST_IF_FALSE(ret < 0); + + /* length too big */ + ret = sys_mseal(ptr, 5 * page_size); + FAIL_TEST_IF_FALSE(ret < 0); + + /* length overflow */ + ret = sys_mseal(ptr, UINT64_MAX/page_size); + FAIL_TEST_IF_FALSE(ret < 0); + + /* start is not in a valid VMA */ + ret = sys_mseal(ptr - page_size, 5 * page_size); + FAIL_TEST_IF_FALSE(ret < 0); + + TEST_END_CHECK(); +} + +static void test_seal_zero_length(void) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + ret = sys_mprotect(ptr, 0, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* seal 0 length will be OK, same as mprotect */ + ret = sys_mseal(ptr, 0); + FAIL_TEST_IF_FALSE(!ret); + + /* verify the 4 pages are not sealed by previous call. */ + ret = sys_mprotect(ptr, size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_zero_address(void) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + int prot; + + /* use mmap to change protection. */ + ptr = sys_mmap(0, size, PROT_NONE, + MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0); + FAIL_TEST_IF_FALSE(ptr == 0); + + size = get_vma_size(ptr, &prot); + FAIL_TEST_IF_FALSE(size == 4 * page_size); + + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + + /* verify the 4 pages are sealed by previous call. */ + ret = sys_mprotect(ptr, size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(ret); + + TEST_END_CHECK(); +} + +static void test_seal_twice(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + + /* apply the same seal will be OK. idempotent. */ + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_mprotect(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = seal_single_address(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + ret = sys_mprotect(ptr, size, PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_start_mprotect(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = seal_single_address(ptr, page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* the first page is sealed. */ + ret = sys_mprotect(ptr, page_size, PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + /* pages after the first page is not sealed. */ + ret = sys_mprotect(ptr + page_size, page_size * 3, + PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_end_mprotect(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = seal_single_address(ptr + page_size, 3 * page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* first page is not sealed */ + ret = sys_mprotect(ptr, page_size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* last 3 page are sealed */ + ret = sys_mprotect(ptr + page_size, page_size * 3, + PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_mprotect_unalign_len(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = seal_single_address(ptr, page_size * 2 - 1); + FAIL_TEST_IF_FALSE(!ret); + } + + /* 2 pages are sealed. */ + ret = sys_mprotect(ptr, page_size * 2, PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_mprotect(ptr + page_size * 2, page_size, + PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_mprotect_unalign_len_variant_2(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + if (seal) { + ret = seal_single_address(ptr, page_size * 2 + 1); + FAIL_TEST_IF_FALSE(!ret); + } + + /* 3 pages are sealed. */ + ret = sys_mprotect(ptr, page_size * 3, PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_mprotect(ptr + page_size * 3, page_size, + PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_mprotect_two_vma(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split */ + ret = sys_mprotect(ptr, page_size * 2, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + if (seal) { + ret = seal_single_address(ptr, page_size * 4); + FAIL_TEST_IF_FALSE(!ret); + } + + ret = sys_mprotect(ptr, page_size * 2, PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_mprotect(ptr + page_size * 2, page_size * 2, + PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_mprotect_two_vma_with_split(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split as two vma. */ + ret = sys_mprotect(ptr, page_size * 2, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* mseal can apply across 2 vma, also split them. */ + if (seal) { + ret = seal_single_address(ptr + page_size, page_size * 2); + FAIL_TEST_IF_FALSE(!ret); + } + + /* the first page is not sealed. */ + ret = sys_mprotect(ptr, page_size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* the second page is sealed. */ + ret = sys_mprotect(ptr + page_size, page_size, PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + /* the third page is sealed. */ + ret = sys_mprotect(ptr + 2 * page_size, page_size, + PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + /* the fouth page is not sealed. */ + ret = sys_mprotect(ptr + 3 * page_size, page_size, + PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_mprotect_partial_mprotect(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* seal one page. */ + if (seal) { + ret = seal_single_address(ptr, page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* mprotect first 2 page will fail, since the first page are sealed. */ + ret = sys_mprotect(ptr, 2 * page_size, PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_mprotect_two_vma_with_gap(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split. */ + ret = sys_mprotect(ptr, page_size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* use mprotect to split. */ + ret = sys_mprotect(ptr + 3 * page_size, page_size, + PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* use munmap to free two pages in the middle */ + ret = sys_munmap(ptr + page_size, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* mprotect will fail, because there is a gap in the address. */ + /* notes, internally mprotect still updated the first page. */ + ret = sys_mprotect(ptr, 4 * page_size, PROT_READ); + FAIL_TEST_IF_FALSE(ret < 0); + + /* mseal will fail as well. */ + ret = sys_mseal(ptr, 4 * page_size); + FAIL_TEST_IF_FALSE(ret < 0); + + /* the first page is not sealed. */ + ret = sys_mprotect(ptr, page_size, PROT_READ); + FAIL_TEST_IF_FALSE(ret == 0); + + /* the last page is not sealed. */ + ret = sys_mprotect(ptr + 3 * page_size, page_size, PROT_READ); + FAIL_TEST_IF_FALSE(ret == 0); + + TEST_END_CHECK(); +} + +static void test_seal_mprotect_split(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split. */ + ret = sys_mprotect(ptr, page_size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* seal all 4 pages. */ + if (seal) { + ret = sys_mseal(ptr, 4 * page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* mprotect is sealed. */ + ret = sys_mprotect(ptr, 2 * page_size, PROT_READ); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + + ret = sys_mprotect(ptr + 2 * page_size, 2 * page_size, PROT_READ); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_mprotect_merge(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split one page. */ + ret = sys_mprotect(ptr, page_size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* seal first two pages. */ + if (seal) { + ret = sys_mseal(ptr, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* 2 pages are sealed. */ + ret = sys_mprotect(ptr, 2 * page_size, PROT_READ); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + /* last 2 pages are not sealed. */ + ret = sys_mprotect(ptr + 2 * page_size, 2 * page_size, PROT_READ); + FAIL_TEST_IF_FALSE(ret == 0); + + TEST_END_CHECK(); +} + +static void test_seal_munmap(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* 4 pages are sealed. */ + ret = sys_munmap(ptr, size); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +/* + * allocate 4 pages, + * use mprotect to split it as two VMAs + * seal the whole range + * munmap will fail on both + */ +static void test_seal_munmap_two_vma(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split */ + ret = sys_mprotect(ptr, page_size * 2, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + ret = sys_munmap(ptr, page_size * 2); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_munmap(ptr + page_size, page_size * 2); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +/* + * allocate a VMA with 4 pages. + * munmap the middle 2 pages. + * seal the whole 4 pages, will fail. + * munmap the first page will be OK. + * munmap the last page will be OK. + */ +static void test_seal_munmap_vma_with_gap(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + ret = sys_munmap(ptr + page_size, page_size * 2); + FAIL_TEST_IF_FALSE(!ret); + + if (seal) { + /* can't have gap in the middle. */ + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(ret < 0); + } + + ret = sys_munmap(ptr, page_size); + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_munmap(ptr + page_size * 2, page_size); + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_munmap(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_munmap_start_freed(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + int prot; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* unmap the first page. */ + ret = sys_munmap(ptr, page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* seal the last 3 pages. */ + if (seal) { + ret = sys_mseal(ptr + page_size, 3 * page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* unmap from the first page. */ + ret = sys_munmap(ptr, size); + if (seal) { + FAIL_TEST_IF_FALSE(ret < 0); + + size = get_vma_size(ptr + page_size, &prot); + FAIL_TEST_IF_FALSE(size == page_size * 3); + } else { + /* note: this will be OK, even the first page is */ + /* already unmapped. */ + FAIL_TEST_IF_FALSE(!ret); + + size = get_vma_size(ptr + page_size, &prot); + FAIL_TEST_IF_FALSE(size == 0); + } + + TEST_END_CHECK(); +} + +static void test_munmap_end_freed(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* unmap last page. */ + ret = sys_munmap(ptr + page_size * 3, page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* seal the first 3 pages. */ + if (seal) { + ret = sys_mseal(ptr, 3 * page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* unmap all pages. */ + ret = sys_munmap(ptr, size); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_munmap_middle_freed(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + int prot; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* unmap 2 pages in the middle. */ + ret = sys_munmap(ptr + page_size, page_size * 2); + FAIL_TEST_IF_FALSE(!ret); + + /* seal the first page. */ + if (seal) { + ret = sys_mseal(ptr, page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* munmap all 4 pages. */ + ret = sys_munmap(ptr, size); + if (seal) { + FAIL_TEST_IF_FALSE(ret < 0); + + size = get_vma_size(ptr, &prot); + FAIL_TEST_IF_FALSE(size == page_size); + + size = get_vma_size(ptr + page_size * 3, &prot); + FAIL_TEST_IF_FALSE(size == page_size); + } else { + FAIL_TEST_IF_FALSE(!ret); + + size = get_vma_size(ptr, &prot); + FAIL_TEST_IF_FALSE(size == 0); + + size = get_vma_size(ptr + page_size * 3, &prot); + FAIL_TEST_IF_FALSE(size == 0); + } + + TEST_END_CHECK(); +} + +static void test_seal_mremap_shrink(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* shrink from 4 pages to 2 pages. */ + ret2 = mremap(ptr, size, 2 * page_size, 0, 0); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else { + FAIL_TEST_IF_FALSE(ret2 != MAP_FAILED); + + } + + TEST_END_CHECK(); +} + +static void test_seal_mremap_expand(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + /* ummap last 2 pages. */ + ret = sys_munmap(ptr + 2 * page_size, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + if (seal) { + ret = sys_mseal(ptr, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* expand from 2 page to 4 pages. */ + ret2 = mremap(ptr, 2 * page_size, 4 * page_size, 0, 0); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else { + FAIL_TEST_IF_FALSE(ret2 == ptr); + + } + + TEST_END_CHECK(); +} + +static void test_seal_mremap_move(bool seal) +{ + void *ptr, *newPtr; + unsigned long page_size = getpagesize(); + unsigned long size = page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + setup_single_address(size, &newPtr); + FAIL_TEST_IF_FALSE(newPtr != (void *)-1); + ret = clean_single_address(newPtr, size); + FAIL_TEST_IF_FALSE(!ret); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* move from ptr to fixed address. */ + ret2 = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_FIXED, newPtr); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else { + FAIL_TEST_IF_FALSE(ret2 != MAP_FAILED); + + } + + TEST_END_CHECK(); +} + +static void test_seal_mmap_overwrite_prot(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* use mmap to change protection. */ + ret2 = sys_mmap(ptr, size, PROT_NONE, + MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else + FAIL_TEST_IF_FALSE(ret2 == ptr); + + TEST_END_CHECK(); +} + +static void test_seal_mmap_expand(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 12 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + /* ummap last 4 pages. */ + ret = sys_munmap(ptr + 8 * page_size, 4 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + if (seal) { + ret = sys_mseal(ptr, 8 * page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* use mmap to expand. */ + ret2 = sys_mmap(ptr, size, PROT_READ, + MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else + FAIL_TEST_IF_FALSE(ret2 == ptr); + + TEST_END_CHECK(); +} + +static void test_seal_mmap_shrink(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 12 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* use mmap to shrink. */ + ret2 = sys_mmap(ptr, 8 * page_size, PROT_READ, + MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else + FAIL_TEST_IF_FALSE(ret2 == ptr); + + TEST_END_CHECK(); +} + +static void test_seal_mremap_shrink_fixed(bool seal) +{ + void *ptr; + void *newAddr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + setup_single_address(size, &newAddr); + FAIL_TEST_IF_FALSE(newAddr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* mremap to move and shrink to fixed address */ + ret2 = mremap(ptr, size, 2 * page_size, MREMAP_MAYMOVE | MREMAP_FIXED, + newAddr); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else + FAIL_TEST_IF_FALSE(ret2 == newAddr); + + TEST_END_CHECK(); +} + +static void test_seal_mremap_expand_fixed(bool seal) +{ + void *ptr; + void *newAddr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + void *ret2; + + setup_single_address(page_size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + setup_single_address(size, &newAddr); + FAIL_TEST_IF_FALSE(newAddr != (void *)-1); + + if (seal) { + ret = sys_mseal(newAddr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* mremap to move and expand to fixed address */ + ret2 = mremap(ptr, page_size, size, MREMAP_MAYMOVE | MREMAP_FIXED, + newAddr); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else + FAIL_TEST_IF_FALSE(ret2 == newAddr); + + TEST_END_CHECK(); +} + +static void test_seal_mremap_move_fixed(bool seal) +{ + void *ptr; + void *newAddr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + setup_single_address(size, &newAddr); + FAIL_TEST_IF_FALSE(newAddr != (void *)-1); + + if (seal) { + ret = sys_mseal(newAddr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* mremap to move to fixed address */ + ret2 = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_FIXED, newAddr); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else + FAIL_TEST_IF_FALSE(ret2 == newAddr); + + TEST_END_CHECK(); +} + +static void test_seal_mremap_move_fixed_zero(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* + * MREMAP_FIXED can move the mapping to zero address + */ + ret2 = mremap(ptr, size, 2 * page_size, MREMAP_MAYMOVE | MREMAP_FIXED, + 0); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else { + FAIL_TEST_IF_FALSE(ret2 == 0); + + } + + TEST_END_CHECK(); +} + +static void test_seal_mremap_move_dontunmap(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* mremap to move, and don't unmap src addr. */ + ret2 = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_DONTUNMAP, 0); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else { + FAIL_TEST_IF_FALSE(ret2 != MAP_FAILED); + + } + + TEST_END_CHECK(); +} + +static void test_seal_mremap_move_dontunmap_anyaddr(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* + * The 0xdeaddead should not have effect on dest addr + * when MREMAP_DONTUNMAP is set. + */ + ret2 = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_DONTUNMAP, + 0xdeaddead); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else { + FAIL_TEST_IF_FALSE(ret2 != MAP_FAILED); + FAIL_TEST_IF_FALSE((long)ret2 != 0xdeaddead); + + } + + TEST_END_CHECK(); +} + + +static void test_seal_merge_and_split(void) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size; + int ret; + int prot; + + /* (24 RO) */ + setup_single_address(24 * page_size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect(NONE) to set out boundary */ + /* (1 NONE) (22 RO) (1 NONE) */ + ret = sys_mprotect(ptr, page_size, PROT_NONE); + FAIL_TEST_IF_FALSE(!ret); + ret = sys_mprotect(ptr + 23 * page_size, page_size, PROT_NONE); + FAIL_TEST_IF_FALSE(!ret); + size = get_vma_size(ptr + page_size, &prot); + FAIL_TEST_IF_FALSE(size == 22 * page_size); + FAIL_TEST_IF_FALSE(prot == 4); + + /* use mseal to split from beginning */ + /* (1 NONE) (1 RO_SEAL) (21 RO) (1 NONE) */ + ret = sys_mseal(ptr + page_size, page_size); + FAIL_TEST_IF_FALSE(!ret); + size = get_vma_size(ptr + page_size, &prot); + FAIL_TEST_IF_FALSE(size == page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + size = get_vma_size(ptr + 2 * page_size, &prot); + FAIL_TEST_IF_FALSE(size == 21 * page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + + /* use mseal to split from the end. */ + /* (1 NONE) (1 RO_SEAL) (20 RO) (1 RO_SEAL) (1 NONE) */ + ret = sys_mseal(ptr + 22 * page_size, page_size); + FAIL_TEST_IF_FALSE(!ret); + size = get_vma_size(ptr + 22 * page_size, &prot); + FAIL_TEST_IF_FALSE(size == page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + size = get_vma_size(ptr + 2 * page_size, &prot); + FAIL_TEST_IF_FALSE(size == 20 * page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + + /* merge with prev. */ + /* (1 NONE) (2 RO_SEAL) (19 RO) (1 RO_SEAL) (1 NONE) */ + ret = sys_mseal(ptr + 2 * page_size, page_size); + FAIL_TEST_IF_FALSE(!ret); + size = get_vma_size(ptr + page_size, &prot); + FAIL_TEST_IF_FALSE(size == 2 * page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + + /* merge with after. */ + /* (1 NONE) (2 RO_SEAL) (18 RO) (2 RO_SEALS) (1 NONE) */ + ret = sys_mseal(ptr + 21 * page_size, page_size); + FAIL_TEST_IF_FALSE(!ret); + size = get_vma_size(ptr + 21 * page_size, &prot); + FAIL_TEST_IF_FALSE(size == 2 * page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + + /* split and merge from prev */ + /* (1 NONE) (3 RO_SEAL) (17 RO) (2 RO_SEALS) (1 NONE) */ + ret = sys_mseal(ptr + 2 * page_size, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + size = get_vma_size(ptr + 1 * page_size, &prot); + FAIL_TEST_IF_FALSE(size == 3 * page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + ret = sys_munmap(ptr + page_size, page_size); + FAIL_TEST_IF_FALSE(ret < 0); + ret = sys_mprotect(ptr + 2 * page_size, page_size, PROT_NONE); + FAIL_TEST_IF_FALSE(ret < 0); + + /* split and merge from next */ + /* (1 NONE) (3 RO_SEAL) (16 RO) (3 RO_SEALS) (1 NONE) */ + ret = sys_mseal(ptr + 20 * page_size, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + FAIL_TEST_IF_FALSE(prot == 0x4); + size = get_vma_size(ptr + 20 * page_size, &prot); + FAIL_TEST_IF_FALSE(size == 3 * page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + + /* merge from middle of prev and middle of next. */ + /* (1 NONE) (22 RO_SEAL) (1 NONE) */ + ret = sys_mseal(ptr + 2 * page_size, 20 * page_size); + FAIL_TEST_IF_FALSE(!ret); + size = get_vma_size(ptr + page_size, &prot); + FAIL_TEST_IF_FALSE(size == 22 * page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + + TEST_END_CHECK(); +} + +static void test_seal_discard_ro_anon_on_rw(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address_rw(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* sealing doesn't take effect on RW memory. */ + ret = sys_madvise(ptr, size, MADV_DONTNEED); + FAIL_TEST_IF_FALSE(!ret); + + /* base seal still apply. */ + ret = sys_munmap(ptr, size); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_discard_ro_anon_on_pkey(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + int pkey; + + SKIP_TEST_IF_FALSE(pkey_supported()); + + setup_single_address_rw(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + pkey = sys_pkey_alloc(0, 0); + FAIL_TEST_IF_FALSE(pkey > 0); + + ret = sys_mprotect_pkey((void *)ptr, size, PROT_READ | PROT_WRITE, pkey); + FAIL_TEST_IF_FALSE(!ret); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* sealing doesn't take effect if PKRU allow write. */ + set_pkey(pkey, 0); + ret = sys_madvise(ptr, size, MADV_DONTNEED); + FAIL_TEST_IF_FALSE(!ret); + + /* sealing will take effect if PKRU deny write. */ + set_pkey(pkey, PKEY_DISABLE_WRITE); + ret = sys_madvise(ptr, size, MADV_DONTNEED); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + /* base seal still apply. */ + ret = sys_munmap(ptr, size); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_discard_ro_anon_on_filebacked(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + int fd; + unsigned long mapflags = MAP_PRIVATE; + + fd = memfd_create("test", 0); + FAIL_TEST_IF_FALSE(fd > 0); + + ret = fallocate(fd, 0, 0, size); + FAIL_TEST_IF_FALSE(!ret); + + ptr = sys_mmap(NULL, size, PROT_READ, mapflags, fd, 0); + FAIL_TEST_IF_FALSE(ptr != MAP_FAILED); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* sealing doesn't apply for file backed mapping. */ + ret = sys_madvise(ptr, size, MADV_DONTNEED); + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_munmap(ptr, size); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + close(fd); + + TEST_END_CHECK(); +} + +static void test_seal_discard_ro_anon_on_shared(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + unsigned long mapflags = MAP_ANONYMOUS | MAP_SHARED; + + ptr = sys_mmap(NULL, size, PROT_READ, mapflags, -1, 0); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* sealing doesn't apply for shared mapping. */ + ret = sys_madvise(ptr, size, MADV_DONTNEED); + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_munmap(ptr, size); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_discard_ro_anon(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = seal_single_address(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + ret = sys_madvise(ptr, size, MADV_DONTNEED); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_munmap(ptr, size); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +int main(int argc, char **argv) +{ + bool test_seal = seal_support(); + + ksft_print_header(); + + if (!test_seal) + ksft_exit_skip("sealing not supported, check CONFIG_64BIT\n"); + + if (!pkey_supported()) + ksft_print_msg("PKEY not supported\n"); + + ksft_set_plan(80); + + test_seal_addseal(); + test_seal_unmapped_start(); + test_seal_unmapped_middle(); + test_seal_unmapped_end(); + test_seal_multiple_vmas(); + test_seal_split_start(); + test_seal_split_end(); + test_seal_invalid_input(); + test_seal_zero_length(); + test_seal_twice(); + + test_seal_mprotect(false); + test_seal_mprotect(true); + + test_seal_start_mprotect(false); + test_seal_start_mprotect(true); + + test_seal_end_mprotect(false); + test_seal_end_mprotect(true); + + test_seal_mprotect_unalign_len(false); + test_seal_mprotect_unalign_len(true); + + test_seal_mprotect_unalign_len_variant_2(false); + test_seal_mprotect_unalign_len_variant_2(true); + + test_seal_mprotect_two_vma(false); + test_seal_mprotect_two_vma(true); + + test_seal_mprotect_two_vma_with_split(false); + test_seal_mprotect_two_vma_with_split(true); + + test_seal_mprotect_partial_mprotect(false); + test_seal_mprotect_partial_mprotect(true); + + test_seal_mprotect_two_vma_with_gap(false); + test_seal_mprotect_two_vma_with_gap(true); + + test_seal_mprotect_merge(false); + test_seal_mprotect_merge(true); + + test_seal_mprotect_split(false); + test_seal_mprotect_split(true); + + test_seal_munmap(false); + test_seal_munmap(true); + test_seal_munmap_two_vma(false); + test_seal_munmap_two_vma(true); + test_seal_munmap_vma_with_gap(false); + test_seal_munmap_vma_with_gap(true); + + test_munmap_start_freed(false); + test_munmap_start_freed(true); + test_munmap_middle_freed(false); + test_munmap_middle_freed(true); + test_munmap_end_freed(false); + test_munmap_end_freed(true); + + test_seal_mremap_shrink(false); + test_seal_mremap_shrink(true); + test_seal_mremap_expand(false); + test_seal_mremap_expand(true); + test_seal_mremap_move(false); + test_seal_mremap_move(true); + + test_seal_mremap_shrink_fixed(false); + test_seal_mremap_shrink_fixed(true); + test_seal_mremap_expand_fixed(false); + test_seal_mremap_expand_fixed(true); + test_seal_mremap_move_fixed(false); + test_seal_mremap_move_fixed(true); + test_seal_mremap_move_dontunmap(false); + test_seal_mremap_move_dontunmap(true); + test_seal_mremap_move_fixed_zero(false); + test_seal_mremap_move_fixed_zero(true); + test_seal_mremap_move_dontunmap_anyaddr(false); + test_seal_mremap_move_dontunmap_anyaddr(true); + test_seal_discard_ro_anon(false); + test_seal_discard_ro_anon(true); + test_seal_discard_ro_anon_on_rw(false); + test_seal_discard_ro_anon_on_rw(true); + test_seal_discard_ro_anon_on_shared(false); + test_seal_discard_ro_anon_on_shared(true); + test_seal_discard_ro_anon_on_filebacked(false); + test_seal_discard_ro_anon_on_filebacked(true); + test_seal_mmap_overwrite_prot(false); + test_seal_mmap_overwrite_prot(true); + test_seal_mmap_expand(false); + test_seal_mmap_expand(true); + test_seal_mmap_shrink(false); + test_seal_mmap_shrink(true); + + test_seal_merge_and_split(); + test_seal_zero_address(); + + test_seal_discard_ro_anon_on_pkey(false); + test_seal_discard_ro_anon_on_pkey(true); + + ksft_finished(); +} diff --git a/tools/testing/selftests/mm/seal_elf.c b/tools/testing/selftests/mm/seal_elf.c new file mode 100644 index 000000000000..f2babec79bb6 --- /dev/null +++ b/tools/testing/selftests/mm/seal_elf.c @@ -0,0 +1,179 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#include <sys/mman.h> +#include <stdint.h> +#include <unistd.h> +#include <string.h> +#include <sys/time.h> +#include <sys/resource.h> +#include <stdbool.h> +#include "../kselftest.h" +#include <syscall.h> +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <fcntl.h> +#include <sys/ioctl.h> +#include <sys/vfs.h> +#include <sys/stat.h> + +/* + * need those definition for manually build using gcc. + * gcc -I ../../../../usr/include -DDEBUG -O3 -DDEBUG -O3 seal_elf.c -o seal_elf + */ +#define FAIL_TEST_IF_FALSE(c) do {\ + if (!(c)) {\ + ksft_test_result_fail("%s, line:%d\n", __func__, __LINE__);\ + goto test_end;\ + } \ + } \ + while (0) + +#define SKIP_TEST_IF_FALSE(c) do {\ + if (!(c)) {\ + ksft_test_result_skip("%s, line:%d\n", __func__, __LINE__);\ + goto test_end;\ + } \ + } \ + while (0) + + +#define TEST_END_CHECK() {\ + ksft_test_result_pass("%s\n", __func__);\ + return;\ +test_end:\ + return;\ +} + +#ifndef u64 +#define u64 unsigned long long +#endif + +/* + * define sys_xyx to call syscall directly. + */ +static int sys_mseal(void *start, size_t len) +{ + int sret; + + errno = 0; + sret = syscall(__NR_mseal, start, len, 0); + return sret; +} + +static void *sys_mmap(void *addr, unsigned long len, unsigned long prot, + unsigned long flags, unsigned long fd, unsigned long offset) +{ + void *sret; + + errno = 0; + sret = (void *) syscall(__NR_mmap, addr, len, prot, + flags, fd, offset); + return sret; +} + +static inline int sys_mprotect(void *ptr, size_t size, unsigned long prot) +{ + int sret; + + errno = 0; + sret = syscall(__NR_mprotect, ptr, size, prot); + return sret; +} + +static bool seal_support(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + + ptr = sys_mmap(NULL, page_size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + if (ptr == (void *) -1) + return false; + + ret = sys_mseal(ptr, page_size); + if (ret < 0) + return false; + + return true; +} + +const char somestr[4096] = {"READONLY"}; + +static void test_seal_elf(void) +{ + int ret; + FILE *maps; + char line[512]; + uintptr_t addr_start, addr_end; + char prot[5]; + char filename[256]; + unsigned long page_size = getpagesize(); + unsigned long long ptr = (unsigned long long) somestr; + char *somestr2 = (char *)somestr; + + /* + * Modify the protection of readonly somestr + */ + if (((unsigned long long)ptr % page_size) != 0) + ptr = (unsigned long long)ptr & ~(page_size - 1); + + ksft_print_msg("somestr = %s\n", somestr); + ksft_print_msg("change protection to rw\n"); + ret = sys_mprotect((void *)ptr, page_size, PROT_READ|PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + *somestr2 = 'A'; + ksft_print_msg("somestr is modified to: %s\n", somestr); + ret = sys_mprotect((void *)ptr, page_size, PROT_READ); + FAIL_TEST_IF_FALSE(!ret); + + maps = fopen("/proc/self/maps", "r"); + FAIL_TEST_IF_FALSE(maps); + + /* + * apply sealing to elf binary + */ + while (fgets(line, sizeof(line), maps)) { + if (sscanf(line, "%lx-%lx %4s %*x %*x:%*x %*u %255[^\n]", + &addr_start, &addr_end, prot, filename) == 4) { + if (strlen(filename)) { + /* + * seal the mapping if read only. + */ + if (strstr(prot, "r-")) { + ret = sys_mseal((void *)addr_start, addr_end - addr_start); + FAIL_TEST_IF_FALSE(!ret); + ksft_print_msg("sealed: %lx-%lx %s %s\n", + addr_start, addr_end, prot, filename); + if ((uintptr_t) somestr >= addr_start && + (uintptr_t) somestr <= addr_end) + ksft_print_msg("mapping for somestr found\n"); + } + } + } + } + fclose(maps); + + ret = sys_mprotect((void *)ptr, page_size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(ret < 0); + ksft_print_msg("somestr is sealed, mprotect is rejected\n"); + + TEST_END_CHECK(); +} + +int main(int argc, char **argv) +{ + bool test_seal = seal_support(); + + ksft_print_header(); + ksft_print_msg("pid=%d\n", getpid()); + + if (!test_seal) + ksft_exit_skip("sealing not supported, check CONFIG_64BIT\n"); + + ksft_set_plan(1); + + test_seal_elf(); + + ksft_finished(); +} diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h index cc5629c3d2aa..a70ae10b5f62 100644 --- a/tools/testing/selftests/mm/uffd-common.h +++ b/tools/testing/selftests/mm/uffd-common.h @@ -8,6 +8,7 @@ #define __UFFD_COMMON_H__ #define _GNU_SOURCE +#define __SANE_USERSPACE_TYPES__ // Use ll64 #include <stdio.h> #include <errno.h> #include <unistd.h> diff --git a/tools/testing/selftests/net/hsr/hsr_ping.sh b/tools/testing/selftests/net/hsr/hsr_ping.sh index 790294c8af83..3684b813b0f6 100755 --- a/tools/testing/selftests/net/hsr/hsr_ping.sh +++ b/tools/testing/selftests/net/hsr/hsr_ping.sh @@ -174,6 +174,8 @@ trap cleanup_all_ns EXIT setup_hsr_interfaces 0 do_complete_ping_test +setup_ns ns1 ns2 ns3 + setup_hsr_interfaces 1 do_complete_ping_test diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index fefa9173bdaa..2b66c5fa71eb 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -261,6 +261,8 @@ reset() TEST_NAME="${1}" + MPTCP_LIB_SUBTEST_FLAKY=0 # reset if modified + if skip_test; then MPTCP_LIB_TEST_COUNTER=$((MPTCP_LIB_TEST_COUNTER+1)) last_test_ignored=1 @@ -448,7 +450,9 @@ reset_with_tcp_filter() # $1: err msg fail_test() { - ret=${KSFT_FAIL} + if ! mptcp_lib_subtest_is_flaky; then + ret=${KSFT_FAIL} + fi if [ ${#} -gt 0 ]; then print_fail "${@}" @@ -3069,6 +3073,7 @@ fullmesh_tests() fastclose_tests() { if reset_check_counter "fastclose test" "MPTcpExtMPFastcloseTx"; then + MPTCP_LIB_SUBTEST_FLAKY=1 test_linkfail=1024 fastclose=client \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 @@ -3077,6 +3082,7 @@ fastclose_tests() fi if reset_check_counter "fastclose server test" "MPTcpExtMPFastcloseRx"; then + MPTCP_LIB_SUBTEST_FLAKY=1 test_linkfail=1024 fastclose=server \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 0 0 0 1 @@ -3095,6 +3101,7 @@ fail_tests() { # single subflow if reset_with_fail "Infinite map" 1; then + MPTCP_LIB_SUBTEST_FLAKY=1 test_linkfail=128 \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 +1 +0 1 0 1 "$(pedit_action_pkts)" @@ -3103,6 +3110,7 @@ fail_tests() # multiple subflows if reset_with_fail "MP_FAIL MP_RST" 2; then + MPTCP_LIB_SUBTEST_FLAKY=1 tc -n $ns2 qdisc add dev ns2eth1 root netem rate 1mbit delay 5ms pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index ad2ebda5cb64..6ffa9b7a3260 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -21,6 +21,7 @@ declare -rx MPTCP_LIB_AF_INET6=10 MPTCP_LIB_SUBTESTS=() MPTCP_LIB_SUBTESTS_DUPLICATED=0 +MPTCP_LIB_SUBTEST_FLAKY=0 MPTCP_LIB_TEST_COUNTER=0 MPTCP_LIB_TEST_FORMAT="%02u %-50s" MPTCP_LIB_IP_MPTCP=0 @@ -41,6 +42,16 @@ else readonly MPTCP_LIB_COLOR_RESET= fi +# SELFTESTS_MPTCP_LIB_OVERRIDE_FLAKY env var can be set not to ignore errors +# from subtests marked as flaky +mptcp_lib_override_flaky() { + [ "${SELFTESTS_MPTCP_LIB_OVERRIDE_FLAKY:-}" = 1 ] +} + +mptcp_lib_subtest_is_flaky() { + [ "${MPTCP_LIB_SUBTEST_FLAKY}" = 1 ] && ! mptcp_lib_override_flaky +} + # $1: color, $2: text mptcp_lib_print_color() { echo -e "${MPTCP_LIB_START_PRINT:-}${*}${MPTCP_LIB_COLOR_RESET}" @@ -72,7 +83,16 @@ mptcp_lib_pr_skip() { } mptcp_lib_pr_fail() { - mptcp_lib_print_err "[FAIL]${1:+ ${*}}" + local title cmt + + if mptcp_lib_subtest_is_flaky; then + title="IGNO" + cmt=" (flaky)" + else + title="FAIL" + fi + + mptcp_lib_print_err "[${title}]${cmt}${1:+ ${*}}" } mptcp_lib_pr_info() { @@ -208,7 +228,13 @@ mptcp_lib_result_pass() { # $1: test name mptcp_lib_result_fail() { - __mptcp_lib_result_add "not ok" "${1}" + if mptcp_lib_subtest_is_flaky; then + # It might sound better to use 'not ok # TODO' or 'ok # SKIP', + # but some CIs don't understand 'TODO' and treat SKIP as errors. + __mptcp_lib_result_add "ok" "${1} # IGNORE Flaky" + else + __mptcp_lib_result_add "not ok" "${1}" + fi } # $1: test name diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index 4b14b4412166..f74e1c3c126d 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -244,7 +244,7 @@ run_test() do_transfer $small $large $time lret=$? mptcp_lib_result_code "${lret}" "${msg}" - if [ $lret -ne 0 ]; then + if [ $lret -ne 0 ] && ! mptcp_lib_subtest_is_flaky; then ret=$lret [ $bail -eq 0 ] || exit $ret fi @@ -254,7 +254,7 @@ run_test() do_transfer $large $small $time lret=$? mptcp_lib_result_code "${lret}" "${msg}" - if [ $lret -ne 0 ]; then + if [ $lret -ne 0 ] && ! mptcp_lib_subtest_is_flaky; then ret=$lret [ $bail -eq 0 ] || exit $ret fi @@ -290,7 +290,7 @@ run_test 10 10 0 0 "balanced bwidth" run_test 10 10 1 25 "balanced bwidth with unbalanced delay" # we still need some additional infrastructure to pass the following test-cases -run_test 10 3 0 0 "unbalanced bwidth" +MPTCP_LIB_SUBTEST_FLAKY=1 run_test 10 3 0 0 "unbalanced bwidth" run_test 10 3 1 25 "unbalanced bwidth with unbalanced delay" run_test 10 3 25 1 "unbalanced bwidth with opposed, unbalanced delay" diff --git a/tools/testing/selftests/riscv/Makefile b/tools/testing/selftests/riscv/Makefile index 4a9ff515a3a0..7ce03d832b64 100644 --- a/tools/testing/selftests/riscv/Makefile +++ b/tools/testing/selftests/riscv/Makefile @@ -5,7 +5,7 @@ ARCH ?= $(shell uname -m 2>/dev/null || echo not) ifneq (,$(filter $(ARCH),riscv)) -RISCV_SUBTARGETS ?= hwprobe vector mm +RISCV_SUBTARGETS ?= hwprobe vector mm sigreturn else RISCV_SUBTARGETS := endif diff --git a/tools/testing/selftests/riscv/hwprobe/.gitignore b/tools/testing/selftests/riscv/hwprobe/.gitignore index 8113dc3bdd03..6e384e80ea1a 100644 --- a/tools/testing/selftests/riscv/hwprobe/.gitignore +++ b/tools/testing/selftests/riscv/hwprobe/.gitignore @@ -1 +1,3 @@ hwprobe +cbo +which-cpus diff --git a/tools/testing/selftests/riscv/sigreturn/.gitignore b/tools/testing/selftests/riscv/sigreturn/.gitignore new file mode 100644 index 000000000000..35002b8ae780 --- /dev/null +++ b/tools/testing/selftests/riscv/sigreturn/.gitignore @@ -0,0 +1 @@ +sigreturn diff --git a/tools/testing/selftests/riscv/sigreturn/Makefile b/tools/testing/selftests/riscv/sigreturn/Makefile new file mode 100644 index 000000000000..eb8bac9279a8 --- /dev/null +++ b/tools/testing/selftests/riscv/sigreturn/Makefile @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: GPL-2.0 +# Copyright (C) 2021 ARM Limited +# Originally tools/testing/arm64/abi/Makefile + +CFLAGS += -I$(top_srcdir)/tools/include + +TEST_GEN_PROGS := sigreturn + +include ../../lib.mk + +$(OUTPUT)/sigreturn: sigreturn.c + $(CC) -static -o$@ $(CFLAGS) $(LDFLAGS) $^ diff --git a/tools/testing/selftests/riscv/sigreturn/sigreturn.c b/tools/testing/selftests/riscv/sigreturn/sigreturn.c new file mode 100644 index 000000000000..62397d5934f1 --- /dev/null +++ b/tools/testing/selftests/riscv/sigreturn/sigreturn.c @@ -0,0 +1,82 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <ucontext.h> +#include <linux/ptrace.h> +#include "../../kselftest_harness.h" + +#define RISCV_V_MAGIC 0x53465457 +#define DEFAULT_VALUE 2 +#define SIGNAL_HANDLER_OVERRIDE 3 + +static void simple_handle(int sig_no, siginfo_t *info, void *vcontext) +{ + ucontext_t *context = vcontext; + + context->uc_mcontext.__gregs[REG_PC] = context->uc_mcontext.__gregs[REG_PC] + 4; +} + +static void vector_override(int sig_no, siginfo_t *info, void *vcontext) +{ + ucontext_t *context = vcontext; + + // vector state + struct __riscv_extra_ext_header *ext; + struct __riscv_v_ext_state *v_ext_state; + + /* Find the vector context. */ + ext = (void *)(&context->uc_mcontext.__fpregs); + if (ext->hdr.magic != RISCV_V_MAGIC) { + fprintf(stderr, "bad vector magic: %x\n", ext->hdr.magic); + abort(); + } + + v_ext_state = (void *)((char *)(ext) + sizeof(*ext)); + + *(int *)v_ext_state->datap = SIGNAL_HANDLER_OVERRIDE; + + context->uc_mcontext.__gregs[REG_PC] = context->uc_mcontext.__gregs[REG_PC] + 4; +} + +static int vector_sigreturn(int data, void (*handler)(int, siginfo_t *, void *)) +{ + int after_sigreturn; + struct sigaction sig_action = { + .sa_sigaction = handler, + .sa_flags = SA_SIGINFO + }; + + sigaction(SIGSEGV, &sig_action, 0); + + asm(".option push \n\ + .option arch, +v \n\ + vsetivli x0, 1, e32, ta, ma \n\ + vmv.s.x v0, %1 \n\ + # Generate SIGSEGV \n\ + lw a0, 0(x0) \n\ + vmv.x.s %0, v0 \n\ + .option pop" : "=r" (after_sigreturn) : "r" (data)); + + return after_sigreturn; +} + +TEST(vector_restore) +{ + int result; + + result = vector_sigreturn(DEFAULT_VALUE, &simple_handle); + + EXPECT_EQ(DEFAULT_VALUE, result); +} + +TEST(vector_restore_signal_handler_override) +{ + int result; + + result = vector_sigreturn(DEFAULT_VALUE, &vector_override); + + EXPECT_EQ(SIGNAL_HANDLER_OVERRIDE, result); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json index 12da0a939e3e..557fb074acf0 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json @@ -133,6 +133,50 @@ ] }, { + "id": "6f62", + "name": "Add taprio Qdisc with too short interval", + "category": [ + "qdisc", + "taprio" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "echo \"1 1 8\" > /sys/bus/netdevsim/new_device" + ], + "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: taprio num_tc 2 queues 1@0 1@1 sched-entry S 01 300 sched-entry S 02 1700 clockid CLOCK_TAI", + "expExitCode": "2", + "verifyCmd": "$TC qdisc show dev $ETH", + "matchPattern": "qdisc taprio 1: root refcnt", + "matchCount": "0", + "teardown": [ + "echo \"1\" > /sys/bus/netdevsim/del_device" + ] + }, + { + "id": "831f", + "name": "Add taprio Qdisc with too short cycle-time", + "category": [ + "qdisc", + "taprio" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "echo \"1 1 8\" > /sys/bus/netdevsim/new_device" + ], + "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: taprio num_tc 2 queues 1@0 1@1 sched-entry S 01 200000 sched-entry S 02 200000 cycle-time 100 clockid CLOCK_TAI", + "expExitCode": "2", + "verifyCmd": "$TC qdisc show dev $ETH", + "matchPattern": "qdisc taprio 1: root refcnt", + "matchCount": "0", + "teardown": [ + "echo \"1\" > /sys/bus/netdevsim/del_device" + ] + }, + { "id": "3e1e", "name": "Add taprio Qdisc with an invalid cycle-time", "category": [ |